[2023-03-09 07:25:21,015][22664] Saving configuration to /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/config.json... [2023-03-09 07:25:21,016][22664] Rollout worker 0 uses device cpu [2023-03-09 07:25:21,017][22664] Rollout worker 1 uses device cpu [2023-03-09 07:25:21,018][22664] Rollout worker 2 uses device cpu [2023-03-09 07:25:21,018][22664] Rollout worker 3 uses device cpu [2023-03-09 07:25:21,019][22664] Rollout worker 4 uses device cpu [2023-03-09 07:25:21,020][22664] Rollout worker 5 uses device cpu [2023-03-09 07:25:21,020][22664] Rollout worker 6 uses device cpu [2023-03-09 07:25:21,021][22664] Rollout worker 7 uses device cpu [2023-03-09 07:25:21,021][22664] Rollout worker 8 uses device cpu [2023-03-09 07:25:21,022][22664] Rollout worker 9 uses device cpu [2023-03-09 07:25:21,023][22664] Rollout worker 10 uses device cpu [2023-03-09 07:25:21,023][22664] Rollout worker 11 uses device cpu [2023-03-09 07:25:21,024][22664] Rollout worker 12 uses device cpu [2023-03-09 07:25:21,024][22664] Rollout worker 13 uses device cpu [2023-03-09 07:25:21,025][22664] Rollout worker 14 uses device cpu [2023-03-09 07:25:21,026][22664] Rollout worker 15 uses device cpu [2023-03-09 07:25:21,026][22664] Rollout worker 16 uses device cpu [2023-03-09 07:25:21,027][22664] Rollout worker 17 uses device cpu [2023-03-09 07:25:21,027][22664] Rollout worker 18 uses device cpu [2023-03-09 07:25:21,028][22664] Rollout worker 19 uses device cpu [2023-03-09 07:25:21,028][22664] Rollout worker 20 uses device cpu [2023-03-09 07:25:21,029][22664] Rollout worker 21 uses device cpu [2023-03-09 07:25:21,030][22664] Rollout worker 22 uses device cpu [2023-03-09 07:25:21,030][22664] Rollout worker 23 uses device cpu [2023-03-09 07:25:21,031][22664] Rollout worker 24 uses device cpu [2023-03-09 07:25:21,031][22664] Rollout worker 25 uses device cpu [2023-03-09 07:25:21,032][22664] Rollout worker 26 uses device cpu [2023-03-09 07:25:21,032][22664] Rollout worker 27 uses device cpu [2023-03-09 07:25:21,033][22664] Rollout worker 28 uses device cpu [2023-03-09 07:25:21,034][22664] Rollout worker 29 uses device cpu [2023-03-09 07:25:21,034][22664] Rollout worker 30 uses device cpu [2023-03-09 07:25:21,035][22664] Rollout worker 31 uses device cpu [2023-03-09 07:25:21,035][22664] Rollout worker 32 uses device cpu [2023-03-09 07:25:21,036][22664] Rollout worker 33 uses device cpu [2023-03-09 07:25:21,037][22664] Rollout worker 34 uses device cpu [2023-03-09 07:25:21,037][22664] Rollout worker 35 uses device cpu [2023-03-09 07:25:21,038][22664] Rollout worker 36 uses device cpu [2023-03-09 07:25:21,038][22664] Rollout worker 37 uses device cpu [2023-03-09 07:25:21,039][22664] Rollout worker 38 uses device cpu [2023-03-09 07:25:21,039][22664] Rollout worker 39 uses device cpu [2023-03-09 07:25:21,040][22664] Rollout worker 40 uses device cpu [2023-03-09 07:25:21,041][22664] Rollout worker 41 uses device cpu [2023-03-09 07:25:21,041][22664] Rollout worker 42 uses device cpu [2023-03-09 07:25:21,042][22664] Rollout worker 43 uses device cpu [2023-03-09 07:25:21,042][22664] Rollout worker 44 uses device cpu [2023-03-09 07:25:21,043][22664] Rollout worker 45 uses device cpu [2023-03-09 07:25:21,043][22664] Rollout worker 46 uses device cpu [2023-03-09 07:25:21,044][22664] Rollout worker 47 uses device cpu [2023-03-09 07:25:21,045][22664] Rollout worker 48 uses device cpu [2023-03-09 07:25:21,045][22664] Rollout worker 49 uses device cpu [2023-03-09 07:25:21,046][22664] Rollout worker 50 uses device cpu [2023-03-09 07:25:21,046][22664] Rollout worker 51 uses device cpu [2023-03-09 07:25:21,047][22664] Rollout worker 52 uses device cpu [2023-03-09 07:25:21,047][22664] Rollout worker 53 uses device cpu [2023-03-09 07:25:21,048][22664] Rollout worker 54 uses device cpu [2023-03-09 07:25:21,049][22664] Rollout worker 55 uses device cpu [2023-03-09 07:25:21,049][22664] Rollout worker 56 uses device cpu [2023-03-09 07:25:21,050][22664] Rollout worker 57 uses device cpu [2023-03-09 07:25:21,050][22664] Rollout worker 58 uses device cpu [2023-03-09 07:25:21,051][22664] Rollout worker 59 uses device cpu [2023-03-09 07:25:21,060][22664] Rollout worker 60 uses device cpu [2023-03-09 07:25:21,061][22664] Rollout worker 61 uses device cpu [2023-03-09 07:25:21,062][22664] Rollout worker 62 uses device cpu [2023-03-09 07:25:21,062][22664] Rollout worker 63 uses device cpu [2023-03-09 07:25:21,063][22664] Rollout worker 64 uses device cpu [2023-03-09 07:25:21,063][22664] Rollout worker 65 uses device cpu [2023-03-09 07:25:21,064][22664] Rollout worker 66 uses device cpu [2023-03-09 07:25:21,065][22664] Rollout worker 67 uses device cpu [2023-03-09 07:25:21,065][22664] Rollout worker 68 uses device cpu [2023-03-09 07:25:21,066][22664] Rollout worker 69 uses device cpu [2023-03-09 07:25:21,066][22664] Rollout worker 70 uses device cpu [2023-03-09 07:25:21,067][22664] Rollout worker 71 uses device cpu [2023-03-09 07:25:21,068][22664] Rollout worker 72 uses device cpu [2023-03-09 07:25:21,068][22664] Rollout worker 73 uses device cpu [2023-03-09 07:25:21,069][22664] Rollout worker 74 uses device cpu [2023-03-09 07:25:21,069][22664] Rollout worker 75 uses device cpu [2023-03-09 07:25:21,070][22664] Rollout worker 76 uses device cpu [2023-03-09 07:25:21,070][22664] Rollout worker 77 uses device cpu [2023-03-09 07:25:21,071][22664] Rollout worker 78 uses device cpu [2023-03-09 07:25:21,072][22664] Rollout worker 79 uses device cpu [2023-03-09 07:25:21,072][22664] Rollout worker 80 uses device cpu [2023-03-09 07:25:21,073][22664] Rollout worker 81 uses device cpu [2023-03-09 07:25:21,073][22664] Rollout worker 82 uses device cpu [2023-03-09 07:25:21,074][22664] Rollout worker 83 uses device cpu [2023-03-09 07:25:21,074][22664] Rollout worker 84 uses device cpu [2023-03-09 07:25:21,075][22664] Rollout worker 85 uses device cpu [2023-03-09 07:25:21,076][22664] Rollout worker 86 uses device cpu [2023-03-09 07:25:21,076][22664] Rollout worker 87 uses device cpu [2023-03-09 07:25:21,077][22664] Rollout worker 88 uses device cpu [2023-03-09 07:25:21,077][22664] Rollout worker 89 uses device cpu [2023-03-09 07:25:21,078][22664] Rollout worker 90 uses device cpu [2023-03-09 07:25:21,078][22664] Rollout worker 91 uses device cpu [2023-03-09 07:25:21,079][22664] Rollout worker 92 uses device cpu [2023-03-09 07:25:21,080][22664] Rollout worker 93 uses device cpu [2023-03-09 07:25:21,080][22664] Rollout worker 94 uses device cpu [2023-03-09 07:25:21,081][22664] Rollout worker 95 uses device cpu [2023-03-09 07:25:21,081][22664] Rollout worker 96 uses device cpu [2023-03-09 07:25:21,082][22664] Rollout worker 97 uses device cpu [2023-03-09 07:25:21,083][22664] Rollout worker 98 uses device cpu [2023-03-09 07:25:21,083][22664] Rollout worker 99 uses device cpu [2023-03-09 07:25:21,084][22664] Rollout worker 100 uses device cpu [2023-03-09 07:25:21,084][22664] Rollout worker 101 uses device cpu [2023-03-09 07:25:21,085][22664] Rollout worker 102 uses device cpu [2023-03-09 07:25:21,085][22664] Rollout worker 103 uses device cpu [2023-03-09 07:25:21,086][22664] Rollout worker 104 uses device cpu [2023-03-09 07:25:21,087][22664] Rollout worker 105 uses device cpu [2023-03-09 07:25:21,087][22664] Rollout worker 106 uses device cpu [2023-03-09 07:25:21,088][22664] Rollout worker 107 uses device cpu [2023-03-09 07:25:21,088][22664] Rollout worker 108 uses device cpu [2023-03-09 07:25:21,089][22664] Rollout worker 109 uses device cpu [2023-03-09 07:25:21,090][22664] Rollout worker 110 uses device cpu [2023-03-09 07:25:21,090][22664] Rollout worker 111 uses device cpu [2023-03-09 07:25:21,091][22664] Rollout worker 112 uses device cpu [2023-03-09 07:25:21,091][22664] Rollout worker 113 uses device cpu [2023-03-09 07:25:21,092][22664] Rollout worker 114 uses device cpu [2023-03-09 07:25:21,093][22664] Rollout worker 115 uses device cpu [2023-03-09 07:25:21,093][22664] Rollout worker 116 uses device cpu [2023-03-09 07:25:21,094][22664] Rollout worker 117 uses device cpu [2023-03-09 07:25:21,094][22664] Rollout worker 118 uses device cpu [2023-03-09 07:25:21,095][22664] Rollout worker 119 uses device cpu [2023-03-09 07:25:21,102][22664] Rollout worker 120 uses device cpu [2023-03-09 07:25:21,103][22664] Rollout worker 121 uses device cpu [2023-03-09 07:25:21,103][22664] Rollout worker 122 uses device cpu [2023-03-09 07:25:21,104][22664] Rollout worker 123 uses device cpu [2023-03-09 07:25:21,104][22664] Rollout worker 124 uses device cpu [2023-03-09 07:25:21,104][22664] Rollout worker 125 uses device cpu [2023-03-09 07:25:21,105][22664] Rollout worker 126 uses device cpu [2023-03-09 07:25:21,105][22664] Rollout worker 127 uses device cpu [2023-03-09 07:25:23,239][22664] Using GPUs [0] for process 0 (actually maps to GPUs [0]) [2023-03-09 07:25:23,240][22664] InferenceWorker_p0-w0: min num requests: 42 [2023-03-09 07:25:23,585][22664] Starting all processes... [2023-03-09 07:25:23,586][22664] Starting process learner_proc0 [2023-03-09 07:25:24,449][22664] Starting all processes... [2023-03-09 07:25:24,450][22940] Using GPUs [0] for process 0 (actually maps to GPUs [0]) [2023-03-09 07:25:24,450][22940] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0 [2023-03-09 07:25:24,455][22664] Starting process inference_proc0-0 [2023-03-09 07:25:24,456][22664] Starting process rollout_proc2 [2023-03-09 07:25:24,459][22940] Num visible devices: 1 [2023-03-09 07:25:24,457][22664] Starting process rollout_proc5 [2023-03-09 07:25:24,457][22664] Starting process rollout_proc8 [2023-03-09 07:25:24,464][22940] Starting seed is not provided [2023-03-09 07:25:24,464][22940] Using GPUs [0] for process 0 (actually maps to GPUs [0]) [2023-03-09 07:25:24,464][22940] Initializing actor-critic model on device cuda:0 [2023-03-09 07:25:24,464][22940] RunningMeanStd input shape: (3, 72, 128) [2023-03-09 07:25:24,464][22940] RunningMeanStd input shape: (1,) [2023-03-09 07:25:24,458][22664] Starting process rollout_proc11 [2023-03-09 07:25:24,474][22940] ConvEncoder: input_channels=3 [2023-03-09 07:25:24,459][22664] Starting process rollout_proc14 [2023-03-09 07:25:24,459][22664] Starting process rollout_proc17 [2023-03-09 07:25:24,460][22664] Starting process rollout_proc20 [2023-03-09 07:25:24,461][22664] Starting process rollout_proc23 [2023-03-09 07:25:24,463][22664] Starting process rollout_proc26 [2023-03-09 07:25:24,466][22664] Starting process rollout_proc29 [2023-03-09 07:25:24,466][22664] Starting process rollout_proc32 [2023-03-09 07:25:24,467][22664] Starting process rollout_proc35 [2023-03-09 07:25:24,470][22664] Starting process rollout_proc38 [2023-03-09 07:25:24,470][22664] Starting process rollout_proc41 [2023-03-09 07:25:24,478][22664] Starting process rollout_proc44 [2023-03-09 07:25:24,494][22664] Starting process rollout_proc3 [2023-03-09 07:25:24,496][22664] Starting process rollout_proc6 [2023-03-09 07:25:24,504][22664] Starting process rollout_proc9 [2023-03-09 07:25:24,510][22664] Starting process rollout_proc12 [2023-03-09 07:25:24,515][22664] Starting process rollout_proc15 [2023-03-09 07:25:24,522][22664] Starting process rollout_proc18 [2023-03-09 07:25:24,525][22664] Starting process rollout_proc21 [2023-03-09 07:25:24,532][22664] Starting process rollout_proc27 [2023-03-09 07:25:24,535][22664] Starting process rollout_proc24 [2023-03-09 07:25:24,543][22664] Starting process rollout_proc33 [2023-03-09 07:25:24,545][22664] Starting process rollout_proc30 [2023-03-09 07:25:24,549][22664] Starting process rollout_proc36 [2023-03-09 07:25:24,553][22664] Starting process rollout_proc39 [2023-03-09 07:25:24,576][22664] Starting process rollout_proc42 [2023-03-09 07:25:24,595][22940] Conv encoder output size: 512 [2023-03-09 07:25:24,576][22664] Starting process rollout_proc45 [2023-03-09 07:25:24,595][22940] Policy head output size: 512 [2023-03-09 07:25:24,577][22664] Starting process rollout_proc4 [2023-03-09 07:25:24,580][22664] Starting process rollout_proc7 [2023-03-09 07:25:24,613][22940] Created Actor Critic model with architecture: [2023-03-09 07:25:24,613][22940] ActorCriticSharedWeights( (obs_normalizer): ObservationNormalizer( (running_mean_std): RunningMeanStdDictInPlace( (running_mean_std): ModuleDict( (obs): RunningMeanStdInPlace() ) ) ) (returns_normalizer): RecursiveScriptModule(original_name=RunningMeanStdInPlace) (encoder): VizdoomEncoder( (basic_encoder): ConvEncoder( (enc): RecursiveScriptModule( original_name=ConvEncoderImpl (conv_head): RecursiveScriptModule( original_name=Sequential (0): RecursiveScriptModule(original_name=Conv2d) (1): RecursiveScriptModule(original_name=ELU) (2): RecursiveScriptModule(original_name=Conv2d) (3): RecursiveScriptModule(original_name=ELU) (4): RecursiveScriptModule(original_name=Conv2d) (5): RecursiveScriptModule(original_name=ELU) ) (mlp_layers): RecursiveScriptModule( original_name=Sequential (0): RecursiveScriptModule(original_name=Linear) (1): RecursiveScriptModule(original_name=ELU) ) ) ) ) (core): ModelCoreRNN( (core): GRU(512, 512) ) (decoder): MlpDecoder( (mlp): Identity() ) (critic_linear): Linear(in_features=512, out_features=1, bias=True) (action_parameterization): ActionParameterizationDefault( (distribution_linear): Linear(in_features=512, out_features=5, bias=True) ) ) [2023-03-09 07:25:24,587][22664] Starting process rollout_proc10 [2023-03-09 07:25:24,600][22664] Starting process rollout_proc13 [2023-03-09 07:25:24,610][22664] Starting process rollout_proc16 [2023-03-09 07:25:24,610][22664] Starting process rollout_proc19 [2023-03-09 07:25:24,615][22664] Starting process rollout_proc22 [2023-03-09 07:25:24,620][22664] Starting process rollout_proc28 [2023-03-09 07:25:24,627][22664] Starting process rollout_proc25 [2023-03-09 07:25:24,632][22664] Starting process rollout_proc34 [2023-03-09 07:25:24,637][22664] Starting process rollout_proc31 [2023-03-09 07:25:24,647][22664] Starting process rollout_proc40 [2023-03-09 07:25:24,648][22664] Starting process rollout_proc37 [2023-03-09 07:25:24,649][22664] Starting process rollout_proc46 [2023-03-09 07:25:24,654][22664] Starting process rollout_proc47 [2023-03-09 07:25:24,655][22664] Starting process rollout_proc43 [2023-03-09 07:25:24,656][22664] Starting process rollout_proc50 [2023-03-09 07:25:24,661][22664] Starting process rollout_proc53 [2023-03-09 07:25:24,665][22664] Starting process rollout_proc56 [2023-03-09 07:25:24,669][22664] Starting process rollout_proc59 [2023-03-09 07:25:24,672][22664] Starting process rollout_proc62 [2023-03-09 07:25:24,675][22664] Starting process rollout_proc65 [2023-03-09 07:25:24,681][22664] Starting process rollout_proc68 [2023-03-09 07:25:24,686][22664] Starting process rollout_proc71 [2023-03-09 07:25:24,695][22664] Starting process rollout_proc74 [2023-03-09 07:25:24,699][22664] Starting process rollout_proc77 [2023-03-09 07:25:24,704][22664] Starting process rollout_proc80 [2023-03-09 07:25:24,710][22664] Starting process rollout_proc83 [2023-03-09 07:25:24,713][22664] Starting process rollout_proc48 [2023-03-09 07:25:24,719][22664] Starting process rollout_proc51 [2023-03-09 07:25:24,722][22664] Starting process rollout_proc86 [2023-03-09 07:25:24,726][22664] Starting process rollout_proc89 [2023-03-09 07:25:24,733][22664] Starting process rollout_proc57 [2023-03-09 07:25:24,737][22664] Starting process rollout_proc54 [2023-03-09 07:25:24,744][22664] Starting process rollout_proc66 [2023-03-09 07:25:24,747][22664] Starting process rollout_proc63 [2023-03-09 07:25:24,755][22664] Starting process rollout_proc60 [2023-03-09 07:25:24,756][22664] Starting process rollout_proc69 [2023-03-09 07:25:24,765][22664] Starting process rollout_proc72 [2023-03-09 07:25:24,772][22664] Starting process rollout_proc75 [2023-03-09 07:25:24,772][22664] Starting process rollout_proc78 [2023-03-09 07:25:24,779][22664] Starting process rollout_proc81 [2023-03-09 07:25:24,786][22664] Starting process rollout_proc84 [2023-03-09 07:25:24,793][22664] Starting process rollout_proc49 [2023-03-09 07:25:24,799][22664] Starting process rollout_proc52 [2023-03-09 07:25:24,808][22664] Starting process rollout_proc87 [2023-03-09 07:25:24,824][22664] Starting process rollout_proc58 [2023-03-09 07:25:24,838][22664] Starting process rollout_proc90 [2023-03-09 07:25:24,890][22664] Starting process rollout_proc85 [2023-03-09 07:25:24,892][22664] Starting process rollout_proc73 [2023-03-09 07:25:24,896][22664] Starting process rollout_proc67 [2023-03-09 07:25:24,898][22664] Starting process rollout_proc64 [2023-03-09 07:25:24,900][22664] Starting process rollout_proc88 [2023-03-09 07:25:24,901][22664] Starting process rollout_proc70 [2023-03-09 07:25:24,902][22664] Starting process rollout_proc82 [2023-03-09 07:25:24,907][22664] Starting process rollout_proc92 [2023-03-09 07:25:24,910][22664] Starting process rollout_proc76 [2023-03-09 07:25:24,911][22664] Starting process rollout_proc55 [2023-03-09 07:25:24,911][22664] Starting process rollout_proc61 [2023-03-09 07:25:24,911][22664] Starting process rollout_proc91 [2023-03-09 07:25:24,912][22664] Starting process rollout_proc95 [2023-03-09 07:25:24,915][22664] Starting process rollout_proc79 [2023-03-09 07:25:24,922][22664] Starting process rollout_proc98 [2023-03-09 07:25:24,948][22664] Starting process rollout_proc101 [2023-03-09 07:25:24,962][22664] Starting process rollout_proc104 [2023-03-09 07:25:24,976][22664] Starting process rollout_proc107 [2023-03-09 07:25:24,976][22664] Starting process rollout_proc110 [2023-03-09 07:25:24,977][22664] Starting process rollout_proc113 [2023-03-09 07:25:24,978][22664] Starting process rollout_proc116 [2023-03-09 07:25:25,000][22664] Starting process rollout_proc119 [2023-03-09 07:25:25,000][22664] Starting process rollout_proc93 [2023-03-09 07:25:25,000][22664] Starting process rollout_proc122 [2023-03-09 07:25:25,008][22664] Starting process rollout_proc125 [2023-03-09 07:25:25,040][22664] Starting process rollout_proc96 [2023-03-09 07:25:25,087][22664] Starting process rollout_proc99 [2023-03-09 07:25:25,141][22664] Starting process rollout_proc108 [2023-03-09 07:25:25,156][22664] Starting process rollout_proc102 [2023-03-09 07:25:25,173][22664] Starting process rollout_proc105 [2023-03-09 07:25:25,202][22664] Starting process rollout_proc111 [2023-03-09 07:25:25,219][22664] Starting process rollout_proc117 [2023-03-09 07:25:25,245][22664] Starting process rollout_proc120 [2023-03-09 07:25:25,251][22664] Starting process rollout_proc114 [2023-03-09 07:25:25,252][22664] Starting process rollout_proc123 [2023-03-09 07:25:25,278][22664] Starting process rollout_proc126 [2023-03-09 07:25:25,339][22664] Starting process rollout_proc94 [2023-03-09 07:25:25,339][22664] Starting process rollout_proc97 [2023-03-09 07:25:25,340][22664] Starting process rollout_proc103 [2023-03-09 07:25:25,340][22664] Starting process rollout_proc112 [2023-03-09 07:25:25,340][22664] Starting process rollout_proc106 [2023-03-09 07:25:25,351][22664] Starting process rollout_proc100 [2023-03-09 07:25:25,351][22664] Starting process rollout_proc118 [2023-03-09 07:25:25,361][22664] Starting process rollout_proc109 [2023-03-09 07:25:25,424][22664] Starting process rollout_proc127 [2023-03-09 07:25:25,425][22664] Starting process rollout_proc121 [2023-03-09 07:25:25,434][22664] Starting process rollout_proc115 [2023-03-09 07:25:25,494][22664] Starting process rollout_proc124 [2023-03-09 07:25:27,035][23093] Worker 17 uses CPU cores [17] [2023-03-09 07:25:27,080][23094] Worker 20 uses CPU cores [20] [2023-03-09 07:25:27,092][23088] Worker 5 uses CPU cores [5] [2023-03-09 07:25:27,113][23089] Worker 8 uses CPU cores [8] [2023-03-09 07:25:27,114][23092] Worker 14 uses CPU cores [14] [2023-03-09 07:25:27,157][23174] Worker 15 uses CPU cores [15] [2023-03-09 07:25:27,192][23091] Worker 11 uses CPU cores [11] [2023-03-09 07:25:27,240][23087] Worker 2 uses CPU cores [2] [2023-03-09 07:25:27,258][23175] Worker 18 uses CPU cores [18] [2023-03-09 07:25:27,264][23171] Worker 3 uses CPU cores [3] [2023-03-09 07:25:27,338][23098] Worker 32 uses CPU cores [32] [2023-03-09 07:25:27,354][23103] Worker 38 uses CPU cores [38] [2023-03-09 07:25:27,413][23177] Worker 27 uses CPU cores [27] [2023-03-09 07:25:27,421][23096] Worker 23 uses CPU cores [23] [2023-03-09 07:25:27,434][23169] Worker 44 uses CPU cores [44] [2023-03-09 07:25:27,511][23176] Worker 21 uses CPU cores [21] [2023-03-09 07:25:27,522][23212] Worker 77 uses CPU cores [77] [2023-03-09 07:25:27,515][23097] Worker 29 uses CPU cores [29] [2023-03-09 07:25:27,572][23170] Worker 6 uses CPU cores [6] [2023-03-09 07:25:27,599][23099] Worker 35 uses CPU cores [35] [2023-03-09 07:25:27,608][23186] Worker 4 uses CPU cores [4] [2023-03-09 07:25:27,619][23172] Worker 9 uses CPU cores [9] [2023-03-09 07:25:27,652][23179] Worker 33 uses CPU cores [33] [2023-03-09 07:25:27,689][23095] Worker 26 uses CPU cores [26] [2023-03-09 07:25:27,706][22664] Starting process rollout_proc0 [2023-03-09 07:25:27,722][23090] Using GPUs [0] for process 0 (actually maps to GPUs [0]) [2023-03-09 07:25:27,723][23090] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0 [2023-03-09 07:25:27,728][23185] Worker 45 uses CPU cores [45] [2023-03-09 07:25:27,742][23202] Worker 43 uses CPU cores [43] [2023-03-09 07:25:27,747][23090] Num visible devices: 1 [2023-03-09 07:25:27,760][23199] Worker 46 uses CPU cores [46] [2023-03-09 07:25:27,770][23192] Worker 28 uses CPU cores [28] [2023-03-09 07:25:27,777][23204] Worker 56 uses CPU cores [56] [2023-03-09 07:25:27,780][23193] Worker 22 uses CPU cores [22] [2023-03-09 07:25:27,815][23191] Worker 19 uses CPU cores [19] [2023-03-09 07:25:27,815][23190] Worker 13 uses CPU cores [13] [2023-03-09 07:25:27,836][23181] Worker 39 uses CPU cores [39] [2023-03-09 07:25:27,836][23213] Worker 80 uses CPU cores [80] [2023-03-09 07:25:27,840][23188] Worker 10 uses CPU cores [10] [2023-03-09 07:25:27,852][23182] Worker 36 uses CPU cores [36] [2023-03-09 07:25:27,854][22664] Starting process rollout_proc1 [2023-03-09 07:25:27,864][23173] Worker 12 uses CPU cores [12] [2023-03-09 07:25:27,866][23197] Worker 37 uses CPU cores [37] [2023-03-09 07:25:27,870][23208] Worker 59 uses CPU cores [59] [2023-03-09 07:25:27,892][23183] Worker 42 uses CPU cores [42] [2023-03-09 07:25:27,893][23207] Worker 62 uses CPU cores [62] [2023-03-09 07:25:27,896][23194] Worker 25 uses CPU cores [25] [2023-03-09 07:25:27,904][23187] Worker 7 uses CPU cores [7] [2023-03-09 07:25:27,904][23201] Worker 50 uses CPU cores [50] [2023-03-09 07:25:27,911][23211] Worker 74 uses CPU cores [74] [2023-03-09 07:25:27,938][23180] Worker 30 uses CPU cores [30] [2023-03-09 07:25:27,964][23218] Worker 57 uses CPU cores [57] [2023-03-09 07:25:27,968][23196] Worker 31 uses CPU cores [31] [2023-03-09 07:25:27,969][23228] Worker 54 uses CPU cores [54] [2023-03-09 07:25:27,970][23217] Worker 86 uses CPU cores [86] [2023-03-09 07:25:27,992][23178] Worker 24 uses CPU cores [24] [2023-03-09 07:25:27,998][23214] Worker 83 uses CPU cores [83] [2023-03-09 07:25:28,008][23216] Worker 51 uses CPU cores [51] [2023-03-09 07:25:28,008][23200] Worker 47 uses CPU cores [47] [2023-03-09 07:25:28,028][23118] Worker 41 uses CPU cores [41] [2023-03-09 07:25:28,056][23209] Worker 68 uses CPU cores [68] [2023-03-09 07:25:28,063][23224] Worker 63 uses CPU cores [63] [2023-03-09 07:25:28,064][23223] Worker 66 uses CPU cores [66] [2023-03-09 07:25:28,068][23210] Worker 71 uses CPU cores [71] [2023-03-09 07:25:28,072][23203] Worker 40 uses CPU cores [40] [2023-03-09 07:25:28,084][23205] Worker 53 uses CPU cores [53] [2023-03-09 07:25:28,096][23232] Worker 49 uses CPU cores [49] [2023-03-09 07:25:28,096][23206] Worker 65 uses CPU cores [65] [2023-03-09 07:25:28,104][23225] Worker 69 uses CPU cores [69] [2023-03-09 07:25:28,104][23238] Worker 67 uses CPU cores [67] [2023-03-09 07:25:28,104][23231] Worker 60 uses CPU cores [60] [2023-03-09 07:25:28,108][23215] Worker 48 uses CPU cores [48] [2023-03-09 07:25:28,120][23229] Worker 75 uses CPU cores [75] [2023-03-09 07:25:28,122][23244] Worker 76 uses CPU cores [76] [2023-03-09 07:25:28,124][23189] Worker 16 uses CPU cores [16] [2023-03-09 07:25:28,125][23195] Worker 34 uses CPU cores [34] [2023-03-09 07:25:28,131][23314] Worker 101 uses CPU cores [101] [2023-03-09 07:25:28,134][23235] Worker 90 uses CPU cores [90] [2023-03-09 07:25:28,136][23237] Worker 73 uses CPU cores [73] [2023-03-09 07:25:28,136][23236] Worker 85 uses CPU cores [85] [2023-03-09 07:25:28,144][23222] Worker 72 uses CPU cores [72] [2023-03-09 07:25:28,160][23219] Worker 89 uses CPU cores [89] [2023-03-09 07:25:28,161][23243] Worker 82 uses CPU cores [82] [2023-03-09 07:25:28,184][23525] Worker 104 uses CPU cores [104] [2023-03-09 07:25:28,188][23245] Worker 55 uses CPU cores [55] [2023-03-09 07:25:28,208][23233] Worker 78 uses CPU cores [78] [2023-03-09 07:25:28,218][23248] Worker 95 uses CPU cores [95] [2023-03-09 07:25:28,228][23485] Worker 110 uses CPU cores [110] [2023-03-09 07:25:28,232][23441] Worker 107 uses CPU cores [107] [2023-03-09 07:25:28,240][23242] Worker 92 uses CPU cores [92] [2023-03-09 07:25:28,244][23240] Worker 64 uses CPU cores [64] [2023-03-09 07:25:28,252][23230] Worker 52 uses CPU cores [52] [2023-03-09 07:25:28,272][23221] Worker 84 uses CPU cores [84] [2023-03-09 07:25:28,286][23227] Worker 81 uses CPU cores [81] [2023-03-09 07:25:28,298][23636] Worker 122 uses CPU cores [122] [2023-03-09 07:25:28,300][23247] Worker 91 uses CPU cores [91] [2023-03-09 07:25:28,312][23638] Worker 125 uses CPU cores [125] [2023-03-09 07:25:28,320][23246] Worker 61 uses CPU cores [61] [2023-03-09 07:25:28,340][23239] Worker 88 uses CPU cores [88] [2023-03-09 07:25:28,352][23637] Worker 96 uses CPU cores [96] [2023-03-09 07:25:28,376][24120] Worker 97 uses CPU cores [97] [2023-03-09 07:25:28,378][23867] Worker 117 uses CPU cores [117] [2023-03-09 07:25:28,379][23249] Worker 98 uses CPU cores [98] [2023-03-09 07:25:28,384][23241] Worker 70 uses CPU cores [70] [2023-03-09 07:25:28,390][23865] Worker 102 uses CPU cores [102] [2023-03-09 07:25:28,396][23961] Worker 120 uses CPU cores [120] [2023-03-09 07:25:28,400][24434] Worker 100 uses CPU cores [100] [2023-03-09 07:25:28,402][23623] Worker 116 uses CPU cores [116] [2023-03-09 07:25:28,404][23817] Worker 108 uses CPU cores [108] [2023-03-09 07:25:28,408][23226] Worker 87 uses CPU cores [87] [2023-03-09 07:25:28,410][23657] Worker 93 uses CPU cores [93] [2023-03-09 07:25:28,423][24121] Worker 94 uses CPU cores [94] [2023-03-09 07:25:28,432][23635] Worker 119 uses CPU cores [119] [2023-03-09 07:25:28,433][23634] Worker 113 uses CPU cores [113] [2023-03-09 07:25:28,436][23662] Worker 99 uses CPU cores [99] [2023-03-09 07:25:28,439][24156] Worker 103 uses CPU cores [103] [2023-03-09 07:25:28,449][23234] Worker 58 uses CPU cores [58] [2023-03-09 07:25:28,455][23250] Worker 79 uses CPU cores [79] [2023-03-09 07:25:28,480][24666] Worker 127 uses CPU cores [127] [2023-03-09 07:25:28,489][24157] Worker 106 uses CPU cores [106] [2023-03-09 07:25:28,494][24818] Worker 115 uses CPU cores [115] [2023-03-09 07:25:28,508][24118] Worker 126 uses CPU cores [126] [2023-03-09 07:25:28,520][24858] Worker 124 uses CPU cores [124] [2023-03-09 07:25:28,535][23823] Worker 105 uses CPU cores [105] [2023-03-09 07:25:28,562][24352] Worker 109 uses CPU cores [109] [2023-03-09 07:25:28,575][24793] Worker 121 uses CPU cores [121] [2023-03-09 07:25:28,593][23866] Worker 111 uses CPU cores [111] [2023-03-09 07:25:28,604][24089] Worker 123 uses CPU cores [123] [2023-03-09 07:25:28,610][24025] Worker 114 uses CPU cores [114] [2023-03-09 07:25:28,665][24158] Worker 112 uses CPU cores [112] [2023-03-09 07:25:28,673][24539] Worker 118 uses CPU cores [118] [2023-03-09 07:25:28,882][22940] Using optimizer [2023-03-09 07:25:28,882][22940] No checkpoints found [2023-03-09 07:25:28,883][22940] Did not load from checkpoint, starting from scratch! [2023-03-09 07:25:28,883][22940] Initialized policy 0 weights for model version 0 [2023-03-09 07:25:28,884][22940] LearnerWorker_p0 finished initialization! [2023-03-09 07:25:28,885][22940] Using GPUs [0] for process 0 (actually maps to GPUs [0]) [2023-03-09 07:25:28,935][23090] RunningMeanStd input shape: (3, 72, 128) [2023-03-09 07:25:28,936][23090] RunningMeanStd input shape: (1,) [2023-03-09 07:25:28,946][23090] ConvEncoder: input_channels=3 [2023-03-09 07:25:29,018][23090] Conv encoder output size: 512 [2023-03-09 07:25:29,019][23090] Policy head output size: 512 [2023-03-09 07:25:29,043][32460] Worker 0 uses CPU cores [0] [2023-03-09 07:25:29,058][22664] Fps is (10 sec: nan, 60 sec: nan, 300 sec: nan). Total num frames: 0. Throughput: 0: nan. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) [2023-03-09 07:25:29,068][33428] Worker 1 uses CPU cores [1] [2023-03-09 07:25:29,874][22664] Inference worker 0-0 is ready! [2023-03-09 07:25:29,875][22664] All inference workers are ready! Signal rollout workers to start! [2023-03-09 07:25:29,953][23196] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:29,954][23961] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:29,956][24157] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:29,956][23638] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:29,957][23200] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:29,957][23485] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:29,959][23218] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:29,960][23238] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:29,960][23242] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:29,961][23244] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:29,962][23094] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:29,963][24120] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:29,962][23195] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:29,963][23187] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:29,963][23441] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:29,964][23088] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:29,964][23222] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:29,964][23193] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:29,965][23243] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:29,965][23212] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:29,965][23237] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:29,966][23209] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:29,966][32460] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:29,966][23203] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:29,966][23095] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:29,967][23096] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:29,967][24118] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:29,967][23211] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:29,967][23097] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:29,968][23099] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:29,968][23087] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:29,968][23219] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:29,968][23089] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:29,968][23241] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:29,968][23636] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:29,969][24089] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:29,969][23171] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:29,969][23233] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:29,969][23225] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:29,969][23186] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:29,969][23180] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:29,969][23188] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:29,970][23867] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:29,970][23240] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:29,970][23092] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:29,970][23250] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:29,970][23634] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:29,967][23093] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:29,971][24539] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:29,971][23223] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:29,971][23174] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:29,971][23245] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:29,971][23201] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:29,972][23208] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:29,972][23247] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:29,972][23235] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:29,972][23183] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:29,972][23637] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:29,973][23216] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:29,973][23635] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:29,973][23189] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:29,973][23866] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:29,973][23213] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:29,974][24818] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:29,974][23202] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:29,974][23178] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:29,974][23239] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:29,974][23228] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:29,975][23217] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:29,976][23197] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:29,976][23226] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:29,976][23230] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:29,976][23657] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:29,977][23314] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:29,977][23169] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:29,977][23118] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:29,977][23206] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:29,977][23182] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:29,977][23170] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:29,977][23227] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:29,977][23175] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:29,977][23234] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:29,978][23185] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:29,978][23215] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:29,978][23103] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:29,978][23249] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:29,978][24793] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:29,978][23865] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:29,979][23525] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:29,979][23248] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:29,979][24121] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:29,979][23823] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:29,979][23236] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:29,979][23224] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:29,979][23207] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:29,979][23173] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:29,980][23181] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:29,980][24156] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:29,980][23623] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:29,980][23205] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:29,980][24025] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:29,980][24158] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:29,980][24434] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:29,980][23199] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:29,981][23190] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:29,981][24666] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:29,981][23662] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:29,981][23191] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:29,981][23194] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:29,981][23098] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:29,981][23204] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:29,982][23246] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:29,982][24858] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:29,982][23231] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:29,982][23221] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:29,982][23232] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:29,983][23091] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:29,983][23214] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:29,983][33428] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:29,985][23817] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:29,987][23229] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:29,988][23192] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:29,988][24352] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:29,990][23176] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:29,991][23179] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:29,990][23210] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:29,992][23172] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:30,595][23177] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 07:25:30,978][24118] Decorrelating experience for 0 frames... [2023-03-09 07:25:30,979][23865] Decorrelating experience for 0 frames... [2023-03-09 07:25:30,988][23247] Decorrelating experience for 0 frames... [2023-03-09 07:25:31,089][24157] Decorrelating experience for 0 frames... [2023-03-09 07:25:31,089][23961] Decorrelating experience for 0 frames... [2023-03-09 07:25:31,089][23215] Decorrelating experience for 0 frames... [2023-03-09 07:25:31,089][23485] Decorrelating experience for 0 frames... [2023-03-09 07:25:31,089][32460] Decorrelating experience for 0 frames... [2023-03-09 07:25:31,090][23244] Decorrelating experience for 0 frames... [2023-03-09 07:25:31,090][23226] Decorrelating experience for 0 frames... [2023-03-09 07:25:31,146][23094] Decorrelating experience for 0 frames... [2023-03-09 07:25:31,149][23187] Decorrelating experience for 0 frames... [2023-03-09 07:25:31,155][23170] Decorrelating experience for 0 frames... [2023-03-09 07:25:31,265][24157] Decorrelating experience for 32 frames... [2023-03-09 07:25:31,267][23215] Decorrelating experience for 32 frames... [2023-03-09 07:25:31,270][32460] Decorrelating experience for 32 frames... [2023-03-09 07:25:31,271][23224] Decorrelating experience for 0 frames... [2023-03-09 07:25:31,271][23244] Decorrelating experience for 32 frames... [2023-03-09 07:25:31,272][23223] Decorrelating experience for 0 frames... [2023-03-09 07:25:31,272][23216] Decorrelating experience for 0 frames... [2023-03-09 07:25:31,316][23817] Decorrelating experience for 0 frames... [2023-03-09 07:25:31,321][23172] Decorrelating experience for 0 frames... [2023-03-09 07:25:31,349][23662] Decorrelating experience for 0 frames... [2023-03-09 07:25:31,447][24793] Decorrelating experience for 0 frames... [2023-03-09 07:25:31,449][23223] Decorrelating experience for 32 frames... [2023-03-09 07:25:31,450][23525] Decorrelating experience for 0 frames... [2023-03-09 07:25:31,451][23213] Decorrelating experience for 0 frames... [2023-03-09 07:25:31,470][23099] Decorrelating experience for 0 frames... [2023-03-09 07:25:31,492][23172] Decorrelating experience for 32 frames... [2023-03-09 07:25:31,494][23216] Decorrelating experience for 32 frames... [2023-03-09 07:25:31,518][23623] Decorrelating experience for 0 frames... [2023-03-09 07:25:31,520][23173] Decorrelating experience for 0 frames... [2023-03-09 07:25:31,525][23244] Decorrelating experience for 64 frames... [2023-03-09 07:25:31,620][23098] Decorrelating experience for 0 frames... [2023-03-09 07:25:31,623][24156] Decorrelating experience for 0 frames... [2023-03-09 07:25:31,630][23170] Decorrelating experience for 32 frames... [2023-03-09 07:25:31,633][23231] Decorrelating experience for 0 frames... [2023-03-09 07:25:31,652][23865] Decorrelating experience for 32 frames... [2023-03-09 07:25:31,665][23247] Decorrelating experience for 32 frames... [2023-03-09 07:25:31,668][24025] Decorrelating experience for 0 frames... [2023-03-09 07:25:31,701][23173] Decorrelating experience for 32 frames... [2023-03-09 07:25:31,711][23245] Decorrelating experience for 0 frames... [2023-03-09 07:25:31,713][23230] Decorrelating experience for 0 frames... [2023-03-09 07:25:31,794][23224] Decorrelating experience for 32 frames... [2023-03-09 07:25:31,796][23207] Decorrelating experience for 0 frames... [2023-03-09 07:25:31,811][23092] Decorrelating experience for 0 frames... [2023-03-09 07:25:31,811][23180] Decorrelating experience for 0 frames... [2023-03-09 07:25:31,822][23662] Decorrelating experience for 32 frames... [2023-03-09 07:25:31,854][23638] Decorrelating experience for 0 frames... [2023-03-09 07:25:31,855][23118] Decorrelating experience for 0 frames... [2023-03-09 07:25:31,874][23095] Decorrelating experience for 0 frames... [2023-03-09 07:25:31,887][23203] Decorrelating experience for 0 frames... [2023-03-09 07:25:31,925][23222] Decorrelating experience for 0 frames... [2023-03-09 07:25:31,967][23186] Decorrelating experience for 0 frames... [2023-03-09 07:25:31,995][23099] Decorrelating experience for 32 frames... [2023-03-09 07:25:32,009][24121] Decorrelating experience for 0 frames... [2023-03-09 07:25:32,028][23093] Decorrelating experience for 0 frames... [2023-03-09 07:25:32,034][23865] Decorrelating experience for 64 frames... [2023-03-09 07:25:32,034][23089] Decorrelating experience for 0 frames... [2023-03-09 07:25:32,051][23247] Decorrelating experience for 64 frames... [2023-03-09 07:25:32,089][23103] Decorrelating experience for 0 frames... [2023-03-09 07:25:32,090][23170] Decorrelating experience for 64 frames... [2023-03-09 07:25:32,123][23222] Decorrelating experience for 32 frames... [2023-03-09 07:25:32,141][23171] Decorrelating experience for 0 frames... [2023-03-09 07:25:32,179][23216] Decorrelating experience for 64 frames... [2023-03-09 07:25:32,202][23241] Decorrelating experience for 0 frames... [2023-03-09 07:25:32,206][23176] Decorrelating experience for 0 frames... [2023-03-09 07:25:32,209][23091] Decorrelating experience for 0 frames... [2023-03-09 07:25:32,211][23203] Decorrelating experience for 32 frames... [2023-03-09 07:25:32,270][23207] Decorrelating experience for 32 frames... [2023-03-09 07:25:32,271][24434] Decorrelating experience for 0 frames... [2023-03-09 07:25:32,297][23177] Decorrelating experience for 0 frames... [2023-03-09 07:25:32,312][23234] Decorrelating experience for 0 frames... [2023-03-09 07:25:32,314][23182] Decorrelating experience for 0 frames... [2023-03-09 07:25:32,348][23093] Decorrelating experience for 32 frames... [2023-03-09 07:25:32,375][23196] Decorrelating experience for 0 frames... [2023-03-09 07:25:32,378][23187] Decorrelating experience for 32 frames... [2023-03-09 07:25:32,381][24121] Decorrelating experience for 32 frames... [2023-03-09 07:25:32,389][23199] Decorrelating experience for 0 frames... [2023-03-09 07:25:32,446][23219] Decorrelating experience for 0 frames... [2023-03-09 07:25:32,447][23203] Decorrelating experience for 64 frames... [2023-03-09 07:25:32,488][23092] Decorrelating experience for 32 frames... [2023-03-09 07:25:32,488][23218] Decorrelating experience for 0 frames... [2023-03-09 07:25:32,503][23183] Decorrelating experience for 0 frames... [2023-03-09 07:25:32,519][33428] Decorrelating experience for 0 frames... [2023-03-09 07:25:32,554][24089] Decorrelating experience for 0 frames... [2023-03-09 07:25:32,555][23207] Decorrelating experience for 64 frames... [2023-03-09 07:25:32,562][23199] Decorrelating experience for 32 frames... [2023-03-09 07:25:32,588][24157] Decorrelating experience for 64 frames... [2023-03-09 07:25:32,621][23188] Decorrelating experience for 0 frames... [2023-03-09 07:25:32,626][23185] Decorrelating experience for 0 frames... [2023-03-09 07:25:32,660][23218] Decorrelating experience for 32 frames... [2023-03-09 07:25:32,662][23193] Decorrelating experience for 0 frames... [2023-03-09 07:25:32,674][23197] Decorrelating experience for 0 frames... [2023-03-09 07:25:32,688][33428] Decorrelating experience for 32 frames... [2023-03-09 07:25:32,727][23225] Decorrelating experience for 0 frames... [2023-03-09 07:25:32,733][23243] Decorrelating experience for 0 frames... [2023-03-09 07:25:32,745][23196] Decorrelating experience for 32 frames... [2023-03-09 07:25:32,760][23229] Decorrelating experience for 0 frames... [2023-03-09 07:25:32,798][23202] Decorrelating experience for 0 frames... [2023-03-09 07:25:32,799][23207] Decorrelating experience for 96 frames... [2023-03-09 07:25:32,839][23235] Decorrelating experience for 0 frames... [2023-03-09 07:25:32,845][24025] Decorrelating experience for 32 frames... [2023-03-09 07:25:32,862][23103] Decorrelating experience for 32 frames... [2023-03-09 07:25:32,866][23176] Decorrelating experience for 32 frames... [2023-03-09 07:25:32,910][23243] Decorrelating experience for 32 frames... [2023-03-09 07:25:32,917][23209] Decorrelating experience for 0 frames... [2023-03-09 07:25:32,934][23091] Decorrelating experience for 32 frames... [2023-03-09 07:25:32,949][23236] Decorrelating experience for 0 frames... [2023-03-09 07:25:32,972][23250] Decorrelating experience for 0 frames... [2023-03-09 07:25:32,978][23228] Decorrelating experience for 0 frames... [2023-03-09 07:25:33,007][23215] Decorrelating experience for 64 frames... [2023-03-09 07:25:33,023][23221] Decorrelating experience for 0 frames... [2023-03-09 07:25:33,036][23234] Decorrelating experience for 32 frames... [2023-03-09 07:25:33,040][23191] Decorrelating experience for 0 frames... [2023-03-09 07:25:33,081][23213] Decorrelating experience for 32 frames... [2023-03-09 07:25:33,102][24156] Decorrelating experience for 32 frames... [2023-03-09 07:25:33,109][23237] Decorrelating experience for 0 frames... [2023-03-09 07:25:33,121][23246] Decorrelating experience for 0 frames... [2023-03-09 07:25:33,144][23218] Decorrelating experience for 64 frames... [2023-03-09 07:25:33,153][23095] Decorrelating experience for 32 frames... [2023-03-09 07:25:33,176][23212] Decorrelating experience for 0 frames... [2023-03-09 07:25:33,198][23215] Decorrelating experience for 96 frames... [2023-03-09 07:25:33,214][32460] Decorrelating experience for 64 frames... [2023-03-09 07:25:33,218][23192] Decorrelating experience for 0 frames... [2023-03-09 07:25:33,252][23176] Decorrelating experience for 64 frames... [2023-03-09 07:25:33,274][23206] Decorrelating experience for 0 frames... [2023-03-09 07:25:33,315][23867] Decorrelating experience for 0 frames... [2023-03-09 07:25:33,333][23118] Decorrelating experience for 32 frames... [2023-03-09 07:25:33,347][23525] Decorrelating experience for 32 frames... [2023-03-09 07:25:33,351][23247] Decorrelating experience for 96 frames... [2023-03-09 07:25:33,361][23203] Decorrelating experience for 96 frames... [2023-03-09 07:25:33,378][23200] Decorrelating experience for 0 frames... [2023-03-09 07:25:33,390][23245] Decorrelating experience for 32 frames... [2023-03-09 07:25:33,417][23187] Decorrelating experience for 64 frames... [2023-03-09 07:25:33,429][23236] Decorrelating experience for 32 frames... [2023-03-09 07:25:33,446][23212] Decorrelating experience for 32 frames... [2023-03-09 07:25:33,485][24157] Decorrelating experience for 96 frames... [2023-03-09 07:25:33,514][23235] Decorrelating experience for 32 frames... [2023-03-09 07:25:33,520][23238] Decorrelating experience for 0 frames... [2023-03-09 07:25:33,523][23219] Decorrelating experience for 32 frames... [2023-03-09 07:25:33,537][23093] Decorrelating experience for 64 frames... [2023-03-09 07:25:33,566][23231] Decorrelating experience for 32 frames... [2023-03-09 07:25:33,567][23118] Decorrelating experience for 64 frames... [2023-03-09 07:25:33,600][23197] Decorrelating experience for 32 frames... [2023-03-09 07:25:33,605][23200] Decorrelating experience for 32 frames... [2023-03-09 07:25:33,624][23662] Decorrelating experience for 64 frames... [2023-03-09 07:25:33,658][23207] Decorrelating experience for 128 frames... [2023-03-09 07:25:33,690][23224] Decorrelating experience for 64 frames... [2023-03-09 07:25:33,691][23094] Decorrelating experience for 32 frames... [2023-03-09 07:25:33,696][23223] Decorrelating experience for 64 frames... [2023-03-09 07:25:33,718][23178] Decorrelating experience for 0 frames... [2023-03-09 07:25:33,740][24156] Decorrelating experience for 64 frames... [2023-03-09 07:25:33,741][23218] Decorrelating experience for 96 frames... [2023-03-09 07:25:33,776][23485] Decorrelating experience for 32 frames... [2023-03-09 07:25:33,779][23226] Decorrelating experience for 32 frames... [2023-03-09 07:25:33,797][23192] Decorrelating experience for 32 frames... [2023-03-09 07:25:33,830][23216] Decorrelating experience for 96 frames... [2023-03-09 07:25:33,870][23210] Decorrelating experience for 0 frames... [2023-03-09 07:25:33,871][23248] Decorrelating experience for 0 frames... [2023-03-09 07:25:33,874][23191] Decorrelating experience for 32 frames... [2023-03-09 07:25:33,891][23169] Decorrelating experience for 0 frames... [2023-03-09 07:25:33,917][23203] Decorrelating experience for 128 frames... [2023-03-09 07:25:33,924][23094] Decorrelating experience for 64 frames... [2023-03-09 07:25:33,950][24434] Decorrelating experience for 32 frames... [2023-03-09 07:25:33,972][23213] Decorrelating experience for 64 frames... [2023-03-09 07:25:33,973][23171] Decorrelating experience for 32 frames... [2023-03-09 07:25:34,012][23242] Decorrelating experience for 0 frames... [2023-03-09 07:25:34,048][23180] Decorrelating experience for 32 frames... [2023-03-09 07:25:34,049][23099] Decorrelating experience for 64 frames... [2023-03-09 07:25:34,050][23173] Decorrelating experience for 64 frames... [2023-03-09 07:25:34,059][22664] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 0.0. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) [2023-03-09 07:25:34,063][23118] Decorrelating experience for 96 frames... [2023-03-09 07:25:34,094][23223] Decorrelating experience for 96 frames... [2023-03-09 07:25:34,098][23246] Decorrelating experience for 32 frames... [2023-03-09 07:25:34,130][23249] Decorrelating experience for 0 frames... [2023-03-09 07:25:34,146][24157] Decorrelating experience for 128 frames... [2023-03-09 07:25:34,151][23200] Decorrelating experience for 64 frames... [2023-03-09 07:25:34,180][24434] Decorrelating experience for 64 frames... [2023-03-09 07:25:34,221][23094] Decorrelating experience for 96 frames... [2023-03-09 07:25:34,226][24121] Decorrelating experience for 64 frames... [2023-03-09 07:25:34,229][23089] Decorrelating experience for 32 frames... [2023-03-09 07:25:34,240][23093] Decorrelating experience for 96 frames... [2023-03-09 07:25:34,270][23118] Decorrelating experience for 128 frames... [2023-03-09 07:25:34,272][23662] Decorrelating experience for 96 frames... [2023-03-09 07:25:34,331][23202] Decorrelating experience for 32 frames... [2023-03-09 07:25:34,360][23250] Decorrelating experience for 32 frames... [2023-03-09 07:25:34,366][23190] Decorrelating experience for 0 frames... [2023-03-09 07:25:34,392][23174] Decorrelating experience for 0 frames... [2023-03-09 07:25:34,401][23865] Decorrelating experience for 96 frames... [2023-03-09 07:25:34,404][23188] Decorrelating experience for 32 frames... [2023-03-09 07:25:34,412][23221] Decorrelating experience for 32 frames... [2023-03-09 07:25:34,426][23087] Decorrelating experience for 0 frames... [2023-03-09 07:25:34,446][23096] Decorrelating experience for 0 frames... [2023-03-09 07:25:34,459][23099] Decorrelating experience for 96 frames... [2023-03-09 07:25:34,503][23249] Decorrelating experience for 32 frames... [2023-03-09 07:25:34,537][23180] Decorrelating experience for 64 frames... [2023-03-09 07:25:34,539][24156] Decorrelating experience for 96 frames... [2023-03-09 07:25:34,564][23202] Decorrelating experience for 64 frames... [2023-03-09 07:25:34,577][23234] Decorrelating experience for 64 frames... [2023-03-09 07:25:34,588][23212] Decorrelating experience for 64 frames... [2023-03-09 07:25:34,602][23238] Decorrelating experience for 32 frames... [2023-03-09 07:25:34,619][23188] Decorrelating experience for 64 frames... [2023-03-09 07:25:34,627][23206] Decorrelating experience for 32 frames... [2023-03-09 07:25:34,630][23217] Decorrelating experience for 0 frames... [2023-03-09 07:25:34,714][23191] Decorrelating experience for 64 frames... [2023-03-09 07:25:34,722][23222] Decorrelating experience for 64 frames... [2023-03-09 07:25:34,723][23211] Decorrelating experience for 0 frames... [2023-03-09 07:25:34,737][23205] Decorrelating experience for 0 frames... [2023-03-09 07:25:34,755][23195] Decorrelating experience for 0 frames... [2023-03-09 07:25:34,769][23171] Decorrelating experience for 64 frames... [2023-03-09 07:25:34,780][23634] Decorrelating experience for 0 frames... [2023-03-09 07:25:34,809][23170] Decorrelating experience for 96 frames... [2023-03-09 07:25:34,863][23095] Decorrelating experience for 64 frames... [2023-03-09 07:25:34,871][23235] Decorrelating experience for 64 frames... [2023-03-09 07:25:34,892][23240] Decorrelating experience for 0 frames... [2023-03-09 07:25:34,899][23244] Decorrelating experience for 96 frames... [2023-03-09 07:25:34,913][23176] Decorrelating experience for 96 frames... [2023-03-09 07:25:34,927][24434] Decorrelating experience for 96 frames... [2023-03-09 07:25:34,937][33428] Decorrelating experience for 64 frames... [2023-03-09 07:25:34,948][23238] Decorrelating experience for 64 frames... [2023-03-09 07:25:34,956][23186] Decorrelating experience for 32 frames... [2023-03-09 07:25:34,981][23636] Decorrelating experience for 0 frames... [2023-03-09 07:25:35,043][23224] Decorrelating experience for 96 frames... [2023-03-09 07:25:35,043][23214] Decorrelating experience for 0 frames... [2023-03-09 07:25:35,066][23170] Decorrelating experience for 128 frames... [2023-03-09 07:25:35,072][24118] Decorrelating experience for 32 frames... [2023-03-09 07:25:35,084][23088] Decorrelating experience for 0 frames... [2023-03-09 07:25:35,108][23097] Decorrelating experience for 0 frames... [2023-03-09 07:25:35,119][23095] Decorrelating experience for 96 frames... [2023-03-09 07:25:35,131][33428] Decorrelating experience for 96 frames... [2023-03-09 07:25:35,141][24025] Decorrelating experience for 64 frames... [2023-03-09 07:25:35,151][23636] Decorrelating experience for 32 frames... [2023-03-09 07:25:35,216][23247] Decorrelating experience for 128 frames... [2023-03-09 07:25:35,233][23091] Decorrelating experience for 64 frames... [2023-03-09 07:25:35,246][23179] Decorrelating experience for 0 frames... [2023-03-09 07:25:35,284][23233] Decorrelating experience for 0 frames... [2023-03-09 07:25:35,293][23866] Decorrelating experience for 0 frames... [2023-03-09 07:25:35,305][23634] Decorrelating experience for 32 frames... [2023-03-09 07:25:35,314][23228] Decorrelating experience for 32 frames... [2023-03-09 07:25:35,321][23087] Decorrelating experience for 32 frames... [2023-03-09 07:25:35,324][23223] Decorrelating experience for 128 frames... [2023-03-09 07:25:35,328][23213] Decorrelating experience for 96 frames... [2023-03-09 07:25:35,392][23216] Decorrelating experience for 128 frames... [2023-03-09 07:25:35,426][23188] Decorrelating experience for 96 frames... [2023-03-09 07:25:35,434][23170] Decorrelating experience for 160 frames... [2023-03-09 07:25:35,462][23204] Decorrelating experience for 0 frames... [2023-03-09 07:25:35,471][23089] Decorrelating experience for 64 frames... [2023-03-09 07:25:35,483][23097] Decorrelating experience for 32 frames... [2023-03-09 07:25:35,487][23636] Decorrelating experience for 64 frames... [2023-03-09 07:25:35,493][23180] Decorrelating experience for 96 frames... [2023-03-09 07:25:35,499][23638] Decorrelating experience for 32 frames... [2023-03-09 07:25:35,501][23248] Decorrelating experience for 32 frames... [2023-03-09 07:25:35,570][23226] Decorrelating experience for 64 frames... [2023-03-09 07:25:35,598][23194] Decorrelating experience for 0 frames... [2023-03-09 07:25:35,614][23866] Decorrelating experience for 32 frames... [2023-03-09 07:25:35,636][23245] Decorrelating experience for 64 frames... [2023-03-09 07:25:35,643][23186] Decorrelating experience for 64 frames... [2023-03-09 07:25:35,662][24118] Decorrelating experience for 64 frames... [2023-03-09 07:25:35,663][23088] Decorrelating experience for 32 frames... [2023-03-09 07:25:35,668][23097] Decorrelating experience for 64 frames... [2023-03-09 07:25:35,674][23176] Decorrelating experience for 128 frames... [2023-03-09 07:25:35,676][23171] Decorrelating experience for 96 frames... [2023-03-09 07:25:35,750][24156] Decorrelating experience for 128 frames... [2023-03-09 07:25:35,769][23194] Decorrelating experience for 32 frames... [2023-03-09 07:25:35,788][24025] Decorrelating experience for 96 frames... [2023-03-09 07:25:35,814][23170] Decorrelating experience for 192 frames... [2023-03-09 07:25:35,822][23215] Decorrelating experience for 128 frames... [2023-03-09 07:25:35,839][23204] Decorrelating experience for 32 frames... [2023-03-09 07:25:35,846][23635] Decorrelating experience for 0 frames... [2023-03-09 07:25:35,847][23634] Decorrelating experience for 64 frames... [2023-03-09 07:25:35,849][23314] Decorrelating experience for 0 frames... [2023-03-09 07:25:35,853][23229] Decorrelating experience for 32 frames... [2023-03-09 07:25:35,927][23234] Decorrelating experience for 96 frames... [2023-03-09 07:25:35,951][23193] Decorrelating experience for 32 frames... [2023-03-09 07:25:35,990][23186] Decorrelating experience for 96 frames... [2023-03-09 07:25:35,995][23249] Decorrelating experience for 64 frames... [2023-03-09 07:25:35,997][23088] Decorrelating experience for 64 frames... [2023-03-09 07:25:36,013][23244] Decorrelating experience for 128 frames... [2023-03-09 07:25:36,024][24156] Decorrelating experience for 160 frames... [2023-03-09 07:25:36,026][23240] Decorrelating experience for 32 frames... [2023-03-09 07:25:36,031][23236] Decorrelating experience for 64 frames... [2023-03-09 07:25:36,032][23623] Decorrelating experience for 32 frames... [2023-03-09 07:25:36,106][23250] Decorrelating experience for 64 frames... [2023-03-09 07:25:36,131][23095] Decorrelating experience for 128 frames... [2023-03-09 07:25:36,167][23202] Decorrelating experience for 96 frames... [2023-03-09 07:25:36,171][23204] Decorrelating experience for 64 frames... [2023-03-09 07:25:36,193][23246] Decorrelating experience for 64 frames... [2023-03-09 07:25:36,207][23867] Decorrelating experience for 32 frames... [2023-03-09 07:25:36,210][23232] Decorrelating experience for 0 frames... [2023-03-09 07:25:36,214][23200] Decorrelating experience for 96 frames... [2023-03-09 07:25:36,214][23182] Decorrelating experience for 32 frames... [2023-03-09 07:25:36,231][23233] Decorrelating experience for 32 frames... [2023-03-09 07:25:36,306][23175] Decorrelating experience for 0 frames... [2023-03-09 07:25:36,311][23091] Decorrelating experience for 96 frames... [2023-03-09 07:25:36,354][23634] Decorrelating experience for 96 frames... [2023-03-09 07:25:36,367][23092] Decorrelating experience for 64 frames... [2023-03-09 07:25:36,368][23097] Decorrelating experience for 96 frames... [2023-03-09 07:25:36,389][23638] Decorrelating experience for 64 frames... [2023-03-09 07:25:36,407][24156] Decorrelating experience for 192 frames... [2023-03-09 07:25:36,416][23196] Decorrelating experience for 64 frames... [2023-03-09 07:25:36,417][23636] Decorrelating experience for 96 frames... [2023-03-09 07:25:36,432][23229] Decorrelating experience for 64 frames... [2023-03-09 07:25:36,487][23193] Decorrelating experience for 64 frames... [2023-03-09 07:25:36,528][23179] Decorrelating experience for 32 frames... [2023-03-09 07:25:36,529][23234] Decorrelating experience for 128 frames... [2023-03-09 07:25:36,548][23441] Decorrelating experience for 0 frames... [2023-03-09 07:25:36,564][24858] Decorrelating experience for 0 frames... [2023-03-09 07:25:36,565][23248] Decorrelating experience for 64 frames... [2023-03-09 07:25:36,583][23199] Decorrelating experience for 64 frames... [2023-03-09 07:25:36,594][23195] Decorrelating experience for 32 frames... [2023-03-09 07:25:36,605][23525] Decorrelating experience for 64 frames... [2023-03-09 07:25:36,609][23172] Decorrelating experience for 64 frames... [2023-03-09 07:25:36,658][23221] Decorrelating experience for 64 frames... [2023-03-09 07:25:36,701][23186] Decorrelating experience for 128 frames... [2023-03-09 07:25:36,703][23183] Decorrelating experience for 32 frames... [2023-03-09 07:25:36,741][23867] Decorrelating experience for 64 frames... [2023-03-09 07:25:36,763][23092] Decorrelating experience for 96 frames... [2023-03-09 07:25:36,779][23195] Decorrelating experience for 64 frames... [2023-03-09 07:25:36,784][23623] Decorrelating experience for 64 frames... [2023-03-09 07:25:36,787][23635] Decorrelating experience for 32 frames... [2023-03-09 07:25:36,788][23636] Decorrelating experience for 128 frames... [2023-03-09 07:25:36,802][23245] Decorrelating experience for 96 frames... [2023-03-09 07:25:36,833][23638] Decorrelating experience for 96 frames... [2023-03-09 07:25:36,878][23202] Decorrelating experience for 128 frames... [2023-03-09 07:25:36,880][23199] Decorrelating experience for 96 frames... [2023-03-09 07:25:36,913][23179] Decorrelating experience for 64 frames... [2023-03-09 07:25:36,951][33428] Decorrelating experience for 128 frames... [2023-03-09 07:25:36,957][23223] Decorrelating experience for 160 frames... [2023-03-09 07:25:36,959][24352] Decorrelating experience for 0 frames... [2023-03-09 07:25:36,961][23194] Decorrelating experience for 64 frames... [2023-03-09 07:25:36,963][23180] Decorrelating experience for 128 frames... [2023-03-09 07:25:36,974][23195] Decorrelating experience for 96 frames... [2023-03-09 07:25:37,011][23209] Decorrelating experience for 32 frames... [2023-03-09 07:25:37,052][23182] Decorrelating experience for 64 frames... [2023-03-09 07:25:37,053][23525] Decorrelating experience for 96 frames... [2023-03-09 07:25:37,099][23239] Decorrelating experience for 0 frames... [2023-03-09 07:25:37,123][23205] Decorrelating experience for 32 frames... [2023-03-09 07:25:37,142][23232] Decorrelating experience for 32 frames... [2023-03-09 07:25:37,143][23183] Decorrelating experience for 64 frames... [2023-03-09 07:25:37,147][23188] Decorrelating experience for 128 frames... [2023-03-09 07:25:37,149][23207] Decorrelating experience for 160 frames... [2023-03-09 07:25:37,158][23185] Decorrelating experience for 32 frames... [2023-03-09 07:25:37,187][23223] Decorrelating experience for 192 frames... [2023-03-09 07:25:37,231][23623] Decorrelating experience for 96 frames... [2023-03-09 07:25:37,262][24352] Decorrelating experience for 32 frames... [2023-03-09 07:25:37,269][33428] Decorrelating experience for 160 frames... [2023-03-09 07:25:37,300][23176] Decorrelating experience for 160 frames... [2023-03-09 07:25:37,315][23237] Decorrelating experience for 32 frames... [2023-03-09 07:25:37,325][23865] Decorrelating experience for 128 frames... [2023-03-09 07:25:37,336][23174] Decorrelating experience for 32 frames... [2023-03-09 07:25:37,337][23097] Decorrelating experience for 128 frames... [2023-03-09 07:25:37,343][23170] Decorrelating experience for 224 frames... [2023-03-09 07:25:37,360][23525] Decorrelating experience for 128 frames... [2023-03-09 07:25:37,435][23193] Decorrelating experience for 96 frames... [2023-03-09 07:25:37,450][23088] Decorrelating experience for 96 frames... [2023-03-09 07:25:37,467][23241] Decorrelating experience for 32 frames... [2023-03-09 07:25:37,488][23089] Decorrelating experience for 96 frames... [2023-03-09 07:25:37,491][24858] Decorrelating experience for 32 frames... [2023-03-09 07:25:37,499][24434] Decorrelating experience for 128 frames... [2023-03-09 07:25:37,512][23250] Decorrelating experience for 96 frames... [2023-03-09 07:25:37,519][23210] Decorrelating experience for 32 frames... [2023-03-09 07:25:37,523][23239] Decorrelating experience for 32 frames... [2023-03-09 07:25:37,537][23183] Decorrelating experience for 96 frames... [2023-03-09 07:25:37,608][23221] Decorrelating experience for 96 frames... [2023-03-09 07:25:37,623][23216] Decorrelating experience for 160 frames... [2023-03-09 07:25:37,639][23193] Decorrelating experience for 128 frames... [2023-03-09 07:25:37,663][23224] Decorrelating experience for 128 frames... [2023-03-09 07:25:37,677][23232] Decorrelating experience for 64 frames... [2023-03-09 07:25:37,686][23195] Decorrelating experience for 128 frames... [2023-03-09 07:25:37,699][24352] Decorrelating experience for 64 frames... [2023-03-09 07:25:37,701][23961] Decorrelating experience for 32 frames... [2023-03-09 07:25:37,711][23238] Decorrelating experience for 96 frames... [2023-03-09 07:25:37,720][24118] Decorrelating experience for 96 frames... [2023-03-09 07:25:37,791][23623] Decorrelating experience for 128 frames... [2023-03-09 07:25:37,797][23089] Decorrelating experience for 128 frames... [2023-03-09 07:25:37,813][23179] Decorrelating experience for 96 frames... [2023-03-09 07:25:37,854][23237] Decorrelating experience for 64 frames... [2023-03-09 07:25:37,854][23817] Decorrelating experience for 32 frames... [2023-03-09 07:25:37,859][23181] Decorrelating experience for 0 frames... [2023-03-09 07:25:37,895][23199] Decorrelating experience for 128 frames... [2023-03-09 07:25:37,898][23865] Decorrelating experience for 160 frames... [2023-03-09 07:25:37,900][23207] Decorrelating experience for 192 frames... [2023-03-09 07:25:37,917][24434] Decorrelating experience for 160 frames... [2023-03-09 07:25:37,971][23188] Decorrelating experience for 160 frames... [2023-03-09 07:25:37,975][23218] Decorrelating experience for 128 frames... [2023-03-09 07:25:37,985][24157] Decorrelating experience for 160 frames... [2023-03-09 07:25:38,030][24858] Decorrelating experience for 64 frames... [2023-03-09 07:25:38,032][23525] Decorrelating experience for 160 frames... [2023-03-09 07:25:38,037][23214] Decorrelating experience for 32 frames... [2023-03-09 07:25:38,069][23192] Decorrelating experience for 64 frames... [2023-03-09 07:25:38,072][23240] Decorrelating experience for 64 frames... [2023-03-09 07:25:38,086][23217] Decorrelating experience for 32 frames... [2023-03-09 07:25:38,121][23179] Decorrelating experience for 128 frames... [2023-03-09 07:25:38,143][24118] Decorrelating experience for 128 frames... [2023-03-09 07:25:38,160][23097] Decorrelating experience for 160 frames... [2023-03-09 07:25:38,173][23246] Decorrelating experience for 96 frames... [2023-03-09 07:25:38,204][23241] Decorrelating experience for 64 frames... [2023-03-09 07:25:38,219][23199] Decorrelating experience for 160 frames... [2023-03-09 07:25:38,228][23193] Decorrelating experience for 160 frames... [2023-03-09 07:25:38,252][23169] Decorrelating experience for 32 frames... [2023-03-09 07:25:38,264][23213] Decorrelating experience for 128 frames... [2023-03-09 07:25:38,289][23638] Decorrelating experience for 128 frames... [2023-03-09 07:25:38,303][23188] Decorrelating experience for 192 frames... [2023-03-09 07:25:38,317][24157] Decorrelating experience for 192 frames... [2023-03-09 07:25:38,338][23236] Decorrelating experience for 96 frames... [2023-03-09 07:25:38,353][23185] Decorrelating experience for 64 frames... [2023-03-09 07:25:38,375][24858] Decorrelating experience for 96 frames... [2023-03-09 07:25:38,390][23097] Decorrelating experience for 192 frames... [2023-03-09 07:25:38,415][23636] Decorrelating experience for 160 frames... [2023-03-09 07:25:38,442][23817] Decorrelating experience for 64 frames... [2023-03-09 07:25:38,463][23525] Decorrelating experience for 192 frames... [2023-03-09 07:25:38,463][23178] Decorrelating experience for 32 frames... [2023-03-09 07:25:38,532][23196] Decorrelating experience for 96 frames... [2023-03-09 07:25:38,548][23244] Decorrelating experience for 160 frames... [2023-03-09 07:25:38,553][23239] Decorrelating experience for 64 frames... [2023-03-09 07:25:38,556][23485] Decorrelating experience for 64 frames... [2023-03-09 07:25:38,568][23199] Decorrelating experience for 192 frames... [2023-03-09 07:25:38,579][23214] Decorrelating experience for 64 frames... [2023-03-09 07:25:38,589][23224] Decorrelating experience for 160 frames... [2023-03-09 07:25:38,614][23201] Decorrelating experience for 0 frames... [2023-03-09 07:25:38,640][23181] Decorrelating experience for 32 frames... [2023-03-09 07:25:38,670][23223] Decorrelating experience for 224 frames... [2023-03-09 07:25:38,703][23209] Decorrelating experience for 64 frames... [2023-03-09 07:25:38,722][23089] Decorrelating experience for 160 frames... [2023-03-09 07:25:38,733][23174] Decorrelating experience for 64 frames... [2023-03-09 07:25:38,750][24352] Decorrelating experience for 96 frames... [2023-03-09 07:25:38,774][23248] Decorrelating experience for 96 frames... [2023-03-09 07:25:38,777][23188] Decorrelating experience for 224 frames... [2023-03-09 07:25:38,791][23176] Decorrelating experience for 192 frames... [2023-03-09 07:25:38,796][23087] Decorrelating experience for 64 frames... [2023-03-09 07:25:38,822][23240] Decorrelating experience for 96 frames... [2023-03-09 07:25:38,843][23246] Decorrelating experience for 128 frames... [2023-03-09 07:25:38,885][23103] Decorrelating experience for 64 frames... [2023-03-09 07:25:38,895][23207] Decorrelating experience for 224 frames... [2023-03-09 07:25:38,909][33428] Decorrelating experience for 192 frames... [2023-03-09 07:25:38,925][23181] Decorrelating experience for 64 frames... [2023-03-09 07:25:38,958][24352] Decorrelating experience for 128 frames... [2023-03-09 07:25:38,969][23637] Decorrelating experience for 0 frames... [2023-03-09 07:25:38,979][23236] Decorrelating experience for 128 frames... [2023-03-09 07:25:38,993][23211] Decorrelating experience for 32 frames... [2023-03-09 07:25:38,999][23218] Decorrelating experience for 160 frames... [2023-03-09 07:25:39,022][23866] Decorrelating experience for 64 frames... [2023-03-09 07:25:39,058][23249] Decorrelating experience for 96 frames... [2023-03-09 07:25:39,059][22664] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 0.0. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) [2023-03-09 07:25:39,067][24089] Decorrelating experience for 32 frames... [2023-03-09 07:25:39,090][23213] Decorrelating experience for 160 frames... [2023-03-09 07:25:39,101][23823] Decorrelating experience for 0 frames... [2023-03-09 07:25:39,131][24157] Decorrelating experience for 224 frames... [2023-03-09 07:25:39,187][23817] Decorrelating experience for 96 frames... [2023-03-09 07:25:39,189][23179] Decorrelating experience for 160 frames... [2023-03-09 07:25:39,190][23961] Decorrelating experience for 64 frames... [2023-03-09 07:25:39,192][23200] Decorrelating experience for 128 frames... [2023-03-09 07:25:39,235][33428] Decorrelating experience for 224 frames... [2023-03-09 07:25:39,236][23093] Decorrelating experience for 128 frames... [2023-03-09 07:25:39,244][23225] Decorrelating experience for 32 frames... [2023-03-09 07:25:39,269][23249] Decorrelating experience for 128 frames... [2023-03-09 07:25:39,282][23207] Decorrelating experience for 256 frames... [2023-03-09 07:25:39,331][23181] Decorrelating experience for 96 frames... [2023-03-09 07:25:39,387][23183] Decorrelating experience for 128 frames... [2023-03-09 07:25:39,391][24434] Decorrelating experience for 192 frames... [2023-03-09 07:25:39,393][23089] Decorrelating experience for 192 frames... [2023-03-09 07:25:39,393][23866] Decorrelating experience for 96 frames... [2023-03-09 07:25:39,425][23823] Decorrelating experience for 32 frames... [2023-03-09 07:25:39,436][23196] Decorrelating experience for 128 frames... [2023-03-09 07:25:39,437][23213] Decorrelating experience for 192 frames... [2023-03-09 07:25:39,445][23216] Decorrelating experience for 192 frames... [2023-03-09 07:25:39,484][23229] Decorrelating experience for 96 frames... [2023-03-09 07:25:39,517][23179] Decorrelating experience for 192 frames... [2023-03-09 07:25:39,583][23225] Decorrelating experience for 64 frames... [2023-03-09 07:25:39,588][23210] Decorrelating experience for 64 frames... [2023-03-09 07:25:39,591][24118] Decorrelating experience for 160 frames... [2023-03-09 07:25:39,592][23636] Decorrelating experience for 192 frames... [2023-03-09 07:25:39,622][23200] Decorrelating experience for 160 frames... [2023-03-09 07:25:39,637][23087] Decorrelating experience for 96 frames... [2023-03-09 07:25:39,640][23188] Decorrelating experience for 256 frames... [2023-03-09 07:25:39,642][23235] Decorrelating experience for 96 frames... [2023-03-09 07:25:39,686][23237] Decorrelating experience for 96 frames... [2023-03-09 07:25:39,691][23201] Decorrelating experience for 32 frames... [2023-03-09 07:25:39,761][23823] Decorrelating experience for 64 frames... [2023-03-09 07:25:39,763][23179] Decorrelating experience for 224 frames... [2023-03-09 07:25:39,785][23210] Decorrelating experience for 96 frames... [2023-03-09 07:25:39,793][24434] Decorrelating experience for 224 frames... [2023-03-09 07:25:39,796][23180] Decorrelating experience for 160 frames... [2023-03-09 07:25:39,837][23213] Decorrelating experience for 224 frames... [2023-03-09 07:25:39,838][23638] Decorrelating experience for 160 frames... [2023-03-09 07:25:39,840][23176] Decorrelating experience for 224 frames... [2023-03-09 07:25:39,872][24118] Decorrelating experience for 192 frames... [2023-03-09 07:25:39,901][23200] Decorrelating experience for 192 frames... [2023-03-09 07:25:39,936][23218] Decorrelating experience for 192 frames... [2023-03-09 07:25:39,975][23182] Decorrelating experience for 96 frames... [2023-03-09 07:25:39,987][23636] Decorrelating experience for 224 frames... [2023-03-09 07:25:39,992][23187] Decorrelating experience for 96 frames... [2023-03-09 07:25:40,027][23189] Decorrelating experience for 0 frames... [2023-03-09 07:25:40,030][23180] Decorrelating experience for 192 frames... [2023-03-09 07:25:40,032][23201] Decorrelating experience for 64 frames... [2023-03-09 07:25:40,038][23171] Decorrelating experience for 128 frames... [2023-03-09 07:25:40,068][23179] Decorrelating experience for 256 frames... [2023-03-09 07:25:40,108][23196] Decorrelating experience for 160 frames... [2023-03-09 07:25:40,112][24118] Decorrelating experience for 224 frames... [2023-03-09 07:25:40,151][23235] Decorrelating experience for 128 frames... [2023-03-09 07:25:40,191][23118] Decorrelating experience for 160 frames... [2023-03-09 07:25:40,193][23222] Decorrelating experience for 96 frames... [2023-03-09 07:25:40,205][23866] Decorrelating experience for 128 frames... [2023-03-09 07:25:40,210][23183] Decorrelating experience for 160 frames... [2023-03-09 07:25:40,225][24434] Decorrelating experience for 256 frames... [2023-03-09 07:25:40,232][23201] Decorrelating experience for 96 frames... [2023-03-09 07:25:40,244][23247] Decorrelating experience for 160 frames... [2023-03-09 07:25:40,315][23240] Decorrelating experience for 128 frames... [2023-03-09 07:25:40,320][23638] Decorrelating experience for 192 frames... [2023-03-09 07:25:40,332][23225] Decorrelating experience for 96 frames... [2023-03-09 07:25:40,394][24818] Decorrelating experience for 0 frames... [2023-03-09 07:25:40,395][23095] Decorrelating experience for 160 frames... [2023-03-09 07:25:40,406][24025] Decorrelating experience for 128 frames... [2023-03-09 07:25:40,409][23171] Decorrelating experience for 160 frames... [2023-03-09 07:25:40,423][23118] Decorrelating experience for 192 frames... [2023-03-09 07:25:40,437][32460] Decorrelating experience for 96 frames... [2023-03-09 07:25:40,439][23196] Decorrelating experience for 192 frames... [2023-03-09 07:25:40,495][23209] Decorrelating experience for 96 frames... [2023-03-09 07:25:40,508][24089] Decorrelating experience for 64 frames... [2023-03-09 07:25:40,522][23213] Decorrelating experience for 256 frames... [2023-03-09 07:25:40,600][23169] Decorrelating experience for 64 frames... [2023-03-09 07:25:40,603][24793] Decorrelating experience for 32 frames... [2023-03-09 07:25:40,604][24434] Decorrelating experience for 288 frames... [2023-03-09 07:25:40,604][23096] Decorrelating experience for 32 frames... [2023-03-09 07:25:40,605][23210] Decorrelating experience for 128 frames... [2023-03-09 07:25:40,645][23231] Decorrelating experience for 64 frames... [2023-03-09 07:25:40,645][23223] Decorrelating experience for 256 frames... [2023-03-09 07:25:40,665][23118] Decorrelating experience for 224 frames... [2023-03-09 07:25:40,691][23211] Decorrelating experience for 64 frames... [2023-03-09 07:25:40,703][23209] Decorrelating experience for 128 frames... [2023-03-09 07:25:40,780][24025] Decorrelating experience for 160 frames... [2023-03-09 07:25:40,782][23866] Decorrelating experience for 160 frames... [2023-03-09 07:25:40,786][23218] Decorrelating experience for 224 frames... [2023-03-09 07:25:40,793][23171] Decorrelating experience for 192 frames... [2023-03-09 07:25:40,812][23095] Decorrelating experience for 192 frames... [2023-03-09 07:25:40,840][23096] Decorrelating experience for 64 frames... [2023-03-09 07:25:40,849][23246] Decorrelating experience for 160 frames... [2023-03-09 07:25:40,850][23195] Decorrelating experience for 160 frames... [2023-03-09 07:25:40,896][23225] Decorrelating experience for 128 frames... [2023-03-09 07:25:40,932][23235] Decorrelating experience for 160 frames... [2023-03-09 07:25:40,958][23222] Decorrelating experience for 128 frames... [2023-03-09 07:25:40,959][23219] Decorrelating experience for 64 frames... [2023-03-09 07:25:40,971][23118] Decorrelating experience for 256 frames... [2023-03-09 07:25:40,992][23231] Decorrelating experience for 96 frames... [2023-03-09 07:25:40,994][23657] Decorrelating experience for 0 frames... [2023-03-09 07:25:41,037][23096] Decorrelating experience for 96 frames... [2023-03-09 07:25:41,047][23232] Decorrelating experience for 96 frames... [2023-03-09 07:25:41,049][23185] Decorrelating experience for 96 frames... [2023-03-09 07:25:41,104][23201] Decorrelating experience for 128 frames... [2023-03-09 07:25:41,131][23195] Decorrelating experience for 192 frames... [2023-03-09 07:25:41,147][23193] Decorrelating experience for 192 frames... [2023-03-09 07:25:41,149][24157] Decorrelating experience for 256 frames... [2023-03-09 07:25:41,187][23171] Decorrelating experience for 224 frames... [2023-03-09 07:25:41,206][23638] Decorrelating experience for 224 frames... [2023-03-09 07:25:41,211][23236] Decorrelating experience for 160 frames... [2023-03-09 07:25:41,241][23118] Decorrelating experience for 288 frames... [2023-03-09 07:25:41,278][23180] Decorrelating experience for 224 frames... [2023-03-09 07:25:41,297][23246] Decorrelating experience for 192 frames... [2023-03-09 07:25:41,302][23243] Decorrelating experience for 64 frames... [2023-03-09 07:25:41,324][24118] Decorrelating experience for 256 frames... [2023-03-09 07:25:41,330][23210] Decorrelating experience for 160 frames... [2023-03-09 07:25:41,363][23223] Decorrelating experience for 288 frames... [2023-03-09 07:25:41,380][23247] Decorrelating experience for 192 frames... [2023-03-09 07:25:41,409][23182] Decorrelating experience for 128 frames... [2023-03-09 07:25:41,467][23194] Decorrelating experience for 96 frames... [2023-03-09 07:25:41,485][23222] Decorrelating experience for 160 frames... [2023-03-09 07:25:41,500][23637] Decorrelating experience for 32 frames... [2023-03-09 07:25:41,505][23635] Decorrelating experience for 64 frames... [2023-03-09 07:25:41,516][23638] Decorrelating experience for 256 frames... [2023-03-09 07:25:41,521][23219] Decorrelating experience for 96 frames... [2023-03-09 07:25:41,532][23180] Decorrelating experience for 256 frames... [2023-03-09 07:25:41,551][23218] Decorrelating experience for 256 frames... [2023-03-09 07:25:41,554][23170] Decorrelating experience for 256 frames... [2023-03-09 07:25:41,599][23204] Decorrelating experience for 96 frames... [2023-03-09 07:25:41,647][23096] Decorrelating experience for 128 frames... [2023-03-09 07:25:41,662][23228] Decorrelating experience for 64 frames... [2023-03-09 07:25:41,675][23195] Decorrelating experience for 224 frames... [2023-03-09 07:25:41,695][23213] Decorrelating experience for 288 frames... [2023-03-09 07:25:41,701][23212] Decorrelating experience for 96 frames... [2023-03-09 07:25:41,717][23210] Decorrelating experience for 192 frames... [2023-03-09 07:25:41,727][23209] Decorrelating experience for 160 frames... [2023-03-09 07:25:41,741][24793] Decorrelating experience for 64 frames... [2023-03-09 07:25:41,745][24118] Decorrelating experience for 288 frames... [2023-03-09 07:25:41,803][23635] Decorrelating experience for 96 frames... [2023-03-09 07:25:41,820][23118] Decorrelating experience for 320 frames... [2023-03-09 07:25:41,844][24434] Decorrelating experience for 320 frames... [2023-03-09 07:25:41,850][23224] Decorrelating experience for 192 frames... [2023-03-09 07:25:41,866][24157] Decorrelating experience for 288 frames... [2023-03-09 07:25:41,886][23637] Decorrelating experience for 64 frames... [2023-03-09 07:25:41,900][23214] Decorrelating experience for 96 frames... [2023-03-09 07:25:41,918][24025] Decorrelating experience for 192 frames... [2023-03-09 07:25:41,936][23095] Decorrelating experience for 224 frames... [2023-03-09 07:25:41,980][24793] Decorrelating experience for 96 frames... [2023-03-09 07:25:42,001][23180] Decorrelating experience for 288 frames... [2023-03-09 07:25:42,020][23188] Decorrelating experience for 288 frames... [2023-03-09 07:25:42,050][23193] Decorrelating experience for 224 frames... [2023-03-09 07:25:42,051][23171] Decorrelating experience for 256 frames... [2023-03-09 07:25:42,056][23218] Decorrelating experience for 288 frames... [2023-03-09 07:25:42,061][23230] Decorrelating experience for 32 frames... [2023-03-09 07:25:42,073][23657] Decorrelating experience for 32 frames... [2023-03-09 07:25:42,103][24352] Decorrelating experience for 160 frames... [2023-03-09 07:25:42,108][23209] Decorrelating experience for 192 frames... [2023-03-09 07:25:42,177][23247] Decorrelating experience for 224 frames... [2023-03-09 07:25:42,196][23224] Decorrelating experience for 224 frames... [2023-03-09 07:25:42,198][23223] Decorrelating experience for 320 frames... [2023-03-09 07:25:42,233][23195] Decorrelating experience for 256 frames... [2023-03-09 07:25:42,246][23095] Decorrelating experience for 256 frames... [2023-03-09 07:25:42,249][23230] Decorrelating experience for 64 frames... [2023-03-09 07:25:42,255][23199] Decorrelating experience for 224 frames... [2023-03-09 07:25:42,282][24793] Decorrelating experience for 128 frames... [2023-03-09 07:25:42,294][24157] Decorrelating experience for 320 frames... [2023-03-09 07:25:42,297][23194] Decorrelating experience for 128 frames... [2023-03-09 07:25:42,353][23241] Decorrelating experience for 96 frames... [2023-03-09 07:25:42,377][24118] Decorrelating experience for 320 frames... [2023-03-09 07:25:42,409][23193] Decorrelating experience for 256 frames... [2023-03-09 07:25:42,429][24818] Decorrelating experience for 32 frames... [2023-03-09 07:25:42,439][23087] Decorrelating experience for 128 frames... [2023-03-09 07:25:42,455][23209] Decorrelating experience for 224 frames... [2023-03-09 07:25:42,458][23224] Decorrelating experience for 256 frames... [2023-03-09 07:25:42,459][23226] Decorrelating experience for 96 frames... [2023-03-09 07:25:42,473][23866] Decorrelating experience for 192 frames... [2023-03-09 07:25:42,496][23230] Decorrelating experience for 96 frames... [2023-03-09 07:25:42,530][23201] Decorrelating experience for 160 frames... [2023-03-09 07:25:42,551][23236] Decorrelating experience for 192 frames... [2023-03-09 07:25:42,584][23247] Decorrelating experience for 256 frames... [2023-03-09 07:25:42,605][23183] Decorrelating experience for 192 frames... [2023-03-09 07:25:42,613][23237] Decorrelating experience for 128 frames... [2023-03-09 07:25:42,650][23188] Decorrelating experience for 320 frames... [2023-03-09 07:25:42,663][23192] Decorrelating experience for 96 frames... [2023-03-09 07:25:42,663][23103] Decorrelating experience for 96 frames... [2023-03-09 07:25:42,663][23227] Decorrelating experience for 0 frames... [2023-03-09 07:25:42,709][23099] Decorrelating experience for 128 frames... [2023-03-09 07:25:42,757][24666] Decorrelating experience for 0 frames... [2023-03-09 07:25:42,766][23241] Decorrelating experience for 128 frames... [2023-03-09 07:25:42,770][23638] Decorrelating experience for 288 frames... [2023-03-09 07:25:42,790][24352] Decorrelating experience for 192 frames... [2023-03-09 07:25:42,823][23224] Decorrelating experience for 288 frames... [2023-03-09 07:25:42,849][23236] Decorrelating experience for 224 frames... [2023-03-09 07:25:42,860][23175] Decorrelating experience for 32 frames... [2023-03-09 07:25:42,861][23098] Decorrelating experience for 32 frames... [2023-03-09 07:25:42,887][23182] Decorrelating experience for 160 frames... [2023-03-09 07:25:42,896][23246] Decorrelating experience for 224 frames... [2023-03-09 07:25:42,960][23230] Decorrelating experience for 128 frames... [2023-03-09 07:25:42,961][24158] Decorrelating experience for 0 frames... [2023-03-09 07:25:42,967][23223] Decorrelating experience for 352 frames... [2023-03-09 07:25:42,970][23635] Decorrelating experience for 128 frames... [2023-03-09 07:25:42,996][23196] Decorrelating experience for 224 frames... [2023-03-09 07:25:43,023][23103] Decorrelating experience for 128 frames... [2023-03-09 07:25:43,049][23188] Decorrelating experience for 352 frames... [2023-03-09 07:25:43,049][23175] Decorrelating experience for 64 frames... [2023-03-09 07:25:43,062][23214] Decorrelating experience for 128 frames... [2023-03-09 07:25:43,070][23178] Decorrelating experience for 64 frames... [2023-03-09 07:25:43,135][24352] Decorrelating experience for 224 frames... [2023-03-09 07:25:43,151][23195] Decorrelating experience for 288 frames... [2023-03-09 07:25:43,160][23177] Decorrelating experience for 32 frames... [2023-03-09 07:25:43,172][24539] Decorrelating experience for 0 frames... [2023-03-09 07:25:43,182][23099] Decorrelating experience for 160 frames... [2023-03-09 07:25:43,208][23525] Decorrelating experience for 224 frames... [2023-03-09 07:25:43,235][22664] Heartbeat connected on Batcher_0 [2023-03-09 07:25:43,237][22664] Heartbeat connected on LearnerWorker_p0 [2023-03-09 07:25:43,240][23638] Decorrelating experience for 320 frames... [2023-03-09 07:25:43,265][23229] Decorrelating experience for 128 frames... [2023-03-09 07:25:43,266][22664] Heartbeat connected on InferenceWorker_p0-w0 [2023-03-09 07:25:43,285][23194] Decorrelating experience for 160 frames... [2023-03-09 07:25:43,309][23242] Decorrelating experience for 32 frames... [2023-03-09 07:25:43,312][23219] Decorrelating experience for 128 frames... [2023-03-09 07:25:43,331][23222] Decorrelating experience for 192 frames... [2023-03-09 07:25:43,347][23175] Decorrelating experience for 96 frames... [2023-03-09 07:25:43,360][23174] Decorrelating experience for 96 frames... [2023-03-09 07:25:43,372][23223] Decorrelating experience for 384 frames... [2023-03-09 07:25:43,387][23225] Decorrelating experience for 160 frames... [2023-03-09 07:25:43,424][23095] Decorrelating experience for 288 frames... [2023-03-09 07:25:43,440][23227] Decorrelating experience for 32 frames... [2023-03-09 07:25:43,460][23190] Decorrelating experience for 32 frames... [2023-03-09 07:25:43,490][24666] Decorrelating experience for 32 frames... [2023-03-09 07:25:43,491][23237] Decorrelating experience for 160 frames... [2023-03-09 07:25:43,505][23179] Decorrelating experience for 288 frames... [2023-03-09 07:25:43,526][23096] Decorrelating experience for 160 frames... [2023-03-09 07:25:43,544][23103] Decorrelating experience for 160 frames... [2023-03-09 07:25:43,564][23173] Decorrelating experience for 96 frames... [2023-03-09 07:25:43,584][23088] Decorrelating experience for 128 frames... [2023-03-09 07:25:43,600][24539] Decorrelating experience for 32 frames... [2023-03-09 07:25:43,624][23441] Decorrelating experience for 32 frames... [2023-03-09 07:25:43,667][23216] Decorrelating experience for 224 frames... [2023-03-09 07:25:43,672][23174] Decorrelating experience for 128 frames... [2023-03-09 07:25:43,687][24158] Decorrelating experience for 32 frames... [2023-03-09 07:25:43,690][23244] Decorrelating experience for 192 frames... [2023-03-09 07:25:43,708][23224] Decorrelating experience for 320 frames... [2023-03-09 07:25:43,724][23237] Decorrelating experience for 192 frames... [2023-03-09 07:25:43,746][23190] Decorrelating experience for 64 frames... [2023-03-09 07:25:43,777][23866] Decorrelating experience for 224 frames... [2023-03-09 07:25:43,778][23202] Decorrelating experience for 160 frames... [2023-03-09 07:25:43,843][23095] Decorrelating experience for 320 frames... [2023-03-09 07:25:43,851][23177] Decorrelating experience for 64 frames... [2023-03-09 07:25:43,864][23865] Decorrelating experience for 192 frames... [2023-03-09 07:25:43,901][23222] Decorrelating experience for 224 frames... [2023-03-09 07:25:43,907][24434] Decorrelating experience for 352 frames... [2023-03-09 07:25:43,918][23657] Decorrelating experience for 64 frames... [2023-03-09 07:25:43,939][23182] Decorrelating experience for 192 frames... [2023-03-09 07:25:43,951][23235] Decorrelating experience for 192 frames... [2023-03-09 07:25:43,961][23096] Decorrelating experience for 192 frames... [2023-03-09 07:25:43,970][32460] Decorrelating experience for 128 frames... [2023-03-09 07:25:44,023][23237] Decorrelating experience for 224 frames... [2023-03-09 07:25:44,027][23662] Decorrelating experience for 128 frames... [2023-03-09 07:25:44,058][23196] Decorrelating experience for 256 frames... [2023-03-09 07:25:44,059][22664] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 0.0. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) [2023-03-09 07:25:44,091][23179] Decorrelating experience for 320 frames... [2023-03-09 07:25:44,103][23098] Decorrelating experience for 64 frames... [2023-03-09 07:25:44,119][23087] Decorrelating experience for 160 frames... [2023-03-09 07:25:44,128][23249] Decorrelating experience for 160 frames... [2023-03-09 07:25:44,137][23866] Decorrelating experience for 256 frames... [2023-03-09 07:25:44,139][24539] Decorrelating experience for 64 frames... [2023-03-09 07:25:44,169][23231] Decorrelating experience for 128 frames... [2023-03-09 07:25:44,213][23188] Decorrelating experience for 384 frames... [2023-03-09 07:25:44,213][23213] Decorrelating experience for 320 frames... [2023-03-09 07:25:44,278][23210] Decorrelating experience for 224 frames... [2023-03-09 07:25:44,290][24434] Decorrelating experience for 384 frames... [2023-03-09 07:25:44,295][23229] Decorrelating experience for 160 frames... [2023-03-09 07:25:44,301][23662] Decorrelating experience for 160 frames... [2023-03-09 07:25:44,312][23865] Decorrelating experience for 224 frames... [2023-03-09 07:25:44,320][23221] Decorrelating experience for 128 frames... [2023-03-09 07:25:44,354][23096] Decorrelating experience for 224 frames... [2023-03-09 07:25:44,387][23182] Decorrelating experience for 224 frames... [2023-03-09 07:25:44,387][23227] Decorrelating experience for 64 frames... [2023-03-09 07:25:44,430][23189] Decorrelating experience for 32 frames... [2023-03-09 07:25:44,471][23243] Decorrelating experience for 96 frames... [2023-03-09 07:25:44,472][23088] Decorrelating experience for 160 frames... [2023-03-09 07:25:44,476][23218] Decorrelating experience for 320 frames... [2023-03-09 07:25:44,499][24157] Decorrelating experience for 352 frames... [2023-03-09 07:25:44,510][23866] Decorrelating experience for 288 frames... [2023-03-09 07:25:44,562][24352] Decorrelating experience for 256 frames... [2023-03-09 07:25:44,565][23211] Decorrelating experience for 96 frames... [2023-03-09 07:25:44,567][23247] Decorrelating experience for 288 frames... [2023-03-09 07:25:44,596][23185] Decorrelating experience for 128 frames... [2023-03-09 07:25:44,620][23865] Decorrelating experience for 256 frames... [2023-03-09 07:25:44,661][23093] Decorrelating experience for 160 frames... [2023-03-09 07:25:44,670][23202] Decorrelating experience for 192 frames... [2023-03-09 07:25:44,674][23099] Decorrelating experience for 192 frames... [2023-03-09 07:25:44,721][23200] Decorrelating experience for 224 frames... [2023-03-09 07:25:44,742][23210] Decorrelating experience for 256 frames... [2023-03-09 07:25:44,744][23214] Decorrelating experience for 160 frames... [2023-03-09 07:25:44,747][23190] Decorrelating experience for 96 frames... [2023-03-09 07:25:44,761][23236] Decorrelating experience for 256 frames... [2023-03-09 07:25:44,795][23230] Decorrelating experience for 160 frames... [2023-03-09 07:25:44,837][23176] Decorrelating experience for 256 frames... [2023-03-09 07:25:44,859][23247] Decorrelating experience for 320 frames... [2023-03-09 07:25:44,866][23088] Decorrelating experience for 192 frames... [2023-03-09 07:25:44,867][23204] Decorrelating experience for 128 frames... [2023-03-09 07:25:44,895][23180] Decorrelating experience for 320 frames... [2023-03-09 07:25:44,916][23249] Decorrelating experience for 192 frames... [2023-03-09 07:25:44,922][23657] Decorrelating experience for 96 frames... [2023-03-09 07:25:44,960][23227] Decorrelating experience for 96 frames... [2023-03-09 07:25:44,973][23248] Decorrelating experience for 128 frames... [2023-03-09 07:25:44,977][23206] Decorrelating experience for 64 frames... [2023-03-09 07:25:45,037][23226] Decorrelating experience for 128 frames... [2023-03-09 07:25:45,038][24089] Decorrelating experience for 96 frames... [2023-03-09 07:25:45,071][23210] Decorrelating experience for 288 frames... [2023-03-09 07:25:45,071][23175] Decorrelating experience for 128 frames... [2023-03-09 07:25:45,081][23093] Decorrelating experience for 192 frames... [2023-03-09 07:25:45,096][32460] Decorrelating experience for 160 frames... [2023-03-09 07:25:45,104][23225] Decorrelating experience for 192 frames... [2023-03-09 07:25:45,139][23865] Decorrelating experience for 288 frames... [2023-03-09 07:25:45,150][23213] Decorrelating experience for 352 frames... [2023-03-09 07:25:45,173][23485] Decorrelating experience for 96 frames... [2023-03-09 07:25:45,211][23249] Decorrelating experience for 224 frames... [2023-03-09 07:25:45,219][23235] Decorrelating experience for 224 frames... [2023-03-09 07:25:45,257][23637] Decorrelating experience for 96 frames... [2023-03-09 07:25:45,258][23226] Decorrelating experience for 160 frames... [2023-03-09 07:25:45,271][23218] Decorrelating experience for 352 frames... [2023-03-09 07:25:45,282][23230] Decorrelating experience for 192 frames... [2023-03-09 07:25:45,283][23214] Decorrelating experience for 192 frames... [2023-03-09 07:25:45,321][24434] Decorrelating experience for 416 frames... [2023-03-09 07:25:45,333][23118] Decorrelating experience for 352 frames... [2023-03-09 07:25:45,348][24089] Decorrelating experience for 128 frames... [2023-03-09 07:25:45,386][23194] Decorrelating experience for 192 frames... [2023-03-09 07:25:45,395][23231] Decorrelating experience for 160 frames... [2023-03-09 07:25:45,433][23240] Decorrelating experience for 160 frames... [2023-03-09 07:25:45,455][23195] Decorrelating experience for 320 frames... [2023-03-09 07:25:45,461][23225] Decorrelating experience for 224 frames... [2023-03-09 07:25:45,462][24157] Decorrelating experience for 384 frames... [2023-03-09 07:25:45,465][23173] Decorrelating experience for 128 frames... [2023-03-09 07:25:45,506][23241] Decorrelating experience for 160 frames... [2023-03-09 07:25:45,508][23190] Decorrelating experience for 128 frames... [2023-03-09 07:25:45,529][24121] Decorrelating experience for 96 frames... [2023-03-09 07:25:45,572][23637] Decorrelating experience for 128 frames... [2023-03-09 07:25:45,574][24793] Decorrelating experience for 160 frames... [2023-03-09 07:25:45,634][23214] Decorrelating experience for 224 frames... [2023-03-09 07:25:45,635][23194] Decorrelating experience for 224 frames... [2023-03-09 07:25:45,640][23199] Decorrelating experience for 256 frames... [2023-03-09 07:25:45,644][23662] Decorrelating experience for 192 frames... [2023-03-09 07:25:45,645][23181] Decorrelating experience for 128 frames... [2023-03-09 07:25:45,689][23186] Decorrelating experience for 160 frames... [2023-03-09 07:25:45,705][23180] Decorrelating experience for 352 frames... [2023-03-09 07:25:45,733][23961] Decorrelating experience for 96 frames... [2023-03-09 07:25:45,744][23193] Decorrelating experience for 288 frames... [2023-03-09 07:25:45,773][23634] Decorrelating experience for 128 frames... [2023-03-09 07:25:45,809][23177] Decorrelating experience for 96 frames... [2023-03-09 07:25:45,821][23240] Decorrelating experience for 192 frames... [2023-03-09 07:25:45,828][23236] Decorrelating experience for 288 frames... [2023-03-09 07:25:45,830][24157] Decorrelating experience for 416 frames... [2023-03-09 07:25:45,869][23225] Decorrelating experience for 256 frames... [2023-03-09 07:25:45,894][23175] Decorrelating experience for 160 frames... [2023-03-09 07:25:45,919][23865] Decorrelating experience for 320 frames... [2023-03-09 07:25:45,937][23088] Decorrelating experience for 224 frames... [2023-03-09 07:25:45,938][23187] Decorrelating experience for 128 frames... [2023-03-09 07:25:45,984][23215] Decorrelating experience for 160 frames... [2023-03-09 07:25:45,993][23961] Decorrelating experience for 128 frames... [2023-03-09 07:25:46,010][24793] Decorrelating experience for 192 frames... [2023-03-09 07:25:46,012][23213] Decorrelating experience for 384 frames... [2023-03-09 07:25:46,014][23098] Decorrelating experience for 96 frames... [2023-03-09 07:25:46,041][23214] Decorrelating experience for 256 frames... [2023-03-09 07:25:46,074][24089] Decorrelating experience for 160 frames... [2023-03-09 07:25:46,100][23638] Decorrelating experience for 352 frames... [2023-03-09 07:25:46,138][23095] Decorrelating experience for 352 frames... [2023-03-09 07:25:46,147][24158] Decorrelating experience for 64 frames... [2023-03-09 07:25:46,175][23202] Decorrelating experience for 224 frames... [2023-03-09 07:25:46,177][23186] Decorrelating experience for 192 frames... [2023-03-09 07:25:46,189][23094] Decorrelating experience for 128 frames... [2023-03-09 07:25:46,192][23188] Decorrelating experience for 416 frames... [2023-03-09 07:25:46,192][23229] Decorrelating experience for 192 frames... [2023-03-09 07:25:46,235][23200] Decorrelating experience for 256 frames... [2023-03-09 07:25:46,261][23087] Decorrelating experience for 192 frames... [2023-03-09 07:25:46,274][23098] Decorrelating experience for 128 frames... [2023-03-09 07:25:46,325][23225] Decorrelating experience for 288 frames... [2023-03-09 07:25:46,339][23212] Decorrelating experience for 128 frames... [2023-03-09 07:25:46,352][23195] Decorrelating experience for 352 frames... [2023-03-09 07:25:46,361][23180] Decorrelating experience for 384 frames... [2023-03-09 07:25:46,371][23240] Decorrelating experience for 224 frames... [2023-03-09 07:25:46,372][23635] Decorrelating experience for 160 frames... [2023-03-09 07:25:46,380][23203] Decorrelating experience for 160 frames... [2023-03-09 07:25:46,408][23236] Decorrelating experience for 320 frames... [2023-03-09 07:25:46,447][23817] Decorrelating experience for 128 frames... [2023-03-09 07:25:46,461][23214] Decorrelating experience for 288 frames... [2023-03-09 07:25:46,522][23187] Decorrelating experience for 160 frames... [2023-03-09 07:25:46,533][23250] Decorrelating experience for 128 frames... [2023-03-09 07:25:46,534][23233] Decorrelating experience for 64 frames... [2023-03-09 07:25:46,549][23088] Decorrelating experience for 256 frames... [2023-03-09 07:25:46,549][23241] Decorrelating experience for 192 frames... [2023-03-09 07:25:46,553][24434] Decorrelating experience for 448 frames... [2023-03-09 07:25:46,586][23091] Decorrelating experience for 128 frames... [2023-03-09 07:25:46,591][24025] Decorrelating experience for 224 frames... [2023-03-09 07:25:46,633][23206] Decorrelating experience for 96 frames... [2023-03-09 07:25:46,697][23098] Decorrelating experience for 160 frames... [2023-03-09 07:25:46,699][23210] Decorrelating experience for 320 frames... [2023-03-09 07:25:46,712][24089] Decorrelating experience for 192 frames... [2023-03-09 07:25:46,737][23193] Decorrelating experience for 320 frames... [2023-03-09 07:25:46,738][23222] Decorrelating experience for 256 frames... [2023-03-09 07:25:46,738][23180] Decorrelating experience for 416 frames... [2023-03-09 07:25:46,739][23961] Decorrelating experience for 160 frames... [2023-03-09 07:25:46,762][23203] Decorrelating experience for 192 frames... [2023-03-09 07:25:46,793][23173] Decorrelating experience for 160 frames... [2023-03-09 07:25:46,847][24793] Decorrelating experience for 224 frames... [2023-03-09 07:25:46,888][23232] Decorrelating experience for 128 frames... [2023-03-09 07:25:46,894][23202] Decorrelating experience for 256 frames... [2023-03-09 07:25:46,920][24157] Decorrelating experience for 448 frames... [2023-03-09 07:25:46,920][23199] Decorrelating experience for 288 frames... [2023-03-09 07:25:46,933][23098] Decorrelating experience for 192 frames... [2023-03-09 07:25:46,934][23186] Decorrelating experience for 224 frames... [2023-03-09 07:25:46,938][23230] Decorrelating experience for 224 frames... [2023-03-09 07:25:46,954][23218] Decorrelating experience for 384 frames... [2023-03-09 07:25:46,993][23210] Decorrelating experience for 352 frames... [2023-03-09 07:25:47,034][23176] Decorrelating experience for 288 frames... [2023-03-09 07:25:47,068][23242] Decorrelating experience for 64 frames... [2023-03-09 07:25:47,074][23817] Decorrelating experience for 160 frames... [2023-03-09 07:25:47,104][23205] Decorrelating experience for 64 frames... [2023-03-09 07:25:47,104][23662] Decorrelating experience for 224 frames... [2023-03-09 07:25:47,110][23087] Decorrelating experience for 224 frames... [2023-03-09 07:25:47,116][23180] Decorrelating experience for 448 frames... [2023-03-09 07:25:47,125][23173] Decorrelating experience for 192 frames... [2023-03-09 07:25:47,135][23093] Decorrelating experience for 224 frames... [2023-03-09 07:25:47,166][23865] Decorrelating experience for 352 frames... [2023-03-09 07:25:47,214][23091] Decorrelating experience for 160 frames... [2023-03-09 07:25:47,246][23230] Decorrelating experience for 256 frames... [2023-03-09 07:25:47,250][23219] Decorrelating experience for 160 frames... [2023-03-09 07:25:47,280][23098] Decorrelating experience for 224 frames... [2023-03-09 07:25:47,290][23235] Decorrelating experience for 256 frames... [2023-03-09 07:25:47,295][33428] Decorrelating experience for 256 frames... [2023-03-09 07:25:47,296][23190] Decorrelating experience for 160 frames... [2023-03-09 07:25:47,299][23171] Decorrelating experience for 288 frames... [2023-03-09 07:25:47,325][23177] Decorrelating experience for 128 frames... [2023-03-09 07:25:47,351][23525] Decorrelating experience for 256 frames... [2023-03-09 07:25:47,419][32460] Decorrelating experience for 192 frames... [2023-03-09 07:25:47,436][23233] Decorrelating experience for 96 frames... [2023-03-09 07:25:47,444][23213] Decorrelating experience for 416 frames... [2023-03-09 07:25:47,458][23178] Decorrelating experience for 96 frames... [2023-03-09 07:25:47,467][23634] Decorrelating experience for 160 frames... [2023-03-09 07:25:47,484][23193] Decorrelating experience for 352 frames... [2023-03-09 07:25:47,490][23187] Decorrelating experience for 192 frames... [2023-03-09 07:25:47,503][23205] Decorrelating experience for 96 frames... [2023-03-09 07:25:47,544][23240] Decorrelating experience for 256 frames... [2023-03-09 07:25:47,563][23190] Decorrelating experience for 192 frames... [2023-03-09 07:25:47,596][23214] Decorrelating experience for 320 frames... [2023-03-09 07:25:47,611][24158] Decorrelating experience for 96 frames... [2023-03-09 07:25:47,650][23206] Decorrelating experience for 128 frames... [2023-03-09 07:25:47,654][23091] Decorrelating experience for 192 frames... [2023-03-09 07:25:47,662][23207] Decorrelating experience for 288 frames... [2023-03-09 07:25:47,670][23087] Decorrelating experience for 256 frames... [2023-03-09 07:25:47,680][23212] Decorrelating experience for 160 frames... [2023-03-09 07:25:47,693][23093] Decorrelating experience for 256 frames... [2023-03-09 07:25:47,718][23242] Decorrelating experience for 96 frames... [2023-03-09 07:25:47,789][23219] Decorrelating experience for 192 frames... [2023-03-09 07:25:47,794][24793] Decorrelating experience for 256 frames... [2023-03-09 07:25:47,835][23181] Decorrelating experience for 160 frames... [2023-03-09 07:25:47,840][23188] Decorrelating experience for 448 frames... [2023-03-09 07:25:47,842][23099] Decorrelating experience for 224 frames... [2023-03-09 07:25:47,842][23218] Decorrelating experience for 416 frames... [2023-03-09 07:25:47,845][23186] Decorrelating experience for 256 frames... [2023-03-09 07:25:47,861][23817] Decorrelating experience for 192 frames... [2023-03-09 07:25:47,887][23214] Decorrelating experience for 352 frames... [2023-03-09 07:25:47,896][24858] Decorrelating experience for 128 frames... [2023-03-09 07:25:47,966][23222] Decorrelating experience for 288 frames... [2023-03-09 07:25:47,970][23202] Decorrelating experience for 288 frames... [2023-03-09 07:25:48,012][23236] Decorrelating experience for 352 frames... [2023-03-09 07:25:48,016][23230] Decorrelating experience for 288 frames... [2023-03-09 07:25:48,019][23823] Decorrelating experience for 96 frames... [2023-03-09 07:25:48,042][23193] Decorrelating experience for 384 frames... [2023-03-09 07:25:48,043][23175] Decorrelating experience for 192 frames... [2023-03-09 07:25:48,046][23207] Decorrelating experience for 320 frames... [2023-03-09 07:25:48,086][23219] Decorrelating experience for 224 frames... [2023-03-09 07:25:48,123][23182] Decorrelating experience for 256 frames... [2023-03-09 07:25:48,158][23637] Decorrelating experience for 160 frames... [2023-03-09 07:25:48,198][23218] Decorrelating experience for 448 frames... [2023-03-09 07:25:48,199][24352] Decorrelating experience for 288 frames... [2023-03-09 07:25:48,215][23170] Decorrelating experience for 288 frames... [2023-03-09 07:25:48,217][24434] Decorrelating experience for 480 frames... [2023-03-09 07:25:48,229][23823] Decorrelating experience for 128 frames... [2023-03-09 07:25:48,232][23188] Decorrelating experience for 480 frames... [2023-03-09 07:25:48,244][24156] Decorrelating experience for 224 frames... [2023-03-09 07:25:48,273][23093] Decorrelating experience for 288 frames... [2023-03-09 07:25:48,298][23225] Decorrelating experience for 320 frames... [2023-03-09 07:25:48,336][23192] Decorrelating experience for 128 frames... [2023-03-09 07:25:48,375][23213] Decorrelating experience for 448 frames... [2023-03-09 07:25:48,399][23230] Decorrelating experience for 320 frames... [2023-03-09 07:25:48,409][23210] Decorrelating experience for 384 frames... [2023-03-09 07:25:48,419][23185] Decorrelating experience for 160 frames... [2023-03-09 07:25:48,422][23098] Decorrelating experience for 256 frames... [2023-03-09 07:25:48,460][23097] Decorrelating experience for 224 frames... [2023-03-09 07:25:48,462][23227] Decorrelating experience for 128 frames... [2023-03-09 07:25:48,474][23206] Decorrelating experience for 160 frames... [2023-03-09 07:25:48,513][23204] Decorrelating experience for 160 frames... [2023-03-09 07:25:48,554][23233] Decorrelating experience for 128 frames... [2023-03-09 07:25:48,557][23637] Decorrelating experience for 192 frames... [2023-03-09 07:25:48,576][23173] Decorrelating experience for 224 frames... [2023-03-09 07:25:48,588][23218] Decorrelating experience for 480 frames... [2023-03-09 07:25:48,607][23222] Decorrelating experience for 320 frames... [2023-03-09 07:25:48,611][23243] Decorrelating experience for 128 frames... [2023-03-09 07:25:48,647][23219] Decorrelating experience for 256 frames... [2023-03-09 07:25:48,653][23201] Decorrelating experience for 192 frames... [2023-03-09 07:25:48,664][23623] Decorrelating experience for 160 frames... [2023-03-09 07:25:48,696][23170] Decorrelating experience for 320 frames... [2023-03-09 07:25:48,749][23634] Decorrelating experience for 192 frames... [2023-03-09 07:25:48,750][23188] Decorrelating experience for 512 frames... [2023-03-09 07:25:48,776][23233] Decorrelating experience for 160 frames... [2023-03-09 07:25:48,784][23823] Decorrelating experience for 160 frames... [2023-03-09 07:25:48,798][23193] Decorrelating experience for 416 frames... [2023-03-09 07:25:48,800][23209] Decorrelating experience for 256 frames... [2023-03-09 07:25:48,853][24156] Decorrelating experience for 256 frames... [2023-03-09 07:25:48,853][23866] Decorrelating experience for 320 frames... [2023-03-09 07:25:48,895][23206] Decorrelating experience for 192 frames... [2023-03-09 07:25:48,902][23118] Decorrelating experience for 384 frames... [2023-03-09 07:25:48,945][23623] Decorrelating experience for 192 frames... [2023-03-09 07:25:48,991][23243] Decorrelating experience for 160 frames... [2023-03-09 07:25:48,991][23218] Decorrelating experience for 512 frames... [2023-03-09 07:25:48,993][23170] Decorrelating experience for 352 frames... [2023-03-09 07:25:48,997][23179] Decorrelating experience for 352 frames... [2023-03-09 07:25:49,035][23173] Decorrelating experience for 256 frames... [2023-03-09 07:25:49,044][23634] Decorrelating experience for 224 frames... [2023-03-09 07:25:49,059][22664] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 0.0. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) [2023-03-09 07:25:49,099][23095] Decorrelating experience for 384 frames... [2023-03-09 07:25:49,125][23200] Decorrelating experience for 288 frames... [2023-03-09 07:25:49,125][23193] Decorrelating experience for 448 frames... [2023-03-09 07:25:49,168][23823] Decorrelating experience for 192 frames... [2023-03-09 07:25:49,174][23248] Decorrelating experience for 160 frames... [2023-03-09 07:25:49,188][23623] Decorrelating experience for 224 frames... [2023-03-09 07:25:49,204][23195] Decorrelating experience for 384 frames... [2023-03-09 07:25:49,205][23087] Decorrelating experience for 288 frames... [2023-03-09 07:25:49,219][23209] Decorrelating experience for 288 frames... [2023-03-09 07:25:49,256][24118] Decorrelating experience for 352 frames... [2023-03-09 07:25:49,291][23206] Decorrelating experience for 224 frames... [2023-03-09 07:25:49,303][23638] Decorrelating experience for 384 frames... [2023-03-09 07:25:49,325][23243] Decorrelating experience for 192 frames... [2023-03-09 07:25:49,357][23098] Decorrelating experience for 288 frames... [2023-03-09 07:25:49,358][23213] Decorrelating experience for 480 frames... [2023-03-09 07:25:49,402][23179] Decorrelating experience for 384 frames... [2023-03-09 07:25:49,408][23118] Decorrelating experience for 416 frames... [2023-03-09 07:25:49,408][23241] Decorrelating experience for 224 frames... [2023-03-09 07:25:49,446][23194] Decorrelating experience for 256 frames... [2023-03-09 07:25:49,459][24666] Decorrelating experience for 64 frames... [2023-03-09 07:25:49,484][23087] Decorrelating experience for 320 frames... [2023-03-09 07:25:49,513][23095] Decorrelating experience for 416 frames... [2023-03-09 07:25:49,537][23219] Decorrelating experience for 288 frames... [2023-03-09 07:25:49,552][23209] Decorrelating experience for 320 frames... [2023-03-09 07:25:49,571][24158] Decorrelating experience for 128 frames... [2023-03-09 07:25:49,599][23623] Decorrelating experience for 256 frames... [2023-03-09 07:25:49,604][23206] Decorrelating experience for 256 frames... [2023-03-09 07:25:49,605][24793] Decorrelating experience for 288 frames... [2023-03-09 07:25:49,655][23204] Decorrelating experience for 192 frames... [2023-03-09 07:25:49,656][23228] Decorrelating experience for 96 frames... [2023-03-09 07:25:49,661][24121] Decorrelating experience for 128 frames... [2023-03-09 07:25:49,712][23248] Decorrelating experience for 192 frames... [2023-03-09 07:25:49,734][23118] Decorrelating experience for 448 frames... [2023-03-09 07:25:49,761][23232] Decorrelating experience for 160 frames... [2023-03-09 07:25:49,762][23176] Decorrelating experience for 320 frames... [2023-03-09 07:25:49,788][23098] Decorrelating experience for 320 frames... [2023-03-09 07:25:49,802][23170] Decorrelating experience for 384 frames... [2023-03-09 07:25:49,805][23187] Decorrelating experience for 224 frames... [2023-03-09 07:25:49,846][23209] Decorrelating experience for 352 frames... [2023-03-09 07:25:49,848][24158] Decorrelating experience for 160 frames... [2023-03-09 07:25:49,857][24434] Decorrelating experience for 512 frames... [2023-03-09 07:25:49,901][23194] Decorrelating experience for 288 frames... [2023-03-09 07:25:49,956][23214] Decorrelating experience for 384 frames... [2023-03-09 07:25:49,956][23093] Decorrelating experience for 320 frames... [2023-03-09 07:25:49,972][23193] Decorrelating experience for 480 frames... [2023-03-09 07:25:49,986][24121] Decorrelating experience for 160 frames... [2023-03-09 07:25:49,990][23095] Decorrelating experience for 448 frames... [2023-03-09 07:25:50,023][23242] Decorrelating experience for 128 frames... [2023-03-09 07:25:50,028][23087] Decorrelating experience for 352 frames... [2023-03-09 07:25:50,037][24793] Decorrelating experience for 320 frames... [2023-03-09 07:25:50,079][24158] Decorrelating experience for 192 frames... [2023-03-09 07:25:50,158][23230] Decorrelating experience for 352 frames... [2023-03-09 07:25:50,165][24858] Decorrelating experience for 160 frames... [2023-03-09 07:25:50,168][23088] Decorrelating experience for 288 frames... [2023-03-09 07:25:50,174][23206] Decorrelating experience for 288 frames... [2023-03-09 07:25:50,199][23219] Decorrelating experience for 320 frames... [2023-03-09 07:25:50,202][23209] Decorrelating experience for 384 frames... [2023-03-09 07:25:50,211][23091] Decorrelating experience for 224 frames... [2023-03-09 07:25:50,222][23094] Decorrelating experience for 160 frames... [2023-03-09 07:25:50,255][23202] Decorrelating experience for 320 frames... [2023-03-09 07:25:50,271][23194] Decorrelating experience for 320 frames... [2023-03-09 07:25:50,350][23242] Decorrelating experience for 160 frames... [2023-03-09 07:25:50,353][23093] Decorrelating experience for 352 frames... [2023-03-09 07:25:50,355][23204] Decorrelating experience for 224 frames... [2023-03-09 07:25:50,362][23224] Decorrelating experience for 352 frames... [2023-03-09 07:25:50,382][24118] Decorrelating experience for 384 frames... [2023-03-09 07:25:50,414][23092] Decorrelating experience for 128 frames... [2023-03-09 07:25:50,416][24858] Decorrelating experience for 192 frames... [2023-03-09 07:25:50,416][23238] Decorrelating experience for 128 frames... [2023-03-09 07:25:50,453][23206] Decorrelating experience for 320 frames... [2023-03-09 07:25:50,527][23823] Decorrelating experience for 224 frames... [2023-03-09 07:25:50,548][23232] Decorrelating experience for 192 frames... [2023-03-09 07:25:50,561][23094] Decorrelating experience for 192 frames... [2023-03-09 07:25:50,563][23223] Decorrelating experience for 416 frames... [2023-03-09 07:25:50,567][23219] Decorrelating experience for 352 frames... [2023-03-09 07:25:50,599][23202] Decorrelating experience for 352 frames... [2023-03-09 07:25:50,613][24539] Decorrelating experience for 96 frames... [2023-03-09 07:25:50,613][23218] Decorrelating experience for 544 frames... [2023-03-09 07:25:50,635][23092] Decorrelating experience for 160 frames... [2023-03-09 07:25:50,656][23227] Decorrelating experience for 160 frames... [2023-03-09 07:25:50,752][23088] Decorrelating experience for 320 frames... [2023-03-09 07:25:50,759][23173] Decorrelating experience for 288 frames... [2023-03-09 07:25:50,760][23250] Decorrelating experience for 160 frames... [2023-03-09 07:25:50,766][24025] Decorrelating experience for 256 frames... [2023-03-09 07:25:50,775][24158] Decorrelating experience for 224 frames... [2023-03-09 07:25:50,815][23867] Decorrelating experience for 96 frames... [2023-03-09 07:25:50,825][23244] Decorrelating experience for 224 frames... [2023-03-09 07:25:50,831][23634] Decorrelating experience for 256 frames... [2023-03-09 07:25:50,850][23206] Decorrelating experience for 352 frames... [2023-03-09 07:25:50,868][23092] Decorrelating experience for 192 frames... [2023-03-09 07:25:50,890][23208] Another process currently holds the lock /tmp/sf2_rolo/doom_002.lockfile, attempt: 1 [2023-03-09 07:25:50,890][24120] Another process currently holds the lock /tmp/sf2_rolo/doom_002.lockfile, attempt: 1 [2023-03-09 07:25:50,926][24121] Decorrelating experience for 192 frames... [2023-03-09 07:25:50,936][23242] Decorrelating experience for 192 frames... [2023-03-09 07:25:50,944][23238] Decorrelating experience for 160 frames... [2023-03-09 07:25:50,958][23093] Decorrelating experience for 384 frames... [2023-03-09 07:25:50,999][23232] Decorrelating experience for 224 frames... [2023-03-09 07:25:51,022][23169] Decorrelating experience for 96 frames... [2023-03-09 07:25:51,023][23245] Decorrelating experience for 128 frames... [2023-03-09 07:25:51,024][23212] Decorrelating experience for 192 frames... [2023-03-09 07:25:51,029][23195] Decorrelating experience for 416 frames... [2023-03-09 07:25:51,045][23250] Decorrelating experience for 192 frames... [2023-03-09 07:25:51,104][23094] Decorrelating experience for 224 frames... [2023-03-09 07:25:51,127][24539] Decorrelating experience for 128 frames... [2023-03-09 07:25:51,134][23170] Decorrelating experience for 416 frames... [2023-03-09 07:25:51,143][23223] Decorrelating experience for 448 frames... [2023-03-09 07:25:51,177][23091] Decorrelating experience for 256 frames... [2023-03-09 07:25:51,209][23202] Decorrelating experience for 384 frames... [2023-03-09 07:25:51,218][23097] Decorrelating experience for 256 frames... [2023-03-09 07:25:51,220][23181] Decorrelating experience for 192 frames... [2023-03-09 07:25:51,223][23219] Decorrelating experience for 384 frames... [2023-03-09 07:25:51,250][24118] Decorrelating experience for 416 frames... [2023-03-09 07:25:51,306][23206] Decorrelating experience for 384 frames... [2023-03-09 07:25:51,314][23635] Decorrelating experience for 192 frames... [2023-03-09 07:25:51,329][23238] Decorrelating experience for 192 frames... [2023-03-09 07:25:51,348][23207] Decorrelating experience for 352 frames... [2023-03-09 07:25:51,366][23186] Decorrelating experience for 288 frames... [2023-03-09 07:25:51,386][23634] Decorrelating experience for 288 frames... [2023-03-09 07:25:51,401][23088] Decorrelating experience for 352 frames... [2023-03-09 07:25:51,413][23094] Decorrelating experience for 256 frames... [2023-03-09 07:25:51,427][23093] Decorrelating experience for 416 frames... [2023-03-09 07:25:51,429][23204] Decorrelating experience for 256 frames... [2023-03-09 07:25:51,517][23177] Decorrelating experience for 160 frames... [2023-03-09 07:25:51,528][23244] Decorrelating experience for 256 frames... [2023-03-09 07:25:51,531][23194] Decorrelating experience for 352 frames... [2023-03-09 07:25:51,532][23623] Decorrelating experience for 288 frames... [2023-03-09 07:25:51,571][23485] Decorrelating experience for 128 frames... [2023-03-09 07:25:51,571][23248] Decorrelating experience for 224 frames... [2023-03-09 07:25:51,579][23241] Decorrelating experience for 256 frames... [2023-03-09 07:25:51,589][24793] Decorrelating experience for 352 frames... [2023-03-09 07:25:51,617][23181] Decorrelating experience for 224 frames... [2023-03-09 07:25:51,682][23219] Decorrelating experience for 416 frames... [2023-03-09 07:25:51,722][23634] Decorrelating experience for 320 frames... [2023-03-09 07:25:51,725][23176] Decorrelating experience for 352 frames... [2023-03-09 07:25:51,726][23637] Decorrelating experience for 224 frames... [2023-03-09 07:25:51,752][23195] Decorrelating experience for 448 frames... [2023-03-09 07:25:51,761][23635] Decorrelating experience for 224 frames... [2023-03-09 07:25:51,770][23636] Decorrelating experience for 256 frames... [2023-03-09 07:25:51,786][23209] Decorrelating experience for 416 frames... [2023-03-09 07:25:51,814][23088] Decorrelating experience for 384 frames... [2023-03-09 07:25:51,835][23249] Decorrelating experience for 256 frames... [2023-03-09 07:25:51,884][23242] Decorrelating experience for 224 frames... [2023-03-09 07:25:51,903][23204] Decorrelating experience for 288 frames... [2023-03-09 07:25:51,944][24156] Decorrelating experience for 288 frames... [2023-03-09 07:25:51,945][23095] Decorrelating experience for 480 frames... [2023-03-09 07:25:51,952][23241] Decorrelating experience for 288 frames... [2023-03-09 07:25:51,979][23093] Decorrelating experience for 448 frames... [2023-03-09 07:25:51,980][23227] Decorrelating experience for 192 frames... [2023-03-09 07:25:51,987][23224] Decorrelating experience for 384 frames... [2023-03-09 07:25:51,992][24158] Decorrelating experience for 256 frames... [2023-03-09 07:25:52,021][23172] Decorrelating experience for 96 frames... [2023-03-09 07:25:52,085][23248] Decorrelating experience for 256 frames... [2023-03-09 07:25:52,089][23637] Decorrelating experience for 256 frames... [2023-03-09 07:25:52,121][23219] Decorrelating experience for 448 frames... [2023-03-09 07:25:52,130][23180] Decorrelating experience for 480 frames... [2023-03-09 07:25:52,142][23203] Decorrelating experience for 224 frames... [2023-03-09 07:25:52,175][23634] Decorrelating experience for 352 frames... [2023-03-09 07:25:52,176][23209] Decorrelating experience for 448 frames... [2023-03-09 07:25:52,176][23623] Decorrelating experience for 320 frames... [2023-03-09 07:25:52,190][23223] Decorrelating experience for 480 frames... [2023-03-09 07:25:52,222][23201] Decorrelating experience for 224 frames... [2023-03-09 07:25:52,283][23088] Decorrelating experience for 416 frames... [2023-03-09 07:25:52,304][23245] Decorrelating experience for 160 frames... [2023-03-09 07:25:52,313][23525] Decorrelating experience for 288 frames... [2023-03-09 07:25:52,325][23234] Decorrelating experience for 160 frames... [2023-03-09 07:25:52,327][23657] Decorrelating experience for 128 frames... [2023-03-09 07:25:52,358][23224] Decorrelating experience for 416 frames... [2023-03-09 07:25:52,360][23177] Decorrelating experience for 192 frames... [2023-03-09 07:25:52,397][24118] Decorrelating experience for 448 frames... [2023-03-09 07:25:52,409][23227] Decorrelating experience for 224 frames... [2023-03-09 07:25:52,467][23093] Decorrelating experience for 480 frames... [2023-03-09 07:25:52,480][23634] Decorrelating experience for 384 frames... [2023-03-09 07:25:52,483][23176] Decorrelating experience for 384 frames... [2023-03-09 07:25:52,500][23095] Decorrelating experience for 512 frames... [2023-03-09 07:25:52,506][23218] Decorrelating experience for 576 frames... [2023-03-09 07:25:52,508][23248] Decorrelating experience for 288 frames... [2023-03-09 07:25:52,535][23172] Decorrelating experience for 128 frames... [2023-03-09 07:25:52,543][23096] Decorrelating experience for 256 frames... [2023-03-09 07:25:52,583][23203] Decorrelating experience for 256 frames... [2023-03-09 07:25:52,587][23094] Decorrelating experience for 288 frames... [2023-03-09 07:25:52,641][23097] Decorrelating experience for 288 frames... [2023-03-09 07:25:52,660][23195] Decorrelating experience for 480 frames... [2023-03-09 07:25:52,665][23088] Decorrelating experience for 448 frames... [2023-03-09 07:25:52,679][23170] Decorrelating experience for 448 frames... [2023-03-09 07:25:52,683][23238] Decorrelating experience for 224 frames... [2023-03-09 07:25:52,691][23175] Decorrelating experience for 224 frames... [2023-03-09 07:25:52,717][23219] Decorrelating experience for 480 frames... [2023-03-09 07:25:52,753][23236] Decorrelating experience for 384 frames... [2023-03-09 07:25:52,765][24158] Decorrelating experience for 288 frames... [2023-03-09 07:25:52,774][23240] Decorrelating experience for 288 frames... [2023-03-09 07:25:52,829][23211] Decorrelating experience for 128 frames... [2023-03-09 07:25:52,841][23204] Decorrelating experience for 320 frames... [2023-03-09 07:25:52,854][23203] Decorrelating experience for 288 frames... [2023-03-09 07:25:52,858][23177] Decorrelating experience for 224 frames... [2023-03-09 07:25:52,872][23094] Decorrelating experience for 320 frames... [2023-03-09 07:25:52,890][23209] Decorrelating experience for 480 frames... [2023-03-09 07:25:52,910][23172] Decorrelating experience for 160 frames... [2023-03-09 07:25:52,931][24666] Decorrelating experience for 96 frames... [2023-03-09 07:25:52,941][23238] Decorrelating experience for 256 frames... [2023-03-09 07:25:52,989][23249] Decorrelating experience for 288 frames... [2023-03-09 07:25:53,013][23173] Decorrelating experience for 320 frames... [2023-03-09 07:25:53,035][23201] Decorrelating experience for 256 frames... [2023-03-09 07:25:53,049][24793] Decorrelating experience for 384 frames... [2023-03-09 07:25:53,060][24539] Decorrelating experience for 160 frames... [2023-03-09 07:25:53,069][23623] Decorrelating experience for 352 frames... [2023-03-09 07:25:53,090][23186] Decorrelating experience for 320 frames... [2023-03-09 07:25:53,091][23245] Decorrelating experience for 192 frames... [2023-03-09 07:25:53,112][23095] Decorrelating experience for 544 frames... [2023-03-09 07:25:53,140][24118] Decorrelating experience for 480 frames... [2023-03-09 07:25:53,177][24157] Decorrelating experience for 480 frames... [2023-03-09 07:25:53,189][23179] Decorrelating experience for 416 frames... [2023-03-09 07:25:53,230][23239] Decorrelating experience for 96 frames... [2023-03-09 07:25:53,252][23182] Decorrelating experience for 288 frames... [2023-03-09 07:25:53,254][23244] Decorrelating experience for 288 frames... [2023-03-09 07:25:53,274][23232] Decorrelating experience for 256 frames... [2023-03-09 07:25:53,275][23249] Decorrelating experience for 320 frames... [2023-03-09 07:25:53,287][24121] Decorrelating experience for 224 frames... [2023-03-09 07:25:53,292][23224] Decorrelating experience for 448 frames... [2023-03-09 07:25:53,343][23223] Decorrelating experience for 512 frames... [2023-03-09 07:25:53,368][23637] Decorrelating experience for 288 frames... [2023-03-09 07:25:53,373][23177] Decorrelating experience for 256 frames... [2023-03-09 07:25:53,411][23242] Decorrelating experience for 256 frames... [2023-03-09 07:25:53,428][23662] Decorrelating experience for 256 frames... [2023-03-09 07:25:53,448][24158] Decorrelating experience for 320 frames... [2023-03-09 07:25:53,454][23201] Decorrelating experience for 288 frames... [2023-03-09 07:25:53,458][23175] Decorrelating experience for 256 frames... [2023-03-09 07:25:53,469][23186] Decorrelating experience for 352 frames... [2023-03-09 07:25:53,471][23096] Decorrelating experience for 288 frames... [2023-03-09 07:25:53,554][23169] Decorrelating experience for 128 frames... [2023-03-09 07:25:53,555][23118] Decorrelating experience for 480 frames... [2023-03-09 07:25:53,583][24666] Decorrelating experience for 128 frames... [2023-03-09 07:25:53,589][23441] Decorrelating experience for 64 frames... [2023-03-09 07:25:53,606][23525] Decorrelating experience for 320 frames... [2023-03-09 07:25:53,623][23197] Another process currently holds the lock /tmp/sf2_rolo/doom_002.lockfile, attempt: 1 [2023-03-09 07:25:53,630][23236] Decorrelating experience for 416 frames... [2023-03-09 07:25:53,639][24157] Decorrelating experience for 512 frames... [2023-03-09 07:25:53,640][23245] Decorrelating experience for 224 frames... [2023-03-09 07:25:53,648][23638] Decorrelating experience for 416 frames... [2023-03-09 07:25:53,651][23248] Decorrelating experience for 320 frames... [2023-03-09 07:25:53,734][24120] Decorrelating experience for 0 frames... [2023-03-09 07:25:53,736][23200] Decorrelating experience for 320 frames... [2023-03-09 07:25:53,766][23088] Decorrelating experience for 480 frames... [2023-03-09 07:25:53,774][23209] Decorrelating experience for 512 frames... [2023-03-09 07:25:53,810][23241] Decorrelating experience for 320 frames... [2023-03-09 07:25:53,818][23234] Decorrelating experience for 192 frames... [2023-03-09 07:25:53,837][23171] Decorrelating experience for 320 frames... [2023-03-09 07:25:53,838][23250] Decorrelating experience for 224 frames... [2023-03-09 07:25:53,841][23182] Decorrelating experience for 320 frames... [2023-03-09 07:25:53,851][23176] Decorrelating experience for 416 frames... [2023-03-09 07:25:53,925][23224] Decorrelating experience for 480 frames... [2023-03-09 07:25:53,925][23094] Decorrelating experience for 352 frames... [2023-03-09 07:25:53,954][24539] Decorrelating experience for 192 frames... [2023-03-09 07:25:53,956][23103] Decorrelating experience for 192 frames... [2023-03-09 07:25:53,988][23244] Decorrelating experience for 320 frames... [2023-03-09 07:25:53,997][23232] Decorrelating experience for 288 frames... [2023-03-09 07:25:54,033][23638] Decorrelating experience for 448 frames... [2023-03-09 07:25:54,036][23199] Decorrelating experience for 320 frames... [2023-03-09 07:25:54,036][23200] Decorrelating experience for 352 frames... [2023-03-09 07:25:54,059][22664] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 0.0. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) [2023-03-09 07:25:54,063][23230] Decorrelating experience for 384 frames... [2023-03-09 07:25:54,105][23197] Decorrelating experience for 64 frames... [2023-03-09 07:25:54,105][23181] Decorrelating experience for 256 frames... [2023-03-09 07:25:54,146][23209] Decorrelating experience for 544 frames... [2023-03-09 07:25:54,166][23238] Decorrelating experience for 288 frames... [2023-03-09 07:25:54,183][23170] Decorrelating experience for 480 frames... [2023-03-09 07:25:54,202][23623] Decorrelating experience for 384 frames... [2023-03-09 07:25:54,211][24120] Decorrelating experience for 32 frames... [2023-03-09 07:25:54,227][23094] Decorrelating experience for 384 frames... [2023-03-09 07:25:54,241][23190] Decorrelating experience for 224 frames... [2023-03-09 07:25:54,246][24158] Decorrelating experience for 352 frames... [2023-03-09 07:25:54,291][23099] Decorrelating experience for 256 frames... [2023-03-09 07:25:54,292][23201] Decorrelating experience for 320 frames... [2023-03-09 07:25:54,348][23865] Decorrelating experience for 384 frames... [2023-03-09 07:25:54,361][23096] Decorrelating experience for 320 frames... [2023-03-09 07:25:54,363][24157] Decorrelating experience for 544 frames... [2023-03-09 07:25:54,383][23097] Decorrelating experience for 320 frames... [2023-03-09 07:25:54,389][23231] Decorrelating experience for 192 frames... [2023-03-09 07:25:54,403][23525] Decorrelating experience for 352 frames... [2023-03-09 07:25:54,423][23091] Decorrelating experience for 288 frames... [2023-03-09 07:25:54,435][23232] Decorrelating experience for 320 frames... [2023-03-09 07:25:54,474][23234] Decorrelating experience for 224 frames... [2023-03-09 07:25:54,515][23199] Decorrelating experience for 352 frames... [2023-03-09 07:25:54,555][23245] Decorrelating experience for 256 frames... [2023-03-09 07:25:54,561][23224] Decorrelating experience for 512 frames... [2023-03-09 07:25:54,564][23211] Decorrelating experience for 160 frames... [2023-03-09 07:25:54,579][23181] Decorrelating experience for 288 frames... [2023-03-09 07:25:54,591][23182] Decorrelating experience for 352 frames... [2023-03-09 07:25:54,599][23866] Decorrelating experience for 352 frames... [2023-03-09 07:25:54,630][23485] Decorrelating experience for 160 frames... [2023-03-09 07:25:54,655][23214] Decorrelating experience for 416 frames... [2023-03-09 07:25:54,685][24666] Decorrelating experience for 160 frames... [2023-03-09 07:25:54,692][23206] Decorrelating experience for 416 frames... [2023-03-09 07:25:54,736][23170] Decorrelating experience for 512 frames... [2023-03-09 07:25:54,744][23215] Decorrelating experience for 192 frames... [2023-03-09 07:25:54,751][23250] Decorrelating experience for 256 frames... [2023-03-09 07:25:54,761][23634] Decorrelating experience for 416 frames... [2023-03-09 07:25:54,778][23191] Another process currently holds the lock /tmp/sf2_rolo/doom_002.lockfile, attempt: 1 [2023-03-09 07:25:54,797][24793] Decorrelating experience for 416 frames... [2023-03-09 07:25:54,797][23186] Decorrelating experience for 384 frames... [2023-03-09 07:25:54,824][23179] Decorrelating experience for 448 frames... [2023-03-09 07:25:54,833][23176] Decorrelating experience for 448 frames... [2023-03-09 07:25:54,879][23097] Decorrelating experience for 352 frames... [2023-03-09 07:25:54,891][23231] Decorrelating experience for 224 frames... [2023-03-09 07:25:54,916][23865] Decorrelating experience for 416 frames... [2023-03-09 07:25:54,932][23249] Decorrelating experience for 352 frames... [2023-03-09 07:25:54,940][23222] Decorrelating experience for 352 frames... [2023-03-09 07:25:54,983][23196] Decorrelating experience for 288 frames... [2023-03-09 07:25:54,998][23232] Decorrelating experience for 352 frames... [2023-03-09 07:25:54,999][23441] Decorrelating experience for 96 frames... [2023-03-09 07:25:55,005][23096] Decorrelating experience for 352 frames... [2023-03-09 07:25:55,012][24025] Decorrelating experience for 288 frames... [2023-03-09 07:25:55,057][23217] Decorrelating experience for 64 frames... [2023-03-09 07:25:55,092][23224] Decorrelating experience for 544 frames... [2023-03-09 07:25:55,108][23866] Decorrelating experience for 384 frames... [2023-03-09 07:25:55,156][23241] Decorrelating experience for 352 frames... [2023-03-09 07:25:55,166][23210] Decorrelating experience for 416 frames... [2023-03-09 07:25:55,167][23103] Decorrelating experience for 224 frames... [2023-03-09 07:25:55,185][23234] Decorrelating experience for 256 frames... [2023-03-09 07:25:55,196][23229] Decorrelating experience for 224 frames... [2023-03-09 07:25:55,203][23177] Decorrelating experience for 288 frames... [2023-03-09 07:25:55,232][23219] Decorrelating experience for 512 frames... [2023-03-09 07:25:55,270][23170] Decorrelating experience for 544 frames... [2023-03-09 07:25:55,289][23249] Decorrelating experience for 384 frames... [2023-03-09 07:25:55,291][23485] Decorrelating experience for 192 frames... [2023-03-09 07:25:55,339][23214] Decorrelating experience for 448 frames... [2023-03-09 07:25:55,347][24352] Decorrelating experience for 320 frames... [2023-03-09 07:25:55,363][23525] Decorrelating experience for 384 frames... [2023-03-09 07:25:55,375][23206] Decorrelating experience for 448 frames... [2023-03-09 07:25:55,387][23192] Decorrelating experience for 160 frames... [2023-03-09 07:25:55,409][24539] Decorrelating experience for 224 frames... [2023-03-09 07:25:55,470][23242] Decorrelating experience for 288 frames... [2023-03-09 07:25:55,473][23657] Decorrelating experience for 160 frames... [2023-03-09 07:25:55,478][23103] Decorrelating experience for 256 frames... [2023-03-09 07:25:55,480][23866] Decorrelating experience for 416 frames... [2023-03-09 07:25:55,517][23223] Decorrelating experience for 544 frames... [2023-03-09 07:25:55,539][24793] Decorrelating experience for 448 frames... [2023-03-09 07:25:55,574][23186] Decorrelating experience for 416 frames... [2023-03-09 07:25:55,589][23485] Decorrelating experience for 224 frames... [2023-03-09 07:25:55,609][23169] Decorrelating experience for 160 frames... [2023-03-09 07:25:55,620][23817] Decorrelating experience for 224 frames... [2023-03-09 07:25:55,660][23190] Decorrelating experience for 256 frames... [2023-03-09 07:25:55,664][23217] Decorrelating experience for 96 frames... [2023-03-09 07:25:55,671][23636] Decorrelating experience for 288 frames... [2023-03-09 07:25:55,674][23210] Decorrelating experience for 448 frames... [2023-03-09 07:25:55,694][23635] Decorrelating experience for 256 frames... [2023-03-09 07:25:55,722][32460] Decorrelating experience for 224 frames... [2023-03-09 07:25:55,751][23233] Decorrelating experience for 192 frames... [2023-03-09 07:25:55,793][23247] Decorrelating experience for 352 frames... [2023-03-09 07:25:55,819][23441] Decorrelating experience for 128 frames... [2023-03-09 07:25:55,851][23623] Decorrelating experience for 416 frames... [2023-03-09 07:25:55,864][23202] Decorrelating experience for 416 frames... [2023-03-09 07:25:55,867][23196] Decorrelating experience for 320 frames... [2023-03-09 07:25:55,873][23206] Decorrelating experience for 480 frames... [2023-03-09 07:25:55,878][23087] Decorrelating experience for 384 frames... [2023-03-09 07:25:55,882][23199] Decorrelating experience for 384 frames... [2023-03-09 07:25:55,883][23314] Another process currently holds the lock /tmp/sf2_rolo/doom_002.lockfile, attempt: 1 [2023-03-09 07:25:55,899][23222] Decorrelating experience for 384 frames... [2023-03-09 07:25:55,926][23250] Decorrelating experience for 288 frames... [2023-03-09 07:25:55,973][23227] Decorrelating experience for 256 frames... [2023-03-09 07:25:55,996][24352] Decorrelating experience for 352 frames... [2023-03-09 07:25:56,037][23214] Decorrelating experience for 480 frames... [2023-03-09 07:25:56,044][23097] Decorrelating experience for 384 frames... [2023-03-09 07:25:56,048][23201] Decorrelating experience for 352 frames... [2023-03-09 07:25:56,057][23242] Decorrelating experience for 320 frames... [2023-03-09 07:25:56,063][23186] Decorrelating experience for 448 frames... [2023-03-09 07:25:56,080][23224] Decorrelating experience for 576 frames... [2023-03-09 07:25:56,084][23190] Decorrelating experience for 288 frames... [2023-03-09 07:25:56,106][23231] Decorrelating experience for 256 frames... [2023-03-09 07:25:56,170][23485] Decorrelating experience for 256 frames... [2023-03-09 07:25:56,180][23170] Decorrelating experience for 576 frames... [2023-03-09 07:25:56,217][23196] Decorrelating experience for 352 frames... [2023-03-09 07:25:56,229][23217] Decorrelating experience for 128 frames... [2023-03-09 07:25:56,234][23236] Decorrelating experience for 448 frames... [2023-03-09 07:25:56,250][23171] Decorrelating experience for 352 frames... [2023-03-09 07:25:56,278][23206] Decorrelating experience for 512 frames... [2023-03-09 07:25:56,289][23249] Decorrelating experience for 416 frames... [2023-03-09 07:25:56,290][23245] Decorrelating experience for 288 frames... [2023-03-09 07:25:56,347][23247] Decorrelating experience for 384 frames... [2023-03-09 07:25:56,362][23097] Decorrelating experience for 416 frames... [2023-03-09 07:25:56,399][23087] Decorrelating experience for 416 frames... [2023-03-09 07:25:56,408][23200] Decorrelating experience for 384 frames... [2023-03-09 07:25:56,426][23199] Decorrelating experience for 416 frames... [2023-03-09 07:25:56,429][23195] Decorrelating experience for 512 frames... [2023-03-09 07:25:56,470][23096] Decorrelating experience for 384 frames... [2023-03-09 07:25:56,471][23180] Decorrelating experience for 512 frames... [2023-03-09 07:25:56,490][32460] Decorrelating experience for 256 frames... [2023-03-09 07:25:56,492][23176] Decorrelating experience for 480 frames... [2023-03-09 07:25:56,532][23210] Decorrelating experience for 480 frames... [2023-03-09 07:25:56,579][23170] Decorrelating experience for 608 frames... [2023-03-09 07:25:56,584][23169] Decorrelating experience for 192 frames... [2023-03-09 07:25:56,595][23638] Decorrelating experience for 480 frames... [2023-03-09 07:25:56,608][23242] Decorrelating experience for 352 frames... [2023-03-09 07:25:56,610][23216] Decorrelating experience for 256 frames... [2023-03-09 07:25:56,655][33428] Decorrelating experience for 288 frames... [2023-03-09 07:25:56,665][23230] Decorrelating experience for 416 frames... [2023-03-09 07:25:56,671][23218] Decorrelating experience for 608 frames... [2023-03-09 07:25:56,719][23223] Decorrelating experience for 576 frames... [2023-03-09 07:25:56,748][23249] Decorrelating experience for 448 frames... [2023-03-09 07:25:56,760][23211] Decorrelating experience for 192 frames... [2023-03-09 07:25:56,792][23525] Decorrelating experience for 416 frames... [2023-03-09 07:25:56,818][23817] Decorrelating experience for 256 frames... [2023-03-09 07:25:56,850][23097] Decorrelating experience for 448 frames... [2023-03-09 07:25:56,856][23235] Decorrelating experience for 288 frames... [2023-03-09 07:25:56,859][23183] Decorrelating experience for 224 frames... [2023-03-09 07:25:56,862][23623] Decorrelating experience for 448 frames... [2023-03-09 07:25:56,901][23227] Decorrelating experience for 288 frames... [2023-03-09 07:25:56,939][23236] Decorrelating experience for 480 frames... [2023-03-09 07:25:56,942][23195] Decorrelating experience for 544 frames... [2023-03-09 07:25:56,975][23091] Decorrelating experience for 320 frames... [2023-03-09 07:25:56,994][24793] Decorrelating experience for 480 frames... [2023-03-09 07:25:57,029][23179] Decorrelating experience for 480 frames... [2023-03-09 07:25:57,040][23178] Decorrelating experience for 128 frames... [2023-03-09 07:25:57,042][23173] Decorrelating experience for 352 frames... [2023-03-09 07:25:57,050][23638] Decorrelating experience for 512 frames... [2023-03-09 07:25:57,050][23177] Decorrelating experience for 320 frames... [2023-03-09 07:25:57,080][23181] Decorrelating experience for 320 frames... [2023-03-09 07:25:57,143][23657] Decorrelating experience for 192 frames... [2023-03-09 07:25:57,156][24352] Decorrelating experience for 384 frames... [2023-03-09 07:25:57,200][23170] Decorrelating experience for 640 frames... [2023-03-09 07:25:57,221][24158] Decorrelating experience for 384 frames... [2023-03-09 07:25:57,226][23525] Decorrelating experience for 448 frames... [2023-03-09 07:25:57,228][23196] Decorrelating experience for 384 frames... [2023-03-09 07:25:57,268][23242] Decorrelating experience for 384 frames... [2023-03-09 07:25:57,272][23201] Decorrelating experience for 384 frames... [2023-03-09 07:25:57,292][23247] Decorrelating experience for 416 frames... [2023-03-09 07:25:57,322][23226] Decorrelating experience for 192 frames... [2023-03-09 07:25:57,335][23227] Decorrelating experience for 320 frames... [2023-03-09 07:25:57,399][23214] Decorrelating experience for 512 frames... [2023-03-09 07:25:57,412][23623] Decorrelating experience for 480 frames... [2023-03-09 07:25:57,412][23205] Decorrelating experience for 128 frames... [2023-03-09 07:25:57,445][23169] Decorrelating experience for 224 frames... [2023-03-09 07:25:57,463][23212] Decorrelating experience for 224 frames... [2023-03-09 07:25:57,463][23177] Decorrelating experience for 352 frames... [2023-03-09 07:25:57,470][23183] Decorrelating experience for 256 frames... [2023-03-09 07:25:57,475][24025] Decorrelating experience for 320 frames... [2023-03-09 07:25:57,532][23202] Decorrelating experience for 448 frames... [2023-03-09 07:25:57,561][23093] Decorrelating experience for 512 frames... [2023-03-09 07:25:57,589][23231] Decorrelating experience for 288 frames... [2023-03-09 07:25:57,602][23249] Decorrelating experience for 480 frames... [2023-03-09 07:25:57,647][23205] Decorrelating experience for 160 frames... [2023-03-09 07:25:57,652][24793] Decorrelating experience for 512 frames... [2023-03-09 07:25:57,657][23192] Decorrelating experience for 192 frames... [2023-03-09 07:25:57,673][23226] Decorrelating experience for 224 frames... [2023-03-09 07:25:57,696][23441] Decorrelating experience for 160 frames... [2023-03-09 07:25:57,702][23095] Decorrelating experience for 576 frames... [2023-03-09 07:25:57,709][23223] Decorrelating experience for 608 frames... [2023-03-09 07:25:57,768][23638] Decorrelating experience for 544 frames... [2023-03-09 07:25:57,809][23235] Decorrelating experience for 320 frames... [2023-03-09 07:25:57,810][23485] Decorrelating experience for 288 frames... [2023-03-09 07:25:57,832][23245] Decorrelating experience for 320 frames... [2023-03-09 07:25:57,835][23200] Decorrelating experience for 416 frames... [2023-03-09 07:25:57,844][23183] Decorrelating experience for 288 frames... [2023-03-09 07:25:57,894][23099] Decorrelating experience for 288 frames... [2023-03-09 07:25:57,894][23089] Decorrelating experience for 224 frames... [2023-03-09 07:25:57,894][23205] Decorrelating experience for 192 frames... [2023-03-09 07:25:57,899][23236] Decorrelating experience for 512 frames... [2023-03-09 07:25:57,950][23196] Decorrelating experience for 416 frames... [2023-03-09 07:25:57,988][24156] Decorrelating experience for 320 frames... [2023-03-09 07:25:58,023][23185] Decorrelating experience for 192 frames... [2023-03-09 07:25:58,025][23244] Decorrelating experience for 352 frames... [2023-03-09 07:25:58,028][23217] Decorrelating experience for 160 frames... [2023-03-09 07:25:58,029][23231] Decorrelating experience for 320 frames... [2023-03-09 07:25:58,076][23229] Decorrelating experience for 256 frames... [2023-03-09 07:25:58,079][23187] Decorrelating experience for 256 frames... [2023-03-09 07:25:58,086][23179] Decorrelating experience for 512 frames... [2023-03-09 07:25:58,113][23866] Decorrelating experience for 448 frames... [2023-03-09 07:25:58,127][23218] Decorrelating experience for 640 frames... [2023-03-09 07:25:58,169][23215] Decorrelating experience for 224 frames... [2023-03-09 07:25:58,213][24157] Decorrelating experience for 576 frames... [2023-03-09 07:25:58,218][23186] Decorrelating experience for 480 frames... [2023-03-09 07:25:58,226][23170] Decorrelating experience for 672 frames... [2023-03-09 07:25:58,227][23623] Decorrelating experience for 512 frames... [2023-03-09 07:25:58,292][23197] Decorrelating experience for 96 frames... [2023-03-09 07:25:58,293][23180] Decorrelating experience for 544 frames... [2023-03-09 07:25:58,294][23485] Decorrelating experience for 320 frames... [2023-03-09 07:25:58,335][23228] Decorrelating experience for 128 frames... [2023-03-09 07:25:58,338][23226] Decorrelating experience for 256 frames... [2023-03-09 07:25:58,381][23657] Decorrelating experience for 224 frames... [2023-03-09 07:25:58,397][23229] Decorrelating experience for 288 frames... [2023-03-09 07:25:58,426][23231] Decorrelating experience for 352 frames... [2023-03-09 07:25:58,431][23638] Decorrelating experience for 576 frames... [2023-03-09 07:25:58,435][24156] Decorrelating experience for 352 frames... [2023-03-09 07:25:58,487][23215] Decorrelating experience for 256 frames... [2023-03-09 07:25:58,491][23190] Decorrelating experience for 320 frames... [2023-03-09 07:25:58,491][23249] Decorrelating experience for 512 frames... [2023-03-09 07:25:58,538][23182] Decorrelating experience for 384 frames... [2023-03-09 07:25:58,539][23248] Decorrelating experience for 352 frames... [2023-03-09 07:25:58,585][23200] Decorrelating experience for 448 frames... [2023-03-09 07:25:58,586][23206] Decorrelating experience for 544 frames... [2023-03-09 07:25:58,626][23186] Decorrelating experience for 512 frames... [2023-03-09 07:25:58,672][23180] Decorrelating experience for 576 frames... [2023-03-09 07:25:58,677][23228] Decorrelating experience for 160 frames... [2023-03-09 07:25:58,687][23089] Decorrelating experience for 256 frames... [2023-03-09 07:25:58,688][23087] Decorrelating experience for 448 frames... [2023-03-09 07:25:58,695][24539] Decorrelating experience for 256 frames... [2023-03-09 07:25:58,737][23176] Decorrelating experience for 512 frames... [2023-03-09 07:25:58,738][32460] Decorrelating experience for 288 frames... [2023-03-09 07:25:58,778][24156] Decorrelating experience for 384 frames... [2023-03-09 07:25:58,805][24157] Decorrelating experience for 608 frames... [2023-03-09 07:25:58,854][23209] Decorrelating experience for 576 frames... [2023-03-09 07:25:58,862][23178] Decorrelating experience for 160 frames... [2023-03-09 07:25:58,890][23866] Decorrelating experience for 480 frames... [2023-03-09 07:25:58,894][23229] Decorrelating experience for 320 frames... [2023-03-09 07:25:58,895][24793] Decorrelating experience for 544 frames... [2023-03-09 07:25:58,895][23210] Decorrelating experience for 512 frames... [2023-03-09 07:25:58,917][23226] Decorrelating experience for 288 frames... [2023-03-09 07:25:58,933][24120] Decorrelating experience for 64 frames... [2023-03-09 07:25:58,985][23188] Decorrelating experience for 544 frames... [2023-03-09 07:25:59,032][23236] Decorrelating experience for 544 frames... [2023-03-09 07:25:59,034][23175] Decorrelating experience for 288 frames... [2023-03-09 07:25:59,059][22664] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 0.0. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) [2023-03-09 07:25:59,084][23087] Decorrelating experience for 480 frames... [2023-03-09 07:25:59,099][23192] Decorrelating experience for 224 frames... [2023-03-09 07:25:59,100][23228] Decorrelating experience for 192 frames... [2023-03-09 07:25:59,101][23224] Decorrelating experience for 608 frames... [2023-03-09 07:25:59,102][24156] Decorrelating experience for 416 frames... [2023-03-09 07:25:59,136][23199] Decorrelating experience for 448 frames... [2023-03-09 07:25:59,154][24666] Decorrelating experience for 192 frames... [2023-03-09 07:25:59,186][23238] Decorrelating experience for 320 frames... [2023-03-09 07:25:59,211][23197] Decorrelating experience for 128 frames... [2023-03-09 07:25:59,236][23441] Decorrelating experience for 192 frames... [2023-03-09 07:25:59,296][24120] Decorrelating experience for 96 frames... [2023-03-09 07:25:59,299][23212] Decorrelating experience for 256 frames... [2023-03-09 07:25:59,301][23218] Decorrelating experience for 672 frames... [2023-03-09 07:25:59,303][23248] Decorrelating experience for 384 frames... [2023-03-09 07:25:59,323][24858] Decorrelating experience for 224 frames... [2023-03-09 07:25:59,342][23817] Decorrelating experience for 288 frames... [2023-03-09 07:25:59,344][33428] Decorrelating experience for 320 frames... [2023-03-09 07:25:59,400][23623] Decorrelating experience for 544 frames... [2023-03-09 07:25:59,436][24539] Decorrelating experience for 288 frames... [2023-03-09 07:25:59,451][23231] Decorrelating experience for 384 frames... [2023-03-09 07:25:59,495][23087] Decorrelating experience for 512 frames... [2023-03-09 07:25:59,495][23525] Decorrelating experience for 480 frames... [2023-03-09 07:25:59,502][23219] Decorrelating experience for 544 frames... [2023-03-09 07:25:59,520][23175] Decorrelating experience for 320 frames... [2023-03-09 07:25:59,536][23211] Decorrelating experience for 224 frames... [2023-03-09 07:25:59,572][23197] Decorrelating experience for 160 frames... [2023-03-09 07:25:59,573][23314] Decorrelating experience for 32 frames... [2023-03-09 07:25:59,585][23441] Decorrelating experience for 224 frames... [2023-03-09 07:25:59,633][24156] Decorrelating experience for 448 frames... [2023-03-09 07:25:59,642][23244] Decorrelating experience for 384 frames... [2023-03-09 07:25:59,676][32460] Decorrelating experience for 320 frames... [2023-03-09 07:25:59,690][23216] Decorrelating experience for 288 frames... [2023-03-09 07:25:59,697][23099] Decorrelating experience for 320 frames... [2023-03-09 07:25:59,714][23192] Decorrelating experience for 256 frames... [2023-03-09 07:25:59,720][23089] Decorrelating experience for 288 frames... [2023-03-09 07:25:59,757][23189] Decorrelating experience for 64 frames... [2023-03-09 07:25:59,759][23170] Decorrelating experience for 704 frames... [2023-03-09 07:25:59,789][23217] Decorrelating experience for 192 frames... [2023-03-09 07:25:59,844][23183] Decorrelating experience for 320 frames... [2023-03-09 07:25:59,856][23094] Decorrelating experience for 416 frames... [2023-03-09 07:25:59,869][23199] Decorrelating experience for 480 frames... [2023-03-09 07:25:59,869][23188] Decorrelating experience for 576 frames... [2023-03-09 07:25:59,888][23238] Decorrelating experience for 352 frames... [2023-03-09 07:25:59,940][23201] Decorrelating experience for 416 frames... [2023-03-09 07:25:59,963][23485] Decorrelating experience for 352 frames... [2023-03-09 07:25:59,967][23179] Decorrelating experience for 544 frames... [2023-03-09 07:25:59,994][23091] Decorrelating experience for 352 frames... [2023-03-09 07:26:00,031][24120] Decorrelating experience for 128 frames... [2023-03-09 07:26:00,044][23099] Decorrelating experience for 352 frames... [2023-03-09 07:26:00,059][23172] Decorrelating experience for 192 frames... [2023-03-09 07:26:00,059][23193] Decorrelating experience for 512 frames... [2023-03-09 07:26:00,060][23865] Decorrelating experience for 448 frames... [2023-03-09 07:26:00,065][23215] Decorrelating experience for 288 frames... [2023-03-09 07:26:00,118][23175] Decorrelating experience for 352 frames... [2023-03-09 07:26:00,142][23196] Decorrelating experience for 448 frames... [2023-03-09 07:26:00,156][23089] Decorrelating experience for 320 frames... [2023-03-09 07:26:00,186][23094] Decorrelating experience for 448 frames... [2023-03-09 07:26:00,221][23210] Decorrelating experience for 544 frames... [2023-03-09 07:26:00,243][23183] Decorrelating experience for 352 frames... [2023-03-09 07:26:00,246][23223] Decorrelating experience for 640 frames... [2023-03-09 07:26:00,296][23191] Decorrelating experience for 96 frames... [2023-03-09 07:26:00,314][23217] Decorrelating experience for 224 frames... [2023-03-09 07:26:00,328][23213] Decorrelating experience for 512 frames... [2023-03-09 07:26:00,331][23095] Decorrelating experience for 608 frames... [2023-03-09 07:26:00,332][23235] Decorrelating experience for 352 frames... [2023-03-09 07:26:00,366][23182] Decorrelating experience for 416 frames... [2023-03-09 07:26:00,371][23231] Decorrelating experience for 416 frames... [2023-03-09 07:26:00,420][23638] Decorrelating experience for 608 frames... [2023-03-09 07:26:00,429][23817] Decorrelating experience for 320 frames... [2023-03-09 07:26:00,446][23181] Decorrelating experience for 352 frames... [2023-03-09 07:26:00,480][23248] Decorrelating experience for 416 frames... [2023-03-09 07:26:00,498][23203] Decorrelating experience for 320 frames... [2023-03-09 07:26:00,510][23226] Decorrelating experience for 320 frames... [2023-03-09 07:26:00,524][23206] Decorrelating experience for 576 frames... [2023-03-09 07:26:00,557][23170] Decorrelating experience for 736 frames... [2023-03-09 07:26:00,558][23089] Decorrelating experience for 352 frames... [2023-03-09 07:26:00,570][23087] Decorrelating experience for 544 frames... [2023-03-09 07:26:00,624][23098] Decorrelating experience for 352 frames... [2023-03-09 07:26:00,635][23485] Decorrelating experience for 384 frames... [2023-03-09 07:26:00,653][23183] Decorrelating experience for 384 frames... [2023-03-09 07:26:00,667][23209] Decorrelating experience for 608 frames... [2023-03-09 07:26:00,682][32460] Decorrelating experience for 352 frames... [2023-03-09 07:26:00,696][23097] Decorrelating experience for 480 frames... [2023-03-09 07:26:00,741][23525] Decorrelating experience for 512 frames... [2023-03-09 07:26:00,746][23193] Decorrelating experience for 544 frames... [2023-03-09 07:26:00,753][23215] Decorrelating experience for 320 frames... [2023-03-09 07:26:00,796][23096] Decorrelating experience for 416 frames... [2023-03-09 07:26:00,803][23865] Decorrelating experience for 480 frames... [2023-03-09 07:26:00,836][23219] Decorrelating experience for 576 frames... [2023-03-09 07:26:00,845][23213] Decorrelating experience for 544 frames... [2023-03-09 07:26:00,856][23239] Decorrelating experience for 128 frames... [2023-03-09 07:26:00,862][23172] Decorrelating experience for 224 frames... [2023-03-09 07:26:00,934][23216] Decorrelating experience for 320 frames... [2023-03-09 07:26:00,936][23212] Decorrelating experience for 288 frames... [2023-03-09 07:26:00,945][23226] Decorrelating experience for 352 frames... [2023-03-09 07:26:00,962][23191] Decorrelating experience for 128 frames... [2023-03-09 07:26:00,999][23205] Decorrelating experience for 224 frames... [2023-03-09 07:26:01,034][23217] Decorrelating experience for 256 frames... [2023-03-09 07:26:01,044][23186] Decorrelating experience for 544 frames... [2023-03-09 07:26:01,052][23192] Decorrelating experience for 288 frames... [2023-03-09 07:26:01,053][32460] Decorrelating experience for 384 frames... [2023-03-09 07:26:01,054][23095] Decorrelating experience for 640 frames... [2023-03-09 07:26:01,135][23239] Decorrelating experience for 160 frames... [2023-03-09 07:26:01,138][23094] Decorrelating experience for 480 frames... [2023-03-09 07:26:01,141][23623] Decorrelating experience for 576 frames... [2023-03-09 07:26:01,164][23200] Decorrelating experience for 480 frames... [2023-03-09 07:26:01,177][23172] Decorrelating experience for 256 frames... [2023-03-09 07:26:01,213][23228] Decorrelating experience for 224 frames... [2023-03-09 07:26:01,221][23180] Decorrelating experience for 608 frames... [2023-03-09 07:26:01,236][23191] Decorrelating experience for 160 frames... [2023-03-09 07:26:01,258][23181] Decorrelating experience for 384 frames... [2023-03-09 07:26:01,261][23099] Decorrelating experience for 384 frames... [2023-03-09 07:26:01,323][23212] Decorrelating experience for 320 frames... [2023-03-09 07:26:01,328][23216] Decorrelating experience for 352 frames... [2023-03-09 07:26:01,372][23176] Decorrelating experience for 544 frames... [2023-03-09 07:26:01,391][23193] Decorrelating experience for 576 frames... [2023-03-09 07:26:01,399][33428] Decorrelating experience for 352 frames... [2023-03-09 07:26:01,409][23250] Decorrelating experience for 320 frames... [2023-03-09 07:26:01,416][23224] Decorrelating experience for 640 frames... [2023-03-09 07:26:01,422][23217] Decorrelating experience for 288 frames... [2023-03-09 07:26:01,454][23172] Decorrelating experience for 288 frames... [2023-03-09 07:26:01,459][23865] Decorrelating experience for 512 frames... [2023-03-09 07:26:01,503][23087] Decorrelating experience for 576 frames... [2023-03-09 07:26:01,510][23170] Decorrelating experience for 768 frames... [2023-03-09 07:26:01,566][23095] Decorrelating experience for 672 frames... [2023-03-09 07:26:01,573][32460] Decorrelating experience for 416 frames... [2023-03-09 07:26:01,584][23203] Decorrelating experience for 352 frames... [2023-03-09 07:26:01,589][24793] Decorrelating experience for 576 frames... [2023-03-09 07:26:01,601][23242] Decorrelating experience for 416 frames... [2023-03-09 07:26:01,605][23636] Decorrelating experience for 320 frames... [2023-03-09 07:26:01,664][23199] Decorrelating experience for 512 frames... [2023-03-09 07:26:01,675][23191] Decorrelating experience for 192 frames... [2023-03-09 07:26:01,692][23209] Decorrelating experience for 640 frames... [2023-03-09 07:26:01,736][23216] Decorrelating experience for 384 frames... [2023-03-09 07:26:01,757][23097] Decorrelating experience for 512 frames... [2023-03-09 07:26:01,768][23177] Decorrelating experience for 384 frames... [2023-03-09 07:26:01,773][23637] Decorrelating experience for 320 frames... [2023-03-09 07:26:01,778][23206] Decorrelating experience for 608 frames... [2023-03-09 07:26:01,789][23201] Decorrelating experience for 448 frames... [2023-03-09 07:26:01,794][23196] Decorrelating experience for 480 frames... [2023-03-09 07:26:01,863][23250] Decorrelating experience for 352 frames... [2023-03-09 07:26:01,870][23212] Decorrelating experience for 352 frames... [2023-03-09 07:26:01,888][23203] Decorrelating experience for 384 frames... [2023-03-09 07:26:01,942][23172] Decorrelating experience for 320 frames... [2023-03-09 07:26:01,955][23176] Decorrelating experience for 576 frames... [2023-03-09 07:26:01,958][23217] Decorrelating experience for 320 frames... [2023-03-09 07:26:01,960][23229] Decorrelating experience for 352 frames... [2023-03-09 07:26:01,975][23089] Decorrelating experience for 384 frames... [2023-03-09 07:26:01,979][23187] Decorrelating experience for 288 frames... [2023-03-09 07:26:01,984][23623] Decorrelating experience for 608 frames... [2023-03-09 07:26:02,062][23636] Decorrelating experience for 352 frames... [2023-03-09 07:26:02,062][24120] Decorrelating experience for 160 frames... [2023-03-09 07:26:02,081][23199] Decorrelating experience for 544 frames... [2023-03-09 07:26:02,145][24793] Decorrelating experience for 608 frames... [2023-03-09 07:26:02,145][24539] Decorrelating experience for 320 frames... [2023-03-09 07:26:02,170][23240] Decorrelating experience for 320 frames... [2023-03-09 07:26:02,170][23662] Decorrelating experience for 288 frames... [2023-03-09 07:26:02,173][23192] Decorrelating experience for 320 frames... [2023-03-09 07:26:02,174][23181] Decorrelating experience for 416 frames... [2023-03-09 07:26:02,215][23193] Decorrelating experience for 608 frames... [2023-03-09 07:26:02,266][23187] Decorrelating experience for 320 frames... [2023-03-09 07:26:02,310][24156] Decorrelating experience for 480 frames... [2023-03-09 07:26:02,330][23189] Decorrelating experience for 96 frames... [2023-03-09 07:26:02,348][23242] Decorrelating experience for 448 frames... [2023-03-09 07:26:02,349][23201] Decorrelating experience for 480 frames... [2023-03-09 07:26:02,377][23216] Decorrelating experience for 416 frames... [2023-03-09 07:26:02,377][24666] Decorrelating experience for 224 frames... [2023-03-09 07:26:02,377][23185] Decorrelating experience for 224 frames... [2023-03-09 07:26:02,377][23214] Decorrelating experience for 544 frames... [2023-03-09 07:26:02,393][23095] Decorrelating experience for 704 frames... [2023-03-09 07:26:02,447][24120] Decorrelating experience for 192 frames... [2023-03-09 07:26:02,487][24818] Another process currently holds the lock /tmp/sf2_rolo/doom_002.lockfile, attempt: 1 [2023-03-09 07:26:02,507][23203] Decorrelating experience for 416 frames... [2023-03-09 07:26:02,512][23209] Decorrelating experience for 672 frames... [2023-03-09 07:26:02,555][23087] Decorrelating experience for 608 frames... [2023-03-09 07:26:02,566][23662] Decorrelating experience for 320 frames... [2023-03-09 07:26:02,574][23222] Decorrelating experience for 416 frames... [2023-03-09 07:26:02,574][23202] Decorrelating experience for 480 frames... [2023-03-09 07:26:02,574][23199] Decorrelating experience for 576 frames... [2023-03-09 07:26:02,594][23189] Decorrelating experience for 128 frames... [2023-03-09 07:26:02,626][23097] Decorrelating experience for 544 frames... [2023-03-09 07:26:02,695][23096] Decorrelating experience for 448 frames... [2023-03-09 07:26:02,716][23240] Decorrelating experience for 352 frames... [2023-03-09 07:26:02,771][23098] Decorrelating experience for 384 frames... [2023-03-09 07:26:02,772][23214] Decorrelating experience for 576 frames... [2023-03-09 07:26:02,773][23216] Decorrelating experience for 448 frames... [2023-03-09 07:26:02,777][23225] Decorrelating experience for 352 frames... [2023-03-09 07:26:02,777][23192] Decorrelating experience for 352 frames... [2023-03-09 07:26:02,794][24156] Decorrelating experience for 512 frames... [2023-03-09 07:26:02,874][23095] Decorrelating experience for 736 frames... [2023-03-09 07:26:02,897][23223] Decorrelating experience for 672 frames... [2023-03-09 07:26:02,919][23231] Decorrelating experience for 448 frames... [2023-03-09 07:26:02,958][23222] Decorrelating experience for 448 frames... [2023-03-09 07:26:02,969][23230] Decorrelating experience for 448 frames... [2023-03-09 07:26:02,977][23092] Decorrelating experience for 224 frames... [2023-03-09 07:26:02,978][23238] Decorrelating experience for 384 frames... [2023-03-09 07:26:02,980][23636] Decorrelating experience for 384 frames... [2023-03-09 07:26:02,989][23246] Another process currently holds the lock /tmp/sf2_rolo/doom_002.lockfile, attempt: 1 [2023-03-09 07:26:03,051][23181] Decorrelating experience for 448 frames... [2023-03-09 07:26:03,054][23097] Decorrelating experience for 576 frames... [2023-03-09 07:26:03,076][23087] Decorrelating experience for 640 frames... [2023-03-09 07:26:03,080][23236] Decorrelating experience for 576 frames... [2023-03-09 07:26:03,126][23186] Decorrelating experience for 576 frames... [2023-03-09 07:26:03,149][24539] Decorrelating experience for 352 frames... [2023-03-09 07:26:03,173][23214] Decorrelating experience for 608 frames... [2023-03-09 07:26:03,173][24118] Decorrelating experience for 512 frames... [2023-03-09 07:26:03,176][24089] Decorrelating experience for 224 frames... [2023-03-09 07:26:03,189][23098] Decorrelating experience for 416 frames... [2023-03-09 07:26:03,233][23225] Decorrelating experience for 384 frames... [2023-03-09 07:26:03,281][23197] Decorrelating experience for 192 frames... [2023-03-09 07:26:03,334][23092] Decorrelating experience for 256 frames... [2023-03-09 07:26:03,335][23221] Decorrelating experience for 160 frames... [2023-03-09 07:26:03,348][24156] Decorrelating experience for 544 frames... [2023-03-09 07:26:03,363][23230] Decorrelating experience for 480 frames... [2023-03-09 07:26:03,373][23095] Decorrelating experience for 768 frames... [2023-03-09 07:26:03,380][23177] Decorrelating experience for 416 frames... [2023-03-09 07:26:03,384][23224] Decorrelating experience for 672 frames... [2023-03-09 07:26:03,432][24120] Decorrelating experience for 224 frames... [2023-03-09 07:26:03,480][23202] Decorrelating experience for 512 frames... [2023-03-09 07:26:03,504][23181] Decorrelating experience for 480 frames... [2023-03-09 07:26:03,535][23223] Decorrelating experience for 704 frames... [2023-03-09 07:26:03,536][23099] Decorrelating experience for 416 frames... [2023-03-09 07:26:03,541][24118] Decorrelating experience for 544 frames... [2023-03-09 07:26:03,548][23636] Decorrelating experience for 416 frames... [2023-03-09 07:26:03,570][23236] Decorrelating experience for 608 frames... [2023-03-09 07:26:03,583][23197] Decorrelating experience for 224 frames... [2023-03-09 07:26:03,591][23097] Decorrelating experience for 608 frames... [2023-03-09 07:26:03,633][23211] Decorrelating experience for 256 frames... [2023-03-09 07:26:03,685][23199] Decorrelating experience for 608 frames... [2023-03-09 07:26:03,715][24539] Decorrelating experience for 384 frames... [2023-03-09 07:26:03,727][23098] Decorrelating experience for 448 frames... [2023-03-09 07:26:03,729][23221] Decorrelating experience for 192 frames... [2023-03-09 07:26:03,737][23203] Decorrelating experience for 448 frames... [2023-03-09 07:26:03,757][23174] Another process currently holds the lock /tmp/sf2_rolo/doom_004.lockfile, attempt: 1 [2023-03-09 07:26:03,800][23233] Decorrelating experience for 224 frames... [2023-03-09 07:26:03,815][23177] Decorrelating experience for 448 frames... [2023-03-09 07:26:03,824][23234] Decorrelating experience for 288 frames... [2023-03-09 07:26:03,825][23092] Decorrelating experience for 288 frames... [2023-03-09 07:26:03,861][24156] Decorrelating experience for 576 frames... [2023-03-09 07:26:03,885][24858] Decorrelating experience for 256 frames... [2023-03-09 07:26:03,897][23202] Decorrelating experience for 544 frames... [2023-03-09 07:26:03,920][23099] Decorrelating experience for 448 frames... [2023-03-09 07:26:03,983][23095] Decorrelating experience for 800 frames... [2023-03-09 07:26:04,001][23242] Decorrelating experience for 480 frames... [2023-03-09 07:26:04,008][23211] Decorrelating experience for 288 frames... [2023-03-09 07:26:04,011][23192] Decorrelating experience for 384 frames... [2023-03-09 07:26:04,014][23224] Decorrelating experience for 704 frames... [2023-03-09 07:26:04,023][23223] Decorrelating experience for 736 frames... [2023-03-09 07:26:04,059][22664] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 0.0. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) [2023-03-09 07:26:04,073][23230] Decorrelating experience for 512 frames... [2023-03-09 07:26:04,086][23199] Decorrelating experience for 640 frames... [2023-03-09 07:26:04,106][23225] Decorrelating experience for 416 frames... [2023-03-09 07:26:04,111][23237] Another process currently holds the lock /tmp/sf2_rolo/doom_004.lockfile, attempt: 1 [2023-03-09 07:26:04,157][23662] Decorrelating experience for 352 frames... [2023-03-09 07:26:04,173][24118] Decorrelating experience for 576 frames... [2023-03-09 07:26:04,181][23221] Decorrelating experience for 224 frames... [2023-03-09 07:26:04,198][23250] Decorrelating experience for 384 frames... [2023-03-09 07:26:04,198][23096] Decorrelating experience for 480 frames... [2023-03-09 07:26:04,201][23197] Decorrelating experience for 256 frames... [2023-03-09 07:26:04,211][23234] Decorrelating experience for 320 frames... [2023-03-09 07:26:04,263][23177] Decorrelating experience for 480 frames... [2023-03-09 07:26:04,271][23186] Decorrelating experience for 608 frames... [2023-03-09 07:26:04,291][23170] Decorrelating experience for 800 frames... [2023-03-09 07:26:04,346][23180] Decorrelating experience for 640 frames... [2023-03-09 07:26:04,356][23205] Decorrelating experience for 256 frames... [2023-03-09 07:26:04,395][23231] Decorrelating experience for 480 frames... [2023-03-09 07:26:04,409][24156] Decorrelating experience for 608 frames... [2023-03-09 07:26:04,417][24666] Decorrelating experience for 256 frames... [2023-03-09 07:26:04,449][23092] Decorrelating experience for 320 frames... [2023-03-09 07:26:04,465][23235] Decorrelating experience for 384 frames... [2023-03-09 07:26:04,477][23202] Decorrelating experience for 576 frames... [2023-03-09 07:26:04,514][23233] Decorrelating experience for 256 frames... [2023-03-09 07:26:04,549][23183] Decorrelating experience for 416 frames... [2023-03-09 07:26:04,552][23095] Decorrelating experience for 832 frames... [2023-03-09 07:26:04,582][23485] Decorrelating experience for 416 frames... [2023-03-09 07:26:04,591][23525] Decorrelating experience for 544 frames... [2023-03-09 07:26:04,599][23206] Decorrelating experience for 640 frames... [2023-03-09 07:26:04,635][23205] Decorrelating experience for 288 frames... [2023-03-09 07:26:04,647][23192] Decorrelating experience for 416 frames... [2023-03-09 07:26:04,671][23199] Decorrelating experience for 672 frames... [2023-03-09 07:26:04,673][23186] Decorrelating experience for 640 frames... [2023-03-09 07:26:04,719][24118] Decorrelating experience for 608 frames... [2023-03-09 07:26:04,744][23185] Decorrelating experience for 256 frames... [2023-03-09 07:26:04,750][24666] Decorrelating experience for 288 frames... [2023-03-09 07:26:04,766][23215] Decorrelating experience for 352 frames... [2023-03-09 07:26:04,773][23177] Decorrelating experience for 512 frames... [2023-03-09 07:26:04,791][23176] Decorrelating experience for 608 frames... [2023-03-09 07:26:04,818][23170] Decorrelating experience for 832 frames... [2023-03-09 07:26:04,827][23098] Decorrelating experience for 480 frames... [2023-03-09 07:26:04,862][23234] Decorrelating experience for 352 frames... [2023-03-09 07:26:04,877][23250] Decorrelating experience for 416 frames... [2023-03-09 07:26:04,921][23205] Decorrelating experience for 320 frames... [2023-03-09 07:26:04,952][23181] Decorrelating experience for 512 frames... [2023-03-09 07:26:04,957][23237] Decorrelating experience for 256 frames... [2023-03-09 07:26:04,958][23221] Decorrelating experience for 256 frames... [2023-03-09 07:26:04,969][23089] Decorrelating experience for 416 frames... [2023-03-09 07:26:04,973][23662] Decorrelating experience for 384 frames... [2023-03-09 07:26:05,011][23096] Decorrelating experience for 512 frames... [2023-03-09 07:26:05,019][23190] Decorrelating experience for 352 frames... [2023-03-09 07:26:05,070][23185] Decorrelating experience for 288 frames... [2023-03-09 07:26:05,129][23236] Decorrelating experience for 640 frames... [2023-03-09 07:26:05,144][23197] Decorrelating experience for 288 frames... [2023-03-09 07:26:05,144][23095] Decorrelating experience for 864 frames... [2023-03-09 07:26:05,146][23183] Decorrelating experience for 448 frames... [2023-03-09 07:26:05,154][23817] Decorrelating experience for 352 frames... [2023-03-09 07:26:05,159][23217] Decorrelating experience for 352 frames... [2023-03-09 07:26:05,204][23201] Decorrelating experience for 512 frames... [2023-03-09 07:26:05,207][23199] Decorrelating experience for 704 frames... [2023-03-09 07:26:05,217][23212] Decorrelating experience for 384 frames... [2023-03-09 07:26:05,249][23211] Decorrelating experience for 320 frames... [2023-03-09 07:26:05,321][23205] Decorrelating experience for 352 frames... [2023-03-09 07:26:05,329][23099] Decorrelating experience for 480 frames... [2023-03-09 07:26:05,345][23186] Decorrelating experience for 672 frames... [2023-03-09 07:26:05,360][23087] Decorrelating experience for 672 frames... [2023-03-09 07:26:05,391][23203] Decorrelating experience for 480 frames... [2023-03-09 07:26:05,398][33428] Decorrelating experience for 384 frames... [2023-03-09 07:26:05,400][23204] Decorrelating experience for 352 frames... [2023-03-09 07:26:05,409][23485] Decorrelating experience for 448 frames... [2023-03-09 07:26:05,419][23176] Decorrelating experience for 640 frames... [2023-03-09 07:26:05,437][23237] Decorrelating experience for 288 frames... [2023-03-09 07:26:05,521][24156] Decorrelating experience for 640 frames... [2023-03-09 07:26:05,530][23197] Decorrelating experience for 320 frames... [2023-03-09 07:26:05,543][23212] Decorrelating experience for 416 frames... [2023-03-09 07:26:05,546][23183] Decorrelating experience for 480 frames... [2023-03-09 07:26:05,592][23233] Decorrelating experience for 288 frames... [2023-03-09 07:26:05,595][23215] Decorrelating experience for 384 frames... [2023-03-09 07:26:05,596][23636] Decorrelating experience for 448 frames... [2023-03-09 07:26:05,607][23179] Decorrelating experience for 576 frames... [2023-03-09 07:26:05,608][23226] Decorrelating experience for 384 frames... [2023-03-09 07:26:05,643][23224] Decorrelating experience for 736 frames... [2023-03-09 07:26:05,707][23169] Decorrelating experience for 256 frames... [2023-03-09 07:26:05,729][23237] Decorrelating experience for 320 frames... [2023-03-09 07:26:05,736][23205] Decorrelating experience for 384 frames... [2023-03-09 07:26:05,774][33428] Decorrelating experience for 416 frames... [2023-03-09 07:26:05,786][23202] Decorrelating experience for 608 frames... [2023-03-09 07:26:05,803][23092] Decorrelating experience for 352 frames... [2023-03-09 07:26:05,805][32460] Decorrelating experience for 448 frames... [2023-03-09 07:26:05,833][23199] Decorrelating experience for 736 frames... [2023-03-09 07:26:05,848][23234] Decorrelating experience for 384 frames... [2023-03-09 07:26:05,890][23087] Decorrelating experience for 704 frames... [2023-03-09 07:26:05,908][23817] Decorrelating experience for 384 frames... [2023-03-09 07:26:05,941][23098] Decorrelating experience for 512 frames... [2023-03-09 07:26:05,956][24434] Decorrelating experience for 544 frames... [2023-03-09 07:26:05,973][23186] Decorrelating experience for 704 frames... [2023-03-09 07:26:05,978][23485] Decorrelating experience for 480 frames... [2023-03-09 07:26:05,997][23176] Decorrelating experience for 672 frames... [2023-03-09 07:26:06,005][23170] Decorrelating experience for 864 frames... [2023-03-09 07:26:06,014][23228] Decorrelating experience for 256 frames... [2023-03-09 07:26:06,037][23222] Decorrelating experience for 480 frames... [2023-03-09 07:26:06,115][23205] Decorrelating experience for 416 frames... [2023-03-09 07:26:06,141][23099] Decorrelating experience for 512 frames... [2023-03-09 07:26:06,146][23095] Decorrelating experience for 896 frames... [2023-03-09 07:26:06,154][23249] Decorrelating experience for 544 frames... [2023-03-09 07:26:06,161][23223] Decorrelating experience for 768 frames... [2023-03-09 07:26:06,174][23238] Decorrelating experience for 416 frames... [2023-03-09 07:26:06,179][23190] Decorrelating experience for 384 frames... [2023-03-09 07:26:06,221][23180] Decorrelating experience for 672 frames... [2023-03-09 07:26:06,286][23209] Decorrelating experience for 704 frames... [2023-03-09 07:26:06,289][23228] Decorrelating experience for 288 frames... [2023-03-09 07:26:06,321][23215] Decorrelating experience for 416 frames... [2023-03-09 07:26:06,329][23250] Decorrelating experience for 448 frames... [2023-03-09 07:26:06,351][23221] Decorrelating experience for 288 frames... [2023-03-09 07:26:06,351][24156] Decorrelating experience for 672 frames... [2023-03-09 07:26:06,359][23224] Decorrelating experience for 768 frames... [2023-03-09 07:26:06,368][23244] Decorrelating experience for 416 frames... [2023-03-09 07:26:06,368][33428] Decorrelating experience for 448 frames... [2023-03-09 07:26:06,407][23240] Decorrelating experience for 384 frames... [2023-03-09 07:26:06,516][23099] Decorrelating experience for 544 frames... [2023-03-09 07:26:06,526][23176] Decorrelating experience for 704 frames... [2023-03-09 07:26:06,537][23817] Decorrelating experience for 416 frames... [2023-03-09 07:26:06,550][23222] Decorrelating experience for 512 frames... [2023-03-09 07:26:06,553][23172] Decorrelating experience for 352 frames... [2023-03-09 07:26:06,564][23636] Decorrelating experience for 480 frames... [2023-03-09 07:26:06,572][23235] Decorrelating experience for 416 frames... [2023-03-09 07:26:06,594][23236] Decorrelating experience for 672 frames... [2023-03-09 07:26:06,605][23170] Decorrelating experience for 896 frames... [2023-03-09 07:26:06,620][23186] Decorrelating experience for 736 frames... [2023-03-09 07:26:06,699][23180] Decorrelating experience for 704 frames... [2023-03-09 07:26:06,707][23223] Decorrelating experience for 800 frames... [2023-03-09 07:26:06,750][23181] Decorrelating experience for 544 frames... [2023-03-09 07:26:06,758][23243] Decorrelating experience for 224 frames... [2023-03-09 07:26:06,769][24158] Decorrelating experience for 416 frames... [2023-03-09 07:26:06,774][23250] Decorrelating experience for 480 frames... [2023-03-09 07:26:06,787][23237] Decorrelating experience for 352 frames... [2023-03-09 07:26:06,802][23179] Decorrelating experience for 608 frames... [2023-03-09 07:26:06,807][23183] Decorrelating experience for 512 frames... [2023-03-09 07:26:06,827][23961] Another process currently holds the lock /tmp/sf2_rolo/doom_004.lockfile, attempt: 1 [2023-03-09 07:26:06,856][23234] Decorrelating experience for 416 frames... [2023-03-09 07:26:06,892][23197] Decorrelating experience for 352 frames... [2023-03-09 07:26:06,946][23221] Decorrelating experience for 320 frames... [2023-03-09 07:26:06,957][23214] Decorrelating experience for 640 frames... [2023-03-09 07:26:06,963][23195] Decorrelating experience for 576 frames... [2023-03-09 07:26:06,975][23867] Decorrelating experience for 128 frames... [2023-03-09 07:26:06,982][23215] Decorrelating experience for 448 frames... [2023-03-09 07:26:06,990][23226] Decorrelating experience for 416 frames... [2023-03-09 07:26:07,004][23099] Decorrelating experience for 576 frames... [2023-03-09 07:26:07,045][23202] Decorrelating experience for 640 frames... [2023-03-09 07:26:07,052][24156] Decorrelating experience for 704 frames... [2023-03-09 07:26:07,084][23212] Decorrelating experience for 448 frames... [2023-03-09 07:26:07,154][23237] Decorrelating experience for 384 frames... [2023-03-09 07:26:07,165][23636] Decorrelating experience for 512 frames... [2023-03-09 07:26:07,166][23200] Decorrelating experience for 512 frames... [2023-03-09 07:26:07,170][33428] Decorrelating experience for 480 frames... [2023-03-09 07:26:07,188][23176] Decorrelating experience for 736 frames... [2023-03-09 07:26:07,224][24666] Decorrelating experience for 320 frames... [2023-03-09 07:26:07,229][23228] Decorrelating experience for 320 frames... [2023-03-09 07:26:07,237][23250] Decorrelating experience for 512 frames... [2023-03-09 07:26:07,248][23224] Decorrelating experience for 800 frames... [2023-03-09 07:26:07,271][23623] Decorrelating experience for 640 frames... [2023-03-09 07:26:07,348][23221] Decorrelating experience for 352 frames... [2023-03-09 07:26:07,368][23197] Decorrelating experience for 384 frames... [2023-03-09 07:26:07,369][23247] Decorrelating experience for 448 frames... [2023-03-09 07:26:07,378][23817] Decorrelating experience for 448 frames... [2023-03-09 07:26:07,381][23170] Decorrelating experience for 928 frames... [2023-03-09 07:26:07,407][23192] Decorrelating experience for 448 frames... [2023-03-09 07:26:07,419][23095] Decorrelating experience for 928 frames... [2023-03-09 07:26:07,435][23186] Decorrelating experience for 768 frames... [2023-03-09 07:26:07,438][23217] Decorrelating experience for 384 frames... [2023-03-09 07:26:07,460][23179] Decorrelating experience for 640 frames... [2023-03-09 07:26:07,533][23212] Decorrelating experience for 480 frames... [2023-03-09 07:26:07,582][23237] Decorrelating experience for 416 frames... [2023-03-09 07:26:07,611][23199] Decorrelating experience for 768 frames... [2023-03-09 07:26:07,613][23634] Decorrelating experience for 448 frames... [2023-03-09 07:26:07,646][23174] Decorrelating experience for 160 frames... [2023-03-09 07:26:07,652][23200] Decorrelating experience for 544 frames... [2023-03-09 07:26:07,653][23096] Decorrelating experience for 544 frames... [2023-03-09 07:26:07,655][23248] Decorrelating experience for 448 frames... [2023-03-09 07:26:07,655][23196] Decorrelating experience for 512 frames... [2023-03-09 07:26:07,690][23250] Decorrelating experience for 544 frames... [2023-03-09 07:26:07,714][32460] Decorrelating experience for 480 frames... [2023-03-09 07:26:07,814][23094] Decorrelating experience for 512 frames... [2023-03-09 07:26:07,837][23229] Decorrelating experience for 384 frames... [2023-03-09 07:26:07,837][23236] Decorrelating experience for 704 frames... [2023-03-09 07:26:07,858][23206] Decorrelating experience for 672 frames... [2023-03-09 07:26:07,859][24666] Decorrelating experience for 352 frames... [2023-03-09 07:26:07,859][24118] Decorrelating experience for 640 frames... [2023-03-09 07:26:07,859][23201] Decorrelating experience for 544 frames... [2023-03-09 07:26:07,875][23817] Decorrelating experience for 480 frames... [2023-03-09 07:26:07,896][24539] Decorrelating experience for 416 frames... [2023-03-09 07:26:08,019][23235] Decorrelating experience for 448 frames... [2023-03-09 07:26:08,022][23171] Decorrelating experience for 384 frames... [2023-03-09 07:26:08,030][23243] Decorrelating experience for 256 frames... [2023-03-09 07:26:08,052][23636] Decorrelating experience for 544 frames... [2023-03-09 07:26:08,060][23525] Decorrelating experience for 576 frames... [2023-03-09 07:26:08,061][23249] Decorrelating experience for 576 frames... [2023-03-09 07:26:08,066][23867] Decorrelating experience for 160 frames... [2023-03-09 07:26:08,069][23172] Decorrelating experience for 384 frames... [2023-03-09 07:26:08,081][23118] Decorrelating experience for 512 frames... [2023-03-09 07:26:08,107][23248] Decorrelating experience for 480 frames... [2023-03-09 07:26:08,201][23197] Decorrelating experience for 416 frames... [2023-03-09 07:26:08,216][23088] Decorrelating experience for 512 frames... [2023-03-09 07:26:08,296][23196] Decorrelating experience for 544 frames... [2023-03-09 07:26:08,313][23181] Decorrelating experience for 576 frames... [2023-03-09 07:26:08,313][23174] Decorrelating experience for 192 frames... [2023-03-09 07:26:08,315][23180] Decorrelating experience for 736 frames... [2023-03-09 07:26:08,315][23229] Decorrelating experience for 416 frames... [2023-03-09 07:26:08,315][24666] Decorrelating experience for 384 frames... [2023-03-09 07:26:08,315][23242] Decorrelating experience for 512 frames... [2023-03-09 07:26:08,330][24539] Decorrelating experience for 448 frames... [2023-03-09 07:26:08,388][23176] Decorrelating experience for 768 frames... [2023-03-09 07:26:08,405][23243] Decorrelating experience for 288 frames... [2023-03-09 07:26:08,483][23212] Decorrelating experience for 512 frames... [2023-03-09 07:26:08,513][23249] Decorrelating experience for 608 frames... [2023-03-09 07:26:08,514][23525] Decorrelating experience for 608 frames... [2023-03-09 07:26:08,515][23867] Decorrelating experience for 192 frames... [2023-03-09 07:26:08,539][23217] Decorrelating experience for 416 frames... [2023-03-09 07:26:08,539][23634] Decorrelating experience for 480 frames... [2023-03-09 07:26:08,591][23200] Decorrelating experience for 576 frames... [2023-03-09 07:26:08,591][23219] Decorrelating experience for 608 frames... [2023-03-09 07:26:08,599][23236] Decorrelating experience for 736 frames... [2023-03-09 07:26:08,650][23229] Decorrelating experience for 448 frames... [2023-03-09 07:26:08,664][23174] Decorrelating experience for 224 frames... [2023-03-09 07:26:08,712][23103] Decorrelating experience for 288 frames... [2023-03-09 07:26:08,727][23171] Decorrelating experience for 416 frames... [2023-03-09 07:26:08,745][24434] Decorrelating experience for 576 frames... [2023-03-09 07:26:08,746][23170] Decorrelating experience for 960 frames... [2023-03-09 07:26:08,747][23197] Decorrelating experience for 448 frames... [2023-03-09 07:26:08,789][23199] Decorrelating experience for 800 frames... [2023-03-09 07:26:08,818][23190] Decorrelating experience for 416 frames... [2023-03-09 07:26:08,859][23181] Decorrelating experience for 608 frames... [2023-03-09 07:26:08,862][23238] Decorrelating experience for 448 frames... [2023-03-09 07:26:08,927][24539] Decorrelating experience for 480 frames... [2023-03-09 07:26:08,944][23194] Decorrelating experience for 384 frames... [2023-03-09 07:26:08,945][23525] Decorrelating experience for 640 frames... [2023-03-09 07:26:08,950][23191] Decorrelating experience for 224 frames... [2023-03-09 07:26:08,950][23636] Decorrelating experience for 576 frames... [2023-03-09 07:26:09,018][23176] Decorrelating experience for 800 frames... [2023-03-09 07:26:09,027][23174] Decorrelating experience for 256 frames... [2023-03-09 07:26:09,045][23212] Decorrelating experience for 544 frames... [2023-03-09 07:26:09,051][23243] Decorrelating experience for 320 frames... [2023-03-09 07:26:09,055][23623] Decorrelating experience for 672 frames... [2023-03-09 07:26:09,059][22664] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 0.0. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) [2023-03-09 07:26:09,152][23249] Decorrelating experience for 640 frames... [2023-03-09 07:26:09,153][23867] Decorrelating experience for 224 frames... [2023-03-09 07:26:09,161][23202] Decorrelating experience for 672 frames... [2023-03-09 07:26:09,162][24793] Decorrelating experience for 640 frames... [2023-03-09 07:26:09,162][23094] Decorrelating experience for 544 frames... [2023-03-09 07:26:09,229][23171] Decorrelating experience for 448 frames... [2023-03-09 07:26:09,245][23638] Decorrelating experience for 640 frames... [2023-03-09 07:26:09,246][24120] Decorrelating experience for 256 frames... [2023-03-09 07:26:09,309][23224] Decorrelating experience for 832 frames... [2023-03-09 07:26:09,312][24666] Decorrelating experience for 416 frames... [2023-03-09 07:26:09,345][23200] Decorrelating experience for 608 frames... [2023-03-09 07:26:09,356][23637] Decorrelating experience for 352 frames... [2023-03-09 07:26:09,366][23228] Decorrelating experience for 352 frames... [2023-03-09 07:26:09,367][23172] Decorrelating experience for 416 frames... [2023-03-09 07:26:09,367][23088] Decorrelating experience for 544 frames... [2023-03-09 07:26:09,446][23203] Decorrelating experience for 512 frames... [2023-03-09 07:26:09,449][23170] Decorrelating experience for 992 frames... [2023-03-09 07:26:09,498][23201] Decorrelating experience for 576 frames... [2023-03-09 07:26:09,503][23817] Decorrelating experience for 512 frames... [2023-03-09 07:26:09,504][23238] Decorrelating experience for 480 frames... [2023-03-09 07:26:09,544][24121] Decorrelating experience for 256 frames... [2023-03-09 07:26:09,556][23242] Decorrelating experience for 544 frames... [2023-03-09 07:26:09,564][23197] Decorrelating experience for 480 frames... [2023-03-09 07:26:09,564][23195] Decorrelating experience for 608 frames... [2023-03-09 07:26:09,572][23206] Decorrelating experience for 704 frames... [2023-03-09 07:26:09,642][23188] Decorrelating experience for 608 frames... [2023-03-09 07:26:09,662][23237] Decorrelating experience for 448 frames... [2023-03-09 07:26:09,693][24118] Decorrelating experience for 672 frames... [2023-03-09 07:26:09,730][23212] Decorrelating experience for 576 frames... [2023-03-09 07:26:09,753][23623] Decorrelating experience for 704 frames... [2023-03-09 07:26:09,767][24434] Decorrelating experience for 608 frames... [2023-03-09 07:26:09,776][23174] Decorrelating experience for 288 frames... [2023-03-09 07:26:09,778][23103] Decorrelating experience for 320 frames... [2023-03-09 07:26:09,781][33428] Decorrelating experience for 512 frames... [2023-03-09 07:26:09,807][23171] Decorrelating experience for 480 frames... [2023-03-09 07:26:09,830][23235] Decorrelating experience for 480 frames... [2023-03-09 07:26:09,841][23219] Decorrelating experience for 640 frames... [2023-03-09 07:26:09,845][22664] Heartbeat connected on RolloutWorker_w6 [2023-03-09 07:26:09,875][23180] Decorrelating experience for 768 frames... [2023-03-09 07:26:09,964][23202] Decorrelating experience for 704 frames... [2023-03-09 07:26:09,964][23485] Decorrelating experience for 512 frames... [2023-03-09 07:26:09,965][23636] Decorrelating experience for 608 frames... [2023-03-09 07:26:09,967][23239] Decorrelating experience for 192 frames... [2023-03-09 07:26:09,975][23638] Decorrelating experience for 672 frames... [2023-03-09 07:26:09,977][23196] Decorrelating experience for 576 frames... [2023-03-09 07:26:10,001][23200] Decorrelating experience for 640 frames... [2023-03-09 07:26:10,032][24666] Decorrelating experience for 448 frames... [2023-03-09 07:26:10,045][23099] Decorrelating experience for 608 frames... [2023-03-09 07:26:10,066][23118] Decorrelating experience for 544 frames... [2023-03-09 07:26:10,158][23201] Decorrelating experience for 608 frames... [2023-03-09 07:26:10,159][23218] Decorrelating experience for 704 frames... [2023-03-09 07:26:10,172][23094] Decorrelating experience for 576 frames... [2023-03-09 07:26:10,187][23249] Decorrelating experience for 672 frames... [2023-03-09 07:26:10,226][23192] Decorrelating experience for 480 frames... [2023-03-09 07:26:10,232][23172] Decorrelating experience for 448 frames... [2023-03-09 07:26:10,252][23091] Decorrelating experience for 384 frames... [2023-03-09 07:26:10,255][24121] Decorrelating experience for 288 frames... [2023-03-09 07:26:10,256][23087] Decorrelating experience for 736 frames... [2023-03-09 07:26:10,265][23242] Decorrelating experience for 576 frames... [2023-03-09 07:26:10,347][24858] Decorrelating experience for 288 frames... [2023-03-09 07:26:10,370][23174] Decorrelating experience for 320 frames... [2023-03-09 07:26:10,376][23246] Decorrelating experience for 256 frames... [2023-03-09 07:26:10,426][23200] Decorrelating experience for 672 frames... [2023-03-09 07:26:10,443][23485] Decorrelating experience for 544 frames... [2023-03-09 07:26:10,453][23195] Decorrelating experience for 640 frames... [2023-03-09 07:26:10,456][24539] Decorrelating experience for 512 frames... [2023-03-09 07:26:10,457][23635] Decorrelating experience for 288 frames... [2023-03-09 07:26:10,457][23623] Decorrelating experience for 736 frames... [2023-03-09 07:26:10,462][23180] Decorrelating experience for 800 frames... [2023-03-09 07:26:10,556][23188] Decorrelating experience for 640 frames... [2023-03-09 07:26:10,575][23089] Decorrelating experience for 448 frames... [2023-03-09 07:26:10,578][23638] Decorrelating experience for 704 frames... [2023-03-09 07:26:10,609][23189] Decorrelating experience for 160 frames... [2023-03-09 07:26:10,624][23823] Another process currently holds the lock /tmp/sf2_rolo/doom_002.lockfile, attempt: 1 [2023-03-09 07:26:10,645][24858] Decorrelating experience for 320 frames... [2023-03-09 07:26:10,646][24666] Decorrelating experience for 480 frames... [2023-03-09 07:26:10,661][23177] Decorrelating experience for 544 frames... [2023-03-09 07:26:10,661][23226] Decorrelating experience for 448 frames... [2023-03-09 07:26:10,664][23218] Decorrelating experience for 736 frames... [2023-03-09 07:26:10,706][23199] Decorrelating experience for 832 frames... [2023-03-09 07:26:10,755][23183] Decorrelating experience for 544 frames... [2023-03-09 07:26:10,766][33428] Decorrelating experience for 544 frames... [2023-03-09 07:26:10,800][23185] Decorrelating experience for 320 frames... [2023-03-09 07:26:10,835][23196] Decorrelating experience for 608 frames... [2023-03-09 07:26:10,841][23211] Decorrelating experience for 352 frames... [2023-03-09 07:26:10,862][24434] Decorrelating experience for 640 frames... [2023-03-09 07:26:10,864][24089] Decorrelating experience for 256 frames... [2023-03-09 07:26:10,866][23250] Decorrelating experience for 576 frames... [2023-03-09 07:26:10,907][23242] Decorrelating experience for 608 frames... [2023-03-09 07:26:10,918][23224] Decorrelating experience for 864 frames... [2023-03-09 07:26:10,923][23208] Another process currently holds the lock /tmp/sf2_rolo/doom_002.lockfile, attempt: 2 [2023-03-09 07:26:10,944][23103] Decorrelating experience for 352 frames... [2023-03-09 07:26:10,949][24156] Decorrelating experience for 736 frames... [2023-03-09 07:26:11,029][23637] Decorrelating experience for 384 frames... [2023-03-09 07:26:11,035][23638] Decorrelating experience for 736 frames... [2023-03-09 07:26:11,056][23195] Decorrelating experience for 672 frames... [2023-03-09 07:26:11,066][23634] Decorrelating experience for 512 frames... [2023-03-09 07:26:11,078][23485] Decorrelating experience for 576 frames... [2023-03-09 07:26:11,092][23091] Decorrelating experience for 416 frames... [2023-03-09 07:26:11,112][24858] Decorrelating experience for 352 frames... [2023-03-09 07:26:11,118][23087] Decorrelating experience for 768 frames... [2023-03-09 07:26:11,135][23191] Decorrelating experience for 256 frames... [2023-03-09 07:26:11,138][23867] Decorrelating experience for 256 frames... [2023-03-09 07:26:11,226][23314] Decorrelating experience for 64 frames... [2023-03-09 07:26:11,227][23211] Decorrelating experience for 384 frames... [2023-03-09 07:26:11,257][23204] Decorrelating experience for 384 frames... [2023-03-09 07:26:11,270][23657] Decorrelating experience for 256 frames... [2023-03-09 07:26:11,271][32460] Decorrelating experience for 512 frames... [2023-03-09 07:26:11,301][24089] Decorrelating experience for 288 frames... [2023-03-09 07:26:11,321][23242] Decorrelating experience for 640 frames... [2023-03-09 07:26:11,324][23190] Decorrelating experience for 448 frames... [2023-03-09 07:26:11,333][23194] Decorrelating experience for 416 frames... [2023-03-09 07:26:11,356][23181] Decorrelating experience for 640 frames... [2023-03-09 07:26:11,409][23182] Decorrelating experience for 448 frames... [2023-03-09 07:26:11,455][23185] Decorrelating experience for 352 frames... [2023-03-09 07:26:11,485][23223] Decorrelating experience for 832 frames... [2023-03-09 07:26:11,488][23091] Decorrelating experience for 448 frames... [2023-03-09 07:26:11,506][23961] Decorrelating experience for 192 frames... [2023-03-09 07:26:11,510][23637] Decorrelating experience for 416 frames... [2023-03-09 07:26:11,523][23250] Decorrelating experience for 608 frames... [2023-03-09 07:26:11,525][23207] Another process currently holds the lock /tmp/sf2_rolo/doom_002.lockfile, attempt: 1 [2023-03-09 07:26:11,532][24156] Decorrelating experience for 768 frames... [2023-03-09 07:26:11,538][24118] Decorrelating experience for 704 frames... [2023-03-09 07:26:11,540][23228] Decorrelating experience for 384 frames... [2023-03-09 07:26:11,605][23866] Decorrelating experience for 512 frames... [2023-03-09 07:26:11,644][32460] Decorrelating experience for 544 frames... [2023-03-09 07:26:11,679][23203] Decorrelating experience for 544 frames... [2023-03-09 07:26:11,682][23088] Decorrelating experience for 576 frames... [2023-03-09 07:26:11,690][24121] Decorrelating experience for 320 frames... [2023-03-09 07:26:11,707][23211] Decorrelating experience for 416 frames... [2023-03-09 07:26:11,725][23243] Decorrelating experience for 352 frames... [2023-03-09 07:26:11,727][23623] Decorrelating experience for 768 frames... [2023-03-09 07:26:11,736][23204] Decorrelating experience for 416 frames... [2023-03-09 07:26:11,808][23205] Decorrelating experience for 448 frames... [2023-03-09 07:26:11,837][23209] Decorrelating experience for 736 frames... [2023-03-09 07:26:11,874][23191] Decorrelating experience for 288 frames... [2023-03-09 07:26:11,875][23185] Decorrelating experience for 384 frames... [2023-03-09 07:26:11,884][23171] Decorrelating experience for 512 frames... [2023-03-09 07:26:11,892][23222] Decorrelating experience for 544 frames... [2023-03-09 07:26:11,918][23202] Decorrelating experience for 736 frames... [2023-03-09 07:26:11,939][24120] Decorrelating experience for 288 frames... [2023-03-09 07:26:11,975][23239] Decorrelating experience for 224 frames... [2023-03-09 07:26:12,006][23221] Decorrelating experience for 384 frames... [2023-03-09 07:26:12,082][23249] Decorrelating experience for 704 frames... [2023-03-09 07:26:12,082][23226] Decorrelating experience for 480 frames... [2023-03-09 07:26:12,086][23190] Decorrelating experience for 480 frames... [2023-03-09 07:26:12,088][23178] Decorrelating experience for 192 frames... [2023-03-09 07:26:12,106][23214] Decorrelating experience for 672 frames... [2023-03-09 07:26:12,107][23177] Decorrelating experience for 576 frames... [2023-03-09 07:26:12,138][24118] Decorrelating experience for 736 frames... [2023-03-09 07:26:12,184][23179] Decorrelating experience for 672 frames... [2023-03-09 07:26:12,188][23192] Decorrelating experience for 512 frames... [2023-03-09 07:26:12,196][23185] Decorrelating experience for 416 frames... [2023-03-09 07:26:12,275][23188] Decorrelating experience for 672 frames... [2023-03-09 07:26:12,284][23248] Decorrelating experience for 512 frames... [2023-03-09 07:26:12,285][23204] Decorrelating experience for 448 frames... [2023-03-09 07:26:12,291][23194] Decorrelating experience for 448 frames... [2023-03-09 07:26:12,293][23636] Decorrelating experience for 640 frames... [2023-03-09 07:26:12,333][24539] Decorrelating experience for 544 frames... [2023-03-09 07:26:12,340][23243] Decorrelating experience for 384 frames... [2023-03-09 07:26:12,383][32460] Decorrelating experience for 576 frames... [2023-03-09 07:26:12,441][23228] Decorrelating experience for 416 frames... [2023-03-09 07:26:12,465][24158] Decorrelating experience for 448 frames... [2023-03-09 07:26:12,471][23245] Decorrelating experience for 352 frames... [2023-03-09 07:26:12,480][23230] Decorrelating experience for 544 frames... [2023-03-09 07:26:12,484][23089] Decorrelating experience for 480 frames... [2023-03-09 07:26:12,552][23206] Decorrelating experience for 736 frames... [2023-03-09 07:26:12,552][23817] Decorrelating experience for 544 frames... [2023-03-09 07:26:12,555][23219] Decorrelating experience for 672 frames... [2023-03-09 07:26:12,565][23213] Decorrelating experience for 576 frames... [2023-03-09 07:26:12,596][24118] Decorrelating experience for 768 frames... [2023-03-09 07:26:12,622][23249] Decorrelating experience for 736 frames... [2023-03-09 07:26:12,647][23242] Decorrelating experience for 672 frames... [2023-03-09 07:26:12,668][24157] Decorrelating experience for 640 frames... [2023-03-09 07:26:12,669][23179] Decorrelating experience for 704 frames... [2023-03-09 07:26:12,683][23199] Decorrelating experience for 864 frames... [2023-03-09 07:26:12,739][23204] Decorrelating experience for 480 frames... [2023-03-09 07:26:12,748][23214] Decorrelating experience for 704 frames... [2023-03-09 07:26:12,750][23190] Decorrelating experience for 512 frames... [2023-03-09 07:26:12,756][24434] Decorrelating experience for 672 frames... [2023-03-09 07:26:12,811][23188] Decorrelating experience for 704 frames... [2023-03-09 07:26:12,836][23866] Decorrelating experience for 544 frames... [2023-03-09 07:26:12,856][24666] Decorrelating experience for 512 frames... [2023-03-09 07:26:12,877][23636] Decorrelating experience for 672 frames... [2023-03-09 07:26:12,878][23096] Decorrelating experience for 576 frames... [2023-03-09 07:26:12,947][23817] Decorrelating experience for 576 frames... [2023-03-09 07:26:12,949][23089] Decorrelating experience for 512 frames... [2023-03-09 07:26:12,974][23228] Decorrelating experience for 448 frames... [2023-03-09 07:26:12,995][23314] Decorrelating experience for 96 frames... [2023-03-09 07:26:13,021][23212] Decorrelating experience for 608 frames... [2023-03-09 07:26:13,038][23221] Decorrelating experience for 416 frames... [2023-03-09 07:26:13,052][23091] Decorrelating experience for 480 frames... [2023-03-09 07:26:13,070][24158] Decorrelating experience for 480 frames... [2023-03-09 07:26:13,118][23179] Decorrelating experience for 736 frames... [2023-03-09 07:26:13,134][24539] Decorrelating experience for 576 frames... [2023-03-09 07:26:13,141][24157] Decorrelating experience for 672 frames... [2023-03-09 07:26:13,150][23195] Decorrelating experience for 704 frames... [2023-03-09 07:26:13,159][23248] Decorrelating experience for 544 frames... [2023-03-09 07:26:13,179][23240] Decorrelating experience for 416 frames... [2023-03-09 07:26:13,207][23171] Decorrelating experience for 544 frames... [2023-03-09 07:26:13,221][23244] Decorrelating experience for 448 frames... [2023-03-09 07:26:13,234][23185] Decorrelating experience for 448 frames... [2023-03-09 07:26:13,286][23211] Decorrelating experience for 448 frames... [2023-03-09 07:26:13,354][23199] Decorrelating experience for 896 frames... [2023-03-09 07:26:13,354][24666] Decorrelating experience for 544 frames... [2023-03-09 07:26:13,354][23242] Decorrelating experience for 704 frames... [2023-03-09 07:26:13,408][23204] Decorrelating experience for 512 frames... [2023-03-09 07:26:13,410][23218] Decorrelating experience for 768 frames... [2023-03-09 07:26:13,421][23098] Decorrelating experience for 544 frames... [2023-03-09 07:26:13,423][24793] Decorrelating experience for 672 frames... [2023-03-09 07:26:13,433][23188] Decorrelating experience for 736 frames... [2023-03-09 07:26:13,472][23118] Decorrelating experience for 576 frames... [2023-03-09 07:26:13,479][23238] Decorrelating experience for 512 frames... [2023-03-09 07:26:13,552][23817] Decorrelating experience for 608 frames... [2023-03-09 07:26:13,553][23228] Decorrelating experience for 480 frames... [2023-03-09 07:26:13,596][23214] Decorrelating experience for 736 frames... [2023-03-09 07:26:13,606][23194] Decorrelating experience for 480 frames... [2023-03-09 07:26:13,624][23234] Decorrelating experience for 448 frames... [2023-03-09 07:26:13,627][23091] Decorrelating experience for 512 frames... [2023-03-09 07:26:13,665][23219] Decorrelating experience for 704 frames... [2023-03-09 07:26:13,668][23224] Decorrelating experience for 896 frames... [2023-03-09 07:26:13,672][23205] Decorrelating experience for 480 frames... [2023-03-09 07:26:13,738][23171] Decorrelating experience for 576 frames... [2023-03-09 07:26:13,752][24121] Decorrelating experience for 352 frames... [2023-03-09 07:26:13,773][23240] Decorrelating experience for 448 frames... [2023-03-09 07:26:13,797][23088] Decorrelating experience for 608 frames... [2023-03-09 07:26:13,814][24089] Decorrelating experience for 320 frames... [2023-03-09 07:26:13,831][23235] Decorrelating experience for 512 frames... [2023-03-09 07:26:13,845][23182] Decorrelating experience for 480 frames... [2023-03-09 07:26:13,864][23178] Decorrelating experience for 224 frames... [2023-03-09 07:26:13,867][23637] Decorrelating experience for 448 frames... [2023-03-09 07:26:13,879][23211] Decorrelating experience for 480 frames... [2023-03-09 07:26:13,926][23176] Decorrelating experience for 832 frames... [2023-03-09 07:26:13,950][23242] Decorrelating experience for 736 frames... [2023-03-09 07:26:13,977][23234] Decorrelating experience for 480 frames... [2023-03-09 07:26:14,012][23634] Decorrelating experience for 544 frames... [2023-03-09 07:26:14,031][23179] Decorrelating experience for 768 frames... [2023-03-09 07:26:14,058][22664] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 41.2. Samples: 1856. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) [2023-03-09 07:26:14,059][22664] Avg episode reward: [(0, '3.006')] [2023-03-09 07:26:14,072][23218] Decorrelating experience for 800 frames... [2023-03-09 07:26:14,073][23248] Decorrelating experience for 576 frames... [2023-03-09 07:26:14,074][23485] Decorrelating experience for 608 frames... [2023-03-09 07:26:14,078][23638] Decorrelating experience for 768 frames... [2023-03-09 07:26:14,085][23199] Decorrelating experience for 928 frames... [2023-03-09 07:26:14,117][24121] Decorrelating experience for 384 frames... [2023-03-09 07:26:14,137][23171] Decorrelating experience for 608 frames... [2023-03-09 07:26:14,177][24157] Decorrelating experience for 704 frames... [2023-03-09 07:26:14,222][23209] Decorrelating experience for 768 frames... [2023-03-09 07:26:14,281][24156] Decorrelating experience for 800 frames... [2023-03-09 07:26:14,282][23091] Decorrelating experience for 544 frames... [2023-03-09 07:26:14,283][23214] Decorrelating experience for 768 frames... [2023-03-09 07:26:14,286][24089] Decorrelating experience for 352 frames... [2023-03-09 07:26:14,294][23232] Decorrelating experience for 384 frames... [2023-03-09 07:26:14,335][23088] Decorrelating experience for 640 frames... [2023-03-09 07:26:14,336][23118] Decorrelating experience for 608 frames... [2023-03-09 07:26:14,346][23246] Decorrelating experience for 288 frames... [2023-03-09 07:26:14,425][33428] Decorrelating experience for 576 frames... [2023-03-09 07:26:14,462][24793] Decorrelating experience for 704 frames... [2023-03-09 07:26:14,468][23177] Decorrelating experience for 608 frames... [2023-03-09 07:26:14,487][24539] Decorrelating experience for 608 frames... [2023-03-09 07:26:14,495][23099] Decorrelating experience for 640 frames... [2023-03-09 07:26:14,497][23866] Decorrelating experience for 576 frames... [2023-03-09 07:26:14,527][23176] Decorrelating experience for 864 frames... [2023-03-09 07:26:14,540][23240] Decorrelating experience for 480 frames... [2023-03-09 07:26:14,543][23096] Decorrelating experience for 608 frames... [2023-03-09 07:26:14,563][23225] Decorrelating experience for 448 frames... [2023-03-09 07:26:14,631][23095] Decorrelating experience for 960 frames... [2023-03-09 07:26:14,651][23224] Decorrelating experience for 928 frames... [2023-03-09 07:26:14,674][23172] Decorrelating experience for 480 frames... [2023-03-09 07:26:14,679][23094] Decorrelating experience for 608 frames... [2023-03-09 07:26:14,687][24157] Decorrelating experience for 736 frames... [2023-03-09 07:26:14,695][23211] Decorrelating experience for 512 frames... [2023-03-09 07:26:14,720][23634] Decorrelating experience for 576 frames... [2023-03-09 07:26:14,735][23230] Decorrelating experience for 576 frames... [2023-03-09 07:26:14,736][23199] Decorrelating experience for 960 frames... [2023-03-09 07:26:14,794][23241] Decorrelating experience for 384 frames... [2023-03-09 07:26:14,829][24156] Decorrelating experience for 832 frames... [2023-03-09 07:26:14,840][23212] Decorrelating experience for 640 frames... [2023-03-09 07:26:14,875][23817] Decorrelating experience for 640 frames... [2023-03-09 07:26:14,882][33428] Decorrelating experience for 608 frames... [2023-03-09 07:26:14,899][23218] Decorrelating experience for 832 frames... [2023-03-09 07:26:14,906][23657] Decorrelating experience for 288 frames... [2023-03-09 07:26:14,919][23229] Decorrelating experience for 480 frames... [2023-03-09 07:26:14,925][23189] Decorrelating experience for 192 frames... [2023-03-09 07:26:14,933][24434] Decorrelating experience for 704 frames... [2023-03-09 07:26:15,051][23097] Decorrelating experience for 640 frames... [2023-03-09 07:26:15,053][23179] Decorrelating experience for 800 frames... [2023-03-09 07:26:15,056][23204] Decorrelating experience for 544 frames... [2023-03-09 07:26:15,095][23623] Decorrelating experience for 800 frames... [2023-03-09 07:26:15,106][23176] Decorrelating experience for 896 frames... [2023-03-09 07:26:15,107][23865] Decorrelating experience for 544 frames... [2023-03-09 07:26:15,110][23203] Decorrelating experience for 576 frames... [2023-03-09 07:26:15,116][23638] Decorrelating experience for 800 frames... [2023-03-09 07:26:15,120][23209] Decorrelating experience for 800 frames... [2023-03-09 07:26:15,127][23232] Decorrelating experience for 416 frames... [2023-03-09 07:26:15,237][23089] Decorrelating experience for 544 frames... [2023-03-09 07:26:15,251][23185] Decorrelating experience for 480 frames... [2023-03-09 07:26:15,256][23171] Decorrelating experience for 640 frames... [2023-03-09 07:26:15,284][23314] Decorrelating experience for 128 frames... [2023-03-09 07:26:15,311][23224] Decorrelating experience for 960 frames... [2023-03-09 07:26:15,324][32460] Decorrelating experience for 608 frames... [2023-03-09 07:26:15,324][23239] Decorrelating experience for 256 frames... [2023-03-09 07:26:15,325][23188] Decorrelating experience for 768 frames... [2023-03-09 07:26:15,330][23088] Decorrelating experience for 672 frames... [2023-03-09 07:26:15,333][23636] Decorrelating experience for 704 frames... [2023-03-09 07:26:15,425][23093] Decorrelating experience for 544 frames... [2023-03-09 07:26:15,439][23091] Decorrelating experience for 576 frames... [2023-03-09 07:26:15,478][23206] Decorrelating experience for 768 frames... [2023-03-09 07:26:15,517][23244] Decorrelating experience for 480 frames... [2023-03-09 07:26:15,543][24158] Decorrelating experience for 512 frames... [2023-03-09 07:26:15,545][23182] Decorrelating experience for 512 frames... [2023-03-09 07:26:15,545][23314] Decorrelating experience for 160 frames... [2023-03-09 07:26:15,555][23183] Decorrelating experience for 576 frames... [2023-03-09 07:26:15,556][23191] Decorrelating experience for 320 frames... [2023-03-09 07:26:15,558][23240] Decorrelating experience for 512 frames... [2023-03-09 07:26:15,609][23193] Decorrelating experience for 640 frames... [2023-03-09 07:26:15,630][23095] Decorrelating experience for 992 frames... [2023-03-09 07:26:15,665][24858] Decorrelating experience for 384 frames... [2023-03-09 07:26:15,704][23866] Decorrelating experience for 608 frames... [2023-03-09 07:26:15,733][23192] Decorrelating experience for 544 frames... [2023-03-09 07:26:15,741][23089] Decorrelating experience for 576 frames... [2023-03-09 07:26:15,744][23657] Decorrelating experience for 320 frames... [2023-03-09 07:26:15,756][23637] Decorrelating experience for 480 frames... [2023-03-09 07:26:15,773][23234] Decorrelating experience for 512 frames... [2023-03-09 07:26:15,773][23230] Decorrelating experience for 608 frames... [2023-03-09 07:26:15,795][24025] Decorrelating experience for 352 frames... [2023-03-09 07:26:15,839][23171] Decorrelating experience for 672 frames... [2023-03-09 07:26:15,892][23221] Decorrelating experience for 448 frames... [2023-03-09 07:26:15,896][24157] Decorrelating experience for 768 frames... [2023-03-09 07:26:15,939][23634] Decorrelating experience for 608 frames... [2023-03-09 07:26:15,940][23228] Decorrelating experience for 512 frames... [2023-03-09 07:26:15,943][23248] Decorrelating experience for 608 frames... [2023-03-09 07:26:15,949][23188] Decorrelating experience for 800 frames... [2023-03-09 07:26:15,959][23638] Decorrelating experience for 832 frames... [2023-03-09 07:26:15,967][32460] Decorrelating experience for 640 frames... [2023-03-09 07:26:15,981][23214] Decorrelating experience for 800 frames... [2023-03-09 07:26:16,002][22664] Heartbeat connected on RolloutWorker_w26 [2023-03-09 07:26:16,048][23091] Decorrelating experience for 608 frames... [2023-03-09 07:26:16,088][23194] Decorrelating experience for 512 frames... [2023-03-09 07:26:16,089][23176] Decorrelating experience for 928 frames... [2023-03-09 07:26:16,139][24120] Decorrelating experience for 320 frames... [2023-03-09 07:26:16,154][23199] Decorrelating experience for 992 frames... [2023-03-09 07:26:16,155][23314] Decorrelating experience for 192 frames... [2023-03-09 07:26:16,158][23244] Decorrelating experience for 512 frames... [2023-03-09 07:26:16,174][23096] Decorrelating experience for 640 frames... [2023-03-09 07:26:16,212][23196] Decorrelating experience for 640 frames... [2023-03-09 07:26:16,230][23241] Decorrelating experience for 416 frames... [2023-03-09 07:26:16,245][23089] Decorrelating experience for 608 frames... [2023-03-09 07:26:16,280][23171] Decorrelating experience for 704 frames... [2023-03-09 07:26:16,306][23232] Decorrelating experience for 448 frames... [2023-03-09 07:26:16,346][24858] Decorrelating experience for 416 frames... [2023-03-09 07:26:16,366][23657] Decorrelating experience for 352 frames... [2023-03-09 07:26:16,368][23103] Decorrelating experience for 384 frames... [2023-03-09 07:26:16,371][23441] Decorrelating experience for 256 frames... [2023-03-09 07:26:16,373][23637] Decorrelating experience for 512 frames... [2023-03-09 07:26:16,396][23243] Decorrelating experience for 416 frames... [2023-03-09 07:26:16,471][23237] Decorrelating experience for 480 frames... [2023-03-09 07:26:16,520][23188] Decorrelating experience for 832 frames... [2023-03-09 07:26:16,520][23211] Decorrelating experience for 544 frames... [2023-03-09 07:26:16,527][22664] Heartbeat connected on RolloutWorker_w46 [2023-03-09 07:26:16,536][23193] Decorrelating experience for 672 frames... [2023-03-09 07:26:16,573][23867] Decorrelating experience for 288 frames... [2023-03-09 07:26:16,580][23227] Decorrelating experience for 352 frames... [2023-03-09 07:26:16,580][23206] Decorrelating experience for 800 frames... [2023-03-09 07:26:16,581][23865] Decorrelating experience for 576 frames... [2023-03-09 07:26:16,584][23242] Decorrelating experience for 768 frames... [2023-03-09 07:26:16,614][23092] Decorrelating experience for 384 frames... [2023-03-09 07:26:16,654][23232] Decorrelating experience for 480 frames... [2023-03-09 07:26:16,729][23191] Decorrelating experience for 352 frames... [2023-03-09 07:26:16,730][23194] Decorrelating experience for 544 frames... [2023-03-09 07:26:16,759][23485] Decorrelating experience for 640 frames... [2023-03-09 07:26:16,762][23222] Decorrelating experience for 576 frames... [2023-03-09 07:26:16,779][23213] Decorrelating experience for 608 frames... [2023-03-09 07:26:16,783][23094] Decorrelating experience for 640 frames... [2023-03-09 07:26:16,783][23961] Decorrelating experience for 224 frames... [2023-03-09 07:26:16,805][23229] Decorrelating experience for 512 frames... [2023-03-09 07:26:16,831][23235] Decorrelating experience for 544 frames... [2023-03-09 07:26:16,840][23635] Decorrelating experience for 320 frames... [2023-03-09 07:26:16,918][23195] Decorrelating experience for 736 frames... [2023-03-09 07:26:16,951][23237] Decorrelating experience for 512 frames... [2023-03-09 07:26:16,953][24120] Decorrelating experience for 352 frames... [2023-03-09 07:26:16,981][23224] Decorrelating experience for 992 frames... [2023-03-09 07:26:16,986][23118] Decorrelating experience for 640 frames... [2023-03-09 07:26:16,986][23228] Decorrelating experience for 544 frames... [2023-03-09 07:26:16,992][23662] Decorrelating experience for 416 frames... [2023-03-09 07:26:17,031][23221] Decorrelating experience for 480 frames... [2023-03-09 07:26:17,051][23634] Decorrelating experience for 640 frames... [2023-03-09 07:26:17,073][23226] Decorrelating experience for 512 frames... [2023-03-09 07:26:17,145][23230] Decorrelating experience for 640 frames... [2023-03-09 07:26:17,187][23189] Decorrelating experience for 224 frames... [2023-03-09 07:26:17,188][23194] Decorrelating experience for 576 frames... [2023-03-09 07:26:17,191][23096] Decorrelating experience for 672 frames... [2023-03-09 07:26:17,192][23093] Decorrelating experience for 576 frames... [2023-03-09 07:26:17,193][23185] Decorrelating experience for 512 frames... [2023-03-09 07:26:17,205][23239] Decorrelating experience for 288 frames... [2023-03-09 07:26:17,211][23173] Another process currently holds the lock /tmp/sf2_rolo/doom_002.lockfile, attempt: 1 [2023-03-09 07:26:17,215][23638] Decorrelating experience for 864 frames... [2023-03-09 07:26:17,238][23248] Decorrelating experience for 640 frames... [2023-03-09 07:26:17,312][24352] Another process currently holds the lock /tmp/sf2_rolo/doom_002.lockfile, attempt: 1 [2023-03-09 07:26:17,332][23178] Decorrelating experience for 256 frames... [2023-03-09 07:26:17,333][23192] Decorrelating experience for 576 frames... [2023-03-09 07:26:17,364][22664] Heartbeat connected on RolloutWorker_w63 [2023-03-09 07:26:17,412][23225] Decorrelating experience for 480 frames... [2023-03-09 07:26:17,413][23209] Decorrelating experience for 832 frames... [2023-03-09 07:26:17,416][23188] Decorrelating experience for 864 frames... [2023-03-09 07:26:17,416][23250] Decorrelating experience for 640 frames... [2023-03-09 07:26:17,417][23092] Decorrelating experience for 416 frames... [2023-03-09 07:26:17,432][23094] Decorrelating experience for 672 frames... [2023-03-09 07:26:17,448][23243] Decorrelating experience for 448 frames... [2023-03-09 07:26:17,480][23227] Decorrelating experience for 384 frames... [2023-03-09 07:26:17,524][24121] Decorrelating experience for 416 frames... [2023-03-09 07:26:17,528][23091] Decorrelating experience for 640 frames... [2023-03-09 07:26:17,610][23635] Decorrelating experience for 352 frames... [2023-03-09 07:26:17,615][23103] Decorrelating experience for 416 frames... [2023-03-09 07:26:17,616][23208] Decorrelating experience for 0 frames... [2023-03-09 07:26:17,627][23219] Decorrelating experience for 736 frames... [2023-03-09 07:26:17,650][23235] Decorrelating experience for 576 frames... [2023-03-09 07:26:17,660][23246] Decorrelating experience for 320 frames... [2023-03-09 07:26:17,660][23961] Decorrelating experience for 256 frames... [2023-03-09 07:26:17,721][23177] Decorrelating experience for 640 frames... [2023-03-09 07:26:17,728][23242] Decorrelating experience for 800 frames... [2023-03-09 07:26:17,732][23485] Decorrelating experience for 672 frames... [2023-03-09 07:26:17,814][23207] Decorrelating experience for 384 frames... [2023-03-09 07:26:17,814][23243] Decorrelating experience for 480 frames... [2023-03-09 07:26:17,818][23248] Decorrelating experience for 672 frames... [2023-03-09 07:26:17,829][24157] Decorrelating experience for 800 frames... [2023-03-09 07:26:17,849][23250] Decorrelating experience for 672 frames... [2023-03-09 07:26:17,854][23238] Decorrelating experience for 544 frames... [2023-03-09 07:26:17,860][23227] Decorrelating experience for 416 frames... [2023-03-09 07:26:17,932][23209] Decorrelating experience for 864 frames... [2023-03-09 07:26:17,938][24025] Decorrelating experience for 384 frames... [2023-03-09 07:26:17,939][23635] Decorrelating experience for 384 frames... [2023-03-09 07:26:18,007][24858] Decorrelating experience for 448 frames... [2023-03-09 07:26:18,021][23091] Decorrelating experience for 672 frames... [2023-03-09 07:26:18,025][24121] Decorrelating experience for 448 frames... [2023-03-09 07:26:18,052][23087] Decorrelating experience for 800 frames... [2023-03-09 07:26:18,057][23195] Decorrelating experience for 768 frames... [2023-03-09 07:26:18,068][23089] Decorrelating experience for 640 frames... [2023-03-09 07:26:18,128][23094] Decorrelating experience for 704 frames... [2023-03-09 07:26:18,131][24539] Decorrelating experience for 640 frames... [2023-03-09 07:26:18,142][23096] Decorrelating experience for 704 frames... [2023-03-09 07:26:18,142][23222] Decorrelating experience for 608 frames... [2023-03-09 07:26:18,201][23190] Decorrelating experience for 544 frames... [2023-03-09 07:26:18,222][23246] Decorrelating experience for 352 frames... [2023-03-09 07:26:18,232][23193] Decorrelating experience for 704 frames... [2023-03-09 07:26:18,254][23244] Decorrelating experience for 544 frames... [2023-03-09 07:26:18,258][23169] Decorrelating experience for 288 frames... [2023-03-09 07:26:18,267][24025] Decorrelating experience for 416 frames... [2023-03-09 07:26:18,321][23202] Decorrelating experience for 768 frames... [2023-03-09 07:26:18,334][23230] Decorrelating experience for 672 frames... [2023-03-09 07:26:18,334][23185] Decorrelating experience for 544 frames... [2023-03-09 07:26:18,344][23250] Decorrelating experience for 704 frames... [2023-03-09 07:26:18,390][23204] Decorrelating experience for 576 frames... [2023-03-09 07:26:18,433][23867] Decorrelating experience for 320 frames... [2023-03-09 07:26:18,447][23203] Decorrelating experience for 608 frames... [2023-03-09 07:26:18,460][24156] Decorrelating experience for 864 frames... [2023-03-09 07:26:18,460][23179] Decorrelating experience for 832 frames... [2023-03-09 07:26:18,473][24858] Decorrelating experience for 480 frames... [2023-03-09 07:26:18,549][23638] Decorrelating experience for 896 frames... [2023-03-09 07:26:18,552][23200] Decorrelating experience for 704 frames... [2023-03-09 07:26:18,557][23225] Decorrelating experience for 512 frames... [2023-03-09 07:26:18,562][23239] Decorrelating experience for 320 frames... [2023-03-09 07:26:18,579][24121] Decorrelating experience for 480 frames... [2023-03-09 07:26:18,637][24158] Decorrelating experience for 544 frames... [2023-03-09 07:26:18,651][23089] Decorrelating experience for 672 frames... [2023-03-09 07:26:18,677][24157] Decorrelating experience for 832 frames... [2023-03-09 07:26:18,707][23866] Decorrelating experience for 640 frames... [2023-03-09 07:26:18,708][23623] Decorrelating experience for 832 frames... [2023-03-09 07:26:18,737][23228] Decorrelating experience for 576 frames... [2023-03-09 07:26:18,762][23219] Decorrelating experience for 768 frames... [2023-03-09 07:26:18,773][23210] Decorrelating experience for 576 frames... [2023-03-09 07:26:18,780][23248] Decorrelating experience for 704 frames... [2023-03-09 07:26:18,794][23525] Decorrelating experience for 672 frames... [2023-03-09 07:26:18,844][23237] Decorrelating experience for 544 frames... [2023-03-09 07:26:18,854][23250] Decorrelating experience for 736 frames... [2023-03-09 07:26:18,936][24666] Decorrelating experience for 576 frames... [2023-03-09 07:26:18,938][23243] Decorrelating experience for 512 frames... [2023-03-09 07:26:18,962][24434] Decorrelating experience for 736 frames... [2023-03-09 07:26:18,992][23246] Decorrelating experience for 384 frames... [2023-03-09 07:26:18,992][23091] Decorrelating experience for 704 frames... [2023-03-09 07:26:19,003][23201] Decorrelating experience for 640 frames... [2023-03-09 07:26:19,006][23196] Decorrelating experience for 672 frames... [2023-03-09 07:26:19,007][23207] Decorrelating experience for 416 frames... [2023-03-09 07:26:19,044][24089] Decorrelating experience for 384 frames... [2023-03-09 07:26:19,059][22664] Fps is (10 sec: 4915.3, 60 sec: 983.0, 300 sec: 983.0). Total num frames: 49152. Throughput: 0: 262.0. Samples: 11792. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2023-03-09 07:26:19,059][22664] Avg episode reward: [(0, '2.928')] [2023-03-09 07:26:19,128][24156] Decorrelating experience for 896 frames... [2023-03-09 07:26:19,132][24118] Decorrelating experience for 800 frames... [2023-03-09 07:26:19,162][23099] Decorrelating experience for 672 frames... [2023-03-09 07:26:19,187][23225] Decorrelating experience for 544 frames... [2023-03-09 07:26:19,219][23193] Decorrelating experience for 736 frames... [2023-03-09 07:26:19,219][23204] Decorrelating experience for 608 frames... [2023-03-09 07:26:19,219][23093] Decorrelating experience for 608 frames... [2023-03-09 07:26:19,221][23235] Decorrelating experience for 608 frames... [2023-03-09 07:26:19,244][23174] Decorrelating experience for 352 frames... [2023-03-09 07:26:19,296][24858] Decorrelating experience for 512 frames... [2023-03-09 07:26:19,323][23177] Decorrelating experience for 672 frames... [2023-03-09 07:26:19,350][23866] Decorrelating experience for 672 frames... [2023-03-09 07:26:19,456][23092] Decorrelating experience for 448 frames... [2023-03-09 07:26:19,457][24539] Decorrelating experience for 672 frames... [2023-03-09 07:26:19,457][23525] Decorrelating experience for 704 frames... [2023-03-09 07:26:19,458][23210] Decorrelating experience for 608 frames... [2023-03-09 07:26:19,458][23201] Decorrelating experience for 672 frames... [2023-03-09 07:26:19,461][23231] Decorrelating experience for 512 frames... [2023-03-09 07:26:19,489][23200] Decorrelating experience for 736 frames... [2023-03-09 07:26:19,490][23248] Decorrelating experience for 736 frames... [2023-03-09 07:26:19,522][23172] Decorrelating experience for 512 frames... [2023-03-09 07:26:19,565][23230] Decorrelating experience for 704 frames... [2023-03-09 07:26:19,659][23091] Decorrelating experience for 736 frames... [2023-03-09 07:26:19,672][23637] Decorrelating experience for 544 frames... [2023-03-09 07:26:19,675][23242] Decorrelating experience for 832 frames... [2023-03-09 07:26:19,682][23193] Decorrelating experience for 768 frames... [2023-03-09 07:26:19,705][23662] Decorrelating experience for 448 frames... [2023-03-09 07:26:19,715][23206] Decorrelating experience for 832 frames... [2023-03-09 07:26:19,743][23237] Decorrelating experience for 576 frames... [2023-03-09 07:26:19,748][24025] Decorrelating experience for 448 frames... [2023-03-09 07:26:19,774][23196] Decorrelating experience for 704 frames... [2023-03-09 07:26:19,821][23099] Decorrelating experience for 704 frames... [2023-03-09 07:26:19,880][23174] Decorrelating experience for 384 frames... [2023-03-09 07:26:19,891][23181] Decorrelating experience for 672 frames... [2023-03-09 07:26:19,892][23118] Decorrelating experience for 672 frames... [2023-03-09 07:26:19,892][23189] Decorrelating experience for 256 frames... [2023-03-09 07:26:19,927][23233] Decorrelating experience for 320 frames... [2023-03-09 07:26:19,928][23238] Decorrelating experience for 576 frames... [2023-03-09 07:26:19,937][23225] Decorrelating experience for 576 frames... [2023-03-09 07:26:19,976][23244] Decorrelating experience for 576 frames... [2023-03-09 07:26:19,977][23223] Decorrelating experience for 864 frames... [2023-03-09 07:26:20,011][24118] Decorrelating experience for 832 frames... [2023-03-09 07:26:20,069][23227] Decorrelating experience for 448 frames... [2023-03-09 07:26:20,079][23243] Decorrelating experience for 544 frames... [2023-03-09 07:26:20,085][23218] Decorrelating experience for 864 frames... [2023-03-09 07:26:20,128][23240] Decorrelating experience for 544 frames... [2023-03-09 07:26:20,132][23209] Decorrelating experience for 896 frames... [2023-03-09 07:26:20,138][23172] Decorrelating experience for 544 frames... [2023-03-09 07:26:20,181][23865] Decorrelating experience for 608 frames... [2023-03-09 07:26:20,187][24156] Decorrelating experience for 928 frames... [2023-03-09 07:26:20,194][23094] Decorrelating experience for 736 frames... [2023-03-09 07:26:20,217][23195] Decorrelating experience for 800 frames... [2023-03-09 07:26:20,280][23185] Decorrelating experience for 576 frames... [2023-03-09 07:26:20,280][33428] Decorrelating experience for 640 frames... [2023-03-09 07:26:20,284][23242] Decorrelating experience for 864 frames... [2023-03-09 07:26:20,288][23175] Another process currently holds the lock /tmp/sf2_rolo/doom_002.lockfile, attempt: 1 [2023-03-09 07:26:20,332][23250] Decorrelating experience for 768 frames... [2023-03-09 07:26:20,340][23201] Decorrelating experience for 704 frames... [2023-03-09 07:26:20,344][23217] Decorrelating experience for 448 frames... [2023-03-09 07:26:20,378][23096] Decorrelating experience for 736 frames... [2023-03-09 07:26:20,384][23228] Decorrelating experience for 608 frames... [2023-03-09 07:26:20,388][23202] Decorrelating experience for 800 frames... [2023-03-09 07:26:20,416][23099] Decorrelating experience for 736 frames... [2023-03-09 07:26:20,480][23173] Decorrelating experience for 384 frames... [2023-03-09 07:26:20,486][24157] Decorrelating experience for 864 frames... [2023-03-09 07:26:20,542][23172] Decorrelating experience for 576 frames... [2023-03-09 07:26:20,549][23246] Decorrelating experience for 416 frames... [2023-03-09 07:26:20,552][23181] Decorrelating experience for 704 frames... [2023-03-09 07:26:20,581][23657] Decorrelating experience for 384 frames... [2023-03-09 07:26:20,589][23525] Decorrelating experience for 736 frames... [2023-03-09 07:26:20,625][23098] Decorrelating experience for 576 frames... [2023-03-09 07:26:20,630][23249] Decorrelating experience for 768 frames... [2023-03-09 07:26:20,648][23203] Decorrelating experience for 640 frames... [2023-03-09 07:26:20,681][23089] Decorrelating experience for 704 frames... [2023-03-09 07:26:20,685][23209] Decorrelating experience for 928 frames... [2023-03-09 07:26:20,748][23204] Decorrelating experience for 640 frames... [2023-03-09 07:26:20,750][23118] Decorrelating experience for 704 frames... [2023-03-09 07:26:20,763][23636] Decorrelating experience for 736 frames... [2023-03-09 07:26:20,774][23239] Decorrelating experience for 352 frames... [2023-03-09 07:26:20,812][23250] Decorrelating experience for 800 frames... [2023-03-09 07:26:20,824][23171] Decorrelating experience for 736 frames... [2023-03-09 07:26:20,828][23638] Decorrelating experience for 928 frames... [2023-03-09 07:26:20,832][23094] Decorrelating experience for 768 frames... [2023-03-09 07:26:20,874][23205] Decorrelating experience for 512 frames... [2023-03-09 07:26:20,943][23662] Decorrelating experience for 480 frames... [2023-03-09 07:26:20,953][23234] Decorrelating experience for 544 frames... [2023-03-09 07:26:20,954][23201] Decorrelating experience for 736 frames... [2023-03-09 07:26:20,964][23865] Decorrelating experience for 640 frames... [2023-03-09 07:26:20,965][23866] Decorrelating experience for 704 frames... [2023-03-09 07:26:21,018][33428] Decorrelating experience for 672 frames... [2023-03-09 07:26:21,036][23637] Decorrelating experience for 576 frames... [2023-03-09 07:26:21,037][23214] Decorrelating experience for 832 frames... [2023-03-09 07:26:21,055][23194] Decorrelating experience for 608 frames... [2023-03-09 07:26:21,071][24118] Decorrelating experience for 864 frames... [2023-03-09 07:26:21,158][23239] Decorrelating experience for 384 frames... [2023-03-09 07:26:21,160][23088] Decorrelating experience for 704 frames... [2023-03-09 07:26:21,160][24858] Decorrelating experience for 544 frames... [2023-03-09 07:26:21,176][24121] Decorrelating experience for 512 frames... [2023-03-09 07:26:21,219][23218] Decorrelating experience for 896 frames... [2023-03-09 07:26:21,222][23200] Decorrelating experience for 768 frames... [2023-03-09 07:26:21,227][23222] Decorrelating experience for 640 frames... [2023-03-09 07:26:21,276][23211] Decorrelating experience for 576 frames... [2023-03-09 07:26:21,307][24025] Decorrelating experience for 480 frames... [2023-03-09 07:26:21,367][23223] Decorrelating experience for 896 frames... [2023-03-09 07:26:21,367][23187] Decorrelating experience for 352 frames... [2023-03-09 07:26:21,373][23228] Decorrelating experience for 640 frames... [2023-03-09 07:26:21,376][23245] Decorrelating experience for 384 frames... [2023-03-09 07:26:21,413][23094] Decorrelating experience for 800 frames... [2023-03-09 07:26:21,425][23097] Decorrelating experience for 672 frames... [2023-03-09 07:26:21,426][23192] Decorrelating experience for 608 frames... [2023-03-09 07:26:21,478][23634] Decorrelating experience for 672 frames... [2023-03-09 07:26:21,508][23172] Decorrelating experience for 608 frames... [2023-03-09 07:26:21,566][23195] Decorrelating experience for 832 frames... [2023-03-09 07:26:21,574][23205] Decorrelating experience for 544 frames... [2023-03-09 07:26:21,574][24157] Decorrelating experience for 896 frames... [2023-03-09 07:26:21,581][23194] Decorrelating experience for 640 frames... [2023-03-09 07:26:21,617][23225] Decorrelating experience for 608 frames... [2023-03-09 07:26:21,661][23222] Decorrelating experience for 672 frames... [2023-03-09 07:26:21,692][23178] Decorrelating experience for 288 frames... [2023-03-09 07:26:21,705][23188] Decorrelating experience for 896 frames... [2023-03-09 07:26:21,710][23087] Decorrelating experience for 832 frames... [2023-03-09 07:26:21,777][23211] Decorrelating experience for 608 frames... [2023-03-09 07:26:21,780][23173] Decorrelating experience for 416 frames... [2023-03-09 07:26:21,781][23662] Decorrelating experience for 512 frames... [2023-03-09 07:26:21,787][23242] Decorrelating experience for 896 frames... [2023-03-09 07:26:21,804][24156] Decorrelating experience for 960 frames... [2023-03-09 07:26:21,848][23088] Decorrelating experience for 736 frames... [2023-03-09 07:26:21,916][23214] Decorrelating experience for 864 frames... [2023-03-09 07:26:21,917][23201] Decorrelating experience for 768 frames... [2023-03-09 07:26:21,917][24434] Decorrelating experience for 768 frames... [2023-03-09 07:26:21,921][23634] Decorrelating experience for 704 frames... [2023-03-09 07:26:21,975][23172] Decorrelating experience for 640 frames... [2023-03-09 07:26:21,988][23212] Decorrelating experience for 672 frames... [2023-03-09 07:26:21,991][23227] Decorrelating experience for 480 frames... [2023-03-09 07:26:22,008][23249] Decorrelating experience for 800 frames... [2023-03-09 07:26:22,048][24666] Decorrelating experience for 608 frames... [2023-03-09 07:26:22,090][23485] Decorrelating experience for 704 frames... [2023-03-09 07:26:22,115][23096] Decorrelating experience for 768 frames... [2023-03-09 07:26:22,122][23245] Decorrelating experience for 416 frames... [2023-03-09 07:26:22,126][23203] Decorrelating experience for 672 frames... [2023-03-09 07:26:22,181][23193] Decorrelating experience for 800 frames... [2023-03-09 07:26:22,187][23236] Decorrelating experience for 768 frames... [2023-03-09 07:26:22,207][23091] Decorrelating experience for 768 frames... [2023-03-09 07:26:22,207][23246] Decorrelating experience for 448 frames... [2023-03-09 07:26:22,279][23173] Decorrelating experience for 448 frames... [2023-03-09 07:26:22,280][23219] Decorrelating experience for 800 frames... [2023-03-09 07:26:22,303][23865] Decorrelating experience for 672 frames... [2023-03-09 07:26:22,357][23662] Decorrelating experience for 544 frames... [2023-03-09 07:26:22,376][23174] Decorrelating experience for 416 frames... [2023-03-09 07:26:22,388][23194] Decorrelating experience for 672 frames... [2023-03-09 07:26:22,405][24434] Decorrelating experience for 800 frames... [2023-03-09 07:26:22,444][23195] Decorrelating experience for 864 frames... [2023-03-09 07:26:22,472][23226] Decorrelating experience for 544 frames... [2023-03-09 07:26:22,475][33428] Decorrelating experience for 704 frames... [2023-03-09 07:26:22,479][23099] Decorrelating experience for 768 frames... [2023-03-09 07:26:22,487][23623] Decorrelating experience for 864 frames... [2023-03-09 07:26:22,500][24818] Another process currently holds the lock /tmp/sf2_rolo/doom_002.lockfile, attempt: 2 [2023-03-09 07:26:22,501][23233] Decorrelating experience for 352 frames... [2023-03-09 07:26:22,547][23817] Decorrelating experience for 672 frames... [2023-03-09 07:26:22,563][23246] Decorrelating experience for 480 frames... [2023-03-09 07:26:22,572][23192] Decorrelating experience for 640 frames... [2023-03-09 07:26:22,657][24666] Decorrelating experience for 640 frames... [2023-03-09 07:26:22,668][23181] Decorrelating experience for 736 frames... [2023-03-09 07:26:22,672][24539] Decorrelating experience for 704 frames... [2023-03-09 07:26:22,703][23210] Decorrelating experience for 640 frames... [2023-03-09 07:26:22,715][23239] Decorrelating experience for 416 frames... [2023-03-09 07:26:22,726][23249] Decorrelating experience for 832 frames... [2023-03-09 07:26:22,729][23485] Decorrelating experience for 736 frames... [2023-03-09 07:26:22,737][23240] Decorrelating experience for 576 frames... [2023-03-09 07:26:22,750][23213] Decorrelating experience for 640 frames... [2023-03-09 07:26:22,767][23188] Decorrelating experience for 928 frames... [2023-03-09 07:26:22,872][23236] Decorrelating experience for 800 frames... [2023-03-09 07:26:22,907][24434] Decorrelating experience for 832 frames... [2023-03-09 07:26:22,908][23525] Decorrelating experience for 768 frames... [2023-03-09 07:26:22,922][23094] Decorrelating experience for 832 frames... [2023-03-09 07:26:22,933][23636] Decorrelating experience for 768 frames... [2023-03-09 07:26:22,933][24858] Decorrelating experience for 576 frames... [2023-03-09 07:26:22,943][23097] Decorrelating experience for 704 frames... [2023-03-09 07:26:22,944][24158] Decorrelating experience for 576 frames... [2023-03-09 07:26:22,952][23216] Another process currently holds the lock /tmp/sf2_rolo/doom_002.lockfile, attempt: 1 [2023-03-09 07:26:22,957][24089] Decorrelating experience for 416 frames... [2023-03-09 07:26:22,989][23203] Decorrelating experience for 704 frames... [2023-03-09 07:26:23,091][24156] Decorrelating experience for 992 frames... [2023-03-09 07:26:23,104][23961] Decorrelating experience for 288 frames... [2023-03-09 07:26:23,117][23239] Decorrelating experience for 448 frames... [2023-03-09 07:26:23,173][24539] Decorrelating experience for 736 frames... [2023-03-09 07:26:23,173][23196] Decorrelating experience for 736 frames... [2023-03-09 07:26:23,173][24025] Decorrelating experience for 512 frames... [2023-03-09 07:26:23,174][23206] Decorrelating experience for 864 frames... [2023-03-09 07:26:23,174][23197] Decorrelating experience for 512 frames... [2023-03-09 07:26:23,181][23195] Decorrelating experience for 896 frames... [2023-03-09 07:26:23,185][23213] Decorrelating experience for 672 frames... [2023-03-09 07:26:23,279][23217] Decorrelating experience for 480 frames... [2023-03-09 07:26:23,292][23246] Decorrelating experience for 512 frames... [2023-03-09 07:26:23,318][23211] Decorrelating experience for 640 frames... [2023-03-09 07:26:23,378][23242] Decorrelating experience for 928 frames... [2023-03-09 07:26:23,382][23096] Decorrelating experience for 800 frames... [2023-03-09 07:26:23,391][23662] Decorrelating experience for 576 frames... [2023-03-09 07:26:23,453][23176] Decorrelating experience for 960 frames... [2023-03-09 07:26:23,467][23181] Decorrelating experience for 768 frames... [2023-03-09 07:26:23,468][23236] Decorrelating experience for 832 frames... [2023-03-09 07:26:23,468][23228] Decorrelating experience for 672 frames... [2023-03-09 07:26:23,475][23239] Decorrelating experience for 480 frames... [2023-03-09 07:26:23,522][23174] Decorrelating experience for 448 frames... [2023-03-09 07:26:23,534][23485] Decorrelating experience for 768 frames... [2023-03-09 07:26:23,574][22664] Heartbeat connected on RolloutWorker_w103 [2023-03-09 07:26:23,576][23233] Decorrelating experience for 384 frames... [2023-03-09 07:26:23,600][23635] Decorrelating experience for 416 frames... [2023-03-09 07:26:23,603][24858] Decorrelating experience for 608 frames... [2023-03-09 07:26:23,642][23441] Decorrelating experience for 288 frames... [2023-03-09 07:26:23,666][23238] Decorrelating experience for 608 frames... [2023-03-09 07:26:23,676][23525] Decorrelating experience for 800 frames... [2023-03-09 07:26:23,681][23249] Decorrelating experience for 864 frames... [2023-03-09 07:26:23,685][23248] Decorrelating experience for 768 frames... [2023-03-09 07:26:23,728][23246] Decorrelating experience for 544 frames... [2023-03-09 07:26:23,732][23094] Decorrelating experience for 864 frames... [2023-03-09 07:26:23,787][23205] Decorrelating experience for 576 frames... [2023-03-09 07:26:23,810][23866] Decorrelating experience for 736 frames... [2023-03-09 07:26:23,810][23091] Decorrelating experience for 800 frames... [2023-03-09 07:26:23,849][23234] Decorrelating experience for 576 frames... [2023-03-09 07:26:23,860][23217] Decorrelating experience for 512 frames... [2023-03-09 07:26:23,875][23250] Decorrelating experience for 832 frames... [2023-03-09 07:26:23,889][23118] Decorrelating experience for 736 frames... [2023-03-09 07:26:23,899][23192] Decorrelating experience for 672 frames... [2023-03-09 07:26:23,947][23228] Decorrelating experience for 704 frames... [2023-03-09 07:26:23,982][23245] Decorrelating experience for 448 frames... [2023-03-09 07:26:24,015][23243] Decorrelating experience for 576 frames... [2023-03-09 07:26:24,016][23179] Decorrelating experience for 864 frames... [2023-03-09 07:26:24,057][23817] Decorrelating experience for 704 frames... [2023-03-09 07:26:24,058][22664] Fps is (10 sec: 13107.2, 60 sec: 2383.1, 300 sec: 2383.1). Total num frames: 131072. Throughput: 0: 801.8. Samples: 36080. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2023-03-09 07:26:24,059][22664] Avg episode reward: [(0, '4.290')] [2023-03-09 07:26:24,061][22940] Saving new best policy, reward=4.290! [2023-03-09 07:26:24,076][24434] Decorrelating experience for 864 frames... [2023-03-09 07:26:24,080][23229] Decorrelating experience for 544 frames... [2023-03-09 07:26:24,108][23635] Decorrelating experience for 448 frames... [2023-03-09 07:26:24,159][23242] Decorrelating experience for 960 frames... [2023-03-09 07:26:24,185][23181] Decorrelating experience for 800 frames... [2023-03-09 07:26:24,205][23190] Decorrelating experience for 576 frames... [2023-03-09 07:26:24,212][23249] Decorrelating experience for 896 frames... [2023-03-09 07:26:24,218][23244] Decorrelating experience for 608 frames... [2023-03-09 07:26:24,218][23171] Decorrelating experience for 768 frames... [2023-03-09 07:26:24,285][24121] Decorrelating experience for 544 frames... [2023-03-09 07:26:24,313][23191] Decorrelating experience for 384 frames... [2023-03-09 07:26:24,313][23196] Decorrelating experience for 768 frames... [2023-03-09 07:26:24,315][23235] Decorrelating experience for 640 frames... [2023-03-09 07:26:24,375][24118] Decorrelating experience for 896 frames... [2023-03-09 07:26:24,377][23525] Decorrelating experience for 832 frames... [2023-03-09 07:26:24,400][23232] Decorrelating experience for 512 frames... [2023-03-09 07:26:24,415][23202] Decorrelating experience for 832 frames... [2023-03-09 07:26:24,465][23485] Decorrelating experience for 800 frames... [2023-03-09 07:26:24,486][23096] Decorrelating experience for 832 frames... [2023-03-09 07:26:24,506][23230] Decorrelating experience for 736 frames... [2023-03-09 07:26:24,516][23817] Decorrelating experience for 736 frames... [2023-03-09 07:26:24,572][23214] Decorrelating experience for 896 frames... [2023-03-09 07:26:24,585][23239] Decorrelating experience for 512 frames... [2023-03-09 07:26:24,590][24158] Decorrelating experience for 608 frames... [2023-03-09 07:26:24,593][23207] Decorrelating experience for 448 frames... [2023-03-09 07:26:24,660][23234] Decorrelating experience for 608 frames... [2023-03-09 07:26:24,673][23867] Decorrelating experience for 352 frames... [2023-03-09 07:26:24,678][23205] Decorrelating experience for 608 frames... [2023-03-09 07:26:24,687][23179] Decorrelating experience for 896 frames... [2023-03-09 07:26:24,707][23194] Decorrelating experience for 704 frames... [2023-03-09 07:26:24,748][23249] Decorrelating experience for 928 frames... [2023-03-09 07:26:24,766][24352] Decorrelating experience for 416 frames... [2023-03-09 07:26:24,794][23176] Decorrelating experience for 992 frames... [2023-03-09 07:26:24,802][23243] Decorrelating experience for 608 frames... [2023-03-09 07:26:24,803][23657] Decorrelating experience for 416 frames... [2023-03-09 07:26:24,871][23186] Decorrelating experience for 800 frames... [2023-03-09 07:26:24,874][23187] Decorrelating experience for 384 frames... [2023-03-09 07:26:24,908][23441] Decorrelating experience for 320 frames... [2023-03-09 07:26:24,908][23211] Decorrelating experience for 672 frames... [2023-03-09 07:26:24,952][23634] Decorrelating experience for 736 frames... [2023-03-09 07:26:24,961][23247] Decorrelating experience for 480 frames... [2023-03-09 07:26:25,011][23227] Decorrelating experience for 512 frames... [2023-03-09 07:26:25,012][23866] Decorrelating experience for 768 frames... [2023-03-09 07:26:25,015][23232] Decorrelating experience for 544 frames... [2023-03-09 07:26:25,070][23202] Decorrelating experience for 864 frames... [2023-03-09 07:26:25,083][23218] Decorrelating experience for 928 frames... [2023-03-09 07:26:25,085][23088] Decorrelating experience for 768 frames... [2023-03-09 07:26:25,110][23214] Decorrelating experience for 928 frames... [2023-03-09 07:26:25,115][23183] Decorrelating experience for 608 frames... [2023-03-09 07:26:25,151][23171] Decorrelating experience for 800 frames... [2023-03-09 07:26:25,173][22664] Heartbeat connected on RolloutWorker_w21 [2023-03-09 07:26:25,184][23823] Decorrelating experience for 256 frames... [2023-03-09 07:26:25,206][23213] Decorrelating experience for 704 frames... [2023-03-09 07:26:25,219][23205] Decorrelating experience for 640 frames... [2023-03-09 07:26:25,225][23210] Decorrelating experience for 672 frames... [2023-03-09 07:26:25,282][23222] Decorrelating experience for 704 frames... [2023-03-09 07:26:25,288][23961] Decorrelating experience for 320 frames... [2023-03-09 07:26:25,314][23173] Decorrelating experience for 480 frames... [2023-03-09 07:26:25,334][23118] Decorrelating experience for 768 frames... [2023-03-09 07:26:25,343][23234] Decorrelating experience for 640 frames... [2023-03-09 07:26:25,359][24666] Decorrelating experience for 672 frames... [2023-03-09 07:26:25,390][23175] Decorrelating experience for 384 frames... [2023-03-09 07:26:25,400][23092] Decorrelating experience for 480 frames... [2023-03-09 07:26:25,401][23090] Updated weights for policy 0, policy_version 10 (0.0013) [2023-03-09 07:26:25,423][23228] Decorrelating experience for 736 frames... [2023-03-09 07:26:25,443][23247] Decorrelating experience for 512 frames... [2023-03-09 07:26:25,474][23197] Decorrelating experience for 544 frames... [2023-03-09 07:26:25,504][23657] Decorrelating experience for 448 frames... [2023-03-09 07:26:25,517][23237] Decorrelating experience for 608 frames... [2023-03-09 07:26:25,537][23634] Decorrelating experience for 768 frames... [2023-03-09 07:26:25,550][23206] Decorrelating experience for 896 frames... [2023-03-09 07:26:25,602][23243] Decorrelating experience for 640 frames... [2023-03-09 07:26:25,613][23189] Decorrelating experience for 288 frames... [2023-03-09 07:26:25,624][23245] Decorrelating experience for 480 frames... [2023-03-09 07:26:25,651][23196] Decorrelating experience for 800 frames... [2023-03-09 07:26:25,674][23179] Decorrelating experience for 928 frames... [2023-03-09 07:26:25,683][24539] Decorrelating experience for 768 frames... [2023-03-09 07:26:25,718][23867] Decorrelating experience for 384 frames... [2023-03-09 07:26:25,739][23190] Decorrelating experience for 608 frames... [2023-03-09 07:26:25,752][23866] Decorrelating experience for 800 frames... [2023-03-09 07:26:25,777][23314] Decorrelating experience for 224 frames... [2023-03-09 07:26:25,799][23183] Decorrelating experience for 640 frames... [2023-03-09 07:26:25,804][24089] Decorrelating experience for 448 frames... [2023-03-09 07:26:25,823][23203] Decorrelating experience for 736 frames... [2023-03-09 07:26:25,889][23636] Decorrelating experience for 800 frames... [2023-03-09 07:26:25,890][23218] Decorrelating experience for 960 frames... [2023-03-09 07:26:25,919][23817] Decorrelating experience for 768 frames... [2023-03-09 07:26:25,953][23227] Decorrelating experience for 544 frames... [2023-03-09 07:26:25,970][23662] Decorrelating experience for 608 frames... [2023-03-09 07:26:25,974][23175] Decorrelating experience for 416 frames... [2023-03-09 07:26:25,994][23222] Decorrelating experience for 736 frames... [2023-03-09 07:26:26,015][23189] Decorrelating experience for 320 frames... [2023-03-09 07:26:26,030][23238] Decorrelating experience for 640 frames... [2023-03-09 07:26:26,161][23196] Decorrelating experience for 832 frames... [2023-03-09 07:26:26,162][23173] Decorrelating experience for 512 frames... [2023-03-09 07:26:26,163][23181] Decorrelating experience for 832 frames... [2023-03-09 07:26:26,169][23961] Decorrelating experience for 352 frames... [2023-03-09 07:26:26,173][23171] Decorrelating experience for 832 frames... [2023-03-09 07:26:26,237][23211] Decorrelating experience for 704 frames... [2023-03-09 07:26:26,240][23241] Decorrelating experience for 448 frames... [2023-03-09 07:26:26,240][23214] Decorrelating experience for 960 frames... [2023-03-09 07:26:26,244][23103] Decorrelating experience for 448 frames... [2023-03-09 07:26:26,273][23191] Decorrelating experience for 416 frames... [2023-03-09 07:26:26,356][23192] Decorrelating experience for 704 frames... [2023-03-09 07:26:26,362][23205] Decorrelating experience for 672 frames... [2023-03-09 07:26:26,370][24434] Decorrelating experience for 896 frames... [2023-03-09 07:26:26,409][24858] Decorrelating experience for 640 frames... [2023-03-09 07:26:26,433][23206] Decorrelating experience for 928 frames... [2023-03-09 07:26:26,445][23187] Decorrelating experience for 416 frames... [2023-03-09 07:26:26,460][23232] Decorrelating experience for 576 frames... [2023-03-09 07:26:26,488][23235] Decorrelating experience for 672 frames... [2023-03-09 07:26:26,503][23231] Decorrelating experience for 544 frames... [2023-03-09 07:26:26,548][24025] Decorrelating experience for 544 frames... [2023-03-09 07:26:26,563][23638] Decorrelating experience for 960 frames... [2023-03-09 07:26:26,568][23212] Decorrelating experience for 704 frames... [2023-03-09 07:26:26,604][23209] Decorrelating experience for 960 frames... [2023-03-09 07:26:26,627][23087] Decorrelating experience for 864 frames... [2023-03-09 07:26:26,640][23219] Decorrelating experience for 832 frames... [2023-03-09 07:26:26,673][23240] Decorrelating experience for 608 frames... [2023-03-09 07:26:26,679][23637] Decorrelating experience for 608 frames... [2023-03-09 07:26:26,695][23230] Decorrelating experience for 768 frames... [2023-03-09 07:26:26,744][23177] Decorrelating experience for 704 frames... [2023-03-09 07:26:26,760][23213] Decorrelating experience for 736 frames... [2023-03-09 07:26:26,780][23225] Decorrelating experience for 640 frames... [2023-03-09 07:26:26,791][23171] Decorrelating experience for 864 frames... [2023-03-09 07:26:26,841][23248] Decorrelating experience for 800 frames... [2023-03-09 07:26:26,882][24818] Decorrelating experience for 64 frames... [2023-03-09 07:26:26,898][24539] Decorrelating experience for 800 frames... [2023-03-09 07:26:26,900][23246] Decorrelating experience for 576 frames... [2023-03-09 07:26:26,904][23089] Decorrelating experience for 736 frames... [2023-03-09 07:26:26,907][23238] Decorrelating experience for 672 frames... [2023-03-09 07:26:26,947][23229] Decorrelating experience for 576 frames... [2023-03-09 07:26:26,969][23242] Decorrelating experience for 992 frames... [2023-03-09 07:26:26,985][23441] Decorrelating experience for 352 frames... [2023-03-09 07:26:27,015][24858] Decorrelating experience for 672 frames... [2023-03-09 07:26:27,077][23232] Decorrelating experience for 608 frames... [2023-03-09 07:26:27,091][23235] Decorrelating experience for 704 frames... [2023-03-09 07:26:27,099][23183] Decorrelating experience for 672 frames... [2023-03-09 07:26:27,105][24818] Decorrelating experience for 96 frames... [2023-03-09 07:26:27,105][23201] Decorrelating experience for 800 frames... [2023-03-09 07:26:27,151][23662] Decorrelating experience for 640 frames... [2023-03-09 07:26:27,159][24666] Decorrelating experience for 704 frames... [2023-03-09 07:26:27,161][23215] Another process currently holds the lock /tmp/sf2_rolo/doom_007.lockfile, attempt: 1 [2023-03-09 07:26:27,177][23097] Decorrelating experience for 736 frames... [2023-03-09 07:26:27,239][23230] Decorrelating experience for 800 frames... [2023-03-09 07:26:27,248][23222] Decorrelating experience for 768 frames... [2023-03-09 07:26:27,270][24120] Decorrelating experience for 384 frames... [2023-03-09 07:26:27,285][23094] Decorrelating experience for 896 frames... [2023-03-09 07:26:27,302][23195] Decorrelating experience for 928 frames... [2023-03-09 07:26:27,313][23961] Decorrelating experience for 384 frames... [2023-03-09 07:26:27,320][23187] Decorrelating experience for 448 frames... [2023-03-09 07:26:27,361][24793] Decorrelating experience for 736 frames... [2023-03-09 07:26:27,361][23250] Decorrelating experience for 864 frames... [2023-03-09 07:26:27,419][22664] Heartbeat connected on RolloutWorker_w92 [2023-03-09 07:26:27,448][23213] Decorrelating experience for 768 frames... [2023-03-09 07:26:27,455][23206] Decorrelating experience for 960 frames... [2023-03-09 07:26:27,456][23192] Decorrelating experience for 736 frames... [2023-03-09 07:26:27,473][23169] Decorrelating experience for 320 frames... [2023-03-09 07:26:27,478][24089] Decorrelating experience for 480 frames... [2023-03-09 07:26:27,510][23215] Decorrelating experience for 480 frames... [2023-03-09 07:26:27,515][23240] Decorrelating experience for 640 frames... [2023-03-09 07:26:27,560][24121] Decorrelating experience for 576 frames... [2023-03-09 07:26:27,583][24434] Decorrelating experience for 928 frames... [2023-03-09 07:26:27,625][23182] Decorrelating experience for 544 frames... [2023-03-09 07:26:27,672][23232] Decorrelating experience for 640 frames... [2023-03-09 07:26:27,673][23247] Decorrelating experience for 544 frames... [2023-03-09 07:26:27,684][23193] Decorrelating experience for 832 frames... [2023-03-09 07:26:27,688][23203] Decorrelating experience for 768 frames... [2023-03-09 07:26:27,704][23091] Decorrelating experience for 832 frames... [2023-03-09 07:26:27,716][23817] Decorrelating experience for 800 frames... [2023-03-09 07:26:27,729][23635] Decorrelating experience for 480 frames... [2023-03-09 07:26:27,767][23637] Decorrelating experience for 640 frames... [2023-03-09 07:26:27,818][23244] Decorrelating experience for 640 frames... [2023-03-09 07:26:27,931][23200] Decorrelating experience for 800 frames... [2023-03-09 07:26:27,938][23175] Decorrelating experience for 448 frames... [2023-03-09 07:26:27,938][24793] Decorrelating experience for 768 frames... [2023-03-09 07:26:27,939][23250] Decorrelating experience for 896 frames... [2023-03-09 07:26:27,939][23638] Decorrelating experience for 992 frames... [2023-03-09 07:26:27,947][23314] Decorrelating experience for 256 frames... [2023-03-09 07:26:27,947][23223] Decorrelating experience for 928 frames... [2023-03-09 07:26:27,962][23207] Decorrelating experience for 480 frames... [2023-03-09 07:26:27,971][23634] Decorrelating experience for 800 frames... [2023-03-09 07:26:28,039][23171] Decorrelating experience for 896 frames... [2023-03-09 07:26:28,175][23214] Decorrelating experience for 992 frames... [2023-03-09 07:26:28,176][23212] Decorrelating experience for 736 frames... [2023-03-09 07:26:28,176][23215] Decorrelating experience for 512 frames... [2023-03-09 07:26:28,176][24089] Decorrelating experience for 512 frames... [2023-03-09 07:26:28,180][24121] Decorrelating experience for 608 frames... [2023-03-09 07:26:28,208][23238] Decorrelating experience for 704 frames... [2023-03-09 07:26:28,224][24666] Decorrelating experience for 736 frames... [2023-03-09 07:26:28,225][23192] Decorrelating experience for 768 frames... [2023-03-09 07:26:28,240][23087] Decorrelating experience for 896 frames... [2023-03-09 07:26:28,290][23180] Decorrelating experience for 832 frames... [2023-03-09 07:26:28,326][22664] Heartbeat connected on RolloutWorker_w125 [2023-03-09 07:26:28,401][23227] Decorrelating experience for 576 frames... [2023-03-09 07:26:28,401][23091] Decorrelating experience for 864 frames... [2023-03-09 07:26:28,402][23103] Decorrelating experience for 480 frames... [2023-03-09 07:26:28,409][23169] Decorrelating experience for 352 frames... [2023-03-09 07:26:28,413][23441] Decorrelating experience for 384 frames... [2023-03-09 07:26:28,422][23244] Decorrelating experience for 672 frames... [2023-03-09 07:26:28,422][24120] Decorrelating experience for 416 frames... [2023-03-09 07:26:28,430][23200] Decorrelating experience for 832 frames... [2023-03-09 07:26:28,446][24434] Decorrelating experience for 960 frames... [2023-03-09 07:26:28,481][23221] Decorrelating experience for 512 frames... [2023-03-09 07:26:28,561][22664] Heartbeat connected on RolloutWorker_w83 [2023-03-09 07:26:28,605][23098] Decorrelating experience for 608 frames... [2023-03-09 07:26:28,622][23243] Decorrelating experience for 672 frames... [2023-03-09 07:26:28,646][23217] Decorrelating experience for 544 frames... [2023-03-09 07:26:28,647][23961] Decorrelating experience for 416 frames... [2023-03-09 07:26:28,647][23525] Decorrelating experience for 864 frames... [2023-03-09 07:26:28,654][24818] Decorrelating experience for 128 frames... [2023-03-09 07:26:28,657][23089] Decorrelating experience for 768 frames... [2023-03-09 07:26:28,674][23197] Decorrelating experience for 576 frames... [2023-03-09 07:26:28,677][24793] Decorrelating experience for 800 frames... [2023-03-09 07:26:28,715][23314] Decorrelating experience for 288 frames... [2023-03-09 07:26:28,816][23118] Decorrelating experience for 800 frames... [2023-03-09 07:26:28,847][24158] Decorrelating experience for 640 frames... [2023-03-09 07:26:28,848][23169] Decorrelating experience for 384 frames... [2023-03-09 07:26:28,863][23096] Decorrelating experience for 864 frames... [2023-03-09 07:26:28,885][24121] Decorrelating experience for 640 frames... [2023-03-09 07:26:28,887][23222] Decorrelating experience for 800 frames... [2023-03-09 07:26:28,893][23237] Decorrelating experience for 640 frames... [2023-03-09 07:26:28,894][24089] Decorrelating experience for 544 frames... [2023-03-09 07:26:28,905][23244] Decorrelating experience for 704 frames... [2023-03-09 07:26:28,971][23193] Decorrelating experience for 864 frames... [2023-03-09 07:26:29,042][23223] Decorrelating experience for 960 frames... [2023-03-09 07:26:29,059][22664] Fps is (10 sec: 19660.0, 60 sec: 4096.0, 300 sec: 4096.0). Total num frames: 245760. Throughput: 0: 1175.5. Samples: 52896. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) [2023-03-09 07:26:29,061][22664] Avg episode reward: [(0, '3.877')] [2023-03-09 07:26:29,066][23195] Decorrelating experience for 960 frames... [2023-03-09 07:26:29,067][23623] Decorrelating experience for 896 frames... [2023-03-09 07:26:29,077][23173] Decorrelating experience for 544 frames... [2023-03-09 07:26:29,092][23196] Decorrelating experience for 864 frames... [2023-03-09 07:26:29,105][23206] Decorrelating experience for 992 frames... [2023-03-09 07:26:29,113][23178] Decorrelating experience for 320 frames... [2023-03-09 07:26:29,113][23207] Decorrelating experience for 512 frames... [2023-03-09 07:26:29,147][23192] Decorrelating experience for 800 frames... [2023-03-09 07:26:29,179][23221] Decorrelating experience for 544 frames... [2023-03-09 07:26:29,263][23216] Decorrelating experience for 480 frames... [2023-03-09 07:26:29,282][23188] Decorrelating experience for 960 frames... [2023-03-09 07:26:29,282][23240] Decorrelating experience for 672 frames... [2023-03-09 07:26:29,285][23218] Decorrelating experience for 992 frames... [2023-03-09 07:26:29,318][23961] Decorrelating experience for 448 frames... [2023-03-09 07:26:29,318][23175] Decorrelating experience for 480 frames... [2023-03-09 07:26:29,339][23237] Decorrelating experience for 672 frames... [2023-03-09 07:26:29,343][23485] Decorrelating experience for 832 frames... [2023-03-09 07:26:29,421][24818] Decorrelating experience for 160 frames... [2023-03-09 07:26:29,455][24666] Decorrelating experience for 768 frames... [2023-03-09 07:26:29,461][24539] Decorrelating experience for 832 frames... [2023-03-09 07:26:29,479][23182] Decorrelating experience for 576 frames... [2023-03-09 07:26:29,511][23525] Decorrelating experience for 896 frames... [2023-03-09 07:26:29,517][23189] Decorrelating experience for 352 frames... [2023-03-09 07:26:29,550][23093] Decorrelating experience for 640 frames... [2023-03-09 07:26:29,565][23173] Decorrelating experience for 576 frames... [2023-03-09 07:26:29,568][33428] Decorrelating experience for 736 frames... [2023-03-09 07:26:29,571][22664] Heartbeat connected on RolloutWorker_w65 [2023-03-09 07:26:29,572][23207] Decorrelating experience for 544 frames... [2023-03-09 07:26:29,621][23088] Decorrelating experience for 800 frames... [2023-03-09 07:26:29,649][24089] Decorrelating experience for 576 frames... [2023-03-09 07:26:29,667][23193] Decorrelating experience for 896 frames... [2023-03-09 07:26:29,673][22664] Heartbeat connected on RolloutWorker_w57 [2023-03-09 07:26:29,705][23092] Decorrelating experience for 512 frames... [2023-03-09 07:26:29,727][23209] Decorrelating experience for 992 frames... [2023-03-09 07:26:29,752][23240] Decorrelating experience for 704 frames... [2023-03-09 07:26:29,755][23227] Decorrelating experience for 608 frames... [2023-03-09 07:26:29,765][23248] Decorrelating experience for 832 frames... [2023-03-09 07:26:29,793][23235] Decorrelating experience for 736 frames... [2023-03-09 07:26:29,810][23623] Decorrelating experience for 928 frames... [2023-03-09 07:26:29,852][23103] Decorrelating experience for 512 frames... [2023-03-09 07:26:29,856][23191] Decorrelating experience for 448 frames... [2023-03-09 07:26:29,905][23096] Decorrelating experience for 896 frames... [2023-03-09 07:26:29,941][23208] Decorrelating experience for 32 frames... [2023-03-09 07:26:29,975][23094] Decorrelating experience for 928 frames... [2023-03-09 07:26:29,975][23441] Decorrelating experience for 416 frames... [2023-03-09 07:26:29,979][24434] Decorrelating experience for 992 frames... [2023-03-09 07:26:29,987][23210] Decorrelating experience for 704 frames... [2023-03-09 07:26:29,992][23961] Decorrelating experience for 480 frames... [2023-03-09 07:26:30,058][23188] Decorrelating experience for 992 frames... [2023-03-09 07:26:30,062][24818] Decorrelating experience for 192 frames... [2023-03-09 07:26:30,121][23234] Decorrelating experience for 672 frames... [2023-03-09 07:26:30,125][23182] Decorrelating experience for 608 frames... [2023-03-09 07:26:30,128][22664] Heartbeat connected on RolloutWorker_w68 [2023-03-09 07:26:30,146][24120] Decorrelating experience for 448 frames... [2023-03-09 07:26:30,217][23207] Decorrelating experience for 576 frames... [2023-03-09 07:26:30,218][23183] Decorrelating experience for 704 frames... [2023-03-09 07:26:30,218][23229] Decorrelating experience for 608 frames... [2023-03-09 07:26:30,219][23177] Decorrelating experience for 736 frames... [2023-03-09 07:26:30,224][24666] Decorrelating experience for 800 frames... [2023-03-09 07:26:30,260][23243] Decorrelating experience for 704 frames... [2023-03-09 07:26:30,326][24818] Decorrelating experience for 224 frames... [2023-03-09 07:26:30,338][23250] Decorrelating experience for 928 frames... [2023-03-09 07:26:30,345][23187] Decorrelating experience for 480 frames... [2023-03-09 07:26:30,396][23636] Decorrelating experience for 832 frames... [2023-03-09 07:26:30,414][23662] Decorrelating experience for 672 frames... [2023-03-09 07:26:30,436][23089] Decorrelating experience for 800 frames... [2023-03-09 07:26:30,442][23961] Decorrelating experience for 512 frames... [2023-03-09 07:26:30,443][24352] Decorrelating experience for 448 frames... [2023-03-09 07:26:30,447][22664] Heartbeat connected on RolloutWorker_w10 [2023-03-09 07:26:30,468][23236] Decorrelating experience for 864 frames... [2023-03-09 07:26:30,472][23212] Decorrelating experience for 768 frames... [2023-03-09 07:26:30,514][22664] Heartbeat connected on RolloutWorker_w100 [2023-03-09 07:26:30,532][23227] Decorrelating experience for 640 frames... [2023-03-09 07:26:30,574][23193] Decorrelating experience for 928 frames... [2023-03-09 07:26:30,585][23485] Decorrelating experience for 864 frames... [2023-03-09 07:26:30,613][32460] Decorrelating experience for 672 frames... [2023-03-09 07:26:30,637][24793] Decorrelating experience for 832 frames... [2023-03-09 07:26:30,645][23314] Decorrelating experience for 320 frames... [2023-03-09 07:26:30,651][23088] Decorrelating experience for 832 frames... [2023-03-09 07:26:30,654][23817] Decorrelating experience for 832 frames... [2023-03-09 07:26:30,669][23623] Decorrelating experience for 960 frames... [2023-03-09 07:26:30,743][23222] Decorrelating experience for 832 frames... [2023-03-09 07:26:30,773][23204] Decorrelating experience for 672 frames... [2023-03-09 07:26:30,783][23231] Decorrelating experience for 576 frames... [2023-03-09 07:26:30,814][23865] Decorrelating experience for 704 frames... [2023-03-09 07:26:30,841][23196] Decorrelating experience for 896 frames... [2023-03-09 07:26:30,846][24118] Decorrelating experience for 928 frames... [2023-03-09 07:26:30,862][23229] Decorrelating experience for 640 frames... [2023-03-09 07:26:30,874][23223] Decorrelating experience for 992 frames... [2023-03-09 07:26:30,888][23246] Decorrelating experience for 608 frames... [2023-03-09 07:26:30,936][23219] Decorrelating experience for 864 frames... [2023-03-09 07:26:30,978][23212] Decorrelating experience for 800 frames... [2023-03-09 07:26:30,988][23210] Decorrelating experience for 736 frames... [2023-03-09 07:26:31,020][23181] Decorrelating experience for 864 frames... [2023-03-09 07:26:31,033][23441] Decorrelating experience for 448 frames... [2023-03-09 07:26:31,047][23239] Decorrelating experience for 544 frames... [2023-03-09 07:26:31,058][23232] Decorrelating experience for 672 frames... [2023-03-09 07:26:31,083][23225] Decorrelating experience for 672 frames... [2023-03-09 07:26:31,092][23183] Decorrelating experience for 736 frames... [2023-03-09 07:26:31,107][23094] Decorrelating experience for 960 frames... [2023-03-09 07:26:31,196][23244] Decorrelating experience for 736 frames... [2023-03-09 07:26:31,209][23227] Decorrelating experience for 672 frames... [2023-03-09 07:26:31,225][23248] Decorrelating experience for 864 frames... [2023-03-09 07:26:31,245][23096] Decorrelating experience for 928 frames... [2023-03-09 07:26:31,271][22664] Heartbeat connected on RolloutWorker_w66 [2023-03-09 07:26:31,275][23233] Decorrelating experience for 416 frames... [2023-03-09 07:26:31,278][23182] Decorrelating experience for 640 frames... [2023-03-09 07:26:31,290][23314] Decorrelating experience for 352 frames... [2023-03-09 07:26:31,300][23485] Decorrelating experience for 896 frames... [2023-03-09 07:26:31,307][23195] Decorrelating experience for 992 frames... [2023-03-09 07:26:31,364][23090] Updated weights for policy 0, policy_version 20 (0.0011) [2023-03-09 07:26:31,370][23093] Decorrelating experience for 672 frames... [2023-03-09 07:26:31,400][23636] Decorrelating experience for 864 frames... [2023-03-09 07:26:31,418][24158] Decorrelating experience for 672 frames... [2023-03-09 07:26:31,471][23662] Decorrelating experience for 704 frames... [2023-03-09 07:26:31,497][23212] Decorrelating experience for 832 frames... [2023-03-09 07:26:31,519][23173] Decorrelating experience for 608 frames... [2023-03-09 07:26:31,545][23623] Decorrelating experience for 992 frames... [2023-03-09 07:26:31,549][23245] Decorrelating experience for 512 frames... [2023-03-09 07:26:31,568][23635] Decorrelating experience for 512 frames... [2023-03-09 07:26:31,573][23657] Decorrelating experience for 480 frames... [2023-03-09 07:26:31,603][23441] Decorrelating experience for 480 frames... [2023-03-09 07:26:31,613][23239] Decorrelating experience for 576 frames... [2023-03-09 07:26:31,693][22664] Heartbeat connected on RolloutWorker_w34 [2023-03-09 07:26:31,704][24121] Decorrelating experience for 672 frames... [2023-03-09 07:26:31,719][23232] Decorrelating experience for 704 frames... [2023-03-09 07:26:31,744][23230] Decorrelating experience for 832 frames... [2023-03-09 07:26:31,749][23088] Decorrelating experience for 864 frames... [2023-03-09 07:26:31,755][23187] Decorrelating experience for 512 frames... [2023-03-09 07:26:31,784][23103] Decorrelating experience for 544 frames... [2023-03-09 07:26:31,801][23961] Decorrelating experience for 544 frames... [2023-03-09 07:26:31,818][23226] Decorrelating experience for 576 frames... [2023-03-09 07:26:31,818][23177] Decorrelating experience for 768 frames... [2023-03-09 07:26:31,916][23207] Decorrelating experience for 608 frames... [2023-03-09 07:26:31,933][23636] Decorrelating experience for 896 frames... [2023-03-09 07:26:31,962][23485] Decorrelating experience for 928 frames... [2023-03-09 07:26:31,969][24352] Decorrelating experience for 480 frames... [2023-03-09 07:26:32,009][23089] Decorrelating experience for 832 frames... [2023-03-09 07:26:32,023][23215] Decorrelating experience for 544 frames... [2023-03-09 07:26:32,024][23204] Decorrelating experience for 704 frames... [2023-03-09 07:26:32,052][24158] Decorrelating experience for 704 frames... [2023-03-09 07:26:32,053][23202] Decorrelating experience for 896 frames... [2023-03-09 07:26:32,071][24666] Decorrelating experience for 832 frames... [2023-03-09 07:26:32,107][22664] Heartbeat connected on RolloutWorker_w116 [2023-03-09 07:26:32,173][23096] Decorrelating experience for 960 frames... [2023-03-09 07:26:32,174][23250] Decorrelating experience for 960 frames... [2023-03-09 07:26:32,178][23657] Decorrelating experience for 512 frames... [2023-03-09 07:26:32,209][23180] Decorrelating experience for 864 frames... [2023-03-09 07:26:32,229][24818] Decorrelating experience for 256 frames... [2023-03-09 07:26:32,236][23194] Decorrelating experience for 736 frames... [2023-03-09 07:26:32,239][23441] Decorrelating experience for 512 frames... [2023-03-09 07:26:32,258][23205] Decorrelating experience for 704 frames... [2023-03-09 07:26:32,258][23093] Decorrelating experience for 704 frames... [2023-03-09 07:26:32,281][32460] Decorrelating experience for 704 frames... [2023-03-09 07:26:32,376][23229] Decorrelating experience for 672 frames... [2023-03-09 07:26:32,387][23183] Decorrelating experience for 768 frames... [2023-03-09 07:26:32,411][23190] Decorrelating experience for 640 frames... [2023-03-09 07:26:32,438][23201] Decorrelating experience for 832 frames... [2023-03-09 07:26:32,443][23228] Decorrelating experience for 768 frames... [2023-03-09 07:26:32,446][23248] Decorrelating experience for 896 frames... [2023-03-09 07:26:32,472][23247] Decorrelating experience for 576 frames... [2023-03-09 07:26:32,472][23103] Decorrelating experience for 576 frames... [2023-03-09 07:26:32,490][23232] Decorrelating experience for 736 frames... [2023-03-09 07:26:32,534][24025] Decorrelating experience for 576 frames... [2023-03-09 07:26:32,626][23238] Decorrelating experience for 736 frames... [2023-03-09 07:26:32,629][23169] Decorrelating experience for 416 frames... [2023-03-09 07:26:32,651][23234] Decorrelating experience for 704 frames... [2023-03-09 07:26:32,656][23226] Decorrelating experience for 608 frames... [2023-03-09 07:26:32,676][23244] Decorrelating experience for 768 frames... [2023-03-09 07:26:32,695][23246] Decorrelating experience for 640 frames... [2023-03-09 07:26:32,720][24352] Decorrelating experience for 512 frames... [2023-03-09 07:26:32,724][23817] Decorrelating experience for 864 frames... [2023-03-09 07:26:32,757][23314] Decorrelating experience for 384 frames... [2023-03-09 07:26:32,811][23197] Decorrelating experience for 608 frames... [2023-03-09 07:26:32,834][23200] Decorrelating experience for 864 frames... [2023-03-09 07:26:32,855][23961] Decorrelating experience for 576 frames... [2023-03-09 07:26:32,859][23217] Decorrelating experience for 576 frames... [2023-03-09 07:26:32,901][23247] Decorrelating experience for 608 frames... [2023-03-09 07:26:32,926][23092] Decorrelating experience for 544 frames... [2023-03-09 07:26:32,929][23192] Decorrelating experience for 832 frames... [2023-03-09 07:26:32,959][23173] Decorrelating experience for 640 frames... [2023-03-09 07:26:32,961][23103] Decorrelating experience for 608 frames... [2023-03-09 07:26:33,024][23485] Decorrelating experience for 960 frames... [2023-03-09 07:26:33,027][23118] Decorrelating experience for 832 frames... [2023-03-09 07:26:33,041][23657] Decorrelating experience for 544 frames... [2023-03-09 07:26:33,061][23180] Decorrelating experience for 896 frames... [2023-03-09 07:26:33,066][23225] Decorrelating experience for 704 frames... [2023-03-09 07:26:33,108][23248] Decorrelating experience for 928 frames... [2023-03-09 07:26:33,133][23208] Decorrelating experience for 64 frames... [2023-03-09 07:26:33,135][24120] Decorrelating experience for 480 frames... [2023-03-09 07:26:33,168][24158] Decorrelating experience for 736 frames... [2023-03-09 07:26:33,171][24025] Decorrelating experience for 608 frames... [2023-03-09 07:26:33,233][23231] Decorrelating experience for 608 frames... [2023-03-09 07:26:33,241][23212] Decorrelating experience for 864 frames... [2023-03-09 07:26:33,247][23089] Decorrelating experience for 864 frames... [2023-03-09 07:26:33,279][23096] Decorrelating experience for 992 frames... [2023-03-09 07:26:33,281][23637] Decorrelating experience for 672 frames... [2023-03-09 07:26:33,325][24089] Decorrelating experience for 608 frames... [2023-03-09 07:26:33,335][23194] Decorrelating experience for 768 frames... [2023-03-09 07:26:33,342][23221] Decorrelating experience for 576 frames... [2023-03-09 07:26:33,377][32460] Decorrelating experience for 736 frames... [2023-03-09 07:26:33,383][23314] Decorrelating experience for 416 frames... [2023-03-09 07:26:33,449][23200] Decorrelating experience for 896 frames... [2023-03-09 07:26:33,453][23441] Decorrelating experience for 544 frames... [2023-03-09 07:26:33,503][23244] Decorrelating experience for 800 frames... [2023-03-09 07:26:33,503][23088] Decorrelating experience for 896 frames... [2023-03-09 07:26:33,539][24352] Decorrelating experience for 544 frames... [2023-03-09 07:26:33,549][23636] Decorrelating experience for 928 frames... [2023-03-09 07:26:33,562][23823] Decorrelating experience for 288 frames... [2023-03-09 07:26:33,580][23230] Decorrelating experience for 864 frames... [2023-03-09 07:26:33,665][23247] Decorrelating experience for 640 frames... [2023-03-09 07:26:33,666][24539] Decorrelating experience for 864 frames... [2023-03-09 07:26:33,677][23118] Decorrelating experience for 864 frames... [2023-03-09 07:26:33,680][23208] Decorrelating experience for 96 frames... [2023-03-09 07:26:33,682][22664] Heartbeat connected on RolloutWorker_w23 [2023-03-09 07:26:33,706][23097] Decorrelating experience for 768 frames... [2023-03-09 07:26:33,715][23210] Decorrelating experience for 768 frames... [2023-03-09 07:26:33,741][23217] Decorrelating experience for 608 frames... [2023-03-09 07:26:33,759][24158] Decorrelating experience for 768 frames... [2023-03-09 07:26:33,783][24818] Decorrelating experience for 288 frames... [2023-03-09 07:26:33,797][23240] Decorrelating experience for 736 frames... [2023-03-09 07:26:33,873][23817] Decorrelating experience for 896 frames... [2023-03-09 07:26:33,891][23221] Decorrelating experience for 608 frames... [2023-03-09 07:26:33,925][23194] Decorrelating experience for 800 frames... [2023-03-09 07:26:33,925][23212] Decorrelating experience for 896 frames... [2023-03-09 07:26:33,925][23662] Decorrelating experience for 736 frames... [2023-03-09 07:26:33,931][23207] Decorrelating experience for 640 frames... [2023-03-09 07:26:33,959][23174] Decorrelating experience for 480 frames... [2023-03-09 07:26:33,989][24666] Decorrelating experience for 864 frames... [2023-03-09 07:26:34,013][23089] Decorrelating experience for 896 frames... [2023-03-09 07:26:34,049][23191] Decorrelating experience for 480 frames... [2023-03-09 07:26:34,059][22664] Fps is (10 sec: 32767.7, 60 sec: 7645.9, 300 sec: 7057.7). Total num frames: 458752. Throughput: 0: 2465.4. Samples: 110944. Policy #0 lag: (min: 0.0, avg: 1.8, max: 3.0) [2023-03-09 07:26:34,060][22664] Avg episode reward: [(0, '3.829')] [2023-03-09 07:26:34,091][23203] Decorrelating experience for 800 frames... [2023-03-09 07:26:34,103][23225] Decorrelating experience for 736 frames... [2023-03-09 07:26:34,131][24089] Decorrelating experience for 640 frames... [2023-03-09 07:26:34,138][23178] Decorrelating experience for 352 frames... [2023-03-09 07:26:34,172][23196] Decorrelating experience for 928 frames... [2023-03-09 07:26:34,180][23235] Decorrelating experience for 768 frames... [2023-03-09 07:26:34,200][24793] Decorrelating experience for 864 frames... [2023-03-09 07:26:34,224][23204] Decorrelating experience for 736 frames... [2023-03-09 07:26:34,251][23636] Decorrelating experience for 960 frames... [2023-03-09 07:26:34,257][23098] Decorrelating experience for 640 frames... [2023-03-09 07:26:34,373][23211] Decorrelating experience for 736 frames... [2023-03-09 07:26:34,376][23961] Decorrelating experience for 608 frames... [2023-03-09 07:26:34,383][23657] Decorrelating experience for 576 frames... [2023-03-09 07:26:34,393][23314] Decorrelating experience for 448 frames... [2023-03-09 07:26:34,425][23234] Decorrelating experience for 736 frames... [2023-03-09 07:26:34,427][23171] Decorrelating experience for 928 frames... [2023-03-09 07:26:34,443][23230] Decorrelating experience for 896 frames... [2023-03-09 07:26:34,461][23228] Decorrelating experience for 800 frames... [2023-03-09 07:26:34,470][23525] Decorrelating experience for 928 frames... [2023-03-09 07:26:34,510][23090] Updated weights for policy 0, policy_version 30 (0.0010) [2023-03-09 07:26:34,546][23197] Decorrelating experience for 640 frames... [2023-03-09 07:26:34,589][23231] Decorrelating experience for 640 frames... [2023-03-09 07:26:34,591][23817] Decorrelating experience for 928 frames... [2023-03-09 07:26:34,612][24352] Decorrelating experience for 576 frames... [2023-03-09 07:26:34,653][23190] Decorrelating experience for 672 frames... [2023-03-09 07:26:34,653][23179] Decorrelating experience for 960 frames... [2023-03-09 07:26:34,656][23865] Decorrelating experience for 736 frames... [2023-03-09 07:26:34,661][23225] Decorrelating experience for 768 frames... [2023-03-09 07:26:34,680][23239] Decorrelating experience for 608 frames... [2023-03-09 07:26:34,741][23103] Decorrelating experience for 640 frames... [2023-03-09 07:26:34,785][23193] Decorrelating experience for 960 frames... [2023-03-09 07:26:34,841][23232] Decorrelating experience for 768 frames... [2023-03-09 07:26:34,850][23247] Decorrelating experience for 672 frames... [2023-03-09 07:26:34,867][23657] Decorrelating experience for 608 frames... [2023-03-09 07:26:34,917][24793] Decorrelating experience for 896 frames... [2023-03-09 07:26:34,918][23202] Decorrelating experience for 928 frames... [2023-03-09 07:26:34,918][24157] Decorrelating experience for 928 frames... [2023-03-09 07:26:34,919][23662] Decorrelating experience for 768 frames... [2023-03-09 07:26:34,933][23246] Decorrelating experience for 672 frames... [2023-03-09 07:26:34,991][23637] Decorrelating experience for 704 frames... [2023-03-09 07:26:34,998][23091] Decorrelating experience for 896 frames... [2023-03-09 07:26:35,044][23094] Decorrelating experience for 992 frames... [2023-03-09 07:26:35,054][23234] Decorrelating experience for 768 frames... [2023-03-09 07:26:35,118][23235] Decorrelating experience for 800 frames... [2023-03-09 07:26:35,129][23239] Decorrelating experience for 640 frames... [2023-03-09 07:26:35,140][24089] Decorrelating experience for 672 frames... [2023-03-09 07:26:35,228][23441] Decorrelating experience for 576 frames... [2023-03-09 07:26:35,245][23194] Decorrelating experience for 832 frames... [2023-03-09 07:26:35,246][23219] Decorrelating experience for 896 frames... [2023-03-09 07:26:35,252][23250] Decorrelating experience for 992 frames... [2023-03-09 07:26:35,253][23222] Decorrelating experience for 864 frames... [2023-03-09 07:26:35,294][23238] Decorrelating experience for 768 frames... [2023-03-09 07:26:35,297][23211] Decorrelating experience for 768 frames... [2023-03-09 07:26:35,348][23197] Decorrelating experience for 672 frames... [2023-03-09 07:26:35,356][23092] Decorrelating experience for 576 frames... [2023-03-09 07:26:35,357][23200] Decorrelating experience for 928 frames... [2023-03-09 07:26:35,446][24118] Decorrelating experience for 960 frames... [2023-03-09 07:26:35,452][23180] Decorrelating experience for 928 frames... [2023-03-09 07:26:35,498][24158] Decorrelating experience for 800 frames... [2023-03-09 07:26:35,499][23865] Decorrelating experience for 768 frames... [2023-03-09 07:26:35,504][23204] Decorrelating experience for 768 frames... [2023-03-09 07:26:35,526][22664] Heartbeat connected on RolloutWorker_w20 [2023-03-09 07:26:35,530][23221] Decorrelating experience for 640 frames... [2023-03-09 07:26:35,536][23182] Decorrelating experience for 672 frames... [2023-03-09 07:26:35,563][23636] Decorrelating experience for 992 frames... [2023-03-09 07:26:35,581][23817] Decorrelating experience for 960 frames... [2023-03-09 07:26:35,585][23118] Decorrelating experience for 896 frames... [2023-03-09 07:26:35,647][23196] Decorrelating experience for 960 frames... [2023-03-09 07:26:35,651][22664] Heartbeat connected on RolloutWorker_w79 [2023-03-09 07:26:35,697][24157] Decorrelating experience for 960 frames... [2023-03-09 07:26:35,715][24089] Decorrelating experience for 704 frames... [2023-03-09 07:26:35,724][23823] Decorrelating experience for 320 frames... [2023-03-09 07:26:35,740][24793] Decorrelating experience for 928 frames... [2023-03-09 07:26:35,745][23097] Decorrelating experience for 800 frames... [2023-03-09 07:26:35,772][23091] Decorrelating experience for 928 frames... [2023-03-09 07:26:35,807][24025] Decorrelating experience for 640 frames... [2023-03-09 07:26:35,811][23235] Decorrelating experience for 832 frames... [2023-03-09 07:26:35,818][24120] Decorrelating experience for 512 frames... [2023-03-09 07:26:35,883][23226] Decorrelating experience for 640 frames... [2023-03-09 07:26:35,928][23247] Decorrelating experience for 704 frames... [2023-03-09 07:26:35,945][24818] Decorrelating experience for 320 frames... [2023-03-09 07:26:35,951][23172] Decorrelating experience for 672 frames... [2023-03-09 07:26:35,967][22664] Heartbeat connected on RolloutWorker_w122 [2023-03-09 07:26:35,994][23637] Decorrelating experience for 736 frames... [2023-03-09 07:26:36,026][23171] Decorrelating experience for 960 frames... [2023-03-09 07:26:36,036][24158] Decorrelating experience for 832 frames... [2023-03-09 07:26:36,040][23179] Decorrelating experience for 992 frames... [2023-03-09 07:26:36,065][23211] Decorrelating experience for 800 frames... [2023-03-09 07:26:36,126][23230] Decorrelating experience for 928 frames... [2023-03-09 07:26:36,157][24352] Decorrelating experience for 608 frames... [2023-03-09 07:26:36,173][23221] Decorrelating experience for 672 frames... [2023-03-09 07:26:36,191][23207] Decorrelating experience for 672 frames... [2023-03-09 07:26:36,226][23174] Decorrelating experience for 512 frames... [2023-03-09 07:26:36,250][23092] Decorrelating experience for 608 frames... [2023-03-09 07:26:36,261][32460] Decorrelating experience for 768 frames... [2023-03-09 07:26:36,265][23097] Decorrelating experience for 832 frames... [2023-03-09 07:26:36,301][24118] Decorrelating experience for 992 frames... [2023-03-09 07:26:36,331][23662] Decorrelating experience for 800 frames... [2023-03-09 07:26:36,371][23227] Decorrelating experience for 704 frames... [2023-03-09 07:26:36,417][23246] Decorrelating experience for 704 frames... [2023-03-09 07:26:36,423][23226] Decorrelating experience for 672 frames... [2023-03-09 07:26:36,454][22664] Heartbeat connected on RolloutWorker_w33 [2023-03-09 07:26:36,485][23239] Decorrelating experience for 672 frames... [2023-03-09 07:26:36,485][23222] Decorrelating experience for 896 frames... [2023-03-09 07:26:36,504][23823] Decorrelating experience for 352 frames... [2023-03-09 07:26:36,504][23173] Decorrelating experience for 672 frames... [2023-03-09 07:26:36,507][23233] Decorrelating experience for 448 frames... [2023-03-09 07:26:36,512][24539] Decorrelating experience for 896 frames... [2023-03-09 07:26:36,534][23103] Decorrelating experience for 672 frames... [2023-03-09 07:26:36,569][23201] Decorrelating experience for 864 frames... [2023-03-09 07:26:36,624][23525] Decorrelating experience for 960 frames... [2023-03-09 07:26:36,677][23211] Decorrelating experience for 832 frames... [2023-03-09 07:26:36,723][24352] Decorrelating experience for 640 frames... [2023-03-09 07:26:36,727][23232] Decorrelating experience for 800 frames... [2023-03-09 07:26:36,731][23175] Decorrelating experience for 512 frames... [2023-03-09 07:26:36,732][23245] Decorrelating experience for 544 frames... [2023-03-09 07:26:36,772][23204] Decorrelating experience for 800 frames... [2023-03-09 07:26:36,780][23118] Decorrelating experience for 928 frames... [2023-03-09 07:26:36,801][22664] Heartbeat connected on RolloutWorker_w126 [2023-03-09 07:26:36,823][23174] Decorrelating experience for 544 frames... [2023-03-09 07:26:36,826][23244] Decorrelating experience for 832 frames... [2023-03-09 07:26:36,845][23193] Decorrelating experience for 992 frames... [2023-03-09 07:26:36,896][23097] Decorrelating experience for 864 frames... [2023-03-09 07:26:36,934][23202] Decorrelating experience for 960 frames... [2023-03-09 07:26:36,957][23866] Decorrelating experience for 832 frames... [2023-03-09 07:26:36,970][23234] Decorrelating experience for 800 frames... [2023-03-09 07:26:36,992][23226] Decorrelating experience for 704 frames... [2023-03-09 07:26:37,028][23207] Decorrelating experience for 704 frames... [2023-03-09 07:26:37,040][23197] Decorrelating experience for 704 frames... [2023-03-09 07:26:37,073][23222] Decorrelating experience for 928 frames... [2023-03-09 07:26:37,074][23225] Decorrelating experience for 800 frames... [2023-03-09 07:26:37,075][24120] Decorrelating experience for 544 frames... [2023-03-09 07:26:37,157][23235] Decorrelating experience for 864 frames... [2023-03-09 07:26:37,235][23240] Decorrelating experience for 768 frames... [2023-03-09 07:26:37,235][23637] Decorrelating experience for 768 frames... [2023-03-09 07:26:37,254][22664] Heartbeat connected on RolloutWorker_w22 [2023-03-09 07:26:37,262][23098] Decorrelating experience for 672 frames... [2023-03-09 07:26:37,270][24157] Decorrelating experience for 992 frames... [2023-03-09 07:26:37,271][23196] Decorrelating experience for 992 frames... [2023-03-09 07:26:37,271][23823] Decorrelating experience for 384 frames... [2023-03-09 07:26:37,287][23212] Decorrelating experience for 928 frames... [2023-03-09 07:26:37,299][23189] Decorrelating experience for 384 frames... [2023-03-09 07:26:37,304][23216] Decorrelating experience for 512 frames... [2023-03-09 07:26:37,389][23090] Updated weights for policy 0, policy_version 40 (0.0012) [2023-03-09 07:26:37,422][23230] Decorrelating experience for 960 frames... [2023-03-09 07:26:37,515][23177] Decorrelating experience for 800 frames... [2023-03-09 07:26:37,516][23231] Decorrelating experience for 672 frames... [2023-03-09 07:26:37,516][24158] Decorrelating experience for 864 frames... [2023-03-09 07:26:37,517][23171] Decorrelating experience for 992 frames... [2023-03-09 07:26:37,523][23091] Decorrelating experience for 960 frames... [2023-03-09 07:26:37,526][23174] Decorrelating experience for 576 frames... [2023-03-09 07:26:37,557][23241] Decorrelating experience for 480 frames... [2023-03-09 07:26:37,592][23232] Decorrelating experience for 832 frames... [2023-03-09 07:26:37,592][23634] Decorrelating experience for 832 frames... [2023-03-09 07:26:37,645][23204] Decorrelating experience for 832 frames... [2023-03-09 07:26:37,677][22664] Heartbeat connected on RolloutWorker_w31 [2023-03-09 07:26:37,678][22664] Heartbeat connected on RolloutWorker_w106 [2023-03-09 07:26:37,730][23233] Decorrelating experience for 480 frames... [2023-03-09 07:26:37,743][23180] Decorrelating experience for 960 frames... [2023-03-09 07:26:37,755][23243] Decorrelating experience for 736 frames... [2023-03-09 07:26:37,770][23213] Decorrelating experience for 800 frames... [2023-03-09 07:26:37,780][23217] Decorrelating experience for 640 frames... [2023-03-09 07:26:37,795][23207] Decorrelating experience for 736 frames... [2023-03-09 07:26:37,825][23247] Decorrelating experience for 736 frames... [2023-03-09 07:26:37,832][23662] Decorrelating experience for 832 frames... [2023-03-09 07:26:37,832][23089] Decorrelating experience for 928 frames... [2023-03-09 07:26:37,929][23175] Decorrelating experience for 544 frames... [2023-03-09 07:26:37,973][23203] Decorrelating experience for 832 frames... [2023-03-09 07:26:37,983][22664] Heartbeat connected on RolloutWorker_w3 [2023-03-09 07:26:37,989][23211] Decorrelating experience for 864 frames... [2023-03-09 07:26:38,001][23866] Decorrelating experience for 864 frames... [2023-03-09 07:26:38,006][23485] Decorrelating experience for 992 frames... [2023-03-09 07:26:38,043][23212] Decorrelating experience for 960 frames... [2023-03-09 07:26:38,065][24818] Decorrelating experience for 352 frames... [2023-03-09 07:26:38,080][23172] Decorrelating experience for 704 frames... [2023-03-09 07:26:38,080][23637] Decorrelating experience for 800 frames... [2023-03-09 07:26:38,082][23238] Decorrelating experience for 800 frames... [2023-03-09 07:26:38,224][23226] Decorrelating experience for 736 frames... [2023-03-09 07:26:38,227][23174] Decorrelating experience for 608 frames... [2023-03-09 07:26:38,259][24793] Decorrelating experience for 960 frames... [2023-03-09 07:26:38,271][23235] Decorrelating experience for 896 frames... [2023-03-09 07:26:38,272][23249] Decorrelating experience for 960 frames... [2023-03-09 07:26:38,308][23093] Decorrelating experience for 736 frames... [2023-03-09 07:26:38,319][23233] Decorrelating experience for 512 frames... [2023-03-09 07:26:38,323][23087] Decorrelating experience for 928 frames... [2023-03-09 07:26:38,345][23177] Decorrelating experience for 832 frames... [2023-03-09 07:26:38,348][23234] Decorrelating experience for 832 frames... [2023-03-09 07:26:38,436][23091] Decorrelating experience for 992 frames... [2023-03-09 07:26:38,472][23817] Decorrelating experience for 992 frames... [2023-03-09 07:26:38,494][23118] Decorrelating experience for 960 frames... [2023-03-09 07:26:38,495][23194] Decorrelating experience for 864 frames... [2023-03-09 07:26:38,522][23092] Decorrelating experience for 640 frames... [2023-03-09 07:26:38,524][23216] Decorrelating experience for 544 frames... [2023-03-09 07:26:38,528][22664] Heartbeat connected on RolloutWorker_w110 [2023-03-09 07:26:38,549][23441] Decorrelating experience for 608 frames... [2023-03-09 07:26:38,592][23187] Decorrelating experience for 544 frames... [2023-03-09 07:26:38,594][23217] Decorrelating experience for 672 frames... [2023-03-09 07:26:38,594][23243] Decorrelating experience for 768 frames... [2023-03-09 07:26:38,685][23211] Decorrelating experience for 896 frames... [2023-03-09 07:26:38,709][24539] Decorrelating experience for 928 frames... [2023-03-09 07:26:38,748][23227] Decorrelating experience for 736 frames... [2023-03-09 07:26:38,749][24089] Decorrelating experience for 736 frames... [2023-03-09 07:26:38,760][24158] Decorrelating experience for 896 frames... [2023-03-09 07:26:38,775][23175] Decorrelating experience for 576 frames... [2023-03-09 07:26:38,806][23244] Decorrelating experience for 864 frames... [2023-03-09 07:26:38,815][23248] Decorrelating experience for 960 frames... [2023-03-09 07:26:38,846][23247] Decorrelating experience for 768 frames... [2023-03-09 07:26:38,856][22664] Heartbeat connected on RolloutWorker_w11 [2023-03-09 07:26:38,896][22664] Heartbeat connected on RolloutWorker_w108 [2023-03-09 07:26:38,905][23232] Decorrelating experience for 864 frames... [2023-03-09 07:26:38,931][23225] Decorrelating experience for 832 frames... [2023-03-09 07:26:38,989][23240] Decorrelating experience for 800 frames... [2023-03-09 07:26:38,993][23185] Decorrelating experience for 608 frames... [2023-03-09 07:26:39,011][23314] Decorrelating experience for 480 frames... [2023-03-09 07:26:39,027][23226] Decorrelating experience for 768 frames... [2023-03-09 07:26:39,038][23865] Decorrelating experience for 800 frames... [2023-03-09 07:26:39,051][23249] Decorrelating experience for 992 frames... [2023-03-09 07:26:39,059][22664] Fps is (10 sec: 55707.7, 60 sec: 13380.3, 300 sec: 11468.8). Total num frames: 802816. Throughput: 0: 4750.9. Samples: 213792. Policy #0 lag: (min: 0.0, avg: 3.1, max: 7.0) [2023-03-09 07:26:39,059][22664] Avg episode reward: [(0, '3.633')] [2023-03-09 07:26:39,066][23210] Decorrelating experience for 800 frames... [2023-03-09 07:26:39,124][23441] Decorrelating experience for 640 frames... [2023-03-09 07:26:39,127][23238] Decorrelating experience for 832 frames... [2023-03-09 07:26:39,208][23239] Decorrelating experience for 704 frames... [2023-03-09 07:26:39,224][23090] Updated weights for policy 0, policy_version 50 (0.0012) [2023-03-09 07:26:39,225][23187] Decorrelating experience for 576 frames... [2023-03-09 07:26:39,260][23172] Decorrelating experience for 736 frames... [2023-03-09 07:26:39,261][23098] Decorrelating experience for 704 frames... [2023-03-09 07:26:39,301][23194] Decorrelating experience for 896 frames... [2023-03-09 07:26:39,303][23231] Decorrelating experience for 704 frames... [2023-03-09 07:26:39,304][23183] Decorrelating experience for 800 frames... [2023-03-09 07:26:39,311][23227] Decorrelating experience for 768 frames... [2023-03-09 07:26:39,343][24158] Decorrelating experience for 928 frames... [2023-03-09 07:26:39,398][23634] Decorrelating experience for 864 frames... [2023-03-09 07:26:39,449][23177] Decorrelating experience for 864 frames... [2023-03-09 07:26:39,505][23093] Decorrelating experience for 768 frames... [2023-03-09 07:26:39,509][23089] Decorrelating experience for 960 frames... [2023-03-09 07:26:39,524][23212] Decorrelating experience for 992 frames... [2023-03-09 07:26:39,531][23243] Decorrelating experience for 800 frames... [2023-03-09 07:26:39,547][23314] Decorrelating experience for 512 frames... [2023-03-09 07:26:39,578][23174] Decorrelating experience for 640 frames... [2023-03-09 07:26:39,587][23866] Decorrelating experience for 896 frames... [2023-03-09 07:26:39,597][24793] Decorrelating experience for 992 frames... [2023-03-09 07:26:39,604][22664] Heartbeat connected on RolloutWorker_w98 [2023-03-09 07:26:39,629][24089] Decorrelating experience for 768 frames... [2023-03-09 07:26:39,716][23235] Decorrelating experience for 928 frames... [2023-03-09 07:26:39,759][23118] Decorrelating experience for 992 frames... [2023-03-09 07:26:39,760][23189] Decorrelating experience for 416 frames... [2023-03-09 07:26:39,802][23228] Decorrelating experience for 832 frames... [2023-03-09 07:26:39,812][33428] Decorrelating experience for 768 frames... [2023-03-09 07:26:39,828][23232] Decorrelating experience for 896 frames... [2023-03-09 07:26:39,849][23092] Decorrelating experience for 672 frames... [2023-03-09 07:26:39,882][23173] Decorrelating experience for 704 frames... [2023-03-09 07:26:39,939][23098] Decorrelating experience for 736 frames... [2023-03-09 07:26:39,943][23244] Decorrelating experience for 896 frames... [2023-03-09 07:26:39,967][22664] Heartbeat connected on RolloutWorker_w77 [2023-03-09 07:26:40,004][23194] Decorrelating experience for 928 frames... [2023-03-09 07:26:40,011][23865] Decorrelating experience for 832 frames... [2023-03-09 07:26:40,039][23172] Decorrelating experience for 768 frames... [2023-03-09 07:26:40,070][23234] Decorrelating experience for 864 frames... [2023-03-09 07:26:40,086][23177] Decorrelating experience for 896 frames... [2023-03-09 07:26:40,103][23183] Decorrelating experience for 832 frames... [2023-03-09 07:26:40,110][24858] Decorrelating experience for 704 frames... [2023-03-09 07:26:40,132][22664] Heartbeat connected on RolloutWorker_w121 [2023-03-09 07:26:40,134][23089] Decorrelating experience for 992 frames... [2023-03-09 07:26:40,156][23185] Decorrelating experience for 640 frames... [2023-03-09 07:26:40,177][22664] Heartbeat connected on RolloutWorker_w41 [2023-03-09 07:26:40,213][23226] Decorrelating experience for 800 frames... [2023-03-09 07:26:40,240][23866] Decorrelating experience for 928 frames... [2023-03-09 07:26:40,255][23201] Decorrelating experience for 896 frames... [2023-03-09 07:26:40,298][24818] Decorrelating experience for 384 frames... [2023-03-09 07:26:40,339][23186] Decorrelating experience for 832 frames... [2023-03-09 07:26:40,349][23093] Decorrelating experience for 800 frames... [2023-03-09 07:26:40,354][23247] Decorrelating experience for 800 frames... [2023-03-09 07:26:40,382][23662] Decorrelating experience for 864 frames... [2023-03-09 07:26:40,383][24089] Decorrelating experience for 800 frames... [2023-03-09 07:26:40,415][23231] Decorrelating experience for 736 frames... [2023-03-09 07:26:40,437][23314] Decorrelating experience for 544 frames... [2023-03-09 07:26:40,458][23175] Decorrelating experience for 608 frames... [2023-03-09 07:26:40,474][23210] Decorrelating experience for 832 frames... [2023-03-09 07:26:40,568][22664] Heartbeat connected on RolloutWorker_w8 [2023-03-09 07:26:40,571][23215] Decorrelating experience for 576 frames... [2023-03-09 07:26:40,572][23239] Decorrelating experience for 736 frames... [2023-03-09 07:26:40,623][23238] Decorrelating experience for 864 frames... [2023-03-09 07:26:40,635][24120] Decorrelating experience for 576 frames... [2023-03-09 07:26:40,647][23246] Decorrelating experience for 736 frames... [2023-03-09 07:26:40,675][23092] Decorrelating experience for 704 frames... [2023-03-09 07:26:40,676][23180] Decorrelating experience for 992 frames... [2023-03-09 07:26:40,722][23192] Decorrelating experience for 864 frames... [2023-03-09 07:26:40,774][23090] Updated weights for policy 0, policy_version 60 (0.0010) [2023-03-09 07:26:40,780][23243] Decorrelating experience for 832 frames... [2023-03-09 07:26:40,804][23185] Decorrelating experience for 672 frames... [2023-03-09 07:26:40,851][33428] Decorrelating experience for 800 frames... [2023-03-09 07:26:40,890][23201] Decorrelating experience for 928 frames... [2023-03-09 07:26:40,890][23189] Decorrelating experience for 448 frames... [2023-03-09 07:26:40,891][23634] Decorrelating experience for 896 frames... [2023-03-09 07:26:40,902][32460] Decorrelating experience for 800 frames... [2023-03-09 07:26:40,907][23227] Decorrelating experience for 800 frames... [2023-03-09 07:26:40,947][24858] Decorrelating experience for 736 frames... [2023-03-09 07:26:40,947][23173] Decorrelating experience for 736 frames... [2023-03-09 07:26:41,000][23247] Decorrelating experience for 832 frames... [2023-03-09 07:26:41,043][23662] Decorrelating experience for 896 frames... [2023-03-09 07:26:41,118][22664] Heartbeat connected on RolloutWorker_w30 [2023-03-09 07:26:41,148][23210] Decorrelating experience for 864 frames... [2023-03-09 07:26:41,149][23225] Decorrelating experience for 864 frames... [2023-03-09 07:26:41,150][23635] Decorrelating experience for 544 frames... [2023-03-09 07:26:41,150][23186] Decorrelating experience for 864 frames... [2023-03-09 07:26:41,177][23961] Decorrelating experience for 640 frames... [2023-03-09 07:26:41,222][23175] Decorrelating experience for 640 frames... [2023-03-09 07:26:41,225][23213] Decorrelating experience for 832 frames... [2023-03-09 07:26:41,263][24539] Decorrelating experience for 960 frames... [2023-03-09 07:26:41,299][23244] Decorrelating experience for 928 frames... [2023-03-09 07:26:41,406][23181] Decorrelating experience for 896 frames... [2023-03-09 07:26:41,425][23226] Decorrelating experience for 832 frames... [2023-03-09 07:26:41,445][23207] Decorrelating experience for 768 frames... [2023-03-09 07:26:41,453][23314] Decorrelating experience for 576 frames... [2023-03-09 07:26:41,470][23232] Decorrelating experience for 928 frames... [2023-03-09 07:26:41,479][23238] Decorrelating experience for 896 frames... [2023-03-09 07:26:41,491][24858] Decorrelating experience for 768 frames... [2023-03-09 07:26:41,497][23177] Decorrelating experience for 928 frames... [2023-03-09 07:26:41,564][23234] Decorrelating experience for 896 frames... [2023-03-09 07:26:41,595][23634] Decorrelating experience for 928 frames... [2023-03-09 07:26:41,624][23200] Decorrelating experience for 960 frames... [2023-03-09 07:26:41,649][23204] Decorrelating experience for 864 frames... [2023-03-09 07:26:41,702][23865] Decorrelating experience for 864 frames... [2023-03-09 07:26:41,726][23092] Decorrelating experience for 736 frames... [2023-03-09 07:26:41,726][23239] Decorrelating experience for 768 frames... [2023-03-09 07:26:41,739][32460] Decorrelating experience for 832 frames... [2023-03-09 07:26:41,740][23191] Decorrelating experience for 512 frames... [2023-03-09 07:26:41,809][23173] Decorrelating experience for 768 frames... [2023-03-09 07:26:41,848][23225] Decorrelating experience for 896 frames... [2023-03-09 07:26:41,849][23192] Decorrelating experience for 896 frames... [2023-03-09 07:26:41,925][23183] Decorrelating experience for 864 frames... [2023-03-09 07:26:41,933][23227] Decorrelating experience for 832 frames... [2023-03-09 07:26:41,976][24089] Decorrelating experience for 832 frames... [2023-03-09 07:26:41,987][23201] Decorrelating experience for 960 frames... [2023-03-09 07:26:41,987][24158] Decorrelating experience for 960 frames... [2023-03-09 07:26:42,042][23090] Updated weights for policy 0, policy_version 70 (0.0010) [2023-03-09 07:26:42,071][23867] Decorrelating experience for 416 frames... [2023-03-09 07:26:42,085][24120] Decorrelating experience for 608 frames... [2023-03-09 07:26:42,188][23216] Decorrelating experience for 576 frames... [2023-03-09 07:26:42,189][23207] Decorrelating experience for 800 frames... [2023-03-09 07:26:42,190][23103] Decorrelating experience for 704 frames... [2023-03-09 07:26:42,191][23226] Decorrelating experience for 864 frames... [2023-03-09 07:26:42,240][23243] Decorrelating experience for 864 frames... [2023-03-09 07:26:42,240][23635] Decorrelating experience for 576 frames... [2023-03-09 07:26:42,241][23247] Decorrelating experience for 864 frames... [2023-03-09 07:26:42,245][23087] Decorrelating experience for 960 frames... [2023-03-09 07:26:42,347][23244] Decorrelating experience for 960 frames... [2023-03-09 07:26:42,353][23186] Decorrelating experience for 896 frames... [2023-03-09 07:26:42,420][23092] Decorrelating experience for 768 frames... [2023-03-09 07:26:42,502][23232] Decorrelating experience for 960 frames... [2023-03-09 07:26:42,504][23867] Decorrelating experience for 448 frames... [2023-03-09 07:26:42,506][23246] Decorrelating experience for 768 frames... [2023-03-09 07:26:42,507][33428] Decorrelating experience for 832 frames... [2023-03-09 07:26:42,514][23200] Decorrelating experience for 992 frames... [2023-03-09 07:26:42,558][23173] Decorrelating experience for 800 frames... [2023-03-09 07:26:42,592][24858] Decorrelating experience for 800 frames... [2023-03-09 07:26:42,614][23245] Decorrelating experience for 576 frames... [2023-03-09 07:26:42,625][24158] Decorrelating experience for 992 frames... [2023-03-09 07:26:42,679][23234] Decorrelating experience for 928 frames... [2023-03-09 07:26:42,742][23314] Decorrelating experience for 608 frames... [2023-03-09 07:26:42,749][22940] Signal inference workers to stop experience collection... [2023-03-09 07:26:42,749][22940] Signal inference workers to resume experience collection... [2023-03-09 07:26:42,765][23525] Decorrelating experience for 992 frames... [2023-03-09 07:26:42,766][23201] Decorrelating experience for 992 frames... [2023-03-09 07:26:42,768][23208] Decorrelating experience for 128 frames... [2023-03-09 07:26:42,775][23181] Decorrelating experience for 928 frames... [2023-03-09 07:26:42,790][23090] InferenceWorker_p0-w0: stopping experience collection [2023-03-09 07:26:42,791][23090] InferenceWorker_p0-w0: resuming experience collection [2023-03-09 07:26:42,820][23204] Decorrelating experience for 896 frames... [2023-03-09 07:26:42,844][23191] Decorrelating experience for 544 frames... [2023-03-09 07:26:42,870][23099] Another process currently holds the lock /tmp/sf2_rolo/doom_002.lockfile, attempt: 1 [2023-03-09 07:26:42,876][23190] Decorrelating experience for 704 frames... [2023-03-09 07:26:42,914][23867] Decorrelating experience for 480 frames... [2023-03-09 07:26:42,961][23189] Decorrelating experience for 480 frames... [2023-03-09 07:26:42,990][23239] Decorrelating experience for 800 frames... [2023-03-09 07:26:43,007][24818] Decorrelating experience for 416 frames... [2023-03-09 07:26:43,008][23441] Decorrelating experience for 672 frames... [2023-03-09 07:26:43,036][23248] Decorrelating experience for 992 frames... [2023-03-09 07:26:43,042][22664] Heartbeat connected on RolloutWorker_w47 [2023-03-09 07:26:43,066][23227] Decorrelating experience for 864 frames... [2023-03-09 07:26:43,071][22664] Heartbeat connected on RolloutWorker_w112 [2023-03-09 07:26:43,072][23635] Decorrelating experience for 608 frames... [2023-03-09 07:26:43,099][23219] Decorrelating experience for 928 frames... [2023-03-09 07:26:43,188][32460] Decorrelating experience for 864 frames... [2023-03-09 07:26:43,202][22664] Heartbeat connected on RolloutWorker_w104 [2023-03-09 07:26:43,204][23186] Decorrelating experience for 928 frames... [2023-03-09 07:26:43,227][22664] Heartbeat connected on RolloutWorker_w50 [2023-03-09 07:26:43,238][23247] Decorrelating experience for 896 frames... [2023-03-09 07:26:43,244][23097] Decorrelating experience for 896 frames... [2023-03-09 07:26:43,283][23866] Decorrelating experience for 960 frames... [2023-03-09 07:26:43,291][23090] Updated weights for policy 0, policy_version 80 (0.0011) [2023-03-09 07:26:43,301][23173] Decorrelating experience for 832 frames... [2023-03-09 07:26:43,343][23634] Decorrelating experience for 960 frames... [2023-03-09 07:26:43,343][23172] Decorrelating experience for 800 frames... [2023-03-09 07:26:43,345][23207] Decorrelating experience for 832 frames... [2023-03-09 07:26:43,419][23088] Decorrelating experience for 928 frames... [2023-03-09 07:26:43,466][23187] Decorrelating experience for 608 frames... [2023-03-09 07:26:43,488][23192] Decorrelating experience for 928 frames... [2023-03-09 07:26:43,517][23174] Decorrelating experience for 672 frames... [2023-03-09 07:26:43,531][23243] Decorrelating experience for 896 frames... [2023-03-09 07:26:43,544][23190] Decorrelating experience for 736 frames... [2023-03-09 07:26:43,577][24858] Decorrelating experience for 832 frames... [2023-03-09 07:26:43,590][23213] Decorrelating experience for 864 frames... [2023-03-09 07:26:43,601][23244] Decorrelating experience for 992 frames... [2023-03-09 07:26:43,603][22664] Heartbeat connected on RolloutWorker_w95 [2023-03-09 07:26:43,616][23234] Decorrelating experience for 960 frames... [2023-03-09 07:26:43,634][23197] Decorrelating experience for 736 frames... [2023-03-09 07:26:43,689][23204] Decorrelating experience for 928 frames... [2023-03-09 07:26:43,762][23246] Decorrelating experience for 800 frames... [2023-03-09 07:26:43,806][23181] Decorrelating experience for 960 frames... [2023-03-09 07:26:43,826][23098] Decorrelating experience for 768 frames... [2023-03-09 07:26:43,847][23182] Decorrelating experience for 704 frames... [2023-03-09 07:26:43,847][23441] Decorrelating experience for 704 frames... [2023-03-09 07:26:43,856][23185] Decorrelating experience for 704 frames... [2023-03-09 07:26:43,866][23235] Decorrelating experience for 960 frames... [2023-03-09 07:26:43,903][23230] Decorrelating experience for 992 frames... [2023-03-09 07:26:43,917][23097] Decorrelating experience for 928 frames... [2023-03-09 07:26:43,970][23187] Decorrelating experience for 640 frames... [2023-03-09 07:26:44,010][23208] Decorrelating experience for 160 frames... [2023-03-09 07:26:44,053][23237] Decorrelating experience for 704 frames... [2023-03-09 07:26:44,058][22664] Fps is (10 sec: 93389.6, 60 sec: 23210.7, 300 sec: 18568.5). Total num frames: 1392640. Throughput: 0: 6755.9. Samples: 304016. Policy #0 lag: (min: 0.0, avg: 4.9, max: 11.0) [2023-03-09 07:26:44,059][22664] Avg episode reward: [(0, '4.045')] [2023-03-09 07:26:44,081][23215] Decorrelating experience for 608 frames... [2023-03-09 07:26:44,103][22664] Heartbeat connected on RolloutWorker_w76 [2023-03-09 07:26:44,131][23219] Decorrelating experience for 960 frames... [2023-03-09 07:26:44,180][24818] Decorrelating experience for 448 frames... [2023-03-09 07:26:44,208][23240] Decorrelating experience for 832 frames... [2023-03-09 07:26:44,208][23226] Decorrelating experience for 896 frames... [2023-03-09 07:26:44,209][23866] Decorrelating experience for 992 frames... [2023-03-09 07:26:44,210][23216] Decorrelating experience for 608 frames... [2023-03-09 07:26:44,255][23190] Decorrelating experience for 768 frames... [2023-03-09 07:26:44,314][23208] Decorrelating experience for 192 frames... [2023-03-09 07:26:44,315][23192] Decorrelating experience for 960 frames... [2023-03-09 07:26:44,346][23238] Decorrelating experience for 928 frames... [2023-03-09 07:26:44,455][23657] Decorrelating experience for 640 frames... [2023-03-09 07:26:44,476][23092] Decorrelating experience for 800 frames... [2023-03-09 07:26:44,476][23213] Decorrelating experience for 896 frames... [2023-03-09 07:26:44,476][22664] Heartbeat connected on RolloutWorker_w52 [2023-03-09 07:26:44,477][23098] Decorrelating experience for 800 frames... [2023-03-09 07:26:44,514][23197] Decorrelating experience for 768 frames... [2023-03-09 07:26:44,522][23314] Decorrelating experience for 640 frames... [2023-03-09 07:26:44,537][23090] Updated weights for policy 0, policy_version 90 (0.0011) [2023-03-09 07:26:44,544][23207] Decorrelating experience for 864 frames... [2023-03-09 07:26:44,568][24858] Decorrelating experience for 864 frames... [2023-03-09 07:26:44,607][23182] Decorrelating experience for 736 frames... [2023-03-09 07:26:44,609][23183] Decorrelating experience for 896 frames... [2023-03-09 07:26:44,692][23175] Decorrelating experience for 672 frames... [2023-03-09 07:26:44,706][23228] Decorrelating experience for 864 frames... [2023-03-09 07:26:44,761][23865] Decorrelating experience for 896 frames... [2023-03-09 07:26:44,765][23237] Decorrelating experience for 736 frames... [2023-03-09 07:26:44,787][23217] Decorrelating experience for 704 frames... [2023-03-09 07:26:44,833][33428] Decorrelating experience for 864 frames... [2023-03-09 07:26:44,834][22664] Heartbeat connected on RolloutWorker_w111 [2023-03-09 07:26:44,846][23216] Decorrelating experience for 640 frames... [2023-03-09 07:26:44,871][23211] Decorrelating experience for 928 frames... [2023-03-09 07:26:44,922][23172] Decorrelating experience for 832 frames... [2023-03-09 07:26:44,926][23093] Decorrelating experience for 832 frames... [2023-03-09 07:26:45,015][23191] Decorrelating experience for 576 frames... [2023-03-09 07:26:45,054][23233] Decorrelating experience for 544 frames... [2023-03-09 07:26:45,055][23637] Decorrelating experience for 832 frames... [2023-03-09 07:26:45,083][23234] Decorrelating experience for 992 frames... [2023-03-09 07:26:45,112][23213] Decorrelating experience for 928 frames... [2023-03-09 07:26:45,149][23208] Decorrelating experience for 224 frames... [2023-03-09 07:26:45,151][23246] Decorrelating experience for 832 frames... [2023-03-09 07:26:45,189][23203] Decorrelating experience for 864 frames... [2023-03-09 07:26:45,240][23174] Decorrelating experience for 704 frames... [2023-03-09 07:26:45,249][23823] Decorrelating experience for 416 frames... [2023-03-09 07:26:45,298][23097] Decorrelating experience for 960 frames... [2023-03-09 07:26:45,344][23228] Decorrelating experience for 896 frames... [2023-03-09 07:26:45,347][23190] Decorrelating experience for 800 frames... [2023-03-09 07:26:45,354][24858] Decorrelating experience for 896 frames... [2023-03-09 07:26:45,372][23215] Decorrelating experience for 640 frames... [2023-03-09 07:26:45,398][23103] Decorrelating experience for 736 frames... [2023-03-09 07:26:45,423][23099] Decorrelating experience for 800 frames... [2023-03-09 07:26:45,475][23192] Decorrelating experience for 992 frames... [2023-03-09 07:26:45,565][23087] Decorrelating experience for 992 frames... [2023-03-09 07:26:45,566][23090] Updated weights for policy 0, policy_version 100 (0.0012) [2023-03-09 07:26:45,577][23226] Decorrelating experience for 928 frames... [2023-03-09 07:26:45,582][23247] Decorrelating experience for 928 frames... [2023-03-09 07:26:45,614][23186] Decorrelating experience for 960 frames... [2023-03-09 07:26:45,644][23175] Decorrelating experience for 704 frames... [2023-03-09 07:26:45,648][23237] Decorrelating experience for 768 frames... [2023-03-09 07:26:45,669][23205] Decorrelating experience for 736 frames... [2023-03-09 07:26:45,682][23657] Decorrelating experience for 672 frames... [2023-03-09 07:26:45,723][22664] Heartbeat connected on RolloutWorker_w58 [2023-03-09 07:26:45,791][23243] Decorrelating experience for 928 frames... [2023-03-09 07:26:45,812][23216] Decorrelating experience for 672 frames... [2023-03-09 07:26:45,829][23245] Decorrelating experience for 608 frames... [2023-03-09 07:26:45,896][23314] Decorrelating experience for 672 frames... [2023-03-09 07:26:45,898][23182] Decorrelating experience for 768 frames... [2023-03-09 07:26:45,935][23441] Decorrelating experience for 736 frames... [2023-03-09 07:26:45,939][24120] Decorrelating experience for 640 frames... [2023-03-09 07:26:46,004][23181] Decorrelating experience for 992 frames... [2023-03-09 07:26:46,006][23172] Decorrelating experience for 864 frames... [2023-03-09 07:26:46,026][23865] Decorrelating experience for 928 frames... [2023-03-09 07:26:46,079][23099] Decorrelating experience for 832 frames... [2023-03-09 07:26:46,128][22664] Heartbeat connected on RolloutWorker_w28 [2023-03-09 07:26:46,143][23194] Decorrelating experience for 960 frames... [2023-03-09 07:26:46,147][23222] Decorrelating experience for 960 frames... [2023-03-09 07:26:46,173][23088] Decorrelating experience for 960 frames... [2023-03-09 07:26:46,220][22664] Heartbeat connected on RolloutWorker_w2 [2023-03-09 07:26:46,238][23205] Decorrelating experience for 768 frames... [2023-03-09 07:26:46,251][24025] Decorrelating experience for 672 frames... [2023-03-09 07:26:46,324][23190] Decorrelating experience for 832 frames... [2023-03-09 07:26:46,348][23235] Decorrelating experience for 992 frames... [2023-03-09 07:26:46,408][23240] Decorrelating experience for 864 frames... [2023-03-09 07:26:46,409][24352] Decorrelating experience for 672 frames... [2023-03-09 07:26:46,412][23246] Decorrelating experience for 864 frames... [2023-03-09 07:26:46,417][23635] Decorrelating experience for 640 frames... [2023-03-09 07:26:46,491][23208] Decorrelating experience for 256 frames... [2023-03-09 07:26:46,496][23090] Updated weights for policy 0, policy_version 110 (0.0010) [2023-03-09 07:26:46,552][23174] Decorrelating experience for 736 frames... [2023-03-09 07:26:46,566][24818] Decorrelating experience for 480 frames... [2023-03-09 07:26:46,646][22664] Heartbeat connected on RolloutWorker_w39 [2023-03-09 07:26:46,650][23657] Decorrelating experience for 704 frames... [2023-03-09 07:26:46,667][23204] Decorrelating experience for 960 frames... [2023-03-09 07:26:46,678][23207] Decorrelating experience for 896 frames... [2023-03-09 07:26:46,704][23099] Decorrelating experience for 864 frames... [2023-03-09 07:26:46,740][24666] Decorrelating experience for 896 frames... [2023-03-09 07:26:46,744][24858] Decorrelating experience for 928 frames... [2023-03-09 07:26:46,753][23237] Decorrelating experience for 800 frames... [2023-03-09 07:26:46,763][23172] Decorrelating experience for 896 frames... [2023-03-09 07:26:46,791][23228] Decorrelating experience for 928 frames... [2023-03-09 07:26:46,894][23088] Decorrelating experience for 992 frames... [2023-03-09 07:26:46,897][23226] Decorrelating experience for 960 frames... [2023-03-09 07:26:46,945][23314] Decorrelating experience for 704 frames... [2023-03-09 07:26:46,988][22664] Heartbeat connected on RolloutWorker_w90 [2023-03-09 07:26:46,998][23215] Decorrelating experience for 672 frames... [2023-03-09 07:26:47,047][23175] Decorrelating experience for 736 frames... [2023-03-09 07:26:47,048][24352] Decorrelating experience for 704 frames... [2023-03-09 07:26:47,049][32460] Decorrelating experience for 896 frames... [2023-03-09 07:26:47,074][23441] Decorrelating experience for 768 frames... [2023-03-09 07:26:47,106][23221] Decorrelating experience for 704 frames... [2023-03-09 07:26:47,137][23103] Decorrelating experience for 768 frames... [2023-03-09 07:26:47,144][23205] Decorrelating experience for 800 frames... [2023-03-09 07:26:47,215][23637] Decorrelating experience for 864 frames... [2023-03-09 07:26:47,294][24818] Decorrelating experience for 512 frames... [2023-03-09 07:26:47,298][23190] Decorrelating experience for 864 frames... [2023-03-09 07:26:47,308][23174] Decorrelating experience for 768 frames... [2023-03-09 07:26:47,321][23194] Decorrelating experience for 992 frames... [2023-03-09 07:26:47,350][22664] Heartbeat connected on RolloutWorker_w5 [2023-03-09 07:26:47,378][23823] Decorrelating experience for 448 frames... [2023-03-09 07:26:47,379][24025] Decorrelating experience for 704 frames... [2023-03-09 07:26:47,379][23090] Updated weights for policy 0, policy_version 120 (0.0011) [2023-03-09 07:26:47,433][23182] Decorrelating experience for 800 frames... [2023-03-09 07:26:47,455][23657] Decorrelating experience for 736 frames... [2023-03-09 07:26:47,468][23097] Decorrelating experience for 992 frames... [2023-03-09 07:26:47,534][23207] Decorrelating experience for 928 frames... [2023-03-09 07:26:47,540][23210] Decorrelating experience for 896 frames... [2023-03-09 07:26:47,550][24858] Decorrelating experience for 960 frames... [2023-03-09 07:26:47,581][23211] Decorrelating experience for 960 frames... [2023-03-09 07:26:47,594][23175] Decorrelating experience for 768 frames... [2023-03-09 07:26:47,661][23441] Decorrelating experience for 800 frames... [2023-03-09 07:26:47,678][23173] Decorrelating experience for 864 frames... [2023-03-09 07:26:47,688][23237] Decorrelating experience for 832 frames... [2023-03-09 07:26:47,710][23093] Decorrelating experience for 864 frames... [2023-03-09 07:26:47,745][23246] Decorrelating experience for 896 frames... [2023-03-09 07:26:47,773][22664] Heartbeat connected on RolloutWorker_w25 [2023-03-09 07:26:47,855][23203] Decorrelating experience for 896 frames... [2023-03-09 07:26:47,855][23222] Decorrelating experience for 992 frames... [2023-03-09 07:26:47,898][23186] Decorrelating experience for 992 frames... [2023-03-09 07:26:47,930][23172] Decorrelating experience for 928 frames... [2023-03-09 07:26:47,956][23189] Decorrelating experience for 512 frames... [2023-03-09 07:26:47,960][23226] Decorrelating experience for 992 frames... [2023-03-09 07:26:47,978][23208] Decorrelating experience for 288 frames... [2023-03-09 07:26:47,990][23185] Decorrelating experience for 736 frames... [2023-03-09 07:26:47,992][23221] Decorrelating experience for 736 frames... [2023-03-09 07:26:48,042][23823] Decorrelating experience for 480 frames... [2023-03-09 07:26:48,083][22664] Heartbeat connected on RolloutWorker_w29 [2023-03-09 07:26:48,127][23662] Decorrelating experience for 928 frames... [2023-03-09 07:26:48,138][23190] Decorrelating experience for 896 frames... [2023-03-09 07:26:48,170][24121] Decorrelating experience for 704 frames... [2023-03-09 07:26:48,225][23103] Decorrelating experience for 800 frames... [2023-03-09 07:26:48,226][24858] Decorrelating experience for 992 frames... [2023-03-09 07:26:48,231][23215] Decorrelating experience for 704 frames... [2023-03-09 07:26:48,294][24120] Decorrelating experience for 672 frames... [2023-03-09 07:26:48,382][23233] Decorrelating experience for 576 frames... [2023-03-09 07:26:48,424][22664] Heartbeat connected on RolloutWorker_w72 [2023-03-09 07:26:48,432][24352] Decorrelating experience for 736 frames... [2023-03-09 07:26:48,446][23216] Decorrelating experience for 704 frames... [2023-03-09 07:26:48,462][23228] Decorrelating experience for 960 frames... [2023-03-09 07:26:48,464][22664] Heartbeat connected on RolloutWorker_w4 [2023-03-09 07:26:48,470][23177] Decorrelating experience for 960 frames... [2023-03-09 07:26:48,475][23090] Updated weights for policy 0, policy_version 130 (0.0010) [2023-03-09 07:26:48,482][23093] Decorrelating experience for 896 frames... [2023-03-09 07:26:48,532][22664] Heartbeat connected on RolloutWorker_w87 [2023-03-09 07:26:48,545][23202] Decorrelating experience for 992 frames... [2023-03-09 07:26:48,558][23246] Decorrelating experience for 928 frames... [2023-03-09 07:26:48,621][23204] Decorrelating experience for 992 frames... [2023-03-09 07:26:48,640][23203] Decorrelating experience for 928 frames... [2023-03-09 07:26:48,680][22664] Heartbeat connected on RolloutWorker_w124 [2023-03-09 07:26:48,698][23237] Decorrelating experience for 864 frames... [2023-03-09 07:26:48,733][23191] Decorrelating experience for 608 frames... [2023-03-09 07:26:48,789][23092] Decorrelating experience for 832 frames... [2023-03-09 07:26:48,801][23207] Decorrelating experience for 960 frames... [2023-03-09 07:26:48,812][23182] Decorrelating experience for 832 frames... [2023-03-09 07:26:48,845][23314] Decorrelating experience for 736 frames... [2023-03-09 07:26:48,907][23103] Decorrelating experience for 832 frames... [2023-03-09 07:26:48,931][23635] Decorrelating experience for 672 frames... [2023-03-09 07:26:49,000][24089] Decorrelating experience for 864 frames... [2023-03-09 07:26:49,015][22664] Heartbeat connected on RolloutWorker_w43 [2023-03-09 07:26:49,017][23233] Decorrelating experience for 608 frames... [2023-03-09 07:26:49,055][24025] Decorrelating experience for 736 frames... [2023-03-09 07:26:49,059][22664] Fps is (10 sec: 142540.7, 60 sec: 37137.1, 300 sec: 27852.8). Total num frames: 2228224. Throughput: 0: 12008.2. Samples: 540368. Policy #0 lag: (min: 2.0, avg: 6.7, max: 14.0) [2023-03-09 07:26:49,060][22664] Avg episode reward: [(0, '4.081')] [2023-03-09 07:26:49,102][23241] Decorrelating experience for 512 frames... [2023-03-09 07:26:49,105][23093] Decorrelating experience for 928 frames... [2023-03-09 07:26:49,135][24120] Decorrelating experience for 704 frames... [2023-03-09 07:26:49,149][22664] Heartbeat connected on RolloutWorker_w56 [2023-03-09 07:26:49,246][24352] Decorrelating experience for 768 frames... [2023-03-09 07:26:49,252][23208] Decorrelating experience for 320 frames... [2023-03-09 07:26:49,277][23221] Decorrelating experience for 768 frames... [2023-03-09 07:26:49,284][23867] Decorrelating experience for 512 frames... [2023-03-09 07:26:49,345][23187] Decorrelating experience for 672 frames... [2023-03-09 07:26:49,362][23237] Decorrelating experience for 896 frames... [2023-03-09 07:26:49,424][23203] Decorrelating experience for 960 frames... [2023-03-09 07:26:49,513][23216] Decorrelating experience for 736 frames... [2023-03-09 07:26:49,514][23635] Decorrelating experience for 704 frames... [2023-03-09 07:26:49,523][23189] Decorrelating experience for 544 frames... [2023-03-09 07:26:49,543][23183] Decorrelating experience for 928 frames... [2023-03-09 07:26:49,608][23233] Decorrelating experience for 640 frames... [2023-03-09 07:26:49,612][23173] Decorrelating experience for 896 frames... [2023-03-09 07:26:49,629][23182] Decorrelating experience for 864 frames... [2023-03-09 07:26:49,630][23090] Updated weights for policy 0, policy_version 140 (0.0010) [2023-03-09 07:26:49,647][23241] Decorrelating experience for 544 frames... [2023-03-09 07:26:49,706][23208] Decorrelating experience for 352 frames... [2023-03-09 07:26:49,756][23197] Decorrelating experience for 800 frames... [2023-03-09 07:26:49,764][24120] Decorrelating experience for 736 frames... [2023-03-09 07:26:49,770][23177] Decorrelating experience for 992 frames... [2023-03-09 07:26:49,797][23657] Decorrelating experience for 768 frames... [2023-03-09 07:26:49,834][23232] Decorrelating experience for 992 frames... [2023-03-09 07:26:49,851][24818] Decorrelating experience for 544 frames... [2023-03-09 07:26:49,892][23187] Decorrelating experience for 704 frames... [2023-03-09 07:26:49,892][23823] Decorrelating experience for 512 frames... [2023-03-09 07:26:49,930][23221] Decorrelating experience for 800 frames... [2023-03-09 07:26:49,967][23867] Decorrelating experience for 544 frames... [2023-03-09 07:26:50,038][23865] Decorrelating experience for 960 frames... [2023-03-09 07:26:50,039][23213] Decorrelating experience for 960 frames... [2023-03-09 07:26:50,039][24352] Decorrelating experience for 800 frames... [2023-03-09 07:26:50,115][23231] Decorrelating experience for 768 frames... [2023-03-09 07:26:50,168][23092] Decorrelating experience for 864 frames... [2023-03-09 07:26:50,207][23233] Decorrelating experience for 672 frames... [2023-03-09 07:26:50,239][23219] Decorrelating experience for 992 frames... [2023-03-09 07:26:50,239][22664] Heartbeat connected on RolloutWorker_w27 [2023-03-09 07:26:50,291][23093] Decorrelating experience for 960 frames... [2023-03-09 07:26:50,293][22664] Heartbeat connected on RolloutWorker_w49 [2023-03-09 07:26:50,310][23178] Decorrelating experience for 384 frames... [2023-03-09 07:26:50,343][23225] Decorrelating experience for 928 frames... [2023-03-09 07:26:50,396][23169] Decorrelating experience for 448 frames... [2023-03-09 07:26:50,443][33428] Decorrelating experience for 896 frames... [2023-03-09 07:26:50,484][23090] Updated weights for policy 0, policy_version 150 (0.0013) [2023-03-09 07:26:50,487][23172] Decorrelating experience for 960 frames... [2023-03-09 07:26:50,496][23657] Decorrelating experience for 800 frames... [2023-03-09 07:26:50,517][23241] Decorrelating experience for 576 frames... [2023-03-09 07:26:50,538][23208] Decorrelating experience for 384 frames... [2023-03-09 07:26:50,560][23173] Decorrelating experience for 928 frames... [2023-03-09 07:26:50,579][23240] Decorrelating experience for 896 frames... [2023-03-09 07:26:50,623][23314] Decorrelating experience for 768 frames... [2023-03-09 07:26:50,742][24025] Decorrelating experience for 768 frames... [2023-03-09 07:26:50,742][23865] Decorrelating experience for 992 frames... [2023-03-09 07:26:50,760][23178] Decorrelating experience for 416 frames... [2023-03-09 07:26:50,810][23189] Decorrelating experience for 576 frames... [2023-03-09 07:26:50,812][22664] Heartbeat connected on RolloutWorker_w89 [2023-03-09 07:26:50,826][23183] Decorrelating experience for 960 frames... [2023-03-09 07:26:50,839][24352] Decorrelating experience for 832 frames... [2023-03-09 07:26:50,861][23185] Decorrelating experience for 768 frames... [2023-03-09 07:26:50,908][23236] Another process currently holds the lock /tmp/sf2_rolo/doom_002.lockfile, attempt: 1 [2023-03-09 07:26:50,913][23103] Decorrelating experience for 864 frames... [2023-03-09 07:26:50,941][23229] Decorrelating experience for 704 frames... [2023-03-09 07:26:51,041][23092] Decorrelating experience for 896 frames... [2023-03-09 07:26:51,070][24121] Decorrelating experience for 736 frames... [2023-03-09 07:26:51,147][24120] Decorrelating experience for 768 frames... [2023-03-09 07:26:51,158][23203] Decorrelating experience for 992 frames... [2023-03-09 07:26:51,176][23233] Decorrelating experience for 704 frames... [2023-03-09 07:26:51,184][23182] Decorrelating experience for 896 frames... [2023-03-09 07:26:51,272][23169] Decorrelating experience for 480 frames... [2023-03-09 07:26:51,282][23217] Decorrelating experience for 736 frames... [2023-03-09 07:26:51,309][23189] Decorrelating experience for 608 frames... [2023-03-09 07:26:51,404][23090] Updated weights for policy 0, policy_version 160 (0.0011) [2023-03-09 07:26:51,427][23240] Decorrelating experience for 928 frames... [2023-03-09 07:26:51,428][22664] Heartbeat connected on RolloutWorker_w102 [2023-03-09 07:26:51,438][23187] Decorrelating experience for 736 frames... [2023-03-09 07:26:51,440][23173] Decorrelating experience for 960 frames... [2023-03-09 07:26:51,451][23657] Decorrelating experience for 832 frames... [2023-03-09 07:26:51,514][23093] Decorrelating experience for 992 frames... [2023-03-09 07:26:51,518][23208] Decorrelating experience for 416 frames... [2023-03-09 07:26:51,611][32460] Decorrelating experience for 928 frames... [2023-03-09 07:26:51,630][24352] Decorrelating experience for 864 frames... [2023-03-09 07:26:51,664][23314] Decorrelating experience for 800 frames... [2023-03-09 07:26:51,693][23229] Decorrelating experience for 736 frames... [2023-03-09 07:26:51,734][22664] Heartbeat connected on RolloutWorker_w40 [2023-03-09 07:26:51,751][23823] Decorrelating experience for 544 frames... [2023-03-09 07:26:51,770][24025] Decorrelating experience for 800 frames... [2023-03-09 07:26:51,799][23246] Decorrelating experience for 960 frames... [2023-03-09 07:26:51,828][23221] Decorrelating experience for 832 frames... [2023-03-09 07:26:51,846][23228] Decorrelating experience for 992 frames... [2023-03-09 07:26:51,872][23233] Decorrelating experience for 736 frames... [2023-03-09 07:26:51,908][23175] Decorrelating experience for 800 frames... [2023-03-09 07:26:51,943][24120] Decorrelating experience for 800 frames... [2023-03-09 07:26:51,964][22664] Heartbeat connected on RolloutWorker_w17 [2023-03-09 07:26:51,991][23182] Decorrelating experience for 928 frames... [2023-03-09 07:26:52,045][23189] Decorrelating experience for 640 frames... [2023-03-09 07:26:52,047][23187] Decorrelating experience for 768 frames... [2023-03-09 07:26:52,057][23635] Decorrelating experience for 736 frames... [2023-03-09 07:26:52,060][23185] Decorrelating experience for 800 frames... [2023-03-09 07:26:52,133][23247] Decorrelating experience for 960 frames... [2023-03-09 07:26:52,157][24121] Decorrelating experience for 768 frames... [2023-03-09 07:26:52,196][23239] Decorrelating experience for 832 frames... [2023-03-09 07:26:52,239][23657] Decorrelating experience for 864 frames... [2023-03-09 07:26:52,318][23090] Updated weights for policy 0, policy_version 170 (0.0013) [2023-03-09 07:26:52,332][23240] Decorrelating experience for 960 frames... [2023-03-09 07:26:52,347][23217] Decorrelating experience for 768 frames... [2023-03-09 07:26:52,352][22664] Heartbeat connected on RolloutWorker_w54 [2023-03-09 07:26:52,355][23236] Decorrelating experience for 896 frames... [2023-03-09 07:26:52,388][23867] Decorrelating experience for 576 frames... [2023-03-09 07:26:52,389][23178] Decorrelating experience for 448 frames... [2023-03-09 07:26:52,485][23092] Decorrelating experience for 928 frames... [2023-03-09 07:26:52,504][23245] Decorrelating experience for 640 frames... [2023-03-09 07:26:52,540][23233] Decorrelating experience for 768 frames... [2023-03-09 07:26:52,559][24352] Decorrelating experience for 896 frames... [2023-03-09 07:26:52,593][23216] Decorrelating experience for 768 frames... [2023-03-09 07:26:52,597][23314] Decorrelating experience for 832 frames... [2023-03-09 07:26:52,625][23099] Decorrelating experience for 896 frames... [2023-03-09 07:26:52,655][23823] Decorrelating experience for 576 frames... [2023-03-09 07:26:52,678][23183] Decorrelating experience for 992 frames... [2023-03-09 07:26:52,846][23197] Decorrelating experience for 832 frames... [2023-03-09 07:26:52,870][23191] Decorrelating experience for 640 frames... [2023-03-09 07:26:52,895][32460] Decorrelating experience for 960 frames... [2023-03-09 07:26:52,911][23187] Decorrelating experience for 800 frames... [2023-03-09 07:26:52,927][23635] Decorrelating experience for 768 frames... [2023-03-09 07:26:52,941][23867] Decorrelating experience for 608 frames... [2023-03-09 07:26:52,967][23239] Decorrelating experience for 864 frames... [2023-03-09 07:26:52,978][23662] Decorrelating experience for 960 frames... [2023-03-09 07:26:52,988][23247] Decorrelating experience for 992 frames... [2023-03-09 07:26:53,092][23637] Decorrelating experience for 896 frames... [2023-03-09 07:26:53,142][23207] Decorrelating experience for 992 frames... [2023-03-09 07:26:53,158][23090] Updated weights for policy 0, policy_version 181 (0.0013) [2023-03-09 07:26:53,185][23185] Decorrelating experience for 832 frames... [2023-03-09 07:26:53,199][23182] Decorrelating experience for 960 frames... [2023-03-09 07:26:53,224][23246] Decorrelating experience for 992 frames... [2023-03-09 07:26:53,234][23216] Decorrelating experience for 800 frames... [2023-03-09 07:26:53,246][23231] Decorrelating experience for 800 frames... [2023-03-09 07:26:53,257][22664] Heartbeat connected on RolloutWorker_w42 [2023-03-09 07:26:53,291][24120] Decorrelating experience for 832 frames... [2023-03-09 07:26:53,300][23245] Decorrelating experience for 672 frames... [2023-03-09 07:26:53,343][23213] Decorrelating experience for 992 frames... [2023-03-09 07:26:53,446][23314] Decorrelating experience for 864 frames... [2023-03-09 07:26:53,461][23238] Decorrelating experience for 960 frames... [2023-03-09 07:26:53,514][23657] Decorrelating experience for 896 frames... [2023-03-09 07:26:53,518][23240] Decorrelating experience for 992 frames... [2023-03-09 07:26:53,562][23221] Decorrelating experience for 864 frames... [2023-03-09 07:26:53,567][23233] Decorrelating experience for 800 frames... [2023-03-09 07:26:53,604][22664] Heartbeat connected on RolloutWorker_w91 [2023-03-09 07:26:53,618][23103] Decorrelating experience for 896 frames... [2023-03-09 07:26:53,681][23189] Decorrelating experience for 672 frames... [2023-03-09 07:26:53,760][23662] Decorrelating experience for 992 frames... [2023-03-09 07:26:53,804][22664] Heartbeat connected on RolloutWorker_w62 [2023-03-09 07:26:53,813][24121] Decorrelating experience for 800 frames... [2023-03-09 07:26:53,835][23239] Decorrelating experience for 896 frames... [2023-03-09 07:26:53,835][23635] Decorrelating experience for 800 frames... [2023-03-09 07:26:53,856][23217] Decorrelating experience for 800 frames... [2023-03-09 07:26:53,883][22664] Heartbeat connected on RolloutWorker_w61 [2023-03-09 07:26:53,922][23197] Decorrelating experience for 864 frames... [2023-03-09 07:26:53,928][24539] Decorrelating experience for 992 frames... [2023-03-09 07:26:53,931][23205] Decorrelating experience for 832 frames... [2023-03-09 07:26:53,994][22664] Heartbeat connected on RolloutWorker_w80 [2023-03-09 07:26:54,001][22664] Heartbeat connected on RolloutWorker_w64 [2023-03-09 07:26:54,012][23637] Decorrelating experience for 928 frames... [2023-03-09 07:26:54,019][23090] Updated weights for policy 0, policy_version 191 (0.0011) [2023-03-09 07:26:54,058][22664] Fps is (10 sec: 173670.5, 60 sec: 52155.9, 300 sec: 36815.8). Total num frames: 3129344. Throughput: 0: 18159.0. Samples: 817152. Policy #0 lag: (min: 1.0, avg: 9.1, max: 18.0) [2023-03-09 07:26:54,060][22664] Avg episode reward: [(0, '4.708')] [2023-03-09 07:26:54,060][23185] Decorrelating experience for 864 frames... [2023-03-09 07:26:54,061][22940] Saving new best policy, reward=4.708! [2023-03-09 07:26:54,091][23634] Decorrelating experience for 992 frames... [2023-03-09 07:26:54,102][23182] Decorrelating experience for 992 frames... [2023-03-09 07:26:54,173][23191] Decorrelating experience for 672 frames... [2023-03-09 07:26:54,204][23867] Decorrelating experience for 640 frames... [2023-03-09 07:26:54,210][24818] Decorrelating experience for 576 frames... [2023-03-09 07:26:54,228][23225] Decorrelating experience for 960 frames... [2023-03-09 07:26:54,244][23092] Decorrelating experience for 960 frames... [2023-03-09 07:26:54,275][22664] Heartbeat connected on RolloutWorker_w99 [2023-03-09 07:26:54,308][23238] Decorrelating experience for 992 frames... [2023-03-09 07:26:54,365][23187] Decorrelating experience for 832 frames... [2023-03-09 07:26:54,370][23233] Decorrelating experience for 832 frames... [2023-03-09 07:26:54,406][23189] Decorrelating experience for 704 frames... [2023-03-09 07:26:54,418][23099] Decorrelating experience for 928 frames... [2023-03-09 07:26:54,464][24089] Decorrelating experience for 896 frames... [2023-03-09 07:26:54,487][23823] Decorrelating experience for 608 frames... [2023-03-09 07:26:54,498][23178] Decorrelating experience for 480 frames... [2023-03-09 07:26:54,501][22664] Heartbeat connected on RolloutWorker_w118 [2023-03-09 07:26:54,503][23314] Decorrelating experience for 896 frames... [2023-03-09 07:26:54,523][23216] Decorrelating experience for 832 frames... [2023-03-09 07:26:54,542][22940] Signal inference workers to stop experience collection... (50 times) [2023-03-09 07:26:54,543][22940] Signal inference workers to resume experience collection... (50 times) [2023-03-09 07:26:54,564][23090] InferenceWorker_p0-w0: stopping experience collection (50 times) [2023-03-09 07:26:54,565][23090] InferenceWorker_p0-w0: resuming experience collection (50 times) [2023-03-09 07:26:54,664][22664] Heartbeat connected on RolloutWorker_w113 [2023-03-09 07:26:54,697][22664] Heartbeat connected on RolloutWorker_w36 [2023-03-09 07:26:54,718][23185] Decorrelating experience for 896 frames... [2023-03-09 07:26:54,720][23657] Decorrelating experience for 928 frames... [2023-03-09 07:26:54,730][23231] Decorrelating experience for 832 frames... [2023-03-09 07:26:54,812][23236] Decorrelating experience for 928 frames... [2023-03-09 07:26:54,827][23197] Decorrelating experience for 896 frames... [2023-03-09 07:26:54,858][23239] Decorrelating experience for 928 frames... [2023-03-09 07:26:54,888][22664] Heartbeat connected on RolloutWorker_w67 [2023-03-09 07:26:54,940][23090] Updated weights for policy 0, policy_version 201 (0.0011) [2023-03-09 07:26:54,959][23243] Decorrelating experience for 960 frames... [2023-03-09 07:26:55,004][23191] Decorrelating experience for 704 frames... [2023-03-09 07:26:55,024][23221] Decorrelating experience for 896 frames... [2023-03-09 07:26:55,025][23187] Decorrelating experience for 864 frames... [2023-03-09 07:26:55,035][23225] Decorrelating experience for 992 frames... [2023-03-09 07:26:55,071][23174] Decorrelating experience for 800 frames... [2023-03-09 07:26:55,084][23823] Decorrelating experience for 640 frames... [2023-03-09 07:26:55,123][23637] Decorrelating experience for 960 frames... [2023-03-09 07:26:55,152][23229] Decorrelating experience for 768 frames... [2023-03-09 07:26:55,228][32460] Decorrelating experience for 992 frames... [2023-03-09 07:26:55,257][23867] Decorrelating experience for 672 frames... [2023-03-09 07:26:55,396][23178] Decorrelating experience for 512 frames... [2023-03-09 07:26:55,400][33428] Decorrelating experience for 928 frames... [2023-03-09 07:26:55,416][23185] Decorrelating experience for 928 frames... [2023-03-09 07:26:55,537][24025] Decorrelating experience for 832 frames... [2023-03-09 07:26:55,569][23197] Decorrelating experience for 928 frames... [2023-03-09 07:26:55,586][23657] Decorrelating experience for 960 frames... [2023-03-09 07:26:55,586][23217] Decorrelating experience for 832 frames... [2023-03-09 07:26:55,659][22664] Heartbeat connected on RolloutWorker_w69 [2023-03-09 07:26:55,704][23216] Decorrelating experience for 864 frames... [2023-03-09 07:26:55,711][23187] Decorrelating experience for 896 frames... [2023-03-09 07:26:55,730][23099] Decorrelating experience for 960 frames... [2023-03-09 07:26:55,733][24352] Decorrelating experience for 928 frames... [2023-03-09 07:26:55,762][23823] Decorrelating experience for 672 frames... [2023-03-09 07:26:55,791][23090] Updated weights for policy 0, policy_version 211 (0.0012) [2023-03-09 07:26:55,826][23208] Decorrelating experience for 448 frames... [2023-03-09 07:26:55,827][24666] Decorrelating experience for 928 frames... [2023-03-09 07:26:55,834][22664] Heartbeat connected on RolloutWorker_w0 [2023-03-09 07:26:55,857][23191] Decorrelating experience for 736 frames... [2023-03-09 07:26:56,005][23229] Decorrelating experience for 800 frames... [2023-03-09 07:26:56,013][23231] Decorrelating experience for 864 frames... [2023-03-09 07:26:56,046][23221] Decorrelating experience for 928 frames... [2023-03-09 07:26:56,052][23092] Decorrelating experience for 992 frames... [2023-03-09 07:26:56,076][23190] Decorrelating experience for 928 frames... [2023-03-09 07:26:56,089][23239] Decorrelating experience for 960 frames... [2023-03-09 07:26:56,248][24025] Decorrelating experience for 864 frames... [2023-03-09 07:26:56,281][23215] Decorrelating experience for 736 frames... [2023-03-09 07:26:56,288][23243] Decorrelating experience for 992 frames... [2023-03-09 07:26:56,317][23216] Decorrelating experience for 896 frames... [2023-03-09 07:26:56,357][23245] Decorrelating experience for 704 frames... [2023-03-09 07:26:56,371][23657] Decorrelating experience for 992 frames... [2023-03-09 07:26:56,373][23187] Decorrelating experience for 928 frames... [2023-03-09 07:26:56,468][24352] Decorrelating experience for 960 frames... [2023-03-09 07:26:56,501][22664] Heartbeat connected on RolloutWorker_w14 [2023-03-09 07:26:56,503][23099] Decorrelating experience for 992 frames... [2023-03-09 07:26:56,564][23173] Decorrelating experience for 992 frames... [2023-03-09 07:26:56,589][23867] Decorrelating experience for 704 frames... [2023-03-09 07:26:56,606][24666] Decorrelating experience for 960 frames... [2023-03-09 07:26:56,614][23178] Decorrelating experience for 544 frames... [2023-03-09 07:26:56,615][23441] Decorrelating experience for 832 frames... [2023-03-09 07:26:56,646][23191] Decorrelating experience for 768 frames... [2023-03-09 07:26:56,658][23090] Updated weights for policy 0, policy_version 221 (0.0013) [2023-03-09 07:26:56,744][22664] Heartbeat connected on RolloutWorker_w82 [2023-03-09 07:26:56,749][23231] Decorrelating experience for 896 frames... [2023-03-09 07:26:56,811][23221] Decorrelating experience for 960 frames... [2023-03-09 07:26:56,836][23823] Decorrelating experience for 704 frames... [2023-03-09 07:26:56,905][23241] Decorrelating experience for 608 frames... [2023-03-09 07:26:56,914][23229] Decorrelating experience for 832 frames... [2023-03-09 07:26:56,922][22664] Heartbeat connected on RolloutWorker_w93 [2023-03-09 07:26:56,954][23205] Decorrelating experience for 864 frames... [2023-03-09 07:26:56,967][23245] Decorrelating experience for 736 frames... [2023-03-09 07:26:56,969][23215] Decorrelating experience for 768 frames... [2023-03-09 07:26:57,056][22664] Heartbeat connected on RolloutWorker_w35 [2023-03-09 07:26:57,075][23210] Decorrelating experience for 928 frames... [2023-03-09 07:26:57,110][23239] Decorrelating experience for 992 frames... [2023-03-09 07:26:57,122][22664] Heartbeat connected on RolloutWorker_w12 [2023-03-09 07:26:57,136][24352] Decorrelating experience for 992 frames... [2023-03-09 07:26:57,174][23637] Decorrelating experience for 992 frames... [2023-03-09 07:26:57,199][23178] Decorrelating experience for 576 frames... [2023-03-09 07:26:57,222][23216] Decorrelating experience for 928 frames... [2023-03-09 07:26:57,222][23208] Decorrelating experience for 480 frames... [2023-03-09 07:26:57,228][24025] Decorrelating experience for 896 frames... [2023-03-09 07:26:57,338][23227] Decorrelating experience for 896 frames... [2023-03-09 07:26:57,478][23867] Decorrelating experience for 736 frames... [2023-03-09 07:26:57,480][23961] Decorrelating experience for 672 frames... [2023-03-09 07:26:57,514][23231] Decorrelating experience for 928 frames... [2023-03-09 07:26:57,560][23245] Decorrelating experience for 768 frames... [2023-03-09 07:26:57,587][23191] Decorrelating experience for 800 frames... [2023-03-09 07:26:57,587][24121] Decorrelating experience for 832 frames... [2023-03-09 07:26:57,588][23441] Decorrelating experience for 864 frames... [2023-03-09 07:26:57,598][22664] Heartbeat connected on RolloutWorker_w109 [2023-03-09 07:26:57,644][23174] Decorrelating experience for 832 frames... [2023-03-09 07:26:57,676][22664] Heartbeat connected on RolloutWorker_w96 [2023-03-09 07:26:57,700][22664] Heartbeat connected on RolloutWorker_w88 [2023-03-09 07:26:57,736][23210] Decorrelating experience for 960 frames... [2023-03-09 07:26:57,749][23175] Decorrelating experience for 832 frames... [2023-03-09 07:26:57,805][23229] Decorrelating experience for 864 frames... [2023-03-09 07:26:57,810][23208] Decorrelating experience for 512 frames... [2023-03-09 07:26:57,816][23185] Decorrelating experience for 960 frames... [2023-03-09 07:26:57,822][23090] Updated weights for policy 0, policy_version 232 (0.0009) [2023-03-09 07:26:57,847][23215] Decorrelating experience for 800 frames... [2023-03-09 07:26:57,863][23217] Decorrelating experience for 864 frames... [2023-03-09 07:26:57,975][23216] Decorrelating experience for 960 frames... [2023-03-09 07:26:58,000][23172] Decorrelating experience for 992 frames... [2023-03-09 07:26:58,068][23961] Decorrelating experience for 704 frames... [2023-03-09 07:26:58,077][23867] Decorrelating experience for 768 frames... [2023-03-09 07:26:58,104][23189] Decorrelating experience for 736 frames... [2023-03-09 07:26:58,135][23205] Decorrelating experience for 896 frames... [2023-03-09 07:26:58,176][23237] Decorrelating experience for 928 frames... [2023-03-09 07:26:58,241][23245] Decorrelating experience for 800 frames... [2023-03-09 07:26:58,241][23191] Decorrelating experience for 832 frames... [2023-03-09 07:26:58,247][24121] Decorrelating experience for 864 frames... [2023-03-09 07:26:58,315][24818] Decorrelating experience for 608 frames... [2023-03-09 07:26:58,383][23823] Decorrelating experience for 736 frames... [2023-03-09 07:26:58,405][23231] Decorrelating experience for 960 frames... [2023-03-09 07:26:58,482][23210] Decorrelating experience for 992 frames... [2023-03-09 07:26:58,500][23187] Decorrelating experience for 960 frames... [2023-03-09 07:26:58,515][23175] Decorrelating experience for 864 frames... [2023-03-09 07:26:58,526][23227] Decorrelating experience for 928 frames... [2023-03-09 07:26:58,555][23217] Decorrelating experience for 896 frames... [2023-03-09 07:26:58,590][23221] Decorrelating experience for 992 frames... [2023-03-09 07:26:58,625][23208] Decorrelating experience for 544 frames... [2023-03-09 07:26:58,647][22664] Heartbeat connected on RolloutWorker_w9 [2023-03-09 07:26:58,734][23229] Decorrelating experience for 896 frames... [2023-03-09 07:26:58,764][23635] Decorrelating experience for 832 frames... [2023-03-09 07:26:58,783][23090] Updated weights for policy 0, policy_version 242 (0.0012) [2023-03-09 07:26:58,825][23174] Decorrelating experience for 864 frames... [2023-03-09 07:26:58,825][23189] Decorrelating experience for 768 frames... [2023-03-09 07:26:58,832][23216] Decorrelating experience for 992 frames... [2023-03-09 07:26:58,853][24025] Decorrelating experience for 928 frames... [2023-03-09 07:26:58,926][23169] Decorrelating experience for 512 frames... [2023-03-09 07:26:59,046][23823] Decorrelating experience for 768 frames... [2023-03-09 07:26:59,054][23215] Decorrelating experience for 832 frames... [2023-03-09 07:26:59,059][22664] Fps is (10 sec: 176945.1, 60 sec: 66628.2, 300 sec: 44418.7). Total num frames: 3997696. Throughput: 0: 21271.7. Samples: 959088. Policy #0 lag: (min: 1.0, avg: 10.8, max: 21.0) [2023-03-09 07:26:59,060][22664] Avg episode reward: [(0, '5.168')] [2023-03-09 07:26:59,101][24089] Decorrelating experience for 928 frames... [2023-03-09 07:26:59,124][22940] Saving new best policy, reward=5.168! [2023-03-09 07:26:59,132][22664] Heartbeat connected on RolloutWorker_w84 [2023-03-09 07:26:59,159][23867] Decorrelating experience for 800 frames... [2023-03-09 07:26:59,161][22664] Heartbeat connected on RolloutWorker_w71 [2023-03-09 07:26:59,183][23205] Decorrelating experience for 928 frames... [2023-03-09 07:26:59,188][23245] Decorrelating experience for 832 frames... [2023-03-09 07:26:59,290][23227] Decorrelating experience for 960 frames... [2023-03-09 07:26:59,301][22664] Heartbeat connected on RolloutWorker_w51 [2023-03-09 07:26:59,303][23190] Decorrelating experience for 960 frames... [2023-03-09 07:26:59,330][23175] Decorrelating experience for 896 frames... [2023-03-09 07:26:59,346][23178] Decorrelating experience for 608 frames... [2023-03-09 07:26:59,458][23169] Decorrelating experience for 544 frames... [2023-03-09 07:26:59,489][23231] Decorrelating experience for 992 frames... [2023-03-09 07:26:59,502][23189] Decorrelating experience for 800 frames... [2023-03-09 07:26:59,558][23217] Decorrelating experience for 928 frames... [2023-03-09 07:26:59,585][23441] Decorrelating experience for 896 frames... [2023-03-09 07:26:59,621][24025] Decorrelating experience for 960 frames... [2023-03-09 07:26:59,642][23098] Decorrelating experience for 832 frames... [2023-03-09 07:26:59,735][24818] Decorrelating experience for 640 frames... [2023-03-09 07:26:59,764][23215] Decorrelating experience for 864 frames... [2023-03-09 07:26:59,814][23174] Decorrelating experience for 896 frames... [2023-03-09 07:26:59,825][23090] Updated weights for policy 0, policy_version 252 (0.0011) [2023-03-09 07:26:59,845][23187] Decorrelating experience for 992 frames... [2023-03-09 07:26:59,865][23236] Decorrelating experience for 960 frames... [2023-03-09 07:26:59,874][24089] Decorrelating experience for 960 frames... [2023-03-09 07:26:59,919][33428] Decorrelating experience for 960 frames... [2023-03-09 07:26:59,968][23178] Decorrelating experience for 640 frames... [2023-03-09 07:26:59,998][23867] Decorrelating experience for 832 frames... [2023-03-09 07:27:00,012][23237] Decorrelating experience for 960 frames... [2023-03-09 07:27:00,056][22664] Heartbeat connected on RolloutWorker_w60 [2023-03-09 07:27:00,096][23205] Decorrelating experience for 960 frames... [2023-03-09 07:27:00,106][23227] Decorrelating experience for 992 frames... [2023-03-09 07:27:00,137][23169] Decorrelating experience for 576 frames... [2023-03-09 07:27:00,173][23229] Decorrelating experience for 928 frames... [2023-03-09 07:27:00,174][23103] Decorrelating experience for 928 frames... [2023-03-09 07:27:00,205][23233] Decorrelating experience for 864 frames... [2023-03-09 07:27:00,218][23189] Decorrelating experience for 832 frames... [2023-03-09 07:27:00,320][23175] Decorrelating experience for 928 frames... [2023-03-09 07:27:00,321][23185] Decorrelating experience for 992 frames... [2023-03-09 07:27:00,372][23441] Decorrelating experience for 928 frames... [2023-03-09 07:27:00,409][23217] Decorrelating experience for 960 frames... [2023-03-09 07:27:00,434][22664] Heartbeat connected on RolloutWorker_w7 [2023-03-09 07:27:00,451][23245] Decorrelating experience for 864 frames... [2023-03-09 07:27:00,454][23098] Decorrelating experience for 864 frames... [2023-03-09 07:27:00,492][24120] Decorrelating experience for 864 frames... [2023-03-09 07:27:00,526][23208] Decorrelating experience for 576 frames... [2023-03-09 07:27:00,557][23090] Updated weights for policy 0, policy_version 262 (0.0013) [2023-03-09 07:27:00,612][23961] Decorrelating experience for 736 frames... [2023-03-09 07:27:00,620][23178] Decorrelating experience for 672 frames... [2023-03-09 07:27:00,680][22664] Heartbeat connected on RolloutWorker_w81 [2023-03-09 07:27:00,686][24025] Decorrelating experience for 992 frames... [2023-03-09 07:27:00,690][24089] Decorrelating experience for 992 frames... [2023-03-09 07:27:00,769][23174] Decorrelating experience for 928 frames... [2023-03-09 07:27:00,770][23169] Decorrelating experience for 608 frames... [2023-03-09 07:27:00,776][23197] Decorrelating experience for 960 frames... [2023-03-09 07:27:00,834][23867] Decorrelating experience for 864 frames... [2023-03-09 07:27:00,901][23823] Decorrelating experience for 800 frames... [2023-03-09 07:27:00,901][22664] Heartbeat connected on RolloutWorker_w45 [2023-03-09 07:27:00,983][23233] Decorrelating experience for 896 frames... [2023-03-09 07:27:01,014][33428] Decorrelating experience for 992 frames... [2023-03-09 07:27:01,016][23237] Decorrelating experience for 992 frames... [2023-03-09 07:27:01,059][23191] Decorrelating experience for 864 frames... [2023-03-09 07:27:01,075][23189] Decorrelating experience for 864 frames... [2023-03-09 07:27:01,075][24121] Decorrelating experience for 896 frames... [2023-03-09 07:27:01,128][23175] Decorrelating experience for 960 frames... [2023-03-09 07:27:01,129][23103] Decorrelating experience for 960 frames... [2023-03-09 07:27:01,143][23245] Decorrelating experience for 896 frames... [2023-03-09 07:27:01,221][23098] Decorrelating experience for 896 frames... [2023-03-09 07:27:01,261][22664] Heartbeat connected on RolloutWorker_w114 [2023-03-09 07:27:01,273][22664] Heartbeat connected on RolloutWorker_w123 [2023-03-09 07:27:01,285][23229] Decorrelating experience for 960 frames... [2023-03-09 07:27:01,297][23236] Decorrelating experience for 992 frames... [2023-03-09 07:27:01,334][24818] Decorrelating experience for 672 frames... [2023-03-09 07:27:01,344][23961] Decorrelating experience for 768 frames... [2023-03-09 07:27:01,360][23441] Decorrelating experience for 960 frames... [2023-03-09 07:27:01,386][24120] Decorrelating experience for 896 frames... [2023-03-09 07:27:01,393][23178] Decorrelating experience for 704 frames... [2023-03-09 07:27:01,505][23635] Decorrelating experience for 864 frames... [2023-03-09 07:27:01,524][22664] Heartbeat connected on RolloutWorker_w1 [2023-03-09 07:27:01,529][22664] Heartbeat connected on RolloutWorker_w73 [2023-03-09 07:27:01,581][23174] Decorrelating experience for 960 frames... [2023-03-09 07:27:01,591][23867] Decorrelating experience for 896 frames... [2023-03-09 07:27:01,622][23208] Decorrelating experience for 608 frames... [2023-03-09 07:27:01,667][23217] Decorrelating experience for 992 frames... [2023-03-09 07:27:01,751][23191] Decorrelating experience for 896 frames... [2023-03-09 07:27:01,776][22664] Heartbeat connected on RolloutWorker_w85 [2023-03-09 07:27:01,803][23090] Updated weights for policy 0, policy_version 273 (0.0013) [2023-03-09 07:27:01,839][23233] Decorrelating experience for 928 frames... [2023-03-09 07:27:01,873][23175] Decorrelating experience for 992 frames... [2023-03-09 07:27:01,874][23103] Decorrelating experience for 992 frames... [2023-03-09 07:27:01,902][24121] Decorrelating experience for 928 frames... [2023-03-09 07:27:01,906][24666] Decorrelating experience for 992 frames... [2023-03-09 07:27:01,913][23098] Decorrelating experience for 928 frames... [2023-03-09 07:27:01,914][23215] Decorrelating experience for 896 frames... [2023-03-09 07:27:02,048][23205] Decorrelating experience for 992 frames... [2023-03-09 07:27:02,067][24120] Decorrelating experience for 928 frames... [2023-03-09 07:27:02,082][23241] Decorrelating experience for 640 frames... [2023-03-09 07:27:02,113][23245] Decorrelating experience for 928 frames... [2023-03-09 07:27:02,143][22664] Heartbeat connected on RolloutWorker_w86 [2023-03-09 07:27:02,144][23197] Decorrelating experience for 992 frames... [2023-03-09 07:27:02,153][24818] Decorrelating experience for 704 frames... [2023-03-09 07:27:02,187][23961] Decorrelating experience for 800 frames... [2023-03-09 07:27:02,208][23823] Decorrelating experience for 832 frames... [2023-03-09 07:27:02,300][23208] Decorrelating experience for 640 frames... [2023-03-09 07:27:02,381][22664] Heartbeat connected on RolloutWorker_w38 [2023-03-09 07:27:02,386][22664] Heartbeat connected on RolloutWorker_w18 [2023-03-09 07:27:02,396][23635] Decorrelating experience for 896 frames... [2023-03-09 07:27:02,410][23229] Decorrelating experience for 992 frames... [2023-03-09 07:27:02,422][22664] Heartbeat connected on RolloutWorker_w127 [2023-03-09 07:27:02,469][23174] Decorrelating experience for 992 frames... [2023-03-09 07:27:02,493][22664] Heartbeat connected on RolloutWorker_w53 [2023-03-09 07:27:02,526][23233] Decorrelating experience for 960 frames... [2023-03-09 07:27:02,552][23189] Decorrelating experience for 896 frames... [2023-03-09 07:27:02,585][22664] Heartbeat connected on RolloutWorker_w37 [2023-03-09 07:27:02,587][23215] Decorrelating experience for 928 frames... [2023-03-09 07:27:02,594][23098] Decorrelating experience for 960 frames... [2023-03-09 07:27:02,628][24121] Decorrelating experience for 960 frames... [2023-03-09 07:27:02,718][23191] Decorrelating experience for 928 frames... [2023-03-09 07:27:02,726][24818] Decorrelating experience for 736 frames... [2023-03-09 07:27:02,727][24120] Decorrelating experience for 960 frames... [2023-03-09 07:27:02,792][23241] Decorrelating experience for 672 frames... [2023-03-09 07:27:02,798][23961] Decorrelating experience for 832 frames... [2023-03-09 07:27:02,815][23823] Decorrelating experience for 864 frames... [2023-03-09 07:27:02,863][23441] Decorrelating experience for 992 frames... [2023-03-09 07:27:02,869][22664] Heartbeat connected on RolloutWorker_w75 [2023-03-09 07:27:02,951][23245] Decorrelating experience for 960 frames... [2023-03-09 07:27:02,951][23090] Updated weights for policy 0, policy_version 283 (0.0012) [2023-03-09 07:27:02,954][22664] Heartbeat connected on RolloutWorker_w15 [2023-03-09 07:27:03,059][23208] Decorrelating experience for 672 frames... [2023-03-09 07:27:03,061][23169] Decorrelating experience for 640 frames... [2023-03-09 07:27:03,108][23867] Decorrelating experience for 928 frames... [2023-03-09 07:27:03,236][23189] Decorrelating experience for 928 frames... [2023-03-09 07:27:03,236][23233] Decorrelating experience for 992 frames... [2023-03-09 07:27:03,284][23215] Decorrelating experience for 960 frames... [2023-03-09 07:27:03,306][23098] Decorrelating experience for 992 frames... [2023-03-09 07:27:03,365][24818] Decorrelating experience for 768 frames... [2023-03-09 07:27:03,399][22664] Heartbeat connected on RolloutWorker_w107 [2023-03-09 07:27:03,421][23314] Decorrelating experience for 928 frames... [2023-03-09 07:27:03,423][23635] Decorrelating experience for 928 frames... [2023-03-09 07:27:03,431][23241] Decorrelating experience for 704 frames... [2023-03-09 07:27:03,458][23191] Decorrelating experience for 960 frames... [2023-03-09 07:27:03,531][23823] Decorrelating experience for 896 frames... [2023-03-09 07:27:03,588][23961] Decorrelating experience for 864 frames... [2023-03-09 07:27:03,682][23208] Decorrelating experience for 704 frames... [2023-03-09 07:27:03,712][24121] Decorrelating experience for 992 frames... [2023-03-09 07:27:03,713][23211] Decorrelating experience for 992 frames... [2023-03-09 07:27:03,745][23169] Decorrelating experience for 672 frames... [2023-03-09 07:27:03,771][22664] Heartbeat connected on RolloutWorker_w78 [2023-03-09 07:27:03,824][22664] Heartbeat connected on RolloutWorker_w32 [2023-03-09 07:27:03,974][23178] Decorrelating experience for 736 frames... [2023-03-09 07:27:03,989][23189] Decorrelating experience for 960 frames... [2023-03-09 07:27:03,996][24818] Decorrelating experience for 800 frames... [2023-03-09 07:27:04,004][24120] Decorrelating experience for 992 frames... [2023-03-09 07:27:04,027][23241] Decorrelating experience for 736 frames... [2023-03-09 07:27:04,058][22664] Fps is (10 sec: 165478.1, 60 sec: 79735.7, 300 sec: 50359.3). Total num frames: 4784128. Throughput: 0: 26649.6. Samples: 1211024. Policy #0 lag: (min: 1.0, avg: 13.2, max: 25.0) [2023-03-09 07:27:04,060][22664] Avg episode reward: [(0, '4.889')] [2023-03-09 07:27:04,062][23635] Decorrelating experience for 960 frames... [2023-03-09 07:27:04,143][23090] Updated weights for policy 0, policy_version 293 (0.0016) [2023-03-09 07:27:04,190][22664] Heartbeat connected on RolloutWorker_w94 [2023-03-09 07:27:04,196][22664] Heartbeat connected on RolloutWorker_w74 [2023-03-09 07:27:04,263][23191] Decorrelating experience for 992 frames... [2023-03-09 07:27:04,275][23208] Decorrelating experience for 736 frames... [2023-03-09 07:27:04,288][23867] Decorrelating experience for 960 frames... [2023-03-09 07:27:04,317][23314] Decorrelating experience for 960 frames... [2023-03-09 07:27:04,317][23169] Decorrelating experience for 704 frames... [2023-03-09 07:27:04,330][23961] Decorrelating experience for 896 frames... [2023-03-09 07:27:04,468][22664] Heartbeat connected on RolloutWorker_w97 [2023-03-09 07:27:04,519][23823] Decorrelating experience for 928 frames... [2023-03-09 07:27:04,570][23190] Decorrelating experience for 992 frames... [2023-03-09 07:27:04,590][23241] Decorrelating experience for 768 frames... [2023-03-09 07:27:04,627][24818] Decorrelating experience for 832 frames... [2023-03-09 07:27:04,724][22664] Heartbeat connected on RolloutWorker_w19 [2023-03-09 07:27:04,794][23635] Decorrelating experience for 992 frames... [2023-03-09 07:27:04,825][23245] Decorrelating experience for 992 frames... [2023-03-09 07:27:04,839][23178] Decorrelating experience for 768 frames... [2023-03-09 07:27:04,951][23189] Decorrelating experience for 992 frames... [2023-03-09 07:27:04,957][23314] Decorrelating experience for 992 frames... [2023-03-09 07:27:05,016][23208] Decorrelating experience for 768 frames... [2023-03-09 07:27:05,016][22664] Heartbeat connected on RolloutWorker_w13 [2023-03-09 07:27:05,121][23215] Decorrelating experience for 992 frames... [2023-03-09 07:27:05,176][23241] Decorrelating experience for 800 frames... [2023-03-09 07:27:05,208][23823] Decorrelating experience for 960 frames... [2023-03-09 07:27:05,226][23961] Decorrelating experience for 928 frames... [2023-03-09 07:27:05,292][23090] Updated weights for policy 0, policy_version 303 (0.0013) [2023-03-09 07:27:05,313][23169] Decorrelating experience for 736 frames... [2023-03-09 07:27:05,436][22664] Heartbeat connected on RolloutWorker_w119 [2023-03-09 07:27:05,469][22664] Heartbeat connected on RolloutWorker_w16 [2023-03-09 07:27:05,472][22664] Heartbeat connected on RolloutWorker_w101 [2023-03-09 07:27:05,476][23178] Decorrelating experience for 800 frames... [2023-03-09 07:27:05,477][22664] Heartbeat connected on RolloutWorker_w55 [2023-03-09 07:27:05,537][24818] Decorrelating experience for 864 frames... [2023-03-09 07:27:05,557][23867] Decorrelating experience for 992 frames... [2023-03-09 07:27:05,615][22664] Heartbeat connected on RolloutWorker_w48 [2023-03-09 07:27:05,644][23208] Decorrelating experience for 800 frames... [2023-03-09 07:27:05,818][23241] Decorrelating experience for 832 frames... [2023-03-09 07:27:05,909][23169] Decorrelating experience for 768 frames... [2023-03-09 07:27:05,919][23823] Decorrelating experience for 992 frames... [2023-03-09 07:27:05,919][23961] Decorrelating experience for 960 frames... [2023-03-09 07:27:06,009][22664] Heartbeat connected on RolloutWorker_w117 [2023-03-09 07:27:06,043][23178] Decorrelating experience for 832 frames... [2023-03-09 07:27:06,211][23208] Decorrelating experience for 832 frames... [2023-03-09 07:27:06,302][24818] Decorrelating experience for 896 frames... [2023-03-09 07:27:06,372][22664] Heartbeat connected on RolloutWorker_w105 [2023-03-09 07:27:06,430][23241] Decorrelating experience for 864 frames... [2023-03-09 07:27:06,461][23169] Decorrelating experience for 800 frames... [2023-03-09 07:27:06,473][23090] Updated weights for policy 0, policy_version 314 (0.0013) [2023-03-09 07:27:06,573][23961] Decorrelating experience for 992 frames... [2023-03-09 07:27:06,668][23178] Decorrelating experience for 864 frames... [2023-03-09 07:27:06,841][23208] Decorrelating experience for 864 frames... [2023-03-09 07:27:07,070][22664] Heartbeat connected on RolloutWorker_w120 [2023-03-09 07:27:07,106][23169] Decorrelating experience for 832 frames... [2023-03-09 07:27:07,107][23241] Decorrelating experience for 896 frames... [2023-03-09 07:27:07,272][22940] Signal inference workers to stop experience collection... (100 times) [2023-03-09 07:27:07,273][22940] Signal inference workers to resume experience collection... (100 times) [2023-03-09 07:27:07,330][23178] Decorrelating experience for 896 frames... [2023-03-09 07:27:07,337][23090] InferenceWorker_p0-w0: stopping experience collection (100 times) [2023-03-09 07:27:07,337][23090] InferenceWorker_p0-w0: resuming experience collection (100 times) [2023-03-09 07:27:07,347][24818] Decorrelating experience for 928 frames... [2023-03-09 07:27:07,500][23208] Decorrelating experience for 896 frames... [2023-03-09 07:27:07,675][23090] Updated weights for policy 0, policy_version 324 (0.0020) [2023-03-09 07:27:07,730][23169] Decorrelating experience for 864 frames... [2023-03-09 07:27:07,772][23241] Decorrelating experience for 928 frames... [2023-03-09 07:27:08,026][23178] Decorrelating experience for 928 frames... [2023-03-09 07:27:08,048][24818] Decorrelating experience for 960 frames... [2023-03-09 07:27:08,176][23208] Decorrelating experience for 928 frames... [2023-03-09 07:27:08,406][23090] Updated weights for policy 0, policy_version 334 (0.0020) [2023-03-09 07:27:08,435][23169] Decorrelating experience for 896 frames... [2023-03-09 07:27:08,508][23241] Decorrelating experience for 960 frames... [2023-03-09 07:27:08,761][24818] Decorrelating experience for 992 frames... [2023-03-09 07:27:08,812][23178] Decorrelating experience for 960 frames... [2023-03-09 07:27:08,906][23208] Decorrelating experience for 960 frames... [2023-03-09 07:27:09,057][23090] Updated weights for policy 0, policy_version 344 (0.0018) [2023-03-09 07:27:09,059][22664] Fps is (10 sec: 163840.0, 60 sec: 93934.9, 300 sec: 56360.8). Total num frames: 5636096. Throughput: 0: 31686.9. Samples: 1462000. Policy #0 lag: (min: 1.0, avg: 13.7, max: 28.0) [2023-03-09 07:27:09,102][22664] Avg episode reward: [(0, '5.500')] [2023-03-09 07:27:09,111][22940] Saving new best policy, reward=5.500! [2023-03-09 07:27:09,144][23169] Decorrelating experience for 928 frames... [2023-03-09 07:27:09,239][23241] Decorrelating experience for 992 frames... [2023-03-09 07:27:09,270][22664] Heartbeat connected on RolloutWorker_w115 [2023-03-09 07:27:09,559][23178] Decorrelating experience for 992 frames... [2023-03-09 07:27:09,600][23208] Decorrelating experience for 992 frames... [2023-03-09 07:27:09,718][22664] Heartbeat connected on RolloutWorker_w70 [2023-03-09 07:27:09,840][23169] Decorrelating experience for 960 frames... [2023-03-09 07:27:10,034][22664] Heartbeat connected on RolloutWorker_w24 [2023-03-09 07:27:10,092][22664] Heartbeat connected on RolloutWorker_w59 [2023-03-09 07:27:10,309][23090] Updated weights for policy 0, policy_version 354 (0.0012) [2023-03-09 07:27:10,576][23169] Decorrelating experience for 992 frames... [2023-03-09 07:27:11,073][23090] Updated weights for policy 0, policy_version 364 (0.0025) [2023-03-09 07:27:11,090][22664] Heartbeat connected on RolloutWorker_w44 [2023-03-09 07:27:11,771][23090] Updated weights for policy 0, policy_version 374 (0.0013) [2023-03-09 07:27:12,764][23090] Updated weights for policy 0, policy_version 384 (0.0014) [2023-03-09 07:27:13,600][23090] Updated weights for policy 0, policy_version 394 (0.0019) [2023-03-09 07:27:14,059][22664] Fps is (10 sec: 178580.6, 60 sec: 109499.2, 300 sec: 62571.1). Total num frames: 6569984. Throughput: 0: 34451.0. Samples: 1603184. Policy #0 lag: (min: 1.0, avg: 18.0, max: 32.0) [2023-03-09 07:27:14,060][22664] Avg episode reward: [(0, '6.432')] [2023-03-09 07:27:14,106][22940] Saving new best policy, reward=6.432! [2023-03-09 07:27:14,337][23090] Updated weights for policy 0, policy_version 404 (0.0018) [2023-03-09 07:27:15,283][23090] Updated weights for policy 0, policy_version 414 (0.0023) [2023-03-09 07:27:15,986][23090] Updated weights for policy 0, policy_version 424 (0.0021) [2023-03-09 07:27:16,705][23090] Updated weights for policy 0, policy_version 434 (0.0016) [2023-03-09 07:27:17,625][22940] Signal inference workers to stop experience collection... (150 times) [2023-03-09 07:27:17,626][22940] Signal inference workers to resume experience collection... (150 times) [2023-03-09 07:27:17,688][23090] InferenceWorker_p0-w0: stopping experience collection (150 times) [2023-03-09 07:27:17,691][23090] InferenceWorker_p0-w0: resuming experience collection (150 times) [2023-03-09 07:27:17,695][23090] Updated weights for policy 0, policy_version 444 (0.0018) [2023-03-09 07:27:18,496][23090] Updated weights for policy 0, policy_version 455 (0.0017) [2023-03-09 07:27:19,059][22664] Fps is (10 sec: 193333.4, 60 sec: 125337.5, 300 sec: 68812.7). Total num frames: 7569408. Throughput: 0: 39895.4. Samples: 1906240. Policy #0 lag: (min: 1.0, avg: 16.5, max: 33.0) [2023-03-09 07:27:19,060][22664] Avg episode reward: [(0, '7.897')] [2023-03-09 07:27:19,159][22940] Saving /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000000464_7602176.pth... [2023-03-09 07:27:19,213][22940] Saving new best policy, reward=7.897! [2023-03-09 07:27:19,342][23090] Updated weights for policy 0, policy_version 465 (0.0021) [2023-03-09 07:27:20,281][23090] Updated weights for policy 0, policy_version 475 (0.0017) [2023-03-09 07:27:21,064][23090] Updated weights for policy 0, policy_version 485 (0.0016) [2023-03-09 07:27:21,806][23090] Updated weights for policy 0, policy_version 495 (0.0013) [2023-03-09 07:27:22,604][23090] Updated weights for policy 0, policy_version 505 (0.0017) [2023-03-09 07:27:23,518][23090] Updated weights for policy 0, policy_version 515 (0.0013) [2023-03-09 07:27:24,059][22664] Fps is (10 sec: 198245.5, 60 sec: 140355.5, 300 sec: 74368.9). Total num frames: 8552448. Throughput: 0: 44206.4. Samples: 2203088. Policy #0 lag: (min: 1.0, avg: 16.3, max: 33.0) [2023-03-09 07:27:24,061][22664] Avg episode reward: [(0, '9.093')] [2023-03-09 07:27:24,064][22940] Saving new best policy, reward=9.093! [2023-03-09 07:27:24,370][23090] Updated weights for policy 0, policy_version 525 (0.0018) [2023-03-09 07:27:24,961][23090] Updated weights for policy 0, policy_version 535 (0.0016) [2023-03-09 07:27:25,951][23090] Updated weights for policy 0, policy_version 545 (0.0015) [2023-03-09 07:27:26,161][22940] Signal inference workers to stop experience collection... (200 times) [2023-03-09 07:27:26,183][22940] Signal inference workers to resume experience collection... (200 times) [2023-03-09 07:27:26,226][23090] InferenceWorker_p0-w0: stopping experience collection (200 times) [2023-03-09 07:27:26,226][23090] InferenceWorker_p0-w0: resuming experience collection (200 times) [2023-03-09 07:27:26,761][23090] Updated weights for policy 0, policy_version 555 (0.0022) [2023-03-09 07:27:27,407][23090] Updated weights for policy 0, policy_version 565 (0.0013) [2023-03-09 07:27:28,397][23090] Updated weights for policy 0, policy_version 575 (0.0023) [2023-03-09 07:27:29,059][22664] Fps is (10 sec: 198241.5, 60 sec: 155102.2, 300 sec: 79598.7). Total num frames: 9551872. Throughput: 0: 45567.6. Samples: 2354576. Policy #0 lag: (min: 2.0, avg: 16.5, max: 32.0) [2023-03-09 07:27:29,061][22664] Avg episode reward: [(0, '8.911')] [2023-03-09 07:27:29,201][23090] Updated weights for policy 0, policy_version 585 (0.0021) [2023-03-09 07:27:29,884][23090] Updated weights for policy 0, policy_version 595 (0.0013) [2023-03-09 07:27:30,869][23090] Updated weights for policy 0, policy_version 605 (0.0014) [2023-03-09 07:27:31,575][23090] Updated weights for policy 0, policy_version 615 (0.0016) [2023-03-09 07:27:32,339][23090] Updated weights for policy 0, policy_version 625 (0.0014) [2023-03-09 07:27:33,343][23090] Updated weights for policy 0, policy_version 635 (0.0016) [2023-03-09 07:27:34,033][23090] Updated weights for policy 0, policy_version 645 (0.0022) [2023-03-09 07:27:34,059][22664] Fps is (10 sec: 201528.8, 60 sec: 168482.2, 300 sec: 84541.4). Total num frames: 10567680. Throughput: 0: 47003.8. Samples: 2655536. Policy #0 lag: (min: 0.0, avg: 16.3, max: 33.0) [2023-03-09 07:27:34,060][22664] Avg episode reward: [(0, '10.592')] [2023-03-09 07:27:34,089][22940] Saving new best policy, reward=10.592! [2023-03-09 07:27:34,787][23090] Updated weights for policy 0, policy_version 655 (0.0017) [2023-03-09 07:27:35,595][23090] Updated weights for policy 0, policy_version 665 (0.0020) [2023-03-09 07:27:35,922][22940] Signal inference workers to stop experience collection... (250 times) [2023-03-09 07:27:35,923][22940] Signal inference workers to resume experience collection... (250 times) [2023-03-09 07:27:35,983][23090] InferenceWorker_p0-w0: stopping experience collection (250 times) [2023-03-09 07:27:35,983][23090] InferenceWorker_p0-w0: resuming experience collection (250 times) [2023-03-09 07:27:36,578][23090] Updated weights for policy 0, policy_version 675 (0.0016) [2023-03-09 07:27:37,314][23090] Updated weights for policy 0, policy_version 685 (0.0020) [2023-03-09 07:27:38,000][23090] Updated weights for policy 0, policy_version 695 (0.0013) [2023-03-09 07:27:38,992][23090] Updated weights for policy 0, policy_version 705 (0.0013) [2023-03-09 07:27:39,058][22664] Fps is (10 sec: 199891.7, 60 sec: 179132.0, 300 sec: 88851.7). Total num frames: 11550720. Throughput: 0: 47586.1. Samples: 2958528. Policy #0 lag: (min: 1.0, avg: 17.6, max: 33.0) [2023-03-09 07:27:39,059][22664] Avg episode reward: [(0, '12.124')] [2023-03-09 07:27:39,077][22940] Saving new best policy, reward=12.124! [2023-03-09 07:27:39,756][23090] Updated weights for policy 0, policy_version 715 (0.0014) [2023-03-09 07:27:40,456][23090] Updated weights for policy 0, policy_version 725 (0.0028) [2023-03-09 07:27:41,435][23090] Updated weights for policy 0, policy_version 735 (0.0016) [2023-03-09 07:27:42,194][23090] Updated weights for policy 0, policy_version 745 (0.0013) [2023-03-09 07:27:42,877][23090] Updated weights for policy 0, policy_version 755 (0.0020) [2023-03-09 07:27:43,901][23090] Updated weights for policy 0, policy_version 765 (0.0018) [2023-03-09 07:27:44,059][22664] Fps is (10 sec: 199879.6, 60 sec: 186230.5, 300 sec: 93085.2). Total num frames: 12566528. Throughput: 0: 47753.5. Samples: 3108000. Policy #0 lag: (min: 0.0, avg: 18.3, max: 33.0) [2023-03-09 07:27:44,061][22664] Avg episode reward: [(0, '12.863')] [2023-03-09 07:27:44,072][22940] Saving new best policy, reward=12.863! [2023-03-09 07:27:44,545][22940] Signal inference workers to stop experience collection... (300 times) [2023-03-09 07:27:44,546][22940] Signal inference workers to resume experience collection... (300 times) [2023-03-09 07:27:44,610][23090] InferenceWorker_p0-w0: stopping experience collection (300 times) [2023-03-09 07:27:44,611][23090] InferenceWorker_p0-w0: resuming experience collection (300 times) [2023-03-09 07:27:44,613][23090] Updated weights for policy 0, policy_version 775 (0.0018) [2023-03-09 07:27:45,354][23090] Updated weights for policy 0, policy_version 785 (0.0013) [2023-03-09 07:27:46,345][23090] Updated weights for policy 0, policy_version 795 (0.0017) [2023-03-09 07:27:47,096][23090] Updated weights for policy 0, policy_version 805 (0.0019) [2023-03-09 07:27:47,870][23090] Updated weights for policy 0, policy_version 815 (0.0018) [2023-03-09 07:27:48,671][23090] Updated weights for policy 0, policy_version 825 (0.0020) [2023-03-09 07:27:49,059][22664] Fps is (10 sec: 201518.9, 60 sec: 188961.7, 300 sec: 96899.5). Total num frames: 13565952. Throughput: 0: 48887.9. Samples: 3410992. Policy #0 lag: (min: 1.0, avg: 18.3, max: 33.0) [2023-03-09 07:27:49,060][22664] Avg episode reward: [(0, '14.000')] [2023-03-09 07:27:49,069][22940] Saving new best policy, reward=14.000! [2023-03-09 07:27:49,580][23090] Updated weights for policy 0, policy_version 835 (0.0013) [2023-03-09 07:27:50,397][23090] Updated weights for policy 0, policy_version 845 (0.0014) [2023-03-09 07:27:51,113][23090] Updated weights for policy 0, policy_version 855 (0.0015) [2023-03-09 07:27:52,049][23090] Updated weights for policy 0, policy_version 865 (0.0013) [2023-03-09 07:27:52,803][23090] Updated weights for policy 0, policy_version 875 (0.0013) [2023-03-09 07:27:53,527][23090] Updated weights for policy 0, policy_version 885 (0.0020) [2023-03-09 07:27:54,058][22664] Fps is (10 sec: 199891.2, 60 sec: 190600.5, 300 sec: 100450.9). Total num frames: 14565376. Throughput: 0: 49952.3. Samples: 3709840. Policy #0 lag: (min: 0.0, avg: 18.1, max: 34.0) [2023-03-09 07:27:54,059][22664] Avg episode reward: [(0, '13.624')] [2023-03-09 07:27:54,208][22940] Signal inference workers to stop experience collection... (350 times) [2023-03-09 07:27:54,208][22940] Signal inference workers to resume experience collection... (350 times) [2023-03-09 07:27:54,269][23090] InferenceWorker_p0-w0: stopping experience collection (350 times) [2023-03-09 07:27:54,269][23090] InferenceWorker_p0-w0: resuming experience collection (350 times) [2023-03-09 07:27:54,473][23090] Updated weights for policy 0, policy_version 895 (0.0013) [2023-03-09 07:27:55,356][23090] Updated weights for policy 0, policy_version 906 (0.0013) [2023-03-09 07:27:56,111][23090] Updated weights for policy 0, policy_version 917 (0.0015) [2023-03-09 07:27:57,103][23090] Updated weights for policy 0, policy_version 927 (0.0019) [2023-03-09 07:27:57,862][23090] Updated weights for policy 0, policy_version 937 (0.0018) [2023-03-09 07:27:58,666][23090] Updated weights for policy 0, policy_version 947 (0.0017) [2023-03-09 07:27:59,058][22664] Fps is (10 sec: 203166.2, 60 sec: 193331.9, 300 sec: 103983.8). Total num frames: 15597568. Throughput: 0: 50180.9. Samples: 3861312. Policy #0 lag: (min: 0.0, avg: 18.0, max: 34.0) [2023-03-09 07:27:59,059][22664] Avg episode reward: [(0, '15.250')] [2023-03-09 07:27:59,063][22940] Saving new best policy, reward=15.250! [2023-03-09 07:27:59,621][23090] Updated weights for policy 0, policy_version 957 (0.0019) [2023-03-09 07:28:00,288][23090] Updated weights for policy 0, policy_version 967 (0.0018) [2023-03-09 07:28:01,027][23090] Updated weights for policy 0, policy_version 977 (0.0016) [2023-03-09 07:28:02,082][23090] Updated weights for policy 0, policy_version 987 (0.0015) [2023-03-09 07:28:02,810][23090] Updated weights for policy 0, policy_version 997 (0.0013) [2023-03-09 07:28:03,520][22940] Signal inference workers to stop experience collection... (400 times) [2023-03-09 07:28:03,539][22940] Signal inference workers to resume experience collection... (400 times) [2023-03-09 07:28:03,579][23090] InferenceWorker_p0-w0: stopping experience collection (400 times) [2023-03-09 07:28:03,582][23090] Updated weights for policy 0, policy_version 1007 (0.0013) [2023-03-09 07:28:03,623][23090] InferenceWorker_p0-w0: resuming experience collection (400 times) [2023-03-09 07:28:04,059][22664] Fps is (10 sec: 204795.6, 60 sec: 197153.5, 300 sec: 107183.0). Total num frames: 16613376. Throughput: 0: 50135.0. Samples: 4162320. Policy #0 lag: (min: 1.0, avg: 17.9, max: 32.0) [2023-03-09 07:28:04,061][22664] Avg episode reward: [(0, '16.842')] [2023-03-09 07:28:04,062][22940] Saving new best policy, reward=16.842! [2023-03-09 07:28:04,361][23090] Updated weights for policy 0, policy_version 1017 (0.0020) [2023-03-09 07:28:05,313][23090] Updated weights for policy 0, policy_version 1027 (0.0026) [2023-03-09 07:28:06,040][23090] Updated weights for policy 0, policy_version 1037 (0.0013) [2023-03-09 07:28:06,753][23090] Updated weights for policy 0, policy_version 1047 (0.0013) [2023-03-09 07:28:07,703][23090] Updated weights for policy 0, policy_version 1057 (0.0015) [2023-03-09 07:28:08,471][23090] Updated weights for policy 0, policy_version 1067 (0.0021) [2023-03-09 07:28:09,059][22664] Fps is (10 sec: 201516.1, 60 sec: 199611.3, 300 sec: 110079.8). Total num frames: 17612800. Throughput: 0: 50226.8. Samples: 4463296. Policy #0 lag: (min: 1.0, avg: 18.4, max: 33.0) [2023-03-09 07:28:09,061][22664] Avg episode reward: [(0, '18.948')] [2023-03-09 07:28:09,144][22940] Saving new best policy, reward=18.948! [2023-03-09 07:28:09,173][23090] Updated weights for policy 0, policy_version 1077 (0.0016) [2023-03-09 07:28:10,246][23090] Updated weights for policy 0, policy_version 1088 (0.0017) [2023-03-09 07:28:10,984][23090] Updated weights for policy 0, policy_version 1098 (0.0013) [2023-03-09 07:28:11,721][23090] Updated weights for policy 0, policy_version 1108 (0.0022) [2023-03-09 07:28:12,732][23090] Updated weights for policy 0, policy_version 1118 (0.0013) [2023-03-09 07:28:13,462][23090] Updated weights for policy 0, policy_version 1128 (0.0019) [2023-03-09 07:28:13,829][22940] Signal inference workers to stop experience collection... (450 times) [2023-03-09 07:28:13,830][22940] Signal inference workers to resume experience collection... (450 times) [2023-03-09 07:28:13,900][23090] InferenceWorker_p0-w0: stopping experience collection (450 times) [2023-03-09 07:28:13,900][23090] InferenceWorker_p0-w0: resuming experience collection (450 times) [2023-03-09 07:28:14,058][22664] Fps is (10 sec: 198250.8, 60 sec: 200431.9, 300 sec: 112702.1). Total num frames: 18595840. Throughput: 0: 50228.4. Samples: 4614832. Policy #0 lag: (min: 0.0, avg: 17.6, max: 33.0) [2023-03-09 07:28:14,060][22664] Avg episode reward: [(0, '19.577')] [2023-03-09 07:28:14,101][22940] Saving new best policy, reward=19.577! [2023-03-09 07:28:14,230][23090] Updated weights for policy 0, policy_version 1138 (0.0013) [2023-03-09 07:28:15,224][23090] Updated weights for policy 0, policy_version 1148 (0.0018) [2023-03-09 07:28:15,946][23090] Updated weights for policy 0, policy_version 1158 (0.0013) [2023-03-09 07:28:16,682][23090] Updated weights for policy 0, policy_version 1168 (0.0015) [2023-03-09 07:28:17,614][23090] Updated weights for policy 0, policy_version 1178 (0.0016) [2023-03-09 07:28:18,416][23090] Updated weights for policy 0, policy_version 1188 (0.0017) [2023-03-09 07:28:19,059][22664] Fps is (10 sec: 198249.5, 60 sec: 200430.6, 300 sec: 115266.1). Total num frames: 19595264. Throughput: 0: 50182.2. Samples: 4913744. Policy #0 lag: (min: 0.0, avg: 16.9, max: 33.0) [2023-03-09 07:28:19,060][22664] Avg episode reward: [(0, '21.703')] [2023-03-09 07:28:19,101][22940] Saving new best policy, reward=21.703! [2023-03-09 07:28:19,270][23090] Updated weights for policy 0, policy_version 1198 (0.0013) [2023-03-09 07:28:20,291][23090] Updated weights for policy 0, policy_version 1210 (0.0017) [2023-03-09 07:28:21,193][23090] Updated weights for policy 0, policy_version 1221 (0.0023) [2023-03-09 07:28:21,981][23090] Updated weights for policy 0, policy_version 1232 (0.0015) [2023-03-09 07:28:22,928][23090] Updated weights for policy 0, policy_version 1242 (0.0022) [2023-03-09 07:28:23,714][22940] Signal inference workers to stop experience collection... (500 times) [2023-03-09 07:28:23,714][22940] Signal inference workers to resume experience collection... (500 times) [2023-03-09 07:28:23,782][23090] InferenceWorker_p0-w0: stopping experience collection (500 times) [2023-03-09 07:28:23,785][23090] InferenceWorker_p0-w0: resuming experience collection (500 times) [2023-03-09 07:28:23,788][23090] Updated weights for policy 0, policy_version 1252 (0.0016) [2023-03-09 07:28:24,058][22664] Fps is (10 sec: 198246.9, 60 sec: 200432.2, 300 sec: 117590.4). Total num frames: 20578304. Throughput: 0: 49999.7. Samples: 5208512. Policy #0 lag: (min: 1.0, avg: 15.9, max: 34.0) [2023-03-09 07:28:24,059][22664] Avg episode reward: [(0, '19.323')] [2023-03-09 07:28:24,613][23090] Updated weights for policy 0, policy_version 1263 (0.0016) [2023-03-09 07:28:25,413][23090] Updated weights for policy 0, policy_version 1273 (0.0016) [2023-03-09 07:28:26,390][23090] Updated weights for policy 0, policy_version 1284 (0.0013) [2023-03-09 07:28:27,163][23090] Updated weights for policy 0, policy_version 1294 (0.0018) [2023-03-09 07:28:27,971][23090] Updated weights for policy 0, policy_version 1304 (0.0017) [2023-03-09 07:28:28,894][23090] Updated weights for policy 0, policy_version 1314 (0.0023) [2023-03-09 07:28:29,058][22664] Fps is (10 sec: 198250.5, 60 sec: 200432.2, 300 sec: 119876.3). Total num frames: 21577728. Throughput: 0: 50045.5. Samples: 5360032. Policy #0 lag: (min: 0.0, avg: 16.2, max: 32.0) [2023-03-09 07:28:29,059][22664] Avg episode reward: [(0, '23.879')] [2023-03-09 07:28:29,110][22940] Saving new best policy, reward=23.879! [2023-03-09 07:28:29,634][23090] Updated weights for policy 0, policy_version 1324 (0.0015) [2023-03-09 07:28:30,368][23090] Updated weights for policy 0, policy_version 1335 (0.0017) [2023-03-09 07:28:31,393][23090] Updated weights for policy 0, policy_version 1345 (0.0018) [2023-03-09 07:28:32,129][23090] Updated weights for policy 0, policy_version 1355 (0.0021) [2023-03-09 07:28:32,725][22940] Signal inference workers to stop experience collection... (550 times) [2023-03-09 07:28:32,727][22940] Signal inference workers to resume experience collection... (550 times) [2023-03-09 07:28:32,797][23090] InferenceWorker_p0-w0: stopping experience collection (550 times) [2023-03-09 07:28:32,797][23090] InferenceWorker_p0-w0: resuming experience collection (550 times) [2023-03-09 07:28:32,848][23090] Updated weights for policy 0, policy_version 1365 (0.0030) [2023-03-09 07:28:33,821][23090] Updated weights for policy 0, policy_version 1375 (0.0013) [2023-03-09 07:28:34,059][22664] Fps is (10 sec: 198238.3, 60 sec: 199883.7, 300 sec: 121949.9). Total num frames: 22560768. Throughput: 0: 49956.1. Samples: 5659024. Policy #0 lag: (min: 2.0, avg: 16.8, max: 34.0) [2023-03-09 07:28:34,061][22664] Avg episode reward: [(0, '22.473')] [2023-03-09 07:28:34,595][23090] Updated weights for policy 0, policy_version 1385 (0.0021) [2023-03-09 07:28:35,418][23090] Updated weights for policy 0, policy_version 1396 (0.0015) [2023-03-09 07:28:36,344][23090] Updated weights for policy 0, policy_version 1406 (0.0013) [2023-03-09 07:28:37,113][23090] Updated weights for policy 0, policy_version 1416 (0.0013) [2023-03-09 07:28:37,821][23090] Updated weights for policy 0, policy_version 1426 (0.0013) [2023-03-09 07:28:38,843][23090] Updated weights for policy 0, policy_version 1436 (0.0018) [2023-03-09 07:28:39,059][22664] Fps is (10 sec: 199879.0, 60 sec: 200430.0, 300 sec: 124087.1). Total num frames: 23576576. Throughput: 0: 50047.7. Samples: 5962000. Policy #0 lag: (min: 1.0, avg: 16.5, max: 33.0) [2023-03-09 07:28:39,060][22664] Avg episode reward: [(0, '22.107')] [2023-03-09 07:28:39,543][23090] Updated weights for policy 0, policy_version 1446 (0.0018) [2023-03-09 07:28:40,295][23090] Updated weights for policy 0, policy_version 1456 (0.0017) [2023-03-09 07:28:41,200][23090] Updated weights for policy 0, policy_version 1466 (0.0013) [2023-03-09 07:28:41,949][22940] Signal inference workers to stop experience collection... (600 times) [2023-03-09 07:28:41,961][22940] Signal inference workers to resume experience collection... (600 times) [2023-03-09 07:28:42,019][23090] InferenceWorker_p0-w0: stopping experience collection (600 times) [2023-03-09 07:28:42,020][23090] InferenceWorker_p0-w0: resuming experience collection (600 times) [2023-03-09 07:28:42,061][23090] Updated weights for policy 0, policy_version 1476 (0.0015) [2023-03-09 07:28:42,793][23090] Updated weights for policy 0, policy_version 1486 (0.0019) [2023-03-09 07:28:43,595][23090] Updated weights for policy 0, policy_version 1496 (0.0013) [2023-03-09 07:28:44,058][22664] Fps is (10 sec: 203169.4, 60 sec: 200432.0, 300 sec: 126114.8). Total num frames: 24592384. Throughput: 0: 50049.1. Samples: 6113520. Policy #0 lag: (min: 0.0, avg: 18.1, max: 33.0) [2023-03-09 07:28:44,060][22664] Avg episode reward: [(0, '26.186')] [2023-03-09 07:28:44,060][22940] Saving new best policy, reward=26.186! [2023-03-09 07:28:44,582][23090] Updated weights for policy 0, policy_version 1507 (0.0018) [2023-03-09 07:28:45,302][23090] Updated weights for policy 0, policy_version 1517 (0.0013) [2023-03-09 07:28:46,157][23090] Updated weights for policy 0, policy_version 1528 (0.0016) [2023-03-09 07:28:47,073][23090] Updated weights for policy 0, policy_version 1538 (0.0019) [2023-03-09 07:28:47,787][23090] Updated weights for policy 0, policy_version 1548 (0.0015) [2023-03-09 07:28:48,465][23090] Updated weights for policy 0, policy_version 1558 (0.0017) [2023-03-09 07:28:49,058][22664] Fps is (10 sec: 201528.9, 60 sec: 200431.7, 300 sec: 127959.1). Total num frames: 25591808. Throughput: 0: 50138.9. Samples: 6418560. Policy #0 lag: (min: 0.0, avg: 17.1, max: 34.0) [2023-03-09 07:28:49,060][22664] Avg episode reward: [(0, '24.054')] [2023-03-09 07:28:49,516][23090] Updated weights for policy 0, policy_version 1568 (0.0013) [2023-03-09 07:28:49,650][22940] Signal inference workers to stop experience collection... (650 times) [2023-03-09 07:28:49,651][22940] Signal inference workers to resume experience collection... (650 times) [2023-03-09 07:28:49,718][23090] InferenceWorker_p0-w0: stopping experience collection (650 times) [2023-03-09 07:28:49,719][23090] InferenceWorker_p0-w0: resuming experience collection (650 times) [2023-03-09 07:28:50,255][23090] Updated weights for policy 0, policy_version 1578 (0.0020) [2023-03-09 07:28:50,956][23090] Updated weights for policy 0, policy_version 1588 (0.0013) [2023-03-09 07:28:51,884][23090] Updated weights for policy 0, policy_version 1598 (0.0013) [2023-03-09 07:28:52,637][23090] Updated weights for policy 0, policy_version 1608 (0.0016) [2023-03-09 07:28:53,341][23090] Updated weights for policy 0, policy_version 1618 (0.0018) [2023-03-09 07:28:54,059][22664] Fps is (10 sec: 203155.1, 60 sec: 200976.0, 300 sec: 129873.0). Total num frames: 26624000. Throughput: 0: 50184.6. Samples: 6721600. Policy #0 lag: (min: 2.0, avg: 16.5, max: 33.0) [2023-03-09 07:28:54,061][22664] Avg episode reward: [(0, '25.081')] [2023-03-09 07:28:54,367][23090] Updated weights for policy 0, policy_version 1628 (0.0016) [2023-03-09 07:28:55,077][23090] Updated weights for policy 0, policy_version 1639 (0.0017) [2023-03-09 07:28:55,878][23090] Updated weights for policy 0, policy_version 1649 (0.0024) [2023-03-09 07:28:56,888][23090] Updated weights for policy 0, policy_version 1659 (0.0016) [2023-03-09 07:28:57,464][22940] Signal inference workers to stop experience collection... (700 times) [2023-03-09 07:28:57,482][22940] Signal inference workers to resume experience collection... (700 times) [2023-03-09 07:28:57,535][23090] InferenceWorker_p0-w0: stopping experience collection (700 times) [2023-03-09 07:28:57,538][23090] InferenceWorker_p0-w0: resuming experience collection (700 times) [2023-03-09 07:28:57,626][23090] Updated weights for policy 0, policy_version 1669 (0.0016) [2023-03-09 07:28:58,456][23090] Updated weights for policy 0, policy_version 1680 (0.0013) [2023-03-09 07:28:59,059][22664] Fps is (10 sec: 204791.7, 60 sec: 200702.6, 300 sec: 131617.9). Total num frames: 27639808. Throughput: 0: 50183.3. Samples: 6873104. Policy #0 lag: (min: 2.0, avg: 17.7, max: 33.0) [2023-03-09 07:28:59,061][22664] Avg episode reward: [(0, '24.306')] [2023-03-09 07:28:59,313][23090] Updated weights for policy 0, policy_version 1690 (0.0013) [2023-03-09 07:29:00,171][23090] Updated weights for policy 0, policy_version 1701 (0.0014) [2023-03-09 07:29:00,944][23090] Updated weights for policy 0, policy_version 1711 (0.0018) [2023-03-09 07:29:01,918][23090] Updated weights for policy 0, policy_version 1722 (0.0017) [2023-03-09 07:29:02,715][23090] Updated weights for policy 0, policy_version 1732 (0.0022) [2023-03-09 07:29:03,476][23090] Updated weights for policy 0, policy_version 1742 (0.0015) [2023-03-09 07:29:04,059][22664] Fps is (10 sec: 204802.2, 60 sec: 200977.1, 300 sec: 133358.0). Total num frames: 28672000. Throughput: 0: 50273.4. Samples: 7176048. Policy #0 lag: (min: 1.0, avg: 18.5, max: 33.0) [2023-03-09 07:29:04,060][22664] Avg episode reward: [(0, '27.764')] [2023-03-09 07:29:04,061][22940] Saving new best policy, reward=27.764! [2023-03-09 07:29:04,276][23090] Updated weights for policy 0, policy_version 1752 (0.0014) [2023-03-09 07:29:05,239][23090] Updated weights for policy 0, policy_version 1762 (0.0020) [2023-03-09 07:29:05,464][22940] Signal inference workers to stop experience collection... (750 times) [2023-03-09 07:29:05,465][22940] Signal inference workers to resume experience collection... (750 times) [2023-03-09 07:29:05,527][23090] InferenceWorker_p0-w0: stopping experience collection (750 times) [2023-03-09 07:29:05,527][23090] InferenceWorker_p0-w0: resuming experience collection (750 times) [2023-03-09 07:29:05,959][23090] Updated weights for policy 0, policy_version 1772 (0.0021) [2023-03-09 07:29:06,597][23090] Updated weights for policy 0, policy_version 1782 (0.0017) [2023-03-09 07:29:07,624][23090] Updated weights for policy 0, policy_version 1792 (0.0013) [2023-03-09 07:29:08,374][23090] Updated weights for policy 0, policy_version 1802 (0.0019) [2023-03-09 07:29:09,058][22664] Fps is (10 sec: 204808.4, 60 sec: 201251.3, 300 sec: 134944.6). Total num frames: 29687808. Throughput: 0: 50502.0. Samples: 7481104. Policy #0 lag: (min: 0.0, avg: 16.2, max: 33.0) [2023-03-09 07:29:09,060][22664] Avg episode reward: [(0, '24.116')] [2023-03-09 07:29:09,065][23090] Updated weights for policy 0, policy_version 1812 (0.0017) [2023-03-09 07:29:10,014][23090] Updated weights for policy 0, policy_version 1822 (0.0015) [2023-03-09 07:29:10,770][23090] Updated weights for policy 0, policy_version 1832 (0.0019) [2023-03-09 07:29:11,471][23090] Updated weights for policy 0, policy_version 1842 (0.0016) [2023-03-09 07:29:12,502][23090] Updated weights for policy 0, policy_version 1852 (0.0012) [2023-03-09 07:29:13,249][23090] Updated weights for policy 0, policy_version 1862 (0.0019) [2023-03-09 07:29:13,938][22940] Signal inference workers to stop experience collection... (800 times) [2023-03-09 07:29:13,942][22940] Signal inference workers to resume experience collection... (800 times) [2023-03-09 07:29:13,973][23090] Updated weights for policy 0, policy_version 1872 (0.0018) [2023-03-09 07:29:14,013][23090] InferenceWorker_p0-w0: stopping experience collection (800 times) [2023-03-09 07:29:14,018][23090] InferenceWorker_p0-w0: resuming experience collection (800 times) [2023-03-09 07:29:14,059][22664] Fps is (10 sec: 201520.7, 60 sec: 201522.1, 300 sec: 136387.5). Total num frames: 30687232. Throughput: 0: 50501.3. Samples: 7632608. Policy #0 lag: (min: 3.0, avg: 18.1, max: 34.0) [2023-03-09 07:29:14,061][22664] Avg episode reward: [(0, '26.533')] [2023-03-09 07:29:14,867][23090] Updated weights for policy 0, policy_version 1882 (0.0020) [2023-03-09 07:29:15,652][23090] Updated weights for policy 0, policy_version 1892 (0.0015) [2023-03-09 07:29:16,497][23090] Updated weights for policy 0, policy_version 1903 (0.0018) [2023-03-09 07:29:17,476][23090] Updated weights for policy 0, policy_version 1914 (0.0020) [2023-03-09 07:29:18,310][23090] Updated weights for policy 0, policy_version 1924 (0.0019) [2023-03-09 07:29:19,058][22664] Fps is (10 sec: 198246.2, 60 sec: 201250.8, 300 sec: 137696.8). Total num frames: 31670272. Throughput: 0: 50591.7. Samples: 7935632. Policy #0 lag: (min: 0.0, avg: 18.1, max: 33.0) [2023-03-09 07:29:19,059][22664] Avg episode reward: [(0, '26.979')] [2023-03-09 07:29:19,070][23090] Updated weights for policy 0, policy_version 1934 (0.0017) [2023-03-09 07:29:19,126][22940] Saving /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000001935_31703040.pth... [2023-03-09 07:29:19,832][23090] Updated weights for policy 0, policy_version 1944 (0.0022) [2023-03-09 07:29:20,721][23090] Updated weights for policy 0, policy_version 1954 (0.0016) [2023-03-09 07:29:21,504][23090] Updated weights for policy 0, policy_version 1964 (0.0013) [2023-03-09 07:29:21,989][22940] Signal inference workers to stop experience collection... (850 times) [2023-03-09 07:29:22,005][22940] Signal inference workers to resume experience collection... (850 times) [2023-03-09 07:29:22,070][23090] InferenceWorker_p0-w0: stopping experience collection (850 times) [2023-03-09 07:29:22,073][23090] InferenceWorker_p0-w0: resuming experience collection (850 times) [2023-03-09 07:29:22,119][23090] Updated weights for policy 0, policy_version 1974 (0.0022) [2023-03-09 07:29:23,242][23090] Updated weights for policy 0, policy_version 1985 (0.0013) [2023-03-09 07:29:24,053][23090] Updated weights for policy 0, policy_version 1995 (0.0016) [2023-03-09 07:29:24,059][22664] Fps is (10 sec: 199884.7, 60 sec: 201795.0, 300 sec: 139089.5). Total num frames: 32686080. Throughput: 0: 50590.9. Samples: 8238592. Policy #0 lag: (min: 2.0, avg: 16.6, max: 33.0) [2023-03-09 07:29:24,061][22664] Avg episode reward: [(0, '25.186')] [2023-03-09 07:29:24,697][23090] Updated weights for policy 0, policy_version 2005 (0.0015) [2023-03-09 07:29:25,656][23090] Updated weights for policy 0, policy_version 2015 (0.0018) [2023-03-09 07:29:26,387][23090] Updated weights for policy 0, policy_version 2025 (0.0015) [2023-03-09 07:29:27,183][23090] Updated weights for policy 0, policy_version 2035 (0.0016) [2023-03-09 07:29:28,089][23090] Updated weights for policy 0, policy_version 2045 (0.0015) [2023-03-09 07:29:28,842][23090] Updated weights for policy 0, policy_version 2055 (0.0019) [2023-03-09 07:29:29,059][22664] Fps is (10 sec: 203158.0, 60 sec: 202068.7, 300 sec: 140424.4). Total num frames: 33701888. Throughput: 0: 50590.0. Samples: 8390080. Policy #0 lag: (min: 1.0, avg: 17.0, max: 33.0) [2023-03-09 07:29:29,060][22664] Avg episode reward: [(0, '26.824')] [2023-03-09 07:29:29,573][23090] Updated weights for policy 0, policy_version 2065 (0.0021) [2023-03-09 07:29:30,608][23090] Updated weights for policy 0, policy_version 2075 (0.0025) [2023-03-09 07:29:31,300][23090] Updated weights for policy 0, policy_version 2085 (0.0015) [2023-03-09 07:29:31,358][22940] Signal inference workers to stop experience collection... (900 times) [2023-03-09 07:29:31,359][22940] Signal inference workers to resume experience collection... (900 times) [2023-03-09 07:29:31,421][23090] InferenceWorker_p0-w0: stopping experience collection (900 times) [2023-03-09 07:29:31,421][23090] InferenceWorker_p0-w0: resuming experience collection (900 times) [2023-03-09 07:29:32,344][23090] Updated weights for policy 0, policy_version 2095 (0.0012) [2023-03-09 07:29:33,111][23090] Updated weights for policy 0, policy_version 2105 (0.0013) [2023-03-09 07:29:34,023][23090] Updated weights for policy 0, policy_version 2115 (0.0015) [2023-03-09 07:29:34,059][22664] Fps is (10 sec: 196608.4, 60 sec: 201523.4, 300 sec: 141437.2). Total num frames: 34652160. Throughput: 0: 50226.5. Samples: 8678768. Policy #0 lag: (min: 0.0, avg: 15.9, max: 32.0) [2023-03-09 07:29:34,061][22664] Avg episode reward: [(0, '27.437')] [2023-03-09 07:29:34,766][23090] Updated weights for policy 0, policy_version 2125 (0.0012) [2023-03-09 07:29:35,514][23090] Updated weights for policy 0, policy_version 2135 (0.0016) [2023-03-09 07:29:36,456][23090] Updated weights for policy 0, policy_version 2145 (0.0019) [2023-03-09 07:29:37,268][23090] Updated weights for policy 0, policy_version 2155 (0.0017) [2023-03-09 07:29:37,979][23090] Updated weights for policy 0, policy_version 2166 (0.0013) [2023-03-09 07:29:38,959][23090] Updated weights for policy 0, policy_version 2176 (0.0012) [2023-03-09 07:29:39,059][22664] Fps is (10 sec: 196610.9, 60 sec: 201524.0, 300 sec: 142671.9). Total num frames: 35667968. Throughput: 0: 50271.9. Samples: 8983824. Policy #0 lag: (min: 2.0, avg: 16.6, max: 33.0) [2023-03-09 07:29:39,059][22664] Avg episode reward: [(0, '25.984')] [2023-03-09 07:29:39,753][23090] Updated weights for policy 0, policy_version 2186 (0.0015) [2023-03-09 07:29:40,440][23090] Updated weights for policy 0, policy_version 2196 (0.0013) [2023-03-09 07:29:40,506][22940] Signal inference workers to stop experience collection... (950 times) [2023-03-09 07:29:40,506][22940] Signal inference workers to resume experience collection... (950 times) [2023-03-09 07:29:40,564][23090] InferenceWorker_p0-w0: stopping experience collection (950 times) [2023-03-09 07:29:40,564][23090] InferenceWorker_p0-w0: resuming experience collection (950 times) [2023-03-09 07:29:41,382][23090] Updated weights for policy 0, policy_version 2206 (0.0015) [2023-03-09 07:29:42,204][23090] Updated weights for policy 0, policy_version 2217 (0.0016) [2023-03-09 07:29:42,978][23090] Updated weights for policy 0, policy_version 2227 (0.0013) [2023-03-09 07:29:43,980][23090] Updated weights for policy 0, policy_version 2238 (0.0013) [2023-03-09 07:29:44,059][22664] Fps is (10 sec: 203166.3, 60 sec: 201522.9, 300 sec: 143857.9). Total num frames: 36683776. Throughput: 0: 50317.2. Samples: 9137360. Policy #0 lag: (min: 1.0, avg: 17.6, max: 33.0) [2023-03-09 07:29:44,060][22664] Avg episode reward: [(0, '26.417')] [2023-03-09 07:29:44,709][23090] Updated weights for policy 0, policy_version 2248 (0.0017) [2023-03-09 07:29:45,433][23090] Updated weights for policy 0, policy_version 2258 (0.0031) [2023-03-09 07:29:46,435][23090] Updated weights for policy 0, policy_version 2268 (0.0016) [2023-03-09 07:29:47,134][23090] Updated weights for policy 0, policy_version 2278 (0.0013) [2023-03-09 07:29:47,941][23090] Updated weights for policy 0, policy_version 2288 (0.0017) [2023-03-09 07:29:48,771][23090] Updated weights for policy 0, policy_version 2298 (0.0013) [2023-03-09 07:29:49,058][22664] Fps is (10 sec: 201524.2, 60 sec: 201523.3, 300 sec: 144935.4). Total num frames: 37683200. Throughput: 0: 50319.2. Samples: 9440400. Policy #0 lag: (min: 1.0, avg: 16.1, max: 33.0) [2023-03-09 07:29:49,059][22664] Avg episode reward: [(0, '27.706')] [2023-03-09 07:29:49,598][23090] Updated weights for policy 0, policy_version 2308 (0.0016) [2023-03-09 07:29:49,605][22940] Signal inference workers to stop experience collection... (1000 times) [2023-03-09 07:29:49,606][22940] Signal inference workers to resume experience collection... (1000 times) [2023-03-09 07:29:49,687][23090] InferenceWorker_p0-w0: stopping experience collection (1000 times) [2023-03-09 07:29:49,687][23090] InferenceWorker_p0-w0: resuming experience collection (1000 times) [2023-03-09 07:29:50,416][23090] Updated weights for policy 0, policy_version 2318 (0.0016) [2023-03-09 07:29:51,199][23090] Updated weights for policy 0, policy_version 2328 (0.0013) [2023-03-09 07:29:52,108][23090] Updated weights for policy 0, policy_version 2338 (0.0017) [2023-03-09 07:29:52,786][23090] Updated weights for policy 0, policy_version 2348 (0.0015) [2023-03-09 07:29:53,483][23090] Updated weights for policy 0, policy_version 2358 (0.0017) [2023-03-09 07:29:54,058][22664] Fps is (10 sec: 201524.7, 60 sec: 201251.1, 300 sec: 146034.0). Total num frames: 38699008. Throughput: 0: 50318.6. Samples: 9745440. Policy #0 lag: (min: 0.0, avg: 18.2, max: 34.0) [2023-03-09 07:29:54,060][22664] Avg episode reward: [(0, '25.103')] [2023-03-09 07:29:54,474][23090] Updated weights for policy 0, policy_version 2368 (0.0018) [2023-03-09 07:29:55,252][23090] Updated weights for policy 0, policy_version 2378 (0.0015) [2023-03-09 07:29:55,971][23090] Updated weights for policy 0, policy_version 2388 (0.0026) [2023-03-09 07:29:56,927][23090] Updated weights for policy 0, policy_version 2398 (0.0017) [2023-03-09 07:29:57,758][23090] Updated weights for policy 0, policy_version 2409 (0.0018) [2023-03-09 07:29:58,320][22940] Signal inference workers to stop experience collection... (1050 times) [2023-03-09 07:29:58,339][22940] Signal inference workers to resume experience collection... (1050 times) [2023-03-09 07:29:58,398][23090] InferenceWorker_p0-w0: stopping experience collection (1050 times) [2023-03-09 07:29:58,398][23090] InferenceWorker_p0-w0: resuming experience collection (1050 times) [2023-03-09 07:29:58,489][23090] Updated weights for policy 0, policy_version 2419 (0.0021) [2023-03-09 07:29:59,058][22664] Fps is (10 sec: 204799.9, 60 sec: 201524.6, 300 sec: 147152.6). Total num frames: 39731200. Throughput: 0: 50274.1. Samples: 9894928. Policy #0 lag: (min: 1.0, avg: 15.9, max: 33.0) [2023-03-09 07:29:59,059][22664] Avg episode reward: [(0, '29.248')] [2023-03-09 07:29:59,137][22940] Saving new best policy, reward=29.248! [2023-03-09 07:29:59,436][23090] Updated weights for policy 0, policy_version 2429 (0.0024) [2023-03-09 07:30:00,180][23090] Updated weights for policy 0, policy_version 2439 (0.0018) [2023-03-09 07:30:00,952][23090] Updated weights for policy 0, policy_version 2449 (0.0013) [2023-03-09 07:30:01,956][23090] Updated weights for policy 0, policy_version 2459 (0.0017) [2023-03-09 07:30:02,646][23090] Updated weights for policy 0, policy_version 2469 (0.0017) [2023-03-09 07:30:03,425][23090] Updated weights for policy 0, policy_version 2479 (0.0013) [2023-03-09 07:30:04,058][22664] Fps is (10 sec: 204800.0, 60 sec: 201250.8, 300 sec: 148171.0). Total num frames: 40747008. Throughput: 0: 50273.8. Samples: 10197952. Policy #0 lag: (min: 0.0, avg: 18.3, max: 34.0) [2023-03-09 07:30:04,059][22664] Avg episode reward: [(0, '31.064')] [2023-03-09 07:30:04,106][22940] Saving new best policy, reward=31.064! [2023-03-09 07:30:04,225][23090] Updated weights for policy 0, policy_version 2489 (0.0013) [2023-03-09 07:30:05,118][23090] Updated weights for policy 0, policy_version 2499 (0.0013) [2023-03-09 07:30:05,882][23090] Updated weights for policy 0, policy_version 2509 (0.0019) [2023-03-09 07:30:06,385][22940] Signal inference workers to stop experience collection... (1100 times) [2023-03-09 07:30:06,387][22940] Signal inference workers to resume experience collection... (1100 times) [2023-03-09 07:30:06,447][23090] InferenceWorker_p0-w0: stopping experience collection (1100 times) [2023-03-09 07:30:06,447][23090] InferenceWorker_p0-w0: resuming experience collection (1100 times) [2023-03-09 07:30:06,642][23090] Updated weights for policy 0, policy_version 2519 (0.0016) [2023-03-09 07:30:07,601][23090] Updated weights for policy 0, policy_version 2529 (0.0017) [2023-03-09 07:30:08,410][23090] Updated weights for policy 0, policy_version 2539 (0.0022) [2023-03-09 07:30:09,054][23090] Updated weights for policy 0, policy_version 2549 (0.0016) [2023-03-09 07:30:09,059][22664] Fps is (10 sec: 203148.7, 60 sec: 201248.0, 300 sec: 149152.6). Total num frames: 41762816. Throughput: 0: 50229.0. Samples: 10498912. Policy #0 lag: (min: 1.0, avg: 16.1, max: 33.0) [2023-03-09 07:30:09,062][22664] Avg episode reward: [(0, '30.679')] [2023-03-09 07:30:09,987][23090] Updated weights for policy 0, policy_version 2559 (0.0017) [2023-03-09 07:30:10,788][23090] Updated weights for policy 0, policy_version 2569 (0.0025) [2023-03-09 07:30:11,493][23090] Updated weights for policy 0, policy_version 2579 (0.0021) [2023-03-09 07:30:12,555][23090] Updated weights for policy 0, policy_version 2590 (0.0018) [2023-03-09 07:30:13,327][23090] Updated weights for policy 0, policy_version 2600 (0.0017) [2023-03-09 07:30:14,025][23090] Updated weights for policy 0, policy_version 2610 (0.0013) [2023-03-09 07:30:14,059][22664] Fps is (10 sec: 201522.2, 60 sec: 201251.0, 300 sec: 150042.9). Total num frames: 42762240. Throughput: 0: 50275.4. Samples: 10652464. Policy #0 lag: (min: 1.0, avg: 16.7, max: 33.0) [2023-03-09 07:30:14,060][22664] Avg episode reward: [(0, '26.054')] [2023-03-09 07:30:15,017][23090] Updated weights for policy 0, policy_version 2620 (0.0021) [2023-03-09 07:30:15,717][23090] Updated weights for policy 0, policy_version 2630 (0.0021) [2023-03-09 07:30:16,525][23090] Updated weights for policy 0, policy_version 2640 (0.0020) [2023-03-09 07:30:17,381][23090] Updated weights for policy 0, policy_version 2650 (0.0019) [2023-03-09 07:30:17,534][22940] Signal inference workers to stop experience collection... (1150 times) [2023-03-09 07:30:17,536][22940] Signal inference workers to resume experience collection... (1150 times) [2023-03-09 07:30:17,617][23090] InferenceWorker_p0-w0: stopping experience collection (1150 times) [2023-03-09 07:30:17,618][23090] InferenceWorker_p0-w0: resuming experience collection (1150 times) [2023-03-09 07:30:18,260][23090] Updated weights for policy 0, policy_version 2660 (0.0021) [2023-03-09 07:30:19,051][23090] Updated weights for policy 0, policy_version 2670 (0.0015) [2023-03-09 07:30:19,059][22664] Fps is (10 sec: 198251.0, 60 sec: 201248.9, 300 sec: 150845.6). Total num frames: 43745280. Throughput: 0: 50503.4. Samples: 10951424. Policy #0 lag: (min: 1.0, avg: 17.3, max: 34.0) [2023-03-09 07:30:19,061][22664] Avg episode reward: [(0, '29.669')] [2023-03-09 07:30:19,817][23090] Updated weights for policy 0, policy_version 2680 (0.0016) [2023-03-09 07:30:20,747][23090] Updated weights for policy 0, policy_version 2690 (0.0013) [2023-03-09 07:30:21,482][23090] Updated weights for policy 0, policy_version 2700 (0.0013) [2023-03-09 07:30:22,312][23090] Updated weights for policy 0, policy_version 2711 (0.0015) [2023-03-09 07:30:23,212][23090] Updated weights for policy 0, policy_version 2721 (0.0016) [2023-03-09 07:30:24,011][23090] Updated weights for policy 0, policy_version 2731 (0.0016) [2023-03-09 07:30:24,059][22664] Fps is (10 sec: 199877.5, 60 sec: 201249.8, 300 sec: 151732.3). Total num frames: 44761088. Throughput: 0: 50457.9. Samples: 11254448. Policy #0 lag: (min: 1.0, avg: 18.7, max: 33.0) [2023-03-09 07:30:24,061][22664] Avg episode reward: [(0, '28.664')] [2023-03-09 07:30:24,719][23090] Updated weights for policy 0, policy_version 2742 (0.0019) [2023-03-09 07:30:25,711][23090] Updated weights for policy 0, policy_version 2752 (0.0014) [2023-03-09 07:30:26,514][23090] Updated weights for policy 0, policy_version 2762 (0.0017) [2023-03-09 07:30:27,101][22940] Signal inference workers to stop experience collection... (1200 times) [2023-03-09 07:30:27,103][22940] Signal inference workers to resume experience collection... (1200 times) [2023-03-09 07:30:27,177][23090] InferenceWorker_p0-w0: stopping experience collection (1200 times) [2023-03-09 07:30:27,177][23090] InferenceWorker_p0-w0: resuming experience collection (1200 times) [2023-03-09 07:30:27,180][23090] Updated weights for policy 0, policy_version 2772 (0.0017) [2023-03-09 07:30:28,127][23090] Updated weights for policy 0, policy_version 2782 (0.0015) [2023-03-09 07:30:28,896][23090] Updated weights for policy 0, policy_version 2792 (0.0013) [2023-03-09 07:30:29,059][22664] Fps is (10 sec: 201516.9, 60 sec: 200975.3, 300 sec: 155120.1). Total num frames: 45760512. Throughput: 0: 50412.4. Samples: 11405952. Policy #0 lag: (min: 1.0, avg: 16.0, max: 32.0) [2023-03-09 07:30:29,062][22664] Avg episode reward: [(0, '32.193')] [2023-03-09 07:30:29,071][22940] Saving new best policy, reward=32.193! [2023-03-09 07:30:29,615][23090] Updated weights for policy 0, policy_version 2802 (0.0019) [2023-03-09 07:30:30,599][23090] Updated weights for policy 0, policy_version 2812 (0.0015) [2023-03-09 07:30:31,329][23090] Updated weights for policy 0, policy_version 2822 (0.0013) [2023-03-09 07:30:32,102][23090] Updated weights for policy 0, policy_version 2832 (0.0013) [2023-03-09 07:30:33,162][23090] Updated weights for policy 0, policy_version 2843 (0.0017) [2023-03-09 07:30:33,876][23090] Updated weights for policy 0, policy_version 2853 (0.0016) [2023-03-09 07:30:34,058][22664] Fps is (10 sec: 201531.9, 60 sec: 202070.4, 300 sec: 158563.9). Total num frames: 46776320. Throughput: 0: 50413.2. Samples: 11708992. Policy #0 lag: (min: 0.0, avg: 16.1, max: 32.0) [2023-03-09 07:30:34,059][22664] Avg episode reward: [(0, '31.652')] [2023-03-09 07:30:34,662][23090] Updated weights for policy 0, policy_version 2863 (0.0020) [2023-03-09 07:30:35,428][23090] Updated weights for policy 0, policy_version 2873 (0.0014) [2023-03-09 07:30:36,416][23090] Updated weights for policy 0, policy_version 2883 (0.0015) [2023-03-09 07:30:37,150][23090] Updated weights for policy 0, policy_version 2893 (0.0021) [2023-03-09 07:30:37,397][22940] Signal inference workers to stop experience collection... (1250 times) [2023-03-09 07:30:37,397][22940] Signal inference workers to resume experience collection... (1250 times) [2023-03-09 07:30:37,471][23090] InferenceWorker_p0-w0: stopping experience collection (1250 times) [2023-03-09 07:30:37,472][23090] InferenceWorker_p0-w0: resuming experience collection (1250 times) [2023-03-09 07:30:38,025][23090] Updated weights for policy 0, policy_version 2904 (0.0017) [2023-03-09 07:30:38,902][23090] Updated weights for policy 0, policy_version 2914 (0.0013) [2023-03-09 07:30:39,059][22664] Fps is (10 sec: 201536.2, 60 sec: 201796.2, 300 sec: 161951.7). Total num frames: 47775744. Throughput: 0: 50322.4. Samples: 12009952. Policy #0 lag: (min: 0.0, avg: 16.1, max: 32.0) [2023-03-09 07:30:39,059][22664] Avg episode reward: [(0, '31.776')] [2023-03-09 07:30:39,678][23090] Updated weights for policy 0, policy_version 2924 (0.0015) [2023-03-09 07:30:40,504][23090] Updated weights for policy 0, policy_version 2935 (0.0016) [2023-03-09 07:30:41,398][23090] Updated weights for policy 0, policy_version 2945 (0.0013) [2023-03-09 07:30:42,238][23090] Updated weights for policy 0, policy_version 2955 (0.0019) [2023-03-09 07:30:42,854][23090] Updated weights for policy 0, policy_version 2965 (0.0019) [2023-03-09 07:30:43,865][23090] Updated weights for policy 0, policy_version 2975 (0.0023) [2023-03-09 07:30:44,058][22664] Fps is (10 sec: 199884.2, 60 sec: 201523.4, 300 sec: 165339.6). Total num frames: 48775168. Throughput: 0: 50368.0. Samples: 12161488. Policy #0 lag: (min: 0.0, avg: 17.1, max: 33.0) [2023-03-09 07:30:44,060][22664] Avg episode reward: [(0, '31.873')] [2023-03-09 07:30:44,636][23090] Updated weights for policy 0, policy_version 2985 (0.0013) [2023-03-09 07:30:45,337][23090] Updated weights for policy 0, policy_version 2995 (0.0017) [2023-03-09 07:30:46,334][23090] Updated weights for policy 0, policy_version 3005 (0.0016) [2023-03-09 07:30:47,006][23090] Updated weights for policy 0, policy_version 3015 (0.0018) [2023-03-09 07:30:47,813][22940] Signal inference workers to stop experience collection... (1300 times) [2023-03-09 07:30:47,815][22940] Signal inference workers to resume experience collection... (1300 times) [2023-03-09 07:30:47,848][23090] Updated weights for policy 0, policy_version 3025 (0.0014) [2023-03-09 07:30:47,889][23090] InferenceWorker_p0-w0: stopping experience collection (1300 times) [2023-03-09 07:30:47,889][23090] InferenceWorker_p0-w0: resuming experience collection (1300 times) [2023-03-09 07:30:48,829][23090] Updated weights for policy 0, policy_version 3036 (0.0016) [2023-03-09 07:30:49,059][22664] Fps is (10 sec: 201516.6, 60 sec: 201794.9, 300 sec: 168782.8). Total num frames: 49790976. Throughput: 0: 50322.4. Samples: 12462480. Policy #0 lag: (min: 1.0, avg: 17.7, max: 33.0) [2023-03-09 07:30:49,061][22664] Avg episode reward: [(0, '29.171')] [2023-03-09 07:30:49,577][23090] Updated weights for policy 0, policy_version 3046 (0.0013) [2023-03-09 07:30:50,315][23090] Updated weights for policy 0, policy_version 3056 (0.0015) [2023-03-09 07:30:51,175][23090] Updated weights for policy 0, policy_version 3066 (0.0018) [2023-03-09 07:30:51,993][23090] Updated weights for policy 0, policy_version 3076 (0.0013) [2023-03-09 07:30:52,806][23090] Updated weights for policy 0, policy_version 3086 (0.0018) [2023-03-09 07:30:53,620][23090] Updated weights for policy 0, policy_version 3096 (0.0016) [2023-03-09 07:30:54,059][22664] Fps is (10 sec: 201513.1, 60 sec: 201521.4, 300 sec: 172170.6). Total num frames: 50790400. Throughput: 0: 50368.5. Samples: 12765488. Policy #0 lag: (min: 0.0, avg: 16.9, max: 33.0) [2023-03-09 07:30:54,061][22664] Avg episode reward: [(0, '30.799')] [2023-03-09 07:30:54,491][23090] Updated weights for policy 0, policy_version 3106 (0.0017) [2023-03-09 07:30:55,296][23090] Updated weights for policy 0, policy_version 3116 (0.0014) [2023-03-09 07:30:55,938][23090] Updated weights for policy 0, policy_version 3126 (0.0013) [2023-03-09 07:30:56,929][23090] Updated weights for policy 0, policy_version 3136 (0.0020) [2023-03-09 07:30:57,755][23090] Updated weights for policy 0, policy_version 3146 (0.0013) [2023-03-09 07:30:58,416][23090] Updated weights for policy 0, policy_version 3156 (0.0013) [2023-03-09 07:30:58,479][22940] Signal inference workers to stop experience collection... (1350 times) [2023-03-09 07:30:58,480][22940] Signal inference workers to resume experience collection... (1350 times) [2023-03-09 07:30:58,540][23090] InferenceWorker_p0-w0: stopping experience collection (1350 times) [2023-03-09 07:30:58,540][23090] InferenceWorker_p0-w0: resuming experience collection (1350 times) [2023-03-09 07:30:59,059][22664] Fps is (10 sec: 201523.6, 60 sec: 201248.9, 300 sec: 175614.2). Total num frames: 51806208. Throughput: 0: 50323.2. Samples: 12917024. Policy #0 lag: (min: 1.0, avg: 17.4, max: 32.0) [2023-03-09 07:30:59,061][22664] Avg episode reward: [(0, '34.587')] [2023-03-09 07:30:59,108][22940] Saving new best policy, reward=34.587! [2023-03-09 07:30:59,411][23090] Updated weights for policy 0, policy_version 3166 (0.0017) [2023-03-09 07:31:00,159][23090] Updated weights for policy 0, policy_version 3176 (0.0015) [2023-03-09 07:31:00,884][23090] Updated weights for policy 0, policy_version 3186 (0.0020) [2023-03-09 07:31:01,865][23090] Updated weights for policy 0, policy_version 3196 (0.0013) [2023-03-09 07:31:02,589][23090] Updated weights for policy 0, policy_version 3206 (0.0017) [2023-03-09 07:31:03,350][23090] Updated weights for policy 0, policy_version 3216 (0.0016) [2023-03-09 07:31:04,059][22664] Fps is (10 sec: 204807.9, 60 sec: 201522.7, 300 sec: 179113.3). Total num frames: 52838400. Throughput: 0: 50414.2. Samples: 13220048. Policy #0 lag: (min: 0.0, avg: 16.9, max: 33.0) [2023-03-09 07:31:04,060][22664] Avg episode reward: [(0, '34.279')] [2023-03-09 07:31:04,215][23090] Updated weights for policy 0, policy_version 3226 (0.0013) [2023-03-09 07:31:05,041][23090] Updated weights for policy 0, policy_version 3236 (0.0016) [2023-03-09 07:31:05,844][23090] Updated weights for policy 0, policy_version 3246 (0.0013) [2023-03-09 07:31:06,619][23090] Updated weights for policy 0, policy_version 3256 (0.0018) [2023-03-09 07:31:07,555][23090] Updated weights for policy 0, policy_version 3266 (0.0016) [2023-03-09 07:31:08,308][23090] Updated weights for policy 0, policy_version 3276 (0.0014) [2023-03-09 07:31:08,699][22940] Signal inference workers to stop experience collection... (1400 times) [2023-03-09 07:31:08,701][22940] Signal inference workers to resume experience collection... (1400 times) [2023-03-09 07:31:08,778][23090] InferenceWorker_p0-w0: stopping experience collection (1400 times) [2023-03-09 07:31:08,778][23090] InferenceWorker_p0-w0: resuming experience collection (1400 times) [2023-03-09 07:31:08,930][23090] Updated weights for policy 0, policy_version 3286 (0.0016) [2023-03-09 07:31:09,059][22664] Fps is (10 sec: 203166.4, 60 sec: 201251.8, 300 sec: 182501.0). Total num frames: 53837824. Throughput: 0: 50323.9. Samples: 13519008. Policy #0 lag: (min: 1.0, avg: 16.2, max: 32.0) [2023-03-09 07:31:09,060][22664] Avg episode reward: [(0, '32.678')] [2023-03-09 07:31:09,959][23090] Updated weights for policy 0, policy_version 3296 (0.0016) [2023-03-09 07:31:10,814][23090] Updated weights for policy 0, policy_version 3306 (0.0016) [2023-03-09 07:31:11,441][23090] Updated weights for policy 0, policy_version 3316 (0.0013) [2023-03-09 07:31:12,428][23090] Updated weights for policy 0, policy_version 3326 (0.0019) [2023-03-09 07:31:13,198][23090] Updated weights for policy 0, policy_version 3336 (0.0018) [2023-03-09 07:31:14,004][23090] Updated weights for policy 0, policy_version 3347 (0.0013) [2023-03-09 07:31:14,059][22664] Fps is (10 sec: 201518.8, 60 sec: 201522.2, 300 sec: 185777.7). Total num frames: 54853632. Throughput: 0: 50324.3. Samples: 13670528. Policy #0 lag: (min: 0.0, avg: 16.1, max: 32.0) [2023-03-09 07:31:14,061][22664] Avg episode reward: [(0, '28.751')] [2023-03-09 07:31:14,945][23090] Updated weights for policy 0, policy_version 3357 (0.0018) [2023-03-09 07:31:15,677][23090] Updated weights for policy 0, policy_version 3367 (0.0018) [2023-03-09 07:31:16,528][23090] Updated weights for policy 0, policy_version 3378 (0.0015) [2023-03-09 07:31:17,462][23090] Updated weights for policy 0, policy_version 3388 (0.0013) [2023-03-09 07:31:18,254][23090] Updated weights for policy 0, policy_version 3399 (0.0019) [2023-03-09 07:31:18,889][22940] Signal inference workers to stop experience collection... (1450 times) [2023-03-09 07:31:18,890][22940] Signal inference workers to resume experience collection... (1450 times) [2023-03-09 07:31:18,973][23090] InferenceWorker_p0-w0: stopping experience collection (1450 times) [2023-03-09 07:31:18,973][23090] InferenceWorker_p0-w0: resuming experience collection (1450 times) [2023-03-09 07:31:19,021][23090] Updated weights for policy 0, policy_version 3409 (0.0017) [2023-03-09 07:31:19,059][22664] Fps is (10 sec: 201521.1, 60 sec: 201796.8, 300 sec: 188887.9). Total num frames: 55853056. Throughput: 0: 50368.1. Samples: 13975568. Policy #0 lag: (min: 2.0, avg: 16.9, max: 34.0) [2023-03-09 07:31:19,061][22664] Avg episode reward: [(0, '31.619')] [2023-03-09 07:31:19,136][22940] Saving /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000003411_55885824.pth... [2023-03-09 07:31:19,200][22940] Removing /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000000464_7602176.pth [2023-03-09 07:31:20,003][23090] Updated weights for policy 0, policy_version 3419 (0.0019) [2023-03-09 07:31:20,736][23090] Updated weights for policy 0, policy_version 3429 (0.0013) [2023-03-09 07:31:21,478][23090] Updated weights for policy 0, policy_version 3439 (0.0022) [2023-03-09 07:31:22,286][23090] Updated weights for policy 0, policy_version 3449 (0.0013) [2023-03-09 07:31:23,203][23090] Updated weights for policy 0, policy_version 3459 (0.0016) [2023-03-09 07:31:24,002][23090] Updated weights for policy 0, policy_version 3469 (0.0013) [2023-03-09 07:31:24,059][22664] Fps is (10 sec: 198246.3, 60 sec: 201250.3, 300 sec: 191831.7). Total num frames: 56836096. Throughput: 0: 50323.9. Samples: 14274544. Policy #0 lag: (min: 1.0, avg: 15.9, max: 33.0) [2023-03-09 07:31:24,061][22664] Avg episode reward: [(0, '33.132')] [2023-03-09 07:31:24,741][23090] Updated weights for policy 0, policy_version 3479 (0.0024) [2023-03-09 07:31:25,679][23090] Updated weights for policy 0, policy_version 3489 (0.0013) [2023-03-09 07:31:26,480][23090] Updated weights for policy 0, policy_version 3499 (0.0015) [2023-03-09 07:31:27,113][23090] Updated weights for policy 0, policy_version 3509 (0.0016) [2023-03-09 07:31:28,176][23090] Updated weights for policy 0, policy_version 3519 (0.0013) [2023-03-09 07:31:28,912][23090] Updated weights for policy 0, policy_version 3529 (0.0016) [2023-03-09 07:31:29,059][22664] Fps is (10 sec: 198242.9, 60 sec: 201251.1, 300 sec: 194497.3). Total num frames: 57835520. Throughput: 0: 50323.5. Samples: 14426064. Policy #0 lag: (min: 1.0, avg: 16.5, max: 33.0) [2023-03-09 07:31:29,061][22664] Avg episode reward: [(0, '34.334')] [2023-03-09 07:31:29,619][23090] Updated weights for policy 0, policy_version 3539 (0.0017) [2023-03-09 07:31:30,428][22940] Signal inference workers to stop experience collection... (1500 times) [2023-03-09 07:31:30,428][22940] Signal inference workers to resume experience collection... (1500 times) [2023-03-09 07:31:30,515][23090] InferenceWorker_p0-w0: stopping experience collection (1500 times) [2023-03-09 07:31:30,515][23090] InferenceWorker_p0-w0: resuming experience collection (1500 times) [2023-03-09 07:31:30,602][23090] Updated weights for policy 0, policy_version 3549 (0.0016) [2023-03-09 07:31:31,290][23090] Updated weights for policy 0, policy_version 3559 (0.0022) [2023-03-09 07:31:32,081][23090] Updated weights for policy 0, policy_version 3569 (0.0012) [2023-03-09 07:31:33,025][23090] Updated weights for policy 0, policy_version 3579 (0.0016) [2023-03-09 07:31:33,807][23090] Updated weights for policy 0, policy_version 3589 (0.0013) [2023-03-09 07:31:34,059][22664] Fps is (10 sec: 201527.0, 60 sec: 201249.5, 300 sec: 196774.6). Total num frames: 58851328. Throughput: 0: 50370.4. Samples: 14729136. Policy #0 lag: (min: 1.0, avg: 17.5, max: 33.0) [2023-03-09 07:31:34,060][22664] Avg episode reward: [(0, '33.287')] [2023-03-09 07:31:34,561][23090] Updated weights for policy 0, policy_version 3599 (0.0013) [2023-03-09 07:31:35,328][23090] Updated weights for policy 0, policy_version 3609 (0.0020) [2023-03-09 07:31:36,264][23090] Updated weights for policy 0, policy_version 3619 (0.0016) [2023-03-09 07:31:37,030][23090] Updated weights for policy 0, policy_version 3629 (0.0018) [2023-03-09 07:31:37,752][23090] Updated weights for policy 0, policy_version 3639 (0.0013) [2023-03-09 07:31:38,763][23090] Updated weights for policy 0, policy_version 3650 (0.0014) [2023-03-09 07:31:39,059][22664] Fps is (10 sec: 203162.9, 60 sec: 201522.2, 300 sec: 198218.4). Total num frames: 59867136. Throughput: 0: 50324.8. Samples: 15030096. Policy #0 lag: (min: 1.0, avg: 16.2, max: 33.0) [2023-03-09 07:31:39,061][22664] Avg episode reward: [(0, '32.327')] [2023-03-09 07:31:39,573][23090] Updated weights for policy 0, policy_version 3660 (0.0021) [2023-03-09 07:31:40,374][23090] Updated weights for policy 0, policy_version 3671 (0.0018) [2023-03-09 07:31:41,173][22940] Signal inference workers to stop experience collection... (1550 times) [2023-03-09 07:31:41,174][22940] Signal inference workers to resume experience collection... (1550 times) [2023-03-09 07:31:41,239][23090] InferenceWorker_p0-w0: stopping experience collection (1550 times) [2023-03-09 07:31:41,239][23090] InferenceWorker_p0-w0: resuming experience collection (1550 times) [2023-03-09 07:31:41,287][23090] Updated weights for policy 0, policy_version 3681 (0.0015) [2023-03-09 07:31:42,087][23090] Updated weights for policy 0, policy_version 3691 (0.0025) [2023-03-09 07:31:42,807][23090] Updated weights for policy 0, policy_version 3702 (0.0016) [2023-03-09 07:31:43,798][23090] Updated weights for policy 0, policy_version 3712 (0.0016) [2023-03-09 07:31:44,059][22664] Fps is (10 sec: 201523.1, 60 sec: 201522.7, 300 sec: 198774.0). Total num frames: 60866560. Throughput: 0: 50324.1. Samples: 15181600. Policy #0 lag: (min: 1.0, avg: 15.5, max: 32.0) [2023-03-09 07:31:44,060][22664] Avg episode reward: [(0, '35.389')] [2023-03-09 07:31:44,085][22940] Saving new best policy, reward=35.389! [2023-03-09 07:31:44,647][23090] Updated weights for policy 0, policy_version 3722 (0.0016) [2023-03-09 07:31:45,353][23090] Updated weights for policy 0, policy_version 3732 (0.0013) [2023-03-09 07:31:46,323][23090] Updated weights for policy 0, policy_version 3742 (0.0026) [2023-03-09 07:31:47,043][23090] Updated weights for policy 0, policy_version 3752 (0.0019) [2023-03-09 07:31:47,824][23090] Updated weights for policy 0, policy_version 3762 (0.0016) [2023-03-09 07:31:48,746][23090] Updated weights for policy 0, policy_version 3772 (0.0018) [2023-03-09 07:31:49,058][22664] Fps is (10 sec: 199891.7, 60 sec: 201251.4, 300 sec: 199107.2). Total num frames: 61865984. Throughput: 0: 50278.9. Samples: 15482592. Policy #0 lag: (min: 1.0, avg: 17.6, max: 33.0) [2023-03-09 07:31:49,060][22664] Avg episode reward: [(0, '34.110')] [2023-03-09 07:31:49,493][23090] Updated weights for policy 0, policy_version 3782 (0.0022) [2023-03-09 07:31:50,270][23090] Updated weights for policy 0, policy_version 3792 (0.0024) [2023-03-09 07:31:50,915][22940] Signal inference workers to stop experience collection... (1600 times) [2023-03-09 07:31:50,916][22940] Signal inference workers to resume experience collection... (1600 times) [2023-03-09 07:31:51,012][23090] InferenceWorker_p0-w0: stopping experience collection (1600 times) [2023-03-09 07:31:51,012][23090] InferenceWorker_p0-w0: resuming experience collection (1600 times) [2023-03-09 07:31:51,133][23090] Updated weights for policy 0, policy_version 3802 (0.0020) [2023-03-09 07:31:51,937][23090] Updated weights for policy 0, policy_version 3812 (0.0015) [2023-03-09 07:31:52,755][23090] Updated weights for policy 0, policy_version 3822 (0.0015) [2023-03-09 07:31:53,581][23090] Updated weights for policy 0, policy_version 3832 (0.0013) [2023-03-09 07:31:54,059][22664] Fps is (10 sec: 199882.9, 60 sec: 201251.0, 300 sec: 199551.5). Total num frames: 62865408. Throughput: 0: 50324.5. Samples: 15783616. Policy #0 lag: (min: 0.0, avg: 17.2, max: 33.0) [2023-03-09 07:31:54,060][22664] Avg episode reward: [(0, '35.093')] [2023-03-09 07:31:54,414][23090] Updated weights for policy 0, policy_version 3842 (0.0025) [2023-03-09 07:31:55,247][23090] Updated weights for policy 0, policy_version 3852 (0.0020) [2023-03-09 07:31:55,873][23090] Updated weights for policy 0, policy_version 3862 (0.0013) [2023-03-09 07:31:56,859][23090] Updated weights for policy 0, policy_version 3872 (0.0016) [2023-03-09 07:31:57,688][23090] Updated weights for policy 0, policy_version 3882 (0.0017) [2023-03-09 07:31:58,351][23090] Updated weights for policy 0, policy_version 3892 (0.0013) [2023-03-09 07:31:59,058][22664] Fps is (10 sec: 199884.3, 60 sec: 200978.2, 300 sec: 200273.6). Total num frames: 63864832. Throughput: 0: 50325.7. Samples: 15935168. Policy #0 lag: (min: 2.0, avg: 17.3, max: 33.0) [2023-03-09 07:31:59,059][22664] Avg episode reward: [(0, '33.114')] [2023-03-09 07:31:59,363][23090] Updated weights for policy 0, policy_version 3902 (0.0013) [2023-03-09 07:32:00,125][23090] Updated weights for policy 0, policy_version 3912 (0.0017) [2023-03-09 07:32:00,867][23090] Updated weights for policy 0, policy_version 3922 (0.0014) [2023-03-09 07:32:00,987][22940] Signal inference workers to stop experience collection... (1650 times) [2023-03-09 07:32:00,990][22940] Signal inference workers to resume experience collection... (1650 times) [2023-03-09 07:32:01,025][23090] InferenceWorker_p0-w0: stopping experience collection (1650 times) [2023-03-09 07:32:01,076][23090] InferenceWorker_p0-w0: resuming experience collection (1650 times) [2023-03-09 07:32:01,780][23090] Updated weights for policy 0, policy_version 3932 (0.0020) [2023-03-09 07:32:02,545][23090] Updated weights for policy 0, policy_version 3942 (0.0019) [2023-03-09 07:32:03,343][23090] Updated weights for policy 0, policy_version 3952 (0.0016) [2023-03-09 07:32:04,059][22664] Fps is (10 sec: 203155.2, 60 sec: 200975.6, 300 sec: 200884.3). Total num frames: 64897024. Throughput: 0: 50236.4. Samples: 16236224. Policy #0 lag: (min: 1.0, avg: 16.5, max: 32.0) [2023-03-09 07:32:04,061][22664] Avg episode reward: [(0, '35.316')] [2023-03-09 07:32:04,177][23090] Updated weights for policy 0, policy_version 3962 (0.0019) [2023-03-09 07:32:05,083][23090] Updated weights for policy 0, policy_version 3973 (0.0013) [2023-03-09 07:32:05,843][23090] Updated weights for policy 0, policy_version 3983 (0.0011) [2023-03-09 07:32:06,776][23090] Updated weights for policy 0, policy_version 3994 (0.0020) [2023-03-09 07:32:07,611][23090] Updated weights for policy 0, policy_version 4004 (0.0012) [2023-03-09 07:32:08,400][23090] Updated weights for policy 0, policy_version 4014 (0.0016) [2023-03-09 07:32:09,058][22664] Fps is (10 sec: 204800.3, 60 sec: 201250.5, 300 sec: 201162.4). Total num frames: 65912832. Throughput: 0: 50280.6. Samples: 16537152. Policy #0 lag: (min: 0.0, avg: 17.1, max: 34.0) [2023-03-09 07:32:09,059][22664] Avg episode reward: [(0, '32.367')] [2023-03-09 07:32:09,157][23090] Updated weights for policy 0, policy_version 4024 (0.0013) [2023-03-09 07:32:10,054][23090] Updated weights for policy 0, policy_version 4034 (0.0013) [2023-03-09 07:32:10,865][23090] Updated weights for policy 0, policy_version 4044 (0.0020) [2023-03-09 07:32:11,046][22940] Signal inference workers to stop experience collection... (1700 times) [2023-03-09 07:32:11,047][22940] Signal inference workers to resume experience collection... (1700 times) [2023-03-09 07:32:11,110][23090] InferenceWorker_p0-w0: stopping experience collection (1700 times) [2023-03-09 07:32:11,110][23090] InferenceWorker_p0-w0: resuming experience collection (1700 times) [2023-03-09 07:32:11,672][23090] Updated weights for policy 0, policy_version 4055 (0.0019) [2023-03-09 07:32:12,587][23090] Updated weights for policy 0, policy_version 4065 (0.0013) [2023-03-09 07:32:13,504][23090] Updated weights for policy 0, policy_version 4076 (0.0015) [2023-03-09 07:32:14,058][22664] Fps is (10 sec: 203174.0, 60 sec: 201251.4, 300 sec: 201217.8). Total num frames: 66928640. Throughput: 0: 50280.7. Samples: 16688672. Policy #0 lag: (min: 1.0, avg: 17.6, max: 33.0) [2023-03-09 07:32:14,059][22664] Avg episode reward: [(0, '31.384')] [2023-03-09 07:32:14,143][23090] Updated weights for policy 0, policy_version 4086 (0.0015) [2023-03-09 07:32:15,174][23090] Updated weights for policy 0, policy_version 4096 (0.0018) [2023-03-09 07:32:15,962][23090] Updated weights for policy 0, policy_version 4106 (0.0013) [2023-03-09 07:32:16,657][23090] Updated weights for policy 0, policy_version 4116 (0.0013) [2023-03-09 07:32:17,634][23090] Updated weights for policy 0, policy_version 4126 (0.0021) [2023-03-09 07:32:18,363][23090] Updated weights for policy 0, policy_version 4136 (0.0016) [2023-03-09 07:32:19,059][22664] Fps is (10 sec: 199877.5, 60 sec: 200976.6, 300 sec: 201217.7). Total num frames: 67911680. Throughput: 0: 50188.2. Samples: 16987616. Policy #0 lag: (min: 2.0, avg: 17.2, max: 33.0) [2023-03-09 07:32:19,061][22664] Avg episode reward: [(0, '38.845')] [2023-03-09 07:32:19,120][22940] Saving new best policy, reward=38.845! [2023-03-09 07:32:19,129][23090] Updated weights for policy 0, policy_version 4146 (0.0016) [2023-03-09 07:32:20,213][23090] Updated weights for policy 0, policy_version 4157 (0.0015) [2023-03-09 07:32:20,944][23090] Updated weights for policy 0, policy_version 4167 (0.0023) [2023-03-09 07:32:21,728][23090] Updated weights for policy 0, policy_version 4177 (0.0017) [2023-03-09 07:32:21,829][22940] Signal inference workers to stop experience collection... (1750 times) [2023-03-09 07:32:21,852][22940] Signal inference workers to resume experience collection... (1750 times) [2023-03-09 07:32:21,893][23090] InferenceWorker_p0-w0: stopping experience collection (1750 times) [2023-03-09 07:32:21,893][23090] InferenceWorker_p0-w0: resuming experience collection (1750 times) [2023-03-09 07:32:22,647][23090] Updated weights for policy 0, policy_version 4187 (0.0024) [2023-03-09 07:32:23,398][23090] Updated weights for policy 0, policy_version 4197 (0.0015) [2023-03-09 07:32:24,058][22664] Fps is (10 sec: 196608.1, 60 sec: 200978.4, 300 sec: 201162.5). Total num frames: 68894720. Throughput: 0: 50144.1. Samples: 17286560. Policy #0 lag: (min: 1.0, avg: 16.1, max: 33.0) [2023-03-09 07:32:24,059][22664] Avg episode reward: [(0, '36.338')] [2023-03-09 07:32:24,190][23090] Updated weights for policy 0, policy_version 4207 (0.0016) [2023-03-09 07:32:24,992][23090] Updated weights for policy 0, policy_version 4217 (0.0016) [2023-03-09 07:32:25,940][23090] Updated weights for policy 0, policy_version 4227 (0.0021) [2023-03-09 07:32:26,666][23090] Updated weights for policy 0, policy_version 4237 (0.0017) [2023-03-09 07:32:27,392][23090] Updated weights for policy 0, policy_version 4247 (0.0019) [2023-03-09 07:32:28,331][23090] Updated weights for policy 0, policy_version 4257 (0.0018) [2023-03-09 07:32:29,059][22664] Fps is (10 sec: 198240.2, 60 sec: 200976.1, 300 sec: 201106.2). Total num frames: 69894144. Throughput: 0: 50143.1. Samples: 17438064. Policy #0 lag: (min: 2.0, avg: 19.1, max: 34.0) [2023-03-09 07:32:29,061][22664] Avg episode reward: [(0, '39.250')] [2023-03-09 07:32:29,072][22940] Saving new best policy, reward=39.250! [2023-03-09 07:32:29,220][23090] Updated weights for policy 0, policy_version 4267 (0.0013) [2023-03-09 07:32:29,825][23090] Updated weights for policy 0, policy_version 4277 (0.0021) [2023-03-09 07:32:30,814][23090] Updated weights for policy 0, policy_version 4287 (0.0016) [2023-03-09 07:32:31,610][23090] Updated weights for policy 0, policy_version 4297 (0.0016) [2023-03-09 07:32:32,308][22940] Signal inference workers to stop experience collection... (1800 times) [2023-03-09 07:32:32,330][22940] Signal inference workers to resume experience collection... (1800 times) [2023-03-09 07:32:32,362][23090] InferenceWorker_p0-w0: stopping experience collection (1800 times) [2023-03-09 07:32:32,407][23090] InferenceWorker_p0-w0: resuming experience collection (1800 times) [2023-03-09 07:32:32,410][23090] Updated weights for policy 0, policy_version 4308 (0.0020) [2023-03-09 07:32:33,394][23090] Updated weights for policy 0, policy_version 4318 (0.0013) [2023-03-09 07:32:34,058][22664] Fps is (10 sec: 199884.3, 60 sec: 200704.6, 300 sec: 201162.2). Total num frames: 70893568. Throughput: 0: 50143.7. Samples: 17739056. Policy #0 lag: (min: 1.0, avg: 16.3, max: 33.0) [2023-03-09 07:32:34,059][22664] Avg episode reward: [(0, '34.105')] [2023-03-09 07:32:34,110][23090] Updated weights for policy 0, policy_version 4328 (0.0013) [2023-03-09 07:32:34,880][23090] Updated weights for policy 0, policy_version 4338 (0.0016) [2023-03-09 07:32:35,780][23090] Updated weights for policy 0, policy_version 4348 (0.0020) [2023-03-09 07:32:36,541][23090] Updated weights for policy 0, policy_version 4358 (0.0015) [2023-03-09 07:32:37,320][23090] Updated weights for policy 0, policy_version 4368 (0.0021) [2023-03-09 07:32:38,195][23090] Updated weights for policy 0, policy_version 4378 (0.0013) [2023-03-09 07:32:39,016][23090] Updated weights for policy 0, policy_version 4388 (0.0015) [2023-03-09 07:32:39,059][22664] Fps is (10 sec: 199893.7, 60 sec: 200431.3, 300 sec: 201106.7). Total num frames: 71892992. Throughput: 0: 50143.0. Samples: 18040048. Policy #0 lag: (min: 0.0, avg: 16.2, max: 33.0) [2023-03-09 07:32:39,061][22664] Avg episode reward: [(0, '36.831')] [2023-03-09 07:32:39,773][23090] Updated weights for policy 0, policy_version 4398 (0.0013) [2023-03-09 07:32:40,534][23090] Updated weights for policy 0, policy_version 4408 (0.0018) [2023-03-09 07:32:41,455][23090] Updated weights for policy 0, policy_version 4418 (0.0016) [2023-03-09 07:32:42,316][23090] Updated weights for policy 0, policy_version 4429 (0.0019) [2023-03-09 07:32:43,079][23090] Updated weights for policy 0, policy_version 4439 (0.0015) [2023-03-09 07:32:44,012][23090] Updated weights for policy 0, policy_version 4449 (0.0013) [2023-03-09 07:32:44,059][22664] Fps is (10 sec: 199879.9, 60 sec: 200430.7, 300 sec: 201106.7). Total num frames: 72892416. Throughput: 0: 50140.9. Samples: 18191520. Policy #0 lag: (min: 1.0, avg: 19.0, max: 33.0) [2023-03-09 07:32:44,060][22664] Avg episode reward: [(0, '35.435')] [2023-03-09 07:32:44,254][22940] Signal inference workers to stop experience collection... (1850 times) [2023-03-09 07:32:44,255][22940] Signal inference workers to resume experience collection... (1850 times) [2023-03-09 07:32:44,328][23090] InferenceWorker_p0-w0: stopping experience collection (1850 times) [2023-03-09 07:32:44,328][23090] InferenceWorker_p0-w0: resuming experience collection (1850 times) [2023-03-09 07:32:44,830][23090] Updated weights for policy 0, policy_version 4459 (0.0013) [2023-03-09 07:32:45,507][23090] Updated weights for policy 0, policy_version 4469 (0.0026) [2023-03-09 07:32:46,488][23090] Updated weights for policy 0, policy_version 4479 (0.0018) [2023-03-09 07:32:47,284][23090] Updated weights for policy 0, policy_version 4489 (0.0020) [2023-03-09 07:32:48,096][23090] Updated weights for policy 0, policy_version 4500 (0.0016) [2023-03-09 07:32:49,058][22664] Fps is (10 sec: 199889.5, 60 sec: 200430.9, 300 sec: 201106.6). Total num frames: 73891840. Throughput: 0: 50094.5. Samples: 18490448. Policy #0 lag: (min: 2.0, avg: 16.9, max: 33.0) [2023-03-09 07:32:49,060][22664] Avg episode reward: [(0, '36.270')] [2023-03-09 07:32:49,077][23090] Updated weights for policy 0, policy_version 4510 (0.0013) [2023-03-09 07:32:49,767][23090] Updated weights for policy 0, policy_version 4520 (0.0017) [2023-03-09 07:32:50,572][23090] Updated weights for policy 0, policy_version 4530 (0.0013) [2023-03-09 07:32:51,513][23090] Updated weights for policy 0, policy_version 4540 (0.0018) [2023-03-09 07:32:52,234][23090] Updated weights for policy 0, policy_version 4550 (0.0014) [2023-03-09 07:32:53,013][23090] Updated weights for policy 0, policy_version 4560 (0.0017) [2023-03-09 07:32:53,932][23090] Updated weights for policy 0, policy_version 4570 (0.0018) [2023-03-09 07:32:54,059][22664] Fps is (10 sec: 199883.2, 60 sec: 200430.8, 300 sec: 200995.4). Total num frames: 74891264. Throughput: 0: 50048.4. Samples: 18789344. Policy #0 lag: (min: 1.0, avg: 17.1, max: 34.0) [2023-03-09 07:32:54,060][22664] Avg episode reward: [(0, '36.910')] [2023-03-09 07:32:54,785][23090] Updated weights for policy 0, policy_version 4580 (0.0022) [2023-03-09 07:32:55,511][23090] Updated weights for policy 0, policy_version 4590 (0.0013) [2023-03-09 07:32:56,316][23090] Updated weights for policy 0, policy_version 4600 (0.0013) [2023-03-09 07:32:57,296][23090] Updated weights for policy 0, policy_version 4611 (0.0015) [2023-03-09 07:32:58,062][23090] Updated weights for policy 0, policy_version 4621 (0.0013) [2023-03-09 07:32:58,151][22940] Signal inference workers to stop experience collection... (1900 times) [2023-03-09 07:32:58,162][22940] Signal inference workers to resume experience collection... (1900 times) [2023-03-09 07:32:58,229][23090] InferenceWorker_p0-w0: stopping experience collection (1900 times) [2023-03-09 07:32:58,230][23090] InferenceWorker_p0-w0: resuming experience collection (1900 times) [2023-03-09 07:32:58,789][23090] Updated weights for policy 0, policy_version 4631 (0.0020) [2023-03-09 07:32:59,059][22664] Fps is (10 sec: 201519.8, 60 sec: 200703.5, 300 sec: 200995.6). Total num frames: 75907072. Throughput: 0: 50048.5. Samples: 18940864. Policy #0 lag: (min: 2.0, avg: 15.9, max: 33.0) [2023-03-09 07:32:59,060][22664] Avg episode reward: [(0, '36.503')] [2023-03-09 07:32:59,772][23090] Updated weights for policy 0, policy_version 4641 (0.0016) [2023-03-09 07:33:00,524][23090] Updated weights for policy 0, policy_version 4651 (0.0015) [2023-03-09 07:33:01,213][23090] Updated weights for policy 0, policy_version 4661 (0.0012) [2023-03-09 07:33:02,194][23090] Updated weights for policy 0, policy_version 4671 (0.0017) [2023-03-09 07:33:02,983][23090] Updated weights for policy 0, policy_version 4681 (0.0013) [2023-03-09 07:33:03,686][23090] Updated weights for policy 0, policy_version 4691 (0.0017) [2023-03-09 07:33:04,059][22664] Fps is (10 sec: 203160.7, 60 sec: 200431.7, 300 sec: 201051.1). Total num frames: 76922880. Throughput: 0: 50093.9. Samples: 19241840. Policy #0 lag: (min: 0.0, avg: 16.9, max: 33.0) [2023-03-09 07:33:04,061][22664] Avg episode reward: [(0, '35.157')] [2023-03-09 07:33:04,751][23090] Updated weights for policy 0, policy_version 4701 (0.0016) [2023-03-09 07:33:05,401][23090] Updated weights for policy 0, policy_version 4711 (0.0018) [2023-03-09 07:33:06,182][23090] Updated weights for policy 0, policy_version 4721 (0.0015) [2023-03-09 07:33:07,126][23090] Updated weights for policy 0, policy_version 4731 (0.0013) [2023-03-09 07:33:07,900][23090] Updated weights for policy 0, policy_version 4741 (0.0013) [2023-03-09 07:33:08,675][23090] Updated weights for policy 0, policy_version 4751 (0.0019) [2023-03-09 07:33:09,059][22664] Fps is (10 sec: 203161.4, 60 sec: 200430.4, 300 sec: 201162.1). Total num frames: 77938688. Throughput: 0: 50093.6. Samples: 19540784. Policy #0 lag: (min: 0.0, avg: 18.1, max: 33.0) [2023-03-09 07:33:09,060][22664] Avg episode reward: [(0, '35.764')] [2023-03-09 07:33:09,449][23090] Updated weights for policy 0, policy_version 4761 (0.0017) [2023-03-09 07:33:10,356][23090] Updated weights for policy 0, policy_version 4771 (0.0013) [2023-03-09 07:33:11,121][23090] Updated weights for policy 0, policy_version 4781 (0.0014) [2023-03-09 07:33:11,210][22940] Signal inference workers to stop experience collection... (1950 times) [2023-03-09 07:33:11,228][22940] Signal inference workers to resume experience collection... (1950 times) [2023-03-09 07:33:11,299][23090] InferenceWorker_p0-w0: stopping experience collection (1950 times) [2023-03-09 07:33:11,300][23090] InferenceWorker_p0-w0: resuming experience collection (1950 times) [2023-03-09 07:33:12,039][23090] Updated weights for policy 0, policy_version 4792 (0.0013) [2023-03-09 07:33:12,954][23090] Updated weights for policy 0, policy_version 4802 (0.0016) [2023-03-09 07:33:13,724][23090] Updated weights for policy 0, policy_version 4812 (0.0015) [2023-03-09 07:33:14,058][22664] Fps is (10 sec: 198253.8, 60 sec: 199611.7, 300 sec: 201051.3). Total num frames: 78905344. Throughput: 0: 50093.9. Samples: 19692256. Policy #0 lag: (min: 1.0, avg: 17.3, max: 33.0) [2023-03-09 07:33:14,059][22664] Avg episode reward: [(0, '39.054')] [2023-03-09 07:33:14,366][23090] Updated weights for policy 0, policy_version 4822 (0.0022) [2023-03-09 07:33:15,396][23090] Updated weights for policy 0, policy_version 4832 (0.0013) [2023-03-09 07:33:16,185][23090] Updated weights for policy 0, policy_version 4842 (0.0022) [2023-03-09 07:33:16,872][23090] Updated weights for policy 0, policy_version 4852 (0.0013) [2023-03-09 07:33:17,889][23090] Updated weights for policy 0, policy_version 4862 (0.0013) [2023-03-09 07:33:18,587][23090] Updated weights for policy 0, policy_version 4872 (0.0015) [2023-03-09 07:33:19,059][22664] Fps is (10 sec: 196603.6, 60 sec: 199884.7, 300 sec: 201106.3). Total num frames: 79904768. Throughput: 0: 50046.5. Samples: 19991168. Policy #0 lag: (min: 1.0, avg: 16.4, max: 33.0) [2023-03-09 07:33:19,061][22664] Avg episode reward: [(0, '36.620')] [2023-03-09 07:33:19,106][22940] Saving /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000004878_79921152.pth... [2023-03-09 07:33:19,162][22940] Removing /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000001935_31703040.pth [2023-03-09 07:33:19,453][23090] Updated weights for policy 0, policy_version 4883 (0.0013) [2023-03-09 07:33:20,446][23090] Updated weights for policy 0, policy_version 4893 (0.0015) [2023-03-09 07:33:21,135][23090] Updated weights for policy 0, policy_version 4903 (0.0016) [2023-03-09 07:33:21,901][23090] Updated weights for policy 0, policy_version 4913 (0.0021) [2023-03-09 07:33:22,836][23090] Updated weights for policy 0, policy_version 4923 (0.0013) [2023-03-09 07:33:23,052][22940] Signal inference workers to stop experience collection... (2000 times) [2023-03-09 07:33:23,052][22940] Signal inference workers to resume experience collection... (2000 times) [2023-03-09 07:33:23,116][23090] InferenceWorker_p0-w0: stopping experience collection (2000 times) [2023-03-09 07:33:23,116][23090] InferenceWorker_p0-w0: resuming experience collection (2000 times) [2023-03-09 07:33:23,666][23090] Updated weights for policy 0, policy_version 4933 (0.0023) [2023-03-09 07:33:24,058][22664] Fps is (10 sec: 199884.2, 60 sec: 200157.7, 300 sec: 201106.6). Total num frames: 80904192. Throughput: 0: 50046.1. Samples: 20292112. Policy #0 lag: (min: 1.0, avg: 16.9, max: 32.0) [2023-03-09 07:33:24,060][22664] Avg episode reward: [(0, '36.083')] [2023-03-09 07:33:24,363][23090] Updated weights for policy 0, policy_version 4943 (0.0017) [2023-03-09 07:33:25,189][23090] Updated weights for policy 0, policy_version 4953 (0.0016) [2023-03-09 07:33:26,065][23090] Updated weights for policy 0, policy_version 4963 (0.0013) [2023-03-09 07:33:26,847][23090] Updated weights for policy 0, policy_version 4973 (0.0012) [2023-03-09 07:33:27,615][23090] Updated weights for policy 0, policy_version 4983 (0.0013) [2023-03-09 07:33:28,632][23090] Updated weights for policy 0, policy_version 4994 (0.0019) [2023-03-09 07:33:29,059][22664] Fps is (10 sec: 201528.6, 60 sec: 200432.8, 300 sec: 201217.9). Total num frames: 81920000. Throughput: 0: 50001.2. Samples: 20441568. Policy #0 lag: (min: 1.0, avg: 16.5, max: 33.0) [2023-03-09 07:33:29,060][22664] Avg episode reward: [(0, '37.668')] [2023-03-09 07:33:29,387][23090] Updated weights for policy 0, policy_version 5004 (0.0020) [2023-03-09 07:33:30,052][23090] Updated weights for policy 0, policy_version 5014 (0.0015) [2023-03-09 07:33:31,080][23090] Updated weights for policy 0, policy_version 5024 (0.0013) [2023-03-09 07:33:31,935][23090] Updated weights for policy 0, policy_version 5035 (0.0019) [2023-03-09 07:33:32,615][23090] Updated weights for policy 0, policy_version 5045 (0.0013) [2023-03-09 07:33:33,601][23090] Updated weights for policy 0, policy_version 5055 (0.0015) [2023-03-09 07:33:34,059][22664] Fps is (10 sec: 201518.3, 60 sec: 200430.0, 300 sec: 201162.2). Total num frames: 82919424. Throughput: 0: 50092.9. Samples: 20744640. Policy #0 lag: (min: 1.0, avg: 15.9, max: 33.0) [2023-03-09 07:33:34,060][22664] Avg episode reward: [(0, '38.299')] [2023-03-09 07:33:34,474][23090] Updated weights for policy 0, policy_version 5065 (0.0016) [2023-03-09 07:33:35,131][23090] Updated weights for policy 0, policy_version 5075 (0.0024) [2023-03-09 07:33:35,240][22940] Signal inference workers to stop experience collection... (2050 times) [2023-03-09 07:33:35,241][22940] Signal inference workers to resume experience collection... (2050 times) [2023-03-09 07:33:35,265][23090] InferenceWorker_p0-w0: stopping experience collection (2050 times) [2023-03-09 07:33:35,265][23090] InferenceWorker_p0-w0: resuming experience collection (2050 times) [2023-03-09 07:33:36,123][23090] Updated weights for policy 0, policy_version 5085 (0.0013) [2023-03-09 07:33:36,812][23090] Updated weights for policy 0, policy_version 5095 (0.0017) [2023-03-09 07:33:37,577][23090] Updated weights for policy 0, policy_version 5105 (0.0019) [2023-03-09 07:33:38,543][23090] Updated weights for policy 0, policy_version 5115 (0.0013) [2023-03-09 07:33:39,059][22664] Fps is (10 sec: 198242.3, 60 sec: 200157.5, 300 sec: 201050.9). Total num frames: 83902464. Throughput: 0: 50094.5. Samples: 21043600. Policy #0 lag: (min: 1.0, avg: 15.8, max: 33.0) [2023-03-09 07:33:39,061][22664] Avg episode reward: [(0, '34.269')] [2023-03-09 07:33:39,365][23090] Updated weights for policy 0, policy_version 5125 (0.0018) [2023-03-09 07:33:40,083][23090] Updated weights for policy 0, policy_version 5135 (0.0026) [2023-03-09 07:33:40,849][23090] Updated weights for policy 0, policy_version 5145 (0.0019) [2023-03-09 07:33:41,807][23090] Updated weights for policy 0, policy_version 5155 (0.0026) [2023-03-09 07:33:42,533][23090] Updated weights for policy 0, policy_version 5165 (0.0019) [2023-03-09 07:33:43,359][23090] Updated weights for policy 0, policy_version 5175 (0.0018) [2023-03-09 07:33:44,059][22664] Fps is (10 sec: 198247.1, 60 sec: 200157.9, 300 sec: 201051.0). Total num frames: 84901888. Throughput: 0: 50049.7. Samples: 21193104. Policy #0 lag: (min: 0.0, avg: 16.0, max: 33.0) [2023-03-09 07:33:44,060][22664] Avg episode reward: [(0, '39.186')] [2023-03-09 07:33:44,253][23090] Updated weights for policy 0, policy_version 5185 (0.0020) [2023-03-09 07:33:45,012][23090] Updated weights for policy 0, policy_version 5195 (0.0020) [2023-03-09 07:33:45,701][23090] Updated weights for policy 0, policy_version 5205 (0.0019) [2023-03-09 07:33:46,696][23090] Updated weights for policy 0, policy_version 5215 (0.0021) [2023-03-09 07:33:47,520][23090] Updated weights for policy 0, policy_version 5225 (0.0025) [2023-03-09 07:33:48,126][22940] Signal inference workers to stop experience collection... (2100 times) [2023-03-09 07:33:48,135][22940] Signal inference workers to resume experience collection... (2100 times) [2023-03-09 07:33:48,167][23090] InferenceWorker_p0-w0: stopping experience collection (2100 times) [2023-03-09 07:33:48,217][23090] InferenceWorker_p0-w0: resuming experience collection (2100 times) [2023-03-09 07:33:48,223][23090] Updated weights for policy 0, policy_version 5235 (0.0017) [2023-03-09 07:33:49,058][22664] Fps is (10 sec: 199891.5, 60 sec: 200157.8, 300 sec: 200940.2). Total num frames: 85901312. Throughput: 0: 50051.2. Samples: 21494128. Policy #0 lag: (min: 0.0, avg: 16.5, max: 33.0) [2023-03-09 07:33:49,059][22664] Avg episode reward: [(0, '35.851')] [2023-03-09 07:33:49,194][23090] Updated weights for policy 0, policy_version 5245 (0.0013) [2023-03-09 07:33:49,891][23090] Updated weights for policy 0, policy_version 5255 (0.0018) [2023-03-09 07:33:50,792][23090] Updated weights for policy 0, policy_version 5266 (0.0016) [2023-03-09 07:33:51,725][23090] Updated weights for policy 0, policy_version 5276 (0.0016) [2023-03-09 07:33:52,453][23090] Updated weights for policy 0, policy_version 5286 (0.0016) [2023-03-09 07:33:53,204][23090] Updated weights for policy 0, policy_version 5296 (0.0013) [2023-03-09 07:33:54,058][22664] Fps is (10 sec: 201527.7, 60 sec: 200432.0, 300 sec: 200940.3). Total num frames: 86917120. Throughput: 0: 50096.2. Samples: 21795104. Policy #0 lag: (min: 0.0, avg: 17.0, max: 33.0) [2023-03-09 07:33:54,059][22664] Avg episode reward: [(0, '39.758')] [2023-03-09 07:33:54,081][23090] Updated weights for policy 0, policy_version 5306 (0.0016) [2023-03-09 07:33:54,104][22940] Saving new best policy, reward=39.758! [2023-03-09 07:33:54,929][23090] Updated weights for policy 0, policy_version 5316 (0.0015) [2023-03-09 07:33:55,696][23090] Updated weights for policy 0, policy_version 5326 (0.0014) [2023-03-09 07:33:56,489][23090] Updated weights for policy 0, policy_version 5336 (0.0028) [2023-03-09 07:33:57,454][23090] Updated weights for policy 0, policy_version 5346 (0.0013) [2023-03-09 07:33:58,197][23090] Updated weights for policy 0, policy_version 5356 (0.0021) [2023-03-09 07:33:58,849][23090] Updated weights for policy 0, policy_version 5366 (0.0024) [2023-03-09 07:33:59,059][22664] Fps is (10 sec: 203155.4, 60 sec: 200430.5, 300 sec: 200884.4). Total num frames: 87932928. Throughput: 0: 50050.1. Samples: 21944528. Policy #0 lag: (min: 0.0, avg: 17.0, max: 33.0) [2023-03-09 07:33:59,061][22664] Avg episode reward: [(0, '37.999')] [2023-03-09 07:33:59,910][23090] Updated weights for policy 0, policy_version 5376 (0.0018) [2023-03-09 07:34:00,117][22940] Signal inference workers to stop experience collection... (2150 times) [2023-03-09 07:34:00,118][22940] Signal inference workers to resume experience collection... (2150 times) [2023-03-09 07:34:00,208][23090] InferenceWorker_p0-w0: stopping experience collection (2150 times) [2023-03-09 07:34:00,209][23090] InferenceWorker_p0-w0: resuming experience collection (2150 times) [2023-03-09 07:34:00,685][23090] Updated weights for policy 0, policy_version 5386 (0.0016) [2023-03-09 07:34:01,380][23090] Updated weights for policy 0, policy_version 5396 (0.0013) [2023-03-09 07:34:02,403][23090] Updated weights for policy 0, policy_version 5406 (0.0016) [2023-03-09 07:34:03,096][23090] Updated weights for policy 0, policy_version 5416 (0.0016) [2023-03-09 07:34:03,858][23090] Updated weights for policy 0, policy_version 5426 (0.0013) [2023-03-09 07:34:04,058][22664] Fps is (10 sec: 203161.4, 60 sec: 200432.1, 300 sec: 200884.5). Total num frames: 88948736. Throughput: 0: 50096.4. Samples: 22245488. Policy #0 lag: (min: 0.0, avg: 17.2, max: 33.0) [2023-03-09 07:34:04,060][22664] Avg episode reward: [(0, '35.453')] [2023-03-09 07:34:04,796][23090] Updated weights for policy 0, policy_version 5436 (0.0013) [2023-03-09 07:34:05,533][23090] Updated weights for policy 0, policy_version 5446 (0.0018) [2023-03-09 07:34:06,263][23090] Updated weights for policy 0, policy_version 5456 (0.0019) [2023-03-09 07:34:07,176][23090] Updated weights for policy 0, policy_version 5466 (0.0020) [2023-03-09 07:34:07,981][23090] Updated weights for policy 0, policy_version 5476 (0.0014) [2023-03-09 07:34:08,772][23090] Updated weights for policy 0, policy_version 5486 (0.0019) [2023-03-09 07:34:09,059][22664] Fps is (10 sec: 199885.7, 60 sec: 199884.5, 300 sec: 200829.0). Total num frames: 89931776. Throughput: 0: 50097.1. Samples: 22546496. Policy #0 lag: (min: 0.0, avg: 17.2, max: 33.0) [2023-03-09 07:34:09,061][22664] Avg episode reward: [(0, '39.268')] [2023-03-09 07:34:09,223][22940] Signal inference workers to stop experience collection... (2200 times) [2023-03-09 07:34:09,234][22940] Signal inference workers to resume experience collection... (2200 times) [2023-03-09 07:34:09,262][23090] InferenceWorker_p0-w0: stopping experience collection (2200 times) [2023-03-09 07:34:09,262][23090] InferenceWorker_p0-w0: resuming experience collection (2200 times) [2023-03-09 07:34:09,610][23090] Updated weights for policy 0, policy_version 5496 (0.0013) [2023-03-09 07:34:10,527][23090] Updated weights for policy 0, policy_version 5506 (0.0018) [2023-03-09 07:34:11,305][23090] Updated weights for policy 0, policy_version 5516 (0.0018) [2023-03-09 07:34:11,960][23090] Updated weights for policy 0, policy_version 5526 (0.0012) [2023-03-09 07:34:12,948][23090] Updated weights for policy 0, policy_version 5536 (0.0015) [2023-03-09 07:34:13,740][23090] Updated weights for policy 0, policy_version 5546 (0.0018) [2023-03-09 07:34:14,059][22664] Fps is (10 sec: 198242.0, 60 sec: 200430.1, 300 sec: 200884.3). Total num frames: 90931200. Throughput: 0: 50097.3. Samples: 22695952. Policy #0 lag: (min: 0.0, avg: 17.2, max: 33.0) [2023-03-09 07:34:14,063][22664] Avg episode reward: [(0, '37.640')] [2023-03-09 07:34:14,514][23090] Updated weights for policy 0, policy_version 5557 (0.0013) [2023-03-09 07:34:15,531][23090] Updated weights for policy 0, policy_version 5567 (0.0015) [2023-03-09 07:34:16,350][23090] Updated weights for policy 0, policy_version 5577 (0.0017) [2023-03-09 07:34:17,027][23090] Updated weights for policy 0, policy_version 5587 (0.0013) [2023-03-09 07:34:17,995][23090] Updated weights for policy 0, policy_version 5597 (0.0013) [2023-03-09 07:34:18,683][23090] Updated weights for policy 0, policy_version 5607 (0.0013) [2023-03-09 07:34:19,059][22664] Fps is (10 sec: 199888.1, 60 sec: 200431.9, 300 sec: 200829.1). Total num frames: 91930624. Throughput: 0: 50051.0. Samples: 22996928. Policy #0 lag: (min: 0.0, avg: 16.6, max: 33.0) [2023-03-09 07:34:19,060][22664] Avg episode reward: [(0, '42.475')] [2023-03-09 07:34:19,067][22940] Saving new best policy, reward=42.475! [2023-03-09 07:34:19,287][22940] Signal inference workers to stop experience collection... (2250 times) [2023-03-09 07:34:19,310][22940] Signal inference workers to resume experience collection... (2250 times) [2023-03-09 07:34:19,347][23090] InferenceWorker_p0-w0: stopping experience collection (2250 times) [2023-03-09 07:34:19,391][23090] InferenceWorker_p0-w0: resuming experience collection (2250 times) [2023-03-09 07:34:19,556][23090] Updated weights for policy 0, policy_version 5617 (0.0013) [2023-03-09 07:34:20,402][23090] Updated weights for policy 0, policy_version 5627 (0.0013) [2023-03-09 07:34:21,199][23090] Updated weights for policy 0, policy_version 5637 (0.0013) [2023-03-09 07:34:21,958][23090] Updated weights for policy 0, policy_version 5647 (0.0021) [2023-03-09 07:34:22,753][23090] Updated weights for policy 0, policy_version 5657 (0.0016) [2023-03-09 07:34:23,691][23090] Updated weights for policy 0, policy_version 5667 (0.0013) [2023-03-09 07:34:24,059][22664] Fps is (10 sec: 199883.3, 60 sec: 200430.0, 300 sec: 200773.3). Total num frames: 92930048. Throughput: 0: 50050.5. Samples: 23295872. Policy #0 lag: (min: 0.0, avg: 16.0, max: 33.0) [2023-03-09 07:34:24,061][22664] Avg episode reward: [(0, '37.374')] [2023-03-09 07:34:24,484][23090] Updated weights for policy 0, policy_version 5677 (0.0018) [2023-03-09 07:34:25,215][23090] Updated weights for policy 0, policy_version 5687 (0.0013) [2023-03-09 07:34:26,195][23090] Updated weights for policy 0, policy_version 5697 (0.0023) [2023-03-09 07:34:26,923][23090] Updated weights for policy 0, policy_version 5707 (0.0018) [2023-03-09 07:34:27,643][23090] Updated weights for policy 0, policy_version 5717 (0.0020) [2023-03-09 07:34:28,638][23090] Updated weights for policy 0, policy_version 5727 (0.0013) [2023-03-09 07:34:29,059][22664] Fps is (10 sec: 199880.1, 60 sec: 200157.2, 300 sec: 200940.0). Total num frames: 93929472. Throughput: 0: 50049.3. Samples: 23445328. Policy #0 lag: (min: 1.0, avg: 15.7, max: 33.0) [2023-03-09 07:34:29,061][22664] Avg episode reward: [(0, '39.768')] [2023-03-09 07:34:29,451][23090] Updated weights for policy 0, policy_version 5737 (0.0021) [2023-03-09 07:34:29,985][22940] Signal inference workers to stop experience collection... (2300 times) [2023-03-09 07:34:29,986][22940] Signal inference workers to resume experience collection... (2300 times) [2023-03-09 07:34:30,055][23090] InferenceWorker_p0-w0: stopping experience collection (2300 times) [2023-03-09 07:34:30,058][23090] InferenceWorker_p0-w0: resuming experience collection (2300 times) [2023-03-09 07:34:30,149][23090] Updated weights for policy 0, policy_version 5747 (0.0025) [2023-03-09 07:34:31,177][23090] Updated weights for policy 0, policy_version 5758 (0.0013) [2023-03-09 07:34:31,894][23090] Updated weights for policy 0, policy_version 5768 (0.0015) [2023-03-09 07:34:32,721][23090] Updated weights for policy 0, policy_version 5779 (0.0017) [2023-03-09 07:34:33,651][23090] Updated weights for policy 0, policy_version 5789 (0.0014) [2023-03-09 07:34:34,059][22664] Fps is (10 sec: 199887.9, 60 sec: 200158.2, 300 sec: 200884.4). Total num frames: 94928896. Throughput: 0: 50049.3. Samples: 23746352. Policy #0 lag: (min: 1.0, avg: 15.5, max: 33.0) [2023-03-09 07:34:34,061][22664] Avg episode reward: [(0, '37.884')] [2023-03-09 07:34:34,378][23090] Updated weights for policy 0, policy_version 5799 (0.0016) [2023-03-09 07:34:35,177][23090] Updated weights for policy 0, policy_version 5809 (0.0013) [2023-03-09 07:34:36,063][23090] Updated weights for policy 0, policy_version 5819 (0.0013) [2023-03-09 07:34:36,879][23090] Updated weights for policy 0, policy_version 5829 (0.0020) [2023-03-09 07:34:37,589][23090] Updated weights for policy 0, policy_version 5839 (0.0016) [2023-03-09 07:34:38,390][23090] Updated weights for policy 0, policy_version 5849 (0.0013) [2023-03-09 07:34:39,058][22664] Fps is (10 sec: 199891.6, 60 sec: 200432.1, 300 sec: 200829.0). Total num frames: 95928320. Throughput: 0: 50140.8. Samples: 24051440. Policy #0 lag: (min: 1.0, avg: 15.5, max: 33.0) [2023-03-09 07:34:39,060][22664] Avg episode reward: [(0, '38.284')] [2023-03-09 07:34:39,355][23090] Updated weights for policy 0, policy_version 5859 (0.0016) [2023-03-09 07:34:40,191][23090] Updated weights for policy 0, policy_version 5870 (0.0019) [2023-03-09 07:34:40,488][22940] Signal inference workers to stop experience collection... (2350 times) [2023-03-09 07:34:40,512][22940] Signal inference workers to resume experience collection... (2350 times) [2023-03-09 07:34:40,556][23090] InferenceWorker_p0-w0: stopping experience collection (2350 times) [2023-03-09 07:34:40,556][23090] InferenceWorker_p0-w0: resuming experience collection (2350 times) [2023-03-09 07:34:40,924][23090] Updated weights for policy 0, policy_version 5880 (0.0016) [2023-03-09 07:34:41,871][23090] Updated weights for policy 0, policy_version 5890 (0.0020) [2023-03-09 07:34:42,686][23090] Updated weights for policy 0, policy_version 5901 (0.0018) [2023-03-09 07:34:43,413][23090] Updated weights for policy 0, policy_version 5911 (0.0013) [2023-03-09 07:34:44,058][22664] Fps is (10 sec: 199888.0, 60 sec: 200431.7, 300 sec: 200829.0). Total num frames: 96927744. Throughput: 0: 50187.7. Samples: 24202960. Policy #0 lag: (min: 2.0, avg: 16.8, max: 34.0) [2023-03-09 07:34:44,059][22664] Avg episode reward: [(0, '38.072')] [2023-03-09 07:34:44,400][23090] Updated weights for policy 0, policy_version 5921 (0.0021) [2023-03-09 07:34:45,162][23090] Updated weights for policy 0, policy_version 5931 (0.0015) [2023-03-09 07:34:45,853][23090] Updated weights for policy 0, policy_version 5942 (0.0013) [2023-03-09 07:34:46,928][23090] Updated weights for policy 0, policy_version 5952 (0.0013) [2023-03-09 07:34:47,785][23090] Updated weights for policy 0, policy_version 5963 (0.0014) [2023-03-09 07:34:48,467][23090] Updated weights for policy 0, policy_version 5973 (0.0017) [2023-03-09 07:34:49,059][22664] Fps is (10 sec: 201521.1, 60 sec: 200703.7, 300 sec: 200828.9). Total num frames: 97943552. Throughput: 0: 50141.1. Samples: 24501840. Policy #0 lag: (min: 0.0, avg: 16.0, max: 32.0) [2023-03-09 07:34:49,060][22664] Avg episode reward: [(0, '39.112')] [2023-03-09 07:34:49,465][23090] Updated weights for policy 0, policy_version 5983 (0.0015) [2023-03-09 07:34:50,246][23090] Updated weights for policy 0, policy_version 5993 (0.0014) [2023-03-09 07:34:50,904][23090] Updated weights for policy 0, policy_version 6003 (0.0018) [2023-03-09 07:34:51,847][23090] Updated weights for policy 0, policy_version 6013 (0.0014) [2023-03-09 07:34:52,294][22940] Signal inference workers to stop experience collection... (2400 times) [2023-03-09 07:34:52,295][22940] Signal inference workers to resume experience collection... (2400 times) [2023-03-09 07:34:52,359][23090] InferenceWorker_p0-w0: stopping experience collection (2400 times) [2023-03-09 07:34:52,359][23090] InferenceWorker_p0-w0: resuming experience collection (2400 times) [2023-03-09 07:34:52,566][23090] Updated weights for policy 0, policy_version 6023 (0.0023) [2023-03-09 07:34:53,362][23090] Updated weights for policy 0, policy_version 6033 (0.0018) [2023-03-09 07:34:54,058][22664] Fps is (10 sec: 204799.8, 60 sec: 200977.0, 300 sec: 200829.0). Total num frames: 98975744. Throughput: 0: 50275.8. Samples: 24808896. Policy #0 lag: (min: 2.0, avg: 17.0, max: 33.0) [2023-03-09 07:34:54,059][22664] Avg episode reward: [(0, '41.817')] [2023-03-09 07:34:54,235][23090] Updated weights for policy 0, policy_version 6043 (0.0016) [2023-03-09 07:34:55,116][23090] Updated weights for policy 0, policy_version 6054 (0.0016) [2023-03-09 07:34:55,885][23090] Updated weights for policy 0, policy_version 6064 (0.0013) [2023-03-09 07:34:56,711][23090] Updated weights for policy 0, policy_version 6074 (0.0021) [2023-03-09 07:34:57,573][23090] Updated weights for policy 0, policy_version 6084 (0.0017) [2023-03-09 07:34:58,379][23090] Updated weights for policy 0, policy_version 6094 (0.0013) [2023-03-09 07:34:59,059][22664] Fps is (10 sec: 204797.5, 60 sec: 200977.4, 300 sec: 200828.8). Total num frames: 99991552. Throughput: 0: 50320.7. Samples: 24960384. Policy #0 lag: (min: 2.0, avg: 17.9, max: 33.0) [2023-03-09 07:34:59,060][22664] Avg episode reward: [(0, '43.241')] [2023-03-09 07:34:59,065][22940] Saving new best policy, reward=43.241! [2023-03-09 07:34:59,206][23090] Updated weights for policy 0, policy_version 6104 (0.0013) [2023-03-09 07:35:00,124][23090] Updated weights for policy 0, policy_version 6114 (0.0019) [2023-03-09 07:35:00,876][23090] Updated weights for policy 0, policy_version 6124 (0.0017) [2023-03-09 07:35:01,511][23090] Updated weights for policy 0, policy_version 6134 (0.0018) [2023-03-09 07:35:02,546][23090] Updated weights for policy 0, policy_version 6144 (0.0013) [2023-03-09 07:35:03,322][23090] Updated weights for policy 0, policy_version 6154 (0.0016) [2023-03-09 07:35:04,032][23090] Updated weights for policy 0, policy_version 6164 (0.0013) [2023-03-09 07:35:04,058][22664] Fps is (10 sec: 201523.1, 60 sec: 200704.0, 300 sec: 200773.8). Total num frames: 100990976. Throughput: 0: 50231.2. Samples: 25257328. Policy #0 lag: (min: 0.0, avg: 17.4, max: 32.0) [2023-03-09 07:35:04,059][22664] Avg episode reward: [(0, '37.175')] [2023-03-09 07:35:04,988][23090] Updated weights for policy 0, policy_version 6174 (0.0016) [2023-03-09 07:35:05,748][23090] Updated weights for policy 0, policy_version 6184 (0.0013) [2023-03-09 07:35:05,956][22940] Signal inference workers to stop experience collection... (2450 times) [2023-03-09 07:35:05,957][22940] Signal inference workers to resume experience collection... (2450 times) [2023-03-09 07:35:06,024][23090] InferenceWorker_p0-w0: stopping experience collection (2450 times) [2023-03-09 07:35:06,024][23090] InferenceWorker_p0-w0: resuming experience collection (2450 times) [2023-03-09 07:35:06,612][23090] Updated weights for policy 0, policy_version 6195 (0.0016) [2023-03-09 07:35:07,551][23090] Updated weights for policy 0, policy_version 6205 (0.0015) [2023-03-09 07:35:08,276][23090] Updated weights for policy 0, policy_version 6215 (0.0025) [2023-03-09 07:35:09,059][22664] Fps is (10 sec: 199885.7, 60 sec: 200977.4, 300 sec: 200773.3). Total num frames: 101990400. Throughput: 0: 50276.4. Samples: 25558304. Policy #0 lag: (min: 0.0, avg: 16.1, max: 33.0) [2023-03-09 07:35:09,060][22664] Avg episode reward: [(0, '37.989')] [2023-03-09 07:35:09,105][23090] Updated weights for policy 0, policy_version 6226 (0.0013) [2023-03-09 07:35:10,047][23090] Updated weights for policy 0, policy_version 6236 (0.0017) [2023-03-09 07:35:10,782][23090] Updated weights for policy 0, policy_version 6246 (0.0017) [2023-03-09 07:35:11,652][23090] Updated weights for policy 0, policy_version 6257 (0.0013) [2023-03-09 07:35:12,568][23090] Updated weights for policy 0, policy_version 6267 (0.0013) [2023-03-09 07:35:13,360][23090] Updated weights for policy 0, policy_version 6277 (0.0015) [2023-03-09 07:35:14,059][22664] Fps is (10 sec: 199880.1, 60 sec: 200977.0, 300 sec: 200829.1). Total num frames: 102989824. Throughput: 0: 50321.9. Samples: 25709808. Policy #0 lag: (min: 2.0, avg: 16.3, max: 34.0) [2023-03-09 07:35:14,061][22664] Avg episode reward: [(0, '42.425')] [2023-03-09 07:35:14,135][23090] Updated weights for policy 0, policy_version 6287 (0.0013) [2023-03-09 07:35:14,898][23090] Updated weights for policy 0, policy_version 6297 (0.0021) [2023-03-09 07:35:15,804][23090] Updated weights for policy 0, policy_version 6307 (0.0016) [2023-03-09 07:35:16,614][23090] Updated weights for policy 0, policy_version 6317 (0.0016) [2023-03-09 07:35:17,361][23090] Updated weights for policy 0, policy_version 6327 (0.0016) [2023-03-09 07:35:18,274][23090] Updated weights for policy 0, policy_version 6337 (0.0021) [2023-03-09 07:35:19,034][23090] Updated weights for policy 0, policy_version 6347 (0.0016) [2023-03-09 07:35:19,059][22664] Fps is (10 sec: 199885.8, 60 sec: 200977.0, 300 sec: 200773.6). Total num frames: 103989248. Throughput: 0: 50365.9. Samples: 26012816. Policy #0 lag: (min: 1.0, avg: 16.4, max: 33.0) [2023-03-09 07:35:19,060][22664] Avg episode reward: [(0, '43.286')] [2023-03-09 07:35:19,065][22940] Saving /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000006347_103989248.pth... [2023-03-09 07:35:19,128][22940] Removing /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000003411_55885824.pth [2023-03-09 07:35:19,137][22940] Saving new best policy, reward=43.286! [2023-03-09 07:35:19,203][22940] Signal inference workers to stop experience collection... (2500 times) [2023-03-09 07:35:19,252][22940] Signal inference workers to resume experience collection... (2500 times) [2023-03-09 07:35:19,273][23090] InferenceWorker_p0-w0: stopping experience collection (2500 times) [2023-03-09 07:35:19,315][23090] InferenceWorker_p0-w0: resuming experience collection (2500 times) [2023-03-09 07:35:20,207][23090] Updated weights for policy 0, policy_version 6359 (0.0013) [2023-03-09 07:35:21,181][23090] Updated weights for policy 0, policy_version 6369 (0.0013) [2023-03-09 07:35:21,987][23090] Updated weights for policy 0, policy_version 6379 (0.0013) [2023-03-09 07:35:22,608][23090] Updated weights for policy 0, policy_version 6389 (0.0013) [2023-03-09 07:35:23,617][23090] Updated weights for policy 0, policy_version 6399 (0.0013) [2023-03-09 07:35:24,059][22664] Fps is (10 sec: 194969.0, 60 sec: 200158.0, 300 sec: 200607.1). Total num frames: 104939520. Throughput: 0: 49956.3. Samples: 26299488. Policy #0 lag: (min: 1.0, avg: 16.4, max: 33.0) [2023-03-09 07:35:24,060][22664] Avg episode reward: [(0, '39.664')] [2023-03-09 07:35:24,409][23090] Updated weights for policy 0, policy_version 6409 (0.0024) [2023-03-09 07:35:25,124][23090] Updated weights for policy 0, policy_version 6419 (0.0020) [2023-03-09 07:35:26,105][23090] Updated weights for policy 0, policy_version 6429 (0.0013) [2023-03-09 07:35:26,836][23090] Updated weights for policy 0, policy_version 6439 (0.0016) [2023-03-09 07:35:27,597][23090] Updated weights for policy 0, policy_version 6449 (0.0016) [2023-03-09 07:35:28,501][23090] Updated weights for policy 0, policy_version 6459 (0.0020) [2023-03-09 07:35:29,058][22664] Fps is (10 sec: 193333.6, 60 sec: 199885.9, 300 sec: 200495.7). Total num frames: 105922560. Throughput: 0: 49866.3. Samples: 26446944. Policy #0 lag: (min: 2.0, avg: 17.1, max: 33.0) [2023-03-09 07:35:29,059][22664] Avg episode reward: [(0, '43.064')] [2023-03-09 07:35:29,309][23090] Updated weights for policy 0, policy_version 6469 (0.0019) [2023-03-09 07:35:29,822][22940] Signal inference workers to stop experience collection... (2550 times) [2023-03-09 07:35:29,837][22940] Signal inference workers to resume experience collection... (2550 times) [2023-03-09 07:35:29,895][23090] InferenceWorker_p0-w0: stopping experience collection (2550 times) [2023-03-09 07:35:29,895][23090] InferenceWorker_p0-w0: resuming experience collection (2550 times) [2023-03-09 07:35:30,066][23090] Updated weights for policy 0, policy_version 6479 (0.0013) [2023-03-09 07:35:30,865][23090] Updated weights for policy 0, policy_version 6489 (0.0013) [2023-03-09 07:35:31,777][23090] Updated weights for policy 0, policy_version 6499 (0.0021) [2023-03-09 07:35:32,572][23090] Updated weights for policy 0, policy_version 6509 (0.0018) [2023-03-09 07:35:33,351][23090] Updated weights for policy 0, policy_version 6519 (0.0018) [2023-03-09 07:35:34,059][22664] Fps is (10 sec: 198251.4, 60 sec: 199885.2, 300 sec: 200495.7). Total num frames: 106921984. Throughput: 0: 49913.0. Samples: 26747920. Policy #0 lag: (min: 3.0, avg: 19.4, max: 35.0) [2023-03-09 07:35:34,060][22664] Avg episode reward: [(0, '38.013')] [2023-03-09 07:35:34,276][23090] Updated weights for policy 0, policy_version 6529 (0.0022) [2023-03-09 07:35:35,122][23090] Updated weights for policy 0, policy_version 6539 (0.0013) [2023-03-09 07:35:35,771][23090] Updated weights for policy 0, policy_version 6549 (0.0016) [2023-03-09 07:35:36,744][23090] Updated weights for policy 0, policy_version 6559 (0.0018) [2023-03-09 07:35:37,549][23090] Updated weights for policy 0, policy_version 6569 (0.0016) [2023-03-09 07:35:38,269][23090] Updated weights for policy 0, policy_version 6579 (0.0016) [2023-03-09 07:35:39,059][22664] Fps is (10 sec: 199884.0, 60 sec: 199884.7, 300 sec: 200495.7). Total num frames: 107921408. Throughput: 0: 49777.7. Samples: 27048896. Policy #0 lag: (min: 0.0, avg: 16.2, max: 33.0) [2023-03-09 07:35:39,060][22664] Avg episode reward: [(0, '44.105')] [2023-03-09 07:35:39,075][22940] Saving new best policy, reward=44.105! [2023-03-09 07:35:39,202][23090] Updated weights for policy 0, policy_version 6589 (0.0016) [2023-03-09 07:35:39,895][23090] Updated weights for policy 0, policy_version 6599 (0.0020) [2023-03-09 07:35:40,657][23090] Updated weights for policy 0, policy_version 6609 (0.0013) [2023-03-09 07:35:40,923][22940] Signal inference workers to stop experience collection... (2600 times) [2023-03-09 07:35:40,925][22940] Signal inference workers to resume experience collection... (2600 times) [2023-03-09 07:35:40,988][23090] InferenceWorker_p0-w0: stopping experience collection (2600 times) [2023-03-09 07:35:40,988][23090] InferenceWorker_p0-w0: resuming experience collection (2600 times) [2023-03-09 07:35:41,566][23090] Updated weights for policy 0, policy_version 6619 (0.0022) [2023-03-09 07:35:42,377][23090] Updated weights for policy 0, policy_version 6629 (0.0020) [2023-03-09 07:35:43,134][23090] Updated weights for policy 0, policy_version 6639 (0.0013) [2023-03-09 07:35:43,934][23090] Updated weights for policy 0, policy_version 6649 (0.0017) [2023-03-09 07:35:44,059][22664] Fps is (10 sec: 203155.1, 60 sec: 200429.8, 300 sec: 200551.3). Total num frames: 108953600. Throughput: 0: 49778.4. Samples: 27200416. Policy #0 lag: (min: 1.0, avg: 16.9, max: 33.0) [2023-03-09 07:35:44,061][22664] Avg episode reward: [(0, '41.534')] [2023-03-09 07:35:44,817][23090] Updated weights for policy 0, policy_version 6659 (0.0018) [2023-03-09 07:35:45,611][23090] Updated weights for policy 0, policy_version 6669 (0.0013) [2023-03-09 07:35:46,536][23090] Updated weights for policy 0, policy_version 6680 (0.0013) [2023-03-09 07:35:47,415][23090] Updated weights for policy 0, policy_version 6690 (0.0015) [2023-03-09 07:35:48,179][23090] Updated weights for policy 0, policy_version 6700 (0.0013) [2023-03-09 07:35:49,025][23090] Updated weights for policy 0, policy_version 6711 (0.0013) [2023-03-09 07:35:49,059][22664] Fps is (10 sec: 203161.6, 60 sec: 200158.1, 300 sec: 200551.6). Total num frames: 109953024. Throughput: 0: 49869.5. Samples: 27501456. Policy #0 lag: (min: 2.0, avg: 17.3, max: 33.0) [2023-03-09 07:35:49,071][22664] Avg episode reward: [(0, '44.066')] [2023-03-09 07:35:49,940][23090] Updated weights for policy 0, policy_version 6721 (0.0015) [2023-03-09 07:35:50,763][23090] Updated weights for policy 0, policy_version 6731 (0.0013) [2023-03-09 07:35:51,380][23090] Updated weights for policy 0, policy_version 6741 (0.0021) [2023-03-09 07:35:52,391][23090] Updated weights for policy 0, policy_version 6751 (0.0024) [2023-03-09 07:35:53,218][23090] Updated weights for policy 0, policy_version 6761 (0.0018) [2023-03-09 07:35:53,931][23090] Updated weights for policy 0, policy_version 6771 (0.0019) [2023-03-09 07:35:54,033][22940] Signal inference workers to stop experience collection... (2650 times) [2023-03-09 07:35:54,036][22940] Signal inference workers to resume experience collection... (2650 times) [2023-03-09 07:35:54,059][22664] Fps is (10 sec: 201528.8, 60 sec: 199884.6, 300 sec: 200551.5). Total num frames: 110968832. Throughput: 0: 49824.5. Samples: 27800400. Policy #0 lag: (min: 2.0, avg: 17.3, max: 33.0) [2023-03-09 07:35:54,060][22664] Avg episode reward: [(0, '40.292')] [2023-03-09 07:35:54,101][23090] InferenceWorker_p0-w0: stopping experience collection (2650 times) [2023-03-09 07:35:54,104][23090] InferenceWorker_p0-w0: resuming experience collection (2650 times) [2023-03-09 07:35:54,878][23090] Updated weights for policy 0, policy_version 6781 (0.0016) [2023-03-09 07:35:55,643][23090] Updated weights for policy 0, policy_version 6791 (0.0025) [2023-03-09 07:35:56,400][23090] Updated weights for policy 0, policy_version 6801 (0.0022) [2023-03-09 07:35:57,388][23090] Updated weights for policy 0, policy_version 6812 (0.0019) [2023-03-09 07:35:58,141][23090] Updated weights for policy 0, policy_version 6822 (0.0016) [2023-03-09 07:35:58,906][23090] Updated weights for policy 0, policy_version 6832 (0.0019) [2023-03-09 07:35:59,058][22664] Fps is (10 sec: 199885.6, 60 sec: 199339.4, 300 sec: 200384.7). Total num frames: 111951872. Throughput: 0: 49779.5. Samples: 27949872. Policy #0 lag: (min: 1.0, avg: 17.3, max: 32.0) [2023-03-09 07:35:59,059][22664] Avg episode reward: [(0, '40.026')] [2023-03-09 07:35:59,737][23090] Updated weights for policy 0, policy_version 6842 (0.0013) [2023-03-09 07:36:00,612][23090] Updated weights for policy 0, policy_version 6852 (0.0018) [2023-03-09 07:36:01,390][23090] Updated weights for policy 0, policy_version 6862 (0.0020) [2023-03-09 07:36:02,180][23090] Updated weights for policy 0, policy_version 6872 (0.0015) [2023-03-09 07:36:03,083][23090] Updated weights for policy 0, policy_version 6882 (0.0013) [2023-03-09 07:36:03,891][23090] Updated weights for policy 0, policy_version 6892 (0.0016) [2023-03-09 07:36:04,059][22664] Fps is (10 sec: 198243.2, 60 sec: 199338.0, 300 sec: 200384.6). Total num frames: 112951296. Throughput: 0: 49779.4. Samples: 28252896. Policy #0 lag: (min: 1.0, avg: 15.7, max: 33.0) [2023-03-09 07:36:04,061][22664] Avg episode reward: [(0, '41.658')] [2023-03-09 07:36:04,548][23090] Updated weights for policy 0, policy_version 6902 (0.0013) [2023-03-09 07:36:05,570][23090] Updated weights for policy 0, policy_version 6912 (0.0013) [2023-03-09 07:36:06,424][23090] Updated weights for policy 0, policy_version 6922 (0.0014) [2023-03-09 07:36:06,923][22940] Signal inference workers to stop experience collection... (2700 times) [2023-03-09 07:36:06,925][22940] Signal inference workers to resume experience collection... (2700 times) [2023-03-09 07:36:06,994][23090] InferenceWorker_p0-w0: stopping experience collection (2700 times) [2023-03-09 07:36:06,995][23090] InferenceWorker_p0-w0: resuming experience collection (2700 times) [2023-03-09 07:36:07,078][23090] Updated weights for policy 0, policy_version 6932 (0.0019) [2023-03-09 07:36:08,017][23090] Updated weights for policy 0, policy_version 6942 (0.0013) [2023-03-09 07:36:08,768][23090] Updated weights for policy 0, policy_version 6952 (0.0020) [2023-03-09 07:36:09,059][22664] Fps is (10 sec: 199879.8, 60 sec: 199338.4, 300 sec: 200329.2). Total num frames: 113950720. Throughput: 0: 50052.7. Samples: 28551856. Policy #0 lag: (min: 2.0, avg: 16.5, max: 34.0) [2023-03-09 07:36:09,060][22664] Avg episode reward: [(0, '41.912')] [2023-03-09 07:36:09,585][23090] Updated weights for policy 0, policy_version 6962 (0.0023) [2023-03-09 07:36:10,456][23090] Updated weights for policy 0, policy_version 6972 (0.0017) [2023-03-09 07:36:11,206][23090] Updated weights for policy 0, policy_version 6982 (0.0021) [2023-03-09 07:36:11,992][23090] Updated weights for policy 0, policy_version 6992 (0.0015) [2023-03-09 07:36:12,857][23090] Updated weights for policy 0, policy_version 7002 (0.0019) [2023-03-09 07:36:13,745][23090] Updated weights for policy 0, policy_version 7012 (0.0013) [2023-03-09 07:36:14,059][22664] Fps is (10 sec: 199876.4, 60 sec: 199337.3, 300 sec: 200328.8). Total num frames: 114950144. Throughput: 0: 50141.9. Samples: 28703360. Policy #0 lag: (min: 1.0, avg: 17.3, max: 32.0) [2023-03-09 07:36:14,061][22664] Avg episode reward: [(0, '40.745')] [2023-03-09 07:36:14,499][23090] Updated weights for policy 0, policy_version 7022 (0.0017) [2023-03-09 07:36:15,401][23090] Updated weights for policy 0, policy_version 7033 (0.0016) [2023-03-09 07:36:16,310][23090] Updated weights for policy 0, policy_version 7043 (0.0016) [2023-03-09 07:36:17,149][23090] Updated weights for policy 0, policy_version 7053 (0.0019) [2023-03-09 07:36:17,867][23090] Updated weights for policy 0, policy_version 7063 (0.0013) [2023-03-09 07:36:18,830][23090] Updated weights for policy 0, policy_version 7073 (0.0017) [2023-03-09 07:36:19,058][22664] Fps is (10 sec: 199889.3, 60 sec: 199339.0, 300 sec: 200384.9). Total num frames: 115949568. Throughput: 0: 50051.2. Samples: 29000224. Policy #0 lag: (min: 1.0, avg: 15.6, max: 33.0) [2023-03-09 07:36:19,059][22664] Avg episode reward: [(0, '40.278')] [2023-03-09 07:36:19,621][23090] Updated weights for policy 0, policy_version 7083 (0.0013) [2023-03-09 07:36:19,799][22940] Signal inference workers to stop experience collection... (2750 times) [2023-03-09 07:36:19,800][22940] Signal inference workers to resume experience collection... (2750 times) [2023-03-09 07:36:19,863][23090] InferenceWorker_p0-w0: stopping experience collection (2750 times) [2023-03-09 07:36:19,863][23090] InferenceWorker_p0-w0: resuming experience collection (2750 times) [2023-03-09 07:36:20,278][23090] Updated weights for policy 0, policy_version 7093 (0.0015) [2023-03-09 07:36:21,229][23090] Updated weights for policy 0, policy_version 7103 (0.0017) [2023-03-09 07:36:22,060][23090] Updated weights for policy 0, policy_version 7113 (0.0018) [2023-03-09 07:36:22,751][23090] Updated weights for policy 0, policy_version 7123 (0.0013) [2023-03-09 07:36:23,699][23090] Updated weights for policy 0, policy_version 7133 (0.0015) [2023-03-09 07:36:24,059][22664] Fps is (10 sec: 198258.1, 60 sec: 199885.5, 300 sec: 200329.3). Total num frames: 116932608. Throughput: 0: 50050.8. Samples: 29301184. Policy #0 lag: (min: 1.0, avg: 15.6, max: 33.0) [2023-03-09 07:36:24,060][22664] Avg episode reward: [(0, '41.294')] [2023-03-09 07:36:24,443][23090] Updated weights for policy 0, policy_version 7143 (0.0024) [2023-03-09 07:36:25,219][23090] Updated weights for policy 0, policy_version 7153 (0.0019) [2023-03-09 07:36:26,131][23090] Updated weights for policy 0, policy_version 7163 (0.0013) [2023-03-09 07:36:26,940][23090] Updated weights for policy 0, policy_version 7173 (0.0023) [2023-03-09 07:36:27,787][23090] Updated weights for policy 0, policy_version 7184 (0.0025) [2023-03-09 07:36:28,686][23090] Updated weights for policy 0, policy_version 7194 (0.0013) [2023-03-09 07:36:29,059][22664] Fps is (10 sec: 198231.1, 60 sec: 200155.2, 300 sec: 200273.1). Total num frames: 117932032. Throughput: 0: 50005.5. Samples: 29450688. Policy #0 lag: (min: 2.0, avg: 16.8, max: 33.0) [2023-03-09 07:36:29,061][22664] Avg episode reward: [(0, '42.495')] [2023-03-09 07:36:29,483][23090] Updated weights for policy 0, policy_version 7204 (0.0013) [2023-03-09 07:36:30,305][23090] Updated weights for policy 0, policy_version 7214 (0.0013) [2023-03-09 07:36:31,084][23090] Updated weights for policy 0, policy_version 7224 (0.0026) [2023-03-09 07:36:31,974][23090] Updated weights for policy 0, policy_version 7234 (0.0013) [2023-03-09 07:36:32,798][23090] Updated weights for policy 0, policy_version 7244 (0.0013) [2023-03-09 07:36:32,871][22940] Signal inference workers to stop experience collection... (2800 times) [2023-03-09 07:36:32,889][22940] Signal inference workers to resume experience collection... (2800 times) [2023-03-09 07:36:32,916][23090] InferenceWorker_p0-w0: stopping experience collection (2800 times) [2023-03-09 07:36:32,957][23090] InferenceWorker_p0-w0: resuming experience collection (2800 times) [2023-03-09 07:36:33,408][23090] Updated weights for policy 0, policy_version 7254 (0.0015) [2023-03-09 07:36:34,058][22664] Fps is (10 sec: 199885.6, 60 sec: 200157.9, 300 sec: 200218.3). Total num frames: 118931456. Throughput: 0: 49959.5. Samples: 29749632. Policy #0 lag: (min: 0.0, avg: 17.2, max: 33.0) [2023-03-09 07:36:34,059][22664] Avg episode reward: [(0, '44.925')] [2023-03-09 07:36:34,061][22940] Saving new best policy, reward=44.925! [2023-03-09 07:36:34,504][23090] Updated weights for policy 0, policy_version 7265 (0.0014) [2023-03-09 07:36:35,306][23090] Updated weights for policy 0, policy_version 7275 (0.0021) [2023-03-09 07:36:35,945][23090] Updated weights for policy 0, policy_version 7285 (0.0013) [2023-03-09 07:36:36,862][23090] Updated weights for policy 0, policy_version 7295 (0.0011) [2023-03-09 07:36:37,697][23090] Updated weights for policy 0, policy_version 7305 (0.0014) [2023-03-09 07:36:38,372][23090] Updated weights for policy 0, policy_version 7315 (0.0013) [2023-03-09 07:36:39,059][22664] Fps is (10 sec: 203176.7, 60 sec: 200703.9, 300 sec: 200329.2). Total num frames: 119963648. Throughput: 0: 50095.7. Samples: 30054704. Policy #0 lag: (min: 0.0, avg: 17.0, max: 33.0) [2023-03-09 07:36:39,060][22664] Avg episode reward: [(0, '41.753')] [2023-03-09 07:36:39,317][23090] Updated weights for policy 0, policy_version 7325 (0.0017) [2023-03-09 07:36:40,060][23090] Updated weights for policy 0, policy_version 7335 (0.0019) [2023-03-09 07:36:40,817][23090] Updated weights for policy 0, policy_version 7345 (0.0024) [2023-03-09 07:36:41,712][23090] Updated weights for policy 0, policy_version 7355 (0.0019) [2023-03-09 07:36:42,527][23090] Updated weights for policy 0, policy_version 7365 (0.0018) [2023-03-09 07:36:43,277][23090] Updated weights for policy 0, policy_version 7375 (0.0018) [2023-03-09 07:36:44,058][22664] Fps is (10 sec: 204800.2, 60 sec: 200432.1, 300 sec: 200384.6). Total num frames: 120979456. Throughput: 0: 50185.9. Samples: 30208240. Policy #0 lag: (min: 0.0, avg: 17.7, max: 33.0) [2023-03-09 07:36:44,060][22664] Avg episode reward: [(0, '38.793')] [2023-03-09 07:36:44,084][23090] Updated weights for policy 0, policy_version 7385 (0.0014) [2023-03-09 07:36:45,031][23090] Updated weights for policy 0, policy_version 7395 (0.0016) [2023-03-09 07:36:45,086][22940] Signal inference workers to stop experience collection... (2850 times) [2023-03-09 07:36:45,087][22940] Signal inference workers to resume experience collection... (2850 times) [2023-03-09 07:36:45,153][23090] InferenceWorker_p0-w0: stopping experience collection (2850 times) [2023-03-09 07:36:45,153][23090] InferenceWorker_p0-w0: resuming experience collection (2850 times) [2023-03-09 07:36:45,793][23090] Updated weights for policy 0, policy_version 7405 (0.0013) [2023-03-09 07:36:46,656][23090] Updated weights for policy 0, policy_version 7416 (0.0014) [2023-03-09 07:36:47,570][23090] Updated weights for policy 0, policy_version 7426 (0.0019) [2023-03-09 07:36:48,356][23090] Updated weights for policy 0, policy_version 7436 (0.0019) [2023-03-09 07:36:49,020][23090] Updated weights for policy 0, policy_version 7446 (0.0019) [2023-03-09 07:36:49,059][22664] Fps is (10 sec: 203155.6, 60 sec: 200703.0, 300 sec: 200440.1). Total num frames: 121995264. Throughput: 0: 50140.0. Samples: 30509200. Policy #0 lag: (min: 0.0, avg: 17.7, max: 33.0) [2023-03-09 07:36:49,061][22664] Avg episode reward: [(0, '43.565')] [2023-03-09 07:36:49,967][23090] Updated weights for policy 0, policy_version 7456 (0.0019) [2023-03-09 07:36:50,785][23090] Updated weights for policy 0, policy_version 7466 (0.0013) [2023-03-09 07:36:51,492][23090] Updated weights for policy 0, policy_version 7477 (0.0016) [2023-03-09 07:36:52,546][23090] Updated weights for policy 0, policy_version 7487 (0.0013) [2023-03-09 07:36:53,360][23090] Updated weights for policy 0, policy_version 7497 (0.0019) [2023-03-09 07:36:54,053][23090] Updated weights for policy 0, policy_version 7507 (0.0013) [2023-03-09 07:36:54,059][22664] Fps is (10 sec: 201518.8, 60 sec: 200430.4, 300 sec: 200440.1). Total num frames: 122994688. Throughput: 0: 50140.5. Samples: 30808176. Policy #0 lag: (min: 2.0, avg: 16.8, max: 33.0) [2023-03-09 07:36:54,060][22664] Avg episode reward: [(0, '42.352')] [2023-03-09 07:36:54,964][23090] Updated weights for policy 0, policy_version 7517 (0.0015) [2023-03-09 07:36:55,316][22940] Signal inference workers to stop experience collection... (2900 times) [2023-03-09 07:36:55,317][22940] Signal inference workers to resume experience collection... (2900 times) [2023-03-09 07:36:55,390][23090] InferenceWorker_p0-w0: stopping experience collection (2900 times) [2023-03-09 07:36:55,390][23090] InferenceWorker_p0-w0: resuming experience collection (2900 times) [2023-03-09 07:36:55,706][23090] Updated weights for policy 0, policy_version 7527 (0.0015) [2023-03-09 07:36:56,485][23090] Updated weights for policy 0, policy_version 7537 (0.0019) [2023-03-09 07:36:57,504][23090] Updated weights for policy 0, policy_version 7548 (0.0016) [2023-03-09 07:36:58,307][23090] Updated weights for policy 0, policy_version 7558 (0.0016) [2023-03-09 07:36:59,031][23090] Updated weights for policy 0, policy_version 7568 (0.0015) [2023-03-09 07:36:59,058][22664] Fps is (10 sec: 199891.7, 60 sec: 200704.0, 300 sec: 200329.5). Total num frames: 123994112. Throughput: 0: 50096.0. Samples: 30957648. Policy #0 lag: (min: 0.0, avg: 18.9, max: 34.0) [2023-03-09 07:36:59,060][22664] Avg episode reward: [(0, '46.453')] [2023-03-09 07:36:59,108][22940] Saving new best policy, reward=46.453! [2023-03-09 07:36:59,931][23090] Updated weights for policy 0, policy_version 7578 (0.0013) [2023-03-09 07:37:00,770][23090] Updated weights for policy 0, policy_version 7589 (0.0016) [2023-03-09 07:37:01,580][23090] Updated weights for policy 0, policy_version 7599 (0.0013) [2023-03-09 07:37:02,404][23090] Updated weights for policy 0, policy_version 7609 (0.0021) [2023-03-09 07:37:03,283][23090] Updated weights for policy 0, policy_version 7619 (0.0013) [2023-03-09 07:37:04,059][22664] Fps is (10 sec: 199887.6, 60 sec: 200704.5, 300 sec: 200273.5). Total num frames: 124993536. Throughput: 0: 50278.7. Samples: 31262768. Policy #0 lag: (min: 2.0, avg: 16.6, max: 33.0) [2023-03-09 07:37:04,060][22664] Avg episode reward: [(0, '43.397')] [2023-03-09 07:37:04,069][23090] Updated weights for policy 0, policy_version 7629 (0.0015) [2023-03-09 07:37:04,500][22940] Signal inference workers to stop experience collection... (2950 times) [2023-03-09 07:37:04,521][22940] Signal inference workers to resume experience collection... (2950 times) [2023-03-09 07:37:04,553][23090] InferenceWorker_p0-w0: stopping experience collection (2950 times) [2023-03-09 07:37:04,591][23090] InferenceWorker_p0-w0: resuming experience collection (2950 times) [2023-03-09 07:37:04,827][23090] Updated weights for policy 0, policy_version 7639 (0.0015) [2023-03-09 07:37:05,802][23090] Updated weights for policy 0, policy_version 7649 (0.0013) [2023-03-09 07:37:06,540][23090] Updated weights for policy 0, policy_version 7659 (0.0013) [2023-03-09 07:37:07,176][23090] Updated weights for policy 0, policy_version 7669 (0.0024) [2023-03-09 07:37:08,192][23090] Updated weights for policy 0, policy_version 7679 (0.0019) [2023-03-09 07:37:08,957][23090] Updated weights for policy 0, policy_version 7689 (0.0017) [2023-03-09 07:37:09,059][22664] Fps is (10 sec: 199881.2, 60 sec: 200704.2, 300 sec: 200217.9). Total num frames: 125992960. Throughput: 0: 50325.9. Samples: 31565856. Policy #0 lag: (min: 2.0, avg: 16.6, max: 33.0) [2023-03-09 07:37:09,060][22664] Avg episode reward: [(0, '42.715')] [2023-03-09 07:37:09,675][23090] Updated weights for policy 0, policy_version 7699 (0.0015) [2023-03-09 07:37:10,615][23090] Updated weights for policy 0, policy_version 7709 (0.0017) [2023-03-09 07:37:11,342][23090] Updated weights for policy 0, policy_version 7719 (0.0016) [2023-03-09 07:37:12,135][23090] Updated weights for policy 0, policy_version 7729 (0.0012) [2023-03-09 07:37:13,147][23090] Updated weights for policy 0, policy_version 7740 (0.0018) [2023-03-09 07:37:13,875][23090] Updated weights for policy 0, policy_version 7750 (0.0018) [2023-03-09 07:37:14,058][22664] Fps is (10 sec: 199887.1, 60 sec: 200706.3, 300 sec: 200273.8). Total num frames: 126992384. Throughput: 0: 50327.0. Samples: 31715360. Policy #0 lag: (min: 0.0, avg: 18.8, max: 34.0) [2023-03-09 07:37:14,059][22664] Avg episode reward: [(0, '42.569')] [2023-03-09 07:37:14,674][23090] Updated weights for policy 0, policy_version 7760 (0.0015) [2023-03-09 07:37:14,897][22940] Signal inference workers to stop experience collection... (3000 times) [2023-03-09 07:37:14,913][22940] Signal inference workers to resume experience collection... (3000 times) [2023-03-09 07:37:14,964][23090] InferenceWorker_p0-w0: stopping experience collection (3000 times) [2023-03-09 07:37:14,964][23090] InferenceWorker_p0-w0: resuming experience collection (3000 times) [2023-03-09 07:37:15,671][23090] Updated weights for policy 0, policy_version 7771 (0.0013) [2023-03-09 07:37:16,443][23090] Updated weights for policy 0, policy_version 7781 (0.0013) [2023-03-09 07:37:17,197][23090] Updated weights for policy 0, policy_version 7791 (0.0023) [2023-03-09 07:37:17,997][23090] Updated weights for policy 0, policy_version 7801 (0.0018) [2023-03-09 07:37:18,937][23090] Updated weights for policy 0, policy_version 7811 (0.0018) [2023-03-09 07:37:19,059][22664] Fps is (10 sec: 201515.1, 60 sec: 200975.2, 300 sec: 200384.2). Total num frames: 128008192. Throughput: 0: 50372.0. Samples: 32016400. Policy #0 lag: (min: 2.0, avg: 17.0, max: 33.0) [2023-03-09 07:37:19,061][22664] Avg episode reward: [(0, '44.246')] [2023-03-09 07:37:19,089][22940] Saving /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000007814_128024576.pth... [2023-03-09 07:37:19,155][22940] Removing /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000004878_79921152.pth [2023-03-09 07:37:19,733][23090] Updated weights for policy 0, policy_version 7821 (0.0014) [2023-03-09 07:37:20,535][23090] Updated weights for policy 0, policy_version 7831 (0.0022) [2023-03-09 07:37:21,516][23090] Updated weights for policy 0, policy_version 7842 (0.0017) [2023-03-09 07:37:22,286][23090] Updated weights for policy 0, policy_version 7852 (0.0013) [2023-03-09 07:37:23,130][23090] Updated weights for policy 0, policy_version 7863 (0.0016) [2023-03-09 07:37:24,059][22664] Fps is (10 sec: 199882.5, 60 sec: 200977.0, 300 sec: 200329.5). Total num frames: 128991232. Throughput: 0: 50281.9. Samples: 32317392. Policy #0 lag: (min: 0.0, avg: 17.9, max: 33.0) [2023-03-09 07:37:24,060][22664] Avg episode reward: [(0, '40.833')] [2023-03-09 07:37:24,084][23090] Updated weights for policy 0, policy_version 7873 (0.0017) [2023-03-09 07:37:24,844][22940] Signal inference workers to stop experience collection... (3050 times) [2023-03-09 07:37:24,856][22940] Signal inference workers to resume experience collection... (3050 times) [2023-03-09 07:37:24,886][23090] InferenceWorker_p0-w0: stopping experience collection (3050 times) [2023-03-09 07:37:24,889][23090] Updated weights for policy 0, policy_version 7883 (0.0015) [2023-03-09 07:37:24,927][23090] InferenceWorker_p0-w0: resuming experience collection (3050 times) [2023-03-09 07:37:25,465][23090] Updated weights for policy 0, policy_version 7893 (0.0021) [2023-03-09 07:37:26,464][23090] Updated weights for policy 0, policy_version 7903 (0.0013) [2023-03-09 07:37:27,299][23090] Updated weights for policy 0, policy_version 7913 (0.0013) [2023-03-09 07:37:27,989][23090] Updated weights for policy 0, policy_version 7923 (0.0023) [2023-03-09 07:37:28,960][23090] Updated weights for policy 0, policy_version 7933 (0.0018) [2023-03-09 07:37:29,059][22664] Fps is (10 sec: 198250.2, 60 sec: 200978.4, 300 sec: 200328.8). Total num frames: 129990656. Throughput: 0: 50146.1. Samples: 32464832. Policy #0 lag: (min: 0.0, avg: 17.9, max: 33.0) [2023-03-09 07:37:29,060][22664] Avg episode reward: [(0, '45.290')] [2023-03-09 07:37:29,660][23090] Updated weights for policy 0, policy_version 7943 (0.0023) [2023-03-09 07:37:30,427][23090] Updated weights for policy 0, policy_version 7953 (0.0023) [2023-03-09 07:37:31,365][23090] Updated weights for policy 0, policy_version 7963 (0.0020) [2023-03-09 07:37:32,172][23090] Updated weights for policy 0, policy_version 7973 (0.0020) [2023-03-09 07:37:32,886][23090] Updated weights for policy 0, policy_version 7983 (0.0013) [2023-03-09 07:37:33,685][23090] Updated weights for policy 0, policy_version 7993 (0.0020) [2023-03-09 07:37:34,058][22664] Fps is (10 sec: 201524.8, 60 sec: 201250.2, 300 sec: 200384.8). Total num frames: 131006464. Throughput: 0: 50192.7. Samples: 32767856. Policy #0 lag: (min: 0.0, avg: 17.0, max: 33.0) [2023-03-09 07:37:34,059][22664] Avg episode reward: [(0, '41.577')] [2023-03-09 07:37:34,670][23090] Updated weights for policy 0, policy_version 8003 (0.0022) [2023-03-09 07:37:35,291][22940] Signal inference workers to stop experience collection... (3100 times) [2023-03-09 07:37:35,292][22940] Signal inference workers to resume experience collection... (3100 times) [2023-03-09 07:37:35,359][23090] InferenceWorker_p0-w0: stopping experience collection (3100 times) [2023-03-09 07:37:35,360][23090] InferenceWorker_p0-w0: resuming experience collection (3100 times) [2023-03-09 07:37:35,399][23090] Updated weights for policy 0, policy_version 8013 (0.0013) [2023-03-09 07:37:36,180][23090] Updated weights for policy 0, policy_version 8023 (0.0029) [2023-03-09 07:37:37,116][23090] Updated weights for policy 0, policy_version 8033 (0.0015) [2023-03-09 07:37:37,889][23090] Updated weights for policy 0, policy_version 8043 (0.0013) [2023-03-09 07:37:38,536][23090] Updated weights for policy 0, policy_version 8053 (0.0017) [2023-03-09 07:37:39,058][22664] Fps is (10 sec: 201531.1, 60 sec: 200704.2, 300 sec: 200384.8). Total num frames: 132005888. Throughput: 0: 50190.5. Samples: 33066736. Policy #0 lag: (min: 0.0, avg: 17.0, max: 33.0) [2023-03-09 07:37:39,060][22664] Avg episode reward: [(0, '46.181')] [2023-03-09 07:37:39,558][23090] Updated weights for policy 0, policy_version 8063 (0.0019) [2023-03-09 07:37:40,327][23090] Updated weights for policy 0, policy_version 8073 (0.0019) [2023-03-09 07:37:41,081][23090] Updated weights for policy 0, policy_version 8083 (0.0016) [2023-03-09 07:37:41,986][23090] Updated weights for policy 0, policy_version 8093 (0.0013) [2023-03-09 07:37:42,708][23090] Updated weights for policy 0, policy_version 8103 (0.0019) [2023-03-09 07:37:43,512][23090] Updated weights for policy 0, policy_version 8113 (0.0019) [2023-03-09 07:37:44,059][22664] Fps is (10 sec: 203155.4, 60 sec: 200976.0, 300 sec: 200495.5). Total num frames: 133038080. Throughput: 0: 50235.4. Samples: 33218256. Policy #0 lag: (min: 2.0, avg: 17.2, max: 33.0) [2023-03-09 07:37:44,061][22664] Avg episode reward: [(0, '42.097')] [2023-03-09 07:37:44,308][22940] Signal inference workers to stop experience collection... (3150 times) [2023-03-09 07:37:44,309][22940] Signal inference workers to resume experience collection... (3150 times) [2023-03-09 07:37:44,372][23090] InferenceWorker_p0-w0: stopping experience collection (3150 times) [2023-03-09 07:37:44,372][23090] InferenceWorker_p0-w0: resuming experience collection (3150 times) [2023-03-09 07:37:44,375][23090] Updated weights for policy 0, policy_version 8123 (0.0015) [2023-03-09 07:37:45,208][23090] Updated weights for policy 0, policy_version 8133 (0.0017) [2023-03-09 07:37:45,950][23090] Updated weights for policy 0, policy_version 8143 (0.0013) [2023-03-09 07:37:46,778][23090] Updated weights for policy 0, policy_version 8153 (0.0014) [2023-03-09 07:37:47,626][23090] Updated weights for policy 0, policy_version 8163 (0.0017) [2023-03-09 07:37:48,432][23090] Updated weights for policy 0, policy_version 8173 (0.0013) [2023-03-09 07:37:49,059][22664] Fps is (10 sec: 204789.0, 60 sec: 200976.4, 300 sec: 200551.1). Total num frames: 134053888. Throughput: 0: 50189.0. Samples: 33521296. Policy #0 lag: (min: 2.0, avg: 17.2, max: 33.0) [2023-03-09 07:37:49,061][22664] Avg episode reward: [(0, '44.082')] [2023-03-09 07:37:49,198][23090] Updated weights for policy 0, policy_version 8183 (0.0013) [2023-03-09 07:37:50,186][23090] Updated weights for policy 0, policy_version 8193 (0.0013) [2023-03-09 07:37:50,936][23090] Updated weights for policy 0, policy_version 8203 (0.0015) [2023-03-09 07:37:51,583][23090] Updated weights for policy 0, policy_version 8213 (0.0013) [2023-03-09 07:37:52,575][23090] Updated weights for policy 0, policy_version 8223 (0.0018) [2023-03-09 07:37:53,437][23090] Updated weights for policy 0, policy_version 8234 (0.0016) [2023-03-09 07:37:54,023][22940] Signal inference workers to stop experience collection... (3200 times) [2023-03-09 07:37:54,039][22940] Signal inference workers to resume experience collection... (3200 times) [2023-03-09 07:37:54,058][22664] Fps is (10 sec: 201529.9, 60 sec: 200977.9, 300 sec: 200495.9). Total num frames: 135053312. Throughput: 0: 50188.7. Samples: 33824336. Policy #0 lag: (min: 0.0, avg: 15.9, max: 32.0) [2023-03-09 07:37:54,059][22664] Avg episode reward: [(0, '44.004')] [2023-03-09 07:37:54,076][23090] InferenceWorker_p0-w0: stopping experience collection (3200 times) [2023-03-09 07:37:54,118][23090] InferenceWorker_p0-w0: resuming experience collection (3200 times) [2023-03-09 07:37:54,126][23090] Updated weights for policy 0, policy_version 8244 (0.0013) [2023-03-09 07:37:55,097][23090] Updated weights for policy 0, policy_version 8254 (0.0023) [2023-03-09 07:37:55,819][23090] Updated weights for policy 0, policy_version 8264 (0.0016) [2023-03-09 07:37:56,646][23090] Updated weights for policy 0, policy_version 8275 (0.0019) [2023-03-09 07:37:57,599][23090] Updated weights for policy 0, policy_version 8285 (0.0020) [2023-03-09 07:37:58,293][23090] Updated weights for policy 0, policy_version 8295 (0.0019) [2023-03-09 07:37:59,059][22664] Fps is (10 sec: 199893.9, 60 sec: 200976.8, 300 sec: 200440.4). Total num frames: 136052736. Throughput: 0: 50186.2. Samples: 33973744. Policy #0 lag: (min: 0.0, avg: 17.9, max: 33.0) [2023-03-09 07:37:59,060][22664] Avg episode reward: [(0, '47.503')] [2023-03-09 07:37:59,064][22940] Saving new best policy, reward=47.503! [2023-03-09 07:37:59,271][23090] Updated weights for policy 0, policy_version 8305 (0.0016) [2023-03-09 07:38:00,018][23090] Updated weights for policy 0, policy_version 8315 (0.0013) [2023-03-09 07:38:00,827][23090] Updated weights for policy 0, policy_version 8325 (0.0016) [2023-03-09 07:38:01,586][23090] Updated weights for policy 0, policy_version 8335 (0.0015) [2023-03-09 07:38:02,393][23090] Updated weights for policy 0, policy_version 8345 (0.0016) [2023-03-09 07:38:03,264][23090] Updated weights for policy 0, policy_version 8355 (0.0016) [2023-03-09 07:38:04,059][22664] Fps is (10 sec: 199877.9, 60 sec: 200976.3, 300 sec: 200384.5). Total num frames: 137052160. Throughput: 0: 50231.0. Samples: 34276784. Policy #0 lag: (min: 1.0, avg: 16.0, max: 32.0) [2023-03-09 07:38:04,061][22664] Avg episode reward: [(0, '43.894')] [2023-03-09 07:38:04,132][23090] Updated weights for policy 0, policy_version 8366 (0.0013) [2023-03-09 07:38:04,348][22940] Signal inference workers to stop experience collection... (3250 times) [2023-03-09 07:38:04,349][22940] Signal inference workers to resume experience collection... (3250 times) [2023-03-09 07:38:04,418][23090] InferenceWorker_p0-w0: stopping experience collection (3250 times) [2023-03-09 07:38:04,421][23090] InferenceWorker_p0-w0: resuming experience collection (3250 times) [2023-03-09 07:38:04,900][23090] Updated weights for policy 0, policy_version 8376 (0.0013) [2023-03-09 07:38:05,835][23090] Updated weights for policy 0, policy_version 8386 (0.0015) [2023-03-09 07:38:06,630][23090] Updated weights for policy 0, policy_version 8396 (0.0013) [2023-03-09 07:38:07,244][23090] Updated weights for policy 0, policy_version 8406 (0.0016) [2023-03-09 07:38:08,243][23090] Updated weights for policy 0, policy_version 8416 (0.0014) [2023-03-09 07:38:09,047][23090] Updated weights for policy 0, policy_version 8426 (0.0020) [2023-03-09 07:38:09,059][22664] Fps is (10 sec: 199882.9, 60 sec: 200977.1, 300 sec: 200495.6). Total num frames: 138051584. Throughput: 0: 50275.8. Samples: 34579808. Policy #0 lag: (min: 1.0, avg: 16.0, max: 32.0) [2023-03-09 07:38:09,060][22664] Avg episode reward: [(0, '40.569')] [2023-03-09 07:38:09,708][23090] Updated weights for policy 0, policy_version 8436 (0.0027) [2023-03-09 07:38:10,661][23090] Updated weights for policy 0, policy_version 8446 (0.0014) [2023-03-09 07:38:11,526][23090] Updated weights for policy 0, policy_version 8457 (0.0018) [2023-03-09 07:38:12,217][23090] Updated weights for policy 0, policy_version 8467 (0.0013) [2023-03-09 07:38:13,200][23090] Updated weights for policy 0, policy_version 8477 (0.0013) [2023-03-09 07:38:13,874][23090] Updated weights for policy 0, policy_version 8487 (0.0022) [2023-03-09 07:38:14,058][22664] Fps is (10 sec: 201530.0, 60 sec: 201250.1, 300 sec: 200551.5). Total num frames: 139067392. Throughput: 0: 50367.4. Samples: 34731344. Policy #0 lag: (min: 1.0, avg: 15.9, max: 33.0) [2023-03-09 07:38:14,060][22664] Avg episode reward: [(0, '40.378')] [2023-03-09 07:38:14,368][22940] Signal inference workers to stop experience collection... (3300 times) [2023-03-09 07:38:14,371][22940] Signal inference workers to resume experience collection... (3300 times) [2023-03-09 07:38:14,434][23090] InferenceWorker_p0-w0: stopping experience collection (3300 times) [2023-03-09 07:38:14,434][23090] InferenceWorker_p0-w0: resuming experience collection (3300 times) [2023-03-09 07:38:14,711][23090] Updated weights for policy 0, policy_version 8497 (0.0016) [2023-03-09 07:38:15,592][23090] Updated weights for policy 0, policy_version 8507 (0.0019) [2023-03-09 07:38:16,419][23090] Updated weights for policy 0, policy_version 8517 (0.0017) [2023-03-09 07:38:17,141][23090] Updated weights for policy 0, policy_version 8527 (0.0020) [2023-03-09 07:38:17,954][23090] Updated weights for policy 0, policy_version 8537 (0.0013) [2023-03-09 07:38:18,854][23090] Updated weights for policy 0, policy_version 8547 (0.0011) [2023-03-09 07:38:19,059][22664] Fps is (10 sec: 203157.6, 60 sec: 201250.8, 300 sec: 200606.6). Total num frames: 140083200. Throughput: 0: 50365.8. Samples: 35034336. Policy #0 lag: (min: 1.0, avg: 17.5, max: 33.0) [2023-03-09 07:38:19,061][22664] Avg episode reward: [(0, '43.370')] [2023-03-09 07:38:19,646][23090] Updated weights for policy 0, policy_version 8557 (0.0016) [2023-03-09 07:38:20,409][23090] Updated weights for policy 0, policy_version 8567 (0.0017) [2023-03-09 07:38:21,298][23090] Updated weights for policy 0, policy_version 8577 (0.0019) [2023-03-09 07:38:22,099][23090] Updated weights for policy 0, policy_version 8587 (0.0021) [2023-03-09 07:38:22,745][23090] Updated weights for policy 0, policy_version 8597 (0.0015) [2023-03-09 07:38:23,812][23090] Updated weights for policy 0, policy_version 8607 (0.0019) [2023-03-09 07:38:24,059][22664] Fps is (10 sec: 199876.6, 60 sec: 201249.1, 300 sec: 200495.5). Total num frames: 141066240. Throughput: 0: 50412.0. Samples: 35335296. Policy #0 lag: (min: 1.0, avg: 17.5, max: 33.0) [2023-03-09 07:38:24,061][22664] Avg episode reward: [(0, '44.722')] [2023-03-09 07:38:24,537][23090] Updated weights for policy 0, policy_version 8617 (0.0013) [2023-03-09 07:38:24,809][22940] Signal inference workers to stop experience collection... (3350 times) [2023-03-09 07:38:24,822][22940] Signal inference workers to resume experience collection... (3350 times) [2023-03-09 07:38:24,856][23090] InferenceWorker_p0-w0: stopping experience collection (3350 times) [2023-03-09 07:38:24,899][23090] InferenceWorker_p0-w0: resuming experience collection (3350 times) [2023-03-09 07:38:25,272][23090] Updated weights for policy 0, policy_version 8627 (0.0013) [2023-03-09 07:38:26,246][23090] Updated weights for policy 0, policy_version 8637 (0.0016) [2023-03-09 07:38:26,992][23090] Updated weights for policy 0, policy_version 8647 (0.0016) [2023-03-09 07:38:27,796][23090] Updated weights for policy 0, policy_version 8657 (0.0018) [2023-03-09 07:38:28,672][23090] Updated weights for policy 0, policy_version 8667 (0.0019) [2023-03-09 07:38:29,059][22664] Fps is (10 sec: 198253.0, 60 sec: 201251.3, 300 sec: 200495.9). Total num frames: 142065664. Throughput: 0: 50366.9. Samples: 35484752. Policy #0 lag: (min: 3.0, avg: 17.7, max: 34.0) [2023-03-09 07:38:29,059][22664] Avg episode reward: [(0, '45.461')] [2023-03-09 07:38:29,461][23090] Updated weights for policy 0, policy_version 8677 (0.0013) [2023-03-09 07:38:30,241][23090] Updated weights for policy 0, policy_version 8687 (0.0018) [2023-03-09 07:38:31,043][23090] Updated weights for policy 0, policy_version 8697 (0.0020) [2023-03-09 07:38:31,990][23090] Updated weights for policy 0, policy_version 8707 (0.0017) [2023-03-09 07:38:32,741][23090] Updated weights for policy 0, policy_version 8717 (0.0021) [2023-03-09 07:38:33,461][23090] Updated weights for policy 0, policy_version 8727 (0.0015) [2023-03-09 07:38:34,059][22664] Fps is (10 sec: 199889.6, 60 sec: 200976.5, 300 sec: 200551.4). Total num frames: 143065088. Throughput: 0: 50320.8. Samples: 35785712. Policy #0 lag: (min: 2.0, avg: 17.2, max: 34.0) [2023-03-09 07:38:34,060][22664] Avg episode reward: [(0, '44.612')] [2023-03-09 07:38:34,410][23090] Updated weights for policy 0, policy_version 8737 (0.0014) [2023-03-09 07:38:35,218][23090] Updated weights for policy 0, policy_version 8747 (0.0018) [2023-03-09 07:38:35,348][22940] Signal inference workers to stop experience collection... (3400 times) [2023-03-09 07:38:35,370][22940] Signal inference workers to resume experience collection... (3400 times) [2023-03-09 07:38:35,416][23090] InferenceWorker_p0-w0: stopping experience collection (3400 times) [2023-03-09 07:38:35,454][23090] InferenceWorker_p0-w0: resuming experience collection (3400 times) [2023-03-09 07:38:35,974][23090] Updated weights for policy 0, policy_version 8758 (0.0013) [2023-03-09 07:38:36,939][23090] Updated weights for policy 0, policy_version 8768 (0.0016) [2023-03-09 07:38:37,780][23090] Updated weights for policy 0, policy_version 8778 (0.0017) [2023-03-09 07:38:38,417][23090] Updated weights for policy 0, policy_version 8788 (0.0013) [2023-03-09 07:38:39,059][22664] Fps is (10 sec: 201523.0, 60 sec: 201250.0, 300 sec: 200606.9). Total num frames: 144080896. Throughput: 0: 50275.1. Samples: 36086720. Policy #0 lag: (min: 2.0, avg: 17.2, max: 34.0) [2023-03-09 07:38:39,060][22664] Avg episode reward: [(0, '43.517')] [2023-03-09 07:38:39,466][23090] Updated weights for policy 0, policy_version 8798 (0.0013) [2023-03-09 07:38:40,185][23090] Updated weights for policy 0, policy_version 8808 (0.0017) [2023-03-09 07:38:41,001][23090] Updated weights for policy 0, policy_version 8819 (0.0015) [2023-03-09 07:38:41,926][23090] Updated weights for policy 0, policy_version 8829 (0.0013) [2023-03-09 07:38:42,712][23090] Updated weights for policy 0, policy_version 8839 (0.0022) [2023-03-09 07:38:43,476][23090] Updated weights for policy 0, policy_version 8849 (0.0013) [2023-03-09 07:38:44,059][22664] Fps is (10 sec: 203157.7, 60 sec: 200976.9, 300 sec: 200662.1). Total num frames: 145096704. Throughput: 0: 50277.0. Samples: 36236224. Policy #0 lag: (min: 0.0, avg: 16.5, max: 33.0) [2023-03-09 07:38:44,061][22664] Avg episode reward: [(0, '42.678')] [2023-03-09 07:38:44,325][23090] Updated weights for policy 0, policy_version 8859 (0.0012) [2023-03-09 07:38:45,099][23090] Updated weights for policy 0, policy_version 8869 (0.0018) [2023-03-09 07:38:45,898][23090] Updated weights for policy 0, policy_version 8879 (0.0019) [2023-03-09 07:38:46,193][22940] Signal inference workers to stop experience collection... (3450 times) [2023-03-09 07:38:46,194][22940] Signal inference workers to resume experience collection... (3450 times) [2023-03-09 07:38:46,265][23090] InferenceWorker_p0-w0: stopping experience collection (3450 times) [2023-03-09 07:38:46,265][23090] InferenceWorker_p0-w0: resuming experience collection (3450 times) [2023-03-09 07:38:46,709][23090] Updated weights for policy 0, policy_version 8889 (0.0018) [2023-03-09 07:38:47,670][23090] Updated weights for policy 0, policy_version 8899 (0.0017) [2023-03-09 07:38:48,475][23090] Updated weights for policy 0, policy_version 8909 (0.0021) [2023-03-09 07:38:49,059][22664] Fps is (10 sec: 201518.2, 60 sec: 200704.8, 300 sec: 200606.6). Total num frames: 146096128. Throughput: 0: 50231.8. Samples: 36537216. Policy #0 lag: (min: 0.0, avg: 18.9, max: 34.0) [2023-03-09 07:38:49,061][22664] Avg episode reward: [(0, '44.554')] [2023-03-09 07:38:49,209][23090] Updated weights for policy 0, policy_version 8919 (0.0013) [2023-03-09 07:38:50,134][23090] Updated weights for policy 0, policy_version 8929 (0.0016) [2023-03-09 07:38:50,943][23090] Updated weights for policy 0, policy_version 8939 (0.0015) [2023-03-09 07:38:51,692][23090] Updated weights for policy 0, policy_version 8950 (0.0015) [2023-03-09 07:38:52,658][23090] Updated weights for policy 0, policy_version 8960 (0.0013) [2023-03-09 07:38:53,533][23090] Updated weights for policy 0, policy_version 8970 (0.0013) [2023-03-09 07:38:54,058][22664] Fps is (10 sec: 201530.8, 60 sec: 200977.1, 300 sec: 200607.0). Total num frames: 147111936. Throughput: 0: 50142.4. Samples: 36836208. Policy #0 lag: (min: 2.0, avg: 16.7, max: 33.0) [2023-03-09 07:38:54,059][22664] Avg episode reward: [(0, '42.132')] [2023-03-09 07:38:54,108][23090] Updated weights for policy 0, policy_version 8980 (0.0013) [2023-03-09 07:38:55,209][23090] Updated weights for policy 0, policy_version 8990 (0.0016) [2023-03-09 07:38:55,910][23090] Updated weights for policy 0, policy_version 9000 (0.0013) [2023-03-09 07:38:56,625][23090] Updated weights for policy 0, policy_version 9010 (0.0019) [2023-03-09 07:38:56,672][22940] Signal inference workers to stop experience collection... (3500 times) [2023-03-09 07:38:56,674][22940] Signal inference workers to resume experience collection... (3500 times) [2023-03-09 07:38:56,749][23090] InferenceWorker_p0-w0: stopping experience collection (3500 times) [2023-03-09 07:38:56,749][23090] InferenceWorker_p0-w0: resuming experience collection (3500 times) [2023-03-09 07:38:57,567][23090] Updated weights for policy 0, policy_version 9020 (0.0013) [2023-03-09 07:38:58,304][23090] Updated weights for policy 0, policy_version 9030 (0.0020) [2023-03-09 07:38:59,059][22664] Fps is (10 sec: 201528.8, 60 sec: 200977.3, 300 sec: 200551.3). Total num frames: 148111360. Throughput: 0: 50141.1. Samples: 36987696. Policy #0 lag: (min: 2.0, avg: 16.7, max: 33.0) [2023-03-09 07:38:59,060][22664] Avg episode reward: [(0, '44.841')] [2023-03-09 07:38:59,072][23090] Updated weights for policy 0, policy_version 9040 (0.0020) [2023-03-09 07:38:59,956][23090] Updated weights for policy 0, policy_version 9050 (0.0016) [2023-03-09 07:39:00,790][23090] Updated weights for policy 0, policy_version 9060 (0.0013) [2023-03-09 07:39:01,568][23090] Updated weights for policy 0, policy_version 9070 (0.0023) [2023-03-09 07:39:02,364][23090] Updated weights for policy 0, policy_version 9080 (0.0024) [2023-03-09 07:39:03,291][23090] Updated weights for policy 0, policy_version 9090 (0.0013) [2023-03-09 07:39:04,059][22664] Fps is (10 sec: 196601.9, 60 sec: 200431.1, 300 sec: 200495.7). Total num frames: 149078016. Throughput: 0: 50052.0. Samples: 37286672. Policy #0 lag: (min: 1.0, avg: 17.0, max: 33.0) [2023-03-09 07:39:04,061][22664] Avg episode reward: [(0, '41.900')] [2023-03-09 07:39:04,100][23090] Updated weights for policy 0, policy_version 9100 (0.0013) [2023-03-09 07:39:04,781][23090] Updated weights for policy 0, policy_version 9110 (0.0022) [2023-03-09 07:39:05,739][23090] Updated weights for policy 0, policy_version 9120 (0.0013) [2023-03-09 07:39:06,571][23090] Updated weights for policy 0, policy_version 9130 (0.0020) [2023-03-09 07:39:07,208][22940] Signal inference workers to stop experience collection... (3550 times) [2023-03-09 07:39:07,225][22940] Signal inference workers to resume experience collection... (3550 times) [2023-03-09 07:39:07,238][23090] Updated weights for policy 0, policy_version 9140 (0.0013) [2023-03-09 07:39:07,276][23090] InferenceWorker_p0-w0: stopping experience collection (3550 times) [2023-03-09 07:39:07,277][23090] InferenceWorker_p0-w0: resuming experience collection (3550 times) [2023-03-09 07:39:08,297][23090] Updated weights for policy 0, policy_version 9151 (0.0013) [2023-03-09 07:39:09,058][23090] Updated weights for policy 0, policy_version 9161 (0.0016) [2023-03-09 07:39:09,059][22664] Fps is (10 sec: 198236.8, 60 sec: 200702.9, 300 sec: 200551.1). Total num frames: 150093824. Throughput: 0: 50052.5. Samples: 37587664. Policy #0 lag: (min: 2.0, avg: 16.2, max: 34.0) [2023-03-09 07:39:09,060][22664] Avg episode reward: [(0, '41.416')] [2023-03-09 07:39:09,778][23090] Updated weights for policy 0, policy_version 9171 (0.0013) [2023-03-09 07:39:10,734][23090] Updated weights for policy 0, policy_version 9181 (0.0016) [2023-03-09 07:39:11,485][23090] Updated weights for policy 0, policy_version 9191 (0.0019) [2023-03-09 07:39:12,302][23090] Updated weights for policy 0, policy_version 9201 (0.0017) [2023-03-09 07:39:13,314][23090] Updated weights for policy 0, policy_version 9212 (0.0016) [2023-03-09 07:39:13,998][23090] Updated weights for policy 0, policy_version 9222 (0.0017) [2023-03-09 07:39:14,058][22664] Fps is (10 sec: 201529.2, 60 sec: 200430.9, 300 sec: 200551.3). Total num frames: 151093248. Throughput: 0: 50053.4. Samples: 37737152. Policy #0 lag: (min: 2.0, avg: 16.2, max: 34.0) [2023-03-09 07:39:14,059][22664] Avg episode reward: [(0, '42.012')] [2023-03-09 07:39:14,796][23090] Updated weights for policy 0, policy_version 9232 (0.0013) [2023-03-09 07:39:15,668][23090] Updated weights for policy 0, policy_version 9242 (0.0013) [2023-03-09 07:39:16,459][23090] Updated weights for policy 0, policy_version 9252 (0.0020) [2023-03-09 07:39:17,272][23090] Updated weights for policy 0, policy_version 9262 (0.0018) [2023-03-09 07:39:18,069][23090] Updated weights for policy 0, policy_version 9272 (0.0013) [2023-03-09 07:39:18,992][22940] Signal inference workers to stop experience collection... (3600 times) [2023-03-09 07:39:18,995][22940] Signal inference workers to resume experience collection... (3600 times) [2023-03-09 07:39:19,023][23090] Updated weights for policy 0, policy_version 9282 (0.0013) [2023-03-09 07:39:19,059][22664] Fps is (10 sec: 198254.6, 60 sec: 199885.8, 300 sec: 200495.9). Total num frames: 152076288. Throughput: 0: 50053.4. Samples: 38038112. Policy #0 lag: (min: 1.0, avg: 16.5, max: 33.0) [2023-03-09 07:39:19,059][22664] Avg episode reward: [(0, '43.347')] [2023-03-09 07:39:19,065][23090] InferenceWorker_p0-w0: stopping experience collection (3600 times) [2023-03-09 07:39:19,068][23090] InferenceWorker_p0-w0: resuming experience collection (3600 times) [2023-03-09 07:39:19,102][22940] Saving /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000009284_152109056.pth... [2023-03-09 07:39:19,162][22940] Removing /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000006347_103989248.pth [2023-03-09 07:39:19,830][23090] Updated weights for policy 0, policy_version 9292 (0.0020) [2023-03-09 07:39:20,521][23090] Updated weights for policy 0, policy_version 9302 (0.0018) [2023-03-09 07:39:21,475][23090] Updated weights for policy 0, policy_version 9312 (0.0021) [2023-03-09 07:39:22,281][23090] Updated weights for policy 0, policy_version 9322 (0.0024) [2023-03-09 07:39:22,947][23090] Updated weights for policy 0, policy_version 9332 (0.0018) [2023-03-09 07:39:23,962][23090] Updated weights for policy 0, policy_version 9342 (0.0016) [2023-03-09 07:39:24,059][22664] Fps is (10 sec: 198241.0, 60 sec: 200158.4, 300 sec: 200495.8). Total num frames: 153075712. Throughput: 0: 50007.6. Samples: 38337072. Policy #0 lag: (min: 0.0, avg: 17.9, max: 33.0) [2023-03-09 07:39:24,061][22664] Avg episode reward: [(0, '45.395')] [2023-03-09 07:39:24,702][23090] Updated weights for policy 0, policy_version 9352 (0.0016) [2023-03-09 07:39:25,475][23090] Updated weights for policy 0, policy_version 9362 (0.0016) [2023-03-09 07:39:26,381][23090] Updated weights for policy 0, policy_version 9372 (0.0013) [2023-03-09 07:39:27,110][23090] Updated weights for policy 0, policy_version 9382 (0.0017) [2023-03-09 07:39:27,906][23090] Updated weights for policy 0, policy_version 9392 (0.0013) [2023-03-09 07:39:28,793][23090] Updated weights for policy 0, policy_version 9402 (0.0019) [2023-03-09 07:39:29,059][22664] Fps is (10 sec: 199885.2, 60 sec: 200157.8, 300 sec: 200495.8). Total num frames: 154075136. Throughput: 0: 50053.3. Samples: 38488608. Policy #0 lag: (min: 0.0, avg: 17.9, max: 33.0) [2023-03-09 07:39:29,060][22664] Avg episode reward: [(0, '45.340')] [2023-03-09 07:39:29,206][22940] Signal inference workers to stop experience collection... (3650 times) [2023-03-09 07:39:29,206][22940] Signal inference workers to resume experience collection... (3650 times) [2023-03-09 07:39:29,269][23090] InferenceWorker_p0-w0: stopping experience collection (3650 times) [2023-03-09 07:39:29,269][23090] InferenceWorker_p0-w0: resuming experience collection (3650 times) [2023-03-09 07:39:29,616][23090] Updated weights for policy 0, policy_version 9412 (0.0019) [2023-03-09 07:39:30,424][23090] Updated weights for policy 0, policy_version 9422 (0.0025) [2023-03-09 07:39:31,187][23090] Updated weights for policy 0, policy_version 9432 (0.0013) [2023-03-09 07:39:32,134][23090] Updated weights for policy 0, policy_version 9442 (0.0015) [2023-03-09 07:39:32,961][23090] Updated weights for policy 0, policy_version 9452 (0.0024) [2023-03-09 07:39:33,620][23090] Updated weights for policy 0, policy_version 9462 (0.0016) [2023-03-09 07:39:34,059][22664] Fps is (10 sec: 199885.8, 60 sec: 200157.7, 300 sec: 200495.6). Total num frames: 155074560. Throughput: 0: 49962.1. Samples: 38785504. Policy #0 lag: (min: 1.0, avg: 17.5, max: 33.0) [2023-03-09 07:39:34,061][22664] Avg episode reward: [(0, '43.280')] [2023-03-09 07:39:34,569][23090] Updated weights for policy 0, policy_version 9472 (0.0017) [2023-03-09 07:39:35,378][23090] Updated weights for policy 0, policy_version 9482 (0.0022) [2023-03-09 07:39:36,055][23090] Updated weights for policy 0, policy_version 9492 (0.0018) [2023-03-09 07:39:37,054][23090] Updated weights for policy 0, policy_version 9502 (0.0020) [2023-03-09 07:39:37,781][23090] Updated weights for policy 0, policy_version 9512 (0.0017) [2023-03-09 07:39:38,552][23090] Updated weights for policy 0, policy_version 9522 (0.0013) [2023-03-09 07:39:38,624][22940] Signal inference workers to stop experience collection... (3700 times) [2023-03-09 07:39:38,649][22940] Signal inference workers to resume experience collection... (3700 times) [2023-03-09 07:39:38,698][23090] InferenceWorker_p0-w0: stopping experience collection (3700 times) [2023-03-09 07:39:38,699][23090] InferenceWorker_p0-w0: resuming experience collection (3700 times) [2023-03-09 07:39:39,059][22664] Fps is (10 sec: 203156.1, 60 sec: 200430.0, 300 sec: 200606.6). Total num frames: 156106752. Throughput: 0: 50051.5. Samples: 39088544. Policy #0 lag: (min: 2.0, avg: 17.6, max: 34.0) [2023-03-09 07:39:39,061][22664] Avg episode reward: [(0, '43.978')] [2023-03-09 07:39:39,540][23090] Updated weights for policy 0, policy_version 9533 (0.0015) [2023-03-09 07:39:40,297][23090] Updated weights for policy 0, policy_version 9543 (0.0013) [2023-03-09 07:39:41,055][23090] Updated weights for policy 0, policy_version 9553 (0.0015) [2023-03-09 07:39:42,082][23090] Updated weights for policy 0, policy_version 9564 (0.0017) [2023-03-09 07:39:42,809][23090] Updated weights for policy 0, policy_version 9574 (0.0014) [2023-03-09 07:39:43,578][23090] Updated weights for policy 0, policy_version 9584 (0.0013) [2023-03-09 07:39:44,058][22664] Fps is (10 sec: 204805.0, 60 sec: 200432.2, 300 sec: 200606.9). Total num frames: 157122560. Throughput: 0: 50053.0. Samples: 39240080. Policy #0 lag: (min: 2.0, avg: 17.6, max: 34.0) [2023-03-09 07:39:44,060][22664] Avg episode reward: [(0, '44.373')] [2023-03-09 07:39:44,462][23090] Updated weights for policy 0, policy_version 9594 (0.0013) [2023-03-09 07:39:45,298][23090] Updated weights for policy 0, policy_version 9604 (0.0017) [2023-03-09 07:39:46,095][23090] Updated weights for policy 0, policy_version 9615 (0.0019) [2023-03-09 07:39:46,891][23090] Updated weights for policy 0, policy_version 9625 (0.0011) [2023-03-09 07:39:47,853][23090] Updated weights for policy 0, policy_version 9635 (0.0014) [2023-03-09 07:39:48,631][23090] Updated weights for policy 0, policy_version 9645 (0.0018) [2023-03-09 07:39:49,059][22664] Fps is (10 sec: 201524.3, 60 sec: 200431.0, 300 sec: 200495.5). Total num frames: 158121984. Throughput: 0: 50097.4. Samples: 39541056. Policy #0 lag: (min: 1.0, avg: 16.5, max: 33.0) [2023-03-09 07:39:49,060][22664] Avg episode reward: [(0, '44.474')] [2023-03-09 07:39:49,358][23090] Updated weights for policy 0, policy_version 9655 (0.0017) [2023-03-09 07:39:50,120][22940] Signal inference workers to stop experience collection... (3750 times) [2023-03-09 07:39:50,120][22940] Signal inference workers to resume experience collection... (3750 times) [2023-03-09 07:39:50,190][23090] InferenceWorker_p0-w0: stopping experience collection (3750 times) [2023-03-09 07:39:50,190][23090] InferenceWorker_p0-w0: resuming experience collection (3750 times) [2023-03-09 07:39:50,315][23090] Updated weights for policy 0, policy_version 9665 (0.0013) [2023-03-09 07:39:51,124][23090] Updated weights for policy 0, policy_version 9675 (0.0018) [2023-03-09 07:39:51,811][23090] Updated weights for policy 0, policy_version 9685 (0.0016) [2023-03-09 07:39:52,841][23090] Updated weights for policy 0, policy_version 9695 (0.0015) [2023-03-09 07:39:53,604][23090] Updated weights for policy 0, policy_version 9705 (0.0020) [2023-03-09 07:39:54,059][22664] Fps is (10 sec: 199879.6, 60 sec: 200157.0, 300 sec: 200440.2). Total num frames: 159121408. Throughput: 0: 50051.5. Samples: 39839968. Policy #0 lag: (min: 0.0, avg: 16.2, max: 32.0) [2023-03-09 07:39:54,061][22664] Avg episode reward: [(0, '47.015')] [2023-03-09 07:39:54,363][23090] Updated weights for policy 0, policy_version 9715 (0.0024) [2023-03-09 07:39:55,251][23090] Updated weights for policy 0, policy_version 9725 (0.0013) [2023-03-09 07:39:56,026][23090] Updated weights for policy 0, policy_version 9735 (0.0013) [2023-03-09 07:39:56,923][23090] Updated weights for policy 0, policy_version 9746 (0.0016) [2023-03-09 07:39:57,826][23090] Updated weights for policy 0, policy_version 9756 (0.0016) [2023-03-09 07:39:58,567][23090] Updated weights for policy 0, policy_version 9766 (0.0018) [2023-03-09 07:39:59,059][22664] Fps is (10 sec: 194969.9, 60 sec: 199337.8, 300 sec: 200273.4). Total num frames: 160071680. Throughput: 0: 50004.3. Samples: 39987360. Policy #0 lag: (min: 0.0, avg: 16.2, max: 32.0) [2023-03-09 07:39:59,061][22664] Avg episode reward: [(0, '49.589')] [2023-03-09 07:39:59,135][22940] Saving new best policy, reward=49.589! [2023-03-09 07:39:59,411][23090] Updated weights for policy 0, policy_version 9776 (0.0015) [2023-03-09 07:40:00,287][23090] Updated weights for policy 0, policy_version 9786 (0.0023) [2023-03-09 07:40:00,726][22940] Signal inference workers to stop experience collection... (3800 times) [2023-03-09 07:40:00,739][22940] Signal inference workers to resume experience collection... (3800 times) [2023-03-09 07:40:00,784][23090] InferenceWorker_p0-w0: stopping experience collection (3800 times) [2023-03-09 07:40:00,784][23090] InferenceWorker_p0-w0: resuming experience collection (3800 times) [2023-03-09 07:40:01,189][23090] Updated weights for policy 0, policy_version 9797 (0.0020) [2023-03-09 07:40:02,057][23090] Updated weights for policy 0, policy_version 9808 (0.0020) [2023-03-09 07:40:02,900][23090] Updated weights for policy 0, policy_version 9818 (0.0016) [2023-03-09 07:40:03,717][23090] Updated weights for policy 0, policy_version 9828 (0.0024) [2023-03-09 07:40:04,059][22664] Fps is (10 sec: 196608.9, 60 sec: 200158.2, 300 sec: 200329.1). Total num frames: 161087488. Throughput: 0: 49960.1. Samples: 40286320. Policy #0 lag: (min: 0.0, avg: 17.1, max: 33.0) [2023-03-09 07:40:04,060][22664] Avg episode reward: [(0, '43.651')] [2023-03-09 07:40:04,497][23090] Updated weights for policy 0, policy_version 9838 (0.0014) [2023-03-09 07:40:05,322][23090] Updated weights for policy 0, policy_version 9848 (0.0013) [2023-03-09 07:40:06,245][23090] Updated weights for policy 0, policy_version 9858 (0.0017) [2023-03-09 07:40:07,016][23090] Updated weights for policy 0, policy_version 9868 (0.0013) [2023-03-09 07:40:07,693][23090] Updated weights for policy 0, policy_version 9878 (0.0019) [2023-03-09 07:40:08,707][23090] Updated weights for policy 0, policy_version 9888 (0.0017) [2023-03-09 07:40:09,059][22664] Fps is (10 sec: 201522.6, 60 sec: 199885.5, 300 sec: 200329.1). Total num frames: 162086912. Throughput: 0: 50004.9. Samples: 40587296. Policy #0 lag: (min: 0.0, avg: 17.1, max: 33.0) [2023-03-09 07:40:09,060][22664] Avg episode reward: [(0, '45.070')] [2023-03-09 07:40:09,471][23090] Updated weights for policy 0, policy_version 9898 (0.0018) [2023-03-09 07:40:10,168][23090] Updated weights for policy 0, policy_version 9908 (0.0013) [2023-03-09 07:40:11,136][23090] Updated weights for policy 0, policy_version 9918 (0.0017) [2023-03-09 07:40:11,570][22940] Signal inference workers to stop experience collection... (3850 times) [2023-03-09 07:40:11,571][22940] Signal inference workers to resume experience collection... (3850 times) [2023-03-09 07:40:11,635][23090] InferenceWorker_p0-w0: stopping experience collection (3850 times) [2023-03-09 07:40:11,635][23090] InferenceWorker_p0-w0: resuming experience collection (3850 times) [2023-03-09 07:40:11,882][23090] Updated weights for policy 0, policy_version 9928 (0.0022) [2023-03-09 07:40:12,658][23090] Updated weights for policy 0, policy_version 9938 (0.0013) [2023-03-09 07:40:13,553][23090] Updated weights for policy 0, policy_version 9948 (0.0013) [2023-03-09 07:40:14,058][22664] Fps is (10 sec: 199888.6, 60 sec: 199884.8, 300 sec: 200329.2). Total num frames: 163086336. Throughput: 0: 49958.5. Samples: 40736736. Policy #0 lag: (min: 0.0, avg: 17.0, max: 33.0) [2023-03-09 07:40:14,059][22664] Avg episode reward: [(0, '44.894')] [2023-03-09 07:40:14,279][23090] Updated weights for policy 0, policy_version 9958 (0.0020) [2023-03-09 07:40:15,110][23090] Updated weights for policy 0, policy_version 9968 (0.0020) [2023-03-09 07:40:16,017][23090] Updated weights for policy 0, policy_version 9978 (0.0012) [2023-03-09 07:40:16,787][23090] Updated weights for policy 0, policy_version 9988 (0.0021) [2023-03-09 07:40:17,561][23090] Updated weights for policy 0, policy_version 9998 (0.0015) [2023-03-09 07:40:18,417][23090] Updated weights for policy 0, policy_version 10008 (0.0020) [2023-03-09 07:40:19,059][22664] Fps is (10 sec: 199883.5, 60 sec: 200156.9, 300 sec: 200495.7). Total num frames: 164085760. Throughput: 0: 50050.3. Samples: 41037776. Policy #0 lag: (min: 0.0, avg: 17.0, max: 33.0) [2023-03-09 07:40:19,061][22664] Avg episode reward: [(0, '47.223')] [2023-03-09 07:40:19,299][23090] Updated weights for policy 0, policy_version 10018 (0.0016) [2023-03-09 07:40:20,072][23090] Updated weights for policy 0, policy_version 10028 (0.0012) [2023-03-09 07:40:20,699][23090] Updated weights for policy 0, policy_version 10038 (0.0019) [2023-03-09 07:40:21,722][23090] Updated weights for policy 0, policy_version 10048 (0.0016) [2023-03-09 07:40:22,527][22940] Signal inference workers to stop experience collection... (3900 times) [2023-03-09 07:40:22,528][22940] Signal inference workers to resume experience collection... (3900 times) [2023-03-09 07:40:22,547][23090] Updated weights for policy 0, policy_version 10058 (0.0015) [2023-03-09 07:40:22,583][23090] InferenceWorker_p0-w0: stopping experience collection (3900 times) [2023-03-09 07:40:22,583][23090] InferenceWorker_p0-w0: resuming experience collection (3900 times) [2023-03-09 07:40:23,200][23090] Updated weights for policy 0, policy_version 10068 (0.0017) [2023-03-09 07:40:24,059][22664] Fps is (10 sec: 201509.7, 60 sec: 200429.6, 300 sec: 200606.4). Total num frames: 165101568. Throughput: 0: 50047.6. Samples: 41340704. Policy #0 lag: (min: 0.0, avg: 17.0, max: 33.0) [2023-03-09 07:40:24,061][22664] Avg episode reward: [(0, '43.316')] [2023-03-09 07:40:24,232][23090] Updated weights for policy 0, policy_version 10078 (0.0013) [2023-03-09 07:40:24,943][23090] Updated weights for policy 0, policy_version 10088 (0.0015) [2023-03-09 07:40:25,681][23090] Updated weights for policy 0, policy_version 10098 (0.0013) [2023-03-09 07:40:26,570][23090] Updated weights for policy 0, policy_version 10108 (0.0012) [2023-03-09 07:40:27,367][23090] Updated weights for policy 0, policy_version 10118 (0.0019) [2023-03-09 07:40:28,125][23090] Updated weights for policy 0, policy_version 10128 (0.0013) [2023-03-09 07:40:29,047][23090] Updated weights for policy 0, policy_version 10138 (0.0019) [2023-03-09 07:40:29,059][22664] Fps is (10 sec: 203157.2, 60 sec: 200702.3, 300 sec: 200662.0). Total num frames: 166117376. Throughput: 0: 50047.0. Samples: 41492224. Policy #0 lag: (min: 0.0, avg: 16.5, max: 33.0) [2023-03-09 07:40:29,061][22664] Avg episode reward: [(0, '46.683')] [2023-03-09 07:40:29,845][23090] Updated weights for policy 0, policy_version 10148 (0.0026) [2023-03-09 07:40:30,614][23090] Updated weights for policy 0, policy_version 10158 (0.0013) [2023-03-09 07:40:31,399][23090] Updated weights for policy 0, policy_version 10168 (0.0025) [2023-03-09 07:40:32,093][22940] Signal inference workers to stop experience collection... (3950 times) [2023-03-09 07:40:32,094][22940] Signal inference workers to resume experience collection... (3950 times) [2023-03-09 07:40:32,157][23090] InferenceWorker_p0-w0: stopping experience collection (3950 times) [2023-03-09 07:40:32,157][23090] InferenceWorker_p0-w0: resuming experience collection (3950 times) [2023-03-09 07:40:32,286][23090] Updated weights for policy 0, policy_version 10178 (0.0020) [2023-03-09 07:40:33,159][23090] Updated weights for policy 0, policy_version 10189 (0.0013) [2023-03-09 07:40:33,877][23090] Updated weights for policy 0, policy_version 10199 (0.0013) [2023-03-09 07:40:34,059][22664] Fps is (10 sec: 201535.6, 60 sec: 200704.6, 300 sec: 200662.3). Total num frames: 167116800. Throughput: 0: 50046.9. Samples: 41793152. Policy #0 lag: (min: 0.0, avg: 16.1, max: 33.0) [2023-03-09 07:40:34,060][22664] Avg episode reward: [(0, '46.677')] [2023-03-09 07:40:34,942][23090] Updated weights for policy 0, policy_version 10210 (0.0015) [2023-03-09 07:40:35,694][23090] Updated weights for policy 0, policy_version 10220 (0.0013) [2023-03-09 07:40:36,333][23090] Updated weights for policy 0, policy_version 10230 (0.0013) [2023-03-09 07:40:37,357][23090] Updated weights for policy 0, policy_version 10240 (0.0018) [2023-03-09 07:40:38,193][23090] Updated weights for policy 0, policy_version 10250 (0.0013) [2023-03-09 07:40:38,861][23090] Updated weights for policy 0, policy_version 10260 (0.0028) [2023-03-09 07:40:39,059][22664] Fps is (10 sec: 201530.2, 60 sec: 200431.3, 300 sec: 200606.9). Total num frames: 168132608. Throughput: 0: 50093.5. Samples: 42094176. Policy #0 lag: (min: 0.0, avg: 16.1, max: 33.0) [2023-03-09 07:40:39,060][22664] Avg episode reward: [(0, '45.252')] [2023-03-09 07:40:39,879][23090] Updated weights for policy 0, policy_version 10270 (0.0017) [2023-03-09 07:40:40,612][23090] Updated weights for policy 0, policy_version 10280 (0.0019) [2023-03-09 07:40:41,276][22940] Signal inference workers to stop experience collection... (4000 times) [2023-03-09 07:40:41,278][22940] Signal inference workers to resume experience collection... (4000 times) [2023-03-09 07:40:41,344][23090] InferenceWorker_p0-w0: stopping experience collection (4000 times) [2023-03-09 07:40:41,344][23090] InferenceWorker_p0-w0: resuming experience collection (4000 times) [2023-03-09 07:40:41,346][23090] Updated weights for policy 0, policy_version 10290 (0.0016) [2023-03-09 07:40:42,213][23090] Updated weights for policy 0, policy_version 10300 (0.0020) [2023-03-09 07:40:42,969][23090] Updated weights for policy 0, policy_version 10310 (0.0019) [2023-03-09 07:40:43,746][23090] Updated weights for policy 0, policy_version 10320 (0.0013) [2023-03-09 07:40:44,058][22664] Fps is (10 sec: 203162.7, 60 sec: 200430.9, 300 sec: 200662.4). Total num frames: 169148416. Throughput: 0: 50185.2. Samples: 42245680. Policy #0 lag: (min: 3.0, avg: 17.0, max: 33.0) [2023-03-09 07:40:44,059][22664] Avg episode reward: [(0, '44.421')] [2023-03-09 07:40:44,724][23090] Updated weights for policy 0, policy_version 10330 (0.0017) [2023-03-09 07:40:45,466][23090] Updated weights for policy 0, policy_version 10340 (0.0013) [2023-03-09 07:40:46,278][23090] Updated weights for policy 0, policy_version 10350 (0.0016) [2023-03-09 07:40:47,031][23090] Updated weights for policy 0, policy_version 10360 (0.0020) [2023-03-09 07:40:47,929][23090] Updated weights for policy 0, policy_version 10370 (0.0014) [2023-03-09 07:40:48,740][23090] Updated weights for policy 0, policy_version 10380 (0.0018) [2023-03-09 07:40:49,059][22664] Fps is (10 sec: 199882.7, 60 sec: 200157.7, 300 sec: 200551.1). Total num frames: 170131456. Throughput: 0: 50230.6. Samples: 42546704. Policy #0 lag: (min: 3.0, avg: 17.0, max: 33.0) [2023-03-09 07:40:49,061][22664] Avg episode reward: [(0, '46.386')] [2023-03-09 07:40:49,404][23090] Updated weights for policy 0, policy_version 10390 (0.0015) [2023-03-09 07:40:50,393][23090] Updated weights for policy 0, policy_version 10400 (0.0015) [2023-03-09 07:40:51,255][23090] Updated weights for policy 0, policy_version 10410 (0.0012) [2023-03-09 07:40:51,302][22940] Signal inference workers to stop experience collection... (4050 times) [2023-03-09 07:40:51,337][22940] Signal inference workers to resume experience collection... (4050 times) [2023-03-09 07:40:51,378][23090] InferenceWorker_p0-w0: stopping experience collection (4050 times) [2023-03-09 07:40:51,419][23090] InferenceWorker_p0-w0: resuming experience collection (4050 times) [2023-03-09 07:40:51,871][23090] Updated weights for policy 0, policy_version 10420 (0.0021) [2023-03-09 07:40:52,847][23090] Updated weights for policy 0, policy_version 10430 (0.0013) [2023-03-09 07:40:53,619][23090] Updated weights for policy 0, policy_version 10440 (0.0020) [2023-03-09 07:40:54,058][22664] Fps is (10 sec: 199885.1, 60 sec: 200431.8, 300 sec: 200662.4). Total num frames: 171147264. Throughput: 0: 50276.3. Samples: 42849712. Policy #0 lag: (min: 1.0, avg: 17.3, max: 33.0) [2023-03-09 07:40:54,059][22664] Avg episode reward: [(0, '45.228')] [2023-03-09 07:40:54,354][23090] Updated weights for policy 0, policy_version 10450 (0.0016) [2023-03-09 07:40:55,339][23090] Updated weights for policy 0, policy_version 10461 (0.0014) [2023-03-09 07:40:56,127][23090] Updated weights for policy 0, policy_version 10471 (0.0016) [2023-03-09 07:40:56,947][23090] Updated weights for policy 0, policy_version 10481 (0.0020) [2023-03-09 07:40:57,895][23090] Updated weights for policy 0, policy_version 10492 (0.0013) [2023-03-09 07:40:58,615][23090] Updated weights for policy 0, policy_version 10502 (0.0018) [2023-03-09 07:40:59,059][22664] Fps is (10 sec: 199882.8, 60 sec: 200976.5, 300 sec: 200606.7). Total num frames: 172130304. Throughput: 0: 50275.8. Samples: 42999168. Policy #0 lag: (min: 1.0, avg: 18.6, max: 33.0) [2023-03-09 07:40:59,062][22664] Avg episode reward: [(0, '45.654')] [2023-03-09 07:40:59,439][23090] Updated weights for policy 0, policy_version 10512 (0.0020) [2023-03-09 07:41:00,344][23090] Updated weights for policy 0, policy_version 10522 (0.0015) [2023-03-09 07:41:01,145][23090] Updated weights for policy 0, policy_version 10532 (0.0013) [2023-03-09 07:41:01,183][22940] Signal inference workers to stop experience collection... (4100 times) [2023-03-09 07:41:01,189][22940] Signal inference workers to resume experience collection... (4100 times) [2023-03-09 07:41:01,267][23090] InferenceWorker_p0-w0: stopping experience collection (4100 times) [2023-03-09 07:41:01,267][23090] InferenceWorker_p0-w0: resuming experience collection (4100 times) [2023-03-09 07:41:01,911][23090] Updated weights for policy 0, policy_version 10542 (0.0019) [2023-03-09 07:41:02,705][23090] Updated weights for policy 0, policy_version 10552 (0.0013) [2023-03-09 07:41:03,579][23090] Updated weights for policy 0, policy_version 10562 (0.0016) [2023-03-09 07:41:04,059][22664] Fps is (10 sec: 198243.1, 60 sec: 200704.1, 300 sec: 200606.9). Total num frames: 173129728. Throughput: 0: 50276.2. Samples: 43300192. Policy #0 lag: (min: 1.0, avg: 18.6, max: 33.0) [2023-03-09 07:41:04,060][22664] Avg episode reward: [(0, '49.772')] [2023-03-09 07:41:04,088][22940] Saving new best policy, reward=49.772! [2023-03-09 07:41:04,448][23090] Updated weights for policy 0, policy_version 10572 (0.0017) [2023-03-09 07:41:05,062][23090] Updated weights for policy 0, policy_version 10582 (0.0019) [2023-03-09 07:41:06,062][23090] Updated weights for policy 0, policy_version 10592 (0.0013) [2023-03-09 07:41:06,936][23090] Updated weights for policy 0, policy_version 10602 (0.0013) [2023-03-09 07:41:07,558][23090] Updated weights for policy 0, policy_version 10612 (0.0013) [2023-03-09 07:41:08,572][23090] Updated weights for policy 0, policy_version 10622 (0.0013) [2023-03-09 07:41:09,058][22664] Fps is (10 sec: 201531.9, 60 sec: 200978.1, 300 sec: 200662.8). Total num frames: 174145536. Throughput: 0: 50233.6. Samples: 43601184. Policy #0 lag: (min: 0.0, avg: 16.8, max: 33.0) [2023-03-09 07:41:09,060][22664] Avg episode reward: [(0, '49.704')] [2023-03-09 07:41:09,315][23090] Updated weights for policy 0, policy_version 10632 (0.0025) [2023-03-09 07:41:10,102][23090] Updated weights for policy 0, policy_version 10642 (0.0024) [2023-03-09 07:41:10,787][22940] Signal inference workers to stop experience collection... (4150 times) [2023-03-09 07:41:10,787][22940] Signal inference workers to resume experience collection... (4150 times) [2023-03-09 07:41:10,871][23090] InferenceWorker_p0-w0: stopping experience collection (4150 times) [2023-03-09 07:41:10,871][23090] InferenceWorker_p0-w0: resuming experience collection (4150 times) [2023-03-09 07:41:10,957][23090] Updated weights for policy 0, policy_version 10652 (0.0013) [2023-03-09 07:41:11,723][23090] Updated weights for policy 0, policy_version 10662 (0.0021) [2023-03-09 07:41:12,659][23090] Updated weights for policy 0, policy_version 10673 (0.0020) [2023-03-09 07:41:13,492][23090] Updated weights for policy 0, policy_version 10683 (0.0013) [2023-03-09 07:41:14,059][22664] Fps is (10 sec: 201520.5, 60 sec: 200976.1, 300 sec: 200662.2). Total num frames: 175144960. Throughput: 0: 50187.0. Samples: 43750624. Policy #0 lag: (min: 0.0, avg: 15.9, max: 33.0) [2023-03-09 07:41:14,061][22664] Avg episode reward: [(0, '46.203')] [2023-03-09 07:41:14,305][23090] Updated weights for policy 0, policy_version 10693 (0.0013) [2023-03-09 07:41:15,100][23090] Updated weights for policy 0, policy_version 10703 (0.0013) [2023-03-09 07:41:15,894][23090] Updated weights for policy 0, policy_version 10713 (0.0015) [2023-03-09 07:41:16,776][23090] Updated weights for policy 0, policy_version 10723 (0.0025) [2023-03-09 07:41:17,628][23090] Updated weights for policy 0, policy_version 10733 (0.0019) [2023-03-09 07:41:18,295][23090] Updated weights for policy 0, policy_version 10743 (0.0016) [2023-03-09 07:41:19,058][22664] Fps is (10 sec: 196608.2, 60 sec: 200432.2, 300 sec: 200606.8). Total num frames: 176111616. Throughput: 0: 50188.1. Samples: 44051616. Policy #0 lag: (min: 0.0, avg: 15.9, max: 33.0) [2023-03-09 07:41:19,059][22664] Avg episode reward: [(0, '45.195')] [2023-03-09 07:41:19,080][22940] Saving /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000010750_176128000.pth... [2023-03-09 07:41:19,140][22940] Removing /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000007814_128024576.pth [2023-03-09 07:41:19,394][23090] Updated weights for policy 0, policy_version 10754 (0.0015) [2023-03-09 07:41:20,271][23090] Updated weights for policy 0, policy_version 10765 (0.0013) [2023-03-09 07:41:20,575][22940] Signal inference workers to stop experience collection... (4200 times) [2023-03-09 07:41:20,575][22940] Signal inference workers to resume experience collection... (4200 times) [2023-03-09 07:41:20,642][23090] InferenceWorker_p0-w0: stopping experience collection (4200 times) [2023-03-09 07:41:20,642][23090] InferenceWorker_p0-w0: resuming experience collection (4200 times) [2023-03-09 07:41:21,018][23090] Updated weights for policy 0, policy_version 10775 (0.0013) [2023-03-09 07:41:21,973][23090] Updated weights for policy 0, policy_version 10785 (0.0018) [2023-03-09 07:41:22,783][23090] Updated weights for policy 0, policy_version 10795 (0.0013) [2023-03-09 07:41:23,439][23090] Updated weights for policy 0, policy_version 10805 (0.0014) [2023-03-09 07:41:24,059][22664] Fps is (10 sec: 198250.4, 60 sec: 200432.9, 300 sec: 200662.8). Total num frames: 177127424. Throughput: 0: 50050.7. Samples: 44346448. Policy #0 lag: (min: 1.0, avg: 16.3, max: 33.0) [2023-03-09 07:41:24,060][22664] Avg episode reward: [(0, '48.175')] [2023-03-09 07:41:24,507][23090] Updated weights for policy 0, policy_version 10815 (0.0016) [2023-03-09 07:41:25,270][23090] Updated weights for policy 0, policy_version 10825 (0.0016) [2023-03-09 07:41:25,972][23090] Updated weights for policy 0, policy_version 10835 (0.0013) [2023-03-09 07:41:26,871][23090] Updated weights for policy 0, policy_version 10845 (0.0018) [2023-03-09 07:41:27,634][23090] Updated weights for policy 0, policy_version 10855 (0.0017) [2023-03-09 07:41:28,430][23090] Updated weights for policy 0, policy_version 10865 (0.0013) [2023-03-09 07:41:29,059][22664] Fps is (10 sec: 203159.0, 60 sec: 200432.5, 300 sec: 200717.8). Total num frames: 178143232. Throughput: 0: 50005.9. Samples: 44495952. Policy #0 lag: (min: 1.0, avg: 16.3, max: 33.0) [2023-03-09 07:41:29,060][22664] Avg episode reward: [(0, '48.737')] [2023-03-09 07:41:29,375][23090] Updated weights for policy 0, policy_version 10876 (0.0015) [2023-03-09 07:41:30,135][23090] Updated weights for policy 0, policy_version 10886 (0.0016) [2023-03-09 07:41:30,904][23090] Updated weights for policy 0, policy_version 10896 (0.0015) [2023-03-09 07:41:31,110][22940] Signal inference workers to stop experience collection... (4250 times) [2023-03-09 07:41:31,111][22940] Signal inference workers to resume experience collection... (4250 times) [2023-03-09 07:41:31,186][23090] InferenceWorker_p0-w0: stopping experience collection (4250 times) [2023-03-09 07:41:31,186][23090] InferenceWorker_p0-w0: resuming experience collection (4250 times) [2023-03-09 07:41:31,786][23090] Updated weights for policy 0, policy_version 10906 (0.0013) [2023-03-09 07:41:32,612][23090] Updated weights for policy 0, policy_version 10916 (0.0018) [2023-03-09 07:41:33,458][23090] Updated weights for policy 0, policy_version 10927 (0.0016) [2023-03-09 07:41:34,059][22664] Fps is (10 sec: 201522.6, 60 sec: 200430.7, 300 sec: 200606.8). Total num frames: 179142656. Throughput: 0: 50049.7. Samples: 44798928. Policy #0 lag: (min: 1.0, avg: 15.9, max: 32.0) [2023-03-09 07:41:34,060][22664] Avg episode reward: [(0, '48.182')] [2023-03-09 07:41:34,272][23090] Updated weights for policy 0, policy_version 10937 (0.0013) [2023-03-09 07:41:35,136][23090] Updated weights for policy 0, policy_version 10947 (0.0019) [2023-03-09 07:41:35,970][23090] Updated weights for policy 0, policy_version 10957 (0.0020) [2023-03-09 07:41:36,659][23090] Updated weights for policy 0, policy_version 10967 (0.0019) [2023-03-09 07:41:37,608][23090] Updated weights for policy 0, policy_version 10977 (0.0013) [2023-03-09 07:41:38,486][23090] Updated weights for policy 0, policy_version 10987 (0.0019) [2023-03-09 07:41:39,056][23090] Updated weights for policy 0, policy_version 10997 (0.0017) [2023-03-09 07:41:39,059][22664] Fps is (10 sec: 203159.1, 60 sec: 200703.9, 300 sec: 200662.2). Total num frames: 180174848. Throughput: 0: 50004.7. Samples: 45099936. Policy #0 lag: (min: 2.0, avg: 18.6, max: 34.0) [2023-03-09 07:41:39,062][22664] Avg episode reward: [(0, '46.549')] [2023-03-09 07:41:40,110][23090] Updated weights for policy 0, policy_version 11007 (0.0016) [2023-03-09 07:41:40,838][23090] Updated weights for policy 0, policy_version 11017 (0.0014) [2023-03-09 07:41:41,637][23090] Updated weights for policy 0, policy_version 11028 (0.0016) [2023-03-09 07:41:42,669][23090] Updated weights for policy 0, policy_version 11038 (0.0018) [2023-03-09 07:41:43,407][23090] Updated weights for policy 0, policy_version 11048 (0.0016) [2023-03-09 07:41:43,667][22940] Signal inference workers to stop experience collection... (4300 times) [2023-03-09 07:41:43,669][22940] Signal inference workers to resume experience collection... (4300 times) [2023-03-09 07:41:43,734][23090] InferenceWorker_p0-w0: stopping experience collection (4300 times) [2023-03-09 07:41:43,737][23090] InferenceWorker_p0-w0: resuming experience collection (4300 times) [2023-03-09 07:41:44,059][22664] Fps is (10 sec: 201524.7, 60 sec: 200157.7, 300 sec: 200551.5). Total num frames: 181157888. Throughput: 0: 50006.2. Samples: 45249424. Policy #0 lag: (min: 2.0, avg: 18.6, max: 34.0) [2023-03-09 07:41:44,060][22664] Avg episode reward: [(0, '45.557')] [2023-03-09 07:41:44,115][23090] Updated weights for policy 0, policy_version 11058 (0.0019) [2023-03-09 07:41:45,013][23090] Updated weights for policy 0, policy_version 11068 (0.0016) [2023-03-09 07:41:45,771][23090] Updated weights for policy 0, policy_version 11078 (0.0018) [2023-03-09 07:41:46,532][23090] Updated weights for policy 0, policy_version 11088 (0.0017) [2023-03-09 07:41:47,488][23090] Updated weights for policy 0, policy_version 11098 (0.0015) [2023-03-09 07:41:48,256][23090] Updated weights for policy 0, policy_version 11108 (0.0019) [2023-03-09 07:41:49,052][23090] Updated weights for policy 0, policy_version 11118 (0.0017) [2023-03-09 07:41:49,059][22664] Fps is (10 sec: 198244.3, 60 sec: 200430.9, 300 sec: 200551.2). Total num frames: 182157312. Throughput: 0: 50049.9. Samples: 45552448. Policy #0 lag: (min: 0.0, avg: 16.7, max: 32.0) [2023-03-09 07:41:49,061][22664] Avg episode reward: [(0, '48.363')] [2023-03-09 07:41:49,859][23090] Updated weights for policy 0, policy_version 11128 (0.0017) [2023-03-09 07:41:50,748][23090] Updated weights for policy 0, policy_version 11138 (0.0025) [2023-03-09 07:41:51,604][23090] Updated weights for policy 0, policy_version 11148 (0.0022) [2023-03-09 07:41:52,223][23090] Updated weights for policy 0, policy_version 11158 (0.0015) [2023-03-09 07:41:53,233][23090] Updated weights for policy 0, policy_version 11168 (0.0019) [2023-03-09 07:41:54,026][23090] Updated weights for policy 0, policy_version 11178 (0.0012) [2023-03-09 07:41:54,059][22664] Fps is (10 sec: 198245.9, 60 sec: 199884.5, 300 sec: 200495.7). Total num frames: 183140352. Throughput: 0: 50049.4. Samples: 45853408. Policy #0 lag: (min: 0.0, avg: 16.7, max: 32.0) [2023-03-09 07:41:54,060][22664] Avg episode reward: [(0, '48.217')] [2023-03-09 07:41:54,147][22940] Signal inference workers to stop experience collection... (4350 times) [2023-03-09 07:41:54,172][22940] Signal inference workers to resume experience collection... (4350 times) [2023-03-09 07:41:54,226][23090] InferenceWorker_p0-w0: stopping experience collection (4350 times) [2023-03-09 07:41:54,226][23090] InferenceWorker_p0-w0: resuming experience collection (4350 times) [2023-03-09 07:41:54,755][23090] Updated weights for policy 0, policy_version 11189 (0.0013) [2023-03-09 07:41:55,789][23090] Updated weights for policy 0, policy_version 11199 (0.0016) [2023-03-09 07:41:56,553][23090] Updated weights for policy 0, policy_version 11209 (0.0013) [2023-03-09 07:41:57,313][23090] Updated weights for policy 0, policy_version 11219 (0.0013) [2023-03-09 07:41:58,209][23090] Updated weights for policy 0, policy_version 11229 (0.0022) [2023-03-09 07:41:59,007][23090] Updated weights for policy 0, policy_version 11239 (0.0013) [2023-03-09 07:41:59,059][22664] Fps is (10 sec: 199884.6, 60 sec: 200431.2, 300 sec: 200551.1). Total num frames: 184156160. Throughput: 0: 50049.7. Samples: 46002864. Policy #0 lag: (min: 1.0, avg: 16.3, max: 33.0) [2023-03-09 07:41:59,061][22664] Avg episode reward: [(0, '48.593')] [2023-03-09 07:41:59,843][23090] Updated weights for policy 0, policy_version 11250 (0.0013) [2023-03-09 07:42:00,679][23090] Updated weights for policy 0, policy_version 11260 (0.0013) [2023-03-09 07:42:01,440][23090] Updated weights for policy 0, policy_version 11270 (0.0020) [2023-03-09 07:42:02,262][23090] Updated weights for policy 0, policy_version 11280 (0.0021) [2023-03-09 07:42:03,193][23090] Updated weights for policy 0, policy_version 11290 (0.0017) [2023-03-09 07:42:03,958][23090] Updated weights for policy 0, policy_version 11300 (0.0016) [2023-03-09 07:42:04,059][22664] Fps is (10 sec: 201519.8, 60 sec: 200430.7, 300 sec: 200551.2). Total num frames: 185155584. Throughput: 0: 50049.5. Samples: 46303856. Policy #0 lag: (min: 1.0, avg: 16.3, max: 33.0) [2023-03-09 07:42:04,060][22664] Avg episode reward: [(0, '45.840')] [2023-03-09 07:42:04,712][22940] Signal inference workers to stop experience collection... (4400 times) [2023-03-09 07:42:04,728][22940] Signal inference workers to resume experience collection... (4400 times) [2023-03-09 07:42:04,758][23090] InferenceWorker_p0-w0: stopping experience collection (4400 times) [2023-03-09 07:42:04,801][23090] InferenceWorker_p0-w0: resuming experience collection (4400 times) [2023-03-09 07:42:04,804][23090] Updated weights for policy 0, policy_version 11310 (0.0019) [2023-03-09 07:42:05,531][23090] Updated weights for policy 0, policy_version 11320 (0.0013) [2023-03-09 07:42:06,433][23090] Updated weights for policy 0, policy_version 11330 (0.0016) [2023-03-09 07:42:07,247][23090] Updated weights for policy 0, policy_version 11340 (0.0015) [2023-03-09 07:42:07,890][23090] Updated weights for policy 0, policy_version 11350 (0.0025) [2023-03-09 07:42:08,891][23090] Updated weights for policy 0, policy_version 11360 (0.0013) [2023-03-09 07:42:09,059][22664] Fps is (10 sec: 199884.9, 60 sec: 200156.7, 300 sec: 200551.0). Total num frames: 186155008. Throughput: 0: 50186.7. Samples: 46604864. Policy #0 lag: (min: 1.0, avg: 16.4, max: 33.0) [2023-03-09 07:42:09,061][22664] Avg episode reward: [(0, '47.923')] [2023-03-09 07:42:09,711][23090] Updated weights for policy 0, policy_version 11370 (0.0015) [2023-03-09 07:42:10,409][23090] Updated weights for policy 0, policy_version 11380 (0.0018) [2023-03-09 07:42:11,419][23090] Updated weights for policy 0, policy_version 11390 (0.0017) [2023-03-09 07:42:12,132][23090] Updated weights for policy 0, policy_version 11400 (0.0016) [2023-03-09 07:42:12,897][23090] Updated weights for policy 0, policy_version 11410 (0.0013) [2023-03-09 07:42:13,761][23090] Updated weights for policy 0, policy_version 11420 (0.0016) [2023-03-09 07:42:14,058][22664] Fps is (10 sec: 199889.5, 60 sec: 200158.8, 300 sec: 200496.1). Total num frames: 187154432. Throughput: 0: 50230.2. Samples: 46756304. Policy #0 lag: (min: 0.0, avg: 17.5, max: 32.0) [2023-03-09 07:42:14,059][22664] Avg episode reward: [(0, '48.027')] [2023-03-09 07:42:14,524][23090] Updated weights for policy 0, policy_version 11430 (0.0018) [2023-03-09 07:42:15,022][22940] Signal inference workers to stop experience collection... (4450 times) [2023-03-09 07:42:15,023][22940] Signal inference workers to resume experience collection... (4450 times) [2023-03-09 07:42:15,086][23090] InferenceWorker_p0-w0: stopping experience collection (4450 times) [2023-03-09 07:42:15,128][23090] InferenceWorker_p0-w0: resuming experience collection (4450 times) [2023-03-09 07:42:15,297][23090] Updated weights for policy 0, policy_version 11440 (0.0023) [2023-03-09 07:42:16,232][23090] Updated weights for policy 0, policy_version 11450 (0.0016) [2023-03-09 07:42:17,003][23090] Updated weights for policy 0, policy_version 11460 (0.0013) [2023-03-09 07:42:17,832][23090] Updated weights for policy 0, policy_version 11471 (0.0015) [2023-03-09 07:42:18,638][23090] Updated weights for policy 0, policy_version 11481 (0.0013) [2023-03-09 07:42:19,059][22664] Fps is (10 sec: 201529.0, 60 sec: 200976.8, 300 sec: 200606.8). Total num frames: 188170240. Throughput: 0: 50185.6. Samples: 47057280. Policy #0 lag: (min: 0.0, avg: 17.5, max: 32.0) [2023-03-09 07:42:19,060][22664] Avg episode reward: [(0, '45.492')] [2023-03-09 07:42:19,510][23090] Updated weights for policy 0, policy_version 11491 (0.0015) [2023-03-09 07:42:20,396][23090] Updated weights for policy 0, policy_version 11501 (0.0013) [2023-03-09 07:42:21,037][23090] Updated weights for policy 0, policy_version 11511 (0.0013) [2023-03-09 07:42:22,105][23090] Updated weights for policy 0, policy_version 11522 (0.0015) [2023-03-09 07:42:22,944][23090] Updated weights for policy 0, policy_version 11532 (0.0015) [2023-03-09 07:42:23,612][23090] Updated weights for policy 0, policy_version 11542 (0.0012) [2023-03-09 07:42:24,059][22664] Fps is (10 sec: 199878.2, 60 sec: 200430.1, 300 sec: 200551.3). Total num frames: 189153280. Throughput: 0: 50094.9. Samples: 47354208. Policy #0 lag: (min: 1.0, avg: 16.3, max: 33.0) [2023-03-09 07:42:24,061][22664] Avg episode reward: [(0, '47.500')] [2023-03-09 07:42:24,608][23090] Updated weights for policy 0, policy_version 11552 (0.0019) [2023-03-09 07:42:25,427][23090] Updated weights for policy 0, policy_version 11562 (0.0016) [2023-03-09 07:42:25,746][22940] Signal inference workers to stop experience collection... (4500 times) [2023-03-09 07:42:25,748][22940] Signal inference workers to resume experience collection... (4500 times) [2023-03-09 07:42:25,827][23090] InferenceWorker_p0-w0: stopping experience collection (4500 times) [2023-03-09 07:42:25,867][23090] InferenceWorker_p0-w0: resuming experience collection (4500 times) [2023-03-09 07:42:26,117][23090] Updated weights for policy 0, policy_version 11572 (0.0013) [2023-03-09 07:42:27,079][23090] Updated weights for policy 0, policy_version 11582 (0.0013) [2023-03-09 07:42:27,804][23090] Updated weights for policy 0, policy_version 11592 (0.0016) [2023-03-09 07:42:28,595][23090] Updated weights for policy 0, policy_version 11602 (0.0023) [2023-03-09 07:42:29,058][22664] Fps is (10 sec: 201524.8, 60 sec: 200704.4, 300 sec: 200606.8). Total num frames: 190185472. Throughput: 0: 50185.3. Samples: 47507760. Policy #0 lag: (min: 1.0, avg: 16.3, max: 33.0) [2023-03-09 07:42:29,060][22664] Avg episode reward: [(0, '48.121')] [2023-03-09 07:42:29,430][23090] Updated weights for policy 0, policy_version 11612 (0.0017) [2023-03-09 07:42:30,325][23090] Updated weights for policy 0, policy_version 11623 (0.0013) [2023-03-09 07:42:31,135][23090] Updated weights for policy 0, policy_version 11633 (0.0015) [2023-03-09 07:42:31,922][23090] Updated weights for policy 0, policy_version 11643 (0.0016) [2023-03-09 07:42:32,760][23090] Updated weights for policy 0, policy_version 11653 (0.0020) [2023-03-09 07:42:33,513][23090] Updated weights for policy 0, policy_version 11663 (0.0013) [2023-03-09 07:42:34,059][22664] Fps is (10 sec: 204803.4, 60 sec: 200976.9, 300 sec: 200662.2). Total num frames: 191201280. Throughput: 0: 50139.3. Samples: 47808704. Policy #0 lag: (min: 3.0, avg: 17.5, max: 34.0) [2023-03-09 07:42:34,061][22664] Avg episode reward: [(0, '47.970')] [2023-03-09 07:42:34,497][23090] Updated weights for policy 0, policy_version 11674 (0.0017) [2023-03-09 07:42:35,316][23090] Updated weights for policy 0, policy_version 11684 (0.0020) [2023-03-09 07:42:36,054][22940] Signal inference workers to stop experience collection... (4550 times) [2023-03-09 07:42:36,076][22940] Signal inference workers to resume experience collection... (4550 times) [2023-03-09 07:42:36,093][23090] InferenceWorker_p0-w0: stopping experience collection (4550 times) [2023-03-09 07:42:36,094][23090] InferenceWorker_p0-w0: resuming experience collection (4550 times) [2023-03-09 07:42:36,097][23090] Updated weights for policy 0, policy_version 11694 (0.0014) [2023-03-09 07:42:36,817][23090] Updated weights for policy 0, policy_version 11704 (0.0020) [2023-03-09 07:42:37,732][23090] Updated weights for policy 0, policy_version 11714 (0.0018) [2023-03-09 07:42:38,573][23090] Updated weights for policy 0, policy_version 11724 (0.0017) [2023-03-09 07:42:39,059][22664] Fps is (10 sec: 201520.8, 60 sec: 200431.4, 300 sec: 200551.4). Total num frames: 192200704. Throughput: 0: 50185.2. Samples: 48111744. Policy #0 lag: (min: 3.0, avg: 17.5, max: 34.0) [2023-03-09 07:42:39,060][22664] Avg episode reward: [(0, '48.231')] [2023-03-09 07:42:39,187][23090] Updated weights for policy 0, policy_version 11734 (0.0022) [2023-03-09 07:42:40,203][23090] Updated weights for policy 0, policy_version 11744 (0.0019) [2023-03-09 07:42:41,033][23090] Updated weights for policy 0, policy_version 11754 (0.0019) [2023-03-09 07:42:41,705][23090] Updated weights for policy 0, policy_version 11765 (0.0017) [2023-03-09 07:42:42,733][23090] Updated weights for policy 0, policy_version 11775 (0.0016) [2023-03-09 07:42:43,540][23090] Updated weights for policy 0, policy_version 11785 (0.0019) [2023-03-09 07:42:44,059][22664] Fps is (10 sec: 199887.0, 60 sec: 200704.0, 300 sec: 200496.1). Total num frames: 193200128. Throughput: 0: 50230.8. Samples: 48263232. Policy #0 lag: (min: 1.0, avg: 16.8, max: 33.0) [2023-03-09 07:42:44,060][22664] Avg episode reward: [(0, '48.603')] [2023-03-09 07:42:44,244][23090] Updated weights for policy 0, policy_version 11795 (0.0018) [2023-03-09 07:42:45,179][23090] Updated weights for policy 0, policy_version 11805 (0.0013) [2023-03-09 07:42:45,941][23090] Updated weights for policy 0, policy_version 11815 (0.0024) [2023-03-09 07:42:46,568][22940] Signal inference workers to stop experience collection... (4600 times) [2023-03-09 07:42:46,569][22940] Signal inference workers to resume experience collection... (4600 times) [2023-03-09 07:42:46,627][23090] InferenceWorker_p0-w0: stopping experience collection (4600 times) [2023-03-09 07:42:46,631][23090] InferenceWorker_p0-w0: resuming experience collection (4600 times) [2023-03-09 07:42:46,755][23090] Updated weights for policy 0, policy_version 11825 (0.0014) [2023-03-09 07:42:47,593][23090] Updated weights for policy 0, policy_version 11835 (0.0013) [2023-03-09 07:42:48,421][23090] Updated weights for policy 0, policy_version 11845 (0.0016) [2023-03-09 07:42:49,059][22664] Fps is (10 sec: 198248.2, 60 sec: 200432.0, 300 sec: 200440.2). Total num frames: 194183168. Throughput: 0: 50231.0. Samples: 48564240. Policy #0 lag: (min: 0.0, avg: 16.5, max: 33.0) [2023-03-09 07:42:49,060][22664] Avg episode reward: [(0, '45.694')] [2023-03-09 07:42:49,200][23090] Updated weights for policy 0, policy_version 11855 (0.0016) [2023-03-09 07:42:50,013][23090] Updated weights for policy 0, policy_version 11865 (0.0018) [2023-03-09 07:42:50,953][23090] Updated weights for policy 0, policy_version 11875 (0.0015) [2023-03-09 07:42:51,714][23090] Updated weights for policy 0, policy_version 11885 (0.0017) [2023-03-09 07:42:52,444][23090] Updated weights for policy 0, policy_version 11895 (0.0016) [2023-03-09 07:42:53,373][23090] Updated weights for policy 0, policy_version 11905 (0.0016) [2023-03-09 07:42:54,059][22664] Fps is (10 sec: 198241.3, 60 sec: 200703.2, 300 sec: 200440.0). Total num frames: 195182592. Throughput: 0: 50138.7. Samples: 48861104. Policy #0 lag: (min: 0.0, avg: 16.5, max: 33.0) [2023-03-09 07:42:54,060][22664] Avg episode reward: [(0, '45.907')] [2023-03-09 07:42:54,246][23090] Updated weights for policy 0, policy_version 11915 (0.0016) [2023-03-09 07:42:54,862][23090] Updated weights for policy 0, policy_version 11925 (0.0013) [2023-03-09 07:42:55,850][23090] Updated weights for policy 0, policy_version 11935 (0.0013) [2023-03-09 07:42:56,815][23090] Updated weights for policy 0, policy_version 11946 (0.0018) [2023-03-09 07:42:57,074][22940] Signal inference workers to stop experience collection... (4650 times) [2023-03-09 07:42:57,074][22940] Signal inference workers to resume experience collection... (4650 times) [2023-03-09 07:42:57,137][23090] InferenceWorker_p0-w0: stopping experience collection (4650 times) [2023-03-09 07:42:57,140][23090] InferenceWorker_p0-w0: resuming experience collection (4650 times) [2023-03-09 07:42:57,429][23090] Updated weights for policy 0, policy_version 11957 (0.0016) [2023-03-09 07:42:58,478][23090] Updated weights for policy 0, policy_version 11967 (0.0017) [2023-03-09 07:42:59,059][22664] Fps is (10 sec: 201515.8, 60 sec: 200703.9, 300 sec: 200495.7). Total num frames: 196198400. Throughput: 0: 50140.7. Samples: 49012656. Policy #0 lag: (min: 0.0, avg: 17.6, max: 32.0) [2023-03-09 07:42:59,061][22664] Avg episode reward: [(0, '47.520')] [2023-03-09 07:42:59,304][23090] Updated weights for policy 0, policy_version 11977 (0.0013) [2023-03-09 07:42:59,996][23090] Updated weights for policy 0, policy_version 11987 (0.0019) [2023-03-09 07:43:00,940][23090] Updated weights for policy 0, policy_version 11997 (0.0017) [2023-03-09 07:43:01,671][23090] Updated weights for policy 0, policy_version 12007 (0.0021) [2023-03-09 07:43:02,480][23090] Updated weights for policy 0, policy_version 12017 (0.0013) [2023-03-09 07:43:03,390][23090] Updated weights for policy 0, policy_version 12028 (0.0022) [2023-03-09 07:43:04,059][22664] Fps is (10 sec: 199889.5, 60 sec: 200431.5, 300 sec: 200440.3). Total num frames: 197181440. Throughput: 0: 50139.8. Samples: 49313568. Policy #0 lag: (min: 0.0, avg: 17.6, max: 32.0) [2023-03-09 07:43:04,060][22664] Avg episode reward: [(0, '44.620')] [2023-03-09 07:43:04,195][23090] Updated weights for policy 0, policy_version 12038 (0.0015) [2023-03-09 07:43:04,977][23090] Updated weights for policy 0, policy_version 12048 (0.0017) [2023-03-09 07:43:05,839][23090] Updated weights for policy 0, policy_version 12058 (0.0016) [2023-03-09 07:43:06,698][23090] Updated weights for policy 0, policy_version 12068 (0.0018) [2023-03-09 07:43:07,274][22940] Signal inference workers to stop experience collection... (4700 times) [2023-03-09 07:43:07,294][22940] Signal inference workers to resume experience collection... (4700 times) [2023-03-09 07:43:07,347][23090] InferenceWorker_p0-w0: stopping experience collection (4700 times) [2023-03-09 07:43:07,347][23090] InferenceWorker_p0-w0: resuming experience collection (4700 times) [2023-03-09 07:43:07,468][23090] Updated weights for policy 0, policy_version 12078 (0.0019) [2023-03-09 07:43:08,262][23090] Updated weights for policy 0, policy_version 12088 (0.0017) [2023-03-09 07:43:09,059][22664] Fps is (10 sec: 198252.5, 60 sec: 200431.9, 300 sec: 200384.6). Total num frames: 198180864. Throughput: 0: 50229.9. Samples: 49614544. Policy #0 lag: (min: 2.0, avg: 17.1, max: 33.0) [2023-03-09 07:43:09,059][22664] Avg episode reward: [(0, '45.909')] [2023-03-09 07:43:09,145][23090] Updated weights for policy 0, policy_version 12098 (0.0016) [2023-03-09 07:43:10,026][23090] Updated weights for policy 0, policy_version 12108 (0.0013) [2023-03-09 07:43:10,601][23090] Updated weights for policy 0, policy_version 12118 (0.0015) [2023-03-09 07:43:11,625][23090] Updated weights for policy 0, policy_version 12128 (0.0013) [2023-03-09 07:43:12,536][23090] Updated weights for policy 0, policy_version 12139 (0.0015) [2023-03-09 07:43:13,205][23090] Updated weights for policy 0, policy_version 12150 (0.0013) [2023-03-09 07:43:14,058][22664] Fps is (10 sec: 199885.7, 60 sec: 200430.8, 300 sec: 200329.4). Total num frames: 199180288. Throughput: 0: 50184.9. Samples: 49766080. Policy #0 lag: (min: 2.0, avg: 17.1, max: 33.0) [2023-03-09 07:43:14,059][22664] Avg episode reward: [(0, '46.767')] [2023-03-09 07:43:14,276][23090] Updated weights for policy 0, policy_version 12160 (0.0015) [2023-03-09 07:43:15,105][23090] Updated weights for policy 0, policy_version 12170 (0.0016) [2023-03-09 07:43:15,746][23090] Updated weights for policy 0, policy_version 12181 (0.0020) [2023-03-09 07:43:16,769][23090] Updated weights for policy 0, policy_version 12191 (0.0013) [2023-03-09 07:43:17,572][23090] Updated weights for policy 0, policy_version 12201 (0.0024) [2023-03-09 07:43:17,868][22940] Signal inference workers to stop experience collection... (4750 times) [2023-03-09 07:43:17,889][22940] Signal inference workers to resume experience collection... (4750 times) [2023-03-09 07:43:17,937][23090] InferenceWorker_p0-w0: stopping experience collection (4750 times) [2023-03-09 07:43:17,937][23090] InferenceWorker_p0-w0: resuming experience collection (4750 times) [2023-03-09 07:43:18,274][23090] Updated weights for policy 0, policy_version 12211 (0.0013) [2023-03-09 07:43:19,059][22664] Fps is (10 sec: 201523.7, 60 sec: 200431.0, 300 sec: 200440.4). Total num frames: 200196096. Throughput: 0: 50141.6. Samples: 50065072. Policy #0 lag: (min: 1.0, avg: 18.3, max: 32.0) [2023-03-09 07:43:19,059][22664] Avg episode reward: [(0, '48.534')] [2023-03-09 07:43:19,064][22940] Saving /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000012220_200212480.pth... [2023-03-09 07:43:19,129][22940] Removing /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000009284_152109056.pth [2023-03-09 07:43:19,188][23090] Updated weights for policy 0, policy_version 12221 (0.0013) [2023-03-09 07:43:19,969][23090] Updated weights for policy 0, policy_version 12231 (0.0013) [2023-03-09 07:43:20,741][23090] Updated weights for policy 0, policy_version 12241 (0.0014) [2023-03-09 07:43:21,605][23090] Updated weights for policy 0, policy_version 12251 (0.0013) [2023-03-09 07:43:22,456][23090] Updated weights for policy 0, policy_version 12261 (0.0015) [2023-03-09 07:43:23,245][23090] Updated weights for policy 0, policy_version 12271 (0.0019) [2023-03-09 07:43:24,030][23090] Updated weights for policy 0, policy_version 12281 (0.0013) [2023-03-09 07:43:24,058][22664] Fps is (10 sec: 203162.6, 60 sec: 200978.2, 300 sec: 200495.8). Total num frames: 201211904. Throughput: 0: 50096.2. Samples: 50366064. Policy #0 lag: (min: 1.0, avg: 18.3, max: 32.0) [2023-03-09 07:43:24,059][22664] Avg episode reward: [(0, '47.084')] [2023-03-09 07:43:24,894][23090] Updated weights for policy 0, policy_version 12291 (0.0013) [2023-03-09 07:43:25,706][23090] Updated weights for policy 0, policy_version 12301 (0.0020) [2023-03-09 07:43:26,386][23090] Updated weights for policy 0, policy_version 12311 (0.0020) [2023-03-09 07:43:27,362][23090] Updated weights for policy 0, policy_version 12321 (0.0016) [2023-03-09 07:43:27,615][22940] Signal inference workers to stop experience collection... (4800 times) [2023-03-09 07:43:27,625][22940] Signal inference workers to resume experience collection... (4800 times) [2023-03-09 07:43:27,690][23090] InferenceWorker_p0-w0: stopping experience collection (4800 times) [2023-03-09 07:43:27,691][23090] InferenceWorker_p0-w0: resuming experience collection (4800 times) [2023-03-09 07:43:28,234][23090] Updated weights for policy 0, policy_version 12332 (0.0018) [2023-03-09 07:43:28,847][23090] Updated weights for policy 0, policy_version 12342 (0.0013) [2023-03-09 07:43:29,059][22664] Fps is (10 sec: 203161.6, 60 sec: 200703.8, 300 sec: 200551.3). Total num frames: 202227712. Throughput: 0: 50097.4. Samples: 50517616. Policy #0 lag: (min: 2.0, avg: 17.1, max: 33.0) [2023-03-09 07:43:29,060][22664] Avg episode reward: [(0, '45.870')] [2023-03-09 07:43:29,911][23090] Updated weights for policy 0, policy_version 12352 (0.0013) [2023-03-09 07:43:30,763][23090] Updated weights for policy 0, policy_version 12362 (0.0016) [2023-03-09 07:43:31,374][23090] Updated weights for policy 0, policy_version 12372 (0.0016) [2023-03-09 07:43:32,359][23090] Updated weights for policy 0, policy_version 12382 (0.0015) [2023-03-09 07:43:33,129][23090] Updated weights for policy 0, policy_version 12392 (0.0013) [2023-03-09 07:43:33,868][23090] Updated weights for policy 0, policy_version 12402 (0.0013) [2023-03-09 07:43:34,058][22664] Fps is (10 sec: 203161.4, 60 sec: 200704.6, 300 sec: 200551.3). Total num frames: 203243520. Throughput: 0: 50097.8. Samples: 50818640. Policy #0 lag: (min: 2.0, avg: 17.1, max: 33.0) [2023-03-09 07:43:34,059][22664] Avg episode reward: [(0, '50.001')] [2023-03-09 07:43:34,072][22940] Saving new best policy, reward=50.001! [2023-03-09 07:43:34,724][23090] Updated weights for policy 0, policy_version 12412 (0.0017) [2023-03-09 07:43:35,527][23090] Updated weights for policy 0, policy_version 12422 (0.0014) [2023-03-09 07:43:36,324][23090] Updated weights for policy 0, policy_version 12432 (0.0018) [2023-03-09 07:43:37,164][23090] Updated weights for policy 0, policy_version 12442 (0.0019) [2023-03-09 07:43:37,767][22940] Signal inference workers to stop experience collection... (4850 times) [2023-03-09 07:43:37,767][22940] Signal inference workers to resume experience collection... (4850 times) [2023-03-09 07:43:37,826][23090] InferenceWorker_p0-w0: stopping experience collection (4850 times) [2023-03-09 07:43:37,870][23090] InferenceWorker_p0-w0: resuming experience collection (4850 times) [2023-03-09 07:43:38,076][23090] Updated weights for policy 0, policy_version 12452 (0.0013) [2023-03-09 07:43:38,829][23090] Updated weights for policy 0, policy_version 12462 (0.0013) [2023-03-09 07:43:39,059][22664] Fps is (10 sec: 199885.1, 60 sec: 200431.2, 300 sec: 200440.4). Total num frames: 204226560. Throughput: 0: 50190.1. Samples: 51119648. Policy #0 lag: (min: 0.0, avg: 17.6, max: 32.0) [2023-03-09 07:43:39,060][22664] Avg episode reward: [(0, '45.738')] [2023-03-09 07:43:39,591][23090] Updated weights for policy 0, policy_version 12472 (0.0020) [2023-03-09 07:43:40,471][23090] Updated weights for policy 0, policy_version 12482 (0.0019) [2023-03-09 07:43:41,263][23090] Updated weights for policy 0, policy_version 12492 (0.0018) [2023-03-09 07:43:41,924][23090] Updated weights for policy 0, policy_version 12502 (0.0013) [2023-03-09 07:43:43,008][23090] Updated weights for policy 0, policy_version 12512 (0.0015) [2023-03-09 07:43:43,805][23090] Updated weights for policy 0, policy_version 12522 (0.0013) [2023-03-09 07:43:44,059][22664] Fps is (10 sec: 198238.8, 60 sec: 200429.8, 300 sec: 200440.2). Total num frames: 205225984. Throughput: 0: 50143.7. Samples: 51269120. Policy #0 lag: (min: 1.0, avg: 16.3, max: 33.0) [2023-03-09 07:43:44,061][22664] Avg episode reward: [(0, '48.411')] [2023-03-09 07:43:44,463][23090] Updated weights for policy 0, policy_version 12532 (0.0015) [2023-03-09 07:43:45,451][23090] Updated weights for policy 0, policy_version 12542 (0.0019) [2023-03-09 07:43:46,194][23090] Updated weights for policy 0, policy_version 12552 (0.0013) [2023-03-09 07:43:46,922][23090] Updated weights for policy 0, policy_version 12562 (0.0013) [2023-03-09 07:43:47,784][23090] Updated weights for policy 0, policy_version 12572 (0.0018) [2023-03-09 07:43:48,580][23090] Updated weights for policy 0, policy_version 12582 (0.0013) [2023-03-09 07:43:48,994][22940] Signal inference workers to stop experience collection... (4900 times) [2023-03-09 07:43:48,994][22940] Signal inference workers to resume experience collection... (4900 times) [2023-03-09 07:43:49,058][23090] InferenceWorker_p0-w0: stopping experience collection (4900 times) [2023-03-09 07:43:49,059][23090] InferenceWorker_p0-w0: resuming experience collection (4900 times) [2023-03-09 07:43:49,059][22664] Fps is (10 sec: 199871.7, 60 sec: 200701.8, 300 sec: 200384.2). Total num frames: 206225408. Throughput: 0: 50189.9. Samples: 51572144. Policy #0 lag: (min: 1.0, avg: 16.3, max: 33.0) [2023-03-09 07:43:49,063][22664] Avg episode reward: [(0, '49.076')] [2023-03-09 07:43:49,357][23090] Updated weights for policy 0, policy_version 12592 (0.0013) [2023-03-09 07:43:50,219][23090] Updated weights for policy 0, policy_version 12602 (0.0016) [2023-03-09 07:43:51,109][23090] Updated weights for policy 0, policy_version 12612 (0.0020) [2023-03-09 07:43:51,845][23090] Updated weights for policy 0, policy_version 12622 (0.0021) [2023-03-09 07:43:52,720][23090] Updated weights for policy 0, policy_version 12633 (0.0016) [2023-03-09 07:43:53,620][23090] Updated weights for policy 0, policy_version 12643 (0.0013) [2023-03-09 07:43:54,059][22664] Fps is (10 sec: 199886.2, 60 sec: 200704.0, 300 sec: 200384.5). Total num frames: 207224832. Throughput: 0: 50146.3. Samples: 51871136. Policy #0 lag: (min: 0.0, avg: 16.4, max: 33.0) [2023-03-09 07:43:54,061][22664] Avg episode reward: [(0, '50.176')] [2023-03-09 07:43:54,063][22940] Saving new best policy, reward=50.176! [2023-03-09 07:43:54,470][23090] Updated weights for policy 0, policy_version 12653 (0.0017) [2023-03-09 07:43:55,158][23090] Updated weights for policy 0, policy_version 12663 (0.0020) [2023-03-09 07:43:56,145][23090] Updated weights for policy 0, policy_version 12673 (0.0016) [2023-03-09 07:43:56,965][23090] Updated weights for policy 0, policy_version 12683 (0.0020) [2023-03-09 07:43:57,565][23090] Updated weights for policy 0, policy_version 12693 (0.0013) [2023-03-09 07:43:58,571][23090] Updated weights for policy 0, policy_version 12703 (0.0018) [2023-03-09 07:43:59,058][22664] Fps is (10 sec: 201537.8, 60 sec: 200705.4, 300 sec: 200551.5). Total num frames: 208240640. Throughput: 0: 50146.9. Samples: 52022688. Policy #0 lag: (min: 0.0, avg: 16.4, max: 33.0) [2023-03-09 07:43:59,059][22664] Avg episode reward: [(0, '47.477')] [2023-03-09 07:43:59,348][23090] Updated weights for policy 0, policy_version 12713 (0.0019) [2023-03-09 07:43:59,957][22940] Signal inference workers to stop experience collection... (4950 times) [2023-03-09 07:43:59,958][22940] Signal inference workers to resume experience collection... (4950 times) [2023-03-09 07:44:00,028][23090] InferenceWorker_p0-w0: stopping experience collection (4950 times) [2023-03-09 07:44:00,031][23090] InferenceWorker_p0-w0: resuming experience collection (4950 times) [2023-03-09 07:44:00,070][23090] Updated weights for policy 0, policy_version 12723 (0.0013) [2023-03-09 07:44:01,011][23090] Updated weights for policy 0, policy_version 12733 (0.0013) [2023-03-09 07:44:01,818][23090] Updated weights for policy 0, policy_version 12743 (0.0017) [2023-03-09 07:44:02,580][23090] Updated weights for policy 0, policy_version 12753 (0.0018) [2023-03-09 07:44:03,389][23090] Updated weights for policy 0, policy_version 12763 (0.0015) [2023-03-09 07:44:04,059][22664] Fps is (10 sec: 199884.7, 60 sec: 200703.2, 300 sec: 200440.3). Total num frames: 209223680. Throughput: 0: 50191.7. Samples: 52323712. Policy #0 lag: (min: 1.0, avg: 17.2, max: 33.0) [2023-03-09 07:44:04,061][22664] Avg episode reward: [(0, '46.088')] [2023-03-09 07:44:04,261][23090] Updated weights for policy 0, policy_version 12773 (0.0015) [2023-03-09 07:44:05,000][23090] Updated weights for policy 0, policy_version 12783 (0.0024) [2023-03-09 07:44:05,823][23090] Updated weights for policy 0, policy_version 12793 (0.0017) [2023-03-09 07:44:06,706][23090] Updated weights for policy 0, policy_version 12803 (0.0015) [2023-03-09 07:44:07,558][23090] Updated weights for policy 0, policy_version 12813 (0.0013) [2023-03-09 07:44:08,204][23090] Updated weights for policy 0, policy_version 12823 (0.0015) [2023-03-09 07:44:09,059][22664] Fps is (10 sec: 198237.9, 60 sec: 200702.9, 300 sec: 200439.9). Total num frames: 210223104. Throughput: 0: 50146.0. Samples: 52622656. Policy #0 lag: (min: 1.0, avg: 17.2, max: 33.0) [2023-03-09 07:44:09,061][22664] Avg episode reward: [(0, '47.882')] [2023-03-09 07:44:09,226][23090] Updated weights for policy 0, policy_version 12833 (0.0018) [2023-03-09 07:44:10,073][23090] Updated weights for policy 0, policy_version 12843 (0.0018) [2023-03-09 07:44:10,503][22940] Signal inference workers to stop experience collection... (5000 times) [2023-03-09 07:44:10,514][22940] Signal inference workers to resume experience collection... (5000 times) [2023-03-09 07:44:10,574][23090] InferenceWorker_p0-w0: stopping experience collection (5000 times) [2023-03-09 07:44:10,575][23090] InferenceWorker_p0-w0: resuming experience collection (5000 times) [2023-03-09 07:44:10,695][23090] Updated weights for policy 0, policy_version 12853 (0.0013) [2023-03-09 07:44:11,700][23090] Updated weights for policy 0, policy_version 12863 (0.0021) [2023-03-09 07:44:12,509][23090] Updated weights for policy 0, policy_version 12873 (0.0017) [2023-03-09 07:44:13,234][23090] Updated weights for policy 0, policy_version 12883 (0.0015) [2023-03-09 07:44:14,059][22664] Fps is (10 sec: 199884.6, 60 sec: 200703.0, 300 sec: 200495.6). Total num frames: 211222528. Throughput: 0: 50100.7. Samples: 52772160. Policy #0 lag: (min: 1.0, avg: 16.4, max: 33.0) [2023-03-09 07:44:14,061][22664] Avg episode reward: [(0, '49.787')] [2023-03-09 07:44:14,135][23090] Updated weights for policy 0, policy_version 12893 (0.0013) [2023-03-09 07:44:14,893][23090] Updated weights for policy 0, policy_version 12903 (0.0013) [2023-03-09 07:44:15,740][23090] Updated weights for policy 0, policy_version 12913 (0.0013) [2023-03-09 07:44:16,539][23090] Updated weights for policy 0, policy_version 12923 (0.0013) [2023-03-09 07:44:17,398][23090] Updated weights for policy 0, policy_version 12933 (0.0012) [2023-03-09 07:44:18,118][23090] Updated weights for policy 0, policy_version 12943 (0.0015) [2023-03-09 07:44:18,977][23090] Updated weights for policy 0, policy_version 12953 (0.0021) [2023-03-09 07:44:19,059][22664] Fps is (10 sec: 199885.9, 60 sec: 200430.0, 300 sec: 200495.7). Total num frames: 212221952. Throughput: 0: 50098.8. Samples: 53073104. Policy #0 lag: (min: 1.0, avg: 16.4, max: 33.0) [2023-03-09 07:44:19,061][22664] Avg episode reward: [(0, '45.696')] [2023-03-09 07:44:19,830][23090] Updated weights for policy 0, policy_version 12963 (0.0013) [2023-03-09 07:44:20,667][23090] Updated weights for policy 0, policy_version 12973 (0.0013) [2023-03-09 07:44:21,079][22940] Signal inference workers to stop experience collection... (5050 times) [2023-03-09 07:44:21,097][22940] Signal inference workers to resume experience collection... (5050 times) [2023-03-09 07:44:21,155][23090] InferenceWorker_p0-w0: stopping experience collection (5050 times) [2023-03-09 07:44:21,156][23090] InferenceWorker_p0-w0: resuming experience collection (5050 times) [2023-03-09 07:44:21,347][23090] Updated weights for policy 0, policy_version 12983 (0.0016) [2023-03-09 07:44:22,343][23090] Updated weights for policy 0, policy_version 12993 (0.0015) [2023-03-09 07:44:23,173][23090] Updated weights for policy 0, policy_version 13003 (0.0013) [2023-03-09 07:44:23,826][23090] Updated weights for policy 0, policy_version 13013 (0.0014) [2023-03-09 07:44:24,059][22664] Fps is (10 sec: 201522.3, 60 sec: 200429.6, 300 sec: 200551.1). Total num frames: 213237760. Throughput: 0: 50053.0. Samples: 53372048. Policy #0 lag: (min: 1.0, avg: 16.5, max: 33.0) [2023-03-09 07:44:24,061][22664] Avg episode reward: [(0, '47.503')] [2023-03-09 07:44:24,776][23090] Updated weights for policy 0, policy_version 13023 (0.0013) [2023-03-09 07:44:25,529][23090] Updated weights for policy 0, policy_version 13033 (0.0014) [2023-03-09 07:44:26,324][23090] Updated weights for policy 0, policy_version 13044 (0.0012) [2023-03-09 07:44:27,325][23090] Updated weights for policy 0, policy_version 13055 (0.0013) [2023-03-09 07:44:28,160][23090] Updated weights for policy 0, policy_version 13065 (0.0016) [2023-03-09 07:44:28,816][23090] Updated weights for policy 0, policy_version 13075 (0.0018) [2023-03-09 07:44:29,059][22664] Fps is (10 sec: 204802.0, 60 sec: 200703.4, 300 sec: 200662.3). Total num frames: 214269952. Throughput: 0: 50143.8. Samples: 53525584. Policy #0 lag: (min: 1.0, avg: 16.5, max: 33.0) [2023-03-09 07:44:29,060][22664] Avg episode reward: [(0, '46.748')] [2023-03-09 07:44:29,762][23090] Updated weights for policy 0, policy_version 13085 (0.0013) [2023-03-09 07:44:30,557][23090] Updated weights for policy 0, policy_version 13095 (0.0016) [2023-03-09 07:44:31,306][22940] Signal inference workers to stop experience collection... (5100 times) [2023-03-09 07:44:31,324][22940] Signal inference workers to resume experience collection... (5100 times) [2023-03-09 07:44:31,344][23090] InferenceWorker_p0-w0: stopping experience collection (5100 times) [2023-03-09 07:44:31,344][23090] InferenceWorker_p0-w0: resuming experience collection (5100 times) [2023-03-09 07:44:31,420][23090] Updated weights for policy 0, policy_version 13106 (0.0017) [2023-03-09 07:44:32,217][23090] Updated weights for policy 0, policy_version 13116 (0.0013) [2023-03-09 07:44:33,047][23090] Updated weights for policy 0, policy_version 13126 (0.0013) [2023-03-09 07:44:33,887][23090] Updated weights for policy 0, policy_version 13136 (0.0015) [2023-03-09 07:44:34,059][22664] Fps is (10 sec: 203162.2, 60 sec: 200429.8, 300 sec: 200551.3). Total num frames: 215269376. Throughput: 0: 50098.6. Samples: 53826560. Policy #0 lag: (min: 2.0, avg: 17.5, max: 33.0) [2023-03-09 07:44:34,061][22664] Avg episode reward: [(0, '48.523')] [2023-03-09 07:44:34,728][23090] Updated weights for policy 0, policy_version 13146 (0.0021) [2023-03-09 07:44:35,525][23090] Updated weights for policy 0, policy_version 13156 (0.0016) [2023-03-09 07:44:36,319][23090] Updated weights for policy 0, policy_version 13166 (0.0023) [2023-03-09 07:44:37,078][23090] Updated weights for policy 0, policy_version 13176 (0.0016) [2023-03-09 07:44:37,956][23090] Updated weights for policy 0, policy_version 13186 (0.0015) [2023-03-09 07:44:38,795][23090] Updated weights for policy 0, policy_version 13196 (0.0016) [2023-03-09 07:44:39,059][22664] Fps is (10 sec: 199886.7, 60 sec: 200703.6, 300 sec: 200495.6). Total num frames: 216268800. Throughput: 0: 50189.3. Samples: 54129648. Policy #0 lag: (min: 2.0, avg: 17.5, max: 33.0) [2023-03-09 07:44:39,060][22664] Avg episode reward: [(0, '46.244')] [2023-03-09 07:44:39,436][23090] Updated weights for policy 0, policy_version 13206 (0.0013) [2023-03-09 07:44:40,422][23090] Updated weights for policy 0, policy_version 13216 (0.0013) [2023-03-09 07:44:40,439][22940] Signal inference workers to stop experience collection... (5150 times) [2023-03-09 07:44:40,439][22940] Signal inference workers to resume experience collection... (5150 times) [2023-03-09 07:44:40,497][23090] InferenceWorker_p0-w0: stopping experience collection (5150 times) [2023-03-09 07:44:40,497][23090] InferenceWorker_p0-w0: resuming experience collection (5150 times) [2023-03-09 07:44:41,249][23090] Updated weights for policy 0, policy_version 13226 (0.0013) [2023-03-09 07:44:41,902][23090] Updated weights for policy 0, policy_version 13236 (0.0016) [2023-03-09 07:44:42,862][23090] Updated weights for policy 0, policy_version 13246 (0.0019) [2023-03-09 07:44:43,657][23090] Updated weights for policy 0, policy_version 13256 (0.0013) [2023-03-09 07:44:44,058][22664] Fps is (10 sec: 199891.3, 60 sec: 200705.2, 300 sec: 200495.9). Total num frames: 217268224. Throughput: 0: 50187.4. Samples: 54281120. Policy #0 lag: (min: 0.0, avg: 16.3, max: 33.0) [2023-03-09 07:44:44,060][22664] Avg episode reward: [(0, '46.929')] [2023-03-09 07:44:44,385][23090] Updated weights for policy 0, policy_version 13266 (0.0014) [2023-03-09 07:44:45,266][23090] Updated weights for policy 0, policy_version 13276 (0.0012) [2023-03-09 07:44:46,029][23090] Updated weights for policy 0, policy_version 13286 (0.0019) [2023-03-09 07:44:46,858][23090] Updated weights for policy 0, policy_version 13296 (0.0015) [2023-03-09 07:44:47,726][23090] Updated weights for policy 0, policy_version 13306 (0.0016) [2023-03-09 07:44:48,523][23090] Updated weights for policy 0, policy_version 13316 (0.0018) [2023-03-09 07:44:49,059][22664] Fps is (10 sec: 199886.4, 60 sec: 200706.1, 300 sec: 200495.8). Total num frames: 218267648. Throughput: 0: 50231.0. Samples: 54584096. Policy #0 lag: (min: 0.0, avg: 16.3, max: 33.0) [2023-03-09 07:44:49,060][22664] Avg episode reward: [(0, '48.190')] [2023-03-09 07:44:49,310][23090] Updated weights for policy 0, policy_version 13326 (0.0017) [2023-03-09 07:44:50,069][23090] Updated weights for policy 0, policy_version 13336 (0.0015) [2023-03-09 07:44:50,979][23090] Updated weights for policy 0, policy_version 13346 (0.0018) [2023-03-09 07:44:51,643][22940] Signal inference workers to stop experience collection... (5200 times) [2023-03-09 07:44:51,644][22940] Signal inference workers to resume experience collection... (5200 times) [2023-03-09 07:44:51,733][23090] InferenceWorker_p0-w0: stopping experience collection (5200 times) [2023-03-09 07:44:51,734][23090] InferenceWorker_p0-w0: resuming experience collection (5200 times) [2023-03-09 07:44:51,816][23090] Updated weights for policy 0, policy_version 13356 (0.0022) [2023-03-09 07:44:52,437][23090] Updated weights for policy 0, policy_version 13366 (0.0016) [2023-03-09 07:44:53,440][23090] Updated weights for policy 0, policy_version 13376 (0.0013) [2023-03-09 07:44:54,059][22664] Fps is (10 sec: 199883.7, 60 sec: 200704.8, 300 sec: 200662.5). Total num frames: 219267072. Throughput: 0: 50230.8. Samples: 54883024. Policy #0 lag: (min: 2.0, avg: 16.3, max: 33.0) [2023-03-09 07:44:54,059][22664] Avg episode reward: [(0, '48.229')] [2023-03-09 07:44:54,320][23090] Updated weights for policy 0, policy_version 13386 (0.0016) [2023-03-09 07:44:54,947][23090] Updated weights for policy 0, policy_version 13396 (0.0016) [2023-03-09 07:44:55,946][23090] Updated weights for policy 0, policy_version 13406 (0.0013) [2023-03-09 07:44:56,671][23090] Updated weights for policy 0, policy_version 13416 (0.0017) [2023-03-09 07:44:57,427][23090] Updated weights for policy 0, policy_version 13426 (0.0013) [2023-03-09 07:44:58,273][23090] Updated weights for policy 0, policy_version 13436 (0.0020) [2023-03-09 07:44:59,059][22664] Fps is (10 sec: 201521.2, 60 sec: 200703.4, 300 sec: 200662.4). Total num frames: 220282880. Throughput: 0: 50275.4. Samples: 55034544. Policy #0 lag: (min: 2.0, avg: 16.3, max: 33.0) [2023-03-09 07:44:59,060][22664] Avg episode reward: [(0, '48.281')] [2023-03-09 07:44:59,081][23090] Updated weights for policy 0, policy_version 13446 (0.0016) [2023-03-09 07:44:59,909][23090] Updated weights for policy 0, policy_version 13456 (0.0017) [2023-03-09 07:45:00,839][23090] Updated weights for policy 0, policy_version 13466 (0.0021) [2023-03-09 07:45:01,633][23090] Updated weights for policy 0, policy_version 13476 (0.0024) [2023-03-09 07:45:02,415][23090] Updated weights for policy 0, policy_version 13486 (0.0013) [2023-03-09 07:45:03,147][23090] Updated weights for policy 0, policy_version 13496 (0.0025) [2023-03-09 07:45:03,392][22940] Signal inference workers to stop experience collection... (5250 times) [2023-03-09 07:45:03,394][22940] Signal inference workers to resume experience collection... (5250 times) [2023-03-09 07:45:03,450][23090] InferenceWorker_p0-w0: stopping experience collection (5250 times) [2023-03-09 07:45:03,450][23090] InferenceWorker_p0-w0: resuming experience collection (5250 times) [2023-03-09 07:45:04,058][22664] Fps is (10 sec: 199885.7, 60 sec: 200705.0, 300 sec: 200607.0). Total num frames: 221265920. Throughput: 0: 50277.0. Samples: 55335552. Policy #0 lag: (min: 0.0, avg: 16.5, max: 33.0) [2023-03-09 07:45:04,059][22664] Avg episode reward: [(0, '47.512')] [2023-03-09 07:45:04,123][23090] Updated weights for policy 0, policy_version 13506 (0.0013) [2023-03-09 07:45:04,853][23090] Updated weights for policy 0, policy_version 13516 (0.0013) [2023-03-09 07:45:05,506][23090] Updated weights for policy 0, policy_version 13526 (0.0013) [2023-03-09 07:45:06,601][23090] Updated weights for policy 0, policy_version 13537 (0.0020) [2023-03-09 07:45:07,435][23090] Updated weights for policy 0, policy_version 13547 (0.0013) [2023-03-09 07:45:08,077][23090] Updated weights for policy 0, policy_version 13557 (0.0020) [2023-03-09 07:45:09,029][23090] Updated weights for policy 0, policy_version 13567 (0.0015) [2023-03-09 07:45:09,058][22664] Fps is (10 sec: 199888.5, 60 sec: 200978.5, 300 sec: 200662.3). Total num frames: 222281728. Throughput: 0: 50368.1. Samples: 55638592. Policy #0 lag: (min: 0.0, avg: 16.5, max: 33.0) [2023-03-09 07:45:09,059][22664] Avg episode reward: [(0, '47.709')] [2023-03-09 07:45:09,818][23090] Updated weights for policy 0, policy_version 13577 (0.0015) [2023-03-09 07:45:10,494][23090] Updated weights for policy 0, policy_version 13587 (0.0018) [2023-03-09 07:45:11,417][23090] Updated weights for policy 0, policy_version 13597 (0.0013) [2023-03-09 07:45:12,345][23090] Updated weights for policy 0, policy_version 13608 (0.0013) [2023-03-09 07:45:13,070][23090] Updated weights for policy 0, policy_version 13618 (0.0023) [2023-03-09 07:45:13,936][23090] Updated weights for policy 0, policy_version 13628 (0.0013) [2023-03-09 07:45:14,059][22664] Fps is (10 sec: 203159.0, 60 sec: 201250.7, 300 sec: 200718.1). Total num frames: 223297536. Throughput: 0: 50278.2. Samples: 55788096. Policy #0 lag: (min: 0.0, avg: 18.2, max: 33.0) [2023-03-09 07:45:14,060][22664] Avg episode reward: [(0, '45.813')] [2023-03-09 07:45:14,525][22940] Signal inference workers to stop experience collection... (5300 times) [2023-03-09 07:45:14,525][22940] Signal inference workers to resume experience collection... (5300 times) [2023-03-09 07:45:14,592][23090] InferenceWorker_p0-w0: stopping experience collection (5300 times) [2023-03-09 07:45:14,592][23090] InferenceWorker_p0-w0: resuming experience collection (5300 times) [2023-03-09 07:45:14,904][23090] Updated weights for policy 0, policy_version 13639 (0.0017) [2023-03-09 07:45:15,676][23090] Updated weights for policy 0, policy_version 13649 (0.0017) [2023-03-09 07:45:16,516][23090] Updated weights for policy 0, policy_version 13659 (0.0017) [2023-03-09 07:45:17,348][23090] Updated weights for policy 0, policy_version 13669 (0.0015) [2023-03-09 07:45:18,100][23090] Updated weights for policy 0, policy_version 13679 (0.0013) [2023-03-09 07:45:19,059][22664] Fps is (10 sec: 199875.2, 60 sec: 200976.7, 300 sec: 200606.9). Total num frames: 224280576. Throughput: 0: 50278.9. Samples: 56089120. Policy #0 lag: (min: 0.0, avg: 18.2, max: 33.0) [2023-03-09 07:45:19,061][22664] Avg episode reward: [(0, '47.566')] [2023-03-09 07:45:19,095][23090] Updated weights for policy 0, policy_version 13690 (0.0016) [2023-03-09 07:45:19,111][22940] Saving /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000013691_224313344.pth... [2023-03-09 07:45:19,167][22940] Removing /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000010750_176128000.pth [2023-03-09 07:45:19,894][23090] Updated weights for policy 0, policy_version 13700 (0.0015) [2023-03-09 07:45:20,710][23090] Updated weights for policy 0, policy_version 13710 (0.0019) [2023-03-09 07:45:21,578][23090] Updated weights for policy 0, policy_version 13721 (0.0020) [2023-03-09 07:45:22,446][23090] Updated weights for policy 0, policy_version 13731 (0.0016) [2023-03-09 07:45:23,330][23090] Updated weights for policy 0, policy_version 13742 (0.0022) [2023-03-09 07:45:24,059][22664] Fps is (10 sec: 199880.8, 60 sec: 200977.1, 300 sec: 200607.0). Total num frames: 225296384. Throughput: 0: 50186.8. Samples: 56388064. Policy #0 lag: (min: 1.0, avg: 17.3, max: 34.0) [2023-03-09 07:45:24,060][22664] Avg episode reward: [(0, '47.856')] [2023-03-09 07:45:24,092][23090] Updated weights for policy 0, policy_version 13752 (0.0013) [2023-03-09 07:45:25,041][23090] Updated weights for policy 0, policy_version 13762 (0.0015) [2023-03-09 07:45:25,777][23090] Updated weights for policy 0, policy_version 13772 (0.0017) [2023-03-09 07:45:26,331][22940] Signal inference workers to stop experience collection... (5350 times) [2023-03-09 07:45:26,332][22940] Signal inference workers to resume experience collection... (5350 times) [2023-03-09 07:45:26,393][23090] InferenceWorker_p0-w0: stopping experience collection (5350 times) [2023-03-09 07:45:26,393][23090] InferenceWorker_p0-w0: resuming experience collection (5350 times) [2023-03-09 07:45:26,438][23090] Updated weights for policy 0, policy_version 13782 (0.0018) [2023-03-09 07:45:27,459][23090] Updated weights for policy 0, policy_version 13792 (0.0015) [2023-03-09 07:45:28,267][23090] Updated weights for policy 0, policy_version 13802 (0.0018) [2023-03-09 07:45:28,926][23090] Updated weights for policy 0, policy_version 13812 (0.0018) [2023-03-09 07:45:29,059][22664] Fps is (10 sec: 204807.9, 60 sec: 200977.7, 300 sec: 200717.9). Total num frames: 226328576. Throughput: 0: 50188.7. Samples: 56539616. Policy #0 lag: (min: 1.0, avg: 17.3, max: 34.0) [2023-03-09 07:45:29,060][22664] Avg episode reward: [(0, '47.211')] [2023-03-09 07:45:29,903][23090] Updated weights for policy 0, policy_version 13822 (0.0016) [2023-03-09 07:45:30,694][23090] Updated weights for policy 0, policy_version 13832 (0.0015) [2023-03-09 07:45:31,476][23090] Updated weights for policy 0, policy_version 13842 (0.0024) [2023-03-09 07:45:32,322][23090] Updated weights for policy 0, policy_version 13852 (0.0013) [2023-03-09 07:45:33,095][23090] Updated weights for policy 0, policy_version 13862 (0.0023) [2023-03-09 07:45:33,929][23090] Updated weights for policy 0, policy_version 13872 (0.0013) [2023-03-09 07:45:34,059][22664] Fps is (10 sec: 199885.1, 60 sec: 200431.0, 300 sec: 200551.2). Total num frames: 227295232. Throughput: 0: 50098.2. Samples: 56838528. Policy #0 lag: (min: 0.0, avg: 16.0, max: 33.0) [2023-03-09 07:45:34,061][22664] Avg episode reward: [(0, '47.691')] [2023-03-09 07:45:34,813][23090] Updated weights for policy 0, policy_version 13882 (0.0013) [2023-03-09 07:45:35,616][23090] Updated weights for policy 0, policy_version 13892 (0.0015) [2023-03-09 07:45:36,387][23090] Updated weights for policy 0, policy_version 13902 (0.0016) [2023-03-09 07:45:37,260][23090] Updated weights for policy 0, policy_version 13913 (0.0013) [2023-03-09 07:45:38,138][23090] Updated weights for policy 0, policy_version 13923 (0.0013) [2023-03-09 07:45:38,181][22940] Signal inference workers to stop experience collection... (5400 times) [2023-03-09 07:45:38,191][22940] Signal inference workers to resume experience collection... (5400 times) [2023-03-09 07:45:38,257][23090] InferenceWorker_p0-w0: stopping experience collection (5400 times) [2023-03-09 07:45:38,261][23090] InferenceWorker_p0-w0: resuming experience collection (5400 times) [2023-03-09 07:45:38,901][23090] Updated weights for policy 0, policy_version 13933 (0.0018) [2023-03-09 07:45:39,059][22664] Fps is (10 sec: 198241.5, 60 sec: 200703.4, 300 sec: 200551.0). Total num frames: 228311040. Throughput: 0: 50189.9. Samples: 57141584. Policy #0 lag: (min: 0.0, avg: 16.0, max: 33.0) [2023-03-09 07:45:39,060][22664] Avg episode reward: [(0, '50.446')] [2023-03-09 07:45:39,084][22940] Saving new best policy, reward=50.446! [2023-03-09 07:45:39,575][23090] Updated weights for policy 0, policy_version 13943 (0.0013) [2023-03-09 07:45:40,557][23090] Updated weights for policy 0, policy_version 13953 (0.0017) [2023-03-09 07:45:41,355][23090] Updated weights for policy 0, policy_version 13963 (0.0019) [2023-03-09 07:45:42,021][23090] Updated weights for policy 0, policy_version 13973 (0.0015) [2023-03-09 07:45:42,974][23090] Updated weights for policy 0, policy_version 13983 (0.0013) [2023-03-09 07:45:43,746][23090] Updated weights for policy 0, policy_version 13993 (0.0015) [2023-03-09 07:45:44,059][22664] Fps is (10 sec: 201524.6, 60 sec: 200703.2, 300 sec: 200606.9). Total num frames: 229310464. Throughput: 0: 50188.7. Samples: 57293040. Policy #0 lag: (min: 1.0, avg: 16.6, max: 33.0) [2023-03-09 07:45:44,061][22664] Avg episode reward: [(0, '47.862')] [2023-03-09 07:45:44,536][23090] Updated weights for policy 0, policy_version 14003 (0.0017) [2023-03-09 07:45:45,390][23090] Updated weights for policy 0, policy_version 14013 (0.0013) [2023-03-09 07:45:46,232][23090] Updated weights for policy 0, policy_version 14023 (0.0022) [2023-03-09 07:45:47,008][23090] Updated weights for policy 0, policy_version 14033 (0.0025) [2023-03-09 07:45:47,873][23090] Updated weights for policy 0, policy_version 14043 (0.0013) [2023-03-09 07:45:48,674][23090] Updated weights for policy 0, policy_version 14053 (0.0012) [2023-03-09 07:45:49,059][22664] Fps is (10 sec: 199888.5, 60 sec: 200703.8, 300 sec: 200551.2). Total num frames: 230309888. Throughput: 0: 50187.9. Samples: 57594016. Policy #0 lag: (min: 1.0, avg: 16.6, max: 33.0) [2023-03-09 07:45:49,060][22664] Avg episode reward: [(0, '48.431')] [2023-03-09 07:45:49,469][23090] Updated weights for policy 0, policy_version 14063 (0.0022) [2023-03-09 07:45:50,277][23090] Updated weights for policy 0, policy_version 14073 (0.0012) [2023-03-09 07:45:51,161][23090] Updated weights for policy 0, policy_version 14083 (0.0015) [2023-03-09 07:45:51,937][23090] Updated weights for policy 0, policy_version 14093 (0.0020) [2023-03-09 07:45:52,318][22940] Signal inference workers to stop experience collection... (5450 times) [2023-03-09 07:45:52,338][22940] Signal inference workers to resume experience collection... (5450 times) [2023-03-09 07:45:52,381][23090] InferenceWorker_p0-w0: stopping experience collection (5450 times) [2023-03-09 07:45:52,420][23090] InferenceWorker_p0-w0: resuming experience collection (5450 times) [2023-03-09 07:45:52,763][23090] Updated weights for policy 0, policy_version 14104 (0.0014) [2023-03-09 07:45:53,684][23090] Updated weights for policy 0, policy_version 14114 (0.0013) [2023-03-09 07:45:54,059][22664] Fps is (10 sec: 199877.5, 60 sec: 200702.1, 300 sec: 200606.7). Total num frames: 231309312. Throughput: 0: 50140.8. Samples: 57894960. Policy #0 lag: (min: 1.0, avg: 16.9, max: 33.0) [2023-03-09 07:45:54,062][22664] Avg episode reward: [(0, '49.548')] [2023-03-09 07:45:54,460][23090] Updated weights for policy 0, policy_version 14124 (0.0018) [2023-03-09 07:45:55,159][23090] Updated weights for policy 0, policy_version 14134 (0.0017) [2023-03-09 07:45:56,147][23090] Updated weights for policy 0, policy_version 14144 (0.0016) [2023-03-09 07:45:56,989][23090] Updated weights for policy 0, policy_version 14154 (0.0018) [2023-03-09 07:45:57,615][23090] Updated weights for policy 0, policy_version 14164 (0.0023) [2023-03-09 07:45:58,583][23090] Updated weights for policy 0, policy_version 14174 (0.0020) [2023-03-09 07:45:59,059][22664] Fps is (10 sec: 199880.0, 60 sec: 200430.2, 300 sec: 200606.6). Total num frames: 232308736. Throughput: 0: 50186.7. Samples: 58046512. Policy #0 lag: (min: 1.0, avg: 16.9, max: 33.0) [2023-03-09 07:45:59,061][22664] Avg episode reward: [(0, '47.722')] [2023-03-09 07:45:59,416][23090] Updated weights for policy 0, policy_version 14184 (0.0021) [2023-03-09 07:46:00,146][23090] Updated weights for policy 0, policy_version 14194 (0.0016) [2023-03-09 07:46:01,011][23090] Updated weights for policy 0, policy_version 14204 (0.0018) [2023-03-09 07:46:01,796][23090] Updated weights for policy 0, policy_version 14214 (0.0022) [2023-03-09 07:46:02,599][23090] Updated weights for policy 0, policy_version 14224 (0.0020) [2023-03-09 07:46:03,543][23090] Updated weights for policy 0, policy_version 14235 (0.0012) [2023-03-09 07:46:04,059][22664] Fps is (10 sec: 199892.8, 60 sec: 200703.3, 300 sec: 200551.1). Total num frames: 233308160. Throughput: 0: 50095.6. Samples: 58343408. Policy #0 lag: (min: 2.0, avg: 16.4, max: 32.0) [2023-03-09 07:46:04,060][22664] Avg episode reward: [(0, '48.429')] [2023-03-09 07:46:04,397][23090] Updated weights for policy 0, policy_version 14245 (0.0017) [2023-03-09 07:46:05,138][23090] Updated weights for policy 0, policy_version 14255 (0.0013) [2023-03-09 07:46:05,938][23090] Updated weights for policy 0, policy_version 14265 (0.0012) [2023-03-09 07:46:06,835][23090] Updated weights for policy 0, policy_version 14275 (0.0013) [2023-03-09 07:46:07,400][22940] Signal inference workers to stop experience collection... (5500 times) [2023-03-09 07:46:07,412][22940] Signal inference workers to resume experience collection... (5500 times) [2023-03-09 07:46:07,467][23090] InferenceWorker_p0-w0: stopping experience collection (5500 times) [2023-03-09 07:46:07,468][23090] InferenceWorker_p0-w0: resuming experience collection (5500 times) [2023-03-09 07:46:07,593][23090] Updated weights for policy 0, policy_version 14285 (0.0013) [2023-03-09 07:46:08,329][23090] Updated weights for policy 0, policy_version 14295 (0.0017) [2023-03-09 07:46:09,059][22664] Fps is (10 sec: 201523.0, 60 sec: 200702.7, 300 sec: 200606.7). Total num frames: 234323968. Throughput: 0: 50183.8. Samples: 58646336. Policy #0 lag: (min: 2.0, avg: 16.4, max: 32.0) [2023-03-09 07:46:09,061][22664] Avg episode reward: [(0, '50.890')] [2023-03-09 07:46:09,116][22940] Saving new best policy, reward=50.890! [2023-03-09 07:46:09,323][23090] Updated weights for policy 0, policy_version 14305 (0.0014) [2023-03-09 07:46:10,109][23090] Updated weights for policy 0, policy_version 14315 (0.0013) [2023-03-09 07:46:10,771][23090] Updated weights for policy 0, policy_version 14325 (0.0013) [2023-03-09 07:46:11,765][23090] Updated weights for policy 0, policy_version 14335 (0.0013) [2023-03-09 07:46:12,554][23090] Updated weights for policy 0, policy_version 14345 (0.0019) [2023-03-09 07:46:13,292][23090] Updated weights for policy 0, policy_version 14355 (0.0013) [2023-03-09 07:46:14,059][22664] Fps is (10 sec: 201520.4, 60 sec: 200430.2, 300 sec: 200717.7). Total num frames: 235323392. Throughput: 0: 50137.0. Samples: 58795792. Policy #0 lag: (min: 1.0, avg: 16.3, max: 34.0) [2023-03-09 07:46:14,061][22664] Avg episode reward: [(0, '47.023')] [2023-03-09 07:46:14,216][23090] Updated weights for policy 0, policy_version 14365 (0.0013) [2023-03-09 07:46:15,133][23090] Updated weights for policy 0, policy_version 14376 (0.0013) [2023-03-09 07:46:15,844][23090] Updated weights for policy 0, policy_version 14386 (0.0016) [2023-03-09 07:46:16,712][23090] Updated weights for policy 0, policy_version 14396 (0.0018) [2023-03-09 07:46:17,525][23090] Updated weights for policy 0, policy_version 14406 (0.0015) [2023-03-09 07:46:18,423][23090] Updated weights for policy 0, policy_version 14417 (0.0015) [2023-03-09 07:46:19,059][22664] Fps is (10 sec: 201526.5, 60 sec: 200977.9, 300 sec: 200717.8). Total num frames: 236339200. Throughput: 0: 50185.0. Samples: 59096848. Policy #0 lag: (min: 1.0, avg: 16.3, max: 34.0) [2023-03-09 07:46:19,061][22664] Avg episode reward: [(0, '46.348')] [2023-03-09 07:46:19,224][23090] Updated weights for policy 0, policy_version 14427 (0.0016) [2023-03-09 07:46:20,064][23090] Updated weights for policy 0, policy_version 14437 (0.0018) [2023-03-09 07:46:20,815][23090] Updated weights for policy 0, policy_version 14447 (0.0021) [2023-03-09 07:46:21,611][23090] Updated weights for policy 0, policy_version 14457 (0.0018) [2023-03-09 07:46:22,532][23090] Updated weights for policy 0, policy_version 14467 (0.0019) [2023-03-09 07:46:23,311][23090] Updated weights for policy 0, policy_version 14477 (0.0016) [2023-03-09 07:46:24,058][22664] Fps is (10 sec: 201530.3, 60 sec: 200705.1, 300 sec: 200662.4). Total num frames: 237338624. Throughput: 0: 50139.4. Samples: 59397840. Policy #0 lag: (min: 1.0, avg: 16.3, max: 33.0) [2023-03-09 07:46:24,059][22664] Avg episode reward: [(0, '49.105')] [2023-03-09 07:46:24,074][23090] Updated weights for policy 0, policy_version 14487 (0.0018) [2023-03-09 07:46:25,011][23090] Updated weights for policy 0, policy_version 14497 (0.0022) [2023-03-09 07:46:25,816][23090] Updated weights for policy 0, policy_version 14507 (0.0019) [2023-03-09 07:46:26,236][22940] Signal inference workers to stop experience collection... (5550 times) [2023-03-09 07:46:26,237][22940] Signal inference workers to resume experience collection... (5550 times) [2023-03-09 07:46:26,298][23090] InferenceWorker_p0-w0: stopping experience collection (5550 times) [2023-03-09 07:46:26,299][23090] InferenceWorker_p0-w0: resuming experience collection (5550 times) [2023-03-09 07:46:26,465][23090] Updated weights for policy 0, policy_version 14517 (0.0014) [2023-03-09 07:46:27,475][23090] Updated weights for policy 0, policy_version 14527 (0.0016) [2023-03-09 07:46:28,271][23090] Updated weights for policy 0, policy_version 14537 (0.0016) [2023-03-09 07:46:29,029][23090] Updated weights for policy 0, policy_version 14547 (0.0019) [2023-03-09 07:46:29,058][22664] Fps is (10 sec: 201527.6, 60 sec: 200431.2, 300 sec: 200717.9). Total num frames: 238354432. Throughput: 0: 50095.5. Samples: 59547328. Policy #0 lag: (min: 1.0, avg: 16.3, max: 33.0) [2023-03-09 07:46:29,059][22664] Avg episode reward: [(0, '47.901')] [2023-03-09 07:46:29,938][23090] Updated weights for policy 0, policy_version 14557 (0.0017) [2023-03-09 07:46:30,752][23090] Updated weights for policy 0, policy_version 14567 (0.0016) [2023-03-09 07:46:31,556][23090] Updated weights for policy 0, policy_version 14577 (0.0024) [2023-03-09 07:46:32,364][23090] Updated weights for policy 0, policy_version 14587 (0.0019) [2023-03-09 07:46:33,175][23090] Updated weights for policy 0, policy_version 14597 (0.0015) [2023-03-09 07:46:33,935][23090] Updated weights for policy 0, policy_version 14607 (0.0020) [2023-03-09 07:46:34,059][22664] Fps is (10 sec: 199878.0, 60 sec: 200703.9, 300 sec: 200551.2). Total num frames: 239337472. Throughput: 0: 50051.0. Samples: 59846320. Policy #0 lag: (min: 1.0, avg: 16.2, max: 33.0) [2023-03-09 07:46:34,061][22664] Avg episode reward: [(0, '48.502')] [2023-03-09 07:46:34,777][23090] Updated weights for policy 0, policy_version 14617 (0.0015) [2023-03-09 07:46:35,664][23090] Updated weights for policy 0, policy_version 14627 (0.0013) [2023-03-09 07:46:36,460][23090] Updated weights for policy 0, policy_version 14637 (0.0013) [2023-03-09 07:46:37,191][23090] Updated weights for policy 0, policy_version 14647 (0.0016) [2023-03-09 07:46:38,146][23090] Updated weights for policy 0, policy_version 14657 (0.0019) [2023-03-09 07:46:38,943][23090] Updated weights for policy 0, policy_version 14667 (0.0017) [2023-03-09 07:46:39,058][22664] Fps is (10 sec: 198247.0, 60 sec: 200432.1, 300 sec: 200606.8). Total num frames: 240336896. Throughput: 0: 50053.0. Samples: 60147312. Policy #0 lag: (min: 1.0, avg: 16.2, max: 33.0) [2023-03-09 07:46:39,059][22664] Avg episode reward: [(0, '50.221')] [2023-03-09 07:46:39,599][23090] Updated weights for policy 0, policy_version 14677 (0.0013) [2023-03-09 07:46:40,599][23090] Updated weights for policy 0, policy_version 14687 (0.0013) [2023-03-09 07:46:41,377][23090] Updated weights for policy 0, policy_version 14697 (0.0019) [2023-03-09 07:46:42,131][23090] Updated weights for policy 0, policy_version 14707 (0.0019) [2023-03-09 07:46:43,060][23090] Updated weights for policy 0, policy_version 14717 (0.0018) [2023-03-09 07:46:43,944][23090] Updated weights for policy 0, policy_version 14727 (0.0017) [2023-03-09 07:46:44,059][22664] Fps is (10 sec: 198251.9, 60 sec: 200158.5, 300 sec: 200551.5). Total num frames: 241319936. Throughput: 0: 49959.8. Samples: 60294688. Policy #0 lag: (min: 1.0, avg: 16.2, max: 33.0) [2023-03-09 07:46:44,059][22664] Avg episode reward: [(0, '47.321')] [2023-03-09 07:46:44,672][23090] Updated weights for policy 0, policy_version 14737 (0.0019) [2023-03-09 07:46:45,516][23090] Updated weights for policy 0, policy_version 14747 (0.0017) [2023-03-09 07:46:46,296][23090] Updated weights for policy 0, policy_version 14757 (0.0016) [2023-03-09 07:46:46,512][22940] Signal inference workers to stop experience collection... (5600 times) [2023-03-09 07:46:46,513][22940] Signal inference workers to resume experience collection... (5600 times) [2023-03-09 07:46:46,575][23090] InferenceWorker_p0-w0: stopping experience collection (5600 times) [2023-03-09 07:46:46,575][23090] InferenceWorker_p0-w0: resuming experience collection (5600 times) [2023-03-09 07:46:47,099][23090] Updated weights for policy 0, policy_version 14767 (0.0019) [2023-03-09 07:46:47,901][23090] Updated weights for policy 0, policy_version 14777 (0.0013) [2023-03-09 07:46:48,815][23090] Updated weights for policy 0, policy_version 14787 (0.0013) [2023-03-09 07:46:49,059][22664] Fps is (10 sec: 198242.4, 60 sec: 200157.7, 300 sec: 200606.7). Total num frames: 242319360. Throughput: 0: 50051.6. Samples: 60595728. Policy #0 lag: (min: 1.0, avg: 16.2, max: 33.0) [2023-03-09 07:46:49,060][22664] Avg episode reward: [(0, '48.623')] [2023-03-09 07:46:49,599][23090] Updated weights for policy 0, policy_version 14797 (0.0015) [2023-03-09 07:46:50,341][23090] Updated weights for policy 0, policy_version 14807 (0.0018) [2023-03-09 07:46:51,291][23090] Updated weights for policy 0, policy_version 14817 (0.0020) [2023-03-09 07:46:52,088][23090] Updated weights for policy 0, policy_version 14827 (0.0015) [2023-03-09 07:46:52,739][23090] Updated weights for policy 0, policy_version 14837 (0.0019) [2023-03-09 07:46:53,705][23090] Updated weights for policy 0, policy_version 14847 (0.0019) [2023-03-09 07:46:54,058][22664] Fps is (10 sec: 199886.5, 60 sec: 200160.0, 300 sec: 200551.5). Total num frames: 243318784. Throughput: 0: 50009.4. Samples: 60896736. Policy #0 lag: (min: 1.0, avg: 16.2, max: 33.0) [2023-03-09 07:46:54,059][22664] Avg episode reward: [(0, '48.357')] [2023-03-09 07:46:54,629][23090] Updated weights for policy 0, policy_version 14858 (0.0017) [2023-03-09 07:46:55,324][23090] Updated weights for policy 0, policy_version 14868 (0.0016) [2023-03-09 07:46:56,298][23090] Updated weights for policy 0, policy_version 14878 (0.0013) [2023-03-09 07:46:57,070][23090] Updated weights for policy 0, policy_version 14888 (0.0017) [2023-03-09 07:46:57,794][23090] Updated weights for policy 0, policy_version 14898 (0.0015) [2023-03-09 07:46:58,680][23090] Updated weights for policy 0, policy_version 14908 (0.0013) [2023-03-09 07:46:59,059][22664] Fps is (10 sec: 199887.2, 60 sec: 200158.9, 300 sec: 200551.4). Total num frames: 244318208. Throughput: 0: 50009.6. Samples: 61046208. Policy #0 lag: (min: 1.0, avg: 16.7, max: 33.0) [2023-03-09 07:46:59,060][22664] Avg episode reward: [(0, '48.944')] [2023-03-09 07:46:59,496][23090] Updated weights for policy 0, policy_version 14918 (0.0016) [2023-03-09 07:47:00,283][23090] Updated weights for policy 0, policy_version 14928 (0.0020) [2023-03-09 07:47:01,169][23090] Updated weights for policy 0, policy_version 14938 (0.0016) [2023-03-09 07:47:01,997][23090] Updated weights for policy 0, policy_version 14948 (0.0017) [2023-03-09 07:47:02,759][23090] Updated weights for policy 0, policy_version 14958 (0.0016) [2023-03-09 07:47:03,555][23090] Updated weights for policy 0, policy_version 14968 (0.0015) [2023-03-09 07:47:04,059][22664] Fps is (10 sec: 199876.1, 60 sec: 200157.2, 300 sec: 200551.2). Total num frames: 245317632. Throughput: 0: 49960.7. Samples: 61345088. Policy #0 lag: (min: 1.0, avg: 16.7, max: 33.0) [2023-03-09 07:47:04,061][22664] Avg episode reward: [(0, '48.169')] [2023-03-09 07:47:04,504][23090] Updated weights for policy 0, policy_version 14978 (0.0019) [2023-03-09 07:47:05,229][23090] Updated weights for policy 0, policy_version 14988 (0.0019) [2023-03-09 07:47:05,393][22940] Signal inference workers to stop experience collection... (5650 times) [2023-03-09 07:47:05,395][22940] Signal inference workers to resume experience collection... (5650 times) [2023-03-09 07:47:05,470][23090] InferenceWorker_p0-w0: stopping experience collection (5650 times) [2023-03-09 07:47:05,470][23090] InferenceWorker_p0-w0: resuming experience collection (5650 times) [2023-03-09 07:47:05,925][23090] Updated weights for policy 0, policy_version 14998 (0.0024) [2023-03-09 07:47:06,912][23090] Updated weights for policy 0, policy_version 15008 (0.0016) [2023-03-09 07:47:07,721][23090] Updated weights for policy 0, policy_version 15018 (0.0020) [2023-03-09 07:47:08,432][23090] Updated weights for policy 0, policy_version 15028 (0.0021) [2023-03-09 07:47:09,059][22664] Fps is (10 sec: 199885.2, 60 sec: 199886.0, 300 sec: 200551.2). Total num frames: 246317056. Throughput: 0: 49960.1. Samples: 61646048. Policy #0 lag: (min: 2.0, avg: 16.5, max: 32.0) [2023-03-09 07:47:09,060][22664] Avg episode reward: [(0, '48.529')] [2023-03-09 07:47:09,352][23090] Updated weights for policy 0, policy_version 15038 (0.0013) [2023-03-09 07:47:10,266][23090] Updated weights for policy 0, policy_version 15049 (0.0017) [2023-03-09 07:47:10,961][23090] Updated weights for policy 0, policy_version 15059 (0.0013) [2023-03-09 07:47:11,906][23090] Updated weights for policy 0, policy_version 15069 (0.0013) [2023-03-09 07:47:12,729][23090] Updated weights for policy 0, policy_version 15079 (0.0019) [2023-03-09 07:47:13,562][23090] Updated weights for policy 0, policy_version 15090 (0.0017) [2023-03-09 07:47:14,059][22664] Fps is (10 sec: 201530.6, 60 sec: 200158.9, 300 sec: 200551.3). Total num frames: 247332864. Throughput: 0: 49959.4. Samples: 61795504. Policy #0 lag: (min: 2.0, avg: 16.5, max: 32.0) [2023-03-09 07:47:14,060][22664] Avg episode reward: [(0, '47.764')] [2023-03-09 07:47:14,402][23090] Updated weights for policy 0, policy_version 15100 (0.0022) [2023-03-09 07:47:15,226][23090] Updated weights for policy 0, policy_version 15110 (0.0017) [2023-03-09 07:47:15,989][23090] Updated weights for policy 0, policy_version 15120 (0.0017) [2023-03-09 07:47:16,851][23090] Updated weights for policy 0, policy_version 15130 (0.0017) [2023-03-09 07:47:17,761][23090] Updated weights for policy 0, policy_version 15140 (0.0020) [2023-03-09 07:47:18,559][23090] Updated weights for policy 0, policy_version 15150 (0.0018) [2023-03-09 07:47:19,059][22664] Fps is (10 sec: 203154.9, 60 sec: 200157.4, 300 sec: 200662.3). Total num frames: 248348672. Throughput: 0: 49959.1. Samples: 62094480. Policy #0 lag: (min: 2.0, avg: 16.9, max: 34.0) [2023-03-09 07:47:19,061][22664] Avg episode reward: [(0, '47.193')] [2023-03-09 07:47:19,070][22940] Saving /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000015158_248348672.pth... [2023-03-09 07:47:19,131][22940] Removing /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000012220_200212480.pth [2023-03-09 07:47:19,282][23090] Updated weights for policy 0, policy_version 15160 (0.0019) [2023-03-09 07:47:20,199][23090] Updated weights for policy 0, policy_version 15170 (0.0017) [2023-03-09 07:47:21,011][23090] Updated weights for policy 0, policy_version 15180 (0.0019) [2023-03-09 07:47:21,657][23090] Updated weights for policy 0, policy_version 15190 (0.0024) [2023-03-09 07:47:22,675][23090] Updated weights for policy 0, policy_version 15200 (0.0016) [2023-03-09 07:47:23,484][23090] Updated weights for policy 0, policy_version 15210 (0.0014) [2023-03-09 07:47:23,616][22940] Signal inference workers to stop experience collection... (5700 times) [2023-03-09 07:47:23,638][22940] Signal inference workers to resume experience collection... (5700 times) [2023-03-09 07:47:23,693][23090] InferenceWorker_p0-w0: stopping experience collection (5700 times) [2023-03-09 07:47:23,693][23090] InferenceWorker_p0-w0: resuming experience collection (5700 times) [2023-03-09 07:47:24,059][22664] Fps is (10 sec: 198246.5, 60 sec: 199611.6, 300 sec: 200440.2). Total num frames: 249315328. Throughput: 0: 49911.8. Samples: 62393344. Policy #0 lag: (min: 2.0, avg: 16.9, max: 34.0) [2023-03-09 07:47:24,059][22664] Avg episode reward: [(0, '49.024')] [2023-03-09 07:47:24,187][23090] Updated weights for policy 0, policy_version 15220 (0.0018) [2023-03-09 07:47:25,113][23090] Updated weights for policy 0, policy_version 15230 (0.0017) [2023-03-09 07:47:25,981][23090] Updated weights for policy 0, policy_version 15240 (0.0020) [2023-03-09 07:47:26,700][23090] Updated weights for policy 0, policy_version 15250 (0.0016) [2023-03-09 07:47:27,527][23090] Updated weights for policy 0, policy_version 15260 (0.0013) [2023-03-09 07:47:28,337][23090] Updated weights for policy 0, policy_version 15270 (0.0013) [2023-03-09 07:47:29,059][22664] Fps is (10 sec: 198248.1, 60 sec: 199610.8, 300 sec: 200440.1). Total num frames: 250331136. Throughput: 0: 50004.0. Samples: 62544880. Policy #0 lag: (min: 1.0, avg: 17.4, max: 33.0) [2023-03-09 07:47:29,060][22664] Avg episode reward: [(0, '50.099')] [2023-03-09 07:47:29,127][23090] Updated weights for policy 0, policy_version 15280 (0.0016) [2023-03-09 07:47:29,974][23090] Updated weights for policy 0, policy_version 15290 (0.0018) [2023-03-09 07:47:30,839][23090] Updated weights for policy 0, policy_version 15300 (0.0013) [2023-03-09 07:47:31,619][23090] Updated weights for policy 0, policy_version 15310 (0.0016) [2023-03-09 07:47:32,445][23090] Updated weights for policy 0, policy_version 15320 (0.0017) [2023-03-09 07:47:33,292][23090] Updated weights for policy 0, policy_version 15330 (0.0016) [2023-03-09 07:47:34,059][22664] Fps is (10 sec: 199880.5, 60 sec: 199612.0, 300 sec: 200384.6). Total num frames: 251314176. Throughput: 0: 49956.9. Samples: 62843792. Policy #0 lag: (min: 1.0, avg: 17.4, max: 33.0) [2023-03-09 07:47:34,060][22664] Avg episode reward: [(0, '47.652')] [2023-03-09 07:47:34,126][23090] Updated weights for policy 0, policy_version 15340 (0.0013) [2023-03-09 07:47:34,779][23090] Updated weights for policy 0, policy_version 15350 (0.0016) [2023-03-09 07:47:35,874][23090] Updated weights for policy 0, policy_version 15361 (0.0013) [2023-03-09 07:47:36,698][23090] Updated weights for policy 0, policy_version 15371 (0.0021) [2023-03-09 07:47:37,292][22940] Signal inference workers to stop experience collection... (5750 times) [2023-03-09 07:47:37,293][22940] Signal inference workers to resume experience collection... (5750 times) [2023-03-09 07:47:37,327][23090] Updated weights for policy 0, policy_version 15381 (0.0013) [2023-03-09 07:47:37,363][23090] InferenceWorker_p0-w0: stopping experience collection (5750 times) [2023-03-09 07:47:37,363][23090] InferenceWorker_p0-w0: resuming experience collection (5750 times) [2023-03-09 07:47:38,423][23090] Updated weights for policy 0, policy_version 15392 (0.0015) [2023-03-09 07:47:39,059][22664] Fps is (10 sec: 198248.8, 60 sec: 199611.1, 300 sec: 200384.6). Total num frames: 252313600. Throughput: 0: 49956.0. Samples: 63144768. Policy #0 lag: (min: 0.0, avg: 17.6, max: 33.0) [2023-03-09 07:47:39,060][22664] Avg episode reward: [(0, '47.042')] [2023-03-09 07:47:39,199][23090] Updated weights for policy 0, policy_version 15402 (0.0015) [2023-03-09 07:47:39,890][23090] Updated weights for policy 0, policy_version 15412 (0.0015) [2023-03-09 07:47:40,872][23090] Updated weights for policy 0, policy_version 15422 (0.0013) [2023-03-09 07:47:41,636][23090] Updated weights for policy 0, policy_version 15432 (0.0019) [2023-03-09 07:47:42,427][23090] Updated weights for policy 0, policy_version 15442 (0.0014) [2023-03-09 07:47:43,386][23090] Updated weights for policy 0, policy_version 15453 (0.0016) [2023-03-09 07:47:44,058][22664] Fps is (10 sec: 201527.9, 60 sec: 200158.0, 300 sec: 200495.7). Total num frames: 253329408. Throughput: 0: 49956.3. Samples: 63294240. Policy #0 lag: (min: 0.0, avg: 17.6, max: 33.0) [2023-03-09 07:47:44,060][22664] Avg episode reward: [(0, '48.988')] [2023-03-09 07:47:44,181][23090] Updated weights for policy 0, policy_version 15463 (0.0016) [2023-03-09 07:47:44,946][23090] Updated weights for policy 0, policy_version 15473 (0.0016) [2023-03-09 07:47:45,824][23090] Updated weights for policy 0, policy_version 15483 (0.0019) [2023-03-09 07:47:46,630][23090] Updated weights for policy 0, policy_version 15493 (0.0025) [2023-03-09 07:47:47,395][23090] Updated weights for policy 0, policy_version 15503 (0.0013) [2023-03-09 07:47:48,251][23090] Updated weights for policy 0, policy_version 15513 (0.0024) [2023-03-09 07:47:49,059][22664] Fps is (10 sec: 201520.2, 60 sec: 200157.4, 300 sec: 200495.7). Total num frames: 254328832. Throughput: 0: 50003.3. Samples: 63595232. Policy #0 lag: (min: 1.0, avg: 16.2, max: 33.0) [2023-03-09 07:47:49,061][22664] Avg episode reward: [(0, '50.355')] [2023-03-09 07:47:49,062][23090] Updated weights for policy 0, policy_version 15523 (0.0016) [2023-03-09 07:47:49,855][23090] Updated weights for policy 0, policy_version 15533 (0.0022) [2023-03-09 07:47:50,109][22940] Signal inference workers to stop experience collection... (5800 times) [2023-03-09 07:47:50,110][22940] Signal inference workers to resume experience collection... (5800 times) [2023-03-09 07:47:50,171][23090] InferenceWorker_p0-w0: stopping experience collection (5800 times) [2023-03-09 07:47:50,172][23090] InferenceWorker_p0-w0: resuming experience collection (5800 times) [2023-03-09 07:47:50,580][23090] Updated weights for policy 0, policy_version 15543 (0.0015) [2023-03-09 07:47:51,536][23090] Updated weights for policy 0, policy_version 15553 (0.0021) [2023-03-09 07:47:52,317][23090] Updated weights for policy 0, policy_version 15563 (0.0013) [2023-03-09 07:47:53,002][23090] Updated weights for policy 0, policy_version 15573 (0.0018) [2023-03-09 07:47:53,948][23090] Updated weights for policy 0, policy_version 15583 (0.0015) [2023-03-09 07:47:54,059][22664] Fps is (10 sec: 198241.5, 60 sec: 199883.8, 300 sec: 200384.7). Total num frames: 255311872. Throughput: 0: 50047.8. Samples: 63898208. Policy #0 lag: (min: 1.0, avg: 16.2, max: 33.0) [2023-03-09 07:47:54,061][22664] Avg episode reward: [(0, '47.953')] [2023-03-09 07:47:54,745][23090] Updated weights for policy 0, policy_version 15593 (0.0018) [2023-03-09 07:47:55,469][23090] Updated weights for policy 0, policy_version 15603 (0.0017) [2023-03-09 07:47:56,425][23090] Updated weights for policy 0, policy_version 15613 (0.0019) [2023-03-09 07:47:57,188][23090] Updated weights for policy 0, policy_version 15623 (0.0021) [2023-03-09 07:47:57,983][23090] Updated weights for policy 0, policy_version 15633 (0.0015) [2023-03-09 07:47:58,822][23090] Updated weights for policy 0, policy_version 15643 (0.0020) [2023-03-09 07:47:59,059][22664] Fps is (10 sec: 199889.0, 60 sec: 200157.7, 300 sec: 200495.7). Total num frames: 256327680. Throughput: 0: 50092.7. Samples: 64049680. Policy #0 lag: (min: 1.0, avg: 16.2, max: 33.0) [2023-03-09 07:47:59,060][22664] Avg episode reward: [(0, '49.083')] [2023-03-09 07:47:59,699][23090] Updated weights for policy 0, policy_version 15654 (0.0023) [2023-03-09 07:48:00,505][23090] Updated weights for policy 0, policy_version 15664 (0.0015) [2023-03-09 07:48:01,415][23090] Updated weights for policy 0, policy_version 15675 (0.0019) [2023-03-09 07:48:02,259][23090] Updated weights for policy 0, policy_version 15685 (0.0013) [2023-03-09 07:48:02,999][23090] Updated weights for policy 0, policy_version 15695 (0.0020) [2023-03-09 07:48:03,897][23090] Updated weights for policy 0, policy_version 15705 (0.0016) [2023-03-09 07:48:04,059][22664] Fps is (10 sec: 203164.7, 60 sec: 200431.9, 300 sec: 200551.3). Total num frames: 257343488. Throughput: 0: 50137.9. Samples: 64350672. Policy #0 lag: (min: 1.0, avg: 16.5, max: 33.0) [2023-03-09 07:48:04,060][22664] Avg episode reward: [(0, '50.071')] [2023-03-09 07:48:04,709][23090] Updated weights for policy 0, policy_version 15715 (0.0015) [2023-03-09 07:48:05,477][22940] Signal inference workers to stop experience collection... (5850 times) [2023-03-09 07:48:05,478][22940] Signal inference workers to resume experience collection... (5850 times) [2023-03-09 07:48:05,543][23090] InferenceWorker_p0-w0: stopping experience collection (5850 times) [2023-03-09 07:48:05,543][23090] InferenceWorker_p0-w0: resuming experience collection (5850 times) [2023-03-09 07:48:05,546][23090] Updated weights for policy 0, policy_version 15725 (0.0017) [2023-03-09 07:48:06,241][23090] Updated weights for policy 0, policy_version 15735 (0.0017) [2023-03-09 07:48:07,196][23090] Updated weights for policy 0, policy_version 15745 (0.0020) [2023-03-09 07:48:07,995][23090] Updated weights for policy 0, policy_version 15755 (0.0015) [2023-03-09 07:48:08,679][23090] Updated weights for policy 0, policy_version 15765 (0.0016) [2023-03-09 07:48:09,059][22664] Fps is (10 sec: 201524.8, 60 sec: 200431.0, 300 sec: 200551.3). Total num frames: 258342912. Throughput: 0: 50140.4. Samples: 64649664. Policy #0 lag: (min: 1.0, avg: 16.5, max: 33.0) [2023-03-09 07:48:09,059][22664] Avg episode reward: [(0, '48.502')] [2023-03-09 07:48:09,671][23090] Updated weights for policy 0, policy_version 15775 (0.0013) [2023-03-09 07:48:10,431][23090] Updated weights for policy 0, policy_version 15785 (0.0016) [2023-03-09 07:48:11,184][23090] Updated weights for policy 0, policy_version 15795 (0.0016) [2023-03-09 07:48:12,148][23090] Updated weights for policy 0, policy_version 15805 (0.0013) [2023-03-09 07:48:12,914][23090] Updated weights for policy 0, policy_version 15815 (0.0020) [2023-03-09 07:48:13,670][23090] Updated weights for policy 0, policy_version 15825 (0.0014) [2023-03-09 07:48:14,059][22664] Fps is (10 sec: 201524.4, 60 sec: 200430.9, 300 sec: 200551.3). Total num frames: 259358720. Throughput: 0: 50094.8. Samples: 64799136. Policy #0 lag: (min: 1.0, avg: 17.5, max: 33.0) [2023-03-09 07:48:14,060][22664] Avg episode reward: [(0, '50.361')] [2023-03-09 07:48:14,513][23090] Updated weights for policy 0, policy_version 15835 (0.0017) [2023-03-09 07:48:15,362][23090] Updated weights for policy 0, policy_version 15845 (0.0014) [2023-03-09 07:48:16,158][23090] Updated weights for policy 0, policy_version 15855 (0.0016) [2023-03-09 07:48:16,982][23090] Updated weights for policy 0, policy_version 15865 (0.0017) [2023-03-09 07:48:17,828][23090] Updated weights for policy 0, policy_version 15875 (0.0017) [2023-03-09 07:48:18,643][23090] Updated weights for policy 0, policy_version 15885 (0.0013) [2023-03-09 07:48:19,059][22664] Fps is (10 sec: 201509.9, 60 sec: 200156.8, 300 sec: 200495.2). Total num frames: 260358144. Throughput: 0: 50139.2. Samples: 65100080. Policy #0 lag: (min: 1.0, avg: 17.5, max: 33.0) [2023-03-09 07:48:19,061][22664] Avg episode reward: [(0, '49.582')] [2023-03-09 07:48:19,328][23090] Updated weights for policy 0, policy_version 15895 (0.0015) [2023-03-09 07:48:20,312][23090] Updated weights for policy 0, policy_version 15905 (0.0013) [2023-03-09 07:48:20,537][22940] Signal inference workers to stop experience collection... (5900 times) [2023-03-09 07:48:20,538][22940] Signal inference workers to resume experience collection... (5900 times) [2023-03-09 07:48:20,602][23090] InferenceWorker_p0-w0: stopping experience collection (5900 times) [2023-03-09 07:48:20,602][23090] InferenceWorker_p0-w0: resuming experience collection (5900 times) [2023-03-09 07:48:21,116][23090] Updated weights for policy 0, policy_version 15915 (0.0016) [2023-03-09 07:48:21,811][23090] Updated weights for policy 0, policy_version 15925 (0.0018) [2023-03-09 07:48:22,799][23090] Updated weights for policy 0, policy_version 15935 (0.0013) [2023-03-09 07:48:23,568][23090] Updated weights for policy 0, policy_version 15945 (0.0017) [2023-03-09 07:48:24,059][22664] Fps is (10 sec: 198240.6, 60 sec: 200429.9, 300 sec: 200384.5). Total num frames: 261341184. Throughput: 0: 50095.8. Samples: 65399088. Policy #0 lag: (min: 1.0, avg: 16.6, max: 33.0) [2023-03-09 07:48:24,060][22664] Avg episode reward: [(0, '48.112')] [2023-03-09 07:48:24,266][23090] Updated weights for policy 0, policy_version 15955 (0.0017) [2023-03-09 07:48:25,222][23090] Updated weights for policy 0, policy_version 15965 (0.0013) [2023-03-09 07:48:26,016][23090] Updated weights for policy 0, policy_version 15975 (0.0013) [2023-03-09 07:48:26,827][23090] Updated weights for policy 0, policy_version 15985 (0.0013) [2023-03-09 07:48:27,656][23090] Updated weights for policy 0, policy_version 15995 (0.0016) [2023-03-09 07:48:28,485][23090] Updated weights for policy 0, policy_version 16005 (0.0013) [2023-03-09 07:48:29,059][22664] Fps is (10 sec: 196609.1, 60 sec: 199883.6, 300 sec: 200273.1). Total num frames: 262324224. Throughput: 0: 50140.8. Samples: 65550608. Policy #0 lag: (min: 1.0, avg: 16.6, max: 33.0) [2023-03-09 07:48:29,062][22664] Avg episode reward: [(0, '51.422')] [2023-03-09 07:48:29,108][22940] Saving new best policy, reward=51.422! [2023-03-09 07:48:29,327][23090] Updated weights for policy 0, policy_version 16015 (0.0012) [2023-03-09 07:48:30,093][23090] Updated weights for policy 0, policy_version 16025 (0.0016) [2023-03-09 07:48:30,929][23090] Updated weights for policy 0, policy_version 16035 (0.0019) [2023-03-09 07:48:31,728][23090] Updated weights for policy 0, policy_version 16045 (0.0011) [2023-03-09 07:48:32,433][23090] Updated weights for policy 0, policy_version 16055 (0.0013) [2023-03-09 07:48:33,409][23090] Updated weights for policy 0, policy_version 16065 (0.0013) [2023-03-09 07:48:34,059][22664] Fps is (10 sec: 199891.1, 60 sec: 200431.7, 300 sec: 200384.7). Total num frames: 263340032. Throughput: 0: 50094.5. Samples: 65849472. Policy #0 lag: (min: 1.0, avg: 16.6, max: 33.0) [2023-03-09 07:48:34,060][22664] Avg episode reward: [(0, '48.335')] [2023-03-09 07:48:34,191][23090] Updated weights for policy 0, policy_version 16075 (0.0017) [2023-03-09 07:48:34,916][23090] Updated weights for policy 0, policy_version 16085 (0.0019) [2023-03-09 07:48:35,879][23090] Updated weights for policy 0, policy_version 16095 (0.0017) [2023-03-09 07:48:36,674][23090] Updated weights for policy 0, policy_version 16105 (0.0018) [2023-03-09 07:48:37,431][23090] Updated weights for policy 0, policy_version 16115 (0.0016) [2023-03-09 07:48:38,097][22940] Signal inference workers to stop experience collection... (5950 times) [2023-03-09 07:48:38,098][22940] Signal inference workers to resume experience collection... (5950 times) [2023-03-09 07:48:38,154][23090] InferenceWorker_p0-w0: stopping experience collection (5950 times) [2023-03-09 07:48:38,154][23090] InferenceWorker_p0-w0: resuming experience collection (5950 times) [2023-03-09 07:48:38,357][23090] Updated weights for policy 0, policy_version 16125 (0.0017) [2023-03-09 07:48:39,058][22664] Fps is (10 sec: 201536.5, 60 sec: 200431.6, 300 sec: 200384.9). Total num frames: 264339456. Throughput: 0: 50004.6. Samples: 66148400. Policy #0 lag: (min: 1.0, avg: 16.6, max: 33.0) [2023-03-09 07:48:39,059][22664] Avg episode reward: [(0, '48.338')] [2023-03-09 07:48:39,148][23090] Updated weights for policy 0, policy_version 16135 (0.0013) [2023-03-09 07:48:39,922][23090] Updated weights for policy 0, policy_version 16145 (0.0015) [2023-03-09 07:48:40,762][23090] Updated weights for policy 0, policy_version 16155 (0.0015) [2023-03-09 07:48:41,591][23090] Updated weights for policy 0, policy_version 16165 (0.0013) [2023-03-09 07:48:42,376][23090] Updated weights for policy 0, policy_version 16175 (0.0016) [2023-03-09 07:48:43,250][23090] Updated weights for policy 0, policy_version 16185 (0.0013) [2023-03-09 07:48:44,058][22664] Fps is (10 sec: 199885.3, 60 sec: 200157.9, 300 sec: 200385.1). Total num frames: 265338880. Throughput: 0: 50005.4. Samples: 66299920. Policy #0 lag: (min: 1.0, avg: 16.6, max: 33.0) [2023-03-09 07:48:44,060][22664] Avg episode reward: [(0, '50.426')] [2023-03-09 07:48:44,064][23090] Updated weights for policy 0, policy_version 16195 (0.0014) [2023-03-09 07:48:44,950][23090] Updated weights for policy 0, policy_version 16205 (0.0013) [2023-03-09 07:48:45,641][23090] Updated weights for policy 0, policy_version 16215 (0.0021) [2023-03-09 07:48:46,533][23090] Updated weights for policy 0, policy_version 16225 (0.0021) [2023-03-09 07:48:47,358][23090] Updated weights for policy 0, policy_version 16235 (0.0013) [2023-03-09 07:48:48,083][23090] Updated weights for policy 0, policy_version 16245 (0.0016) [2023-03-09 07:48:49,035][23090] Updated weights for policy 0, policy_version 16255 (0.0018) [2023-03-09 07:48:49,058][22664] Fps is (10 sec: 198245.9, 60 sec: 199885.8, 300 sec: 200329.3). Total num frames: 266321920. Throughput: 0: 49913.7. Samples: 66596784. Policy #0 lag: (min: 1.0, avg: 17.4, max: 33.0) [2023-03-09 07:48:49,059][22664] Avg episode reward: [(0, '48.496')] [2023-03-09 07:48:49,803][23090] Updated weights for policy 0, policy_version 16265 (0.0016) [2023-03-09 07:48:50,549][23090] Updated weights for policy 0, policy_version 16275 (0.0016) [2023-03-09 07:48:51,488][23090] Updated weights for policy 0, policy_version 16285 (0.0013) [2023-03-09 07:48:52,269][23090] Updated weights for policy 0, policy_version 16295 (0.0018) [2023-03-09 07:48:53,098][23090] Updated weights for policy 0, policy_version 16305 (0.0018) [2023-03-09 07:48:53,933][23090] Updated weights for policy 0, policy_version 16315 (0.0016) [2023-03-09 07:48:54,059][22664] Fps is (10 sec: 198236.6, 60 sec: 200157.1, 300 sec: 200273.2). Total num frames: 267321344. Throughput: 0: 49910.9. Samples: 66895680. Policy #0 lag: (min: 1.0, avg: 17.4, max: 33.0) [2023-03-09 07:48:54,061][22664] Avg episode reward: [(0, '49.878')] [2023-03-09 07:48:54,738][23090] Updated weights for policy 0, policy_version 16325 (0.0015) [2023-03-09 07:48:55,540][23090] Updated weights for policy 0, policy_version 16335 (0.0013) [2023-03-09 07:48:56,378][23090] Updated weights for policy 0, policy_version 16345 (0.0018) [2023-03-09 07:48:57,163][22940] Signal inference workers to stop experience collection... (6000 times) [2023-03-09 07:48:57,173][22940] Signal inference workers to resume experience collection... (6000 times) [2023-03-09 07:48:57,237][23090] InferenceWorker_p0-w0: stopping experience collection (6000 times) [2023-03-09 07:48:57,238][23090] InferenceWorker_p0-w0: resuming experience collection (6000 times) [2023-03-09 07:48:57,243][23090] Updated weights for policy 0, policy_version 16355 (0.0018) [2023-03-09 07:48:58,021][23090] Updated weights for policy 0, policy_version 16365 (0.0013) [2023-03-09 07:48:58,752][23090] Updated weights for policy 0, policy_version 16375 (0.0016) [2023-03-09 07:48:59,059][22664] Fps is (10 sec: 199884.1, 60 sec: 199885.0, 300 sec: 200329.3). Total num frames: 268320768. Throughput: 0: 49956.6. Samples: 67047184. Policy #0 lag: (min: 1.0, avg: 16.1, max: 33.0) [2023-03-09 07:48:59,060][22664] Avg episode reward: [(0, '49.951')] [2023-03-09 07:48:59,668][23090] Updated weights for policy 0, policy_version 16385 (0.0013) [2023-03-09 07:49:00,459][23090] Updated weights for policy 0, policy_version 16395 (0.0012) [2023-03-09 07:49:01,181][23090] Updated weights for policy 0, policy_version 16405 (0.0022) [2023-03-09 07:49:02,122][23090] Updated weights for policy 0, policy_version 16415 (0.0015) [2023-03-09 07:49:02,885][23090] Updated weights for policy 0, policy_version 16425 (0.0013) [2023-03-09 07:49:03,621][23090] Updated weights for policy 0, policy_version 16435 (0.0013) [2023-03-09 07:49:04,059][22664] Fps is (10 sec: 201527.9, 60 sec: 199884.3, 300 sec: 200384.7). Total num frames: 269336576. Throughput: 0: 49958.2. Samples: 67348176. Policy #0 lag: (min: 1.0, avg: 16.1, max: 33.0) [2023-03-09 07:49:04,061][22664] Avg episode reward: [(0, '49.447')] [2023-03-09 07:49:04,572][23090] Updated weights for policy 0, policy_version 16445 (0.0016) [2023-03-09 07:49:05,344][23090] Updated weights for policy 0, policy_version 16455 (0.0016) [2023-03-09 07:49:06,128][23090] Updated weights for policy 0, policy_version 16465 (0.0016) [2023-03-09 07:49:06,971][23090] Updated weights for policy 0, policy_version 16475 (0.0016) [2023-03-09 07:49:07,783][23090] Updated weights for policy 0, policy_version 16485 (0.0016) [2023-03-09 07:49:08,554][23090] Updated weights for policy 0, policy_version 16495 (0.0014) [2023-03-09 07:49:09,058][22664] Fps is (10 sec: 203162.4, 60 sec: 200158.0, 300 sec: 200440.4). Total num frames: 270352384. Throughput: 0: 50000.7. Samples: 67649104. Policy #0 lag: (min: 1.0, avg: 16.7, max: 33.0) [2023-03-09 07:49:09,060][22664] Avg episode reward: [(0, '50.280')] [2023-03-09 07:49:09,432][23090] Updated weights for policy 0, policy_version 16505 (0.0022) [2023-03-09 07:49:10,307][23090] Updated weights for policy 0, policy_version 16515 (0.0015) [2023-03-09 07:49:11,074][23090] Updated weights for policy 0, policy_version 16525 (0.0016) [2023-03-09 07:49:11,803][23090] Updated weights for policy 0, policy_version 16535 (0.0014) [2023-03-09 07:49:12,755][23090] Updated weights for policy 0, policy_version 16545 (0.0019) [2023-03-09 07:49:13,527][23090] Updated weights for policy 0, policy_version 16555 (0.0015) [2023-03-09 07:49:14,059][22664] Fps is (10 sec: 201523.1, 60 sec: 199884.1, 300 sec: 200440.2). Total num frames: 271351808. Throughput: 0: 49956.0. Samples: 67798608. Policy #0 lag: (min: 1.0, avg: 16.7, max: 33.0) [2023-03-09 07:49:14,061][22664] Avg episode reward: [(0, '49.963')] [2023-03-09 07:49:14,301][23090] Updated weights for policy 0, policy_version 16565 (0.0016) [2023-03-09 07:49:15,224][23090] Updated weights for policy 0, policy_version 16575 (0.0015) [2023-03-09 07:49:16,130][23090] Updated weights for policy 0, policy_version 16586 (0.0016) [2023-03-09 07:49:16,880][23090] Updated weights for policy 0, policy_version 16596 (0.0013) [2023-03-09 07:49:17,824][23090] Updated weights for policy 0, policy_version 16606 (0.0021) [2023-03-09 07:49:18,002][22940] Signal inference workers to stop experience collection... (6050 times) [2023-03-09 07:49:18,003][22940] Signal inference workers to resume experience collection... (6050 times) [2023-03-09 07:49:18,064][23090] InferenceWorker_p0-w0: stopping experience collection (6050 times) [2023-03-09 07:49:18,065][23090] InferenceWorker_p0-w0: resuming experience collection (6050 times) [2023-03-09 07:49:18,595][23090] Updated weights for policy 0, policy_version 16616 (0.0018) [2023-03-09 07:49:19,059][22664] Fps is (10 sec: 196606.2, 60 sec: 199340.7, 300 sec: 200273.8). Total num frames: 272318464. Throughput: 0: 49911.8. Samples: 68095504. Policy #0 lag: (min: 1.0, avg: 16.7, max: 33.0) [2023-03-09 07:49:19,060][22664] Avg episode reward: [(0, '48.536')] [2023-03-09 07:49:19,146][22940] Saving /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000016623_272351232.pth... [2023-03-09 07:49:19,205][22940] Removing /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000013691_224313344.pth [2023-03-09 07:49:19,410][23090] Updated weights for policy 0, policy_version 16626 (0.0021) [2023-03-09 07:49:20,283][23090] Updated weights for policy 0, policy_version 16636 (0.0018) [2023-03-09 07:49:21,081][23090] Updated weights for policy 0, policy_version 16646 (0.0013) [2023-03-09 07:49:21,852][23090] Updated weights for policy 0, policy_version 16656 (0.0017) [2023-03-09 07:49:22,773][23090] Updated weights for policy 0, policy_version 16666 (0.0019) [2023-03-09 07:49:23,628][23090] Updated weights for policy 0, policy_version 16677 (0.0016) [2023-03-09 07:49:24,058][22664] Fps is (10 sec: 194975.0, 60 sec: 199339.8, 300 sec: 200107.1). Total num frames: 273301504. Throughput: 0: 49867.4. Samples: 68392432. Policy #0 lag: (min: 1.0, avg: 16.7, max: 33.0) [2023-03-09 07:49:24,059][22664] Avg episode reward: [(0, '49.682')] [2023-03-09 07:49:24,440][23090] Updated weights for policy 0, policy_version 16687 (0.0013) [2023-03-09 07:49:25,393][23090] Updated weights for policy 0, policy_version 16698 (0.0013) [2023-03-09 07:49:26,210][23090] Updated weights for policy 0, policy_version 16708 (0.0020) [2023-03-09 07:49:26,981][23090] Updated weights for policy 0, policy_version 16718 (0.0013) [2023-03-09 07:49:27,815][23090] Updated weights for policy 0, policy_version 16728 (0.0013) [2023-03-09 07:49:28,745][23090] Updated weights for policy 0, policy_version 16738 (0.0017) [2023-03-09 07:49:29,059][22664] Fps is (10 sec: 199885.1, 60 sec: 199886.7, 300 sec: 200162.7). Total num frames: 274317312. Throughput: 0: 49822.1. Samples: 68541920. Policy #0 lag: (min: 1.0, avg: 16.7, max: 33.0) [2023-03-09 07:49:29,060][22664] Avg episode reward: [(0, '47.919')] [2023-03-09 07:49:29,466][23090] Updated weights for policy 0, policy_version 16748 (0.0022) [2023-03-09 07:49:30,240][23090] Updated weights for policy 0, policy_version 16758 (0.0018) [2023-03-09 07:49:31,160][23090] Updated weights for policy 0, policy_version 16768 (0.0016) [2023-03-09 07:49:31,956][23090] Updated weights for policy 0, policy_version 16778 (0.0015) [2023-03-09 07:49:32,687][23090] Updated weights for policy 0, policy_version 16788 (0.0014) [2023-03-09 07:49:33,649][23090] Updated weights for policy 0, policy_version 16798 (0.0013) [2023-03-09 07:49:34,059][22664] Fps is (10 sec: 199881.4, 60 sec: 199338.2, 300 sec: 200107.0). Total num frames: 275300352. Throughput: 0: 49822.4. Samples: 68838800. Policy #0 lag: (min: 1.0, avg: 16.4, max: 33.0) [2023-03-09 07:49:34,060][22664] Avg episode reward: [(0, '49.138')] [2023-03-09 07:49:34,417][23090] Updated weights for policy 0, policy_version 16808 (0.0016) [2023-03-09 07:49:35,208][23090] Updated weights for policy 0, policy_version 16818 (0.0015) [2023-03-09 07:49:36,118][23090] Updated weights for policy 0, policy_version 16828 (0.0016) [2023-03-09 07:49:36,932][23090] Updated weights for policy 0, policy_version 16838 (0.0020) [2023-03-09 07:49:37,182][22940] Signal inference workers to stop experience collection... (6100 times) [2023-03-09 07:49:37,183][22940] Signal inference workers to resume experience collection... (6100 times) [2023-03-09 07:49:37,243][23090] InferenceWorker_p0-w0: stopping experience collection (6100 times) [2023-03-09 07:49:37,246][23090] InferenceWorker_p0-w0: resuming experience collection (6100 times) [2023-03-09 07:49:37,702][23090] Updated weights for policy 0, policy_version 16848 (0.0016) [2023-03-09 07:49:38,607][23090] Updated weights for policy 0, policy_version 16859 (0.0017) [2023-03-09 07:49:39,059][22664] Fps is (10 sec: 198245.9, 60 sec: 199338.3, 300 sec: 200106.9). Total num frames: 276299776. Throughput: 0: 49869.2. Samples: 69139776. Policy #0 lag: (min: 1.0, avg: 16.4, max: 33.0) [2023-03-09 07:49:39,060][22664] Avg episode reward: [(0, '46.824')] [2023-03-09 07:49:39,440][23090] Updated weights for policy 0, policy_version 16869 (0.0022) [2023-03-09 07:49:40,219][23090] Updated weights for policy 0, policy_version 16879 (0.0023) [2023-03-09 07:49:41,065][23090] Updated weights for policy 0, policy_version 16889 (0.0015) [2023-03-09 07:49:41,918][23090] Updated weights for policy 0, policy_version 16899 (0.0012) [2023-03-09 07:49:42,718][23090] Updated weights for policy 0, policy_version 16909 (0.0015) [2023-03-09 07:49:43,590][23090] Updated weights for policy 0, policy_version 16920 (0.0022) [2023-03-09 07:49:44,058][22664] Fps is (10 sec: 199888.2, 60 sec: 199338.7, 300 sec: 200107.0). Total num frames: 277299200. Throughput: 0: 49823.3. Samples: 69289232. Policy #0 lag: (min: 1.0, avg: 16.8, max: 33.0) [2023-03-09 07:49:44,059][22664] Avg episode reward: [(0, '48.667')] [2023-03-09 07:49:44,506][23090] Updated weights for policy 0, policy_version 16930 (0.0012) [2023-03-09 07:49:45,232][23090] Updated weights for policy 0, policy_version 16940 (0.0013) [2023-03-09 07:49:45,958][23090] Updated weights for policy 0, policy_version 16950 (0.0013) [2023-03-09 07:49:46,952][23090] Updated weights for policy 0, policy_version 16960 (0.0015) [2023-03-09 07:49:47,701][23090] Updated weights for policy 0, policy_version 16970 (0.0013) [2023-03-09 07:49:48,389][23090] Updated weights for policy 0, policy_version 16980 (0.0013) [2023-03-09 07:49:49,059][22664] Fps is (10 sec: 201524.4, 60 sec: 199884.7, 300 sec: 200162.5). Total num frames: 278315008. Throughput: 0: 49869.1. Samples: 69592272. Policy #0 lag: (min: 1.0, avg: 16.8, max: 33.0) [2023-03-09 07:49:49,060][22664] Avg episode reward: [(0, '49.119')] [2023-03-09 07:49:49,352][23090] Updated weights for policy 0, policy_version 16990 (0.0013) [2023-03-09 07:49:50,153][23090] Updated weights for policy 0, policy_version 17000 (0.0016) [2023-03-09 07:49:50,947][23090] Updated weights for policy 0, policy_version 17010 (0.0016) [2023-03-09 07:49:51,759][23090] Updated weights for policy 0, policy_version 17020 (0.0015) [2023-03-09 07:49:52,639][23090] Updated weights for policy 0, policy_version 17030 (0.0018) [2023-03-09 07:49:52,734][22940] Signal inference workers to stop experience collection... (6150 times) [2023-03-09 07:49:52,735][22940] Signal inference workers to resume experience collection... (6150 times) [2023-03-09 07:49:52,796][23090] InferenceWorker_p0-w0: stopping experience collection (6150 times) [2023-03-09 07:49:52,800][23090] InferenceWorker_p0-w0: resuming experience collection (6150 times) [2023-03-09 07:49:53,425][23090] Updated weights for policy 0, policy_version 17040 (0.0018) [2023-03-09 07:49:54,059][22664] Fps is (10 sec: 199881.9, 60 sec: 199612.9, 300 sec: 200051.4). Total num frames: 279298048. Throughput: 0: 49779.4. Samples: 69889184. Policy #0 lag: (min: 1.0, avg: 16.8, max: 33.0) [2023-03-09 07:49:54,060][22664] Avg episode reward: [(0, '49.921')] [2023-03-09 07:49:54,279][23090] Updated weights for policy 0, policy_version 17050 (0.0017) [2023-03-09 07:49:55,064][23090] Updated weights for policy 0, policy_version 17060 (0.0016) [2023-03-09 07:49:55,878][23090] Updated weights for policy 0, policy_version 17070 (0.0016) [2023-03-09 07:49:56,708][23090] Updated weights for policy 0, policy_version 17080 (0.0015) [2023-03-09 07:49:57,562][23090] Updated weights for policy 0, policy_version 17090 (0.0013) [2023-03-09 07:49:58,382][23090] Updated weights for policy 0, policy_version 17100 (0.0014) [2023-03-09 07:49:59,059][22664] Fps is (10 sec: 199877.9, 60 sec: 199883.7, 300 sec: 200162.2). Total num frames: 280313856. Throughput: 0: 49777.7. Samples: 70038608. Policy #0 lag: (min: 2.0, avg: 16.8, max: 33.0) [2023-03-09 07:49:59,061][22664] Avg episode reward: [(0, '49.010')] [2023-03-09 07:49:59,098][23090] Updated weights for policy 0, policy_version 17110 (0.0018) [2023-03-09 07:50:00,087][23090] Updated weights for policy 0, policy_version 17120 (0.0019) [2023-03-09 07:50:00,812][23090] Updated weights for policy 0, policy_version 17130 (0.0016) [2023-03-09 07:50:01,560][23090] Updated weights for policy 0, policy_version 17140 (0.0020) [2023-03-09 07:50:02,490][23090] Updated weights for policy 0, policy_version 17150 (0.0013) [2023-03-09 07:50:03,405][23090] Updated weights for policy 0, policy_version 17162 (0.0016) [2023-03-09 07:50:04,059][22664] Fps is (10 sec: 201520.5, 60 sec: 199611.7, 300 sec: 200106.8). Total num frames: 281313280. Throughput: 0: 49869.0. Samples: 70339616. Policy #0 lag: (min: 2.0, avg: 16.8, max: 33.0) [2023-03-09 07:50:04,061][22664] Avg episode reward: [(0, '51.443')] [2023-03-09 07:50:04,101][22940] Saving new best policy, reward=51.443! [2023-03-09 07:50:04,250][23090] Updated weights for policy 0, policy_version 17172 (0.0013) [2023-03-09 07:50:05,098][23090] Updated weights for policy 0, policy_version 17182 (0.0017) [2023-03-09 07:50:05,925][23090] Updated weights for policy 0, policy_version 17192 (0.0013) [2023-03-09 07:50:06,575][22940] Signal inference workers to stop experience collection... (6200 times) [2023-03-09 07:50:06,592][22940] Signal inference workers to resume experience collection... (6200 times) [2023-03-09 07:50:06,649][23090] InferenceWorker_p0-w0: stopping experience collection (6200 times) [2023-03-09 07:50:06,652][23090] InferenceWorker_p0-w0: resuming experience collection (6200 times) [2023-03-09 07:50:06,655][23090] Updated weights for policy 0, policy_version 17202 (0.0022) [2023-03-09 07:50:07,524][23090] Updated weights for policy 0, policy_version 17212 (0.0020) [2023-03-09 07:50:08,364][23090] Updated weights for policy 0, policy_version 17222 (0.0019) [2023-03-09 07:50:09,059][22664] Fps is (10 sec: 199886.2, 60 sec: 199337.6, 300 sec: 200051.3). Total num frames: 282312704. Throughput: 0: 49958.8. Samples: 70640592. Policy #0 lag: (min: 1.0, avg: 16.2, max: 33.0) [2023-03-09 07:50:09,061][22664] Avg episode reward: [(0, '47.946')] [2023-03-09 07:50:09,129][23090] Updated weights for policy 0, policy_version 17232 (0.0017) [2023-03-09 07:50:09,968][23090] Updated weights for policy 0, policy_version 17242 (0.0015) [2023-03-09 07:50:10,770][23090] Updated weights for policy 0, policy_version 17252 (0.0019) [2023-03-09 07:50:11,561][23090] Updated weights for policy 0, policy_version 17262 (0.0015) [2023-03-09 07:50:12,422][23090] Updated weights for policy 0, policy_version 17272 (0.0013) [2023-03-09 07:50:13,331][23090] Updated weights for policy 0, policy_version 17282 (0.0022) [2023-03-09 07:50:14,059][22664] Fps is (10 sec: 198246.5, 60 sec: 199065.6, 300 sec: 200051.6). Total num frames: 283295744. Throughput: 0: 49958.9. Samples: 70790080. Policy #0 lag: (min: 1.0, avg: 16.2, max: 33.0) [2023-03-09 07:50:14,060][22664] Avg episode reward: [(0, '48.182')] [2023-03-09 07:50:14,088][23090] Updated weights for policy 0, policy_version 17292 (0.0015) [2023-03-09 07:50:14,813][23090] Updated weights for policy 0, policy_version 17302 (0.0013) [2023-03-09 07:50:15,780][23090] Updated weights for policy 0, policy_version 17312 (0.0015) [2023-03-09 07:50:16,540][23090] Updated weights for policy 0, policy_version 17322 (0.0019) [2023-03-09 07:50:17,260][23090] Updated weights for policy 0, policy_version 17332 (0.0018) [2023-03-09 07:50:18,231][23090] Updated weights for policy 0, policy_version 17342 (0.0017) [2023-03-09 07:50:19,036][23090] Updated weights for policy 0, policy_version 17352 (0.0016) [2023-03-09 07:50:19,058][22664] Fps is (10 sec: 198252.3, 60 sec: 199612.0, 300 sec: 199996.1). Total num frames: 284295168. Throughput: 0: 50005.5. Samples: 71089040. Policy #0 lag: (min: 1.0, avg: 16.2, max: 33.0) [2023-03-09 07:50:19,060][22664] Avg episode reward: [(0, '48.331')] [2023-03-09 07:50:19,871][23090] Updated weights for policy 0, policy_version 17363 (0.0015) [2023-03-09 07:50:20,802][23090] Updated weights for policy 0, policy_version 17373 (0.0016) [2023-03-09 07:50:21,569][23090] Updated weights for policy 0, policy_version 17383 (0.0017) [2023-03-09 07:50:22,257][22940] Signal inference workers to stop experience collection... (6250 times) [2023-03-09 07:50:22,270][22940] Signal inference workers to resume experience collection... (6250 times) [2023-03-09 07:50:22,298][23090] InferenceWorker_p0-w0: stopping experience collection (6250 times) [2023-03-09 07:50:22,342][23090] InferenceWorker_p0-w0: resuming experience collection (6250 times) [2023-03-09 07:50:22,344][23090] Updated weights for policy 0, policy_version 17393 (0.0013) [2023-03-09 07:50:23,177][23090] Updated weights for policy 0, policy_version 17403 (0.0017) [2023-03-09 07:50:23,981][23090] Updated weights for policy 0, policy_version 17413 (0.0024) [2023-03-09 07:50:24,059][22664] Fps is (10 sec: 199885.1, 60 sec: 199884.0, 300 sec: 199884.7). Total num frames: 285294592. Throughput: 0: 50005.2. Samples: 71390016. Policy #0 lag: (min: 1.0, avg: 17.7, max: 32.0) [2023-03-09 07:50:24,060][22664] Avg episode reward: [(0, '48.741')] [2023-03-09 07:50:24,808][23090] Updated weights for policy 0, policy_version 17423 (0.0015) [2023-03-09 07:50:25,678][23090] Updated weights for policy 0, policy_version 17433 (0.0013) [2023-03-09 07:50:26,488][23090] Updated weights for policy 0, policy_version 17443 (0.0025) [2023-03-09 07:50:27,253][23090] Updated weights for policy 0, policy_version 17453 (0.0016) [2023-03-09 07:50:27,982][23090] Updated weights for policy 0, policy_version 17463 (0.0017) [2023-03-09 07:50:28,899][23090] Updated weights for policy 0, policy_version 17473 (0.0022) [2023-03-09 07:50:29,059][22664] Fps is (10 sec: 201520.5, 60 sec: 199884.5, 300 sec: 200051.5). Total num frames: 286310400. Throughput: 0: 50006.2. Samples: 71539520. Policy #0 lag: (min: 1.0, avg: 17.7, max: 32.0) [2023-03-09 07:50:29,060][22664] Avg episode reward: [(0, '48.680')] [2023-03-09 07:50:29,728][23090] Updated weights for policy 0, policy_version 17483 (0.0016) [2023-03-09 07:50:30,410][23090] Updated weights for policy 0, policy_version 17493 (0.0016) [2023-03-09 07:50:31,376][23090] Updated weights for policy 0, policy_version 17503 (0.0013) [2023-03-09 07:50:32,240][23090] Updated weights for policy 0, policy_version 17513 (0.0022) [2023-03-09 07:50:32,925][23090] Updated weights for policy 0, policy_version 17523 (0.0013) [2023-03-09 07:50:33,876][23090] Updated weights for policy 0, policy_version 17533 (0.0025) [2023-03-09 07:50:34,059][22664] Fps is (10 sec: 199886.1, 60 sec: 199884.7, 300 sec: 199940.4). Total num frames: 287293440. Throughput: 0: 49961.1. Samples: 71840528. Policy #0 lag: (min: 1.0, avg: 16.6, max: 33.0) [2023-03-09 07:50:34,060][22664] Avg episode reward: [(0, '47.751')] [2023-03-09 07:50:34,645][23090] Updated weights for policy 0, policy_version 17543 (0.0015) [2023-03-09 07:50:35,417][23090] Updated weights for policy 0, policy_version 17553 (0.0023) [2023-03-09 07:50:36,282][23090] Updated weights for policy 0, policy_version 17563 (0.0019) [2023-03-09 07:50:36,488][22940] Signal inference workers to stop experience collection... (6300 times) [2023-03-09 07:50:36,489][22940] Signal inference workers to resume experience collection... (6300 times) [2023-03-09 07:50:36,554][23090] InferenceWorker_p0-w0: stopping experience collection (6300 times) [2023-03-09 07:50:36,557][23090] InferenceWorker_p0-w0: resuming experience collection (6300 times) [2023-03-09 07:50:37,045][23090] Updated weights for policy 0, policy_version 17573 (0.0013) [2023-03-09 07:50:37,852][23090] Updated weights for policy 0, policy_version 17583 (0.0016) [2023-03-09 07:50:38,754][23090] Updated weights for policy 0, policy_version 17593 (0.0016) [2023-03-09 07:50:39,058][22664] Fps is (10 sec: 198249.4, 60 sec: 199885.1, 300 sec: 199940.5). Total num frames: 288292864. Throughput: 0: 50051.4. Samples: 72141488. Policy #0 lag: (min: 1.0, avg: 16.6, max: 33.0) [2023-03-09 07:50:39,059][22664] Avg episode reward: [(0, '48.778')] [2023-03-09 07:50:39,558][23090] Updated weights for policy 0, policy_version 17603 (0.0017) [2023-03-09 07:50:40,335][23090] Updated weights for policy 0, policy_version 17613 (0.0015) [2023-03-09 07:50:41,087][23090] Updated weights for policy 0, policy_version 17623 (0.0025) [2023-03-09 07:50:41,999][23090] Updated weights for policy 0, policy_version 17633 (0.0020) [2023-03-09 07:50:42,874][23090] Updated weights for policy 0, policy_version 17643 (0.0024) [2023-03-09 07:50:43,553][23090] Updated weights for policy 0, policy_version 17653 (0.0022) [2023-03-09 07:50:44,059][22664] Fps is (10 sec: 201522.2, 60 sec: 200157.1, 300 sec: 199995.8). Total num frames: 289308672. Throughput: 0: 50098.7. Samples: 72293040. Policy #0 lag: (min: 1.0, avg: 16.6, max: 33.0) [2023-03-09 07:50:44,060][22664] Avg episode reward: [(0, '49.944')] [2023-03-09 07:50:44,584][23090] Updated weights for policy 0, policy_version 17664 (0.0014) [2023-03-09 07:50:45,347][23090] Updated weights for policy 0, policy_version 17674 (0.0016) [2023-03-09 07:50:46,098][23090] Updated weights for policy 0, policy_version 17684 (0.0013) [2023-03-09 07:50:47,081][23090] Updated weights for policy 0, policy_version 17695 (0.0015) [2023-03-09 07:50:47,925][23090] Updated weights for policy 0, policy_version 17705 (0.0015) [2023-03-09 07:50:48,612][23090] Updated weights for policy 0, policy_version 17715 (0.0016) [2023-03-09 07:50:49,059][22664] Fps is (10 sec: 203156.0, 60 sec: 200157.1, 300 sec: 200051.6). Total num frames: 290324480. Throughput: 0: 50053.3. Samples: 72592016. Policy #0 lag: (min: 1.0, avg: 16.4, max: 33.0) [2023-03-09 07:50:49,060][22664] Avg episode reward: [(0, '49.756')] [2023-03-09 07:50:49,540][22940] Signal inference workers to stop experience collection... (6350 times) [2023-03-09 07:50:49,541][22940] Signal inference workers to resume experience collection... (6350 times) [2023-03-09 07:50:49,567][23090] Updated weights for policy 0, policy_version 17725 (0.0021) [2023-03-09 07:50:49,608][23090] InferenceWorker_p0-w0: stopping experience collection (6350 times) [2023-03-09 07:50:49,608][23090] InferenceWorker_p0-w0: resuming experience collection (6350 times) [2023-03-09 07:50:50,316][23090] Updated weights for policy 0, policy_version 17735 (0.0017) [2023-03-09 07:50:51,063][23090] Updated weights for policy 0, policy_version 17745 (0.0013) [2023-03-09 07:50:51,924][23090] Updated weights for policy 0, policy_version 17755 (0.0015) [2023-03-09 07:50:52,738][23090] Updated weights for policy 0, policy_version 17765 (0.0019) [2023-03-09 07:50:53,520][23090] Updated weights for policy 0, policy_version 17775 (0.0016) [2023-03-09 07:50:54,059][22664] Fps is (10 sec: 203159.7, 60 sec: 200703.4, 300 sec: 200107.0). Total num frames: 291340288. Throughput: 0: 50098.5. Samples: 72895024. Policy #0 lag: (min: 1.0, avg: 16.4, max: 33.0) [2023-03-09 07:50:54,060][22664] Avg episode reward: [(0, '49.189')] [2023-03-09 07:50:54,367][23090] Updated weights for policy 0, policy_version 17785 (0.0013) [2023-03-09 07:50:55,316][23090] Updated weights for policy 0, policy_version 17796 (0.0019) [2023-03-09 07:50:56,083][23090] Updated weights for policy 0, policy_version 17806 (0.0013) [2023-03-09 07:50:56,839][23090] Updated weights for policy 0, policy_version 17816 (0.0019) [2023-03-09 07:50:57,761][23090] Updated weights for policy 0, policy_version 17827 (0.0020) [2023-03-09 07:50:58,534][23090] Updated weights for policy 0, policy_version 17837 (0.0016) [2023-03-09 07:50:59,059][22664] Fps is (10 sec: 201512.1, 60 sec: 200429.5, 300 sec: 200106.5). Total num frames: 292339712. Throughput: 0: 50143.4. Samples: 73046560. Policy #0 lag: (min: 0.0, avg: 16.9, max: 33.0) [2023-03-09 07:50:59,062][22664] Avg episode reward: [(0, '45.760')] [2023-03-09 07:50:59,292][23090] Updated weights for policy 0, policy_version 17847 (0.0014) [2023-03-09 07:51:00,314][23090] Updated weights for policy 0, policy_version 17858 (0.0013) [2023-03-09 07:51:01,118][23090] Updated weights for policy 0, policy_version 17868 (0.0013) [2023-03-09 07:51:01,253][22940] Signal inference workers to stop experience collection... (6400 times) [2023-03-09 07:51:01,254][22940] Signal inference workers to resume experience collection... (6400 times) [2023-03-09 07:51:01,315][23090] InferenceWorker_p0-w0: stopping experience collection (6400 times) [2023-03-09 07:51:01,315][23090] InferenceWorker_p0-w0: resuming experience collection (6400 times) [2023-03-09 07:51:01,799][23090] Updated weights for policy 0, policy_version 17878 (0.0013) [2023-03-09 07:51:02,754][23090] Updated weights for policy 0, policy_version 17888 (0.0028) [2023-03-09 07:51:03,505][23090] Updated weights for policy 0, policy_version 17898 (0.0013) [2023-03-09 07:51:04,059][22664] Fps is (10 sec: 201529.1, 60 sec: 200704.8, 300 sec: 200107.2). Total num frames: 293355520. Throughput: 0: 50279.4. Samples: 73351616. Policy #0 lag: (min: 0.0, avg: 16.9, max: 33.0) [2023-03-09 07:51:04,059][22664] Avg episode reward: [(0, '50.394')] [2023-03-09 07:51:04,312][23090] Updated weights for policy 0, policy_version 17908 (0.0018) [2023-03-09 07:51:05,203][23090] Updated weights for policy 0, policy_version 17918 (0.0015) [2023-03-09 07:51:06,057][23090] Updated weights for policy 0, policy_version 17929 (0.0013) [2023-03-09 07:51:06,893][23090] Updated weights for policy 0, policy_version 17940 (0.0016) [2023-03-09 07:51:07,804][23090] Updated weights for policy 0, policy_version 17950 (0.0021) [2023-03-09 07:51:08,592][23090] Updated weights for policy 0, policy_version 17960 (0.0015) [2023-03-09 07:51:09,058][22664] Fps is (10 sec: 201540.2, 60 sec: 200705.1, 300 sec: 200107.2). Total num frames: 294354944. Throughput: 0: 50278.7. Samples: 73652544. Policy #0 lag: (min: 0.0, avg: 16.9, max: 33.0) [2023-03-09 07:51:09,059][22664] Avg episode reward: [(0, '47.988')] [2023-03-09 07:51:09,315][23090] Updated weights for policy 0, policy_version 17970 (0.0020) [2023-03-09 07:51:10,183][23090] Updated weights for policy 0, policy_version 17980 (0.0013) [2023-03-09 07:51:11,029][23090] Updated weights for policy 0, policy_version 17990 (0.0013) [2023-03-09 07:51:11,842][23090] Updated weights for policy 0, policy_version 18000 (0.0022) [2023-03-09 07:51:12,719][23090] Updated weights for policy 0, policy_version 18010 (0.0021) [2023-03-09 07:51:13,491][23090] Updated weights for policy 0, policy_version 18020 (0.0019) [2023-03-09 07:51:14,059][22664] Fps is (10 sec: 198240.9, 60 sec: 200703.8, 300 sec: 199995.8). Total num frames: 295337984. Throughput: 0: 50277.9. Samples: 73802032. Policy #0 lag: (min: 1.0, avg: 17.4, max: 33.0) [2023-03-09 07:51:14,061][22664] Avg episode reward: [(0, '50.519')] [2023-03-09 07:51:14,140][22940] Signal inference workers to stop experience collection... (6450 times) [2023-03-09 07:51:14,141][22940] Signal inference workers to resume experience collection... (6450 times) [2023-03-09 07:51:14,208][23090] InferenceWorker_p0-w0: stopping experience collection (6450 times) [2023-03-09 07:51:14,209][23090] InferenceWorker_p0-w0: resuming experience collection (6450 times) [2023-03-09 07:51:14,279][23090] Updated weights for policy 0, policy_version 18030 (0.0014) [2023-03-09 07:51:15,119][23090] Updated weights for policy 0, policy_version 18040 (0.0013) [2023-03-09 07:51:15,916][23090] Updated weights for policy 0, policy_version 18050 (0.0013) [2023-03-09 07:51:16,757][23090] Updated weights for policy 0, policy_version 18060 (0.0013) [2023-03-09 07:51:17,495][23090] Updated weights for policy 0, policy_version 18070 (0.0017) [2023-03-09 07:51:18,405][23090] Updated weights for policy 0, policy_version 18080 (0.0017) [2023-03-09 07:51:19,059][22664] Fps is (10 sec: 199876.6, 60 sec: 200975.8, 300 sec: 200051.1). Total num frames: 296353792. Throughput: 0: 50276.0. Samples: 74102960. Policy #0 lag: (min: 1.0, avg: 17.4, max: 33.0) [2023-03-09 07:51:19,061][22664] Avg episode reward: [(0, '47.711')] [2023-03-09 07:51:19,126][22940] Saving /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000018089_296370176.pth... [2023-03-09 07:51:19,198][22940] Removing /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000015158_248348672.pth [2023-03-09 07:51:19,282][23090] Updated weights for policy 0, policy_version 18090 (0.0015) [2023-03-09 07:51:19,931][23090] Updated weights for policy 0, policy_version 18100 (0.0012) [2023-03-09 07:51:20,872][23090] Updated weights for policy 0, policy_version 18110 (0.0017) [2023-03-09 07:51:21,635][23090] Updated weights for policy 0, policy_version 18120 (0.0012) [2023-03-09 07:51:22,464][23090] Updated weights for policy 0, policy_version 18131 (0.0016) [2023-03-09 07:51:23,415][23090] Updated weights for policy 0, policy_version 18141 (0.0021) [2023-03-09 07:51:24,059][22664] Fps is (10 sec: 201528.8, 60 sec: 200977.8, 300 sec: 199995.9). Total num frames: 297353216. Throughput: 0: 50320.0. Samples: 74405888. Policy #0 lag: (min: 2.0, avg: 16.9, max: 33.0) [2023-03-09 07:51:24,059][22664] Avg episode reward: [(0, '50.577')] [2023-03-09 07:51:24,193][23090] Updated weights for policy 0, policy_version 18151 (0.0016) [2023-03-09 07:51:24,960][23090] Updated weights for policy 0, policy_version 18161 (0.0013) [2023-03-09 07:51:25,782][23090] Updated weights for policy 0, policy_version 18171 (0.0021) [2023-03-09 07:51:26,599][23090] Updated weights for policy 0, policy_version 18181 (0.0020) [2023-03-09 07:51:27,388][23090] Updated weights for policy 0, policy_version 18191 (0.0018) [2023-03-09 07:51:27,617][22940] Signal inference workers to stop experience collection... (6500 times) [2023-03-09 07:51:27,635][22940] Signal inference workers to resume experience collection... (6500 times) [2023-03-09 07:51:27,667][23090] InferenceWorker_p0-w0: stopping experience collection (6500 times) [2023-03-09 07:51:27,705][23090] InferenceWorker_p0-w0: resuming experience collection (6500 times) [2023-03-09 07:51:28,251][23090] Updated weights for policy 0, policy_version 18201 (0.0017) [2023-03-09 07:51:29,055][23090] Updated weights for policy 0, policy_version 18211 (0.0013) [2023-03-09 07:51:29,059][22664] Fps is (10 sec: 201525.8, 60 sec: 200976.7, 300 sec: 200107.0). Total num frames: 298369024. Throughput: 0: 50273.8. Samples: 74555360. Policy #0 lag: (min: 2.0, avg: 16.9, max: 33.0) [2023-03-09 07:51:29,060][22664] Avg episode reward: [(0, '48.030')] [2023-03-09 07:51:29,907][23090] Updated weights for policy 0, policy_version 18222 (0.0013) [2023-03-09 07:51:30,772][23090] Updated weights for policy 0, policy_version 18232 (0.0020) [2023-03-09 07:51:31,585][23090] Updated weights for policy 0, policy_version 18242 (0.0013) [2023-03-09 07:51:32,431][23090] Updated weights for policy 0, policy_version 18252 (0.0024) [2023-03-09 07:51:33,164][23090] Updated weights for policy 0, policy_version 18262 (0.0013) [2023-03-09 07:51:34,058][22664] Fps is (10 sec: 199885.3, 60 sec: 200977.7, 300 sec: 200051.4). Total num frames: 299352064. Throughput: 0: 50273.7. Samples: 74854320. Policy #0 lag: (min: 2.0, avg: 16.9, max: 33.0) [2023-03-09 07:51:34,059][22664] Avg episode reward: [(0, '49.210')] [2023-03-09 07:51:34,077][23090] Updated weights for policy 0, policy_version 18272 (0.0013) [2023-03-09 07:51:34,967][23090] Updated weights for policy 0, policy_version 18282 (0.0017) [2023-03-09 07:51:35,665][23090] Updated weights for policy 0, policy_version 18292 (0.0018) [2023-03-09 07:51:36,581][23090] Updated weights for policy 0, policy_version 18302 (0.0015) [2023-03-09 07:51:37,410][23090] Updated weights for policy 0, policy_version 18312 (0.0017) [2023-03-09 07:51:38,187][23090] Updated weights for policy 0, policy_version 18322 (0.0014) [2023-03-09 07:51:39,019][23090] Updated weights for policy 0, policy_version 18332 (0.0016) [2023-03-09 07:51:39,059][22664] Fps is (10 sec: 198246.6, 60 sec: 200976.2, 300 sec: 200106.8). Total num frames: 300351488. Throughput: 0: 50228.7. Samples: 75155312. Policy #0 lag: (min: 0.0, avg: 16.3, max: 33.0) [2023-03-09 07:51:39,060][22664] Avg episode reward: [(0, '49.956')] [2023-03-09 07:51:39,833][23090] Updated weights for policy 0, policy_version 18342 (0.0017) [2023-03-09 07:51:40,638][23090] Updated weights for policy 0, policy_version 18352 (0.0018) [2023-03-09 07:51:41,525][23090] Updated weights for policy 0, policy_version 18363 (0.0016) [2023-03-09 07:51:42,284][22940] Signal inference workers to stop experience collection... (6550 times) [2023-03-09 07:51:42,297][22940] Signal inference workers to resume experience collection... (6550 times) [2023-03-09 07:51:42,361][23090] InferenceWorker_p0-w0: stopping experience collection (6550 times) [2023-03-09 07:51:42,362][23090] InferenceWorker_p0-w0: resuming experience collection (6550 times) [2023-03-09 07:51:42,364][23090] Updated weights for policy 0, policy_version 18373 (0.0016) [2023-03-09 07:51:43,173][23090] Updated weights for policy 0, policy_version 18383 (0.0013) [2023-03-09 07:51:44,009][23090] Updated weights for policy 0, policy_version 18393 (0.0016) [2023-03-09 07:51:44,059][22664] Fps is (10 sec: 199878.1, 60 sec: 200703.6, 300 sec: 200106.8). Total num frames: 301350912. Throughput: 0: 50183.3. Samples: 75304784. Policy #0 lag: (min: 0.0, avg: 16.3, max: 33.0) [2023-03-09 07:51:44,061][22664] Avg episode reward: [(0, '49.799')] [2023-03-09 07:51:44,812][23090] Updated weights for policy 0, policy_version 18403 (0.0015) [2023-03-09 07:51:45,602][23090] Updated weights for policy 0, policy_version 18413 (0.0013) [2023-03-09 07:51:46,337][23090] Updated weights for policy 0, policy_version 18423 (0.0013) [2023-03-09 07:51:47,361][23090] Updated weights for policy 0, policy_version 18434 (0.0017) [2023-03-09 07:51:48,241][23090] Updated weights for policy 0, policy_version 18445 (0.0013) [2023-03-09 07:51:48,976][23090] Updated weights for policy 0, policy_version 18455 (0.0015) [2023-03-09 07:51:49,059][22664] Fps is (10 sec: 201521.6, 60 sec: 200703.8, 300 sec: 200162.3). Total num frames: 302366720. Throughput: 0: 50046.6. Samples: 75603728. Policy #0 lag: (min: 1.0, avg: 16.5, max: 33.0) [2023-03-09 07:51:49,060][22664] Avg episode reward: [(0, '47.064')] [2023-03-09 07:51:49,882][23090] Updated weights for policy 0, policy_version 18465 (0.0013) [2023-03-09 07:51:50,786][23090] Updated weights for policy 0, policy_version 18476 (0.0013) [2023-03-09 07:51:51,517][23090] Updated weights for policy 0, policy_version 18486 (0.0018) [2023-03-09 07:51:52,423][23090] Updated weights for policy 0, policy_version 18496 (0.0015) [2023-03-09 07:51:53,261][23090] Updated weights for policy 0, policy_version 18506 (0.0018) [2023-03-09 07:51:54,028][23090] Updated weights for policy 0, policy_version 18516 (0.0016) [2023-03-09 07:51:54,059][22664] Fps is (10 sec: 201529.4, 60 sec: 200431.9, 300 sec: 200162.5). Total num frames: 303366144. Throughput: 0: 50001.7. Samples: 75902624. Policy #0 lag: (min: 1.0, avg: 16.5, max: 33.0) [2023-03-09 07:51:54,059][22664] Avg episode reward: [(0, '49.767')] [2023-03-09 07:51:54,938][23090] Updated weights for policy 0, policy_version 18526 (0.0013) [2023-03-09 07:51:55,745][23090] Updated weights for policy 0, policy_version 18536 (0.0018) [2023-03-09 07:51:55,842][22940] Signal inference workers to stop experience collection... (6600 times) [2023-03-09 07:51:55,842][22940] Signal inference workers to resume experience collection... (6600 times) [2023-03-09 07:51:55,902][23090] InferenceWorker_p0-w0: stopping experience collection (6600 times) [2023-03-09 07:51:55,902][23090] InferenceWorker_p0-w0: resuming experience collection (6600 times) [2023-03-09 07:51:56,506][23090] Updated weights for policy 0, policy_version 18546 (0.0013) [2023-03-09 07:51:57,378][23090] Updated weights for policy 0, policy_version 18556 (0.0012) [2023-03-09 07:51:58,203][23090] Updated weights for policy 0, policy_version 18566 (0.0013) [2023-03-09 07:51:59,043][23090] Updated weights for policy 0, policy_version 18576 (0.0013) [2023-03-09 07:51:59,059][22664] Fps is (10 sec: 198251.7, 60 sec: 200160.4, 300 sec: 200107.2). Total num frames: 304349184. Throughput: 0: 50047.9. Samples: 76054176. Policy #0 lag: (min: 1.0, avg: 16.5, max: 33.0) [2023-03-09 07:51:59,060][22664] Avg episode reward: [(0, '49.476')] [2023-03-09 07:51:59,850][23090] Updated weights for policy 0, policy_version 18586 (0.0022) [2023-03-09 07:52:00,665][23090] Updated weights for policy 0, policy_version 18597 (0.0013) [2023-03-09 07:52:01,474][23090] Updated weights for policy 0, policy_version 18607 (0.0016) [2023-03-09 07:52:02,409][23090] Updated weights for policy 0, policy_version 18618 (0.0016) [2023-03-09 07:52:03,217][23090] Updated weights for policy 0, policy_version 18628 (0.0013) [2023-03-09 07:52:04,003][23090] Updated weights for policy 0, policy_version 18638 (0.0015) [2023-03-09 07:52:04,059][22664] Fps is (10 sec: 199882.9, 60 sec: 200157.5, 300 sec: 200162.4). Total num frames: 305364992. Throughput: 0: 50050.4. Samples: 76355216. Policy #0 lag: (min: 1.0, avg: 16.6, max: 33.0) [2023-03-09 07:52:04,060][22664] Avg episode reward: [(0, '51.217')] [2023-03-09 07:52:04,837][23090] Updated weights for policy 0, policy_version 18648 (0.0013) [2023-03-09 07:52:05,662][23090] Updated weights for policy 0, policy_version 18658 (0.0013) [2023-03-09 07:52:06,481][23090] Updated weights for policy 0, policy_version 18668 (0.0013) [2023-03-09 07:52:07,259][23090] Updated weights for policy 0, policy_version 18678 (0.0022) [2023-03-09 07:52:08,134][23090] Updated weights for policy 0, policy_version 18688 (0.0017) [2023-03-09 07:52:08,873][22940] Signal inference workers to stop experience collection... (6650 times) [2023-03-09 07:52:08,874][22940] Signal inference workers to resume experience collection... (6650 times) [2023-03-09 07:52:08,959][23090] InferenceWorker_p0-w0: stopping experience collection (6650 times) [2023-03-09 07:52:08,959][23090] InferenceWorker_p0-w0: resuming experience collection (6650 times) [2023-03-09 07:52:08,963][23090] Updated weights for policy 0, policy_version 18698 (0.0020) [2023-03-09 07:52:09,059][22664] Fps is (10 sec: 201519.1, 60 sec: 200156.9, 300 sec: 200106.8). Total num frames: 306364416. Throughput: 0: 50050.6. Samples: 76658176. Policy #0 lag: (min: 1.0, avg: 16.6, max: 33.0) [2023-03-09 07:52:09,061][22664] Avg episode reward: [(0, '51.344')] [2023-03-09 07:52:09,739][23090] Updated weights for policy 0, policy_version 18708 (0.0018) [2023-03-09 07:52:10,692][23090] Updated weights for policy 0, policy_version 18718 (0.0016) [2023-03-09 07:52:11,496][23090] Updated weights for policy 0, policy_version 18728 (0.0018) [2023-03-09 07:52:12,341][23090] Updated weights for policy 0, policy_version 18739 (0.0013) [2023-03-09 07:52:13,260][23090] Updated weights for policy 0, policy_version 18749 (0.0018) [2023-03-09 07:52:14,058][22664] Fps is (10 sec: 196610.6, 60 sec: 199885.8, 300 sec: 199940.6). Total num frames: 307331072. Throughput: 0: 49958.3. Samples: 76803472. Policy #0 lag: (min: 0.0, avg: 17.0, max: 33.0) [2023-03-09 07:52:14,059][22664] Avg episode reward: [(0, '48.759')] [2023-03-09 07:52:14,111][23090] Updated weights for policy 0, policy_version 18759 (0.0017) [2023-03-09 07:52:14,846][23090] Updated weights for policy 0, policy_version 18769 (0.0012) [2023-03-09 07:52:15,723][23090] Updated weights for policy 0, policy_version 18779 (0.0013) [2023-03-09 07:52:16,509][23090] Updated weights for policy 0, policy_version 18789 (0.0019) [2023-03-09 07:52:17,356][23090] Updated weights for policy 0, policy_version 18799 (0.0014) [2023-03-09 07:52:18,204][23090] Updated weights for policy 0, policy_version 18809 (0.0022) [2023-03-09 07:52:18,967][23090] Updated weights for policy 0, policy_version 18819 (0.0013) [2023-03-09 07:52:19,059][22664] Fps is (10 sec: 198245.3, 60 sec: 199885.0, 300 sec: 200106.8). Total num frames: 308346880. Throughput: 0: 49859.2. Samples: 77098000. Policy #0 lag: (min: 0.0, avg: 17.0, max: 33.0) [2023-03-09 07:52:19,060][22664] Avg episode reward: [(0, '48.500')] [2023-03-09 07:52:19,809][23090] Updated weights for policy 0, policy_version 18829 (0.0013) [2023-03-09 07:52:20,700][23090] Updated weights for policy 0, policy_version 18840 (0.0022) [2023-03-09 07:52:21,568][23090] Updated weights for policy 0, policy_version 18850 (0.0022) [2023-03-09 07:52:22,377][23090] Updated weights for policy 0, policy_version 18860 (0.0016) [2023-03-09 07:52:22,713][22940] Signal inference workers to stop experience collection... (6700 times) [2023-03-09 07:52:22,714][22940] Signal inference workers to resume experience collection... (6700 times) [2023-03-09 07:52:22,778][23090] InferenceWorker_p0-w0: stopping experience collection (6700 times) [2023-03-09 07:52:22,781][23090] InferenceWorker_p0-w0: resuming experience collection (6700 times) [2023-03-09 07:52:23,115][23090] Updated weights for policy 0, policy_version 18870 (0.0019) [2023-03-09 07:52:24,059][22664] Fps is (10 sec: 199884.2, 60 sec: 199611.8, 300 sec: 199996.1). Total num frames: 309329920. Throughput: 0: 49814.3. Samples: 77396944. Policy #0 lag: (min: 0.0, avg: 17.0, max: 33.0) [2023-03-09 07:52:24,060][22664] Avg episode reward: [(0, '50.516')] [2023-03-09 07:52:24,065][23090] Updated weights for policy 0, policy_version 18880 (0.0016) [2023-03-09 07:52:24,886][23090] Updated weights for policy 0, policy_version 18890 (0.0021) [2023-03-09 07:52:25,659][23090] Updated weights for policy 0, policy_version 18900 (0.0021) [2023-03-09 07:52:26,610][23090] Updated weights for policy 0, policy_version 18910 (0.0015) [2023-03-09 07:52:27,417][23090] Updated weights for policy 0, policy_version 18920 (0.0017) [2023-03-09 07:52:28,113][23090] Updated weights for policy 0, policy_version 18930 (0.0013) [2023-03-09 07:52:29,025][23090] Updated weights for policy 0, policy_version 18940 (0.0023) [2023-03-09 07:52:29,059][22664] Fps is (10 sec: 196610.2, 60 sec: 199065.8, 300 sec: 199995.9). Total num frames: 310312960. Throughput: 0: 49756.6. Samples: 77543824. Policy #0 lag: (min: 1.0, avg: 16.4, max: 33.0) [2023-03-09 07:52:29,060][22664] Avg episode reward: [(0, '50.386')] [2023-03-09 07:52:29,837][23090] Updated weights for policy 0, policy_version 18950 (0.0016) [2023-03-09 07:52:30,662][23090] Updated weights for policy 0, policy_version 18960 (0.0012) [2023-03-09 07:52:31,533][23090] Updated weights for policy 0, policy_version 18970 (0.0017) [2023-03-09 07:52:32,280][23090] Updated weights for policy 0, policy_version 18980 (0.0013) [2023-03-09 07:52:33,058][23090] Updated weights for policy 0, policy_version 18990 (0.0019) [2023-03-09 07:52:33,905][23090] Updated weights for policy 0, policy_version 19000 (0.0017) [2023-03-09 07:52:34,058][22664] Fps is (10 sec: 198247.3, 60 sec: 199338.7, 300 sec: 199996.0). Total num frames: 311312384. Throughput: 0: 49801.6. Samples: 77844784. Policy #0 lag: (min: 1.0, avg: 16.4, max: 33.0) [2023-03-09 07:52:34,059][22664] Avg episode reward: [(0, '50.391')] [2023-03-09 07:52:34,778][23090] Updated weights for policy 0, policy_version 19010 (0.0022) [2023-03-09 07:52:35,572][23090] Updated weights for policy 0, policy_version 19020 (0.0016) [2023-03-09 07:52:36,308][23090] Updated weights for policy 0, policy_version 19030 (0.0016) [2023-03-09 07:52:37,213][23090] Updated weights for policy 0, policy_version 19040 (0.0013) [2023-03-09 07:52:38,052][23090] Updated weights for policy 0, policy_version 19050 (0.0019) [2023-03-09 07:52:38,065][22940] Signal inference workers to stop experience collection... (6750 times) [2023-03-09 07:52:38,066][22940] Signal inference workers to resume experience collection... (6750 times) [2023-03-09 07:52:38,128][23090] InferenceWorker_p0-w0: stopping experience collection (6750 times) [2023-03-09 07:52:38,128][23090] InferenceWorker_p0-w0: resuming experience collection (6750 times) [2023-03-09 07:52:38,898][23090] Updated weights for policy 0, policy_version 19061 (0.0017) [2023-03-09 07:52:39,058][22664] Fps is (10 sec: 201526.9, 60 sec: 199612.5, 300 sec: 199995.9). Total num frames: 312328192. Throughput: 0: 49757.9. Samples: 78141728. Policy #0 lag: (min: 1.0, avg: 16.4, max: 33.0) [2023-03-09 07:52:39,060][22664] Avg episode reward: [(0, '47.156')] [2023-03-09 07:52:39,782][23090] Updated weights for policy 0, policy_version 19071 (0.0031) [2023-03-09 07:52:40,635][23090] Updated weights for policy 0, policy_version 19081 (0.0013) [2023-03-09 07:52:41,389][23090] Updated weights for policy 0, policy_version 19091 (0.0016) [2023-03-09 07:52:42,306][23090] Updated weights for policy 0, policy_version 19101 (0.0018) [2023-03-09 07:52:43,178][23090] Updated weights for policy 0, policy_version 19111 (0.0020) [2023-03-09 07:52:43,832][23090] Updated weights for policy 0, policy_version 19121 (0.0020) [2023-03-09 07:52:44,059][22664] Fps is (10 sec: 199879.8, 60 sec: 199339.0, 300 sec: 199940.4). Total num frames: 313311232. Throughput: 0: 49711.8. Samples: 78291216. Policy #0 lag: (min: 0.0, avg: 16.6, max: 33.0) [2023-03-09 07:52:44,061][22664] Avg episode reward: [(0, '51.328')] [2023-03-09 07:52:44,733][23090] Updated weights for policy 0, policy_version 19131 (0.0016) [2023-03-09 07:52:45,577][23090] Updated weights for policy 0, policy_version 19141 (0.0019) [2023-03-09 07:52:46,356][23090] Updated weights for policy 0, policy_version 19151 (0.0015) [2023-03-09 07:52:47,210][23090] Updated weights for policy 0, policy_version 19161 (0.0013) [2023-03-09 07:52:48,037][23090] Updated weights for policy 0, policy_version 19171 (0.0017) [2023-03-09 07:52:48,840][23090] Updated weights for policy 0, policy_version 19181 (0.0013) [2023-03-09 07:52:49,058][22664] Fps is (10 sec: 196608.7, 60 sec: 198793.7, 300 sec: 199940.5). Total num frames: 314294272. Throughput: 0: 49667.0. Samples: 78590224. Policy #0 lag: (min: 0.0, avg: 16.6, max: 33.0) [2023-03-09 07:52:49,059][22664] Avg episode reward: [(0, '48.115')] [2023-03-09 07:52:49,612][23090] Updated weights for policy 0, policy_version 19191 (0.0020) [2023-03-09 07:52:50,564][23090] Updated weights for policy 0, policy_version 19201 (0.0021) [2023-03-09 07:52:51,364][23090] Updated weights for policy 0, policy_version 19211 (0.0015) [2023-03-09 07:52:52,125][23090] Updated weights for policy 0, policy_version 19221 (0.0013) [2023-03-09 07:52:53,015][23090] Updated weights for policy 0, policy_version 19231 (0.0013) [2023-03-09 07:52:53,829][23090] Updated weights for policy 0, policy_version 19241 (0.0013) [2023-03-09 07:52:54,058][22664] Fps is (10 sec: 198251.3, 60 sec: 198792.7, 300 sec: 199884.9). Total num frames: 315293696. Throughput: 0: 49533.8. Samples: 78887184. Policy #0 lag: (min: 0.0, avg: 16.5, max: 32.0) [2023-03-09 07:52:54,059][22664] Avg episode reward: [(0, '47.903')] [2023-03-09 07:52:54,597][23090] Updated weights for policy 0, policy_version 19251 (0.0016) [2023-03-09 07:52:55,232][22940] Signal inference workers to stop experience collection... (6800 times) [2023-03-09 07:52:55,242][22940] Signal inference workers to resume experience collection... (6800 times) [2023-03-09 07:52:55,308][23090] InferenceWorker_p0-w0: stopping experience collection (6800 times) [2023-03-09 07:52:55,311][23090] InferenceWorker_p0-w0: resuming experience collection (6800 times) [2023-03-09 07:52:55,563][23090] Updated weights for policy 0, policy_version 19261 (0.0016) [2023-03-09 07:52:56,461][23090] Updated weights for policy 0, policy_version 19272 (0.0021) [2023-03-09 07:52:57,204][23090] Updated weights for policy 0, policy_version 19282 (0.0018) [2023-03-09 07:52:58,088][23090] Updated weights for policy 0, policy_version 19292 (0.0019) [2023-03-09 07:52:58,908][23090] Updated weights for policy 0, policy_version 19302 (0.0013) [2023-03-09 07:52:59,059][22664] Fps is (10 sec: 196605.8, 60 sec: 198519.3, 300 sec: 199718.2). Total num frames: 316260352. Throughput: 0: 49535.9. Samples: 79032592. Policy #0 lag: (min: 0.0, avg: 16.5, max: 32.0) [2023-03-09 07:52:59,060][22664] Avg episode reward: [(0, '50.430')] [2023-03-09 07:52:59,684][23090] Updated weights for policy 0, policy_version 19312 (0.0020) [2023-03-09 07:53:00,594][23090] Updated weights for policy 0, policy_version 19322 (0.0017) [2023-03-09 07:53:01,361][23090] Updated weights for policy 0, policy_version 19332 (0.0023) [2023-03-09 07:53:02,170][23090] Updated weights for policy 0, policy_version 19342 (0.0013) [2023-03-09 07:53:02,971][23090] Updated weights for policy 0, policy_version 19352 (0.0019) [2023-03-09 07:53:03,832][23090] Updated weights for policy 0, policy_version 19362 (0.0013) [2023-03-09 07:53:04,059][22664] Fps is (10 sec: 198243.9, 60 sec: 198519.5, 300 sec: 199773.7). Total num frames: 317276160. Throughput: 0: 49635.8. Samples: 79331600. Policy #0 lag: (min: 0.0, avg: 16.5, max: 32.0) [2023-03-09 07:53:04,060][22664] Avg episode reward: [(0, '51.736')] [2023-03-09 07:53:04,061][22940] Saving new best policy, reward=51.736! [2023-03-09 07:53:04,618][23090] Updated weights for policy 0, policy_version 19372 (0.0016) [2023-03-09 07:53:05,369][23090] Updated weights for policy 0, policy_version 19382 (0.0014) [2023-03-09 07:53:06,312][23090] Updated weights for policy 0, policy_version 19392 (0.0013) [2023-03-09 07:53:07,129][23090] Updated weights for policy 0, policy_version 19402 (0.0020) [2023-03-09 07:53:07,969][23090] Updated weights for policy 0, policy_version 19413 (0.0018) [2023-03-09 07:53:08,876][23090] Updated weights for policy 0, policy_version 19423 (0.0015) [2023-03-09 07:53:09,059][22664] Fps is (10 sec: 199878.6, 60 sec: 198245.9, 300 sec: 199662.4). Total num frames: 318259200. Throughput: 0: 49634.8. Samples: 79630528. Policy #0 lag: (min: 1.0, avg: 16.2, max: 32.0) [2023-03-09 07:53:09,061][22664] Avg episode reward: [(0, '51.529')] [2023-03-09 07:53:09,726][23090] Updated weights for policy 0, policy_version 19433 (0.0013) [2023-03-09 07:53:10,472][23090] Updated weights for policy 0, policy_version 19443 (0.0018) [2023-03-09 07:53:11,459][23090] Updated weights for policy 0, policy_version 19453 (0.0018) [2023-03-09 07:53:11,470][22940] Signal inference workers to stop experience collection... (6850 times) [2023-03-09 07:53:11,492][22940] Signal inference workers to resume experience collection... (6850 times) [2023-03-09 07:53:11,549][23090] InferenceWorker_p0-w0: stopping experience collection (6850 times) [2023-03-09 07:53:11,549][23090] InferenceWorker_p0-w0: resuming experience collection (6850 times) [2023-03-09 07:53:12,349][23090] Updated weights for policy 0, policy_version 19463 (0.0015) [2023-03-09 07:53:13,085][23090] Updated weights for policy 0, policy_version 19473 (0.0013) [2023-03-09 07:53:13,932][23090] Updated weights for policy 0, policy_version 19483 (0.0013) [2023-03-09 07:53:14,058][22664] Fps is (10 sec: 194971.7, 60 sec: 198246.4, 300 sec: 199552.0). Total num frames: 319225856. Throughput: 0: 49602.0. Samples: 79775904. Policy #0 lag: (min: 1.0, avg: 16.2, max: 32.0) [2023-03-09 07:53:14,060][22664] Avg episode reward: [(0, '51.243')] [2023-03-09 07:53:14,773][23090] Updated weights for policy 0, policy_version 19493 (0.0024) [2023-03-09 07:53:15,583][23090] Updated weights for policy 0, policy_version 19503 (0.0013) [2023-03-09 07:53:16,431][23090] Updated weights for policy 0, policy_version 19513 (0.0014) [2023-03-09 07:53:17,242][23090] Updated weights for policy 0, policy_version 19523 (0.0018) [2023-03-09 07:53:18,079][23090] Updated weights for policy 0, policy_version 19533 (0.0013) [2023-03-09 07:53:18,779][23090] Updated weights for policy 0, policy_version 19543 (0.0016) [2023-03-09 07:53:19,059][22664] Fps is (10 sec: 196609.3, 60 sec: 197973.3, 300 sec: 199607.1). Total num frames: 320225280. Throughput: 0: 49466.3. Samples: 80070784. Policy #0 lag: (min: 1.0, avg: 16.2, max: 32.0) [2023-03-09 07:53:19,061][22664] Avg episode reward: [(0, '49.412')] [2023-03-09 07:53:19,071][22940] Saving /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000019545_320225280.pth... [2023-03-09 07:53:19,129][22940] Removing /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000016623_272351232.pth [2023-03-09 07:53:19,734][23090] Updated weights for policy 0, policy_version 19553 (0.0013) [2023-03-09 07:53:20,558][23090] Updated weights for policy 0, policy_version 19563 (0.0019) [2023-03-09 07:53:21,349][23090] Updated weights for policy 0, policy_version 19573 (0.0013) [2023-03-09 07:53:22,206][23090] Updated weights for policy 0, policy_version 19583 (0.0013) [2023-03-09 07:53:23,020][23090] Updated weights for policy 0, policy_version 19593 (0.0017) [2023-03-09 07:53:23,859][23090] Updated weights for policy 0, policy_version 19604 (0.0018) [2023-03-09 07:53:24,058][22664] Fps is (10 sec: 201524.0, 60 sec: 198519.7, 300 sec: 199718.6). Total num frames: 321241088. Throughput: 0: 49464.2. Samples: 80367616. Policy #0 lag: (min: 1.0, avg: 16.2, max: 32.0) [2023-03-09 07:53:24,059][22664] Avg episode reward: [(0, '48.433')] [2023-03-09 07:53:24,785][23090] Updated weights for policy 0, policy_version 19614 (0.0024) [2023-03-09 07:53:25,630][23090] Updated weights for policy 0, policy_version 19624 (0.0016) [2023-03-09 07:53:26,015][22940] Signal inference workers to stop experience collection... (6900 times) [2023-03-09 07:53:26,016][22940] Signal inference workers to resume experience collection... (6900 times) [2023-03-09 07:53:26,086][23090] InferenceWorker_p0-w0: stopping experience collection (6900 times) [2023-03-09 07:53:26,089][23090] InferenceWorker_p0-w0: resuming experience collection (6900 times) [2023-03-09 07:53:26,405][23090] Updated weights for policy 0, policy_version 19634 (0.0013) [2023-03-09 07:53:27,255][23090] Updated weights for policy 0, policy_version 19644 (0.0014) [2023-03-09 07:53:28,075][23090] Updated weights for policy 0, policy_version 19654 (0.0016) [2023-03-09 07:53:28,879][23090] Updated weights for policy 0, policy_version 19664 (0.0021) [2023-03-09 07:53:29,059][22664] Fps is (10 sec: 198246.3, 60 sec: 198245.9, 300 sec: 199551.3). Total num frames: 322207744. Throughput: 0: 49418.9. Samples: 80515072. Policy #0 lag: (min: 1.0, avg: 16.2, max: 32.0) [2023-03-09 07:53:29,060][22664] Avg episode reward: [(0, '50.217')] [2023-03-09 07:53:29,733][23090] Updated weights for policy 0, policy_version 19674 (0.0016) [2023-03-09 07:53:30,579][23090] Updated weights for policy 0, policy_version 19684 (0.0013) [2023-03-09 07:53:31,379][23090] Updated weights for policy 0, policy_version 19694 (0.0017) [2023-03-09 07:53:32,146][23090] Updated weights for policy 0, policy_version 19704 (0.0019) [2023-03-09 07:53:33,039][23090] Updated weights for policy 0, policy_version 19714 (0.0020) [2023-03-09 07:53:33,856][23090] Updated weights for policy 0, policy_version 19724 (0.0020) [2023-03-09 07:53:34,059][22664] Fps is (10 sec: 194961.4, 60 sec: 197972.0, 300 sec: 199495.8). Total num frames: 323190784. Throughput: 0: 49372.4. Samples: 80812000. Policy #0 lag: (min: 0.0, avg: 16.0, max: 32.0) [2023-03-09 07:53:34,061][22664] Avg episode reward: [(0, '50.690')] [2023-03-09 07:53:34,725][23090] Updated weights for policy 0, policy_version 19735 (0.0013) [2023-03-09 07:53:35,619][23090] Updated weights for policy 0, policy_version 19745 (0.0013) [2023-03-09 07:53:36,488][23090] Updated weights for policy 0, policy_version 19755 (0.0021) [2023-03-09 07:53:37,279][23090] Updated weights for policy 0, policy_version 19765 (0.0015) [2023-03-09 07:53:38,146][23090] Updated weights for policy 0, policy_version 19775 (0.0013) [2023-03-09 07:53:38,964][23090] Updated weights for policy 0, policy_version 19785 (0.0017) [2023-03-09 07:53:39,059][22664] Fps is (10 sec: 196603.8, 60 sec: 197425.4, 300 sec: 199440.1). Total num frames: 324173824. Throughput: 0: 49324.9. Samples: 81106832. Policy #0 lag: (min: 0.0, avg: 16.0, max: 32.0) [2023-03-09 07:53:39,061][22664] Avg episode reward: [(0, '47.976')] [2023-03-09 07:53:39,731][23090] Updated weights for policy 0, policy_version 19795 (0.0017) [2023-03-09 07:53:40,693][23090] Updated weights for policy 0, policy_version 19805 (0.0013) [2023-03-09 07:53:41,496][23090] Updated weights for policy 0, policy_version 19815 (0.0013) [2023-03-09 07:53:41,505][22940] Signal inference workers to stop experience collection... (6950 times) [2023-03-09 07:53:41,507][22940] Signal inference workers to resume experience collection... (6950 times) [2023-03-09 07:53:41,569][23090] InferenceWorker_p0-w0: stopping experience collection (6950 times) [2023-03-09 07:53:41,570][23090] InferenceWorker_p0-w0: resuming experience collection (6950 times) [2023-03-09 07:53:42,232][23090] Updated weights for policy 0, policy_version 19825 (0.0016) [2023-03-09 07:53:43,098][23090] Updated weights for policy 0, policy_version 19835 (0.0019) [2023-03-09 07:53:43,926][23090] Updated weights for policy 0, policy_version 19845 (0.0019) [2023-03-09 07:53:44,059][22664] Fps is (10 sec: 196614.5, 60 sec: 197427.8, 300 sec: 199440.5). Total num frames: 325156864. Throughput: 0: 49415.5. Samples: 81256288. Policy #0 lag: (min: 0.0, avg: 16.0, max: 32.0) [2023-03-09 07:53:44,060][22664] Avg episode reward: [(0, '51.934')] [2023-03-09 07:53:44,061][22940] Saving new best policy, reward=51.934! [2023-03-09 07:53:44,757][23090] Updated weights for policy 0, policy_version 19855 (0.0019) [2023-03-09 07:53:45,578][23090] Updated weights for policy 0, policy_version 19865 (0.0013) [2023-03-09 07:53:46,389][23090] Updated weights for policy 0, policy_version 19875 (0.0025) [2023-03-09 07:53:47,226][23090] Updated weights for policy 0, policy_version 19885 (0.0017) [2023-03-09 07:53:47,952][23090] Updated weights for policy 0, policy_version 19895 (0.0018) [2023-03-09 07:53:48,836][23090] Updated weights for policy 0, policy_version 19905 (0.0013) [2023-03-09 07:53:49,059][22664] Fps is (10 sec: 198250.1, 60 sec: 197699.0, 300 sec: 199440.6). Total num frames: 326156288. Throughput: 0: 49368.3. Samples: 81553184. Policy #0 lag: (min: 1.0, avg: 16.7, max: 33.0) [2023-03-09 07:53:49,061][22664] Avg episode reward: [(0, '49.076')] [2023-03-09 07:53:49,684][23090] Updated weights for policy 0, policy_version 19915 (0.0017) [2023-03-09 07:53:50,547][23090] Updated weights for policy 0, policy_version 19925 (0.0014) [2023-03-09 07:53:51,362][23090] Updated weights for policy 0, policy_version 19935 (0.0017) [2023-03-09 07:53:52,179][23090] Updated weights for policy 0, policy_version 19945 (0.0016) [2023-03-09 07:53:52,950][23090] Updated weights for policy 0, policy_version 19955 (0.0015) [2023-03-09 07:53:53,901][23090] Updated weights for policy 0, policy_version 19965 (0.0015) [2023-03-09 07:53:54,059][22664] Fps is (10 sec: 198246.4, 60 sec: 197427.0, 300 sec: 199384.9). Total num frames: 327139328. Throughput: 0: 49370.3. Samples: 81852176. Policy #0 lag: (min: 1.0, avg: 16.7, max: 33.0) [2023-03-09 07:53:54,060][22664] Avg episode reward: [(0, '49.657')] [2023-03-09 07:53:54,710][23090] Updated weights for policy 0, policy_version 19975 (0.0027) [2023-03-09 07:53:55,456][23090] Updated weights for policy 0, policy_version 19985 (0.0013) [2023-03-09 07:53:56,325][23090] Updated weights for policy 0, policy_version 19995 (0.0013) [2023-03-09 07:53:57,140][23090] Updated weights for policy 0, policy_version 20005 (0.0015) [2023-03-09 07:53:57,341][22940] Signal inference workers to stop experience collection... (7000 times) [2023-03-09 07:53:57,341][22940] Signal inference workers to resume experience collection... (7000 times) [2023-03-09 07:53:57,404][23090] InferenceWorker_p0-w0: stopping experience collection (7000 times) [2023-03-09 07:53:57,404][23090] InferenceWorker_p0-w0: resuming experience collection (7000 times) [2023-03-09 07:53:57,941][23090] Updated weights for policy 0, policy_version 20015 (0.0021) [2023-03-09 07:53:58,772][23090] Updated weights for policy 0, policy_version 20025 (0.0015) [2023-03-09 07:53:59,059][22664] Fps is (10 sec: 198250.4, 60 sec: 197973.1, 300 sec: 199329.5). Total num frames: 328138752. Throughput: 0: 49415.3. Samples: 81999600. Policy #0 lag: (min: 1.0, avg: 16.7, max: 33.0) [2023-03-09 07:53:59,060][22664] Avg episode reward: [(0, '47.362')] [2023-03-09 07:53:59,609][23090] Updated weights for policy 0, policy_version 20035 (0.0013) [2023-03-09 07:54:00,412][23090] Updated weights for policy 0, policy_version 20045 (0.0016) [2023-03-09 07:54:01,150][23090] Updated weights for policy 0, policy_version 20055 (0.0013) [2023-03-09 07:54:02,072][23090] Updated weights for policy 0, policy_version 20065 (0.0020) [2023-03-09 07:54:02,996][23090] Updated weights for policy 0, policy_version 20076 (0.0016) [2023-03-09 07:54:03,787][23090] Updated weights for policy 0, policy_version 20086 (0.0016) [2023-03-09 07:54:04,058][22664] Fps is (10 sec: 198248.0, 60 sec: 197427.7, 300 sec: 199218.3). Total num frames: 329121792. Throughput: 0: 49506.9. Samples: 82298576. Policy #0 lag: (min: 1.0, avg: 16.6, max: 33.0) [2023-03-09 07:54:04,060][22664] Avg episode reward: [(0, '47.480')] [2023-03-09 07:54:04,653][23090] Updated weights for policy 0, policy_version 20096 (0.0017) [2023-03-09 07:54:05,475][23090] Updated weights for policy 0, policy_version 20106 (0.0013) [2023-03-09 07:54:06,257][23090] Updated weights for policy 0, policy_version 20116 (0.0019) [2023-03-09 07:54:07,206][23090] Updated weights for policy 0, policy_version 20126 (0.0016) [2023-03-09 07:54:08,034][23090] Updated weights for policy 0, policy_version 20136 (0.0025) [2023-03-09 07:54:08,769][23090] Updated weights for policy 0, policy_version 20146 (0.0014) [2023-03-09 07:54:09,059][22664] Fps is (10 sec: 198237.1, 60 sec: 197699.5, 300 sec: 199218.1). Total num frames: 330121216. Throughput: 0: 49416.5. Samples: 82591392. Policy #0 lag: (min: 1.0, avg: 16.6, max: 33.0) [2023-03-09 07:54:09,061][22664] Avg episode reward: [(0, '50.101')] [2023-03-09 07:54:09,812][23090] Updated weights for policy 0, policy_version 20157 (0.0016) [2023-03-09 07:54:10,675][23090] Updated weights for policy 0, policy_version 20167 (0.0016) [2023-03-09 07:54:11,410][23090] Updated weights for policy 0, policy_version 20177 (0.0014) [2023-03-09 07:54:12,340][23090] Updated weights for policy 0, policy_version 20188 (0.0016) [2023-03-09 07:54:13,192][23090] Updated weights for policy 0, policy_version 20198 (0.0014) [2023-03-09 07:54:13,353][22940] Signal inference workers to stop experience collection... (7050 times) [2023-03-09 07:54:13,354][22940] Signal inference workers to resume experience collection... (7050 times) [2023-03-09 07:54:13,432][23090] InferenceWorker_p0-w0: stopping experience collection (7050 times) [2023-03-09 07:54:13,432][23090] InferenceWorker_p0-w0: resuming experience collection (7050 times) [2023-03-09 07:54:14,047][23090] Updated weights for policy 0, policy_version 20209 (0.0017) [2023-03-09 07:54:14,059][22664] Fps is (10 sec: 198240.4, 60 sec: 197972.4, 300 sec: 199273.7). Total num frames: 331104256. Throughput: 0: 49416.3. Samples: 82738800. Policy #0 lag: (min: 1.0, avg: 16.9, max: 33.0) [2023-03-09 07:54:14,060][22664] Avg episode reward: [(0, '50.093')] [2023-03-09 07:54:14,953][23090] Updated weights for policy 0, policy_version 20219 (0.0028) [2023-03-09 07:54:15,757][23090] Updated weights for policy 0, policy_version 20229 (0.0022) [2023-03-09 07:54:16,584][23090] Updated weights for policy 0, policy_version 20239 (0.0018) [2023-03-09 07:54:17,413][23090] Updated weights for policy 0, policy_version 20249 (0.0016) [2023-03-09 07:54:18,332][23090] Updated weights for policy 0, policy_version 20260 (0.0016) [2023-03-09 07:54:19,059][22664] Fps is (10 sec: 194980.2, 60 sec: 197428.0, 300 sec: 199218.3). Total num frames: 332070912. Throughput: 0: 49415.4. Samples: 83035680. Policy #0 lag: (min: 1.0, avg: 16.9, max: 33.0) [2023-03-09 07:54:19,060][22664] Avg episode reward: [(0, '49.690')] [2023-03-09 07:54:19,151][23090] Updated weights for policy 0, policy_version 20270 (0.0018) [2023-03-09 07:54:20,004][23090] Updated weights for policy 0, policy_version 20280 (0.0024) [2023-03-09 07:54:20,809][23090] Updated weights for policy 0, policy_version 20290 (0.0016) [2023-03-09 07:54:21,647][23090] Updated weights for policy 0, policy_version 20300 (0.0023) [2023-03-09 07:54:22,420][23090] Updated weights for policy 0, policy_version 20310 (0.0013) [2023-03-09 07:54:23,330][23090] Updated weights for policy 0, policy_version 20320 (0.0013) [2023-03-09 07:54:24,058][22664] Fps is (10 sec: 196613.7, 60 sec: 197154.1, 300 sec: 199162.9). Total num frames: 333070336. Throughput: 0: 49462.0. Samples: 83332592. Policy #0 lag: (min: 1.0, avg: 16.9, max: 33.0) [2023-03-09 07:54:24,059][22664] Avg episode reward: [(0, '50.901')] [2023-03-09 07:54:24,110][23090] Updated weights for policy 0, policy_version 20330 (0.0013) [2023-03-09 07:54:24,874][23090] Updated weights for policy 0, policy_version 20340 (0.0016) [2023-03-09 07:54:25,782][23090] Updated weights for policy 0, policy_version 20350 (0.0018) [2023-03-09 07:54:26,594][23090] Updated weights for policy 0, policy_version 20360 (0.0018) [2023-03-09 07:54:27,409][23090] Updated weights for policy 0, policy_version 20370 (0.0019) [2023-03-09 07:54:28,199][23090] Updated weights for policy 0, policy_version 20380 (0.0020) [2023-03-09 07:54:29,059][22664] Fps is (10 sec: 198247.3, 60 sec: 197428.2, 300 sec: 199162.9). Total num frames: 334053376. Throughput: 0: 49462.0. Samples: 83482080. Policy #0 lag: (min: 1.0, avg: 17.5, max: 33.0) [2023-03-09 07:54:29,060][22664] Avg episode reward: [(0, '49.193')] [2023-03-09 07:54:29,068][23090] Updated weights for policy 0, policy_version 20390 (0.0016) [2023-03-09 07:54:29,614][22940] Signal inference workers to stop experience collection... (7100 times) [2023-03-09 07:54:29,615][22940] Signal inference workers to resume experience collection... (7100 times) [2023-03-09 07:54:29,683][23090] InferenceWorker_p0-w0: stopping experience collection (7100 times) [2023-03-09 07:54:29,683][23090] InferenceWorker_p0-w0: resuming experience collection (7100 times) [2023-03-09 07:54:29,815][23090] Updated weights for policy 0, policy_version 20400 (0.0016) [2023-03-09 07:54:30,756][23090] Updated weights for policy 0, policy_version 20410 (0.0015) [2023-03-09 07:54:31,499][23090] Updated weights for policy 0, policy_version 20420 (0.0022) [2023-03-09 07:54:32,337][23090] Updated weights for policy 0, policy_version 20430 (0.0017) [2023-03-09 07:54:33,199][23090] Updated weights for policy 0, policy_version 20440 (0.0018) [2023-03-09 07:54:33,973][23090] Updated weights for policy 0, policy_version 20450 (0.0013) [2023-03-09 07:54:34,059][22664] Fps is (10 sec: 199880.3, 60 sec: 197973.9, 300 sec: 199218.3). Total num frames: 335069184. Throughput: 0: 49508.8. Samples: 83781072. Policy #0 lag: (min: 1.0, avg: 17.5, max: 33.0) [2023-03-09 07:54:34,061][22664] Avg episode reward: [(0, '49.388')] [2023-03-09 07:54:34,778][23090] Updated weights for policy 0, policy_version 20460 (0.0017) [2023-03-09 07:54:35,576][23090] Updated weights for policy 0, policy_version 20470 (0.0016) [2023-03-09 07:54:36,525][23090] Updated weights for policy 0, policy_version 20481 (0.0013) [2023-03-09 07:54:37,336][23090] Updated weights for policy 0, policy_version 20491 (0.0013) [2023-03-09 07:54:38,159][23090] Updated weights for policy 0, policy_version 20501 (0.0022) [2023-03-09 07:54:38,964][23090] Updated weights for policy 0, policy_version 20511 (0.0025) [2023-03-09 07:54:39,059][22664] Fps is (10 sec: 201518.8, 60 sec: 198247.4, 300 sec: 199218.1). Total num frames: 336068608. Throughput: 0: 49508.0. Samples: 84080048. Policy #0 lag: (min: 1.0, avg: 17.5, max: 33.0) [2023-03-09 07:54:39,060][22664] Avg episode reward: [(0, '50.201')] [2023-03-09 07:54:39,811][23090] Updated weights for policy 0, policy_version 20521 (0.0013) [2023-03-09 07:54:40,593][23090] Updated weights for policy 0, policy_version 20531 (0.0014) [2023-03-09 07:54:41,578][23090] Updated weights for policy 0, policy_version 20542 (0.0013) [2023-03-09 07:54:42,411][23090] Updated weights for policy 0, policy_version 20552 (0.0018) [2023-03-09 07:54:43,140][23090] Updated weights for policy 0, policy_version 20562 (0.0016) [2023-03-09 07:54:43,988][23090] Updated weights for policy 0, policy_version 20572 (0.0017) [2023-03-09 07:54:44,058][22664] Fps is (10 sec: 198250.7, 60 sec: 198246.6, 300 sec: 199107.3). Total num frames: 337051648. Throughput: 0: 49554.3. Samples: 84229536. Policy #0 lag: (min: 2.0, avg: 16.9, max: 34.0) [2023-03-09 07:54:44,060][22664] Avg episode reward: [(0, '52.725')] [2023-03-09 07:54:44,099][22940] Saving new best policy, reward=52.725! [2023-03-09 07:54:44,826][23090] Updated weights for policy 0, policy_version 20582 (0.0013) [2023-03-09 07:54:45,601][23090] Updated weights for policy 0, policy_version 20592 (0.0016) [2023-03-09 07:54:45,776][22940] Signal inference workers to stop experience collection... (7150 times) [2023-03-09 07:54:45,776][22940] Signal inference workers to resume experience collection... (7150 times) [2023-03-09 07:54:45,837][23090] InferenceWorker_p0-w0: stopping experience collection (7150 times) [2023-03-09 07:54:45,838][23090] InferenceWorker_p0-w0: resuming experience collection (7150 times) [2023-03-09 07:54:46,528][23090] Updated weights for policy 0, policy_version 20602 (0.0019) [2023-03-09 07:54:47,271][23090] Updated weights for policy 0, policy_version 20612 (0.0013) [2023-03-09 07:54:48,100][23090] Updated weights for policy 0, policy_version 20622 (0.0016) [2023-03-09 07:54:48,920][23090] Updated weights for policy 0, policy_version 20632 (0.0016) [2023-03-09 07:54:49,059][22664] Fps is (10 sec: 198244.3, 60 sec: 198246.4, 300 sec: 199162.6). Total num frames: 338051072. Throughput: 0: 49553.3. Samples: 84528496. Policy #0 lag: (min: 2.0, avg: 16.9, max: 34.0) [2023-03-09 07:54:49,060][22664] Avg episode reward: [(0, '50.236')] [2023-03-09 07:54:49,732][23090] Updated weights for policy 0, policy_version 20642 (0.0016) [2023-03-09 07:54:50,578][23090] Updated weights for policy 0, policy_version 20652 (0.0013) [2023-03-09 07:54:51,389][23090] Updated weights for policy 0, policy_version 20662 (0.0016) [2023-03-09 07:54:52,230][23090] Updated weights for policy 0, policy_version 20672 (0.0013) [2023-03-09 07:54:53,047][23090] Updated weights for policy 0, policy_version 20682 (0.0017) [2023-03-09 07:54:53,912][23090] Updated weights for policy 0, policy_version 20693 (0.0021) [2023-03-09 07:54:54,058][22664] Fps is (10 sec: 201522.9, 60 sec: 198792.7, 300 sec: 199163.0). Total num frames: 339066880. Throughput: 0: 49692.1. Samples: 84827504. Policy #0 lag: (min: 2.0, avg: 16.9, max: 34.0) [2023-03-09 07:54:54,059][22664] Avg episode reward: [(0, '50.120')] [2023-03-09 07:54:54,753][23090] Updated weights for policy 0, policy_version 20703 (0.0018) [2023-03-09 07:54:55,583][23090] Updated weights for policy 0, policy_version 20713 (0.0019) [2023-03-09 07:54:56,353][23090] Updated weights for policy 0, policy_version 20723 (0.0016) [2023-03-09 07:54:57,275][23090] Updated weights for policy 0, policy_version 20733 (0.0024) [2023-03-09 07:54:58,073][23090] Updated weights for policy 0, policy_version 20743 (0.0016) [2023-03-09 07:54:58,811][23090] Updated weights for policy 0, policy_version 20753 (0.0013) [2023-03-09 07:54:59,059][22664] Fps is (10 sec: 201529.3, 60 sec: 198792.9, 300 sec: 199162.9). Total num frames: 340066304. Throughput: 0: 49737.8. Samples: 84976992. Policy #0 lag: (min: 1.0, avg: 16.6, max: 33.0) [2023-03-09 07:54:59,059][22664] Avg episode reward: [(0, '49.599')] [2023-03-09 07:54:59,748][23090] Updated weights for policy 0, policy_version 20764 (0.0013) [2023-03-09 07:55:00,627][23090] Updated weights for policy 0, policy_version 20774 (0.0018) [2023-03-09 07:55:01,373][23090] Updated weights for policy 0, policy_version 20784 (0.0013) [2023-03-09 07:55:01,552][22940] Signal inference workers to stop experience collection... (7200 times) [2023-03-09 07:55:01,553][22940] Signal inference workers to resume experience collection... (7200 times) [2023-03-09 07:55:01,618][23090] InferenceWorker_p0-w0: stopping experience collection (7200 times) [2023-03-09 07:55:01,620][23090] InferenceWorker_p0-w0: resuming experience collection (7200 times) [2023-03-09 07:55:02,312][23090] Updated weights for policy 0, policy_version 20794 (0.0021) [2023-03-09 07:55:03,043][23090] Updated weights for policy 0, policy_version 20804 (0.0014) [2023-03-09 07:55:03,883][23090] Updated weights for policy 0, policy_version 20814 (0.0016) [2023-03-09 07:55:04,059][22664] Fps is (10 sec: 198238.6, 60 sec: 198791.1, 300 sec: 199107.2). Total num frames: 341049344. Throughput: 0: 49784.2. Samples: 85275984. Policy #0 lag: (min: 1.0, avg: 16.6, max: 33.0) [2023-03-09 07:55:04,060][22664] Avg episode reward: [(0, '53.026')] [2023-03-09 07:55:04,106][22940] Saving new best policy, reward=53.026! [2023-03-09 07:55:04,707][23090] Updated weights for policy 0, policy_version 20824 (0.0016) [2023-03-09 07:55:05,669][23090] Updated weights for policy 0, policy_version 20835 (0.0019) [2023-03-09 07:55:06,446][23090] Updated weights for policy 0, policy_version 20845 (0.0016) [2023-03-09 07:55:07,181][23090] Updated weights for policy 0, policy_version 20855 (0.0013) [2023-03-09 07:55:08,197][23090] Updated weights for policy 0, policy_version 20866 (0.0017) [2023-03-09 07:55:08,975][23090] Updated weights for policy 0, policy_version 20876 (0.0017) [2023-03-09 07:55:09,059][22664] Fps is (10 sec: 196600.6, 60 sec: 198520.1, 300 sec: 199107.1). Total num frames: 342032384. Throughput: 0: 49829.2. Samples: 85574928. Policy #0 lag: (min: 1.0, avg: 16.6, max: 33.0) [2023-03-09 07:55:09,061][22664] Avg episode reward: [(0, '47.632')] [2023-03-09 07:55:09,823][23090] Updated weights for policy 0, policy_version 20886 (0.0013) [2023-03-09 07:55:10,654][23090] Updated weights for policy 0, policy_version 20896 (0.0021) [2023-03-09 07:55:11,501][23090] Updated weights for policy 0, policy_version 20906 (0.0017) [2023-03-09 07:55:12,246][23090] Updated weights for policy 0, policy_version 20916 (0.0013) [2023-03-09 07:55:13,166][23090] Updated weights for policy 0, policy_version 20926 (0.0012) [2023-03-09 07:55:13,986][23090] Updated weights for policy 0, policy_version 20936 (0.0013) [2023-03-09 07:55:14,059][22664] Fps is (10 sec: 198253.1, 60 sec: 198793.2, 300 sec: 199107.2). Total num frames: 343031808. Throughput: 0: 49829.3. Samples: 85724400. Policy #0 lag: (min: 2.0, avg: 17.8, max: 33.0) [2023-03-09 07:55:14,060][22664] Avg episode reward: [(0, '47.036')] [2023-03-09 07:55:14,836][23090] Updated weights for policy 0, policy_version 20947 (0.0018) [2023-03-09 07:55:15,754][23090] Updated weights for policy 0, policy_version 20957 (0.0021) [2023-03-09 07:55:16,552][23090] Updated weights for policy 0, policy_version 20967 (0.0026) [2023-03-09 07:55:16,755][22940] Signal inference workers to stop experience collection... (7250 times) [2023-03-09 07:55:16,760][22940] Signal inference workers to resume experience collection... (7250 times) [2023-03-09 07:55:16,826][23090] InferenceWorker_p0-w0: stopping experience collection (7250 times) [2023-03-09 07:55:16,826][23090] InferenceWorker_p0-w0: resuming experience collection (7250 times) [2023-03-09 07:55:17,289][23090] Updated weights for policy 0, policy_version 20977 (0.0016) [2023-03-09 07:55:18,183][23090] Updated weights for policy 0, policy_version 20987 (0.0015) [2023-03-09 07:55:18,959][23090] Updated weights for policy 0, policy_version 20997 (0.0022) [2023-03-09 07:55:19,059][22664] Fps is (10 sec: 198253.1, 60 sec: 199065.6, 300 sec: 199051.8). Total num frames: 344014848. Throughput: 0: 49783.9. Samples: 86021344. Policy #0 lag: (min: 2.0, avg: 17.8, max: 33.0) [2023-03-09 07:55:19,059][22664] Avg episode reward: [(0, '50.691')] [2023-03-09 07:55:19,073][22940] Saving /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000020998_344031232.pth... [2023-03-09 07:55:19,142][22940] Removing /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000018089_296370176.pth [2023-03-09 07:55:19,847][23090] Updated weights for policy 0, policy_version 21008 (0.0013) [2023-03-09 07:55:20,777][23090] Updated weights for policy 0, policy_version 21018 (0.0013) [2023-03-09 07:55:21,561][23090] Updated weights for policy 0, policy_version 21028 (0.0019) [2023-03-09 07:55:22,326][23090] Updated weights for policy 0, policy_version 21038 (0.0017) [2023-03-09 07:55:23,133][23090] Updated weights for policy 0, policy_version 21048 (0.0013) [2023-03-09 07:55:23,986][23090] Updated weights for policy 0, policy_version 21058 (0.0017) [2023-03-09 07:55:24,059][22664] Fps is (10 sec: 198246.5, 60 sec: 199065.4, 300 sec: 198996.2). Total num frames: 345014272. Throughput: 0: 49783.7. Samples: 86320304. Policy #0 lag: (min: 2.0, avg: 17.8, max: 33.0) [2023-03-09 07:55:24,059][22664] Avg episode reward: [(0, '52.349')] [2023-03-09 07:55:24,805][23090] Updated weights for policy 0, policy_version 21068 (0.0019) [2023-03-09 07:55:25,624][23090] Updated weights for policy 0, policy_version 21078 (0.0017) [2023-03-09 07:55:26,485][23090] Updated weights for policy 0, policy_version 21088 (0.0017) [2023-03-09 07:55:27,291][23090] Updated weights for policy 0, policy_version 21098 (0.0015) [2023-03-09 07:55:28,064][23090] Updated weights for policy 0, policy_version 21108 (0.0017) [2023-03-09 07:55:28,949][23090] Updated weights for policy 0, policy_version 21118 (0.0018) [2023-03-09 07:55:29,059][22664] Fps is (10 sec: 199885.7, 60 sec: 199338.6, 300 sec: 199051.8). Total num frames: 346013696. Throughput: 0: 49783.8. Samples: 86469808. Policy #0 lag: (min: 1.0, avg: 16.5, max: 32.0) [2023-03-09 07:55:29,059][22664] Avg episode reward: [(0, '51.106')] [2023-03-09 07:55:29,737][23090] Updated weights for policy 0, policy_version 21128 (0.0017) [2023-03-09 07:55:30,505][23090] Updated weights for policy 0, policy_version 21138 (0.0018) [2023-03-09 07:55:31,427][23090] Updated weights for policy 0, policy_version 21148 (0.0013) [2023-03-09 07:55:31,508][22940] Signal inference workers to stop experience collection... (7300 times) [2023-03-09 07:55:31,521][22940] Signal inference workers to resume experience collection... (7300 times) [2023-03-09 07:55:31,583][23090] InferenceWorker_p0-w0: stopping experience collection (7300 times) [2023-03-09 07:55:31,586][23090] InferenceWorker_p0-w0: resuming experience collection (7300 times) [2023-03-09 07:55:32,235][23090] Updated weights for policy 0, policy_version 21158 (0.0013) [2023-03-09 07:55:32,998][23090] Updated weights for policy 0, policy_version 21168 (0.0027) [2023-03-09 07:55:33,926][23090] Updated weights for policy 0, policy_version 21178 (0.0013) [2023-03-09 07:55:34,059][22664] Fps is (10 sec: 199884.9, 60 sec: 199066.1, 300 sec: 199051.7). Total num frames: 347013120. Throughput: 0: 49784.2. Samples: 86768768. Policy #0 lag: (min: 1.0, avg: 16.5, max: 32.0) [2023-03-09 07:55:34,060][22664] Avg episode reward: [(0, '47.112')] [2023-03-09 07:55:34,688][23090] Updated weights for policy 0, policy_version 21188 (0.0020) [2023-03-09 07:55:35,526][23090] Updated weights for policy 0, policy_version 21198 (0.0013) [2023-03-09 07:55:36,330][23090] Updated weights for policy 0, policy_version 21208 (0.0016) [2023-03-09 07:55:37,264][23090] Updated weights for policy 0, policy_version 21218 (0.0016) [2023-03-09 07:55:38,033][23090] Updated weights for policy 0, policy_version 21228 (0.0022) [2023-03-09 07:55:38,876][23090] Updated weights for policy 0, policy_version 21238 (0.0015) [2023-03-09 07:55:39,058][22664] Fps is (10 sec: 198247.8, 60 sec: 198793.5, 300 sec: 198940.8). Total num frames: 347996160. Throughput: 0: 49647.0. Samples: 87061616. Policy #0 lag: (min: 1.0, avg: 17.2, max: 33.0) [2023-03-09 07:55:39,059][22664] Avg episode reward: [(0, '47.414')] [2023-03-09 07:55:39,722][23090] Updated weights for policy 0, policy_version 21248 (0.0015) [2023-03-09 07:55:40,553][23090] Updated weights for policy 0, policy_version 21258 (0.0013) [2023-03-09 07:55:41,272][23090] Updated weights for policy 0, policy_version 21268 (0.0013) [2023-03-09 07:55:42,165][23090] Updated weights for policy 0, policy_version 21278 (0.0013) [2023-03-09 07:55:42,990][23090] Updated weights for policy 0, policy_version 21288 (0.0015) [2023-03-09 07:55:43,721][23090] Updated weights for policy 0, policy_version 21298 (0.0016) [2023-03-09 07:55:44,030][22940] Signal inference workers to stop experience collection... (7350 times) [2023-03-09 07:55:44,059][22664] Fps is (10 sec: 198244.9, 60 sec: 199065.2, 300 sec: 198885.2). Total num frames: 348995584. Throughput: 0: 49691.7. Samples: 87213120. Policy #0 lag: (min: 1.0, avg: 17.2, max: 33.0) [2023-03-09 07:55:44,060][22664] Avg episode reward: [(0, '50.528')] [2023-03-09 07:55:44,062][22940] Signal inference workers to resume experience collection... (7350 times) [2023-03-09 07:55:44,083][23090] InferenceWorker_p0-w0: stopping experience collection (7350 times) [2023-03-09 07:55:44,083][23090] InferenceWorker_p0-w0: resuming experience collection (7350 times) [2023-03-09 07:55:44,634][23090] Updated weights for policy 0, policy_version 21308 (0.0022) [2023-03-09 07:55:45,431][23090] Updated weights for policy 0, policy_version 21318 (0.0022) [2023-03-09 07:55:46,190][23090] Updated weights for policy 0, policy_version 21328 (0.0017) [2023-03-09 07:55:47,114][23090] Updated weights for policy 0, policy_version 21338 (0.0013) [2023-03-09 07:55:47,872][23090] Updated weights for policy 0, policy_version 21348 (0.0013) [2023-03-09 07:55:48,692][23090] Updated weights for policy 0, policy_version 21358 (0.0013) [2023-03-09 07:55:49,059][22664] Fps is (10 sec: 199883.6, 60 sec: 199066.7, 300 sec: 198829.7). Total num frames: 349995008. Throughput: 0: 49736.9. Samples: 87514128. Policy #0 lag: (min: 1.0, avg: 17.2, max: 33.0) [2023-03-09 07:55:49,060][22664] Avg episode reward: [(0, '49.979')] [2023-03-09 07:55:49,503][23090] Updated weights for policy 0, policy_version 21368 (0.0013) [2023-03-09 07:55:50,341][23090] Updated weights for policy 0, policy_version 21378 (0.0016) [2023-03-09 07:55:51,135][23090] Updated weights for policy 0, policy_version 21388 (0.0015) [2023-03-09 07:55:51,940][23090] Updated weights for policy 0, policy_version 21398 (0.0017) [2023-03-09 07:55:52,809][23090] Updated weights for policy 0, policy_version 21408 (0.0013) [2023-03-09 07:55:53,655][23090] Updated weights for policy 0, policy_version 21418 (0.0013) [2023-03-09 07:55:54,059][22664] Fps is (10 sec: 199883.0, 60 sec: 198791.8, 300 sec: 198830.0). Total num frames: 350994432. Throughput: 0: 49692.0. Samples: 87811056. Policy #0 lag: (min: 1.0, avg: 16.7, max: 33.0) [2023-03-09 07:55:54,060][22664] Avg episode reward: [(0, '52.249')] [2023-03-09 07:55:54,377][23090] Updated weights for policy 0, policy_version 21428 (0.0016) [2023-03-09 07:55:55,310][23090] Updated weights for policy 0, policy_version 21438 (0.0016) [2023-03-09 07:55:56,127][23090] Updated weights for policy 0, policy_version 21448 (0.0013) [2023-03-09 07:55:56,265][22940] Signal inference workers to stop experience collection... (7400 times) [2023-03-09 07:55:56,279][22940] Signal inference workers to resume experience collection... (7400 times) [2023-03-09 07:55:56,338][23090] InferenceWorker_p0-w0: stopping experience collection (7400 times) [2023-03-09 07:55:56,338][23090] InferenceWorker_p0-w0: resuming experience collection (7400 times) [2023-03-09 07:55:56,873][23090] Updated weights for policy 0, policy_version 21458 (0.0021) [2023-03-09 07:55:57,755][23090] Updated weights for policy 0, policy_version 21468 (0.0016) [2023-03-09 07:55:58,583][23090] Updated weights for policy 0, policy_version 21478 (0.0016) [2023-03-09 07:55:59,058][22664] Fps is (10 sec: 199885.9, 60 sec: 198792.8, 300 sec: 198774.0). Total num frames: 351993856. Throughput: 0: 49738.0. Samples: 87962608. Policy #0 lag: (min: 1.0, avg: 16.7, max: 33.0) [2023-03-09 07:55:59,060][22664] Avg episode reward: [(0, '50.146')] [2023-03-09 07:55:59,326][23090] Updated weights for policy 0, policy_version 21488 (0.0013) [2023-03-09 07:56:00,268][23090] Updated weights for policy 0, policy_version 21498 (0.0014) [2023-03-09 07:56:00,992][23090] Updated weights for policy 0, policy_version 21508 (0.0020) [2023-03-09 07:56:01,907][23090] Updated weights for policy 0, policy_version 21519 (0.0013) [2023-03-09 07:56:02,735][23090] Updated weights for policy 0, policy_version 21529 (0.0016) [2023-03-09 07:56:03,584][23090] Updated weights for policy 0, policy_version 21539 (0.0013) [2023-03-09 07:56:04,058][22664] Fps is (10 sec: 198250.9, 60 sec: 198793.9, 300 sec: 198718.5). Total num frames: 352976896. Throughput: 0: 49783.6. Samples: 88261600. Policy #0 lag: (min: 1.0, avg: 16.7, max: 33.0) [2023-03-09 07:56:04,059][22664] Avg episode reward: [(0, '50.154')] [2023-03-09 07:56:04,364][23090] Updated weights for policy 0, policy_version 21549 (0.0016) [2023-03-09 07:56:05,126][23090] Updated weights for policy 0, policy_version 21559 (0.0016) [2023-03-09 07:56:05,986][23090] Updated weights for policy 0, policy_version 21569 (0.0023) [2023-03-09 07:56:06,789][23090] Updated weights for policy 0, policy_version 21579 (0.0022) [2023-03-09 07:56:07,676][23090] Updated weights for policy 0, policy_version 21589 (0.0023) [2023-03-09 07:56:07,688][22940] Signal inference workers to stop experience collection... (7450 times) [2023-03-09 07:56:07,706][22940] Signal inference workers to resume experience collection... (7450 times) [2023-03-09 07:56:07,764][23090] InferenceWorker_p0-w0: stopping experience collection (7450 times) [2023-03-09 07:56:07,764][23090] InferenceWorker_p0-w0: resuming experience collection (7450 times) [2023-03-09 07:56:08,492][23090] Updated weights for policy 0, policy_version 21599 (0.0013) [2023-03-09 07:56:09,059][22664] Fps is (10 sec: 199874.4, 60 sec: 199338.5, 300 sec: 198829.4). Total num frames: 353992704. Throughput: 0: 49829.2. Samples: 88562640. Policy #0 lag: (min: 0.0, avg: 17.8, max: 34.0) [2023-03-09 07:56:09,061][22664] Avg episode reward: [(0, '50.160')] [2023-03-09 07:56:09,312][23090] Updated weights for policy 0, policy_version 21609 (0.0017) [2023-03-09 07:56:10,030][23090] Updated weights for policy 0, policy_version 21619 (0.0018) [2023-03-09 07:56:10,923][23090] Updated weights for policy 0, policy_version 21629 (0.0020) [2023-03-09 07:56:11,752][23090] Updated weights for policy 0, policy_version 21639 (0.0017) [2023-03-09 07:56:12,653][23090] Updated weights for policy 0, policy_version 21650 (0.0018) [2023-03-09 07:56:13,495][23090] Updated weights for policy 0, policy_version 21660 (0.0023) [2023-03-09 07:56:14,059][22664] Fps is (10 sec: 201514.7, 60 sec: 199337.5, 300 sec: 198774.0). Total num frames: 354992128. Throughput: 0: 49874.5. Samples: 88714176. Policy #0 lag: (min: 0.0, avg: 17.8, max: 34.0) [2023-03-09 07:56:14,061][22664] Avg episode reward: [(0, '51.457')] [2023-03-09 07:56:14,328][23090] Updated weights for policy 0, policy_version 21670 (0.0019) [2023-03-09 07:56:15,074][23090] Updated weights for policy 0, policy_version 21680 (0.0016) [2023-03-09 07:56:15,967][23090] Updated weights for policy 0, policy_version 21690 (0.0015) [2023-03-09 07:56:16,745][23090] Updated weights for policy 0, policy_version 21700 (0.0017) [2023-03-09 07:56:17,595][23090] Updated weights for policy 0, policy_version 21710 (0.0018) [2023-03-09 07:56:18,360][23090] Updated weights for policy 0, policy_version 21720 (0.0016) [2023-03-09 07:56:19,059][22664] Fps is (10 sec: 199887.9, 60 sec: 199610.9, 300 sec: 198773.8). Total num frames: 355991552. Throughput: 0: 49830.1. Samples: 89011136. Policy #0 lag: (min: 0.0, avg: 17.8, max: 34.0) [2023-03-09 07:56:19,061][22664] Avg episode reward: [(0, '52.588')] [2023-03-09 07:56:19,220][23090] Updated weights for policy 0, policy_version 21730 (0.0018) [2023-03-09 07:56:20,005][23090] Updated weights for policy 0, policy_version 21740 (0.0017) [2023-03-09 07:56:20,171][22940] Signal inference workers to stop experience collection... (7500 times) [2023-03-09 07:56:20,172][22940] Signal inference workers to resume experience collection... (7500 times) [2023-03-09 07:56:20,232][23090] InferenceWorker_p0-w0: stopping experience collection (7500 times) [2023-03-09 07:56:20,235][23090] InferenceWorker_p0-w0: resuming experience collection (7500 times) [2023-03-09 07:56:20,821][23090] Updated weights for policy 0, policy_version 21750 (0.0018) [2023-03-09 07:56:21,664][23090] Updated weights for policy 0, policy_version 21760 (0.0016) [2023-03-09 07:56:22,512][23090] Updated weights for policy 0, policy_version 21770 (0.0015) [2023-03-09 07:56:23,239][23090] Updated weights for policy 0, policy_version 21780 (0.0013) [2023-03-09 07:56:24,059][22664] Fps is (10 sec: 199887.1, 60 sec: 199610.9, 300 sec: 198718.4). Total num frames: 356990976. Throughput: 0: 50012.4. Samples: 89312192. Policy #0 lag: (min: 1.0, avg: 16.7, max: 33.0) [2023-03-09 07:56:24,061][22664] Avg episode reward: [(0, '52.953')] [2023-03-09 07:56:24,091][23090] Updated weights for policy 0, policy_version 21790 (0.0013) [2023-03-09 07:56:24,977][23090] Updated weights for policy 0, policy_version 21800 (0.0015) [2023-03-09 07:56:25,858][23090] Updated weights for policy 0, policy_version 21811 (0.0015) [2023-03-09 07:56:26,735][23090] Updated weights for policy 0, policy_version 21821 (0.0013) [2023-03-09 07:56:27,567][23090] Updated weights for policy 0, policy_version 21831 (0.0015) [2023-03-09 07:56:28,299][23090] Updated weights for policy 0, policy_version 21841 (0.0017) [2023-03-09 07:56:29,059][22664] Fps is (10 sec: 198252.1, 60 sec: 199338.7, 300 sec: 198718.4). Total num frames: 357974016. Throughput: 0: 49922.9. Samples: 89459648. Policy #0 lag: (min: 1.0, avg: 16.7, max: 33.0) [2023-03-09 07:56:29,059][22664] Avg episode reward: [(0, '50.286')] [2023-03-09 07:56:29,171][23090] Updated weights for policy 0, policy_version 21851 (0.0015) [2023-03-09 07:56:29,941][23090] Updated weights for policy 0, policy_version 21861 (0.0022) [2023-03-09 07:56:30,787][23090] Updated weights for policy 0, policy_version 21871 (0.0019) [2023-03-09 07:56:31,615][23090] Updated weights for policy 0, policy_version 21881 (0.0016) [2023-03-09 07:56:32,364][22940] Signal inference workers to stop experience collection... (7550 times) [2023-03-09 07:56:32,365][22940] Signal inference workers to resume experience collection... (7550 times) [2023-03-09 07:56:32,425][23090] InferenceWorker_p0-w0: stopping experience collection (7550 times) [2023-03-09 07:56:32,425][23090] InferenceWorker_p0-w0: resuming experience collection (7550 times) [2023-03-09 07:56:32,428][23090] Updated weights for policy 0, policy_version 21891 (0.0013) [2023-03-09 07:56:33,201][23090] Updated weights for policy 0, policy_version 21901 (0.0013) [2023-03-09 07:56:33,963][23090] Updated weights for policy 0, policy_version 21911 (0.0017) [2023-03-09 07:56:34,059][22664] Fps is (10 sec: 199890.2, 60 sec: 199611.8, 300 sec: 198774.2). Total num frames: 358989824. Throughput: 0: 49968.0. Samples: 89762688. Policy #0 lag: (min: 1.0, avg: 16.7, max: 33.0) [2023-03-09 07:56:34,060][22664] Avg episode reward: [(0, '48.604')] [2023-03-09 07:56:34,886][23090] Updated weights for policy 0, policy_version 21921 (0.0016) [2023-03-09 07:56:35,654][23090] Updated weights for policy 0, policy_version 21931 (0.0013) [2023-03-09 07:56:36,490][23090] Updated weights for policy 0, policy_version 21941 (0.0013) [2023-03-09 07:56:37,407][23090] Updated weights for policy 0, policy_version 21951 (0.0015) [2023-03-09 07:56:38,218][23090] Updated weights for policy 0, policy_version 21961 (0.0019) [2023-03-09 07:56:38,905][23090] Updated weights for policy 0, policy_version 21971 (0.0017) [2023-03-09 07:56:39,059][22664] Fps is (10 sec: 201523.8, 60 sec: 199884.6, 300 sec: 198774.2). Total num frames: 359989248. Throughput: 0: 50013.7. Samples: 90061664. Policy #0 lag: (min: 1.0, avg: 16.8, max: 33.0) [2023-03-09 07:56:39,060][22664] Avg episode reward: [(0, '50.796')] [2023-03-09 07:56:39,911][23090] Updated weights for policy 0, policy_version 21982 (0.0014) [2023-03-09 07:56:40,727][23090] Updated weights for policy 0, policy_version 21992 (0.0013) [2023-03-09 07:56:41,521][23090] Updated weights for policy 0, policy_version 22002 (0.0013) [2023-03-09 07:56:42,392][23090] Updated weights for policy 0, policy_version 22012 (0.0030) [2023-03-09 07:56:43,202][23090] Updated weights for policy 0, policy_version 22022 (0.0013) [2023-03-09 07:56:43,972][23090] Updated weights for policy 0, policy_version 22032 (0.0013) [2023-03-09 07:56:44,059][22664] Fps is (10 sec: 199881.2, 60 sec: 199884.5, 300 sec: 198718.6). Total num frames: 360988672. Throughput: 0: 49921.5. Samples: 90209088. Policy #0 lag: (min: 1.0, avg: 16.8, max: 33.0) [2023-03-09 07:56:44,061][22664] Avg episode reward: [(0, '51.899')] [2023-03-09 07:56:44,858][23090] Updated weights for policy 0, policy_version 22042 (0.0019) [2023-03-09 07:56:45,618][23090] Updated weights for policy 0, policy_version 22052 (0.0017) [2023-03-09 07:56:46,078][22940] Signal inference workers to stop experience collection... (7600 times) [2023-03-09 07:56:46,079][22940] Signal inference workers to resume experience collection... (7600 times) [2023-03-09 07:56:46,168][23090] InferenceWorker_p0-w0: stopping experience collection (7600 times) [2023-03-09 07:56:46,168][23090] InferenceWorker_p0-w0: resuming experience collection (7600 times) [2023-03-09 07:56:46,539][23090] Updated weights for policy 0, policy_version 22063 (0.0018) [2023-03-09 07:56:47,406][23090] Updated weights for policy 0, policy_version 22073 (0.0013) [2023-03-09 07:56:48,213][23090] Updated weights for policy 0, policy_version 22083 (0.0013) [2023-03-09 07:56:48,985][23090] Updated weights for policy 0, policy_version 22093 (0.0018) [2023-03-09 07:56:49,058][22664] Fps is (10 sec: 198247.1, 60 sec: 199611.9, 300 sec: 198663.0). Total num frames: 361971712. Throughput: 0: 49921.1. Samples: 90508048. Policy #0 lag: (min: 1.0, avg: 16.8, max: 33.0) [2023-03-09 07:56:49,059][22664] Avg episode reward: [(0, '49.029')] [2023-03-09 07:56:49,757][23090] Updated weights for policy 0, policy_version 22103 (0.0016) [2023-03-09 07:56:50,656][23090] Updated weights for policy 0, policy_version 22113 (0.0016) [2023-03-09 07:56:51,439][23090] Updated weights for policy 0, policy_version 22123 (0.0015) [2023-03-09 07:56:52,282][23090] Updated weights for policy 0, policy_version 22133 (0.0019) [2023-03-09 07:56:53,103][23090] Updated weights for policy 0, policy_version 22143 (0.0013) [2023-03-09 07:56:53,924][23090] Updated weights for policy 0, policy_version 22153 (0.0017) [2023-03-09 07:56:54,059][22664] Fps is (10 sec: 199885.8, 60 sec: 199885.0, 300 sec: 198774.0). Total num frames: 362987520. Throughput: 0: 49920.7. Samples: 90809056. Policy #0 lag: (min: 1.0, avg: 17.2, max: 33.0) [2023-03-09 07:56:54,060][22664] Avg episode reward: [(0, '49.573')] [2023-03-09 07:56:54,718][23090] Updated weights for policy 0, policy_version 22163 (0.0013) [2023-03-09 07:56:55,578][23090] Updated weights for policy 0, policy_version 22173 (0.0014) [2023-03-09 07:56:56,376][23090] Updated weights for policy 0, policy_version 22183 (0.0013) [2023-03-09 07:56:57,135][23090] Updated weights for policy 0, policy_version 22193 (0.0013) [2023-03-09 07:56:57,974][23090] Updated weights for policy 0, policy_version 22203 (0.0013) [2023-03-09 07:56:58,814][23090] Updated weights for policy 0, policy_version 22213 (0.0016) [2023-03-09 07:56:59,059][22664] Fps is (10 sec: 201516.7, 60 sec: 199883.7, 300 sec: 198718.4). Total num frames: 363986944. Throughput: 0: 49920.8. Samples: 90960608. Policy #0 lag: (min: 1.0, avg: 17.2, max: 33.0) [2023-03-09 07:56:59,061][22664] Avg episode reward: [(0, '50.071')] [2023-03-09 07:56:59,148][22940] Signal inference workers to stop experience collection... (7650 times) [2023-03-09 07:56:59,149][22940] Signal inference workers to resume experience collection... (7650 times) [2023-03-09 07:56:59,215][23090] InferenceWorker_p0-w0: stopping experience collection (7650 times) [2023-03-09 07:56:59,215][23090] InferenceWorker_p0-w0: resuming experience collection (7650 times) [2023-03-09 07:56:59,633][23090] Updated weights for policy 0, policy_version 22223 (0.0016) [2023-03-09 07:57:00,456][23090] Updated weights for policy 0, policy_version 22233 (0.0019) [2023-03-09 07:57:01,271][23090] Updated weights for policy 0, policy_version 22243 (0.0013) [2023-03-09 07:57:02,046][23090] Updated weights for policy 0, policy_version 22253 (0.0017) [2023-03-09 07:57:02,839][23090] Updated weights for policy 0, policy_version 22263 (0.0013) [2023-03-09 07:57:03,723][23090] Updated weights for policy 0, policy_version 22273 (0.0013) [2023-03-09 07:57:04,059][22664] Fps is (10 sec: 199881.4, 60 sec: 200156.7, 300 sec: 198718.4). Total num frames: 364986368. Throughput: 0: 49965.5. Samples: 91259584. Policy #0 lag: (min: 1.0, avg: 17.2, max: 33.0) [2023-03-09 07:57:04,062][22664] Avg episode reward: [(0, '48.547')] [2023-03-09 07:57:04,507][23090] Updated weights for policy 0, policy_version 22283 (0.0018) [2023-03-09 07:57:05,346][23090] Updated weights for policy 0, policy_version 22293 (0.0013) [2023-03-09 07:57:06,188][23090] Updated weights for policy 0, policy_version 22303 (0.0013) [2023-03-09 07:57:07,066][23090] Updated weights for policy 0, policy_version 22313 (0.0016) [2023-03-09 07:57:07,762][23090] Updated weights for policy 0, policy_version 22323 (0.0017) [2023-03-09 07:57:08,667][23090] Updated weights for policy 0, policy_version 22333 (0.0016) [2023-03-09 07:57:09,058][22664] Fps is (10 sec: 198252.6, 60 sec: 199613.4, 300 sec: 198774.0). Total num frames: 365969408. Throughput: 0: 49965.1. Samples: 91560608. Policy #0 lag: (min: 1.0, avg: 16.7, max: 33.0) [2023-03-09 07:57:09,059][22664] Avg episode reward: [(0, '52.490')] [2023-03-09 07:57:09,515][23090] Updated weights for policy 0, policy_version 22343 (0.0013) [2023-03-09 07:57:10,255][23090] Updated weights for policy 0, policy_version 22353 (0.0016) [2023-03-09 07:57:11,129][23090] Updated weights for policy 0, policy_version 22363 (0.0015) [2023-03-09 07:57:11,773][22940] Signal inference workers to stop experience collection... (7700 times) [2023-03-09 07:57:11,774][22940] Signal inference workers to resume experience collection... (7700 times) [2023-03-09 07:57:11,845][23090] InferenceWorker_p0-w0: stopping experience collection (7700 times) [2023-03-09 07:57:11,845][23090] InferenceWorker_p0-w0: resuming experience collection (7700 times) [2023-03-09 07:57:11,944][23090] Updated weights for policy 0, policy_version 22373 (0.0013) [2023-03-09 07:57:12,814][23090] Updated weights for policy 0, policy_version 22384 (0.0013) [2023-03-09 07:57:13,665][23090] Updated weights for policy 0, policy_version 22394 (0.0017) [2023-03-09 07:57:14,058][22664] Fps is (10 sec: 198253.1, 60 sec: 199613.1, 300 sec: 198718.7). Total num frames: 366968832. Throughput: 0: 50010.0. Samples: 91710096. Policy #0 lag: (min: 1.0, avg: 16.7, max: 33.0) [2023-03-09 07:57:14,059][22664] Avg episode reward: [(0, '50.177')] [2023-03-09 07:57:14,471][23090] Updated weights for policy 0, policy_version 22404 (0.0013) [2023-03-09 07:57:15,274][23090] Updated weights for policy 0, policy_version 22414 (0.0013) [2023-03-09 07:57:16,071][23090] Updated weights for policy 0, policy_version 22424 (0.0015) [2023-03-09 07:57:16,940][23090] Updated weights for policy 0, policy_version 22434 (0.0024) [2023-03-09 07:57:17,712][23090] Updated weights for policy 0, policy_version 22444 (0.0013) [2023-03-09 07:57:18,517][23090] Updated weights for policy 0, policy_version 22454 (0.0013) [2023-03-09 07:57:19,058][22664] Fps is (10 sec: 201522.9, 60 sec: 199885.9, 300 sec: 198829.6). Total num frames: 367984640. Throughput: 0: 49965.2. Samples: 92011120. Policy #0 lag: (min: 1.0, avg: 16.7, max: 33.0) [2023-03-09 07:57:19,059][22664] Avg episode reward: [(0, '49.863')] [2023-03-09 07:57:19,063][22940] Saving /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000022460_367984640.pth... [2023-03-09 07:57:19,117][22940] Removing /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000019545_320225280.pth [2023-03-09 07:57:19,389][23090] Updated weights for policy 0, policy_version 22464 (0.0017) [2023-03-09 07:57:20,206][23090] Updated weights for policy 0, policy_version 22474 (0.0013) [2023-03-09 07:57:20,938][23090] Updated weights for policy 0, policy_version 22484 (0.0019) [2023-03-09 07:57:21,849][23090] Updated weights for policy 0, policy_version 22494 (0.0019) [2023-03-09 07:57:22,703][23090] Updated weights for policy 0, policy_version 22504 (0.0017) [2023-03-09 07:57:23,449][23090] Updated weights for policy 0, policy_version 22514 (0.0020) [2023-03-09 07:57:24,058][22664] Fps is (10 sec: 199885.1, 60 sec: 199612.8, 300 sec: 198829.7). Total num frames: 368967680. Throughput: 0: 49920.1. Samples: 92308064. Policy #0 lag: (min: 1.0, avg: 16.7, max: 34.0) [2023-03-09 07:57:24,059][22664] Avg episode reward: [(0, '49.739')] [2023-03-09 07:57:24,357][23090] Updated weights for policy 0, policy_version 22524 (0.0013) [2023-03-09 07:57:25,176][23090] Updated weights for policy 0, policy_version 22534 (0.0013) [2023-03-09 07:57:25,427][22940] Signal inference workers to stop experience collection... (7750 times) [2023-03-09 07:57:25,427][22940] Signal inference workers to resume experience collection... (7750 times) [2023-03-09 07:57:25,499][23090] InferenceWorker_p0-w0: stopping experience collection (7750 times) [2023-03-09 07:57:25,499][23090] InferenceWorker_p0-w0: resuming experience collection (7750 times) [2023-03-09 07:57:25,979][23090] Updated weights for policy 0, policy_version 22544 (0.0013) [2023-03-09 07:57:26,880][23090] Updated weights for policy 0, policy_version 22554 (0.0023) [2023-03-09 07:57:27,676][23090] Updated weights for policy 0, policy_version 22564 (0.0017) [2023-03-09 07:57:28,457][23090] Updated weights for policy 0, policy_version 22574 (0.0019) [2023-03-09 07:57:29,059][22664] Fps is (10 sec: 198245.2, 60 sec: 199884.8, 300 sec: 198829.5). Total num frames: 369967104. Throughput: 0: 49920.1. Samples: 92455488. Policy #0 lag: (min: 1.0, avg: 16.7, max: 34.0) [2023-03-09 07:57:29,061][22664] Avg episode reward: [(0, '52.284')] [2023-03-09 07:57:29,264][23090] Updated weights for policy 0, policy_version 22584 (0.0014) [2023-03-09 07:57:30,218][23090] Updated weights for policy 0, policy_version 22595 (0.0015) [2023-03-09 07:57:30,998][23090] Updated weights for policy 0, policy_version 22605 (0.0016) [2023-03-09 07:57:31,762][23090] Updated weights for policy 0, policy_version 22615 (0.0013) [2023-03-09 07:57:32,657][23090] Updated weights for policy 0, policy_version 22625 (0.0013) [2023-03-09 07:57:33,437][23090] Updated weights for policy 0, policy_version 22635 (0.0018) [2023-03-09 07:57:34,058][22664] Fps is (10 sec: 199885.0, 60 sec: 199612.0, 300 sec: 198774.1). Total num frames: 370966528. Throughput: 0: 49965.9. Samples: 92756512. Policy #0 lag: (min: 1.0, avg: 16.7, max: 34.0) [2023-03-09 07:57:34,060][22664] Avg episode reward: [(0, '52.276')] [2023-03-09 07:57:34,279][23090] Updated weights for policy 0, policy_version 22645 (0.0013) [2023-03-09 07:57:35,128][23090] Updated weights for policy 0, policy_version 22655 (0.0021) [2023-03-09 07:57:35,951][23090] Updated weights for policy 0, policy_version 22665 (0.0019) [2023-03-09 07:57:36,750][23090] Updated weights for policy 0, policy_version 22675 (0.0019) [2023-03-09 07:57:37,598][23090] Updated weights for policy 0, policy_version 22685 (0.0018) [2023-03-09 07:57:38,408][23090] Updated weights for policy 0, policy_version 22695 (0.0019) [2023-03-09 07:57:39,043][22940] Signal inference workers to stop experience collection... (7800 times) [2023-03-09 07:57:39,043][22940] Signal inference workers to resume experience collection... (7800 times) [2023-03-09 07:57:39,059][22664] Fps is (10 sec: 199885.3, 60 sec: 199611.7, 300 sec: 198829.7). Total num frames: 371965952. Throughput: 0: 49920.5. Samples: 93055472. Policy #0 lag: (min: 1.0, avg: 16.3, max: 32.0) [2023-03-09 07:57:39,060][22664] Avg episode reward: [(0, '54.182')] [2023-03-09 07:57:39,103][23090] InferenceWorker_p0-w0: stopping experience collection (7800 times) [2023-03-09 07:57:39,106][23090] InferenceWorker_p0-w0: resuming experience collection (7800 times) [2023-03-09 07:57:39,114][22940] Saving new best policy, reward=54.182! [2023-03-09 07:57:39,261][23090] Updated weights for policy 0, policy_version 22705 (0.0017) [2023-03-09 07:57:40,062][23090] Updated weights for policy 0, policy_version 22715 (0.0016) [2023-03-09 07:57:40,863][23090] Updated weights for policy 0, policy_version 22725 (0.0013) [2023-03-09 07:57:41,657][23090] Updated weights for policy 0, policy_version 22735 (0.0013) [2023-03-09 07:57:42,518][23090] Updated weights for policy 0, policy_version 22745 (0.0016) [2023-03-09 07:57:43,404][23090] Updated weights for policy 0, policy_version 22756 (0.0013) [2023-03-09 07:57:44,059][22664] Fps is (10 sec: 199876.7, 60 sec: 199611.2, 300 sec: 198884.8). Total num frames: 372965376. Throughput: 0: 49828.6. Samples: 93202896. Policy #0 lag: (min: 1.0, avg: 16.3, max: 32.0) [2023-03-09 07:57:44,061][22664] Avg episode reward: [(0, '49.148')] [2023-03-09 07:57:44,226][23090] Updated weights for policy 0, policy_version 22766 (0.0024) [2023-03-09 07:57:45,031][23090] Updated weights for policy 0, policy_version 22776 (0.0013) [2023-03-09 07:57:45,907][23090] Updated weights for policy 0, policy_version 22786 (0.0015) [2023-03-09 07:57:46,685][23090] Updated weights for policy 0, policy_version 22796 (0.0013) [2023-03-09 07:57:47,500][23090] Updated weights for policy 0, policy_version 22806 (0.0013) [2023-03-09 07:57:48,367][23090] Updated weights for policy 0, policy_version 22816 (0.0020) [2023-03-09 07:57:49,059][22664] Fps is (10 sec: 198240.6, 60 sec: 199610.6, 300 sec: 198829.3). Total num frames: 373948416. Throughput: 0: 49874.1. Samples: 93503920. Policy #0 lag: (min: 1.0, avg: 16.3, max: 32.0) [2023-03-09 07:57:49,060][22664] Avg episode reward: [(0, '52.337')] [2023-03-09 07:57:49,177][23090] Updated weights for policy 0, policy_version 22826 (0.0013) [2023-03-09 07:57:49,927][23090] Updated weights for policy 0, policy_version 22836 (0.0013) [2023-03-09 07:57:50,813][23090] Updated weights for policy 0, policy_version 22846 (0.0013) [2023-03-09 07:57:51,655][23090] Updated weights for policy 0, policy_version 22856 (0.0016) [2023-03-09 07:57:51,833][22940] Signal inference workers to stop experience collection... (7850 times) [2023-03-09 07:57:51,834][22940] Signal inference workers to resume experience collection... (7850 times) [2023-03-09 07:57:51,893][23090] InferenceWorker_p0-w0: stopping experience collection (7850 times) [2023-03-09 07:57:51,893][23090] InferenceWorker_p0-w0: resuming experience collection (7850 times) [2023-03-09 07:57:52,423][23090] Updated weights for policy 0, policy_version 22866 (0.0021) [2023-03-09 07:57:53,275][23090] Updated weights for policy 0, policy_version 22876 (0.0020) [2023-03-09 07:57:54,059][22664] Fps is (10 sec: 198248.9, 60 sec: 199338.4, 300 sec: 198940.5). Total num frames: 374947840. Throughput: 0: 49829.1. Samples: 93802928. Policy #0 lag: (min: 0.0, avg: 17.8, max: 33.0) [2023-03-09 07:57:54,061][22664] Avg episode reward: [(0, '49.779')] [2023-03-09 07:57:54,094][23090] Updated weights for policy 0, policy_version 22886 (0.0016) [2023-03-09 07:57:54,863][23090] Updated weights for policy 0, policy_version 22896 (0.0013) [2023-03-09 07:57:55,738][23090] Updated weights for policy 0, policy_version 22906 (0.0021) [2023-03-09 07:57:56,644][23090] Updated weights for policy 0, policy_version 22917 (0.0013) [2023-03-09 07:57:57,425][23090] Updated weights for policy 0, policy_version 22927 (0.0017) [2023-03-09 07:57:58,271][23090] Updated weights for policy 0, policy_version 22937 (0.0015) [2023-03-09 07:57:59,059][22664] Fps is (10 sec: 199891.1, 60 sec: 199339.6, 300 sec: 198885.2). Total num frames: 375947264. Throughput: 0: 49829.6. Samples: 93952432. Policy #0 lag: (min: 0.0, avg: 17.8, max: 33.0) [2023-03-09 07:57:59,059][22664] Avg episode reward: [(0, '50.983')] [2023-03-09 07:57:59,113][23090] Updated weights for policy 0, policy_version 22947 (0.0019) [2023-03-09 07:57:59,875][23090] Updated weights for policy 0, policy_version 22957 (0.0013) [2023-03-09 07:58:00,649][23090] Updated weights for policy 0, policy_version 22967 (0.0013) [2023-03-09 07:58:01,563][23090] Updated weights for policy 0, policy_version 22977 (0.0015) [2023-03-09 07:58:02,379][23090] Updated weights for policy 0, policy_version 22987 (0.0013) [2023-03-09 07:58:03,174][23090] Updated weights for policy 0, policy_version 22997 (0.0012) [2023-03-09 07:58:04,030][22940] Signal inference workers to stop experience collection... (7900 times) [2023-03-09 07:58:04,031][22940] Signal inference workers to resume experience collection... (7900 times) [2023-03-09 07:58:04,061][23090] Updated weights for policy 0, policy_version 23007 (0.0022) [2023-03-09 07:58:04,059][22664] Fps is (10 sec: 199877.5, 60 sec: 199337.7, 300 sec: 198940.5). Total num frames: 376946688. Throughput: 0: 49783.2. Samples: 94251392. Policy #0 lag: (min: 0.0, avg: 17.8, max: 33.0) [2023-03-09 07:58:04,062][22664] Avg episode reward: [(0, '51.739')] [2023-03-09 07:58:04,094][23090] InferenceWorker_p0-w0: stopping experience collection (7900 times) [2023-03-09 07:58:04,097][23090] InferenceWorker_p0-w0: resuming experience collection (7900 times) [2023-03-09 07:58:04,839][23090] Updated weights for policy 0, policy_version 23017 (0.0013) [2023-03-09 07:58:05,683][23090] Updated weights for policy 0, policy_version 23028 (0.0013) [2023-03-09 07:58:06,579][23090] Updated weights for policy 0, policy_version 23038 (0.0013) [2023-03-09 07:58:07,390][23090] Updated weights for policy 0, policy_version 23048 (0.0013) [2023-03-09 07:58:08,188][23090] Updated weights for policy 0, policy_version 23058 (0.0018) [2023-03-09 07:58:09,035][23090] Updated weights for policy 0, policy_version 23068 (0.0016) [2023-03-09 07:58:09,059][22664] Fps is (10 sec: 199884.2, 60 sec: 199611.6, 300 sec: 199051.7). Total num frames: 377946112. Throughput: 0: 49829.2. Samples: 94550384. Policy #0 lag: (min: 1.0, avg: 17.2, max: 33.0) [2023-03-09 07:58:09,060][22664] Avg episode reward: [(0, '51.084')] [2023-03-09 07:58:09,850][23090] Updated weights for policy 0, policy_version 23078 (0.0013) [2023-03-09 07:58:10,647][23090] Updated weights for policy 0, policy_version 23088 (0.0016) [2023-03-09 07:58:11,490][23090] Updated weights for policy 0, policy_version 23098 (0.0013) [2023-03-09 07:58:12,480][23090] Updated weights for policy 0, policy_version 23110 (0.0014) [2023-03-09 07:58:13,208][23090] Updated weights for policy 0, policy_version 23120 (0.0013) [2023-03-09 07:58:14,059][22664] Fps is (10 sec: 199892.5, 60 sec: 199611.0, 300 sec: 199051.8). Total num frames: 378945536. Throughput: 0: 49920.5. Samples: 94701920. Policy #0 lag: (min: 1.0, avg: 17.2, max: 33.0) [2023-03-09 07:58:14,060][22664] Avg episode reward: [(0, '49.546')] [2023-03-09 07:58:14,141][23090] Updated weights for policy 0, policy_version 23130 (0.0018) [2023-03-09 07:58:14,926][23090] Updated weights for policy 0, policy_version 23140 (0.0014) [2023-03-09 07:58:15,845][23090] Updated weights for policy 0, policy_version 23151 (0.0020) [2023-03-09 07:58:16,641][23090] Updated weights for policy 0, policy_version 23161 (0.0019) [2023-03-09 07:58:17,169][22940] Signal inference workers to stop experience collection... (7950 times) [2023-03-09 07:58:17,170][22940] Signal inference workers to resume experience collection... (7950 times) [2023-03-09 07:58:17,232][23090] InferenceWorker_p0-w0: stopping experience collection (7950 times) [2023-03-09 07:58:17,235][23090] InferenceWorker_p0-w0: resuming experience collection (7950 times) [2023-03-09 07:58:17,520][23090] Updated weights for policy 0, policy_version 23171 (0.0017) [2023-03-09 07:58:18,251][23090] Updated weights for policy 0, policy_version 23181 (0.0019) [2023-03-09 07:58:19,026][23090] Updated weights for policy 0, policy_version 23191 (0.0013) [2023-03-09 07:58:19,059][22664] Fps is (10 sec: 201523.6, 60 sec: 199611.7, 300 sec: 199051.7). Total num frames: 379961344. Throughput: 0: 49875.8. Samples: 95000928. Policy #0 lag: (min: 1.0, avg: 17.2, max: 33.0) [2023-03-09 07:58:19,059][22664] Avg episode reward: [(0, '49.840')] [2023-03-09 07:58:19,935][23090] Updated weights for policy 0, policy_version 23201 (0.0013) [2023-03-09 07:58:20,752][23090] Updated weights for policy 0, policy_version 23211 (0.0018) [2023-03-09 07:58:21,557][23090] Updated weights for policy 0, policy_version 23221 (0.0019) [2023-03-09 07:58:22,434][23090] Updated weights for policy 0, policy_version 23231 (0.0016) [2023-03-09 07:58:23,194][23090] Updated weights for policy 0, policy_version 23241 (0.0013) [2023-03-09 07:58:23,972][23090] Updated weights for policy 0, policy_version 23251 (0.0016) [2023-03-09 07:58:24,059][22664] Fps is (10 sec: 201522.8, 60 sec: 199883.9, 300 sec: 199162.9). Total num frames: 380960768. Throughput: 0: 49875.3. Samples: 95299872. Policy #0 lag: (min: 1.0, avg: 17.0, max: 33.0) [2023-03-09 07:58:24,061][22664] Avg episode reward: [(0, '48.913')] [2023-03-09 07:58:24,860][23090] Updated weights for policy 0, policy_version 23261 (0.0013) [2023-03-09 07:58:25,696][23090] Updated weights for policy 0, policy_version 23271 (0.0013) [2023-03-09 07:58:26,515][23090] Updated weights for policy 0, policy_version 23281 (0.0016) [2023-03-09 07:58:27,344][23090] Updated weights for policy 0, policy_version 23291 (0.0019) [2023-03-09 07:58:28,187][23090] Updated weights for policy 0, policy_version 23301 (0.0013) [2023-03-09 07:58:29,013][23090] Updated weights for policy 0, policy_version 23311 (0.0016) [2023-03-09 07:58:29,059][22664] Fps is (10 sec: 198240.4, 60 sec: 199610.8, 300 sec: 199162.8). Total num frames: 381943808. Throughput: 0: 49921.5. Samples: 95449360. Policy #0 lag: (min: 1.0, avg: 17.0, max: 33.0) [2023-03-09 07:58:29,061][22664] Avg episode reward: [(0, '51.159')] [2023-03-09 07:58:29,817][23090] Updated weights for policy 0, policy_version 23321 (0.0026) [2023-03-09 07:58:30,686][23090] Updated weights for policy 0, policy_version 23331 (0.0017) [2023-03-09 07:58:31,458][23090] Updated weights for policy 0, policy_version 23341 (0.0014) [2023-03-09 07:58:32,150][22940] Signal inference workers to stop experience collection... (8000 times) [2023-03-09 07:58:32,164][22940] Signal inference workers to resume experience collection... (8000 times) [2023-03-09 07:58:32,222][23090] InferenceWorker_p0-w0: stopping experience collection (8000 times) [2023-03-09 07:58:32,222][23090] InferenceWorker_p0-w0: resuming experience collection (8000 times) [2023-03-09 07:58:32,224][23090] Updated weights for policy 0, policy_version 23351 (0.0013) [2023-03-09 07:58:33,118][23090] Updated weights for policy 0, policy_version 23361 (0.0016) [2023-03-09 07:58:33,926][23090] Updated weights for policy 0, policy_version 23371 (0.0022) [2023-03-09 07:58:34,059][22664] Fps is (10 sec: 196607.7, 60 sec: 199337.7, 300 sec: 199163.0). Total num frames: 382926848. Throughput: 0: 49876.0. Samples: 95748336. Policy #0 lag: (min: 1.0, avg: 17.0, max: 33.0) [2023-03-09 07:58:34,061][22664] Avg episode reward: [(0, '52.049')] [2023-03-09 07:58:34,782][23090] Updated weights for policy 0, policy_version 23381 (0.0013) [2023-03-09 07:58:35,662][23090] Updated weights for policy 0, policy_version 23392 (0.0025) [2023-03-09 07:58:36,551][23090] Updated weights for policy 0, policy_version 23402 (0.0017) [2023-03-09 07:58:37,254][23090] Updated weights for policy 0, policy_version 23412 (0.0015) [2023-03-09 07:58:38,173][23090] Updated weights for policy 0, policy_version 23422 (0.0016) [2023-03-09 07:58:39,010][23090] Updated weights for policy 0, policy_version 23432 (0.0018) [2023-03-09 07:58:39,059][22664] Fps is (10 sec: 196609.0, 60 sec: 199064.8, 300 sec: 199162.6). Total num frames: 383909888. Throughput: 0: 49784.8. Samples: 96043248. Policy #0 lag: (min: 1.0, avg: 17.0, max: 33.0) [2023-03-09 07:58:39,061][22664] Avg episode reward: [(0, '47.538')] [2023-03-09 07:58:39,782][23090] Updated weights for policy 0, policy_version 23442 (0.0013) [2023-03-09 07:58:40,656][23090] Updated weights for policy 0, policy_version 23452 (0.0016) [2023-03-09 07:58:41,471][23090] Updated weights for policy 0, policy_version 23462 (0.0013) [2023-03-09 07:58:42,238][23090] Updated weights for policy 0, policy_version 23472 (0.0013) [2023-03-09 07:58:43,087][23090] Updated weights for policy 0, policy_version 23482 (0.0016) [2023-03-09 07:58:43,915][23090] Updated weights for policy 0, policy_version 23492 (0.0019) [2023-03-09 07:58:44,059][22664] Fps is (10 sec: 198247.0, 60 sec: 199066.1, 300 sec: 199162.9). Total num frames: 384909312. Throughput: 0: 49830.2. Samples: 96194800. Policy #0 lag: (min: 1.0, avg: 17.0, max: 33.0) [2023-03-09 07:58:44,060][22664] Avg episode reward: [(0, '51.152')] [2023-03-09 07:58:44,711][23090] Updated weights for policy 0, policy_version 23502 (0.0018) [2023-03-09 07:58:45,666][23090] Updated weights for policy 0, policy_version 23513 (0.0015) [2023-03-09 07:58:46,510][23090] Updated weights for policy 0, policy_version 23523 (0.0016) [2023-03-09 07:58:47,280][23090] Updated weights for policy 0, policy_version 23533 (0.0013) [2023-03-09 07:58:48,045][23090] Updated weights for policy 0, policy_version 23543 (0.0013) [2023-03-09 07:58:48,776][22940] Signal inference workers to stop experience collection... (8050 times) [2023-03-09 07:58:48,777][22940] Signal inference workers to resume experience collection... (8050 times) [2023-03-09 07:58:48,842][23090] InferenceWorker_p0-w0: stopping experience collection (8050 times) [2023-03-09 07:58:48,842][23090] InferenceWorker_p0-w0: resuming experience collection (8050 times) [2023-03-09 07:58:48,929][23090] Updated weights for policy 0, policy_version 23553 (0.0013) [2023-03-09 07:58:49,059][22664] Fps is (10 sec: 199884.3, 60 sec: 199338.7, 300 sec: 199218.2). Total num frames: 385908736. Throughput: 0: 49785.9. Samples: 96491744. Policy #0 lag: (min: 1.0, avg: 17.0, max: 33.0) [2023-03-09 07:58:49,061][22664] Avg episode reward: [(0, '52.273')] [2023-03-09 07:58:49,773][23090] Updated weights for policy 0, policy_version 23563 (0.0022) [2023-03-09 07:58:50,558][23090] Updated weights for policy 0, policy_version 23573 (0.0018) [2023-03-09 07:58:51,439][23090] Updated weights for policy 0, policy_version 23583 (0.0016) [2023-03-09 07:58:52,252][23090] Updated weights for policy 0, policy_version 23593 (0.0020) [2023-03-09 07:58:53,070][23090] Updated weights for policy 0, policy_version 23604 (0.0018) [2023-03-09 07:58:53,965][23090] Updated weights for policy 0, policy_version 23614 (0.0013) [2023-03-09 07:58:54,059][22664] Fps is (10 sec: 199880.3, 60 sec: 199338.0, 300 sec: 199218.1). Total num frames: 386908160. Throughput: 0: 49784.1. Samples: 96790688. Policy #0 lag: (min: 1.0, avg: 17.0, max: 33.0) [2023-03-09 07:58:54,061][22664] Avg episode reward: [(0, '50.514')] [2023-03-09 07:58:54,809][23090] Updated weights for policy 0, policy_version 23624 (0.0016) [2023-03-09 07:58:55,581][23090] Updated weights for policy 0, policy_version 23634 (0.0017) [2023-03-09 07:58:56,423][23090] Updated weights for policy 0, policy_version 23644 (0.0016) [2023-03-09 07:58:57,257][23090] Updated weights for policy 0, policy_version 23654 (0.0023) [2023-03-09 07:58:58,020][23090] Updated weights for policy 0, policy_version 23664 (0.0022) [2023-03-09 07:58:58,888][23090] Updated weights for policy 0, policy_version 23674 (0.0013) [2023-03-09 07:58:59,059][22664] Fps is (10 sec: 199883.5, 60 sec: 199337.5, 300 sec: 199273.6). Total num frames: 387907584. Throughput: 0: 49784.4. Samples: 96942224. Policy #0 lag: (min: 1.0, avg: 17.0, max: 33.0) [2023-03-09 07:58:59,061][22664] Avg episode reward: [(0, '49.841')] [2023-03-09 07:58:59,703][23090] Updated weights for policy 0, policy_version 23684 (0.0017) [2023-03-09 07:59:00,473][23090] Updated weights for policy 0, policy_version 23694 (0.0017) [2023-03-09 07:59:01,319][23090] Updated weights for policy 0, policy_version 23704 (0.0016) [2023-03-09 07:59:02,189][23090] Updated weights for policy 0, policy_version 23714 (0.0015) [2023-03-09 07:59:02,963][23090] Updated weights for policy 0, policy_version 23724 (0.0013) [2023-03-09 07:59:03,807][23090] Updated weights for policy 0, policy_version 23735 (0.0016) [2023-03-09 07:59:04,059][22664] Fps is (10 sec: 199890.8, 60 sec: 199340.2, 300 sec: 199274.2). Total num frames: 388907008. Throughput: 0: 49783.7. Samples: 97241200. Policy #0 lag: (min: 1.0, avg: 17.0, max: 33.0) [2023-03-09 07:59:04,061][22664] Avg episode reward: [(0, '52.132')] [2023-03-09 07:59:04,569][22940] Signal inference workers to stop experience collection... (8100 times) [2023-03-09 07:59:04,570][22940] Signal inference workers to resume experience collection... (8100 times) [2023-03-09 07:59:04,630][23090] InferenceWorker_p0-w0: stopping experience collection (8100 times) [2023-03-09 07:59:04,633][23090] InferenceWorker_p0-w0: resuming experience collection (8100 times) [2023-03-09 07:59:04,747][23090] Updated weights for policy 0, policy_version 23745 (0.0013) [2023-03-09 07:59:05,532][23090] Updated weights for policy 0, policy_version 23755 (0.0019) [2023-03-09 07:59:06,300][23090] Updated weights for policy 0, policy_version 23765 (0.0021) [2023-03-09 07:59:07,197][23090] Updated weights for policy 0, policy_version 23775 (0.0015) [2023-03-09 07:59:08,063][23090] Updated weights for policy 0, policy_version 23785 (0.0015) [2023-03-09 07:59:08,754][23090] Updated weights for policy 0, policy_version 23795 (0.0019) [2023-03-09 07:59:09,059][22664] Fps is (10 sec: 201521.8, 60 sec: 199610.4, 300 sec: 199384.8). Total num frames: 389922816. Throughput: 0: 49830.2. Samples: 97542240. Policy #0 lag: (min: 1.0, avg: 17.0, max: 33.0) [2023-03-09 07:59:09,061][22664] Avg episode reward: [(0, '49.684')] [2023-03-09 07:59:09,671][23090] Updated weights for policy 0, policy_version 23805 (0.0017) [2023-03-09 07:59:10,442][23090] Updated weights for policy 0, policy_version 23815 (0.0013) [2023-03-09 07:59:11,237][23090] Updated weights for policy 0, policy_version 23825 (0.0013) [2023-03-09 07:59:12,087][23090] Updated weights for policy 0, policy_version 23835 (0.0016) [2023-03-09 07:59:12,896][23090] Updated weights for policy 0, policy_version 23845 (0.0025) [2023-03-09 07:59:13,726][23090] Updated weights for policy 0, policy_version 23855 (0.0020) [2023-03-09 07:59:14,059][22664] Fps is (10 sec: 201519.2, 60 sec: 199611.3, 300 sec: 199495.9). Total num frames: 390922240. Throughput: 0: 49785.2. Samples: 97689696. Policy #0 lag: (min: 1.0, avg: 17.0, max: 33.0) [2023-03-09 07:59:14,061][22664] Avg episode reward: [(0, '50.910')] [2023-03-09 07:59:14,566][23090] Updated weights for policy 0, policy_version 23865 (0.0022) [2023-03-09 07:59:15,391][23090] Updated weights for policy 0, policy_version 23875 (0.0015) [2023-03-09 07:59:16,141][23090] Updated weights for policy 0, policy_version 23885 (0.0028) [2023-03-09 07:59:16,918][23090] Updated weights for policy 0, policy_version 23895 (0.0026) [2023-03-09 07:59:17,817][23090] Updated weights for policy 0, policy_version 23905 (0.0022) [2023-03-09 07:59:18,635][23090] Updated weights for policy 0, policy_version 23915 (0.0018) [2023-03-09 07:59:19,058][22664] Fps is (10 sec: 198255.3, 60 sec: 199065.7, 300 sec: 199440.5). Total num frames: 391905280. Throughput: 0: 49830.3. Samples: 97990688. Policy #0 lag: (min: 1.0, avg: 17.0, max: 33.0) [2023-03-09 07:59:19,059][22664] Avg episode reward: [(0, '52.721')] [2023-03-09 07:59:19,114][22940] Saving /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000023921_391921664.pth... [2023-03-09 07:59:19,183][22940] Removing /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000020998_344031232.pth [2023-03-09 07:59:19,446][23090] Updated weights for policy 0, policy_version 23925 (0.0016) [2023-03-09 07:59:19,449][22940] Signal inference workers to stop experience collection... (8150 times) [2023-03-09 07:59:19,450][22940] Signal inference workers to resume experience collection... (8150 times) [2023-03-09 07:59:19,529][23090] InferenceWorker_p0-w0: stopping experience collection (8150 times) [2023-03-09 07:59:19,530][23090] InferenceWorker_p0-w0: resuming experience collection (8150 times) [2023-03-09 07:59:20,400][23090] Updated weights for policy 0, policy_version 23936 (0.0021) [2023-03-09 07:59:21,247][23090] Updated weights for policy 0, policy_version 23946 (0.0026) [2023-03-09 07:59:21,947][23090] Updated weights for policy 0, policy_version 23956 (0.0015) [2023-03-09 07:59:22,868][23090] Updated weights for policy 0, policy_version 23966 (0.0018) [2023-03-09 07:59:23,716][23090] Updated weights for policy 0, policy_version 23976 (0.0013) [2023-03-09 07:59:24,059][22664] Fps is (10 sec: 196608.3, 60 sec: 198792.2, 300 sec: 199440.3). Total num frames: 392888320. Throughput: 0: 49874.8. Samples: 98287616. Policy #0 lag: (min: 1.0, avg: 17.0, max: 33.0) [2023-03-09 07:59:24,061][22664] Avg episode reward: [(0, '52.323')] [2023-03-09 07:59:24,490][23090] Updated weights for policy 0, policy_version 23986 (0.0020) [2023-03-09 07:59:25,363][23090] Updated weights for policy 0, policy_version 23996 (0.0016) [2023-03-09 07:59:26,174][23090] Updated weights for policy 0, policy_version 24006 (0.0015) [2023-03-09 07:59:26,967][23090] Updated weights for policy 0, policy_version 24016 (0.0013) [2023-03-09 07:59:27,811][23090] Updated weights for policy 0, policy_version 24026 (0.0016) [2023-03-09 07:59:28,618][23090] Updated weights for policy 0, policy_version 24036 (0.0017) [2023-03-09 07:59:29,058][22664] Fps is (10 sec: 196608.4, 60 sec: 198793.7, 300 sec: 199329.6). Total num frames: 393871360. Throughput: 0: 49783.7. Samples: 98435056. Policy #0 lag: (min: 1.0, avg: 17.2, max: 33.0) [2023-03-09 07:59:29,059][22664] Avg episode reward: [(0, '53.816')] [2023-03-09 07:59:29,432][23090] Updated weights for policy 0, policy_version 24046 (0.0013) [2023-03-09 07:59:30,235][23090] Updated weights for policy 0, policy_version 24056 (0.0013) [2023-03-09 07:59:31,094][23090] Updated weights for policy 0, policy_version 24066 (0.0013) [2023-03-09 07:59:31,883][23090] Updated weights for policy 0, policy_version 24076 (0.0015) [2023-03-09 07:59:32,704][23090] Updated weights for policy 0, policy_version 24086 (0.0021) [2023-03-09 07:59:33,542][23090] Updated weights for policy 0, policy_version 24096 (0.0013) [2023-03-09 07:59:34,058][22664] Fps is (10 sec: 198253.1, 60 sec: 199066.5, 300 sec: 199329.6). Total num frames: 394870784. Throughput: 0: 49874.1. Samples: 98736064. Policy #0 lag: (min: 1.0, avg: 17.2, max: 33.0) [2023-03-09 07:59:34,060][22664] Avg episode reward: [(0, '49.759')] [2023-03-09 07:59:34,435][23090] Updated weights for policy 0, policy_version 24106 (0.0013) [2023-03-09 07:59:35,160][23090] Updated weights for policy 0, policy_version 24116 (0.0017) [2023-03-09 07:59:35,289][22940] Signal inference workers to stop experience collection... (8200 times) [2023-03-09 07:59:35,289][22940] Signal inference workers to resume experience collection... (8200 times) [2023-03-09 07:59:35,358][23090] InferenceWorker_p0-w0: stopping experience collection (8200 times) [2023-03-09 07:59:35,358][23090] InferenceWorker_p0-w0: resuming experience collection (8200 times) [2023-03-09 07:59:36,045][23090] Updated weights for policy 0, policy_version 24126 (0.0013) [2023-03-09 07:59:36,924][23090] Updated weights for policy 0, policy_version 24136 (0.0016) [2023-03-09 07:59:37,718][23090] Updated weights for policy 0, policy_version 24146 (0.0022) [2023-03-09 07:59:38,538][23090] Updated weights for policy 0, policy_version 24156 (0.0016) [2023-03-09 07:59:39,059][22664] Fps is (10 sec: 198245.4, 60 sec: 199066.4, 300 sec: 199329.4). Total num frames: 395853824. Throughput: 0: 49829.4. Samples: 99032992. Policy #0 lag: (min: 1.0, avg: 17.2, max: 33.0) [2023-03-09 07:59:39,060][22664] Avg episode reward: [(0, '52.024')] [2023-03-09 07:59:39,385][23090] Updated weights for policy 0, policy_version 24166 (0.0019) [2023-03-09 07:59:40,149][23090] Updated weights for policy 0, policy_version 24176 (0.0015) [2023-03-09 07:59:40,978][23090] Updated weights for policy 0, policy_version 24186 (0.0014) [2023-03-09 07:59:41,793][23090] Updated weights for policy 0, policy_version 24196 (0.0013) [2023-03-09 07:59:42,544][23090] Updated weights for policy 0, policy_version 24206 (0.0012) [2023-03-09 07:59:43,357][23090] Updated weights for policy 0, policy_version 24216 (0.0016) [2023-03-09 07:59:44,059][22664] Fps is (10 sec: 201521.6, 60 sec: 199612.2, 300 sec: 199440.7). Total num frames: 396886016. Throughput: 0: 49784.2. Samples: 99182496. Policy #0 lag: (min: 1.0, avg: 17.3, max: 33.0) [2023-03-09 07:59:44,060][22664] Avg episode reward: [(0, '51.743')] [2023-03-09 07:59:44,227][23090] Updated weights for policy 0, policy_version 24226 (0.0015) [2023-03-09 07:59:45,024][23090] Updated weights for policy 0, policy_version 24236 (0.0016) [2023-03-09 07:59:45,784][23090] Updated weights for policy 0, policy_version 24246 (0.0018) [2023-03-09 07:59:46,622][23090] Updated weights for policy 0, policy_version 24256 (0.0012) [2023-03-09 07:59:47,484][23090] Updated weights for policy 0, policy_version 24266 (0.0014) [2023-03-09 07:59:48,177][23090] Updated weights for policy 0, policy_version 24276 (0.0020) [2023-03-09 07:59:49,058][22664] Fps is (10 sec: 204801.2, 60 sec: 199885.9, 300 sec: 199440.5). Total num frames: 397901824. Throughput: 0: 49920.5. Samples: 99487616. Policy #0 lag: (min: 1.0, avg: 17.3, max: 33.0) [2023-03-09 07:59:49,059][22664] Avg episode reward: [(0, '48.997')] [2023-03-09 07:59:49,078][23090] Updated weights for policy 0, policy_version 24286 (0.0025) [2023-03-09 07:59:49,887][23090] Updated weights for policy 0, policy_version 24296 (0.0019) [2023-03-09 07:59:50,676][23090] Updated weights for policy 0, policy_version 24306 (0.0014) [2023-03-09 07:59:51,507][23090] Updated weights for policy 0, policy_version 24316 (0.0018) [2023-03-09 07:59:52,119][22940] Signal inference workers to stop experience collection... (8250 times) [2023-03-09 07:59:52,120][22940] Signal inference workers to resume experience collection... (8250 times) [2023-03-09 07:59:52,182][23090] InferenceWorker_p0-w0: stopping experience collection (8250 times) [2023-03-09 07:59:52,182][23090] InferenceWorker_p0-w0: resuming experience collection (8250 times) [2023-03-09 07:59:52,348][23090] Updated weights for policy 0, policy_version 24326 (0.0013) [2023-03-09 07:59:53,086][23090] Updated weights for policy 0, policy_version 24336 (0.0013) [2023-03-09 07:59:53,959][23090] Updated weights for policy 0, policy_version 24346 (0.0016) [2023-03-09 07:59:54,059][22664] Fps is (10 sec: 201522.9, 60 sec: 199886.0, 300 sec: 199440.5). Total num frames: 398901248. Throughput: 0: 49919.3. Samples: 99788592. Policy #0 lag: (min: 1.0, avg: 17.3, max: 33.0) [2023-03-09 07:59:54,059][22664] Avg episode reward: [(0, '53.262')] [2023-03-09 07:59:54,800][23090] Updated weights for policy 0, policy_version 24356 (0.0013) [2023-03-09 07:59:55,529][23090] Updated weights for policy 0, policy_version 24366 (0.0019) [2023-03-09 07:59:56,359][23090] Updated weights for policy 0, policy_version 24376 (0.0013) [2023-03-09 07:59:57,249][23090] Updated weights for policy 0, policy_version 24386 (0.0013) [2023-03-09 07:59:58,062][23090] Updated weights for policy 0, policy_version 24396 (0.0013) [2023-03-09 07:59:58,815][23090] Updated weights for policy 0, policy_version 24406 (0.0018) [2023-03-09 07:59:59,059][22664] Fps is (10 sec: 199869.5, 60 sec: 199883.6, 300 sec: 199495.8). Total num frames: 399900672. Throughput: 0: 50008.8. Samples: 99940112. Policy #0 lag: (min: 1.0, avg: 17.3, max: 33.0) [2023-03-09 07:59:59,062][22664] Avg episode reward: [(0, '49.834')] [2023-03-09 07:59:59,700][23090] Updated weights for policy 0, policy_version 24416 (0.0013) [2023-03-09 08:00:00,548][23090] Updated weights for policy 0, policy_version 24426 (0.0015) [2023-03-09 08:00:01,271][23090] Updated weights for policy 0, policy_version 24436 (0.0018) [2023-03-09 08:00:02,154][23090] Updated weights for policy 0, policy_version 24446 (0.0013) [2023-03-09 08:00:03,006][23090] Updated weights for policy 0, policy_version 24456 (0.0021) [2023-03-09 08:00:03,764][23090] Updated weights for policy 0, policy_version 24466 (0.0021) [2023-03-09 08:00:04,059][22664] Fps is (10 sec: 199881.9, 60 sec: 199884.5, 300 sec: 199551.7). Total num frames: 400900096. Throughput: 0: 49918.3. Samples: 100237024. Policy #0 lag: (min: 1.0, avg: 16.4, max: 32.0) [2023-03-09 08:00:04,061][22664] Avg episode reward: [(0, '50.903')] [2023-03-09 08:00:04,616][23090] Updated weights for policy 0, policy_version 24476 (0.0015) [2023-03-09 08:00:05,441][23090] Updated weights for policy 0, policy_version 24486 (0.0015) [2023-03-09 08:00:06,210][23090] Updated weights for policy 0, policy_version 24496 (0.0023) [2023-03-09 08:00:07,083][23090] Updated weights for policy 0, policy_version 24506 (0.0020) [2023-03-09 08:00:07,864][22940] Signal inference workers to stop experience collection... (8300 times) [2023-03-09 08:00:07,865][22940] Signal inference workers to resume experience collection... (8300 times) [2023-03-09 08:00:07,926][23090] InferenceWorker_p0-w0: stopping experience collection (8300 times) [2023-03-09 08:00:07,926][23090] InferenceWorker_p0-w0: resuming experience collection (8300 times) [2023-03-09 08:00:07,929][23090] Updated weights for policy 0, policy_version 24516 (0.0016) [2023-03-09 08:00:08,663][23090] Updated weights for policy 0, policy_version 24526 (0.0018) [2023-03-09 08:00:09,059][22664] Fps is (10 sec: 201533.3, 60 sec: 199885.5, 300 sec: 199607.0). Total num frames: 401915904. Throughput: 0: 50055.2. Samples: 100540096. Policy #0 lag: (min: 1.0, avg: 16.4, max: 32.0) [2023-03-09 08:00:09,060][22664] Avg episode reward: [(0, '53.133')] [2023-03-09 08:00:09,661][23090] Updated weights for policy 0, policy_version 24537 (0.0013) [2023-03-09 08:00:10,516][23090] Updated weights for policy 0, policy_version 24547 (0.0019) [2023-03-09 08:00:11,238][23090] Updated weights for policy 0, policy_version 24557 (0.0013) [2023-03-09 08:00:12,163][23090] Updated weights for policy 0, policy_version 24568 (0.0012) [2023-03-09 08:00:13,052][23090] Updated weights for policy 0, policy_version 24578 (0.0013) [2023-03-09 08:00:13,848][23090] Updated weights for policy 0, policy_version 24588 (0.0019) [2023-03-09 08:00:14,059][22664] Fps is (10 sec: 199873.9, 60 sec: 199610.3, 300 sec: 199606.6). Total num frames: 402898944. Throughput: 0: 50051.0. Samples: 100687392. Policy #0 lag: (min: 1.0, avg: 16.4, max: 32.0) [2023-03-09 08:00:14,062][22664] Avg episode reward: [(0, '49.860')] [2023-03-09 08:00:14,661][23090] Updated weights for policy 0, policy_version 24598 (0.0018) [2023-03-09 08:00:15,516][23090] Updated weights for policy 0, policy_version 24608 (0.0013) [2023-03-09 08:00:16,383][23090] Updated weights for policy 0, policy_version 24618 (0.0016) [2023-03-09 08:00:17,132][23090] Updated weights for policy 0, policy_version 24628 (0.0013) [2023-03-09 08:00:17,980][23090] Updated weights for policy 0, policy_version 24638 (0.0016) [2023-03-09 08:00:18,898][23090] Updated weights for policy 0, policy_version 24648 (0.0021) [2023-03-09 08:00:19,059][22664] Fps is (10 sec: 194968.3, 60 sec: 199337.7, 300 sec: 199495.9). Total num frames: 403865600. Throughput: 0: 49961.6. Samples: 100984352. Policy #0 lag: (min: 1.0, avg: 16.2, max: 33.0) [2023-03-09 08:00:19,061][22664] Avg episode reward: [(0, '53.348')] [2023-03-09 08:00:19,596][23090] Updated weights for policy 0, policy_version 24658 (0.0013) [2023-03-09 08:00:20,486][23090] Updated weights for policy 0, policy_version 24668 (0.0019) [2023-03-09 08:00:21,294][23090] Updated weights for policy 0, policy_version 24678 (0.0016) [2023-03-09 08:00:22,072][23090] Updated weights for policy 0, policy_version 24688 (0.0016) [2023-03-09 08:00:22,935][23090] Updated weights for policy 0, policy_version 24698 (0.0013) [2023-03-09 08:00:23,816][23090] Updated weights for policy 0, policy_version 24708 (0.0022) [2023-03-09 08:00:24,059][22664] Fps is (10 sec: 196622.4, 60 sec: 199612.7, 300 sec: 199496.0). Total num frames: 404865024. Throughput: 0: 49961.6. Samples: 101281264. Policy #0 lag: (min: 1.0, avg: 16.2, max: 33.0) [2023-03-09 08:00:24,059][22664] Avg episode reward: [(0, '53.141')] [2023-03-09 08:00:24,562][23090] Updated weights for policy 0, policy_version 24718 (0.0021) [2023-03-09 08:00:25,411][23090] Updated weights for policy 0, policy_version 24728 (0.0016) [2023-03-09 08:00:26,329][23090] Updated weights for policy 0, policy_version 24738 (0.0015) [2023-03-09 08:00:27,043][22940] Signal inference workers to stop experience collection... (8350 times) [2023-03-09 08:00:27,044][22940] Signal inference workers to resume experience collection... (8350 times) [2023-03-09 08:00:27,105][23090] InferenceWorker_p0-w0: stopping experience collection (8350 times) [2023-03-09 08:00:27,105][23090] InferenceWorker_p0-w0: resuming experience collection (8350 times) [2023-03-09 08:00:27,108][23090] Updated weights for policy 0, policy_version 24748 (0.0013) [2023-03-09 08:00:27,875][23090] Updated weights for policy 0, policy_version 24758 (0.0013) [2023-03-09 08:00:28,763][23090] Updated weights for policy 0, policy_version 24768 (0.0019) [2023-03-09 08:00:29,059][22664] Fps is (10 sec: 198244.5, 60 sec: 199610.3, 300 sec: 199440.3). Total num frames: 405848064. Throughput: 0: 49915.4. Samples: 101428704. Policy #0 lag: (min: 1.0, avg: 16.2, max: 33.0) [2023-03-09 08:00:29,061][22664] Avg episode reward: [(0, '51.223')] [2023-03-09 08:00:29,617][23090] Updated weights for policy 0, policy_version 24778 (0.0016) [2023-03-09 08:00:30,379][23090] Updated weights for policy 0, policy_version 24788 (0.0018) [2023-03-09 08:00:31,244][23090] Updated weights for policy 0, policy_version 24798 (0.0018) [2023-03-09 08:00:32,116][23090] Updated weights for policy 0, policy_version 24808 (0.0018) [2023-03-09 08:00:32,893][23090] Updated weights for policy 0, policy_version 24818 (0.0020) [2023-03-09 08:00:33,762][23090] Updated weights for policy 0, policy_version 24828 (0.0015) [2023-03-09 08:00:34,059][22664] Fps is (10 sec: 198236.7, 60 sec: 199609.9, 300 sec: 199495.7). Total num frames: 406847488. Throughput: 0: 49732.4. Samples: 101725600. Policy #0 lag: (min: 1.0, avg: 16.3, max: 33.0) [2023-03-09 08:00:34,061][22664] Avg episode reward: [(0, '51.742')] [2023-03-09 08:00:34,556][23090] Updated weights for policy 0, policy_version 24838 (0.0024) [2023-03-09 08:00:35,332][23090] Updated weights for policy 0, policy_version 24848 (0.0024) [2023-03-09 08:00:36,175][23090] Updated weights for policy 0, policy_version 24858 (0.0015) [2023-03-09 08:00:37,012][23090] Updated weights for policy 0, policy_version 24868 (0.0021) [2023-03-09 08:00:37,778][23090] Updated weights for policy 0, policy_version 24878 (0.0019) [2023-03-09 08:00:38,594][23090] Updated weights for policy 0, policy_version 24888 (0.0016) [2023-03-09 08:00:39,059][22664] Fps is (10 sec: 198251.5, 60 sec: 199611.4, 300 sec: 199440.5). Total num frames: 407830528. Throughput: 0: 49688.5. Samples: 102024576. Policy #0 lag: (min: 1.0, avg: 16.3, max: 33.0) [2023-03-09 08:00:39,060][22664] Avg episode reward: [(0, '53.226')] [2023-03-09 08:00:39,502][23090] Updated weights for policy 0, policy_version 24898 (0.0013) [2023-03-09 08:00:40,302][23090] Updated weights for policy 0, policy_version 24908 (0.0017) [2023-03-09 08:00:41,083][23090] Updated weights for policy 0, policy_version 24918 (0.0013) [2023-03-09 08:00:41,964][23090] Updated weights for policy 0, policy_version 24928 (0.0022) [2023-03-09 08:00:42,843][23090] Updated weights for policy 0, policy_version 24938 (0.0013) [2023-03-09 08:00:43,664][23090] Updated weights for policy 0, policy_version 24949 (0.0025) [2023-03-09 08:00:44,059][22664] Fps is (10 sec: 198256.2, 60 sec: 199065.7, 300 sec: 199440.5). Total num frames: 408829952. Throughput: 0: 49598.3. Samples: 102172000. Policy #0 lag: (min: 1.0, avg: 16.3, max: 33.0) [2023-03-09 08:00:44,060][22664] Avg episode reward: [(0, '54.064')] [2023-03-09 08:00:44,523][23090] Updated weights for policy 0, policy_version 24959 (0.0016) [2023-03-09 08:00:45,453][23090] Updated weights for policy 0, policy_version 24969 (0.0013) [2023-03-09 08:00:46,206][23090] Updated weights for policy 0, policy_version 24979 (0.0020) [2023-03-09 08:00:46,414][22940] Signal inference workers to stop experience collection... (8400 times) [2023-03-09 08:00:46,415][22940] Signal inference workers to resume experience collection... (8400 times) [2023-03-09 08:00:46,482][23090] InferenceWorker_p0-w0: stopping experience collection (8400 times) [2023-03-09 08:00:46,482][23090] InferenceWorker_p0-w0: resuming experience collection (8400 times) [2023-03-09 08:00:47,057][23090] Updated weights for policy 0, policy_version 24989 (0.0016) [2023-03-09 08:00:47,854][23090] Updated weights for policy 0, policy_version 24999 (0.0013) [2023-03-09 08:00:48,640][23090] Updated weights for policy 0, policy_version 25009 (0.0015) [2023-03-09 08:00:49,059][22664] Fps is (10 sec: 199881.8, 60 sec: 198791.5, 300 sec: 199440.4). Total num frames: 409829376. Throughput: 0: 49597.1. Samples: 102468896. Policy #0 lag: (min: 1.0, avg: 17.1, max: 33.0) [2023-03-09 08:00:49,061][22664] Avg episode reward: [(0, '49.635')] [2023-03-09 08:00:49,520][23090] Updated weights for policy 0, policy_version 25019 (0.0017) [2023-03-09 08:00:50,332][23090] Updated weights for policy 0, policy_version 25029 (0.0014) [2023-03-09 08:00:51,134][23090] Updated weights for policy 0, policy_version 25039 (0.0019) [2023-03-09 08:00:51,974][23090] Updated weights for policy 0, policy_version 25049 (0.0013) [2023-03-09 08:00:52,864][23090] Updated weights for policy 0, policy_version 25059 (0.0013) [2023-03-09 08:00:53,568][23090] Updated weights for policy 0, policy_version 25069 (0.0018) [2023-03-09 08:00:54,059][22664] Fps is (10 sec: 199882.7, 60 sec: 198792.4, 300 sec: 199440.4). Total num frames: 410828800. Throughput: 0: 49506.2. Samples: 102767872. Policy #0 lag: (min: 1.0, avg: 17.1, max: 33.0) [2023-03-09 08:00:54,060][22664] Avg episode reward: [(0, '52.199')] [2023-03-09 08:00:54,471][23090] Updated weights for policy 0, policy_version 25080 (0.0015) [2023-03-09 08:00:55,371][23090] Updated weights for policy 0, policy_version 25090 (0.0020) [2023-03-09 08:00:56,159][23090] Updated weights for policy 0, policy_version 25100 (0.0015) [2023-03-09 08:00:56,962][23090] Updated weights for policy 0, policy_version 25110 (0.0013) [2023-03-09 08:00:57,807][23090] Updated weights for policy 0, policy_version 25120 (0.0016) [2023-03-09 08:00:58,664][23090] Updated weights for policy 0, policy_version 25130 (0.0013) [2023-03-09 08:00:59,058][22664] Fps is (10 sec: 198251.9, 60 sec: 198521.9, 300 sec: 199440.5). Total num frames: 411811840. Throughput: 0: 49555.7. Samples: 102917360. Policy #0 lag: (min: 1.0, avg: 17.1, max: 33.0) [2023-03-09 08:00:59,059][22664] Avg episode reward: [(0, '53.918')] [2023-03-09 08:00:59,395][23090] Updated weights for policy 0, policy_version 25140 (0.0021) [2023-03-09 08:01:00,277][23090] Updated weights for policy 0, policy_version 25150 (0.0018) [2023-03-09 08:01:01,124][23090] Updated weights for policy 0, policy_version 25160 (0.0013) [2023-03-09 08:01:01,226][22940] Signal inference workers to stop experience collection... (8450 times) [2023-03-09 08:01:01,226][22940] Signal inference workers to resume experience collection... (8450 times) [2023-03-09 08:01:01,288][23090] InferenceWorker_p0-w0: stopping experience collection (8450 times) [2023-03-09 08:01:01,291][23090] InferenceWorker_p0-w0: resuming experience collection (8450 times) [2023-03-09 08:01:01,901][23090] Updated weights for policy 0, policy_version 25170 (0.0019) [2023-03-09 08:01:02,741][23090] Updated weights for policy 0, policy_version 25180 (0.0014) [2023-03-09 08:01:03,520][23090] Updated weights for policy 0, policy_version 25190 (0.0015) [2023-03-09 08:01:04,058][22664] Fps is (10 sec: 198249.9, 60 sec: 198520.3, 300 sec: 199385.3). Total num frames: 412811264. Throughput: 0: 49645.5. Samples: 103218384. Policy #0 lag: (min: 1.0, avg: 17.1, max: 33.0) [2023-03-09 08:01:04,059][22664] Avg episode reward: [(0, '52.103')] [2023-03-09 08:01:04,323][23090] Updated weights for policy 0, policy_version 25200 (0.0013) [2023-03-09 08:01:05,207][23090] Updated weights for policy 0, policy_version 25210 (0.0014) [2023-03-09 08:01:06,051][23090] Updated weights for policy 0, policy_version 25220 (0.0023) [2023-03-09 08:01:06,885][23090] Updated weights for policy 0, policy_version 25230 (0.0017) [2023-03-09 08:01:07,772][23090] Updated weights for policy 0, policy_version 25241 (0.0025) [2023-03-09 08:01:08,666][23090] Updated weights for policy 0, policy_version 25251 (0.0013) [2023-03-09 08:01:09,058][22664] Fps is (10 sec: 198246.7, 60 sec: 197974.1, 300 sec: 199329.7). Total num frames: 413794304. Throughput: 0: 49645.6. Samples: 103515312. Policy #0 lag: (min: 2.0, avg: 16.9, max: 33.0) [2023-03-09 08:01:09,060][22664] Avg episode reward: [(0, '54.150')] [2023-03-09 08:01:09,367][23090] Updated weights for policy 0, policy_version 25261 (0.0016) [2023-03-09 08:01:10,192][23090] Updated weights for policy 0, policy_version 25271 (0.0013) [2023-03-09 08:01:11,082][23090] Updated weights for policy 0, policy_version 25281 (0.0019) [2023-03-09 08:01:11,895][23090] Updated weights for policy 0, policy_version 25291 (0.0016) [2023-03-09 08:01:12,804][23090] Updated weights for policy 0, policy_version 25302 (0.0016) [2023-03-09 08:01:13,618][23090] Updated weights for policy 0, policy_version 25312 (0.0013) [2023-03-09 08:01:14,058][22664] Fps is (10 sec: 198245.7, 60 sec: 198249.0, 300 sec: 199329.6). Total num frames: 414793728. Throughput: 0: 49646.3. Samples: 103662768. Policy #0 lag: (min: 2.0, avg: 16.9, max: 33.0) [2023-03-09 08:01:14,059][22664] Avg episode reward: [(0, '49.893')] [2023-03-09 08:01:14,442][22940] Signal inference workers to stop experience collection... (8500 times) [2023-03-09 08:01:14,443][22940] Signal inference workers to resume experience collection... (8500 times) [2023-03-09 08:01:14,506][23090] InferenceWorker_p0-w0: stopping experience collection (8500 times) [2023-03-09 08:01:14,508][23090] InferenceWorker_p0-w0: resuming experience collection (8500 times) [2023-03-09 08:01:14,511][23090] Updated weights for policy 0, policy_version 25322 (0.0013) [2023-03-09 08:01:15,232][23090] Updated weights for policy 0, policy_version 25332 (0.0013) [2023-03-09 08:01:16,078][23090] Updated weights for policy 0, policy_version 25342 (0.0013) [2023-03-09 08:01:16,958][23090] Updated weights for policy 0, policy_version 25352 (0.0017) [2023-03-09 08:01:17,760][23090] Updated weights for policy 0, policy_version 25362 (0.0016) [2023-03-09 08:01:18,643][23090] Updated weights for policy 0, policy_version 25372 (0.0025) [2023-03-09 08:01:19,059][22664] Fps is (10 sec: 198241.8, 60 sec: 198519.7, 300 sec: 199273.9). Total num frames: 415776768. Throughput: 0: 49646.6. Samples: 103959680. Policy #0 lag: (min: 2.0, avg: 16.9, max: 33.0) [2023-03-09 08:01:19,060][22664] Avg episode reward: [(0, '50.959')] [2023-03-09 08:01:19,098][22940] Saving /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000025378_415793152.pth... [2023-03-09 08:01:19,167][22940] Removing /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000022460_367984640.pth [2023-03-09 08:01:19,393][23090] Updated weights for policy 0, policy_version 25382 (0.0019) [2023-03-09 08:01:20,180][23090] Updated weights for policy 0, policy_version 25392 (0.0013) [2023-03-09 08:01:21,045][23090] Updated weights for policy 0, policy_version 25402 (0.0013) [2023-03-09 08:01:21,894][23090] Updated weights for policy 0, policy_version 25412 (0.0020) [2023-03-09 08:01:22,653][23090] Updated weights for policy 0, policy_version 25422 (0.0017) [2023-03-09 08:01:23,474][23090] Updated weights for policy 0, policy_version 25432 (0.0021) [2023-03-09 08:01:24,059][22664] Fps is (10 sec: 198243.5, 60 sec: 198519.1, 300 sec: 199329.3). Total num frames: 416776192. Throughput: 0: 49645.9. Samples: 104258640. Policy #0 lag: (min: 1.0, avg: 16.4, max: 33.0) [2023-03-09 08:01:24,060][22664] Avg episode reward: [(0, '51.267')] [2023-03-09 08:01:24,437][23090] Updated weights for policy 0, policy_version 25442 (0.0024) [2023-03-09 08:01:25,176][23090] Updated weights for policy 0, policy_version 25452 (0.0015) [2023-03-09 08:01:25,990][23090] Updated weights for policy 0, policy_version 25462 (0.0018) [2023-03-09 08:01:26,824][23090] Updated weights for policy 0, policy_version 25472 (0.0016) [2023-03-09 08:01:27,106][22940] Signal inference workers to stop experience collection... (8550 times) [2023-03-09 08:01:27,109][22940] Signal inference workers to resume experience collection... (8550 times) [2023-03-09 08:01:27,177][23090] InferenceWorker_p0-w0: stopping experience collection (8550 times) [2023-03-09 08:01:27,177][23090] InferenceWorker_p0-w0: resuming experience collection (8550 times) [2023-03-09 08:01:27,705][23090] Updated weights for policy 0, policy_version 25482 (0.0018) [2023-03-09 08:01:28,430][23090] Updated weights for policy 0, policy_version 25492 (0.0016) [2023-03-09 08:01:29,059][22664] Fps is (10 sec: 198243.5, 60 sec: 198519.5, 300 sec: 199218.1). Total num frames: 417759232. Throughput: 0: 49691.0. Samples: 104408112. Policy #0 lag: (min: 1.0, avg: 16.4, max: 33.0) [2023-03-09 08:01:29,061][22664] Avg episode reward: [(0, '52.235')] [2023-03-09 08:01:29,293][23090] Updated weights for policy 0, policy_version 25502 (0.0013) [2023-03-09 08:01:30,179][23090] Updated weights for policy 0, policy_version 25512 (0.0024) [2023-03-09 08:01:30,945][23090] Updated weights for policy 0, policy_version 25522 (0.0022) [2023-03-09 08:01:31,830][23090] Updated weights for policy 0, policy_version 25532 (0.0013) [2023-03-09 08:01:32,578][23090] Updated weights for policy 0, policy_version 25542 (0.0017) [2023-03-09 08:01:33,413][23090] Updated weights for policy 0, policy_version 25552 (0.0018) [2023-03-09 08:01:34,059][22664] Fps is (10 sec: 199883.4, 60 sec: 198793.6, 300 sec: 199273.7). Total num frames: 418775040. Throughput: 0: 49737.7. Samples: 104707088. Policy #0 lag: (min: 1.0, avg: 16.4, max: 33.0) [2023-03-09 08:01:34,060][22664] Avg episode reward: [(0, '50.424')] [2023-03-09 08:01:34,293][23090] Updated weights for policy 0, policy_version 25562 (0.0019) [2023-03-09 08:01:35,110][23090] Updated weights for policy 0, policy_version 25572 (0.0016) [2023-03-09 08:01:35,879][23090] Updated weights for policy 0, policy_version 25582 (0.0017) [2023-03-09 08:01:36,652][23090] Updated weights for policy 0, policy_version 25592 (0.0016) [2023-03-09 08:01:37,552][23090] Updated weights for policy 0, policy_version 25602 (0.0013) [2023-03-09 08:01:38,387][23090] Updated weights for policy 0, policy_version 25613 (0.0016) [2023-03-09 08:01:39,059][22664] Fps is (10 sec: 199891.5, 60 sec: 198792.9, 300 sec: 199218.4). Total num frames: 419758080. Throughput: 0: 49737.7. Samples: 105006064. Policy #0 lag: (min: 1.0, avg: 16.4, max: 33.0) [2023-03-09 08:01:39,060][22664] Avg episode reward: [(0, '51.375')] [2023-03-09 08:01:39,197][23090] Updated weights for policy 0, policy_version 25623 (0.0016) [2023-03-09 08:01:40,099][23090] Updated weights for policy 0, policy_version 25633 (0.0013) [2023-03-09 08:01:40,269][22940] Signal inference workers to stop experience collection... (8600 times) [2023-03-09 08:01:40,270][22940] Signal inference workers to resume experience collection... (8600 times) [2023-03-09 08:01:40,337][23090] InferenceWorker_p0-w0: stopping experience collection (8600 times) [2023-03-09 08:01:40,338][23090] InferenceWorker_p0-w0: resuming experience collection (8600 times) [2023-03-09 08:01:40,917][23090] Updated weights for policy 0, policy_version 25643 (0.0022) [2023-03-09 08:01:41,710][23090] Updated weights for policy 0, policy_version 25653 (0.0018) [2023-03-09 08:01:42,493][23090] Updated weights for policy 0, policy_version 25663 (0.0020) [2023-03-09 08:01:43,383][23090] Updated weights for policy 0, policy_version 25673 (0.0022) [2023-03-09 08:01:44,058][22664] Fps is (10 sec: 199889.7, 60 sec: 199065.8, 300 sec: 199329.4). Total num frames: 420773888. Throughput: 0: 49738.0. Samples: 105155568. Policy #0 lag: (min: 1.0, avg: 17.4, max: 34.0) [2023-03-09 08:01:44,059][22664] Avg episode reward: [(0, '50.165')] [2023-03-09 08:01:44,117][23090] Updated weights for policy 0, policy_version 25683 (0.0013) [2023-03-09 08:01:45,066][23090] Updated weights for policy 0, policy_version 25693 (0.0013) [2023-03-09 08:01:45,882][23090] Updated weights for policy 0, policy_version 25703 (0.0013) [2023-03-09 08:01:46,699][23090] Updated weights for policy 0, policy_version 25714 (0.0015) [2023-03-09 08:01:47,619][23090] Updated weights for policy 0, policy_version 25724 (0.0013) [2023-03-09 08:01:48,372][23090] Updated weights for policy 0, policy_version 25734 (0.0020) [2023-03-09 08:01:49,059][22664] Fps is (10 sec: 199880.6, 60 sec: 198792.7, 300 sec: 199218.3). Total num frames: 421756928. Throughput: 0: 49691.1. Samples: 105454496. Policy #0 lag: (min: 1.0, avg: 17.4, max: 34.0) [2023-03-09 08:01:49,061][22664] Avg episode reward: [(0, '51.690')] [2023-03-09 08:01:49,283][23090] Updated weights for policy 0, policy_version 25745 (0.0016) [2023-03-09 08:01:50,128][23090] Updated weights for policy 0, policy_version 25755 (0.0013) [2023-03-09 08:01:50,926][23090] Updated weights for policy 0, policy_version 25765 (0.0016) [2023-03-09 08:01:51,778][23090] Updated weights for policy 0, policy_version 25775 (0.0019) [2023-03-09 08:01:52,568][23090] Updated weights for policy 0, policy_version 25785 (0.0013) [2023-03-09 08:01:52,908][22940] Signal inference workers to stop experience collection... (8650 times) [2023-03-09 08:01:52,932][22940] Signal inference workers to resume experience collection... (8650 times) [2023-03-09 08:01:52,984][23090] InferenceWorker_p0-w0: stopping experience collection (8650 times) [2023-03-09 08:01:52,987][23090] InferenceWorker_p0-w0: resuming experience collection (8650 times) [2023-03-09 08:01:53,472][23090] Updated weights for policy 0, policy_version 25795 (0.0013) [2023-03-09 08:01:54,058][22664] Fps is (10 sec: 196608.1, 60 sec: 198520.1, 300 sec: 199163.0). Total num frames: 422739968. Throughput: 0: 49691.4. Samples: 105751424. Policy #0 lag: (min: 1.0, avg: 17.4, max: 34.0) [2023-03-09 08:01:54,059][22664] Avg episode reward: [(0, '52.551')] [2023-03-09 08:01:54,192][23090] Updated weights for policy 0, policy_version 25805 (0.0013) [2023-03-09 08:01:55,017][23090] Updated weights for policy 0, policy_version 25815 (0.0016) [2023-03-09 08:01:55,914][23090] Updated weights for policy 0, policy_version 25825 (0.0013) [2023-03-09 08:01:56,759][23090] Updated weights for policy 0, policy_version 25835 (0.0013) [2023-03-09 08:01:57,561][23090] Updated weights for policy 0, policy_version 25845 (0.0013) [2023-03-09 08:01:58,344][23090] Updated weights for policy 0, policy_version 25855 (0.0018) [2023-03-09 08:01:59,059][22664] Fps is (10 sec: 198238.4, 60 sec: 198790.4, 300 sec: 199162.6). Total num frames: 423739392. Throughput: 0: 49690.3. Samples: 105898864. Policy #0 lag: (min: 1.0, avg: 16.8, max: 33.0) [2023-03-09 08:01:59,061][22664] Avg episode reward: [(0, '50.914')] [2023-03-09 08:01:59,210][23090] Updated weights for policy 0, policy_version 25865 (0.0016) [2023-03-09 08:01:59,948][23090] Updated weights for policy 0, policy_version 25875 (0.0013) [2023-03-09 08:02:00,857][23090] Updated weights for policy 0, policy_version 25885 (0.0016) [2023-03-09 08:02:01,677][23090] Updated weights for policy 0, policy_version 25895 (0.0017) [2023-03-09 08:02:02,434][23090] Updated weights for policy 0, policy_version 25905 (0.0013) [2023-03-09 08:02:03,302][23090] Updated weights for policy 0, policy_version 25915 (0.0023) [2023-03-09 08:02:04,059][22664] Fps is (10 sec: 199883.8, 60 sec: 198792.4, 300 sec: 199218.3). Total num frames: 424738816. Throughput: 0: 49781.9. Samples: 106199856. Policy #0 lag: (min: 1.0, avg: 16.8, max: 33.0) [2023-03-09 08:02:04,060][22664] Avg episode reward: [(0, '52.145')] [2023-03-09 08:02:04,078][23090] Updated weights for policy 0, policy_version 25925 (0.0016) [2023-03-09 08:02:04,930][23090] Updated weights for policy 0, policy_version 25935 (0.0013) [2023-03-09 08:02:05,764][23090] Updated weights for policy 0, policy_version 25945 (0.0019) [2023-03-09 08:02:06,612][23090] Updated weights for policy 0, policy_version 25955 (0.0013) [2023-03-09 08:02:06,629][22940] Signal inference workers to stop experience collection... (8700 times) [2023-03-09 08:02:06,630][22940] Signal inference workers to resume experience collection... (8700 times) [2023-03-09 08:02:06,690][23090] InferenceWorker_p0-w0: stopping experience collection (8700 times) [2023-03-09 08:02:06,690][23090] InferenceWorker_p0-w0: resuming experience collection (8700 times) [2023-03-09 08:02:07,333][23090] Updated weights for policy 0, policy_version 25965 (0.0013) [2023-03-09 08:02:08,178][23090] Updated weights for policy 0, policy_version 25975 (0.0016) [2023-03-09 08:02:09,059][22664] Fps is (10 sec: 198258.8, 60 sec: 198792.5, 300 sec: 199162.8). Total num frames: 425721856. Throughput: 0: 49782.2. Samples: 106498832. Policy #0 lag: (min: 1.0, avg: 16.8, max: 33.0) [2023-03-09 08:02:09,059][22664] Avg episode reward: [(0, '51.850')] [2023-03-09 08:02:09,072][23090] Updated weights for policy 0, policy_version 25985 (0.0015) [2023-03-09 08:02:09,922][23090] Updated weights for policy 0, policy_version 25995 (0.0013) [2023-03-09 08:02:10,726][23090] Updated weights for policy 0, policy_version 26005 (0.0018) [2023-03-09 08:02:11,525][23090] Updated weights for policy 0, policy_version 26015 (0.0015) [2023-03-09 08:02:12,459][23090] Updated weights for policy 0, policy_version 26026 (0.0016) [2023-03-09 08:02:13,178][23090] Updated weights for policy 0, policy_version 26036 (0.0016) [2023-03-09 08:02:14,059][22664] Fps is (10 sec: 199880.3, 60 sec: 199064.8, 300 sec: 199162.6). Total num frames: 426737664. Throughput: 0: 49736.7. Samples: 106646256. Policy #0 lag: (min: 1.0, avg: 17.8, max: 34.0) [2023-03-09 08:02:14,061][22664] Avg episode reward: [(0, '51.673')] [2023-03-09 08:02:14,062][23090] Updated weights for policy 0, policy_version 26046 (0.0013) [2023-03-09 08:02:14,973][23090] Updated weights for policy 0, policy_version 26056 (0.0017) [2023-03-09 08:02:15,702][23090] Updated weights for policy 0, policy_version 26066 (0.0013) [2023-03-09 08:02:16,650][23090] Updated weights for policy 0, policy_version 26076 (0.0021) [2023-03-09 08:02:17,420][23090] Updated weights for policy 0, policy_version 26086 (0.0016) [2023-03-09 08:02:18,183][23090] Updated weights for policy 0, policy_version 26096 (0.0015) [2023-03-09 08:02:19,054][23090] Updated weights for policy 0, policy_version 26106 (0.0017) [2023-03-09 08:02:19,059][22664] Fps is (10 sec: 199878.4, 60 sec: 199065.2, 300 sec: 199162.5). Total num frames: 427720704. Throughput: 0: 49735.7. Samples: 106945200. Policy #0 lag: (min: 1.0, avg: 17.8, max: 34.0) [2023-03-09 08:02:19,061][22664] Avg episode reward: [(0, '53.846')] [2023-03-09 08:02:19,951][23090] Updated weights for policy 0, policy_version 26117 (0.0013) [2023-03-09 08:02:20,330][22940] Signal inference workers to stop experience collection... (8750 times) [2023-03-09 08:02:20,330][22940] Signal inference workers to resume experience collection... (8750 times) [2023-03-09 08:02:20,398][23090] InferenceWorker_p0-w0: stopping experience collection (8750 times) [2023-03-09 08:02:20,398][23090] InferenceWorker_p0-w0: resuming experience collection (8750 times) [2023-03-09 08:02:20,808][23090] Updated weights for policy 0, policy_version 26127 (0.0013) [2023-03-09 08:02:21,584][23090] Updated weights for policy 0, policy_version 26137 (0.0019) [2023-03-09 08:02:22,431][23090] Updated weights for policy 0, policy_version 26147 (0.0018) [2023-03-09 08:02:23,177][23090] Updated weights for policy 0, policy_version 26157 (0.0017) [2023-03-09 08:02:23,995][23090] Updated weights for policy 0, policy_version 26167 (0.0013) [2023-03-09 08:02:24,058][22664] Fps is (10 sec: 198251.7, 60 sec: 199066.2, 300 sec: 199162.9). Total num frames: 428720128. Throughput: 0: 49735.9. Samples: 107244176. Policy #0 lag: (min: 1.0, avg: 17.8, max: 34.0) [2023-03-09 08:02:24,059][22664] Avg episode reward: [(0, '53.296')] [2023-03-09 08:02:24,907][23090] Updated weights for policy 0, policy_version 26177 (0.0017) [2023-03-09 08:02:25,715][23090] Updated weights for policy 0, policy_version 26187 (0.0017) [2023-03-09 08:02:26,515][23090] Updated weights for policy 0, policy_version 26197 (0.0015) [2023-03-09 08:02:27,326][23090] Updated weights for policy 0, policy_version 26207 (0.0017) [2023-03-09 08:02:28,246][23090] Updated weights for policy 0, policy_version 26217 (0.0013) [2023-03-09 08:02:28,970][23090] Updated weights for policy 0, policy_version 26227 (0.0013) [2023-03-09 08:02:29,059][22664] Fps is (10 sec: 199879.7, 60 sec: 199337.9, 300 sec: 199162.4). Total num frames: 429719552. Throughput: 0: 49734.8. Samples: 107393664. Policy #0 lag: (min: 1.0, avg: 17.8, max: 34.0) [2023-03-09 08:02:29,061][22664] Avg episode reward: [(0, '52.699')] [2023-03-09 08:02:29,869][23090] Updated weights for policy 0, policy_version 26237 (0.0013) [2023-03-09 08:02:30,663][23090] Updated weights for policy 0, policy_version 26247 (0.0015) [2023-03-09 08:02:31,432][23090] Updated weights for policy 0, policy_version 26257 (0.0017) [2023-03-09 08:02:32,303][23090] Updated weights for policy 0, policy_version 26267 (0.0016) [2023-03-09 08:02:32,967][22940] Signal inference workers to stop experience collection... (8800 times) [2023-03-09 08:02:32,968][22940] Signal inference workers to resume experience collection... (8800 times) [2023-03-09 08:02:33,031][23090] InferenceWorker_p0-w0: stopping experience collection (8800 times) [2023-03-09 08:02:33,031][23090] InferenceWorker_p0-w0: resuming experience collection (8800 times) [2023-03-09 08:02:33,084][23090] Updated weights for policy 0, policy_version 26277 (0.0017) [2023-03-09 08:02:33,982][23090] Updated weights for policy 0, policy_version 26288 (0.0017) [2023-03-09 08:02:34,058][22664] Fps is (10 sec: 199885.1, 60 sec: 199066.4, 300 sec: 199162.8). Total num frames: 430718976. Throughput: 0: 49737.2. Samples: 107692656. Policy #0 lag: (min: 1.0, avg: 16.5, max: 33.0) [2023-03-09 08:02:34,059][22664] Avg episode reward: [(0, '51.726')] [2023-03-09 08:02:34,853][23090] Updated weights for policy 0, policy_version 26298 (0.0019) [2023-03-09 08:02:35,656][23090] Updated weights for policy 0, policy_version 26308 (0.0013) [2023-03-09 08:02:36,427][23090] Updated weights for policy 0, policy_version 26318 (0.0013) [2023-03-09 08:02:37,264][23090] Updated weights for policy 0, policy_version 26328 (0.0020) [2023-03-09 08:02:38,109][23090] Updated weights for policy 0, policy_version 26338 (0.0013) [2023-03-09 08:02:38,926][23090] Updated weights for policy 0, policy_version 26348 (0.0022) [2023-03-09 08:02:39,059][22664] Fps is (10 sec: 198250.9, 60 sec: 199064.5, 300 sec: 199107.2). Total num frames: 431702016. Throughput: 0: 49735.4. Samples: 107989536. Policy #0 lag: (min: 1.0, avg: 16.5, max: 33.0) [2023-03-09 08:02:39,061][22664] Avg episode reward: [(0, '52.530')] [2023-03-09 08:02:39,739][23090] Updated weights for policy 0, policy_version 26358 (0.0017) [2023-03-09 08:02:40,581][23090] Updated weights for policy 0, policy_version 26368 (0.0024) [2023-03-09 08:02:41,500][23090] Updated weights for policy 0, policy_version 26378 (0.0013) [2023-03-09 08:02:42,205][23090] Updated weights for policy 0, policy_version 26388 (0.0017) [2023-03-09 08:02:43,091][23090] Updated weights for policy 0, policy_version 26398 (0.0016) [2023-03-09 08:02:43,903][23090] Updated weights for policy 0, policy_version 26408 (0.0013) [2023-03-09 08:02:44,059][22664] Fps is (10 sec: 196603.5, 60 sec: 198518.7, 300 sec: 199107.4). Total num frames: 432685056. Throughput: 0: 49736.3. Samples: 108136976. Policy #0 lag: (min: 1.0, avg: 16.5, max: 33.0) [2023-03-09 08:02:44,061][22664] Avg episode reward: [(0, '54.297')] [2023-03-09 08:02:44,069][22940] Saving new best policy, reward=54.297! [2023-03-09 08:02:44,702][23090] Updated weights for policy 0, policy_version 26418 (0.0013) [2023-03-09 08:02:45,573][22940] Signal inference workers to stop experience collection... (8850 times) [2023-03-09 08:02:45,589][22940] Signal inference workers to resume experience collection... (8850 times) [2023-03-09 08:02:45,621][23090] Updated weights for policy 0, policy_version 26428 (0.0013) [2023-03-09 08:02:45,662][23090] InferenceWorker_p0-w0: stopping experience collection (8850 times) [2023-03-09 08:02:45,663][23090] InferenceWorker_p0-w0: resuming experience collection (8850 times) [2023-03-09 08:02:46,357][23090] Updated weights for policy 0, policy_version 26438 (0.0019) [2023-03-09 08:02:47,155][23090] Updated weights for policy 0, policy_version 26448 (0.0013) [2023-03-09 08:02:48,018][23090] Updated weights for policy 0, policy_version 26458 (0.0013) [2023-03-09 08:02:48,824][23090] Updated weights for policy 0, policy_version 26468 (0.0013) [2023-03-09 08:02:49,058][22664] Fps is (10 sec: 198253.9, 60 sec: 198793.4, 300 sec: 199107.4). Total num frames: 433684480. Throughput: 0: 49734.8. Samples: 108437920. Policy #0 lag: (min: 0.0, avg: 16.3, max: 33.0) [2023-03-09 08:02:49,059][22664] Avg episode reward: [(0, '53.997')] [2023-03-09 08:02:49,592][23090] Updated weights for policy 0, policy_version 26478 (0.0016) [2023-03-09 08:02:50,450][23090] Updated weights for policy 0, policy_version 26488 (0.0014) [2023-03-09 08:02:51,300][23090] Updated weights for policy 0, policy_version 26498 (0.0013) [2023-03-09 08:02:52,126][23090] Updated weights for policy 0, policy_version 26508 (0.0019) [2023-03-09 08:02:52,897][23090] Updated weights for policy 0, policy_version 26518 (0.0017) [2023-03-09 08:02:53,739][23090] Updated weights for policy 0, policy_version 26528 (0.0013) [2023-03-09 08:02:54,058][22664] Fps is (10 sec: 199889.3, 60 sec: 199065.6, 300 sec: 199107.3). Total num frames: 434683904. Throughput: 0: 49735.2. Samples: 108736912. Policy #0 lag: (min: 0.0, avg: 16.3, max: 33.0) [2023-03-09 08:02:54,059][22664] Avg episode reward: [(0, '51.632')] [2023-03-09 08:02:54,646][23090] Updated weights for policy 0, policy_version 26538 (0.0013) [2023-03-09 08:02:55,363][23090] Updated weights for policy 0, policy_version 26548 (0.0013) [2023-03-09 08:02:56,247][23090] Updated weights for policy 0, policy_version 26558 (0.0013) [2023-03-09 08:02:57,128][23090] Updated weights for policy 0, policy_version 26568 (0.0022) [2023-03-09 08:02:57,622][22940] Signal inference workers to stop experience collection... (8900 times) [2023-03-09 08:02:57,623][22940] Signal inference workers to resume experience collection... (8900 times) [2023-03-09 08:02:57,690][23090] InferenceWorker_p0-w0: stopping experience collection (8900 times) [2023-03-09 08:02:57,690][23090] InferenceWorker_p0-w0: resuming experience collection (8900 times) [2023-03-09 08:02:57,856][23090] Updated weights for policy 0, policy_version 26578 (0.0020) [2023-03-09 08:02:58,771][23090] Updated weights for policy 0, policy_version 26588 (0.0013) [2023-03-09 08:02:59,059][22664] Fps is (10 sec: 199877.8, 60 sec: 199066.6, 300 sec: 199107.4). Total num frames: 435683328. Throughput: 0: 49735.3. Samples: 108884352. Policy #0 lag: (min: 0.0, avg: 16.3, max: 33.0) [2023-03-09 08:02:59,061][22664] Avg episode reward: [(0, '52.022')] [2023-03-09 08:02:59,539][23090] Updated weights for policy 0, policy_version 26598 (0.0013) [2023-03-09 08:03:00,319][23090] Updated weights for policy 0, policy_version 26608 (0.0024) [2023-03-09 08:03:01,286][23090] Updated weights for policy 0, policy_version 26619 (0.0015) [2023-03-09 08:03:02,102][23090] Updated weights for policy 0, policy_version 26629 (0.0018) [2023-03-09 08:03:02,870][23090] Updated weights for policy 0, policy_version 26639 (0.0015) [2023-03-09 08:03:03,716][23090] Updated weights for policy 0, policy_version 26649 (0.0013) [2023-03-09 08:03:04,058][22664] Fps is (10 sec: 198246.3, 60 sec: 198792.7, 300 sec: 199051.8). Total num frames: 436666368. Throughput: 0: 49782.1. Samples: 109185376. Policy #0 lag: (min: 0.0, avg: 16.3, max: 33.0) [2023-03-09 08:03:04,059][22664] Avg episode reward: [(0, '53.635')] [2023-03-09 08:03:04,555][23090] Updated weights for policy 0, policy_version 26659 (0.0018) [2023-03-09 08:03:05,283][23090] Updated weights for policy 0, policy_version 26669 (0.0013) [2023-03-09 08:03:06,086][23090] Updated weights for policy 0, policy_version 26679 (0.0013) [2023-03-09 08:03:07,006][23090] Updated weights for policy 0, policy_version 26689 (0.0015) [2023-03-09 08:03:07,834][23090] Updated weights for policy 0, policy_version 26699 (0.0013) [2023-03-09 08:03:08,665][23090] Updated weights for policy 0, policy_version 26709 (0.0015) [2023-03-09 08:03:09,059][22664] Fps is (10 sec: 198252.2, 60 sec: 199065.5, 300 sec: 199051.8). Total num frames: 437665792. Throughput: 0: 49736.1. Samples: 109482304. Policy #0 lag: (min: 1.0, avg: 17.1, max: 33.0) [2023-03-09 08:03:09,059][22664] Avg episode reward: [(0, '54.048')] [2023-03-09 08:03:09,468][23090] Updated weights for policy 0, policy_version 26719 (0.0019) [2023-03-09 08:03:10,329][23090] Updated weights for policy 0, policy_version 26729 (0.0013) [2023-03-09 08:03:10,426][22940] Signal inference workers to stop experience collection... (8950 times) [2023-03-09 08:03:10,427][22940] Signal inference workers to resume experience collection... (8950 times) [2023-03-09 08:03:10,497][23090] InferenceWorker_p0-w0: stopping experience collection (8950 times) [2023-03-09 08:03:10,497][23090] InferenceWorker_p0-w0: resuming experience collection (8950 times) [2023-03-09 08:03:11,118][23090] Updated weights for policy 0, policy_version 26739 (0.0013) [2023-03-09 08:03:12,042][23090] Updated weights for policy 0, policy_version 26749 (0.0017) [2023-03-09 08:03:12,812][23090] Updated weights for policy 0, policy_version 26759 (0.0015) [2023-03-09 08:03:13,595][23090] Updated weights for policy 0, policy_version 26769 (0.0018) [2023-03-09 08:03:14,058][22664] Fps is (10 sec: 199885.2, 60 sec: 198793.5, 300 sec: 198996.2). Total num frames: 438665216. Throughput: 0: 49736.5. Samples: 109631776. Policy #0 lag: (min: 1.0, avg: 17.1, max: 33.0) [2023-03-09 08:03:14,059][22664] Avg episode reward: [(0, '52.835')] [2023-03-09 08:03:14,478][23090] Updated weights for policy 0, policy_version 26779 (0.0013) [2023-03-09 08:03:15,292][23090] Updated weights for policy 0, policy_version 26789 (0.0023) [2023-03-09 08:03:16,138][23090] Updated weights for policy 0, policy_version 26799 (0.0015) [2023-03-09 08:03:16,947][23090] Updated weights for policy 0, policy_version 26809 (0.0013) [2023-03-09 08:03:17,902][23090] Updated weights for policy 0, policy_version 26820 (0.0013) [2023-03-09 08:03:18,813][23090] Updated weights for policy 0, policy_version 26831 (0.0013) [2023-03-09 08:03:19,059][22664] Fps is (10 sec: 198239.9, 60 sec: 198792.4, 300 sec: 198940.5). Total num frames: 439648256. Throughput: 0: 49644.0. Samples: 109926656. Policy #0 lag: (min: 1.0, avg: 17.1, max: 33.0) [2023-03-09 08:03:19,061][22664] Avg episode reward: [(0, '52.669')] [2023-03-09 08:03:19,071][22940] Saving /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000026835_439664640.pth... [2023-03-09 08:03:19,140][22940] Removing /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000023921_391921664.pth [2023-03-09 08:03:19,580][23090] Updated weights for policy 0, policy_version 26841 (0.0017) [2023-03-09 08:03:20,429][23090] Updated weights for policy 0, policy_version 26851 (0.0016) [2023-03-09 08:03:21,194][23090] Updated weights for policy 0, policy_version 26861 (0.0013) [2023-03-09 08:03:22,017][23090] Updated weights for policy 0, policy_version 26871 (0.0013) [2023-03-09 08:03:22,569][22940] Signal inference workers to stop experience collection... (9000 times) [2023-03-09 08:03:22,571][22940] Signal inference workers to resume experience collection... (9000 times) [2023-03-09 08:03:22,640][23090] InferenceWorker_p0-w0: stopping experience collection (9000 times) [2023-03-09 08:03:22,640][23090] InferenceWorker_p0-w0: resuming experience collection (9000 times) [2023-03-09 08:03:22,939][23090] Updated weights for policy 0, policy_version 26881 (0.0013) [2023-03-09 08:03:23,801][23090] Updated weights for policy 0, policy_version 26891 (0.0013) [2023-03-09 08:03:24,059][22664] Fps is (10 sec: 198240.1, 60 sec: 198791.5, 300 sec: 198996.2). Total num frames: 440647680. Throughput: 0: 49644.9. Samples: 110223552. Policy #0 lag: (min: 1.0, avg: 16.7, max: 33.0) [2023-03-09 08:03:24,060][22664] Avg episode reward: [(0, '55.551')] [2023-03-09 08:03:24,094][22940] Saving new best policy, reward=55.551! [2023-03-09 08:03:24,568][23090] Updated weights for policy 0, policy_version 26901 (0.0019) [2023-03-09 08:03:25,413][23090] Updated weights for policy 0, policy_version 26911 (0.0020) [2023-03-09 08:03:26,268][23090] Updated weights for policy 0, policy_version 26921 (0.0021) [2023-03-09 08:03:27,055][23090] Updated weights for policy 0, policy_version 26931 (0.0016) [2023-03-09 08:03:27,966][23090] Updated weights for policy 0, policy_version 26941 (0.0016) [2023-03-09 08:03:28,731][23090] Updated weights for policy 0, policy_version 26951 (0.0013) [2023-03-09 08:03:29,059][22664] Fps is (10 sec: 196613.6, 60 sec: 198248.1, 300 sec: 198940.7). Total num frames: 441614336. Throughput: 0: 49644.9. Samples: 110370992. Policy #0 lag: (min: 1.0, avg: 16.7, max: 33.0) [2023-03-09 08:03:29,060][22664] Avg episode reward: [(0, '54.088')] [2023-03-09 08:03:29,531][23090] Updated weights for policy 0, policy_version 26961 (0.0014) [2023-03-09 08:03:30,399][23090] Updated weights for policy 0, policy_version 26971 (0.0013) [2023-03-09 08:03:31,204][23090] Updated weights for policy 0, policy_version 26981 (0.0013) [2023-03-09 08:03:32,035][23090] Updated weights for policy 0, policy_version 26991 (0.0018) [2023-03-09 08:03:32,937][23090] Updated weights for policy 0, policy_version 27002 (0.0013) [2023-03-09 08:03:33,776][23090] Updated weights for policy 0, policy_version 27012 (0.0014) [2023-03-09 08:03:34,059][22664] Fps is (10 sec: 196608.1, 60 sec: 198245.4, 300 sec: 198996.2). Total num frames: 442613760. Throughput: 0: 49599.3. Samples: 110669904. Policy #0 lag: (min: 1.0, avg: 16.7, max: 33.0) [2023-03-09 08:03:34,061][22664] Avg episode reward: [(0, '52.445')] [2023-03-09 08:03:34,613][23090] Updated weights for policy 0, policy_version 27022 (0.0015) [2023-03-09 08:03:35,381][23090] Updated weights for policy 0, policy_version 27032 (0.0013) [2023-03-09 08:03:36,231][23090] Updated weights for policy 0, policy_version 27042 (0.0017) [2023-03-09 08:03:37,039][23090] Updated weights for policy 0, policy_version 27052 (0.0015) [2023-03-09 08:03:37,853][23090] Updated weights for policy 0, policy_version 27062 (0.0013) [2023-03-09 08:03:38,715][23090] Updated weights for policy 0, policy_version 27072 (0.0013) [2023-03-09 08:03:39,059][22664] Fps is (10 sec: 199885.2, 60 sec: 198520.4, 300 sec: 198996.3). Total num frames: 443613184. Throughput: 0: 49553.7. Samples: 110966832. Policy #0 lag: (min: 1.0, avg: 16.7, max: 33.0) [2023-03-09 08:03:39,060][22664] Avg episode reward: [(0, '51.890')] [2023-03-09 08:03:39,541][23090] Updated weights for policy 0, policy_version 27082 (0.0013) [2023-03-09 08:03:39,617][22940] Signal inference workers to stop experience collection... (9050 times) [2023-03-09 08:03:39,631][22940] Signal inference workers to resume experience collection... (9050 times) [2023-03-09 08:03:39,661][23090] InferenceWorker_p0-w0: stopping experience collection (9050 times) [2023-03-09 08:03:39,701][23090] InferenceWorker_p0-w0: resuming experience collection (9050 times) [2023-03-09 08:03:40,315][23090] Updated weights for policy 0, policy_version 27092 (0.0013) [2023-03-09 08:03:41,207][23090] Updated weights for policy 0, policy_version 27102 (0.0024) [2023-03-09 08:03:42,024][23090] Updated weights for policy 0, policy_version 27112 (0.0019) [2023-03-09 08:03:42,830][23090] Updated weights for policy 0, policy_version 27122 (0.0016) [2023-03-09 08:03:43,739][23090] Updated weights for policy 0, policy_version 27132 (0.0016) [2023-03-09 08:03:44,059][22664] Fps is (10 sec: 198245.7, 60 sec: 198519.1, 300 sec: 198940.6). Total num frames: 444596224. Throughput: 0: 49598.3. Samples: 111116272. Policy #0 lag: (min: 1.0, avg: 16.4, max: 32.0) [2023-03-09 08:03:44,060][22664] Avg episode reward: [(0, '50.142')] [2023-03-09 08:03:44,511][23090] Updated weights for policy 0, policy_version 27142 (0.0016) [2023-03-09 08:03:45,285][23090] Updated weights for policy 0, policy_version 27152 (0.0020) [2023-03-09 08:03:46,243][23090] Updated weights for policy 0, policy_version 27163 (0.0013) [2023-03-09 08:03:47,058][23090] Updated weights for policy 0, policy_version 27173 (0.0015) [2023-03-09 08:03:47,862][23090] Updated weights for policy 0, policy_version 27183 (0.0013) [2023-03-09 08:03:48,653][23090] Updated weights for policy 0, policy_version 27193 (0.0020) [2023-03-09 08:03:49,059][22664] Fps is (10 sec: 196597.4, 60 sec: 198244.4, 300 sec: 198885.0). Total num frames: 445579264. Throughput: 0: 49506.5. Samples: 111413200. Policy #0 lag: (min: 1.0, avg: 16.4, max: 32.0) [2023-03-09 08:03:49,061][22664] Avg episode reward: [(0, '50.118')] [2023-03-09 08:03:49,536][23090] Updated weights for policy 0, policy_version 27203 (0.0020) [2023-03-09 08:03:50,313][23090] Updated weights for policy 0, policy_version 27213 (0.0016) [2023-03-09 08:03:51,068][23090] Updated weights for policy 0, policy_version 27223 (0.0016) [2023-03-09 08:03:51,987][23090] Updated weights for policy 0, policy_version 27233 (0.0018) [2023-03-09 08:03:52,800][23090] Updated weights for policy 0, policy_version 27243 (0.0018) [2023-03-09 08:03:53,593][23090] Updated weights for policy 0, policy_version 27253 (0.0016) [2023-03-09 08:03:54,059][22664] Fps is (10 sec: 199883.5, 60 sec: 198518.1, 300 sec: 198940.6). Total num frames: 446595072. Throughput: 0: 49551.7. Samples: 111712144. Policy #0 lag: (min: 1.0, avg: 16.4, max: 32.0) [2023-03-09 08:03:54,061][22664] Avg episode reward: [(0, '53.016')] [2023-03-09 08:03:54,478][23090] Updated weights for policy 0, policy_version 27263 (0.0023) [2023-03-09 08:03:55,274][23090] Updated weights for policy 0, policy_version 27273 (0.0017) [2023-03-09 08:03:56,090][23090] Updated weights for policy 0, policy_version 27283 (0.0013) [2023-03-09 08:03:56,863][22940] Signal inference workers to stop experience collection... (9100 times) [2023-03-09 08:03:56,864][22940] Signal inference workers to resume experience collection... (9100 times) [2023-03-09 08:03:56,932][23090] InferenceWorker_p0-w0: stopping experience collection (9100 times) [2023-03-09 08:03:56,932][23090] InferenceWorker_p0-w0: resuming experience collection (9100 times) [2023-03-09 08:03:56,936][23090] Updated weights for policy 0, policy_version 27293 (0.0013) [2023-03-09 08:03:57,705][23090] Updated weights for policy 0, policy_version 27303 (0.0014) [2023-03-09 08:03:58,502][23090] Updated weights for policy 0, policy_version 27313 (0.0020) [2023-03-09 08:03:59,058][22664] Fps is (10 sec: 201536.2, 60 sec: 198520.7, 300 sec: 198940.8). Total num frames: 447594496. Throughput: 0: 49597.1. Samples: 111863648. Policy #0 lag: (min: 1.0, avg: 16.4, max: 32.0) [2023-03-09 08:03:59,059][22664] Avg episode reward: [(0, '50.152')] [2023-03-09 08:03:59,375][23090] Updated weights for policy 0, policy_version 27323 (0.0015) [2023-03-09 08:04:00,168][23090] Updated weights for policy 0, policy_version 27333 (0.0013) [2023-03-09 08:04:00,947][23090] Updated weights for policy 0, policy_version 27343 (0.0015) [2023-03-09 08:04:01,828][23090] Updated weights for policy 0, policy_version 27353 (0.0013) [2023-03-09 08:04:02,673][23090] Updated weights for policy 0, policy_version 27363 (0.0013) [2023-03-09 08:04:03,463][23090] Updated weights for policy 0, policy_version 27373 (0.0020) [2023-03-09 08:04:04,059][22664] Fps is (10 sec: 199887.0, 60 sec: 198791.6, 300 sec: 198885.2). Total num frames: 448593920. Throughput: 0: 49687.3. Samples: 112162576. Policy #0 lag: (min: 0.0, avg: 17.1, max: 32.0) [2023-03-09 08:04:04,061][22664] Avg episode reward: [(0, '53.595')] [2023-03-09 08:04:04,337][23090] Updated weights for policy 0, policy_version 27384 (0.0013) [2023-03-09 08:04:05,220][23090] Updated weights for policy 0, policy_version 27394 (0.0017) [2023-03-09 08:04:06,045][23090] Updated weights for policy 0, policy_version 27404 (0.0017) [2023-03-09 08:04:06,778][23090] Updated weights for policy 0, policy_version 27414 (0.0013) [2023-03-09 08:04:07,650][23090] Updated weights for policy 0, policy_version 27424 (0.0015) [2023-03-09 08:04:08,536][23090] Updated weights for policy 0, policy_version 27434 (0.0013) [2023-03-09 08:04:09,059][22664] Fps is (10 sec: 199883.5, 60 sec: 198792.6, 300 sec: 198885.3). Total num frames: 449593344. Throughput: 0: 49779.1. Samples: 112463600. Policy #0 lag: (min: 0.0, avg: 17.1, max: 32.0) [2023-03-09 08:04:09,060][22664] Avg episode reward: [(0, '50.315')] [2023-03-09 08:04:09,241][23090] Updated weights for policy 0, policy_version 27444 (0.0013) [2023-03-09 08:04:10,013][22940] Signal inference workers to stop experience collection... (9150 times) [2023-03-09 08:04:10,026][22940] Signal inference workers to resume experience collection... (9150 times) [2023-03-09 08:04:10,056][23090] InferenceWorker_p0-w0: stopping experience collection (9150 times) [2023-03-09 08:04:10,094][23090] InferenceWorker_p0-w0: resuming experience collection (9150 times) [2023-03-09 08:04:10,099][23090] Updated weights for policy 0, policy_version 27454 (0.0013) [2023-03-09 08:04:10,942][23090] Updated weights for policy 0, policy_version 27464 (0.0013) [2023-03-09 08:04:11,709][23090] Updated weights for policy 0, policy_version 27474 (0.0013) [2023-03-09 08:04:12,666][23090] Updated weights for policy 0, policy_version 27484 (0.0014) [2023-03-09 08:04:13,422][23090] Updated weights for policy 0, policy_version 27494 (0.0020) [2023-03-09 08:04:14,058][22664] Fps is (10 sec: 199890.1, 60 sec: 198792.4, 300 sec: 198940.6). Total num frames: 450592768. Throughput: 0: 49779.0. Samples: 112611040. Policy #0 lag: (min: 0.0, avg: 17.1, max: 32.0) [2023-03-09 08:04:14,059][22664] Avg episode reward: [(0, '51.605')] [2023-03-09 08:04:14,209][23090] Updated weights for policy 0, policy_version 27504 (0.0034) [2023-03-09 08:04:15,053][23090] Updated weights for policy 0, policy_version 27514 (0.0013) [2023-03-09 08:04:15,986][23090] Updated weights for policy 0, policy_version 27525 (0.0022) [2023-03-09 08:04:16,757][23090] Updated weights for policy 0, policy_version 27535 (0.0013) [2023-03-09 08:04:17,588][23090] Updated weights for policy 0, policy_version 27545 (0.0013) [2023-03-09 08:04:18,531][23090] Updated weights for policy 0, policy_version 27556 (0.0023) [2023-03-09 08:04:19,059][22664] Fps is (10 sec: 198236.0, 60 sec: 198791.9, 300 sec: 198940.5). Total num frames: 451575808. Throughput: 0: 49779.6. Samples: 112910000. Policy #0 lag: (min: 1.0, avg: 17.1, max: 33.0) [2023-03-09 08:04:19,061][22664] Avg episode reward: [(0, '51.481')] [2023-03-09 08:04:19,303][23090] Updated weights for policy 0, policy_version 27566 (0.0014) [2023-03-09 08:04:20,121][23090] Updated weights for policy 0, policy_version 27576 (0.0017) [2023-03-09 08:04:21,071][23090] Updated weights for policy 0, policy_version 27587 (0.0017) [2023-03-09 08:04:21,846][23090] Updated weights for policy 0, policy_version 27597 (0.0021) [2023-03-09 08:04:22,618][23090] Updated weights for policy 0, policy_version 27607 (0.0021) [2023-03-09 08:04:23,538][23090] Updated weights for policy 0, policy_version 27617 (0.0020) [2023-03-09 08:04:23,672][22940] Signal inference workers to stop experience collection... (9200 times) [2023-03-09 08:04:23,673][22940] Signal inference workers to resume experience collection... (9200 times) [2023-03-09 08:04:23,736][23090] InferenceWorker_p0-w0: stopping experience collection (9200 times) [2023-03-09 08:04:23,736][23090] InferenceWorker_p0-w0: resuming experience collection (9200 times) [2023-03-09 08:04:24,058][22664] Fps is (10 sec: 198246.8, 60 sec: 198793.5, 300 sec: 198996.2). Total num frames: 452575232. Throughput: 0: 49824.8. Samples: 113208944. Policy #0 lag: (min: 1.0, avg: 17.1, max: 33.0) [2023-03-09 08:04:24,059][22664] Avg episode reward: [(0, '51.229')] [2023-03-09 08:04:24,380][23090] Updated weights for policy 0, policy_version 27627 (0.0013) [2023-03-09 08:04:25,185][23090] Updated weights for policy 0, policy_version 27637 (0.0016) [2023-03-09 08:04:26,014][23090] Updated weights for policy 0, policy_version 27647 (0.0013) [2023-03-09 08:04:26,824][23090] Updated weights for policy 0, policy_version 27657 (0.0018) [2023-03-09 08:04:27,669][23090] Updated weights for policy 0, policy_version 27667 (0.0017) [2023-03-09 08:04:28,536][23090] Updated weights for policy 0, policy_version 27678 (0.0013) [2023-03-09 08:04:29,059][22664] Fps is (10 sec: 199881.0, 60 sec: 199336.5, 300 sec: 198995.7). Total num frames: 453574656. Throughput: 0: 49825.3. Samples: 113358432. Policy #0 lag: (min: 1.0, avg: 17.1, max: 33.0) [2023-03-09 08:04:29,061][22664] Avg episode reward: [(0, '51.871')] [2023-03-09 08:04:29,386][23090] Updated weights for policy 0, policy_version 27688 (0.0023) [2023-03-09 08:04:30,191][23090] Updated weights for policy 0, policy_version 27698 (0.0015) [2023-03-09 08:04:31,129][23090] Updated weights for policy 0, policy_version 27708 (0.0015) [2023-03-09 08:04:31,883][23090] Updated weights for policy 0, policy_version 27718 (0.0018) [2023-03-09 08:04:32,647][23090] Updated weights for policy 0, policy_version 27728 (0.0013) [2023-03-09 08:04:33,533][23090] Updated weights for policy 0, policy_version 27738 (0.0028) [2023-03-09 08:04:34,058][22664] Fps is (10 sec: 198245.4, 60 sec: 199066.4, 300 sec: 198996.2). Total num frames: 454557696. Throughput: 0: 49825.7. Samples: 113655328. Policy #0 lag: (min: 1.0, avg: 17.1, max: 33.0) [2023-03-09 08:04:34,060][22664] Avg episode reward: [(0, '55.019')] [2023-03-09 08:04:34,357][23090] Updated weights for policy 0, policy_version 27748 (0.0022) [2023-03-09 08:04:35,224][23090] Updated weights for policy 0, policy_version 27758 (0.0016) [2023-03-09 08:04:36,061][23090] Updated weights for policy 0, policy_version 27769 (0.0013) [2023-03-09 08:04:36,951][23090] Updated weights for policy 0, policy_version 27779 (0.0013) [2023-03-09 08:04:37,758][23090] Updated weights for policy 0, policy_version 27789 (0.0016) [2023-03-09 08:04:38,523][23090] Updated weights for policy 0, policy_version 27799 (0.0016) [2023-03-09 08:04:39,059][22664] Fps is (10 sec: 196615.8, 60 sec: 198791.6, 300 sec: 198829.4). Total num frames: 455540736. Throughput: 0: 49735.1. Samples: 113950224. Policy #0 lag: (min: 1.0, avg: 16.8, max: 33.0) [2023-03-09 08:04:39,061][22664] Avg episode reward: [(0, '51.131')] [2023-03-09 08:04:39,265][22940] Signal inference workers to stop experience collection... (9250 times) [2023-03-09 08:04:39,265][22940] Signal inference workers to resume experience collection... (9250 times) [2023-03-09 08:04:39,331][23090] InferenceWorker_p0-w0: stopping experience collection (9250 times) [2023-03-09 08:04:39,331][23090] InferenceWorker_p0-w0: resuming experience collection (9250 times) [2023-03-09 08:04:39,448][23090] Updated weights for policy 0, policy_version 27809 (0.0020) [2023-03-09 08:04:40,266][23090] Updated weights for policy 0, policy_version 27819 (0.0021) [2023-03-09 08:04:41,056][23090] Updated weights for policy 0, policy_version 27829 (0.0015) [2023-03-09 08:04:41,892][23090] Updated weights for policy 0, policy_version 27840 (0.0015) [2023-03-09 08:04:42,798][23090] Updated weights for policy 0, policy_version 27850 (0.0015) [2023-03-09 08:04:43,556][23090] Updated weights for policy 0, policy_version 27860 (0.0019) [2023-03-09 08:04:44,058][22664] Fps is (10 sec: 198247.4, 60 sec: 199066.7, 300 sec: 198774.0). Total num frames: 456540160. Throughput: 0: 49735.8. Samples: 114101760. Policy #0 lag: (min: 1.0, avg: 16.8, max: 33.0) [2023-03-09 08:04:44,059][22664] Avg episode reward: [(0, '50.479')] [2023-03-09 08:04:44,409][23090] Updated weights for policy 0, policy_version 27870 (0.0016) [2023-03-09 08:04:45,225][23090] Updated weights for policy 0, policy_version 27880 (0.0013) [2023-03-09 08:04:46,016][23090] Updated weights for policy 0, policy_version 27890 (0.0023) [2023-03-09 08:04:46,895][23090] Updated weights for policy 0, policy_version 27900 (0.0019) [2023-03-09 08:04:47,691][23090] Updated weights for policy 0, policy_version 27910 (0.0016) [2023-03-09 08:04:48,469][23090] Updated weights for policy 0, policy_version 27920 (0.0017) [2023-03-09 08:04:49,058][22664] Fps is (10 sec: 201531.2, 60 sec: 199613.9, 300 sec: 198829.6). Total num frames: 457555968. Throughput: 0: 49736.2. Samples: 114400688. Policy #0 lag: (min: 1.0, avg: 16.8, max: 33.0) [2023-03-09 08:04:49,060][22664] Avg episode reward: [(0, '53.741')] [2023-03-09 08:04:49,343][23090] Updated weights for policy 0, policy_version 27930 (0.0013) [2023-03-09 08:04:50,162][23090] Updated weights for policy 0, policy_version 27940 (0.0016) [2023-03-09 08:04:51,007][23090] Updated weights for policy 0, policy_version 27950 (0.0013) [2023-03-09 08:04:51,773][23090] Updated weights for policy 0, policy_version 27960 (0.0013) [2023-03-09 08:04:52,793][23090] Updated weights for policy 0, policy_version 27971 (0.0013) [2023-03-09 08:04:53,548][23090] Updated weights for policy 0, policy_version 27981 (0.0014) [2023-03-09 08:04:54,059][22664] Fps is (10 sec: 199881.4, 60 sec: 199066.4, 300 sec: 198774.4). Total num frames: 458539008. Throughput: 0: 49644.7. Samples: 114697616. Policy #0 lag: (min: 1.0, avg: 17.0, max: 33.0) [2023-03-09 08:04:54,060][22664] Avg episode reward: [(0, '51.505')] [2023-03-09 08:04:54,247][22940] Signal inference workers to stop experience collection... (9300 times) [2023-03-09 08:04:54,261][22940] Signal inference workers to resume experience collection... (9300 times) [2023-03-09 08:04:54,281][23090] InferenceWorker_p0-w0: stopping experience collection (9300 times) [2023-03-09 08:04:54,281][23090] InferenceWorker_p0-w0: resuming experience collection (9300 times) [2023-03-09 08:04:54,325][23090] Updated weights for policy 0, policy_version 27991 (0.0013) [2023-03-09 08:04:55,169][23090] Updated weights for policy 0, policy_version 28001 (0.0021) [2023-03-09 08:04:56,061][23090] Updated weights for policy 0, policy_version 28011 (0.0016) [2023-03-09 08:04:56,898][23090] Updated weights for policy 0, policy_version 28021 (0.0016) [2023-03-09 08:04:57,708][23090] Updated weights for policy 0, policy_version 28031 (0.0017) [2023-03-09 08:04:58,481][23090] Updated weights for policy 0, policy_version 28041 (0.0020) [2023-03-09 08:04:59,059][22664] Fps is (10 sec: 198240.1, 60 sec: 199064.6, 300 sec: 198774.0). Total num frames: 459538432. Throughput: 0: 49690.0. Samples: 114847104. Policy #0 lag: (min: 1.0, avg: 17.0, max: 33.0) [2023-03-09 08:04:59,061][22664] Avg episode reward: [(0, '51.424')] [2023-03-09 08:04:59,326][23090] Updated weights for policy 0, policy_version 28051 (0.0021) [2023-03-09 08:05:00,146][23090] Updated weights for policy 0, policy_version 28061 (0.0013) [2023-03-09 08:05:00,950][23090] Updated weights for policy 0, policy_version 28071 (0.0013) [2023-03-09 08:05:01,707][23090] Updated weights for policy 0, policy_version 28081 (0.0014) [2023-03-09 08:05:02,595][23090] Updated weights for policy 0, policy_version 28091 (0.0019) [2023-03-09 08:05:03,348][23090] Updated weights for policy 0, policy_version 28101 (0.0019) [2023-03-09 08:05:04,058][22664] Fps is (10 sec: 199887.0, 60 sec: 199066.4, 300 sec: 198718.6). Total num frames: 460537856. Throughput: 0: 49779.8. Samples: 115150064. Policy #0 lag: (min: 1.0, avg: 17.0, max: 33.0) [2023-03-09 08:05:04,059][22664] Avg episode reward: [(0, '52.057')] [2023-03-09 08:05:04,192][23090] Updated weights for policy 0, policy_version 28111 (0.0013) [2023-03-09 08:05:05,008][23090] Updated weights for policy 0, policy_version 28121 (0.0019) [2023-03-09 08:05:05,895][23090] Updated weights for policy 0, policy_version 28131 (0.0013) [2023-03-09 08:05:06,652][23090] Updated weights for policy 0, policy_version 28141 (0.0016) [2023-03-09 08:05:07,461][23090] Updated weights for policy 0, policy_version 28151 (0.0015) [2023-03-09 08:05:08,315][23090] Updated weights for policy 0, policy_version 28161 (0.0019) [2023-03-09 08:05:09,059][22664] Fps is (10 sec: 198251.0, 60 sec: 198792.5, 300 sec: 198719.0). Total num frames: 461520896. Throughput: 0: 49735.0. Samples: 115447024. Policy #0 lag: (min: 1.0, avg: 17.0, max: 33.0) [2023-03-09 08:05:09,060][22664] Avg episode reward: [(0, '53.425')] [2023-03-09 08:05:09,189][23090] Updated weights for policy 0, policy_version 28171 (0.0016) [2023-03-09 08:05:09,403][22940] Signal inference workers to stop experience collection... (9350 times) [2023-03-09 08:05:09,405][22940] Signal inference workers to resume experience collection... (9350 times) [2023-03-09 08:05:09,477][23090] InferenceWorker_p0-w0: stopping experience collection (9350 times) [2023-03-09 08:05:09,477][23090] InferenceWorker_p0-w0: resuming experience collection (9350 times) [2023-03-09 08:05:10,007][23090] Updated weights for policy 0, policy_version 28181 (0.0016) [2023-03-09 08:05:10,891][23090] Updated weights for policy 0, policy_version 28192 (0.0022) [2023-03-09 08:05:11,747][23090] Updated weights for policy 0, policy_version 28202 (0.0013) [2023-03-09 08:05:12,516][23090] Updated weights for policy 0, policy_version 28212 (0.0013) [2023-03-09 08:05:13,370][23090] Updated weights for policy 0, policy_version 28222 (0.0013) [2023-03-09 08:05:14,059][22664] Fps is (10 sec: 198240.8, 60 sec: 198791.5, 300 sec: 198829.6). Total num frames: 462520320. Throughput: 0: 49734.5. Samples: 115596464. Policy #0 lag: (min: 2.0, avg: 17.0, max: 33.0) [2023-03-09 08:05:14,060][22664] Avg episode reward: [(0, '53.124')] [2023-03-09 08:05:14,210][23090] Updated weights for policy 0, policy_version 28232 (0.0016) [2023-03-09 08:05:15,024][23090] Updated weights for policy 0, policy_version 28242 (0.0022) [2023-03-09 08:05:15,866][23090] Updated weights for policy 0, policy_version 28252 (0.0017) [2023-03-09 08:05:16,647][23090] Updated weights for policy 0, policy_version 28262 (0.0013) [2023-03-09 08:05:17,419][23090] Updated weights for policy 0, policy_version 28272 (0.0014) [2023-03-09 08:05:18,293][23090] Updated weights for policy 0, policy_version 28282 (0.0014) [2023-03-09 08:05:19,059][22664] Fps is (10 sec: 198242.5, 60 sec: 198793.6, 300 sec: 198773.9). Total num frames: 463503360. Throughput: 0: 49734.2. Samples: 115893376. Policy #0 lag: (min: 2.0, avg: 17.0, max: 33.0) [2023-03-09 08:05:19,060][22664] Avg episode reward: [(0, '51.963')] [2023-03-09 08:05:19,070][22940] Saving /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000028291_463519744.pth... [2023-03-09 08:05:19,130][22940] Removing /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000025378_415793152.pth [2023-03-09 08:05:19,218][23090] Updated weights for policy 0, policy_version 28292 (0.0018) [2023-03-09 08:05:20,027][23090] Updated weights for policy 0, policy_version 28303 (0.0014) [2023-03-09 08:05:20,834][23090] Updated weights for policy 0, policy_version 28313 (0.0016) [2023-03-09 08:05:21,725][23090] Updated weights for policy 0, policy_version 28323 (0.0013) [2023-03-09 08:05:22,609][23090] Updated weights for policy 0, policy_version 28334 (0.0016) [2023-03-09 08:05:23,219][22940] Signal inference workers to stop experience collection... (9400 times) [2023-03-09 08:05:23,241][22940] Signal inference workers to resume experience collection... (9400 times) [2023-03-09 08:05:23,296][23090] InferenceWorker_p0-w0: stopping experience collection (9400 times) [2023-03-09 08:05:23,299][23090] InferenceWorker_p0-w0: resuming experience collection (9400 times) [2023-03-09 08:05:23,418][23090] Updated weights for policy 0, policy_version 28344 (0.0013) [2023-03-09 08:05:24,059][22664] Fps is (10 sec: 199890.2, 60 sec: 199065.4, 300 sec: 198885.3). Total num frames: 464519168. Throughput: 0: 49824.7. Samples: 116192320. Policy #0 lag: (min: 2.0, avg: 17.0, max: 33.0) [2023-03-09 08:05:24,059][22664] Avg episode reward: [(0, '52.928')] [2023-03-09 08:05:24,304][23090] Updated weights for policy 0, policy_version 28354 (0.0015) [2023-03-09 08:05:25,069][23090] Updated weights for policy 0, policy_version 28364 (0.0016) [2023-03-09 08:05:25,878][23090] Updated weights for policy 0, policy_version 28374 (0.0013) [2023-03-09 08:05:26,650][23090] Updated weights for policy 0, policy_version 28384 (0.0016) [2023-03-09 08:05:27,541][23090] Updated weights for policy 0, policy_version 28394 (0.0016) [2023-03-09 08:05:28,291][23090] Updated weights for policy 0, policy_version 28404 (0.0013) [2023-03-09 08:05:29,059][22664] Fps is (10 sec: 199882.9, 60 sec: 198793.9, 300 sec: 198829.7). Total num frames: 465502208. Throughput: 0: 49778.4. Samples: 116341808. Policy #0 lag: (min: 2.0, avg: 17.0, max: 33.0) [2023-03-09 08:05:29,061][22664] Avg episode reward: [(0, '49.443')] [2023-03-09 08:05:29,134][23090] Updated weights for policy 0, policy_version 28414 (0.0019) [2023-03-09 08:05:29,943][23090] Updated weights for policy 0, policy_version 28424 (0.0014) [2023-03-09 08:05:30,779][23090] Updated weights for policy 0, policy_version 28434 (0.0013) [2023-03-09 08:05:31,698][23090] Updated weights for policy 0, policy_version 28444 (0.0019) [2023-03-09 08:05:32,430][23090] Updated weights for policy 0, policy_version 28454 (0.0013) [2023-03-09 08:05:33,269][23090] Updated weights for policy 0, policy_version 28464 (0.0015) [2023-03-09 08:05:34,059][22664] Fps is (10 sec: 198246.7, 60 sec: 199065.6, 300 sec: 198885.2). Total num frames: 466501632. Throughput: 0: 49825.0. Samples: 116642816. Policy #0 lag: (min: 1.0, avg: 17.0, max: 33.0) [2023-03-09 08:05:34,060][22664] Avg episode reward: [(0, '50.747')] [2023-03-09 08:05:34,075][23090] Updated weights for policy 0, policy_version 28474 (0.0013) [2023-03-09 08:05:34,919][23090] Updated weights for policy 0, policy_version 28484 (0.0021) [2023-03-09 08:05:35,716][23090] Updated weights for policy 0, policy_version 28494 (0.0015) [2023-03-09 08:05:36,293][22940] Signal inference workers to stop experience collection... (9450 times) [2023-03-09 08:05:36,296][22940] Signal inference workers to resume experience collection... (9450 times) [2023-03-09 08:05:36,363][23090] InferenceWorker_p0-w0: stopping experience collection (9450 times) [2023-03-09 08:05:36,363][23090] InferenceWorker_p0-w0: resuming experience collection (9450 times) [2023-03-09 08:05:36,524][23090] Updated weights for policy 0, policy_version 28504 (0.0013) [2023-03-09 08:05:37,441][23090] Updated weights for policy 0, policy_version 28514 (0.0016) [2023-03-09 08:05:38,138][23090] Updated weights for policy 0, policy_version 28524 (0.0019) [2023-03-09 08:05:38,984][23090] Updated weights for policy 0, policy_version 28534 (0.0013) [2023-03-09 08:05:39,059][22664] Fps is (10 sec: 201529.5, 60 sec: 199612.8, 300 sec: 198940.6). Total num frames: 467517440. Throughput: 0: 49870.4. Samples: 116941776. Policy #0 lag: (min: 1.0, avg: 17.0, max: 33.0) [2023-03-09 08:05:39,060][22664] Avg episode reward: [(0, '52.319')] [2023-03-09 08:05:39,772][23090] Updated weights for policy 0, policy_version 28544 (0.0016) [2023-03-09 08:05:40,685][23090] Updated weights for policy 0, policy_version 28554 (0.0016) [2023-03-09 08:05:41,425][23090] Updated weights for policy 0, policy_version 28564 (0.0016) [2023-03-09 08:05:42,298][23090] Updated weights for policy 0, policy_version 28574 (0.0014) [2023-03-09 08:05:43,135][23090] Updated weights for policy 0, policy_version 28584 (0.0016) [2023-03-09 08:05:43,904][23090] Updated weights for policy 0, policy_version 28594 (0.0015) [2023-03-09 08:05:44,058][22664] Fps is (10 sec: 201523.6, 60 sec: 199611.6, 300 sec: 198940.8). Total num frames: 468516864. Throughput: 0: 49825.4. Samples: 117089232. Policy #0 lag: (min: 1.0, avg: 17.0, max: 33.0) [2023-03-09 08:05:44,059][22664] Avg episode reward: [(0, '49.730')] [2023-03-09 08:05:44,771][23090] Updated weights for policy 0, policy_version 28604 (0.0013) [2023-03-09 08:05:45,531][23090] Updated weights for policy 0, policy_version 28614 (0.0013) [2023-03-09 08:05:46,329][23090] Updated weights for policy 0, policy_version 28624 (0.0013) [2023-03-09 08:05:47,180][23090] Updated weights for policy 0, policy_version 28634 (0.0022) [2023-03-09 08:05:48,124][23090] Updated weights for policy 0, policy_version 28645 (0.0012) [2023-03-09 08:05:48,899][23090] Updated weights for policy 0, policy_version 28655 (0.0023) [2023-03-09 08:05:48,983][22940] Signal inference workers to stop experience collection... (9500 times) [2023-03-09 08:05:48,984][22940] Signal inference workers to resume experience collection... (9500 times) [2023-03-09 08:05:49,053][23090] InferenceWorker_p0-w0: stopping experience collection (9500 times) [2023-03-09 08:05:49,053][23090] InferenceWorker_p0-w0: resuming experience collection (9500 times) [2023-03-09 08:05:49,059][22664] Fps is (10 sec: 199880.2, 60 sec: 199337.7, 300 sec: 198940.6). Total num frames: 469516288. Throughput: 0: 49782.2. Samples: 117390272. Policy #0 lag: (min: 1.0, avg: 17.0, max: 33.0) [2023-03-09 08:05:49,105][22664] Avg episode reward: [(0, '50.928')] [2023-03-09 08:05:49,824][23090] Updated weights for policy 0, policy_version 28666 (0.0016) [2023-03-09 08:05:50,620][23090] Updated weights for policy 0, policy_version 28676 (0.0013) [2023-03-09 08:05:51,426][23090] Updated weights for policy 0, policy_version 28686 (0.0013) [2023-03-09 08:05:52,244][23090] Updated weights for policy 0, policy_version 28696 (0.0024) [2023-03-09 08:05:53,140][23090] Updated weights for policy 0, policy_version 28706 (0.0022) [2023-03-09 08:05:53,866][23090] Updated weights for policy 0, policy_version 28716 (0.0016) [2023-03-09 08:05:54,058][22664] Fps is (10 sec: 199885.3, 60 sec: 199612.3, 300 sec: 198996.2). Total num frames: 470515712. Throughput: 0: 49917.2. Samples: 117693296. Policy #0 lag: (min: 1.0, avg: 17.2, max: 33.0) [2023-03-09 08:05:54,059][22664] Avg episode reward: [(0, '52.710')] [2023-03-09 08:05:54,675][23090] Updated weights for policy 0, policy_version 28726 (0.0013) [2023-03-09 08:05:55,518][23090] Updated weights for policy 0, policy_version 28736 (0.0020) [2023-03-09 08:05:56,366][23090] Updated weights for policy 0, policy_version 28746 (0.0016) [2023-03-09 08:05:57,113][23090] Updated weights for policy 0, policy_version 28756 (0.0015) [2023-03-09 08:05:57,969][23090] Updated weights for policy 0, policy_version 28766 (0.0016) [2023-03-09 08:05:58,841][23090] Updated weights for policy 0, policy_version 28776 (0.0020) [2023-03-09 08:05:59,059][22664] Fps is (10 sec: 198245.2, 60 sec: 199338.5, 300 sec: 198940.4). Total num frames: 471498752. Throughput: 0: 49918.2. Samples: 117842784. Policy #0 lag: (min: 1.0, avg: 17.2, max: 33.0) [2023-03-09 08:05:59,061][22664] Avg episode reward: [(0, '52.384')] [2023-03-09 08:05:59,637][23090] Updated weights for policy 0, policy_version 28786 (0.0016) [2023-03-09 08:06:00,495][23090] Updated weights for policy 0, policy_version 28796 (0.0016) [2023-03-09 08:06:01,245][23090] Updated weights for policy 0, policy_version 28806 (0.0012) [2023-03-09 08:06:02,081][23090] Updated weights for policy 0, policy_version 28816 (0.0014) [2023-03-09 08:06:02,251][22940] Signal inference workers to stop experience collection... (9550 times) [2023-03-09 08:06:02,252][22940] Signal inference workers to resume experience collection... (9550 times) [2023-03-09 08:06:02,319][23090] InferenceWorker_p0-w0: stopping experience collection (9550 times) [2023-03-09 08:06:02,320][23090] InferenceWorker_p0-w0: resuming experience collection (9550 times) [2023-03-09 08:06:02,896][23090] Updated weights for policy 0, policy_version 28826 (0.0021) [2023-03-09 08:06:03,771][23090] Updated weights for policy 0, policy_version 28836 (0.0013) [2023-03-09 08:06:04,059][22664] Fps is (10 sec: 198238.7, 60 sec: 199337.5, 300 sec: 198995.9). Total num frames: 472498176. Throughput: 0: 49963.6. Samples: 118141744. Policy #0 lag: (min: 1.0, avg: 17.2, max: 33.0) [2023-03-09 08:06:04,061][22664] Avg episode reward: [(0, '52.678')] [2023-03-09 08:06:04,548][23090] Updated weights for policy 0, policy_version 28846 (0.0013) [2023-03-09 08:06:05,392][23090] Updated weights for policy 0, policy_version 28856 (0.0013) [2023-03-09 08:06:06,318][23090] Updated weights for policy 0, policy_version 28866 (0.0016) [2023-03-09 08:06:07,036][23090] Updated weights for policy 0, policy_version 28876 (0.0014) [2023-03-09 08:06:07,837][23090] Updated weights for policy 0, policy_version 28886 (0.0015) [2023-03-09 08:06:08,677][23090] Updated weights for policy 0, policy_version 28896 (0.0018) [2023-03-09 08:06:09,058][22664] Fps is (10 sec: 199890.8, 60 sec: 199611.8, 300 sec: 198996.2). Total num frames: 473497600. Throughput: 0: 49919.3. Samples: 118438688. Policy #0 lag: (min: 1.0, avg: 17.3, max: 32.0) [2023-03-09 08:06:09,060][22664] Avg episode reward: [(0, '50.435')] [2023-03-09 08:06:09,530][23090] Updated weights for policy 0, policy_version 28906 (0.0018) [2023-03-09 08:06:10,255][23090] Updated weights for policy 0, policy_version 28916 (0.0020) [2023-03-09 08:06:11,126][23090] Updated weights for policy 0, policy_version 28926 (0.0013) [2023-03-09 08:06:11,960][23090] Updated weights for policy 0, policy_version 28936 (0.0014) [2023-03-09 08:06:12,763][23090] Updated weights for policy 0, policy_version 28946 (0.0016) [2023-03-09 08:06:13,664][23090] Updated weights for policy 0, policy_version 28956 (0.0020) [2023-03-09 08:06:14,059][22664] Fps is (10 sec: 199887.6, 60 sec: 199612.0, 300 sec: 199051.7). Total num frames: 474497024. Throughput: 0: 49964.9. Samples: 118590224. Policy #0 lag: (min: 1.0, avg: 17.3, max: 32.0) [2023-03-09 08:06:14,060][22664] Avg episode reward: [(0, '53.115')] [2023-03-09 08:06:14,415][23090] Updated weights for policy 0, policy_version 28966 (0.0013) [2023-03-09 08:06:15,228][23090] Updated weights for policy 0, policy_version 28976 (0.0013) [2023-03-09 08:06:16,040][23090] Updated weights for policy 0, policy_version 28986 (0.0016) [2023-03-09 08:06:16,915][22940] Signal inference workers to stop experience collection... (9600 times) [2023-03-09 08:06:16,916][22940] Signal inference workers to resume experience collection... (9600 times) [2023-03-09 08:06:16,977][23090] InferenceWorker_p0-w0: stopping experience collection (9600 times) [2023-03-09 08:06:16,977][23090] InferenceWorker_p0-w0: resuming experience collection (9600 times) [2023-03-09 08:06:16,980][23090] Updated weights for policy 0, policy_version 28997 (0.0017) [2023-03-09 08:06:17,808][23090] Updated weights for policy 0, policy_version 29007 (0.0028) [2023-03-09 08:06:18,598][23090] Updated weights for policy 0, policy_version 29017 (0.0016) [2023-03-09 08:06:19,059][22664] Fps is (10 sec: 199879.4, 60 sec: 199884.7, 300 sec: 199051.6). Total num frames: 475496448. Throughput: 0: 49919.4. Samples: 118889200. Policy #0 lag: (min: 1.0, avg: 17.3, max: 32.0) [2023-03-09 08:06:19,060][22664] Avg episode reward: [(0, '50.847')] [2023-03-09 08:06:19,546][23090] Updated weights for policy 0, policy_version 29027 (0.0014) [2023-03-09 08:06:20,281][23090] Updated weights for policy 0, policy_version 29037 (0.0025) [2023-03-09 08:06:21,084][23090] Updated weights for policy 0, policy_version 29047 (0.0018) [2023-03-09 08:06:21,892][23090] Updated weights for policy 0, policy_version 29057 (0.0016) [2023-03-09 08:06:22,761][23090] Updated weights for policy 0, policy_version 29067 (0.0013) [2023-03-09 08:06:23,659][23090] Updated weights for policy 0, policy_version 29079 (0.0016) [2023-03-09 08:06:24,059][22664] Fps is (10 sec: 198250.5, 60 sec: 199338.7, 300 sec: 199052.0). Total num frames: 476479488. Throughput: 0: 49920.7. Samples: 119188208. Policy #0 lag: (min: 1.0, avg: 17.3, max: 32.0) [2023-03-09 08:06:24,059][22664] Avg episode reward: [(0, '50.485')] [2023-03-09 08:06:24,577][23090] Updated weights for policy 0, policy_version 29089 (0.0018) [2023-03-09 08:06:25,392][23090] Updated weights for policy 0, policy_version 29099 (0.0024) [2023-03-09 08:06:26,182][23090] Updated weights for policy 0, policy_version 29109 (0.0023) [2023-03-09 08:06:27,007][23090] Updated weights for policy 0, policy_version 29119 (0.0022) [2023-03-09 08:06:27,868][23090] Updated weights for policy 0, policy_version 29129 (0.0014) [2023-03-09 08:06:28,664][23090] Updated weights for policy 0, policy_version 29139 (0.0013) [2023-03-09 08:06:29,059][22664] Fps is (10 sec: 199889.6, 60 sec: 199885.8, 300 sec: 199051.8). Total num frames: 477495296. Throughput: 0: 49920.7. Samples: 119335664. Policy #0 lag: (min: 2.0, avg: 16.6, max: 33.0) [2023-03-09 08:06:29,060][22664] Avg episode reward: [(0, '49.164')] [2023-03-09 08:06:29,540][23090] Updated weights for policy 0, policy_version 29149 (0.0017) [2023-03-09 08:06:30,349][23090] Updated weights for policy 0, policy_version 29159 (0.0016) [2023-03-09 08:06:31,119][23090] Updated weights for policy 0, policy_version 29169 (0.0013) [2023-03-09 08:06:31,961][23090] Updated weights for policy 0, policy_version 29179 (0.0016) [2023-03-09 08:06:32,797][23090] Updated weights for policy 0, policy_version 29189 (0.0018) [2023-03-09 08:06:33,201][22940] Signal inference workers to stop experience collection... (9650 times) [2023-03-09 08:06:33,204][22940] Signal inference workers to resume experience collection... (9650 times) [2023-03-09 08:06:33,289][23090] InferenceWorker_p0-w0: stopping experience collection (9650 times) [2023-03-09 08:06:33,290][23090] InferenceWorker_p0-w0: resuming experience collection (9650 times) [2023-03-09 08:06:33,586][23090] Updated weights for policy 0, policy_version 29199 (0.0019) [2023-03-09 08:06:34,059][22664] Fps is (10 sec: 199884.9, 60 sec: 199611.8, 300 sec: 199051.7). Total num frames: 478478336. Throughput: 0: 49920.6. Samples: 119636688. Policy #0 lag: (min: 2.0, avg: 16.6, max: 33.0) [2023-03-09 08:06:34,059][22664] Avg episode reward: [(0, '52.974')] [2023-03-09 08:06:34,428][23090] Updated weights for policy 0, policy_version 29209 (0.0013) [2023-03-09 08:06:35,320][23090] Updated weights for policy 0, policy_version 29219 (0.0020) [2023-03-09 08:06:36,047][23090] Updated weights for policy 0, policy_version 29229 (0.0013) [2023-03-09 08:06:36,894][23090] Updated weights for policy 0, policy_version 29239 (0.0021) [2023-03-09 08:06:37,716][23090] Updated weights for policy 0, policy_version 29249 (0.0016) [2023-03-09 08:06:38,660][23090] Updated weights for policy 0, policy_version 29260 (0.0013) [2023-03-09 08:06:39,059][22664] Fps is (10 sec: 198244.0, 60 sec: 199338.2, 300 sec: 198996.0). Total num frames: 479477760. Throughput: 0: 49784.3. Samples: 119933600. Policy #0 lag: (min: 2.0, avg: 16.6, max: 33.0) [2023-03-09 08:06:39,060][22664] Avg episode reward: [(0, '51.623')] [2023-03-09 08:06:39,479][23090] Updated weights for policy 0, policy_version 29270 (0.0018) [2023-03-09 08:06:40,381][23090] Updated weights for policy 0, policy_version 29281 (0.0020) [2023-03-09 08:06:41,194][23090] Updated weights for policy 0, policy_version 29291 (0.0016) [2023-03-09 08:06:41,994][23090] Updated weights for policy 0, policy_version 29301 (0.0016) [2023-03-09 08:06:42,804][23090] Updated weights for policy 0, policy_version 29311 (0.0013) [2023-03-09 08:06:43,643][23090] Updated weights for policy 0, policy_version 29321 (0.0020) [2023-03-09 08:06:44,058][22664] Fps is (10 sec: 199884.9, 60 sec: 199338.6, 300 sec: 199051.9). Total num frames: 480477184. Throughput: 0: 49739.0. Samples: 120081024. Policy #0 lag: (min: 2.0, avg: 16.6, max: 33.0) [2023-03-09 08:06:44,060][22664] Avg episode reward: [(0, '50.733')] [2023-03-09 08:06:44,443][23090] Updated weights for policy 0, policy_version 29331 (0.0018) [2023-03-09 08:06:45,303][23090] Updated weights for policy 0, policy_version 29341 (0.0018) [2023-03-09 08:06:46,139][23090] Updated weights for policy 0, policy_version 29351 (0.0013) [2023-03-09 08:06:46,912][23090] Updated weights for policy 0, policy_version 29361 (0.0013) [2023-03-09 08:06:47,799][23090] Updated weights for policy 0, policy_version 29371 (0.0015) [2023-03-09 08:06:48,597][23090] Updated weights for policy 0, policy_version 29381 (0.0014) [2023-03-09 08:06:49,059][22664] Fps is (10 sec: 199884.5, 60 sec: 199338.9, 300 sec: 199107.1). Total num frames: 481476608. Throughput: 0: 49738.5. Samples: 120379968. Policy #0 lag: (min: 2.0, avg: 17.0, max: 34.0) [2023-03-09 08:06:49,060][22664] Avg episode reward: [(0, '50.770')] [2023-03-09 08:06:49,419][22940] Signal inference workers to stop experience collection... (9700 times) [2023-03-09 08:06:49,422][22940] Signal inference workers to resume experience collection... (9700 times) [2023-03-09 08:06:49,452][23090] Updated weights for policy 0, policy_version 29391 (0.0021) [2023-03-09 08:06:49,487][23090] InferenceWorker_p0-w0: stopping experience collection (9700 times) [2023-03-09 08:06:49,487][23090] InferenceWorker_p0-w0: resuming experience collection (9700 times) [2023-03-09 08:06:50,219][23090] Updated weights for policy 0, policy_version 29401 (0.0022) [2023-03-09 08:06:51,118][23090] Updated weights for policy 0, policy_version 29411 (0.0018) [2023-03-09 08:06:51,848][23090] Updated weights for policy 0, policy_version 29421 (0.0013) [2023-03-09 08:06:52,645][23090] Updated weights for policy 0, policy_version 29431 (0.0018) [2023-03-09 08:06:53,688][23090] Updated weights for policy 0, policy_version 29442 (0.0013) [2023-03-09 08:06:54,059][22664] Fps is (10 sec: 198241.6, 60 sec: 199064.7, 300 sec: 199052.0). Total num frames: 482459648. Throughput: 0: 49828.0. Samples: 120680960. Policy #0 lag: (min: 2.0, avg: 17.0, max: 34.0) [2023-03-09 08:06:54,060][22664] Avg episode reward: [(0, '52.104')] [2023-03-09 08:06:54,397][23090] Updated weights for policy 0, policy_version 29452 (0.0013) [2023-03-09 08:06:55,240][23090] Updated weights for policy 0, policy_version 29462 (0.0013) [2023-03-09 08:06:56,044][23090] Updated weights for policy 0, policy_version 29472 (0.0016) [2023-03-09 08:06:56,929][23090] Updated weights for policy 0, policy_version 29482 (0.0017) [2023-03-09 08:06:57,620][23090] Updated weights for policy 0, policy_version 29492 (0.0017) [2023-03-09 08:06:58,484][23090] Updated weights for policy 0, policy_version 29502 (0.0013) [2023-03-09 08:06:59,059][22664] Fps is (10 sec: 199886.9, 60 sec: 199612.5, 300 sec: 199107.2). Total num frames: 483475456. Throughput: 0: 49782.2. Samples: 120830416. Policy #0 lag: (min: 2.0, avg: 17.0, max: 34.0) [2023-03-09 08:06:59,060][22664] Avg episode reward: [(0, '51.155')] [2023-03-09 08:06:59,326][23090] Updated weights for policy 0, policy_version 29512 (0.0013) [2023-03-09 08:07:00,108][23090] Updated weights for policy 0, policy_version 29522 (0.0013) [2023-03-09 08:07:00,987][23090] Updated weights for policy 0, policy_version 29532 (0.0016) [2023-03-09 08:07:01,782][23090] Updated weights for policy 0, policy_version 29542 (0.0020) [2023-03-09 08:07:02,600][23090] Updated weights for policy 0, policy_version 29552 (0.0016) [2023-03-09 08:07:03,415][23090] Updated weights for policy 0, policy_version 29562 (0.0021) [2023-03-09 08:07:04,059][22664] Fps is (10 sec: 199887.4, 60 sec: 199339.5, 300 sec: 199107.2). Total num frames: 484458496. Throughput: 0: 49782.9. Samples: 121129424. Policy #0 lag: (min: 2.0, avg: 17.0, max: 34.0) [2023-03-09 08:07:04,060][22664] Avg episode reward: [(0, '55.053')] [2023-03-09 08:07:04,276][23090] Updated weights for policy 0, policy_version 29572 (0.0013) [2023-03-09 08:07:05,063][23090] Updated weights for policy 0, policy_version 29582 (0.0015) [2023-03-09 08:07:05,162][22940] Signal inference workers to stop experience collection... (9750 times) [2023-03-09 08:07:05,167][22940] Signal inference workers to resume experience collection... (9750 times) [2023-03-09 08:07:05,232][23090] InferenceWorker_p0-w0: stopping experience collection (9750 times) [2023-03-09 08:07:05,233][23090] InferenceWorker_p0-w0: resuming experience collection (9750 times) [2023-03-09 08:07:05,915][23090] Updated weights for policy 0, policy_version 29592 (0.0018) [2023-03-09 08:07:06,826][23090] Updated weights for policy 0, policy_version 29602 (0.0016) [2023-03-09 08:07:07,576][23090] Updated weights for policy 0, policy_version 29612 (0.0020) [2023-03-09 08:07:08,391][23090] Updated weights for policy 0, policy_version 29622 (0.0016) [2023-03-09 08:07:09,059][22664] Fps is (10 sec: 198247.4, 60 sec: 199338.6, 300 sec: 199051.9). Total num frames: 485457920. Throughput: 0: 49782.8. Samples: 121428432. Policy #0 lag: (min: 1.0, avg: 16.8, max: 32.0) [2023-03-09 08:07:09,060][22664] Avg episode reward: [(0, '52.015')] [2023-03-09 08:07:09,190][23090] Updated weights for policy 0, policy_version 29632 (0.0013) [2023-03-09 08:07:10,112][23090] Updated weights for policy 0, policy_version 29642 (0.0016) [2023-03-09 08:07:10,800][23090] Updated weights for policy 0, policy_version 29652 (0.0013) [2023-03-09 08:07:11,647][23090] Updated weights for policy 0, policy_version 29662 (0.0013) [2023-03-09 08:07:12,620][23090] Updated weights for policy 0, policy_version 29673 (0.0020) [2023-03-09 08:07:13,395][23090] Updated weights for policy 0, policy_version 29683 (0.0017) [2023-03-09 08:07:14,058][22664] Fps is (10 sec: 198248.8, 60 sec: 199066.4, 300 sec: 199052.0). Total num frames: 486440960. Throughput: 0: 49827.3. Samples: 121577888. Policy #0 lag: (min: 1.0, avg: 16.8, max: 32.0) [2023-03-09 08:07:14,059][22664] Avg episode reward: [(0, '53.549')] [2023-03-09 08:07:14,277][23090] Updated weights for policy 0, policy_version 29693 (0.0018) [2023-03-09 08:07:15,113][23090] Updated weights for policy 0, policy_version 29703 (0.0018) [2023-03-09 08:07:15,898][23090] Updated weights for policy 0, policy_version 29713 (0.0013) [2023-03-09 08:07:16,777][23090] Updated weights for policy 0, policy_version 29723 (0.0013) [2023-03-09 08:07:17,579][23090] Updated weights for policy 0, policy_version 29733 (0.0013) [2023-03-09 08:07:18,375][23090] Updated weights for policy 0, policy_version 29743 (0.0025) [2023-03-09 08:07:19,059][22664] Fps is (10 sec: 198236.6, 60 sec: 199064.8, 300 sec: 199051.3). Total num frames: 487440384. Throughput: 0: 49690.1. Samples: 121872768. Policy #0 lag: (min: 1.0, avg: 16.8, max: 32.0) [2023-03-09 08:07:19,061][22664] Avg episode reward: [(0, '51.835')] [2023-03-09 08:07:19,088][22940] Saving /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000029752_487456768.pth... [2023-03-09 08:07:19,159][22940] Removing /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000026835_439664640.pth [2023-03-09 08:07:19,258][23090] Updated weights for policy 0, policy_version 29753 (0.0018) [2023-03-09 08:07:19,470][22940] Signal inference workers to stop experience collection... (9800 times) [2023-03-09 08:07:19,472][22940] Signal inference workers to resume experience collection... (9800 times) [2023-03-09 08:07:19,542][23090] InferenceWorker_p0-w0: stopping experience collection (9800 times) [2023-03-09 08:07:19,542][23090] InferenceWorker_p0-w0: resuming experience collection (9800 times) [2023-03-09 08:07:20,098][23090] Updated weights for policy 0, policy_version 29763 (0.0022) [2023-03-09 08:07:20,857][23090] Updated weights for policy 0, policy_version 29773 (0.0022) [2023-03-09 08:07:21,667][23090] Updated weights for policy 0, policy_version 29783 (0.0013) [2023-03-09 08:07:22,484][23090] Updated weights for policy 0, policy_version 29793 (0.0025) [2023-03-09 08:07:23,337][23090] Updated weights for policy 0, policy_version 29803 (0.0015) [2023-03-09 08:07:24,059][22664] Fps is (10 sec: 199880.4, 60 sec: 199338.0, 300 sec: 199052.0). Total num frames: 488439808. Throughput: 0: 49735.8. Samples: 122171712. Policy #0 lag: (min: 1.0, avg: 16.8, max: 32.0) [2023-03-09 08:07:24,061][22664] Avg episode reward: [(0, '52.940')] [2023-03-09 08:07:24,137][23090] Updated weights for policy 0, policy_version 29813 (0.0024) [2023-03-09 08:07:24,985][23090] Updated weights for policy 0, policy_version 29823 (0.0013) [2023-03-09 08:07:25,821][23090] Updated weights for policy 0, policy_version 29833 (0.0019) [2023-03-09 08:07:26,619][23090] Updated weights for policy 0, policy_version 29843 (0.0013) [2023-03-09 08:07:27,461][23090] Updated weights for policy 0, policy_version 29853 (0.0016) [2023-03-09 08:07:28,253][23090] Updated weights for policy 0, policy_version 29863 (0.0013) [2023-03-09 08:07:29,057][23090] Updated weights for policy 0, policy_version 29873 (0.0015) [2023-03-09 08:07:29,059][22664] Fps is (10 sec: 199888.0, 60 sec: 199064.6, 300 sec: 199051.4). Total num frames: 489439232. Throughput: 0: 49781.7. Samples: 122321216. Policy #0 lag: (min: 1.0, avg: 16.9, max: 33.0) [2023-03-09 08:07:29,061][22664] Avg episode reward: [(0, '53.154')] [2023-03-09 08:07:29,925][23090] Updated weights for policy 0, policy_version 29883 (0.0017) [2023-03-09 08:07:30,737][23090] Updated weights for policy 0, policy_version 29893 (0.0016) [2023-03-09 08:07:31,540][23090] Updated weights for policy 0, policy_version 29903 (0.0017) [2023-03-09 08:07:32,357][23090] Updated weights for policy 0, policy_version 29913 (0.0018) [2023-03-09 08:07:33,296][23090] Updated weights for policy 0, policy_version 29924 (0.0016) [2023-03-09 08:07:34,058][22664] Fps is (10 sec: 198251.5, 60 sec: 199065.8, 300 sec: 199052.0). Total num frames: 490422272. Throughput: 0: 49782.6. Samples: 122620176. Policy #0 lag: (min: 1.0, avg: 16.9, max: 33.0) [2023-03-09 08:07:34,059][22664] Avg episode reward: [(0, '51.687')] [2023-03-09 08:07:34,145][23090] Updated weights for policy 0, policy_version 29934 (0.0017) [2023-03-09 08:07:34,915][23090] Updated weights for policy 0, policy_version 29944 (0.0013) [2023-03-09 08:07:35,294][22940] Signal inference workers to stop experience collection... (9850 times) [2023-03-09 08:07:35,294][22940] Signal inference workers to resume experience collection... (9850 times) [2023-03-09 08:07:35,354][23090] InferenceWorker_p0-w0: stopping experience collection (9850 times) [2023-03-09 08:07:35,354][23090] InferenceWorker_p0-w0: resuming experience collection (9850 times) [2023-03-09 08:07:35,878][23090] Updated weights for policy 0, policy_version 29955 (0.0018) [2023-03-09 08:07:36,655][23090] Updated weights for policy 0, policy_version 29965 (0.0022) [2023-03-09 08:07:37,470][23090] Updated weights for policy 0, policy_version 29975 (0.0017) [2023-03-09 08:07:38,284][23090] Updated weights for policy 0, policy_version 29985 (0.0016) [2023-03-09 08:07:39,058][22664] Fps is (10 sec: 196615.6, 60 sec: 198793.2, 300 sec: 199051.9). Total num frames: 491405312. Throughput: 0: 49736.5. Samples: 122919088. Policy #0 lag: (min: 1.0, avg: 16.9, max: 33.0) [2023-03-09 08:07:39,103][22664] Avg episode reward: [(0, '50.489')] [2023-03-09 08:07:39,157][23090] Updated weights for policy 0, policy_version 29995 (0.0016) [2023-03-09 08:07:39,937][23090] Updated weights for policy 0, policy_version 30005 (0.0017) [2023-03-09 08:07:40,812][23090] Updated weights for policy 0, policy_version 30015 (0.0017) [2023-03-09 08:07:41,590][23090] Updated weights for policy 0, policy_version 30025 (0.0017) [2023-03-09 08:07:42,394][23090] Updated weights for policy 0, policy_version 30035 (0.0016) [2023-03-09 08:07:43,281][23090] Updated weights for policy 0, policy_version 30045 (0.0013) [2023-03-09 08:07:44,059][22664] Fps is (10 sec: 198240.4, 60 sec: 198791.7, 300 sec: 199051.5). Total num frames: 492404736. Throughput: 0: 49736.3. Samples: 123068560. Policy #0 lag: (min: 1.0, avg: 16.9, max: 33.0) [2023-03-09 08:07:44,061][22664] Avg episode reward: [(0, '52.206')] [2023-03-09 08:07:44,089][23090] Updated weights for policy 0, policy_version 30055 (0.0019) [2023-03-09 08:07:44,936][23090] Updated weights for policy 0, policy_version 30065 (0.0021) [2023-03-09 08:07:45,781][23090] Updated weights for policy 0, policy_version 30075 (0.0020) [2023-03-09 08:07:46,518][23090] Updated weights for policy 0, policy_version 30085 (0.0013) [2023-03-09 08:07:47,392][23090] Updated weights for policy 0, policy_version 30095 (0.0013) [2023-03-09 08:07:48,190][23090] Updated weights for policy 0, policy_version 30105 (0.0016) [2023-03-09 08:07:48,679][22940] Signal inference workers to stop experience collection... (9900 times) [2023-03-09 08:07:48,681][22940] Signal inference workers to resume experience collection... (9900 times) [2023-03-09 08:07:48,745][23090] InferenceWorker_p0-w0: stopping experience collection (9900 times) [2023-03-09 08:07:48,745][23090] InferenceWorker_p0-w0: resuming experience collection (9900 times) [2023-03-09 08:07:49,058][22664] Fps is (10 sec: 199884.8, 60 sec: 198793.2, 300 sec: 199051.7). Total num frames: 493404160. Throughput: 0: 49690.1. Samples: 123365472. Policy #0 lag: (min: 0.0, avg: 16.7, max: 33.0) [2023-03-09 08:07:49,059][22664] Avg episode reward: [(0, '52.427')] [2023-03-09 08:07:49,070][23090] Updated weights for policy 0, policy_version 30115 (0.0013) [2023-03-09 08:07:49,961][23090] Updated weights for policy 0, policy_version 30126 (0.0017) [2023-03-09 08:07:50,747][23090] Updated weights for policy 0, policy_version 30136 (0.0018) [2023-03-09 08:07:51,629][23090] Updated weights for policy 0, policy_version 30146 (0.0019) [2023-03-09 08:07:52,369][23090] Updated weights for policy 0, policy_version 30156 (0.0013) [2023-03-09 08:07:53,171][23090] Updated weights for policy 0, policy_version 30166 (0.0013) [2023-03-09 08:07:54,023][23090] Updated weights for policy 0, policy_version 30176 (0.0016) [2023-03-09 08:07:54,059][22664] Fps is (10 sec: 199889.4, 60 sec: 199066.3, 300 sec: 199051.9). Total num frames: 494403584. Throughput: 0: 49689.2. Samples: 123664448. Policy #0 lag: (min: 0.0, avg: 16.7, max: 33.0) [2023-03-09 08:07:54,060][22664] Avg episode reward: [(0, '52.349')] [2023-03-09 08:07:54,884][23090] Updated weights for policy 0, policy_version 30186 (0.0017) [2023-03-09 08:07:55,680][23090] Updated weights for policy 0, policy_version 30196 (0.0016) [2023-03-09 08:07:56,496][23090] Updated weights for policy 0, policy_version 30206 (0.0013) [2023-03-09 08:07:57,355][23090] Updated weights for policy 0, policy_version 30216 (0.0013) [2023-03-09 08:07:58,131][23090] Updated weights for policy 0, policy_version 30226 (0.0013) [2023-03-09 08:07:59,044][23090] Updated weights for policy 0, policy_version 30236 (0.0018) [2023-03-09 08:07:59,059][22664] Fps is (10 sec: 198239.5, 60 sec: 198518.6, 300 sec: 199051.5). Total num frames: 495386624. Throughput: 0: 49689.6. Samples: 123813936. Policy #0 lag: (min: 0.0, avg: 16.7, max: 33.0) [2023-03-09 08:07:59,061][22664] Avg episode reward: [(0, '51.886')] [2023-03-09 08:07:59,774][23090] Updated weights for policy 0, policy_version 30246 (0.0013) [2023-03-09 08:08:00,614][23090] Updated weights for policy 0, policy_version 30256 (0.0016) [2023-03-09 08:08:01,473][23090] Updated weights for policy 0, policy_version 30266 (0.0016) [2023-03-09 08:08:01,636][22940] Signal inference workers to stop experience collection... (9950 times) [2023-03-09 08:08:01,653][22940] Signal inference workers to resume experience collection... (9950 times) [2023-03-09 08:08:01,734][23090] InferenceWorker_p0-w0: stopping experience collection (9950 times) [2023-03-09 08:08:01,734][23090] InferenceWorker_p0-w0: resuming experience collection (9950 times) [2023-03-09 08:08:02,348][23090] Updated weights for policy 0, policy_version 30277 (0.0013) [2023-03-09 08:08:03,203][23090] Updated weights for policy 0, policy_version 30287 (0.0014) [2023-03-09 08:08:03,979][23090] Updated weights for policy 0, policy_version 30297 (0.0015) [2023-03-09 08:08:04,059][22664] Fps is (10 sec: 198245.4, 60 sec: 198792.6, 300 sec: 199051.7). Total num frames: 496386048. Throughput: 0: 49735.6. Samples: 124110848. Policy #0 lag: (min: 1.0, avg: 16.9, max: 33.0) [2023-03-09 08:08:04,060][22664] Avg episode reward: [(0, '53.283')] [2023-03-09 08:08:04,884][23090] Updated weights for policy 0, policy_version 30307 (0.0018) [2023-03-09 08:08:05,662][23090] Updated weights for policy 0, policy_version 30317 (0.0021) [2023-03-09 08:08:06,449][23090] Updated weights for policy 0, policy_version 30327 (0.0016) [2023-03-09 08:08:07,319][23090] Updated weights for policy 0, policy_version 30337 (0.0013) [2023-03-09 08:08:08,128][23090] Updated weights for policy 0, policy_version 30347 (0.0013) [2023-03-09 08:08:08,910][23090] Updated weights for policy 0, policy_version 30357 (0.0021) [2023-03-09 08:08:09,058][22664] Fps is (10 sec: 201530.3, 60 sec: 199065.8, 300 sec: 199107.2). Total num frames: 497401856. Throughput: 0: 49782.3. Samples: 124411904. Policy #0 lag: (min: 1.0, avg: 16.9, max: 33.0) [2023-03-09 08:08:09,059][22664] Avg episode reward: [(0, '51.107')] [2023-03-09 08:08:09,736][23090] Updated weights for policy 0, policy_version 30367 (0.0016) [2023-03-09 08:08:10,566][23090] Updated weights for policy 0, policy_version 30377 (0.0016) [2023-03-09 08:08:11,424][23090] Updated weights for policy 0, policy_version 30387 (0.0015) [2023-03-09 08:08:12,271][23090] Updated weights for policy 0, policy_version 30397 (0.0016) [2023-03-09 08:08:13,068][23090] Updated weights for policy 0, policy_version 30407 (0.0026) [2023-03-09 08:08:13,328][22940] Signal inference workers to stop experience collection... (10000 times) [2023-03-09 08:08:13,329][22940] Signal inference workers to resume experience collection... (10000 times) [2023-03-09 08:08:13,395][23090] InferenceWorker_p0-w0: stopping experience collection (10000 times) [2023-03-09 08:08:13,396][23090] InferenceWorker_p0-w0: resuming experience collection (10000 times) [2023-03-09 08:08:13,847][23090] Updated weights for policy 0, policy_version 30417 (0.0023) [2023-03-09 08:08:14,059][22664] Fps is (10 sec: 199881.9, 60 sec: 199064.8, 300 sec: 199107.4). Total num frames: 498384896. Throughput: 0: 49781.5. Samples: 124561376. Policy #0 lag: (min: 1.0, avg: 16.9, max: 33.0) [2023-03-09 08:08:14,060][22664] Avg episode reward: [(0, '52.077')] [2023-03-09 08:08:14,771][23090] Updated weights for policy 0, policy_version 30427 (0.0019) [2023-03-09 08:08:15,481][23090] Updated weights for policy 0, policy_version 30437 (0.0013) [2023-03-09 08:08:16,336][23090] Updated weights for policy 0, policy_version 30447 (0.0013) [2023-03-09 08:08:17,113][23090] Updated weights for policy 0, policy_version 30457 (0.0022) [2023-03-09 08:08:18,018][23090] Updated weights for policy 0, policy_version 30467 (0.0019) [2023-03-09 08:08:18,901][23090] Updated weights for policy 0, policy_version 30478 (0.0013) [2023-03-09 08:08:19,059][22664] Fps is (10 sec: 198239.2, 60 sec: 199066.2, 300 sec: 199107.2). Total num frames: 499384320. Throughput: 0: 49781.3. Samples: 124860352. Policy #0 lag: (min: 1.0, avg: 16.9, max: 33.0) [2023-03-09 08:08:19,061][22664] Avg episode reward: [(0, '54.103')] [2023-03-09 08:08:19,666][23090] Updated weights for policy 0, policy_version 30488 (0.0020) [2023-03-09 08:08:20,561][23090] Updated weights for policy 0, policy_version 30498 (0.0018) [2023-03-09 08:08:21,313][23090] Updated weights for policy 0, policy_version 30508 (0.0016) [2023-03-09 08:08:22,175][23090] Updated weights for policy 0, policy_version 30518 (0.0016) [2023-03-09 08:08:22,950][23090] Updated weights for policy 0, policy_version 30528 (0.0016) [2023-03-09 08:08:23,869][23090] Updated weights for policy 0, policy_version 30538 (0.0013) [2023-03-09 08:08:24,059][22664] Fps is (10 sec: 198249.9, 60 sec: 198793.1, 300 sec: 199162.8). Total num frames: 500367360. Throughput: 0: 49783.7. Samples: 125159360. Policy #0 lag: (min: 0.0, avg: 16.6, max: 33.0) [2023-03-09 08:08:24,060][22664] Avg episode reward: [(0, '48.588')] [2023-03-09 08:08:24,598][23090] Updated weights for policy 0, policy_version 30548 (0.0013) [2023-03-09 08:08:25,448][23090] Updated weights for policy 0, policy_version 30558 (0.0013) [2023-03-09 08:08:25,811][22940] Signal inference workers to stop experience collection... (10050 times) [2023-03-09 08:08:25,813][22940] Signal inference workers to resume experience collection... (10050 times) [2023-03-09 08:08:25,878][23090] InferenceWorker_p0-w0: stopping experience collection (10050 times) [2023-03-09 08:08:25,879][23090] InferenceWorker_p0-w0: resuming experience collection (10050 times) [2023-03-09 08:08:26,269][23090] Updated weights for policy 0, policy_version 30568 (0.0016) [2023-03-09 08:08:27,071][23090] Updated weights for policy 0, policy_version 30578 (0.0013) [2023-03-09 08:08:27,946][23090] Updated weights for policy 0, policy_version 30588 (0.0015) [2023-03-09 08:08:28,700][23090] Updated weights for policy 0, policy_version 30598 (0.0019) [2023-03-09 08:08:29,059][22664] Fps is (10 sec: 199890.2, 60 sec: 199066.6, 300 sec: 199218.5). Total num frames: 501383168. Throughput: 0: 49829.9. Samples: 125310896. Policy #0 lag: (min: 0.0, avg: 16.6, max: 33.0) [2023-03-09 08:08:29,060][22664] Avg episode reward: [(0, '51.554')] [2023-03-09 08:08:29,544][23090] Updated weights for policy 0, policy_version 30608 (0.0022) [2023-03-09 08:08:30,349][23090] Updated weights for policy 0, policy_version 30618 (0.0022) [2023-03-09 08:08:31,183][23090] Updated weights for policy 0, policy_version 30628 (0.0019) [2023-03-09 08:08:31,996][23090] Updated weights for policy 0, policy_version 30638 (0.0016) [2023-03-09 08:08:32,885][23090] Updated weights for policy 0, policy_version 30649 (0.0015) [2023-03-09 08:08:33,766][23090] Updated weights for policy 0, policy_version 30659 (0.0015) [2023-03-09 08:08:34,059][22664] Fps is (10 sec: 201512.7, 60 sec: 199336.6, 300 sec: 199218.0). Total num frames: 502382592. Throughput: 0: 49828.7. Samples: 125607792. Policy #0 lag: (min: 0.0, avg: 16.6, max: 33.0) [2023-03-09 08:08:34,061][22664] Avg episode reward: [(0, '51.018')] [2023-03-09 08:08:34,641][23090] Updated weights for policy 0, policy_version 30670 (0.0016) [2023-03-09 08:08:35,417][23090] Updated weights for policy 0, policy_version 30680 (0.0026) [2023-03-09 08:08:36,442][23090] Updated weights for policy 0, policy_version 30691 (0.0015) [2023-03-09 08:08:37,242][23090] Updated weights for policy 0, policy_version 30701 (0.0021) [2023-03-09 08:08:38,005][23090] Updated weights for policy 0, policy_version 30711 (0.0015) [2023-03-09 08:08:38,464][22940] Signal inference workers to stop experience collection... (10100 times) [2023-03-09 08:08:38,481][22940] Signal inference workers to resume experience collection... (10100 times) [2023-03-09 08:08:38,531][23090] InferenceWorker_p0-w0: stopping experience collection (10100 times) [2023-03-09 08:08:38,531][23090] InferenceWorker_p0-w0: resuming experience collection (10100 times) [2023-03-09 08:08:38,850][23090] Updated weights for policy 0, policy_version 30721 (0.0016) [2023-03-09 08:08:39,059][22664] Fps is (10 sec: 198241.9, 60 sec: 199337.6, 300 sec: 199218.3). Total num frames: 503365632. Throughput: 0: 49829.8. Samples: 125906800. Policy #0 lag: (min: 0.0, avg: 16.6, max: 33.0) [2023-03-09 08:08:39,061][22664] Avg episode reward: [(0, '51.831')] [2023-03-09 08:08:39,731][23090] Updated weights for policy 0, policy_version 30732 (0.0013) [2023-03-09 08:08:40,549][23090] Updated weights for policy 0, policy_version 30742 (0.0013) [2023-03-09 08:08:41,366][23090] Updated weights for policy 0, policy_version 30752 (0.0017) [2023-03-09 08:08:42,264][23090] Updated weights for policy 0, policy_version 30762 (0.0016) [2023-03-09 08:08:42,998][23090] Updated weights for policy 0, policy_version 30772 (0.0013) [2023-03-09 08:08:43,840][23090] Updated weights for policy 0, policy_version 30782 (0.0015) [2023-03-09 08:08:44,058][22664] Fps is (10 sec: 198258.1, 60 sec: 199339.6, 300 sec: 199274.3). Total num frames: 504365056. Throughput: 0: 49829.7. Samples: 126056256. Policy #0 lag: (min: 0.0, avg: 16.8, max: 33.0) [2023-03-09 08:08:44,059][22664] Avg episode reward: [(0, '53.260')] [2023-03-09 08:08:44,747][23090] Updated weights for policy 0, policy_version 30793 (0.0016) [2023-03-09 08:08:45,568][23090] Updated weights for policy 0, policy_version 30803 (0.0015) [2023-03-09 08:08:46,412][23090] Updated weights for policy 0, policy_version 30813 (0.0013) [2023-03-09 08:08:47,214][23090] Updated weights for policy 0, policy_version 30823 (0.0015) [2023-03-09 08:08:48,018][23090] Updated weights for policy 0, policy_version 30833 (0.0017) [2023-03-09 08:08:48,928][23090] Updated weights for policy 0, policy_version 30843 (0.0015) [2023-03-09 08:08:49,059][22664] Fps is (10 sec: 201522.7, 60 sec: 199610.6, 300 sec: 199273.9). Total num frames: 505380864. Throughput: 0: 49873.2. Samples: 126355152. Policy #0 lag: (min: 0.0, avg: 16.8, max: 33.0) [2023-03-09 08:08:49,060][22664] Avg episode reward: [(0, '53.026')] [2023-03-09 08:08:49,623][23090] Updated weights for policy 0, policy_version 30853 (0.0020) [2023-03-09 08:08:50,564][23090] Updated weights for policy 0, policy_version 30864 (0.0013) [2023-03-09 08:08:51,385][23090] Updated weights for policy 0, policy_version 30874 (0.0020) [2023-03-09 08:08:51,638][22940] Signal inference workers to stop experience collection... (10150 times) [2023-03-09 08:08:51,638][22940] Signal inference workers to resume experience collection... (10150 times) [2023-03-09 08:08:51,703][23090] InferenceWorker_p0-w0: stopping experience collection (10150 times) [2023-03-09 08:08:51,704][23090] InferenceWorker_p0-w0: resuming experience collection (10150 times) [2023-03-09 08:08:52,203][23090] Updated weights for policy 0, policy_version 30884 (0.0017) [2023-03-09 08:08:53,005][23090] Updated weights for policy 0, policy_version 30894 (0.0013) [2023-03-09 08:08:53,807][23090] Updated weights for policy 0, policy_version 30904 (0.0018) [2023-03-09 08:08:54,059][22664] Fps is (10 sec: 199878.4, 60 sec: 199337.8, 300 sec: 199218.1). Total num frames: 506363904. Throughput: 0: 49871.6. Samples: 126656144. Policy #0 lag: (min: 0.0, avg: 16.8, max: 33.0) [2023-03-09 08:08:54,060][22664] Avg episode reward: [(0, '50.037')] [2023-03-09 08:08:54,732][23090] Updated weights for policy 0, policy_version 30914 (0.0013) [2023-03-09 08:08:55,432][23090] Updated weights for policy 0, policy_version 30924 (0.0014) [2023-03-09 08:08:56,286][23090] Updated weights for policy 0, policy_version 30934 (0.0016) [2023-03-09 08:08:57,096][23090] Updated weights for policy 0, policy_version 30944 (0.0015) [2023-03-09 08:08:58,009][23090] Updated weights for policy 0, policy_version 30954 (0.0013) [2023-03-09 08:08:58,767][23090] Updated weights for policy 0, policy_version 30964 (0.0016) [2023-03-09 08:08:59,059][22664] Fps is (10 sec: 198246.3, 60 sec: 199611.7, 300 sec: 199218.3). Total num frames: 507363328. Throughput: 0: 49872.3. Samples: 126805632. Policy #0 lag: (min: 0.0, avg: 16.8, max: 33.0) [2023-03-09 08:08:59,061][22664] Avg episode reward: [(0, '52.903')] [2023-03-09 08:08:59,594][23090] Updated weights for policy 0, policy_version 30974 (0.0020) [2023-03-09 08:09:00,479][23090] Updated weights for policy 0, policy_version 30984 (0.0017) [2023-03-09 08:09:01,341][23090] Updated weights for policy 0, policy_version 30994 (0.0013) [2023-03-09 08:09:02,151][23090] Updated weights for policy 0, policy_version 31004 (0.0023) [2023-03-09 08:09:02,885][23090] Updated weights for policy 0, policy_version 31014 (0.0016) [2023-03-09 08:09:03,765][23090] Updated weights for policy 0, policy_version 31024 (0.0015) [2023-03-09 08:09:04,059][22664] Fps is (10 sec: 199880.2, 60 sec: 199610.2, 300 sec: 199218.0). Total num frames: 508362752. Throughput: 0: 49827.0. Samples: 127102576. Policy #0 lag: (min: 1.0, avg: 16.5, max: 33.0) [2023-03-09 08:09:04,061][22664] Avg episode reward: [(0, '53.120')] [2023-03-09 08:09:04,580][23090] Updated weights for policy 0, policy_version 31034 (0.0016) [2023-03-09 08:09:05,427][23090] Updated weights for policy 0, policy_version 31044 (0.0016) [2023-03-09 08:09:06,224][23090] Updated weights for policy 0, policy_version 31054 (0.0013) [2023-03-09 08:09:07,102][23090] Updated weights for policy 0, policy_version 31065 (0.0014) [2023-03-09 08:09:07,936][22940] Signal inference workers to stop experience collection... (10200 times) [2023-03-09 08:09:07,951][22940] Signal inference workers to resume experience collection... (10200 times) [2023-03-09 08:09:08,021][23090] InferenceWorker_p0-w0: stopping experience collection (10200 times) [2023-03-09 08:09:08,021][23090] InferenceWorker_p0-w0: resuming experience collection (10200 times) [2023-03-09 08:09:08,023][23090] Updated weights for policy 0, policy_version 31075 (0.0013) [2023-03-09 08:09:08,803][23090] Updated weights for policy 0, policy_version 31085 (0.0014) [2023-03-09 08:09:09,059][22664] Fps is (10 sec: 198246.3, 60 sec: 199064.4, 300 sec: 199162.6). Total num frames: 509345792. Throughput: 0: 49780.7. Samples: 127399504. Policy #0 lag: (min: 1.0, avg: 16.5, max: 33.0) [2023-03-09 08:09:09,061][22664] Avg episode reward: [(0, '53.661')] [2023-03-09 08:09:09,579][23090] Updated weights for policy 0, policy_version 31095 (0.0017) [2023-03-09 08:09:10,448][23090] Updated weights for policy 0, policy_version 31105 (0.0013) [2023-03-09 08:09:11,233][23090] Updated weights for policy 0, policy_version 31115 (0.0013) [2023-03-09 08:09:12,035][23090] Updated weights for policy 0, policy_version 31125 (0.0020) [2023-03-09 08:09:12,885][23090] Updated weights for policy 0, policy_version 31135 (0.0013) [2023-03-09 08:09:13,747][23090] Updated weights for policy 0, policy_version 31145 (0.0021) [2023-03-09 08:09:14,059][22664] Fps is (10 sec: 198256.3, 60 sec: 199339.3, 300 sec: 199218.7). Total num frames: 510345216. Throughput: 0: 49779.9. Samples: 127550992. Policy #0 lag: (min: 1.0, avg: 16.5, max: 33.0) [2023-03-09 08:09:14,059][22664] Avg episode reward: [(0, '50.710')] [2023-03-09 08:09:14,518][23090] Updated weights for policy 0, policy_version 31155 (0.0016) [2023-03-09 08:09:15,362][23090] Updated weights for policy 0, policy_version 31165 (0.0018) [2023-03-09 08:09:16,226][23090] Updated weights for policy 0, policy_version 31175 (0.0018) [2023-03-09 08:09:16,960][23090] Updated weights for policy 0, policy_version 31185 (0.0016) [2023-03-09 08:09:17,845][23090] Updated weights for policy 0, policy_version 31195 (0.0013) [2023-03-09 08:09:18,679][23090] Updated weights for policy 0, policy_version 31206 (0.0022) [2023-03-09 08:09:19,059][22664] Fps is (10 sec: 198251.0, 60 sec: 199066.4, 300 sec: 199162.7). Total num frames: 511328256. Throughput: 0: 49826.0. Samples: 127849936. Policy #0 lag: (min: 1.0, avg: 16.5, max: 33.0) [2023-03-09 08:09:19,060][22664] Avg episode reward: [(0, '51.181')] [2023-03-09 08:09:19,106][22940] Saving /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000031211_511361024.pth... [2023-03-09 08:09:19,162][22940] Removing /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000028291_463519744.pth [2023-03-09 08:09:19,521][23090] Updated weights for policy 0, policy_version 31216 (0.0013) [2023-03-09 08:09:20,335][23090] Updated weights for policy 0, policy_version 31226 (0.0016) [2023-03-09 08:09:21,174][23090] Updated weights for policy 0, policy_version 31236 (0.0013) [2023-03-09 08:09:21,754][22940] Signal inference workers to stop experience collection... (10250 times) [2023-03-09 08:09:21,756][22940] Signal inference workers to resume experience collection... (10250 times) [2023-03-09 08:09:21,819][23090] InferenceWorker_p0-w0: stopping experience collection (10250 times) [2023-03-09 08:09:21,822][23090] InferenceWorker_p0-w0: resuming experience collection (10250 times) [2023-03-09 08:09:21,988][23090] Updated weights for policy 0, policy_version 31246 (0.0018) [2023-03-09 08:09:22,790][23090] Updated weights for policy 0, policy_version 31256 (0.0013) [2023-03-09 08:09:23,681][23090] Updated weights for policy 0, policy_version 31266 (0.0021) [2023-03-09 08:09:24,059][22664] Fps is (10 sec: 199881.1, 60 sec: 199611.2, 300 sec: 199218.7). Total num frames: 512344064. Throughput: 0: 49824.1. Samples: 128148880. Policy #0 lag: (min: 1.0, avg: 16.6, max: 33.0) [2023-03-09 08:09:24,060][22664] Avg episode reward: [(0, '53.966')] [2023-03-09 08:09:24,446][23090] Updated weights for policy 0, policy_version 31276 (0.0018) [2023-03-09 08:09:25,278][23090] Updated weights for policy 0, policy_version 31286 (0.0013) [2023-03-09 08:09:26,060][23090] Updated weights for policy 0, policy_version 31296 (0.0016) [2023-03-09 08:09:26,990][23090] Updated weights for policy 0, policy_version 31306 (0.0017) [2023-03-09 08:09:27,709][23090] Updated weights for policy 0, policy_version 31316 (0.0017) [2023-03-09 08:09:28,577][23090] Updated weights for policy 0, policy_version 31326 (0.0014) [2023-03-09 08:09:29,059][22664] Fps is (10 sec: 199884.5, 60 sec: 199065.5, 300 sec: 199218.3). Total num frames: 513327104. Throughput: 0: 49824.6. Samples: 128298368. Policy #0 lag: (min: 1.0, avg: 16.6, max: 33.0) [2023-03-09 08:09:29,060][22664] Avg episode reward: [(0, '53.304')] [2023-03-09 08:09:29,412][23090] Updated weights for policy 0, policy_version 31336 (0.0027) [2023-03-09 08:09:30,220][23090] Updated weights for policy 0, policy_version 31346 (0.0016) [2023-03-09 08:09:31,068][23090] Updated weights for policy 0, policy_version 31356 (0.0013) [2023-03-09 08:09:31,935][23090] Updated weights for policy 0, policy_version 31367 (0.0019) [2023-03-09 08:09:32,732][23090] Updated weights for policy 0, policy_version 31377 (0.0013) [2023-03-09 08:09:33,151][22940] Signal inference workers to stop experience collection... (10300 times) [2023-03-09 08:09:33,152][22940] Signal inference workers to resume experience collection... (10300 times) [2023-03-09 08:09:33,214][23090] InferenceWorker_p0-w0: stopping experience collection (10300 times) [2023-03-09 08:09:33,214][23090] InferenceWorker_p0-w0: resuming experience collection (10300 times) [2023-03-09 08:09:33,618][23090] Updated weights for policy 0, policy_version 31387 (0.0018) [2023-03-09 08:09:34,058][22664] Fps is (10 sec: 199889.6, 60 sec: 199340.6, 300 sec: 199329.7). Total num frames: 514342912. Throughput: 0: 49870.6. Samples: 128599312. Policy #0 lag: (min: 1.0, avg: 16.6, max: 33.0) [2023-03-09 08:09:34,060][22664] Avg episode reward: [(0, '53.272')] [2023-03-09 08:09:34,357][23090] Updated weights for policy 0, policy_version 31397 (0.0021) [2023-03-09 08:09:35,229][23090] Updated weights for policy 0, policy_version 31407 (0.0021) [2023-03-09 08:09:35,994][23090] Updated weights for policy 0, policy_version 31417 (0.0018) [2023-03-09 08:09:36,879][23090] Updated weights for policy 0, policy_version 31427 (0.0017) [2023-03-09 08:09:37,657][23090] Updated weights for policy 0, policy_version 31437 (0.0013) [2023-03-09 08:09:38,476][23090] Updated weights for policy 0, policy_version 31447 (0.0019) [2023-03-09 08:09:39,059][22664] Fps is (10 sec: 201519.1, 60 sec: 199611.7, 300 sec: 199329.2). Total num frames: 515342336. Throughput: 0: 49871.3. Samples: 128900352. Policy #0 lag: (min: 1.0, avg: 16.6, max: 33.0) [2023-03-09 08:09:39,061][22664] Avg episode reward: [(0, '50.551')] [2023-03-09 08:09:39,313][23090] Updated weights for policy 0, policy_version 31457 (0.0021) [2023-03-09 08:09:40,121][23090] Updated weights for policy 0, policy_version 31467 (0.0017) [2023-03-09 08:09:40,912][23090] Updated weights for policy 0, policy_version 31477 (0.0015) [2023-03-09 08:09:41,715][23090] Updated weights for policy 0, policy_version 31487 (0.0017) [2023-03-09 08:09:42,645][23090] Updated weights for policy 0, policy_version 31497 (0.0021) [2023-03-09 08:09:43,061][22940] Signal inference workers to stop experience collection... (10350 times) [2023-03-09 08:09:43,062][22940] Signal inference workers to resume experience collection... (10350 times) [2023-03-09 08:09:43,127][23090] InferenceWorker_p0-w0: stopping experience collection (10350 times) [2023-03-09 08:09:43,127][23090] InferenceWorker_p0-w0: resuming experience collection (10350 times) [2023-03-09 08:09:43,405][23090] Updated weights for policy 0, policy_version 31507 (0.0013) [2023-03-09 08:09:44,059][22664] Fps is (10 sec: 198244.9, 60 sec: 199338.4, 300 sec: 199218.3). Total num frames: 516325376. Throughput: 0: 49871.6. Samples: 129049840. Policy #0 lag: (min: 1.0, avg: 16.6, max: 33.0) [2023-03-09 08:09:44,060][22664] Avg episode reward: [(0, '51.551')] [2023-03-09 08:09:44,244][23090] Updated weights for policy 0, policy_version 31517 (0.0020) [2023-03-09 08:09:45,049][23090] Updated weights for policy 0, policy_version 31527 (0.0019) [2023-03-09 08:09:45,816][23090] Updated weights for policy 0, policy_version 31537 (0.0018) [2023-03-09 08:09:46,755][23090] Updated weights for policy 0, policy_version 31547 (0.0013) [2023-03-09 08:09:47,487][23090] Updated weights for policy 0, policy_version 31557 (0.0021) [2023-03-09 08:09:48,356][23090] Updated weights for policy 0, policy_version 31567 (0.0020) [2023-03-09 08:09:49,059][22664] Fps is (10 sec: 199890.1, 60 sec: 199339.6, 300 sec: 199329.5). Total num frames: 517341184. Throughput: 0: 49917.7. Samples: 129348848. Policy #0 lag: (min: 1.0, avg: 16.6, max: 33.0) [2023-03-09 08:09:49,060][22664] Avg episode reward: [(0, '51.685')] [2023-03-09 08:09:49,078][23090] Updated weights for policy 0, policy_version 31577 (0.0019) [2023-03-09 08:09:50,029][23090] Updated weights for policy 0, policy_version 31587 (0.0013) [2023-03-09 08:09:50,761][23090] Updated weights for policy 0, policy_version 31597 (0.0013) [2023-03-09 08:09:51,597][23090] Updated weights for policy 0, policy_version 31607 (0.0021) [2023-03-09 08:09:52,403][23090] Updated weights for policy 0, policy_version 31617 (0.0018) [2023-03-09 08:09:53,246][23090] Updated weights for policy 0, policy_version 31627 (0.0013) [2023-03-09 08:09:53,585][22940] Signal inference workers to stop experience collection... (10400 times) [2023-03-09 08:09:53,601][22940] Signal inference workers to resume experience collection... (10400 times) [2023-03-09 08:09:53,654][23090] InferenceWorker_p0-w0: stopping experience collection (10400 times) [2023-03-09 08:09:53,654][23090] InferenceWorker_p0-w0: resuming experience collection (10400 times) [2023-03-09 08:09:54,044][23090] Updated weights for policy 0, policy_version 31637 (0.0016) [2023-03-09 08:09:54,061][22664] Fps is (10 sec: 201481.6, 60 sec: 199605.7, 300 sec: 199328.2). Total num frames: 518340608. Throughput: 0: 49959.6. Samples: 129647776. Policy #0 lag: (min: 1.0, avg: 16.6, max: 33.0) [2023-03-09 08:09:54,062][22664] Avg episode reward: [(0, '51.425')] [2023-03-09 08:09:54,857][23090] Updated weights for policy 0, policy_version 31647 (0.0017) [2023-03-09 08:09:55,748][23090] Updated weights for policy 0, policy_version 31657 (0.0018) [2023-03-09 08:09:56,513][23090] Updated weights for policy 0, policy_version 31667 (0.0013) [2023-03-09 08:09:57,325][23090] Updated weights for policy 0, policy_version 31677 (0.0015) [2023-03-09 08:09:58,148][23090] Updated weights for policy 0, policy_version 31687 (0.0019) [2023-03-09 08:09:58,952][23090] Updated weights for policy 0, policy_version 31697 (0.0019) [2023-03-09 08:09:59,059][22664] Fps is (10 sec: 198246.4, 60 sec: 199339.6, 300 sec: 199273.9). Total num frames: 519323648. Throughput: 0: 49917.5. Samples: 129797280. Policy #0 lag: (min: 1.0, avg: 16.6, max: 33.0) [2023-03-09 08:09:59,059][22664] Avg episode reward: [(0, '51.192')] [2023-03-09 08:09:59,878][23090] Updated weights for policy 0, policy_version 31707 (0.0018) [2023-03-09 08:10:00,653][23090] Updated weights for policy 0, policy_version 31718 (0.0018) [2023-03-09 08:10:01,529][23090] Updated weights for policy 0, policy_version 31728 (0.0017) [2023-03-09 08:10:02,370][23090] Updated weights for policy 0, policy_version 31738 (0.0013) [2023-03-09 08:10:03,214][23090] Updated weights for policy 0, policy_version 31748 (0.0016) [2023-03-09 08:10:04,056][23090] Updated weights for policy 0, policy_version 31758 (0.0013) [2023-03-09 08:10:04,059][22664] Fps is (10 sec: 198282.8, 60 sec: 199339.5, 300 sec: 199329.2). Total num frames: 520323072. Throughput: 0: 49917.7. Samples: 130096240. Policy #0 lag: (min: 1.0, avg: 16.6, max: 33.0) [2023-03-09 08:10:04,061][22664] Avg episode reward: [(0, '52.304')] [2023-03-09 08:10:04,812][23090] Updated weights for policy 0, policy_version 31768 (0.0016) [2023-03-09 08:10:05,095][22940] Signal inference workers to stop experience collection... (10450 times) [2023-03-09 08:10:05,096][22940] Signal inference workers to resume experience collection... (10450 times) [2023-03-09 08:10:05,171][23090] InferenceWorker_p0-w0: stopping experience collection (10450 times) [2023-03-09 08:10:05,172][23090] InferenceWorker_p0-w0: resuming experience collection (10450 times) [2023-03-09 08:10:05,664][23090] Updated weights for policy 0, policy_version 31778 (0.0017) [2023-03-09 08:10:06,464][23090] Updated weights for policy 0, policy_version 31788 (0.0015) [2023-03-09 08:10:07,281][23090] Updated weights for policy 0, policy_version 31798 (0.0027) [2023-03-09 08:10:08,043][23090] Updated weights for policy 0, policy_version 31808 (0.0013) [2023-03-09 08:10:08,957][23090] Updated weights for policy 0, policy_version 31818 (0.0019) [2023-03-09 08:10:09,059][22664] Fps is (10 sec: 199883.8, 60 sec: 199612.5, 300 sec: 199329.6). Total num frames: 521322496. Throughput: 0: 49962.8. Samples: 130397200. Policy #0 lag: (min: 1.0, avg: 16.9, max: 32.0) [2023-03-09 08:10:09,059][22664] Avg episode reward: [(0, '52.088')] [2023-03-09 08:10:09,692][23090] Updated weights for policy 0, policy_version 31828 (0.0018) [2023-03-09 08:10:10,555][23090] Updated weights for policy 0, policy_version 31838 (0.0017) [2023-03-09 08:10:11,411][23090] Updated weights for policy 0, policy_version 31848 (0.0020) [2023-03-09 08:10:12,245][23090] Updated weights for policy 0, policy_version 31858 (0.0017) [2023-03-09 08:10:13,048][23090] Updated weights for policy 0, policy_version 31868 (0.0013) [2023-03-09 08:10:13,843][23090] Updated weights for policy 0, policy_version 31878 (0.0016) [2023-03-09 08:10:14,059][22664] Fps is (10 sec: 199885.6, 60 sec: 199611.0, 300 sec: 199384.9). Total num frames: 522321920. Throughput: 0: 49917.0. Samples: 130544640. Policy #0 lag: (min: 1.0, avg: 16.9, max: 32.0) [2023-03-09 08:10:14,060][22664] Avg episode reward: [(0, '51.985')] [2023-03-09 08:10:14,654][23090] Updated weights for policy 0, policy_version 31888 (0.0018) [2023-03-09 08:10:15,507][23090] Updated weights for policy 0, policy_version 31898 (0.0013) [2023-03-09 08:10:16,361][23090] Updated weights for policy 0, policy_version 31908 (0.0017) [2023-03-09 08:10:17,185][22940] Signal inference workers to stop experience collection... (10500 times) [2023-03-09 08:10:17,186][22940] Signal inference workers to resume experience collection... (10500 times) [2023-03-09 08:10:17,254][23090] InferenceWorker_p0-w0: stopping experience collection (10500 times) [2023-03-09 08:10:17,254][23090] InferenceWorker_p0-w0: resuming experience collection (10500 times) [2023-03-09 08:10:17,259][23090] Updated weights for policy 0, policy_version 31919 (0.0019) [2023-03-09 08:10:18,058][23090] Updated weights for policy 0, policy_version 31929 (0.0017) [2023-03-09 08:10:18,961][23090] Updated weights for policy 0, policy_version 31939 (0.0013) [2023-03-09 08:10:19,059][22664] Fps is (10 sec: 199882.4, 60 sec: 199884.4, 300 sec: 199329.3). Total num frames: 523321344. Throughput: 0: 49871.7. Samples: 130843552. Policy #0 lag: (min: 1.0, avg: 16.9, max: 32.0) [2023-03-09 08:10:19,060][22664] Avg episode reward: [(0, '48.623')] [2023-03-09 08:10:19,724][23090] Updated weights for policy 0, policy_version 31949 (0.0023) [2023-03-09 08:10:20,543][23090] Updated weights for policy 0, policy_version 31959 (0.0021) [2023-03-09 08:10:21,359][23090] Updated weights for policy 0, policy_version 31969 (0.0022) [2023-03-09 08:10:22,174][23090] Updated weights for policy 0, policy_version 31979 (0.0013) [2023-03-09 08:10:22,968][23090] Updated weights for policy 0, policy_version 31989 (0.0014) [2023-03-09 08:10:23,771][23090] Updated weights for policy 0, policy_version 31999 (0.0013) [2023-03-09 08:10:24,059][22664] Fps is (10 sec: 198249.5, 60 sec: 199339.1, 300 sec: 199329.6). Total num frames: 524304384. Throughput: 0: 49780.5. Samples: 131140464. Policy #0 lag: (min: 1.0, avg: 16.9, max: 32.0) [2023-03-09 08:10:24,059][22664] Avg episode reward: [(0, '53.554')] [2023-03-09 08:10:24,686][23090] Updated weights for policy 0, policy_version 32009 (0.0020) [2023-03-09 08:10:25,459][23090] Updated weights for policy 0, policy_version 32019 (0.0021) [2023-03-09 08:10:26,270][23090] Updated weights for policy 0, policy_version 32029 (0.0013) [2023-03-09 08:10:27,114][23090] Updated weights for policy 0, policy_version 32039 (0.0013) [2023-03-09 08:10:27,921][23090] Updated weights for policy 0, policy_version 32049 (0.0023) [2023-03-09 08:10:28,831][23090] Updated weights for policy 0, policy_version 32059 (0.0013) [2023-03-09 08:10:29,059][22664] Fps is (10 sec: 199885.6, 60 sec: 199884.6, 300 sec: 199384.8). Total num frames: 525320192. Throughput: 0: 49826.0. Samples: 131292016. Policy #0 lag: (min: 1.0, avg: 17.1, max: 33.0) [2023-03-09 08:10:29,060][22664] Avg episode reward: [(0, '50.410')] [2023-03-09 08:10:29,572][23090] Updated weights for policy 0, policy_version 32069 (0.0016) [2023-03-09 08:10:30,408][23090] Updated weights for policy 0, policy_version 32079 (0.0017) [2023-03-09 08:10:31,201][23090] Updated weights for policy 0, policy_version 32089 (0.0018) [2023-03-09 08:10:31,420][22940] Signal inference workers to stop experience collection... (10550 times) [2023-03-09 08:10:31,421][22940] Signal inference workers to resume experience collection... (10550 times) [2023-03-09 08:10:31,486][23090] InferenceWorker_p0-w0: stopping experience collection (10550 times) [2023-03-09 08:10:31,486][23090] InferenceWorker_p0-w0: resuming experience collection (10550 times) [2023-03-09 08:10:32,100][23090] Updated weights for policy 0, policy_version 32099 (0.0020) [2023-03-09 08:10:32,846][23090] Updated weights for policy 0, policy_version 32109 (0.0013) [2023-03-09 08:10:33,658][23090] Updated weights for policy 0, policy_version 32119 (0.0015) [2023-03-09 08:10:34,058][22664] Fps is (10 sec: 199887.1, 60 sec: 199338.7, 300 sec: 199273.9). Total num frames: 526303232. Throughput: 0: 49823.7. Samples: 131590912. Policy #0 lag: (min: 1.0, avg: 17.1, max: 33.0) [2023-03-09 08:10:34,059][22664] Avg episode reward: [(0, '50.658')] [2023-03-09 08:10:34,478][23090] Updated weights for policy 0, policy_version 32129 (0.0016) [2023-03-09 08:10:35,307][23090] Updated weights for policy 0, policy_version 32139 (0.0018) [2023-03-09 08:10:36,088][23090] Updated weights for policy 0, policy_version 32149 (0.0016) [2023-03-09 08:10:36,924][23090] Updated weights for policy 0, policy_version 32159 (0.0016) [2023-03-09 08:10:37,842][23090] Updated weights for policy 0, policy_version 32169 (0.0017) [2023-03-09 08:10:38,609][23090] Updated weights for policy 0, policy_version 32179 (0.0016) [2023-03-09 08:10:39,059][22664] Fps is (10 sec: 198240.8, 60 sec: 199338.2, 300 sec: 199273.6). Total num frames: 527302656. Throughput: 0: 49826.9. Samples: 131889904. Policy #0 lag: (min: 1.0, avg: 17.1, max: 33.0) [2023-03-09 08:10:39,062][22664] Avg episode reward: [(0, '51.953')] [2023-03-09 08:10:39,418][23090] Updated weights for policy 0, policy_version 32189 (0.0016) [2023-03-09 08:10:40,267][23090] Updated weights for policy 0, policy_version 32199 (0.0020) [2023-03-09 08:10:41,055][23090] Updated weights for policy 0, policy_version 32209 (0.0013) [2023-03-09 08:10:41,934][23090] Updated weights for policy 0, policy_version 32219 (0.0020) [2023-03-09 08:10:42,653][23090] Updated weights for policy 0, policy_version 32229 (0.0015) [2023-03-09 08:10:43,517][22940] Signal inference workers to stop experience collection... (10600 times) [2023-03-09 08:10:43,535][22940] Signal inference workers to resume experience collection... (10600 times) [2023-03-09 08:10:43,548][23090] Updated weights for policy 0, policy_version 32239 (0.0016) [2023-03-09 08:10:43,584][23090] InferenceWorker_p0-w0: stopping experience collection (10600 times) [2023-03-09 08:10:43,584][23090] InferenceWorker_p0-w0: resuming experience collection (10600 times) [2023-03-09 08:10:44,058][22664] Fps is (10 sec: 199884.0, 60 sec: 199611.9, 300 sec: 199274.0). Total num frames: 528302080. Throughput: 0: 49869.6. Samples: 132041408. Policy #0 lag: (min: 1.0, avg: 17.1, max: 33.0) [2023-03-09 08:10:44,059][22664] Avg episode reward: [(0, '49.021')] [2023-03-09 08:10:44,316][23090] Updated weights for policy 0, policy_version 32249 (0.0020) [2023-03-09 08:10:45,286][23090] Updated weights for policy 0, policy_version 32260 (0.0016) [2023-03-09 08:10:46,163][23090] Updated weights for policy 0, policy_version 32271 (0.0023) [2023-03-09 08:10:46,977][23090] Updated weights for policy 0, policy_version 32281 (0.0017) [2023-03-09 08:10:47,940][23090] Updated weights for policy 0, policy_version 32292 (0.0013) [2023-03-09 08:10:48,776][23090] Updated weights for policy 0, policy_version 32302 (0.0016) [2023-03-09 08:10:49,059][22664] Fps is (10 sec: 198253.4, 60 sec: 199065.4, 300 sec: 199218.3). Total num frames: 529285120. Throughput: 0: 49824.6. Samples: 132338336. Policy #0 lag: (min: 0.0, avg: 16.5, max: 33.0) [2023-03-09 08:10:49,060][22664] Avg episode reward: [(0, '51.487')] [2023-03-09 08:10:49,542][23090] Updated weights for policy 0, policy_version 32312 (0.0019) [2023-03-09 08:10:50,395][23090] Updated weights for policy 0, policy_version 32322 (0.0017) [2023-03-09 08:10:51,169][23090] Updated weights for policy 0, policy_version 32332 (0.0013) [2023-03-09 08:10:52,082][23090] Updated weights for policy 0, policy_version 32343 (0.0013) [2023-03-09 08:10:52,895][23090] Updated weights for policy 0, policy_version 32353 (0.0017) [2023-03-09 08:10:53,820][23090] Updated weights for policy 0, policy_version 32364 (0.0013) [2023-03-09 08:10:54,059][22664] Fps is (10 sec: 198245.2, 60 sec: 199072.4, 300 sec: 199274.0). Total num frames: 530284544. Throughput: 0: 49780.3. Samples: 132637312. Policy #0 lag: (min: 0.0, avg: 16.5, max: 33.0) [2023-03-09 08:10:54,060][22664] Avg episode reward: [(0, '51.128')] [2023-03-09 08:10:54,655][23090] Updated weights for policy 0, policy_version 32374 (0.0017) [2023-03-09 08:10:55,235][22940] Signal inference workers to stop experience collection... (10650 times) [2023-03-09 08:10:55,260][22940] Signal inference workers to resume experience collection... (10650 times) [2023-03-09 08:10:55,304][23090] InferenceWorker_p0-w0: stopping experience collection (10650 times) [2023-03-09 08:10:55,304][23090] InferenceWorker_p0-w0: resuming experience collection (10650 times) [2023-03-09 08:10:55,437][23090] Updated weights for policy 0, policy_version 32384 (0.0018) [2023-03-09 08:10:56,327][23090] Updated weights for policy 0, policy_version 32394 (0.0016) [2023-03-09 08:10:57,164][23090] Updated weights for policy 0, policy_version 32405 (0.0015) [2023-03-09 08:10:58,021][23090] Updated weights for policy 0, policy_version 32415 (0.0015) [2023-03-09 08:10:58,971][23090] Updated weights for policy 0, policy_version 32426 (0.0022) [2023-03-09 08:10:59,059][22664] Fps is (10 sec: 199878.6, 60 sec: 199337.5, 300 sec: 199273.8). Total num frames: 531283968. Throughput: 0: 49780.1. Samples: 132784752. Policy #0 lag: (min: 0.0, avg: 16.5, max: 33.0) [2023-03-09 08:10:59,061][22664] Avg episode reward: [(0, '51.588')] [2023-03-09 08:10:59,749][23090] Updated weights for policy 0, policy_version 32436 (0.0023) [2023-03-09 08:11:00,588][23090] Updated weights for policy 0, policy_version 32446 (0.0016) [2023-03-09 08:11:01,509][23090] Updated weights for policy 0, policy_version 32457 (0.0013) [2023-03-09 08:11:02,364][23090] Updated weights for policy 0, policy_version 32467 (0.0018) [2023-03-09 08:11:03,177][23090] Updated weights for policy 0, policy_version 32477 (0.0017) [2023-03-09 08:11:03,984][23090] Updated weights for policy 0, policy_version 32487 (0.0013) [2023-03-09 08:11:04,058][22664] Fps is (10 sec: 198247.8, 60 sec: 199066.5, 300 sec: 199218.3). Total num frames: 532267008. Throughput: 0: 49781.2. Samples: 133083696. Policy #0 lag: (min: 0.0, avg: 16.5, max: 33.0) [2023-03-09 08:11:04,059][22664] Avg episode reward: [(0, '53.457')] [2023-03-09 08:11:04,758][23090] Updated weights for policy 0, policy_version 32497 (0.0013) [2023-03-09 08:11:05,783][23090] Updated weights for policy 0, policy_version 32508 (0.0012) [2023-03-09 08:11:06,510][23090] Updated weights for policy 0, policy_version 32518 (0.0017) [2023-03-09 08:11:07,436][23090] Updated weights for policy 0, policy_version 32529 (0.0013) [2023-03-09 08:11:07,544][22940] Signal inference workers to stop experience collection... (10700 times) [2023-03-09 08:11:07,561][22940] Signal inference workers to resume experience collection... (10700 times) [2023-03-09 08:11:07,590][23090] InferenceWorker_p0-w0: stopping experience collection (10700 times) [2023-03-09 08:11:07,633][23090] InferenceWorker_p0-w0: resuming experience collection (10700 times) [2023-03-09 08:11:08,306][23090] Updated weights for policy 0, policy_version 32539 (0.0015) [2023-03-09 08:11:09,059][22664] Fps is (10 sec: 198247.1, 60 sec: 199064.7, 300 sec: 199218.2). Total num frames: 533266432. Throughput: 0: 49781.4. Samples: 133380640. Policy #0 lag: (min: 1.0, avg: 16.7, max: 32.0) [2023-03-09 08:11:09,061][22664] Avg episode reward: [(0, '54.042')] [2023-03-09 08:11:09,083][23090] Updated weights for policy 0, policy_version 32549 (0.0013) [2023-03-09 08:11:09,946][23090] Updated weights for policy 0, policy_version 32559 (0.0021) [2023-03-09 08:11:10,731][23090] Updated weights for policy 0, policy_version 32569 (0.0016) [2023-03-09 08:11:11,608][23090] Updated weights for policy 0, policy_version 32579 (0.0013) [2023-03-09 08:11:12,370][23090] Updated weights for policy 0, policy_version 32589 (0.0018) [2023-03-09 08:11:13,183][23090] Updated weights for policy 0, policy_version 32599 (0.0013) [2023-03-09 08:11:14,022][23090] Updated weights for policy 0, policy_version 32609 (0.0016) [2023-03-09 08:11:14,059][22664] Fps is (10 sec: 199883.5, 60 sec: 199066.2, 300 sec: 199218.5). Total num frames: 534265856. Throughput: 0: 49781.5. Samples: 133532176. Policy #0 lag: (min: 1.0, avg: 16.7, max: 32.0) [2023-03-09 08:11:14,060][22664] Avg episode reward: [(0, '51.947')] [2023-03-09 08:11:14,826][23090] Updated weights for policy 0, policy_version 32619 (0.0019) [2023-03-09 08:11:15,594][23090] Updated weights for policy 0, policy_version 32629 (0.0015) [2023-03-09 08:11:16,460][23090] Updated weights for policy 0, policy_version 32639 (0.0015) [2023-03-09 08:11:17,341][23090] Updated weights for policy 0, policy_version 32649 (0.0013) [2023-03-09 08:11:18,108][23090] Updated weights for policy 0, policy_version 32659 (0.0016) [2023-03-09 08:11:18,939][23090] Updated weights for policy 0, policy_version 32669 (0.0013) [2023-03-09 08:11:19,059][22664] Fps is (10 sec: 201523.9, 60 sec: 199338.2, 300 sec: 199329.2). Total num frames: 535281664. Throughput: 0: 49827.5. Samples: 133833168. Policy #0 lag: (min: 1.0, avg: 16.7, max: 32.0) [2023-03-09 08:11:19,062][22664] Avg episode reward: [(0, '52.938')] [2023-03-09 08:11:19,104][22940] Saving /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000032672_535298048.pth... [2023-03-09 08:11:19,161][22940] Removing /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000029752_487456768.pth [2023-03-09 08:11:19,414][22940] Signal inference workers to stop experience collection... (10750 times) [2023-03-09 08:11:19,418][22940] Signal inference workers to resume experience collection... (10750 times) [2023-03-09 08:11:19,488][23090] InferenceWorker_p0-w0: stopping experience collection (10750 times) [2023-03-09 08:11:19,488][23090] InferenceWorker_p0-w0: resuming experience collection (10750 times) [2023-03-09 08:11:19,727][23090] Updated weights for policy 0, policy_version 32679 (0.0016) [2023-03-09 08:11:20,532][23090] Updated weights for policy 0, policy_version 32689 (0.0013) [2023-03-09 08:11:21,371][23090] Updated weights for policy 0, policy_version 32699 (0.0013) [2023-03-09 08:11:22,182][23090] Updated weights for policy 0, policy_version 32709 (0.0016) [2023-03-09 08:11:23,031][23090] Updated weights for policy 0, policy_version 32719 (0.0016) [2023-03-09 08:11:23,806][23090] Updated weights for policy 0, policy_version 32729 (0.0013) [2023-03-09 08:11:24,059][22664] Fps is (10 sec: 199880.8, 60 sec: 199338.1, 300 sec: 199218.2). Total num frames: 536264704. Throughput: 0: 49827.4. Samples: 134132128. Policy #0 lag: (min: 1.0, avg: 16.7, max: 32.0) [2023-03-09 08:11:24,060][22664] Avg episode reward: [(0, '50.945')] [2023-03-09 08:11:24,771][23090] Updated weights for policy 0, policy_version 32740 (0.0016) [2023-03-09 08:11:25,655][23090] Updated weights for policy 0, policy_version 32750 (0.0025) [2023-03-09 08:11:26,396][23090] Updated weights for policy 0, policy_version 32760 (0.0019) [2023-03-09 08:11:27,240][23090] Updated weights for policy 0, policy_version 32770 (0.0013) [2023-03-09 08:11:28,046][23090] Updated weights for policy 0, policy_version 32780 (0.0015) [2023-03-09 08:11:28,855][23090] Updated weights for policy 0, policy_version 32790 (0.0013) [2023-03-09 08:11:29,059][22664] Fps is (10 sec: 198241.0, 60 sec: 199064.1, 300 sec: 199273.5). Total num frames: 537264128. Throughput: 0: 49736.6. Samples: 134279584. Policy #0 lag: (min: 0.0, avg: 16.9, max: 33.0) [2023-03-09 08:11:29,061][22664] Avg episode reward: [(0, '51.517')] [2023-03-09 08:11:29,765][23090] Updated weights for policy 0, policy_version 32801 (0.0013) [2023-03-09 08:11:30,589][23090] Updated weights for policy 0, policy_version 32811 (0.0019) [2023-03-09 08:11:31,190][22940] Signal inference workers to stop experience collection... (10800 times) [2023-03-09 08:11:31,201][22940] Signal inference workers to resume experience collection... (10800 times) [2023-03-09 08:11:31,232][23090] InferenceWorker_p0-w0: stopping experience collection (10800 times) [2023-03-09 08:11:31,299][23090] InferenceWorker_p0-w0: resuming experience collection (10800 times) [2023-03-09 08:11:31,538][23090] Updated weights for policy 0, policy_version 32822 (0.0016) [2023-03-09 08:11:32,317][23090] Updated weights for policy 0, policy_version 32832 (0.0023) [2023-03-09 08:11:33,152][23090] Updated weights for policy 0, policy_version 32842 (0.0015) [2023-03-09 08:11:33,963][23090] Updated weights for policy 0, policy_version 32852 (0.0015) [2023-03-09 08:11:34,059][22664] Fps is (10 sec: 199884.2, 60 sec: 199337.6, 300 sec: 199273.8). Total num frames: 538263552. Throughput: 0: 49827.7. Samples: 134580592. Policy #0 lag: (min: 0.0, avg: 16.9, max: 33.0) [2023-03-09 08:11:34,060][22664] Avg episode reward: [(0, '51.559')] [2023-03-09 08:11:34,779][23090] Updated weights for policy 0, policy_version 32862 (0.0016) [2023-03-09 08:11:35,647][23090] Updated weights for policy 0, policy_version 32872 (0.0013) [2023-03-09 08:11:36,504][23090] Updated weights for policy 0, policy_version 32882 (0.0013) [2023-03-09 08:11:37,300][23090] Updated weights for policy 0, policy_version 32892 (0.0020) [2023-03-09 08:11:38,029][23090] Updated weights for policy 0, policy_version 32902 (0.0013) [2023-03-09 08:11:38,913][23090] Updated weights for policy 0, policy_version 32912 (0.0013) [2023-03-09 08:11:39,059][22664] Fps is (10 sec: 198258.1, 60 sec: 199067.0, 300 sec: 199218.3). Total num frames: 539246592. Throughput: 0: 49781.4. Samples: 134877472. Policy #0 lag: (min: 0.0, avg: 16.9, max: 33.0) [2023-03-09 08:11:39,059][22664] Avg episode reward: [(0, '52.636')] [2023-03-09 08:11:39,736][23090] Updated weights for policy 0, policy_version 32922 (0.0017) [2023-03-09 08:11:40,615][23090] Updated weights for policy 0, policy_version 32932 (0.0017) [2023-03-09 08:11:41,487][23090] Updated weights for policy 0, policy_version 32943 (0.0019) [2023-03-09 08:11:42,291][23090] Updated weights for policy 0, policy_version 32953 (0.0013) [2023-03-09 08:11:43,250][23090] Updated weights for policy 0, policy_version 32964 (0.0022) [2023-03-09 08:11:44,059][22664] Fps is (10 sec: 198250.5, 60 sec: 199065.3, 300 sec: 199218.4). Total num frames: 540246016. Throughput: 0: 49781.3. Samples: 135024896. Policy #0 lag: (min: 0.0, avg: 16.9, max: 33.0) [2023-03-09 08:11:44,061][22664] Avg episode reward: [(0, '54.173')] [2023-03-09 08:11:44,062][23090] Updated weights for policy 0, policy_version 32974 (0.0015) [2023-03-09 08:11:44,474][22940] Signal inference workers to stop experience collection... (10850 times) [2023-03-09 08:11:44,490][22940] Signal inference workers to resume experience collection... (10850 times) [2023-03-09 08:11:44,542][23090] InferenceWorker_p0-w0: stopping experience collection (10850 times) [2023-03-09 08:11:44,543][23090] InferenceWorker_p0-w0: resuming experience collection (10850 times) [2023-03-09 08:11:44,912][23090] Updated weights for policy 0, policy_version 32984 (0.0019) [2023-03-09 08:11:45,732][23090] Updated weights for policy 0, policy_version 32994 (0.0013) [2023-03-09 08:11:46,538][23090] Updated weights for policy 0, policy_version 33004 (0.0016) [2023-03-09 08:11:47,345][23090] Updated weights for policy 0, policy_version 33014 (0.0021) [2023-03-09 08:11:48,127][23090] Updated weights for policy 0, policy_version 33024 (0.0013) [2023-03-09 08:11:49,009][23090] Updated weights for policy 0, policy_version 33034 (0.0013) [2023-03-09 08:11:49,059][22664] Fps is (10 sec: 198239.7, 60 sec: 199064.7, 300 sec: 199218.3). Total num frames: 541229056. Throughput: 0: 49780.6. Samples: 135323840. Policy #0 lag: (min: 0.0, avg: 16.9, max: 33.0) [2023-03-09 08:11:49,061][22664] Avg episode reward: [(0, '50.492')] [2023-03-09 08:11:49,890][23090] Updated weights for policy 0, policy_version 33045 (0.0016) [2023-03-09 08:11:50,713][23090] Updated weights for policy 0, policy_version 33055 (0.0017) [2023-03-09 08:11:51,670][23090] Updated weights for policy 0, policy_version 33066 (0.0013) [2023-03-09 08:11:52,470][23090] Updated weights for policy 0, policy_version 33076 (0.0022) [2023-03-09 08:11:53,289][23090] Updated weights for policy 0, policy_version 33086 (0.0017) [2023-03-09 08:11:54,059][22664] Fps is (10 sec: 198243.7, 60 sec: 199065.1, 300 sec: 199162.7). Total num frames: 542228480. Throughput: 0: 49781.5. Samples: 135620800. Policy #0 lag: (min: 1.0, avg: 16.6, max: 33.0) [2023-03-09 08:11:54,061][22664] Avg episode reward: [(0, '52.756')] [2023-03-09 08:11:54,139][23090] Updated weights for policy 0, policy_version 33096 (0.0016) [2023-03-09 08:11:55,018][23090] Updated weights for policy 0, policy_version 33106 (0.0013) [2023-03-09 08:11:55,848][23090] Updated weights for policy 0, policy_version 33116 (0.0016) [2023-03-09 08:11:56,544][23090] Updated weights for policy 0, policy_version 33126 (0.0019) [2023-03-09 08:11:57,367][22940] Signal inference workers to stop experience collection... (10900 times) [2023-03-09 08:11:57,382][22940] Signal inference workers to resume experience collection... (10900 times) [2023-03-09 08:11:57,433][23090] InferenceWorker_p0-w0: stopping experience collection (10900 times) [2023-03-09 08:11:57,436][23090] InferenceWorker_p0-w0: resuming experience collection (10900 times) [2023-03-09 08:11:57,439][23090] Updated weights for policy 0, policy_version 33136 (0.0013) [2023-03-09 08:11:58,308][23090] Updated weights for policy 0, policy_version 33146 (0.0013) [2023-03-09 08:11:59,059][22664] Fps is (10 sec: 196613.4, 60 sec: 198520.6, 300 sec: 199107.3). Total num frames: 543195136. Throughput: 0: 49735.4. Samples: 135770272. Policy #0 lag: (min: 1.0, avg: 16.6, max: 33.0) [2023-03-09 08:11:59,060][22664] Avg episode reward: [(0, '49.160')] [2023-03-09 08:11:59,161][23090] Updated weights for policy 0, policy_version 33156 (0.0013) [2023-03-09 08:12:00,009][23090] Updated weights for policy 0, policy_version 33166 (0.0018) [2023-03-09 08:12:00,807][23090] Updated weights for policy 0, policy_version 33176 (0.0016) [2023-03-09 08:12:01,676][23090] Updated weights for policy 0, policy_version 33186 (0.0029) [2023-03-09 08:12:02,414][23090] Updated weights for policy 0, policy_version 33196 (0.0016) [2023-03-09 08:12:03,281][23090] Updated weights for policy 0, policy_version 33206 (0.0013) [2023-03-09 08:12:04,059][23090] Updated weights for policy 0, policy_version 33216 (0.0013) [2023-03-09 08:12:04,059][22664] Fps is (10 sec: 198239.0, 60 sec: 199063.6, 300 sec: 199162.4). Total num frames: 544210944. Throughput: 0: 49553.9. Samples: 136063104. Policy #0 lag: (min: 1.0, avg: 16.6, max: 33.0) [2023-03-09 08:12:04,061][22664] Avg episode reward: [(0, '51.886')] [2023-03-09 08:12:04,936][23090] Updated weights for policy 0, policy_version 33226 (0.0013) [2023-03-09 08:12:05,722][23090] Updated weights for policy 0, policy_version 33236 (0.0020) [2023-03-09 08:12:06,528][23090] Updated weights for policy 0, policy_version 33246 (0.0017) [2023-03-09 08:12:07,400][23090] Updated weights for policy 0, policy_version 33256 (0.0016) [2023-03-09 08:12:08,266][23090] Updated weights for policy 0, policy_version 33266 (0.0013) [2023-03-09 08:12:09,034][23090] Updated weights for policy 0, policy_version 33276 (0.0018) [2023-03-09 08:12:09,058][22664] Fps is (10 sec: 199886.6, 60 sec: 198793.8, 300 sec: 199162.8). Total num frames: 545193984. Throughput: 0: 49600.3. Samples: 136364128. Policy #0 lag: (min: 1.0, avg: 16.6, max: 33.0) [2023-03-09 08:12:09,059][22664] Avg episode reward: [(0, '52.840')] [2023-03-09 08:12:09,812][23090] Updated weights for policy 0, policy_version 33286 (0.0013) [2023-03-09 08:12:10,191][22940] Signal inference workers to stop experience collection... (10950 times) [2023-03-09 08:12:10,192][22940] Signal inference workers to resume experience collection... (10950 times) [2023-03-09 08:12:10,252][23090] InferenceWorker_p0-w0: stopping experience collection (10950 times) [2023-03-09 08:12:10,252][23090] InferenceWorker_p0-w0: resuming experience collection (10950 times) [2023-03-09 08:12:10,626][23090] Updated weights for policy 0, policy_version 33296 (0.0013) [2023-03-09 08:12:11,447][23090] Updated weights for policy 0, policy_version 33306 (0.0013) [2023-03-09 08:12:12,333][23090] Updated weights for policy 0, policy_version 33316 (0.0017) [2023-03-09 08:12:13,137][23090] Updated weights for policy 0, policy_version 33326 (0.0015) [2023-03-09 08:12:13,997][23090] Updated weights for policy 0, policy_version 33336 (0.0017) [2023-03-09 08:12:14,059][22664] Fps is (10 sec: 198257.6, 60 sec: 198792.7, 300 sec: 199163.1). Total num frames: 546193408. Throughput: 0: 49645.4. Samples: 136513600. Policy #0 lag: (min: 0.0, avg: 16.7, max: 33.0) [2023-03-09 08:12:14,059][22664] Avg episode reward: [(0, '50.463')] [2023-03-09 08:12:14,786][23090] Updated weights for policy 0, policy_version 33346 (0.0016) [2023-03-09 08:12:15,604][23090] Updated weights for policy 0, policy_version 33356 (0.0020) [2023-03-09 08:12:16,397][23090] Updated weights for policy 0, policy_version 33366 (0.0013) [2023-03-09 08:12:17,203][23090] Updated weights for policy 0, policy_version 33376 (0.0020) [2023-03-09 08:12:18,079][23090] Updated weights for policy 0, policy_version 33386 (0.0013) [2023-03-09 08:12:18,845][23090] Updated weights for policy 0, policy_version 33396 (0.0016) [2023-03-09 08:12:19,059][22664] Fps is (10 sec: 199879.7, 60 sec: 198519.8, 300 sec: 199162.8). Total num frames: 547192832. Throughput: 0: 49599.3. Samples: 136812560. Policy #0 lag: (min: 0.0, avg: 16.7, max: 33.0) [2023-03-09 08:12:19,060][22664] Avg episode reward: [(0, '51.295')] [2023-03-09 08:12:19,662][23090] Updated weights for policy 0, policy_version 33406 (0.0021) [2023-03-09 08:12:20,527][23090] Updated weights for policy 0, policy_version 33416 (0.0015) [2023-03-09 08:12:21,392][23090] Updated weights for policy 0, policy_version 33426 (0.0019) [2023-03-09 08:12:22,204][23090] Updated weights for policy 0, policy_version 33436 (0.0013) [2023-03-09 08:12:22,212][22940] Signal inference workers to stop experience collection... (11000 times) [2023-03-09 08:12:22,224][22940] Signal inference workers to resume experience collection... (11000 times) [2023-03-09 08:12:22,284][23090] InferenceWorker_p0-w0: stopping experience collection (11000 times) [2023-03-09 08:12:22,284][23090] InferenceWorker_p0-w0: resuming experience collection (11000 times) [2023-03-09 08:12:22,927][23090] Updated weights for policy 0, policy_version 33446 (0.0017) [2023-03-09 08:12:23,770][23090] Updated weights for policy 0, policy_version 33456 (0.0017) [2023-03-09 08:12:24,059][22664] Fps is (10 sec: 199878.3, 60 sec: 198792.2, 300 sec: 199162.8). Total num frames: 548192256. Throughput: 0: 49645.5. Samples: 137111536. Policy #0 lag: (min: 0.0, avg: 16.7, max: 33.0) [2023-03-09 08:12:24,061][22664] Avg episode reward: [(0, '50.745')] [2023-03-09 08:12:24,574][23090] Updated weights for policy 0, policy_version 33466 (0.0016) [2023-03-09 08:12:25,450][23090] Updated weights for policy 0, policy_version 33476 (0.0015) [2023-03-09 08:12:26,314][23090] Updated weights for policy 0, policy_version 33486 (0.0013) [2023-03-09 08:12:27,142][23090] Updated weights for policy 0, policy_version 33496 (0.0016) [2023-03-09 08:12:27,917][23090] Updated weights for policy 0, policy_version 33506 (0.0013) [2023-03-09 08:12:28,824][23090] Updated weights for policy 0, policy_version 33517 (0.0016) [2023-03-09 08:12:29,059][22664] Fps is (10 sec: 199883.1, 60 sec: 198793.5, 300 sec: 199218.1). Total num frames: 549191680. Throughput: 0: 49690.4. Samples: 137260976. Policy #0 lag: (min: 0.0, avg: 16.7, max: 33.0) [2023-03-09 08:12:29,061][22664] Avg episode reward: [(0, '52.852')] [2023-03-09 08:12:29,591][23090] Updated weights for policy 0, policy_version 33527 (0.0013) [2023-03-09 08:12:30,427][23090] Updated weights for policy 0, policy_version 33537 (0.0018) [2023-03-09 08:12:31,274][23090] Updated weights for policy 0, policy_version 33547 (0.0017) [2023-03-09 08:12:32,132][23090] Updated weights for policy 0, policy_version 33557 (0.0013) [2023-03-09 08:12:32,855][23090] Updated weights for policy 0, policy_version 33567 (0.0013) [2023-03-09 08:12:33,835][23090] Updated weights for policy 0, policy_version 33578 (0.0021) [2023-03-09 08:12:34,059][22664] Fps is (10 sec: 199890.6, 60 sec: 198793.3, 300 sec: 199273.8). Total num frames: 550191104. Throughput: 0: 49736.2. Samples: 137561952. Policy #0 lag: (min: 0.0, avg: 17.0, max: 33.0) [2023-03-09 08:12:34,060][22664] Avg episode reward: [(0, '49.602')] [2023-03-09 08:12:34,453][22940] Signal inference workers to stop experience collection... (11050 times) [2023-03-09 08:12:34,454][22940] Signal inference workers to resume experience collection... (11050 times) [2023-03-09 08:12:34,518][23090] InferenceWorker_p0-w0: stopping experience collection (11050 times) [2023-03-09 08:12:34,521][23090] InferenceWorker_p0-w0: resuming experience collection (11050 times) [2023-03-09 08:12:34,567][23090] Updated weights for policy 0, policy_version 33588 (0.0013) [2023-03-09 08:12:35,410][23090] Updated weights for policy 0, policy_version 33598 (0.0013) [2023-03-09 08:12:36,258][23090] Updated weights for policy 0, policy_version 33608 (0.0013) [2023-03-09 08:12:37,125][23090] Updated weights for policy 0, policy_version 33618 (0.0015) [2023-03-09 08:12:37,892][23090] Updated weights for policy 0, policy_version 33628 (0.0018) [2023-03-09 08:12:38,650][23090] Updated weights for policy 0, policy_version 33638 (0.0013) [2023-03-09 08:12:39,059][22664] Fps is (10 sec: 199886.9, 60 sec: 199064.9, 300 sec: 199273.9). Total num frames: 551190528. Throughput: 0: 49778.8. Samples: 137860848. Policy #0 lag: (min: 0.0, avg: 17.0, max: 33.0) [2023-03-09 08:12:39,060][22664] Avg episode reward: [(0, '49.622')] [2023-03-09 08:12:39,503][23090] Updated weights for policy 0, policy_version 33648 (0.0013) [2023-03-09 08:12:40,350][23090] Updated weights for policy 0, policy_version 33658 (0.0020) [2023-03-09 08:12:41,217][23090] Updated weights for policy 0, policy_version 33668 (0.0016) [2023-03-09 08:12:42,023][23090] Updated weights for policy 0, policy_version 33678 (0.0014) [2023-03-09 08:12:42,823][23090] Updated weights for policy 0, policy_version 33688 (0.0016) [2023-03-09 08:12:43,607][23090] Updated weights for policy 0, policy_version 33698 (0.0018) [2023-03-09 08:12:44,059][22664] Fps is (10 sec: 199885.2, 60 sec: 199065.8, 300 sec: 199273.8). Total num frames: 552189952. Throughput: 0: 49824.8. Samples: 138012384. Policy #0 lag: (min: 0.0, avg: 17.0, max: 33.0) [2023-03-09 08:12:44,060][22664] Avg episode reward: [(0, '52.376')] [2023-03-09 08:12:44,417][23090] Updated weights for policy 0, policy_version 33708 (0.0018) [2023-03-09 08:12:45,252][23090] Updated weights for policy 0, policy_version 33718 (0.0017) [2023-03-09 08:12:46,010][23090] Updated weights for policy 0, policy_version 33728 (0.0024) [2023-03-09 08:12:46,914][23090] Updated weights for policy 0, policy_version 33738 (0.0016) [2023-03-09 08:12:47,655][23090] Updated weights for policy 0, policy_version 33748 (0.0015) [2023-03-09 08:12:47,792][22940] Signal inference workers to stop experience collection... (11100 times) [2023-03-09 08:12:47,793][22940] Signal inference workers to resume experience collection... (11100 times) [2023-03-09 08:12:47,852][23090] InferenceWorker_p0-w0: stopping experience collection (11100 times) [2023-03-09 08:12:47,852][23090] InferenceWorker_p0-w0: resuming experience collection (11100 times) [2023-03-09 08:12:48,482][23090] Updated weights for policy 0, policy_version 33758 (0.0019) [2023-03-09 08:12:49,059][22664] Fps is (10 sec: 199882.6, 60 sec: 199338.7, 300 sec: 199273.7). Total num frames: 553189376. Throughput: 0: 50007.0. Samples: 138313408. Policy #0 lag: (min: 0.0, avg: 17.0, max: 33.0) [2023-03-09 08:12:49,061][22664] Avg episode reward: [(0, '51.965')] [2023-03-09 08:12:49,367][23090] Updated weights for policy 0, policy_version 33768 (0.0013) [2023-03-09 08:12:50,218][23090] Updated weights for policy 0, policy_version 33778 (0.0029) [2023-03-09 08:12:51,020][23090] Updated weights for policy 0, policy_version 33788 (0.0018) [2023-03-09 08:12:51,743][23090] Updated weights for policy 0, policy_version 33798 (0.0013) [2023-03-09 08:12:52,595][23090] Updated weights for policy 0, policy_version 33808 (0.0018) [2023-03-09 08:12:53,441][23090] Updated weights for policy 0, policy_version 33818 (0.0017) [2023-03-09 08:12:54,059][22664] Fps is (10 sec: 199880.3, 60 sec: 199338.5, 300 sec: 199329.5). Total num frames: 554188800. Throughput: 0: 49960.9. Samples: 138612384. Policy #0 lag: (min: 0.0, avg: 17.0, max: 33.0) [2023-03-09 08:12:54,061][22664] Avg episode reward: [(0, '51.604')] [2023-03-09 08:12:54,277][23090] Updated weights for policy 0, policy_version 33828 (0.0013) [2023-03-09 08:12:55,076][23090] Updated weights for policy 0, policy_version 33838 (0.0013) [2023-03-09 08:12:55,878][23090] Updated weights for policy 0, policy_version 33848 (0.0018) [2023-03-09 08:12:56,746][23090] Updated weights for policy 0, policy_version 33858 (0.0013) [2023-03-09 08:12:57,521][23090] Updated weights for policy 0, policy_version 33868 (0.0017) [2023-03-09 08:12:58,358][23090] Updated weights for policy 0, policy_version 33878 (0.0017) [2023-03-09 08:12:59,059][22664] Fps is (10 sec: 201529.6, 60 sec: 200158.1, 300 sec: 199385.0). Total num frames: 555204608. Throughput: 0: 50006.8. Samples: 138763904. Policy #0 lag: (min: 0.0, avg: 16.6, max: 32.0) [2023-03-09 08:12:59,059][22664] Avg episode reward: [(0, '52.101')] [2023-03-09 08:12:59,232][23090] Updated weights for policy 0, policy_version 33889 (0.0017) [2023-03-09 08:13:00,083][23090] Updated weights for policy 0, policy_version 33899 (0.0013) [2023-03-09 08:13:00,734][22940] Signal inference workers to stop experience collection... (11150 times) [2023-03-09 08:13:00,735][22940] Signal inference workers to resume experience collection... (11150 times) [2023-03-09 08:13:00,805][23090] InferenceWorker_p0-w0: stopping experience collection (11150 times) [2023-03-09 08:13:00,805][23090] InferenceWorker_p0-w0: resuming experience collection (11150 times) [2023-03-09 08:13:00,887][23090] Updated weights for policy 0, policy_version 33909 (0.0013) [2023-03-09 08:13:01,689][23090] Updated weights for policy 0, policy_version 33919 (0.0016) [2023-03-09 08:13:02,586][23090] Updated weights for policy 0, policy_version 33929 (0.0013) [2023-03-09 08:13:03,360][23090] Updated weights for policy 0, policy_version 33939 (0.0013) [2023-03-09 08:13:04,059][22664] Fps is (10 sec: 199884.1, 60 sec: 199612.7, 300 sec: 199273.6). Total num frames: 556187648. Throughput: 0: 49961.2. Samples: 139060816. Policy #0 lag: (min: 0.0, avg: 16.6, max: 32.0) [2023-03-09 08:13:04,061][22664] Avg episode reward: [(0, '52.221')] [2023-03-09 08:13:04,174][23090] Updated weights for policy 0, policy_version 33949 (0.0020) [2023-03-09 08:13:05,013][23090] Updated weights for policy 0, policy_version 33959 (0.0018) [2023-03-09 08:13:05,752][23090] Updated weights for policy 0, policy_version 33969 (0.0013) [2023-03-09 08:13:06,625][23090] Updated weights for policy 0, policy_version 33979 (0.0013) [2023-03-09 08:13:07,433][23090] Updated weights for policy 0, policy_version 33989 (0.0020) [2023-03-09 08:13:08,235][23090] Updated weights for policy 0, policy_version 33999 (0.0019) [2023-03-09 08:13:09,059][22664] Fps is (10 sec: 199884.6, 60 sec: 200157.7, 300 sec: 199385.1). Total num frames: 557203456. Throughput: 0: 50052.6. Samples: 139363888. Policy #0 lag: (min: 0.0, avg: 16.6, max: 32.0) [2023-03-09 08:13:09,060][22664] Avg episode reward: [(0, '51.781')] [2023-03-09 08:13:09,068][23090] Updated weights for policy 0, policy_version 34009 (0.0018) [2023-03-09 08:13:09,953][23090] Updated weights for policy 0, policy_version 34019 (0.0017) [2023-03-09 08:13:10,749][23090] Updated weights for policy 0, policy_version 34029 (0.0017) [2023-03-09 08:13:11,533][23090] Updated weights for policy 0, policy_version 34039 (0.0013) [2023-03-09 08:13:12,374][23090] Updated weights for policy 0, policy_version 34049 (0.0019) [2023-03-09 08:13:13,171][23090] Updated weights for policy 0, policy_version 34059 (0.0015) [2023-03-09 08:13:14,003][23090] Updated weights for policy 0, policy_version 34069 (0.0022) [2023-03-09 08:13:14,059][22664] Fps is (10 sec: 201526.3, 60 sec: 200157.5, 300 sec: 199385.1). Total num frames: 558202880. Throughput: 0: 50008.4. Samples: 139511344. Policy #0 lag: (min: 0.0, avg: 16.6, max: 32.0) [2023-03-09 08:13:14,060][22664] Avg episode reward: [(0, '53.335')] [2023-03-09 08:13:14,796][23090] Updated weights for policy 0, policy_version 34079 (0.0022) [2023-03-09 08:13:15,119][22940] Signal inference workers to stop experience collection... (11200 times) [2023-03-09 08:13:15,121][22940] Signal inference workers to resume experience collection... (11200 times) [2023-03-09 08:13:15,200][23090] InferenceWorker_p0-w0: stopping experience collection (11200 times) [2023-03-09 08:13:15,206][23090] InferenceWorker_p0-w0: resuming experience collection (11200 times) [2023-03-09 08:13:15,734][23090] Updated weights for policy 0, policy_version 34090 (0.0021) [2023-03-09 08:13:16,495][23090] Updated weights for policy 0, policy_version 34100 (0.0025) [2023-03-09 08:13:17,314][23090] Updated weights for policy 0, policy_version 34110 (0.0021) [2023-03-09 08:13:18,209][23090] Updated weights for policy 0, policy_version 34120 (0.0013) [2023-03-09 08:13:19,053][23090] Updated weights for policy 0, policy_version 34131 (0.0013) [2023-03-09 08:13:19,059][22664] Fps is (10 sec: 199877.3, 60 sec: 200157.3, 300 sec: 199440.3). Total num frames: 559202304. Throughput: 0: 50008.5. Samples: 139812352. Policy #0 lag: (min: 1.0, avg: 16.8, max: 33.0) [2023-03-09 08:13:19,061][22664] Avg episode reward: [(0, '53.751')] [2023-03-09 08:13:19,095][22940] Saving /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000034132_559218688.pth... [2023-03-09 08:13:19,162][22940] Removing /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000031211_511361024.pth [2023-03-09 08:13:19,873][23090] Updated weights for policy 0, policy_version 34141 (0.0023) [2023-03-09 08:13:20,736][23090] Updated weights for policy 0, policy_version 34151 (0.0013) [2023-03-09 08:13:21,493][23090] Updated weights for policy 0, policy_version 34161 (0.0018) [2023-03-09 08:13:22,325][23090] Updated weights for policy 0, policy_version 34171 (0.0013) [2023-03-09 08:13:23,122][23090] Updated weights for policy 0, policy_version 34181 (0.0025) [2023-03-09 08:13:23,969][23090] Updated weights for policy 0, policy_version 34191 (0.0023) [2023-03-09 08:13:24,059][22664] Fps is (10 sec: 199881.7, 60 sec: 200158.0, 300 sec: 199384.8). Total num frames: 560201728. Throughput: 0: 50054.7. Samples: 140113312. Policy #0 lag: (min: 1.0, avg: 16.8, max: 33.0) [2023-03-09 08:13:24,060][22664] Avg episode reward: [(0, '54.282')] [2023-03-09 08:13:24,773][23090] Updated weights for policy 0, policy_version 34201 (0.0017) [2023-03-09 08:13:25,682][23090] Updated weights for policy 0, policy_version 34212 (0.0021) [2023-03-09 08:13:26,561][23090] Updated weights for policy 0, policy_version 34222 (0.0015) [2023-03-09 08:13:27,308][23090] Updated weights for policy 0, policy_version 34232 (0.0013) [2023-03-09 08:13:28,155][23090] Updated weights for policy 0, policy_version 34242 (0.0027) [2023-03-09 08:13:28,288][22940] Signal inference workers to stop experience collection... (11250 times) [2023-03-09 08:13:28,289][22940] Signal inference workers to resume experience collection... (11250 times) [2023-03-09 08:13:28,353][23090] InferenceWorker_p0-w0: stopping experience collection (11250 times) [2023-03-09 08:13:28,353][23090] InferenceWorker_p0-w0: resuming experience collection (11250 times) [2023-03-09 08:13:29,029][23090] Updated weights for policy 0, policy_version 34253 (0.0025) [2023-03-09 08:13:29,059][22664] Fps is (10 sec: 199892.4, 60 sec: 200158.9, 300 sec: 199385.3). Total num frames: 561201152. Throughput: 0: 50054.1. Samples: 140264816. Policy #0 lag: (min: 1.0, avg: 16.8, max: 33.0) [2023-03-09 08:13:29,059][22664] Avg episode reward: [(0, '53.547')] [2023-03-09 08:13:29,800][23090] Updated weights for policy 0, policy_version 34263 (0.0017) [2023-03-09 08:13:30,635][23090] Updated weights for policy 0, policy_version 34273 (0.0013) [2023-03-09 08:13:31,481][23090] Updated weights for policy 0, policy_version 34283 (0.0016) [2023-03-09 08:13:32,323][23090] Updated weights for policy 0, policy_version 34293 (0.0023) [2023-03-09 08:13:33,131][23090] Updated weights for policy 0, policy_version 34303 (0.0016) [2023-03-09 08:13:33,984][23090] Updated weights for policy 0, policy_version 34313 (0.0023) [2023-03-09 08:13:34,059][22664] Fps is (10 sec: 199886.0, 60 sec: 200157.3, 300 sec: 199440.5). Total num frames: 562200576. Throughput: 0: 50008.3. Samples: 140563776. Policy #0 lag: (min: 1.0, avg: 16.8, max: 33.0) [2023-03-09 08:13:34,061][22664] Avg episode reward: [(0, '51.812')] [2023-03-09 08:13:34,744][23090] Updated weights for policy 0, policy_version 34323 (0.0013) [2023-03-09 08:13:35,574][23090] Updated weights for policy 0, policy_version 34333 (0.0017) [2023-03-09 08:13:36,427][23090] Updated weights for policy 0, policy_version 34343 (0.0019) [2023-03-09 08:13:37,227][23090] Updated weights for policy 0, policy_version 34353 (0.0015) [2023-03-09 08:13:38,033][23090] Updated weights for policy 0, policy_version 34363 (0.0024) [2023-03-09 08:13:38,807][23090] Updated weights for policy 0, policy_version 34373 (0.0020) [2023-03-09 08:13:39,059][22664] Fps is (10 sec: 199881.5, 60 sec: 200158.0, 300 sec: 199440.4). Total num frames: 563200000. Throughput: 0: 50054.5. Samples: 140864832. Policy #0 lag: (min: 1.0, avg: 17.0, max: 33.0) [2023-03-09 08:13:39,060][22664] Avg episode reward: [(0, '52.829')] [2023-03-09 08:13:39,701][23090] Updated weights for policy 0, policy_version 34383 (0.0013) [2023-03-09 08:13:40,517][23090] Updated weights for policy 0, policy_version 34393 (0.0019) [2023-03-09 08:13:41,362][23090] Updated weights for policy 0, policy_version 34403 (0.0016) [2023-03-09 08:13:42,153][23090] Updated weights for policy 0, policy_version 34413 (0.0018) [2023-03-09 08:13:42,805][22940] Signal inference workers to stop experience collection... (11300 times) [2023-03-09 08:13:42,806][22940] Signal inference workers to resume experience collection... (11300 times) [2023-03-09 08:13:42,868][23090] InferenceWorker_p0-w0: stopping experience collection (11300 times) [2023-03-09 08:13:42,868][23090] InferenceWorker_p0-w0: resuming experience collection (11300 times) [2023-03-09 08:13:42,915][23090] Updated weights for policy 0, policy_version 34423 (0.0019) [2023-03-09 08:13:43,792][23090] Updated weights for policy 0, policy_version 34433 (0.0015) [2023-03-09 08:13:44,059][22664] Fps is (10 sec: 199889.1, 60 sec: 200157.9, 300 sec: 199385.1). Total num frames: 564199424. Throughput: 0: 50008.9. Samples: 141014304. Policy #0 lag: (min: 1.0, avg: 17.0, max: 33.0) [2023-03-09 08:13:44,060][22664] Avg episode reward: [(0, '51.201')] [2023-03-09 08:13:44,599][23090] Updated weights for policy 0, policy_version 34443 (0.0016) [2023-03-09 08:13:45,415][23090] Updated weights for policy 0, policy_version 34453 (0.0020) [2023-03-09 08:13:46,231][23090] Updated weights for policy 0, policy_version 34463 (0.0016) [2023-03-09 08:13:47,149][23090] Updated weights for policy 0, policy_version 34473 (0.0015) [2023-03-09 08:13:47,876][23090] Updated weights for policy 0, policy_version 34483 (0.0017) [2023-03-09 08:13:48,761][23090] Updated weights for policy 0, policy_version 34493 (0.0020) [2023-03-09 08:13:49,059][22664] Fps is (10 sec: 199887.2, 60 sec: 200158.8, 300 sec: 199440.6). Total num frames: 565198848. Throughput: 0: 50100.9. Samples: 141315344. Policy #0 lag: (min: 1.0, avg: 17.0, max: 33.0) [2023-03-09 08:13:49,060][22664] Avg episode reward: [(0, '49.825')] [2023-03-09 08:13:49,563][23090] Updated weights for policy 0, policy_version 34503 (0.0020) [2023-03-09 08:13:50,354][23090] Updated weights for policy 0, policy_version 34513 (0.0023) [2023-03-09 08:13:51,175][23090] Updated weights for policy 0, policy_version 34523 (0.0013) [2023-03-09 08:13:51,982][23090] Updated weights for policy 0, policy_version 34533 (0.0013) [2023-03-09 08:13:52,853][23090] Updated weights for policy 0, policy_version 34544 (0.0017) [2023-03-09 08:13:53,714][23090] Updated weights for policy 0, policy_version 34554 (0.0016) [2023-03-09 08:13:54,059][22664] Fps is (10 sec: 199879.6, 60 sec: 200157.8, 300 sec: 199440.5). Total num frames: 566198272. Throughput: 0: 49963.8. Samples: 141612272. Policy #0 lag: (min: 1.0, avg: 17.0, max: 33.0) [2023-03-09 08:13:54,060][22664] Avg episode reward: [(0, '51.879')] [2023-03-09 08:13:54,565][23090] Updated weights for policy 0, policy_version 34564 (0.0013) [2023-03-09 08:13:55,401][23090] Updated weights for policy 0, policy_version 34574 (0.0013) [2023-03-09 08:13:56,174][23090] Updated weights for policy 0, policy_version 34584 (0.0016) [2023-03-09 08:13:57,035][23090] Updated weights for policy 0, policy_version 34594 (0.0015) [2023-03-09 08:13:57,805][23090] Updated weights for policy 0, policy_version 34604 (0.0020) [2023-03-09 08:13:57,995][22940] Signal inference workers to stop experience collection... (11350 times) [2023-03-09 08:13:58,014][22940] Signal inference workers to resume experience collection... (11350 times) [2023-03-09 08:13:58,041][23090] InferenceWorker_p0-w0: stopping experience collection (11350 times) [2023-03-09 08:13:58,087][23090] InferenceWorker_p0-w0: resuming experience collection (11350 times) [2023-03-09 08:13:58,606][23090] Updated weights for policy 0, policy_version 34614 (0.0015) [2023-03-09 08:13:59,059][22664] Fps is (10 sec: 199869.9, 60 sec: 199882.2, 300 sec: 199440.3). Total num frames: 567197696. Throughput: 0: 50008.1. Samples: 141761744. Policy #0 lag: (min: 1.0, avg: 17.0, max: 33.0) [2023-03-09 08:13:59,062][22664] Avg episode reward: [(0, '49.433')] [2023-03-09 08:13:59,382][23090] Updated weights for policy 0, policy_version 34624 (0.0014) [2023-03-09 08:14:00,289][23090] Updated weights for policy 0, policy_version 34634 (0.0026) [2023-03-09 08:14:01,033][23090] Updated weights for policy 0, policy_version 34644 (0.0020) [2023-03-09 08:14:01,908][23090] Updated weights for policy 0, policy_version 34654 (0.0018) [2023-03-09 08:14:02,758][23090] Updated weights for policy 0, policy_version 34664 (0.0013) [2023-03-09 08:14:03,593][23090] Updated weights for policy 0, policy_version 34674 (0.0013) [2023-03-09 08:14:04,059][22664] Fps is (10 sec: 199885.8, 60 sec: 200158.1, 300 sec: 199496.1). Total num frames: 568197120. Throughput: 0: 50010.1. Samples: 142062800. Policy #0 lag: (min: 0.0, avg: 16.2, max: 32.0) [2023-03-09 08:14:04,060][22664] Avg episode reward: [(0, '53.284')] [2023-03-09 08:14:04,360][23090] Updated weights for policy 0, policy_version 34684 (0.0016) [2023-03-09 08:14:05,121][23090] Updated weights for policy 0, policy_version 34694 (0.0014) [2023-03-09 08:14:05,984][23090] Updated weights for policy 0, policy_version 34704 (0.0018) [2023-03-09 08:14:06,832][23090] Updated weights for policy 0, policy_version 34714 (0.0020) [2023-03-09 08:14:07,645][23090] Updated weights for policy 0, policy_version 34724 (0.0013) [2023-03-09 08:14:08,505][23090] Updated weights for policy 0, policy_version 34734 (0.0021) [2023-03-09 08:14:09,059][22664] Fps is (10 sec: 199895.9, 60 sec: 199884.0, 300 sec: 199495.9). Total num frames: 569196544. Throughput: 0: 50010.0. Samples: 142363760. Policy #0 lag: (min: 0.0, avg: 16.2, max: 32.0) [2023-03-09 08:14:09,061][22664] Avg episode reward: [(0, '52.367')] [2023-03-09 08:14:09,265][23090] Updated weights for policy 0, policy_version 34744 (0.0013) [2023-03-09 08:14:10,132][23090] Updated weights for policy 0, policy_version 34754 (0.0017) [2023-03-09 08:14:10,923][23090] Updated weights for policy 0, policy_version 34764 (0.0013) [2023-03-09 08:14:11,731][23090] Updated weights for policy 0, policy_version 34774 (0.0019) [2023-03-09 08:14:12,532][23090] Updated weights for policy 0, policy_version 34784 (0.0019) [2023-03-09 08:14:13,429][23090] Updated weights for policy 0, policy_version 34794 (0.0013) [2023-03-09 08:14:13,798][22940] Signal inference workers to stop experience collection... (11400 times) [2023-03-09 08:14:13,817][22940] Signal inference workers to resume experience collection... (11400 times) [2023-03-09 08:14:13,843][23090] InferenceWorker_p0-w0: stopping experience collection (11400 times) [2023-03-09 08:14:13,882][23090] InferenceWorker_p0-w0: resuming experience collection (11400 times) [2023-03-09 08:14:14,059][22664] Fps is (10 sec: 198245.5, 60 sec: 199611.3, 300 sec: 199495.9). Total num frames: 570179584. Throughput: 0: 49963.4. Samples: 142513184. Policy #0 lag: (min: 0.0, avg: 16.2, max: 32.0) [2023-03-09 08:14:14,061][22664] Avg episode reward: [(0, '53.513')] [2023-03-09 08:14:14,177][23090] Updated weights for policy 0, policy_version 34804 (0.0017) [2023-03-09 08:14:15,033][23090] Updated weights for policy 0, policy_version 34814 (0.0013) [2023-03-09 08:14:15,916][23090] Updated weights for policy 0, policy_version 34824 (0.0018) [2023-03-09 08:14:16,795][23090] Updated weights for policy 0, policy_version 34835 (0.0016) [2023-03-09 08:14:17,608][23090] Updated weights for policy 0, policy_version 34845 (0.0019) [2023-03-09 08:14:18,447][23090] Updated weights for policy 0, policy_version 34855 (0.0016) [2023-03-09 08:14:19,059][22664] Fps is (10 sec: 198245.3, 60 sec: 199612.0, 300 sec: 199440.4). Total num frames: 571179008. Throughput: 0: 49918.5. Samples: 142810112. Policy #0 lag: (min: 0.0, avg: 16.2, max: 32.0) [2023-03-09 08:14:19,061][22664] Avg episode reward: [(0, '52.979')] [2023-03-09 08:14:19,217][23090] Updated weights for policy 0, policy_version 34865 (0.0013) [2023-03-09 08:14:20,090][23090] Updated weights for policy 0, policy_version 34875 (0.0013) [2023-03-09 08:14:20,830][23090] Updated weights for policy 0, policy_version 34885 (0.0016) [2023-03-09 08:14:21,714][23090] Updated weights for policy 0, policy_version 34895 (0.0016) [2023-03-09 08:14:22,550][23090] Updated weights for policy 0, policy_version 34905 (0.0016) [2023-03-09 08:14:23,405][23090] Updated weights for policy 0, policy_version 34915 (0.0016) [2023-03-09 08:14:24,059][22664] Fps is (10 sec: 201522.8, 60 sec: 199884.8, 300 sec: 199551.4). Total num frames: 572194816. Throughput: 0: 49918.1. Samples: 143111152. Policy #0 lag: (min: 0.0, avg: 16.9, max: 33.0) [2023-03-09 08:14:24,061][22664] Avg episode reward: [(0, '49.815')] [2023-03-09 08:14:24,204][23090] Updated weights for policy 0, policy_version 34925 (0.0028) [2023-03-09 08:14:24,967][23090] Updated weights for policy 0, policy_version 34935 (0.0013) [2023-03-09 08:14:25,788][23090] Updated weights for policy 0, policy_version 34945 (0.0025) [2023-03-09 08:14:26,639][23090] Updated weights for policy 0, policy_version 34955 (0.0017) [2023-03-09 08:14:27,416][23090] Updated weights for policy 0, policy_version 34965 (0.0019) [2023-03-09 08:14:28,304][23090] Updated weights for policy 0, policy_version 34976 (0.0016) [2023-03-09 08:14:28,560][22940] Signal inference workers to stop experience collection... (11450 times) [2023-03-09 08:14:28,561][22940] Signal inference workers to resume experience collection... (11450 times) [2023-03-09 08:14:28,626][23090] InferenceWorker_p0-w0: stopping experience collection (11450 times) [2023-03-09 08:14:28,626][23090] InferenceWorker_p0-w0: resuming experience collection (11450 times) [2023-03-09 08:14:29,059][22664] Fps is (10 sec: 199890.1, 60 sec: 199611.6, 300 sec: 199440.4). Total num frames: 573177856. Throughput: 0: 49917.1. Samples: 143260576. Policy #0 lag: (min: 0.0, avg: 16.9, max: 33.0) [2023-03-09 08:14:29,059][22664] Avg episode reward: [(0, '51.933')] [2023-03-09 08:14:29,191][23090] Updated weights for policy 0, policy_version 34986 (0.0014) [2023-03-09 08:14:29,950][23090] Updated weights for policy 0, policy_version 34996 (0.0013) [2023-03-09 08:14:30,804][23090] Updated weights for policy 0, policy_version 35006 (0.0016) [2023-03-09 08:14:31,707][23090] Updated weights for policy 0, policy_version 35016 (0.0017) [2023-03-09 08:14:32,517][23090] Updated weights for policy 0, policy_version 35027 (0.0017) [2023-03-09 08:14:33,345][23090] Updated weights for policy 0, policy_version 35037 (0.0019) [2023-03-09 08:14:34,059][22664] Fps is (10 sec: 199888.1, 60 sec: 199885.1, 300 sec: 199496.1). Total num frames: 574193664. Throughput: 0: 49870.5. Samples: 143559520. Policy #0 lag: (min: 0.0, avg: 16.9, max: 33.0) [2023-03-09 08:14:34,060][22664] Avg episode reward: [(0, '51.210')] [2023-03-09 08:14:34,239][23090] Updated weights for policy 0, policy_version 35047 (0.0017) [2023-03-09 08:14:34,957][23090] Updated weights for policy 0, policy_version 35057 (0.0026) [2023-03-09 08:14:35,889][23090] Updated weights for policy 0, policy_version 35067 (0.0018) [2023-03-09 08:14:36,643][23090] Updated weights for policy 0, policy_version 35077 (0.0013) [2023-03-09 08:14:37,481][23090] Updated weights for policy 0, policy_version 35087 (0.0015) [2023-03-09 08:14:38,273][23090] Updated weights for policy 0, policy_version 35097 (0.0016) [2023-03-09 08:14:39,059][22664] Fps is (10 sec: 199884.2, 60 sec: 199612.1, 300 sec: 199496.0). Total num frames: 575176704. Throughput: 0: 49916.3. Samples: 143858496. Policy #0 lag: (min: 0.0, avg: 16.9, max: 33.0) [2023-03-09 08:14:39,060][22664] Avg episode reward: [(0, '51.194')] [2023-03-09 08:14:39,186][23090] Updated weights for policy 0, policy_version 35107 (0.0016) [2023-03-09 08:14:39,955][23090] Updated weights for policy 0, policy_version 35117 (0.0013) [2023-03-09 08:14:40,030][22940] Signal inference workers to stop experience collection... (11500 times) [2023-03-09 08:14:40,042][22940] Signal inference workers to resume experience collection... (11500 times) [2023-03-09 08:14:40,071][23090] InferenceWorker_p0-w0: stopping experience collection (11500 times) [2023-03-09 08:14:40,114][23090] InferenceWorker_p0-w0: resuming experience collection (11500 times) [2023-03-09 08:14:40,725][23090] Updated weights for policy 0, policy_version 35127 (0.0016) [2023-03-09 08:14:41,551][23090] Updated weights for policy 0, policy_version 35137 (0.0013) [2023-03-09 08:14:42,381][23090] Updated weights for policy 0, policy_version 35147 (0.0019) [2023-03-09 08:14:43,180][23090] Updated weights for policy 0, policy_version 35157 (0.0022) [2023-03-09 08:14:43,995][23090] Updated weights for policy 0, policy_version 35167 (0.0019) [2023-03-09 08:14:44,059][22664] Fps is (10 sec: 199885.8, 60 sec: 199884.6, 300 sec: 199496.0). Total num frames: 576192512. Throughput: 0: 49962.8. Samples: 144010032. Policy #0 lag: (min: 0.0, avg: 16.9, max: 33.0) [2023-03-09 08:14:44,060][22664] Avg episode reward: [(0, '52.348')] [2023-03-09 08:14:44,881][23090] Updated weights for policy 0, policy_version 35177 (0.0019) [2023-03-09 08:14:45,652][23090] Updated weights for policy 0, policy_version 35187 (0.0019) [2023-03-09 08:14:46,482][23090] Updated weights for policy 0, policy_version 35197 (0.0018) [2023-03-09 08:14:47,344][23090] Updated weights for policy 0, policy_version 35207 (0.0013) [2023-03-09 08:14:48,120][23090] Updated weights for policy 0, policy_version 35217 (0.0022) [2023-03-09 08:14:49,015][23090] Updated weights for policy 0, policy_version 35227 (0.0015) [2023-03-09 08:14:49,059][22664] Fps is (10 sec: 199880.0, 60 sec: 199610.9, 300 sec: 199441.7). Total num frames: 577175552. Throughput: 0: 49915.3. Samples: 144308992. Policy #0 lag: (min: 1.0, avg: 16.8, max: 33.0) [2023-03-09 08:14:49,061][22664] Avg episode reward: [(0, '50.823')] [2023-03-09 08:14:49,743][23090] Updated weights for policy 0, policy_version 35237 (0.0013) [2023-03-09 08:14:50,589][23090] Updated weights for policy 0, policy_version 35247 (0.0017) [2023-03-09 08:14:51,396][23090] Updated weights for policy 0, policy_version 35257 (0.0020) [2023-03-09 08:14:52,241][23090] Updated weights for policy 0, policy_version 35267 (0.0013) [2023-03-09 08:14:53,080][23090] Updated weights for policy 0, policy_version 35277 (0.0017) [2023-03-09 08:14:53,201][22940] Signal inference workers to stop experience collection... (11550 times) [2023-03-09 08:14:53,221][22940] Signal inference workers to resume experience collection... (11550 times) [2023-03-09 08:14:53,241][23090] InferenceWorker_p0-w0: stopping experience collection (11550 times) [2023-03-09 08:14:53,241][23090] InferenceWorker_p0-w0: resuming experience collection (11550 times) [2023-03-09 08:14:53,888][23090] Updated weights for policy 0, policy_version 35287 (0.0017) [2023-03-09 08:14:54,059][22664] Fps is (10 sec: 198242.2, 60 sec: 199611.7, 300 sec: 199495.9). Total num frames: 578174976. Throughput: 0: 49826.1. Samples: 144605936. Policy #0 lag: (min: 1.0, avg: 16.8, max: 33.0) [2023-03-09 08:14:54,061][22664] Avg episode reward: [(0, '51.921')] [2023-03-09 08:14:54,708][23090] Updated weights for policy 0, policy_version 35297 (0.0017) [2023-03-09 08:14:55,504][23090] Updated weights for policy 0, policy_version 35307 (0.0018) [2023-03-09 08:14:56,409][23090] Updated weights for policy 0, policy_version 35318 (0.0013) [2023-03-09 08:14:57,195][23090] Updated weights for policy 0, policy_version 35328 (0.0021) [2023-03-09 08:14:58,087][23090] Updated weights for policy 0, policy_version 35338 (0.0013) [2023-03-09 08:14:58,827][23090] Updated weights for policy 0, policy_version 35348 (0.0012) [2023-03-09 08:14:59,058][22664] Fps is (10 sec: 199891.4, 60 sec: 199614.5, 300 sec: 199496.2). Total num frames: 579174400. Throughput: 0: 49873.0. Samples: 144757456. Policy #0 lag: (min: 1.0, avg: 16.8, max: 33.0) [2023-03-09 08:14:59,059][22664] Avg episode reward: [(0, '51.094')] [2023-03-09 08:14:59,706][23090] Updated weights for policy 0, policy_version 35358 (0.0014) [2023-03-09 08:15:00,592][23090] Updated weights for policy 0, policy_version 35368 (0.0016) [2023-03-09 08:15:01,380][23090] Updated weights for policy 0, policy_version 35378 (0.0013) [2023-03-09 08:15:02,199][23090] Updated weights for policy 0, policy_version 35388 (0.0013) [2023-03-09 08:15:02,986][23090] Updated weights for policy 0, policy_version 35398 (0.0015) [2023-03-09 08:15:03,814][23090] Updated weights for policy 0, policy_version 35408 (0.0021) [2023-03-09 08:15:04,059][22664] Fps is (10 sec: 199885.9, 60 sec: 199611.7, 300 sec: 199495.9). Total num frames: 580173824. Throughput: 0: 49917.6. Samples: 145056400. Policy #0 lag: (min: 1.0, avg: 16.8, max: 33.0) [2023-03-09 08:15:04,061][22664] Avg episode reward: [(0, '53.542')] [2023-03-09 08:15:04,626][23090] Updated weights for policy 0, policy_version 35418 (0.0013) [2023-03-09 08:15:05,480][23090] Updated weights for policy 0, policy_version 35428 (0.0019) [2023-03-09 08:15:06,295][23090] Updated weights for policy 0, policy_version 35438 (0.0013) [2023-03-09 08:15:06,623][22940] Signal inference workers to stop experience collection... (11600 times) [2023-03-09 08:15:06,623][22940] Signal inference workers to resume experience collection... (11600 times) [2023-03-09 08:15:06,680][23090] InferenceWorker_p0-w0: stopping experience collection (11600 times) [2023-03-09 08:15:06,680][23090] InferenceWorker_p0-w0: resuming experience collection (11600 times) [2023-03-09 08:15:07,096][23090] Updated weights for policy 0, policy_version 35448 (0.0017) [2023-03-09 08:15:07,951][23090] Updated weights for policy 0, policy_version 35458 (0.0018) [2023-03-09 08:15:08,740][23090] Updated weights for policy 0, policy_version 35468 (0.0022) [2023-03-09 08:15:09,058][22664] Fps is (10 sec: 199885.0, 60 sec: 199612.7, 300 sec: 199496.2). Total num frames: 581173248. Throughput: 0: 49872.0. Samples: 145355376. Policy #0 lag: (min: 1.0, avg: 16.8, max: 33.0) [2023-03-09 08:15:09,060][22664] Avg episode reward: [(0, '49.867')] [2023-03-09 08:15:09,582][23090] Updated weights for policy 0, policy_version 35478 (0.0013) [2023-03-09 08:15:10,353][23090] Updated weights for policy 0, policy_version 35488 (0.0017) [2023-03-09 08:15:11,234][23090] Updated weights for policy 0, policy_version 35498 (0.0016) [2023-03-09 08:15:12,156][23090] Updated weights for policy 0, policy_version 35509 (0.0013) [2023-03-09 08:15:12,929][23090] Updated weights for policy 0, policy_version 35519 (0.0017) [2023-03-09 08:15:13,829][23090] Updated weights for policy 0, policy_version 35529 (0.0013) [2023-03-09 08:15:14,058][22664] Fps is (10 sec: 198251.6, 60 sec: 199612.8, 300 sec: 199440.6). Total num frames: 582156288. Throughput: 0: 49873.1. Samples: 145504864. Policy #0 lag: (min: 1.0, avg: 16.8, max: 33.0) [2023-03-09 08:15:14,060][22664] Avg episode reward: [(0, '50.175')] [2023-03-09 08:15:14,561][23090] Updated weights for policy 0, policy_version 35539 (0.0013) [2023-03-09 08:15:15,398][23090] Updated weights for policy 0, policy_version 35549 (0.0013) [2023-03-09 08:15:16,287][23090] Updated weights for policy 0, policy_version 35559 (0.0017) [2023-03-09 08:15:17,019][23090] Updated weights for policy 0, policy_version 35569 (0.0013) [2023-03-09 08:15:17,937][23090] Updated weights for policy 0, policy_version 35579 (0.0013) [2023-03-09 08:15:18,674][23090] Updated weights for policy 0, policy_version 35589 (0.0013) [2023-03-09 08:15:19,058][22664] Fps is (10 sec: 198245.9, 60 sec: 199612.8, 300 sec: 199496.1). Total num frames: 583155712. Throughput: 0: 49874.3. Samples: 145803856. Policy #0 lag: (min: 1.0, avg: 16.8, max: 33.0) [2023-03-09 08:15:19,060][22664] Avg episode reward: [(0, '51.091')] [2023-03-09 08:15:19,150][22940] Saving /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000035595_583188480.pth... [2023-03-09 08:15:19,216][22940] Removing /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000032672_535298048.pth [2023-03-09 08:15:19,549][23090] Updated weights for policy 0, policy_version 35600 (0.0013) [2023-03-09 08:15:20,408][23090] Updated weights for policy 0, policy_version 35610 (0.0025) [2023-03-09 08:15:21,270][23090] Updated weights for policy 0, policy_version 35620 (0.0013) [2023-03-09 08:15:21,557][22940] Signal inference workers to stop experience collection... (11650 times) [2023-03-09 08:15:21,558][22940] Signal inference workers to resume experience collection... (11650 times) [2023-03-09 08:15:21,622][23090] InferenceWorker_p0-w0: stopping experience collection (11650 times) [2023-03-09 08:15:21,623][23090] InferenceWorker_p0-w0: resuming experience collection (11650 times) [2023-03-09 08:15:22,132][23090] Updated weights for policy 0, policy_version 35630 (0.0016) [2023-03-09 08:15:22,887][23090] Updated weights for policy 0, policy_version 35640 (0.0021) [2023-03-09 08:15:23,743][23090] Updated weights for policy 0, policy_version 35650 (0.0015) [2023-03-09 08:15:24,058][22664] Fps is (10 sec: 199884.7, 60 sec: 199339.7, 300 sec: 199440.6). Total num frames: 584155136. Throughput: 0: 49873.5. Samples: 146102800. Policy #0 lag: (min: 1.0, avg: 16.8, max: 33.0) [2023-03-09 08:15:24,061][22664] Avg episode reward: [(0, '51.177')] [2023-03-09 08:15:24,525][23090] Updated weights for policy 0, policy_version 35660 (0.0019) [2023-03-09 08:15:25,313][23090] Updated weights for policy 0, policy_version 35670 (0.0018) [2023-03-09 08:15:26,107][23090] Updated weights for policy 0, policy_version 35680 (0.0013) [2023-03-09 08:15:26,985][23090] Updated weights for policy 0, policy_version 35690 (0.0013) [2023-03-09 08:15:27,798][23090] Updated weights for policy 0, policy_version 35700 (0.0013) [2023-03-09 08:15:28,612][23090] Updated weights for policy 0, policy_version 35710 (0.0013) [2023-03-09 08:15:29,059][22664] Fps is (10 sec: 198241.2, 60 sec: 199337.9, 300 sec: 199440.3). Total num frames: 585138176. Throughput: 0: 49873.2. Samples: 146254336. Policy #0 lag: (min: 1.0, avg: 16.8, max: 33.0) [2023-03-09 08:15:29,061][22664] Avg episode reward: [(0, '52.357')] [2023-03-09 08:15:29,571][23090] Updated weights for policy 0, policy_version 35720 (0.0016) [2023-03-09 08:15:30,296][23090] Updated weights for policy 0, policy_version 35730 (0.0018) [2023-03-09 08:15:31,142][23090] Updated weights for policy 0, policy_version 35740 (0.0017) [2023-03-09 08:15:31,949][23090] Updated weights for policy 0, policy_version 35750 (0.0026) [2023-03-09 08:15:32,769][23090] Updated weights for policy 0, policy_version 35760 (0.0022) [2023-03-09 08:15:33,590][23090] Updated weights for policy 0, policy_version 35770 (0.0017) [2023-03-09 08:15:34,058][22664] Fps is (10 sec: 199885.0, 60 sec: 199339.2, 300 sec: 199496.4). Total num frames: 586153984. Throughput: 0: 49782.4. Samples: 146549184. Policy #0 lag: (min: 1.0, avg: 17.2, max: 33.0) [2023-03-09 08:15:34,059][22664] Avg episode reward: [(0, '52.730')] [2023-03-09 08:15:34,436][23090] Updated weights for policy 0, policy_version 35780 (0.0013) [2023-03-09 08:15:35,032][22940] Signal inference workers to stop experience collection... (11700 times) [2023-03-09 08:15:35,034][22940] Signal inference workers to resume experience collection... (11700 times) [2023-03-09 08:15:35,099][23090] InferenceWorker_p0-w0: stopping experience collection (11700 times) [2023-03-09 08:15:35,099][23090] InferenceWorker_p0-w0: resuming experience collection (11700 times) [2023-03-09 08:15:35,304][23090] Updated weights for policy 0, policy_version 35790 (0.0013) [2023-03-09 08:15:36,045][23090] Updated weights for policy 0, policy_version 35800 (0.0018) [2023-03-09 08:15:36,925][23090] Updated weights for policy 0, policy_version 35810 (0.0018) [2023-03-09 08:15:37,722][23090] Updated weights for policy 0, policy_version 35820 (0.0013) [2023-03-09 08:15:38,488][23090] Updated weights for policy 0, policy_version 35830 (0.0013) [2023-03-09 08:15:39,059][22664] Fps is (10 sec: 201527.5, 60 sec: 199611.8, 300 sec: 199496.0). Total num frames: 587153408. Throughput: 0: 49872.6. Samples: 146850192. Policy #0 lag: (min: 1.0, avg: 17.2, max: 33.0) [2023-03-09 08:15:39,060][22664] Avg episode reward: [(0, '50.481')] [2023-03-09 08:15:39,284][23090] Updated weights for policy 0, policy_version 35840 (0.0016) [2023-03-09 08:15:40,169][23090] Updated weights for policy 0, policy_version 35850 (0.0013) [2023-03-09 08:15:40,970][23090] Updated weights for policy 0, policy_version 35860 (0.0013) [2023-03-09 08:15:41,787][23090] Updated weights for policy 0, policy_version 35870 (0.0017) [2023-03-09 08:15:42,682][23090] Updated weights for policy 0, policy_version 35880 (0.0016) [2023-03-09 08:15:43,417][23090] Updated weights for policy 0, policy_version 35890 (0.0013) [2023-03-09 08:15:44,059][22664] Fps is (10 sec: 198239.9, 60 sec: 199064.9, 300 sec: 199495.9). Total num frames: 588136448. Throughput: 0: 49826.1. Samples: 146999648. Policy #0 lag: (min: 1.0, avg: 17.2, max: 33.0) [2023-03-09 08:15:44,061][22664] Avg episode reward: [(0, '51.570')] [2023-03-09 08:15:44,295][23090] Updated weights for policy 0, policy_version 35900 (0.0016) [2023-03-09 08:15:45,028][23090] Updated weights for policy 0, policy_version 35910 (0.0016) [2023-03-09 08:15:45,895][23090] Updated weights for policy 0, policy_version 35920 (0.0013) [2023-03-09 08:15:46,760][23090] Updated weights for policy 0, policy_version 35930 (0.0016) [2023-03-09 08:15:47,581][23090] Updated weights for policy 0, policy_version 35940 (0.0018) [2023-03-09 08:15:48,403][23090] Updated weights for policy 0, policy_version 35950 (0.0013) [2023-03-09 08:15:49,059][22664] Fps is (10 sec: 198246.1, 60 sec: 199339.5, 300 sec: 199496.0). Total num frames: 589135872. Throughput: 0: 49827.0. Samples: 147298608. Policy #0 lag: (min: 1.0, avg: 17.2, max: 33.0) [2023-03-09 08:15:49,060][22664] Avg episode reward: [(0, '52.739')] [2023-03-09 08:15:49,214][23090] Updated weights for policy 0, policy_version 35960 (0.0016) [2023-03-09 08:15:50,066][23090] Updated weights for policy 0, policy_version 35970 (0.0022) [2023-03-09 08:15:50,632][22940] Signal inference workers to stop experience collection... (11750 times) [2023-03-09 08:15:50,634][22940] Signal inference workers to resume experience collection... (11750 times) [2023-03-09 08:15:50,697][23090] InferenceWorker_p0-w0: stopping experience collection (11750 times) [2023-03-09 08:15:50,698][23090] InferenceWorker_p0-w0: resuming experience collection (11750 times) [2023-03-09 08:15:50,901][23090] Updated weights for policy 0, policy_version 35980 (0.0013) [2023-03-09 08:15:51,715][23090] Updated weights for policy 0, policy_version 35990 (0.0013) [2023-03-09 08:15:52,484][23090] Updated weights for policy 0, policy_version 36000 (0.0020) [2023-03-09 08:15:53,402][23090] Updated weights for policy 0, policy_version 36010 (0.0015) [2023-03-09 08:15:54,059][22664] Fps is (10 sec: 198246.5, 60 sec: 199065.6, 300 sec: 199440.6). Total num frames: 590118912. Throughput: 0: 49735.5. Samples: 147593488. Policy #0 lag: (min: 1.0, avg: 16.2, max: 33.0) [2023-03-09 08:15:54,061][22664] Avg episode reward: [(0, '51.656')] [2023-03-09 08:15:54,181][23090] Updated weights for policy 0, policy_version 36020 (0.0017) [2023-03-09 08:15:55,022][23090] Updated weights for policy 0, policy_version 36030 (0.0017) [2023-03-09 08:15:55,904][23090] Updated weights for policy 0, policy_version 36040 (0.0019) [2023-03-09 08:15:56,667][23090] Updated weights for policy 0, policy_version 36050 (0.0013) [2023-03-09 08:15:57,473][23090] Updated weights for policy 0, policy_version 36060 (0.0013) [2023-03-09 08:15:58,265][23090] Updated weights for policy 0, policy_version 36070 (0.0016) [2023-03-09 08:15:59,059][22664] Fps is (10 sec: 198244.6, 60 sec: 199065.1, 300 sec: 199495.9). Total num frames: 591118336. Throughput: 0: 49780.8. Samples: 147745008. Policy #0 lag: (min: 1.0, avg: 16.2, max: 33.0) [2023-03-09 08:15:59,060][22664] Avg episode reward: [(0, '52.668')] [2023-03-09 08:15:59,079][23090] Updated weights for policy 0, policy_version 36080 (0.0017) [2023-03-09 08:15:59,924][23090] Updated weights for policy 0, policy_version 36090 (0.0013) [2023-03-09 08:16:00,767][23090] Updated weights for policy 0, policy_version 36100 (0.0012) [2023-03-09 08:16:01,605][23090] Updated weights for policy 0, policy_version 36110 (0.0021) [2023-03-09 08:16:02,372][23090] Updated weights for policy 0, policy_version 36120 (0.0015) [2023-03-09 08:16:03,234][23090] Updated weights for policy 0, policy_version 36130 (0.0019) [2023-03-09 08:16:04,030][23090] Updated weights for policy 0, policy_version 36140 (0.0025) [2023-03-09 08:16:04,059][22664] Fps is (10 sec: 199890.5, 60 sec: 199066.4, 300 sec: 199496.3). Total num frames: 592117760. Throughput: 0: 49733.7. Samples: 148041872. Policy #0 lag: (min: 1.0, avg: 16.2, max: 33.0) [2023-03-09 08:16:04,059][22664] Avg episode reward: [(0, '52.424')] [2023-03-09 08:16:04,809][23090] Updated weights for policy 0, policy_version 36150 (0.0013) [2023-03-09 08:16:05,272][22940] Signal inference workers to stop experience collection... (11800 times) [2023-03-09 08:16:05,285][22940] Signal inference workers to resume experience collection... (11800 times) [2023-03-09 08:16:05,349][23090] InferenceWorker_p0-w0: stopping experience collection (11800 times) [2023-03-09 08:16:05,393][23090] InferenceWorker_p0-w0: resuming experience collection (11800 times) [2023-03-09 08:16:05,609][23090] Updated weights for policy 0, policy_version 36160 (0.0013) [2023-03-09 08:16:06,535][23090] Updated weights for policy 0, policy_version 36170 (0.0020) [2023-03-09 08:16:07,358][23090] Updated weights for policy 0, policy_version 36181 (0.0018) [2023-03-09 08:16:08,206][23090] Updated weights for policy 0, policy_version 36191 (0.0017) [2023-03-09 08:16:09,059][22664] Fps is (10 sec: 198245.3, 60 sec: 198791.8, 300 sec: 199440.4). Total num frames: 593100800. Throughput: 0: 49778.2. Samples: 148342832. Policy #0 lag: (min: 1.0, avg: 16.2, max: 33.0) [2023-03-09 08:16:09,060][22664] Avg episode reward: [(0, '54.087')] [2023-03-09 08:16:09,087][23090] Updated weights for policy 0, policy_version 36201 (0.0016) [2023-03-09 08:16:09,818][23090] Updated weights for policy 0, policy_version 36211 (0.0016) [2023-03-09 08:16:10,664][23090] Updated weights for policy 0, policy_version 36221 (0.0017) [2023-03-09 08:16:11,548][23090] Updated weights for policy 0, policy_version 36231 (0.0015) [2023-03-09 08:16:12,317][23090] Updated weights for policy 0, policy_version 36241 (0.0019) [2023-03-09 08:16:13,191][23090] Updated weights for policy 0, policy_version 36251 (0.0016) [2023-03-09 08:16:13,955][23090] Updated weights for policy 0, policy_version 36261 (0.0013) [2023-03-09 08:16:14,058][22664] Fps is (10 sec: 199885.5, 60 sec: 199338.7, 300 sec: 199440.7). Total num frames: 594116608. Throughput: 0: 49778.4. Samples: 148494352. Policy #0 lag: (min: 1.0, avg: 16.2, max: 33.0) [2023-03-09 08:16:14,059][22664] Avg episode reward: [(0, '51.140')] [2023-03-09 08:16:14,795][23090] Updated weights for policy 0, policy_version 36271 (0.0026) [2023-03-09 08:16:15,590][23090] Updated weights for policy 0, policy_version 36281 (0.0013) [2023-03-09 08:16:16,487][23090] Updated weights for policy 0, policy_version 36291 (0.0015) [2023-03-09 08:16:17,271][23090] Updated weights for policy 0, policy_version 36301 (0.0016) [2023-03-09 08:16:18,069][23090] Updated weights for policy 0, policy_version 36311 (0.0014) [2023-03-09 08:16:18,876][23090] Updated weights for policy 0, policy_version 36321 (0.0013) [2023-03-09 08:16:19,059][22664] Fps is (10 sec: 199888.5, 60 sec: 199065.5, 300 sec: 199440.6). Total num frames: 595099648. Throughput: 0: 49824.7. Samples: 148791296. Policy #0 lag: (min: 1.0, avg: 16.4, max: 32.0) [2023-03-09 08:16:19,059][22664] Avg episode reward: [(0, '51.793')] [2023-03-09 08:16:19,798][23090] Updated weights for policy 0, policy_version 36331 (0.0018) [2023-03-09 08:16:20,534][23090] Updated weights for policy 0, policy_version 36341 (0.0019) [2023-03-09 08:16:21,372][23090] Updated weights for policy 0, policy_version 36351 (0.0016) [2023-03-09 08:16:21,743][22940] Signal inference workers to stop experience collection... (11850 times) [2023-03-09 08:16:21,744][22940] Signal inference workers to resume experience collection... (11850 times) [2023-03-09 08:16:21,816][23090] InferenceWorker_p0-w0: stopping experience collection (11850 times) [2023-03-09 08:16:21,816][23090] InferenceWorker_p0-w0: resuming experience collection (11850 times) [2023-03-09 08:16:22,261][23090] Updated weights for policy 0, policy_version 36361 (0.0017) [2023-03-09 08:16:23,016][23090] Updated weights for policy 0, policy_version 36371 (0.0013) [2023-03-09 08:16:23,825][23090] Updated weights for policy 0, policy_version 36381 (0.0013) [2023-03-09 08:16:24,059][22664] Fps is (10 sec: 199883.6, 60 sec: 199338.5, 300 sec: 199496.4). Total num frames: 596115456. Throughput: 0: 49778.5. Samples: 149090224. Policy #0 lag: (min: 1.0, avg: 16.4, max: 32.0) [2023-03-09 08:16:24,061][22664] Avg episode reward: [(0, '54.109')] [2023-03-09 08:16:24,704][23090] Updated weights for policy 0, policy_version 36391 (0.0019) [2023-03-09 08:16:25,491][23090] Updated weights for policy 0, policy_version 36401 (0.0013) [2023-03-09 08:16:26,344][23090] Updated weights for policy 0, policy_version 36411 (0.0016) [2023-03-09 08:16:27,075][23090] Updated weights for policy 0, policy_version 36421 (0.0024) [2023-03-09 08:16:27,939][23090] Updated weights for policy 0, policy_version 36431 (0.0013) [2023-03-09 08:16:28,718][23090] Updated weights for policy 0, policy_version 36441 (0.0023) [2023-03-09 08:16:29,058][22664] Fps is (10 sec: 199886.0, 60 sec: 199339.7, 300 sec: 199440.7). Total num frames: 597098496. Throughput: 0: 49824.4. Samples: 149241728. Policy #0 lag: (min: 1.0, avg: 16.4, max: 32.0) [2023-03-09 08:16:29,059][22664] Avg episode reward: [(0, '50.760')] [2023-03-09 08:16:29,635][23090] Updated weights for policy 0, policy_version 36451 (0.0016) [2023-03-09 08:16:30,433][23090] Updated weights for policy 0, policy_version 36461 (0.0013) [2023-03-09 08:16:31,199][23090] Updated weights for policy 0, policy_version 36471 (0.0016) [2023-03-09 08:16:32,016][23090] Updated weights for policy 0, policy_version 36481 (0.0013) [2023-03-09 08:16:32,968][23090] Updated weights for policy 0, policy_version 36491 (0.0019) [2023-03-09 08:16:33,691][23090] Updated weights for policy 0, policy_version 36501 (0.0017) [2023-03-09 08:16:34,059][22664] Fps is (10 sec: 198240.9, 60 sec: 199064.5, 300 sec: 199495.8). Total num frames: 598097920. Throughput: 0: 49778.9. Samples: 149538672. Policy #0 lag: (min: 1.0, avg: 16.4, max: 32.0) [2023-03-09 08:16:34,061][22664] Avg episode reward: [(0, '53.909')] [2023-03-09 08:16:34,509][23090] Updated weights for policy 0, policy_version 36511 (0.0021) [2023-03-09 08:16:35,376][23090] Updated weights for policy 0, policy_version 36521 (0.0015) [2023-03-09 08:16:36,131][23090] Updated weights for policy 0, policy_version 36531 (0.0018) [2023-03-09 08:16:36,949][23090] Updated weights for policy 0, policy_version 36541 (0.0020) [2023-03-09 08:16:37,107][22940] Signal inference workers to stop experience collection... (11900 times) [2023-03-09 08:16:37,107][22940] Signal inference workers to resume experience collection... (11900 times) [2023-03-09 08:16:37,170][23090] InferenceWorker_p0-w0: stopping experience collection (11900 times) [2023-03-09 08:16:37,170][23090] InferenceWorker_p0-w0: resuming experience collection (11900 times) [2023-03-09 08:16:37,851][23090] Updated weights for policy 0, policy_version 36551 (0.0016) [2023-03-09 08:16:38,680][23090] Updated weights for policy 0, policy_version 36561 (0.0013) [2023-03-09 08:16:39,059][22664] Fps is (10 sec: 199878.8, 60 sec: 199064.9, 300 sec: 199495.9). Total num frames: 599097344. Throughput: 0: 49869.5. Samples: 149837616. Policy #0 lag: (min: 1.0, avg: 16.4, max: 32.0) [2023-03-09 08:16:39,060][22664] Avg episode reward: [(0, '50.876')] [2023-03-09 08:16:39,489][23090] Updated weights for policy 0, policy_version 36571 (0.0017) [2023-03-09 08:16:40,237][23090] Updated weights for policy 0, policy_version 36581 (0.0019) [2023-03-09 08:16:41,095][23090] Updated weights for policy 0, policy_version 36591 (0.0013) [2023-03-09 08:16:41,877][23090] Updated weights for policy 0, policy_version 36601 (0.0018) [2023-03-09 08:16:42,747][23090] Updated weights for policy 0, policy_version 36611 (0.0016) [2023-03-09 08:16:43,563][23090] Updated weights for policy 0, policy_version 36621 (0.0016) [2023-03-09 08:16:44,059][22664] Fps is (10 sec: 199885.3, 60 sec: 199338.7, 300 sec: 199551.6). Total num frames: 600096768. Throughput: 0: 49868.6. Samples: 149989104. Policy #0 lag: (min: 1.0, avg: 17.2, max: 33.0) [2023-03-09 08:16:44,061][22664] Avg episode reward: [(0, '55.542')] [2023-03-09 08:16:44,396][23090] Updated weights for policy 0, policy_version 36632 (0.0013) [2023-03-09 08:16:45,318][23090] Updated weights for policy 0, policy_version 36642 (0.0016) [2023-03-09 08:16:46,151][23090] Updated weights for policy 0, policy_version 36652 (0.0013) [2023-03-09 08:16:46,918][23090] Updated weights for policy 0, policy_version 36662 (0.0013) [2023-03-09 08:16:47,713][23090] Updated weights for policy 0, policy_version 36672 (0.0016) [2023-03-09 08:16:48,604][23090] Updated weights for policy 0, policy_version 36682 (0.0023) [2023-03-09 08:16:49,058][22664] Fps is (10 sec: 198252.0, 60 sec: 199065.9, 300 sec: 199496.2). Total num frames: 601079808. Throughput: 0: 49914.7. Samples: 150288032. Policy #0 lag: (min: 1.0, avg: 17.2, max: 33.0) [2023-03-09 08:16:49,059][22664] Avg episode reward: [(0, '50.957')] [2023-03-09 08:16:49,441][23090] Updated weights for policy 0, policy_version 36693 (0.0018) [2023-03-09 08:16:50,288][23090] Updated weights for policy 0, policy_version 36703 (0.0015) [2023-03-09 08:16:51,117][23090] Updated weights for policy 0, policy_version 36713 (0.0013) [2023-03-09 08:16:51,772][22940] Signal inference workers to stop experience collection... (11950 times) [2023-03-09 08:16:51,773][22940] Signal inference workers to resume experience collection... (11950 times) [2023-03-09 08:16:51,839][23090] InferenceWorker_p0-w0: stopping experience collection (11950 times) [2023-03-09 08:16:51,840][23090] InferenceWorker_p0-w0: resuming experience collection (11950 times) [2023-03-09 08:16:51,882][23090] Updated weights for policy 0, policy_version 36723 (0.0018) [2023-03-09 08:16:52,698][23090] Updated weights for policy 0, policy_version 36733 (0.0016) [2023-03-09 08:16:53,595][23090] Updated weights for policy 0, policy_version 36743 (0.0013) [2023-03-09 08:16:54,058][22664] Fps is (10 sec: 198252.4, 60 sec: 199339.7, 300 sec: 199607.2). Total num frames: 602079232. Throughput: 0: 49870.8. Samples: 150587008. Policy #0 lag: (min: 1.0, avg: 17.2, max: 33.0) [2023-03-09 08:16:54,059][22664] Avg episode reward: [(0, '49.268')] [2023-03-09 08:16:54,444][23090] Updated weights for policy 0, policy_version 36753 (0.0013) [2023-03-09 08:16:55,288][23090] Updated weights for policy 0, policy_version 36763 (0.0013) [2023-03-09 08:16:56,009][23090] Updated weights for policy 0, policy_version 36773 (0.0013) [2023-03-09 08:16:56,879][23090] Updated weights for policy 0, policy_version 36783 (0.0016) [2023-03-09 08:16:57,688][23090] Updated weights for policy 0, policy_version 36793 (0.0014) [2023-03-09 08:16:58,559][23090] Updated weights for policy 0, policy_version 36803 (0.0016) [2023-03-09 08:16:59,059][22664] Fps is (10 sec: 199877.5, 60 sec: 199338.0, 300 sec: 199551.7). Total num frames: 603078656. Throughput: 0: 49778.8. Samples: 150734416. Policy #0 lag: (min: 1.0, avg: 17.2, max: 33.0) [2023-03-09 08:16:59,060][22664] Avg episode reward: [(0, '51.873')] [2023-03-09 08:16:59,335][23090] Updated weights for policy 0, policy_version 36813 (0.0021) [2023-03-09 08:17:00,153][23090] Updated weights for policy 0, policy_version 36823 (0.0019) [2023-03-09 08:17:00,904][23090] Updated weights for policy 0, policy_version 36833 (0.0021) [2023-03-09 08:17:01,833][23090] Updated weights for policy 0, policy_version 36843 (0.0013) [2023-03-09 08:17:02,598][23090] Updated weights for policy 0, policy_version 36853 (0.0013) [2023-03-09 08:17:03,410][23090] Updated weights for policy 0, policy_version 36863 (0.0013) [2023-03-09 08:17:04,058][22664] Fps is (10 sec: 199885.1, 60 sec: 199338.8, 300 sec: 199607.1). Total num frames: 604078080. Throughput: 0: 49869.6. Samples: 151035424. Policy #0 lag: (min: 1.0, avg: 16.8, max: 33.0) [2023-03-09 08:17:04,059][22664] Avg episode reward: [(0, '50.160')] [2023-03-09 08:17:04,320][23090] Updated weights for policy 0, policy_version 36873 (0.0014) [2023-03-09 08:17:05,088][23090] Updated weights for policy 0, policy_version 36883 (0.0013) [2023-03-09 08:17:05,887][23090] Updated weights for policy 0, policy_version 36893 (0.0018) [2023-03-09 08:17:06,418][22940] Signal inference workers to stop experience collection... (12000 times) [2023-03-09 08:17:06,419][22940] Signal inference workers to resume experience collection... (12000 times) [2023-03-09 08:17:06,488][23090] InferenceWorker_p0-w0: stopping experience collection (12000 times) [2023-03-09 08:17:06,489][23090] InferenceWorker_p0-w0: resuming experience collection (12000 times) [2023-03-09 08:17:06,766][23090] Updated weights for policy 0, policy_version 36903 (0.0024) [2023-03-09 08:17:07,535][23090] Updated weights for policy 0, policy_version 36913 (0.0015) [2023-03-09 08:17:08,405][23090] Updated weights for policy 0, policy_version 36923 (0.0017) [2023-03-09 08:17:09,059][22664] Fps is (10 sec: 199888.4, 60 sec: 199611.9, 300 sec: 199607.0). Total num frames: 605077504. Throughput: 0: 49869.7. Samples: 151334368. Policy #0 lag: (min: 1.0, avg: 16.8, max: 33.0) [2023-03-09 08:17:09,060][22664] Avg episode reward: [(0, '53.311')] [2023-03-09 08:17:09,129][23090] Updated weights for policy 0, policy_version 36933 (0.0021) [2023-03-09 08:17:09,978][23090] Updated weights for policy 0, policy_version 36943 (0.0013) [2023-03-09 08:17:10,817][23090] Updated weights for policy 0, policy_version 36953 (0.0017) [2023-03-09 08:17:11,627][23090] Updated weights for policy 0, policy_version 36963 (0.0019) [2023-03-09 08:17:12,470][23090] Updated weights for policy 0, policy_version 36973 (0.0016) [2023-03-09 08:17:13,284][23090] Updated weights for policy 0, policy_version 36983 (0.0021) [2023-03-09 08:17:14,059][22664] Fps is (10 sec: 199884.0, 60 sec: 199338.6, 300 sec: 199607.3). Total num frames: 606076928. Throughput: 0: 49823.6. Samples: 151483792. Policy #0 lag: (min: 1.0, avg: 16.8, max: 33.0) [2023-03-09 08:17:14,059][22664] Avg episode reward: [(0, '52.169')] [2023-03-09 08:17:14,082][23090] Updated weights for policy 0, policy_version 36993 (0.0016) [2023-03-09 08:17:14,967][23090] Updated weights for policy 0, policy_version 37003 (0.0013) [2023-03-09 08:17:15,724][23090] Updated weights for policy 0, policy_version 37013 (0.0016) [2023-03-09 08:17:16,531][23090] Updated weights for policy 0, policy_version 37023 (0.0015) [2023-03-09 08:17:17,492][23090] Updated weights for policy 0, policy_version 37033 (0.0022) [2023-03-09 08:17:18,211][23090] Updated weights for policy 0, policy_version 37043 (0.0016) [2023-03-09 08:17:19,049][23090] Updated weights for policy 0, policy_version 37053 (0.0013) [2023-03-09 08:17:19,059][22664] Fps is (10 sec: 199882.2, 60 sec: 199610.8, 300 sec: 199607.1). Total num frames: 607076352. Throughput: 0: 49868.1. Samples: 151782736. Policy #0 lag: (min: 1.0, avg: 16.8, max: 33.0) [2023-03-09 08:17:19,061][22664] Avg episode reward: [(0, '51.183')] [2023-03-09 08:17:19,113][22940] Saving /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000037054_607092736.pth... [2023-03-09 08:17:19,168][22940] Removing /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000034132_559218688.pth [2023-03-09 08:17:19,921][23090] Updated weights for policy 0, policy_version 37063 (0.0015) [2023-03-09 08:17:20,089][22940] Signal inference workers to stop experience collection... (12050 times) [2023-03-09 08:17:20,094][22940] Signal inference workers to resume experience collection... (12050 times) [2023-03-09 08:17:20,158][23090] InferenceWorker_p0-w0: stopping experience collection (12050 times) [2023-03-09 08:17:20,158][23090] InferenceWorker_p0-w0: resuming experience collection (12050 times) [2023-03-09 08:17:20,818][23090] Updated weights for policy 0, policy_version 37074 (0.0017) [2023-03-09 08:17:21,584][23090] Updated weights for policy 0, policy_version 37084 (0.0019) [2023-03-09 08:17:22,389][23090] Updated weights for policy 0, policy_version 37094 (0.0018) [2023-03-09 08:17:23,230][23090] Updated weights for policy 0, policy_version 37104 (0.0013) [2023-03-09 08:17:24,059][22664] Fps is (10 sec: 199879.7, 60 sec: 199337.9, 300 sec: 199607.1). Total num frames: 608075776. Throughput: 0: 49867.4. Samples: 152081648. Policy #0 lag: (min: 1.0, avg: 16.8, max: 33.0) [2023-03-09 08:17:24,060][23090] Updated weights for policy 0, policy_version 37114 (0.0013) [2023-03-09 08:17:24,061][22664] Avg episode reward: [(0, '53.678')] [2023-03-09 08:17:24,928][23090] Updated weights for policy 0, policy_version 37124 (0.0022) [2023-03-09 08:17:25,769][23090] Updated weights for policy 0, policy_version 37134 (0.0015) [2023-03-09 08:17:26,553][23090] Updated weights for policy 0, policy_version 37144 (0.0013) [2023-03-09 08:17:27,405][23090] Updated weights for policy 0, policy_version 37154 (0.0013) [2023-03-09 08:17:28,220][23090] Updated weights for policy 0, policy_version 37164 (0.0013) [2023-03-09 08:17:29,059][22664] Fps is (10 sec: 198250.1, 60 sec: 199338.2, 300 sec: 199551.5). Total num frames: 609058816. Throughput: 0: 49777.3. Samples: 152229072. Policy #0 lag: (min: 1.0, avg: 16.7, max: 33.0) [2023-03-09 08:17:29,061][22664] Avg episode reward: [(0, '51.065')] [2023-03-09 08:17:29,097][23090] Updated weights for policy 0, policy_version 37175 (0.0013) [2023-03-09 08:17:29,909][23090] Updated weights for policy 0, policy_version 37185 (0.0021) [2023-03-09 08:17:30,782][23090] Updated weights for policy 0, policy_version 37195 (0.0013) [2023-03-09 08:17:31,514][23090] Updated weights for policy 0, policy_version 37205 (0.0018) [2023-03-09 08:17:32,333][23090] Updated weights for policy 0, policy_version 37215 (0.0014) [2023-03-09 08:17:32,753][22940] Signal inference workers to stop experience collection... (12100 times) [2023-03-09 08:17:32,781][22940] Signal inference workers to resume experience collection... (12100 times) [2023-03-09 08:17:32,810][23090] InferenceWorker_p0-w0: stopping experience collection (12100 times) [2023-03-09 08:17:32,850][23090] InferenceWorker_p0-w0: resuming experience collection (12100 times) [2023-03-09 08:17:33,214][23090] Updated weights for policy 0, policy_version 37225 (0.0021) [2023-03-09 08:17:34,013][23090] Updated weights for policy 0, policy_version 37235 (0.0017) [2023-03-09 08:17:34,059][22664] Fps is (10 sec: 199884.2, 60 sec: 199611.8, 300 sec: 199607.1). Total num frames: 610074624. Throughput: 0: 49822.9. Samples: 152530080. Policy #0 lag: (min: 1.0, avg: 16.7, max: 33.0) [2023-03-09 08:17:34,061][22664] Avg episode reward: [(0, '54.622')] [2023-03-09 08:17:34,830][23090] Updated weights for policy 0, policy_version 37245 (0.0016) [2023-03-09 08:17:35,780][23090] Updated weights for policy 0, policy_version 37256 (0.0013) [2023-03-09 08:17:36,554][23090] Updated weights for policy 0, policy_version 37266 (0.0017) [2023-03-09 08:17:37,383][23090] Updated weights for policy 0, policy_version 37276 (0.0013) [2023-03-09 08:17:38,151][23090] Updated weights for policy 0, policy_version 37286 (0.0015) [2023-03-09 08:17:39,023][23090] Updated weights for policy 0, policy_version 37296 (0.0013) [2023-03-09 08:17:39,058][22664] Fps is (10 sec: 199887.4, 60 sec: 199339.6, 300 sec: 199551.6). Total num frames: 611057664. Throughput: 0: 49823.6. Samples: 152829072. Policy #0 lag: (min: 1.0, avg: 16.7, max: 33.0) [2023-03-09 08:17:39,060][22664] Avg episode reward: [(0, '52.502')] [2023-03-09 08:17:39,841][23090] Updated weights for policy 0, policy_version 37306 (0.0019) [2023-03-09 08:17:40,714][23090] Updated weights for policy 0, policy_version 37316 (0.0013) [2023-03-09 08:17:41,524][23090] Updated weights for policy 0, policy_version 37326 (0.0013) [2023-03-09 08:17:42,306][23090] Updated weights for policy 0, policy_version 37336 (0.0013) [2023-03-09 08:17:43,216][23090] Updated weights for policy 0, policy_version 37346 (0.0018) [2023-03-09 08:17:43,987][23090] Updated weights for policy 0, policy_version 37356 (0.0019) [2023-03-09 08:17:44,058][22664] Fps is (10 sec: 196613.9, 60 sec: 199066.6, 300 sec: 199496.3). Total num frames: 612040704. Throughput: 0: 49869.5. Samples: 152978528. Policy #0 lag: (min: 1.0, avg: 16.7, max: 33.0) [2023-03-09 08:17:44,060][22664] Avg episode reward: [(0, '51.213')] [2023-03-09 08:17:44,759][23090] Updated weights for policy 0, policy_version 37366 (0.0015) [2023-03-09 08:17:45,583][23090] Updated weights for policy 0, policy_version 37376 (0.0013) [2023-03-09 08:17:46,477][23090] Updated weights for policy 0, policy_version 37386 (0.0015) [2023-03-09 08:17:46,823][22940] Signal inference workers to stop experience collection... (12150 times) [2023-03-09 08:17:46,825][22940] Signal inference workers to resume experience collection... (12150 times) [2023-03-09 08:17:46,891][23090] InferenceWorker_p0-w0: stopping experience collection (12150 times) [2023-03-09 08:17:46,891][23090] InferenceWorker_p0-w0: resuming experience collection (12150 times) [2023-03-09 08:17:47,228][23090] Updated weights for policy 0, policy_version 37396 (0.0016) [2023-03-09 08:17:48,084][23090] Updated weights for policy 0, policy_version 37406 (0.0013) [2023-03-09 08:17:48,941][23090] Updated weights for policy 0, policy_version 37416 (0.0022) [2023-03-09 08:17:49,059][22664] Fps is (10 sec: 198245.6, 60 sec: 199338.5, 300 sec: 199496.2). Total num frames: 613040128. Throughput: 0: 49777.7. Samples: 153275424. Policy #0 lag: (min: 1.0, avg: 16.7, max: 33.0) [2023-03-09 08:17:49,059][22664] Avg episode reward: [(0, '53.210')] [2023-03-09 08:17:49,757][23090] Updated weights for policy 0, policy_version 37426 (0.0018) [2023-03-09 08:17:50,526][23090] Updated weights for policy 0, policy_version 37436 (0.0020) [2023-03-09 08:17:51,343][23090] Updated weights for policy 0, policy_version 37446 (0.0013) [2023-03-09 08:17:52,150][23090] Updated weights for policy 0, policy_version 37456 (0.0013) [2023-03-09 08:17:53,023][23090] Updated weights for policy 0, policy_version 37466 (0.0013) [2023-03-09 08:17:53,878][23090] Updated weights for policy 0, policy_version 37477 (0.0018) [2023-03-09 08:17:54,059][22664] Fps is (10 sec: 199884.4, 60 sec: 199338.6, 300 sec: 199440.5). Total num frames: 614039552. Throughput: 0: 49778.3. Samples: 153574384. Policy #0 lag: (min: 1.0, avg: 17.3, max: 33.0) [2023-03-09 08:17:54,059][22664] Avg episode reward: [(0, '53.064')] [2023-03-09 08:17:54,772][23090] Updated weights for policy 0, policy_version 37487 (0.0019) [2023-03-09 08:17:55,579][23090] Updated weights for policy 0, policy_version 37497 (0.0013) [2023-03-09 08:17:56,464][23090] Updated weights for policy 0, policy_version 37508 (0.0017) [2023-03-09 08:17:57,348][23090] Updated weights for policy 0, policy_version 37518 (0.0019) [2023-03-09 08:17:58,086][23090] Updated weights for policy 0, policy_version 37528 (0.0013) [2023-03-09 08:17:59,000][23090] Updated weights for policy 0, policy_version 37538 (0.0018) [2023-03-09 08:17:59,059][22664] Fps is (10 sec: 199879.2, 60 sec: 199338.8, 300 sec: 199496.0). Total num frames: 615038976. Throughput: 0: 49824.7. Samples: 153725920. Policy #0 lag: (min: 1.0, avg: 17.3, max: 33.0) [2023-03-09 08:17:59,061][22664] Avg episode reward: [(0, '51.883')] [2023-03-09 08:17:59,859][23090] Updated weights for policy 0, policy_version 37549 (0.0013) [2023-03-09 08:18:00,662][23090] Updated weights for policy 0, policy_version 37559 (0.0021) [2023-03-09 08:18:01,472][23090] Updated weights for policy 0, policy_version 37569 (0.0017) [2023-03-09 08:18:01,618][22940] Signal inference workers to stop experience collection... (12200 times) [2023-03-09 08:18:01,642][22940] Signal inference workers to resume experience collection... (12200 times) [2023-03-09 08:18:01,705][23090] InferenceWorker_p0-w0: stopping experience collection (12200 times) [2023-03-09 08:18:01,706][23090] InferenceWorker_p0-w0: resuming experience collection (12200 times) [2023-03-09 08:18:02,315][23090] Updated weights for policy 0, policy_version 37579 (0.0019) [2023-03-09 08:18:03,084][23090] Updated weights for policy 0, policy_version 37589 (0.0015) [2023-03-09 08:18:03,895][23090] Updated weights for policy 0, policy_version 37599 (0.0013) [2023-03-09 08:18:04,059][22664] Fps is (10 sec: 199879.0, 60 sec: 199337.6, 300 sec: 199440.3). Total num frames: 616038400. Throughput: 0: 49825.4. Samples: 154024880. Policy #0 lag: (min: 1.0, avg: 17.3, max: 33.0) [2023-03-09 08:18:04,061][22664] Avg episode reward: [(0, '51.292')] [2023-03-09 08:18:04,799][23090] Updated weights for policy 0, policy_version 37609 (0.0013) [2023-03-09 08:18:05,582][23090] Updated weights for policy 0, policy_version 37619 (0.0014) [2023-03-09 08:18:06,414][23090] Updated weights for policy 0, policy_version 37629 (0.0014) [2023-03-09 08:18:07,266][23090] Updated weights for policy 0, policy_version 37639 (0.0013) [2023-03-09 08:18:08,045][23090] Updated weights for policy 0, policy_version 37649 (0.0021) [2023-03-09 08:18:08,851][23090] Updated weights for policy 0, policy_version 37659 (0.0018) [2023-03-09 08:18:09,059][22664] Fps is (10 sec: 201522.1, 60 sec: 199611.1, 300 sec: 199495.9). Total num frames: 617054208. Throughput: 0: 49827.1. Samples: 154323872. Policy #0 lag: (min: 1.0, avg: 17.3, max: 33.0) [2023-03-09 08:18:09,061][22664] Avg episode reward: [(0, '51.161')] [2023-03-09 08:18:09,676][23090] Updated weights for policy 0, policy_version 37669 (0.0016) [2023-03-09 08:18:10,536][23090] Updated weights for policy 0, policy_version 37679 (0.0018) [2023-03-09 08:18:11,327][23090] Updated weights for policy 0, policy_version 37689 (0.0013) [2023-03-09 08:18:12,174][23090] Updated weights for policy 0, policy_version 37699 (0.0016) [2023-03-09 08:18:13,005][23090] Updated weights for policy 0, policy_version 37709 (0.0019) [2023-03-09 08:18:13,771][23090] Updated weights for policy 0, policy_version 37719 (0.0016) [2023-03-09 08:18:14,059][22664] Fps is (10 sec: 199886.6, 60 sec: 199338.0, 300 sec: 199440.6). Total num frames: 618037248. Throughput: 0: 49871.9. Samples: 154473312. Policy #0 lag: (min: 1.0, avg: 17.3, max: 33.0) [2023-03-09 08:18:14,061][22664] Avg episode reward: [(0, '52.698')] [2023-03-09 08:18:14,584][23090] Updated weights for policy 0, policy_version 37729 (0.0013) [2023-03-09 08:18:15,475][23090] Updated weights for policy 0, policy_version 37739 (0.0013) [2023-03-09 08:18:16,247][23090] Updated weights for policy 0, policy_version 37749 (0.0016) [2023-03-09 08:18:16,857][22940] Signal inference workers to stop experience collection... (12250 times) [2023-03-09 08:18:16,858][22940] Signal inference workers to resume experience collection... (12250 times) [2023-03-09 08:18:16,919][23090] InferenceWorker_p0-w0: stopping experience collection (12250 times) [2023-03-09 08:18:16,919][23090] InferenceWorker_p0-w0: resuming experience collection (12250 times) [2023-03-09 08:18:17,086][23090] Updated weights for policy 0, policy_version 37759 (0.0016) [2023-03-09 08:18:17,939][23090] Updated weights for policy 0, policy_version 37769 (0.0013) [2023-03-09 08:18:18,775][23090] Updated weights for policy 0, policy_version 37779 (0.0013) [2023-03-09 08:18:19,059][22664] Fps is (10 sec: 198237.4, 60 sec: 199337.0, 300 sec: 199440.1). Total num frames: 619036672. Throughput: 0: 49825.6. Samples: 154772256. Policy #0 lag: (min: 0.0, avg: 17.3, max: 33.0) [2023-03-09 08:18:19,061][22664] Avg episode reward: [(0, '55.052')] [2023-03-09 08:18:19,556][23090] Updated weights for policy 0, policy_version 37789 (0.0016) [2023-03-09 08:18:20,426][23090] Updated weights for policy 0, policy_version 37799 (0.0013) [2023-03-09 08:18:21,278][23090] Updated weights for policy 0, policy_version 37809 (0.0018) [2023-03-09 08:18:22,045][23090] Updated weights for policy 0, policy_version 37819 (0.0013) [2023-03-09 08:18:22,927][23090] Updated weights for policy 0, policy_version 37830 (0.0013) [2023-03-09 08:18:23,761][23090] Updated weights for policy 0, policy_version 37840 (0.0013) [2023-03-09 08:18:24,059][22664] Fps is (10 sec: 199886.8, 60 sec: 199339.2, 300 sec: 199440.4). Total num frames: 620036096. Throughput: 0: 49780.5. Samples: 155069200. Policy #0 lag: (min: 0.0, avg: 17.3, max: 33.0) [2023-03-09 08:18:24,060][22664] Avg episode reward: [(0, '52.243')] [2023-03-09 08:18:24,567][23090] Updated weights for policy 0, policy_version 37850 (0.0017) [2023-03-09 08:18:25,447][23090] Updated weights for policy 0, policy_version 37860 (0.0019) [2023-03-09 08:18:26,305][23090] Updated weights for policy 0, policy_version 37870 (0.0013) [2023-03-09 08:18:27,110][23090] Updated weights for policy 0, policy_version 37880 (0.0013) [2023-03-09 08:18:27,911][23090] Updated weights for policy 0, policy_version 37890 (0.0013) [2023-03-09 08:18:28,726][23090] Updated weights for policy 0, policy_version 37900 (0.0013) [2023-03-09 08:18:29,059][22664] Fps is (10 sec: 198260.0, 60 sec: 199338.6, 300 sec: 199385.0). Total num frames: 621019136. Throughput: 0: 49781.2. Samples: 155218688. Policy #0 lag: (min: 0.0, avg: 17.3, max: 33.0) [2023-03-09 08:18:29,060][22664] Avg episode reward: [(0, '52.797')] [2023-03-09 08:18:29,608][23090] Updated weights for policy 0, policy_version 37911 (0.0020) [2023-03-09 08:18:30,420][23090] Updated weights for policy 0, policy_version 37921 (0.0021) [2023-03-09 08:18:31,321][23090] Updated weights for policy 0, policy_version 37931 (0.0017) [2023-03-09 08:18:32,228][23090] Updated weights for policy 0, policy_version 37942 (0.0018) [2023-03-09 08:18:32,958][23090] Updated weights for policy 0, policy_version 37952 (0.0020) [2023-03-09 08:18:33,841][23090] Updated weights for policy 0, policy_version 37962 (0.0013) [2023-03-09 08:18:34,059][22664] Fps is (10 sec: 196605.1, 60 sec: 198792.7, 300 sec: 199329.4). Total num frames: 622002176. Throughput: 0: 49827.3. Samples: 155517664. Policy #0 lag: (min: 0.0, avg: 17.3, max: 33.0) [2023-03-09 08:18:34,060][22664] Avg episode reward: [(0, '51.995')] [2023-03-09 08:18:34,176][22940] Signal inference workers to stop experience collection... (12300 times) [2023-03-09 08:18:34,180][22940] Signal inference workers to resume experience collection... (12300 times) [2023-03-09 08:18:34,243][23090] InferenceWorker_p0-w0: stopping experience collection (12300 times) [2023-03-09 08:18:34,288][23090] InferenceWorker_p0-w0: resuming experience collection (12300 times) [2023-03-09 08:18:34,641][23090] Updated weights for policy 0, policy_version 37972 (0.0020) [2023-03-09 08:18:35,418][23090] Updated weights for policy 0, policy_version 37982 (0.0018) [2023-03-09 08:18:36,337][23090] Updated weights for policy 0, policy_version 37992 (0.0017) [2023-03-09 08:18:37,115][23090] Updated weights for policy 0, policy_version 38002 (0.0016) [2023-03-09 08:18:37,941][23090] Updated weights for policy 0, policy_version 38012 (0.0013) [2023-03-09 08:18:38,758][23090] Updated weights for policy 0, policy_version 38022 (0.0013) [2023-03-09 08:18:39,059][22664] Fps is (10 sec: 198248.0, 60 sec: 199065.4, 300 sec: 199329.4). Total num frames: 623001600. Throughput: 0: 49828.2. Samples: 155816656. Policy #0 lag: (min: 0.0, avg: 17.2, max: 33.0) [2023-03-09 08:18:39,060][22664] Avg episode reward: [(0, '50.993')] [2023-03-09 08:18:39,570][23090] Updated weights for policy 0, policy_version 38032 (0.0013) [2023-03-09 08:18:40,440][23090] Updated weights for policy 0, policy_version 38042 (0.0018) [2023-03-09 08:18:41,252][23090] Updated weights for policy 0, policy_version 38052 (0.0016) [2023-03-09 08:18:42,128][23090] Updated weights for policy 0, policy_version 38062 (0.0013) [2023-03-09 08:18:42,890][23090] Updated weights for policy 0, policy_version 38072 (0.0013) [2023-03-09 08:18:43,725][23090] Updated weights for policy 0, policy_version 38082 (0.0013) [2023-03-09 08:18:44,059][22664] Fps is (10 sec: 199885.8, 60 sec: 199338.0, 300 sec: 199329.3). Total num frames: 624001024. Throughput: 0: 49737.7. Samples: 155964112. Policy #0 lag: (min: 0.0, avg: 17.2, max: 33.0) [2023-03-09 08:18:44,060][22664] Avg episode reward: [(0, '50.925')] [2023-03-09 08:18:44,547][23090] Updated weights for policy 0, policy_version 38092 (0.0017) [2023-03-09 08:18:45,355][23090] Updated weights for policy 0, policy_version 38102 (0.0013) [2023-03-09 08:18:46,125][23090] Updated weights for policy 0, policy_version 38112 (0.0017) [2023-03-09 08:18:47,028][23090] Updated weights for policy 0, policy_version 38122 (0.0020) [2023-03-09 08:18:47,798][23090] Updated weights for policy 0, policy_version 38132 (0.0016) [2023-03-09 08:18:48,587][23090] Updated weights for policy 0, policy_version 38142 (0.0015) [2023-03-09 08:18:49,041][22940] Signal inference workers to stop experience collection... (12350 times) [2023-03-09 08:18:49,059][22664] Fps is (10 sec: 198247.0, 60 sec: 199065.6, 300 sec: 199274.1). Total num frames: 624984064. Throughput: 0: 49737.9. Samples: 156263072. Policy #0 lag: (min: 0.0, avg: 17.2, max: 33.0) [2023-03-09 08:18:49,059][22664] Avg episode reward: [(0, '51.518')] [2023-03-09 08:18:49,061][22940] Signal inference workers to resume experience collection... (12350 times) [2023-03-09 08:18:49,111][23090] InferenceWorker_p0-w0: stopping experience collection (12350 times) [2023-03-09 08:18:49,111][23090] InferenceWorker_p0-w0: resuming experience collection (12350 times) [2023-03-09 08:18:49,474][23090] Updated weights for policy 0, policy_version 38152 (0.0013) [2023-03-09 08:18:50,278][23090] Updated weights for policy 0, policy_version 38162 (0.0013) [2023-03-09 08:18:51,088][23090] Updated weights for policy 0, policy_version 38172 (0.0013) [2023-03-09 08:18:52,050][23090] Updated weights for policy 0, policy_version 38183 (0.0013) [2023-03-09 08:18:52,868][23090] Updated weights for policy 0, policy_version 38193 (0.0016) [2023-03-09 08:18:53,721][23090] Updated weights for policy 0, policy_version 38203 (0.0015) [2023-03-09 08:18:54,059][22664] Fps is (10 sec: 199882.1, 60 sec: 199337.6, 300 sec: 199329.7). Total num frames: 625999872. Throughput: 0: 49692.1. Samples: 156560016. Policy #0 lag: (min: 0.0, avg: 17.2, max: 33.0) [2023-03-09 08:18:54,062][22664] Avg episode reward: [(0, '52.100')] [2023-03-09 08:18:54,449][23090] Updated weights for policy 0, policy_version 38213 (0.0018) [2023-03-09 08:18:55,353][23090] Updated weights for policy 0, policy_version 38223 (0.0016) [2023-03-09 08:18:56,182][23090] Updated weights for policy 0, policy_version 38233 (0.0013) [2023-03-09 08:18:56,978][23090] Updated weights for policy 0, policy_version 38243 (0.0012) [2023-03-09 08:18:57,789][23090] Updated weights for policy 0, policy_version 38253 (0.0022) [2023-03-09 08:18:58,570][23090] Updated weights for policy 0, policy_version 38263 (0.0021) [2023-03-09 08:18:59,059][22664] Fps is (10 sec: 201516.5, 60 sec: 199338.5, 300 sec: 199329.3). Total num frames: 626999296. Throughput: 0: 49737.8. Samples: 156711520. Policy #0 lag: (min: 0.0, avg: 17.2, max: 33.0) [2023-03-09 08:18:59,060][22664] Avg episode reward: [(0, '54.174')] [2023-03-09 08:18:59,395][23090] Updated weights for policy 0, policy_version 38273 (0.0022) [2023-03-09 08:19:00,249][23090] Updated weights for policy 0, policy_version 38283 (0.0013) [2023-03-09 08:19:01,046][23090] Updated weights for policy 0, policy_version 38293 (0.0017) [2023-03-09 08:19:01,821][23090] Updated weights for policy 0, policy_version 38303 (0.0013) [2023-03-09 08:19:02,728][23090] Updated weights for policy 0, policy_version 38313 (0.0016) [2023-03-09 08:19:03,554][23090] Updated weights for policy 0, policy_version 38323 (0.0018) [2023-03-09 08:19:04,059][22664] Fps is (10 sec: 198252.8, 60 sec: 199066.5, 300 sec: 199274.0). Total num frames: 627982336. Throughput: 0: 49739.9. Samples: 157010512. Policy #0 lag: (min: 1.0, avg: 16.6, max: 33.0) [2023-03-09 08:19:04,059][22664] Avg episode reward: [(0, '54.414')] [2023-03-09 08:19:04,348][23090] Updated weights for policy 0, policy_version 38333 (0.0013) [2023-03-09 08:19:05,241][23090] Updated weights for policy 0, policy_version 38343 (0.0019) [2023-03-09 08:19:05,808][22940] Signal inference workers to stop experience collection... (12400 times) [2023-03-09 08:19:05,810][22940] Signal inference workers to resume experience collection... (12400 times) [2023-03-09 08:19:05,873][23090] InferenceWorker_p0-w0: stopping experience collection (12400 times) [2023-03-09 08:19:05,873][23090] InferenceWorker_p0-w0: resuming experience collection (12400 times) [2023-03-09 08:19:05,997][23090] Updated weights for policy 0, policy_version 38353 (0.0013) [2023-03-09 08:19:06,847][23090] Updated weights for policy 0, policy_version 38363 (0.0013) [2023-03-09 08:19:07,642][23090] Updated weights for policy 0, policy_version 38373 (0.0017) [2023-03-09 08:19:08,489][23090] Updated weights for policy 0, policy_version 38383 (0.0013) [2023-03-09 08:19:09,059][22664] Fps is (10 sec: 198250.2, 60 sec: 198793.2, 300 sec: 199329.5). Total num frames: 628981760. Throughput: 0: 49783.1. Samples: 157309440. Policy #0 lag: (min: 1.0, avg: 16.6, max: 33.0) [2023-03-09 08:19:09,060][22664] Avg episode reward: [(0, '52.112')] [2023-03-09 08:19:09,266][23090] Updated weights for policy 0, policy_version 38393 (0.0013) [2023-03-09 08:19:10,149][23090] Updated weights for policy 0, policy_version 38404 (0.0017) [2023-03-09 08:19:11,041][23090] Updated weights for policy 0, policy_version 38414 (0.0013) [2023-03-09 08:19:11,814][23090] Updated weights for policy 0, policy_version 38424 (0.0015) [2023-03-09 08:19:12,744][23090] Updated weights for policy 0, policy_version 38434 (0.0016) [2023-03-09 08:19:13,517][23090] Updated weights for policy 0, policy_version 38444 (0.0013) [2023-03-09 08:19:14,059][22664] Fps is (10 sec: 198244.6, 60 sec: 198792.9, 300 sec: 199274.0). Total num frames: 629964800. Throughput: 0: 49783.1. Samples: 157458928. Policy #0 lag: (min: 1.0, avg: 16.6, max: 33.0) [2023-03-09 08:19:14,060][22664] Avg episode reward: [(0, '55.790')] [2023-03-09 08:19:14,072][22940] Saving new best policy, reward=55.790! [2023-03-09 08:19:14,332][23090] Updated weights for policy 0, policy_version 38454 (0.0014) [2023-03-09 08:19:15,113][23090] Updated weights for policy 0, policy_version 38464 (0.0018) [2023-03-09 08:19:16,039][23090] Updated weights for policy 0, policy_version 38474 (0.0018) [2023-03-09 08:19:16,778][23090] Updated weights for policy 0, policy_version 38484 (0.0028) [2023-03-09 08:19:17,663][23090] Updated weights for policy 0, policy_version 38494 (0.0013) [2023-03-09 08:19:18,535][23090] Updated weights for policy 0, policy_version 38504 (0.0017) [2023-03-09 08:19:19,059][22664] Fps is (10 sec: 196610.3, 60 sec: 198522.0, 300 sec: 199163.0). Total num frames: 630947840. Throughput: 0: 49692.3. Samples: 157753808. Policy #0 lag: (min: 1.0, avg: 16.6, max: 33.0) [2023-03-09 08:19:19,060][22664] Avg episode reward: [(0, '53.713')] [2023-03-09 08:19:19,080][22940] Saving /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000038511_630964224.pth... [2023-03-09 08:19:19,196][22940] Removing /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000035595_583188480.pth [2023-03-09 08:19:19,392][23090] Updated weights for policy 0, policy_version 38514 (0.0016) [2023-03-09 08:19:20,201][23090] Updated weights for policy 0, policy_version 38524 (0.0013) [2023-03-09 08:19:20,823][22940] Signal inference workers to stop experience collection... (12450 times) [2023-03-09 08:19:20,823][22940] Signal inference workers to resume experience collection... (12450 times) [2023-03-09 08:19:20,883][23090] InferenceWorker_p0-w0: stopping experience collection (12450 times) [2023-03-09 08:19:20,884][23090] InferenceWorker_p0-w0: resuming experience collection (12450 times) [2023-03-09 08:19:20,969][23090] Updated weights for policy 0, policy_version 38534 (0.0017) [2023-03-09 08:19:21,778][23090] Updated weights for policy 0, policy_version 38544 (0.0013) [2023-03-09 08:19:22,664][23090] Updated weights for policy 0, policy_version 38554 (0.0013) [2023-03-09 08:19:23,447][23090] Updated weights for policy 0, policy_version 38564 (0.0017) [2023-03-09 08:19:24,059][22664] Fps is (10 sec: 196605.0, 60 sec: 198245.9, 300 sec: 199162.6). Total num frames: 631930880. Throughput: 0: 49645.6. Samples: 158050720. Policy #0 lag: (min: 1.0, avg: 16.6, max: 33.0) [2023-03-09 08:19:24,060][22664] Avg episode reward: [(0, '52.597')] [2023-03-09 08:19:24,365][23090] Updated weights for policy 0, policy_version 38574 (0.0013) [2023-03-09 08:19:25,114][23090] Updated weights for policy 0, policy_version 38584 (0.0013) [2023-03-09 08:19:26,069][23090] Updated weights for policy 0, policy_version 38595 (0.0019) [2023-03-09 08:19:26,963][23090] Updated weights for policy 0, policy_version 38605 (0.0018) [2023-03-09 08:19:27,687][23090] Updated weights for policy 0, policy_version 38615 (0.0014) [2023-03-09 08:19:28,491][23090] Updated weights for policy 0, policy_version 38625 (0.0021) [2023-03-09 08:19:29,059][22664] Fps is (10 sec: 198242.9, 60 sec: 198519.2, 300 sec: 199107.2). Total num frames: 632930304. Throughput: 0: 49689.6. Samples: 158200144. Policy #0 lag: (min: 0.0, avg: 17.3, max: 34.0) [2023-03-09 08:19:29,060][22664] Avg episode reward: [(0, '52.406')] [2023-03-09 08:19:29,339][23090] Updated weights for policy 0, policy_version 38635 (0.0018) [2023-03-09 08:19:30,114][23090] Updated weights for policy 0, policy_version 38645 (0.0013) [2023-03-09 08:19:30,956][23090] Updated weights for policy 0, policy_version 38655 (0.0017) [2023-03-09 08:19:31,791][23090] Updated weights for policy 0, policy_version 38665 (0.0016) [2023-03-09 08:19:32,574][23090] Updated weights for policy 0, policy_version 38675 (0.0015) [2023-03-09 08:19:33,406][23090] Updated weights for policy 0, policy_version 38685 (0.0013) [2023-03-09 08:19:34,059][22664] Fps is (10 sec: 201521.2, 60 sec: 199065.3, 300 sec: 199218.1). Total num frames: 633946112. Throughput: 0: 49689.9. Samples: 158499136. Policy #0 lag: (min: 0.0, avg: 17.3, max: 34.0) [2023-03-09 08:19:34,061][22664] Avg episode reward: [(0, '51.714')] [2023-03-09 08:19:34,253][23090] Updated weights for policy 0, policy_version 38695 (0.0013) [2023-03-09 08:19:35,064][23090] Updated weights for policy 0, policy_version 38705 (0.0014) [2023-03-09 08:19:35,956][23090] Updated weights for policy 0, policy_version 38715 (0.0021) [2023-03-09 08:19:36,721][23090] Updated weights for policy 0, policy_version 38725 (0.0016) [2023-03-09 08:19:37,570][23090] Updated weights for policy 0, policy_version 38735 (0.0016) [2023-03-09 08:19:38,383][23090] Updated weights for policy 0, policy_version 38745 (0.0016) [2023-03-09 08:19:38,872][22940] Signal inference workers to stop experience collection... (12500 times) [2023-03-09 08:19:38,875][22940] Signal inference workers to resume experience collection... (12500 times) [2023-03-09 08:19:38,941][23090] InferenceWorker_p0-w0: stopping experience collection (12500 times) [2023-03-09 08:19:38,942][23090] InferenceWorker_p0-w0: resuming experience collection (12500 times) [2023-03-09 08:19:39,059][22664] Fps is (10 sec: 199888.9, 60 sec: 198792.6, 300 sec: 199107.3). Total num frames: 634929152. Throughput: 0: 49690.0. Samples: 158796048. Policy #0 lag: (min: 0.0, avg: 17.3, max: 34.0) [2023-03-09 08:19:39,060][22664] Avg episode reward: [(0, '51.930')] [2023-03-09 08:19:39,193][23090] Updated weights for policy 0, policy_version 38755 (0.0013) [2023-03-09 08:19:40,113][23090] Updated weights for policy 0, policy_version 38765 (0.0015) [2023-03-09 08:19:40,854][23090] Updated weights for policy 0, policy_version 38775 (0.0013) [2023-03-09 08:19:41,685][23090] Updated weights for policy 0, policy_version 38785 (0.0013) [2023-03-09 08:19:42,570][23090] Updated weights for policy 0, policy_version 38795 (0.0013) [2023-03-09 08:19:43,291][23090] Updated weights for policy 0, policy_version 38805 (0.0016) [2023-03-09 08:19:44,059][22664] Fps is (10 sec: 198253.5, 60 sec: 198793.2, 300 sec: 199163.0). Total num frames: 635928576. Throughput: 0: 49599.7. Samples: 158943488. Policy #0 lag: (min: 0.0, avg: 17.3, max: 34.0) [2023-03-09 08:19:44,060][22664] Avg episode reward: [(0, '52.365')] [2023-03-09 08:19:44,114][23090] Updated weights for policy 0, policy_version 38815 (0.0014) [2023-03-09 08:19:44,965][23090] Updated weights for policy 0, policy_version 38825 (0.0012) [2023-03-09 08:19:45,754][23090] Updated weights for policy 0, policy_version 38835 (0.0011) [2023-03-09 08:19:46,640][23090] Updated weights for policy 0, policy_version 38845 (0.0015) [2023-03-09 08:19:47,450][23090] Updated weights for policy 0, policy_version 38855 (0.0016) [2023-03-09 08:19:48,257][23090] Updated weights for policy 0, policy_version 38865 (0.0018) [2023-03-09 08:19:49,059][22664] Fps is (10 sec: 198241.3, 60 sec: 198791.7, 300 sec: 199107.3). Total num frames: 636911616. Throughput: 0: 49643.8. Samples: 159244496. Policy #0 lag: (min: 0.0, avg: 17.3, max: 34.0) [2023-03-09 08:19:49,061][22664] Avg episode reward: [(0, '53.547')] [2023-03-09 08:19:49,102][23090] Updated weights for policy 0, policy_version 38875 (0.0018) [2023-03-09 08:19:49,978][23090] Updated weights for policy 0, policy_version 38886 (0.0024) [2023-03-09 08:19:50,849][23090] Updated weights for policy 0, policy_version 38896 (0.0020) [2023-03-09 08:19:51,682][23090] Updated weights for policy 0, policy_version 38906 (0.0013) [2023-03-09 08:19:52,438][23090] Updated weights for policy 0, policy_version 38916 (0.0019) [2023-03-09 08:19:53,332][23090] Updated weights for policy 0, policy_version 38926 (0.0019) [2023-03-09 08:19:54,059][22664] Fps is (10 sec: 198237.8, 60 sec: 198519.2, 300 sec: 199106.9). Total num frames: 637911040. Throughput: 0: 49598.3. Samples: 159541376. Policy #0 lag: (min: 1.0, avg: 17.3, max: 34.0) [2023-03-09 08:19:54,061][22664] Avg episode reward: [(0, '53.200')] [2023-03-09 08:19:54,097][23090] Updated weights for policy 0, policy_version 38936 (0.0021) [2023-03-09 08:19:54,947][23090] Updated weights for policy 0, policy_version 38946 (0.0013) [2023-03-09 08:19:55,764][23090] Updated weights for policy 0, policy_version 38956 (0.0013) [2023-03-09 08:19:56,597][23090] Updated weights for policy 0, policy_version 38966 (0.0013) [2023-03-09 08:19:57,131][22940] Signal inference workers to stop experience collection... (12550 times) [2023-03-09 08:19:57,134][22940] Signal inference workers to resume experience collection... (12550 times) [2023-03-09 08:19:57,206][23090] InferenceWorker_p0-w0: stopping experience collection (12550 times) [2023-03-09 08:19:57,206][23090] InferenceWorker_p0-w0: resuming experience collection (12550 times) [2023-03-09 08:19:57,364][23090] Updated weights for policy 0, policy_version 38976 (0.0013) [2023-03-09 08:19:58,256][23090] Updated weights for policy 0, policy_version 38986 (0.0016) [2023-03-09 08:19:59,024][23090] Updated weights for policy 0, policy_version 38996 (0.0013) [2023-03-09 08:19:59,059][22664] Fps is (10 sec: 199889.7, 60 sec: 198520.6, 300 sec: 199107.4). Total num frames: 638910464. Throughput: 0: 49598.7. Samples: 159690864. Policy #0 lag: (min: 1.0, avg: 17.3, max: 34.0) [2023-03-09 08:19:59,060][22664] Avg episode reward: [(0, '53.916')] [2023-03-09 08:19:59,836][23090] Updated weights for policy 0, policy_version 39006 (0.0013) [2023-03-09 08:20:00,706][23090] Updated weights for policy 0, policy_version 39016 (0.0016) [2023-03-09 08:20:01,477][23090] Updated weights for policy 0, policy_version 39026 (0.0016) [2023-03-09 08:20:02,360][23090] Updated weights for policy 0, policy_version 39036 (0.0020) [2023-03-09 08:20:03,126][23090] Updated weights for policy 0, policy_version 39046 (0.0013) [2023-03-09 08:20:03,982][23090] Updated weights for policy 0, policy_version 39056 (0.0017) [2023-03-09 08:20:04,059][22664] Fps is (10 sec: 199891.3, 60 sec: 198792.2, 300 sec: 199107.2). Total num frames: 639909888. Throughput: 0: 49687.4. Samples: 159989744. Policy #0 lag: (min: 1.0, avg: 17.3, max: 34.0) [2023-03-09 08:20:04,061][22664] Avg episode reward: [(0, '51.940')] [2023-03-09 08:20:04,830][23090] Updated weights for policy 0, policy_version 39066 (0.0013) [2023-03-09 08:20:05,642][23090] Updated weights for policy 0, policy_version 39076 (0.0024) [2023-03-09 08:20:06,516][23090] Updated weights for policy 0, policy_version 39086 (0.0016) [2023-03-09 08:20:07,266][23090] Updated weights for policy 0, policy_version 39096 (0.0013) [2023-03-09 08:20:08,113][23090] Updated weights for policy 0, policy_version 39106 (0.0017) [2023-03-09 08:20:08,951][23090] Updated weights for policy 0, policy_version 39116 (0.0013) [2023-03-09 08:20:09,059][22664] Fps is (10 sec: 198246.5, 60 sec: 198519.9, 300 sec: 199107.2). Total num frames: 640892928. Throughput: 0: 49777.7. Samples: 160290704. Policy #0 lag: (min: 1.0, avg: 17.3, max: 34.0) [2023-03-09 08:20:09,059][22664] Avg episode reward: [(0, '52.311')] [2023-03-09 08:20:09,725][23090] Updated weights for policy 0, policy_version 39126 (0.0013) [2023-03-09 08:20:10,531][23090] Updated weights for policy 0, policy_version 39136 (0.0016) [2023-03-09 08:20:11,418][23090] Updated weights for policy 0, policy_version 39146 (0.0018) [2023-03-09 08:20:12,250][23090] Updated weights for policy 0, policy_version 39157 (0.0015) [2023-03-09 08:20:13,080][22940] Signal inference workers to stop experience collection... (12600 times) [2023-03-09 08:20:13,081][22940] Signal inference workers to resume experience collection... (12600 times) [2023-03-09 08:20:13,110][23090] Updated weights for policy 0, policy_version 39167 (0.0016) [2023-03-09 08:20:13,141][23090] InferenceWorker_p0-w0: stopping experience collection (12600 times) [2023-03-09 08:20:13,142][23090] InferenceWorker_p0-w0: resuming experience collection (12600 times) [2023-03-09 08:20:13,910][23090] Updated weights for policy 0, policy_version 39177 (0.0021) [2023-03-09 08:20:14,059][22664] Fps is (10 sec: 198243.2, 60 sec: 198792.0, 300 sec: 199107.1). Total num frames: 641892352. Throughput: 0: 49733.6. Samples: 160438160. Policy #0 lag: (min: 1.0, avg: 17.3, max: 34.0) [2023-03-09 08:20:14,061][22664] Avg episode reward: [(0, '51.602')] [2023-03-09 08:20:14,709][23090] Updated weights for policy 0, policy_version 39187 (0.0021) [2023-03-09 08:20:15,558][23090] Updated weights for policy 0, policy_version 39197 (0.0013) [2023-03-09 08:20:16,378][23090] Updated weights for policy 0, policy_version 39207 (0.0017) [2023-03-09 08:20:17,197][23090] Updated weights for policy 0, policy_version 39217 (0.0018) [2023-03-09 08:20:18,010][23090] Updated weights for policy 0, policy_version 39227 (0.0015) [2023-03-09 08:20:18,820][23090] Updated weights for policy 0, policy_version 39237 (0.0014) [2023-03-09 08:20:19,059][22664] Fps is (10 sec: 199878.4, 60 sec: 199064.6, 300 sec: 199107.0). Total num frames: 642891776. Throughput: 0: 49778.2. Samples: 160739152. Policy #0 lag: (min: 1.0, avg: 16.5, max: 33.0) [2023-03-09 08:20:19,061][22664] Avg episode reward: [(0, '50.036')] [2023-03-09 08:20:19,675][23090] Updated weights for policy 0, policy_version 39247 (0.0017) [2023-03-09 08:20:20,593][23090] Updated weights for policy 0, policy_version 39258 (0.0020) [2023-03-09 08:20:21,405][23090] Updated weights for policy 0, policy_version 39268 (0.0016) [2023-03-09 08:20:22,252][23090] Updated weights for policy 0, policy_version 39278 (0.0013) [2023-03-09 08:20:23,045][23090] Updated weights for policy 0, policy_version 39288 (0.0017) [2023-03-09 08:20:23,890][23090] Updated weights for policy 0, policy_version 39298 (0.0020) [2023-03-09 08:20:24,059][22664] Fps is (10 sec: 201523.6, 60 sec: 199611.7, 300 sec: 199218.3). Total num frames: 643907584. Throughput: 0: 49821.9. Samples: 161038048. Policy #0 lag: (min: 1.0, avg: 16.5, max: 33.0) [2023-03-09 08:20:24,061][22664] Avg episode reward: [(0, '51.492')] [2023-03-09 08:20:24,726][23090] Updated weights for policy 0, policy_version 39308 (0.0020) [2023-03-09 08:20:25,534][23090] Updated weights for policy 0, policy_version 39318 (0.0018) [2023-03-09 08:20:26,282][23090] Updated weights for policy 0, policy_version 39328 (0.0013) [2023-03-09 08:20:27,168][23090] Updated weights for policy 0, policy_version 39338 (0.0019) [2023-03-09 08:20:27,901][23090] Updated weights for policy 0, policy_version 39348 (0.0013) [2023-03-09 08:20:28,703][23090] Updated weights for policy 0, policy_version 39358 (0.0013) [2023-03-09 08:20:29,059][22664] Fps is (10 sec: 199889.7, 60 sec: 199339.1, 300 sec: 199107.2). Total num frames: 644890624. Throughput: 0: 49867.6. Samples: 161187536. Policy #0 lag: (min: 1.0, avg: 16.5, max: 33.0) [2023-03-09 08:20:29,060][22664] Avg episode reward: [(0, '50.226')] [2023-03-09 08:20:29,577][23090] Updated weights for policy 0, policy_version 39368 (0.0019) [2023-03-09 08:20:30,033][22940] Signal inference workers to stop experience collection... (12650 times) [2023-03-09 08:20:30,034][22940] Signal inference workers to resume experience collection... (12650 times) [2023-03-09 08:20:30,100][23090] InferenceWorker_p0-w0: stopping experience collection (12650 times) [2023-03-09 08:20:30,101][23090] InferenceWorker_p0-w0: resuming experience collection (12650 times) [2023-03-09 08:20:30,397][23090] Updated weights for policy 0, policy_version 39378 (0.0016) [2023-03-09 08:20:31,227][23090] Updated weights for policy 0, policy_version 39388 (0.0020) [2023-03-09 08:20:31,999][23090] Updated weights for policy 0, policy_version 39398 (0.0020) [2023-03-09 08:20:32,877][23090] Updated weights for policy 0, policy_version 39408 (0.0016) [2023-03-09 08:20:33,684][23090] Updated weights for policy 0, policy_version 39418 (0.0016) [2023-03-09 08:20:34,059][22664] Fps is (10 sec: 198239.4, 60 sec: 199064.8, 300 sec: 199106.9). Total num frames: 645890048. Throughput: 0: 49820.8. Samples: 161486448. Policy #0 lag: (min: 1.0, avg: 16.5, max: 33.0) [2023-03-09 08:20:34,061][22664] Avg episode reward: [(0, '51.775')] [2023-03-09 08:20:34,492][23090] Updated weights for policy 0, policy_version 39428 (0.0016) [2023-03-09 08:20:35,364][23090] Updated weights for policy 0, policy_version 39438 (0.0016) [2023-03-09 08:20:36,144][23090] Updated weights for policy 0, policy_version 39448 (0.0022) [2023-03-09 08:20:36,965][23090] Updated weights for policy 0, policy_version 39458 (0.0013) [2023-03-09 08:20:37,807][23090] Updated weights for policy 0, policy_version 39468 (0.0013) [2023-03-09 08:20:38,665][23090] Updated weights for policy 0, policy_version 39478 (0.0014) [2023-03-09 08:20:39,059][22664] Fps is (10 sec: 201513.7, 60 sec: 199609.9, 300 sec: 199218.2). Total num frames: 646905856. Throughput: 0: 49956.5. Samples: 161789424. Policy #0 lag: (min: 1.0, avg: 16.5, max: 33.0) [2023-03-09 08:20:39,061][22664] Avg episode reward: [(0, '52.725')] [2023-03-09 08:20:39,360][23090] Updated weights for policy 0, policy_version 39488 (0.0015) [2023-03-09 08:20:40,281][23090] Updated weights for policy 0, policy_version 39498 (0.0014) [2023-03-09 08:20:41,022][23090] Updated weights for policy 0, policy_version 39508 (0.0013) [2023-03-09 08:20:41,819][23090] Updated weights for policy 0, policy_version 39518 (0.0016) [2023-03-09 08:20:42,684][23090] Updated weights for policy 0, policy_version 39528 (0.0013) [2023-03-09 08:20:43,487][23090] Updated weights for policy 0, policy_version 39538 (0.0023) [2023-03-09 08:20:44,058][22664] Fps is (10 sec: 199897.8, 60 sec: 199338.8, 300 sec: 199162.9). Total num frames: 647888896. Throughput: 0: 49956.0. Samples: 161938880. Policy #0 lag: (min: 1.0, avg: 17.3, max: 33.0) [2023-03-09 08:20:44,059][22664] Avg episode reward: [(0, '50.587')] [2023-03-09 08:20:44,318][23090] Updated weights for policy 0, policy_version 39548 (0.0013) [2023-03-09 08:20:45,089][23090] Updated weights for policy 0, policy_version 39558 (0.0017) [2023-03-09 08:20:45,962][23090] Updated weights for policy 0, policy_version 39568 (0.0016) [2023-03-09 08:20:46,543][22940] Signal inference workers to stop experience collection... (12700 times) [2023-03-09 08:20:46,557][22940] Signal inference workers to resume experience collection... (12700 times) [2023-03-09 08:20:46,612][23090] InferenceWorker_p0-w0: stopping experience collection (12700 times) [2023-03-09 08:20:46,612][23090] InferenceWorker_p0-w0: resuming experience collection (12700 times) [2023-03-09 08:20:46,809][23090] Updated weights for policy 0, policy_version 39578 (0.0013) [2023-03-09 08:20:47,615][23090] Updated weights for policy 0, policy_version 39588 (0.0013) [2023-03-09 08:20:48,460][23090] Updated weights for policy 0, policy_version 39598 (0.0016) [2023-03-09 08:20:49,059][22664] Fps is (10 sec: 198256.9, 60 sec: 199612.5, 300 sec: 199218.5). Total num frames: 648888320. Throughput: 0: 49957.8. Samples: 162237840. Policy #0 lag: (min: 1.0, avg: 17.3, max: 33.0) [2023-03-09 08:20:49,059][22664] Avg episode reward: [(0, '53.552')] [2023-03-09 08:20:49,245][23090] Updated weights for policy 0, policy_version 39608 (0.0013) [2023-03-09 08:20:50,088][23090] Updated weights for policy 0, policy_version 39618 (0.0014) [2023-03-09 08:20:50,944][23090] Updated weights for policy 0, policy_version 39628 (0.0019) [2023-03-09 08:20:51,820][23090] Updated weights for policy 0, policy_version 39638 (0.0013) [2023-03-09 08:20:52,539][23090] Updated weights for policy 0, policy_version 39648 (0.0013) [2023-03-09 08:20:53,436][23090] Updated weights for policy 0, policy_version 39658 (0.0016) [2023-03-09 08:20:54,059][22664] Fps is (10 sec: 199872.2, 60 sec: 199611.2, 300 sec: 199218.0). Total num frames: 649887744. Throughput: 0: 49867.5. Samples: 162534768. Policy #0 lag: (min: 1.0, avg: 17.3, max: 33.0) [2023-03-09 08:20:54,062][22664] Avg episode reward: [(0, '52.510')] [2023-03-09 08:20:54,213][23090] Updated weights for policy 0, policy_version 39668 (0.0013) [2023-03-09 08:20:55,000][23090] Updated weights for policy 0, policy_version 39678 (0.0017) [2023-03-09 08:20:55,882][23090] Updated weights for policy 0, policy_version 39688 (0.0017) [2023-03-09 08:20:56,687][23090] Updated weights for policy 0, policy_version 39698 (0.0016) [2023-03-09 08:20:57,528][23090] Updated weights for policy 0, policy_version 39708 (0.0017) [2023-03-09 08:20:58,424][23090] Updated weights for policy 0, policy_version 39719 (0.0021) [2023-03-09 08:20:59,058][22664] Fps is (10 sec: 196609.2, 60 sec: 199065.8, 300 sec: 199107.3). Total num frames: 650854400. Throughput: 0: 49913.2. Samples: 162684240. Policy #0 lag: (min: 1.0, avg: 17.3, max: 33.0) [2023-03-09 08:20:59,059][22664] Avg episode reward: [(0, '52.778')] [2023-03-09 08:20:59,321][23090] Updated weights for policy 0, policy_version 39729 (0.0013) [2023-03-09 08:21:00,136][23090] Updated weights for policy 0, policy_version 39739 (0.0017) [2023-03-09 08:21:00,886][23090] Updated weights for policy 0, policy_version 39749 (0.0018) [2023-03-09 08:21:01,761][23090] Updated weights for policy 0, policy_version 39759 (0.0017) [2023-03-09 08:21:02,637][23090] Updated weights for policy 0, policy_version 39770 (0.0016) [2023-03-09 08:21:03,016][22940] Signal inference workers to stop experience collection... (12750 times) [2023-03-09 08:21:03,016][22940] Signal inference workers to resume experience collection... (12750 times) [2023-03-09 08:21:03,083][23090] InferenceWorker_p0-w0: stopping experience collection (12750 times) [2023-03-09 08:21:03,084][23090] InferenceWorker_p0-w0: resuming experience collection (12750 times) [2023-03-09 08:21:03,438][23090] Updated weights for policy 0, policy_version 39780 (0.0013) [2023-03-09 08:21:04,059][22664] Fps is (10 sec: 198253.2, 60 sec: 199338.2, 300 sec: 199218.3). Total num frames: 651870208. Throughput: 0: 49820.2. Samples: 162981056. Policy #0 lag: (min: 1.0, avg: 17.3, max: 33.0) [2023-03-09 08:21:04,061][22664] Avg episode reward: [(0, '51.800')] [2023-03-09 08:21:04,300][23090] Updated weights for policy 0, policy_version 39790 (0.0020) [2023-03-09 08:21:05,074][23090] Updated weights for policy 0, policy_version 39800 (0.0015) [2023-03-09 08:21:06,047][23090] Updated weights for policy 0, policy_version 39811 (0.0016) [2023-03-09 08:21:06,889][23090] Updated weights for policy 0, policy_version 39821 (0.0015) [2023-03-09 08:21:07,779][23090] Updated weights for policy 0, policy_version 39832 (0.0019) [2023-03-09 08:21:08,615][23090] Updated weights for policy 0, policy_version 39842 (0.0013) [2023-03-09 08:21:09,059][22664] Fps is (10 sec: 199877.9, 60 sec: 199337.7, 300 sec: 199107.0). Total num frames: 652853248. Throughput: 0: 49822.5. Samples: 163280064. Policy #0 lag: (min: 1.0, avg: 17.0, max: 33.0) [2023-03-09 08:21:09,061][22664] Avg episode reward: [(0, '53.669')] [2023-03-09 08:21:09,424][23090] Updated weights for policy 0, policy_version 39852 (0.0018) [2023-03-09 08:21:10,234][23090] Updated weights for policy 0, policy_version 39862 (0.0023) [2023-03-09 08:21:10,996][23090] Updated weights for policy 0, policy_version 39872 (0.0013) [2023-03-09 08:21:11,878][23090] Updated weights for policy 0, policy_version 39882 (0.0021) [2023-03-09 08:21:12,725][23090] Updated weights for policy 0, policy_version 39893 (0.0020) [2023-03-09 08:21:13,570][23090] Updated weights for policy 0, policy_version 39903 (0.0013) [2023-03-09 08:21:14,058][22664] Fps is (10 sec: 198251.5, 60 sec: 199339.6, 300 sec: 199162.8). Total num frames: 653852672. Throughput: 0: 49822.7. Samples: 163429552. Policy #0 lag: (min: 1.0, avg: 17.0, max: 33.0) [2023-03-09 08:21:14,059][22664] Avg episode reward: [(0, '52.196')] [2023-03-09 08:21:14,464][23090] Updated weights for policy 0, policy_version 39913 (0.0015) [2023-03-09 08:21:15,204][23090] Updated weights for policy 0, policy_version 39923 (0.0022) [2023-03-09 08:21:16,041][23090] Updated weights for policy 0, policy_version 39933 (0.0022) [2023-03-09 08:21:16,912][23090] Updated weights for policy 0, policy_version 39943 (0.0016) [2023-03-09 08:21:17,247][22940] Signal inference workers to stop experience collection... (12800 times) [2023-03-09 08:21:17,267][22940] Signal inference workers to resume experience collection... (12800 times) [2023-03-09 08:21:17,343][23090] InferenceWorker_p0-w0: stopping experience collection (12800 times) [2023-03-09 08:21:17,347][23090] InferenceWorker_p0-w0: resuming experience collection (12800 times) [2023-03-09 08:21:17,803][23090] Updated weights for policy 0, policy_version 39954 (0.0016) [2023-03-09 08:21:18,632][23090] Updated weights for policy 0, policy_version 39964 (0.0016) [2023-03-09 08:21:19,059][22664] Fps is (10 sec: 199887.7, 60 sec: 199339.2, 300 sec: 199107.2). Total num frames: 654852096. Throughput: 0: 49778.6. Samples: 163726464. Policy #0 lag: (min: 1.0, avg: 17.0, max: 33.0) [2023-03-09 08:21:19,060][22664] Avg episode reward: [(0, '53.660')] [2023-03-09 08:21:19,066][22940] Saving /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000039969_654852096.pth... [2023-03-09 08:21:19,131][22940] Removing /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000037054_607092736.pth [2023-03-09 08:21:19,415][23090] Updated weights for policy 0, policy_version 39974 (0.0022) [2023-03-09 08:21:20,274][23090] Updated weights for policy 0, policy_version 39984 (0.0013) [2023-03-09 08:21:21,084][23090] Updated weights for policy 0, policy_version 39994 (0.0017) [2023-03-09 08:21:21,919][23090] Updated weights for policy 0, policy_version 40004 (0.0016) [2023-03-09 08:21:22,804][23090] Updated weights for policy 0, policy_version 40014 (0.0014) [2023-03-09 08:21:23,563][23090] Updated weights for policy 0, policy_version 40024 (0.0013) [2023-03-09 08:21:24,059][22664] Fps is (10 sec: 199878.8, 60 sec: 199065.5, 300 sec: 199162.6). Total num frames: 655851520. Throughput: 0: 49689.5. Samples: 164025440. Policy #0 lag: (min: 1.0, avg: 17.0, max: 33.0) [2023-03-09 08:21:24,061][22664] Avg episode reward: [(0, '51.870')] [2023-03-09 08:21:24,401][23090] Updated weights for policy 0, policy_version 40034 (0.0016) [2023-03-09 08:21:25,247][23090] Updated weights for policy 0, policy_version 40044 (0.0013) [2023-03-09 08:21:26,134][23090] Updated weights for policy 0, policy_version 40054 (0.0013) [2023-03-09 08:21:26,825][23090] Updated weights for policy 0, policy_version 40064 (0.0015) [2023-03-09 08:21:27,770][23090] Updated weights for policy 0, policy_version 40074 (0.0020) [2023-03-09 08:21:28,476][23090] Updated weights for policy 0, policy_version 40084 (0.0023) [2023-03-09 08:21:29,058][22664] Fps is (10 sec: 198249.8, 60 sec: 199065.9, 300 sec: 199107.5). Total num frames: 656834560. Throughput: 0: 49689.9. Samples: 164174928. Policy #0 lag: (min: 1.0, avg: 17.0, max: 33.0) [2023-03-09 08:21:29,060][22664] Avg episode reward: [(0, '52.789')] [2023-03-09 08:21:29,291][23090] Updated weights for policy 0, policy_version 40094 (0.0017) [2023-03-09 08:21:29,757][22940] Signal inference workers to stop experience collection... (12850 times) [2023-03-09 08:21:29,772][22940] Signal inference workers to resume experience collection... (12850 times) [2023-03-09 08:21:29,836][23090] InferenceWorker_p0-w0: stopping experience collection (12850 times) [2023-03-09 08:21:29,836][23090] InferenceWorker_p0-w0: resuming experience collection (12850 times) [2023-03-09 08:21:30,248][23090] Updated weights for policy 0, policy_version 40104 (0.0017) [2023-03-09 08:21:31,025][23090] Updated weights for policy 0, policy_version 40115 (0.0013) [2023-03-09 08:21:31,867][23090] Updated weights for policy 0, policy_version 40125 (0.0021) [2023-03-09 08:21:32,754][23090] Updated weights for policy 0, policy_version 40135 (0.0016) [2023-03-09 08:21:33,564][23090] Updated weights for policy 0, policy_version 40146 (0.0017) [2023-03-09 08:21:34,058][22664] Fps is (10 sec: 198252.7, 60 sec: 199067.7, 300 sec: 199107.4). Total num frames: 657833984. Throughput: 0: 49643.8. Samples: 164471808. Policy #0 lag: (min: 1.0, avg: 17.1, max: 33.0) [2023-03-09 08:21:34,059][22664] Avg episode reward: [(0, '52.591')] [2023-03-09 08:21:34,464][23090] Updated weights for policy 0, policy_version 40157 (0.0013) [2023-03-09 08:21:35,351][23090] Updated weights for policy 0, policy_version 40167 (0.0013) [2023-03-09 08:21:36,236][23090] Updated weights for policy 0, policy_version 40178 (0.0016) [2023-03-09 08:21:37,048][23090] Updated weights for policy 0, policy_version 40188 (0.0016) [2023-03-09 08:21:37,857][23090] Updated weights for policy 0, policy_version 40198 (0.0015) [2023-03-09 08:21:38,677][23090] Updated weights for policy 0, policy_version 40208 (0.0024) [2023-03-09 08:21:39,059][22664] Fps is (10 sec: 201516.0, 60 sec: 199066.3, 300 sec: 199162.7). Total num frames: 658849792. Throughput: 0: 49734.7. Samples: 164772816. Policy #0 lag: (min: 1.0, avg: 17.1, max: 33.0) [2023-03-09 08:21:39,060][22664] Avg episode reward: [(0, '52.592')] [2023-03-09 08:21:39,552][23090] Updated weights for policy 0, policy_version 40218 (0.0013) [2023-03-09 08:21:40,316][23090] Updated weights for policy 0, policy_version 40228 (0.0013) [2023-03-09 08:21:41,230][23090] Updated weights for policy 0, policy_version 40238 (0.0017) [2023-03-09 08:21:41,853][22940] Signal inference workers to stop experience collection... (12900 times) [2023-03-09 08:21:41,853][22940] Signal inference workers to resume experience collection... (12900 times) [2023-03-09 08:21:41,904][23090] InferenceWorker_p0-w0: stopping experience collection (12900 times) [2023-03-09 08:21:41,904][23090] InferenceWorker_p0-w0: resuming experience collection (12900 times) [2023-03-09 08:21:41,988][23090] Updated weights for policy 0, policy_version 40248 (0.0019) [2023-03-09 08:21:42,794][23090] Updated weights for policy 0, policy_version 40258 (0.0013) [2023-03-09 08:21:43,632][23090] Updated weights for policy 0, policy_version 40268 (0.0016) [2023-03-09 08:21:44,059][22664] Fps is (10 sec: 199882.8, 60 sec: 199065.2, 300 sec: 199162.7). Total num frames: 659832832. Throughput: 0: 49734.3. Samples: 164922288. Policy #0 lag: (min: 1.0, avg: 17.1, max: 33.0) [2023-03-09 08:21:44,105][22664] Avg episode reward: [(0, '54.504')] [2023-03-09 08:21:44,462][23090] Updated weights for policy 0, policy_version 40278 (0.0013) [2023-03-09 08:21:45,192][23090] Updated weights for policy 0, policy_version 40288 (0.0019) [2023-03-09 08:21:46,143][23090] Updated weights for policy 0, policy_version 40298 (0.0018) [2023-03-09 08:21:46,840][23090] Updated weights for policy 0, policy_version 40308 (0.0017) [2023-03-09 08:21:47,668][23090] Updated weights for policy 0, policy_version 40318 (0.0013) [2023-03-09 08:21:48,560][23090] Updated weights for policy 0, policy_version 40328 (0.0013) [2023-03-09 08:21:49,058][22664] Fps is (10 sec: 196615.6, 60 sec: 198792.7, 300 sec: 199107.3). Total num frames: 660815872. Throughput: 0: 49827.2. Samples: 165223264. Policy #0 lag: (min: 1.0, avg: 17.1, max: 33.0) [2023-03-09 08:21:49,059][22664] Avg episode reward: [(0, '51.123')] [2023-03-09 08:21:49,363][23090] Updated weights for policy 0, policy_version 40338 (0.0013) [2023-03-09 08:21:50,174][23090] Updated weights for policy 0, policy_version 40348 (0.0021) [2023-03-09 08:21:50,951][23090] Updated weights for policy 0, policy_version 40358 (0.0018) [2023-03-09 08:21:51,781][23090] Updated weights for policy 0, policy_version 40368 (0.0013) [2023-03-09 08:21:52,692][23090] Updated weights for policy 0, policy_version 40378 (0.0016) [2023-03-09 08:21:52,994][22940] Signal inference workers to stop experience collection... (12950 times) [2023-03-09 08:21:52,995][22940] Signal inference workers to resume experience collection... (12950 times) [2023-03-09 08:21:53,052][23090] InferenceWorker_p0-w0: stopping experience collection (12950 times) [2023-03-09 08:21:53,052][23090] InferenceWorker_p0-w0: resuming experience collection (12950 times) [2023-03-09 08:21:53,418][23090] Updated weights for policy 0, policy_version 40388 (0.0013) [2023-03-09 08:21:54,059][22664] Fps is (10 sec: 198245.1, 60 sec: 198794.0, 300 sec: 199107.4). Total num frames: 661815296. Throughput: 0: 49826.7. Samples: 165522256. Policy #0 lag: (min: 1.0, avg: 17.1, max: 33.0) [2023-03-09 08:21:54,060][22664] Avg episode reward: [(0, '52.987')] [2023-03-09 08:21:54,344][23090] Updated weights for policy 0, policy_version 40398 (0.0016) [2023-03-09 08:21:55,082][23090] Updated weights for policy 0, policy_version 40408 (0.0023) [2023-03-09 08:21:55,990][23090] Updated weights for policy 0, policy_version 40418 (0.0013) [2023-03-09 08:21:56,749][23090] Updated weights for policy 0, policy_version 40428 (0.0013) [2023-03-09 08:21:57,565][23090] Updated weights for policy 0, policy_version 40438 (0.0013) [2023-03-09 08:21:58,335][23090] Updated weights for policy 0, policy_version 40448 (0.0019) [2023-03-09 08:21:59,059][22664] Fps is (10 sec: 199878.0, 60 sec: 199337.5, 300 sec: 199107.0). Total num frames: 662814720. Throughput: 0: 49871.6. Samples: 165673792. Policy #0 lag: (min: 1.0, avg: 16.7, max: 33.0) [2023-03-09 08:21:59,061][22664] Avg episode reward: [(0, '50.668')] [2023-03-09 08:21:59,297][23090] Updated weights for policy 0, policy_version 40458 (0.0020) [2023-03-09 08:21:59,956][23090] Updated weights for policy 0, policy_version 40468 (0.0016) [2023-03-09 08:22:00,798][23090] Updated weights for policy 0, policy_version 40478 (0.0021) [2023-03-09 08:22:01,687][23090] Updated weights for policy 0, policy_version 40488 (0.0022) [2023-03-09 08:22:02,485][23090] Updated weights for policy 0, policy_version 40498 (0.0019) [2023-03-09 08:22:03,188][22940] Signal inference workers to stop experience collection... (13000 times) [2023-03-09 08:22:03,193][22940] Signal inference workers to resume experience collection... (13000 times) [2023-03-09 08:22:03,260][23090] InferenceWorker_p0-w0: stopping experience collection (13000 times) [2023-03-09 08:22:03,261][23090] InferenceWorker_p0-w0: resuming experience collection (13000 times) [2023-03-09 08:22:03,301][23090] Updated weights for policy 0, policy_version 40508 (0.0021) [2023-03-09 08:22:04,058][22664] Fps is (10 sec: 201527.1, 60 sec: 199339.7, 300 sec: 199162.9). Total num frames: 663830528. Throughput: 0: 49872.2. Samples: 165970704. Policy #0 lag: (min: 1.0, avg: 16.7, max: 33.0) [2023-03-09 08:22:04,059][22664] Avg episode reward: [(0, '51.956')] [2023-03-09 08:22:04,275][23090] Updated weights for policy 0, policy_version 40519 (0.0020) [2023-03-09 08:22:05,049][23090] Updated weights for policy 0, policy_version 40529 (0.0016) [2023-03-09 08:22:05,928][23090] Updated weights for policy 0, policy_version 40539 (0.0020) [2023-03-09 08:22:06,760][23090] Updated weights for policy 0, policy_version 40550 (0.0015) [2023-03-09 08:22:07,637][23090] Updated weights for policy 0, policy_version 40560 (0.0013) [2023-03-09 08:22:08,448][23090] Updated weights for policy 0, policy_version 40570 (0.0013) [2023-03-09 08:22:09,059][22664] Fps is (10 sec: 199887.4, 60 sec: 199339.1, 300 sec: 199107.1). Total num frames: 664813568. Throughput: 0: 49826.3. Samples: 166267616. Policy #0 lag: (min: 1.0, avg: 16.7, max: 33.0) [2023-03-09 08:22:09,060][22664] Avg episode reward: [(0, '55.037')] [2023-03-09 08:22:09,243][23090] Updated weights for policy 0, policy_version 40580 (0.0016) [2023-03-09 08:22:10,131][23090] Updated weights for policy 0, policy_version 40590 (0.0016) [2023-03-09 08:22:10,921][23090] Updated weights for policy 0, policy_version 40600 (0.0024) [2023-03-09 08:22:11,745][23090] Updated weights for policy 0, policy_version 40610 (0.0013) [2023-03-09 08:22:12,567][23090] Updated weights for policy 0, policy_version 40620 (0.0016) [2023-03-09 08:22:13,393][23090] Updated weights for policy 0, policy_version 40630 (0.0013) [2023-03-09 08:22:14,058][22664] Fps is (10 sec: 198246.2, 60 sec: 199338.8, 300 sec: 199107.5). Total num frames: 665812992. Throughput: 0: 49826.5. Samples: 166417120. Policy #0 lag: (min: 1.0, avg: 16.7, max: 33.0) [2023-03-09 08:22:14,060][22664] Avg episode reward: [(0, '52.340')] [2023-03-09 08:22:14,158][23090] Updated weights for policy 0, policy_version 40640 (0.0016) [2023-03-09 08:22:14,453][22940] Signal inference workers to stop experience collection... (13050 times) [2023-03-09 08:22:14,475][22940] Signal inference workers to resume experience collection... (13050 times) [2023-03-09 08:22:14,510][23090] InferenceWorker_p0-w0: stopping experience collection (13050 times) [2023-03-09 08:22:14,550][23090] InferenceWorker_p0-w0: resuming experience collection (13050 times) [2023-03-09 08:22:15,109][23090] Updated weights for policy 0, policy_version 40650 (0.0013) [2023-03-09 08:22:15,797][23090] Updated weights for policy 0, policy_version 40660 (0.0018) [2023-03-09 08:22:16,615][23090] Updated weights for policy 0, policy_version 40670 (0.0016) [2023-03-09 08:22:17,503][23090] Updated weights for policy 0, policy_version 40680 (0.0023) [2023-03-09 08:22:18,387][23090] Updated weights for policy 0, policy_version 40691 (0.0023) [2023-03-09 08:22:19,059][22664] Fps is (10 sec: 199883.1, 60 sec: 199338.3, 300 sec: 199107.3). Total num frames: 666812416. Throughput: 0: 49872.7. Samples: 166716096. Policy #0 lag: (min: 1.0, avg: 16.7, max: 33.0) [2023-03-09 08:22:19,061][22664] Avg episode reward: [(0, '53.602')] [2023-03-09 08:22:19,180][23090] Updated weights for policy 0, policy_version 40701 (0.0019) [2023-03-09 08:22:20,029][23090] Updated weights for policy 0, policy_version 40711 (0.0017) [2023-03-09 08:22:20,874][23090] Updated weights for policy 0, policy_version 40721 (0.0020) [2023-03-09 08:22:21,678][23090] Updated weights for policy 0, policy_version 40731 (0.0013) [2023-03-09 08:22:22,485][23090] Updated weights for policy 0, policy_version 40741 (0.0016) [2023-03-09 08:22:23,338][23090] Updated weights for policy 0, policy_version 40751 (0.0015) [2023-03-09 08:22:24,059][22664] Fps is (10 sec: 199883.8, 60 sec: 199339.6, 300 sec: 199162.9). Total num frames: 667811840. Throughput: 0: 49873.4. Samples: 167017104. Policy #0 lag: (min: 2.0, avg: 17.2, max: 33.0) [2023-03-09 08:22:24,060][22664] Avg episode reward: [(0, '50.944')] [2023-03-09 08:22:24,111][23090] Updated weights for policy 0, policy_version 40761 (0.0013) [2023-03-09 08:22:24,946][22940] Signal inference workers to stop experience collection... (13100 times) [2023-03-09 08:22:24,966][22940] Signal inference workers to resume experience collection... (13100 times) [2023-03-09 08:22:24,974][23090] Updated weights for policy 0, policy_version 40771 (0.0013) [2023-03-09 08:22:25,014][23090] InferenceWorker_p0-w0: stopping experience collection (13100 times) [2023-03-09 08:22:25,014][23090] InferenceWorker_p0-w0: resuming experience collection (13100 times) [2023-03-09 08:22:25,805][23090] Updated weights for policy 0, policy_version 40781 (0.0018) [2023-03-09 08:22:26,640][23090] Updated weights for policy 0, policy_version 40791 (0.0020) [2023-03-09 08:22:27,334][23090] Updated weights for policy 0, policy_version 40801 (0.0013) [2023-03-09 08:22:28,257][23090] Updated weights for policy 0, policy_version 40811 (0.0021) [2023-03-09 08:22:28,982][23090] Updated weights for policy 0, policy_version 40821 (0.0017) [2023-03-09 08:22:29,059][22664] Fps is (10 sec: 199885.6, 60 sec: 199611.0, 300 sec: 199107.3). Total num frames: 668811264. Throughput: 0: 49873.3. Samples: 167166592. Policy #0 lag: (min: 2.0, avg: 17.2, max: 33.0) [2023-03-09 08:22:29,061][22664] Avg episode reward: [(0, '50.351')] [2023-03-09 08:22:29,825][23090] Updated weights for policy 0, policy_version 40831 (0.0017) [2023-03-09 08:22:30,663][23090] Updated weights for policy 0, policy_version 40841 (0.0013) [2023-03-09 08:22:31,457][23090] Updated weights for policy 0, policy_version 40851 (0.0019) [2023-03-09 08:22:32,259][23090] Updated weights for policy 0, policy_version 40861 (0.0013) [2023-03-09 08:22:33,131][23090] Updated weights for policy 0, policy_version 40871 (0.0013) [2023-03-09 08:22:33,930][23090] Updated weights for policy 0, policy_version 40881 (0.0013) [2023-03-09 08:22:34,059][22664] Fps is (10 sec: 199879.2, 60 sec: 199610.7, 300 sec: 199162.6). Total num frames: 669810688. Throughput: 0: 49873.8. Samples: 167467600. Policy #0 lag: (min: 2.0, avg: 17.2, max: 33.0) [2023-03-09 08:22:34,061][22664] Avg episode reward: [(0, '51.078')] [2023-03-09 08:22:34,699][22940] Signal inference workers to stop experience collection... (13150 times) [2023-03-09 08:22:34,700][22940] Signal inference workers to resume experience collection... (13150 times) [2023-03-09 08:22:34,771][23090] InferenceWorker_p0-w0: stopping experience collection (13150 times) [2023-03-09 08:22:34,774][23090] InferenceWorker_p0-w0: resuming experience collection (13150 times) [2023-03-09 08:22:34,777][23090] Updated weights for policy 0, policy_version 40891 (0.0013) [2023-03-09 08:22:35,553][23090] Updated weights for policy 0, policy_version 40901 (0.0013) [2023-03-09 08:22:36,450][23090] Updated weights for policy 0, policy_version 40911 (0.0016) [2023-03-09 08:22:37,184][23090] Updated weights for policy 0, policy_version 40921 (0.0021) [2023-03-09 08:22:38,097][23090] Updated weights for policy 0, policy_version 40932 (0.0013) [2023-03-09 08:22:39,012][23090] Updated weights for policy 0, policy_version 40942 (0.0016) [2023-03-09 08:22:39,059][22664] Fps is (10 sec: 199879.6, 60 sec: 199338.2, 300 sec: 199218.0). Total num frames: 670810112. Throughput: 0: 49916.1. Samples: 167768496. Policy #0 lag: (min: 2.0, avg: 17.2, max: 33.0) [2023-03-09 08:22:39,061][22664] Avg episode reward: [(0, '53.872')] [2023-03-09 08:22:39,780][23090] Updated weights for policy 0, policy_version 40952 (0.0013) [2023-03-09 08:22:40,633][23090] Updated weights for policy 0, policy_version 40962 (0.0016) [2023-03-09 08:22:41,395][23090] Updated weights for policy 0, policy_version 40972 (0.0013) [2023-03-09 08:22:42,229][23090] Updated weights for policy 0, policy_version 40982 (0.0013) [2023-03-09 08:22:42,684][22940] Signal inference workers to stop experience collection... (13200 times) [2023-03-09 08:22:42,684][22940] Signal inference workers to resume experience collection... (13200 times) [2023-03-09 08:22:42,757][23090] InferenceWorker_p0-w0: stopping experience collection (13200 times) [2023-03-09 08:22:42,757][23090] InferenceWorker_p0-w0: resuming experience collection (13200 times) [2023-03-09 08:22:42,963][23090] Updated weights for policy 0, policy_version 40992 (0.0016) [2023-03-09 08:22:43,947][23090] Updated weights for policy 0, policy_version 41002 (0.0013) [2023-03-09 08:22:44,058][22664] Fps is (10 sec: 199891.6, 60 sec: 199612.1, 300 sec: 199218.4). Total num frames: 671809536. Throughput: 0: 49871.7. Samples: 167918000. Policy #0 lag: (min: 2.0, avg: 17.2, max: 33.0) [2023-03-09 08:22:44,059][22664] Avg episode reward: [(0, '54.360')] [2023-03-09 08:22:44,685][23090] Updated weights for policy 0, policy_version 41012 (0.0013) [2023-03-09 08:22:45,450][23090] Updated weights for policy 0, policy_version 41022 (0.0021) [2023-03-09 08:22:46,336][23090] Updated weights for policy 0, policy_version 41032 (0.0013) [2023-03-09 08:22:47,197][23090] Updated weights for policy 0, policy_version 41043 (0.0013) [2023-03-09 08:22:48,002][23090] Updated weights for policy 0, policy_version 41053 (0.0017) [2023-03-09 08:22:48,848][23090] Updated weights for policy 0, policy_version 41063 (0.0013) [2023-03-09 08:22:49,059][22664] Fps is (10 sec: 199890.5, 60 sec: 199884.0, 300 sec: 199218.2). Total num frames: 672808960. Throughput: 0: 49915.4. Samples: 168216912. Policy #0 lag: (min: 2.0, avg: 17.2, max: 33.0) [2023-03-09 08:22:49,060][22664] Avg episode reward: [(0, '52.889')] [2023-03-09 08:22:49,654][23090] Updated weights for policy 0, policy_version 41073 (0.0017) [2023-03-09 08:22:50,511][23090] Updated weights for policy 0, policy_version 41083 (0.0016) [2023-03-09 08:22:51,240][23090] Updated weights for policy 0, policy_version 41093 (0.0016) [2023-03-09 08:22:51,581][22940] Signal inference workers to stop experience collection... (13250 times) [2023-03-09 08:22:51,582][22940] Signal inference workers to resume experience collection... (13250 times) [2023-03-09 08:22:51,642][23090] InferenceWorker_p0-w0: stopping experience collection (13250 times) [2023-03-09 08:22:51,642][23090] InferenceWorker_p0-w0: resuming experience collection (13250 times) [2023-03-09 08:22:52,192][23090] Updated weights for policy 0, policy_version 41103 (0.0016) [2023-03-09 08:22:52,920][23090] Updated weights for policy 0, policy_version 41113 (0.0017) [2023-03-09 08:22:53,789][23090] Updated weights for policy 0, policy_version 41123 (0.0013) [2023-03-09 08:22:54,058][22664] Fps is (10 sec: 199884.3, 60 sec: 199885.3, 300 sec: 199218.6). Total num frames: 673808384. Throughput: 0: 50005.9. Samples: 168517872. Policy #0 lag: (min: 1.0, avg: 16.4, max: 33.0) [2023-03-09 08:22:54,060][22664] Avg episode reward: [(0, '51.695')] [2023-03-09 08:22:54,594][23090] Updated weights for policy 0, policy_version 41133 (0.0014) [2023-03-09 08:22:55,410][23090] Updated weights for policy 0, policy_version 41143 (0.0013) [2023-03-09 08:22:56,210][23090] Updated weights for policy 0, policy_version 41153 (0.0013) [2023-03-09 08:22:57,089][23090] Updated weights for policy 0, policy_version 41163 (0.0015) [2023-03-09 08:22:57,823][23090] Updated weights for policy 0, policy_version 41173 (0.0016) [2023-03-09 08:22:58,686][23090] Updated weights for policy 0, policy_version 41184 (0.0019) [2023-03-09 08:22:59,059][22664] Fps is (10 sec: 201522.5, 60 sec: 200158.1, 300 sec: 199273.9). Total num frames: 674824192. Throughput: 0: 50004.7. Samples: 168667344. Policy #0 lag: (min: 1.0, avg: 16.4, max: 33.0) [2023-03-09 08:22:59,061][22664] Avg episode reward: [(0, '52.379')] [2023-03-09 08:22:59,654][23090] Updated weights for policy 0, policy_version 41194 (0.0015) [2023-03-09 08:23:00,391][23090] Updated weights for policy 0, policy_version 41204 (0.0013) [2023-03-09 08:23:00,402][22940] Signal inference workers to stop experience collection... (13300 times) [2023-03-09 08:23:00,403][22940] Signal inference workers to resume experience collection... (13300 times) [2023-03-09 08:23:00,467][23090] InferenceWorker_p0-w0: stopping experience collection (13300 times) [2023-03-09 08:23:00,467][23090] InferenceWorker_p0-w0: resuming experience collection (13300 times) [2023-03-09 08:23:01,182][23090] Updated weights for policy 0, policy_version 41214 (0.0013) [2023-03-09 08:23:02,104][23090] Updated weights for policy 0, policy_version 41224 (0.0013) [2023-03-09 08:23:02,882][23090] Updated weights for policy 0, policy_version 41234 (0.0016) [2023-03-09 08:23:03,740][23090] Updated weights for policy 0, policy_version 41245 (0.0016) [2023-03-09 08:23:04,059][22664] Fps is (10 sec: 199882.2, 60 sec: 199611.2, 300 sec: 199163.0). Total num frames: 675807232. Throughput: 0: 50005.5. Samples: 168966336. Policy #0 lag: (min: 1.0, avg: 16.4, max: 33.0) [2023-03-09 08:23:04,061][22664] Avg episode reward: [(0, '53.419')] [2023-03-09 08:23:04,586][23090] Updated weights for policy 0, policy_version 41255 (0.0017) [2023-03-09 08:23:05,400][23090] Updated weights for policy 0, policy_version 41265 (0.0017) [2023-03-09 08:23:06,237][23090] Updated weights for policy 0, policy_version 41275 (0.0013) [2023-03-09 08:23:07,006][23090] Updated weights for policy 0, policy_version 41285 (0.0016) [2023-03-09 08:23:07,887][23090] Updated weights for policy 0, policy_version 41295 (0.0018) [2023-03-09 08:23:08,644][23090] Updated weights for policy 0, policy_version 41305 (0.0018) [2023-03-09 08:23:09,059][22664] Fps is (10 sec: 199883.0, 60 sec: 200157.3, 300 sec: 199273.8). Total num frames: 676823040. Throughput: 0: 50005.3. Samples: 169267360. Policy #0 lag: (min: 1.0, avg: 16.4, max: 33.0) [2023-03-09 08:23:09,060][22664] Avg episode reward: [(0, '53.251')] [2023-03-09 08:23:09,563][23090] Updated weights for policy 0, policy_version 41316 (0.0017) [2023-03-09 08:23:10,556][23090] Updated weights for policy 0, policy_version 41327 (0.0016) [2023-03-09 08:23:10,733][22940] Signal inference workers to stop experience collection... (13350 times) [2023-03-09 08:23:10,755][22940] Signal inference workers to resume experience collection... (13350 times) [2023-03-09 08:23:10,802][23090] InferenceWorker_p0-w0: stopping experience collection (13350 times) [2023-03-09 08:23:10,802][23090] InferenceWorker_p0-w0: resuming experience collection (13350 times) [2023-03-09 08:23:11,321][23090] Updated weights for policy 0, policy_version 41337 (0.0017) [2023-03-09 08:23:12,199][23090] Updated weights for policy 0, policy_version 41347 (0.0014) [2023-03-09 08:23:13,075][23090] Updated weights for policy 0, policy_version 41357 (0.0019) [2023-03-09 08:23:13,903][23090] Updated weights for policy 0, policy_version 41367 (0.0013) [2023-03-09 08:23:14,059][22664] Fps is (10 sec: 198239.2, 60 sec: 199610.0, 300 sec: 199163.0). Total num frames: 677789696. Throughput: 0: 49959.9. Samples: 169414800. Policy #0 lag: (min: 1.0, avg: 16.4, max: 33.0) [2023-03-09 08:23:14,061][22664] Avg episode reward: [(0, '53.864')] [2023-03-09 08:23:14,655][23090] Updated weights for policy 0, policy_version 41377 (0.0017) [2023-03-09 08:23:15,545][23090] Updated weights for policy 0, policy_version 41387 (0.0023) [2023-03-09 08:23:16,259][23090] Updated weights for policy 0, policy_version 41397 (0.0013) [2023-03-09 08:23:17,088][23090] Updated weights for policy 0, policy_version 41407 (0.0019) [2023-03-09 08:23:17,939][23090] Updated weights for policy 0, policy_version 41417 (0.0016) [2023-03-09 08:23:18,709][23090] Updated weights for policy 0, policy_version 41427 (0.0020) [2023-03-09 08:23:19,059][22664] Fps is (10 sec: 196612.2, 60 sec: 199612.2, 300 sec: 199162.8). Total num frames: 678789120. Throughput: 0: 49915.6. Samples: 169713792. Policy #0 lag: (min: 2.0, avg: 16.9, max: 33.0) [2023-03-09 08:23:19,060][22664] Avg episode reward: [(0, '52.606')] [2023-03-09 08:23:19,110][22940] Saving /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000041432_678821888.pth... [2023-03-09 08:23:19,173][22940] Removing /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000038511_630964224.pth [2023-03-09 08:23:19,514][23090] Updated weights for policy 0, policy_version 41437 (0.0022) [2023-03-09 08:23:20,386][23090] Updated weights for policy 0, policy_version 41447 (0.0016) [2023-03-09 08:23:21,203][23090] Updated weights for policy 0, policy_version 41457 (0.0015) [2023-03-09 08:23:21,996][23090] Updated weights for policy 0, policy_version 41467 (0.0017) [2023-03-09 08:23:22,799][23090] Updated weights for policy 0, policy_version 41477 (0.0015) [2023-03-09 08:23:23,341][22940] Signal inference workers to stop experience collection... (13400 times) [2023-03-09 08:23:23,342][22940] Signal inference workers to resume experience collection... (13400 times) [2023-03-09 08:23:23,409][23090] InferenceWorker_p0-w0: stopping experience collection (13400 times) [2023-03-09 08:23:23,409][23090] InferenceWorker_p0-w0: resuming experience collection (13400 times) [2023-03-09 08:23:23,730][23090] Updated weights for policy 0, policy_version 41487 (0.0013) [2023-03-09 08:23:24,059][22664] Fps is (10 sec: 199889.7, 60 sec: 199611.0, 300 sec: 199218.3). Total num frames: 679788544. Throughput: 0: 49873.4. Samples: 170012784. Policy #0 lag: (min: 2.0, avg: 16.9, max: 33.0) [2023-03-09 08:23:24,061][22664] Avg episode reward: [(0, '49.897')] [2023-03-09 08:23:24,466][23090] Updated weights for policy 0, policy_version 41497 (0.0018) [2023-03-09 08:23:25,356][23090] Updated weights for policy 0, policy_version 41507 (0.0013) [2023-03-09 08:23:26,134][23090] Updated weights for policy 0, policy_version 41517 (0.0021) [2023-03-09 08:23:26,972][23090] Updated weights for policy 0, policy_version 41527 (0.0017) [2023-03-09 08:23:27,749][23090] Updated weights for policy 0, policy_version 41537 (0.0017) [2023-03-09 08:23:28,668][23090] Updated weights for policy 0, policy_version 41547 (0.0021) [2023-03-09 08:23:29,059][22664] Fps is (10 sec: 199886.2, 60 sec: 199612.3, 300 sec: 199274.0). Total num frames: 680787968. Throughput: 0: 49872.6. Samples: 170162272. Policy #0 lag: (min: 2.0, avg: 16.9, max: 33.0) [2023-03-09 08:23:29,059][22664] Avg episode reward: [(0, '51.364')] [2023-03-09 08:23:29,402][23090] Updated weights for policy 0, policy_version 41557 (0.0016) [2023-03-09 08:23:30,244][23090] Updated weights for policy 0, policy_version 41567 (0.0019) [2023-03-09 08:23:31,088][23090] Updated weights for policy 0, policy_version 41577 (0.0019) [2023-03-09 08:23:31,886][23090] Updated weights for policy 0, policy_version 41587 (0.0016) [2023-03-09 08:23:32,850][23090] Updated weights for policy 0, policy_version 41598 (0.0021) [2023-03-09 08:23:33,670][23090] Updated weights for policy 0, policy_version 41608 (0.0020) [2023-03-09 08:23:34,058][22664] Fps is (10 sec: 198251.4, 60 sec: 199339.7, 300 sec: 199218.4). Total num frames: 681771008. Throughput: 0: 49828.5. Samples: 170459184. Policy #0 lag: (min: 2.0, avg: 16.9, max: 33.0) [2023-03-09 08:23:34,059][22664] Avg episode reward: [(0, '52.978')] [2023-03-09 08:23:34,489][23090] Updated weights for policy 0, policy_version 41618 (0.0013) [2023-03-09 08:23:34,929][22940] Signal inference workers to stop experience collection... (13450 times) [2023-03-09 08:23:34,930][22940] Signal inference workers to resume experience collection... (13450 times) [2023-03-09 08:23:34,993][23090] InferenceWorker_p0-w0: stopping experience collection (13450 times) [2023-03-09 08:23:34,994][23090] InferenceWorker_p0-w0: resuming experience collection (13450 times) [2023-03-09 08:23:35,281][23090] Updated weights for policy 0, policy_version 41628 (0.0017) [2023-03-09 08:23:36,125][23090] Updated weights for policy 0, policy_version 41638 (0.0018) [2023-03-09 08:23:36,977][23090] Updated weights for policy 0, policy_version 41648 (0.0013) [2023-03-09 08:23:37,778][23090] Updated weights for policy 0, policy_version 41658 (0.0013) [2023-03-09 08:23:38,595][23090] Updated weights for policy 0, policy_version 41668 (0.0016) [2023-03-09 08:23:39,058][22664] Fps is (10 sec: 198248.0, 60 sec: 199340.4, 300 sec: 199218.5). Total num frames: 682770432. Throughput: 0: 49784.2. Samples: 170758160. Policy #0 lag: (min: 2.0, avg: 16.9, max: 33.0) [2023-03-09 08:23:39,059][22664] Avg episode reward: [(0, '53.685')] [2023-03-09 08:23:39,514][23090] Updated weights for policy 0, policy_version 41678 (0.0014) [2023-03-09 08:23:40,238][23090] Updated weights for policy 0, policy_version 41688 (0.0013) [2023-03-09 08:23:41,083][23090] Updated weights for policy 0, policy_version 41698 (0.0016) [2023-03-09 08:23:41,902][23090] Updated weights for policy 0, policy_version 41708 (0.0018) [2023-03-09 08:23:42,774][23090] Updated weights for policy 0, policy_version 41718 (0.0017) [2023-03-09 08:23:43,532][23090] Updated weights for policy 0, policy_version 41728 (0.0016) [2023-03-09 08:23:44,059][22664] Fps is (10 sec: 199879.9, 60 sec: 199337.8, 300 sec: 199273.7). Total num frames: 683769856. Throughput: 0: 49784.2. Samples: 170907632. Policy #0 lag: (min: 1.0, avg: 16.4, max: 33.0) [2023-03-09 08:23:44,060][22664] Avg episode reward: [(0, '51.094')] [2023-03-09 08:23:44,522][23090] Updated weights for policy 0, policy_version 41738 (0.0013) [2023-03-09 08:23:45,227][23090] Updated weights for policy 0, policy_version 41748 (0.0015) [2023-03-09 08:23:46,055][23090] Updated weights for policy 0, policy_version 41758 (0.0017) [2023-03-09 08:23:46,896][23090] Updated weights for policy 0, policy_version 41768 (0.0013) [2023-03-09 08:23:47,690][23090] Updated weights for policy 0, policy_version 41778 (0.0013) [2023-03-09 08:23:48,506][23090] Updated weights for policy 0, policy_version 41788 (0.0015) [2023-03-09 08:23:49,059][22664] Fps is (10 sec: 198241.7, 60 sec: 199065.6, 300 sec: 199162.9). Total num frames: 684752896. Throughput: 0: 49688.4. Samples: 171202320. Policy #0 lag: (min: 1.0, avg: 16.4, max: 33.0) [2023-03-09 08:23:49,061][22664] Avg episode reward: [(0, '51.985')] [2023-03-09 08:23:49,069][22940] Signal inference workers to stop experience collection... (13500 times) [2023-03-09 08:23:49,082][22940] Signal inference workers to resume experience collection... (13500 times) [2023-03-09 08:23:49,144][23090] InferenceWorker_p0-w0: stopping experience collection (13500 times) [2023-03-09 08:23:49,144][23090] InferenceWorker_p0-w0: resuming experience collection (13500 times) [2023-03-09 08:23:49,271][23090] Updated weights for policy 0, policy_version 41798 (0.0015) [2023-03-09 08:23:50,145][23090] Updated weights for policy 0, policy_version 41808 (0.0016) [2023-03-09 08:23:50,983][23090] Updated weights for policy 0, policy_version 41818 (0.0021) [2023-03-09 08:23:51,802][23090] Updated weights for policy 0, policy_version 41828 (0.0015) [2023-03-09 08:23:52,690][23090] Updated weights for policy 0, policy_version 41838 (0.0013) [2023-03-09 08:23:53,488][23090] Updated weights for policy 0, policy_version 41848 (0.0015) [2023-03-09 08:23:54,059][22664] Fps is (10 sec: 199883.0, 60 sec: 199337.6, 300 sec: 199218.4). Total num frames: 685768704. Throughput: 0: 49683.6. Samples: 171503120. Policy #0 lag: (min: 1.0, avg: 16.4, max: 33.0) [2023-03-09 08:23:54,061][22664] Avg episode reward: [(0, '53.404')] [2023-03-09 08:23:54,259][23090] Updated weights for policy 0, policy_version 41858 (0.0015) [2023-03-09 08:23:55,214][23090] Updated weights for policy 0, policy_version 41869 (0.0013) [2023-03-09 08:23:56,073][23090] Updated weights for policy 0, policy_version 41879 (0.0016) [2023-03-09 08:23:56,794][23090] Updated weights for policy 0, policy_version 41889 (0.0018) [2023-03-09 08:23:57,715][23090] Updated weights for policy 0, policy_version 41899 (0.0016) [2023-03-09 08:23:58,451][23090] Updated weights for policy 0, policy_version 41909 (0.0017) [2023-03-09 08:23:59,059][22664] Fps is (10 sec: 199881.0, 60 sec: 198792.0, 300 sec: 199218.1). Total num frames: 686751744. Throughput: 0: 49682.2. Samples: 171650496. Policy #0 lag: (min: 1.0, avg: 16.4, max: 33.0) [2023-03-09 08:23:59,061][22664] Avg episode reward: [(0, '51.634')] [2023-03-09 08:23:59,299][23090] Updated weights for policy 0, policy_version 41919 (0.0015) [2023-03-09 08:24:00,151][23090] Updated weights for policy 0, policy_version 41929 (0.0016) [2023-03-09 08:24:00,993][23090] Updated weights for policy 0, policy_version 41939 (0.0019) [2023-03-09 08:24:01,791][23090] Updated weights for policy 0, policy_version 41949 (0.0018) [2023-03-09 08:24:02,613][23090] Updated weights for policy 0, policy_version 41959 (0.0020) [2023-03-09 08:24:03,424][23090] Updated weights for policy 0, policy_version 41969 (0.0013) [2023-03-09 08:24:04,059][22664] Fps is (10 sec: 198247.2, 60 sec: 199065.1, 300 sec: 199218.3). Total num frames: 687751168. Throughput: 0: 49679.8. Samples: 171949392. Policy #0 lag: (min: 1.0, avg: 16.4, max: 33.0) [2023-03-09 08:24:04,061][22664] Avg episode reward: [(0, '51.986')] [2023-03-09 08:24:04,205][23090] Updated weights for policy 0, policy_version 41979 (0.0017) [2023-03-09 08:24:04,341][22940] Signal inference workers to stop experience collection... (13550 times) [2023-03-09 08:24:04,342][22940] Signal inference workers to resume experience collection... (13550 times) [2023-03-09 08:24:04,405][23090] InferenceWorker_p0-w0: stopping experience collection (13550 times) [2023-03-09 08:24:04,405][23090] InferenceWorker_p0-w0: resuming experience collection (13550 times) [2023-03-09 08:24:05,058][23090] Updated weights for policy 0, policy_version 41989 (0.0016) [2023-03-09 08:24:05,890][23090] Updated weights for policy 0, policy_version 41999 (0.0017) [2023-03-09 08:24:06,705][23090] Updated weights for policy 0, policy_version 42009 (0.0014) [2023-03-09 08:24:07,565][23090] Updated weights for policy 0, policy_version 42019 (0.0017) [2023-03-09 08:24:08,393][23090] Updated weights for policy 0, policy_version 42029 (0.0013) [2023-03-09 08:24:09,059][22664] Fps is (10 sec: 198252.9, 60 sec: 198520.4, 300 sec: 199218.4). Total num frames: 688734208. Throughput: 0: 49670.6. Samples: 172247952. Policy #0 lag: (min: 2.0, avg: 16.9, max: 33.0) [2023-03-09 08:24:09,060][22664] Avg episode reward: [(0, '51.849')] [2023-03-09 08:24:09,209][23090] Updated weights for policy 0, policy_version 42039 (0.0017) [2023-03-09 08:24:10,105][23090] Updated weights for policy 0, policy_version 42050 (0.0015) [2023-03-09 08:24:10,950][23090] Updated weights for policy 0, policy_version 42060 (0.0016) [2023-03-09 08:24:11,822][23090] Updated weights for policy 0, policy_version 42070 (0.0018) [2023-03-09 08:24:12,538][23090] Updated weights for policy 0, policy_version 42080 (0.0015) [2023-03-09 08:24:13,481][23090] Updated weights for policy 0, policy_version 42090 (0.0013) [2023-03-09 08:24:14,058][22664] Fps is (10 sec: 198252.8, 60 sec: 199067.4, 300 sec: 199273.9). Total num frames: 689733632. Throughput: 0: 49663.8. Samples: 172397136. Policy #0 lag: (min: 2.0, avg: 16.9, max: 33.0) [2023-03-09 08:24:14,059][22664] Avg episode reward: [(0, '51.169')] [2023-03-09 08:24:14,235][23090] Updated weights for policy 0, policy_version 42100 (0.0026) [2023-03-09 08:24:15,056][23090] Updated weights for policy 0, policy_version 42110 (0.0018) [2023-03-09 08:24:15,918][23090] Updated weights for policy 0, policy_version 42120 (0.0016) [2023-03-09 08:24:16,696][23090] Updated weights for policy 0, policy_version 42130 (0.0013) [2023-03-09 08:24:17,528][23090] Updated weights for policy 0, policy_version 42140 (0.0022) [2023-03-09 08:24:18,314][23090] Updated weights for policy 0, policy_version 42150 (0.0017) [2023-03-09 08:24:19,066][22664] Fps is (10 sec: 196466.9, 60 sec: 198495.9, 300 sec: 199213.6). Total num frames: 690700288. Throughput: 0: 49649.6. Samples: 172693776. Policy #0 lag: (min: 2.0, avg: 16.9, max: 33.0) [2023-03-09 08:24:19,068][22664] Avg episode reward: [(0, '51.083')] [2023-03-09 08:24:19,251][23090] Updated weights for policy 0, policy_version 42160 (0.0013) [2023-03-09 08:24:20,033][22940] Signal inference workers to stop experience collection... (13600 times) [2023-03-09 08:24:20,034][22940] Signal inference workers to resume experience collection... (13600 times) [2023-03-09 08:24:20,062][23090] Updated weights for policy 0, policy_version 42170 (0.0016) [2023-03-09 08:24:20,099][23090] InferenceWorker_p0-w0: stopping experience collection (13600 times) [2023-03-09 08:24:20,099][23090] InferenceWorker_p0-w0: resuming experience collection (13600 times) [2023-03-09 08:24:20,827][23090] Updated weights for policy 0, policy_version 42180 (0.0013) [2023-03-09 08:24:21,715][23090] Updated weights for policy 0, policy_version 42190 (0.0016) [2023-03-09 08:24:22,482][23090] Updated weights for policy 0, policy_version 42200 (0.0013) [2023-03-09 08:24:23,322][23090] Updated weights for policy 0, policy_version 42210 (0.0013) [2023-03-09 08:24:24,059][22664] Fps is (10 sec: 196599.9, 60 sec: 198519.0, 300 sec: 199218.2). Total num frames: 691699712. Throughput: 0: 49652.5. Samples: 172992544. Policy #0 lag: (min: 2.0, avg: 16.9, max: 33.0) [2023-03-09 08:24:24,061][22664] Avg episode reward: [(0, '51.947')] [2023-03-09 08:24:24,175][23090] Updated weights for policy 0, policy_version 42220 (0.0016) [2023-03-09 08:24:25,010][23090] Updated weights for policy 0, policy_version 42230 (0.0013) [2023-03-09 08:24:25,768][23090] Updated weights for policy 0, policy_version 42240 (0.0013) [2023-03-09 08:24:26,705][23090] Updated weights for policy 0, policy_version 42250 (0.0014) [2023-03-09 08:24:27,500][23090] Updated weights for policy 0, policy_version 42260 (0.0017) [2023-03-09 08:24:28,265][23090] Updated weights for policy 0, policy_version 42270 (0.0016) [2023-03-09 08:24:29,059][22664] Fps is (10 sec: 200024.2, 60 sec: 198518.7, 300 sec: 199162.8). Total num frames: 692699136. Throughput: 0: 49562.2. Samples: 173137936. Policy #0 lag: (min: 2.0, avg: 16.9, max: 33.0) [2023-03-09 08:24:29,060][22664] Avg episode reward: [(0, '54.313')] [2023-03-09 08:24:29,130][23090] Updated weights for policy 0, policy_version 42280 (0.0013) [2023-03-09 08:24:29,931][23090] Updated weights for policy 0, policy_version 42290 (0.0013) [2023-03-09 08:24:30,782][23090] Updated weights for policy 0, policy_version 42300 (0.0013) [2023-03-09 08:24:31,519][23090] Updated weights for policy 0, policy_version 42310 (0.0016) [2023-03-09 08:24:32,420][23090] Updated weights for policy 0, policy_version 42320 (0.0022) [2023-03-09 08:24:33,267][22940] Signal inference workers to stop experience collection... (13650 times) [2023-03-09 08:24:33,267][22940] Signal inference workers to resume experience collection... (13650 times) [2023-03-09 08:24:33,329][23090] InferenceWorker_p0-w0: stopping experience collection (13650 times) [2023-03-09 08:24:33,332][23090] InferenceWorker_p0-w0: resuming experience collection (13650 times) [2023-03-09 08:24:33,335][23090] Updated weights for policy 0, policy_version 42331 (0.0013) [2023-03-09 08:24:34,058][22664] Fps is (10 sec: 199892.9, 60 sec: 198792.6, 300 sec: 199218.4). Total num frames: 693698560. Throughput: 0: 49657.5. Samples: 173436896. Policy #0 lag: (min: 2.0, avg: 16.9, max: 33.0) [2023-03-09 08:24:34,059][22664] Avg episode reward: [(0, '51.323')] [2023-03-09 08:24:34,159][23090] Updated weights for policy 0, policy_version 42342 (0.0013) [2023-03-09 08:24:35,040][23090] Updated weights for policy 0, policy_version 42352 (0.0018) [2023-03-09 08:24:35,875][23090] Updated weights for policy 0, policy_version 42362 (0.0024) [2023-03-09 08:24:36,650][23090] Updated weights for policy 0, policy_version 42372 (0.0013) [2023-03-09 08:24:37,553][23090] Updated weights for policy 0, policy_version 42382 (0.0013) [2023-03-09 08:24:38,325][23090] Updated weights for policy 0, policy_version 42392 (0.0020) [2023-03-09 08:24:39,059][22664] Fps is (10 sec: 199886.0, 60 sec: 198791.7, 300 sec: 199218.2). Total num frames: 694697984. Throughput: 0: 49616.1. Samples: 173735840. Policy #0 lag: (min: 1.0, avg: 16.2, max: 33.0) [2023-03-09 08:24:39,060][22664] Avg episode reward: [(0, '55.401')] [2023-03-09 08:24:39,124][23090] Updated weights for policy 0, policy_version 42402 (0.0013) [2023-03-09 08:24:39,968][23090] Updated weights for policy 0, policy_version 42412 (0.0020) [2023-03-09 08:24:40,785][23090] Updated weights for policy 0, policy_version 42422 (0.0021) [2023-03-09 08:24:41,584][23090] Updated weights for policy 0, policy_version 42432 (0.0017) [2023-03-09 08:24:42,495][23090] Updated weights for policy 0, policy_version 42442 (0.0013) [2023-03-09 08:24:43,254][23090] Updated weights for policy 0, policy_version 42452 (0.0013) [2023-03-09 08:24:44,010][23090] Updated weights for policy 0, policy_version 42462 (0.0016) [2023-03-09 08:24:44,059][22664] Fps is (10 sec: 199877.2, 60 sec: 198792.2, 300 sec: 199273.8). Total num frames: 695697408. Throughput: 0: 49708.5. Samples: 173887376. Policy #0 lag: (min: 1.0, avg: 16.2, max: 33.0) [2023-03-09 08:24:44,061][22664] Avg episode reward: [(0, '51.442')] [2023-03-09 08:24:44,961][23090] Updated weights for policy 0, policy_version 42473 (0.0020) [2023-03-09 08:24:45,768][23090] Updated weights for policy 0, policy_version 42483 (0.0020) [2023-03-09 08:24:46,511][22940] Signal inference workers to stop experience collection... (13700 times) [2023-03-09 08:24:46,524][22940] Signal inference workers to resume experience collection... (13700 times) [2023-03-09 08:24:46,589][23090] InferenceWorker_p0-w0: stopping experience collection (13700 times) [2023-03-09 08:24:46,589][23090] InferenceWorker_p0-w0: resuming experience collection (13700 times) [2023-03-09 08:24:46,592][23090] Updated weights for policy 0, policy_version 42493 (0.0019) [2023-03-09 08:24:47,408][23090] Updated weights for policy 0, policy_version 42503 (0.0019) [2023-03-09 08:24:48,211][23090] Updated weights for policy 0, policy_version 42513 (0.0013) [2023-03-09 08:24:49,003][23090] Updated weights for policy 0, policy_version 42523 (0.0013) [2023-03-09 08:24:49,059][22664] Fps is (10 sec: 199886.5, 60 sec: 199065.8, 300 sec: 199274.1). Total num frames: 696696832. Throughput: 0: 49756.2. Samples: 174188416. Policy #0 lag: (min: 1.0, avg: 16.2, max: 33.0) [2023-03-09 08:24:49,060][22664] Avg episode reward: [(0, '53.122')] [2023-03-09 08:24:49,755][23090] Updated weights for policy 0, policy_version 42533 (0.0013) [2023-03-09 08:24:50,673][23090] Updated weights for policy 0, policy_version 42543 (0.0013) [2023-03-09 08:24:51,473][23090] Updated weights for policy 0, policy_version 42553 (0.0013) [2023-03-09 08:24:52,281][23090] Updated weights for policy 0, policy_version 42563 (0.0016) [2023-03-09 08:24:53,140][23090] Updated weights for policy 0, policy_version 42573 (0.0016) [2023-03-09 08:24:53,928][23090] Updated weights for policy 0, policy_version 42583 (0.0022) [2023-03-09 08:24:54,059][22664] Fps is (10 sec: 199891.2, 60 sec: 198793.5, 300 sec: 199273.9). Total num frames: 697696256. Throughput: 0: 49811.6. Samples: 174489472. Policy #0 lag: (min: 1.0, avg: 16.2, max: 33.0) [2023-03-09 08:24:54,060][22664] Avg episode reward: [(0, '50.043')] [2023-03-09 08:24:54,696][23090] Updated weights for policy 0, policy_version 42593 (0.0022) [2023-03-09 08:24:55,598][23090] Updated weights for policy 0, policy_version 42603 (0.0016) [2023-03-09 08:24:56,484][23090] Updated weights for policy 0, policy_version 42614 (0.0013) [2023-03-09 08:24:57,250][23090] Updated weights for policy 0, policy_version 42624 (0.0017) [2023-03-09 08:24:58,134][23090] Updated weights for policy 0, policy_version 42634 (0.0017) [2023-03-09 08:24:58,869][23090] Updated weights for policy 0, policy_version 42644 (0.0013) [2023-03-09 08:24:59,059][22664] Fps is (10 sec: 199886.9, 60 sec: 199066.8, 300 sec: 199273.9). Total num frames: 698695680. Throughput: 0: 49818.2. Samples: 174638960. Policy #0 lag: (min: 1.0, avg: 16.2, max: 33.0) [2023-03-09 08:24:59,059][22664] Avg episode reward: [(0, '52.208')] [2023-03-09 08:24:59,784][23090] Updated weights for policy 0, policy_version 42655 (0.0016) [2023-03-09 08:25:00,125][22940] Signal inference workers to stop experience collection... (13750 times) [2023-03-09 08:25:00,126][22940] Signal inference workers to resume experience collection... (13750 times) [2023-03-09 08:25:00,191][23090] InferenceWorker_p0-w0: stopping experience collection (13750 times) [2023-03-09 08:25:00,191][23090] InferenceWorker_p0-w0: resuming experience collection (13750 times) [2023-03-09 08:25:00,641][23090] Updated weights for policy 0, policy_version 42665 (0.0016) [2023-03-09 08:25:01,428][23090] Updated weights for policy 0, policy_version 42675 (0.0013) [2023-03-09 08:25:02,267][23090] Updated weights for policy 0, policy_version 42685 (0.0017) [2023-03-09 08:25:03,107][23090] Updated weights for policy 0, policy_version 42695 (0.0016) [2023-03-09 08:25:03,912][23090] Updated weights for policy 0, policy_version 42705 (0.0017) [2023-03-09 08:25:04,059][22664] Fps is (10 sec: 201520.3, 60 sec: 199339.0, 300 sec: 199384.9). Total num frames: 699711488. Throughput: 0: 49924.0. Samples: 174940000. Policy #0 lag: (min: 0.0, avg: 17.1, max: 33.0) [2023-03-09 08:25:04,061][22664] Avg episode reward: [(0, '54.816')] [2023-03-09 08:25:04,748][23090] Updated weights for policy 0, policy_version 42715 (0.0019) [2023-03-09 08:25:05,476][23090] Updated weights for policy 0, policy_version 42725 (0.0016) [2023-03-09 08:25:06,419][23090] Updated weights for policy 0, policy_version 42735 (0.0019) [2023-03-09 08:25:07,189][23090] Updated weights for policy 0, policy_version 42745 (0.0013) [2023-03-09 08:25:08,062][23090] Updated weights for policy 0, policy_version 42756 (0.0017) [2023-03-09 08:25:08,952][23090] Updated weights for policy 0, policy_version 42766 (0.0019) [2023-03-09 08:25:09,058][22664] Fps is (10 sec: 199886.1, 60 sec: 199339.0, 300 sec: 199329.6). Total num frames: 700694528. Throughput: 0: 49965.6. Samples: 175240976. Policy #0 lag: (min: 0.0, avg: 17.1, max: 33.0) [2023-03-09 08:25:09,059][22664] Avg episode reward: [(0, '52.628')] [2023-03-09 08:25:09,845][23090] Updated weights for policy 0, policy_version 42777 (0.0022) [2023-03-09 08:25:10,647][23090] Updated weights for policy 0, policy_version 42787 (0.0018) [2023-03-09 08:25:11,531][23090] Updated weights for policy 0, policy_version 42797 (0.0015) [2023-03-09 08:25:12,347][23090] Updated weights for policy 0, policy_version 42807 (0.0013) [2023-03-09 08:25:13,189][23090] Updated weights for policy 0, policy_version 42817 (0.0013) [2023-03-09 08:25:13,280][22940] Signal inference workers to stop experience collection... (13800 times) [2023-03-09 08:25:13,281][22940] Signal inference workers to resume experience collection... (13800 times) [2023-03-09 08:25:13,343][23090] InferenceWorker_p0-w0: stopping experience collection (13800 times) [2023-03-09 08:25:13,346][23090] InferenceWorker_p0-w0: resuming experience collection (13800 times) [2023-03-09 08:25:14,022][23090] Updated weights for policy 0, policy_version 42827 (0.0013) [2023-03-09 08:25:14,058][22664] Fps is (10 sec: 198250.6, 60 sec: 199338.7, 300 sec: 199329.7). Total num frames: 701693952. Throughput: 0: 49965.5. Samples: 175386368. Policy #0 lag: (min: 0.0, avg: 17.1, max: 33.0) [2023-03-09 08:25:14,059][22664] Avg episode reward: [(0, '54.312')] [2023-03-09 08:25:14,777][23090] Updated weights for policy 0, policy_version 42837 (0.0018) [2023-03-09 08:25:15,610][23090] Updated weights for policy 0, policy_version 42847 (0.0013) [2023-03-09 08:25:16,456][23090] Updated weights for policy 0, policy_version 42857 (0.0019) [2023-03-09 08:25:17,262][23090] Updated weights for policy 0, policy_version 42867 (0.0013) [2023-03-09 08:25:18,068][23090] Updated weights for policy 0, policy_version 42877 (0.0015) [2023-03-09 08:25:18,890][23090] Updated weights for policy 0, policy_version 42887 (0.0014) [2023-03-09 08:25:19,059][22664] Fps is (10 sec: 199875.1, 60 sec: 199907.4, 300 sec: 199273.7). Total num frames: 702693376. Throughput: 0: 50010.8. Samples: 175687408. Policy #0 lag: (min: 0.0, avg: 17.1, max: 33.0) [2023-03-09 08:25:19,061][22664] Avg episode reward: [(0, '52.445')] [2023-03-09 08:25:19,073][22940] Saving /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000042889_702693376.pth... [2023-03-09 08:25:19,133][22940] Removing /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000039969_654852096.pth [2023-03-09 08:25:19,702][23090] Updated weights for policy 0, policy_version 42897 (0.0016) [2023-03-09 08:25:20,544][23090] Updated weights for policy 0, policy_version 42907 (0.0016) [2023-03-09 08:25:21,268][23090] Updated weights for policy 0, policy_version 42917 (0.0013) [2023-03-09 08:25:22,209][23090] Updated weights for policy 0, policy_version 42927 (0.0014) [2023-03-09 08:25:22,986][23090] Updated weights for policy 0, policy_version 42937 (0.0013) [2023-03-09 08:25:23,791][23090] Updated weights for policy 0, policy_version 42947 (0.0024) [2023-03-09 08:25:24,059][22664] Fps is (10 sec: 199878.0, 60 sec: 199885.0, 300 sec: 199329.3). Total num frames: 703692800. Throughput: 0: 50010.6. Samples: 175986320. Policy #0 lag: (min: 0.0, avg: 17.1, max: 33.0) [2023-03-09 08:25:24,060][22664] Avg episode reward: [(0, '51.998')] [2023-03-09 08:25:24,674][23090] Updated weights for policy 0, policy_version 42957 (0.0013) [2023-03-09 08:25:25,504][23090] Updated weights for policy 0, policy_version 42967 (0.0019) [2023-03-09 08:25:26,266][23090] Updated weights for policy 0, policy_version 42977 (0.0017) [2023-03-09 08:25:26,279][22940] Signal inference workers to stop experience collection... (13850 times) [2023-03-09 08:25:26,280][22940] Signal inference workers to resume experience collection... (13850 times) [2023-03-09 08:25:26,345][23090] InferenceWorker_p0-w0: stopping experience collection (13850 times) [2023-03-09 08:25:26,347][23090] InferenceWorker_p0-w0: resuming experience collection (13850 times) [2023-03-09 08:25:27,172][23090] Updated weights for policy 0, policy_version 42988 (0.0025) [2023-03-09 08:25:28,013][23090] Updated weights for policy 0, policy_version 42998 (0.0016) [2023-03-09 08:25:28,768][23090] Updated weights for policy 0, policy_version 43008 (0.0017) [2023-03-09 08:25:29,059][22664] Fps is (10 sec: 199877.0, 60 sec: 199882.9, 300 sec: 199329.2). Total num frames: 704692224. Throughput: 0: 49964.6. Samples: 176135808. Policy #0 lag: (min: 1.0, avg: 17.2, max: 33.0) [2023-03-09 08:25:29,062][22664] Avg episode reward: [(0, '52.917')] [2023-03-09 08:25:29,660][23090] Updated weights for policy 0, policy_version 43018 (0.0016) [2023-03-09 08:25:30,459][23090] Updated weights for policy 0, policy_version 43028 (0.0013) [2023-03-09 08:25:31,231][23090] Updated weights for policy 0, policy_version 43038 (0.0016) [2023-03-09 08:25:32,066][23090] Updated weights for policy 0, policy_version 43048 (0.0013) [2023-03-09 08:25:32,917][23090] Updated weights for policy 0, policy_version 43058 (0.0017) [2023-03-09 08:25:33,789][23090] Updated weights for policy 0, policy_version 43068 (0.0019) [2023-03-09 08:25:34,058][22664] Fps is (10 sec: 199891.6, 60 sec: 199884.8, 300 sec: 199274.3). Total num frames: 705691648. Throughput: 0: 49963.2. Samples: 176436752. Policy #0 lag: (min: 1.0, avg: 17.2, max: 33.0) [2023-03-09 08:25:34,059][22664] Avg episode reward: [(0, '52.585')] [2023-03-09 08:25:34,516][23090] Updated weights for policy 0, policy_version 43078 (0.0020) [2023-03-09 08:25:35,360][23090] Updated weights for policy 0, policy_version 43088 (0.0024) [2023-03-09 08:25:36,201][23090] Updated weights for policy 0, policy_version 43098 (0.0016) [2023-03-09 08:25:36,980][23090] Updated weights for policy 0, policy_version 43108 (0.0019) [2023-03-09 08:25:37,871][23090] Updated weights for policy 0, policy_version 43118 (0.0018) [2023-03-09 08:25:38,675][23090] Updated weights for policy 0, policy_version 43128 (0.0022) [2023-03-09 08:25:39,058][22664] Fps is (10 sec: 199902.5, 60 sec: 199885.7, 300 sec: 199329.4). Total num frames: 706691072. Throughput: 0: 49914.4. Samples: 176735616. Policy #0 lag: (min: 1.0, avg: 17.2, max: 33.0) [2023-03-09 08:25:39,059][22664] Avg episode reward: [(0, '51.195')] [2023-03-09 08:25:39,498][22940] Signal inference workers to stop experience collection... (13900 times) [2023-03-09 08:25:39,499][22940] Signal inference workers to resume experience collection... (13900 times) [2023-03-09 08:25:39,523][23090] Updated weights for policy 0, policy_version 43138 (0.0015) [2023-03-09 08:25:39,561][23090] InferenceWorker_p0-w0: stopping experience collection (13900 times) [2023-03-09 08:25:39,572][23090] InferenceWorker_p0-w0: resuming experience collection (13900 times) [2023-03-09 08:25:40,336][23090] Updated weights for policy 0, policy_version 43148 (0.0014) [2023-03-09 08:25:41,261][23090] Updated weights for policy 0, policy_version 43158 (0.0018) [2023-03-09 08:25:41,957][23090] Updated weights for policy 0, policy_version 43168 (0.0020) [2023-03-09 08:25:42,843][23090] Updated weights for policy 0, policy_version 43178 (0.0016) [2023-03-09 08:25:43,655][23090] Updated weights for policy 0, policy_version 43188 (0.0016) [2023-03-09 08:25:44,059][22664] Fps is (10 sec: 198237.4, 60 sec: 199611.5, 300 sec: 199273.6). Total num frames: 707674112. Throughput: 0: 49868.7. Samples: 176883072. Policy #0 lag: (min: 1.0, avg: 17.2, max: 33.0) [2023-03-09 08:25:44,060][22664] Avg episode reward: [(0, '51.758')] [2023-03-09 08:25:44,417][23090] Updated weights for policy 0, policy_version 43198 (0.0017) [2023-03-09 08:25:45,275][23090] Updated weights for policy 0, policy_version 43208 (0.0025) [2023-03-09 08:25:46,108][23090] Updated weights for policy 0, policy_version 43218 (0.0013) [2023-03-09 08:25:46,962][23090] Updated weights for policy 0, policy_version 43228 (0.0013) [2023-03-09 08:25:47,707][23090] Updated weights for policy 0, policy_version 43238 (0.0013) [2023-03-09 08:25:48,568][23090] Updated weights for policy 0, policy_version 43248 (0.0013) [2023-03-09 08:25:49,059][22664] Fps is (10 sec: 196602.2, 60 sec: 199338.3, 300 sec: 199218.6). Total num frames: 708657152. Throughput: 0: 49777.7. Samples: 177180000. Policy #0 lag: (min: 1.0, avg: 17.2, max: 33.0) [2023-03-09 08:25:49,061][22664] Avg episode reward: [(0, '52.943')] [2023-03-09 08:25:49,377][23090] Updated weights for policy 0, policy_version 43258 (0.0017) [2023-03-09 08:25:50,176][23090] Updated weights for policy 0, policy_version 43268 (0.0019) [2023-03-09 08:25:51,112][23090] Updated weights for policy 0, policy_version 43278 (0.0018) [2023-03-09 08:25:51,853][23090] Updated weights for policy 0, policy_version 43288 (0.0013) [2023-03-09 08:25:52,680][23090] Updated weights for policy 0, policy_version 43298 (0.0018) [2023-03-09 08:25:53,521][23090] Updated weights for policy 0, policy_version 43308 (0.0013) [2023-03-09 08:25:54,059][22664] Fps is (10 sec: 198250.5, 60 sec: 199338.1, 300 sec: 199329.3). Total num frames: 709656576. Throughput: 0: 49732.7. Samples: 177478960. Policy #0 lag: (min: 1.0, avg: 17.2, max: 33.0) [2023-03-09 08:25:54,060][22664] Avg episode reward: [(0, '54.988')] [2023-03-09 08:25:54,376][23090] Updated weights for policy 0, policy_version 43318 (0.0019) [2023-03-09 08:25:54,391][22940] Signal inference workers to stop experience collection... (13950 times) [2023-03-09 08:25:54,391][22940] Signal inference workers to resume experience collection... (13950 times) [2023-03-09 08:25:54,456][23090] InferenceWorker_p0-w0: stopping experience collection (13950 times) [2023-03-09 08:25:54,457][23090] InferenceWorker_p0-w0: resuming experience collection (13950 times) [2023-03-09 08:25:55,103][23090] Updated weights for policy 0, policy_version 43328 (0.0016) [2023-03-09 08:25:56,025][23090] Updated weights for policy 0, policy_version 43338 (0.0013) [2023-03-09 08:25:56,841][23090] Updated weights for policy 0, policy_version 43348 (0.0017) [2023-03-09 08:25:57,610][23090] Updated weights for policy 0, policy_version 43358 (0.0013) [2023-03-09 08:25:58,498][23090] Updated weights for policy 0, policy_version 43368 (0.0013) [2023-03-09 08:25:59,059][22664] Fps is (10 sec: 198250.9, 60 sec: 199065.6, 300 sec: 199218.5). Total num frames: 710639616. Throughput: 0: 49777.7. Samples: 177626368. Policy #0 lag: (min: 1.0, avg: 16.9, max: 33.0) [2023-03-09 08:25:59,060][22664] Avg episode reward: [(0, '54.830')] [2023-03-09 08:25:59,346][23090] Updated weights for policy 0, policy_version 43378 (0.0016) [2023-03-09 08:26:00,195][23090] Updated weights for policy 0, policy_version 43388 (0.0013) [2023-03-09 08:26:00,927][23090] Updated weights for policy 0, policy_version 43398 (0.0015) [2023-03-09 08:26:01,787][23090] Updated weights for policy 0, policy_version 43408 (0.0022) [2023-03-09 08:26:02,614][23090] Updated weights for policy 0, policy_version 43418 (0.0023) [2023-03-09 08:26:03,407][23090] Updated weights for policy 0, policy_version 43428 (0.0013) [2023-03-09 08:26:04,059][22664] Fps is (10 sec: 198244.9, 60 sec: 198792.1, 300 sec: 199273.9). Total num frames: 711639040. Throughput: 0: 49686.6. Samples: 177923296. Policy #0 lag: (min: 1.0, avg: 16.9, max: 33.0) [2023-03-09 08:26:04,061][22664] Avg episode reward: [(0, '51.813')] [2023-03-09 08:26:04,335][23090] Updated weights for policy 0, policy_version 43438 (0.0013) [2023-03-09 08:26:05,103][23090] Updated weights for policy 0, policy_version 43448 (0.0016) [2023-03-09 08:26:05,970][23090] Updated weights for policy 0, policy_version 43458 (0.0017) [2023-03-09 08:26:06,739][23090] Updated weights for policy 0, policy_version 43468 (0.0013) [2023-03-09 08:26:07,650][23090] Updated weights for policy 0, policy_version 43478 (0.0017) [2023-03-09 08:26:08,074][22940] Signal inference workers to stop experience collection... (14000 times) [2023-03-09 08:26:08,074][22940] Signal inference workers to resume experience collection... (14000 times) [2023-03-09 08:26:08,137][23090] InferenceWorker_p0-w0: stopping experience collection (14000 times) [2023-03-09 08:26:08,137][23090] InferenceWorker_p0-w0: resuming experience collection (14000 times) [2023-03-09 08:26:08,505][23090] Updated weights for policy 0, policy_version 43489 (0.0013) [2023-03-09 08:26:09,059][22664] Fps is (10 sec: 199885.3, 60 sec: 199065.5, 300 sec: 199273.9). Total num frames: 712638464. Throughput: 0: 49733.3. Samples: 178224304. Policy #0 lag: (min: 1.0, avg: 16.9, max: 33.0) [2023-03-09 08:26:09,059][22664] Avg episode reward: [(0, '53.251')] [2023-03-09 08:26:09,352][23090] Updated weights for policy 0, policy_version 43500 (0.0024) [2023-03-09 08:26:10,245][23090] Updated weights for policy 0, policy_version 43510 (0.0013) [2023-03-09 08:26:11,008][23090] Updated weights for policy 0, policy_version 43520 (0.0020) [2023-03-09 08:26:11,952][23090] Updated weights for policy 0, policy_version 43530 (0.0015) [2023-03-09 08:26:12,714][23090] Updated weights for policy 0, policy_version 43540 (0.0018) [2023-03-09 08:26:13,478][23090] Updated weights for policy 0, policy_version 43550 (0.0013) [2023-03-09 08:26:14,059][22664] Fps is (10 sec: 198250.3, 60 sec: 198792.1, 300 sec: 199218.4). Total num frames: 713621504. Throughput: 0: 49688.3. Samples: 178371744. Policy #0 lag: (min: 1.0, avg: 16.9, max: 33.0) [2023-03-09 08:26:14,060][22664] Avg episode reward: [(0, '53.830')] [2023-03-09 08:26:14,364][23090] Updated weights for policy 0, policy_version 43560 (0.0018) [2023-03-09 08:26:15,208][23090] Updated weights for policy 0, policy_version 43570 (0.0016) [2023-03-09 08:26:16,054][23090] Updated weights for policy 0, policy_version 43580 (0.0014) [2023-03-09 08:26:16,808][23090] Updated weights for policy 0, policy_version 43590 (0.0019) [2023-03-09 08:26:17,656][23090] Updated weights for policy 0, policy_version 43600 (0.0013) [2023-03-09 08:26:18,467][23090] Updated weights for policy 0, policy_version 43610 (0.0013) [2023-03-09 08:26:19,059][22664] Fps is (10 sec: 198244.1, 60 sec: 198793.6, 300 sec: 199218.4). Total num frames: 714620928. Throughput: 0: 49597.3. Samples: 178668640. Policy #0 lag: (min: 1.0, avg: 16.9, max: 33.0) [2023-03-09 08:26:19,101][22664] Avg episode reward: [(0, '51.116')] [2023-03-09 08:26:19,274][23090] Updated weights for policy 0, policy_version 43620 (0.0016) [2023-03-09 08:26:20,208][23090] Updated weights for policy 0, policy_version 43630 (0.0016) [2023-03-09 08:26:20,984][23090] Updated weights for policy 0, policy_version 43640 (0.0013) [2023-03-09 08:26:21,821][23090] Updated weights for policy 0, policy_version 43650 (0.0013) [2023-03-09 08:26:22,602][23090] Updated weights for policy 0, policy_version 43660 (0.0017) [2023-03-09 08:26:23,558][23090] Updated weights for policy 0, policy_version 43671 (0.0020) [2023-03-09 08:26:23,571][22940] Signal inference workers to stop experience collection... (14050 times) [2023-03-09 08:26:23,573][22940] Signal inference workers to resume experience collection... (14050 times) [2023-03-09 08:26:23,636][23090] InferenceWorker_p0-w0: stopping experience collection (14050 times) [2023-03-09 08:26:23,636][23090] InferenceWorker_p0-w0: resuming experience collection (14050 times) [2023-03-09 08:26:24,059][22664] Fps is (10 sec: 198235.0, 60 sec: 198518.3, 300 sec: 199217.9). Total num frames: 715603968. Throughput: 0: 49552.7. Samples: 178965520. Policy #0 lag: (min: 2.0, avg: 17.1, max: 34.0) [2023-03-09 08:26:24,062][22664] Avg episode reward: [(0, '51.882')] [2023-03-09 08:26:24,373][23090] Updated weights for policy 0, policy_version 43681 (0.0013) [2023-03-09 08:26:25,212][23090] Updated weights for policy 0, policy_version 43691 (0.0016) [2023-03-09 08:26:25,943][23090] Updated weights for policy 0, policy_version 43701 (0.0013) [2023-03-09 08:26:26,765][23090] Updated weights for policy 0, policy_version 43711 (0.0016) [2023-03-09 08:26:27,622][23090] Updated weights for policy 0, policy_version 43721 (0.0013) [2023-03-09 08:26:28,475][23090] Updated weights for policy 0, policy_version 43731 (0.0013) [2023-03-09 08:26:29,058][22664] Fps is (10 sec: 196611.1, 60 sec: 198249.3, 300 sec: 199162.8). Total num frames: 716587008. Throughput: 0: 49598.7. Samples: 179114992. Policy #0 lag: (min: 2.0, avg: 17.1, max: 34.0) [2023-03-09 08:26:29,059][22664] Avg episode reward: [(0, '53.547')] [2023-03-09 08:26:29,276][23090] Updated weights for policy 0, policy_version 43741 (0.0016) [2023-03-09 08:26:30,112][23090] Updated weights for policy 0, policy_version 43751 (0.0013) [2023-03-09 08:26:30,936][23090] Updated weights for policy 0, policy_version 43761 (0.0026) [2023-03-09 08:26:31,764][23090] Updated weights for policy 0, policy_version 43771 (0.0025) [2023-03-09 08:26:32,521][23090] Updated weights for policy 0, policy_version 43781 (0.0013) [2023-03-09 08:26:33,418][23090] Updated weights for policy 0, policy_version 43791 (0.0013) [2023-03-09 08:26:34,059][22664] Fps is (10 sec: 198253.2, 60 sec: 198245.2, 300 sec: 199107.3). Total num frames: 717586432. Throughput: 0: 49643.7. Samples: 179413968. Policy #0 lag: (min: 2.0, avg: 17.1, max: 34.0) [2023-03-09 08:26:34,061][22664] Avg episode reward: [(0, '53.126')] [2023-03-09 08:26:34,219][23090] Updated weights for policy 0, policy_version 43801 (0.0015) [2023-03-09 08:26:35,033][23090] Updated weights for policy 0, policy_version 43811 (0.0014) [2023-03-09 08:26:35,959][23090] Updated weights for policy 0, policy_version 43821 (0.0016) [2023-03-09 08:26:35,963][22940] Signal inference workers to stop experience collection... (14100 times) [2023-03-09 08:26:35,964][22940] Signal inference workers to resume experience collection... (14100 times) [2023-03-09 08:26:36,035][23090] InferenceWorker_p0-w0: stopping experience collection (14100 times) [2023-03-09 08:26:36,035][23090] InferenceWorker_p0-w0: resuming experience collection (14100 times) [2023-03-09 08:26:36,730][23090] Updated weights for policy 0, policy_version 43831 (0.0016) [2023-03-09 08:26:37,609][23090] Updated weights for policy 0, policy_version 43841 (0.0013) [2023-03-09 08:26:38,420][23090] Updated weights for policy 0, policy_version 43851 (0.0013) [2023-03-09 08:26:39,059][22664] Fps is (10 sec: 198230.9, 60 sec: 197970.7, 300 sec: 199106.8). Total num frames: 718569472. Throughput: 0: 49595.5. Samples: 179710784. Policy #0 lag: (min: 2.0, avg: 17.1, max: 34.0) [2023-03-09 08:26:39,061][22664] Avg episode reward: [(0, '54.187')] [2023-03-09 08:26:39,184][23090] Updated weights for policy 0, policy_version 43861 (0.0017) [2023-03-09 08:26:40,028][23090] Updated weights for policy 0, policy_version 43871 (0.0013) [2023-03-09 08:26:40,868][23090] Updated weights for policy 0, policy_version 43881 (0.0016) [2023-03-09 08:26:41,721][23090] Updated weights for policy 0, policy_version 43891 (0.0013) [2023-03-09 08:26:42,509][23090] Updated weights for policy 0, policy_version 43901 (0.0016) [2023-03-09 08:26:43,313][23090] Updated weights for policy 0, policy_version 43911 (0.0019) [2023-03-09 08:26:44,059][22664] Fps is (10 sec: 198251.6, 60 sec: 198247.6, 300 sec: 199162.7). Total num frames: 719568896. Throughput: 0: 49596.1. Samples: 179858192. Policy #0 lag: (min: 2.0, avg: 17.1, max: 34.0) [2023-03-09 08:26:44,060][22664] Avg episode reward: [(0, '52.911')] [2023-03-09 08:26:44,144][23090] Updated weights for policy 0, policy_version 43921 (0.0013) [2023-03-09 08:26:45,036][23090] Updated weights for policy 0, policy_version 43931 (0.0013) [2023-03-09 08:26:45,794][23090] Updated weights for policy 0, policy_version 43941 (0.0015) [2023-03-09 08:26:46,723][23090] Updated weights for policy 0, policy_version 43951 (0.0018) [2023-03-09 08:26:47,008][22940] Signal inference workers to stop experience collection... (14150 times) [2023-03-09 08:26:47,026][22940] Signal inference workers to resume experience collection... (14150 times) [2023-03-09 08:26:47,080][23090] InferenceWorker_p0-w0: stopping experience collection (14150 times) [2023-03-09 08:26:47,080][23090] InferenceWorker_p0-w0: resuming experience collection (14150 times) [2023-03-09 08:26:47,514][23090] Updated weights for policy 0, policy_version 43961 (0.0015) [2023-03-09 08:26:48,317][23090] Updated weights for policy 0, policy_version 43971 (0.0021) [2023-03-09 08:26:49,058][22664] Fps is (10 sec: 198262.3, 60 sec: 198247.4, 300 sec: 199107.4). Total num frames: 720551936. Throughput: 0: 49593.2. Samples: 180154976. Policy #0 lag: (min: 2.0, avg: 17.1, max: 34.0) [2023-03-09 08:26:49,060][22664] Avg episode reward: [(0, '51.783')] [2023-03-09 08:26:49,237][23090] Updated weights for policy 0, policy_version 43981 (0.0013) [2023-03-09 08:26:50,041][23090] Updated weights for policy 0, policy_version 43991 (0.0022) [2023-03-09 08:26:50,813][23090] Updated weights for policy 0, policy_version 44001 (0.0013) [2023-03-09 08:26:51,678][23090] Updated weights for policy 0, policy_version 44011 (0.0013) [2023-03-09 08:26:52,580][23090] Updated weights for policy 0, policy_version 44022 (0.0016) [2023-03-09 08:26:53,351][23090] Updated weights for policy 0, policy_version 44032 (0.0016) [2023-03-09 08:26:54,059][22664] Fps is (10 sec: 198243.1, 60 sec: 198246.3, 300 sec: 199107.3). Total num frames: 721551360. Throughput: 0: 49454.3. Samples: 180449760. Policy #0 lag: (min: 1.0, avg: 16.9, max: 33.0) [2023-03-09 08:26:54,061][22664] Avg episode reward: [(0, '53.647')] [2023-03-09 08:26:54,246][23090] Updated weights for policy 0, policy_version 44042 (0.0022) [2023-03-09 08:26:55,125][23090] Updated weights for policy 0, policy_version 44053 (0.0016) [2023-03-09 08:26:55,949][23090] Updated weights for policy 0, policy_version 44063 (0.0017) [2023-03-09 08:26:56,826][23090] Updated weights for policy 0, policy_version 44073 (0.0016) [2023-03-09 08:26:57,662][23090] Updated weights for policy 0, policy_version 44083 (0.0013) [2023-03-09 08:26:58,310][22940] Signal inference workers to stop experience collection... (14200 times) [2023-03-09 08:26:58,311][22940] Signal inference workers to resume experience collection... (14200 times) [2023-03-09 08:26:58,372][23090] InferenceWorker_p0-w0: stopping experience collection (14200 times) [2023-03-09 08:26:58,373][23090] InferenceWorker_p0-w0: resuming experience collection (14200 times) [2023-03-09 08:26:58,544][23090] Updated weights for policy 0, policy_version 44094 (0.0015) [2023-03-09 08:26:59,058][22664] Fps is (10 sec: 198246.1, 60 sec: 198246.6, 300 sec: 198996.2). Total num frames: 722534400. Throughput: 0: 49499.5. Samples: 180599216. Policy #0 lag: (min: 1.0, avg: 16.9, max: 33.0) [2023-03-09 08:26:59,059][22664] Avg episode reward: [(0, '51.379')] [2023-03-09 08:26:59,370][23090] Updated weights for policy 0, policy_version 44104 (0.0013) [2023-03-09 08:27:00,250][23090] Updated weights for policy 0, policy_version 44114 (0.0014) [2023-03-09 08:27:01,142][23090] Updated weights for policy 0, policy_version 44125 (0.0021) [2023-03-09 08:27:01,957][23090] Updated weights for policy 0, policy_version 44135 (0.0016) [2023-03-09 08:27:02,839][23090] Updated weights for policy 0, policy_version 44145 (0.0013) [2023-03-09 08:27:03,782][23090] Updated weights for policy 0, policy_version 44156 (0.0014) [2023-03-09 08:27:04,058][22664] Fps is (10 sec: 196613.2, 60 sec: 197974.4, 300 sec: 198996.3). Total num frames: 723517440. Throughput: 0: 49407.5. Samples: 180891968. Policy #0 lag: (min: 1.0, avg: 16.9, max: 33.0) [2023-03-09 08:27:04,059][22664] Avg episode reward: [(0, '54.452')] [2023-03-09 08:27:04,520][23090] Updated weights for policy 0, policy_version 44166 (0.0019) [2023-03-09 08:27:05,419][23090] Updated weights for policy 0, policy_version 44176 (0.0016) [2023-03-09 08:27:06,280][23090] Updated weights for policy 0, policy_version 44186 (0.0016) [2023-03-09 08:27:07,036][23090] Updated weights for policy 0, policy_version 44196 (0.0013) [2023-03-09 08:27:07,942][23090] Updated weights for policy 0, policy_version 44206 (0.0018) [2023-03-09 08:27:08,716][23090] Updated weights for policy 0, policy_version 44216 (0.0013) [2023-03-09 08:27:09,059][22664] Fps is (10 sec: 196600.2, 60 sec: 197699.1, 300 sec: 198940.4). Total num frames: 724500480. Throughput: 0: 49408.7. Samples: 181188896. Policy #0 lag: (min: 1.0, avg: 16.9, max: 33.0) [2023-03-09 08:27:09,061][22664] Avg episode reward: [(0, '53.541')] [2023-03-09 08:27:09,564][23090] Updated weights for policy 0, policy_version 44226 (0.0014) [2023-03-09 08:27:10,419][23090] Updated weights for policy 0, policy_version 44236 (0.0016) [2023-03-09 08:27:11,244][23090] Updated weights for policy 0, policy_version 44246 (0.0013) [2023-03-09 08:27:11,979][23090] Updated weights for policy 0, policy_version 44256 (0.0015) [2023-03-09 08:27:12,150][22940] Signal inference workers to stop experience collection... (14250 times) [2023-03-09 08:27:12,151][22940] Signal inference workers to resume experience collection... (14250 times) [2023-03-09 08:27:12,241][23090] InferenceWorker_p0-w0: stopping experience collection (14250 times) [2023-03-09 08:27:12,244][23090] InferenceWorker_p0-w0: resuming experience collection (14250 times) [2023-03-09 08:27:12,910][23090] Updated weights for policy 0, policy_version 44266 (0.0021) [2023-03-09 08:27:13,718][23090] Updated weights for policy 0, policy_version 44276 (0.0013) [2023-03-09 08:27:14,059][22664] Fps is (10 sec: 196601.7, 60 sec: 197699.6, 300 sec: 198885.1). Total num frames: 725483520. Throughput: 0: 49361.8. Samples: 181336288. Policy #0 lag: (min: 1.0, avg: 16.9, max: 33.0) [2023-03-09 08:27:14,060][22664] Avg episode reward: [(0, '54.627')] [2023-03-09 08:27:14,507][23090] Updated weights for policy 0, policy_version 44286 (0.0017) [2023-03-09 08:27:15,341][23090] Updated weights for policy 0, policy_version 44296 (0.0013) [2023-03-09 08:27:16,198][23090] Updated weights for policy 0, policy_version 44306 (0.0016) [2023-03-09 08:27:16,981][23090] Updated weights for policy 0, policy_version 44316 (0.0017) [2023-03-09 08:27:17,792][23090] Updated weights for policy 0, policy_version 44326 (0.0016) [2023-03-09 08:27:18,654][23090] Updated weights for policy 0, policy_version 44336 (0.0017) [2023-03-09 08:27:19,059][22664] Fps is (10 sec: 198253.0, 60 sec: 197700.6, 300 sec: 198885.1). Total num frames: 726482944. Throughput: 0: 49361.4. Samples: 181635216. Policy #0 lag: (min: 1.0, avg: 17.0, max: 33.0) [2023-03-09 08:27:19,060][22664] Avg episode reward: [(0, '53.873')] [2023-03-09 08:27:19,065][22940] Saving /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000044341_726482944.pth... [2023-03-09 08:27:19,138][22940] Removing /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000041432_678821888.pth [2023-03-09 08:27:19,598][23090] Updated weights for policy 0, policy_version 44347 (0.0018) [2023-03-09 08:27:20,333][23090] Updated weights for policy 0, policy_version 44357 (0.0013) [2023-03-09 08:27:21,252][23090] Updated weights for policy 0, policy_version 44367 (0.0015) [2023-03-09 08:27:22,150][23090] Updated weights for policy 0, policy_version 44377 (0.0013) [2023-03-09 08:27:22,893][23090] Updated weights for policy 0, policy_version 44387 (0.0016) [2023-03-09 08:27:23,771][23090] Updated weights for policy 0, policy_version 44397 (0.0013) [2023-03-09 08:27:24,059][22664] Fps is (10 sec: 196613.0, 60 sec: 197429.3, 300 sec: 198774.2). Total num frames: 727449600. Throughput: 0: 49319.2. Samples: 181930112. Policy #0 lag: (min: 1.0, avg: 17.0, max: 33.0) [2023-03-09 08:27:24,059][22664] Avg episode reward: [(0, '54.608')] [2023-03-09 08:27:24,271][22940] Signal inference workers to stop experience collection... (14300 times) [2023-03-09 08:27:24,295][22940] Signal inference workers to resume experience collection... (14300 times) [2023-03-09 08:27:24,314][23090] InferenceWorker_p0-w0: stopping experience collection (14300 times) [2023-03-09 08:27:24,359][23090] InferenceWorker_p0-w0: resuming experience collection (14300 times) [2023-03-09 08:27:24,610][23090] Updated weights for policy 0, policy_version 44407 (0.0016) [2023-03-09 08:27:25,402][23090] Updated weights for policy 0, policy_version 44417 (0.0013) [2023-03-09 08:27:26,264][23090] Updated weights for policy 0, policy_version 44427 (0.0021) [2023-03-09 08:27:27,024][23090] Updated weights for policy 0, policy_version 44437 (0.0015) [2023-03-09 08:27:27,846][23090] Updated weights for policy 0, policy_version 44447 (0.0013) [2023-03-09 08:27:28,684][23090] Updated weights for policy 0, policy_version 44457 (0.0018) [2023-03-09 08:27:29,059][22664] Fps is (10 sec: 194967.1, 60 sec: 197426.6, 300 sec: 198718.6). Total num frames: 728432640. Throughput: 0: 49364.2. Samples: 182079584. Policy #0 lag: (min: 1.0, avg: 17.0, max: 33.0) [2023-03-09 08:27:29,060][22664] Avg episode reward: [(0, '54.111')] [2023-03-09 08:27:29,572][23090] Updated weights for policy 0, policy_version 44467 (0.0020) [2023-03-09 08:27:30,332][23090] Updated weights for policy 0, policy_version 44477 (0.0019) [2023-03-09 08:27:31,136][23090] Updated weights for policy 0, policy_version 44487 (0.0018) [2023-03-09 08:27:32,014][23090] Updated weights for policy 0, policy_version 44497 (0.0016) [2023-03-09 08:27:32,861][23090] Updated weights for policy 0, policy_version 44507 (0.0013) [2023-03-09 08:27:33,586][23090] Updated weights for policy 0, policy_version 44517 (0.0017) [2023-03-09 08:27:34,058][22664] Fps is (10 sec: 198247.4, 60 sec: 197428.3, 300 sec: 198718.8). Total num frames: 729432064. Throughput: 0: 49366.0. Samples: 182376448. Policy #0 lag: (min: 1.0, avg: 17.0, max: 33.0) [2023-03-09 08:27:34,059][22664] Avg episode reward: [(0, '52.489')] [2023-03-09 08:27:34,489][23090] Updated weights for policy 0, policy_version 44527 (0.0023) [2023-03-09 08:27:35,347][23090] Updated weights for policy 0, policy_version 44537 (0.0013) [2023-03-09 08:27:36,035][22940] Signal inference workers to stop experience collection... (14350 times) [2023-03-09 08:27:36,037][22940] Signal inference workers to resume experience collection... (14350 times) [2023-03-09 08:27:36,103][23090] InferenceWorker_p0-w0: stopping experience collection (14350 times) [2023-03-09 08:27:36,103][23090] InferenceWorker_p0-w0: resuming experience collection (14350 times) [2023-03-09 08:27:36,192][23090] Updated weights for policy 0, policy_version 44547 (0.0014) [2023-03-09 08:27:37,100][23090] Updated weights for policy 0, policy_version 44557 (0.0017) [2023-03-09 08:27:37,942][23090] Updated weights for policy 0, policy_version 44568 (0.0016) [2023-03-09 08:27:38,747][23090] Updated weights for policy 0, policy_version 44578 (0.0018) [2023-03-09 08:27:39,059][22664] Fps is (10 sec: 199886.2, 60 sec: 197702.5, 300 sec: 198718.4). Total num frames: 730431488. Throughput: 0: 49367.3. Samples: 182671280. Policy #0 lag: (min: 1.0, avg: 17.0, max: 33.0) [2023-03-09 08:27:39,060][22664] Avg episode reward: [(0, '51.580')] [2023-03-09 08:27:39,600][23090] Updated weights for policy 0, policy_version 44588 (0.0017) [2023-03-09 08:27:40,399][23090] Updated weights for policy 0, policy_version 44598 (0.0019) [2023-03-09 08:27:41,143][23090] Updated weights for policy 0, policy_version 44608 (0.0017) [2023-03-09 08:27:42,037][23090] Updated weights for policy 0, policy_version 44618 (0.0015) [2023-03-09 08:27:42,869][23090] Updated weights for policy 0, policy_version 44628 (0.0016) [2023-03-09 08:27:43,660][23090] Updated weights for policy 0, policy_version 44638 (0.0016) [2023-03-09 08:27:44,059][22664] Fps is (10 sec: 198241.1, 60 sec: 197426.6, 300 sec: 198662.9). Total num frames: 731414528. Throughput: 0: 49367.2. Samples: 182820752. Policy #0 lag: (min: 1.0, avg: 17.0, max: 33.0) [2023-03-09 08:27:44,061][22664] Avg episode reward: [(0, '54.268')] [2023-03-09 08:27:44,488][23090] Updated weights for policy 0, policy_version 44648 (0.0018) [2023-03-09 08:27:45,364][23090] Updated weights for policy 0, policy_version 44658 (0.0017) [2023-03-09 08:27:46,202][23090] Updated weights for policy 0, policy_version 44668 (0.0014) [2023-03-09 08:27:46,939][23090] Updated weights for policy 0, policy_version 44678 (0.0018) [2023-03-09 08:27:47,814][23090] Updated weights for policy 0, policy_version 44688 (0.0012) [2023-03-09 08:27:48,727][23090] Updated weights for policy 0, policy_version 44698 (0.0020) [2023-03-09 08:27:48,956][22940] Signal inference workers to stop experience collection... (14400 times) [2023-03-09 08:27:48,959][22940] Signal inference workers to resume experience collection... (14400 times) [2023-03-09 08:27:49,020][23090] InferenceWorker_p0-w0: stopping experience collection (14400 times) [2023-03-09 08:27:49,020][23090] InferenceWorker_p0-w0: resuming experience collection (14400 times) [2023-03-09 08:27:49,059][22664] Fps is (10 sec: 198247.1, 60 sec: 197699.9, 300 sec: 198662.9). Total num frames: 732413952. Throughput: 0: 49413.6. Samples: 183115584. Policy #0 lag: (min: 0.0, avg: 16.7, max: 32.0) [2023-03-09 08:27:49,060][22664] Avg episode reward: [(0, '53.341')] [2023-03-09 08:27:49,422][23090] Updated weights for policy 0, policy_version 44708 (0.0016) [2023-03-09 08:27:50,339][23090] Updated weights for policy 0, policy_version 44718 (0.0015) [2023-03-09 08:27:51,102][23090] Updated weights for policy 0, policy_version 44728 (0.0017) [2023-03-09 08:27:51,932][23090] Updated weights for policy 0, policy_version 44738 (0.0018) [2023-03-09 08:27:52,781][23090] Updated weights for policy 0, policy_version 44748 (0.0016) [2023-03-09 08:27:53,602][23090] Updated weights for policy 0, policy_version 44758 (0.0013) [2023-03-09 08:27:54,059][22664] Fps is (10 sec: 199887.3, 60 sec: 197700.6, 300 sec: 198607.5). Total num frames: 733413376. Throughput: 0: 49503.6. Samples: 183416544. Policy #0 lag: (min: 0.0, avg: 16.7, max: 32.0) [2023-03-09 08:27:54,060][22664] Avg episode reward: [(0, '51.589')] [2023-03-09 08:27:54,323][23090] Updated weights for policy 0, policy_version 44768 (0.0013) [2023-03-09 08:27:55,242][23090] Updated weights for policy 0, policy_version 44778 (0.0013) [2023-03-09 08:27:56,069][23090] Updated weights for policy 0, policy_version 44788 (0.0022) [2023-03-09 08:27:56,899][23090] Updated weights for policy 0, policy_version 44798 (0.0013) [2023-03-09 08:27:57,675][23090] Updated weights for policy 0, policy_version 44808 (0.0013) [2023-03-09 08:27:58,539][23090] Updated weights for policy 0, policy_version 44818 (0.0013) [2023-03-09 08:27:59,059][22664] Fps is (10 sec: 198245.7, 60 sec: 197699.9, 300 sec: 198607.4). Total num frames: 734396416. Throughput: 0: 49504.6. Samples: 183563984. Policy #0 lag: (min: 0.0, avg: 16.7, max: 32.0) [2023-03-09 08:27:59,061][22664] Avg episode reward: [(0, '52.035')] [2023-03-09 08:27:59,350][23090] Updated weights for policy 0, policy_version 44828 (0.0016) [2023-03-09 08:28:00,157][23090] Updated weights for policy 0, policy_version 44838 (0.0022) [2023-03-09 08:28:01,034][23090] Updated weights for policy 0, policy_version 44848 (0.0013) [2023-03-09 08:28:01,909][23090] Updated weights for policy 0, policy_version 44858 (0.0016) [2023-03-09 08:28:02,450][22940] Signal inference workers to stop experience collection... (14450 times) [2023-03-09 08:28:02,450][22940] Signal inference workers to resume experience collection... (14450 times) [2023-03-09 08:28:02,507][23090] InferenceWorker_p0-w0: stopping experience collection (14450 times) [2023-03-09 08:28:02,507][23090] InferenceWorker_p0-w0: resuming experience collection (14450 times) [2023-03-09 08:28:02,633][23090] Updated weights for policy 0, policy_version 44868 (0.0015) [2023-03-09 08:28:03,537][23090] Updated weights for policy 0, policy_version 44878 (0.0015) [2023-03-09 08:28:04,058][22664] Fps is (10 sec: 198249.5, 60 sec: 197973.3, 300 sec: 198552.1). Total num frames: 735395840. Throughput: 0: 49460.0. Samples: 183860912. Policy #0 lag: (min: 0.0, avg: 16.7, max: 32.0) [2023-03-09 08:28:04,059][22664] Avg episode reward: [(0, '53.715')] [2023-03-09 08:28:04,280][23090] Updated weights for policy 0, policy_version 44888 (0.0018) [2023-03-09 08:28:05,106][23090] Updated weights for policy 0, policy_version 44898 (0.0016) [2023-03-09 08:28:05,995][23090] Updated weights for policy 0, policy_version 44908 (0.0020) [2023-03-09 08:28:06,780][23090] Updated weights for policy 0, policy_version 44918 (0.0013) [2023-03-09 08:28:07,508][23090] Updated weights for policy 0, policy_version 44928 (0.0023) [2023-03-09 08:28:08,417][23090] Updated weights for policy 0, policy_version 44938 (0.0013) [2023-03-09 08:28:09,058][22664] Fps is (10 sec: 198248.8, 60 sec: 197974.6, 300 sec: 198607.7). Total num frames: 736378880. Throughput: 0: 49595.4. Samples: 184161904. Policy #0 lag: (min: 0.0, avg: 16.7, max: 32.0) [2023-03-09 08:28:09,059][22664] Avg episode reward: [(0, '53.372')] [2023-03-09 08:28:09,234][23090] Updated weights for policy 0, policy_version 44948 (0.0013) [2023-03-09 08:28:10,039][23090] Updated weights for policy 0, policy_version 44958 (0.0019) [2023-03-09 08:28:10,883][23090] Updated weights for policy 0, policy_version 44968 (0.0015) [2023-03-09 08:28:11,738][23090] Updated weights for policy 0, policy_version 44978 (0.0017) [2023-03-09 08:28:12,512][23090] Updated weights for policy 0, policy_version 44988 (0.0013) [2023-03-09 08:28:13,330][23090] Updated weights for policy 0, policy_version 44998 (0.0018) [2023-03-09 08:28:14,058][22664] Fps is (10 sec: 198245.6, 60 sec: 198247.3, 300 sec: 198607.5). Total num frames: 737378304. Throughput: 0: 49596.3. Samples: 184311408. Policy #0 lag: (min: 0.0, avg: 16.7, max: 32.0) [2023-03-09 08:28:14,059][22664] Avg episode reward: [(0, '52.220')] [2023-03-09 08:28:14,188][23090] Updated weights for policy 0, policy_version 45008 (0.0013) [2023-03-09 08:28:15,089][23090] Updated weights for policy 0, policy_version 45019 (0.0019) [2023-03-09 08:28:15,184][22940] Signal inference workers to stop experience collection... (14500 times) [2023-03-09 08:28:15,185][22940] Signal inference workers to resume experience collection... (14500 times) [2023-03-09 08:28:15,244][23090] InferenceWorker_p0-w0: stopping experience collection (14500 times) [2023-03-09 08:28:15,244][23090] InferenceWorker_p0-w0: resuming experience collection (14500 times) [2023-03-09 08:28:15,805][23090] Updated weights for policy 0, policy_version 45029 (0.0020) [2023-03-09 08:28:16,702][23090] Updated weights for policy 0, policy_version 45039 (0.0018) [2023-03-09 08:28:17,642][23090] Updated weights for policy 0, policy_version 45050 (0.0013) [2023-03-09 08:28:18,382][23090] Updated weights for policy 0, policy_version 45060 (0.0020) [2023-03-09 08:28:19,059][22664] Fps is (10 sec: 199883.3, 60 sec: 198246.3, 300 sec: 198607.5). Total num frames: 738377728. Throughput: 0: 49641.2. Samples: 184610304. Policy #0 lag: (min: 1.0, avg: 16.7, max: 33.0) [2023-03-09 08:28:19,060][22664] Avg episode reward: [(0, '52.770')] [2023-03-09 08:28:19,272][23090] Updated weights for policy 0, policy_version 45070 (0.0013) [2023-03-09 08:28:20,049][23090] Updated weights for policy 0, policy_version 45080 (0.0014) [2023-03-09 08:28:20,963][23090] Updated weights for policy 0, policy_version 45091 (0.0016) [2023-03-09 08:28:21,855][23090] Updated weights for policy 0, policy_version 45101 (0.0013) [2023-03-09 08:28:22,652][23090] Updated weights for policy 0, policy_version 45111 (0.0013) [2023-03-09 08:28:23,423][23090] Updated weights for policy 0, policy_version 45121 (0.0013) [2023-03-09 08:28:24,059][22664] Fps is (10 sec: 199880.1, 60 sec: 198791.8, 300 sec: 198607.3). Total num frames: 739377152. Throughput: 0: 49732.1. Samples: 184909232. Policy #0 lag: (min: 1.0, avg: 16.7, max: 33.0) [2023-03-09 08:28:24,060][22664] Avg episode reward: [(0, '52.471')] [2023-03-09 08:28:24,322][23090] Updated weights for policy 0, policy_version 45131 (0.0013) [2023-03-09 08:28:25,074][23090] Updated weights for policy 0, policy_version 45141 (0.0013) [2023-03-09 08:28:25,874][23090] Updated weights for policy 0, policy_version 45151 (0.0013) [2023-03-09 08:28:26,759][23090] Updated weights for policy 0, policy_version 45161 (0.0016) [2023-03-09 08:28:27,613][23090] Updated weights for policy 0, policy_version 45171 (0.0018) [2023-03-09 08:28:27,622][22940] Signal inference workers to stop experience collection... (14550 times) [2023-03-09 08:28:27,638][22940] Signal inference workers to resume experience collection... (14550 times) [2023-03-09 08:28:27,696][23090] InferenceWorker_p0-w0: stopping experience collection (14550 times) [2023-03-09 08:28:27,696][23090] InferenceWorker_p0-w0: resuming experience collection (14550 times) [2023-03-09 08:28:28,375][23090] Updated weights for policy 0, policy_version 45181 (0.0013) [2023-03-09 08:28:29,059][22664] Fps is (10 sec: 199880.4, 60 sec: 199065.2, 300 sec: 198662.7). Total num frames: 740376576. Throughput: 0: 49687.1. Samples: 185056672. Policy #0 lag: (min: 1.0, avg: 16.7, max: 33.0) [2023-03-09 08:28:29,060][22664] Avg episode reward: [(0, '53.316')] [2023-03-09 08:28:29,179][23090] Updated weights for policy 0, policy_version 45191 (0.0018) [2023-03-09 08:28:30,038][23090] Updated weights for policy 0, policy_version 45201 (0.0013) [2023-03-09 08:28:30,903][23090] Updated weights for policy 0, policy_version 45211 (0.0016) [2023-03-09 08:28:31,627][23090] Updated weights for policy 0, policy_version 45221 (0.0019) [2023-03-09 08:28:32,509][23090] Updated weights for policy 0, policy_version 45231 (0.0018) [2023-03-09 08:28:33,416][23090] Updated weights for policy 0, policy_version 45241 (0.0013) [2023-03-09 08:28:34,059][22664] Fps is (10 sec: 199883.6, 60 sec: 199064.5, 300 sec: 198662.7). Total num frames: 741376000. Throughput: 0: 49823.0. Samples: 185357632. Policy #0 lag: (min: 1.0, avg: 16.7, max: 33.0) [2023-03-09 08:28:34,060][22664] Avg episode reward: [(0, '53.906')] [2023-03-09 08:28:34,183][23090] Updated weights for policy 0, policy_version 45251 (0.0023) [2023-03-09 08:28:35,014][23090] Updated weights for policy 0, policy_version 45261 (0.0013) [2023-03-09 08:28:35,866][23090] Updated weights for policy 0, policy_version 45271 (0.0013) [2023-03-09 08:28:36,626][23090] Updated weights for policy 0, policy_version 45281 (0.0018) [2023-03-09 08:28:37,589][23090] Updated weights for policy 0, policy_version 45292 (0.0018) [2023-03-09 08:28:37,751][22940] Signal inference workers to stop experience collection... (14600 times) [2023-03-09 08:28:37,753][22940] Signal inference workers to resume experience collection... (14600 times) [2023-03-09 08:28:37,841][23090] InferenceWorker_p0-w0: stopping experience collection (14600 times) [2023-03-09 08:28:37,841][23090] InferenceWorker_p0-w0: resuming experience collection (14600 times) [2023-03-09 08:28:38,520][23090] Updated weights for policy 0, policy_version 45303 (0.0013) [2023-03-09 08:28:39,059][22664] Fps is (10 sec: 199887.6, 60 sec: 199065.5, 300 sec: 198663.0). Total num frames: 742375424. Throughput: 0: 49733.3. Samples: 185654544. Policy #0 lag: (min: 1.0, avg: 16.7, max: 33.0) [2023-03-09 08:28:39,060][22664] Avg episode reward: [(0, '53.910')] [2023-03-09 08:28:39,282][23090] Updated weights for policy 0, policy_version 45313 (0.0013) [2023-03-09 08:28:40,175][23090] Updated weights for policy 0, policy_version 45323 (0.0021) [2023-03-09 08:28:40,954][23090] Updated weights for policy 0, policy_version 45333 (0.0013) [2023-03-09 08:28:41,714][23090] Updated weights for policy 0, policy_version 45343 (0.0022) [2023-03-09 08:28:42,634][23090] Updated weights for policy 0, policy_version 45353 (0.0018) [2023-03-09 08:28:43,480][23090] Updated weights for policy 0, policy_version 45363 (0.0017) [2023-03-09 08:28:44,059][22664] Fps is (10 sec: 194969.0, 60 sec: 198519.2, 300 sec: 198551.8). Total num frames: 743325696. Throughput: 0: 49733.4. Samples: 185802000. Policy #0 lag: (min: 1.0, avg: 16.7, max: 33.0) [2023-03-09 08:28:44,061][22664] Avg episode reward: [(0, '53.328')] [2023-03-09 08:28:44,262][23090] Updated weights for policy 0, policy_version 45373 (0.0016) [2023-03-09 08:28:45,061][23090] Updated weights for policy 0, policy_version 45383 (0.0016) [2023-03-09 08:28:45,913][23090] Updated weights for policy 0, policy_version 45393 (0.0013) [2023-03-09 08:28:46,753][23090] Updated weights for policy 0, policy_version 45403 (0.0017) [2023-03-09 08:28:47,519][23090] Updated weights for policy 0, policy_version 45413 (0.0022) [2023-03-09 08:28:48,416][23090] Updated weights for policy 0, policy_version 45423 (0.0016) [2023-03-09 08:28:48,677][22940] Signal inference workers to stop experience collection... (14650 times) [2023-03-09 08:28:48,678][22940] Signal inference workers to resume experience collection... (14650 times) [2023-03-09 08:28:48,747][23090] InferenceWorker_p0-w0: stopping experience collection (14650 times) [2023-03-09 08:28:48,748][23090] InferenceWorker_p0-w0: resuming experience collection (14650 times) [2023-03-09 08:28:49,059][22664] Fps is (10 sec: 196598.6, 60 sec: 198790.7, 300 sec: 198551.7). Total num frames: 744341504. Throughput: 0: 49733.3. Samples: 186098944. Policy #0 lag: (min: 1.0, avg: 16.7, max: 33.0) [2023-03-09 08:28:49,062][22664] Avg episode reward: [(0, '52.726')] [2023-03-09 08:28:49,323][23090] Updated weights for policy 0, policy_version 45433 (0.0013) [2023-03-09 08:28:50,054][23090] Updated weights for policy 0, policy_version 45443 (0.0013) [2023-03-09 08:28:50,879][23090] Updated weights for policy 0, policy_version 45453 (0.0014) [2023-03-09 08:28:51,673][23090] Updated weights for policy 0, policy_version 45463 (0.0019) [2023-03-09 08:28:52,474][23090] Updated weights for policy 0, policy_version 45473 (0.0017) [2023-03-09 08:28:53,434][23090] Updated weights for policy 0, policy_version 45484 (0.0022) [2023-03-09 08:28:54,059][22664] Fps is (10 sec: 201525.6, 60 sec: 198792.2, 300 sec: 198607.5). Total num frames: 745340928. Throughput: 0: 49733.4. Samples: 186399920. Policy #0 lag: (min: 1.0, avg: 16.7, max: 33.0) [2023-03-09 08:28:54,060][22664] Avg episode reward: [(0, '54.354')] [2023-03-09 08:28:54,216][23090] Updated weights for policy 0, policy_version 45494 (0.0013) [2023-03-09 08:28:54,976][23090] Updated weights for policy 0, policy_version 45504 (0.0016) [2023-03-09 08:28:55,870][23090] Updated weights for policy 0, policy_version 45514 (0.0013) [2023-03-09 08:28:56,743][23090] Updated weights for policy 0, policy_version 45524 (0.0013) [2023-03-09 08:28:57,490][23090] Updated weights for policy 0, policy_version 45534 (0.0017) [2023-03-09 08:28:58,328][23090] Updated weights for policy 0, policy_version 45544 (0.0017) [2023-03-09 08:28:59,058][22664] Fps is (10 sec: 198258.8, 60 sec: 198792.9, 300 sec: 198552.1). Total num frames: 746323968. Throughput: 0: 49687.5. Samples: 186547344. Policy #0 lag: (min: 1.0, avg: 16.7, max: 33.0) [2023-03-09 08:28:59,059][22664] Avg episode reward: [(0, '52.410')] [2023-03-09 08:28:59,194][23090] Updated weights for policy 0, policy_version 45554 (0.0016) [2023-03-09 08:28:59,248][22940] Signal inference workers to stop experience collection... (14700 times) [2023-03-09 08:28:59,264][22940] Signal inference workers to resume experience collection... (14700 times) [2023-03-09 08:28:59,319][23090] InferenceWorker_p0-w0: stopping experience collection (14700 times) [2023-03-09 08:28:59,319][23090] InferenceWorker_p0-w0: resuming experience collection (14700 times) [2023-03-09 08:28:59,985][23090] Updated weights for policy 0, policy_version 45564 (0.0014) [2023-03-09 08:29:00,780][23090] Updated weights for policy 0, policy_version 45574 (0.0027) [2023-03-09 08:29:01,667][23090] Updated weights for policy 0, policy_version 45584 (0.0016) [2023-03-09 08:29:02,540][23090] Updated weights for policy 0, policy_version 45594 (0.0016) [2023-03-09 08:29:03,291][23090] Updated weights for policy 0, policy_version 45604 (0.0019) [2023-03-09 08:29:04,059][22664] Fps is (10 sec: 196606.3, 60 sec: 198518.4, 300 sec: 198551.7). Total num frames: 747307008. Throughput: 0: 49643.1. Samples: 186844256. Policy #0 lag: (min: 1.0, avg: 16.7, max: 33.0) [2023-03-09 08:29:04,061][22664] Avg episode reward: [(0, '53.266')] [2023-03-09 08:29:04,176][23090] Updated weights for policy 0, policy_version 45614 (0.0013) [2023-03-09 08:29:04,960][23090] Updated weights for policy 0, policy_version 45624 (0.0017) [2023-03-09 08:29:05,767][23090] Updated weights for policy 0, policy_version 45634 (0.0016) [2023-03-09 08:29:06,636][23090] Updated weights for policy 0, policy_version 45644 (0.0013) [2023-03-09 08:29:07,449][23090] Updated weights for policy 0, policy_version 45654 (0.0013) [2023-03-09 08:29:08,214][23090] Updated weights for policy 0, policy_version 45664 (0.0021) [2023-03-09 08:29:09,059][22664] Fps is (10 sec: 198239.5, 60 sec: 198791.4, 300 sec: 198551.6). Total num frames: 748306432. Throughput: 0: 49598.5. Samples: 187141168. Policy #0 lag: (min: 1.0, avg: 16.7, max: 33.0) [2023-03-09 08:29:09,061][22664] Avg episode reward: [(0, '53.746')] [2023-03-09 08:29:09,097][23090] Updated weights for policy 0, policy_version 45674 (0.0016) [2023-03-09 08:29:09,966][23090] Updated weights for policy 0, policy_version 45684 (0.0026) [2023-03-09 08:29:10,176][22940] Signal inference workers to stop experience collection... (14750 times) [2023-03-09 08:29:10,177][22940] Signal inference workers to resume experience collection... (14750 times) [2023-03-09 08:29:10,242][23090] InferenceWorker_p0-w0: stopping experience collection (14750 times) [2023-03-09 08:29:10,242][23090] InferenceWorker_p0-w0: resuming experience collection (14750 times) [2023-03-09 08:29:10,716][23090] Updated weights for policy 0, policy_version 45694 (0.0025) [2023-03-09 08:29:11,565][23090] Updated weights for policy 0, policy_version 45704 (0.0016) [2023-03-09 08:29:12,419][23090] Updated weights for policy 0, policy_version 45714 (0.0019) [2023-03-09 08:29:13,207][23090] Updated weights for policy 0, policy_version 45724 (0.0015) [2023-03-09 08:29:13,979][23090] Updated weights for policy 0, policy_version 45734 (0.0014) [2023-03-09 08:29:14,059][22664] Fps is (10 sec: 199885.3, 60 sec: 198791.6, 300 sec: 198667.7). Total num frames: 749305856. Throughput: 0: 49644.1. Samples: 187290656. Policy #0 lag: (min: 1.0, avg: 16.8, max: 33.0) [2023-03-09 08:29:14,061][22664] Avg episode reward: [(0, '55.264')] [2023-03-09 08:29:14,865][23090] Updated weights for policy 0, policy_version 45744 (0.0020) [2023-03-09 08:29:15,784][23090] Updated weights for policy 0, policy_version 45755 (0.0013) [2023-03-09 08:29:16,550][23090] Updated weights for policy 0, policy_version 45765 (0.0019) [2023-03-09 08:29:17,468][23090] Updated weights for policy 0, policy_version 45775 (0.0013) [2023-03-09 08:29:18,354][23090] Updated weights for policy 0, policy_version 45785 (0.0013) [2023-03-09 08:29:19,059][22664] Fps is (10 sec: 199876.6, 60 sec: 198790.2, 300 sec: 198662.7). Total num frames: 750305280. Throughput: 0: 49554.4. Samples: 187587600. Policy #0 lag: (min: 1.0, avg: 16.8, max: 33.0) [2023-03-09 08:29:19,062][22664] Avg episode reward: [(0, '54.770')] [2023-03-09 08:29:19,093][23090] Updated weights for policy 0, policy_version 45795 (0.0021) [2023-03-09 08:29:19,166][22940] Saving /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000045797_750338048.pth... [2023-03-09 08:29:19,223][22940] Removing /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000042889_702693376.pth [2023-03-09 08:29:19,947][23090] Updated weights for policy 0, policy_version 45805 (0.0013) [2023-03-09 08:29:20,727][23090] Updated weights for policy 0, policy_version 45815 (0.0013) [2023-03-09 08:29:20,974][22940] Signal inference workers to stop experience collection... (14800 times) [2023-03-09 08:29:20,976][22940] Signal inference workers to resume experience collection... (14800 times) [2023-03-09 08:29:21,046][23090] InferenceWorker_p0-w0: stopping experience collection (14800 times) [2023-03-09 08:29:21,046][23090] InferenceWorker_p0-w0: resuming experience collection (14800 times) [2023-03-09 08:29:21,652][23090] Updated weights for policy 0, policy_version 45826 (0.0015) [2023-03-09 08:29:22,515][23090] Updated weights for policy 0, policy_version 45836 (0.0020) [2023-03-09 08:29:23,279][23090] Updated weights for policy 0, policy_version 45846 (0.0016) [2023-03-09 08:29:24,058][22664] Fps is (10 sec: 199890.8, 60 sec: 198793.4, 300 sec: 198663.2). Total num frames: 751304704. Throughput: 0: 49600.2. Samples: 187886544. Policy #0 lag: (min: 1.0, avg: 16.8, max: 33.0) [2023-03-09 08:29:24,059][22664] Avg episode reward: [(0, '52.673')] [2023-03-09 08:29:24,191][23090] Updated weights for policy 0, policy_version 45857 (0.0013) [2023-03-09 08:29:25,040][23090] Updated weights for policy 0, policy_version 45867 (0.0017) [2023-03-09 08:29:25,853][23090] Updated weights for policy 0, policy_version 45877 (0.0018) [2023-03-09 08:29:26,619][23090] Updated weights for policy 0, policy_version 45887 (0.0015) [2023-03-09 08:29:27,487][23090] Updated weights for policy 0, policy_version 45897 (0.0013) [2023-03-09 08:29:28,310][23090] Updated weights for policy 0, policy_version 45907 (0.0021) [2023-03-09 08:29:29,058][22664] Fps is (10 sec: 198261.1, 60 sec: 198520.4, 300 sec: 198607.4). Total num frames: 752287744. Throughput: 0: 49645.2. Samples: 188036016. Policy #0 lag: (min: 1.0, avg: 16.8, max: 33.0) [2023-03-09 08:29:29,059][22664] Avg episode reward: [(0, '51.356')] [2023-03-09 08:29:29,098][23090] Updated weights for policy 0, policy_version 45917 (0.0016) [2023-03-09 08:29:29,949][23090] Updated weights for policy 0, policy_version 45927 (0.0016) [2023-03-09 08:29:30,809][23090] Updated weights for policy 0, policy_version 45937 (0.0013) [2023-03-09 08:29:31,642][23090] Updated weights for policy 0, policy_version 45947 (0.0013) [2023-03-09 08:29:32,387][23090] Updated weights for policy 0, policy_version 45957 (0.0021) [2023-03-09 08:29:33,309][23090] Updated weights for policy 0, policy_version 45967 (0.0013) [2023-03-09 08:29:33,565][22940] Signal inference workers to stop experience collection... (14850 times) [2023-03-09 08:29:33,568][22940] Signal inference workers to resume experience collection... (14850 times) [2023-03-09 08:29:33,632][23090] InferenceWorker_p0-w0: stopping experience collection (14850 times) [2023-03-09 08:29:33,637][23090] InferenceWorker_p0-w0: resuming experience collection (14850 times) [2023-03-09 08:29:34,059][22664] Fps is (10 sec: 196602.1, 60 sec: 198246.5, 300 sec: 198551.8). Total num frames: 753270784. Throughput: 0: 49643.8. Samples: 188332896. Policy #0 lag: (min: 1.0, avg: 16.8, max: 33.0) [2023-03-09 08:29:34,060][22664] Avg episode reward: [(0, '53.509')] [2023-03-09 08:29:34,206][23090] Updated weights for policy 0, policy_version 45977 (0.0016) [2023-03-09 08:29:34,926][23090] Updated weights for policy 0, policy_version 45987 (0.0013) [2023-03-09 08:29:35,793][23090] Updated weights for policy 0, policy_version 45997 (0.0013) [2023-03-09 08:29:36,629][23090] Updated weights for policy 0, policy_version 46007 (0.0019) [2023-03-09 08:29:37,389][23090] Updated weights for policy 0, policy_version 46017 (0.0013) [2023-03-09 08:29:38,265][23090] Updated weights for policy 0, policy_version 46027 (0.0013) [2023-03-09 08:29:39,020][23090] Updated weights for policy 0, policy_version 46037 (0.0013) [2023-03-09 08:29:39,059][22664] Fps is (10 sec: 198239.0, 60 sec: 198245.6, 300 sec: 198551.8). Total num frames: 754270208. Throughput: 0: 49598.0. Samples: 188631840. Policy #0 lag: (min: 1.0, avg: 16.8, max: 33.0) [2023-03-09 08:29:39,061][22664] Avg episode reward: [(0, '52.574')] [2023-03-09 08:29:39,825][23090] Updated weights for policy 0, policy_version 46047 (0.0022) [2023-03-09 08:29:40,679][23090] Updated weights for policy 0, policy_version 46057 (0.0013) [2023-03-09 08:29:41,599][23090] Updated weights for policy 0, policy_version 46067 (0.0017) [2023-03-09 08:29:42,327][23090] Updated weights for policy 0, policy_version 46077 (0.0013) [2023-03-09 08:29:43,127][23090] Updated weights for policy 0, policy_version 46087 (0.0013) [2023-03-09 08:29:44,027][23090] Updated weights for policy 0, policy_version 46097 (0.0013) [2023-03-09 08:29:44,059][22664] Fps is (10 sec: 198249.8, 60 sec: 198793.3, 300 sec: 198496.4). Total num frames: 755253248. Throughput: 0: 49597.7. Samples: 188779248. Policy #0 lag: (min: 1.0, avg: 17.4, max: 33.0) [2023-03-09 08:29:44,060][22664] Avg episode reward: [(0, '53.684')] [2023-03-09 08:29:44,844][23090] Updated weights for policy 0, policy_version 46107 (0.0016) [2023-03-09 08:29:45,496][22940] Signal inference workers to stop experience collection... (14900 times) [2023-03-09 08:29:45,498][22940] Signal inference workers to resume experience collection... (14900 times) [2023-03-09 08:29:45,562][23090] InferenceWorker_p0-w0: stopping experience collection (14900 times) [2023-03-09 08:29:45,565][23090] InferenceWorker_p0-w0: resuming experience collection (14900 times) [2023-03-09 08:29:45,649][23090] Updated weights for policy 0, policy_version 46117 (0.0013) [2023-03-09 08:29:46,511][23090] Updated weights for policy 0, policy_version 46127 (0.0023) [2023-03-09 08:29:47,422][23090] Updated weights for policy 0, policy_version 46137 (0.0017) [2023-03-09 08:29:48,186][23090] Updated weights for policy 0, policy_version 46148 (0.0013) [2023-03-09 08:29:49,059][22664] Fps is (10 sec: 196613.6, 60 sec: 198248.1, 300 sec: 198440.7). Total num frames: 756236288. Throughput: 0: 49642.9. Samples: 189078176. Policy #0 lag: (min: 1.0, avg: 17.4, max: 33.0) [2023-03-09 08:29:49,060][22664] Avg episode reward: [(0, '51.600')] [2023-03-09 08:29:49,116][23090] Updated weights for policy 0, policy_version 46158 (0.0016) [2023-03-09 08:29:49,861][23090] Updated weights for policy 0, policy_version 46168 (0.0026) [2023-03-09 08:29:50,672][23090] Updated weights for policy 0, policy_version 46178 (0.0015) [2023-03-09 08:29:51,554][23090] Updated weights for policy 0, policy_version 46188 (0.0016) [2023-03-09 08:29:52,309][23090] Updated weights for policy 0, policy_version 46198 (0.0016) [2023-03-09 08:29:53,076][23090] Updated weights for policy 0, policy_version 46208 (0.0017) [2023-03-09 08:29:53,984][23090] Updated weights for policy 0, policy_version 46218 (0.0020) [2023-03-09 08:29:54,058][22664] Fps is (10 sec: 198249.1, 60 sec: 198247.2, 300 sec: 198440.8). Total num frames: 757235712. Throughput: 0: 49688.6. Samples: 189377136. Policy #0 lag: (min: 1.0, avg: 17.4, max: 33.0) [2023-03-09 08:29:54,059][22664] Avg episode reward: [(0, '50.198')] [2023-03-09 08:29:54,803][23090] Updated weights for policy 0, policy_version 46228 (0.0022) [2023-03-09 08:29:55,634][23090] Updated weights for policy 0, policy_version 46239 (0.0013) [2023-03-09 08:29:56,523][22940] Signal inference workers to stop experience collection... (14950 times) [2023-03-09 08:29:56,524][22940] Signal inference workers to resume experience collection... (14950 times) [2023-03-09 08:29:56,550][23090] Updated weights for policy 0, policy_version 46249 (0.0013) [2023-03-09 08:29:56,587][23090] InferenceWorker_p0-w0: stopping experience collection (14950 times) [2023-03-09 08:29:56,587][23090] InferenceWorker_p0-w0: resuming experience collection (14950 times) [2023-03-09 08:29:57,355][23090] Updated weights for policy 0, policy_version 46259 (0.0019) [2023-03-09 08:29:58,113][23090] Updated weights for policy 0, policy_version 46269 (0.0013) [2023-03-09 08:29:58,921][23090] Updated weights for policy 0, policy_version 46279 (0.0021) [2023-03-09 08:29:59,059][22664] Fps is (10 sec: 201517.8, 60 sec: 198791.3, 300 sec: 198440.7). Total num frames: 758251520. Throughput: 0: 49732.9. Samples: 189528640. Policy #0 lag: (min: 1.0, avg: 17.4, max: 33.0) [2023-03-09 08:29:59,061][22664] Avg episode reward: [(0, '52.837')] [2023-03-09 08:29:59,780][23090] Updated weights for policy 0, policy_version 46289 (0.0019) [2023-03-09 08:30:00,615][23090] Updated weights for policy 0, policy_version 46299 (0.0016) [2023-03-09 08:30:01,365][23090] Updated weights for policy 0, policy_version 46309 (0.0015) [2023-03-09 08:30:02,253][23090] Updated weights for policy 0, policy_version 46319 (0.0013) [2023-03-09 08:30:03,133][23090] Updated weights for policy 0, policy_version 46329 (0.0019) [2023-03-09 08:30:03,944][23090] Updated weights for policy 0, policy_version 46339 (0.0017) [2023-03-09 08:30:04,058][22664] Fps is (10 sec: 201522.1, 60 sec: 199066.5, 300 sec: 198496.3). Total num frames: 759250944. Throughput: 0: 49732.0. Samples: 189825504. Policy #0 lag: (min: 1.0, avg: 17.4, max: 33.0) [2023-03-09 08:30:04,059][22664] Avg episode reward: [(0, '53.334')] [2023-03-09 08:30:04,803][23090] Updated weights for policy 0, policy_version 46349 (0.0019) [2023-03-09 08:30:05,560][23090] Updated weights for policy 0, policy_version 46359 (0.0020) [2023-03-09 08:30:06,367][23090] Updated weights for policy 0, policy_version 46369 (0.0013) [2023-03-09 08:30:07,251][23090] Updated weights for policy 0, policy_version 46379 (0.0013) [2023-03-09 08:30:08,016][23090] Updated weights for policy 0, policy_version 46389 (0.0014) [2023-03-09 08:30:08,466][22940] Signal inference workers to stop experience collection... (15000 times) [2023-03-09 08:30:08,468][22940] Signal inference workers to resume experience collection... (15000 times) [2023-03-09 08:30:08,530][23090] InferenceWorker_p0-w0: stopping experience collection (15000 times) [2023-03-09 08:30:08,530][23090] InferenceWorker_p0-w0: resuming experience collection (15000 times) [2023-03-09 08:30:08,871][23090] Updated weights for policy 0, policy_version 46399 (0.0017) [2023-03-09 08:30:09,058][22664] Fps is (10 sec: 198253.4, 60 sec: 198793.6, 300 sec: 198440.8). Total num frames: 760233984. Throughput: 0: 49686.4. Samples: 190122432. Policy #0 lag: (min: 1.0, avg: 17.4, max: 33.0) [2023-03-09 08:30:09,060][22664] Avg episode reward: [(0, '52.742')] [2023-03-09 08:30:09,784][23090] Updated weights for policy 0, policy_version 46409 (0.0013) [2023-03-09 08:30:10,557][23090] Updated weights for policy 0, policy_version 46419 (0.0020) [2023-03-09 08:30:11,341][23090] Updated weights for policy 0, policy_version 46429 (0.0016) [2023-03-09 08:30:12,165][23090] Updated weights for policy 0, policy_version 46439 (0.0016) [2023-03-09 08:30:13,019][23090] Updated weights for policy 0, policy_version 46449 (0.0013) [2023-03-09 08:30:13,828][23090] Updated weights for policy 0, policy_version 46459 (0.0013) [2023-03-09 08:30:14,058][22664] Fps is (10 sec: 198246.6, 60 sec: 198793.4, 300 sec: 198441.1). Total num frames: 761233408. Throughput: 0: 49641.2. Samples: 190269872. Policy #0 lag: (min: 1.0, avg: 17.3, max: 32.0) [2023-03-09 08:30:14,059][22664] Avg episode reward: [(0, '53.817')] [2023-03-09 08:30:14,662][23090] Updated weights for policy 0, policy_version 46470 (0.0013) [2023-03-09 08:30:15,549][23090] Updated weights for policy 0, policy_version 46480 (0.0023) [2023-03-09 08:30:16,433][23090] Updated weights for policy 0, policy_version 46490 (0.0013) [2023-03-09 08:30:17,170][23090] Updated weights for policy 0, policy_version 46500 (0.0015) [2023-03-09 08:30:18,051][23090] Updated weights for policy 0, policy_version 46510 (0.0016) [2023-03-09 08:30:18,815][23090] Updated weights for policy 0, policy_version 46520 (0.0013) [2023-03-09 08:30:19,059][22664] Fps is (10 sec: 198238.8, 60 sec: 198520.7, 300 sec: 198385.2). Total num frames: 762216448. Throughput: 0: 49688.1. Samples: 190568864. Policy #0 lag: (min: 1.0, avg: 17.3, max: 32.0) [2023-03-09 08:30:19,061][22664] Avg episode reward: [(0, '53.650')] [2023-03-09 08:30:19,630][23090] Updated weights for policy 0, policy_version 46530 (0.0013) [2023-03-09 08:30:20,584][23090] Updated weights for policy 0, policy_version 46540 (0.0016) [2023-03-09 08:30:21,289][23090] Updated weights for policy 0, policy_version 46550 (0.0023) [2023-03-09 08:30:21,738][22940] Signal inference workers to stop experience collection... (15050 times) [2023-03-09 08:30:21,740][22940] Signal inference workers to resume experience collection... (15050 times) [2023-03-09 08:30:21,807][23090] InferenceWorker_p0-w0: stopping experience collection (15050 times) [2023-03-09 08:30:21,809][23090] InferenceWorker_p0-w0: resuming experience collection (15050 times) [2023-03-09 08:30:22,099][23090] Updated weights for policy 0, policy_version 46560 (0.0021) [2023-03-09 08:30:22,968][23090] Updated weights for policy 0, policy_version 46570 (0.0019) [2023-03-09 08:30:23,853][23090] Updated weights for policy 0, policy_version 46580 (0.0018) [2023-03-09 08:30:24,059][22664] Fps is (10 sec: 198241.9, 60 sec: 198518.6, 300 sec: 198385.7). Total num frames: 763215872. Throughput: 0: 49642.8. Samples: 190865760. Policy #0 lag: (min: 1.0, avg: 17.3, max: 32.0) [2023-03-09 08:30:24,060][22664] Avg episode reward: [(0, '54.642')] [2023-03-09 08:30:24,670][23090] Updated weights for policy 0, policy_version 46590 (0.0015) [2023-03-09 08:30:25,448][23090] Updated weights for policy 0, policy_version 46600 (0.0015) [2023-03-09 08:30:26,339][23090] Updated weights for policy 0, policy_version 46610 (0.0022) [2023-03-09 08:30:27,151][23090] Updated weights for policy 0, policy_version 46620 (0.0013) [2023-03-09 08:30:27,934][23090] Updated weights for policy 0, policy_version 46630 (0.0016) [2023-03-09 08:30:28,819][23090] Updated weights for policy 0, policy_version 46640 (0.0018) [2023-03-09 08:30:29,059][22664] Fps is (10 sec: 196614.6, 60 sec: 198246.2, 300 sec: 198274.1). Total num frames: 764182528. Throughput: 0: 49688.9. Samples: 191015248. Policy #0 lag: (min: 1.0, avg: 17.3, max: 32.0) [2023-03-09 08:30:29,059][22664] Avg episode reward: [(0, '55.124')] [2023-03-09 08:30:29,708][23090] Updated weights for policy 0, policy_version 46650 (0.0019) [2023-03-09 08:30:30,460][23090] Updated weights for policy 0, policy_version 46660 (0.0018) [2023-03-09 08:30:31,342][23090] Updated weights for policy 0, policy_version 46670 (0.0018) [2023-03-09 08:30:32,104][23090] Updated weights for policy 0, policy_version 46680 (0.0019) [2023-03-09 08:30:32,938][23090] Updated weights for policy 0, policy_version 46690 (0.0017) [2023-03-09 08:30:33,814][23090] Updated weights for policy 0, policy_version 46700 (0.0013) [2023-03-09 08:30:34,059][22664] Fps is (10 sec: 196605.7, 60 sec: 198519.2, 300 sec: 198273.9). Total num frames: 765181952. Throughput: 0: 49597.9. Samples: 191310096. Policy #0 lag: (min: 1.0, avg: 17.3, max: 32.0) [2023-03-09 08:30:34,061][22664] Avg episode reward: [(0, '50.537')] [2023-03-09 08:30:34,581][23090] Updated weights for policy 0, policy_version 46710 (0.0020) [2023-03-09 08:30:35,227][22940] Signal inference workers to stop experience collection... (15100 times) [2023-03-09 08:30:35,238][22940] Signal inference workers to resume experience collection... (15100 times) [2023-03-09 08:30:35,268][23090] InferenceWorker_p0-w0: stopping experience collection (15100 times) [2023-03-09 08:30:35,314][23090] InferenceWorker_p0-w0: resuming experience collection (15100 times) [2023-03-09 08:30:35,364][23090] Updated weights for policy 0, policy_version 46720 (0.0019) [2023-03-09 08:30:36,287][23090] Updated weights for policy 0, policy_version 46730 (0.0015) [2023-03-09 08:30:37,096][23090] Updated weights for policy 0, policy_version 46740 (0.0016) [2023-03-09 08:30:37,922][23090] Updated weights for policy 0, policy_version 46750 (0.0013) [2023-03-09 08:30:38,761][23090] Updated weights for policy 0, policy_version 46760 (0.0016) [2023-03-09 08:30:39,059][22664] Fps is (10 sec: 198240.2, 60 sec: 198246.4, 300 sec: 198274.2). Total num frames: 766164992. Throughput: 0: 49552.6. Samples: 191607024. Policy #0 lag: (min: 0.0, avg: 17.3, max: 32.0) [2023-03-09 08:30:39,061][22664] Avg episode reward: [(0, '52.115')] [2023-03-09 08:30:39,582][23090] Updated weights for policy 0, policy_version 46770 (0.0013) [2023-03-09 08:30:40,399][23090] Updated weights for policy 0, policy_version 46780 (0.0017) [2023-03-09 08:30:41,207][23090] Updated weights for policy 0, policy_version 46790 (0.0012) [2023-03-09 08:30:42,057][23090] Updated weights for policy 0, policy_version 46800 (0.0017) [2023-03-09 08:30:42,908][23090] Updated weights for policy 0, policy_version 46810 (0.0013) [2023-03-09 08:30:43,654][23090] Updated weights for policy 0, policy_version 46820 (0.0016) [2023-03-09 08:30:44,059][22664] Fps is (10 sec: 198248.8, 60 sec: 198519.0, 300 sec: 198329.7). Total num frames: 767164416. Throughput: 0: 49507.7. Samples: 191756480. Policy #0 lag: (min: 0.0, avg: 17.3, max: 32.0) [2023-03-09 08:30:44,061][22664] Avg episode reward: [(0, '55.674')] [2023-03-09 08:30:44,577][23090] Updated weights for policy 0, policy_version 46831 (0.0013) [2023-03-09 08:30:45,469][23090] Updated weights for policy 0, policy_version 46841 (0.0013) [2023-03-09 08:30:46,232][23090] Updated weights for policy 0, policy_version 46851 (0.0013) [2023-03-09 08:30:47,124][23090] Updated weights for policy 0, policy_version 46861 (0.0022) [2023-03-09 08:30:47,881][23090] Updated weights for policy 0, policy_version 46871 (0.0013) [2023-03-09 08:30:48,684][23090] Updated weights for policy 0, policy_version 46881 (0.0019) [2023-03-09 08:30:49,058][22664] Fps is (10 sec: 199892.4, 60 sec: 198792.9, 300 sec: 198329.9). Total num frames: 768163840. Throughput: 0: 49509.0. Samples: 192053408. Policy #0 lag: (min: 0.0, avg: 17.3, max: 32.0) [2023-03-09 08:30:49,059][22664] Avg episode reward: [(0, '53.282')] [2023-03-09 08:30:49,570][23090] Updated weights for policy 0, policy_version 46891 (0.0013) [2023-03-09 08:30:49,910][22940] Signal inference workers to stop experience collection... (15150 times) [2023-03-09 08:30:49,910][22940] Signal inference workers to resume experience collection... (15150 times) [2023-03-09 08:30:49,975][23090] InferenceWorker_p0-w0: stopping experience collection (15150 times) [2023-03-09 08:30:49,977][23090] InferenceWorker_p0-w0: resuming experience collection (15150 times) [2023-03-09 08:30:50,348][23090] Updated weights for policy 0, policy_version 46901 (0.0017) [2023-03-09 08:30:51,161][23090] Updated weights for policy 0, policy_version 46911 (0.0017) [2023-03-09 08:30:52,036][23090] Updated weights for policy 0, policy_version 46921 (0.0018) [2023-03-09 08:30:52,872][23090] Updated weights for policy 0, policy_version 46931 (0.0022) [2023-03-09 08:30:53,642][23090] Updated weights for policy 0, policy_version 46941 (0.0014) [2023-03-09 08:30:54,059][22664] Fps is (10 sec: 199883.4, 60 sec: 198791.4, 300 sec: 198385.1). Total num frames: 769163264. Throughput: 0: 49507.6. Samples: 192350288. Policy #0 lag: (min: 0.0, avg: 17.3, max: 32.0) [2023-03-09 08:30:54,061][22664] Avg episode reward: [(0, '49.190')] [2023-03-09 08:30:54,486][23090] Updated weights for policy 0, policy_version 46951 (0.0018) [2023-03-09 08:30:55,335][23090] Updated weights for policy 0, policy_version 46961 (0.0013) [2023-03-09 08:30:56,232][23090] Updated weights for policy 0, policy_version 46971 (0.0018) [2023-03-09 08:30:56,960][23090] Updated weights for policy 0, policy_version 46981 (0.0013) [2023-03-09 08:30:57,928][23090] Updated weights for policy 0, policy_version 46992 (0.0013) [2023-03-09 08:30:58,773][23090] Updated weights for policy 0, policy_version 47002 (0.0013) [2023-03-09 08:30:59,059][22664] Fps is (10 sec: 198242.6, 60 sec: 198247.0, 300 sec: 198329.8). Total num frames: 770146304. Throughput: 0: 49552.9. Samples: 192499760. Policy #0 lag: (min: 0.0, avg: 17.3, max: 32.0) [2023-03-09 08:30:59,060][22664] Avg episode reward: [(0, '52.478')] [2023-03-09 08:30:59,514][23090] Updated weights for policy 0, policy_version 47012 (0.0013) [2023-03-09 08:31:00,519][23090] Updated weights for policy 0, policy_version 47023 (0.0013) [2023-03-09 08:31:01,362][23090] Updated weights for policy 0, policy_version 47033 (0.0013) [2023-03-09 08:31:02,102][23090] Updated weights for policy 0, policy_version 47043 (0.0017) [2023-03-09 08:31:03,021][23090] Updated weights for policy 0, policy_version 47053 (0.0013) [2023-03-09 08:31:03,756][23090] Updated weights for policy 0, policy_version 47063 (0.0016) [2023-03-09 08:31:04,059][22664] Fps is (10 sec: 196607.2, 60 sec: 197972.3, 300 sec: 198274.0). Total num frames: 771129344. Throughput: 0: 49506.9. Samples: 192796672. Policy #0 lag: (min: 0.0, avg: 17.3, max: 32.0) [2023-03-09 08:31:04,061][22664] Avg episode reward: [(0, '50.947')] [2023-03-09 08:31:04,586][23090] Updated weights for policy 0, policy_version 47073 (0.0013) [2023-03-09 08:31:04,932][22940] Signal inference workers to stop experience collection... (15200 times) [2023-03-09 08:31:04,933][22940] Signal inference workers to resume experience collection... (15200 times) [2023-03-09 08:31:04,991][23090] InferenceWorker_p0-w0: stopping experience collection (15200 times) [2023-03-09 08:31:04,992][23090] InferenceWorker_p0-w0: resuming experience collection (15200 times) [2023-03-09 08:31:05,440][23090] Updated weights for policy 0, policy_version 47083 (0.0016) [2023-03-09 08:31:06,225][23090] Updated weights for policy 0, policy_version 47093 (0.0017) [2023-03-09 08:31:07,061][23090] Updated weights for policy 0, policy_version 47103 (0.0013) [2023-03-09 08:31:07,918][23090] Updated weights for policy 0, policy_version 47113 (0.0018) [2023-03-09 08:31:08,811][23090] Updated weights for policy 0, policy_version 47123 (0.0015) [2023-03-09 08:31:09,059][22664] Fps is (10 sec: 198249.2, 60 sec: 198246.3, 300 sec: 198329.7). Total num frames: 772128768. Throughput: 0: 49506.4. Samples: 193093536. Policy #0 lag: (min: 1.0, avg: 16.6, max: 33.0) [2023-03-09 08:31:09,060][22664] Avg episode reward: [(0, '52.658')] [2023-03-09 08:31:09,550][23090] Updated weights for policy 0, policy_version 47133 (0.0013) [2023-03-09 08:31:10,361][23090] Updated weights for policy 0, policy_version 47143 (0.0013) [2023-03-09 08:31:11,254][23090] Updated weights for policy 0, policy_version 47153 (0.0013) [2023-03-09 08:31:12,110][23090] Updated weights for policy 0, policy_version 47163 (0.0013) [2023-03-09 08:31:12,861][23090] Updated weights for policy 0, policy_version 47173 (0.0012) [2023-03-09 08:31:13,724][23090] Updated weights for policy 0, policy_version 47183 (0.0013) [2023-03-09 08:31:14,059][22664] Fps is (10 sec: 198246.9, 60 sec: 197972.3, 300 sec: 198274.1). Total num frames: 773111808. Throughput: 0: 49505.8. Samples: 193243024. Policy #0 lag: (min: 1.0, avg: 16.6, max: 33.0) [2023-03-09 08:31:14,061][22664] Avg episode reward: [(0, '54.354')] [2023-03-09 08:31:14,612][23090] Updated weights for policy 0, policy_version 47193 (0.0017) [2023-03-09 08:31:15,350][23090] Updated weights for policy 0, policy_version 47203 (0.0013) [2023-03-09 08:31:16,279][23090] Updated weights for policy 0, policy_version 47213 (0.0020) [2023-03-09 08:31:17,058][23090] Updated weights for policy 0, policy_version 47223 (0.0027) [2023-03-09 08:31:17,869][23090] Updated weights for policy 0, policy_version 47233 (0.0016) [2023-03-09 08:31:18,726][23090] Updated weights for policy 0, policy_version 47243 (0.0013) [2023-03-09 08:31:19,059][22664] Fps is (10 sec: 196601.7, 60 sec: 197973.4, 300 sec: 198274.4). Total num frames: 774094848. Throughput: 0: 49506.1. Samples: 193537872. Policy #0 lag: (min: 1.0, avg: 16.6, max: 33.0) [2023-03-09 08:31:19,060][22664] Avg episode reward: [(0, '54.319')] [2023-03-09 08:31:19,067][22940] Saving /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000047247_774094848.pth... [2023-03-09 08:31:19,126][22940] Removing /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000044341_726482944.pth [2023-03-09 08:31:19,596][23090] Updated weights for policy 0, policy_version 47254 (0.0013) [2023-03-09 08:31:20,371][23090] Updated weights for policy 0, policy_version 47264 (0.0022) [2023-03-09 08:31:21,288][23090] Updated weights for policy 0, policy_version 47274 (0.0021) [2023-03-09 08:31:22,105][23090] Updated weights for policy 0, policy_version 47284 (0.0013) [2023-03-09 08:31:22,946][23090] Updated weights for policy 0, policy_version 47294 (0.0016) [2023-03-09 08:31:23,703][22940] Signal inference workers to stop experience collection... (15250 times) [2023-03-09 08:31:23,704][22940] Signal inference workers to resume experience collection... (15250 times) [2023-03-09 08:31:23,772][23090] InferenceWorker_p0-w0: stopping experience collection (15250 times) [2023-03-09 08:31:23,772][23090] InferenceWorker_p0-w0: resuming experience collection (15250 times) [2023-03-09 08:31:23,819][23090] Updated weights for policy 0, policy_version 47304 (0.0017) [2023-03-09 08:31:24,059][22664] Fps is (10 sec: 194972.4, 60 sec: 197427.4, 300 sec: 198218.5). Total num frames: 775061504. Throughput: 0: 49460.8. Samples: 193832752. Policy #0 lag: (min: 1.0, avg: 16.6, max: 33.0) [2023-03-09 08:31:24,060][22664] Avg episode reward: [(0, '54.451')] [2023-03-09 08:31:24,710][23090] Updated weights for policy 0, policy_version 47314 (0.0017) [2023-03-09 08:31:25,526][23090] Updated weights for policy 0, policy_version 47324 (0.0026) [2023-03-09 08:31:26,329][23090] Updated weights for policy 0, policy_version 47334 (0.0018) [2023-03-09 08:31:27,174][23090] Updated weights for policy 0, policy_version 47344 (0.0013) [2023-03-09 08:31:28,038][23090] Updated weights for policy 0, policy_version 47354 (0.0020) [2023-03-09 08:31:28,768][23090] Updated weights for policy 0, policy_version 47364 (0.0015) [2023-03-09 08:31:29,059][22664] Fps is (10 sec: 194969.3, 60 sec: 197699.2, 300 sec: 198163.1). Total num frames: 776044544. Throughput: 0: 49369.8. Samples: 193978128. Policy #0 lag: (min: 1.0, avg: 16.6, max: 33.0) [2023-03-09 08:31:29,062][22664] Avg episode reward: [(0, '52.149')] [2023-03-09 08:31:29,650][23090] Updated weights for policy 0, policy_version 47374 (0.0016) [2023-03-09 08:31:30,433][23090] Updated weights for policy 0, policy_version 47384 (0.0021) [2023-03-09 08:31:31,314][23090] Updated weights for policy 0, policy_version 47394 (0.0013) [2023-03-09 08:31:32,220][23090] Updated weights for policy 0, policy_version 47404 (0.0013) [2023-03-09 08:31:32,915][23090] Updated weights for policy 0, policy_version 47414 (0.0016) [2023-03-09 08:31:33,786][23090] Updated weights for policy 0, policy_version 47424 (0.0013) [2023-03-09 08:31:34,059][22664] Fps is (10 sec: 198248.4, 60 sec: 197701.2, 300 sec: 198219.1). Total num frames: 777043968. Throughput: 0: 49415.7. Samples: 194277120. Policy #0 lag: (min: 1.0, avg: 16.6, max: 33.0) [2023-03-09 08:31:34,060][22664] Avg episode reward: [(0, '52.557')] [2023-03-09 08:31:34,614][23090] Updated weights for policy 0, policy_version 47434 (0.0013) [2023-03-09 08:31:35,452][23090] Updated weights for policy 0, policy_version 47444 (0.0013) [2023-03-09 08:31:36,350][23090] Updated weights for policy 0, policy_version 47455 (0.0013) [2023-03-09 08:31:37,207][23090] Updated weights for policy 0, policy_version 47465 (0.0013) [2023-03-09 08:31:38,138][23090] Updated weights for policy 0, policy_version 47476 (0.0018) [2023-03-09 08:31:38,969][23090] Updated weights for policy 0, policy_version 47486 (0.0016) [2023-03-09 08:31:39,059][22664] Fps is (10 sec: 198249.9, 60 sec: 197700.8, 300 sec: 198163.0). Total num frames: 778027008. Throughput: 0: 49326.3. Samples: 194569968. Policy #0 lag: (min: 1.0, avg: 16.3, max: 32.0) [2023-03-09 08:31:39,060][22664] Avg episode reward: [(0, '54.694')] [2023-03-09 08:31:39,786][23090] Updated weights for policy 0, policy_version 47496 (0.0016) [2023-03-09 08:31:40,589][23090] Updated weights for policy 0, policy_version 47506 (0.0013) [2023-03-09 08:31:41,364][22940] Signal inference workers to stop experience collection... (15300 times) [2023-03-09 08:31:41,383][22940] Signal inference workers to resume experience collection... (15300 times) [2023-03-09 08:31:41,393][23090] InferenceWorker_p0-w0: stopping experience collection (15300 times) [2023-03-09 08:31:41,393][23090] InferenceWorker_p0-w0: resuming experience collection (15300 times) [2023-03-09 08:31:41,485][23090] Updated weights for policy 0, policy_version 47516 (0.0022) [2023-03-09 08:31:42,214][23090] Updated weights for policy 0, policy_version 47526 (0.0014) [2023-03-09 08:31:43,064][23090] Updated weights for policy 0, policy_version 47536 (0.0016) [2023-03-09 08:31:43,980][23090] Updated weights for policy 0, policy_version 47546 (0.0013) [2023-03-09 08:31:44,058][22664] Fps is (10 sec: 196609.2, 60 sec: 197427.9, 300 sec: 198163.1). Total num frames: 779010048. Throughput: 0: 49325.7. Samples: 194719408. Policy #0 lag: (min: 1.0, avg: 16.3, max: 32.0) [2023-03-09 08:31:44,059][22664] Avg episode reward: [(0, '51.943')] [2023-03-09 08:31:44,671][23090] Updated weights for policy 0, policy_version 47556 (0.0017) [2023-03-09 08:31:45,640][23090] Updated weights for policy 0, policy_version 47566 (0.0015) [2023-03-09 08:31:46,527][23090] Updated weights for policy 0, policy_version 47577 (0.0013) [2023-03-09 08:31:47,288][23090] Updated weights for policy 0, policy_version 47587 (0.0021) [2023-03-09 08:31:48,182][23090] Updated weights for policy 0, policy_version 47597 (0.0013) [2023-03-09 08:31:48,927][23090] Updated weights for policy 0, policy_version 47607 (0.0019) [2023-03-09 08:31:49,059][22664] Fps is (10 sec: 198244.8, 60 sec: 197426.2, 300 sec: 198163.1). Total num frames: 780009472. Throughput: 0: 49324.5. Samples: 195016272. Policy #0 lag: (min: 1.0, avg: 16.3, max: 32.0) [2023-03-09 08:31:49,061][22664] Avg episode reward: [(0, '54.591')] [2023-03-09 08:31:49,791][23090] Updated weights for policy 0, policy_version 47617 (0.0017) [2023-03-09 08:31:50,611][23090] Updated weights for policy 0, policy_version 47627 (0.0018) [2023-03-09 08:31:51,413][23090] Updated weights for policy 0, policy_version 47637 (0.0014) [2023-03-09 08:31:52,218][23090] Updated weights for policy 0, policy_version 47647 (0.0014) [2023-03-09 08:31:53,110][23090] Updated weights for policy 0, policy_version 47657 (0.0015) [2023-03-09 08:31:53,932][23090] Updated weights for policy 0, policy_version 47667 (0.0019) [2023-03-09 08:31:54,059][22664] Fps is (10 sec: 199881.5, 60 sec: 197427.6, 300 sec: 198218.5). Total num frames: 781008896. Throughput: 0: 49324.6. Samples: 195313152. Policy #0 lag: (min: 1.0, avg: 16.3, max: 32.0) [2023-03-09 08:31:54,060][22664] Avg episode reward: [(0, '55.393')] [2023-03-09 08:31:54,791][23090] Updated weights for policy 0, policy_version 47678 (0.0016) [2023-03-09 08:31:55,666][23090] Updated weights for policy 0, policy_version 47688 (0.0013) [2023-03-09 08:31:56,555][23090] Updated weights for policy 0, policy_version 47698 (0.0013) [2023-03-09 08:31:57,201][22940] Signal inference workers to stop experience collection... (15350 times) [2023-03-09 08:31:57,202][22940] Signal inference workers to resume experience collection... (15350 times) [2023-03-09 08:31:57,277][23090] InferenceWorker_p0-w0: stopping experience collection (15350 times) [2023-03-09 08:31:57,279][23090] InferenceWorker_p0-w0: resuming experience collection (15350 times) [2023-03-09 08:31:57,364][23090] Updated weights for policy 0, policy_version 47709 (0.0016) [2023-03-09 08:31:58,240][23090] Updated weights for policy 0, policy_version 47719 (0.0013) [2023-03-09 08:31:59,047][23090] Updated weights for policy 0, policy_version 47729 (0.0019) [2023-03-09 08:31:59,059][22664] Fps is (10 sec: 198243.6, 60 sec: 197426.4, 300 sec: 198218.3). Total num frames: 781991936. Throughput: 0: 49324.7. Samples: 195462640. Policy #0 lag: (min: 1.0, avg: 16.3, max: 32.0) [2023-03-09 08:31:59,061][22664] Avg episode reward: [(0, '52.251')] [2023-03-09 08:31:59,904][23090] Updated weights for policy 0, policy_version 47739 (0.0013) [2023-03-09 08:32:00,640][23090] Updated weights for policy 0, policy_version 47749 (0.0025) [2023-03-09 08:32:01,548][23090] Updated weights for policy 0, policy_version 47759 (0.0013) [2023-03-09 08:32:02,355][23090] Updated weights for policy 0, policy_version 47769 (0.0013) [2023-03-09 08:32:03,164][23090] Updated weights for policy 0, policy_version 47779 (0.0018) [2023-03-09 08:32:04,011][23090] Updated weights for policy 0, policy_version 47789 (0.0015) [2023-03-09 08:32:04,059][22664] Fps is (10 sec: 196600.5, 60 sec: 197426.5, 300 sec: 198218.5). Total num frames: 782974976. Throughput: 0: 49415.6. Samples: 195761584. Policy #0 lag: (min: 1.0, avg: 16.3, max: 32.0) [2023-03-09 08:32:04,061][22664] Avg episode reward: [(0, '53.867')] [2023-03-09 08:32:04,767][23090] Updated weights for policy 0, policy_version 47799 (0.0023) [2023-03-09 08:32:05,610][23090] Updated weights for policy 0, policy_version 47809 (0.0013) [2023-03-09 08:32:06,430][23090] Updated weights for policy 0, policy_version 47819 (0.0017) [2023-03-09 08:32:07,195][23090] Updated weights for policy 0, policy_version 47829 (0.0015) [2023-03-09 08:32:08,004][23090] Updated weights for policy 0, policy_version 47839 (0.0013) [2023-03-09 08:32:08,889][23090] Updated weights for policy 0, policy_version 47849 (0.0017) [2023-03-09 08:32:09,059][22664] Fps is (10 sec: 199886.9, 60 sec: 197699.4, 300 sec: 198329.7). Total num frames: 783990784. Throughput: 0: 49506.3. Samples: 196060544. Policy #0 lag: (min: 1.0, avg: 17.4, max: 33.0) [2023-03-09 08:32:09,060][22664] Avg episode reward: [(0, '54.466')] [2023-03-09 08:32:09,748][23090] Updated weights for policy 0, policy_version 47859 (0.0026) [2023-03-09 08:32:10,504][23090] Updated weights for policy 0, policy_version 47869 (0.0021) [2023-03-09 08:32:10,600][22940] Signal inference workers to stop experience collection... (15400 times) [2023-03-09 08:32:10,602][22940] Signal inference workers to resume experience collection... (15400 times) [2023-03-09 08:32:10,659][23090] InferenceWorker_p0-w0: stopping experience collection (15400 times) [2023-03-09 08:32:10,660][23090] InferenceWorker_p0-w0: resuming experience collection (15400 times) [2023-03-09 08:32:11,355][23090] Updated weights for policy 0, policy_version 47879 (0.0017) [2023-03-09 08:32:12,325][23090] Updated weights for policy 0, policy_version 47890 (0.0018) [2023-03-09 08:32:13,100][23090] Updated weights for policy 0, policy_version 47900 (0.0016) [2023-03-09 08:32:13,866][23090] Updated weights for policy 0, policy_version 47910 (0.0017) [2023-03-09 08:32:14,059][22664] Fps is (10 sec: 199882.3, 60 sec: 197699.1, 300 sec: 198273.7). Total num frames: 784973824. Throughput: 0: 49642.7. Samples: 196212064. Policy #0 lag: (min: 1.0, avg: 17.4, max: 33.0) [2023-03-09 08:32:14,061][22664] Avg episode reward: [(0, '50.518')] [2023-03-09 08:32:14,779][23090] Updated weights for policy 0, policy_version 47920 (0.0021) [2023-03-09 08:32:15,631][23090] Updated weights for policy 0, policy_version 47930 (0.0025) [2023-03-09 08:32:16,436][23090] Updated weights for policy 0, policy_version 47941 (0.0015) [2023-03-09 08:32:17,347][23090] Updated weights for policy 0, policy_version 47951 (0.0016) [2023-03-09 08:32:18,152][23090] Updated weights for policy 0, policy_version 47961 (0.0014) [2023-03-09 08:32:18,997][23090] Updated weights for policy 0, policy_version 47972 (0.0016) [2023-03-09 08:32:19,059][22664] Fps is (10 sec: 198249.5, 60 sec: 197974.0, 300 sec: 198385.2). Total num frames: 785973248. Throughput: 0: 49595.6. Samples: 196508928. Policy #0 lag: (min: 1.0, avg: 17.4, max: 33.0) [2023-03-09 08:32:19,060][22664] Avg episode reward: [(0, '52.505')] [2023-03-09 08:32:20,041][23090] Updated weights for policy 0, policy_version 47983 (0.0016) [2023-03-09 08:32:20,800][23090] Updated weights for policy 0, policy_version 47993 (0.0020) [2023-03-09 08:32:21,571][23090] Updated weights for policy 0, policy_version 48003 (0.0018) [2023-03-09 08:32:22,439][23090] Updated weights for policy 0, policy_version 48013 (0.0013) [2023-03-09 08:32:23,173][23090] Updated weights for policy 0, policy_version 48023 (0.0017) [2023-03-09 08:32:24,052][23090] Updated weights for policy 0, policy_version 48033 (0.0014) [2023-03-09 08:32:24,059][22664] Fps is (10 sec: 199891.8, 60 sec: 198519.0, 300 sec: 198440.7). Total num frames: 786972672. Throughput: 0: 49686.3. Samples: 196805856. Policy #0 lag: (min: 1.0, avg: 17.4, max: 33.0) [2023-03-09 08:32:24,061][22664] Avg episode reward: [(0, '50.483')] [2023-03-09 08:32:24,904][23090] Updated weights for policy 0, policy_version 48043 (0.0017) [2023-03-09 08:32:25,704][23090] Updated weights for policy 0, policy_version 48053 (0.0017) [2023-03-09 08:32:26,362][22940] Signal inference workers to stop experience collection... (15450 times) [2023-03-09 08:32:26,363][22940] Signal inference workers to resume experience collection... (15450 times) [2023-03-09 08:32:26,434][23090] InferenceWorker_p0-w0: stopping experience collection (15450 times) [2023-03-09 08:32:26,435][23090] InferenceWorker_p0-w0: resuming experience collection (15450 times) [2023-03-09 08:32:26,477][23090] Updated weights for policy 0, policy_version 48063 (0.0018) [2023-03-09 08:32:27,329][23090] Updated weights for policy 0, policy_version 48073 (0.0019) [2023-03-09 08:32:28,223][23090] Updated weights for policy 0, policy_version 48083 (0.0024) [2023-03-09 08:32:29,005][23090] Updated weights for policy 0, policy_version 48093 (0.0017) [2023-03-09 08:32:29,059][22664] Fps is (10 sec: 198240.8, 60 sec: 198519.3, 300 sec: 198384.9). Total num frames: 787955712. Throughput: 0: 49687.3. Samples: 196955360. Policy #0 lag: (min: 1.0, avg: 17.4, max: 33.0) [2023-03-09 08:32:29,060][22664] Avg episode reward: [(0, '51.695')] [2023-03-09 08:32:29,829][23090] Updated weights for policy 0, policy_version 48103 (0.0013) [2023-03-09 08:32:30,709][23090] Updated weights for policy 0, policy_version 48113 (0.0018) [2023-03-09 08:32:31,579][23090] Updated weights for policy 0, policy_version 48123 (0.0017) [2023-03-09 08:32:32,294][23090] Updated weights for policy 0, policy_version 48133 (0.0017) [2023-03-09 08:32:33,196][23090] Updated weights for policy 0, policy_version 48143 (0.0017) [2023-03-09 08:32:34,030][23090] Updated weights for policy 0, policy_version 48153 (0.0021) [2023-03-09 08:32:34,058][22664] Fps is (10 sec: 196614.3, 60 sec: 198246.6, 300 sec: 198329.8). Total num frames: 788938752. Throughput: 0: 49689.5. Samples: 197252288. Policy #0 lag: (min: 1.0, avg: 17.4, max: 33.0) [2023-03-09 08:32:34,059][22664] Avg episode reward: [(0, '55.775')] [2023-03-09 08:32:34,790][23090] Updated weights for policy 0, policy_version 48163 (0.0013) [2023-03-09 08:32:35,645][23090] Updated weights for policy 0, policy_version 48173 (0.0017) [2023-03-09 08:32:36,416][23090] Updated weights for policy 0, policy_version 48183 (0.0016) [2023-03-09 08:32:37,289][23090] Updated weights for policy 0, policy_version 48193 (0.0018) [2023-03-09 08:32:38,140][23090] Updated weights for policy 0, policy_version 48203 (0.0016) [2023-03-09 08:32:38,939][23090] Updated weights for policy 0, policy_version 48214 (0.0013) [2023-03-09 08:32:39,058][22664] Fps is (10 sec: 199893.7, 60 sec: 198793.2, 300 sec: 198441.0). Total num frames: 789954560. Throughput: 0: 49736.0. Samples: 197551264. Policy #0 lag: (min: 1.0, avg: 17.0, max: 33.0) [2023-03-09 08:32:39,059][22664] Avg episode reward: [(0, '53.571')] [2023-03-09 08:32:39,776][23090] Updated weights for policy 0, policy_version 48224 (0.0013) [2023-03-09 08:32:40,643][23090] Updated weights for policy 0, policy_version 48234 (0.0016) [2023-03-09 08:32:41,346][22940] Signal inference workers to stop experience collection... (15500 times) [2023-03-09 08:32:41,348][22940] Signal inference workers to resume experience collection... (15500 times) [2023-03-09 08:32:41,412][23090] InferenceWorker_p0-w0: stopping experience collection (15500 times) [2023-03-09 08:32:41,413][23090] InferenceWorker_p0-w0: resuming experience collection (15500 times) [2023-03-09 08:32:41,462][23090] Updated weights for policy 0, policy_version 48244 (0.0015) [2023-03-09 08:32:42,276][23090] Updated weights for policy 0, policy_version 48254 (0.0021) [2023-03-09 08:32:43,109][23090] Updated weights for policy 0, policy_version 48264 (0.0019) [2023-03-09 08:32:43,990][23090] Updated weights for policy 0, policy_version 48274 (0.0019) [2023-03-09 08:32:44,058][22664] Fps is (10 sec: 199885.4, 60 sec: 198792.6, 300 sec: 198385.3). Total num frames: 790937600. Throughput: 0: 49735.2. Samples: 197700704. Policy #0 lag: (min: 1.0, avg: 17.0, max: 33.0) [2023-03-09 08:32:44,059][22664] Avg episode reward: [(0, '51.536')] [2023-03-09 08:32:44,812][23090] Updated weights for policy 0, policy_version 48284 (0.0016) [2023-03-09 08:32:45,701][23090] Updated weights for policy 0, policy_version 48295 (0.0017) [2023-03-09 08:32:46,528][23090] Updated weights for policy 0, policy_version 48305 (0.0016) [2023-03-09 08:32:47,381][23090] Updated weights for policy 0, policy_version 48315 (0.0021) [2023-03-09 08:32:48,175][23090] Updated weights for policy 0, policy_version 48325 (0.0018) [2023-03-09 08:32:49,060][23090] Updated weights for policy 0, policy_version 48335 (0.0019) [2023-03-09 08:32:49,059][22664] Fps is (10 sec: 196603.2, 60 sec: 198519.6, 300 sec: 198329.6). Total num frames: 791920640. Throughput: 0: 49644.8. Samples: 197995584. Policy #0 lag: (min: 1.0, avg: 17.0, max: 33.0) [2023-03-09 08:32:49,061][22664] Avg episode reward: [(0, '52.622')] [2023-03-09 08:32:49,847][23090] Updated weights for policy 0, policy_version 48345 (0.0018) [2023-03-09 08:32:50,629][23090] Updated weights for policy 0, policy_version 48355 (0.0017) [2023-03-09 08:32:51,528][23090] Updated weights for policy 0, policy_version 48365 (0.0026) [2023-03-09 08:32:52,319][23090] Updated weights for policy 0, policy_version 48375 (0.0021) [2023-03-09 08:32:53,147][23090] Updated weights for policy 0, policy_version 48385 (0.0015) [2023-03-09 08:32:53,988][23090] Updated weights for policy 0, policy_version 48395 (0.0018) [2023-03-09 08:32:54,058][22664] Fps is (10 sec: 196607.2, 60 sec: 198246.9, 300 sec: 198329.8). Total num frames: 792903680. Throughput: 0: 49596.8. Samples: 198292384. Policy #0 lag: (min: 1.0, avg: 17.0, max: 33.0) [2023-03-09 08:32:54,060][22664] Avg episode reward: [(0, '54.240')] [2023-03-09 08:32:54,809][23090] Updated weights for policy 0, policy_version 48405 (0.0021) [2023-03-09 08:32:55,813][23090] Updated weights for policy 0, policy_version 48417 (0.0016) [2023-03-09 08:32:56,640][23090] Updated weights for policy 0, policy_version 48427 (0.0018) [2023-03-09 08:32:57,484][23090] Updated weights for policy 0, policy_version 48437 (0.0018) [2023-03-09 08:32:58,253][23090] Updated weights for policy 0, policy_version 48447 (0.0013) [2023-03-09 08:32:59,059][22664] Fps is (10 sec: 198243.4, 60 sec: 198519.6, 300 sec: 198329.4). Total num frames: 793903104. Throughput: 0: 49506.1. Samples: 198439824. Policy #0 lag: (min: 1.0, avg: 17.0, max: 33.0) [2023-03-09 08:32:59,061][22664] Avg episode reward: [(0, '55.430')] [2023-03-09 08:32:59,136][23090] Updated weights for policy 0, policy_version 48457 (0.0018) [2023-03-09 08:33:00,003][23090] Updated weights for policy 0, policy_version 48467 (0.0020) [2023-03-09 08:33:00,675][22940] Signal inference workers to stop experience collection... (15550 times) [2023-03-09 08:33:00,689][22940] Signal inference workers to resume experience collection... (15550 times) [2023-03-09 08:33:00,720][23090] InferenceWorker_p0-w0: stopping experience collection (15550 times) [2023-03-09 08:33:00,760][23090] InferenceWorker_p0-w0: resuming experience collection (15550 times) [2023-03-09 08:33:00,806][23090] Updated weights for policy 0, policy_version 48477 (0.0016) [2023-03-09 08:33:01,616][23090] Updated weights for policy 0, policy_version 48487 (0.0015) [2023-03-09 08:33:02,469][23090] Updated weights for policy 0, policy_version 48497 (0.0021) [2023-03-09 08:33:03,323][23090] Updated weights for policy 0, policy_version 48507 (0.0017) [2023-03-09 08:33:04,058][22664] Fps is (10 sec: 199885.4, 60 sec: 198794.4, 300 sec: 198385.2). Total num frames: 794902528. Throughput: 0: 49461.2. Samples: 198734672. Policy #0 lag: (min: 1.0, avg: 17.0, max: 33.0) [2023-03-09 08:33:04,059][22664] Avg episode reward: [(0, '52.555')] [2023-03-09 08:33:04,062][23090] Updated weights for policy 0, policy_version 48517 (0.0017) [2023-03-09 08:33:04,994][23090] Updated weights for policy 0, policy_version 48527 (0.0016) [2023-03-09 08:33:05,809][23090] Updated weights for policy 0, policy_version 48537 (0.0017) [2023-03-09 08:33:06,574][23090] Updated weights for policy 0, policy_version 48547 (0.0021) [2023-03-09 08:33:07,433][23090] Updated weights for policy 0, policy_version 48557 (0.0017) [2023-03-09 08:33:08,246][23090] Updated weights for policy 0, policy_version 48568 (0.0016) [2023-03-09 08:33:09,059][22664] Fps is (10 sec: 198246.7, 60 sec: 198246.2, 300 sec: 198329.5). Total num frames: 795885568. Throughput: 0: 49505.4. Samples: 199033600. Policy #0 lag: (min: 1.0, avg: 16.8, max: 33.0) [2023-03-09 08:33:09,061][22664] Avg episode reward: [(0, '53.852')] [2023-03-09 08:33:09,127][23090] Updated weights for policy 0, policy_version 48578 (0.0013) [2023-03-09 08:33:09,996][23090] Updated weights for policy 0, policy_version 48588 (0.0018) [2023-03-09 08:33:10,843][23090] Updated weights for policy 0, policy_version 48598 (0.0016) [2023-03-09 08:33:11,655][23090] Updated weights for policy 0, policy_version 48608 (0.0013) [2023-03-09 08:33:12,472][23090] Updated weights for policy 0, policy_version 48618 (0.0016) [2023-03-09 08:33:13,342][23090] Updated weights for policy 0, policy_version 48628 (0.0013) [2023-03-09 08:33:14,058][22664] Fps is (10 sec: 196608.2, 60 sec: 198248.7, 300 sec: 198274.2). Total num frames: 796868608. Throughput: 0: 49505.6. Samples: 199183088. Policy #0 lag: (min: 1.0, avg: 16.8, max: 33.0) [2023-03-09 08:33:14,059][22664] Avg episode reward: [(0, '53.594')] [2023-03-09 08:33:14,121][23090] Updated weights for policy 0, policy_version 48638 (0.0016) [2023-03-09 08:33:14,942][23090] Updated weights for policy 0, policy_version 48648 (0.0019) [2023-03-09 08:33:15,815][23090] Updated weights for policy 0, policy_version 48658 (0.0021) [2023-03-09 08:33:16,621][23090] Updated weights for policy 0, policy_version 48668 (0.0014) [2023-03-09 08:33:17,369][23090] Updated weights for policy 0, policy_version 48678 (0.0013) [2023-03-09 08:33:18,253][23090] Updated weights for policy 0, policy_version 48688 (0.0013) [2023-03-09 08:33:19,058][22664] Fps is (10 sec: 198254.0, 60 sec: 198247.0, 300 sec: 198274.3). Total num frames: 797868032. Throughput: 0: 49504.7. Samples: 199480000. Policy #0 lag: (min: 1.0, avg: 16.8, max: 33.0) [2023-03-09 08:33:19,059][22664] Avg episode reward: [(0, '52.909')] [2023-03-09 08:33:19,065][22940] Saving /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000048698_797868032.pth... [2023-03-09 08:33:19,071][23090] Updated weights for policy 0, policy_version 48698 (0.0013) [2023-03-09 08:33:19,135][22940] Removing /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000045797_750338048.pth [2023-03-09 08:33:19,303][22940] Signal inference workers to stop experience collection... (15600 times) [2023-03-09 08:33:19,324][22940] Signal inference workers to resume experience collection... (15600 times) [2023-03-09 08:33:19,361][23090] InferenceWorker_p0-w0: stopping experience collection (15600 times) [2023-03-09 08:33:19,432][23090] InferenceWorker_p0-w0: resuming experience collection (15600 times) [2023-03-09 08:33:19,928][23090] Updated weights for policy 0, policy_version 48709 (0.0017) [2023-03-09 08:33:20,884][23090] Updated weights for policy 0, policy_version 48719 (0.0016) [2023-03-09 08:33:21,655][23090] Updated weights for policy 0, policy_version 48729 (0.0016) [2023-03-09 08:33:22,429][23090] Updated weights for policy 0, policy_version 48739 (0.0019) [2023-03-09 08:33:23,324][23090] Updated weights for policy 0, policy_version 48749 (0.0020) [2023-03-09 08:33:24,059][22664] Fps is (10 sec: 198245.7, 60 sec: 197974.4, 300 sec: 198218.8). Total num frames: 798851072. Throughput: 0: 49458.8. Samples: 199776912. Policy #0 lag: (min: 1.0, avg: 16.8, max: 33.0) [2023-03-09 08:33:24,060][22664] Avg episode reward: [(0, '53.465')] [2023-03-09 08:33:24,121][23090] Updated weights for policy 0, policy_version 48759 (0.0016) [2023-03-09 08:33:24,937][23090] Updated weights for policy 0, policy_version 48769 (0.0019) [2023-03-09 08:33:25,794][23090] Updated weights for policy 0, policy_version 48779 (0.0013) [2023-03-09 08:33:26,604][23090] Updated weights for policy 0, policy_version 48789 (0.0013) [2023-03-09 08:33:27,378][23090] Updated weights for policy 0, policy_version 48799 (0.0013) [2023-03-09 08:33:28,296][23090] Updated weights for policy 0, policy_version 48809 (0.0013) [2023-03-09 08:33:29,058][22664] Fps is (10 sec: 196607.5, 60 sec: 197974.7, 300 sec: 198163.3). Total num frames: 799834112. Throughput: 0: 49414.0. Samples: 199924336. Policy #0 lag: (min: 1.0, avg: 16.8, max: 33.0) [2023-03-09 08:33:29,060][22664] Avg episode reward: [(0, '53.456')] [2023-03-09 08:33:29,118][23090] Updated weights for policy 0, policy_version 48819 (0.0018) [2023-03-09 08:33:29,946][23090] Updated weights for policy 0, policy_version 48829 (0.0018) [2023-03-09 08:33:30,720][23090] Updated weights for policy 0, policy_version 48839 (0.0013) [2023-03-09 08:33:31,557][23090] Updated weights for policy 0, policy_version 48849 (0.0019) [2023-03-09 08:33:32,459][23090] Updated weights for policy 0, policy_version 48859 (0.0016) [2023-03-09 08:33:33,161][23090] Updated weights for policy 0, policy_version 48869 (0.0019) [2023-03-09 08:33:34,059][22664] Fps is (10 sec: 198244.3, 60 sec: 198246.0, 300 sec: 198163.1). Total num frames: 800833536. Throughput: 0: 49504.1. Samples: 200223264. Policy #0 lag: (min: 1.0, avg: 16.8, max: 33.0) [2023-03-09 08:33:34,060][22664] Avg episode reward: [(0, '52.412')] [2023-03-09 08:33:34,109][23090] Updated weights for policy 0, policy_version 48880 (0.0013) [2023-03-09 08:33:34,954][23090] Updated weights for policy 0, policy_version 48890 (0.0016) [2023-03-09 08:33:35,733][23090] Updated weights for policy 0, policy_version 48900 (0.0019) [2023-03-09 08:33:36,223][22940] Signal inference workers to stop experience collection... (15650 times) [2023-03-09 08:33:36,224][22940] Signal inference workers to resume experience collection... (15650 times) [2023-03-09 08:33:36,286][23090] InferenceWorker_p0-w0: stopping experience collection (15650 times) [2023-03-09 08:33:36,286][23090] InferenceWorker_p0-w0: resuming experience collection (15650 times) [2023-03-09 08:33:36,658][23090] Updated weights for policy 0, policy_version 48910 (0.0016) [2023-03-09 08:33:37,349][23090] Updated weights for policy 0, policy_version 48920 (0.0018) [2023-03-09 08:33:38,226][23090] Updated weights for policy 0, policy_version 48930 (0.0020) [2023-03-09 08:33:39,059][22664] Fps is (10 sec: 198243.3, 60 sec: 197699.7, 300 sec: 198274.3). Total num frames: 801816576. Throughput: 0: 49505.3. Samples: 200520128. Policy #0 lag: (min: 0.0, avg: 17.3, max: 34.0) [2023-03-09 08:33:39,060][22664] Avg episode reward: [(0, '52.813')] [2023-03-09 08:33:39,081][23090] Updated weights for policy 0, policy_version 48940 (0.0016) [2023-03-09 08:33:39,858][23090] Updated weights for policy 0, policy_version 48950 (0.0016) [2023-03-09 08:33:40,735][23090] Updated weights for policy 0, policy_version 48960 (0.0013) [2023-03-09 08:33:41,579][23090] Updated weights for policy 0, policy_version 48970 (0.0021) [2023-03-09 08:33:42,438][23090] Updated weights for policy 0, policy_version 48981 (0.0013) [2023-03-09 08:33:43,207][23090] Updated weights for policy 0, policy_version 48991 (0.0016) [2023-03-09 08:33:44,059][22664] Fps is (10 sec: 198248.1, 60 sec: 197973.1, 300 sec: 198219.0). Total num frames: 802816000. Throughput: 0: 49551.0. Samples: 200669600. Policy #0 lag: (min: 0.0, avg: 17.3, max: 34.0) [2023-03-09 08:33:44,060][22664] Avg episode reward: [(0, '51.806')] [2023-03-09 08:33:44,125][23090] Updated weights for policy 0, policy_version 49001 (0.0013) [2023-03-09 08:33:44,920][23090] Updated weights for policy 0, policy_version 49011 (0.0020) [2023-03-09 08:33:45,737][23090] Updated weights for policy 0, policy_version 49021 (0.0016) [2023-03-09 08:33:46,533][23090] Updated weights for policy 0, policy_version 49031 (0.0016) [2023-03-09 08:33:47,339][23090] Updated weights for policy 0, policy_version 49041 (0.0013) [2023-03-09 08:33:48,194][23090] Updated weights for policy 0, policy_version 49051 (0.0015) [2023-03-09 08:33:48,716][22940] Signal inference workers to stop experience collection... (15700 times) [2023-03-09 08:33:48,718][22940] Signal inference workers to resume experience collection... (15700 times) [2023-03-09 08:33:48,783][23090] InferenceWorker_p0-w0: stopping experience collection (15700 times) [2023-03-09 08:33:48,783][23090] InferenceWorker_p0-w0: resuming experience collection (15700 times) [2023-03-09 08:33:49,037][23090] Updated weights for policy 0, policy_version 49061 (0.0013) [2023-03-09 08:33:49,059][22664] Fps is (10 sec: 201524.3, 60 sec: 198519.8, 300 sec: 198274.2). Total num frames: 803831808. Throughput: 0: 49686.3. Samples: 200970560. Policy #0 lag: (min: 0.0, avg: 17.3, max: 34.0) [2023-03-09 08:33:49,060][22664] Avg episode reward: [(0, '53.718')] [2023-03-09 08:33:49,883][23090] Updated weights for policy 0, policy_version 49071 (0.0013) [2023-03-09 08:33:50,724][23090] Updated weights for policy 0, policy_version 49081 (0.0013) [2023-03-09 08:33:51,650][23090] Updated weights for policy 0, policy_version 49093 (0.0023) [2023-03-09 08:33:52,503][23090] Updated weights for policy 0, policy_version 49103 (0.0019) [2023-03-09 08:33:53,399][23090] Updated weights for policy 0, policy_version 49113 (0.0016) [2023-03-09 08:33:54,058][22664] Fps is (10 sec: 199885.2, 60 sec: 198519.5, 300 sec: 198274.2). Total num frames: 804814848. Throughput: 0: 49642.0. Samples: 201267472. Policy #0 lag: (min: 0.0, avg: 17.3, max: 34.0) [2023-03-09 08:33:54,059][22664] Avg episode reward: [(0, '53.780')] [2023-03-09 08:33:54,119][23090] Updated weights for policy 0, policy_version 49123 (0.0016) [2023-03-09 08:33:55,060][23090] Updated weights for policy 0, policy_version 49133 (0.0024) [2023-03-09 08:33:55,776][23090] Updated weights for policy 0, policy_version 49143 (0.0020) [2023-03-09 08:33:56,647][23090] Updated weights for policy 0, policy_version 49153 (0.0017) [2023-03-09 08:33:57,451][23090] Updated weights for policy 0, policy_version 49163 (0.0026) [2023-03-09 08:33:58,218][23090] Updated weights for policy 0, policy_version 49173 (0.0016) [2023-03-09 08:33:59,024][23090] Updated weights for policy 0, policy_version 49183 (0.0015) [2023-03-09 08:33:59,059][22664] Fps is (10 sec: 198247.4, 60 sec: 198520.5, 300 sec: 198329.9). Total num frames: 805814272. Throughput: 0: 49596.0. Samples: 201414912. Policy #0 lag: (min: 0.0, avg: 17.3, max: 34.0) [2023-03-09 08:33:59,060][22664] Avg episode reward: [(0, '55.748')] [2023-03-09 08:33:59,901][23090] Updated weights for policy 0, policy_version 49193 (0.0020) [2023-03-09 08:34:00,390][22940] Signal inference workers to stop experience collection... (15750 times) [2023-03-09 08:34:00,391][22940] Signal inference workers to resume experience collection... (15750 times) [2023-03-09 08:34:00,462][23090] InferenceWorker_p0-w0: stopping experience collection (15750 times) [2023-03-09 08:34:00,462][23090] InferenceWorker_p0-w0: resuming experience collection (15750 times) [2023-03-09 08:34:00,776][23090] Updated weights for policy 0, policy_version 49203 (0.0017) [2023-03-09 08:34:01,507][23090] Updated weights for policy 0, policy_version 49213 (0.0018) [2023-03-09 08:34:02,466][23090] Updated weights for policy 0, policy_version 49224 (0.0015) [2023-03-09 08:34:03,270][23090] Updated weights for policy 0, policy_version 49234 (0.0024) [2023-03-09 08:34:04,059][22664] Fps is (10 sec: 199880.2, 60 sec: 198518.6, 300 sec: 198329.8). Total num frames: 806813696. Throughput: 0: 49686.5. Samples: 201715904. Policy #0 lag: (min: 0.0, avg: 17.3, max: 34.0) [2023-03-09 08:34:04,061][22664] Avg episode reward: [(0, '55.542')] [2023-03-09 08:34:04,062][23090] Updated weights for policy 0, policy_version 49244 (0.0012) [2023-03-09 08:34:04,863][23090] Updated weights for policy 0, policy_version 49254 (0.0016) [2023-03-09 08:34:05,727][23090] Updated weights for policy 0, policy_version 49264 (0.0022) [2023-03-09 08:34:06,602][23090] Updated weights for policy 0, policy_version 49274 (0.0016) [2023-03-09 08:34:07,331][23090] Updated weights for policy 0, policy_version 49284 (0.0013) [2023-03-09 08:34:08,251][23090] Updated weights for policy 0, policy_version 49294 (0.0020) [2023-03-09 08:34:08,984][23090] Updated weights for policy 0, policy_version 49304 (0.0022) [2023-03-09 08:34:09,059][22664] Fps is (10 sec: 198241.6, 60 sec: 198519.7, 300 sec: 198274.1). Total num frames: 807796736. Throughput: 0: 49730.9. Samples: 202014816. Policy #0 lag: (min: 1.0, avg: 17.0, max: 32.0) [2023-03-09 08:34:09,061][22664] Avg episode reward: [(0, '54.412')] [2023-03-09 08:34:09,824][23090] Updated weights for policy 0, policy_version 49314 (0.0016) [2023-03-09 08:34:10,662][23090] Updated weights for policy 0, policy_version 49324 (0.0016) [2023-03-09 08:34:11,434][23090] Updated weights for policy 0, policy_version 49334 (0.0016) [2023-03-09 08:34:12,041][22940] Signal inference workers to stop experience collection... (15800 times) [2023-03-09 08:34:12,042][22940] Signal inference workers to resume experience collection... (15800 times) [2023-03-09 08:34:12,104][23090] InferenceWorker_p0-w0: stopping experience collection (15800 times) [2023-03-09 08:34:12,104][23090] InferenceWorker_p0-w0: resuming experience collection (15800 times) [2023-03-09 08:34:12,310][23090] Updated weights for policy 0, policy_version 49344 (0.0016) [2023-03-09 08:34:13,128][23090] Updated weights for policy 0, policy_version 49354 (0.0013) [2023-03-09 08:34:13,930][23090] Updated weights for policy 0, policy_version 49364 (0.0013) [2023-03-09 08:34:14,059][22664] Fps is (10 sec: 198240.8, 60 sec: 198790.7, 300 sec: 198274.3). Total num frames: 808796160. Throughput: 0: 49776.9. Samples: 202164320. Policy #0 lag: (min: 1.0, avg: 17.0, max: 32.0) [2023-03-09 08:34:14,061][22664] Avg episode reward: [(0, '52.587')] [2023-03-09 08:34:14,745][23090] Updated weights for policy 0, policy_version 49374 (0.0013) [2023-03-09 08:34:15,619][23090] Updated weights for policy 0, policy_version 49384 (0.0017) [2023-03-09 08:34:16,436][23090] Updated weights for policy 0, policy_version 49394 (0.0020) [2023-03-09 08:34:17,263][23090] Updated weights for policy 0, policy_version 49404 (0.0016) [2023-03-09 08:34:18,033][23090] Updated weights for policy 0, policy_version 49414 (0.0016) [2023-03-09 08:34:18,879][23090] Updated weights for policy 0, policy_version 49424 (0.0013) [2023-03-09 08:34:19,059][22664] Fps is (10 sec: 199883.6, 60 sec: 198791.3, 300 sec: 198273.9). Total num frames: 809795584. Throughput: 0: 49778.9. Samples: 202463328. Policy #0 lag: (min: 1.0, avg: 17.0, max: 32.0) [2023-03-09 08:34:19,101][22664] Avg episode reward: [(0, '52.585')] [2023-03-09 08:34:19,758][23090] Updated weights for policy 0, policy_version 49434 (0.0022) [2023-03-09 08:34:20,493][23090] Updated weights for policy 0, policy_version 49444 (0.0017) [2023-03-09 08:34:21,382][23090] Updated weights for policy 0, policy_version 49454 (0.0021) [2023-03-09 08:34:22,107][23090] Updated weights for policy 0, policy_version 49464 (0.0017) [2023-03-09 08:34:22,606][22940] Signal inference workers to stop experience collection... (15850 times) [2023-03-09 08:34:22,607][22940] Signal inference workers to resume experience collection... (15850 times) [2023-03-09 08:34:22,663][23090] InferenceWorker_p0-w0: stopping experience collection (15850 times) [2023-03-09 08:34:22,664][23090] InferenceWorker_p0-w0: resuming experience collection (15850 times) [2023-03-09 08:34:23,037][23090] Updated weights for policy 0, policy_version 49475 (0.0016) [2023-03-09 08:34:23,936][23090] Updated weights for policy 0, policy_version 49485 (0.0013) [2023-03-09 08:34:24,059][22664] Fps is (10 sec: 198251.4, 60 sec: 198791.7, 300 sec: 198274.0). Total num frames: 810778624. Throughput: 0: 49824.6. Samples: 202762240. Policy #0 lag: (min: 1.0, avg: 17.0, max: 32.0) [2023-03-09 08:34:24,060][22664] Avg episode reward: [(0, '53.722')] [2023-03-09 08:34:24,685][23090] Updated weights for policy 0, policy_version 49495 (0.0017) [2023-03-09 08:34:25,535][23090] Updated weights for policy 0, policy_version 49505 (0.0016) [2023-03-09 08:34:26,410][23090] Updated weights for policy 0, policy_version 49515 (0.0013) [2023-03-09 08:34:27,179][23090] Updated weights for policy 0, policy_version 49525 (0.0012) [2023-03-09 08:34:27,978][23090] Updated weights for policy 0, policy_version 49535 (0.0016) [2023-03-09 08:34:28,855][23090] Updated weights for policy 0, policy_version 49545 (0.0013) [2023-03-09 08:34:29,059][22664] Fps is (10 sec: 198248.9, 60 sec: 199064.8, 300 sec: 198329.7). Total num frames: 811778048. Throughput: 0: 49823.4. Samples: 202911664. Policy #0 lag: (min: 1.0, avg: 17.0, max: 32.0) [2023-03-09 08:34:29,060][22664] Avg episode reward: [(0, '53.147')] [2023-03-09 08:34:29,629][23090] Updated weights for policy 0, policy_version 49555 (0.0013) [2023-03-09 08:34:30,420][23090] Updated weights for policy 0, policy_version 49565 (0.0015) [2023-03-09 08:34:31,223][23090] Updated weights for policy 0, policy_version 49575 (0.0013) [2023-03-09 08:34:32,074][23090] Updated weights for policy 0, policy_version 49585 (0.0017) [2023-03-09 08:34:32,962][23090] Updated weights for policy 0, policy_version 49595 (0.0013) [2023-03-09 08:34:33,132][22940] Signal inference workers to stop experience collection... (15900 times) [2023-03-09 08:34:33,133][22940] Signal inference workers to resume experience collection... (15900 times) [2023-03-09 08:34:33,199][23090] InferenceWorker_p0-w0: stopping experience collection (15900 times) [2023-03-09 08:34:33,199][23090] InferenceWorker_p0-w0: resuming experience collection (15900 times) [2023-03-09 08:34:33,719][23090] Updated weights for policy 0, policy_version 49605 (0.0018) [2023-03-09 08:34:34,059][22664] Fps is (10 sec: 199886.3, 60 sec: 199065.3, 300 sec: 198329.8). Total num frames: 812777472. Throughput: 0: 49824.6. Samples: 203212672. Policy #0 lag: (min: 1.0, avg: 17.0, max: 32.0) [2023-03-09 08:34:34,060][22664] Avg episode reward: [(0, '54.571')] [2023-03-09 08:34:34,614][23090] Updated weights for policy 0, policy_version 49615 (0.0013) [2023-03-09 08:34:35,453][23090] Updated weights for policy 0, policy_version 49625 (0.0018) [2023-03-09 08:34:36,196][23090] Updated weights for policy 0, policy_version 49635 (0.0015) [2023-03-09 08:34:37,079][23090] Updated weights for policy 0, policy_version 49645 (0.0016) [2023-03-09 08:34:37,842][23090] Updated weights for policy 0, policy_version 49655 (0.0016) [2023-03-09 08:34:38,725][23090] Updated weights for policy 0, policy_version 49665 (0.0016) [2023-03-09 08:34:39,059][22664] Fps is (10 sec: 201521.2, 60 sec: 199611.2, 300 sec: 198440.6). Total num frames: 813793280. Throughput: 0: 49823.3. Samples: 203509536. Policy #0 lag: (min: 1.0, avg: 17.0, max: 32.0) [2023-03-09 08:34:39,061][22664] Avg episode reward: [(0, '54.435')] [2023-03-09 08:34:39,530][23090] Updated weights for policy 0, policy_version 49675 (0.0014) [2023-03-09 08:34:40,391][23090] Updated weights for policy 0, policy_version 49685 (0.0013) [2023-03-09 08:34:41,310][23090] Updated weights for policy 0, policy_version 49696 (0.0019) [2023-03-09 08:34:42,087][23090] Updated weights for policy 0, policy_version 49706 (0.0016) [2023-03-09 08:34:42,932][23090] Updated weights for policy 0, policy_version 49716 (0.0020) [2023-03-09 08:34:43,717][23090] Updated weights for policy 0, policy_version 49726 (0.0013) [2023-03-09 08:34:44,059][22664] Fps is (10 sec: 199883.9, 60 sec: 199338.0, 300 sec: 198440.7). Total num frames: 814776320. Throughput: 0: 49822.7. Samples: 203656944. Policy #0 lag: (min: 1.0, avg: 16.2, max: 33.0) [2023-03-09 08:34:44,060][22664] Avg episode reward: [(0, '54.646')] [2023-03-09 08:34:44,567][23090] Updated weights for policy 0, policy_version 49736 (0.0014) [2023-03-09 08:34:45,391][23090] Updated weights for policy 0, policy_version 49746 (0.0013) [2023-03-09 08:34:45,649][22940] Signal inference workers to stop experience collection... (15950 times) [2023-03-09 08:34:45,651][22940] Signal inference workers to resume experience collection... (15950 times) [2023-03-09 08:34:45,722][23090] InferenceWorker_p0-w0: stopping experience collection (15950 times) [2023-03-09 08:34:45,722][23090] InferenceWorker_p0-w0: resuming experience collection (15950 times) [2023-03-09 08:34:46,220][23090] Updated weights for policy 0, policy_version 49756 (0.0020) [2023-03-09 08:34:46,987][23090] Updated weights for policy 0, policy_version 49766 (0.0016) [2023-03-09 08:34:47,884][23090] Updated weights for policy 0, policy_version 49776 (0.0014) [2023-03-09 08:34:48,748][23090] Updated weights for policy 0, policy_version 49786 (0.0017) [2023-03-09 08:34:49,058][22664] Fps is (10 sec: 196615.2, 60 sec: 198793.0, 300 sec: 198385.2). Total num frames: 815759360. Throughput: 0: 49732.2. Samples: 203953840. Policy #0 lag: (min: 1.0, avg: 16.2, max: 33.0) [2023-03-09 08:34:49,060][22664] Avg episode reward: [(0, '55.451')] [2023-03-09 08:34:49,505][23090] Updated weights for policy 0, policy_version 49796 (0.0018) [2023-03-09 08:34:50,404][23090] Updated weights for policy 0, policy_version 49806 (0.0013) [2023-03-09 08:34:51,143][23090] Updated weights for policy 0, policy_version 49816 (0.0013) [2023-03-09 08:34:52,001][23090] Updated weights for policy 0, policy_version 49826 (0.0013) [2023-03-09 08:34:52,884][23090] Updated weights for policy 0, policy_version 49836 (0.0022) [2023-03-09 08:34:53,685][23090] Updated weights for policy 0, policy_version 49846 (0.0022) [2023-03-09 08:34:54,059][22664] Fps is (10 sec: 196601.3, 60 sec: 198790.7, 300 sec: 198274.0). Total num frames: 816742400. Throughput: 0: 49687.2. Samples: 204250752. Policy #0 lag: (min: 1.0, avg: 16.2, max: 33.0) [2023-03-09 08:34:54,061][22664] Avg episode reward: [(0, '53.932')] [2023-03-09 08:34:54,499][23090] Updated weights for policy 0, policy_version 49856 (0.0013) [2023-03-09 08:34:55,340][23090] Updated weights for policy 0, policy_version 49866 (0.0020) [2023-03-09 08:34:56,166][23090] Updated weights for policy 0, policy_version 49876 (0.0017) [2023-03-09 08:34:56,969][23090] Updated weights for policy 0, policy_version 49886 (0.0016) [2023-03-09 08:34:57,263][22940] Signal inference workers to stop experience collection... (16000 times) [2023-03-09 08:34:57,264][22940] Signal inference workers to resume experience collection... (16000 times) [2023-03-09 08:34:57,322][23090] InferenceWorker_p0-w0: stopping experience collection (16000 times) [2023-03-09 08:34:57,322][23090] InferenceWorker_p0-w0: resuming experience collection (16000 times) [2023-03-09 08:34:57,819][23090] Updated weights for policy 0, policy_version 49896 (0.0017) [2023-03-09 08:34:58,663][23090] Updated weights for policy 0, policy_version 49906 (0.0013) [2023-03-09 08:34:59,058][22664] Fps is (10 sec: 198245.6, 60 sec: 198792.7, 300 sec: 198274.2). Total num frames: 817741824. Throughput: 0: 49641.4. Samples: 204398160. Policy #0 lag: (min: 1.0, avg: 16.2, max: 33.0) [2023-03-09 08:34:59,060][22664] Avg episode reward: [(0, '54.618')] [2023-03-09 08:34:59,483][23090] Updated weights for policy 0, policy_version 49916 (0.0018) [2023-03-09 08:35:00,261][23090] Updated weights for policy 0, policy_version 49926 (0.0016) [2023-03-09 08:35:01,199][23090] Updated weights for policy 0, policy_version 49937 (0.0013) [2023-03-09 08:35:02,116][23090] Updated weights for policy 0, policy_version 49947 (0.0021) [2023-03-09 08:35:02,838][23090] Updated weights for policy 0, policy_version 49957 (0.0013) [2023-03-09 08:35:03,711][23090] Updated weights for policy 0, policy_version 49967 (0.0013) [2023-03-09 08:35:04,059][22664] Fps is (10 sec: 198252.8, 60 sec: 198519.4, 300 sec: 198274.0). Total num frames: 818724864. Throughput: 0: 49593.0. Samples: 204695008. Policy #0 lag: (min: 1.0, avg: 16.2, max: 33.0) [2023-03-09 08:35:04,060][22664] Avg episode reward: [(0, '51.385')] [2023-03-09 08:35:04,529][23090] Updated weights for policy 0, policy_version 49977 (0.0012) [2023-03-09 08:35:05,268][23090] Updated weights for policy 0, policy_version 49987 (0.0013) [2023-03-09 08:35:06,221][23090] Updated weights for policy 0, policy_version 49997 (0.0021) [2023-03-09 08:35:06,927][23090] Updated weights for policy 0, policy_version 50007 (0.0013) [2023-03-09 08:35:07,808][23090] Updated weights for policy 0, policy_version 50017 (0.0021) [2023-03-09 08:35:08,639][23090] Updated weights for policy 0, policy_version 50027 (0.0020) [2023-03-09 08:35:09,059][22664] Fps is (10 sec: 198240.7, 60 sec: 198792.5, 300 sec: 198274.0). Total num frames: 819724288. Throughput: 0: 49593.6. Samples: 204993952. Policy #0 lag: (min: 1.0, avg: 16.2, max: 33.0) [2023-03-09 08:35:09,061][22664] Avg episode reward: [(0, '55.273')] [2023-03-09 08:35:09,464][23090] Updated weights for policy 0, policy_version 50037 (0.0027) [2023-03-09 08:35:10,255][23090] Updated weights for policy 0, policy_version 50047 (0.0016) [2023-03-09 08:35:11,120][22940] Signal inference workers to stop experience collection... (16050 times) [2023-03-09 08:35:11,122][22940] Signal inference workers to resume experience collection... (16050 times) [2023-03-09 08:35:11,155][23090] Updated weights for policy 0, policy_version 50057 (0.0013) [2023-03-09 08:35:11,194][23090] InferenceWorker_p0-w0: stopping experience collection (16050 times) [2023-03-09 08:35:11,195][23090] InferenceWorker_p0-w0: resuming experience collection (16050 times) [2023-03-09 08:35:11,987][23090] Updated weights for policy 0, policy_version 50067 (0.0013) [2023-03-09 08:35:12,758][23090] Updated weights for policy 0, policy_version 50077 (0.0017) [2023-03-09 08:35:13,553][23090] Updated weights for policy 0, policy_version 50087 (0.0013) [2023-03-09 08:35:14,058][22664] Fps is (10 sec: 196613.4, 60 sec: 198248.2, 300 sec: 198218.9). Total num frames: 820690944. Throughput: 0: 49595.0. Samples: 205143424. Policy #0 lag: (min: 1.0, avg: 17.5, max: 33.0) [2023-03-09 08:35:14,059][22664] Avg episode reward: [(0, '54.839')] [2023-03-09 08:35:14,362][23090] Updated weights for policy 0, policy_version 50097 (0.0017) [2023-03-09 08:35:15,247][23090] Updated weights for policy 0, policy_version 50107 (0.0017) [2023-03-09 08:35:16,007][23090] Updated weights for policy 0, policy_version 50117 (0.0016) [2023-03-09 08:35:16,880][23090] Updated weights for policy 0, policy_version 50127 (0.0016) [2023-03-09 08:35:17,707][23090] Updated weights for policy 0, policy_version 50137 (0.0013) [2023-03-09 08:35:18,536][23090] Updated weights for policy 0, policy_version 50147 (0.0016) [2023-03-09 08:35:19,059][22664] Fps is (10 sec: 199886.7, 60 sec: 198793.0, 300 sec: 198329.7). Total num frames: 821723136. Throughput: 0: 49549.1. Samples: 205442384. Policy #0 lag: (min: 1.0, avg: 17.5, max: 33.0) [2023-03-09 08:35:19,064][22664] Avg episode reward: [(0, '52.913')] [2023-03-09 08:35:19,071][22940] Saving /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000050154_821723136.pth... [2023-03-09 08:35:19,128][22940] Removing /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000047247_774094848.pth [2023-03-09 08:35:19,446][23090] Updated weights for policy 0, policy_version 50158 (0.0020) [2023-03-09 08:35:20,192][23090] Updated weights for policy 0, policy_version 50168 (0.0016) [2023-03-09 08:35:21,044][23090] Updated weights for policy 0, policy_version 50178 (0.0016) [2023-03-09 08:35:21,123][22940] Signal inference workers to stop experience collection... (16100 times) [2023-03-09 08:35:21,138][22940] Signal inference workers to resume experience collection... (16100 times) [2023-03-09 08:35:21,203][23090] InferenceWorker_p0-w0: stopping experience collection (16100 times) [2023-03-09 08:35:21,203][23090] InferenceWorker_p0-w0: resuming experience collection (16100 times) [2023-03-09 08:35:21,931][23090] Updated weights for policy 0, policy_version 50188 (0.0013) [2023-03-09 08:35:22,740][23090] Updated weights for policy 0, policy_version 50199 (0.0018) [2023-03-09 08:35:23,598][23090] Updated weights for policy 0, policy_version 50209 (0.0015) [2023-03-09 08:35:24,059][22664] Fps is (10 sec: 201522.1, 60 sec: 198793.3, 300 sec: 198385.3). Total num frames: 822706176. Throughput: 0: 49597.1. Samples: 205741392. Policy #0 lag: (min: 1.0, avg: 17.5, max: 33.0) [2023-03-09 08:35:24,060][22664] Avg episode reward: [(0, '50.746')] [2023-03-09 08:35:24,443][23090] Updated weights for policy 0, policy_version 50219 (0.0016) [2023-03-09 08:35:25,248][23090] Updated weights for policy 0, policy_version 50229 (0.0016) [2023-03-09 08:35:26,052][23090] Updated weights for policy 0, policy_version 50239 (0.0015) [2023-03-09 08:35:26,948][23090] Updated weights for policy 0, policy_version 50249 (0.0013) [2023-03-09 08:35:27,772][23090] Updated weights for policy 0, policy_version 50259 (0.0017) [2023-03-09 08:35:28,516][23090] Updated weights for policy 0, policy_version 50269 (0.0018) [2023-03-09 08:35:29,059][22664] Fps is (10 sec: 198247.9, 60 sec: 198792.9, 300 sec: 198385.4). Total num frames: 823705600. Throughput: 0: 49642.1. Samples: 205890832. Policy #0 lag: (min: 1.0, avg: 17.5, max: 33.0) [2023-03-09 08:35:29,061][22664] Avg episode reward: [(0, '53.761')] [2023-03-09 08:35:29,357][23090] Updated weights for policy 0, policy_version 50279 (0.0016) [2023-03-09 08:35:30,276][23090] Updated weights for policy 0, policy_version 50290 (0.0019) [2023-03-09 08:35:31,123][23090] Updated weights for policy 0, policy_version 50300 (0.0017) [2023-03-09 08:35:31,891][23090] Updated weights for policy 0, policy_version 50310 (0.0016) [2023-03-09 08:35:32,666][22940] Signal inference workers to stop experience collection... (16150 times) [2023-03-09 08:35:32,678][22940] Signal inference workers to resume experience collection... (16150 times) [2023-03-09 08:35:32,738][23090] InferenceWorker_p0-w0: stopping experience collection (16150 times) [2023-03-09 08:35:32,738][23090] InferenceWorker_p0-w0: resuming experience collection (16150 times) [2023-03-09 08:35:32,741][23090] Updated weights for policy 0, policy_version 50320 (0.0018) [2023-03-09 08:35:33,662][23090] Updated weights for policy 0, policy_version 50330 (0.0018) [2023-03-09 08:35:34,059][22664] Fps is (10 sec: 198241.6, 60 sec: 198519.2, 300 sec: 198385.3). Total num frames: 824688640. Throughput: 0: 49687.1. Samples: 206189776. Policy #0 lag: (min: 1.0, avg: 17.5, max: 33.0) [2023-03-09 08:35:34,061][22664] Avg episode reward: [(0, '51.582')] [2023-03-09 08:35:34,420][23090] Updated weights for policy 0, policy_version 50340 (0.0021) [2023-03-09 08:35:35,371][23090] Updated weights for policy 0, policy_version 50351 (0.0017) [2023-03-09 08:35:36,170][23090] Updated weights for policy 0, policy_version 50361 (0.0019) [2023-03-09 08:35:36,978][23090] Updated weights for policy 0, policy_version 50371 (0.0013) [2023-03-09 08:35:37,881][23090] Updated weights for policy 0, policy_version 50381 (0.0018) [2023-03-09 08:35:38,600][23090] Updated weights for policy 0, policy_version 50391 (0.0020) [2023-03-09 08:35:39,059][22664] Fps is (10 sec: 198246.1, 60 sec: 198247.0, 300 sec: 198385.3). Total num frames: 825688064. Throughput: 0: 49687.9. Samples: 206486688. Policy #0 lag: (min: 1.0, avg: 17.5, max: 33.0) [2023-03-09 08:35:39,060][22664] Avg episode reward: [(0, '53.351')] [2023-03-09 08:35:39,471][23090] Updated weights for policy 0, policy_version 50401 (0.0013) [2023-03-09 08:35:40,360][23090] Updated weights for policy 0, policy_version 50411 (0.0022) [2023-03-09 08:35:41,191][23090] Updated weights for policy 0, policy_version 50422 (0.0018) [2023-03-09 08:35:42,062][23090] Updated weights for policy 0, policy_version 50432 (0.0013) [2023-03-09 08:35:42,846][23090] Updated weights for policy 0, policy_version 50442 (0.0025) [2023-03-09 08:35:43,716][23090] Updated weights for policy 0, policy_version 50452 (0.0015) [2023-03-09 08:35:44,059][22664] Fps is (10 sec: 198251.2, 60 sec: 198247.1, 300 sec: 198329.7). Total num frames: 826671104. Throughput: 0: 49688.2. Samples: 206634128. Policy #0 lag: (min: 1.0, avg: 16.8, max: 33.0) [2023-03-09 08:35:44,060][22664] Avg episode reward: [(0, '53.858')] [2023-03-09 08:35:44,365][22940] Signal inference workers to stop experience collection... (16200 times) [2023-03-09 08:35:44,365][22940] Signal inference workers to resume experience collection... (16200 times) [2023-03-09 08:35:44,446][23090] InferenceWorker_p0-w0: stopping experience collection (16200 times) [2023-03-09 08:35:44,446][23090] InferenceWorker_p0-w0: resuming experience collection (16200 times) [2023-03-09 08:35:44,494][23090] Updated weights for policy 0, policy_version 50462 (0.0013) [2023-03-09 08:35:45,345][23090] Updated weights for policy 0, policy_version 50472 (0.0016) [2023-03-09 08:35:46,152][23090] Updated weights for policy 0, policy_version 50482 (0.0017) [2023-03-09 08:35:47,046][23090] Updated weights for policy 0, policy_version 50493 (0.0016) [2023-03-09 08:35:47,866][23090] Updated weights for policy 0, policy_version 50503 (0.0017) [2023-03-09 08:35:48,702][23090] Updated weights for policy 0, policy_version 50513 (0.0019) [2023-03-09 08:35:49,059][22664] Fps is (10 sec: 196600.5, 60 sec: 198244.6, 300 sec: 198274.0). Total num frames: 827654144. Throughput: 0: 49689.3. Samples: 206931040. Policy #0 lag: (min: 1.0, avg: 16.8, max: 33.0) [2023-03-09 08:35:49,061][22664] Avg episode reward: [(0, '52.639')] [2023-03-09 08:35:49,592][23090] Updated weights for policy 0, policy_version 50523 (0.0013) [2023-03-09 08:35:50,371][23090] Updated weights for policy 0, policy_version 50533 (0.0019) [2023-03-09 08:35:51,254][23090] Updated weights for policy 0, policy_version 50543 (0.0027) [2023-03-09 08:35:52,059][23090] Updated weights for policy 0, policy_version 50553 (0.0013) [2023-03-09 08:35:52,865][23090] Updated weights for policy 0, policy_version 50563 (0.0013) [2023-03-09 08:35:53,767][23090] Updated weights for policy 0, policy_version 50573 (0.0019) [2023-03-09 08:35:54,059][22664] Fps is (10 sec: 198242.6, 60 sec: 198520.6, 300 sec: 198329.7). Total num frames: 828653568. Throughput: 0: 49645.2. Samples: 207227984. Policy #0 lag: (min: 1.0, avg: 16.8, max: 33.0) [2023-03-09 08:35:54,105][22664] Avg episode reward: [(0, '54.765')] [2023-03-09 08:35:54,494][23090] Updated weights for policy 0, policy_version 50583 (0.0013) [2023-03-09 08:35:55,306][23090] Updated weights for policy 0, policy_version 50593 (0.0016) [2023-03-09 08:35:55,993][22940] Signal inference workers to stop experience collection... (16250 times) [2023-03-09 08:35:55,995][22940] Signal inference workers to resume experience collection... (16250 times) [2023-03-09 08:35:56,060][23090] InferenceWorker_p0-w0: stopping experience collection (16250 times) [2023-03-09 08:35:56,061][23090] InferenceWorker_p0-w0: resuming experience collection (16250 times) [2023-03-09 08:35:56,216][23090] Updated weights for policy 0, policy_version 50603 (0.0015) [2023-03-09 08:35:56,972][23090] Updated weights for policy 0, policy_version 50613 (0.0018) [2023-03-09 08:35:57,806][23090] Updated weights for policy 0, policy_version 50623 (0.0013) [2023-03-09 08:35:58,638][23090] Updated weights for policy 0, policy_version 50633 (0.0013) [2023-03-09 08:35:59,059][22664] Fps is (10 sec: 198255.2, 60 sec: 198246.2, 300 sec: 198329.9). Total num frames: 829636608. Throughput: 0: 49645.0. Samples: 207377456. Policy #0 lag: (min: 1.0, avg: 16.8, max: 33.0) [2023-03-09 08:35:59,060][22664] Avg episode reward: [(0, '53.437')] [2023-03-09 08:35:59,518][23090] Updated weights for policy 0, policy_version 50643 (0.0019) [2023-03-09 08:36:00,356][23090] Updated weights for policy 0, policy_version 50654 (0.0015) [2023-03-09 08:36:01,198][23090] Updated weights for policy 0, policy_version 50664 (0.0013) [2023-03-09 08:36:02,070][23090] Updated weights for policy 0, policy_version 50674 (0.0013) [2023-03-09 08:36:02,848][23090] Updated weights for policy 0, policy_version 50684 (0.0017) [2023-03-09 08:36:03,660][23090] Updated weights for policy 0, policy_version 50694 (0.0013) [2023-03-09 08:36:04,058][22664] Fps is (10 sec: 198250.8, 60 sec: 198520.3, 300 sec: 198329.7). Total num frames: 830636032. Throughput: 0: 49600.2. Samples: 207674384. Policy #0 lag: (min: 1.0, avg: 16.8, max: 33.0) [2023-03-09 08:36:04,060][22664] Avg episode reward: [(0, '55.692')] [2023-03-09 08:36:04,608][23090] Updated weights for policy 0, policy_version 50705 (0.0015) [2023-03-09 08:36:05,505][23090] Updated weights for policy 0, policy_version 50715 (0.0013) [2023-03-09 08:36:06,242][23090] Updated weights for policy 0, policy_version 50725 (0.0022) [2023-03-09 08:36:07,153][23090] Updated weights for policy 0, policy_version 50735 (0.0013) [2023-03-09 08:36:07,164][22940] Signal inference workers to stop experience collection... (16300 times) [2023-03-09 08:36:07,195][22940] Signal inference workers to resume experience collection... (16300 times) [2023-03-09 08:36:07,243][23090] InferenceWorker_p0-w0: stopping experience collection (16300 times) [2023-03-09 08:36:07,244][23090] InferenceWorker_p0-w0: resuming experience collection (16300 times) [2023-03-09 08:36:07,996][23090] Updated weights for policy 0, policy_version 50745 (0.0024) [2023-03-09 08:36:08,775][23090] Updated weights for policy 0, policy_version 50755 (0.0013) [2023-03-09 08:36:09,059][22664] Fps is (10 sec: 199879.3, 60 sec: 198519.3, 300 sec: 198385.2). Total num frames: 831635456. Throughput: 0: 49552.7. Samples: 207971280. Policy #0 lag: (min: 1.0, avg: 16.8, max: 33.0) [2023-03-09 08:36:09,061][22664] Avg episode reward: [(0, '54.779')] [2023-03-09 08:36:09,610][23090] Updated weights for policy 0, policy_version 50765 (0.0018) [2023-03-09 08:36:10,377][23090] Updated weights for policy 0, policy_version 50775 (0.0013) [2023-03-09 08:36:11,231][23090] Updated weights for policy 0, policy_version 50785 (0.0016) [2023-03-09 08:36:12,078][23090] Updated weights for policy 0, policy_version 50795 (0.0022) [2023-03-09 08:36:12,944][23090] Updated weights for policy 0, policy_version 50805 (0.0018) [2023-03-09 08:36:13,626][23090] Updated weights for policy 0, policy_version 50815 (0.0016) [2023-03-09 08:36:14,059][22664] Fps is (10 sec: 199884.3, 60 sec: 199065.4, 300 sec: 198441.0). Total num frames: 832634880. Throughput: 0: 49553.5. Samples: 208120736. Policy #0 lag: (min: 1.0, avg: 17.6, max: 33.0) [2023-03-09 08:36:14,060][22664] Avg episode reward: [(0, '51.347')] [2023-03-09 08:36:14,544][23090] Updated weights for policy 0, policy_version 50825 (0.0014) [2023-03-09 08:36:15,359][23090] Updated weights for policy 0, policy_version 50835 (0.0016) [2023-03-09 08:36:16,192][23090] Updated weights for policy 0, policy_version 50846 (0.0013) [2023-03-09 08:36:17,040][23090] Updated weights for policy 0, policy_version 50856 (0.0013) [2023-03-09 08:36:17,581][22940] Signal inference workers to stop experience collection... (16350 times) [2023-03-09 08:36:17,605][22940] Signal inference workers to resume experience collection... (16350 times) [2023-03-09 08:36:17,640][23090] InferenceWorker_p0-w0: stopping experience collection (16350 times) [2023-03-09 08:36:17,684][23090] InferenceWorker_p0-w0: resuming experience collection (16350 times) [2023-03-09 08:36:17,894][23090] Updated weights for policy 0, policy_version 50866 (0.0016) [2023-03-09 08:36:18,791][23090] Updated weights for policy 0, policy_version 50877 (0.0016) [2023-03-09 08:36:19,059][22664] Fps is (10 sec: 198249.2, 60 sec: 198246.4, 300 sec: 198496.3). Total num frames: 833617920. Throughput: 0: 49553.5. Samples: 208419680. Policy #0 lag: (min: 1.0, avg: 17.6, max: 33.0) [2023-03-09 08:36:19,060][22664] Avg episode reward: [(0, '55.476')] [2023-03-09 08:36:19,568][23090] Updated weights for policy 0, policy_version 50887 (0.0020) [2023-03-09 08:36:20,444][23090] Updated weights for policy 0, policy_version 50897 (0.0020) [2023-03-09 08:36:21,300][23090] Updated weights for policy 0, policy_version 50907 (0.0019) [2023-03-09 08:36:22,069][23090] Updated weights for policy 0, policy_version 50917 (0.0016) [2023-03-09 08:36:22,984][23090] Updated weights for policy 0, policy_version 50927 (0.0019) [2023-03-09 08:36:23,788][23090] Updated weights for policy 0, policy_version 50937 (0.0013) [2023-03-09 08:36:24,059][22664] Fps is (10 sec: 198243.9, 60 sec: 198519.1, 300 sec: 198552.0). Total num frames: 834617344. Throughput: 0: 49553.4. Samples: 208716592. Policy #0 lag: (min: 1.0, avg: 17.6, max: 33.0) [2023-03-09 08:36:24,060][22664] Avg episode reward: [(0, '52.270')] [2023-03-09 08:36:24,581][23090] Updated weights for policy 0, policy_version 50947 (0.0013) [2023-03-09 08:36:25,452][23090] Updated weights for policy 0, policy_version 50957 (0.0017) [2023-03-09 08:36:26,257][23090] Updated weights for policy 0, policy_version 50968 (0.0013) [2023-03-09 08:36:27,142][23090] Updated weights for policy 0, policy_version 50978 (0.0016) [2023-03-09 08:36:27,983][23090] Updated weights for policy 0, policy_version 50988 (0.0013) [2023-03-09 08:36:28,192][22940] Signal inference workers to stop experience collection... (16400 times) [2023-03-09 08:36:28,214][22940] Signal inference workers to resume experience collection... (16400 times) [2023-03-09 08:36:28,225][23090] InferenceWorker_p0-w0: stopping experience collection (16400 times) [2023-03-09 08:36:28,225][23090] InferenceWorker_p0-w0: resuming experience collection (16400 times) [2023-03-09 08:36:28,758][23090] Updated weights for policy 0, policy_version 50998 (0.0024) [2023-03-09 08:36:29,059][22664] Fps is (10 sec: 198248.9, 60 sec: 198246.5, 300 sec: 198496.3). Total num frames: 835600384. Throughput: 0: 49597.8. Samples: 208866032. Policy #0 lag: (min: 1.0, avg: 17.6, max: 33.0) [2023-03-09 08:36:29,060][22664] Avg episode reward: [(0, '54.828')] [2023-03-09 08:36:29,556][23090] Updated weights for policy 0, policy_version 51008 (0.0013) [2023-03-09 08:36:30,366][23090] Updated weights for policy 0, policy_version 51018 (0.0013) [2023-03-09 08:36:31,227][23090] Updated weights for policy 0, policy_version 51028 (0.0019) [2023-03-09 08:36:31,968][23090] Updated weights for policy 0, policy_version 51038 (0.0020) [2023-03-09 08:36:32,831][23090] Updated weights for policy 0, policy_version 51048 (0.0024) [2023-03-09 08:36:33,681][23090] Updated weights for policy 0, policy_version 51058 (0.0013) [2023-03-09 08:36:34,059][22664] Fps is (10 sec: 199872.3, 60 sec: 198790.9, 300 sec: 198607.0). Total num frames: 836616192. Throughput: 0: 49687.5. Samples: 209166992. Policy #0 lag: (min: 1.0, avg: 17.6, max: 33.0) [2023-03-09 08:36:34,062][22664] Avg episode reward: [(0, '51.098')] [2023-03-09 08:36:34,531][23090] Updated weights for policy 0, policy_version 51068 (0.0013) [2023-03-09 08:36:35,262][23090] Updated weights for policy 0, policy_version 51078 (0.0016) [2023-03-09 08:36:36,179][23090] Updated weights for policy 0, policy_version 51088 (0.0016) [2023-03-09 08:36:37,037][23090] Updated weights for policy 0, policy_version 51098 (0.0020) [2023-03-09 08:36:37,800][23090] Updated weights for policy 0, policy_version 51108 (0.0016) [2023-03-09 08:36:38,226][22940] Signal inference workers to stop experience collection... (16450 times) [2023-03-09 08:36:38,227][22940] Signal inference workers to resume experience collection... (16450 times) [2023-03-09 08:36:38,286][23090] InferenceWorker_p0-w0: stopping experience collection (16450 times) [2023-03-09 08:36:38,289][23090] InferenceWorker_p0-w0: resuming experience collection (16450 times) [2023-03-09 08:36:38,768][23090] Updated weights for policy 0, policy_version 51119 (0.0016) [2023-03-09 08:36:39,059][22664] Fps is (10 sec: 198241.6, 60 sec: 198245.8, 300 sec: 198551.6). Total num frames: 837582848. Throughput: 0: 49641.1. Samples: 209461840. Policy #0 lag: (min: 1.0, avg: 17.6, max: 33.0) [2023-03-09 08:36:39,061][22664] Avg episode reward: [(0, '52.158')] [2023-03-09 08:36:39,624][23090] Updated weights for policy 0, policy_version 51129 (0.0016) [2023-03-09 08:36:40,431][23090] Updated weights for policy 0, policy_version 51139 (0.0015) [2023-03-09 08:36:41,282][23090] Updated weights for policy 0, policy_version 51149 (0.0013) [2023-03-09 08:36:42,022][23090] Updated weights for policy 0, policy_version 51159 (0.0016) [2023-03-09 08:36:42,954][23090] Updated weights for policy 0, policy_version 51170 (0.0013) [2023-03-09 08:36:43,840][23090] Updated weights for policy 0, policy_version 51180 (0.0014) [2023-03-09 08:36:44,059][22664] Fps is (10 sec: 194973.6, 60 sec: 198244.6, 300 sec: 198496.1). Total num frames: 838565888. Throughput: 0: 49640.7. Samples: 209611312. Policy #0 lag: (min: 1.0, avg: 17.6, max: 33.0) [2023-03-09 08:36:44,061][22664] Avg episode reward: [(0, '49.863')] [2023-03-09 08:36:44,640][23090] Updated weights for policy 0, policy_version 51190 (0.0019) [2023-03-09 08:36:45,400][23090] Updated weights for policy 0, policy_version 51200 (0.0013) [2023-03-09 08:36:46,203][23090] Updated weights for policy 0, policy_version 51210 (0.0027) [2023-03-09 08:36:47,110][23090] Updated weights for policy 0, policy_version 51220 (0.0018) [2023-03-09 08:36:47,858][23090] Updated weights for policy 0, policy_version 51230 (0.0013) [2023-03-09 08:36:48,445][22940] Signal inference workers to stop experience collection... (16500 times) [2023-03-09 08:36:48,446][22940] Signal inference workers to resume experience collection... (16500 times) [2023-03-09 08:36:48,507][23090] InferenceWorker_p0-w0: stopping experience collection (16500 times) [2023-03-09 08:36:48,507][23090] InferenceWorker_p0-w0: resuming experience collection (16500 times) [2023-03-09 08:36:48,709][23090] Updated weights for policy 0, policy_version 51240 (0.0013) [2023-03-09 08:36:49,059][22664] Fps is (10 sec: 198252.0, 60 sec: 198521.0, 300 sec: 198496.4). Total num frames: 839565312. Throughput: 0: 49639.8. Samples: 209908176. Policy #0 lag: (min: 0.0, avg: 17.6, max: 33.0) [2023-03-09 08:36:49,060][22664] Avg episode reward: [(0, '53.595')] [2023-03-09 08:36:49,563][23090] Updated weights for policy 0, policy_version 51250 (0.0013) [2023-03-09 08:36:50,406][23090] Updated weights for policy 0, policy_version 51260 (0.0018) [2023-03-09 08:36:51,142][23090] Updated weights for policy 0, policy_version 51270 (0.0016) [2023-03-09 08:36:52,101][23090] Updated weights for policy 0, policy_version 51281 (0.0019) [2023-03-09 08:36:52,939][23090] Updated weights for policy 0, policy_version 51291 (0.0013) [2023-03-09 08:36:53,730][23090] Updated weights for policy 0, policy_version 51301 (0.0021) [2023-03-09 08:36:54,059][22664] Fps is (10 sec: 199889.9, 60 sec: 198519.2, 300 sec: 198551.9). Total num frames: 840564736. Throughput: 0: 49639.2. Samples: 210205040. Policy #0 lag: (min: 0.0, avg: 17.6, max: 33.0) [2023-03-09 08:36:54,061][22664] Avg episode reward: [(0, '53.597')] [2023-03-09 08:36:54,658][23090] Updated weights for policy 0, policy_version 51311 (0.0013) [2023-03-09 08:36:55,546][23090] Updated weights for policy 0, policy_version 51321 (0.0014) [2023-03-09 08:36:56,240][23090] Updated weights for policy 0, policy_version 51331 (0.0016) [2023-03-09 08:36:57,158][23090] Updated weights for policy 0, policy_version 51341 (0.0013) [2023-03-09 08:36:57,890][23090] Updated weights for policy 0, policy_version 51351 (0.0022) [2023-03-09 08:36:58,805][23090] Updated weights for policy 0, policy_version 51362 (0.0018) [2023-03-09 08:36:59,059][22664] Fps is (10 sec: 199880.4, 60 sec: 198791.9, 300 sec: 198607.6). Total num frames: 841564160. Throughput: 0: 49593.7. Samples: 210352464. Policy #0 lag: (min: 0.0, avg: 17.6, max: 33.0) [2023-03-09 08:36:59,061][22664] Avg episode reward: [(0, '50.649')] [2023-03-09 08:36:59,691][23090] Updated weights for policy 0, policy_version 51372 (0.0018) [2023-03-09 08:37:00,546][23090] Updated weights for policy 0, policy_version 51383 (0.0020) [2023-03-09 08:37:00,552][22940] Signal inference workers to stop experience collection... (16550 times) [2023-03-09 08:37:00,553][22940] Signal inference workers to resume experience collection... (16550 times) [2023-03-09 08:37:00,618][23090] InferenceWorker_p0-w0: stopping experience collection (16550 times) [2023-03-09 08:37:00,618][23090] InferenceWorker_p0-w0: resuming experience collection (16550 times) [2023-03-09 08:37:01,335][23090] Updated weights for policy 0, policy_version 51393 (0.0013) [2023-03-09 08:37:02,243][23090] Updated weights for policy 0, policy_version 51403 (0.0013) [2023-03-09 08:37:03,054][23090] Updated weights for policy 0, policy_version 51413 (0.0023) [2023-03-09 08:37:03,764][23090] Updated weights for policy 0, policy_version 51423 (0.0013) [2023-03-09 08:37:04,059][22664] Fps is (10 sec: 199884.1, 60 sec: 198791.4, 300 sec: 198551.8). Total num frames: 842563584. Throughput: 0: 49639.7. Samples: 210653472. Policy #0 lag: (min: 0.0, avg: 17.6, max: 33.0) [2023-03-09 08:37:04,060][22664] Avg episode reward: [(0, '52.209')] [2023-03-09 08:37:04,666][23090] Updated weights for policy 0, policy_version 51433 (0.0020) [2023-03-09 08:37:05,497][23090] Updated weights for policy 0, policy_version 51443 (0.0020) [2023-03-09 08:37:06,304][23090] Updated weights for policy 0, policy_version 51453 (0.0025) [2023-03-09 08:37:07,210][23090] Updated weights for policy 0, policy_version 51464 (0.0016) [2023-03-09 08:37:08,026][23090] Updated weights for policy 0, policy_version 51474 (0.0019) [2023-03-09 08:37:08,834][23090] Updated weights for policy 0, policy_version 51484 (0.0018) [2023-03-09 08:37:09,059][22664] Fps is (10 sec: 199886.8, 60 sec: 198793.2, 300 sec: 198607.7). Total num frames: 843563008. Throughput: 0: 49685.3. Samples: 210952432. Policy #0 lag: (min: 0.0, avg: 17.6, max: 33.0) [2023-03-09 08:37:09,060][22664] Avg episode reward: [(0, '54.000')] [2023-03-09 08:37:09,677][23090] Updated weights for policy 0, policy_version 51495 (0.0025) [2023-03-09 08:37:10,575][23090] Updated weights for policy 0, policy_version 51505 (0.0013) [2023-03-09 08:37:11,444][23090] Updated weights for policy 0, policy_version 51515 (0.0013) [2023-03-09 08:37:12,149][23090] Updated weights for policy 0, policy_version 51525 (0.0020) [2023-03-09 08:37:12,983][22940] Signal inference workers to stop experience collection... (16600 times) [2023-03-09 08:37:12,985][22940] Signal inference workers to resume experience collection... (16600 times) [2023-03-09 08:37:13,056][23090] InferenceWorker_p0-w0: stopping experience collection (16600 times) [2023-03-09 08:37:13,056][23090] InferenceWorker_p0-w0: resuming experience collection (16600 times) [2023-03-09 08:37:13,139][23090] Updated weights for policy 0, policy_version 51535 (0.0013) [2023-03-09 08:37:13,944][23090] Updated weights for policy 0, policy_version 51545 (0.0018) [2023-03-09 08:37:14,058][22664] Fps is (10 sec: 198254.1, 60 sec: 198519.7, 300 sec: 198552.0). Total num frames: 844546048. Throughput: 0: 49685.8. Samples: 211101888. Policy #0 lag: (min: 0.0, avg: 17.6, max: 33.0) [2023-03-09 08:37:14,059][22664] Avg episode reward: [(0, '54.573')] [2023-03-09 08:37:14,747][23090] Updated weights for policy 0, policy_version 51556 (0.0013) [2023-03-09 08:37:15,693][23090] Updated weights for policy 0, policy_version 51566 (0.0013) [2023-03-09 08:37:16,394][23090] Updated weights for policy 0, policy_version 51576 (0.0016) [2023-03-09 08:37:17,263][23090] Updated weights for policy 0, policy_version 51586 (0.0016) [2023-03-09 08:37:18,135][23090] Updated weights for policy 0, policy_version 51596 (0.0013) [2023-03-09 08:37:18,904][23090] Updated weights for policy 0, policy_version 51606 (0.0024) [2023-03-09 08:37:19,059][22664] Fps is (10 sec: 198248.4, 60 sec: 198793.0, 300 sec: 198552.0). Total num frames: 845545472. Throughput: 0: 49642.4. Samples: 211400864. Policy #0 lag: (min: 2.0, avg: 17.3, max: 33.0) [2023-03-09 08:37:19,060][22664] Avg episode reward: [(0, '54.745')] [2023-03-09 08:37:19,112][22940] Saving /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000051608_845545472.pth... [2023-03-09 08:37:19,173][22940] Removing /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000048698_797868032.pth [2023-03-09 08:37:19,678][23090] Updated weights for policy 0, policy_version 51616 (0.0018) [2023-03-09 08:37:20,528][23090] Updated weights for policy 0, policy_version 51626 (0.0024) [2023-03-09 08:37:21,405][23090] Updated weights for policy 0, policy_version 51636 (0.0018) [2023-03-09 08:37:22,162][23090] Updated weights for policy 0, policy_version 51646 (0.0016) [2023-03-09 08:37:22,973][23090] Updated weights for policy 0, policy_version 51656 (0.0014) [2023-03-09 08:37:23,834][23090] Updated weights for policy 0, policy_version 51666 (0.0016) [2023-03-09 08:37:24,059][22664] Fps is (10 sec: 198245.0, 60 sec: 198519.9, 300 sec: 198552.1). Total num frames: 846528512. Throughput: 0: 49733.7. Samples: 211699840. Policy #0 lag: (min: 2.0, avg: 17.3, max: 33.0) [2023-03-09 08:37:24,060][22664] Avg episode reward: [(0, '52.546')] [2023-03-09 08:37:24,449][22940] Signal inference workers to stop experience collection... (16650 times) [2023-03-09 08:37:24,450][22940] Signal inference workers to resume experience collection... (16650 times) [2023-03-09 08:37:24,517][23090] InferenceWorker_p0-w0: stopping experience collection (16650 times) [2023-03-09 08:37:24,565][23090] InferenceWorker_p0-w0: resuming experience collection (16650 times) [2023-03-09 08:37:24,650][23090] Updated weights for policy 0, policy_version 51676 (0.0014) [2023-03-09 08:37:25,401][23090] Updated weights for policy 0, policy_version 51686 (0.0013) [2023-03-09 08:37:26,358][23090] Updated weights for policy 0, policy_version 51696 (0.0016) [2023-03-09 08:37:27,160][23090] Updated weights for policy 0, policy_version 51706 (0.0017) [2023-03-09 08:37:27,925][23090] Updated weights for policy 0, policy_version 51716 (0.0013) [2023-03-09 08:37:28,887][23090] Updated weights for policy 0, policy_version 51726 (0.0015) [2023-03-09 08:37:29,059][22664] Fps is (10 sec: 198242.9, 60 sec: 198792.0, 300 sec: 198607.2). Total num frames: 847527936. Throughput: 0: 49687.8. Samples: 211847248. Policy #0 lag: (min: 2.0, avg: 17.3, max: 33.0) [2023-03-09 08:37:29,061][22664] Avg episode reward: [(0, '53.919')] [2023-03-09 08:37:29,585][23090] Updated weights for policy 0, policy_version 51736 (0.0016) [2023-03-09 08:37:30,404][23090] Updated weights for policy 0, policy_version 51746 (0.0019) [2023-03-09 08:37:31,468][23090] Updated weights for policy 0, policy_version 51757 (0.0016) [2023-03-09 08:37:32,159][23090] Updated weights for policy 0, policy_version 51767 (0.0017) [2023-03-09 08:37:32,963][23090] Updated weights for policy 0, policy_version 51777 (0.0013) [2023-03-09 08:37:33,946][23090] Updated weights for policy 0, policy_version 51788 (0.0013) [2023-03-09 08:37:34,059][22664] Fps is (10 sec: 196608.4, 60 sec: 197975.9, 300 sec: 198440.8). Total num frames: 848494592. Throughput: 0: 49688.2. Samples: 212144144. Policy #0 lag: (min: 2.0, avg: 17.3, max: 33.0) [2023-03-09 08:37:34,061][22664] Avg episode reward: [(0, '54.111')] [2023-03-09 08:37:34,720][23090] Updated weights for policy 0, policy_version 51798 (0.0017) [2023-03-09 08:37:35,505][23090] Updated weights for policy 0, policy_version 51808 (0.0022) [2023-03-09 08:37:36,340][23090] Updated weights for policy 0, policy_version 51818 (0.0019) [2023-03-09 08:37:36,862][22940] Signal inference workers to stop experience collection... (16700 times) [2023-03-09 08:37:36,878][22940] Signal inference workers to resume experience collection... (16700 times) [2023-03-09 08:37:36,906][23090] InferenceWorker_p0-w0: stopping experience collection (16700 times) [2023-03-09 08:37:36,906][23090] InferenceWorker_p0-w0: resuming experience collection (16700 times) [2023-03-09 08:37:37,189][23090] Updated weights for policy 0, policy_version 51828 (0.0013) [2023-03-09 08:37:37,997][23090] Updated weights for policy 0, policy_version 51838 (0.0015) [2023-03-09 08:37:38,823][23090] Updated weights for policy 0, policy_version 51848 (0.0013) [2023-03-09 08:37:39,059][22664] Fps is (10 sec: 198246.4, 60 sec: 198792.8, 300 sec: 198551.7). Total num frames: 849510400. Throughput: 0: 49734.8. Samples: 212443104. Policy #0 lag: (min: 2.0, avg: 17.3, max: 33.0) [2023-03-09 08:37:39,061][22664] Avg episode reward: [(0, '55.154')] [2023-03-09 08:37:39,786][23090] Updated weights for policy 0, policy_version 51859 (0.0019) [2023-03-09 08:37:40,595][23090] Updated weights for policy 0, policy_version 51869 (0.0017) [2023-03-09 08:37:41,347][23090] Updated weights for policy 0, policy_version 51879 (0.0017) [2023-03-09 08:37:42,239][23090] Updated weights for policy 0, policy_version 51889 (0.0013) [2023-03-09 08:37:43,107][23090] Updated weights for policy 0, policy_version 51899 (0.0013) [2023-03-09 08:37:43,811][23090] Updated weights for policy 0, policy_version 51909 (0.0015) [2023-03-09 08:37:44,059][22664] Fps is (10 sec: 201515.2, 60 sec: 199066.2, 300 sec: 198607.3). Total num frames: 850509824. Throughput: 0: 49779.4. Samples: 212592544. Policy #0 lag: (min: 2.0, avg: 17.3, max: 33.0) [2023-03-09 08:37:44,061][22664] Avg episode reward: [(0, '53.232')] [2023-03-09 08:37:44,798][23090] Updated weights for policy 0, policy_version 51919 (0.0022) [2023-03-09 08:37:45,579][23090] Updated weights for policy 0, policy_version 51929 (0.0021) [2023-03-09 08:37:46,366][23090] Updated weights for policy 0, policy_version 51939 (0.0018) [2023-03-09 08:37:47,242][23090] Updated weights for policy 0, policy_version 51949 (0.0022) [2023-03-09 08:37:48,010][23090] Updated weights for policy 0, policy_version 51959 (0.0016) [2023-03-09 08:37:48,785][23090] Updated weights for policy 0, policy_version 51969 (0.0018) [2023-03-09 08:37:49,059][22664] Fps is (10 sec: 199883.4, 60 sec: 199064.7, 300 sec: 198662.7). Total num frames: 851509248. Throughput: 0: 49687.9. Samples: 212889424. Policy #0 lag: (min: 2.0, avg: 17.3, max: 33.0) [2023-03-09 08:37:49,061][22664] Avg episode reward: [(0, '52.795')] [2023-03-09 08:37:49,511][22940] Signal inference workers to stop experience collection... (16750 times) [2023-03-09 08:37:49,513][22940] Signal inference workers to resume experience collection... (16750 times) [2023-03-09 08:37:49,579][23090] InferenceWorker_p0-w0: stopping experience collection (16750 times) [2023-03-09 08:37:49,579][23090] InferenceWorker_p0-w0: resuming experience collection (16750 times) [2023-03-09 08:37:49,698][23090] Updated weights for policy 0, policy_version 51979 (0.0013) [2023-03-09 08:37:50,481][23090] Updated weights for policy 0, policy_version 51989 (0.0013) [2023-03-09 08:37:51,363][23090] Updated weights for policy 0, policy_version 52000 (0.0014) [2023-03-09 08:37:52,210][23090] Updated weights for policy 0, policy_version 52010 (0.0016) [2023-03-09 08:37:53,042][23090] Updated weights for policy 0, policy_version 52020 (0.0013) [2023-03-09 08:37:53,813][23090] Updated weights for policy 0, policy_version 52030 (0.0030) [2023-03-09 08:37:54,058][22664] Fps is (10 sec: 199893.7, 60 sec: 199066.8, 300 sec: 198663.2). Total num frames: 852508672. Throughput: 0: 49688.1. Samples: 213188384. Policy #0 lag: (min: 1.0, avg: 17.0, max: 33.0) [2023-03-09 08:37:54,060][22664] Avg episode reward: [(0, '53.247')] [2023-03-09 08:37:54,809][23090] Updated weights for policy 0, policy_version 52041 (0.0013) [2023-03-09 08:37:55,613][23090] Updated weights for policy 0, policy_version 52051 (0.0014) [2023-03-09 08:37:56,416][23090] Updated weights for policy 0, policy_version 52061 (0.0016) [2023-03-09 08:37:57,147][23090] Updated weights for policy 0, policy_version 52071 (0.0013) [2023-03-09 08:37:58,018][23090] Updated weights for policy 0, policy_version 52081 (0.0013) [2023-03-09 08:37:58,845][23090] Updated weights for policy 0, policy_version 52091 (0.0013) [2023-03-09 08:37:59,059][22664] Fps is (10 sec: 199881.7, 60 sec: 199064.9, 300 sec: 198662.6). Total num frames: 853508096. Throughput: 0: 49687.3. Samples: 213337840. Policy #0 lag: (min: 1.0, avg: 17.0, max: 33.0) [2023-03-09 08:37:59,061][22664] Avg episode reward: [(0, '53.615')] [2023-03-09 08:37:59,642][23090] Updated weights for policy 0, policy_version 52102 (0.0017) [2023-03-09 08:38:00,552][23090] Updated weights for policy 0, policy_version 52112 (0.0016) [2023-03-09 08:38:01,371][22940] Signal inference workers to stop experience collection... (16800 times) [2023-03-09 08:38:01,372][22940] Signal inference workers to resume experience collection... (16800 times) [2023-03-09 08:38:01,434][23090] InferenceWorker_p0-w0: stopping experience collection (16800 times) [2023-03-09 08:38:01,434][23090] InferenceWorker_p0-w0: resuming experience collection (16800 times) [2023-03-09 08:38:01,481][23090] Updated weights for policy 0, policy_version 52123 (0.0024) [2023-03-09 08:38:02,255][23090] Updated weights for policy 0, policy_version 52133 (0.0013) [2023-03-09 08:38:03,189][23090] Updated weights for policy 0, policy_version 52143 (0.0020) [2023-03-09 08:38:04,059][22664] Fps is (10 sec: 198245.0, 60 sec: 198793.6, 300 sec: 198663.2). Total num frames: 854491136. Throughput: 0: 49686.4. Samples: 213636752. Policy #0 lag: (min: 1.0, avg: 17.0, max: 33.0) [2023-03-09 08:38:04,060][22664] Avg episode reward: [(0, '53.833')] [2023-03-09 08:38:04,073][23090] Updated weights for policy 0, policy_version 52154 (0.0016) [2023-03-09 08:38:04,829][23090] Updated weights for policy 0, policy_version 52164 (0.0019) [2023-03-09 08:38:05,776][23090] Updated weights for policy 0, policy_version 52174 (0.0013) [2023-03-09 08:38:06,486][23090] Updated weights for policy 0, policy_version 52184 (0.0018) [2023-03-09 08:38:07,397][23090] Updated weights for policy 0, policy_version 52195 (0.0013) [2023-03-09 08:38:08,397][23090] Updated weights for policy 0, policy_version 52205 (0.0017) [2023-03-09 08:38:09,059][22664] Fps is (10 sec: 196610.5, 60 sec: 198518.9, 300 sec: 198662.7). Total num frames: 855474176. Throughput: 0: 49640.2. Samples: 213933664. Policy #0 lag: (min: 1.0, avg: 17.0, max: 33.0) [2023-03-09 08:38:09,061][22664] Avg episode reward: [(0, '51.187')] [2023-03-09 08:38:09,089][23090] Updated weights for policy 0, policy_version 52215 (0.0018) [2023-03-09 08:38:09,886][23090] Updated weights for policy 0, policy_version 52225 (0.0016) [2023-03-09 08:38:10,773][23090] Updated weights for policy 0, policy_version 52235 (0.0016) [2023-03-09 08:38:11,578][23090] Updated weights for policy 0, policy_version 52245 (0.0019) [2023-03-09 08:38:11,917][22940] Signal inference workers to stop experience collection... (16850 times) [2023-03-09 08:38:11,920][22940] Signal inference workers to resume experience collection... (16850 times) [2023-03-09 08:38:12,004][23090] InferenceWorker_p0-w0: stopping experience collection (16850 times) [2023-03-09 08:38:12,005][23090] InferenceWorker_p0-w0: resuming experience collection (16850 times) [2023-03-09 08:38:12,487][23090] Updated weights for policy 0, policy_version 52256 (0.0019) [2023-03-09 08:38:13,300][23090] Updated weights for policy 0, policy_version 52266 (0.0020) [2023-03-09 08:38:14,059][22664] Fps is (10 sec: 196602.2, 60 sec: 198518.3, 300 sec: 198607.2). Total num frames: 856457216. Throughput: 0: 49732.2. Samples: 214085200. Policy #0 lag: (min: 1.0, avg: 17.0, max: 33.0) [2023-03-09 08:38:14,061][22664] Avg episode reward: [(0, '52.979')] [2023-03-09 08:38:14,177][23090] Updated weights for policy 0, policy_version 52276 (0.0019) [2023-03-09 08:38:14,960][23090] Updated weights for policy 0, policy_version 52286 (0.0022) [2023-03-09 08:38:15,728][23090] Updated weights for policy 0, policy_version 52296 (0.0013) [2023-03-09 08:38:16,612][23090] Updated weights for policy 0, policy_version 52306 (0.0013) [2023-03-09 08:38:17,413][23090] Updated weights for policy 0, policy_version 52316 (0.0016) [2023-03-09 08:38:18,171][23090] Updated weights for policy 0, policy_version 52326 (0.0018) [2023-03-09 08:38:19,059][22664] Fps is (10 sec: 198251.9, 60 sec: 198519.5, 300 sec: 198662.9). Total num frames: 857456640. Throughput: 0: 49687.0. Samples: 214380064. Policy #0 lag: (min: 1.0, avg: 17.0, max: 33.0) [2023-03-09 08:38:19,060][22664] Avg episode reward: [(0, '51.784')] [2023-03-09 08:38:19,245][23090] Updated weights for policy 0, policy_version 52338 (0.0016) [2023-03-09 08:38:20,044][23090] Updated weights for policy 0, policy_version 52348 (0.0013) [2023-03-09 08:38:20,786][23090] Updated weights for policy 0, policy_version 52358 (0.0016) [2023-03-09 08:38:21,742][23090] Updated weights for policy 0, policy_version 52368 (0.0013) [2023-03-09 08:38:22,582][23090] Updated weights for policy 0, policy_version 52379 (0.0013) [2023-03-09 08:38:23,037][22940] Signal inference workers to stop experience collection... (16900 times) [2023-03-09 08:38:23,038][22940] Signal inference workers to resume experience collection... (16900 times) [2023-03-09 08:38:23,108][23090] InferenceWorker_p0-w0: stopping experience collection (16900 times) [2023-03-09 08:38:23,112][23090] InferenceWorker_p0-w0: resuming experience collection (16900 times) [2023-03-09 08:38:23,407][23090] Updated weights for policy 0, policy_version 52389 (0.0014) [2023-03-09 08:38:24,059][22664] Fps is (10 sec: 199888.9, 60 sec: 198792.2, 300 sec: 198718.4). Total num frames: 858456064. Throughput: 0: 49687.3. Samples: 214679024. Policy #0 lag: (min: 0.0, avg: 16.6, max: 32.0) [2023-03-09 08:38:24,060][22664] Avg episode reward: [(0, '52.951')] [2023-03-09 08:38:24,294][23090] Updated weights for policy 0, policy_version 52399 (0.0013) [2023-03-09 08:38:25,217][23090] Updated weights for policy 0, policy_version 52410 (0.0015) [2023-03-09 08:38:25,957][23090] Updated weights for policy 0, policy_version 52420 (0.0020) [2023-03-09 08:38:26,895][23090] Updated weights for policy 0, policy_version 52430 (0.0020) [2023-03-09 08:38:27,628][23090] Updated weights for policy 0, policy_version 52440 (0.0020) [2023-03-09 08:38:28,457][23090] Updated weights for policy 0, policy_version 52450 (0.0016) [2023-03-09 08:38:29,059][22664] Fps is (10 sec: 199879.6, 60 sec: 198792.3, 300 sec: 198718.3). Total num frames: 859455488. Throughput: 0: 49687.2. Samples: 214828464. Policy #0 lag: (min: 0.0, avg: 16.6, max: 32.0) [2023-03-09 08:38:29,060][22664] Avg episode reward: [(0, '52.361')] [2023-03-09 08:38:29,343][23090] Updated weights for policy 0, policy_version 52460 (0.0020) [2023-03-09 08:38:30,154][23090] Updated weights for policy 0, policy_version 52470 (0.0020) [2023-03-09 08:38:30,959][23090] Updated weights for policy 0, policy_version 52480 (0.0018) [2023-03-09 08:38:31,760][23090] Updated weights for policy 0, policy_version 52490 (0.0013) [2023-03-09 08:38:32,633][23090] Updated weights for policy 0, policy_version 52500 (0.0013) [2023-03-09 08:38:33,391][23090] Updated weights for policy 0, policy_version 52510 (0.0013) [2023-03-09 08:38:34,059][22664] Fps is (10 sec: 199886.2, 60 sec: 199338.5, 300 sec: 198774.1). Total num frames: 860454912. Throughput: 0: 49686.3. Samples: 215125296. Policy #0 lag: (min: 0.0, avg: 16.6, max: 32.0) [2023-03-09 08:38:34,060][22664] Avg episode reward: [(0, '54.027')] [2023-03-09 08:38:34,205][23090] Updated weights for policy 0, policy_version 52520 (0.0014) [2023-03-09 08:38:34,814][22940] Signal inference workers to stop experience collection... (16950 times) [2023-03-09 08:38:34,839][22940] Signal inference workers to resume experience collection... (16950 times) [2023-03-09 08:38:34,906][23090] InferenceWorker_p0-w0: stopping experience collection (16950 times) [2023-03-09 08:38:34,906][23090] InferenceWorker_p0-w0: resuming experience collection (16950 times) [2023-03-09 08:38:35,076][23090] Updated weights for policy 0, policy_version 52530 (0.0020) [2023-03-09 08:38:35,886][23090] Updated weights for policy 0, policy_version 52540 (0.0015) [2023-03-09 08:38:36,691][23090] Updated weights for policy 0, policy_version 52551 (0.0018) [2023-03-09 08:38:37,612][23090] Updated weights for policy 0, policy_version 52561 (0.0020) [2023-03-09 08:38:38,443][23090] Updated weights for policy 0, policy_version 52571 (0.0024) [2023-03-09 08:38:39,059][22664] Fps is (10 sec: 198250.8, 60 sec: 198793.0, 300 sec: 198718.4). Total num frames: 861437952. Throughput: 0: 49685.2. Samples: 215424224. Policy #0 lag: (min: 0.0, avg: 16.6, max: 32.0) [2023-03-09 08:38:39,060][22664] Avg episode reward: [(0, '52.803')] [2023-03-09 08:38:39,261][23090] Updated weights for policy 0, policy_version 52581 (0.0016) [2023-03-09 08:38:40,175][23090] Updated weights for policy 0, policy_version 52591 (0.0020) [2023-03-09 08:38:41,011][23090] Updated weights for policy 0, policy_version 52601 (0.0018) [2023-03-09 08:38:41,746][23090] Updated weights for policy 0, policy_version 52611 (0.0013) [2023-03-09 08:38:42,628][23090] Updated weights for policy 0, policy_version 52621 (0.0017) [2023-03-09 08:38:43,384][23090] Updated weights for policy 0, policy_version 52631 (0.0013) [2023-03-09 08:38:44,059][22664] Fps is (10 sec: 198247.1, 60 sec: 198793.8, 300 sec: 198663.0). Total num frames: 862437376. Throughput: 0: 49685.8. Samples: 215573680. Policy #0 lag: (min: 0.0, avg: 16.6, max: 32.0) [2023-03-09 08:38:44,060][22664] Avg episode reward: [(0, '52.115')] [2023-03-09 08:38:44,190][23090] Updated weights for policy 0, policy_version 52641 (0.0016) [2023-03-09 08:38:45,041][23090] Updated weights for policy 0, policy_version 52651 (0.0022) [2023-03-09 08:38:45,873][23090] Updated weights for policy 0, policy_version 52661 (0.0013) [2023-03-09 08:38:46,263][22940] Signal inference workers to stop experience collection... (17000 times) [2023-03-09 08:38:46,278][22940] Signal inference workers to resume experience collection... (17000 times) [2023-03-09 08:38:46,306][23090] InferenceWorker_p0-w0: stopping experience collection (17000 times) [2023-03-09 08:38:46,350][23090] InferenceWorker_p0-w0: resuming experience collection (17000 times) [2023-03-09 08:38:46,601][23090] Updated weights for policy 0, policy_version 52671 (0.0019) [2023-03-09 08:38:47,539][23090] Updated weights for policy 0, policy_version 52682 (0.0013) [2023-03-09 08:38:48,389][23090] Updated weights for policy 0, policy_version 52692 (0.0013) [2023-03-09 08:38:49,058][22664] Fps is (10 sec: 199887.2, 60 sec: 198793.6, 300 sec: 198718.5). Total num frames: 863436800. Throughput: 0: 49730.2. Samples: 215874608. Policy #0 lag: (min: 0.0, avg: 16.6, max: 32.0) [2023-03-09 08:38:49,059][22664] Avg episode reward: [(0, '52.945')] [2023-03-09 08:38:49,231][23090] Updated weights for policy 0, policy_version 52703 (0.0016) [2023-03-09 08:38:50,097][23090] Updated weights for policy 0, policy_version 52713 (0.0016) [2023-03-09 08:38:50,968][23090] Updated weights for policy 0, policy_version 52723 (0.0016) [2023-03-09 08:38:51,724][23090] Updated weights for policy 0, policy_version 52733 (0.0016) [2023-03-09 08:38:52,500][23090] Updated weights for policy 0, policy_version 52743 (0.0023) [2023-03-09 08:38:53,418][23090] Updated weights for policy 0, policy_version 52753 (0.0013) [2023-03-09 08:38:54,059][22664] Fps is (10 sec: 198240.9, 60 sec: 198518.4, 300 sec: 198662.8). Total num frames: 864419840. Throughput: 0: 49775.0. Samples: 216173536. Policy #0 lag: (min: 0.0, avg: 16.6, max: 32.0) [2023-03-09 08:38:54,061][22664] Avg episode reward: [(0, '51.287')] [2023-03-09 08:38:54,266][23090] Updated weights for policy 0, policy_version 52763 (0.0016) [2023-03-09 08:38:54,997][23090] Updated weights for policy 0, policy_version 52773 (0.0017) [2023-03-09 08:38:55,918][23090] Updated weights for policy 0, policy_version 52783 (0.0015) [2023-03-09 08:38:56,727][23090] Updated weights for policy 0, policy_version 52793 (0.0021) [2023-03-09 08:38:57,543][23090] Updated weights for policy 0, policy_version 52803 (0.0016) [2023-03-09 08:38:58,411][23090] Updated weights for policy 0, policy_version 52813 (0.0018) [2023-03-09 08:38:58,501][22940] Signal inference workers to stop experience collection... (17050 times) [2023-03-09 08:38:58,503][22940] Signal inference workers to resume experience collection... (17050 times) [2023-03-09 08:38:58,571][23090] InferenceWorker_p0-w0: stopping experience collection (17050 times) [2023-03-09 08:38:58,571][23090] InferenceWorker_p0-w0: resuming experience collection (17050 times) [2023-03-09 08:38:59,059][22664] Fps is (10 sec: 198242.7, 60 sec: 198520.5, 300 sec: 198663.0). Total num frames: 865419264. Throughput: 0: 49684.1. Samples: 216320976. Policy #0 lag: (min: 0.0, avg: 17.0, max: 33.0) [2023-03-09 08:38:59,060][22664] Avg episode reward: [(0, '52.300')] [2023-03-09 08:38:59,162][23090] Updated weights for policy 0, policy_version 52823 (0.0015) [2023-03-09 08:38:59,966][23090] Updated weights for policy 0, policy_version 52833 (0.0018) [2023-03-09 08:39:00,805][23090] Updated weights for policy 0, policy_version 52843 (0.0018) [2023-03-09 08:39:01,620][23090] Updated weights for policy 0, policy_version 52853 (0.0022) [2023-03-09 08:39:02,499][23090] Updated weights for policy 0, policy_version 52864 (0.0014) [2023-03-09 08:39:03,286][23090] Updated weights for policy 0, policy_version 52874 (0.0016) [2023-03-09 08:39:04,059][22664] Fps is (10 sec: 201527.9, 60 sec: 199065.5, 300 sec: 198774.2). Total num frames: 866435072. Throughput: 0: 49820.8. Samples: 216622000. Policy #0 lag: (min: 0.0, avg: 17.0, max: 33.0) [2023-03-09 08:39:04,060][22664] Avg episode reward: [(0, '52.737')] [2023-03-09 08:39:04,176][23090] Updated weights for policy 0, policy_version 52884 (0.0013) [2023-03-09 08:39:04,910][23090] Updated weights for policy 0, policy_version 52894 (0.0013) [2023-03-09 08:39:05,789][23090] Updated weights for policy 0, policy_version 52904 (0.0023) [2023-03-09 08:39:06,626][23090] Updated weights for policy 0, policy_version 52914 (0.0014) [2023-03-09 08:39:07,467][23090] Updated weights for policy 0, policy_version 52924 (0.0016) [2023-03-09 08:39:08,200][23090] Updated weights for policy 0, policy_version 52934 (0.0013) [2023-03-09 08:39:09,058][22664] Fps is (10 sec: 199888.9, 60 sec: 199066.9, 300 sec: 198718.9). Total num frames: 867418112. Throughput: 0: 49819.2. Samples: 216920880. Policy #0 lag: (min: 0.0, avg: 17.0, max: 33.0) [2023-03-09 08:39:09,059][22664] Avg episode reward: [(0, '53.139')] [2023-03-09 08:39:09,113][23090] Updated weights for policy 0, policy_version 52944 (0.0016) [2023-03-09 08:39:09,656][22940] Signal inference workers to stop experience collection... (17100 times) [2023-03-09 08:39:09,656][22940] Signal inference workers to resume experience collection... (17100 times) [2023-03-09 08:39:09,723][23090] InferenceWorker_p0-w0: stopping experience collection (17100 times) [2023-03-09 08:39:09,723][23090] InferenceWorker_p0-w0: resuming experience collection (17100 times) [2023-03-09 08:39:09,986][23090] Updated weights for policy 0, policy_version 52954 (0.0013) [2023-03-09 08:39:10,689][23090] Updated weights for policy 0, policy_version 52964 (0.0018) [2023-03-09 08:39:11,650][23090] Updated weights for policy 0, policy_version 52974 (0.0016) [2023-03-09 08:39:12,375][23090] Updated weights for policy 0, policy_version 52984 (0.0018) [2023-03-09 08:39:13,184][23090] Updated weights for policy 0, policy_version 52994 (0.0018) [2023-03-09 08:39:14,059][22664] Fps is (10 sec: 196603.5, 60 sec: 199065.7, 300 sec: 198663.0). Total num frames: 868401152. Throughput: 0: 49819.4. Samples: 217070336. Policy #0 lag: (min: 0.0, avg: 17.0, max: 33.0) [2023-03-09 08:39:14,061][22664] Avg episode reward: [(0, '54.698')] [2023-03-09 08:39:14,100][23090] Updated weights for policy 0, policy_version 53004 (0.0016) [2023-03-09 08:39:14,886][23090] Updated weights for policy 0, policy_version 53014 (0.0016) [2023-03-09 08:39:15,726][23090] Updated weights for policy 0, policy_version 53024 (0.0020) [2023-03-09 08:39:16,508][23090] Updated weights for policy 0, policy_version 53034 (0.0019) [2023-03-09 08:39:17,484][23090] Updated weights for policy 0, policy_version 53045 (0.0016) [2023-03-09 08:39:18,173][23090] Updated weights for policy 0, policy_version 53055 (0.0013) [2023-03-09 08:39:19,047][23090] Updated weights for policy 0, policy_version 53065 (0.0015) [2023-03-09 08:39:19,059][22664] Fps is (10 sec: 199872.5, 60 sec: 199337.0, 300 sec: 198773.8). Total num frames: 869416960. Throughput: 0: 49775.4. Samples: 217365216. Policy #0 lag: (min: 0.0, avg: 17.0, max: 33.0) [2023-03-09 08:39:19,061][22664] Avg episode reward: [(0, '54.334')] [2023-03-09 08:39:19,109][22940] Saving /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000053066_869433344.pth... [2023-03-09 08:39:19,171][22940] Removing /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000050154_821723136.pth [2023-03-09 08:39:19,889][23090] Updated weights for policy 0, policy_version 53075 (0.0020) [2023-03-09 08:39:20,499][22940] Signal inference workers to stop experience collection... (17150 times) [2023-03-09 08:39:20,519][22940] Signal inference workers to resume experience collection... (17150 times) [2023-03-09 08:39:20,557][23090] InferenceWorker_p0-w0: stopping experience collection (17150 times) [2023-03-09 08:39:20,596][23090] InferenceWorker_p0-w0: resuming experience collection (17150 times) [2023-03-09 08:39:20,681][23090] Updated weights for policy 0, policy_version 53085 (0.0013) [2023-03-09 08:39:21,449][23090] Updated weights for policy 0, policy_version 53095 (0.0013) [2023-03-09 08:39:22,433][23090] Updated weights for policy 0, policy_version 53106 (0.0018) [2023-03-09 08:39:23,231][23090] Updated weights for policy 0, policy_version 53116 (0.0016) [2023-03-09 08:39:24,026][23090] Updated weights for policy 0, policy_version 53126 (0.0019) [2023-03-09 08:39:24,058][22664] Fps is (10 sec: 201529.6, 60 sec: 199339.2, 300 sec: 198774.2). Total num frames: 870416384. Throughput: 0: 49822.0. Samples: 217666208. Policy #0 lag: (min: 0.0, avg: 17.0, max: 33.0) [2023-03-09 08:39:24,059][22664] Avg episode reward: [(0, '52.698')] [2023-03-09 08:39:24,906][23090] Updated weights for policy 0, policy_version 53136 (0.0013) [2023-03-09 08:39:25,759][23090] Updated weights for policy 0, policy_version 53146 (0.0016) [2023-03-09 08:39:26,478][23090] Updated weights for policy 0, policy_version 53156 (0.0013) [2023-03-09 08:39:27,426][23090] Updated weights for policy 0, policy_version 53166 (0.0018) [2023-03-09 08:39:28,125][23090] Updated weights for policy 0, policy_version 53176 (0.0013) [2023-03-09 08:39:28,943][23090] Updated weights for policy 0, policy_version 53186 (0.0013) [2023-03-09 08:39:29,059][22664] Fps is (10 sec: 199892.2, 60 sec: 199339.1, 300 sec: 198774.0). Total num frames: 871415808. Throughput: 0: 49822.4. Samples: 217815696. Policy #0 lag: (min: 2.0, avg: 16.8, max: 34.0) [2023-03-09 08:39:29,060][22664] Avg episode reward: [(0, '53.235')] [2023-03-09 08:39:29,851][23090] Updated weights for policy 0, policy_version 53196 (0.0015) [2023-03-09 08:39:30,633][23090] Updated weights for policy 0, policy_version 53206 (0.0023) [2023-03-09 08:39:30,911][22940] Signal inference workers to stop experience collection... (17200 times) [2023-03-09 08:39:30,926][22940] Signal inference workers to resume experience collection... (17200 times) [2023-03-09 08:39:30,955][23090] InferenceWorker_p0-w0: stopping experience collection (17200 times) [2023-03-09 08:39:31,001][23090] InferenceWorker_p0-w0: resuming experience collection (17200 times) [2023-03-09 08:39:31,490][23090] Updated weights for policy 0, policy_version 53216 (0.0016) [2023-03-09 08:39:32,258][23090] Updated weights for policy 0, policy_version 53226 (0.0013) [2023-03-09 08:39:33,119][23090] Updated weights for policy 0, policy_version 53236 (0.0024) [2023-03-09 08:39:33,887][23090] Updated weights for policy 0, policy_version 53246 (0.0026) [2023-03-09 08:39:34,059][22664] Fps is (10 sec: 198244.1, 60 sec: 199065.5, 300 sec: 198663.1). Total num frames: 872398848. Throughput: 0: 49824.6. Samples: 218116720. Policy #0 lag: (min: 2.0, avg: 16.8, max: 34.0) [2023-03-09 08:39:34,060][22664] Avg episode reward: [(0, '51.787')] [2023-03-09 08:39:34,730][23090] Updated weights for policy 0, policy_version 53256 (0.0016) [2023-03-09 08:39:35,679][23090] Updated weights for policy 0, policy_version 53267 (0.0013) [2023-03-09 08:39:36,482][23090] Updated weights for policy 0, policy_version 53277 (0.0021) [2023-03-09 08:39:37,241][23090] Updated weights for policy 0, policy_version 53287 (0.0016) [2023-03-09 08:39:38,115][23090] Updated weights for policy 0, policy_version 53297 (0.0013) [2023-03-09 08:39:38,994][23090] Updated weights for policy 0, policy_version 53307 (0.0016) [2023-03-09 08:39:39,058][22664] Fps is (10 sec: 198251.3, 60 sec: 199339.1, 300 sec: 198718.7). Total num frames: 873398272. Throughput: 0: 49781.0. Samples: 218413664. Policy #0 lag: (min: 2.0, avg: 16.8, max: 34.0) [2023-03-09 08:39:39,059][22664] Avg episode reward: [(0, '53.132')] [2023-03-09 08:39:39,725][23090] Updated weights for policy 0, policy_version 53317 (0.0017) [2023-03-09 08:39:40,661][23090] Updated weights for policy 0, policy_version 53327 (0.0015) [2023-03-09 08:39:41,508][23090] Updated weights for policy 0, policy_version 53337 (0.0017) [2023-03-09 08:39:42,193][23090] Updated weights for policy 0, policy_version 53347 (0.0016) [2023-03-09 08:39:43,079][23090] Updated weights for policy 0, policy_version 53357 (0.0015) [2023-03-09 08:39:43,291][22940] Signal inference workers to stop experience collection... (17250 times) [2023-03-09 08:39:43,293][22940] Signal inference workers to resume experience collection... (17250 times) [2023-03-09 08:39:43,358][23090] InferenceWorker_p0-w0: stopping experience collection (17250 times) [2023-03-09 08:39:43,360][23090] InferenceWorker_p0-w0: resuming experience collection (17250 times) [2023-03-09 08:39:43,843][23090] Updated weights for policy 0, policy_version 53367 (0.0023) [2023-03-09 08:39:44,059][22664] Fps is (10 sec: 198243.5, 60 sec: 199064.9, 300 sec: 198718.3). Total num frames: 874381312. Throughput: 0: 49871.2. Samples: 218565184. Policy #0 lag: (min: 2.0, avg: 16.8, max: 34.0) [2023-03-09 08:39:44,061][22664] Avg episode reward: [(0, '54.040')] [2023-03-09 08:39:44,661][23090] Updated weights for policy 0, policy_version 53377 (0.0017) [2023-03-09 08:39:45,524][23090] Updated weights for policy 0, policy_version 53387 (0.0013) [2023-03-09 08:39:46,342][23090] Updated weights for policy 0, policy_version 53397 (0.0018) [2023-03-09 08:39:47,080][23090] Updated weights for policy 0, policy_version 53407 (0.0013) [2023-03-09 08:39:47,983][23090] Updated weights for policy 0, policy_version 53417 (0.0017) [2023-03-09 08:39:48,815][23090] Updated weights for policy 0, policy_version 53427 (0.0013) [2023-03-09 08:39:49,059][22664] Fps is (10 sec: 198237.6, 60 sec: 199064.2, 300 sec: 198774.1). Total num frames: 875380736. Throughput: 0: 49824.0. Samples: 218864096. Policy #0 lag: (min: 2.0, avg: 16.8, max: 34.0) [2023-03-09 08:39:49,061][22664] Avg episode reward: [(0, '51.465')] [2023-03-09 08:39:49,597][23090] Updated weights for policy 0, policy_version 53437 (0.0019) [2023-03-09 08:39:50,375][23090] Updated weights for policy 0, policy_version 53447 (0.0016) [2023-03-09 08:39:51,278][23090] Updated weights for policy 0, policy_version 53457 (0.0017) [2023-03-09 08:39:52,164][23090] Updated weights for policy 0, policy_version 53467 (0.0013) [2023-03-09 08:39:52,893][23090] Updated weights for policy 0, policy_version 53477 (0.0013) [2023-03-09 08:39:53,786][23090] Updated weights for policy 0, policy_version 53487 (0.0019) [2023-03-09 08:39:54,058][22664] Fps is (10 sec: 201528.0, 60 sec: 199612.7, 300 sec: 198829.6). Total num frames: 876396544. Throughput: 0: 49826.1. Samples: 219163056. Policy #0 lag: (min: 2.0, avg: 16.8, max: 34.0) [2023-03-09 08:39:54,060][22664] Avg episode reward: [(0, '53.377')] [2023-03-09 08:39:54,634][23090] Updated weights for policy 0, policy_version 53497 (0.0013) [2023-03-09 08:39:55,408][23090] Updated weights for policy 0, policy_version 53507 (0.0025) [2023-03-09 08:39:55,868][22940] Signal inference workers to stop experience collection... (17300 times) [2023-03-09 08:39:55,869][22940] Signal inference workers to resume experience collection... (17300 times) [2023-03-09 08:39:55,935][23090] InferenceWorker_p0-w0: stopping experience collection (17300 times) [2023-03-09 08:39:55,935][23090] InferenceWorker_p0-w0: resuming experience collection (17300 times) [2023-03-09 08:39:56,261][23090] Updated weights for policy 0, policy_version 53517 (0.0019) [2023-03-09 08:39:57,056][23090] Updated weights for policy 0, policy_version 53527 (0.0017) [2023-03-09 08:39:57,822][23090] Updated weights for policy 0, policy_version 53537 (0.0016) [2023-03-09 08:39:58,660][23090] Updated weights for policy 0, policy_version 53547 (0.0013) [2023-03-09 08:39:59,059][22664] Fps is (10 sec: 201524.7, 60 sec: 199611.2, 300 sec: 198885.0). Total num frames: 877395968. Throughput: 0: 49780.9. Samples: 219310480. Policy #0 lag: (min: 2.0, avg: 16.8, max: 34.0) [2023-03-09 08:39:59,069][22664] Avg episode reward: [(0, '51.980')] [2023-03-09 08:39:59,503][23090] Updated weights for policy 0, policy_version 53557 (0.0013) [2023-03-09 08:40:00,236][23090] Updated weights for policy 0, policy_version 53567 (0.0017) [2023-03-09 08:40:01,182][23090] Updated weights for policy 0, policy_version 53578 (0.0017) [2023-03-09 08:40:02,038][23090] Updated weights for policy 0, policy_version 53588 (0.0016) [2023-03-09 08:40:02,792][23090] Updated weights for policy 0, policy_version 53598 (0.0018) [2023-03-09 08:40:03,668][23090] Updated weights for policy 0, policy_version 53608 (0.0026) [2023-03-09 08:40:04,059][22664] Fps is (10 sec: 196607.4, 60 sec: 198792.7, 300 sec: 198774.2). Total num frames: 878362624. Throughput: 0: 49872.6. Samples: 219609456. Policy #0 lag: (min: 1.0, avg: 17.4, max: 33.0) [2023-03-09 08:40:04,060][22664] Avg episode reward: [(0, '54.436')] [2023-03-09 08:40:04,522][23090] Updated weights for policy 0, policy_version 53618 (0.0020) [2023-03-09 08:40:05,360][23090] Updated weights for policy 0, policy_version 53629 (0.0013) [2023-03-09 08:40:06,178][23090] Updated weights for policy 0, policy_version 53639 (0.0020) [2023-03-09 08:40:07,069][23090] Updated weights for policy 0, policy_version 53649 (0.0017) [2023-03-09 08:40:07,947][23090] Updated weights for policy 0, policy_version 53659 (0.0019) [2023-03-09 08:40:08,640][23090] Updated weights for policy 0, policy_version 53669 (0.0024) [2023-03-09 08:40:08,645][22940] Signal inference workers to stop experience collection... (17350 times) [2023-03-09 08:40:08,645][22940] Signal inference workers to resume experience collection... (17350 times) [2023-03-09 08:40:08,711][23090] InferenceWorker_p0-w0: stopping experience collection (17350 times) [2023-03-09 08:40:08,711][23090] InferenceWorker_p0-w0: resuming experience collection (17350 times) [2023-03-09 08:40:09,058][22664] Fps is (10 sec: 199892.0, 60 sec: 199611.7, 300 sec: 198996.2). Total num frames: 879394816. Throughput: 0: 49872.7. Samples: 219910480. Policy #0 lag: (min: 1.0, avg: 17.4, max: 33.0) [2023-03-09 08:40:09,059][22664] Avg episode reward: [(0, '54.941')] [2023-03-09 08:40:09,540][23090] Updated weights for policy 0, policy_version 53679 (0.0013) [2023-03-09 08:40:10,428][23090] Updated weights for policy 0, policy_version 53689 (0.0017) [2023-03-09 08:40:11,199][23090] Updated weights for policy 0, policy_version 53699 (0.0013) [2023-03-09 08:40:12,041][23090] Updated weights for policy 0, policy_version 53709 (0.0017) [2023-03-09 08:40:12,825][23090] Updated weights for policy 0, policy_version 53719 (0.0017) [2023-03-09 08:40:13,606][23090] Updated weights for policy 0, policy_version 53729 (0.0013) [2023-03-09 08:40:14,059][22664] Fps is (10 sec: 203159.3, 60 sec: 199885.3, 300 sec: 198885.1). Total num frames: 880394240. Throughput: 0: 49826.9. Samples: 220057904. Policy #0 lag: (min: 1.0, avg: 17.4, max: 33.0) [2023-03-09 08:40:14,060][22664] Avg episode reward: [(0, '51.595')] [2023-03-09 08:40:14,513][23090] Updated weights for policy 0, policy_version 53739 (0.0020) [2023-03-09 08:40:15,295][23090] Updated weights for policy 0, policy_version 53749 (0.0020) [2023-03-09 08:40:16,067][23090] Updated weights for policy 0, policy_version 53759 (0.0013) [2023-03-09 08:40:16,964][23090] Updated weights for policy 0, policy_version 53769 (0.0019) [2023-03-09 08:40:17,765][23090] Updated weights for policy 0, policy_version 53779 (0.0012) [2023-03-09 08:40:18,543][23090] Updated weights for policy 0, policy_version 53789 (0.0022) [2023-03-09 08:40:19,058][22664] Fps is (10 sec: 198246.1, 60 sec: 199340.6, 300 sec: 198885.1). Total num frames: 881377280. Throughput: 0: 49780.0. Samples: 220356816. Policy #0 lag: (min: 1.0, avg: 17.4, max: 33.0) [2023-03-09 08:40:19,059][22664] Avg episode reward: [(0, '54.174')] [2023-03-09 08:40:19,320][23090] Updated weights for policy 0, policy_version 53799 (0.0014) [2023-03-09 08:40:20,217][23090] Updated weights for policy 0, policy_version 53809 (0.0018) [2023-03-09 08:40:21,099][23090] Updated weights for policy 0, policy_version 53820 (0.0026) [2023-03-09 08:40:21,102][22940] Signal inference workers to stop experience collection... (17400 times) [2023-03-09 08:40:21,104][22940] Signal inference workers to resume experience collection... (17400 times) [2023-03-09 08:40:21,172][23090] InferenceWorker_p0-w0: stopping experience collection (17400 times) [2023-03-09 08:40:21,173][23090] InferenceWorker_p0-w0: resuming experience collection (17400 times) [2023-03-09 08:40:21,867][23090] Updated weights for policy 0, policy_version 53830 (0.0017) [2023-03-09 08:40:22,795][23090] Updated weights for policy 0, policy_version 53840 (0.0013) [2023-03-09 08:40:23,578][23090] Updated weights for policy 0, policy_version 53850 (0.0013) [2023-03-09 08:40:24,058][22664] Fps is (10 sec: 196610.7, 60 sec: 199065.5, 300 sec: 198829.6). Total num frames: 882360320. Throughput: 0: 49869.8. Samples: 220657808. Policy #0 lag: (min: 1.0, avg: 17.4, max: 33.0) [2023-03-09 08:40:24,059][22664] Avg episode reward: [(0, '52.461')] [2023-03-09 08:40:24,312][23090] Updated weights for policy 0, policy_version 53860 (0.0023) [2023-03-09 08:40:25,253][23090] Updated weights for policy 0, policy_version 53870 (0.0013) [2023-03-09 08:40:26,002][23090] Updated weights for policy 0, policy_version 53880 (0.0020) [2023-03-09 08:40:26,914][23090] Updated weights for policy 0, policy_version 53891 (0.0013) [2023-03-09 08:40:27,802][23090] Updated weights for policy 0, policy_version 53901 (0.0018) [2023-03-09 08:40:28,563][23090] Updated weights for policy 0, policy_version 53911 (0.0018) [2023-03-09 08:40:29,059][22664] Fps is (10 sec: 201517.6, 60 sec: 199611.6, 300 sec: 198996.2). Total num frames: 883392512. Throughput: 0: 49824.7. Samples: 220807296. Policy #0 lag: (min: 1.0, avg: 17.4, max: 33.0) [2023-03-09 08:40:29,060][22664] Avg episode reward: [(0, '51.400')] [2023-03-09 08:40:29,362][23090] Updated weights for policy 0, policy_version 53921 (0.0016) [2023-03-09 08:40:30,202][23090] Updated weights for policy 0, policy_version 53931 (0.0013) [2023-03-09 08:40:31,048][23090] Updated weights for policy 0, policy_version 53941 (0.0021) [2023-03-09 08:40:31,756][23090] Updated weights for policy 0, policy_version 53951 (0.0013) [2023-03-09 08:40:32,224][22940] Signal inference workers to stop experience collection... (17450 times) [2023-03-09 08:40:32,240][22940] Signal inference workers to resume experience collection... (17450 times) [2023-03-09 08:40:32,302][23090] InferenceWorker_p0-w0: stopping experience collection (17450 times) [2023-03-09 08:40:32,302][23090] InferenceWorker_p0-w0: resuming experience collection (17450 times) [2023-03-09 08:40:32,592][23090] Updated weights for policy 0, policy_version 53961 (0.0013) [2023-03-09 08:40:33,464][23090] Updated weights for policy 0, policy_version 53971 (0.0013) [2023-03-09 08:40:34,059][22664] Fps is (10 sec: 201518.9, 60 sec: 199611.3, 300 sec: 198940.6). Total num frames: 884375552. Throughput: 0: 49917.4. Samples: 221110368. Policy #0 lag: (min: 1.0, avg: 16.5, max: 33.0) [2023-03-09 08:40:34,061][22664] Avg episode reward: [(0, '52.243')] [2023-03-09 08:40:34,223][23090] Updated weights for policy 0, policy_version 53981 (0.0013) [2023-03-09 08:40:35,023][23090] Updated weights for policy 0, policy_version 53991 (0.0016) [2023-03-09 08:40:35,907][23090] Updated weights for policy 0, policy_version 54001 (0.0016) [2023-03-09 08:40:36,818][23090] Updated weights for policy 0, policy_version 54012 (0.0013) [2023-03-09 08:40:37,539][23090] Updated weights for policy 0, policy_version 54022 (0.0013) [2023-03-09 08:40:38,440][23090] Updated weights for policy 0, policy_version 54032 (0.0018) [2023-03-09 08:40:39,059][22664] Fps is (10 sec: 199887.5, 60 sec: 199884.2, 300 sec: 199051.6). Total num frames: 885391360. Throughput: 0: 49916.3. Samples: 221409296. Policy #0 lag: (min: 1.0, avg: 16.5, max: 33.0) [2023-03-09 08:40:39,060][22664] Avg episode reward: [(0, '52.969')] [2023-03-09 08:40:39,320][23090] Updated weights for policy 0, policy_version 54043 (0.0017) [2023-03-09 08:40:40,139][23090] Updated weights for policy 0, policy_version 54053 (0.0017) [2023-03-09 08:40:41,030][23090] Updated weights for policy 0, policy_version 54063 (0.0016) [2023-03-09 08:40:41,898][23090] Updated weights for policy 0, policy_version 54073 (0.0019) [2023-03-09 08:40:42,643][23090] Updated weights for policy 0, policy_version 54083 (0.0017) [2023-03-09 08:40:43,486][23090] Updated weights for policy 0, policy_version 54093 (0.0016) [2023-03-09 08:40:43,732][22940] Signal inference workers to stop experience collection... (17500 times) [2023-03-09 08:40:43,732][22940] Signal inference workers to resume experience collection... (17500 times) [2023-03-09 08:40:43,797][23090] InferenceWorker_p0-w0: stopping experience collection (17500 times) [2023-03-09 08:40:43,797][23090] InferenceWorker_p0-w0: resuming experience collection (17500 times) [2023-03-09 08:40:44,059][22664] Fps is (10 sec: 198248.9, 60 sec: 199612.2, 300 sec: 198996.5). Total num frames: 886358016. Throughput: 0: 49962.2. Samples: 221558768. Policy #0 lag: (min: 1.0, avg: 16.5, max: 33.0) [2023-03-09 08:40:44,060][22664] Avg episode reward: [(0, '52.268')] [2023-03-09 08:40:44,333][23090] Updated weights for policy 0, policy_version 54103 (0.0016) [2023-03-09 08:40:45,107][23090] Updated weights for policy 0, policy_version 54113 (0.0020) [2023-03-09 08:40:45,940][23090] Updated weights for policy 0, policy_version 54123 (0.0013) [2023-03-09 08:40:46,785][23090] Updated weights for policy 0, policy_version 54133 (0.0016) [2023-03-09 08:40:47,550][23090] Updated weights for policy 0, policy_version 54143 (0.0013) [2023-03-09 08:40:48,441][23090] Updated weights for policy 0, policy_version 54153 (0.0016) [2023-03-09 08:40:49,059][22664] Fps is (10 sec: 198248.4, 60 sec: 199886.1, 300 sec: 199051.8). Total num frames: 887373824. Throughput: 0: 49914.3. Samples: 221855600. Policy #0 lag: (min: 1.0, avg: 16.5, max: 33.0) [2023-03-09 08:40:49,060][22664] Avg episode reward: [(0, '52.440')] [2023-03-09 08:40:49,244][23090] Updated weights for policy 0, policy_version 54163 (0.0013) [2023-03-09 08:40:50,025][23090] Updated weights for policy 0, policy_version 54173 (0.0016) [2023-03-09 08:40:50,823][23090] Updated weights for policy 0, policy_version 54183 (0.0020) [2023-03-09 08:40:51,703][23090] Updated weights for policy 0, policy_version 54193 (0.0027) [2023-03-09 08:40:52,534][23090] Updated weights for policy 0, policy_version 54203 (0.0013) [2023-03-09 08:40:53,381][23090] Updated weights for policy 0, policy_version 54213 (0.0015) [2023-03-09 08:40:54,058][22664] Fps is (10 sec: 198248.6, 60 sec: 199065.7, 300 sec: 198996.3). Total num frames: 888340480. Throughput: 0: 49867.4. Samples: 222154512. Policy #0 lag: (min: 1.0, avg: 16.5, max: 33.0) [2023-03-09 08:40:54,059][22664] Avg episode reward: [(0, '50.476')] [2023-03-09 08:40:54,161][22940] Signal inference workers to stop experience collection... (17550 times) [2023-03-09 08:40:54,162][22940] Signal inference workers to resume experience collection... (17550 times) [2023-03-09 08:40:54,228][23090] InferenceWorker_p0-w0: stopping experience collection (17550 times) [2023-03-09 08:40:54,228][23090] InferenceWorker_p0-w0: resuming experience collection (17550 times) [2023-03-09 08:40:54,230][23090] Updated weights for policy 0, policy_version 54223 (0.0016) [2023-03-09 08:40:55,078][23090] Updated weights for policy 0, policy_version 54233 (0.0014) [2023-03-09 08:40:55,788][23090] Updated weights for policy 0, policy_version 54243 (0.0013) [2023-03-09 08:40:56,674][23090] Updated weights for policy 0, policy_version 54253 (0.0013) [2023-03-09 08:40:57,471][23090] Updated weights for policy 0, policy_version 54263 (0.0013) [2023-03-09 08:40:58,304][23090] Updated weights for policy 0, policy_version 54273 (0.0016) [2023-03-09 08:40:59,059][22664] Fps is (10 sec: 198241.6, 60 sec: 199338.9, 300 sec: 199051.5). Total num frames: 889356288. Throughput: 0: 49912.4. Samples: 222303968. Policy #0 lag: (min: 1.0, avg: 16.5, max: 33.0) [2023-03-09 08:40:59,061][22664] Avg episode reward: [(0, '53.243')] [2023-03-09 08:40:59,127][23090] Updated weights for policy 0, policy_version 54283 (0.0021) [2023-03-09 08:41:00,004][23090] Updated weights for policy 0, policy_version 54293 (0.0026) [2023-03-09 08:41:00,740][23090] Updated weights for policy 0, policy_version 54303 (0.0013) [2023-03-09 08:41:01,620][23090] Updated weights for policy 0, policy_version 54313 (0.0013) [2023-03-09 08:41:02,433][23090] Updated weights for policy 0, policy_version 54323 (0.0017) [2023-03-09 08:41:03,193][23090] Updated weights for policy 0, policy_version 54333 (0.0016) [2023-03-09 08:41:04,059][22664] Fps is (10 sec: 201522.5, 60 sec: 199884.9, 300 sec: 199052.0). Total num frames: 890355712. Throughput: 0: 49913.2. Samples: 222602912. Policy #0 lag: (min: 1.0, avg: 16.5, max: 33.0) [2023-03-09 08:41:04,060][22664] Avg episode reward: [(0, '51.629')] [2023-03-09 08:41:04,122][23090] Updated weights for policy 0, policy_version 54344 (0.0013) [2023-03-09 08:41:04,828][22940] Signal inference workers to stop experience collection... (17600 times) [2023-03-09 08:41:04,838][22940] Signal inference workers to resume experience collection... (17600 times) [2023-03-09 08:41:04,900][23090] InferenceWorker_p0-w0: stopping experience collection (17600 times) [2023-03-09 08:41:04,901][23090] InferenceWorker_p0-w0: resuming experience collection (17600 times) [2023-03-09 08:41:04,986][23090] Updated weights for policy 0, policy_version 54354 (0.0025) [2023-03-09 08:41:05,810][23090] Updated weights for policy 0, policy_version 54365 (0.0012) [2023-03-09 08:41:06,638][23090] Updated weights for policy 0, policy_version 54375 (0.0013) [2023-03-09 08:41:07,519][23090] Updated weights for policy 0, policy_version 54385 (0.0015) [2023-03-09 08:41:08,387][23090] Updated weights for policy 0, policy_version 54395 (0.0016) [2023-03-09 08:41:09,059][22664] Fps is (10 sec: 199883.9, 60 sec: 199337.5, 300 sec: 199051.5). Total num frames: 891355136. Throughput: 0: 49821.9. Samples: 222899808. Policy #0 lag: (min: 1.0, avg: 16.9, max: 33.0) [2023-03-09 08:41:09,063][22664] Avg episode reward: [(0, '53.724')] [2023-03-09 08:41:09,135][23090] Updated weights for policy 0, policy_version 54405 (0.0018) [2023-03-09 08:41:10,047][23090] Updated weights for policy 0, policy_version 54415 (0.0021) [2023-03-09 08:41:10,868][23090] Updated weights for policy 0, policy_version 54425 (0.0013) [2023-03-09 08:41:11,622][23090] Updated weights for policy 0, policy_version 54435 (0.0016) [2023-03-09 08:41:12,525][23090] Updated weights for policy 0, policy_version 54445 (0.0013) [2023-03-09 08:41:13,335][23090] Updated weights for policy 0, policy_version 54455 (0.0013) [2023-03-09 08:41:14,059][22664] Fps is (10 sec: 196604.9, 60 sec: 198792.4, 300 sec: 198996.2). Total num frames: 892321792. Throughput: 0: 49820.9. Samples: 223049232. Policy #0 lag: (min: 1.0, avg: 16.9, max: 33.0) [2023-03-09 08:41:14,061][22664] Avg episode reward: [(0, '54.622')] [2023-03-09 08:41:14,148][23090] Updated weights for policy 0, policy_version 54465 (0.0016) [2023-03-09 08:41:15,024][23090] Updated weights for policy 0, policy_version 54475 (0.0019) [2023-03-09 08:41:15,834][23090] Updated weights for policy 0, policy_version 54485 (0.0013) [2023-03-09 08:41:16,573][23090] Updated weights for policy 0, policy_version 54495 (0.0015) [2023-03-09 08:41:17,051][22940] Signal inference workers to stop experience collection... (17650 times) [2023-03-09 08:41:17,072][22940] Signal inference workers to resume experience collection... (17650 times) [2023-03-09 08:41:17,117][23090] InferenceWorker_p0-w0: stopping experience collection (17650 times) [2023-03-09 08:41:17,117][23090] InferenceWorker_p0-w0: resuming experience collection (17650 times) [2023-03-09 08:41:17,402][23090] Updated weights for policy 0, policy_version 54505 (0.0026) [2023-03-09 08:41:18,294][23090] Updated weights for policy 0, policy_version 54515 (0.0016) [2023-03-09 08:41:19,053][23090] Updated weights for policy 0, policy_version 54525 (0.0013) [2023-03-09 08:41:19,059][22664] Fps is (10 sec: 198244.5, 60 sec: 199337.2, 300 sec: 199051.5). Total num frames: 893337600. Throughput: 0: 49682.6. Samples: 223346096. Policy #0 lag: (min: 1.0, avg: 16.9, max: 33.0) [2023-03-09 08:41:19,061][22664] Avg episode reward: [(0, '52.671')] [2023-03-09 08:41:19,068][22940] Saving /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000054525_893337600.pth... [2023-03-09 08:41:19,126][22940] Removing /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000051608_845545472.pth [2023-03-09 08:41:19,822][23090] Updated weights for policy 0, policy_version 54535 (0.0013) [2023-03-09 08:41:20,729][23090] Updated weights for policy 0, policy_version 54545 (0.0016) [2023-03-09 08:41:21,592][23090] Updated weights for policy 0, policy_version 54555 (0.0016) [2023-03-09 08:41:22,331][23090] Updated weights for policy 0, policy_version 54565 (0.0018) [2023-03-09 08:41:23,244][23090] Updated weights for policy 0, policy_version 54575 (0.0013) [2023-03-09 08:41:24,058][22664] Fps is (10 sec: 198250.4, 60 sec: 199065.7, 300 sec: 198996.3). Total num frames: 894304256. Throughput: 0: 49637.5. Samples: 223642976. Policy #0 lag: (min: 1.0, avg: 16.9, max: 33.0) [2023-03-09 08:41:24,059][22664] Avg episode reward: [(0, '54.458')] [2023-03-09 08:41:24,074][23090] Updated weights for policy 0, policy_version 54585 (0.0018) [2023-03-09 08:41:24,952][23090] Updated weights for policy 0, policy_version 54596 (0.0013) [2023-03-09 08:41:25,838][23090] Updated weights for policy 0, policy_version 54606 (0.0014) [2023-03-09 08:41:26,611][23090] Updated weights for policy 0, policy_version 54616 (0.0016) [2023-03-09 08:41:27,521][23090] Updated weights for policy 0, policy_version 54627 (0.0016) [2023-03-09 08:41:28,375][23090] Updated weights for policy 0, policy_version 54637 (0.0013) [2023-03-09 08:41:29,059][22664] Fps is (10 sec: 196610.4, 60 sec: 198519.4, 300 sec: 198941.0). Total num frames: 895303680. Throughput: 0: 49637.5. Samples: 223792464. Policy #0 lag: (min: 1.0, avg: 16.9, max: 33.0) [2023-03-09 08:41:29,061][22664] Avg episode reward: [(0, '53.219')] [2023-03-09 08:41:29,182][23090] Updated weights for policy 0, policy_version 54647 (0.0026) [2023-03-09 08:41:30,007][23090] Updated weights for policy 0, policy_version 54657 (0.0020) [2023-03-09 08:41:30,269][22940] Signal inference workers to stop experience collection... (17700 times) [2023-03-09 08:41:30,289][22940] Signal inference workers to resume experience collection... (17700 times) [2023-03-09 08:41:30,336][23090] InferenceWorker_p0-w0: stopping experience collection (17700 times) [2023-03-09 08:41:30,336][23090] InferenceWorker_p0-w0: resuming experience collection (17700 times) [2023-03-09 08:41:30,895][23090] Updated weights for policy 0, policy_version 54667 (0.0022) [2023-03-09 08:41:31,697][23090] Updated weights for policy 0, policy_version 54677 (0.0017) [2023-03-09 08:41:32,436][23090] Updated weights for policy 0, policy_version 54687 (0.0016) [2023-03-09 08:41:33,366][23090] Updated weights for policy 0, policy_version 54698 (0.0020) [2023-03-09 08:41:34,059][22664] Fps is (10 sec: 199878.5, 60 sec: 198792.3, 300 sec: 199051.8). Total num frames: 896303104. Throughput: 0: 49637.4. Samples: 224089296. Policy #0 lag: (min: 1.0, avg: 16.9, max: 33.0) [2023-03-09 08:41:34,061][22664] Avg episode reward: [(0, '53.880')] [2023-03-09 08:41:34,285][23090] Updated weights for policy 0, policy_version 54708 (0.0018) [2023-03-09 08:41:35,020][23090] Updated weights for policy 0, policy_version 54718 (0.0016) [2023-03-09 08:41:35,848][23090] Updated weights for policy 0, policy_version 54728 (0.0018) [2023-03-09 08:41:36,727][23090] Updated weights for policy 0, policy_version 54738 (0.0013) [2023-03-09 08:41:37,563][23090] Updated weights for policy 0, policy_version 54748 (0.0016) [2023-03-09 08:41:38,281][23090] Updated weights for policy 0, policy_version 54758 (0.0016) [2023-03-09 08:41:39,059][22664] Fps is (10 sec: 198250.0, 60 sec: 198246.4, 300 sec: 199052.0). Total num frames: 897286144. Throughput: 0: 49593.1. Samples: 224386208. Policy #0 lag: (min: 1.0, avg: 16.9, max: 33.0) [2023-03-09 08:41:39,061][22664] Avg episode reward: [(0, '54.801')] [2023-03-09 08:41:39,245][23090] Updated weights for policy 0, policy_version 54769 (0.0013) [2023-03-09 08:41:40,141][23090] Updated weights for policy 0, policy_version 54779 (0.0016) [2023-03-09 08:41:40,916][23090] Updated weights for policy 0, policy_version 54790 (0.0018) [2023-03-09 08:41:41,858][23090] Updated weights for policy 0, policy_version 54800 (0.0015) [2023-03-09 08:41:42,696][23090] Updated weights for policy 0, policy_version 54810 (0.0016) [2023-03-09 08:41:43,335][22940] Signal inference workers to stop experience collection... (17750 times) [2023-03-09 08:41:43,336][22940] Signal inference workers to resume experience collection... (17750 times) [2023-03-09 08:41:43,401][23090] InferenceWorker_p0-w0: stopping experience collection (17750 times) [2023-03-09 08:41:43,404][23090] InferenceWorker_p0-w0: resuming experience collection (17750 times) [2023-03-09 08:41:43,451][23090] Updated weights for policy 0, policy_version 54820 (0.0015) [2023-03-09 08:41:44,058][22664] Fps is (10 sec: 196613.6, 60 sec: 198519.8, 300 sec: 198996.2). Total num frames: 898269184. Throughput: 0: 49594.3. Samples: 224535696. Policy #0 lag: (min: 1.0, avg: 16.2, max: 33.0) [2023-03-09 08:41:44,059][22664] Avg episode reward: [(0, '54.375')] [2023-03-09 08:41:44,394][23090] Updated weights for policy 0, policy_version 54830 (0.0016) [2023-03-09 08:41:45,166][23090] Updated weights for policy 0, policy_version 54840 (0.0016) [2023-03-09 08:41:45,974][23090] Updated weights for policy 0, policy_version 54850 (0.0017) [2023-03-09 08:41:46,809][23090] Updated weights for policy 0, policy_version 54860 (0.0013) [2023-03-09 08:41:47,639][23090] Updated weights for policy 0, policy_version 54870 (0.0013) [2023-03-09 08:41:48,501][23090] Updated weights for policy 0, policy_version 54881 (0.0018) [2023-03-09 08:41:49,059][22664] Fps is (10 sec: 199882.2, 60 sec: 198518.8, 300 sec: 199051.8). Total num frames: 899284992. Throughput: 0: 49547.5. Samples: 224832560. Policy #0 lag: (min: 1.0, avg: 16.2, max: 33.0) [2023-03-09 08:41:49,061][22664] Avg episode reward: [(0, '52.529')] [2023-03-09 08:41:49,370][23090] Updated weights for policy 0, policy_version 54891 (0.0013) [2023-03-09 08:41:50,224][23090] Updated weights for policy 0, policy_version 54901 (0.0016) [2023-03-09 08:41:50,928][23090] Updated weights for policy 0, policy_version 54911 (0.0017) [2023-03-09 08:41:51,756][23090] Updated weights for policy 0, policy_version 54921 (0.0021) [2023-03-09 08:41:52,605][23090] Updated weights for policy 0, policy_version 54931 (0.0016) [2023-03-09 08:41:53,405][23090] Updated weights for policy 0, policy_version 54941 (0.0018) [2023-03-09 08:41:54,059][22664] Fps is (10 sec: 201522.1, 60 sec: 199065.4, 300 sec: 199051.9). Total num frames: 900284416. Throughput: 0: 49594.3. Samples: 225131536. Policy #0 lag: (min: 1.0, avg: 16.2, max: 33.0) [2023-03-09 08:41:54,060][22664] Avg episode reward: [(0, '52.934')] [2023-03-09 08:41:54,224][23090] Updated weights for policy 0, policy_version 54951 (0.0022) [2023-03-09 08:41:55,064][23090] Updated weights for policy 0, policy_version 54961 (0.0019) [2023-03-09 08:41:56,031][23090] Updated weights for policy 0, policy_version 54972 (0.0020) [2023-03-09 08:41:56,731][23090] Updated weights for policy 0, policy_version 54982 (0.0018) [2023-03-09 08:41:57,674][23090] Updated weights for policy 0, policy_version 54992 (0.0015) [2023-03-09 08:41:58,538][23090] Updated weights for policy 0, policy_version 55002 (0.0018) [2023-03-09 08:41:59,059][22664] Fps is (10 sec: 198250.9, 60 sec: 198520.3, 300 sec: 198996.4). Total num frames: 901267456. Throughput: 0: 49594.1. Samples: 225280960. Policy #0 lag: (min: 1.0, avg: 16.2, max: 33.0) [2023-03-09 08:41:59,060][22664] Avg episode reward: [(0, '52.507')] [2023-03-09 08:41:59,219][22940] Signal inference workers to stop experience collection... (17800 times) [2023-03-09 08:41:59,220][22940] Signal inference workers to resume experience collection... (17800 times) [2023-03-09 08:41:59,288][23090] InferenceWorker_p0-w0: stopping experience collection (17800 times) [2023-03-09 08:41:59,288][23090] InferenceWorker_p0-w0: resuming experience collection (17800 times) [2023-03-09 08:41:59,290][23090] Updated weights for policy 0, policy_version 55012 (0.0013) [2023-03-09 08:42:00,208][23090] Updated weights for policy 0, policy_version 55022 (0.0013) [2023-03-09 08:42:00,987][23090] Updated weights for policy 0, policy_version 55032 (0.0019) [2023-03-09 08:42:01,800][23090] Updated weights for policy 0, policy_version 55042 (0.0023) [2023-03-09 08:42:02,650][23090] Updated weights for policy 0, policy_version 55052 (0.0018) [2023-03-09 08:42:03,483][23090] Updated weights for policy 0, policy_version 55062 (0.0013) [2023-03-09 08:42:04,058][22664] Fps is (10 sec: 196608.8, 60 sec: 198246.4, 300 sec: 198940.8). Total num frames: 902250496. Throughput: 0: 49594.4. Samples: 225577824. Policy #0 lag: (min: 1.0, avg: 16.2, max: 33.0) [2023-03-09 08:42:04,060][22664] Avg episode reward: [(0, '51.648')] [2023-03-09 08:42:04,360][23090] Updated weights for policy 0, policy_version 55073 (0.0013) [2023-03-09 08:42:05,234][23090] Updated weights for policy 0, policy_version 55083 (0.0013) [2023-03-09 08:42:06,049][23090] Updated weights for policy 0, policy_version 55093 (0.0016) [2023-03-09 08:42:06,775][23090] Updated weights for policy 0, policy_version 55103 (0.0015) [2023-03-09 08:42:07,658][23090] Updated weights for policy 0, policy_version 55113 (0.0017) [2023-03-09 08:42:08,536][23090] Updated weights for policy 0, policy_version 55123 (0.0019) [2023-03-09 08:42:09,059][22664] Fps is (10 sec: 196597.5, 60 sec: 197972.6, 300 sec: 198940.2). Total num frames: 903233536. Throughput: 0: 49593.7. Samples: 225874720. Policy #0 lag: (min: 1.0, avg: 16.2, max: 33.0) [2023-03-09 08:42:09,061][22664] Avg episode reward: [(0, '53.385')] [2023-03-09 08:42:09,300][23090] Updated weights for policy 0, policy_version 55133 (0.0013) [2023-03-09 08:42:10,113][23090] Updated weights for policy 0, policy_version 55143 (0.0020) [2023-03-09 08:42:10,961][23090] Updated weights for policy 0, policy_version 55153 (0.0019) [2023-03-09 08:42:11,826][23090] Updated weights for policy 0, policy_version 55163 (0.0021) [2023-03-09 08:42:12,620][23090] Updated weights for policy 0, policy_version 55173 (0.0013) [2023-03-09 08:42:13,521][23090] Updated weights for policy 0, policy_version 55183 (0.0018) [2023-03-09 08:42:14,059][22664] Fps is (10 sec: 198240.0, 60 sec: 198518.9, 300 sec: 198940.5). Total num frames: 904232960. Throughput: 0: 49594.6. Samples: 226024224. Policy #0 lag: (min: 1.0, avg: 16.2, max: 33.0) [2023-03-09 08:42:14,061][22664] Avg episode reward: [(0, '54.261')] [2023-03-09 08:42:14,331][23090] Updated weights for policy 0, policy_version 55193 (0.0017) [2023-03-09 08:42:14,413][22940] Signal inference workers to stop experience collection... (17850 times) [2023-03-09 08:42:14,425][22940] Signal inference workers to resume experience collection... (17850 times) [2023-03-09 08:42:14,492][23090] InferenceWorker_p0-w0: stopping experience collection (17850 times) [2023-03-09 08:42:14,492][23090] InferenceWorker_p0-w0: resuming experience collection (17850 times) [2023-03-09 08:42:15,135][23090] Updated weights for policy 0, policy_version 55203 (0.0016) [2023-03-09 08:42:16,019][23090] Updated weights for policy 0, policy_version 55213 (0.0019) [2023-03-09 08:42:16,772][23090] Updated weights for policy 0, policy_version 55223 (0.0019) [2023-03-09 08:42:17,560][23090] Updated weights for policy 0, policy_version 55233 (0.0013) [2023-03-09 08:42:18,428][23090] Updated weights for policy 0, policy_version 55243 (0.0022) [2023-03-09 08:42:19,058][22664] Fps is (10 sec: 198257.3, 60 sec: 197974.7, 300 sec: 198940.7). Total num frames: 905216000. Throughput: 0: 49596.4. Samples: 226321120. Policy #0 lag: (min: 2.0, avg: 17.4, max: 32.0) [2023-03-09 08:42:19,060][22664] Avg episode reward: [(0, '54.139')] [2023-03-09 08:42:19,257][23090] Updated weights for policy 0, policy_version 55253 (0.0015) [2023-03-09 08:42:19,989][23090] Updated weights for policy 0, policy_version 55263 (0.0021) [2023-03-09 08:42:20,834][23090] Updated weights for policy 0, policy_version 55273 (0.0019) [2023-03-09 08:42:21,712][23090] Updated weights for policy 0, policy_version 55283 (0.0016) [2023-03-09 08:42:22,490][23090] Updated weights for policy 0, policy_version 55293 (0.0014) [2023-03-09 08:42:23,233][23090] Updated weights for policy 0, policy_version 55303 (0.0024) [2023-03-09 08:42:24,059][22664] Fps is (10 sec: 198251.2, 60 sec: 198519.1, 300 sec: 198940.8). Total num frames: 906215424. Throughput: 0: 49640.2. Samples: 226620016. Policy #0 lag: (min: 2.0, avg: 17.4, max: 32.0) [2023-03-09 08:42:24,060][22664] Avg episode reward: [(0, '54.906')] [2023-03-09 08:42:24,151][23090] Updated weights for policy 0, policy_version 55313 (0.0016) [2023-03-09 08:42:25,037][23090] Updated weights for policy 0, policy_version 55324 (0.0017) [2023-03-09 08:42:25,825][23090] Updated weights for policy 0, policy_version 55334 (0.0017) [2023-03-09 08:42:26,743][23090] Updated weights for policy 0, policy_version 55344 (0.0013) [2023-03-09 08:42:27,579][23090] Updated weights for policy 0, policy_version 55354 (0.0013) [2023-03-09 08:42:28,355][23090] Updated weights for policy 0, policy_version 55364 (0.0013) [2023-03-09 08:42:28,690][22940] Signal inference workers to stop experience collection... (17900 times) [2023-03-09 08:42:28,690][22940] Signal inference workers to resume experience collection... (17900 times) [2023-03-09 08:42:28,779][23090] InferenceWorker_p0-w0: stopping experience collection (17900 times) [2023-03-09 08:42:28,780][23090] InferenceWorker_p0-w0: resuming experience collection (17900 times) [2023-03-09 08:42:29,059][22664] Fps is (10 sec: 198237.0, 60 sec: 198245.8, 300 sec: 198995.9). Total num frames: 907198464. Throughput: 0: 49593.1. Samples: 226767408. Policy #0 lag: (min: 2.0, avg: 17.4, max: 32.0) [2023-03-09 08:42:29,061][22664] Avg episode reward: [(0, '53.225')] [2023-03-09 08:42:29,256][23090] Updated weights for policy 0, policy_version 55374 (0.0016) [2023-03-09 08:42:30,042][23090] Updated weights for policy 0, policy_version 55384 (0.0017) [2023-03-09 08:42:30,849][23090] Updated weights for policy 0, policy_version 55394 (0.0020) [2023-03-09 08:42:31,850][23090] Updated weights for policy 0, policy_version 55405 (0.0016) [2023-03-09 08:42:32,619][23090] Updated weights for policy 0, policy_version 55415 (0.0016) [2023-03-09 08:42:33,399][23090] Updated weights for policy 0, policy_version 55425 (0.0019) [2023-03-09 08:42:34,059][22664] Fps is (10 sec: 199881.4, 60 sec: 198519.5, 300 sec: 198996.2). Total num frames: 908214272. Throughput: 0: 49639.8. Samples: 227066352. Policy #0 lag: (min: 2.0, avg: 17.4, max: 32.0) [2023-03-09 08:42:34,060][22664] Avg episode reward: [(0, '54.309')] [2023-03-09 08:42:34,281][23090] Updated weights for policy 0, policy_version 55435 (0.0016) [2023-03-09 08:42:35,089][23090] Updated weights for policy 0, policy_version 55445 (0.0019) [2023-03-09 08:42:35,824][23090] Updated weights for policy 0, policy_version 55455 (0.0019) [2023-03-09 08:42:36,662][23090] Updated weights for policy 0, policy_version 55465 (0.0013) [2023-03-09 08:42:37,548][23090] Updated weights for policy 0, policy_version 55475 (0.0013) [2023-03-09 08:42:38,347][23090] Updated weights for policy 0, policy_version 55485 (0.0013) [2023-03-09 08:42:39,058][22664] Fps is (10 sec: 201532.7, 60 sec: 198792.9, 300 sec: 198996.4). Total num frames: 909213696. Throughput: 0: 49594.4. Samples: 227363280. Policy #0 lag: (min: 2.0, avg: 17.4, max: 32.0) [2023-03-09 08:42:39,060][22664] Avg episode reward: [(0, '53.082')] [2023-03-09 08:42:39,121][23090] Updated weights for policy 0, policy_version 55495 (0.0020) [2023-03-09 08:42:39,992][23090] Updated weights for policy 0, policy_version 55505 (0.0017) [2023-03-09 08:42:40,849][23090] Updated weights for policy 0, policy_version 55515 (0.0016) [2023-03-09 08:42:41,625][23090] Updated weights for policy 0, policy_version 55525 (0.0018) [2023-03-09 08:42:42,554][23090] Updated weights for policy 0, policy_version 55535 (0.0018) [2023-03-09 08:42:43,322][23090] Updated weights for policy 0, policy_version 55545 (0.0013) [2023-03-09 08:42:44,059][22664] Fps is (10 sec: 198243.7, 60 sec: 198791.2, 300 sec: 198940.6). Total num frames: 910196736. Throughput: 0: 49595.0. Samples: 227512752. Policy #0 lag: (min: 2.0, avg: 17.4, max: 32.0) [2023-03-09 08:42:44,061][22664] Avg episode reward: [(0, '53.397')] [2023-03-09 08:42:44,165][23090] Updated weights for policy 0, policy_version 55555 (0.0018) [2023-03-09 08:42:44,267][22940] Signal inference workers to stop experience collection... (17950 times) [2023-03-09 08:42:44,268][22940] Signal inference workers to resume experience collection... (17950 times) [2023-03-09 08:42:44,329][23090] InferenceWorker_p0-w0: stopping experience collection (17950 times) [2023-03-09 08:42:44,329][23090] InferenceWorker_p0-w0: resuming experience collection (17950 times) [2023-03-09 08:42:45,016][23090] Updated weights for policy 0, policy_version 55565 (0.0023) [2023-03-09 08:42:45,800][23090] Updated weights for policy 0, policy_version 55575 (0.0020) [2023-03-09 08:42:46,579][23090] Updated weights for policy 0, policy_version 55585 (0.0016) [2023-03-09 08:42:47,454][23090] Updated weights for policy 0, policy_version 55595 (0.0021) [2023-03-09 08:42:48,305][23090] Updated weights for policy 0, policy_version 55605 (0.0016) [2023-03-09 08:42:49,036][23090] Updated weights for policy 0, policy_version 55615 (0.0012) [2023-03-09 08:42:49,059][22664] Fps is (10 sec: 198243.6, 60 sec: 198519.8, 300 sec: 198940.5). Total num frames: 911196160. Throughput: 0: 49640.4. Samples: 227811648. Policy #0 lag: (min: 2.0, avg: 17.4, max: 32.0) [2023-03-09 08:42:49,060][22664] Avg episode reward: [(0, '54.320')] [2023-03-09 08:42:49,908][23090] Updated weights for policy 0, policy_version 55625 (0.0013) [2023-03-09 08:42:50,801][23090] Updated weights for policy 0, policy_version 55635 (0.0017) [2023-03-09 08:42:51,549][23090] Updated weights for policy 0, policy_version 55645 (0.0022) [2023-03-09 08:42:52,286][23090] Updated weights for policy 0, policy_version 55655 (0.0015) [2023-03-09 08:42:53,241][23090] Updated weights for policy 0, policy_version 55665 (0.0017) [2023-03-09 08:42:54,058][22664] Fps is (10 sec: 196616.5, 60 sec: 197973.6, 300 sec: 198829.9). Total num frames: 912162816. Throughput: 0: 49641.5. Samples: 228108560. Policy #0 lag: (min: 1.0, avg: 17.5, max: 33.0) [2023-03-09 08:42:54,059][22664] Avg episode reward: [(0, '53.895')] [2023-03-09 08:42:54,102][23090] Updated weights for policy 0, policy_version 55675 (0.0013) [2023-03-09 08:42:54,826][23090] Updated weights for policy 0, policy_version 55685 (0.0022) [2023-03-09 08:42:55,707][23090] Updated weights for policy 0, policy_version 55695 (0.0017) [2023-03-09 08:42:56,558][23090] Updated weights for policy 0, policy_version 55705 (0.0013) [2023-03-09 08:42:57,402][23090] Updated weights for policy 0, policy_version 55716 (0.0022) [2023-03-09 08:42:58,283][23090] Updated weights for policy 0, policy_version 55726 (0.0021) [2023-03-09 08:42:58,505][22940] Signal inference workers to stop experience collection... (18000 times) [2023-03-09 08:42:58,506][22940] Signal inference workers to resume experience collection... (18000 times) [2023-03-09 08:42:58,571][23090] InferenceWorker_p0-w0: stopping experience collection (18000 times) [2023-03-09 08:42:58,574][23090] InferenceWorker_p0-w0: resuming experience collection (18000 times) [2023-03-09 08:42:59,059][22664] Fps is (10 sec: 198247.6, 60 sec: 198519.3, 300 sec: 198940.6). Total num frames: 913178624. Throughput: 0: 49639.7. Samples: 228258000. Policy #0 lag: (min: 1.0, avg: 17.5, max: 33.0) [2023-03-09 08:42:59,060][22664] Avg episode reward: [(0, '53.305')] [2023-03-09 08:42:59,068][23090] Updated weights for policy 0, policy_version 55736 (0.0019) [2023-03-09 08:42:59,863][23090] Updated weights for policy 0, policy_version 55746 (0.0017) [2023-03-09 08:43:00,752][23090] Updated weights for policy 0, policy_version 55756 (0.0013) [2023-03-09 08:43:01,545][23090] Updated weights for policy 0, policy_version 55766 (0.0018) [2023-03-09 08:43:02,363][23090] Updated weights for policy 0, policy_version 55776 (0.0015) [2023-03-09 08:43:03,128][23090] Updated weights for policy 0, policy_version 55786 (0.0017) [2023-03-09 08:43:04,037][23090] Updated weights for policy 0, policy_version 55796 (0.0013) [2023-03-09 08:43:04,058][22664] Fps is (10 sec: 199883.7, 60 sec: 198519.4, 300 sec: 198940.9). Total num frames: 914161664. Throughput: 0: 49639.1. Samples: 228554880. Policy #0 lag: (min: 1.0, avg: 17.5, max: 33.0) [2023-03-09 08:43:04,059][22664] Avg episode reward: [(0, '52.491')] [2023-03-09 08:43:04,781][23090] Updated weights for policy 0, policy_version 55806 (0.0019) [2023-03-09 08:43:05,649][23090] Updated weights for policy 0, policy_version 55816 (0.0020) [2023-03-09 08:43:06,442][23090] Updated weights for policy 0, policy_version 55826 (0.0018) [2023-03-09 08:43:07,294][23090] Updated weights for policy 0, policy_version 55837 (0.0019) [2023-03-09 08:43:08,080][23090] Updated weights for policy 0, policy_version 55847 (0.0018) [2023-03-09 08:43:08,968][23090] Updated weights for policy 0, policy_version 55857 (0.0020) [2023-03-09 08:43:09,059][22664] Fps is (10 sec: 199880.7, 60 sec: 199066.5, 300 sec: 199051.7). Total num frames: 915177472. Throughput: 0: 49730.3. Samples: 228857888. Policy #0 lag: (min: 1.0, avg: 17.5, max: 33.0) [2023-03-09 08:43:09,060][22664] Avg episode reward: [(0, '52.833')] [2023-03-09 08:43:09,799][23090] Updated weights for policy 0, policy_version 55867 (0.0019) [2023-03-09 08:43:10,542][23090] Updated weights for policy 0, policy_version 55877 (0.0015) [2023-03-09 08:43:10,842][22940] Signal inference workers to stop experience collection... (18050 times) [2023-03-09 08:43:10,843][22940] Signal inference workers to resume experience collection... (18050 times) [2023-03-09 08:43:10,903][23090] InferenceWorker_p0-w0: stopping experience collection (18050 times) [2023-03-09 08:43:10,903][23090] InferenceWorker_p0-w0: resuming experience collection (18050 times) [2023-03-09 08:43:11,462][23090] Updated weights for policy 0, policy_version 55887 (0.0018) [2023-03-09 08:43:12,355][23090] Updated weights for policy 0, policy_version 55897 (0.0013) [2023-03-09 08:43:13,116][23090] Updated weights for policy 0, policy_version 55907 (0.0019) [2023-03-09 08:43:13,997][23090] Updated weights for policy 0, policy_version 55917 (0.0013) [2023-03-09 08:43:14,058][22664] Fps is (10 sec: 199885.9, 60 sec: 198793.7, 300 sec: 198996.3). Total num frames: 916160512. Throughput: 0: 49776.9. Samples: 229007344. Policy #0 lag: (min: 1.0, avg: 17.5, max: 33.0) [2023-03-09 08:43:14,059][22664] Avg episode reward: [(0, '53.404')] [2023-03-09 08:43:14,737][23090] Updated weights for policy 0, policy_version 55927 (0.0016) [2023-03-09 08:43:15,617][23090] Updated weights for policy 0, policy_version 55938 (0.0013) [2023-03-09 08:43:16,536][23090] Updated weights for policy 0, policy_version 55948 (0.0027) [2023-03-09 08:43:17,301][23090] Updated weights for policy 0, policy_version 55958 (0.0016) [2023-03-09 08:43:18,132][23090] Updated weights for policy 0, policy_version 55968 (0.0016) [2023-03-09 08:43:18,881][23090] Updated weights for policy 0, policy_version 55978 (0.0016) [2023-03-09 08:43:19,059][22664] Fps is (10 sec: 198250.0, 60 sec: 199065.2, 300 sec: 198996.2). Total num frames: 917159936. Throughput: 0: 49686.2. Samples: 229302224. Policy #0 lag: (min: 1.0, avg: 17.5, max: 33.0) [2023-03-09 08:43:19,059][22664] Avg episode reward: [(0, '55.048')] [2023-03-09 08:43:19,064][22940] Saving /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000055979_917159936.pth... [2023-03-09 08:43:19,128][22940] Removing /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000053066_869433344.pth [2023-03-09 08:43:19,800][23090] Updated weights for policy 0, policy_version 55988 (0.0013) [2023-03-09 08:43:20,536][23090] Updated weights for policy 0, policy_version 55998 (0.0017) [2023-03-09 08:43:21,447][23090] Updated weights for policy 0, policy_version 56008 (0.0021) [2023-03-09 08:43:22,258][23090] Updated weights for policy 0, policy_version 56018 (0.0016) [2023-03-09 08:43:23,070][22940] Signal inference workers to stop experience collection... (18100 times) [2023-03-09 08:43:23,091][22940] Signal inference workers to resume experience collection... (18100 times) [2023-03-09 08:43:23,103][23090] Updated weights for policy 0, policy_version 56028 (0.0016) [2023-03-09 08:43:23,143][23090] InferenceWorker_p0-w0: stopping experience collection (18100 times) [2023-03-09 08:43:23,143][23090] InferenceWorker_p0-w0: resuming experience collection (18100 times) [2023-03-09 08:43:23,828][23090] Updated weights for policy 0, policy_version 56038 (0.0018) [2023-03-09 08:43:24,058][22664] Fps is (10 sec: 199883.9, 60 sec: 199065.9, 300 sec: 198996.4). Total num frames: 918159360. Throughput: 0: 49776.4. Samples: 229603216. Policy #0 lag: (min: 1.0, avg: 17.5, max: 33.0) [2023-03-09 08:43:24,059][22664] Avg episode reward: [(0, '54.928')] [2023-03-09 08:43:24,728][23090] Updated weights for policy 0, policy_version 56048 (0.0013) [2023-03-09 08:43:25,605][23090] Updated weights for policy 0, policy_version 56058 (0.0016) [2023-03-09 08:43:26,345][23090] Updated weights for policy 0, policy_version 56068 (0.0018) [2023-03-09 08:43:27,233][23090] Updated weights for policy 0, policy_version 56078 (0.0022) [2023-03-09 08:43:28,075][23090] Updated weights for policy 0, policy_version 56088 (0.0013) [2023-03-09 08:43:28,815][23090] Updated weights for policy 0, policy_version 56098 (0.0013) [2023-03-09 08:43:29,059][22664] Fps is (10 sec: 199885.6, 60 sec: 199340.0, 300 sec: 198996.2). Total num frames: 919158784. Throughput: 0: 49776.7. Samples: 229752688. Policy #0 lag: (min: 1.0, avg: 16.0, max: 33.0) [2023-03-09 08:43:29,060][22664] Avg episode reward: [(0, '51.993')] [2023-03-09 08:43:29,761][23090] Updated weights for policy 0, policy_version 56108 (0.0020) [2023-03-09 08:43:30,504][23090] Updated weights for policy 0, policy_version 56118 (0.0017) [2023-03-09 08:43:31,429][23090] Updated weights for policy 0, policy_version 56129 (0.0020) [2023-03-09 08:43:32,225][23090] Updated weights for policy 0, policy_version 56139 (0.0017) [2023-03-09 08:43:33,064][23090] Updated weights for policy 0, policy_version 56149 (0.0013) [2023-03-09 08:43:33,803][23090] Updated weights for policy 0, policy_version 56159 (0.0020) [2023-03-09 08:43:34,058][22664] Fps is (10 sec: 198246.4, 60 sec: 198793.4, 300 sec: 198996.2). Total num frames: 920141824. Throughput: 0: 49731.7. Samples: 230049568. Policy #0 lag: (min: 1.0, avg: 16.0, max: 33.0) [2023-03-09 08:43:34,060][22664] Avg episode reward: [(0, '53.162')] [2023-03-09 08:43:34,650][23090] Updated weights for policy 0, policy_version 56169 (0.0020) [2023-03-09 08:43:35,542][23090] Updated weights for policy 0, policy_version 56179 (0.0013) [2023-03-09 08:43:36,347][23090] Updated weights for policy 0, policy_version 56189 (0.0020) [2023-03-09 08:43:36,597][22940] Signal inference workers to stop experience collection... (18150 times) [2023-03-09 08:43:36,598][22940] Signal inference workers to resume experience collection... (18150 times) [2023-03-09 08:43:36,662][23090] InferenceWorker_p0-w0: stopping experience collection (18150 times) [2023-03-09 08:43:36,662][23090] InferenceWorker_p0-w0: resuming experience collection (18150 times) [2023-03-09 08:43:37,108][23090] Updated weights for policy 0, policy_version 56199 (0.0021) [2023-03-09 08:43:38,007][23090] Updated weights for policy 0, policy_version 56209 (0.0017) [2023-03-09 08:43:38,808][23090] Updated weights for policy 0, policy_version 56219 (0.0018) [2023-03-09 08:43:39,059][22664] Fps is (10 sec: 199878.5, 60 sec: 199064.4, 300 sec: 199051.5). Total num frames: 921157632. Throughput: 0: 49777.0. Samples: 230348544. Policy #0 lag: (min: 1.0, avg: 16.0, max: 33.0) [2023-03-09 08:43:39,061][22664] Avg episode reward: [(0, '54.379')] [2023-03-09 08:43:39,573][23090] Updated weights for policy 0, policy_version 56229 (0.0013) [2023-03-09 08:43:40,462][23090] Updated weights for policy 0, policy_version 56239 (0.0013) [2023-03-09 08:43:41,341][23090] Updated weights for policy 0, policy_version 56249 (0.0017) [2023-03-09 08:43:42,076][23090] Updated weights for policy 0, policy_version 56259 (0.0013) [2023-03-09 08:43:42,988][23090] Updated weights for policy 0, policy_version 56269 (0.0018) [2023-03-09 08:43:43,797][23090] Updated weights for policy 0, policy_version 56279 (0.0013) [2023-03-09 08:43:44,059][22664] Fps is (10 sec: 198246.3, 60 sec: 198793.8, 300 sec: 198940.6). Total num frames: 922124288. Throughput: 0: 49778.2. Samples: 230498016. Policy #0 lag: (min: 1.0, avg: 16.0, max: 33.0) [2023-03-09 08:43:44,060][22664] Avg episode reward: [(0, '51.914')] [2023-03-09 08:43:44,581][23090] Updated weights for policy 0, policy_version 56289 (0.0016) [2023-03-09 08:43:45,399][23090] Updated weights for policy 0, policy_version 56299 (0.0017) [2023-03-09 08:43:46,298][23090] Updated weights for policy 0, policy_version 56309 (0.0017) [2023-03-09 08:43:47,014][23090] Updated weights for policy 0, policy_version 56319 (0.0013) [2023-03-09 08:43:47,828][23090] Updated weights for policy 0, policy_version 56329 (0.0013) [2023-03-09 08:43:48,748][23090] Updated weights for policy 0, policy_version 56339 (0.0016) [2023-03-09 08:43:49,059][22664] Fps is (10 sec: 194976.3, 60 sec: 198519.8, 300 sec: 198940.8). Total num frames: 923107328. Throughput: 0: 49822.6. Samples: 230796896. Policy #0 lag: (min: 1.0, avg: 16.0, max: 33.0) [2023-03-09 08:43:49,059][22664] Avg episode reward: [(0, '53.908')] [2023-03-09 08:43:49,505][23090] Updated weights for policy 0, policy_version 56349 (0.0013) [2023-03-09 08:43:49,598][22940] Signal inference workers to stop experience collection... (18200 times) [2023-03-09 08:43:49,599][22940] Signal inference workers to resume experience collection... (18200 times) [2023-03-09 08:43:49,664][23090] InferenceWorker_p0-w0: stopping experience collection (18200 times) [2023-03-09 08:43:49,664][23090] InferenceWorker_p0-w0: resuming experience collection (18200 times) [2023-03-09 08:43:50,305][23090] Updated weights for policy 0, policy_version 56359 (0.0019) [2023-03-09 08:43:51,158][23090] Updated weights for policy 0, policy_version 56369 (0.0021) [2023-03-09 08:43:52,014][23090] Updated weights for policy 0, policy_version 56379 (0.0016) [2023-03-09 08:43:52,774][23090] Updated weights for policy 0, policy_version 56389 (0.0018) [2023-03-09 08:43:53,658][23090] Updated weights for policy 0, policy_version 56399 (0.0013) [2023-03-09 08:43:54,058][22664] Fps is (10 sec: 198247.3, 60 sec: 199065.6, 300 sec: 198940.8). Total num frames: 924106752. Throughput: 0: 49687.8. Samples: 231093824. Policy #0 lag: (min: 1.0, avg: 16.0, max: 33.0) [2023-03-09 08:43:54,060][22664] Avg episode reward: [(0, '53.458')] [2023-03-09 08:43:54,498][23090] Updated weights for policy 0, policy_version 56409 (0.0013) [2023-03-09 08:43:55,337][23090] Updated weights for policy 0, policy_version 56420 (0.0017) [2023-03-09 08:43:56,231][23090] Updated weights for policy 0, policy_version 56430 (0.0022) [2023-03-09 08:43:57,063][23090] Updated weights for policy 0, policy_version 56440 (0.0016) [2023-03-09 08:43:57,798][23090] Updated weights for policy 0, policy_version 56450 (0.0015) [2023-03-09 08:43:58,686][23090] Updated weights for policy 0, policy_version 56460 (0.0018) [2023-03-09 08:43:59,058][22664] Fps is (10 sec: 201523.9, 60 sec: 199065.9, 300 sec: 198940.7). Total num frames: 925122560. Throughput: 0: 49686.7. Samples: 231243248. Policy #0 lag: (min: 1.0, avg: 16.0, max: 33.0) [2023-03-09 08:43:59,060][22664] Avg episode reward: [(0, '51.941')] [2023-03-09 08:43:59,532][23090] Updated weights for policy 0, policy_version 56470 (0.0027) [2023-03-09 08:44:00,337][23090] Updated weights for policy 0, policy_version 56480 (0.0017) [2023-03-09 08:44:01,073][23090] Updated weights for policy 0, policy_version 56490 (0.0013) [2023-03-09 08:44:02,000][23090] Updated weights for policy 0, policy_version 56500 (0.0013) [2023-03-09 08:44:02,738][23090] Updated weights for policy 0, policy_version 56510 (0.0016) [2023-03-09 08:44:03,565][23090] Updated weights for policy 0, policy_version 56520 (0.0016) [2023-03-09 08:44:04,059][22664] Fps is (10 sec: 199879.5, 60 sec: 199064.9, 300 sec: 198940.5). Total num frames: 926105600. Throughput: 0: 49778.0. Samples: 231542240. Policy #0 lag: (min: 1.0, avg: 16.2, max: 33.0) [2023-03-09 08:44:04,060][22664] Avg episode reward: [(0, '50.890')] [2023-03-09 08:44:04,416][23090] Updated weights for policy 0, policy_version 56530 (0.0021) [2023-03-09 08:44:05,249][23090] Updated weights for policy 0, policy_version 56540 (0.0016) [2023-03-09 08:44:05,372][22940] Signal inference workers to stop experience collection... (18250 times) [2023-03-09 08:44:05,384][22940] Signal inference workers to resume experience collection... (18250 times) [2023-03-09 08:44:05,447][23090] InferenceWorker_p0-w0: stopping experience collection (18250 times) [2023-03-09 08:44:05,450][23090] InferenceWorker_p0-w0: resuming experience collection (18250 times) [2023-03-09 08:44:06,012][23090] Updated weights for policy 0, policy_version 56550 (0.0022) [2023-03-09 08:44:06,866][23090] Updated weights for policy 0, policy_version 56560 (0.0016) [2023-03-09 08:44:07,748][23090] Updated weights for policy 0, policy_version 56570 (0.0018) [2023-03-09 08:44:08,495][23090] Updated weights for policy 0, policy_version 56580 (0.0018) [2023-03-09 08:44:09,059][22664] Fps is (10 sec: 198240.6, 60 sec: 198792.5, 300 sec: 198996.2). Total num frames: 927105024. Throughput: 0: 49732.7. Samples: 231841200. Policy #0 lag: (min: 1.0, avg: 16.2, max: 33.0) [2023-03-09 08:44:09,105][22664] Avg episode reward: [(0, '53.222')] [2023-03-09 08:44:09,376][23090] Updated weights for policy 0, policy_version 56590 (0.0013) [2023-03-09 08:44:10,230][23090] Updated weights for policy 0, policy_version 56600 (0.0019) [2023-03-09 08:44:10,963][23090] Updated weights for policy 0, policy_version 56610 (0.0021) [2023-03-09 08:44:11,885][23090] Updated weights for policy 0, policy_version 56620 (0.0016) [2023-03-09 08:44:12,690][23090] Updated weights for policy 0, policy_version 56630 (0.0018) [2023-03-09 08:44:13,505][23090] Updated weights for policy 0, policy_version 56640 (0.0013) [2023-03-09 08:44:14,059][22664] Fps is (10 sec: 199883.1, 60 sec: 199064.4, 300 sec: 198940.8). Total num frames: 928104448. Throughput: 0: 49686.8. Samples: 231988608. Policy #0 lag: (min: 1.0, avg: 16.2, max: 33.0) [2023-03-09 08:44:14,061][22664] Avg episode reward: [(0, '52.096')] [2023-03-09 08:44:14,261][23090] Updated weights for policy 0, policy_version 56650 (0.0013) [2023-03-09 08:44:15,181][23090] Updated weights for policy 0, policy_version 56660 (0.0013) [2023-03-09 08:44:15,923][23090] Updated weights for policy 0, policy_version 56670 (0.0016) [2023-03-09 08:44:16,768][23090] Updated weights for policy 0, policy_version 56680 (0.0019) [2023-03-09 08:44:17,616][23090] Updated weights for policy 0, policy_version 56690 (0.0018) [2023-03-09 08:44:18,462][23090] Updated weights for policy 0, policy_version 56700 (0.0014) [2023-03-09 08:44:19,059][22664] Fps is (10 sec: 198247.6, 60 sec: 198792.1, 300 sec: 198884.9). Total num frames: 929087488. Throughput: 0: 49687.9. Samples: 232285536. Policy #0 lag: (min: 1.0, avg: 16.2, max: 33.0) [2023-03-09 08:44:19,061][22664] Avg episode reward: [(0, '52.785')] [2023-03-09 08:44:19,336][23090] Updated weights for policy 0, policy_version 56711 (0.0013) [2023-03-09 08:44:20,185][23090] Updated weights for policy 0, policy_version 56721 (0.0027) [2023-03-09 08:44:21,004][23090] Updated weights for policy 0, policy_version 56731 (0.0013) [2023-03-09 08:44:21,790][23090] Updated weights for policy 0, policy_version 56741 (0.0017) [2023-03-09 08:44:22,096][22940] Signal inference workers to stop experience collection... (18300 times) [2023-03-09 08:44:22,113][22940] Signal inference workers to resume experience collection... (18300 times) [2023-03-09 08:44:22,141][23090] InferenceWorker_p0-w0: stopping experience collection (18300 times) [2023-03-09 08:44:22,179][23090] InferenceWorker_p0-w0: resuming experience collection (18300 times) [2023-03-09 08:44:22,625][23090] Updated weights for policy 0, policy_version 56751 (0.0013) [2023-03-09 08:44:23,512][23090] Updated weights for policy 0, policy_version 56761 (0.0013) [2023-03-09 08:44:24,058][22664] Fps is (10 sec: 198253.5, 60 sec: 198792.7, 300 sec: 198885.3). Total num frames: 930086912. Throughput: 0: 49734.1. Samples: 232586560. Policy #0 lag: (min: 1.0, avg: 16.2, max: 33.0) [2023-03-09 08:44:24,059][22664] Avg episode reward: [(0, '52.213')] [2023-03-09 08:44:24,236][23090] Updated weights for policy 0, policy_version 56771 (0.0012) [2023-03-09 08:44:25,122][23090] Updated weights for policy 0, policy_version 56781 (0.0018) [2023-03-09 08:44:25,949][23090] Updated weights for policy 0, policy_version 56791 (0.0015) [2023-03-09 08:44:26,723][23090] Updated weights for policy 0, policy_version 56801 (0.0014) [2023-03-09 08:44:27,608][23090] Updated weights for policy 0, policy_version 56811 (0.0016) [2023-03-09 08:44:28,470][23090] Updated weights for policy 0, policy_version 56821 (0.0016) [2023-03-09 08:44:29,059][22664] Fps is (10 sec: 199883.8, 60 sec: 198791.8, 300 sec: 198940.5). Total num frames: 931086336. Throughput: 0: 49733.0. Samples: 232736016. Policy #0 lag: (min: 1.0, avg: 16.2, max: 33.0) [2023-03-09 08:44:29,060][22664] Avg episode reward: [(0, '52.102')] [2023-03-09 08:44:29,171][23090] Updated weights for policy 0, policy_version 56831 (0.0013) [2023-03-09 08:44:30,010][23090] Updated weights for policy 0, policy_version 56841 (0.0017) [2023-03-09 08:44:30,908][23090] Updated weights for policy 0, policy_version 56851 (0.0013) [2023-03-09 08:44:31,713][23090] Updated weights for policy 0, policy_version 56861 (0.0013) [2023-03-09 08:44:32,474][23090] Updated weights for policy 0, policy_version 56871 (0.0016) [2023-03-09 08:44:33,336][23090] Updated weights for policy 0, policy_version 56881 (0.0019) [2023-03-09 08:44:34,058][22664] Fps is (10 sec: 198246.2, 60 sec: 198792.6, 300 sec: 198885.1). Total num frames: 932069376. Throughput: 0: 49734.5. Samples: 233034944. Policy #0 lag: (min: 1.0, avg: 16.2, max: 33.0) [2023-03-09 08:44:34,059][22664] Avg episode reward: [(0, '53.203')] [2023-03-09 08:44:34,162][23090] Updated weights for policy 0, policy_version 56891 (0.0016) [2023-03-09 08:44:35,003][23090] Updated weights for policy 0, policy_version 56902 (0.0017) [2023-03-09 08:44:35,892][23090] Updated weights for policy 0, policy_version 56912 (0.0013) [2023-03-09 08:44:36,744][23090] Updated weights for policy 0, policy_version 56922 (0.0013) [2023-03-09 08:44:37,504][23090] Updated weights for policy 0, policy_version 56932 (0.0016) [2023-03-09 08:44:38,310][22940] Signal inference workers to stop experience collection... (18350 times) [2023-03-09 08:44:38,322][22940] Signal inference workers to resume experience collection... (18350 times) [2023-03-09 08:44:38,387][23090] InferenceWorker_p0-w0: stopping experience collection (18350 times) [2023-03-09 08:44:38,388][23090] InferenceWorker_p0-w0: resuming experience collection (18350 times) [2023-03-09 08:44:38,394][23090] Updated weights for policy 0, policy_version 56942 (0.0026) [2023-03-09 08:44:39,058][22664] Fps is (10 sec: 196614.0, 60 sec: 198247.7, 300 sec: 198885.3). Total num frames: 933052416. Throughput: 0: 49732.6. Samples: 233331792. Policy #0 lag: (min: 1.0, avg: 17.3, max: 34.0) [2023-03-09 08:44:39,059][22664] Avg episode reward: [(0, '54.422')] [2023-03-09 08:44:39,236][23090] Updated weights for policy 0, policy_version 56952 (0.0013) [2023-03-09 08:44:40,046][23090] Updated weights for policy 0, policy_version 56962 (0.0013) [2023-03-09 08:44:40,867][23090] Updated weights for policy 0, policy_version 56972 (0.0015) [2023-03-09 08:44:41,710][23090] Updated weights for policy 0, policy_version 56982 (0.0016) [2023-03-09 08:44:42,517][23090] Updated weights for policy 0, policy_version 56992 (0.0016) [2023-03-09 08:44:43,249][23090] Updated weights for policy 0, policy_version 57002 (0.0022) [2023-03-09 08:44:44,059][22664] Fps is (10 sec: 199877.8, 60 sec: 199064.5, 300 sec: 198940.7). Total num frames: 934068224. Throughput: 0: 49734.0. Samples: 233481296. Policy #0 lag: (min: 1.0, avg: 17.3, max: 34.0) [2023-03-09 08:44:44,061][22664] Avg episode reward: [(0, '54.786')] [2023-03-09 08:44:44,202][23090] Updated weights for policy 0, policy_version 57012 (0.0017) [2023-03-09 08:44:44,976][23090] Updated weights for policy 0, policy_version 57023 (0.0013) [2023-03-09 08:44:45,816][23090] Updated weights for policy 0, policy_version 57033 (0.0013) [2023-03-09 08:44:46,697][23090] Updated weights for policy 0, policy_version 57043 (0.0017) [2023-03-09 08:44:47,450][23090] Updated weights for policy 0, policy_version 57053 (0.0019) [2023-03-09 08:44:48,362][23090] Updated weights for policy 0, policy_version 57064 (0.0013) [2023-03-09 08:44:49,059][22664] Fps is (10 sec: 201522.1, 60 sec: 199338.7, 300 sec: 198885.1). Total num frames: 935067648. Throughput: 0: 49733.9. Samples: 233780256. Policy #0 lag: (min: 1.0, avg: 17.3, max: 34.0) [2023-03-09 08:44:49,060][22664] Avg episode reward: [(0, '53.111')] [2023-03-09 08:44:49,225][23090] Updated weights for policy 0, policy_version 57074 (0.0016) [2023-03-09 08:44:50,045][23090] Updated weights for policy 0, policy_version 57084 (0.0013) [2023-03-09 08:44:50,059][22940] Signal inference workers to stop experience collection... (18400 times) [2023-03-09 08:44:50,060][22940] Signal inference workers to resume experience collection... (18400 times) [2023-03-09 08:44:50,122][23090] InferenceWorker_p0-w0: stopping experience collection (18400 times) [2023-03-09 08:44:50,123][23090] InferenceWorker_p0-w0: resuming experience collection (18400 times) [2023-03-09 08:44:50,780][23090] Updated weights for policy 0, policy_version 57094 (0.0020) [2023-03-09 08:44:51,808][23090] Updated weights for policy 0, policy_version 57105 (0.0016) [2023-03-09 08:44:52,584][23090] Updated weights for policy 0, policy_version 57115 (0.0013) [2023-03-09 08:44:53,409][23090] Updated weights for policy 0, policy_version 57125 (0.0017) [2023-03-09 08:44:54,059][22664] Fps is (10 sec: 198247.9, 60 sec: 199064.7, 300 sec: 198829.6). Total num frames: 936050688. Throughput: 0: 49688.2. Samples: 234077168. Policy #0 lag: (min: 1.0, avg: 17.3, max: 34.0) [2023-03-09 08:44:54,060][22664] Avg episode reward: [(0, '51.546')] [2023-03-09 08:44:54,323][23090] Updated weights for policy 0, policy_version 57135 (0.0020) [2023-03-09 08:44:55,178][23090] Updated weights for policy 0, policy_version 57145 (0.0017) [2023-03-09 08:44:55,895][23090] Updated weights for policy 0, policy_version 57155 (0.0015) [2023-03-09 08:44:56,815][23090] Updated weights for policy 0, policy_version 57165 (0.0015) [2023-03-09 08:44:57,568][23090] Updated weights for policy 0, policy_version 57175 (0.0019) [2023-03-09 08:44:58,373][23090] Updated weights for policy 0, policy_version 57185 (0.0013) [2023-03-09 08:44:59,059][22664] Fps is (10 sec: 199884.5, 60 sec: 199065.4, 300 sec: 198996.2). Total num frames: 937066496. Throughput: 0: 49734.4. Samples: 234226640. Policy #0 lag: (min: 1.0, avg: 17.3, max: 34.0) [2023-03-09 08:44:59,059][22664] Avg episode reward: [(0, '54.176')] [2023-03-09 08:44:59,223][23090] Updated weights for policy 0, policy_version 57195 (0.0013) [2023-03-09 08:45:00,107][23090] Updated weights for policy 0, policy_version 57205 (0.0018) [2023-03-09 08:45:00,949][23090] Updated weights for policy 0, policy_version 57216 (0.0013) [2023-03-09 08:45:01,652][22940] Signal inference workers to stop experience collection... (18450 times) [2023-03-09 08:45:01,653][22940] Signal inference workers to resume experience collection... (18450 times) [2023-03-09 08:45:01,714][23090] InferenceWorker_p0-w0: stopping experience collection (18450 times) [2023-03-09 08:45:01,714][23090] InferenceWorker_p0-w0: resuming experience collection (18450 times) [2023-03-09 08:45:01,716][23090] Updated weights for policy 0, policy_version 57226 (0.0013) [2023-03-09 08:45:02,625][23090] Updated weights for policy 0, policy_version 57236 (0.0016) [2023-03-09 08:45:03,363][23090] Updated weights for policy 0, policy_version 57246 (0.0016) [2023-03-09 08:45:04,059][22664] Fps is (10 sec: 199886.2, 60 sec: 199065.8, 300 sec: 198829.4). Total num frames: 938049536. Throughput: 0: 49778.5. Samples: 234525568. Policy #0 lag: (min: 1.0, avg: 17.3, max: 34.0) [2023-03-09 08:45:04,060][22664] Avg episode reward: [(0, '52.105')] [2023-03-09 08:45:04,168][23090] Updated weights for policy 0, policy_version 57256 (0.0017) [2023-03-09 08:45:05,031][23090] Updated weights for policy 0, policy_version 57266 (0.0016) [2023-03-09 08:45:05,838][23090] Updated weights for policy 0, policy_version 57276 (0.0013) [2023-03-09 08:45:06,594][23090] Updated weights for policy 0, policy_version 57286 (0.0018) [2023-03-09 08:45:07,525][23090] Updated weights for policy 0, policy_version 57296 (0.0013) [2023-03-09 08:45:08,379][23090] Updated weights for policy 0, policy_version 57307 (0.0016) [2023-03-09 08:45:09,059][22664] Fps is (10 sec: 198240.4, 60 sec: 199065.4, 300 sec: 198829.4). Total num frames: 939048960. Throughput: 0: 49731.1. Samples: 234824480. Policy #0 lag: (min: 1.0, avg: 17.3, max: 34.0) [2023-03-09 08:45:09,061][22664] Avg episode reward: [(0, '51.962')] [2023-03-09 08:45:09,181][23090] Updated weights for policy 0, policy_version 57317 (0.0020) [2023-03-09 08:45:10,102][23090] Updated weights for policy 0, policy_version 57327 (0.0019) [2023-03-09 08:45:10,914][23090] Updated weights for policy 0, policy_version 57337 (0.0016) [2023-03-09 08:45:11,679][23090] Updated weights for policy 0, policy_version 57347 (0.0017) [2023-03-09 08:45:12,574][23090] Updated weights for policy 0, policy_version 57357 (0.0018) [2023-03-09 08:45:13,404][23090] Updated weights for policy 0, policy_version 57367 (0.0013) [2023-03-09 08:45:14,059][22664] Fps is (10 sec: 198246.8, 60 sec: 198793.1, 300 sec: 198829.4). Total num frames: 940032000. Throughput: 0: 49686.5. Samples: 234971904. Policy #0 lag: (min: 0.0, avg: 17.5, max: 34.0) [2023-03-09 08:45:14,060][22664] Avg episode reward: [(0, '54.472')] [2023-03-09 08:45:14,203][23090] Updated weights for policy 0, policy_version 57377 (0.0016) [2023-03-09 08:45:14,422][22940] Signal inference workers to stop experience collection... (18500 times) [2023-03-09 08:45:14,423][22940] Signal inference workers to resume experience collection... (18500 times) [2023-03-09 08:45:14,485][23090] InferenceWorker_p0-w0: stopping experience collection (18500 times) [2023-03-09 08:45:14,486][23090] InferenceWorker_p0-w0: resuming experience collection (18500 times) [2023-03-09 08:45:15,056][23090] Updated weights for policy 0, policy_version 57387 (0.0019) [2023-03-09 08:45:15,903][23090] Updated weights for policy 0, policy_version 57397 (0.0016) [2023-03-09 08:45:16,595][23090] Updated weights for policy 0, policy_version 57407 (0.0021) [2023-03-09 08:45:17,482][23090] Updated weights for policy 0, policy_version 57417 (0.0019) [2023-03-09 08:45:18,331][23090] Updated weights for policy 0, policy_version 57427 (0.0013) [2023-03-09 08:45:19,059][22664] Fps is (10 sec: 198248.2, 60 sec: 199065.5, 300 sec: 198884.9). Total num frames: 941031424. Throughput: 0: 49685.7. Samples: 235270816. Policy #0 lag: (min: 0.0, avg: 17.5, max: 34.0) [2023-03-09 08:45:19,060][22664] Avg episode reward: [(0, '55.451')] [2023-03-09 08:45:19,105][22940] Saving /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000057437_941047808.pth... [2023-03-09 08:45:19,167][22940] Removing /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000054525_893337600.pth [2023-03-09 08:45:19,259][23090] Updated weights for policy 0, policy_version 57438 (0.0021) [2023-03-09 08:45:20,028][23090] Updated weights for policy 0, policy_version 57448 (0.0013) [2023-03-09 08:45:20,919][23090] Updated weights for policy 0, policy_version 57458 (0.0019) [2023-03-09 08:45:21,691][23090] Updated weights for policy 0, policy_version 57468 (0.0013) [2023-03-09 08:45:22,451][23090] Updated weights for policy 0, policy_version 57478 (0.0018) [2023-03-09 08:45:23,408][23090] Updated weights for policy 0, policy_version 57488 (0.0016) [2023-03-09 08:45:24,059][22664] Fps is (10 sec: 198243.8, 60 sec: 198791.5, 300 sec: 198718.5). Total num frames: 942014464. Throughput: 0: 49687.5. Samples: 235567744. Policy #0 lag: (min: 0.0, avg: 17.5, max: 34.0) [2023-03-09 08:45:24,061][22664] Avg episode reward: [(0, '53.279')] [2023-03-09 08:45:24,265][23090] Updated weights for policy 0, policy_version 57498 (0.0016) [2023-03-09 08:45:25,015][23090] Updated weights for policy 0, policy_version 57508 (0.0021) [2023-03-09 08:45:25,895][23090] Updated weights for policy 0, policy_version 57518 (0.0015) [2023-03-09 08:45:26,716][23090] Updated weights for policy 0, policy_version 57528 (0.0016) [2023-03-09 08:45:27,519][23090] Updated weights for policy 0, policy_version 57538 (0.0013) [2023-03-09 08:45:28,367][23090] Updated weights for policy 0, policy_version 57548 (0.0013) [2023-03-09 08:45:29,059][22664] Fps is (10 sec: 194969.2, 60 sec: 198246.4, 300 sec: 198662.9). Total num frames: 942981120. Throughput: 0: 49640.6. Samples: 235715120. Policy #0 lag: (min: 0.0, avg: 17.5, max: 34.0) [2023-03-09 08:45:29,061][22664] Avg episode reward: [(0, '52.560')] [2023-03-09 08:45:29,289][23090] Updated weights for policy 0, policy_version 57559 (0.0013) [2023-03-09 08:45:30,065][23090] Updated weights for policy 0, policy_version 57569 (0.0016) [2023-03-09 08:45:30,161][22940] Signal inference workers to stop experience collection... (18550 times) [2023-03-09 08:45:30,162][22940] Signal inference workers to resume experience collection... (18550 times) [2023-03-09 08:45:30,227][23090] InferenceWorker_p0-w0: stopping experience collection (18550 times) [2023-03-09 08:45:30,227][23090] InferenceWorker_p0-w0: resuming experience collection (18550 times) [2023-03-09 08:45:30,941][23090] Updated weights for policy 0, policy_version 57579 (0.0017) [2023-03-09 08:45:31,792][23090] Updated weights for policy 0, policy_version 57589 (0.0013) [2023-03-09 08:45:32,542][23090] Updated weights for policy 0, policy_version 57599 (0.0013) [2023-03-09 08:45:33,355][23090] Updated weights for policy 0, policy_version 57609 (0.0015) [2023-03-09 08:45:34,059][22664] Fps is (10 sec: 198250.8, 60 sec: 198792.2, 300 sec: 198663.0). Total num frames: 943996928. Throughput: 0: 49640.1. Samples: 236014064. Policy #0 lag: (min: 0.0, avg: 17.5, max: 34.0) [2023-03-09 08:45:34,060][22664] Avg episode reward: [(0, '53.681')] [2023-03-09 08:45:34,233][23090] Updated weights for policy 0, policy_version 57619 (0.0016) [2023-03-09 08:45:34,989][23090] Updated weights for policy 0, policy_version 57629 (0.0016) [2023-03-09 08:45:35,764][23090] Updated weights for policy 0, policy_version 57639 (0.0019) [2023-03-09 08:45:36,771][23090] Updated weights for policy 0, policy_version 57650 (0.0016) [2023-03-09 08:45:37,560][23090] Updated weights for policy 0, policy_version 57660 (0.0022) [2023-03-09 08:45:38,293][23090] Updated weights for policy 0, policy_version 57670 (0.0017) [2023-03-09 08:45:39,059][22664] Fps is (10 sec: 201513.4, 60 sec: 199063.0, 300 sec: 198773.6). Total num frames: 944996352. Throughput: 0: 49684.8. Samples: 236313008. Policy #0 lag: (min: 0.0, avg: 17.5, max: 34.0) [2023-03-09 08:45:39,062][22664] Avg episode reward: [(0, '50.575')] [2023-03-09 08:45:39,225][23090] Updated weights for policy 0, policy_version 57680 (0.0013) [2023-03-09 08:45:40,113][23090] Updated weights for policy 0, policy_version 57690 (0.0013) [2023-03-09 08:45:40,809][23090] Updated weights for policy 0, policy_version 57700 (0.0018) [2023-03-09 08:45:41,703][23090] Updated weights for policy 0, policy_version 57710 (0.0016) [2023-03-09 08:45:42,574][23090] Updated weights for policy 0, policy_version 57720 (0.0016) [2023-03-09 08:45:43,308][23090] Updated weights for policy 0, policy_version 57730 (0.0013) [2023-03-09 08:45:44,059][22664] Fps is (10 sec: 198246.4, 60 sec: 198520.3, 300 sec: 198662.9). Total num frames: 945979392. Throughput: 0: 49684.9. Samples: 236462464. Policy #0 lag: (min: 0.0, avg: 17.5, max: 34.0) [2023-03-09 08:45:44,060][22664] Avg episode reward: [(0, '53.653')] [2023-03-09 08:45:44,187][23090] Updated weights for policy 0, policy_version 57740 (0.0015) [2023-03-09 08:45:44,608][22940] Signal inference workers to stop experience collection... (18600 times) [2023-03-09 08:45:44,611][22940] Signal inference workers to resume experience collection... (18600 times) [2023-03-09 08:45:44,673][23090] InferenceWorker_p0-w0: stopping experience collection (18600 times) [2023-03-09 08:45:44,673][23090] InferenceWorker_p0-w0: resuming experience collection (18600 times) [2023-03-09 08:45:44,994][23090] Updated weights for policy 0, policy_version 57750 (0.0016) [2023-03-09 08:45:45,801][23090] Updated weights for policy 0, policy_version 57760 (0.0022) [2023-03-09 08:45:46,584][23090] Updated weights for policy 0, policy_version 57770 (0.0016) [2023-03-09 08:45:47,617][23090] Updated weights for policy 0, policy_version 57781 (0.0013) [2023-03-09 08:45:48,356][23090] Updated weights for policy 0, policy_version 57791 (0.0020) [2023-03-09 08:45:49,059][22664] Fps is (10 sec: 199898.9, 60 sec: 198792.4, 300 sec: 198829.5). Total num frames: 946995200. Throughput: 0: 49638.9. Samples: 236759312. Policy #0 lag: (min: 1.0, avg: 16.2, max: 33.0) [2023-03-09 08:45:49,060][22664] Avg episode reward: [(0, '54.361')] [2023-03-09 08:45:49,180][23090] Updated weights for policy 0, policy_version 57801 (0.0012) [2023-03-09 08:45:50,037][23090] Updated weights for policy 0, policy_version 57811 (0.0016) [2023-03-09 08:45:50,834][23090] Updated weights for policy 0, policy_version 57821 (0.0020) [2023-03-09 08:45:51,636][23090] Updated weights for policy 0, policy_version 57831 (0.0016) [2023-03-09 08:45:52,547][23090] Updated weights for policy 0, policy_version 57841 (0.0018) [2023-03-09 08:45:53,326][23090] Updated weights for policy 0, policy_version 57851 (0.0020) [2023-03-09 08:45:54,058][23090] Updated weights for policy 0, policy_version 57861 (0.0013) [2023-03-09 08:45:54,059][22664] Fps is (10 sec: 201518.6, 60 sec: 199065.4, 300 sec: 198774.0). Total num frames: 947994624. Throughput: 0: 49638.8. Samples: 237058224. Policy #0 lag: (min: 1.0, avg: 16.2, max: 33.0) [2023-03-09 08:45:54,061][22664] Avg episode reward: [(0, '52.436')] [2023-03-09 08:45:55,016][23090] Updated weights for policy 0, policy_version 57871 (0.0019) [2023-03-09 08:45:55,826][23090] Updated weights for policy 0, policy_version 57881 (0.0022) [2023-03-09 08:45:56,592][23090] Updated weights for policy 0, policy_version 57891 (0.0019) [2023-03-09 08:45:57,004][22940] Signal inference workers to stop experience collection... (18650 times) [2023-03-09 08:45:57,005][22940] Signal inference workers to resume experience collection... (18650 times) [2023-03-09 08:45:57,074][23090] InferenceWorker_p0-w0: stopping experience collection (18650 times) [2023-03-09 08:45:57,074][23090] InferenceWorker_p0-w0: resuming experience collection (18650 times) [2023-03-09 08:45:57,474][23090] Updated weights for policy 0, policy_version 57901 (0.0013) [2023-03-09 08:45:58,314][23090] Updated weights for policy 0, policy_version 57911 (0.0016) [2023-03-09 08:45:59,047][23090] Updated weights for policy 0, policy_version 57921 (0.0016) [2023-03-09 08:45:59,059][22664] Fps is (10 sec: 198242.1, 60 sec: 198518.7, 300 sec: 198718.3). Total num frames: 948977664. Throughput: 0: 49684.5. Samples: 237207712. Policy #0 lag: (min: 1.0, avg: 16.2, max: 33.0) [2023-03-09 08:45:59,061][22664] Avg episode reward: [(0, '55.224')] [2023-03-09 08:45:59,957][23090] Updated weights for policy 0, policy_version 57931 (0.0013) [2023-03-09 08:46:00,786][23090] Updated weights for policy 0, policy_version 57941 (0.0013) [2023-03-09 08:46:01,520][23090] Updated weights for policy 0, policy_version 57951 (0.0015) [2023-03-09 08:46:02,356][23090] Updated weights for policy 0, policy_version 57961 (0.0013) [2023-03-09 08:46:03,235][23090] Updated weights for policy 0, policy_version 57971 (0.0013) [2023-03-09 08:46:03,982][23090] Updated weights for policy 0, policy_version 57981 (0.0020) [2023-03-09 08:46:04,058][22664] Fps is (10 sec: 198252.1, 60 sec: 198793.1, 300 sec: 198718.7). Total num frames: 949977088. Throughput: 0: 49640.1. Samples: 237504608. Policy #0 lag: (min: 1.0, avg: 16.2, max: 33.0) [2023-03-09 08:46:04,060][22664] Avg episode reward: [(0, '50.787')] [2023-03-09 08:46:04,771][23090] Updated weights for policy 0, policy_version 57991 (0.0013) [2023-03-09 08:46:05,662][23090] Updated weights for policy 0, policy_version 58001 (0.0016) [2023-03-09 08:46:06,475][23090] Updated weights for policy 0, policy_version 58011 (0.0013) [2023-03-09 08:46:07,239][23090] Updated weights for policy 0, policy_version 58021 (0.0013) [2023-03-09 08:46:08,130][23090] Updated weights for policy 0, policy_version 58031 (0.0022) [2023-03-09 08:46:08,596][22940] Signal inference workers to stop experience collection... (18700 times) [2023-03-09 08:46:08,613][22940] Signal inference workers to resume experience collection... (18700 times) [2023-03-09 08:46:08,678][23090] InferenceWorker_p0-w0: stopping experience collection (18700 times) [2023-03-09 08:46:08,680][23090] InferenceWorker_p0-w0: resuming experience collection (18700 times) [2023-03-09 08:46:09,057][23090] Updated weights for policy 0, policy_version 58041 (0.0020) [2023-03-09 08:46:09,059][22664] Fps is (10 sec: 196607.6, 60 sec: 198246.6, 300 sec: 198718.4). Total num frames: 950943744. Throughput: 0: 49684.3. Samples: 237803536. Policy #0 lag: (min: 1.0, avg: 16.2, max: 33.0) [2023-03-09 08:46:09,060][22664] Avg episode reward: [(0, '54.127')] [2023-03-09 08:46:09,748][23090] Updated weights for policy 0, policy_version 58051 (0.0013) [2023-03-09 08:46:10,645][23090] Updated weights for policy 0, policy_version 58061 (0.0013) [2023-03-09 08:46:11,485][23090] Updated weights for policy 0, policy_version 58071 (0.0013) [2023-03-09 08:46:12,236][23090] Updated weights for policy 0, policy_version 58081 (0.0019) [2023-03-09 08:46:13,115][23090] Updated weights for policy 0, policy_version 58091 (0.0018) [2023-03-09 08:46:13,999][23090] Updated weights for policy 0, policy_version 58102 (0.0013) [2023-03-09 08:46:14,059][22664] Fps is (10 sec: 196605.7, 60 sec: 198519.6, 300 sec: 198663.1). Total num frames: 951943168. Throughput: 0: 49730.7. Samples: 237952992. Policy #0 lag: (min: 1.0, avg: 16.2, max: 33.0) [2023-03-09 08:46:14,060][22664] Avg episode reward: [(0, '53.646')] [2023-03-09 08:46:14,824][23090] Updated weights for policy 0, policy_version 58112 (0.0017) [2023-03-09 08:46:15,598][23090] Updated weights for policy 0, policy_version 58122 (0.0016) [2023-03-09 08:46:16,550][23090] Updated weights for policy 0, policy_version 58132 (0.0013) [2023-03-09 08:46:17,274][23090] Updated weights for policy 0, policy_version 58142 (0.0013) [2023-03-09 08:46:18,123][23090] Updated weights for policy 0, policy_version 58152 (0.0018) [2023-03-09 08:46:18,936][23090] Updated weights for policy 0, policy_version 58162 (0.0025) [2023-03-09 08:46:19,059][22664] Fps is (10 sec: 199884.1, 60 sec: 198519.2, 300 sec: 198773.8). Total num frames: 952942592. Throughput: 0: 49685.4. Samples: 238249920. Policy #0 lag: (min: 1.0, avg: 16.2, max: 33.0) [2023-03-09 08:46:19,061][22664] Avg episode reward: [(0, '54.603')] [2023-03-09 08:46:19,776][23090] Updated weights for policy 0, policy_version 58172 (0.0020) [2023-03-09 08:46:20,321][22940] Signal inference workers to stop experience collection... (18750 times) [2023-03-09 08:46:20,322][22940] Signal inference workers to resume experience collection... (18750 times) [2023-03-09 08:46:20,393][23090] InferenceWorker_p0-w0: stopping experience collection (18750 times) [2023-03-09 08:46:20,394][23090] InferenceWorker_p0-w0: resuming experience collection (18750 times) [2023-03-09 08:46:20,515][23090] Updated weights for policy 0, policy_version 58182 (0.0017) [2023-03-09 08:46:21,434][23090] Updated weights for policy 0, policy_version 58192 (0.0018) [2023-03-09 08:46:22,284][23090] Updated weights for policy 0, policy_version 58202 (0.0015) [2023-03-09 08:46:23,041][23090] Updated weights for policy 0, policy_version 58212 (0.0013) [2023-03-09 08:46:23,885][23090] Updated weights for policy 0, policy_version 58222 (0.0017) [2023-03-09 08:46:24,059][22664] Fps is (10 sec: 199880.8, 60 sec: 198792.4, 300 sec: 198774.0). Total num frames: 953942016. Throughput: 0: 49687.2. Samples: 238548912. Policy #0 lag: (min: 0.0, avg: 16.5, max: 33.0) [2023-03-09 08:46:24,061][22664] Avg episode reward: [(0, '51.405')] [2023-03-09 08:46:24,732][23090] Updated weights for policy 0, policy_version 58232 (0.0016) [2023-03-09 08:46:25,502][23090] Updated weights for policy 0, policy_version 58242 (0.0017) [2023-03-09 08:46:26,390][23090] Updated weights for policy 0, policy_version 58252 (0.0015) [2023-03-09 08:46:27,173][23090] Updated weights for policy 0, policy_version 58262 (0.0016) [2023-03-09 08:46:27,978][23090] Updated weights for policy 0, policy_version 58272 (0.0013) [2023-03-09 08:46:28,754][23090] Updated weights for policy 0, policy_version 58282 (0.0016) [2023-03-09 08:46:29,059][22664] Fps is (10 sec: 198242.2, 60 sec: 199064.7, 300 sec: 198718.3). Total num frames: 954925056. Throughput: 0: 49686.2. Samples: 238698368. Policy #0 lag: (min: 0.0, avg: 16.5, max: 33.0) [2023-03-09 08:46:29,061][22664] Avg episode reward: [(0, '53.270')] [2023-03-09 08:46:29,707][23090] Updated weights for policy 0, policy_version 58292 (0.0020) [2023-03-09 08:46:30,436][23090] Updated weights for policy 0, policy_version 58302 (0.0016) [2023-03-09 08:46:31,300][23090] Updated weights for policy 0, policy_version 58312 (0.0020) [2023-03-09 08:46:32,119][23090] Updated weights for policy 0, policy_version 58322 (0.0014) [2023-03-09 08:46:32,895][22940] Signal inference workers to stop experience collection... (18800 times) [2023-03-09 08:46:32,895][22940] Signal inference workers to resume experience collection... (18800 times) [2023-03-09 08:46:32,960][23090] InferenceWorker_p0-w0: stopping experience collection (18800 times) [2023-03-09 08:46:32,960][23090] InferenceWorker_p0-w0: resuming experience collection (18800 times) [2023-03-09 08:46:32,962][23090] Updated weights for policy 0, policy_version 58332 (0.0013) [2023-03-09 08:46:33,683][23090] Updated weights for policy 0, policy_version 58342 (0.0016) [2023-03-09 08:46:34,059][22664] Fps is (10 sec: 199885.4, 60 sec: 199064.8, 300 sec: 198829.4). Total num frames: 955940864. Throughput: 0: 49685.8. Samples: 238995184. Policy #0 lag: (min: 0.0, avg: 16.5, max: 33.0) [2023-03-09 08:46:34,061][22664] Avg episode reward: [(0, '55.156')] [2023-03-09 08:46:34,608][23090] Updated weights for policy 0, policy_version 58352 (0.0013) [2023-03-09 08:46:35,505][23090] Updated weights for policy 0, policy_version 58362 (0.0019) [2023-03-09 08:46:36,244][23090] Updated weights for policy 0, policy_version 58372 (0.0020) [2023-03-09 08:46:37,106][23090] Updated weights for policy 0, policy_version 58382 (0.0022) [2023-03-09 08:46:37,958][23090] Updated weights for policy 0, policy_version 58392 (0.0013) [2023-03-09 08:46:38,722][23090] Updated weights for policy 0, policy_version 58402 (0.0016) [2023-03-09 08:46:39,059][22664] Fps is (10 sec: 199894.6, 60 sec: 198794.9, 300 sec: 198829.5). Total num frames: 956923904. Throughput: 0: 49640.8. Samples: 239292048. Policy #0 lag: (min: 0.0, avg: 16.5, max: 33.0) [2023-03-09 08:46:39,060][22664] Avg episode reward: [(0, '52.376')] [2023-03-09 08:46:39,714][23090] Updated weights for policy 0, policy_version 58413 (0.0013) [2023-03-09 08:46:40,531][23090] Updated weights for policy 0, policy_version 58423 (0.0019) [2023-03-09 08:46:41,333][23090] Updated weights for policy 0, policy_version 58433 (0.0017) [2023-03-09 08:46:42,158][23090] Updated weights for policy 0, policy_version 58443 (0.0013) [2023-03-09 08:46:43,006][23090] Updated weights for policy 0, policy_version 58453 (0.0013) [2023-03-09 08:46:43,924][23090] Updated weights for policy 0, policy_version 58464 (0.0013) [2023-03-09 08:46:44,059][22664] Fps is (10 sec: 196609.0, 60 sec: 198792.0, 300 sec: 198718.5). Total num frames: 957906944. Throughput: 0: 49640.2. Samples: 239441520. Policy #0 lag: (min: 0.0, avg: 16.5, max: 33.0) [2023-03-09 08:46:44,060][22664] Avg episode reward: [(0, '53.418')] [2023-03-09 08:46:44,653][23090] Updated weights for policy 0, policy_version 58474 (0.0013) [2023-03-09 08:46:45,551][23090] Updated weights for policy 0, policy_version 58484 (0.0017) [2023-03-09 08:46:46,299][23090] Updated weights for policy 0, policy_version 58494 (0.0017) [2023-03-09 08:46:47,149][23090] Updated weights for policy 0, policy_version 58504 (0.0023) [2023-03-09 08:46:48,013][23090] Updated weights for policy 0, policy_version 58514 (0.0025) [2023-03-09 08:46:48,636][22940] Signal inference workers to stop experience collection... (18850 times) [2023-03-09 08:46:48,652][22940] Signal inference workers to resume experience collection... (18850 times) [2023-03-09 08:46:48,670][23090] InferenceWorker_p0-w0: stopping experience collection (18850 times) [2023-03-09 08:46:48,670][23090] InferenceWorker_p0-w0: resuming experience collection (18850 times) [2023-03-09 08:46:48,755][23090] Updated weights for policy 0, policy_version 58524 (0.0013) [2023-03-09 08:46:49,059][22664] Fps is (10 sec: 198243.0, 60 sec: 198518.9, 300 sec: 198718.4). Total num frames: 958906368. Throughput: 0: 49683.7. Samples: 239740384. Policy #0 lag: (min: 0.0, avg: 16.5, max: 33.0) [2023-03-09 08:46:49,060][22664] Avg episode reward: [(0, '50.582')] [2023-03-09 08:46:49,516][23090] Updated weights for policy 0, policy_version 58534 (0.0014) [2023-03-09 08:46:50,432][23090] Updated weights for policy 0, policy_version 58544 (0.0013) [2023-03-09 08:46:51,289][23090] Updated weights for policy 0, policy_version 58554 (0.0017) [2023-03-09 08:46:52,057][23090] Updated weights for policy 0, policy_version 58564 (0.0017) [2023-03-09 08:46:52,918][23090] Updated weights for policy 0, policy_version 58574 (0.0013) [2023-03-09 08:46:53,793][23090] Updated weights for policy 0, policy_version 58584 (0.0013) [2023-03-09 08:46:54,058][22664] Fps is (10 sec: 198251.7, 60 sec: 198247.5, 300 sec: 198718.5). Total num frames: 959889408. Throughput: 0: 49683.9. Samples: 240039296. Policy #0 lag: (min: 0.0, avg: 16.5, max: 33.0) [2023-03-09 08:46:54,059][22664] Avg episode reward: [(0, '54.767')] [2023-03-09 08:46:54,553][23090] Updated weights for policy 0, policy_version 58594 (0.0024) [2023-03-09 08:46:55,445][23090] Updated weights for policy 0, policy_version 58604 (0.0013) [2023-03-09 08:46:56,294][23090] Updated weights for policy 0, policy_version 58614 (0.0016) [2023-03-09 08:46:57,112][23090] Updated weights for policy 0, policy_version 58624 (0.0013) [2023-03-09 08:46:57,851][23090] Updated weights for policy 0, policy_version 58634 (0.0021) [2023-03-09 08:46:58,739][23090] Updated weights for policy 0, policy_version 58644 (0.0023) [2023-03-09 08:46:59,059][22664] Fps is (10 sec: 196607.0, 60 sec: 198246.4, 300 sec: 198718.3). Total num frames: 960872448. Throughput: 0: 49638.2. Samples: 240186720. Policy #0 lag: (min: 2.0, avg: 17.4, max: 34.0) [2023-03-09 08:46:59,060][22664] Avg episode reward: [(0, '55.328')] [2023-03-09 08:46:59,510][23090] Updated weights for policy 0, policy_version 58654 (0.0021) [2023-03-09 08:47:00,337][23090] Updated weights for policy 0, policy_version 58664 (0.0016) [2023-03-09 08:47:01,335][23090] Updated weights for policy 0, policy_version 58675 (0.0018) [2023-03-09 08:47:02,108][23090] Updated weights for policy 0, policy_version 58685 (0.0013) [2023-03-09 08:47:02,928][23090] Updated weights for policy 0, policy_version 58695 (0.0018) [2023-03-09 08:47:03,848][23090] Updated weights for policy 0, policy_version 58705 (0.0013) [2023-03-09 08:47:04,059][22664] Fps is (10 sec: 198239.5, 60 sec: 198245.4, 300 sec: 198774.2). Total num frames: 961871872. Throughput: 0: 49592.9. Samples: 240481600. Policy #0 lag: (min: 2.0, avg: 17.4, max: 34.0) [2023-03-09 08:47:04,061][22664] Avg episode reward: [(0, '55.519')] [2023-03-09 08:47:04,591][23090] Updated weights for policy 0, policy_version 58715 (0.0016) [2023-03-09 08:47:05,236][22940] Signal inference workers to stop experience collection... (18900 times) [2023-03-09 08:47:05,237][22940] Signal inference workers to resume experience collection... (18900 times) [2023-03-09 08:47:05,299][23090] InferenceWorker_p0-w0: stopping experience collection (18900 times) [2023-03-09 08:47:05,299][23090] InferenceWorker_p0-w0: resuming experience collection (18900 times) [2023-03-09 08:47:05,348][23090] Updated weights for policy 0, policy_version 58725 (0.0017) [2023-03-09 08:47:06,239][23090] Updated weights for policy 0, policy_version 58735 (0.0016) [2023-03-09 08:47:07,156][23090] Updated weights for policy 0, policy_version 58745 (0.0019) [2023-03-09 08:47:07,935][23090] Updated weights for policy 0, policy_version 58755 (0.0015) [2023-03-09 08:47:08,789][23090] Updated weights for policy 0, policy_version 58765 (0.0024) [2023-03-09 08:47:09,059][22664] Fps is (10 sec: 198250.7, 60 sec: 198520.3, 300 sec: 198718.7). Total num frames: 962854912. Throughput: 0: 49593.2. Samples: 240780592. Policy #0 lag: (min: 2.0, avg: 17.4, max: 34.0) [2023-03-09 08:47:09,060][22664] Avg episode reward: [(0, '53.474')] [2023-03-09 08:47:09,612][23090] Updated weights for policy 0, policy_version 58775 (0.0023) [2023-03-09 08:47:10,436][23090] Updated weights for policy 0, policy_version 58786 (0.0013) [2023-03-09 08:47:11,330][23090] Updated weights for policy 0, policy_version 58796 (0.0013) [2023-03-09 08:47:12,156][23090] Updated weights for policy 0, policy_version 58806 (0.0022) [2023-03-09 08:47:13,028][23090] Updated weights for policy 0, policy_version 58817 (0.0017) [2023-03-09 08:47:13,862][23090] Updated weights for policy 0, policy_version 58827 (0.0018) [2023-03-09 08:47:14,059][22664] Fps is (10 sec: 199890.5, 60 sec: 198792.8, 300 sec: 198829.5). Total num frames: 963870720. Throughput: 0: 49593.4. Samples: 240930048. Policy #0 lag: (min: 2.0, avg: 17.4, max: 34.0) [2023-03-09 08:47:14,060][22664] Avg episode reward: [(0, '54.535')] [2023-03-09 08:47:14,784][23090] Updated weights for policy 0, policy_version 58838 (0.0013) [2023-03-09 08:47:15,601][23090] Updated weights for policy 0, policy_version 58848 (0.0013) [2023-03-09 08:47:16,337][23090] Updated weights for policy 0, policy_version 58858 (0.0016) [2023-03-09 08:47:17,271][23090] Updated weights for policy 0, policy_version 58868 (0.0019) [2023-03-09 08:47:17,969][23090] Updated weights for policy 0, policy_version 58878 (0.0019) [2023-03-09 08:47:18,813][23090] Updated weights for policy 0, policy_version 58888 (0.0022) [2023-03-09 08:47:19,059][22664] Fps is (10 sec: 201515.3, 60 sec: 198792.1, 300 sec: 198829.3). Total num frames: 964870144. Throughput: 0: 49640.0. Samples: 241228992. Policy #0 lag: (min: 2.0, avg: 17.4, max: 34.0) [2023-03-09 08:47:19,061][22664] Avg episode reward: [(0, '51.418')] [2023-03-09 08:47:19,066][22940] Saving /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000058891_964870144.pth... [2023-03-09 08:47:19,124][22940] Removing /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000055979_917159936.pth [2023-03-09 08:47:19,678][23090] Updated weights for policy 0, policy_version 58898 (0.0015) [2023-03-09 08:47:20,456][23090] Updated weights for policy 0, policy_version 58908 (0.0016) [2023-03-09 08:47:21,000][22940] Signal inference workers to stop experience collection... (18950 times) [2023-03-09 08:47:21,001][22940] Signal inference workers to resume experience collection... (18950 times) [2023-03-09 08:47:21,063][23090] InferenceWorker_p0-w0: stopping experience collection (18950 times) [2023-03-09 08:47:21,063][23090] InferenceWorker_p0-w0: resuming experience collection (18950 times) [2023-03-09 08:47:21,195][23090] Updated weights for policy 0, policy_version 58918 (0.0016) [2023-03-09 08:47:22,101][23090] Updated weights for policy 0, policy_version 58928 (0.0029) [2023-03-09 08:47:22,962][23090] Updated weights for policy 0, policy_version 58938 (0.0014) [2023-03-09 08:47:23,732][23090] Updated weights for policy 0, policy_version 58948 (0.0019) [2023-03-09 08:47:24,059][22664] Fps is (10 sec: 199881.0, 60 sec: 198792.9, 300 sec: 198885.3). Total num frames: 965869568. Throughput: 0: 49685.9. Samples: 241527920. Policy #0 lag: (min: 2.0, avg: 17.4, max: 34.0) [2023-03-09 08:47:24,061][22664] Avg episode reward: [(0, '53.881')] [2023-03-09 08:47:24,571][23090] Updated weights for policy 0, policy_version 58958 (0.0016) [2023-03-09 08:47:25,442][23090] Updated weights for policy 0, policy_version 58968 (0.0016) [2023-03-09 08:47:26,186][23090] Updated weights for policy 0, policy_version 58978 (0.0013) [2023-03-09 08:47:27,066][23090] Updated weights for policy 0, policy_version 58988 (0.0013) [2023-03-09 08:47:28,011][23090] Updated weights for policy 0, policy_version 58999 (0.0013) [2023-03-09 08:47:28,746][23090] Updated weights for policy 0, policy_version 59009 (0.0019) [2023-03-09 08:47:29,059][22664] Fps is (10 sec: 199892.3, 60 sec: 199067.2, 300 sec: 198829.7). Total num frames: 966868992. Throughput: 0: 49732.5. Samples: 241679472. Policy #0 lag: (min: 2.0, avg: 17.4, max: 34.0) [2023-03-09 08:47:29,060][22664] Avg episode reward: [(0, '54.105')] [2023-03-09 08:47:29,545][23090] Updated weights for policy 0, policy_version 59019 (0.0016) [2023-03-09 08:47:30,457][23090] Updated weights for policy 0, policy_version 59029 (0.0013) [2023-03-09 08:47:31,194][23090] Updated weights for policy 0, policy_version 59039 (0.0025) [2023-03-09 08:47:31,998][23090] Updated weights for policy 0, policy_version 59049 (0.0013) [2023-03-09 08:47:32,890][23090] Updated weights for policy 0, policy_version 59059 (0.0017) [2023-03-09 08:47:33,725][23090] Updated weights for policy 0, policy_version 59069 (0.0015) [2023-03-09 08:47:34,059][22664] Fps is (10 sec: 199884.2, 60 sec: 198792.7, 300 sec: 198829.4). Total num frames: 967868416. Throughput: 0: 49732.9. Samples: 241978368. Policy #0 lag: (min: 2.0, avg: 16.9, max: 34.0) [2023-03-09 08:47:34,061][22664] Avg episode reward: [(0, '55.315')] [2023-03-09 08:47:34,474][23090] Updated weights for policy 0, policy_version 59079 (0.0020) [2023-03-09 08:47:35,400][23090] Updated weights for policy 0, policy_version 59089 (0.0017) [2023-03-09 08:47:36,136][23090] Updated weights for policy 0, policy_version 59099 (0.0017) [2023-03-09 08:47:36,548][22940] Signal inference workers to stop experience collection... (19000 times) [2023-03-09 08:47:36,549][22940] Signal inference workers to resume experience collection... (19000 times) [2023-03-09 08:47:36,614][23090] InferenceWorker_p0-w0: stopping experience collection (19000 times) [2023-03-09 08:47:36,615][23090] InferenceWorker_p0-w0: resuming experience collection (19000 times) [2023-03-09 08:47:36,877][23090] Updated weights for policy 0, policy_version 59109 (0.0013) [2023-03-09 08:47:37,793][23090] Updated weights for policy 0, policy_version 59119 (0.0018) [2023-03-09 08:47:38,684][23090] Updated weights for policy 0, policy_version 59129 (0.0022) [2023-03-09 08:47:39,059][22664] Fps is (10 sec: 198241.0, 60 sec: 198791.6, 300 sec: 198829.6). Total num frames: 968851456. Throughput: 0: 49733.3. Samples: 242277312. Policy #0 lag: (min: 2.0, avg: 16.9, max: 34.0) [2023-03-09 08:47:39,061][22664] Avg episode reward: [(0, '53.231')] [2023-03-09 08:47:39,408][23090] Updated weights for policy 0, policy_version 59139 (0.0013) [2023-03-09 08:47:40,293][23090] Updated weights for policy 0, policy_version 59149 (0.0013) [2023-03-09 08:47:41,142][23090] Updated weights for policy 0, policy_version 59159 (0.0016) [2023-03-09 08:47:41,988][23090] Updated weights for policy 0, policy_version 59170 (0.0013) [2023-03-09 08:47:42,909][23090] Updated weights for policy 0, policy_version 59180 (0.0016) [2023-03-09 08:47:43,686][23090] Updated weights for policy 0, policy_version 59190 (0.0017) [2023-03-09 08:47:44,059][22664] Fps is (10 sec: 198247.3, 60 sec: 199065.7, 300 sec: 198829.5). Total num frames: 969850880. Throughput: 0: 49779.3. Samples: 242426784. Policy #0 lag: (min: 2.0, avg: 16.9, max: 34.0) [2023-03-09 08:47:44,061][22664] Avg episode reward: [(0, '54.109')] [2023-03-09 08:47:44,464][23090] Updated weights for policy 0, policy_version 59200 (0.0022) [2023-03-09 08:47:45,227][23090] Updated weights for policy 0, policy_version 59210 (0.0024) [2023-03-09 08:47:46,203][23090] Updated weights for policy 0, policy_version 59220 (0.0018) [2023-03-09 08:47:46,957][23090] Updated weights for policy 0, policy_version 59230 (0.0016) [2023-03-09 08:47:47,764][23090] Updated weights for policy 0, policy_version 59240 (0.0016) [2023-03-09 08:47:48,640][23090] Updated weights for policy 0, policy_version 59250 (0.0018) [2023-03-09 08:47:49,059][22664] Fps is (10 sec: 196613.6, 60 sec: 198520.0, 300 sec: 198829.5). Total num frames: 970817536. Throughput: 0: 49823.2. Samples: 242723632. Policy #0 lag: (min: 2.0, avg: 16.9, max: 34.0) [2023-03-09 08:47:49,060][22664] Avg episode reward: [(0, '52.688')] [2023-03-09 08:47:49,408][23090] Updated weights for policy 0, policy_version 59260 (0.0021) [2023-03-09 08:47:50,243][23090] Updated weights for policy 0, policy_version 59270 (0.0016) [2023-03-09 08:47:51,060][23090] Updated weights for policy 0, policy_version 59280 (0.0019) [2023-03-09 08:47:51,936][23090] Updated weights for policy 0, policy_version 59290 (0.0016) [2023-03-09 08:47:52,381][22940] Signal inference workers to stop experience collection... (19050 times) [2023-03-09 08:47:52,396][22940] Signal inference workers to resume experience collection... (19050 times) [2023-03-09 08:47:52,459][23090] InferenceWorker_p0-w0: stopping experience collection (19050 times) [2023-03-09 08:47:52,460][23090] InferenceWorker_p0-w0: resuming experience collection (19050 times) [2023-03-09 08:47:52,671][23090] Updated weights for policy 0, policy_version 59300 (0.0018) [2023-03-09 08:47:53,570][23090] Updated weights for policy 0, policy_version 59310 (0.0023) [2023-03-09 08:47:54,059][22664] Fps is (10 sec: 196607.8, 60 sec: 198791.7, 300 sec: 198773.9). Total num frames: 971816960. Throughput: 0: 49777.2. Samples: 243020576. Policy #0 lag: (min: 2.0, avg: 16.9, max: 34.0) [2023-03-09 08:47:54,061][22664] Avg episode reward: [(0, '53.209')] [2023-03-09 08:47:54,467][23090] Updated weights for policy 0, policy_version 59320 (0.0018) [2023-03-09 08:47:55,272][23090] Updated weights for policy 0, policy_version 59330 (0.0019) [2023-03-09 08:47:56,087][23090] Updated weights for policy 0, policy_version 59340 (0.0013) [2023-03-09 08:47:57,053][23090] Updated weights for policy 0, policy_version 59351 (0.0013) [2023-03-09 08:47:57,782][23090] Updated weights for policy 0, policy_version 59361 (0.0016) [2023-03-09 08:47:58,666][23090] Updated weights for policy 0, policy_version 59371 (0.0022) [2023-03-09 08:47:59,059][22664] Fps is (10 sec: 199883.7, 60 sec: 199066.1, 300 sec: 198829.5). Total num frames: 972816384. Throughput: 0: 49731.1. Samples: 243167952. Policy #0 lag: (min: 2.0, avg: 16.9, max: 34.0) [2023-03-09 08:47:59,060][22664] Avg episode reward: [(0, '55.113')] [2023-03-09 08:47:59,522][23090] Updated weights for policy 0, policy_version 59381 (0.0016) [2023-03-09 08:48:00,260][23090] Updated weights for policy 0, policy_version 59391 (0.0013) [2023-03-09 08:48:01,096][23090] Updated weights for policy 0, policy_version 59401 (0.0015) [2023-03-09 08:48:01,949][23090] Updated weights for policy 0, policy_version 59411 (0.0013) [2023-03-09 08:48:02,734][23090] Updated weights for policy 0, policy_version 59421 (0.0018) [2023-03-09 08:48:03,544][23090] Updated weights for policy 0, policy_version 59431 (0.0013) [2023-03-09 08:48:04,059][22664] Fps is (10 sec: 198250.5, 60 sec: 198793.6, 300 sec: 198718.7). Total num frames: 973799424. Throughput: 0: 49731.3. Samples: 243466880. Policy #0 lag: (min: 2.0, avg: 16.9, max: 34.0) [2023-03-09 08:48:04,060][22664] Avg episode reward: [(0, '54.479')] [2023-03-09 08:48:04,429][23090] Updated weights for policy 0, policy_version 59441 (0.0013) [2023-03-09 08:48:05,184][22940] Signal inference workers to stop experience collection... (19100 times) [2023-03-09 08:48:05,185][22940] Signal inference workers to resume experience collection... (19100 times) [2023-03-09 08:48:05,247][23090] InferenceWorker_p0-w0: stopping experience collection (19100 times) [2023-03-09 08:48:05,247][23090] InferenceWorker_p0-w0: resuming experience collection (19100 times) [2023-03-09 08:48:05,250][23090] Updated weights for policy 0, policy_version 59451 (0.0019) [2023-03-09 08:48:06,013][23090] Updated weights for policy 0, policy_version 59461 (0.0017) [2023-03-09 08:48:06,862][23090] Updated weights for policy 0, policy_version 59471 (0.0021) [2023-03-09 08:48:07,741][23090] Updated weights for policy 0, policy_version 59481 (0.0016) [2023-03-09 08:48:08,504][23090] Updated weights for policy 0, policy_version 59491 (0.0017) [2023-03-09 08:48:09,058][22664] Fps is (10 sec: 199886.6, 60 sec: 199338.8, 300 sec: 198829.5). Total num frames: 974815232. Throughput: 0: 49731.4. Samples: 243765824. Policy #0 lag: (min: 2.0, avg: 16.9, max: 34.0) [2023-03-09 08:48:09,060][22664] Avg episode reward: [(0, '52.329')] [2023-03-09 08:48:09,350][23090] Updated weights for policy 0, policy_version 59501 (0.0013) [2023-03-09 08:48:10,233][23090] Updated weights for policy 0, policy_version 59511 (0.0013) [2023-03-09 08:48:11,001][23090] Updated weights for policy 0, policy_version 59521 (0.0014) [2023-03-09 08:48:11,816][23090] Updated weights for policy 0, policy_version 59531 (0.0013) [2023-03-09 08:48:12,739][23090] Updated weights for policy 0, policy_version 59541 (0.0021) [2023-03-09 08:48:13,470][23090] Updated weights for policy 0, policy_version 59551 (0.0016) [2023-03-09 08:48:14,059][22664] Fps is (10 sec: 199879.7, 60 sec: 198791.8, 300 sec: 198773.9). Total num frames: 975798272. Throughput: 0: 49594.5. Samples: 243911232. Policy #0 lag: (min: 2.0, avg: 16.5, max: 33.0) [2023-03-09 08:48:14,061][22664] Avg episode reward: [(0, '55.004')] [2023-03-09 08:48:14,307][23090] Updated weights for policy 0, policy_version 59561 (0.0016) [2023-03-09 08:48:15,148][23090] Updated weights for policy 0, policy_version 59571 (0.0018) [2023-03-09 08:48:15,987][23090] Updated weights for policy 0, policy_version 59581 (0.0013) [2023-03-09 08:48:16,786][23090] Updated weights for policy 0, policy_version 59591 (0.0013) [2023-03-09 08:48:17,241][22940] Signal inference workers to stop experience collection... (19150 times) [2023-03-09 08:48:17,242][22940] Signal inference workers to resume experience collection... (19150 times) [2023-03-09 08:48:17,306][23090] InferenceWorker_p0-w0: stopping experience collection (19150 times) [2023-03-09 08:48:17,347][23090] InferenceWorker_p0-w0: resuming experience collection (19150 times) [2023-03-09 08:48:17,638][23090] Updated weights for policy 0, policy_version 59601 (0.0021) [2023-03-09 08:48:18,448][23090] Updated weights for policy 0, policy_version 59611 (0.0015) [2023-03-09 08:48:19,059][22664] Fps is (10 sec: 196605.7, 60 sec: 198520.5, 300 sec: 198718.4). Total num frames: 976781312. Throughput: 0: 49595.9. Samples: 244210176. Policy #0 lag: (min: 2.0, avg: 16.5, max: 33.0) [2023-03-09 08:48:19,060][22664] Avg episode reward: [(0, '53.077')] [2023-03-09 08:48:19,209][23090] Updated weights for policy 0, policy_version 59621 (0.0016) [2023-03-09 08:48:20,131][23090] Updated weights for policy 0, policy_version 59631 (0.0013) [2023-03-09 08:48:20,944][23090] Updated weights for policy 0, policy_version 59641 (0.0016) [2023-03-09 08:48:21,755][23090] Updated weights for policy 0, policy_version 59651 (0.0015) [2023-03-09 08:48:22,624][23090] Updated weights for policy 0, policy_version 59662 (0.0016) [2023-03-09 08:48:23,527][23090] Updated weights for policy 0, policy_version 59672 (0.0015) [2023-03-09 08:48:24,059][22664] Fps is (10 sec: 198245.5, 60 sec: 198519.2, 300 sec: 198718.3). Total num frames: 977780736. Throughput: 0: 49549.2. Samples: 244507024. Policy #0 lag: (min: 2.0, avg: 16.5, max: 33.0) [2023-03-09 08:48:24,061][22664] Avg episode reward: [(0, '53.739')] [2023-03-09 08:48:24,299][23090] Updated weights for policy 0, policy_version 59682 (0.0013) [2023-03-09 08:48:25,196][23090] Updated weights for policy 0, policy_version 59693 (0.0013) [2023-03-09 08:48:26,106][23090] Updated weights for policy 0, policy_version 59703 (0.0017) [2023-03-09 08:48:26,843][23090] Updated weights for policy 0, policy_version 59713 (0.0018) [2023-03-09 08:48:27,716][23090] Updated weights for policy 0, policy_version 59723 (0.0023) [2023-03-09 08:48:28,561][23090] Updated weights for policy 0, policy_version 59733 (0.0019) [2023-03-09 08:48:29,058][22664] Fps is (10 sec: 198249.7, 60 sec: 198246.7, 300 sec: 198718.5). Total num frames: 978763776. Throughput: 0: 49548.0. Samples: 244656432. Policy #0 lag: (min: 2.0, avg: 16.5, max: 33.0) [2023-03-09 08:48:29,059][22664] Avg episode reward: [(0, '54.164')] [2023-03-09 08:48:29,358][23090] Updated weights for policy 0, policy_version 59743 (0.0018) [2023-03-09 08:48:30,162][23090] Updated weights for policy 0, policy_version 59753 (0.0017) [2023-03-09 08:48:31,050][23090] Updated weights for policy 0, policy_version 59763 (0.0018) [2023-03-09 08:48:31,586][22940] Signal inference workers to stop experience collection... (19200 times) [2023-03-09 08:48:31,601][22940] Signal inference workers to resume experience collection... (19200 times) [2023-03-09 08:48:31,664][23090] InferenceWorker_p0-w0: stopping experience collection (19200 times) [2023-03-09 08:48:31,664][23090] InferenceWorker_p0-w0: resuming experience collection (19200 times) [2023-03-09 08:48:31,793][23090] Updated weights for policy 0, policy_version 59773 (0.0024) [2023-03-09 08:48:32,658][23090] Updated weights for policy 0, policy_version 59783 (0.0013) [2023-03-09 08:48:33,465][23090] Updated weights for policy 0, policy_version 59793 (0.0013) [2023-03-09 08:48:34,058][22664] Fps is (10 sec: 198252.3, 60 sec: 198247.2, 300 sec: 198663.2). Total num frames: 979763200. Throughput: 0: 49594.0. Samples: 244955360. Policy #0 lag: (min: 2.0, avg: 16.5, max: 33.0) [2023-03-09 08:48:34,060][22664] Avg episode reward: [(0, '53.262')] [2023-03-09 08:48:34,311][23090] Updated weights for policy 0, policy_version 59803 (0.0015) [2023-03-09 08:48:35,047][23090] Updated weights for policy 0, policy_version 59813 (0.0013) [2023-03-09 08:48:35,930][23090] Updated weights for policy 0, policy_version 59823 (0.0017) [2023-03-09 08:48:36,861][23090] Updated weights for policy 0, policy_version 59833 (0.0016) [2023-03-09 08:48:37,572][23090] Updated weights for policy 0, policy_version 59843 (0.0025) [2023-03-09 08:48:38,409][23090] Updated weights for policy 0, policy_version 59853 (0.0016) [2023-03-09 08:48:39,059][22664] Fps is (10 sec: 198240.4, 60 sec: 198246.6, 300 sec: 198718.3). Total num frames: 980746240. Throughput: 0: 49592.5. Samples: 245252240. Policy #0 lag: (min: 2.0, avg: 16.5, max: 33.0) [2023-03-09 08:48:39,061][22664] Avg episode reward: [(0, '53.085')] [2023-03-09 08:48:39,297][23090] Updated weights for policy 0, policy_version 59863 (0.0022) [2023-03-09 08:48:40,044][23090] Updated weights for policy 0, policy_version 59873 (0.0018) [2023-03-09 08:48:41,004][23090] Updated weights for policy 0, policy_version 59884 (0.0017) [2023-03-09 08:48:41,820][23090] Updated weights for policy 0, policy_version 59894 (0.0013) [2023-03-09 08:48:42,622][23090] Updated weights for policy 0, policy_version 59904 (0.0013) [2023-03-09 08:48:43,326][22940] Signal inference workers to stop experience collection... (19250 times) [2023-03-09 08:48:43,347][22940] Signal inference workers to resume experience collection... (19250 times) [2023-03-09 08:48:43,393][23090] InferenceWorker_p0-w0: stopping experience collection (19250 times) [2023-03-09 08:48:43,398][23090] Updated weights for policy 0, policy_version 59914 (0.0016) [2023-03-09 08:48:43,430][23090] InferenceWorker_p0-w0: resuming experience collection (19250 times) [2023-03-09 08:48:44,059][22664] Fps is (10 sec: 198240.7, 60 sec: 198246.1, 300 sec: 198773.8). Total num frames: 981745664. Throughput: 0: 49638.9. Samples: 245401712. Policy #0 lag: (min: 2.0, avg: 16.5, max: 33.0) [2023-03-09 08:48:44,061][22664] Avg episode reward: [(0, '52.762')] [2023-03-09 08:48:44,345][23090] Updated weights for policy 0, policy_version 59924 (0.0016) [2023-03-09 08:48:45,077][23090] Updated weights for policy 0, policy_version 59934 (0.0019) [2023-03-09 08:48:45,927][23090] Updated weights for policy 0, policy_version 59944 (0.0016) [2023-03-09 08:48:46,796][23090] Updated weights for policy 0, policy_version 59954 (0.0018) [2023-03-09 08:48:47,591][23090] Updated weights for policy 0, policy_version 59964 (0.0021) [2023-03-09 08:48:48,348][23090] Updated weights for policy 0, policy_version 59974 (0.0018) [2023-03-09 08:48:49,059][22664] Fps is (10 sec: 198246.0, 60 sec: 198518.7, 300 sec: 198718.3). Total num frames: 982728704. Throughput: 0: 49592.6. Samples: 245698560. Policy #0 lag: (min: 1.0, avg: 15.9, max: 33.0) [2023-03-09 08:48:49,061][22664] Avg episode reward: [(0, '51.854')] [2023-03-09 08:48:49,334][23090] Updated weights for policy 0, policy_version 59985 (0.0017) [2023-03-09 08:48:50,152][23090] Updated weights for policy 0, policy_version 59995 (0.0018) [2023-03-09 08:48:50,917][23090] Updated weights for policy 0, policy_version 60005 (0.0017) [2023-03-09 08:48:51,809][23090] Updated weights for policy 0, policy_version 60015 (0.0016) [2023-03-09 08:48:52,727][23090] Updated weights for policy 0, policy_version 60025 (0.0016) [2023-03-09 08:48:53,427][23090] Updated weights for policy 0, policy_version 60035 (0.0016) [2023-03-09 08:48:54,059][22664] Fps is (10 sec: 198249.5, 60 sec: 198519.7, 300 sec: 198662.8). Total num frames: 983728128. Throughput: 0: 49591.7. Samples: 245997456. Policy #0 lag: (min: 1.0, avg: 15.9, max: 33.0) [2023-03-09 08:48:54,060][22664] Avg episode reward: [(0, '53.442')] [2023-03-09 08:48:54,308][23090] Updated weights for policy 0, policy_version 60045 (0.0020) [2023-03-09 08:48:55,166][23090] Updated weights for policy 0, policy_version 60055 (0.0021) [2023-03-09 08:48:55,804][22940] Signal inference workers to stop experience collection... (19300 times) [2023-03-09 08:48:55,807][22940] Signal inference workers to resume experience collection... (19300 times) [2023-03-09 08:48:55,870][23090] InferenceWorker_p0-w0: stopping experience collection (19300 times) [2023-03-09 08:48:55,870][23090] InferenceWorker_p0-w0: resuming experience collection (19300 times) [2023-03-09 08:48:55,913][23090] Updated weights for policy 0, policy_version 60065 (0.0013) [2023-03-09 08:48:56,765][23090] Updated weights for policy 0, policy_version 60075 (0.0016) [2023-03-09 08:48:57,627][23090] Updated weights for policy 0, policy_version 60085 (0.0016) [2023-03-09 08:48:58,446][23090] Updated weights for policy 0, policy_version 60095 (0.0013) [2023-03-09 08:48:59,059][22664] Fps is (10 sec: 199886.9, 60 sec: 198519.2, 300 sec: 198718.5). Total num frames: 984727552. Throughput: 0: 49636.7. Samples: 246144880. Policy #0 lag: (min: 1.0, avg: 15.9, max: 33.0) [2023-03-09 08:48:59,060][22664] Avg episode reward: [(0, '52.337')] [2023-03-09 08:48:59,248][23090] Updated weights for policy 0, policy_version 60106 (0.0017) [2023-03-09 08:49:00,165][23090] Updated weights for policy 0, policy_version 60116 (0.0024) [2023-03-09 08:49:00,933][23090] Updated weights for policy 0, policy_version 60126 (0.0018) [2023-03-09 08:49:01,788][23090] Updated weights for policy 0, policy_version 60136 (0.0012) [2023-03-09 08:49:02,742][23090] Updated weights for policy 0, policy_version 60147 (0.0017) [2023-03-09 08:49:03,576][23090] Updated weights for policy 0, policy_version 60158 (0.0015) [2023-03-09 08:49:04,058][22664] Fps is (10 sec: 199888.0, 60 sec: 198792.6, 300 sec: 198718.7). Total num frames: 985726976. Throughput: 0: 49636.4. Samples: 246443808. Policy #0 lag: (min: 1.0, avg: 15.9, max: 33.0) [2023-03-09 08:49:04,060][22664] Avg episode reward: [(0, '53.601')] [2023-03-09 08:49:04,397][23090] Updated weights for policy 0, policy_version 60168 (0.0015) [2023-03-09 08:49:05,310][23090] Updated weights for policy 0, policy_version 60178 (0.0020) [2023-03-09 08:49:06,078][23090] Updated weights for policy 0, policy_version 60188 (0.0016) [2023-03-09 08:49:06,863][23090] Updated weights for policy 0, policy_version 60198 (0.0022) [2023-03-09 08:49:07,824][23090] Updated weights for policy 0, policy_version 60209 (0.0013) [2023-03-09 08:49:08,572][22940] Signal inference workers to stop experience collection... (19350 times) [2023-03-09 08:49:08,585][22940] Signal inference workers to resume experience collection... (19350 times) [2023-03-09 08:49:08,640][23090] InferenceWorker_p0-w0: stopping experience collection (19350 times) [2023-03-09 08:49:08,640][23090] InferenceWorker_p0-w0: resuming experience collection (19350 times) [2023-03-09 08:49:08,642][23090] Updated weights for policy 0, policy_version 60219 (0.0020) [2023-03-09 08:49:09,059][22664] Fps is (10 sec: 198244.8, 60 sec: 198245.6, 300 sec: 198663.0). Total num frames: 986710016. Throughput: 0: 49636.7. Samples: 246740672. Policy #0 lag: (min: 1.0, avg: 15.9, max: 33.0) [2023-03-09 08:49:09,061][22664] Avg episode reward: [(0, '54.200')] [2023-03-09 08:49:09,528][23090] Updated weights for policy 0, policy_version 60230 (0.0013) [2023-03-09 08:49:10,378][23090] Updated weights for policy 0, policy_version 60240 (0.0013) [2023-03-09 08:49:11,266][23090] Updated weights for policy 0, policy_version 60250 (0.0017) [2023-03-09 08:49:12,013][23090] Updated weights for policy 0, policy_version 60260 (0.0020) [2023-03-09 08:49:12,894][23090] Updated weights for policy 0, policy_version 60270 (0.0018) [2023-03-09 08:49:13,752][23090] Updated weights for policy 0, policy_version 60280 (0.0016) [2023-03-09 08:49:14,059][22664] Fps is (10 sec: 196604.7, 60 sec: 198246.8, 300 sec: 198663.0). Total num frames: 987693056. Throughput: 0: 49592.7. Samples: 246888112. Policy #0 lag: (min: 1.0, avg: 15.9, max: 33.0) [2023-03-09 08:49:14,060][22664] Avg episode reward: [(0, '51.861')] [2023-03-09 08:49:14,516][23090] Updated weights for policy 0, policy_version 60290 (0.0017) [2023-03-09 08:49:15,365][23090] Updated weights for policy 0, policy_version 60300 (0.0016) [2023-03-09 08:49:16,214][23090] Updated weights for policy 0, policy_version 60310 (0.0017) [2023-03-09 08:49:17,033][23090] Updated weights for policy 0, policy_version 60320 (0.0013) [2023-03-09 08:49:17,815][23090] Updated weights for policy 0, policy_version 60330 (0.0021) [2023-03-09 08:49:18,788][23090] Updated weights for policy 0, policy_version 60340 (0.0017) [2023-03-09 08:49:19,058][22664] Fps is (10 sec: 196613.3, 60 sec: 198246.9, 300 sec: 198607.4). Total num frames: 988676096. Throughput: 0: 49501.9. Samples: 247182944. Policy #0 lag: (min: 1.0, avg: 15.9, max: 33.0) [2023-03-09 08:49:19,059][22664] Avg episode reward: [(0, '54.697')] [2023-03-09 08:49:19,063][22940] Saving /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000060344_988676096.pth... [2023-03-09 08:49:19,125][22940] Removing /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000057437_941047808.pth [2023-03-09 08:49:19,493][23090] Updated weights for policy 0, policy_version 60350 (0.0024) [2023-03-09 08:49:20,355][23090] Updated weights for policy 0, policy_version 60360 (0.0013) [2023-03-09 08:49:21,208][23090] Updated weights for policy 0, policy_version 60370 (0.0016) [2023-03-09 08:49:21,962][23090] Updated weights for policy 0, policy_version 60380 (0.0013) [2023-03-09 08:49:22,813][23090] Updated weights for policy 0, policy_version 60390 (0.0022) [2023-03-09 08:49:23,320][22940] Signal inference workers to stop experience collection... (19400 times) [2023-03-09 08:49:23,336][22940] Signal inference workers to resume experience collection... (19400 times) [2023-03-09 08:49:23,414][23090] InferenceWorker_p0-w0: stopping experience collection (19400 times) [2023-03-09 08:49:23,414][23090] InferenceWorker_p0-w0: resuming experience collection (19400 times) [2023-03-09 08:49:23,744][23090] Updated weights for policy 0, policy_version 60401 (0.0016) [2023-03-09 08:49:24,059][22664] Fps is (10 sec: 196608.3, 60 sec: 197973.9, 300 sec: 198552.0). Total num frames: 989659136. Throughput: 0: 49547.5. Samples: 247481872. Policy #0 lag: (min: 1.0, avg: 16.0, max: 32.0) [2023-03-09 08:49:24,060][22664] Avg episode reward: [(0, '53.665')] [2023-03-09 08:49:24,563][23090] Updated weights for policy 0, policy_version 60411 (0.0014) [2023-03-09 08:49:25,344][23090] Updated weights for policy 0, policy_version 60421 (0.0014) [2023-03-09 08:49:26,210][23090] Updated weights for policy 0, policy_version 60431 (0.0017) [2023-03-09 08:49:27,105][23090] Updated weights for policy 0, policy_version 60441 (0.0014) [2023-03-09 08:49:27,838][23090] Updated weights for policy 0, policy_version 60451 (0.0018) [2023-03-09 08:49:28,723][23090] Updated weights for policy 0, policy_version 60461 (0.0017) [2023-03-09 08:49:29,059][22664] Fps is (10 sec: 198240.7, 60 sec: 198245.4, 300 sec: 198607.2). Total num frames: 990658560. Throughput: 0: 49547.0. Samples: 247631328. Policy #0 lag: (min: 1.0, avg: 16.0, max: 32.0) [2023-03-09 08:49:29,060][22664] Avg episode reward: [(0, '52.795')] [2023-03-09 08:49:29,579][23090] Updated weights for policy 0, policy_version 60471 (0.0018) [2023-03-09 08:49:30,354][23090] Updated weights for policy 0, policy_version 60481 (0.0018) [2023-03-09 08:49:31,154][23090] Updated weights for policy 0, policy_version 60491 (0.0019) [2023-03-09 08:49:32,065][23090] Updated weights for policy 0, policy_version 60501 (0.0020) [2023-03-09 08:49:32,835][23090] Updated weights for policy 0, policy_version 60511 (0.0015) [2023-03-09 08:49:33,616][23090] Updated weights for policy 0, policy_version 60521 (0.0017) [2023-03-09 08:49:34,058][22664] Fps is (10 sec: 198249.4, 60 sec: 197973.4, 300 sec: 198607.4). Total num frames: 991641600. Throughput: 0: 49549.1. Samples: 247928256. Policy #0 lag: (min: 1.0, avg: 16.0, max: 32.0) [2023-03-09 08:49:34,059][22664] Avg episode reward: [(0, '50.699')] [2023-03-09 08:49:34,535][23090] Updated weights for policy 0, policy_version 60531 (0.0013) [2023-03-09 08:49:35,277][23090] Updated weights for policy 0, policy_version 60541 (0.0013) [2023-03-09 08:49:36,117][23090] Updated weights for policy 0, policy_version 60551 (0.0016) [2023-03-09 08:49:36,967][23090] Updated weights for policy 0, policy_version 60561 (0.0013) [2023-03-09 08:49:37,806][23090] Updated weights for policy 0, policy_version 60571 (0.0015) [2023-03-09 08:49:38,554][23090] Updated weights for policy 0, policy_version 60581 (0.0013) [2023-03-09 08:49:39,059][22664] Fps is (10 sec: 198246.9, 60 sec: 198246.4, 300 sec: 198551.9). Total num frames: 992641024. Throughput: 0: 49458.7. Samples: 248223104. Policy #0 lag: (min: 1.0, avg: 16.0, max: 32.0) [2023-03-09 08:49:39,061][22664] Avg episode reward: [(0, '52.147')] [2023-03-09 08:49:39,447][23090] Updated weights for policy 0, policy_version 60591 (0.0016) [2023-03-09 08:49:40,386][23090] Updated weights for policy 0, policy_version 60601 (0.0013) [2023-03-09 08:49:41,115][23090] Updated weights for policy 0, policy_version 60611 (0.0019) [2023-03-09 08:49:41,969][23090] Updated weights for policy 0, policy_version 60621 (0.0013) [2023-03-09 08:49:42,825][23090] Updated weights for policy 0, policy_version 60631 (0.0022) [2023-03-09 08:49:43,563][22940] Signal inference workers to stop experience collection... (19450 times) [2023-03-09 08:49:43,563][22940] Signal inference workers to resume experience collection... (19450 times) [2023-03-09 08:49:43,629][23090] InferenceWorker_p0-w0: stopping experience collection (19450 times) [2023-03-09 08:49:43,629][23090] InferenceWorker_p0-w0: resuming experience collection (19450 times) [2023-03-09 08:49:43,631][23090] Updated weights for policy 0, policy_version 60641 (0.0020) [2023-03-09 08:49:44,058][22664] Fps is (10 sec: 198246.0, 60 sec: 197974.3, 300 sec: 198496.3). Total num frames: 993624064. Throughput: 0: 49458.7. Samples: 248370512. Policy #0 lag: (min: 1.0, avg: 16.0, max: 32.0) [2023-03-09 08:49:44,059][22664] Avg episode reward: [(0, '52.763')] [2023-03-09 08:49:44,428][23090] Updated weights for policy 0, policy_version 60651 (0.0016) [2023-03-09 08:49:45,330][23090] Updated weights for policy 0, policy_version 60661 (0.0016) [2023-03-09 08:49:46,109][23090] Updated weights for policy 0, policy_version 60671 (0.0027) [2023-03-09 08:49:46,941][23090] Updated weights for policy 0, policy_version 60681 (0.0017) [2023-03-09 08:49:47,793][23090] Updated weights for policy 0, policy_version 60691 (0.0015) [2023-03-09 08:49:48,551][23090] Updated weights for policy 0, policy_version 60701 (0.0018) [2023-03-09 08:49:49,058][22664] Fps is (10 sec: 198252.0, 60 sec: 198247.4, 300 sec: 198552.0). Total num frames: 994623488. Throughput: 0: 49458.8. Samples: 248669456. Policy #0 lag: (min: 1.0, avg: 16.0, max: 32.0) [2023-03-09 08:49:49,059][22664] Avg episode reward: [(0, '53.498')] [2023-03-09 08:49:49,465][23090] Updated weights for policy 0, policy_version 60712 (0.0013) [2023-03-09 08:49:50,362][23090] Updated weights for policy 0, policy_version 60722 (0.0013) [2023-03-09 08:49:51,152][23090] Updated weights for policy 0, policy_version 60732 (0.0024) [2023-03-09 08:49:51,950][23090] Updated weights for policy 0, policy_version 60742 (0.0013) [2023-03-09 08:49:52,818][23090] Updated weights for policy 0, policy_version 60752 (0.0016) [2023-03-09 08:49:53,686][23090] Updated weights for policy 0, policy_version 60762 (0.0017) [2023-03-09 08:49:54,059][22664] Fps is (10 sec: 196602.3, 60 sec: 197699.8, 300 sec: 198385.1). Total num frames: 995590144. Throughput: 0: 49414.4. Samples: 248964320. Policy #0 lag: (min: 1.0, avg: 16.0, max: 32.0) [2023-03-09 08:49:54,061][22664] Avg episode reward: [(0, '54.703')] [2023-03-09 08:49:54,444][23090] Updated weights for policy 0, policy_version 60772 (0.0013) [2023-03-09 08:49:55,285][23090] Updated weights for policy 0, policy_version 60782 (0.0017) [2023-03-09 08:49:56,216][23090] Updated weights for policy 0, policy_version 60792 (0.0020) [2023-03-09 08:49:56,940][23090] Updated weights for policy 0, policy_version 60802 (0.0021) [2023-03-09 08:49:57,747][23090] Updated weights for policy 0, policy_version 60812 (0.0019) [2023-03-09 08:49:58,645][23090] Updated weights for policy 0, policy_version 60822 (0.0016) [2023-03-09 08:49:59,059][22664] Fps is (10 sec: 196597.5, 60 sec: 197699.2, 300 sec: 198440.6). Total num frames: 996589568. Throughput: 0: 49458.4. Samples: 249113760. Policy #0 lag: (min: 1.0, avg: 16.0, max: 32.0) [2023-03-09 08:49:59,061][22664] Avg episode reward: [(0, '52.083')] [2023-03-09 08:49:59,470][23090] Updated weights for policy 0, policy_version 60832 (0.0016) [2023-03-09 08:50:00,210][23090] Updated weights for policy 0, policy_version 60842 (0.0014) [2023-03-09 08:50:01,134][23090] Updated weights for policy 0, policy_version 60852 (0.0015) [2023-03-09 08:50:01,872][23090] Updated weights for policy 0, policy_version 60862 (0.0015) [2023-03-09 08:50:02,748][23090] Updated weights for policy 0, policy_version 60873 (0.0019) [2023-03-09 08:50:03,679][23090] Updated weights for policy 0, policy_version 60883 (0.0017) [2023-03-09 08:50:04,059][22664] Fps is (10 sec: 198246.0, 60 sec: 197426.1, 300 sec: 198385.3). Total num frames: 997572608. Throughput: 0: 49503.7. Samples: 249410624. Policy #0 lag: (min: 0.0, avg: 15.9, max: 32.0) [2023-03-09 08:50:04,061][22664] Avg episode reward: [(0, '53.025')] [2023-03-09 08:50:04,457][23090] Updated weights for policy 0, policy_version 60893 (0.0021) [2023-03-09 08:50:04,465][22940] Signal inference workers to stop experience collection... (19500 times) [2023-03-09 08:50:04,466][22940] Signal inference workers to resume experience collection... (19500 times) [2023-03-09 08:50:04,535][23090] InferenceWorker_p0-w0: stopping experience collection (19500 times) [2023-03-09 08:50:04,536][23090] InferenceWorker_p0-w0: resuming experience collection (19500 times) [2023-03-09 08:50:05,261][23090] Updated weights for policy 0, policy_version 60903 (0.0013) [2023-03-09 08:50:06,116][23090] Updated weights for policy 0, policy_version 60913 (0.0013) [2023-03-09 08:50:07,001][23090] Updated weights for policy 0, policy_version 60924 (0.0017) [2023-03-09 08:50:07,798][23090] Updated weights for policy 0, policy_version 60934 (0.0013) [2023-03-09 08:50:08,675][23090] Updated weights for policy 0, policy_version 60944 (0.0013) [2023-03-09 08:50:09,058][22664] Fps is (10 sec: 196617.9, 60 sec: 197428.1, 300 sec: 198385.3). Total num frames: 998555648. Throughput: 0: 49503.8. Samples: 249709536. Policy #0 lag: (min: 0.0, avg: 15.9, max: 32.0) [2023-03-09 08:50:09,059][22664] Avg episode reward: [(0, '53.215')] [2023-03-09 08:50:09,520][23090] Updated weights for policy 0, policy_version 60954 (0.0019) [2023-03-09 08:50:10,260][23090] Updated weights for policy 0, policy_version 60964 (0.0017) [2023-03-09 08:50:11,216][23090] Updated weights for policy 0, policy_version 60974 (0.0013) [2023-03-09 08:50:12,039][23090] Updated weights for policy 0, policy_version 60984 (0.0016) [2023-03-09 08:50:12,794][23090] Updated weights for policy 0, policy_version 60994 (0.0013) [2023-03-09 08:50:13,712][23090] Updated weights for policy 0, policy_version 61005 (0.0013) [2023-03-09 08:50:14,058][22664] Fps is (10 sec: 199891.3, 60 sec: 197973.9, 300 sec: 198441.0). Total num frames: 999571456. Throughput: 0: 49504.0. Samples: 249858992. Policy #0 lag: (min: 0.0, avg: 15.9, max: 32.0) [2023-03-09 08:50:14,059][22664] Avg episode reward: [(0, '53.867')] [2023-03-09 08:50:14,627][23090] Updated weights for policy 0, policy_version 61015 (0.0013) [2023-03-09 08:50:15,324][23090] Updated weights for policy 0, policy_version 61025 (0.0013) [2023-03-09 08:50:16,134][23090] Updated weights for policy 0, policy_version 61035 (0.0017) [2023-03-09 08:50:17,045][23090] Updated weights for policy 0, policy_version 61045 (0.0013) [2023-03-09 08:50:17,221][22940] Signal inference workers to stop experience collection... (19550 times) [2023-03-09 08:50:17,222][22940] Signal inference workers to resume experience collection... (19550 times) [2023-03-09 08:50:17,283][23090] InferenceWorker_p0-w0: stopping experience collection (19550 times) [2023-03-09 08:50:17,283][23090] InferenceWorker_p0-w0: resuming experience collection (19550 times) [2023-03-09 08:50:17,844][23090] Updated weights for policy 0, policy_version 61055 (0.0016) [2023-03-09 08:50:18,634][23090] Updated weights for policy 0, policy_version 61066 (0.0018) [2023-03-09 08:50:19,058][22664] Fps is (10 sec: 201523.1, 60 sec: 198246.4, 300 sec: 198496.5). Total num frames: 1000570880. Throughput: 0: 49549.5. Samples: 250157984. Policy #0 lag: (min: 0.0, avg: 15.9, max: 32.0) [2023-03-09 08:50:19,060][22664] Avg episode reward: [(0, '53.795')] [2023-03-09 08:50:19,567][23090] Updated weights for policy 0, policy_version 61076 (0.0017) [2023-03-09 08:50:20,291][23090] Updated weights for policy 0, policy_version 61086 (0.0013) [2023-03-09 08:50:21,103][23090] Updated weights for policy 0, policy_version 61096 (0.0018) [2023-03-09 08:50:22,015][23090] Updated weights for policy 0, policy_version 61106 (0.0017) [2023-03-09 08:50:22,777][23090] Updated weights for policy 0, policy_version 61116 (0.0019) [2023-03-09 08:50:23,656][23090] Updated weights for policy 0, policy_version 61127 (0.0016) [2023-03-09 08:50:24,059][22664] Fps is (10 sec: 199882.3, 60 sec: 198519.5, 300 sec: 198607.5). Total num frames: 1001570304. Throughput: 0: 49640.7. Samples: 250456928. Policy #0 lag: (min: 0.0, avg: 15.9, max: 32.0) [2023-03-09 08:50:24,060][22664] Avg episode reward: [(0, '51.771')] [2023-03-09 08:50:24,576][23090] Updated weights for policy 0, policy_version 61137 (0.0016) [2023-03-09 08:50:25,404][23090] Updated weights for policy 0, policy_version 61147 (0.0013) [2023-03-09 08:50:26,130][23090] Updated weights for policy 0, policy_version 61157 (0.0017) [2023-03-09 08:50:27,047][23090] Updated weights for policy 0, policy_version 61167 (0.0017) [2023-03-09 08:50:27,855][23090] Updated weights for policy 0, policy_version 61177 (0.0022) [2023-03-09 08:50:28,585][23090] Updated weights for policy 0, policy_version 61187 (0.0020) [2023-03-09 08:50:28,677][22940] Signal inference workers to stop experience collection... (19600 times) [2023-03-09 08:50:28,678][22940] Signal inference workers to resume experience collection... (19600 times) [2023-03-09 08:50:28,743][23090] InferenceWorker_p0-w0: stopping experience collection (19600 times) [2023-03-09 08:50:28,743][23090] InferenceWorker_p0-w0: resuming experience collection (19600 times) [2023-03-09 08:50:29,059][22664] Fps is (10 sec: 199883.6, 60 sec: 198520.2, 300 sec: 198551.9). Total num frames: 1002569728. Throughput: 0: 49640.5. Samples: 250604336. Policy #0 lag: (min: 0.0, avg: 15.9, max: 32.0) [2023-03-09 08:50:29,060][22664] Avg episode reward: [(0, '54.038')] [2023-03-09 08:50:29,483][23090] Updated weights for policy 0, policy_version 61197 (0.0013) [2023-03-09 08:50:30,409][23090] Updated weights for policy 0, policy_version 61207 (0.0022) [2023-03-09 08:50:31,127][23090] Updated weights for policy 0, policy_version 61217 (0.0019) [2023-03-09 08:50:31,898][23090] Updated weights for policy 0, policy_version 61227 (0.0013) [2023-03-09 08:50:32,858][23090] Updated weights for policy 0, policy_version 61237 (0.0019) [2023-03-09 08:50:33,627][23090] Updated weights for policy 0, policy_version 61247 (0.0013) [2023-03-09 08:50:34,059][22664] Fps is (10 sec: 199886.0, 60 sec: 198792.3, 300 sec: 198552.3). Total num frames: 1003569152. Throughput: 0: 49641.2. Samples: 250903312. Policy #0 lag: (min: 0.0, avg: 15.9, max: 32.0) [2023-03-09 08:50:34,060][22664] Avg episode reward: [(0, '53.091')] [2023-03-09 08:50:34,389][23090] Updated weights for policy 0, policy_version 61257 (0.0016) [2023-03-09 08:50:35,288][23090] Updated weights for policy 0, policy_version 61267 (0.0016) [2023-03-09 08:50:36,060][23090] Updated weights for policy 0, policy_version 61277 (0.0018) [2023-03-09 08:50:36,815][23090] Updated weights for policy 0, policy_version 61287 (0.0018) [2023-03-09 08:50:37,748][23090] Updated weights for policy 0, policy_version 61297 (0.0020) [2023-03-09 08:50:38,553][23090] Updated weights for policy 0, policy_version 61307 (0.0022) [2023-03-09 08:50:39,058][22664] Fps is (10 sec: 198248.0, 60 sec: 198520.4, 300 sec: 198551.9). Total num frames: 1004552192. Throughput: 0: 49733.3. Samples: 251202304. Policy #0 lag: (min: 2.0, avg: 17.1, max: 33.0) [2023-03-09 08:50:39,059][22664] Avg episode reward: [(0, '51.576')] [2023-03-09 08:50:39,316][23090] Updated weights for policy 0, policy_version 61317 (0.0022) [2023-03-09 08:50:40,230][23090] Updated weights for policy 0, policy_version 61327 (0.0013) [2023-03-09 08:50:41,035][23090] Updated weights for policy 0, policy_version 61337 (0.0016) [2023-03-09 08:50:41,777][23090] Updated weights for policy 0, policy_version 61347 (0.0017) [2023-03-09 08:50:42,683][23090] Updated weights for policy 0, policy_version 61357 (0.0015) [2023-03-09 08:50:42,779][22940] Signal inference workers to stop experience collection... (19650 times) [2023-03-09 08:50:42,780][22940] Signal inference workers to resume experience collection... (19650 times) [2023-03-09 08:50:42,843][23090] InferenceWorker_p0-w0: stopping experience collection (19650 times) [2023-03-09 08:50:42,843][23090] InferenceWorker_p0-w0: resuming experience collection (19650 times) [2023-03-09 08:50:43,576][23090] Updated weights for policy 0, policy_version 61367 (0.0013) [2023-03-09 08:50:44,059][22664] Fps is (10 sec: 198242.9, 60 sec: 198791.8, 300 sec: 198496.2). Total num frames: 1005551616. Throughput: 0: 49688.8. Samples: 251349744. Policy #0 lag: (min: 2.0, avg: 17.1, max: 33.0) [2023-03-09 08:50:44,104][22664] Avg episode reward: [(0, '52.408')] [2023-03-09 08:50:44,368][23090] Updated weights for policy 0, policy_version 61378 (0.0016) [2023-03-09 08:50:45,242][23090] Updated weights for policy 0, policy_version 61388 (0.0016) [2023-03-09 08:50:46,063][23090] Updated weights for policy 0, policy_version 61398 (0.0013) [2023-03-09 08:50:46,903][23090] Updated weights for policy 0, policy_version 61408 (0.0013) [2023-03-09 08:50:47,624][23090] Updated weights for policy 0, policy_version 61418 (0.0019) [2023-03-09 08:50:48,613][23090] Updated weights for policy 0, policy_version 61428 (0.0019) [2023-03-09 08:50:49,059][22664] Fps is (10 sec: 198239.9, 60 sec: 198518.3, 300 sec: 198440.8). Total num frames: 1006534656. Throughput: 0: 49780.3. Samples: 251650736. Policy #0 lag: (min: 2.0, avg: 17.1, max: 33.0) [2023-03-09 08:50:49,103][22664] Avg episode reward: [(0, '51.711')] [2023-03-09 08:50:49,307][23090] Updated weights for policy 0, policy_version 61438 (0.0013) [2023-03-09 08:50:50,106][23090] Updated weights for policy 0, policy_version 61448 (0.0014) [2023-03-09 08:50:50,990][23090] Updated weights for policy 0, policy_version 61458 (0.0013) [2023-03-09 08:50:51,766][23090] Updated weights for policy 0, policy_version 61468 (0.0016) [2023-03-09 08:50:52,642][23090] Updated weights for policy 0, policy_version 61478 (0.0015) [2023-03-09 08:50:53,453][23090] Updated weights for policy 0, policy_version 61488 (0.0019) [2023-03-09 08:50:54,059][22664] Fps is (10 sec: 196606.6, 60 sec: 198792.5, 300 sec: 198440.8). Total num frames: 1007517696. Throughput: 0: 49780.7. Samples: 251949680. Policy #0 lag: (min: 2.0, avg: 17.1, max: 33.0) [2023-03-09 08:50:54,061][22664] Avg episode reward: [(0, '53.340')] [2023-03-09 08:50:54,295][23090] Updated weights for policy 0, policy_version 61498 (0.0020) [2023-03-09 08:50:55,027][23090] Updated weights for policy 0, policy_version 61508 (0.0013) [2023-03-09 08:50:55,937][23090] Updated weights for policy 0, policy_version 61518 (0.0024) [2023-03-09 08:50:55,946][22940] Signal inference workers to stop experience collection... (19700 times) [2023-03-09 08:50:55,947][22940] Signal inference workers to resume experience collection... (19700 times) [2023-03-09 08:50:56,011][23090] InferenceWorker_p0-w0: stopping experience collection (19700 times) [2023-03-09 08:50:56,015][23090] InferenceWorker_p0-w0: resuming experience collection (19700 times) [2023-03-09 08:50:56,788][23090] Updated weights for policy 0, policy_version 61528 (0.0020) [2023-03-09 08:50:57,525][23090] Updated weights for policy 0, policy_version 61538 (0.0019) [2023-03-09 08:50:58,395][23090] Updated weights for policy 0, policy_version 61548 (0.0021) [2023-03-09 08:50:59,059][22664] Fps is (10 sec: 198249.6, 60 sec: 198793.7, 300 sec: 198440.7). Total num frames: 1008517120. Throughput: 0: 49781.1. Samples: 252099152. Policy #0 lag: (min: 2.0, avg: 17.1, max: 33.0) [2023-03-09 08:50:59,060][22664] Avg episode reward: [(0, '54.680')] [2023-03-09 08:50:59,244][23090] Updated weights for policy 0, policy_version 61558 (0.0015) [2023-03-09 08:51:00,045][23090] Updated weights for policy 0, policy_version 61568 (0.0016) [2023-03-09 08:51:00,805][23090] Updated weights for policy 0, policy_version 61578 (0.0016) [2023-03-09 08:51:01,731][23090] Updated weights for policy 0, policy_version 61588 (0.0018) [2023-03-09 08:51:02,494][23090] Updated weights for policy 0, policy_version 61598 (0.0019) [2023-03-09 08:51:03,253][23090] Updated weights for policy 0, policy_version 61608 (0.0016) [2023-03-09 08:51:04,059][22664] Fps is (10 sec: 201526.6, 60 sec: 199339.3, 300 sec: 198607.5). Total num frames: 1009532928. Throughput: 0: 49734.6. Samples: 252396048. Policy #0 lag: (min: 2.0, avg: 17.1, max: 33.0) [2023-03-09 08:51:04,061][22664] Avg episode reward: [(0, '53.362')] [2023-03-09 08:51:04,142][23090] Updated weights for policy 0, policy_version 61618 (0.0012) [2023-03-09 08:51:04,939][23090] Updated weights for policy 0, policy_version 61628 (0.0015) [2023-03-09 08:51:05,747][23090] Updated weights for policy 0, policy_version 61638 (0.0016) [2023-03-09 08:51:06,581][23090] Updated weights for policy 0, policy_version 61648 (0.0017) [2023-03-09 08:51:07,480][23090] Updated weights for policy 0, policy_version 61658 (0.0014) [2023-03-09 08:51:08,179][22940] Signal inference workers to stop experience collection... (19750 times) [2023-03-09 08:51:08,180][22940] Signal inference workers to resume experience collection... (19750 times) [2023-03-09 08:51:08,208][23090] Updated weights for policy 0, policy_version 61668 (0.0021) [2023-03-09 08:51:08,243][23090] InferenceWorker_p0-w0: stopping experience collection (19750 times) [2023-03-09 08:51:08,243][23090] InferenceWorker_p0-w0: resuming experience collection (19750 times) [2023-03-09 08:51:09,059][22664] Fps is (10 sec: 199884.8, 60 sec: 199338.2, 300 sec: 198551.8). Total num frames: 1010515968. Throughput: 0: 49734.4. Samples: 252694976. Policy #0 lag: (min: 2.0, avg: 17.1, max: 33.0) [2023-03-09 08:51:09,060][22664] Avg episode reward: [(0, '53.366')] [2023-03-09 08:51:09,130][23090] Updated weights for policy 0, policy_version 61678 (0.0016) [2023-03-09 08:51:09,930][23090] Updated weights for policy 0, policy_version 61688 (0.0016) [2023-03-09 08:51:10,687][23090] Updated weights for policy 0, policy_version 61698 (0.0013) [2023-03-09 08:51:11,563][23090] Updated weights for policy 0, policy_version 61708 (0.0025) [2023-03-09 08:51:12,416][23090] Updated weights for policy 0, policy_version 61718 (0.0019) [2023-03-09 08:51:13,204][23090] Updated weights for policy 0, policy_version 61728 (0.0020) [2023-03-09 08:51:13,896][23090] Updated weights for policy 0, policy_version 61738 (0.0013) [2023-03-09 08:51:14,059][22664] Fps is (10 sec: 199886.1, 60 sec: 199338.4, 300 sec: 198607.6). Total num frames: 1011531776. Throughput: 0: 49780.3. Samples: 252844448. Policy #0 lag: (min: 2.0, avg: 17.1, max: 33.0) [2023-03-09 08:51:14,060][22664] Avg episode reward: [(0, '52.333')] [2023-03-09 08:51:14,899][23090] Updated weights for policy 0, policy_version 61748 (0.0013) [2023-03-09 08:51:15,819][23090] Updated weights for policy 0, policy_version 61759 (0.0020) [2023-03-09 08:51:16,556][23090] Updated weights for policy 0, policy_version 61769 (0.0016) [2023-03-09 08:51:17,444][23090] Updated weights for policy 0, policy_version 61779 (0.0020) [2023-03-09 08:51:18,266][23090] Updated weights for policy 0, policy_version 61789 (0.0020) [2023-03-09 08:51:19,059][22664] Fps is (10 sec: 199884.2, 60 sec: 199065.0, 300 sec: 198552.0). Total num frames: 1012514816. Throughput: 0: 49688.7. Samples: 253139312. Policy #0 lag: (min: 1.0, avg: 16.6, max: 33.0) [2023-03-09 08:51:19,060][22664] Avg episode reward: [(0, '53.199')] [2023-03-09 08:51:19,081][23090] Updated weights for policy 0, policy_version 61799 (0.0019) [2023-03-09 08:51:19,093][22940] Saving /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000061800_1012531200.pth... [2023-03-09 08:51:19,153][22940] Removing /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000058891_964870144.pth [2023-03-09 08:51:19,895][23090] Updated weights for policy 0, policy_version 61809 (0.0016) [2023-03-09 08:51:20,666][22940] Signal inference workers to stop experience collection... (19800 times) [2023-03-09 08:51:20,690][22940] Signal inference workers to resume experience collection... (19800 times) [2023-03-09 08:51:20,731][23090] InferenceWorker_p0-w0: stopping experience collection (19800 times) [2023-03-09 08:51:20,769][23090] InferenceWorker_p0-w0: resuming experience collection (19800 times) [2023-03-09 08:51:20,775][23090] Updated weights for policy 0, policy_version 61819 (0.0021) [2023-03-09 08:51:21,465][23090] Updated weights for policy 0, policy_version 61829 (0.0016) [2023-03-09 08:51:22,409][23090] Updated weights for policy 0, policy_version 61840 (0.0012) [2023-03-09 08:51:23,303][23090] Updated weights for policy 0, policy_version 61850 (0.0013) [2023-03-09 08:51:24,042][23090] Updated weights for policy 0, policy_version 61860 (0.0016) [2023-03-09 08:51:24,059][22664] Fps is (10 sec: 199884.4, 60 sec: 199338.8, 300 sec: 198663.2). Total num frames: 1013530624. Throughput: 0: 49731.4. Samples: 253440224. Policy #0 lag: (min: 1.0, avg: 16.6, max: 33.0) [2023-03-09 08:51:24,061][22664] Avg episode reward: [(0, '52.959')] [2023-03-09 08:51:24,936][23090] Updated weights for policy 0, policy_version 61870 (0.0020) [2023-03-09 08:51:25,820][23090] Updated weights for policy 0, policy_version 61880 (0.0015) [2023-03-09 08:51:26,600][23090] Updated weights for policy 0, policy_version 61890 (0.0018) [2023-03-09 08:51:27,419][23090] Updated weights for policy 0, policy_version 61900 (0.0016) [2023-03-09 08:51:28,267][23090] Updated weights for policy 0, policy_version 61910 (0.0013) [2023-03-09 08:51:29,058][22664] Fps is (10 sec: 198250.5, 60 sec: 198792.8, 300 sec: 198496.5). Total num frames: 1014497280. Throughput: 0: 49731.8. Samples: 253587664. Policy #0 lag: (min: 1.0, avg: 16.6, max: 33.0) [2023-03-09 08:51:29,059][22664] Avg episode reward: [(0, '55.474')] [2023-03-09 08:51:29,072][23090] Updated weights for policy 0, policy_version 61920 (0.0013) [2023-03-09 08:51:29,807][23090] Updated weights for policy 0, policy_version 61930 (0.0013) [2023-03-09 08:51:30,766][23090] Updated weights for policy 0, policy_version 61940 (0.0018) [2023-03-09 08:51:31,496][23090] Updated weights for policy 0, policy_version 61950 (0.0015) [2023-03-09 08:51:32,339][23090] Updated weights for policy 0, policy_version 61960 (0.0016) [2023-03-09 08:51:33,192][23090] Updated weights for policy 0, policy_version 61970 (0.0016) [2023-03-09 08:51:33,993][23090] Updated weights for policy 0, policy_version 61980 (0.0017) [2023-03-09 08:51:34,058][22664] Fps is (10 sec: 194971.4, 60 sec: 198519.6, 300 sec: 198496.4). Total num frames: 1015480320. Throughput: 0: 49686.8. Samples: 253886624. Policy #0 lag: (min: 1.0, avg: 16.6, max: 33.0) [2023-03-09 08:51:34,059][22664] Avg episode reward: [(0, '54.080')] [2023-03-09 08:51:34,827][23090] Updated weights for policy 0, policy_version 61990 (0.0026) [2023-03-09 08:51:34,923][22940] Signal inference workers to stop experience collection... (19850 times) [2023-03-09 08:51:34,924][22940] Signal inference workers to resume experience collection... (19850 times) [2023-03-09 08:51:34,989][23090] InferenceWorker_p0-w0: stopping experience collection (19850 times) [2023-03-09 08:51:34,989][23090] InferenceWorker_p0-w0: resuming experience collection (19850 times) [2023-03-09 08:51:35,644][23090] Updated weights for policy 0, policy_version 62000 (0.0013) [2023-03-09 08:51:36,543][23090] Updated weights for policy 0, policy_version 62010 (0.0020) [2023-03-09 08:51:37,274][23090] Updated weights for policy 0, policy_version 62020 (0.0015) [2023-03-09 08:51:38,149][23090] Updated weights for policy 0, policy_version 62030 (0.0013) [2023-03-09 08:51:38,999][23090] Updated weights for policy 0, policy_version 62040 (0.0015) [2023-03-09 08:51:39,059][22664] Fps is (10 sec: 196605.1, 60 sec: 198519.0, 300 sec: 198496.4). Total num frames: 1016463360. Throughput: 0: 49641.1. Samples: 254183520. Policy #0 lag: (min: 1.0, avg: 16.6, max: 33.0) [2023-03-09 08:51:39,060][22664] Avg episode reward: [(0, '52.741')] [2023-03-09 08:51:39,782][23090] Updated weights for policy 0, policy_version 62050 (0.0013) [2023-03-09 08:51:40,639][23090] Updated weights for policy 0, policy_version 62060 (0.0013) [2023-03-09 08:51:41,599][23090] Updated weights for policy 0, policy_version 62071 (0.0017) [2023-03-09 08:51:42,328][23090] Updated weights for policy 0, policy_version 62081 (0.0019) [2023-03-09 08:51:43,131][23090] Updated weights for policy 0, policy_version 62091 (0.0020) [2023-03-09 08:51:44,052][23090] Updated weights for policy 0, policy_version 62101 (0.0013) [2023-03-09 08:51:44,059][22664] Fps is (10 sec: 198232.0, 60 sec: 198517.8, 300 sec: 198496.0). Total num frames: 1017462784. Throughput: 0: 49595.1. Samples: 254330960. Policy #0 lag: (min: 1.0, avg: 16.6, max: 33.0) [2023-03-09 08:51:44,062][22664] Avg episode reward: [(0, '55.417')] [2023-03-09 08:51:44,862][23090] Updated weights for policy 0, policy_version 62111 (0.0017) [2023-03-09 08:51:45,605][23090] Updated weights for policy 0, policy_version 62121 (0.0015) [2023-03-09 08:51:46,533][23090] Updated weights for policy 0, policy_version 62131 (0.0013) [2023-03-09 08:51:47,295][23090] Updated weights for policy 0, policy_version 62141 (0.0013) [2023-03-09 08:51:48,112][23090] Updated weights for policy 0, policy_version 62151 (0.0016) [2023-03-09 08:51:49,018][23090] Updated weights for policy 0, policy_version 62161 (0.0016) [2023-03-09 08:51:49,059][22664] Fps is (10 sec: 198243.6, 60 sec: 198519.6, 300 sec: 198496.1). Total num frames: 1018445824. Throughput: 0: 49640.7. Samples: 254629888. Policy #0 lag: (min: 1.0, avg: 16.6, max: 33.0) [2023-03-09 08:51:49,061][22664] Avg episode reward: [(0, '56.201')] [2023-03-09 08:51:49,071][22940] Saving new best policy, reward=56.201! [2023-03-09 08:51:49,784][23090] Updated weights for policy 0, policy_version 62171 (0.0017) [2023-03-09 08:51:50,438][22940] Signal inference workers to stop experience collection... (19900 times) [2023-03-09 08:51:50,455][22940] Signal inference workers to resume experience collection... (19900 times) [2023-03-09 08:51:50,517][23090] InferenceWorker_p0-w0: stopping experience collection (19900 times) [2023-03-09 08:51:50,518][23090] InferenceWorker_p0-w0: resuming experience collection (19900 times) [2023-03-09 08:51:50,520][23090] Updated weights for policy 0, policy_version 62181 (0.0013) [2023-03-09 08:51:51,441][23090] Updated weights for policy 0, policy_version 62191 (0.0017) [2023-03-09 08:51:52,307][23090] Updated weights for policy 0, policy_version 62201 (0.0018) [2023-03-09 08:51:53,037][23090] Updated weights for policy 0, policy_version 62211 (0.0015) [2023-03-09 08:51:53,919][23090] Updated weights for policy 0, policy_version 62221 (0.0014) [2023-03-09 08:51:54,059][22664] Fps is (10 sec: 198257.5, 60 sec: 198793.0, 300 sec: 198551.9). Total num frames: 1019445248. Throughput: 0: 49595.4. Samples: 254926768. Policy #0 lag: (min: 1.0, avg: 16.6, max: 33.0) [2023-03-09 08:51:54,061][22664] Avg episode reward: [(0, '52.494')] [2023-03-09 08:51:54,768][23090] Updated weights for policy 0, policy_version 62231 (0.0019) [2023-03-09 08:51:55,623][23090] Updated weights for policy 0, policy_version 62242 (0.0013) [2023-03-09 08:51:56,463][23090] Updated weights for policy 0, policy_version 62252 (0.0019) [2023-03-09 08:51:57,318][23090] Updated weights for policy 0, policy_version 62262 (0.0022) [2023-03-09 08:51:58,101][23090] Updated weights for policy 0, policy_version 62272 (0.0013) [2023-03-09 08:51:58,868][23090] Updated weights for policy 0, policy_version 62282 (0.0017) [2023-03-09 08:51:59,059][22664] Fps is (10 sec: 199887.2, 60 sec: 198792.6, 300 sec: 198552.0). Total num frames: 1020444672. Throughput: 0: 49641.2. Samples: 255078304. Policy #0 lag: (min: 1.0, avg: 17.0, max: 33.0) [2023-03-09 08:51:59,063][22664] Avg episode reward: [(0, '51.409')] [2023-03-09 08:51:59,784][23090] Updated weights for policy 0, policy_version 62292 (0.0024) [2023-03-09 08:52:00,553][23090] Updated weights for policy 0, policy_version 62302 (0.0016) [2023-03-09 08:52:01,400][23090] Updated weights for policy 0, policy_version 62312 (0.0017) [2023-03-09 08:52:02,263][23090] Updated weights for policy 0, policy_version 62322 (0.0016) [2023-03-09 08:52:03,043][23090] Updated weights for policy 0, policy_version 62332 (0.0013) [2023-03-09 08:52:03,933][23090] Updated weights for policy 0, policy_version 62343 (0.0019) [2023-03-09 08:52:04,059][22664] Fps is (10 sec: 199884.8, 60 sec: 198519.3, 300 sec: 198607.3). Total num frames: 1021444096. Throughput: 0: 49686.4. Samples: 255375200. Policy #0 lag: (min: 1.0, avg: 17.0, max: 33.0) [2023-03-09 08:52:04,060][22664] Avg episode reward: [(0, '53.547')] [2023-03-09 08:52:04,817][23090] Updated weights for policy 0, policy_version 62353 (0.0013) [2023-03-09 08:52:05,307][22940] Signal inference workers to stop experience collection... (19950 times) [2023-03-09 08:52:05,321][22940] Signal inference workers to resume experience collection... (19950 times) [2023-03-09 08:52:05,378][23090] InferenceWorker_p0-w0: stopping experience collection (19950 times) [2023-03-09 08:52:05,378][23090] InferenceWorker_p0-w0: resuming experience collection (19950 times) [2023-03-09 08:52:05,585][23090] Updated weights for policy 0, policy_version 62363 (0.0016) [2023-03-09 08:52:06,472][23090] Updated weights for policy 0, policy_version 62374 (0.0019) [2023-03-09 08:52:07,326][23090] Updated weights for policy 0, policy_version 62384 (0.0018) [2023-03-09 08:52:08,187][23090] Updated weights for policy 0, policy_version 62394 (0.0015) [2023-03-09 08:52:08,887][23090] Updated weights for policy 0, policy_version 62404 (0.0013) [2023-03-09 08:52:09,059][22664] Fps is (10 sec: 199880.5, 60 sec: 198791.9, 300 sec: 198551.6). Total num frames: 1022443520. Throughput: 0: 49643.4. Samples: 255674192. Policy #0 lag: (min: 1.0, avg: 17.0, max: 33.0) [2023-03-09 08:52:09,061][22664] Avg episode reward: [(0, '54.238')] [2023-03-09 08:52:09,813][23090] Updated weights for policy 0, policy_version 62414 (0.0017) [2023-03-09 08:52:10,626][23090] Updated weights for policy 0, policy_version 62424 (0.0016) [2023-03-09 08:52:11,405][23090] Updated weights for policy 0, policy_version 62434 (0.0013) [2023-03-09 08:52:12,444][23090] Updated weights for policy 0, policy_version 62446 (0.0017) [2023-03-09 08:52:13,284][23090] Updated weights for policy 0, policy_version 62456 (0.0013) [2023-03-09 08:52:14,059][22664] Fps is (10 sec: 199885.0, 60 sec: 198519.2, 300 sec: 198552.1). Total num frames: 1023442944. Throughput: 0: 49688.7. Samples: 255823664. Policy #0 lag: (min: 1.0, avg: 17.0, max: 33.0) [2023-03-09 08:52:14,060][22664] Avg episode reward: [(0, '52.142')] [2023-03-09 08:52:14,086][23090] Updated weights for policy 0, policy_version 62466 (0.0015) [2023-03-09 08:52:14,899][23090] Updated weights for policy 0, policy_version 62476 (0.0020) [2023-03-09 08:52:15,773][23090] Updated weights for policy 0, policy_version 62486 (0.0013) [2023-03-09 08:52:16,575][23090] Updated weights for policy 0, policy_version 62496 (0.0013) [2023-03-09 08:52:17,322][23090] Updated weights for policy 0, policy_version 62506 (0.0018) [2023-03-09 08:52:18,280][23090] Updated weights for policy 0, policy_version 62516 (0.0017) [2023-03-09 08:52:18,726][22940] Signal inference workers to stop experience collection... (20000 times) [2023-03-09 08:52:18,746][22940] Signal inference workers to resume experience collection... (20000 times) [2023-03-09 08:52:18,809][23090] InferenceWorker_p0-w0: stopping experience collection (20000 times) [2023-03-09 08:52:18,809][23090] InferenceWorker_p0-w0: resuming experience collection (20000 times) [2023-03-09 08:52:19,011][23090] Updated weights for policy 0, policy_version 62526 (0.0016) [2023-03-09 08:52:19,059][22664] Fps is (10 sec: 198245.9, 60 sec: 198518.8, 300 sec: 198496.2). Total num frames: 1024425984. Throughput: 0: 49597.4. Samples: 256118528. Policy #0 lag: (min: 1.0, avg: 17.0, max: 33.0) [2023-03-09 08:52:19,061][22664] Avg episode reward: [(0, '51.646')] [2023-03-09 08:52:19,869][23090] Updated weights for policy 0, policy_version 62536 (0.0013) [2023-03-09 08:52:20,758][23090] Updated weights for policy 0, policy_version 62546 (0.0016) [2023-03-09 08:52:21,521][23090] Updated weights for policy 0, policy_version 62556 (0.0013) [2023-03-09 08:52:22,340][23090] Updated weights for policy 0, policy_version 62566 (0.0017) [2023-03-09 08:52:23,224][23090] Updated weights for policy 0, policy_version 62576 (0.0013) [2023-03-09 08:52:24,059][22664] Fps is (10 sec: 194967.0, 60 sec: 197699.6, 300 sec: 198385.1). Total num frames: 1025392640. Throughput: 0: 49597.3. Samples: 256415408. Policy #0 lag: (min: 1.0, avg: 17.0, max: 33.0) [2023-03-09 08:52:24,061][22664] Avg episode reward: [(0, '55.553')] [2023-03-09 08:52:24,098][23090] Updated weights for policy 0, policy_version 62586 (0.0013) [2023-03-09 08:52:24,833][23090] Updated weights for policy 0, policy_version 62596 (0.0026) [2023-03-09 08:52:25,699][23090] Updated weights for policy 0, policy_version 62606 (0.0016) [2023-03-09 08:52:26,576][23090] Updated weights for policy 0, policy_version 62616 (0.0017) [2023-03-09 08:52:27,360][23090] Updated weights for policy 0, policy_version 62626 (0.0019) [2023-03-09 08:52:28,193][23090] Updated weights for policy 0, policy_version 62636 (0.0020) [2023-03-09 08:52:29,049][23090] Updated weights for policy 0, policy_version 62646 (0.0013) [2023-03-09 08:52:29,059][22664] Fps is (10 sec: 196607.7, 60 sec: 198245.0, 300 sec: 198385.1). Total num frames: 1026392064. Throughput: 0: 49642.7. Samples: 256564864. Policy #0 lag: (min: 1.0, avg: 17.0, max: 33.0) [2023-03-09 08:52:29,061][22664] Avg episode reward: [(0, '54.297')] [2023-03-09 08:52:29,829][23090] Updated weights for policy 0, policy_version 62656 (0.0016) [2023-03-09 08:52:30,597][23090] Updated weights for policy 0, policy_version 62666 (0.0013) [2023-03-09 08:52:31,524][23090] Updated weights for policy 0, policy_version 62676 (0.0017) [2023-03-09 08:52:32,303][23090] Updated weights for policy 0, policy_version 62686 (0.0016) [2023-03-09 08:52:33,221][23090] Updated weights for policy 0, policy_version 62697 (0.0016) [2023-03-09 08:52:34,059][22664] Fps is (10 sec: 198250.2, 60 sec: 198246.1, 300 sec: 198385.4). Total num frames: 1027375104. Throughput: 0: 49552.2. Samples: 256859728. Policy #0 lag: (min: 1.0, avg: 16.5, max: 32.0) [2023-03-09 08:52:34,060][22664] Avg episode reward: [(0, '54.853')] [2023-03-09 08:52:34,103][23090] Updated weights for policy 0, policy_version 62707 (0.0013) [2023-03-09 08:52:34,843][23090] Updated weights for policy 0, policy_version 62717 (0.0019) [2023-03-09 08:52:35,773][22940] Signal inference workers to stop experience collection... (20050 times) [2023-03-09 08:52:35,776][22940] Signal inference workers to resume experience collection... (20050 times) [2023-03-09 08:52:35,803][23090] Updated weights for policy 0, policy_version 62728 (0.0013) [2023-03-09 08:52:35,852][23090] InferenceWorker_p0-w0: stopping experience collection (20050 times) [2023-03-09 08:52:35,890][23090] InferenceWorker_p0-w0: resuming experience collection (20050 times) [2023-03-09 08:52:36,653][23090] Updated weights for policy 0, policy_version 62738 (0.0017) [2023-03-09 08:52:37,438][23090] Updated weights for policy 0, policy_version 62748 (0.0019) [2023-03-09 08:52:38,277][23090] Updated weights for policy 0, policy_version 62758 (0.0017) [2023-03-09 08:52:39,059][22664] Fps is (10 sec: 196615.3, 60 sec: 198246.7, 300 sec: 198329.8). Total num frames: 1028358144. Throughput: 0: 49553.2. Samples: 257156656. Policy #0 lag: (min: 1.0, avg: 16.5, max: 32.0) [2023-03-09 08:52:39,060][22664] Avg episode reward: [(0, '52.300')] [2023-03-09 08:52:39,156][23090] Updated weights for policy 0, policy_version 62768 (0.0022) [2023-03-09 08:52:40,017][23090] Updated weights for policy 0, policy_version 62778 (0.0013) [2023-03-09 08:52:40,754][23090] Updated weights for policy 0, policy_version 62788 (0.0017) [2023-03-09 08:52:41,628][23090] Updated weights for policy 0, policy_version 62798 (0.0016) [2023-03-09 08:52:42,514][23090] Updated weights for policy 0, policy_version 62808 (0.0017) [2023-03-09 08:52:43,232][23090] Updated weights for policy 0, policy_version 62818 (0.0013) [2023-03-09 08:52:44,059][22664] Fps is (10 sec: 198246.0, 60 sec: 198248.4, 300 sec: 198440.7). Total num frames: 1029357568. Throughput: 0: 49506.2. Samples: 257306080. Policy #0 lag: (min: 1.0, avg: 16.5, max: 32.0) [2023-03-09 08:52:44,060][22664] Avg episode reward: [(0, '52.408')] [2023-03-09 08:52:44,127][23090] Updated weights for policy 0, policy_version 62828 (0.0013) [2023-03-09 08:52:45,136][23090] Updated weights for policy 0, policy_version 62839 (0.0015) [2023-03-09 08:52:45,795][23090] Updated weights for policy 0, policy_version 62849 (0.0013) [2023-03-09 08:52:46,594][23090] Updated weights for policy 0, policy_version 62859 (0.0018) [2023-03-09 08:52:47,544][23090] Updated weights for policy 0, policy_version 62869 (0.0013) [2023-03-09 08:52:48,311][23090] Updated weights for policy 0, policy_version 62879 (0.0027) [2023-03-09 08:52:49,059][22664] Fps is (10 sec: 201523.0, 60 sec: 198793.3, 300 sec: 198496.4). Total num frames: 1030373376. Throughput: 0: 49505.9. Samples: 257602960. Policy #0 lag: (min: 1.0, avg: 16.5, max: 32.0) [2023-03-09 08:52:49,060][22664] Avg episode reward: [(0, '54.096')] [2023-03-09 08:52:49,072][23090] Updated weights for policy 0, policy_version 62889 (0.0020) [2023-03-09 08:52:49,981][23090] Updated weights for policy 0, policy_version 62899 (0.0013) [2023-03-09 08:52:50,718][23090] Updated weights for policy 0, policy_version 62909 (0.0013) [2023-03-09 08:52:50,944][22940] Signal inference workers to stop experience collection... (20100 times) [2023-03-09 08:52:50,945][22940] Signal inference workers to resume experience collection... (20100 times) [2023-03-09 08:52:51,006][23090] InferenceWorker_p0-w0: stopping experience collection (20100 times) [2023-03-09 08:52:51,007][23090] InferenceWorker_p0-w0: resuming experience collection (20100 times) [2023-03-09 08:52:51,595][23090] Updated weights for policy 0, policy_version 62919 (0.0019) [2023-03-09 08:52:52,485][23090] Updated weights for policy 0, policy_version 62929 (0.0019) [2023-03-09 08:52:53,251][23090] Updated weights for policy 0, policy_version 62939 (0.0013) [2023-03-09 08:52:54,031][23090] Updated weights for policy 0, policy_version 62949 (0.0019) [2023-03-09 08:52:54,058][22664] Fps is (10 sec: 199887.2, 60 sec: 198520.0, 300 sec: 198440.9). Total num frames: 1031356416. Throughput: 0: 49503.7. Samples: 257901840. Policy #0 lag: (min: 1.0, avg: 16.5, max: 32.0) [2023-03-09 08:52:54,059][22664] Avg episode reward: [(0, '51.264')] [2023-03-09 08:52:54,900][23090] Updated weights for policy 0, policy_version 62959 (0.0017) [2023-03-09 08:52:55,797][23090] Updated weights for policy 0, policy_version 62969 (0.0023) [2023-03-09 08:52:56,505][23090] Updated weights for policy 0, policy_version 62979 (0.0017) [2023-03-09 08:52:57,493][23090] Updated weights for policy 0, policy_version 62990 (0.0024) [2023-03-09 08:52:58,388][23090] Updated weights for policy 0, policy_version 63000 (0.0022) [2023-03-09 08:52:59,059][22664] Fps is (10 sec: 196604.5, 60 sec: 198246.2, 300 sec: 198440.6). Total num frames: 1032339456. Throughput: 0: 49503.2. Samples: 258051312. Policy #0 lag: (min: 1.0, avg: 16.5, max: 32.0) [2023-03-09 08:52:59,061][22664] Avg episode reward: [(0, '53.058')] [2023-03-09 08:52:59,083][23090] Updated weights for policy 0, policy_version 63010 (0.0018) [2023-03-09 08:53:00,034][23090] Updated weights for policy 0, policy_version 63021 (0.0019) [2023-03-09 08:53:00,914][23090] Updated weights for policy 0, policy_version 63031 (0.0013) [2023-03-09 08:53:01,613][23090] Updated weights for policy 0, policy_version 63041 (0.0022) [2023-03-09 08:53:02,446][23090] Updated weights for policy 0, policy_version 63051 (0.0016) [2023-03-09 08:53:03,344][23090] Updated weights for policy 0, policy_version 63061 (0.0013) [2023-03-09 08:53:04,059][22664] Fps is (10 sec: 198246.0, 60 sec: 198246.9, 300 sec: 198385.2). Total num frames: 1033338880. Throughput: 0: 49548.8. Samples: 258348208. Policy #0 lag: (min: 1.0, avg: 16.5, max: 32.0) [2023-03-09 08:53:04,060][22664] Avg episode reward: [(0, '52.574')] [2023-03-09 08:53:04,203][23090] Updated weights for policy 0, policy_version 63072 (0.0013) [2023-03-09 08:53:04,342][22940] Signal inference workers to stop experience collection... (20150 times) [2023-03-09 08:53:04,344][22940] Signal inference workers to resume experience collection... (20150 times) [2023-03-09 08:53:04,409][23090] InferenceWorker_p0-w0: stopping experience collection (20150 times) [2023-03-09 08:53:04,412][23090] InferenceWorker_p0-w0: resuming experience collection (20150 times) [2023-03-09 08:53:05,080][23090] Updated weights for policy 0, policy_version 63083 (0.0015) [2023-03-09 08:53:06,011][23090] Updated weights for policy 0, policy_version 63093 (0.0017) [2023-03-09 08:53:06,840][23090] Updated weights for policy 0, policy_version 63104 (0.0013) [2023-03-09 08:53:07,655][23090] Updated weights for policy 0, policy_version 63114 (0.0016) [2023-03-09 08:53:08,529][23090] Updated weights for policy 0, policy_version 63124 (0.0024) [2023-03-09 08:53:09,059][22664] Fps is (10 sec: 199885.2, 60 sec: 198246.9, 300 sec: 198440.8). Total num frames: 1034338304. Throughput: 0: 49593.3. Samples: 258647104. Policy #0 lag: (min: 1.0, avg: 16.5, max: 32.0) [2023-03-09 08:53:09,061][22664] Avg episode reward: [(0, '53.868')] [2023-03-09 08:53:09,265][23090] Updated weights for policy 0, policy_version 63134 (0.0013) [2023-03-09 08:53:10,140][23090] Updated weights for policy 0, policy_version 63144 (0.0017) [2023-03-09 08:53:10,978][23090] Updated weights for policy 0, policy_version 63154 (0.0013) [2023-03-09 08:53:11,771][23090] Updated weights for policy 0, policy_version 63164 (0.0013) [2023-03-09 08:53:12,579][23090] Updated weights for policy 0, policy_version 63174 (0.0015) [2023-03-09 08:53:13,389][23090] Updated weights for policy 0, policy_version 63184 (0.0013) [2023-03-09 08:53:14,059][22664] Fps is (10 sec: 198241.8, 60 sec: 197973.0, 300 sec: 198440.7). Total num frames: 1035321344. Throughput: 0: 49594.1. Samples: 258796592. Policy #0 lag: (min: 1.0, avg: 17.6, max: 33.0) [2023-03-09 08:53:14,061][22664] Avg episode reward: [(0, '53.043')] [2023-03-09 08:53:14,261][23090] Updated weights for policy 0, policy_version 63194 (0.0013) [2023-03-09 08:53:14,953][23090] Updated weights for policy 0, policy_version 63204 (0.0017) [2023-03-09 08:53:15,857][23090] Updated weights for policy 0, policy_version 63214 (0.0014) [2023-03-09 08:53:16,792][23090] Updated weights for policy 0, policy_version 63224 (0.0021) [2023-03-09 08:53:17,062][22940] Signal inference workers to stop experience collection... (20200 times) [2023-03-09 08:53:17,063][22940] Signal inference workers to resume experience collection... (20200 times) [2023-03-09 08:53:17,127][23090] InferenceWorker_p0-w0: stopping experience collection (20200 times) [2023-03-09 08:53:17,127][23090] InferenceWorker_p0-w0: resuming experience collection (20200 times) [2023-03-09 08:53:17,492][23090] Updated weights for policy 0, policy_version 63234 (0.0019) [2023-03-09 08:53:18,378][23090] Updated weights for policy 0, policy_version 63244 (0.0018) [2023-03-09 08:53:19,059][22664] Fps is (10 sec: 198243.8, 60 sec: 198246.6, 300 sec: 198440.8). Total num frames: 1036320768. Throughput: 0: 49682.6. Samples: 259095456. Policy #0 lag: (min: 1.0, avg: 17.6, max: 33.0) [2023-03-09 08:53:19,061][22664] Avg episode reward: [(0, '51.186')] [2023-03-09 08:53:19,066][22940] Saving /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000063252_1036320768.pth... [2023-03-09 08:53:19,132][22940] Removing /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000060344_988676096.pth [2023-03-09 08:53:19,253][23090] Updated weights for policy 0, policy_version 63254 (0.0016) [2023-03-09 08:53:20,000][23090] Updated weights for policy 0, policy_version 63264 (0.0013) [2023-03-09 08:53:20,797][23090] Updated weights for policy 0, policy_version 63274 (0.0017) [2023-03-09 08:53:21,708][23090] Updated weights for policy 0, policy_version 63284 (0.0013) [2023-03-09 08:53:22,444][23090] Updated weights for policy 0, policy_version 63294 (0.0017) [2023-03-09 08:53:23,299][23090] Updated weights for policy 0, policy_version 63304 (0.0018) [2023-03-09 08:53:24,059][22664] Fps is (10 sec: 198246.1, 60 sec: 198519.5, 300 sec: 198440.6). Total num frames: 1037303808. Throughput: 0: 49682.2. Samples: 259392368. Policy #0 lag: (min: 1.0, avg: 17.6, max: 33.0) [2023-03-09 08:53:24,061][22664] Avg episode reward: [(0, '52.376')] [2023-03-09 08:53:24,247][23090] Updated weights for policy 0, policy_version 63315 (0.0013) [2023-03-09 08:53:25,019][23090] Updated weights for policy 0, policy_version 63325 (0.0020) [2023-03-09 08:53:25,828][23090] Updated weights for policy 0, policy_version 63335 (0.0017) [2023-03-09 08:53:26,747][23090] Updated weights for policy 0, policy_version 63345 (0.0017) [2023-03-09 08:53:27,487][23090] Updated weights for policy 0, policy_version 63355 (0.0018) [2023-03-09 08:53:28,288][23090] Updated weights for policy 0, policy_version 63365 (0.0013) [2023-03-09 08:53:29,059][22664] Fps is (10 sec: 199885.4, 60 sec: 198792.9, 300 sec: 198496.1). Total num frames: 1038319616. Throughput: 0: 49728.1. Samples: 259543856. Policy #0 lag: (min: 1.0, avg: 17.6, max: 33.0) [2023-03-09 08:53:29,061][22664] Avg episode reward: [(0, '51.738')] [2023-03-09 08:53:29,170][23090] Updated weights for policy 0, policy_version 63375 (0.0014) [2023-03-09 08:53:30,026][22940] Signal inference workers to stop experience collection... (20250 times) [2023-03-09 08:53:30,040][22940] Signal inference workers to resume experience collection... (20250 times) [2023-03-09 08:53:30,061][23090] Updated weights for policy 0, policy_version 63385 (0.0013) [2023-03-09 08:53:30,098][23090] InferenceWorker_p0-w0: stopping experience collection (20250 times) [2023-03-09 08:53:30,101][23090] InferenceWorker_p0-w0: resuming experience collection (20250 times) [2023-03-09 08:53:30,780][23090] Updated weights for policy 0, policy_version 63395 (0.0013) [2023-03-09 08:53:31,657][23090] Updated weights for policy 0, policy_version 63405 (0.0021) [2023-03-09 08:53:32,544][23090] Updated weights for policy 0, policy_version 63415 (0.0019) [2023-03-09 08:53:33,260][23090] Updated weights for policy 0, policy_version 63425 (0.0014) [2023-03-09 08:53:34,034][23090] Updated weights for policy 0, policy_version 63435 (0.0016) [2023-03-09 08:53:34,059][22664] Fps is (10 sec: 201528.1, 60 sec: 199065.8, 300 sec: 198552.0). Total num frames: 1039319040. Throughput: 0: 49728.7. Samples: 259840752. Policy #0 lag: (min: 1.0, avg: 17.6, max: 33.0) [2023-03-09 08:53:34,059][22664] Avg episode reward: [(0, '53.974')] [2023-03-09 08:53:34,997][23090] Updated weights for policy 0, policy_version 63445 (0.0013) [2023-03-09 08:53:35,754][23090] Updated weights for policy 0, policy_version 63455 (0.0013) [2023-03-09 08:53:36,525][23090] Updated weights for policy 0, policy_version 63465 (0.0020) [2023-03-09 08:53:37,438][23090] Updated weights for policy 0, policy_version 63475 (0.0018) [2023-03-09 08:53:38,252][23090] Updated weights for policy 0, policy_version 63485 (0.0013) [2023-03-09 08:53:38,978][23090] Updated weights for policy 0, policy_version 63495 (0.0016) [2023-03-09 08:53:39,059][22664] Fps is (10 sec: 198251.1, 60 sec: 199065.5, 300 sec: 198496.5). Total num frames: 1040302080. Throughput: 0: 49729.7. Samples: 260139680. Policy #0 lag: (min: 1.0, avg: 17.6, max: 33.0) [2023-03-09 08:53:39,060][22664] Avg episode reward: [(0, '53.192')] [2023-03-09 08:53:39,895][23090] Updated weights for policy 0, policy_version 63505 (0.0016) [2023-03-09 08:53:40,670][23090] Updated weights for policy 0, policy_version 63515 (0.0021) [2023-03-09 08:53:41,506][23090] Updated weights for policy 0, policy_version 63525 (0.0015) [2023-03-09 08:53:42,324][23090] Updated weights for policy 0, policy_version 63535 (0.0022) [2023-03-09 08:53:42,931][22940] Signal inference workers to stop experience collection... (20300 times) [2023-03-09 08:53:42,932][22940] Signal inference workers to resume experience collection... (20300 times) [2023-03-09 08:53:42,992][23090] InferenceWorker_p0-w0: stopping experience collection (20300 times) [2023-03-09 08:53:42,995][23090] InferenceWorker_p0-w0: resuming experience collection (20300 times) [2023-03-09 08:53:43,245][23090] Updated weights for policy 0, policy_version 63545 (0.0013) [2023-03-09 08:53:43,928][23090] Updated weights for policy 0, policy_version 63555 (0.0013) [2023-03-09 08:53:44,059][22664] Fps is (10 sec: 198242.5, 60 sec: 199065.3, 300 sec: 198551.9). Total num frames: 1041301504. Throughput: 0: 49684.3. Samples: 260287104. Policy #0 lag: (min: 1.0, avg: 17.6, max: 33.0) [2023-03-09 08:53:44,060][22664] Avg episode reward: [(0, '53.491')] [2023-03-09 08:53:44,846][23090] Updated weights for policy 0, policy_version 63565 (0.0018) [2023-03-09 08:53:45,688][23090] Updated weights for policy 0, policy_version 63575 (0.0015) [2023-03-09 08:53:46,429][23090] Updated weights for policy 0, policy_version 63585 (0.0020) [2023-03-09 08:53:47,204][23090] Updated weights for policy 0, policy_version 63595 (0.0015) [2023-03-09 08:53:48,167][23090] Updated weights for policy 0, policy_version 63605 (0.0015) [2023-03-09 08:53:48,887][23090] Updated weights for policy 0, policy_version 63615 (0.0015) [2023-03-09 08:53:49,059][22664] Fps is (10 sec: 199881.1, 60 sec: 198791.8, 300 sec: 198551.8). Total num frames: 1042300928. Throughput: 0: 49775.0. Samples: 260588096. Policy #0 lag: (min: 1.0, avg: 17.6, max: 33.0) [2023-03-09 08:53:49,061][22664] Avg episode reward: [(0, '54.116')] [2023-03-09 08:53:49,655][23090] Updated weights for policy 0, policy_version 63625 (0.0017) [2023-03-09 08:53:50,557][23090] Updated weights for policy 0, policy_version 63635 (0.0017) [2023-03-09 08:53:51,351][23090] Updated weights for policy 0, policy_version 63645 (0.0013) [2023-03-09 08:53:52,111][23090] Updated weights for policy 0, policy_version 63655 (0.0018) [2023-03-09 08:53:52,990][23090] Updated weights for policy 0, policy_version 63665 (0.0016) [2023-03-09 08:53:53,863][23090] Updated weights for policy 0, policy_version 63675 (0.0013) [2023-03-09 08:53:54,058][22664] Fps is (10 sec: 199889.9, 60 sec: 199065.7, 300 sec: 198552.0). Total num frames: 1043300352. Throughput: 0: 49774.1. Samples: 260886928. Policy #0 lag: (min: 1.0, avg: 16.9, max: 33.0) [2023-03-09 08:53:54,059][22664] Avg episode reward: [(0, '53.306')] [2023-03-09 08:53:54,605][23090] Updated weights for policy 0, policy_version 63685 (0.0016) [2023-03-09 08:53:55,566][23090] Updated weights for policy 0, policy_version 63696 (0.0013) [2023-03-09 08:53:56,454][23090] Updated weights for policy 0, policy_version 63706 (0.0017) [2023-03-09 08:53:56,665][22940] Signal inference workers to stop experience collection... (20350 times) [2023-03-09 08:53:56,666][22940] Signal inference workers to resume experience collection... (20350 times) [2023-03-09 08:53:56,730][23090] InferenceWorker_p0-w0: stopping experience collection (20350 times) [2023-03-09 08:53:56,731][23090] InferenceWorker_p0-w0: resuming experience collection (20350 times) [2023-03-09 08:53:57,187][23090] Updated weights for policy 0, policy_version 63716 (0.0016) [2023-03-09 08:53:58,110][23090] Updated weights for policy 0, policy_version 63726 (0.0021) [2023-03-09 08:53:58,941][23090] Updated weights for policy 0, policy_version 63736 (0.0013) [2023-03-09 08:53:59,058][22664] Fps is (10 sec: 196613.0, 60 sec: 198793.3, 300 sec: 198440.8). Total num frames: 1044267008. Throughput: 0: 49729.0. Samples: 261034384. Policy #0 lag: (min: 1.0, avg: 16.9, max: 33.0) [2023-03-09 08:53:59,060][22664] Avg episode reward: [(0, '52.413')] [2023-03-09 08:53:59,670][23090] Updated weights for policy 0, policy_version 63746 (0.0013) [2023-03-09 08:54:00,581][23090] Updated weights for policy 0, policy_version 63756 (0.0017) [2023-03-09 08:54:01,389][23090] Updated weights for policy 0, policy_version 63766 (0.0016) [2023-03-09 08:54:02,232][23090] Updated weights for policy 0, policy_version 63777 (0.0013) [2023-03-09 08:54:03,007][23090] Updated weights for policy 0, policy_version 63787 (0.0015) [2023-03-09 08:54:03,992][23090] Updated weights for policy 0, policy_version 63797 (0.0015) [2023-03-09 08:54:04,058][22664] Fps is (10 sec: 196608.0, 60 sec: 198792.7, 300 sec: 198496.5). Total num frames: 1045266432. Throughput: 0: 49774.3. Samples: 261335280. Policy #0 lag: (min: 1.0, avg: 16.9, max: 33.0) [2023-03-09 08:54:04,059][22664] Avg episode reward: [(0, '52.568')] [2023-03-09 08:54:04,685][23090] Updated weights for policy 0, policy_version 63807 (0.0018) [2023-03-09 08:54:05,459][23090] Updated weights for policy 0, policy_version 63817 (0.0013) [2023-03-09 08:54:06,415][23090] Updated weights for policy 0, policy_version 63827 (0.0016) [2023-03-09 08:54:07,155][23090] Updated weights for policy 0, policy_version 63837 (0.0016) [2023-03-09 08:54:07,989][23090] Updated weights for policy 0, policy_version 63847 (0.0016) [2023-03-09 08:54:08,832][23090] Updated weights for policy 0, policy_version 63857 (0.0016) [2023-03-09 08:54:09,058][22664] Fps is (10 sec: 199884.9, 60 sec: 198793.2, 300 sec: 198552.0). Total num frames: 1046265856. Throughput: 0: 49819.3. Samples: 261634224. Policy #0 lag: (min: 1.0, avg: 16.9, max: 33.0) [2023-03-09 08:54:09,060][22664] Avg episode reward: [(0, '55.385')] [2023-03-09 08:54:09,666][23090] Updated weights for policy 0, policy_version 63867 (0.0013) [2023-03-09 08:54:10,405][23090] Updated weights for policy 0, policy_version 63877 (0.0016) [2023-03-09 08:54:11,283][23090] Updated weights for policy 0, policy_version 63887 (0.0013) [2023-03-09 08:54:11,860][22940] Signal inference workers to stop experience collection... (20400 times) [2023-03-09 08:54:11,861][22940] Signal inference workers to resume experience collection... (20400 times) [2023-03-09 08:54:11,921][23090] InferenceWorker_p0-w0: stopping experience collection (20400 times) [2023-03-09 08:54:11,922][23090] InferenceWorker_p0-w0: resuming experience collection (20400 times) [2023-03-09 08:54:12,183][23090] Updated weights for policy 0, policy_version 63897 (0.0018) [2023-03-09 08:54:12,914][23090] Updated weights for policy 0, policy_version 63907 (0.0013) [2023-03-09 08:54:13,892][23090] Updated weights for policy 0, policy_version 63918 (0.0013) [2023-03-09 08:54:14,059][22664] Fps is (10 sec: 199879.8, 60 sec: 199065.7, 300 sec: 198607.3). Total num frames: 1047265280. Throughput: 0: 49726.7. Samples: 261781552. Policy #0 lag: (min: 1.0, avg: 16.9, max: 33.0) [2023-03-09 08:54:14,060][22664] Avg episode reward: [(0, '53.351')] [2023-03-09 08:54:14,737][23090] Updated weights for policy 0, policy_version 63928 (0.0013) [2023-03-09 08:54:15,544][23090] Updated weights for policy 0, policy_version 63939 (0.0013) [2023-03-09 08:54:16,390][23090] Updated weights for policy 0, policy_version 63949 (0.0014) [2023-03-09 08:54:17,339][23090] Updated weights for policy 0, policy_version 63959 (0.0017) [2023-03-09 08:54:17,997][23090] Updated weights for policy 0, policy_version 63969 (0.0013) [2023-03-09 08:54:18,811][23090] Updated weights for policy 0, policy_version 63979 (0.0013) [2023-03-09 08:54:19,059][22664] Fps is (10 sec: 199878.4, 60 sec: 199065.7, 300 sec: 198662.8). Total num frames: 1048264704. Throughput: 0: 49814.4. Samples: 262082416. Policy #0 lag: (min: 1.0, avg: 16.9, max: 33.0) [2023-03-09 08:54:19,061][22664] Avg episode reward: [(0, '54.235')] [2023-03-09 08:54:19,764][23090] Updated weights for policy 0, policy_version 63989 (0.0013) [2023-03-09 08:54:20,458][23090] Updated weights for policy 0, policy_version 63999 (0.0018) [2023-03-09 08:54:21,233][23090] Updated weights for policy 0, policy_version 64009 (0.0013) [2023-03-09 08:54:22,190][23090] Updated weights for policy 0, policy_version 64019 (0.0018) [2023-03-09 08:54:23,041][23090] Updated weights for policy 0, policy_version 64030 (0.0019) [2023-03-09 08:54:23,814][23090] Updated weights for policy 0, policy_version 64040 (0.0020) [2023-03-09 08:54:24,059][22664] Fps is (10 sec: 199883.4, 60 sec: 199338.6, 300 sec: 198662.9). Total num frames: 1049264128. Throughput: 0: 49769.7. Samples: 262379328. Policy #0 lag: (min: 1.0, avg: 16.9, max: 33.0) [2023-03-09 08:54:24,062][22664] Avg episode reward: [(0, '53.412')] [2023-03-09 08:54:24,719][23090] Updated weights for policy 0, policy_version 64050 (0.0019) [2023-03-09 08:54:25,536][23090] Updated weights for policy 0, policy_version 64060 (0.0016) [2023-03-09 08:54:26,321][23090] Updated weights for policy 0, policy_version 64070 (0.0015) [2023-03-09 08:54:27,021][22940] Signal inference workers to stop experience collection... (20450 times) [2023-03-09 08:54:27,022][22940] Signal inference workers to resume experience collection... (20450 times) [2023-03-09 08:54:27,082][23090] InferenceWorker_p0-w0: stopping experience collection (20450 times) [2023-03-09 08:54:27,082][23090] InferenceWorker_p0-w0: resuming experience collection (20450 times) [2023-03-09 08:54:27,131][23090] Updated weights for policy 0, policy_version 64080 (0.0017) [2023-03-09 08:54:28,041][23090] Updated weights for policy 0, policy_version 64090 (0.0019) [2023-03-09 08:54:28,757][23090] Updated weights for policy 0, policy_version 64100 (0.0023) [2023-03-09 08:54:29,058][22664] Fps is (10 sec: 199891.0, 60 sec: 199066.6, 300 sec: 198718.5). Total num frames: 1050263552. Throughput: 0: 49815.4. Samples: 262528784. Policy #0 lag: (min: 1.0, avg: 16.9, max: 33.0) [2023-03-09 08:54:29,059][22664] Avg episode reward: [(0, '53.642')] [2023-03-09 08:54:29,707][23090] Updated weights for policy 0, policy_version 64110 (0.0016) [2023-03-09 08:54:30,549][23090] Updated weights for policy 0, policy_version 64120 (0.0018) [2023-03-09 08:54:31,317][23090] Updated weights for policy 0, policy_version 64130 (0.0013) [2023-03-09 08:54:32,135][23090] Updated weights for policy 0, policy_version 64140 (0.0020) [2023-03-09 08:54:32,980][23090] Updated weights for policy 0, policy_version 64150 (0.0017) [2023-03-09 08:54:33,769][23090] Updated weights for policy 0, policy_version 64160 (0.0015) [2023-03-09 08:54:34,059][22664] Fps is (10 sec: 199889.2, 60 sec: 199065.5, 300 sec: 198718.6). Total num frames: 1051262976. Throughput: 0: 49769.1. Samples: 262827696. Policy #0 lag: (min: 1.0, avg: 16.0, max: 33.0) [2023-03-09 08:54:34,060][22664] Avg episode reward: [(0, '54.999')] [2023-03-09 08:54:34,555][23090] Updated weights for policy 0, policy_version 64170 (0.0016) [2023-03-09 08:54:35,480][23090] Updated weights for policy 0, policy_version 64180 (0.0020) [2023-03-09 08:54:36,212][23090] Updated weights for policy 0, policy_version 64190 (0.0017) [2023-03-09 08:54:37,033][23090] Updated weights for policy 0, policy_version 64200 (0.0018) [2023-03-09 08:54:37,890][23090] Updated weights for policy 0, policy_version 64210 (0.0013) [2023-03-09 08:54:38,701][23090] Updated weights for policy 0, policy_version 64220 (0.0013) [2023-03-09 08:54:39,058][22664] Fps is (10 sec: 198246.9, 60 sec: 199065.9, 300 sec: 198718.5). Total num frames: 1052246016. Throughput: 0: 49770.7. Samples: 263126608. Policy #0 lag: (min: 1.0, avg: 16.0, max: 33.0) [2023-03-09 08:54:39,059][22664] Avg episode reward: [(0, '51.190')] [2023-03-09 08:54:39,504][23090] Updated weights for policy 0, policy_version 64230 (0.0015) [2023-03-09 08:54:40,311][23090] Updated weights for policy 0, policy_version 64240 (0.0019) [2023-03-09 08:54:41,114][22940] Signal inference workers to stop experience collection... (20500 times) [2023-03-09 08:54:41,115][22940] Signal inference workers to resume experience collection... (20500 times) [2023-03-09 08:54:41,188][23090] InferenceWorker_p0-w0: stopping experience collection (20500 times) [2023-03-09 08:54:41,188][23090] InferenceWorker_p0-w0: resuming experience collection (20500 times) [2023-03-09 08:54:41,306][23090] Updated weights for policy 0, policy_version 64251 (0.0013) [2023-03-09 08:54:42,074][23090] Updated weights for policy 0, policy_version 64261 (0.0021) [2023-03-09 08:54:42,875][23090] Updated weights for policy 0, policy_version 64271 (0.0017) [2023-03-09 08:54:43,755][23090] Updated weights for policy 0, policy_version 64281 (0.0013) [2023-03-09 08:54:44,059][22664] Fps is (10 sec: 198247.0, 60 sec: 199066.2, 300 sec: 198718.4). Total num frames: 1053245440. Throughput: 0: 49813.7. Samples: 263276000. Policy #0 lag: (min: 1.0, avg: 16.0, max: 33.0) [2023-03-09 08:54:44,060][22664] Avg episode reward: [(0, '52.945')] [2023-03-09 08:54:44,520][23090] Updated weights for policy 0, policy_version 64291 (0.0016) [2023-03-09 08:54:45,366][23090] Updated weights for policy 0, policy_version 64301 (0.0016) [2023-03-09 08:54:46,278][23090] Updated weights for policy 0, policy_version 64311 (0.0022) [2023-03-09 08:54:46,980][23090] Updated weights for policy 0, policy_version 64321 (0.0015) [2023-03-09 08:54:47,801][23090] Updated weights for policy 0, policy_version 64331 (0.0020) [2023-03-09 08:54:48,754][23090] Updated weights for policy 0, policy_version 64341 (0.0020) [2023-03-09 08:54:49,058][22664] Fps is (10 sec: 198246.2, 60 sec: 198793.4, 300 sec: 198774.2). Total num frames: 1054228480. Throughput: 0: 49769.9. Samples: 263574928. Policy #0 lag: (min: 1.0, avg: 16.0, max: 33.0) [2023-03-09 08:54:49,060][22664] Avg episode reward: [(0, '53.183')] [2023-03-09 08:54:49,485][23090] Updated weights for policy 0, policy_version 64351 (0.0013) [2023-03-09 08:54:50,362][23090] Updated weights for policy 0, policy_version 64362 (0.0013) [2023-03-09 08:54:51,306][23090] Updated weights for policy 0, policy_version 64372 (0.0013) [2023-03-09 08:54:52,048][23090] Updated weights for policy 0, policy_version 64382 (0.0017) [2023-03-09 08:54:52,823][23090] Updated weights for policy 0, policy_version 64392 (0.0016) [2023-03-09 08:54:53,182][22940] Signal inference workers to stop experience collection... (20550 times) [2023-03-09 08:54:53,198][22940] Signal inference workers to resume experience collection... (20550 times) [2023-03-09 08:54:53,277][23090] InferenceWorker_p0-w0: stopping experience collection (20550 times) [2023-03-09 08:54:53,277][23090] InferenceWorker_p0-w0: resuming experience collection (20550 times) [2023-03-09 08:54:53,745][23090] Updated weights for policy 0, policy_version 64402 (0.0013) [2023-03-09 08:54:54,058][22664] Fps is (10 sec: 196609.2, 60 sec: 198519.5, 300 sec: 198718.8). Total num frames: 1055211520. Throughput: 0: 49724.8. Samples: 263871840. Policy #0 lag: (min: 1.0, avg: 16.0, max: 33.0) [2023-03-09 08:54:54,059][22664] Avg episode reward: [(0, '52.627')] [2023-03-09 08:54:54,530][23090] Updated weights for policy 0, policy_version 64412 (0.0017) [2023-03-09 08:54:55,305][23090] Updated weights for policy 0, policy_version 64422 (0.0020) [2023-03-09 08:54:56,270][23090] Updated weights for policy 0, policy_version 64433 (0.0017) [2023-03-09 08:54:57,101][23090] Updated weights for policy 0, policy_version 64443 (0.0018) [2023-03-09 08:54:57,979][23090] Updated weights for policy 0, policy_version 64454 (0.0016) [2023-03-09 08:54:58,826][23090] Updated weights for policy 0, policy_version 64464 (0.0020) [2023-03-09 08:54:59,058][22664] Fps is (10 sec: 198245.5, 60 sec: 199065.5, 300 sec: 198774.2). Total num frames: 1056210944. Throughput: 0: 49727.8. Samples: 264019296. Policy #0 lag: (min: 1.0, avg: 16.0, max: 33.0) [2023-03-09 08:54:59,059][22664] Avg episode reward: [(0, '56.232')] [2023-03-09 08:54:59,065][22940] Saving new best policy, reward=56.232! [2023-03-09 08:54:59,704][23090] Updated weights for policy 0, policy_version 64474 (0.0017) [2023-03-09 08:55:00,446][23090] Updated weights for policy 0, policy_version 64484 (0.0027) [2023-03-09 08:55:01,335][23090] Updated weights for policy 0, policy_version 64494 (0.0013) [2023-03-09 08:55:02,210][23090] Updated weights for policy 0, policy_version 64504 (0.0013) [2023-03-09 08:55:02,987][23090] Updated weights for policy 0, policy_version 64514 (0.0013) [2023-03-09 08:55:03,825][23090] Updated weights for policy 0, policy_version 64524 (0.0013) [2023-03-09 08:55:04,058][22664] Fps is (10 sec: 199884.2, 60 sec: 199065.5, 300 sec: 198829.6). Total num frames: 1057210368. Throughput: 0: 49684.6. Samples: 264318208. Policy #0 lag: (min: 1.0, avg: 16.0, max: 33.0) [2023-03-09 08:55:04,059][22664] Avg episode reward: [(0, '53.562')] [2023-03-09 08:55:04,529][22940] Signal inference workers to stop experience collection... (20600 times) [2023-03-09 08:55:04,531][22940] Signal inference workers to resume experience collection... (20600 times) [2023-03-09 08:55:04,597][23090] InferenceWorker_p0-w0: stopping experience collection (20600 times) [2023-03-09 08:55:04,599][23090] InferenceWorker_p0-w0: resuming experience collection (20600 times) [2023-03-09 08:55:04,644][23090] Updated weights for policy 0, policy_version 64534 (0.0013) [2023-03-09 08:55:05,433][23090] Updated weights for policy 0, policy_version 64544 (0.0017) [2023-03-09 08:55:06,215][23090] Updated weights for policy 0, policy_version 64554 (0.0013) [2023-03-09 08:55:07,157][23090] Updated weights for policy 0, policy_version 64564 (0.0018) [2023-03-09 08:55:07,883][23090] Updated weights for policy 0, policy_version 64574 (0.0019) [2023-03-09 08:55:08,663][23090] Updated weights for policy 0, policy_version 64584 (0.0020) [2023-03-09 08:55:09,059][22664] Fps is (10 sec: 199880.0, 60 sec: 199064.7, 300 sec: 198773.8). Total num frames: 1058209792. Throughput: 0: 49684.3. Samples: 264615120. Policy #0 lag: (min: 1.0, avg: 16.0, max: 33.0) [2023-03-09 08:55:09,061][22664] Avg episode reward: [(0, '54.209')] [2023-03-09 08:55:09,530][23090] Updated weights for policy 0, policy_version 64594 (0.0013) [2023-03-09 08:55:10,346][23090] Updated weights for policy 0, policy_version 64604 (0.0016) [2023-03-09 08:55:11,181][23090] Updated weights for policy 0, policy_version 64614 (0.0013) [2023-03-09 08:55:11,976][23090] Updated weights for policy 0, policy_version 64624 (0.0020) [2023-03-09 08:55:12,856][23090] Updated weights for policy 0, policy_version 64634 (0.0017) [2023-03-09 08:55:13,611][23090] Updated weights for policy 0, policy_version 64644 (0.0013) [2023-03-09 08:55:14,059][22664] Fps is (10 sec: 199879.4, 60 sec: 199065.4, 300 sec: 198773.8). Total num frames: 1059209216. Throughput: 0: 49730.2. Samples: 264766656. Policy #0 lag: (min: 0.0, avg: 15.9, max: 33.0) [2023-03-09 08:55:14,061][22664] Avg episode reward: [(0, '53.037')] [2023-03-09 08:55:14,463][23090] Updated weights for policy 0, policy_version 64654 (0.0022) [2023-03-09 08:55:15,381][23090] Updated weights for policy 0, policy_version 64664 (0.0013) [2023-03-09 08:55:15,418][22940] Signal inference workers to stop experience collection... (20650 times) [2023-03-09 08:55:15,430][22940] Signal inference workers to resume experience collection... (20650 times) [2023-03-09 08:55:15,497][23090] InferenceWorker_p0-w0: stopping experience collection (20650 times) [2023-03-09 08:55:15,497][23090] InferenceWorker_p0-w0: resuming experience collection (20650 times) [2023-03-09 08:55:16,138][23090] Updated weights for policy 0, policy_version 64674 (0.0018) [2023-03-09 08:55:16,926][23090] Updated weights for policy 0, policy_version 64684 (0.0013) [2023-03-09 08:55:17,825][23090] Updated weights for policy 0, policy_version 64694 (0.0021) [2023-03-09 08:55:18,586][23090] Updated weights for policy 0, policy_version 64704 (0.0020) [2023-03-09 08:55:19,059][22664] Fps is (10 sec: 198248.9, 60 sec: 198793.1, 300 sec: 198718.5). Total num frames: 1060192256. Throughput: 0: 49730.8. Samples: 265065584. Policy #0 lag: (min: 0.0, avg: 15.9, max: 33.0) [2023-03-09 08:55:19,060][22664] Avg episode reward: [(0, '51.893')] [2023-03-09 08:55:19,065][22940] Saving /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000064710_1060208640.pth... [2023-03-09 08:55:19,132][22940] Removing /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000061800_1012531200.pth [2023-03-09 08:55:19,387][23090] Updated weights for policy 0, policy_version 64714 (0.0013) [2023-03-09 08:55:20,322][23090] Updated weights for policy 0, policy_version 64724 (0.0013) [2023-03-09 08:55:21,135][23090] Updated weights for policy 0, policy_version 64735 (0.0016) [2023-03-09 08:55:21,927][23090] Updated weights for policy 0, policy_version 64745 (0.0017) [2023-03-09 08:55:22,859][23090] Updated weights for policy 0, policy_version 64755 (0.0013) [2023-03-09 08:55:23,706][23090] Updated weights for policy 0, policy_version 64765 (0.0013) [2023-03-09 08:55:24,058][22664] Fps is (10 sec: 196614.1, 60 sec: 198520.5, 300 sec: 198663.0). Total num frames: 1061175296. Throughput: 0: 49639.8. Samples: 265360400. Policy #0 lag: (min: 0.0, avg: 15.9, max: 33.0) [2023-03-09 08:55:24,059][22664] Avg episode reward: [(0, '52.626')] [2023-03-09 08:55:24,601][23090] Updated weights for policy 0, policy_version 64776 (0.0019) [2023-03-09 08:55:25,413][23090] Updated weights for policy 0, policy_version 64786 (0.0017) [2023-03-09 08:55:26,265][23090] Updated weights for policy 0, policy_version 64796 (0.0017) [2023-03-09 08:55:27,067][23090] Updated weights for policy 0, policy_version 64806 (0.0016) [2023-03-09 08:55:27,564][22940] Signal inference workers to stop experience collection... (20700 times) [2023-03-09 08:55:27,564][22940] Signal inference workers to resume experience collection... (20700 times) [2023-03-09 08:55:27,628][23090] InferenceWorker_p0-w0: stopping experience collection (20700 times) [2023-03-09 08:55:27,629][23090] InferenceWorker_p0-w0: resuming experience collection (20700 times) [2023-03-09 08:55:27,881][23090] Updated weights for policy 0, policy_version 64816 (0.0015) [2023-03-09 08:55:28,795][23090] Updated weights for policy 0, policy_version 64826 (0.0013) [2023-03-09 08:55:29,059][22664] Fps is (10 sec: 198245.8, 60 sec: 198518.9, 300 sec: 198662.9). Total num frames: 1062174720. Throughput: 0: 49596.6. Samples: 265507856. Policy #0 lag: (min: 0.0, avg: 15.9, max: 33.0) [2023-03-09 08:55:29,060][22664] Avg episode reward: [(0, '51.509')] [2023-03-09 08:55:29,531][23090] Updated weights for policy 0, policy_version 64836 (0.0017) [2023-03-09 08:55:30,412][23090] Updated weights for policy 0, policy_version 64846 (0.0014) [2023-03-09 08:55:31,348][23090] Updated weights for policy 0, policy_version 64856 (0.0017) [2023-03-09 08:55:32,131][23090] Updated weights for policy 0, policy_version 64866 (0.0017) [2023-03-09 08:55:32,909][23090] Updated weights for policy 0, policy_version 64876 (0.0020) [2023-03-09 08:55:33,793][23090] Updated weights for policy 0, policy_version 64886 (0.0017) [2023-03-09 08:55:34,059][22664] Fps is (10 sec: 198245.1, 60 sec: 198246.5, 300 sec: 198662.9). Total num frames: 1063157760. Throughput: 0: 49506.4. Samples: 265802720. Policy #0 lag: (min: 0.0, avg: 15.9, max: 33.0) [2023-03-09 08:55:34,060][22664] Avg episode reward: [(0, '53.224')] [2023-03-09 08:55:34,636][23090] Updated weights for policy 0, policy_version 64897 (0.0013) [2023-03-09 08:55:35,445][23090] Updated weights for policy 0, policy_version 64907 (0.0021) [2023-03-09 08:55:36,366][23090] Updated weights for policy 0, policy_version 64917 (0.0016) [2023-03-09 08:55:37,105][23090] Updated weights for policy 0, policy_version 64927 (0.0016) [2023-03-09 08:55:37,867][23090] Updated weights for policy 0, policy_version 64937 (0.0022) [2023-03-09 08:55:38,793][23090] Updated weights for policy 0, policy_version 64947 (0.0013) [2023-03-09 08:55:39,058][22664] Fps is (10 sec: 196612.0, 60 sec: 198246.4, 300 sec: 198607.6). Total num frames: 1064140800. Throughput: 0: 49551.6. Samples: 266101664. Policy #0 lag: (min: 0.0, avg: 15.9, max: 33.0) [2023-03-09 08:55:39,060][22664] Avg episode reward: [(0, '52.465')] [2023-03-09 08:55:39,561][23090] Updated weights for policy 0, policy_version 64957 (0.0013) [2023-03-09 08:55:40,375][23090] Updated weights for policy 0, policy_version 64967 (0.0013) [2023-03-09 08:55:41,299][23090] Updated weights for policy 0, policy_version 64978 (0.0016) [2023-03-09 08:55:41,634][22940] Signal inference workers to stop experience collection... (20750 times) [2023-03-09 08:55:41,638][22940] Signal inference workers to resume experience collection... (20750 times) [2023-03-09 08:55:41,699][23090] InferenceWorker_p0-w0: stopping experience collection (20750 times) [2023-03-09 08:55:41,702][23090] InferenceWorker_p0-w0: resuming experience collection (20750 times) [2023-03-09 08:55:42,262][23090] Updated weights for policy 0, policy_version 64989 (0.0013) [2023-03-09 08:55:43,031][23090] Updated weights for policy 0, policy_version 64999 (0.0016) [2023-03-09 08:55:43,874][23090] Updated weights for policy 0, policy_version 65009 (0.0015) [2023-03-09 08:55:44,059][22664] Fps is (10 sec: 196607.3, 60 sec: 197973.2, 300 sec: 198607.6). Total num frames: 1065123840. Throughput: 0: 49597.1. Samples: 266251168. Policy #0 lag: (min: 0.0, avg: 15.9, max: 33.0) [2023-03-09 08:55:44,060][22664] Avg episode reward: [(0, '51.973')] [2023-03-09 08:55:44,685][23090] Updated weights for policy 0, policy_version 65019 (0.0013) [2023-03-09 08:55:45,501][23090] Updated weights for policy 0, policy_version 65029 (0.0014) [2023-03-09 08:55:46,341][23090] Updated weights for policy 0, policy_version 65039 (0.0018) [2023-03-09 08:55:47,251][23090] Updated weights for policy 0, policy_version 65050 (0.0013) [2023-03-09 08:55:48,033][23090] Updated weights for policy 0, policy_version 65060 (0.0016) [2023-03-09 08:55:48,912][23090] Updated weights for policy 0, policy_version 65070 (0.0016) [2023-03-09 08:55:49,059][22664] Fps is (10 sec: 199883.7, 60 sec: 198519.3, 300 sec: 198718.7). Total num frames: 1066139648. Throughput: 0: 49552.3. Samples: 266548064. Policy #0 lag: (min: 0.0, avg: 15.9, max: 33.0) [2023-03-09 08:55:49,060][22664] Avg episode reward: [(0, '52.426')] [2023-03-09 08:55:49,764][23090] Updated weights for policy 0, policy_version 65080 (0.0017) [2023-03-09 08:55:50,527][23090] Updated weights for policy 0, policy_version 65090 (0.0013) [2023-03-09 08:55:51,336][23090] Updated weights for policy 0, policy_version 65100 (0.0013) [2023-03-09 08:55:52,252][23090] Updated weights for policy 0, policy_version 65110 (0.0013) [2023-03-09 08:55:53,016][23090] Updated weights for policy 0, policy_version 65120 (0.0013) [2023-03-09 08:55:53,798][23090] Updated weights for policy 0, policy_version 65130 (0.0020) [2023-03-09 08:55:54,059][22664] Fps is (10 sec: 199885.4, 60 sec: 198519.3, 300 sec: 198663.0). Total num frames: 1067122688. Throughput: 0: 49552.3. Samples: 266844960. Policy #0 lag: (min: 1.0, avg: 16.4, max: 33.0) [2023-03-09 08:55:54,060][22664] Avg episode reward: [(0, '52.411')] [2023-03-09 08:55:54,722][23090] Updated weights for policy 0, policy_version 65140 (0.0016) [2023-03-09 08:55:55,471][23090] Updated weights for policy 0, policy_version 65150 (0.0013) [2023-03-09 08:55:56,313][23090] Updated weights for policy 0, policy_version 65161 (0.0019) [2023-03-09 08:55:57,253][23090] Updated weights for policy 0, policy_version 65171 (0.0014) [2023-03-09 08:55:58,046][22940] Signal inference workers to stop experience collection... (20800 times) [2023-03-09 08:55:58,054][22940] Signal inference workers to resume experience collection... (20800 times) [2023-03-09 08:55:58,089][23090] Updated weights for policy 0, policy_version 65181 (0.0017) [2023-03-09 08:55:58,122][23090] InferenceWorker_p0-w0: stopping experience collection (20800 times) [2023-03-09 08:55:58,123][23090] InferenceWorker_p0-w0: resuming experience collection (20800 times) [2023-03-09 08:55:58,849][23090] Updated weights for policy 0, policy_version 65191 (0.0013) [2023-03-09 08:55:59,059][22664] Fps is (10 sec: 199881.8, 60 sec: 198792.0, 300 sec: 198662.9). Total num frames: 1068138496. Throughput: 0: 49506.9. Samples: 266994464. Policy #0 lag: (min: 1.0, avg: 16.4, max: 33.0) [2023-03-09 08:55:59,060][22664] Avg episode reward: [(0, '53.377')] [2023-03-09 08:55:59,655][23090] Updated weights for policy 0, policy_version 65201 (0.0013) [2023-03-09 08:56:00,535][23090] Updated weights for policy 0, policy_version 65211 (0.0019) [2023-03-09 08:56:01,278][23090] Updated weights for policy 0, policy_version 65221 (0.0014) [2023-03-09 08:56:02,182][23090] Updated weights for policy 0, policy_version 65231 (0.0013) [2023-03-09 08:56:03,067][23090] Updated weights for policy 0, policy_version 65241 (0.0013) [2023-03-09 08:56:03,802][23090] Updated weights for policy 0, policy_version 65251 (0.0017) [2023-03-09 08:56:04,059][22664] Fps is (10 sec: 199884.2, 60 sec: 198519.3, 300 sec: 198663.0). Total num frames: 1069121536. Throughput: 0: 49507.3. Samples: 267293408. Policy #0 lag: (min: 1.0, avg: 16.4, max: 33.0) [2023-03-09 08:56:04,060][22664] Avg episode reward: [(0, '53.830')] [2023-03-09 08:56:04,609][23090] Updated weights for policy 0, policy_version 65261 (0.0013) [2023-03-09 08:56:05,525][23090] Updated weights for policy 0, policy_version 65271 (0.0015) [2023-03-09 08:56:06,265][23090] Updated weights for policy 0, policy_version 65281 (0.0016) [2023-03-09 08:56:07,077][23090] Updated weights for policy 0, policy_version 65291 (0.0013) [2023-03-09 08:56:08,014][23090] Updated weights for policy 0, policy_version 65301 (0.0019) [2023-03-09 08:56:08,865][23090] Updated weights for policy 0, policy_version 65312 (0.0019) [2023-03-09 08:56:09,058][22664] Fps is (10 sec: 196612.0, 60 sec: 198247.4, 300 sec: 198551.9). Total num frames: 1070104576. Throughput: 0: 49553.4. Samples: 267590304. Policy #0 lag: (min: 1.0, avg: 16.4, max: 33.0) [2023-03-09 08:56:09,059][22664] Avg episode reward: [(0, '50.709')] [2023-03-09 08:56:09,639][23090] Updated weights for policy 0, policy_version 65322 (0.0013) [2023-03-09 08:56:10,597][23090] Updated weights for policy 0, policy_version 65332 (0.0017) [2023-03-09 08:56:11,301][23090] Updated weights for policy 0, policy_version 65342 (0.0013) [2023-03-09 08:56:12,149][23090] Updated weights for policy 0, policy_version 65352 (0.0013) [2023-03-09 08:56:12,992][23090] Updated weights for policy 0, policy_version 65362 (0.0016) [2023-03-09 08:56:13,825][23090] Updated weights for policy 0, policy_version 65372 (0.0013) [2023-03-09 08:56:14,059][22664] Fps is (10 sec: 198246.7, 60 sec: 198247.1, 300 sec: 198607.5). Total num frames: 1071104000. Throughput: 0: 49598.7. Samples: 267739792. Policy #0 lag: (min: 1.0, avg: 16.4, max: 33.0) [2023-03-09 08:56:14,060][22664] Avg episode reward: [(0, '55.595')] [2023-03-09 08:56:14,271][22940] Signal inference workers to stop experience collection... (20850 times) [2023-03-09 08:56:14,280][22940] Signal inference workers to resume experience collection... (20850 times) [2023-03-09 08:56:14,349][23090] InferenceWorker_p0-w0: stopping experience collection (20850 times) [2023-03-09 08:56:14,349][23090] InferenceWorker_p0-w0: resuming experience collection (20850 times) [2023-03-09 08:56:14,624][23090] Updated weights for policy 0, policy_version 65382 (0.0017) [2023-03-09 08:56:15,424][23090] Updated weights for policy 0, policy_version 65392 (0.0026) [2023-03-09 08:56:16,281][23090] Updated weights for policy 0, policy_version 65402 (0.0013) [2023-03-09 08:56:17,029][23090] Updated weights for policy 0, policy_version 65412 (0.0016) [2023-03-09 08:56:17,925][23090] Updated weights for policy 0, policy_version 65422 (0.0020) [2023-03-09 08:56:18,839][23090] Updated weights for policy 0, policy_version 65432 (0.0020) [2023-03-09 08:56:19,059][22664] Fps is (10 sec: 199879.5, 60 sec: 198519.1, 300 sec: 198551.8). Total num frames: 1072103424. Throughput: 0: 49687.9. Samples: 268038688. Policy #0 lag: (min: 1.0, avg: 16.4, max: 33.0) [2023-03-09 08:56:19,061][22664] Avg episode reward: [(0, '52.691')] [2023-03-09 08:56:19,593][23090] Updated weights for policy 0, policy_version 65442 (0.0017) [2023-03-09 08:56:20,391][23090] Updated weights for policy 0, policy_version 65452 (0.0013) [2023-03-09 08:56:21,290][23090] Updated weights for policy 0, policy_version 65462 (0.0016) [2023-03-09 08:56:22,126][23090] Updated weights for policy 0, policy_version 65473 (0.0020) [2023-03-09 08:56:23,019][23090] Updated weights for policy 0, policy_version 65484 (0.0013) [2023-03-09 08:56:23,952][23090] Updated weights for policy 0, policy_version 65494 (0.0021) [2023-03-09 08:56:24,059][22664] Fps is (10 sec: 194969.8, 60 sec: 197973.1, 300 sec: 198496.3). Total num frames: 1073053696. Throughput: 0: 49643.7. Samples: 268335632. Policy #0 lag: (min: 1.0, avg: 16.4, max: 33.0) [2023-03-09 08:56:24,059][22664] Avg episode reward: [(0, '52.142')] [2023-03-09 08:56:24,681][23090] Updated weights for policy 0, policy_version 65504 (0.0020) [2023-03-09 08:56:25,477][23090] Updated weights for policy 0, policy_version 65514 (0.0017) [2023-03-09 08:56:26,409][23090] Updated weights for policy 0, policy_version 65524 (0.0019) [2023-03-09 08:56:27,151][23090] Updated weights for policy 0, policy_version 65534 (0.0023) [2023-03-09 08:56:27,980][23090] Updated weights for policy 0, policy_version 65544 (0.0013) [2023-03-09 08:56:28,837][23090] Updated weights for policy 0, policy_version 65554 (0.0023) [2023-03-09 08:56:29,059][22664] Fps is (10 sec: 194970.9, 60 sec: 197973.3, 300 sec: 198551.7). Total num frames: 1074053120. Throughput: 0: 49642.9. Samples: 268485104. Policy #0 lag: (min: 1.0, avg: 16.4, max: 33.0) [2023-03-09 08:56:29,060][22664] Avg episode reward: [(0, '54.601')] [2023-03-09 08:56:29,390][22940] Signal inference workers to stop experience collection... (20900 times) [2023-03-09 08:56:29,406][22940] Signal inference workers to resume experience collection... (20900 times) [2023-03-09 08:56:29,474][23090] InferenceWorker_p0-w0: stopping experience collection (20900 times) [2023-03-09 08:56:29,475][23090] InferenceWorker_p0-w0: resuming experience collection (20900 times) [2023-03-09 08:56:29,686][23090] Updated weights for policy 0, policy_version 65564 (0.0019) [2023-03-09 08:56:30,453][23090] Updated weights for policy 0, policy_version 65574 (0.0022) [2023-03-09 08:56:31,258][23090] Updated weights for policy 0, policy_version 65584 (0.0016) [2023-03-09 08:56:32,181][23090] Updated weights for policy 0, policy_version 65594 (0.0013) [2023-03-09 08:56:32,989][23090] Updated weights for policy 0, policy_version 65605 (0.0023) [2023-03-09 08:56:33,874][23090] Updated weights for policy 0, policy_version 65615 (0.0013) [2023-03-09 08:56:34,058][22664] Fps is (10 sec: 201524.9, 60 sec: 198519.7, 300 sec: 198663.1). Total num frames: 1075068928. Throughput: 0: 49643.5. Samples: 268782016. Policy #0 lag: (min: 1.0, avg: 17.1, max: 33.0) [2023-03-09 08:56:34,059][22664] Avg episode reward: [(0, '52.164')] [2023-03-09 08:56:34,781][23090] Updated weights for policy 0, policy_version 65625 (0.0015) [2023-03-09 08:56:35,476][23090] Updated weights for policy 0, policy_version 65635 (0.0013) [2023-03-09 08:56:36,419][23090] Updated weights for policy 0, policy_version 65646 (0.0016) [2023-03-09 08:56:37,316][23090] Updated weights for policy 0, policy_version 65656 (0.0020) [2023-03-09 08:56:38,079][23090] Updated weights for policy 0, policy_version 65666 (0.0020) [2023-03-09 08:56:38,850][23090] Updated weights for policy 0, policy_version 65676 (0.0013) [2023-03-09 08:56:39,059][22664] Fps is (10 sec: 201519.7, 60 sec: 198791.3, 300 sec: 198663.2). Total num frames: 1076068352. Throughput: 0: 49686.4. Samples: 269080864. Policy #0 lag: (min: 1.0, avg: 17.1, max: 33.0) [2023-03-09 08:56:39,061][22664] Avg episode reward: [(0, '53.755')] [2023-03-09 08:56:39,751][23090] Updated weights for policy 0, policy_version 65686 (0.0020) [2023-03-09 08:56:40,584][23090] Updated weights for policy 0, policy_version 65697 (0.0013) [2023-03-09 08:56:41,392][23090] Updated weights for policy 0, policy_version 65707 (0.0016) [2023-03-09 08:56:42,307][23090] Updated weights for policy 0, policy_version 65717 (0.0013) [2023-03-09 08:56:42,691][22940] Signal inference workers to stop experience collection... (20950 times) [2023-03-09 08:56:42,691][22940] Signal inference workers to resume experience collection... (20950 times) [2023-03-09 08:56:42,750][23090] InferenceWorker_p0-w0: stopping experience collection (20950 times) [2023-03-09 08:56:42,750][23090] InferenceWorker_p0-w0: resuming experience collection (20950 times) [2023-03-09 08:56:43,118][23090] Updated weights for policy 0, policy_version 65727 (0.0018) [2023-03-09 08:56:43,833][23090] Updated weights for policy 0, policy_version 65737 (0.0013) [2023-03-09 08:56:44,058][22664] Fps is (10 sec: 199884.4, 60 sec: 199065.9, 300 sec: 198718.7). Total num frames: 1077067776. Throughput: 0: 49686.6. Samples: 269230352. Policy #0 lag: (min: 1.0, avg: 17.1, max: 33.0) [2023-03-09 08:56:44,059][22664] Avg episode reward: [(0, '54.912')] [2023-03-09 08:56:44,723][23090] Updated weights for policy 0, policy_version 65747 (0.0013) [2023-03-09 08:56:45,497][23090] Updated weights for policy 0, policy_version 65757 (0.0013) [2023-03-09 08:56:46,406][23090] Updated weights for policy 0, policy_version 65768 (0.0013) [2023-03-09 08:56:47,308][23090] Updated weights for policy 0, policy_version 65778 (0.0018) [2023-03-09 08:56:48,172][23090] Updated weights for policy 0, policy_version 65788 (0.0013) [2023-03-09 08:56:48,933][23090] Updated weights for policy 0, policy_version 65798 (0.0013) [2023-03-09 08:56:49,059][22664] Fps is (10 sec: 201525.9, 60 sec: 199065.0, 300 sec: 198774.0). Total num frames: 1078083584. Throughput: 0: 49640.4. Samples: 269527232. Policy #0 lag: (min: 1.0, avg: 17.1, max: 33.0) [2023-03-09 08:56:49,061][22664] Avg episode reward: [(0, '52.995')] [2023-03-09 08:56:49,726][23090] Updated weights for policy 0, policy_version 65808 (0.0023) [2023-03-09 08:56:50,628][23090] Updated weights for policy 0, policy_version 65818 (0.0013) [2023-03-09 08:56:51,319][23090] Updated weights for policy 0, policy_version 65828 (0.0019) [2023-03-09 08:56:52,271][23090] Updated weights for policy 0, policy_version 65838 (0.0013) [2023-03-09 08:56:53,128][23090] Updated weights for policy 0, policy_version 65848 (0.0023) [2023-03-09 08:56:53,824][23090] Updated weights for policy 0, policy_version 65858 (0.0012) [2023-03-09 08:56:54,058][22664] Fps is (10 sec: 199884.6, 60 sec: 199065.8, 300 sec: 198718.6). Total num frames: 1079066624. Throughput: 0: 49730.8. Samples: 269828192. Policy #0 lag: (min: 1.0, avg: 17.1, max: 33.0) [2023-03-09 08:56:54,059][22664] Avg episode reward: [(0, '53.624')] [2023-03-09 08:56:54,631][23090] Updated weights for policy 0, policy_version 65868 (0.0019) [2023-03-09 08:56:55,536][23090] Updated weights for policy 0, policy_version 65878 (0.0019) [2023-03-09 08:56:55,987][22940] Signal inference workers to stop experience collection... (21000 times) [2023-03-09 08:56:55,988][22940] Signal inference workers to resume experience collection... (21000 times) [2023-03-09 08:56:56,055][23090] InferenceWorker_p0-w0: stopping experience collection (21000 times) [2023-03-09 08:56:56,103][23090] InferenceWorker_p0-w0: resuming experience collection (21000 times) [2023-03-09 08:56:56,304][23090] Updated weights for policy 0, policy_version 65888 (0.0019) [2023-03-09 08:56:57,030][23090] Updated weights for policy 0, policy_version 65898 (0.0016) [2023-03-09 08:56:58,008][23090] Updated weights for policy 0, policy_version 65908 (0.0018) [2023-03-09 08:56:58,715][23090] Updated weights for policy 0, policy_version 65918 (0.0014) [2023-03-09 08:56:59,059][22664] Fps is (10 sec: 196611.1, 60 sec: 198519.9, 300 sec: 198663.0). Total num frames: 1080049664. Throughput: 0: 49775.6. Samples: 269979696. Policy #0 lag: (min: 1.0, avg: 17.1, max: 33.0) [2023-03-09 08:56:59,059][22664] Avg episode reward: [(0, '50.721')] [2023-03-09 08:56:59,555][23090] Updated weights for policy 0, policy_version 65928 (0.0017) [2023-03-09 08:57:00,459][23090] Updated weights for policy 0, policy_version 65938 (0.0012) [2023-03-09 08:57:01,211][23090] Updated weights for policy 0, policy_version 65948 (0.0024) [2023-03-09 08:57:02,022][23090] Updated weights for policy 0, policy_version 65958 (0.0019) [2023-03-09 08:57:02,829][23090] Updated weights for policy 0, policy_version 65968 (0.0023) [2023-03-09 08:57:03,712][23090] Updated weights for policy 0, policy_version 65978 (0.0013) [2023-03-09 08:57:04,058][22664] Fps is (10 sec: 198246.6, 60 sec: 198792.8, 300 sec: 198663.2). Total num frames: 1081049088. Throughput: 0: 49776.3. Samples: 270278608. Policy #0 lag: (min: 1.0, avg: 17.1, max: 33.0) [2023-03-09 08:57:04,059][22664] Avg episode reward: [(0, '55.436')] [2023-03-09 08:57:04,442][23090] Updated weights for policy 0, policy_version 65988 (0.0017) [2023-03-09 08:57:05,324][23090] Updated weights for policy 0, policy_version 65998 (0.0020) [2023-03-09 08:57:06,240][23090] Updated weights for policy 0, policy_version 66008 (0.0013) [2023-03-09 08:57:06,501][22940] Signal inference workers to stop experience collection... (21050 times) [2023-03-09 08:57:06,502][22940] Signal inference workers to resume experience collection... (21050 times) [2023-03-09 08:57:06,571][23090] InferenceWorker_p0-w0: stopping experience collection (21050 times) [2023-03-09 08:57:06,571][23090] InferenceWorker_p0-w0: resuming experience collection (21050 times) [2023-03-09 08:57:06,980][23090] Updated weights for policy 0, policy_version 66018 (0.0013) [2023-03-09 08:57:07,904][23090] Updated weights for policy 0, policy_version 66029 (0.0016) [2023-03-09 08:57:08,841][23090] Updated weights for policy 0, policy_version 66039 (0.0017) [2023-03-09 08:57:09,059][22664] Fps is (10 sec: 199878.7, 60 sec: 199064.3, 300 sec: 198662.8). Total num frames: 1082048512. Throughput: 0: 49773.9. Samples: 270575472. Policy #0 lag: (min: 1.0, avg: 17.1, max: 33.0) [2023-03-09 08:57:09,061][22664] Avg episode reward: [(0, '54.254')] [2023-03-09 08:57:09,551][23090] Updated weights for policy 0, policy_version 66049 (0.0016) [2023-03-09 08:57:10,319][23090] Updated weights for policy 0, policy_version 66059 (0.0013) [2023-03-09 08:57:11,273][23090] Updated weights for policy 0, policy_version 66069 (0.0015) [2023-03-09 08:57:12,015][23090] Updated weights for policy 0, policy_version 66079 (0.0022) [2023-03-09 08:57:12,846][23090] Updated weights for policy 0, policy_version 66090 (0.0020) [2023-03-09 08:57:13,849][23090] Updated weights for policy 0, policy_version 66100 (0.0013) [2023-03-09 08:57:14,059][22664] Fps is (10 sec: 198241.9, 60 sec: 198792.0, 300 sec: 198663.1). Total num frames: 1083031552. Throughput: 0: 49774.2. Samples: 270724944. Policy #0 lag: (min: 0.0, avg: 17.4, max: 32.0) [2023-03-09 08:57:14,061][22664] Avg episode reward: [(0, '53.364')] [2023-03-09 08:57:14,500][23090] Updated weights for policy 0, policy_version 66110 (0.0013) [2023-03-09 08:57:15,319][23090] Updated weights for policy 0, policy_version 66120 (0.0017) [2023-03-09 08:57:16,197][23090] Updated weights for policy 0, policy_version 66130 (0.0015) [2023-03-09 08:57:17,011][23090] Updated weights for policy 0, policy_version 66140 (0.0015) [2023-03-09 08:57:17,830][23090] Updated weights for policy 0, policy_version 66150 (0.0016) [2023-03-09 08:57:17,885][22940] Signal inference workers to stop experience collection... (21100 times) [2023-03-09 08:57:17,887][22940] Signal inference workers to resume experience collection... (21100 times) [2023-03-09 08:57:17,960][23090] InferenceWorker_p0-w0: stopping experience collection (21100 times) [2023-03-09 08:57:17,961][23090] InferenceWorker_p0-w0: resuming experience collection (21100 times) [2023-03-09 08:57:18,593][23090] Updated weights for policy 0, policy_version 66160 (0.0014) [2023-03-09 08:57:19,059][22664] Fps is (10 sec: 196608.3, 60 sec: 198519.1, 300 sec: 198718.4). Total num frames: 1084014592. Throughput: 0: 49862.7. Samples: 271025856. Policy #0 lag: (min: 0.0, avg: 17.4, max: 32.0) [2023-03-09 08:57:19,061][22664] Avg episode reward: [(0, '52.209')] [2023-03-09 08:57:19,114][22940] Saving /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000066165_1084047360.pth... [2023-03-09 08:57:19,172][22940] Removing /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000063252_1036320768.pth [2023-03-09 08:57:19,542][23090] Updated weights for policy 0, policy_version 66170 (0.0013) [2023-03-09 08:57:20,237][23090] Updated weights for policy 0, policy_version 66180 (0.0026) [2023-03-09 08:57:21,120][23090] Updated weights for policy 0, policy_version 66190 (0.0020) [2023-03-09 08:57:22,051][23090] Updated weights for policy 0, policy_version 66200 (0.0013) [2023-03-09 08:57:22,754][23090] Updated weights for policy 0, policy_version 66210 (0.0020) [2023-03-09 08:57:23,681][23090] Updated weights for policy 0, policy_version 66221 (0.0015) [2023-03-09 08:57:24,059][22664] Fps is (10 sec: 199884.3, 60 sec: 199611.1, 300 sec: 198774.1). Total num frames: 1085030400. Throughput: 0: 49819.2. Samples: 271322720. Policy #0 lag: (min: 0.0, avg: 17.4, max: 32.0) [2023-03-09 08:57:24,060][22664] Avg episode reward: [(0, '53.519')] [2023-03-09 08:57:24,648][23090] Updated weights for policy 0, policy_version 66231 (0.0019) [2023-03-09 08:57:25,375][23090] Updated weights for policy 0, policy_version 66241 (0.0016) [2023-03-09 08:57:26,097][23090] Updated weights for policy 0, policy_version 66251 (0.0013) [2023-03-09 08:57:27,049][23090] Updated weights for policy 0, policy_version 66261 (0.0016) [2023-03-09 08:57:27,789][23090] Updated weights for policy 0, policy_version 66271 (0.0014) [2023-03-09 08:57:28,521][23090] Updated weights for policy 0, policy_version 66281 (0.0027) [2023-03-09 08:57:29,059][22664] Fps is (10 sec: 203162.0, 60 sec: 199884.3, 300 sec: 198884.9). Total num frames: 1086046208. Throughput: 0: 49817.2. Samples: 271472144. Policy #0 lag: (min: 0.0, avg: 17.4, max: 32.0) [2023-03-09 08:57:29,061][22664] Avg episode reward: [(0, '54.407')] [2023-03-09 08:57:29,480][23090] Updated weights for policy 0, policy_version 66291 (0.0019) [2023-03-09 08:57:29,824][22940] Signal inference workers to stop experience collection... (21150 times) [2023-03-09 08:57:29,856][22940] Signal inference workers to resume experience collection... (21150 times) [2023-03-09 08:57:29,880][23090] InferenceWorker_p0-w0: stopping experience collection (21150 times) [2023-03-09 08:57:29,952][23090] InferenceWorker_p0-w0: resuming experience collection (21150 times) [2023-03-09 08:57:30,238][23090] Updated weights for policy 0, policy_version 66301 (0.0013) [2023-03-09 08:57:31,012][23090] Updated weights for policy 0, policy_version 66311 (0.0020) [2023-03-09 08:57:31,896][23090] Updated weights for policy 0, policy_version 66321 (0.0017) [2023-03-09 08:57:32,754][23090] Updated weights for policy 0, policy_version 66331 (0.0016) [2023-03-09 08:57:33,454][23090] Updated weights for policy 0, policy_version 66341 (0.0019) [2023-03-09 08:57:34,059][22664] Fps is (10 sec: 199883.9, 60 sec: 199337.6, 300 sec: 198884.9). Total num frames: 1087029248. Throughput: 0: 49909.3. Samples: 271773152. Policy #0 lag: (min: 0.0, avg: 17.4, max: 32.0) [2023-03-09 08:57:34,061][22664] Avg episode reward: [(0, '52.632')] [2023-03-09 08:57:34,372][23090] Updated weights for policy 0, policy_version 66351 (0.0013) [2023-03-09 08:57:35,285][23090] Updated weights for policy 0, policy_version 66361 (0.0013) [2023-03-09 08:57:36,008][23090] Updated weights for policy 0, policy_version 66371 (0.0020) [2023-03-09 08:57:36,819][23090] Updated weights for policy 0, policy_version 66381 (0.0016) [2023-03-09 08:57:37,822][23090] Updated weights for policy 0, policy_version 66391 (0.0015) [2023-03-09 08:57:38,479][23090] Updated weights for policy 0, policy_version 66401 (0.0016) [2023-03-09 08:57:39,059][22664] Fps is (10 sec: 198247.5, 60 sec: 199338.9, 300 sec: 198885.0). Total num frames: 1088028672. Throughput: 0: 49818.0. Samples: 272070016. Policy #0 lag: (min: 0.0, avg: 17.4, max: 32.0) [2023-03-09 08:57:39,061][22664] Avg episode reward: [(0, '51.184')] [2023-03-09 08:57:39,285][23090] Updated weights for policy 0, policy_version 66411 (0.0016) [2023-03-09 08:57:40,252][23090] Updated weights for policy 0, policy_version 66421 (0.0016) [2023-03-09 08:57:40,746][22940] Signal inference workers to stop experience collection... (21200 times) [2023-03-09 08:57:40,747][22940] Signal inference workers to resume experience collection... (21200 times) [2023-03-09 08:57:40,811][23090] InferenceWorker_p0-w0: stopping experience collection (21200 times) [2023-03-09 08:57:40,811][23090] InferenceWorker_p0-w0: resuming experience collection (21200 times) [2023-03-09 08:57:40,979][23090] Updated weights for policy 0, policy_version 66431 (0.0022) [2023-03-09 08:57:41,720][23090] Updated weights for policy 0, policy_version 66441 (0.0024) [2023-03-09 08:57:42,674][23090] Updated weights for policy 0, policy_version 66451 (0.0013) [2023-03-09 08:57:43,452][23090] Updated weights for policy 0, policy_version 66461 (0.0018) [2023-03-09 08:57:44,058][22664] Fps is (10 sec: 199890.2, 60 sec: 199338.6, 300 sec: 198829.6). Total num frames: 1089028096. Throughput: 0: 49773.2. Samples: 272219488. Policy #0 lag: (min: 0.0, avg: 17.4, max: 32.0) [2023-03-09 08:57:44,059][22664] Avg episode reward: [(0, '52.709')] [2023-03-09 08:57:44,260][23090] Updated weights for policy 0, policy_version 66471 (0.0019) [2023-03-09 08:57:45,111][23090] Updated weights for policy 0, policy_version 66481 (0.0017) [2023-03-09 08:57:45,970][23090] Updated weights for policy 0, policy_version 66491 (0.0018) [2023-03-09 08:57:46,678][23090] Updated weights for policy 0, policy_version 66501 (0.0017) [2023-03-09 08:57:47,596][23090] Updated weights for policy 0, policy_version 66511 (0.0020) [2023-03-09 08:57:48,533][23090] Updated weights for policy 0, policy_version 66521 (0.0018) [2023-03-09 08:57:49,058][22664] Fps is (10 sec: 196612.9, 60 sec: 198520.1, 300 sec: 198774.0). Total num frames: 1089994752. Throughput: 0: 49682.1. Samples: 272514304. Policy #0 lag: (min: 0.0, avg: 17.4, max: 32.0) [2023-03-09 08:57:49,060][22664] Avg episode reward: [(0, '52.164')] [2023-03-09 08:57:49,227][23090] Updated weights for policy 0, policy_version 66531 (0.0016) [2023-03-09 08:57:50,036][23090] Updated weights for policy 0, policy_version 66541 (0.0013) [2023-03-09 08:57:51,025][23090] Updated weights for policy 0, policy_version 66551 (0.0013) [2023-03-09 08:57:51,781][23090] Updated weights for policy 0, policy_version 66562 (0.0017) [2023-03-09 08:57:52,182][22940] Signal inference workers to stop experience collection... (21250 times) [2023-03-09 08:57:52,183][22940] Signal inference workers to resume experience collection... (21250 times) [2023-03-09 08:57:52,250][23090] InferenceWorker_p0-w0: stopping experience collection (21250 times) [2023-03-09 08:57:52,253][23090] InferenceWorker_p0-w0: resuming experience collection (21250 times) [2023-03-09 08:57:52,614][23090] Updated weights for policy 0, policy_version 66572 (0.0013) [2023-03-09 08:57:53,485][23090] Updated weights for policy 0, policy_version 66582 (0.0013) [2023-03-09 08:57:54,059][22664] Fps is (10 sec: 198244.7, 60 sec: 199065.3, 300 sec: 198885.2). Total num frames: 1091010560. Throughput: 0: 49729.7. Samples: 272813296. Policy #0 lag: (min: 0.0, avg: 15.7, max: 32.0) [2023-03-09 08:57:54,060][22664] Avg episode reward: [(0, '53.403')] [2023-03-09 08:57:54,263][23090] Updated weights for policy 0, policy_version 66592 (0.0015) [2023-03-09 08:57:55,030][23090] Updated weights for policy 0, policy_version 66602 (0.0013) [2023-03-09 08:57:56,048][23090] Updated weights for policy 0, policy_version 66612 (0.0013) [2023-03-09 08:57:56,718][23090] Updated weights for policy 0, policy_version 66622 (0.0011) [2023-03-09 08:57:57,522][23090] Updated weights for policy 0, policy_version 66632 (0.0013) [2023-03-09 08:57:58,437][23090] Updated weights for policy 0, policy_version 66642 (0.0021) [2023-03-09 08:57:59,059][22664] Fps is (10 sec: 198239.3, 60 sec: 198791.5, 300 sec: 198773.8). Total num frames: 1091977216. Throughput: 0: 49728.9. Samples: 272962752. Policy #0 lag: (min: 0.0, avg: 15.7, max: 32.0) [2023-03-09 08:57:59,061][22664] Avg episode reward: [(0, '55.515')] [2023-03-09 08:57:59,248][23090] Updated weights for policy 0, policy_version 66652 (0.0022) [2023-03-09 08:57:59,978][23090] Updated weights for policy 0, policy_version 66662 (0.0013) [2023-03-09 08:58:00,853][23090] Updated weights for policy 0, policy_version 66672 (0.0022) [2023-03-09 08:58:01,762][23090] Updated weights for policy 0, policy_version 66683 (0.0013) [2023-03-09 08:58:02,500][23090] Updated weights for policy 0, policy_version 66693 (0.0020) [2023-03-09 08:58:03,407][23090] Updated weights for policy 0, policy_version 66703 (0.0019) [2023-03-09 08:58:04,059][22664] Fps is (10 sec: 196603.1, 60 sec: 198791.3, 300 sec: 198773.9). Total num frames: 1092976640. Throughput: 0: 49639.1. Samples: 273259616. Policy #0 lag: (min: 0.0, avg: 15.7, max: 32.0) [2023-03-09 08:58:04,061][22664] Avg episode reward: [(0, '52.783')] [2023-03-09 08:58:04,256][22940] Signal inference workers to stop experience collection... (21300 times) [2023-03-09 08:58:04,275][22940] Signal inference workers to resume experience collection... (21300 times) [2023-03-09 08:58:04,284][23090] InferenceWorker_p0-w0: stopping experience collection (21300 times) [2023-03-09 08:58:04,284][23090] InferenceWorker_p0-w0: resuming experience collection (21300 times) [2023-03-09 08:58:04,369][23090] Updated weights for policy 0, policy_version 66713 (0.0016) [2023-03-09 08:58:05,067][23090] Updated weights for policy 0, policy_version 66723 (0.0020) [2023-03-09 08:58:05,973][23090] Updated weights for policy 0, policy_version 66733 (0.0016) [2023-03-09 08:58:06,864][23090] Updated weights for policy 0, policy_version 66743 (0.0013) [2023-03-09 08:58:07,565][23090] Updated weights for policy 0, policy_version 66753 (0.0023) [2023-03-09 08:58:08,341][23090] Updated weights for policy 0, policy_version 66763 (0.0013) [2023-03-09 08:58:09,059][22664] Fps is (10 sec: 199888.2, 60 sec: 198793.1, 300 sec: 198829.6). Total num frames: 1093976064. Throughput: 0: 49685.4. Samples: 273558560. Policy #0 lag: (min: 0.0, avg: 15.7, max: 32.0) [2023-03-09 08:58:09,061][22664] Avg episode reward: [(0, '56.582')] [2023-03-09 08:58:09,073][22940] Saving new best policy, reward=56.582! [2023-03-09 08:58:09,295][23090] Updated weights for policy 0, policy_version 66774 (0.0018) [2023-03-09 08:58:10,107][23090] Updated weights for policy 0, policy_version 66784 (0.0013) [2023-03-09 08:58:10,879][23090] Updated weights for policy 0, policy_version 66794 (0.0018) [2023-03-09 08:58:11,824][23090] Updated weights for policy 0, policy_version 66804 (0.0023) [2023-03-09 08:58:12,555][23090] Updated weights for policy 0, policy_version 66814 (0.0013) [2023-03-09 08:58:13,352][23090] Updated weights for policy 0, policy_version 66824 (0.0015) [2023-03-09 08:58:13,974][22940] Signal inference workers to stop experience collection... (21350 times) [2023-03-09 08:58:13,978][22940] Signal inference workers to resume experience collection... (21350 times) [2023-03-09 08:58:14,043][23090] InferenceWorker_p0-w0: stopping experience collection (21350 times) [2023-03-09 08:58:14,044][23090] InferenceWorker_p0-w0: resuming experience collection (21350 times) [2023-03-09 08:58:14,059][22664] Fps is (10 sec: 199879.7, 60 sec: 199064.3, 300 sec: 198829.4). Total num frames: 1094975488. Throughput: 0: 49685.0. Samples: 273707984. Policy #0 lag: (min: 0.0, avg: 15.7, max: 32.0) [2023-03-09 08:58:14,061][22664] Avg episode reward: [(0, '52.225')] [2023-03-09 08:58:14,249][23090] Updated weights for policy 0, policy_version 66834 (0.0019) [2023-03-09 08:58:15,015][23090] Updated weights for policy 0, policy_version 66844 (0.0019) [2023-03-09 08:58:15,816][23090] Updated weights for policy 0, policy_version 66854 (0.0015) [2023-03-09 08:58:16,673][23090] Updated weights for policy 0, policy_version 66864 (0.0018) [2023-03-09 08:58:17,593][23090] Updated weights for policy 0, policy_version 66874 (0.0017) [2023-03-09 08:58:18,284][23090] Updated weights for policy 0, policy_version 66884 (0.0013) [2023-03-09 08:58:19,059][22664] Fps is (10 sec: 198245.2, 60 sec: 199065.9, 300 sec: 198829.6). Total num frames: 1095958528. Throughput: 0: 49640.2. Samples: 274006960. Policy #0 lag: (min: 0.0, avg: 15.7, max: 32.0) [2023-03-09 08:58:19,099][22664] Avg episode reward: [(0, '55.074')] [2023-03-09 08:58:19,169][23090] Updated weights for policy 0, policy_version 66894 (0.0016) [2023-03-09 08:58:20,167][23090] Updated weights for policy 0, policy_version 66905 (0.0016) [2023-03-09 08:58:20,865][23090] Updated weights for policy 0, policy_version 66915 (0.0020) [2023-03-09 08:58:21,733][23090] Updated weights for policy 0, policy_version 66925 (0.0013) [2023-03-09 08:58:22,628][23090] Updated weights for policy 0, policy_version 66935 (0.0017) [2023-03-09 08:58:23,330][23090] Updated weights for policy 0, policy_version 66945 (0.0013) [2023-03-09 08:58:24,059][22664] Fps is (10 sec: 199891.0, 60 sec: 199065.4, 300 sec: 198829.6). Total num frames: 1096974336. Throughput: 0: 49687.1. Samples: 274305936. Policy #0 lag: (min: 0.0, avg: 15.7, max: 32.0) [2023-03-09 08:58:24,060][22664] Avg episode reward: [(0, '53.241')] [2023-03-09 08:58:24,099][23090] Updated weights for policy 0, policy_version 66955 (0.0018) [2023-03-09 08:58:24,418][22940] Signal inference workers to stop experience collection... (21400 times) [2023-03-09 08:58:24,441][22940] Signal inference workers to resume experience collection... (21400 times) [2023-03-09 08:58:24,486][23090] InferenceWorker_p0-w0: stopping experience collection (21400 times) [2023-03-09 08:58:24,486][23090] InferenceWorker_p0-w0: resuming experience collection (21400 times) [2023-03-09 08:58:25,049][23090] Updated weights for policy 0, policy_version 66965 (0.0013) [2023-03-09 08:58:25,807][23090] Updated weights for policy 0, policy_version 66975 (0.0016) [2023-03-09 08:58:26,579][23090] Updated weights for policy 0, policy_version 66985 (0.0013) [2023-03-09 08:58:27,493][23090] Updated weights for policy 0, policy_version 66995 (0.0017) [2023-03-09 08:58:28,302][23090] Updated weights for policy 0, policy_version 67005 (0.0021) [2023-03-09 08:58:29,037][23090] Updated weights for policy 0, policy_version 67015 (0.0013) [2023-03-09 08:58:29,059][22664] Fps is (10 sec: 201527.6, 60 sec: 198793.5, 300 sec: 198829.5). Total num frames: 1097973760. Throughput: 0: 49687.4. Samples: 274455424. Policy #0 lag: (min: 0.0, avg: 15.7, max: 32.0) [2023-03-09 08:58:29,060][22664] Avg episode reward: [(0, '55.045')] [2023-03-09 08:58:30,041][23090] Updated weights for policy 0, policy_version 67026 (0.0016) [2023-03-09 08:58:30,842][23090] Updated weights for policy 0, policy_version 67036 (0.0017) [2023-03-09 08:58:31,592][23090] Updated weights for policy 0, policy_version 67046 (0.0020) [2023-03-09 08:58:32,397][23090] Updated weights for policy 0, policy_version 67056 (0.0016) [2023-03-09 08:58:33,350][23090] Updated weights for policy 0, policy_version 67066 (0.0013) [2023-03-09 08:58:34,059][22664] Fps is (10 sec: 199884.6, 60 sec: 199065.5, 300 sec: 198885.0). Total num frames: 1098973184. Throughput: 0: 49776.8. Samples: 274754272. Policy #0 lag: (min: 1.0, avg: 17.6, max: 33.0) [2023-03-09 08:58:34,060][22664] Avg episode reward: [(0, '53.794')] [2023-03-09 08:58:34,088][23090] Updated weights for policy 0, policy_version 67076 (0.0021) [2023-03-09 08:58:34,381][22940] Signal inference workers to stop experience collection... (21450 times) [2023-03-09 08:58:34,382][22940] Signal inference workers to resume experience collection... (21450 times) [2023-03-09 08:58:34,444][23090] InferenceWorker_p0-w0: stopping experience collection (21450 times) [2023-03-09 08:58:34,445][23090] InferenceWorker_p0-w0: resuming experience collection (21450 times) [2023-03-09 08:58:34,945][23090] Updated weights for policy 0, policy_version 67086 (0.0019) [2023-03-09 08:58:35,837][23090] Updated weights for policy 0, policy_version 67096 (0.0016) [2023-03-09 08:58:36,668][23090] Updated weights for policy 0, policy_version 67108 (0.0018) [2023-03-09 08:58:37,579][23090] Updated weights for policy 0, policy_version 67118 (0.0016) [2023-03-09 08:58:38,460][23090] Updated weights for policy 0, policy_version 67128 (0.0019) [2023-03-09 08:58:39,059][22664] Fps is (10 sec: 198243.9, 60 sec: 198792.9, 300 sec: 198829.6). Total num frames: 1099956224. Throughput: 0: 49821.1. Samples: 275055248. Policy #0 lag: (min: 1.0, avg: 17.6, max: 33.0) [2023-03-09 08:58:39,060][22664] Avg episode reward: [(0, '52.533')] [2023-03-09 08:58:39,178][23090] Updated weights for policy 0, policy_version 67138 (0.0013) [2023-03-09 08:58:40,027][23090] Updated weights for policy 0, policy_version 67148 (0.0016) [2023-03-09 08:58:40,860][23090] Updated weights for policy 0, policy_version 67158 (0.0013) [2023-03-09 08:58:41,609][23090] Updated weights for policy 0, policy_version 67168 (0.0013) [2023-03-09 08:58:42,388][23090] Updated weights for policy 0, policy_version 67178 (0.0013) [2023-03-09 08:58:43,330][23090] Updated weights for policy 0, policy_version 67188 (0.0013) [2023-03-09 08:58:43,989][22940] Signal inference workers to stop experience collection... (21500 times) [2023-03-09 08:58:44,012][22940] Signal inference workers to resume experience collection... (21500 times) [2023-03-09 08:58:44,058][22664] Fps is (10 sec: 199891.5, 60 sec: 199065.8, 300 sec: 198885.3). Total num frames: 1100972032. Throughput: 0: 49820.9. Samples: 275204672. Policy #0 lag: (min: 1.0, avg: 17.6, max: 33.0) [2023-03-09 08:58:44,059][22664] Avg episode reward: [(0, '54.541')] [2023-03-09 08:58:44,087][23090] InferenceWorker_p0-w0: stopping experience collection (21500 times) [2023-03-09 08:58:44,102][23090] InferenceWorker_p0-w0: resuming experience collection (21500 times) [2023-03-09 08:58:44,104][23090] Updated weights for policy 0, policy_version 67198 (0.0016) [2023-03-09 08:58:44,865][23090] Updated weights for policy 0, policy_version 67208 (0.0013) [2023-03-09 08:58:45,781][23090] Updated weights for policy 0, policy_version 67218 (0.0019) [2023-03-09 08:58:46,595][23090] Updated weights for policy 0, policy_version 67228 (0.0014) [2023-03-09 08:58:47,340][23090] Updated weights for policy 0, policy_version 67238 (0.0023) [2023-03-09 08:58:48,213][23090] Updated weights for policy 0, policy_version 67248 (0.0025) [2023-03-09 08:58:49,059][22664] Fps is (10 sec: 198233.0, 60 sec: 199062.9, 300 sec: 198773.4). Total num frames: 1101938688. Throughput: 0: 49820.2. Samples: 275501552. Policy #0 lag: (min: 1.0, avg: 17.6, max: 33.0) [2023-03-09 08:58:49,062][22664] Avg episode reward: [(0, '54.139')] [2023-03-09 08:58:49,093][23090] Updated weights for policy 0, policy_version 67258 (0.0017) [2023-03-09 08:58:49,848][23090] Updated weights for policy 0, policy_version 67269 (0.0013) [2023-03-09 08:58:50,749][23090] Updated weights for policy 0, policy_version 67279 (0.0019) [2023-03-09 08:58:51,678][23090] Updated weights for policy 0, policy_version 67289 (0.0018) [2023-03-09 08:58:52,458][23090] Updated weights for policy 0, policy_version 67299 (0.0018) [2023-03-09 08:58:53,325][23090] Updated weights for policy 0, policy_version 67309 (0.0016) [2023-03-09 08:58:54,059][22664] Fps is (10 sec: 194962.2, 60 sec: 198518.7, 300 sec: 198829.3). Total num frames: 1102921728. Throughput: 0: 49775.2. Samples: 275798448. Policy #0 lag: (min: 1.0, avg: 17.6, max: 33.0) [2023-03-09 08:58:54,061][22664] Avg episode reward: [(0, '55.025')] [2023-03-09 08:58:54,218][23090] Updated weights for policy 0, policy_version 67319 (0.0016) [2023-03-09 08:58:54,592][22940] Signal inference workers to stop experience collection... (21550 times) [2023-03-09 08:58:54,608][22940] Signal inference workers to resume experience collection... (21550 times) [2023-03-09 08:58:54,666][23090] InferenceWorker_p0-w0: stopping experience collection (21550 times) [2023-03-09 08:58:54,666][23090] InferenceWorker_p0-w0: resuming experience collection (21550 times) [2023-03-09 08:58:55,020][23090] Updated weights for policy 0, policy_version 67329 (0.0013) [2023-03-09 08:58:55,719][23090] Updated weights for policy 0, policy_version 67339 (0.0016) [2023-03-09 08:58:56,678][23090] Updated weights for policy 0, policy_version 67349 (0.0022) [2023-03-09 08:58:57,416][23090] Updated weights for policy 0, policy_version 67359 (0.0018) [2023-03-09 08:58:58,189][23090] Updated weights for policy 0, policy_version 67369 (0.0017) [2023-03-09 08:58:59,059][22664] Fps is (10 sec: 198259.6, 60 sec: 199066.2, 300 sec: 198829.4). Total num frames: 1103921152. Throughput: 0: 49776.8. Samples: 275947920. Policy #0 lag: (min: 1.0, avg: 17.6, max: 33.0) [2023-03-09 08:58:59,061][22664] Avg episode reward: [(0, '54.762')] [2023-03-09 08:58:59,142][23090] Updated weights for policy 0, policy_version 67379 (0.0019) [2023-03-09 08:58:59,925][23090] Updated weights for policy 0, policy_version 67389 (0.0019) [2023-03-09 08:59:00,736][23090] Updated weights for policy 0, policy_version 67399 (0.0022) [2023-03-09 08:59:01,586][23090] Updated weights for policy 0, policy_version 67409 (0.0014) [2023-03-09 08:59:02,433][23090] Updated weights for policy 0, policy_version 67419 (0.0020) [2023-03-09 08:59:03,193][23090] Updated weights for policy 0, policy_version 67429 (0.0016) [2023-03-09 08:59:04,058][22664] Fps is (10 sec: 199891.9, 60 sec: 199066.8, 300 sec: 198829.6). Total num frames: 1104920576. Throughput: 0: 49683.9. Samples: 276242720. Policy #0 lag: (min: 1.0, avg: 17.6, max: 33.0) [2023-03-09 08:59:04,059][22664] Avg episode reward: [(0, '54.764')] [2023-03-09 08:59:04,080][23090] Updated weights for policy 0, policy_version 67439 (0.0013) [2023-03-09 08:59:04,993][23090] Updated weights for policy 0, policy_version 67450 (0.0016) [2023-03-09 08:59:05,208][22940] Signal inference workers to stop experience collection... (21600 times) [2023-03-09 08:59:05,229][22940] Signal inference workers to resume experience collection... (21600 times) [2023-03-09 08:59:05,279][23090] InferenceWorker_p0-w0: stopping experience collection (21600 times) [2023-03-09 08:59:05,279][23090] InferenceWorker_p0-w0: resuming experience collection (21600 times) [2023-03-09 08:59:05,765][23090] Updated weights for policy 0, policy_version 67460 (0.0013) [2023-03-09 08:59:06,623][23090] Updated weights for policy 0, policy_version 67470 (0.0022) [2023-03-09 08:59:07,530][23090] Updated weights for policy 0, policy_version 67480 (0.0013) [2023-03-09 08:59:08,268][23090] Updated weights for policy 0, policy_version 67490 (0.0015) [2023-03-09 08:59:09,059][22664] Fps is (10 sec: 198248.8, 60 sec: 198793.0, 300 sec: 198774.1). Total num frames: 1105903616. Throughput: 0: 49637.2. Samples: 276539600. Policy #0 lag: (min: 1.0, avg: 17.6, max: 33.0) [2023-03-09 08:59:09,060][22664] Avg episode reward: [(0, '53.355')] [2023-03-09 08:59:09,121][23090] Updated weights for policy 0, policy_version 67500 (0.0013) [2023-03-09 08:59:10,005][23090] Updated weights for policy 0, policy_version 67510 (0.0013) [2023-03-09 08:59:10,754][23090] Updated weights for policy 0, policy_version 67520 (0.0013) [2023-03-09 08:59:11,491][23090] Updated weights for policy 0, policy_version 67530 (0.0018) [2023-03-09 08:59:12,546][23090] Updated weights for policy 0, policy_version 67541 (0.0015) [2023-03-09 08:59:13,274][23090] Updated weights for policy 0, policy_version 67551 (0.0018) [2023-03-09 08:59:14,048][23090] Updated weights for policy 0, policy_version 67561 (0.0016) [2023-03-09 08:59:14,059][22664] Fps is (10 sec: 199877.3, 60 sec: 199066.4, 300 sec: 198829.5). Total num frames: 1106919424. Throughput: 0: 49681.1. Samples: 276691088. Policy #0 lag: (min: 1.0, avg: 17.5, max: 34.0) [2023-03-09 08:59:14,061][22664] Avg episode reward: [(0, '51.833')] [2023-03-09 08:59:14,996][23090] Updated weights for policy 0, policy_version 67571 (0.0016) [2023-03-09 08:59:15,757][23090] Updated weights for policy 0, policy_version 67581 (0.0016) [2023-03-09 08:59:16,161][22940] Signal inference workers to stop experience collection... (21650 times) [2023-03-09 08:59:16,184][22940] Signal inference workers to resume experience collection... (21650 times) [2023-03-09 08:59:16,233][23090] InferenceWorker_p0-w0: stopping experience collection (21650 times) [2023-03-09 08:59:16,233][23090] InferenceWorker_p0-w0: resuming experience collection (21650 times) [2023-03-09 08:59:16,500][23090] Updated weights for policy 0, policy_version 67591 (0.0015) [2023-03-09 08:59:17,353][23090] Updated weights for policy 0, policy_version 67601 (0.0017) [2023-03-09 08:59:18,305][23090] Updated weights for policy 0, policy_version 67612 (0.0013) [2023-03-09 08:59:19,035][23090] Updated weights for policy 0, policy_version 67622 (0.0019) [2023-03-09 08:59:19,058][22664] Fps is (10 sec: 201524.3, 60 sec: 199339.5, 300 sec: 198829.7). Total num frames: 1107918848. Throughput: 0: 49683.2. Samples: 276990000. Policy #0 lag: (min: 1.0, avg: 17.5, max: 34.0) [2023-03-09 08:59:19,059][22664] Avg episode reward: [(0, '54.783')] [2023-03-09 08:59:19,064][22940] Saving /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000067622_1107918848.pth... [2023-03-09 08:59:19,130][22940] Removing /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000064710_1060208640.pth [2023-03-09 08:59:19,918][23090] Updated weights for policy 0, policy_version 67632 (0.0016) [2023-03-09 08:59:20,806][23090] Updated weights for policy 0, policy_version 67642 (0.0013) [2023-03-09 08:59:21,573][23090] Updated weights for policy 0, policy_version 67652 (0.0018) [2023-03-09 08:59:22,419][23090] Updated weights for policy 0, policy_version 67662 (0.0016) [2023-03-09 08:59:23,348][23090] Updated weights for policy 0, policy_version 67672 (0.0013) [2023-03-09 08:59:24,058][22664] Fps is (10 sec: 196615.5, 60 sec: 198520.5, 300 sec: 198718.5). Total num frames: 1108885504. Throughput: 0: 49591.3. Samples: 277286848. Policy #0 lag: (min: 1.0, avg: 17.5, max: 34.0) [2023-03-09 08:59:24,059][22664] Avg episode reward: [(0, '54.640')] [2023-03-09 08:59:24,155][23090] Updated weights for policy 0, policy_version 67683 (0.0015) [2023-03-09 08:59:25,053][23090] Updated weights for policy 0, policy_version 67693 (0.0016) [2023-03-09 08:59:25,971][23090] Updated weights for policy 0, policy_version 67703 (0.0021) [2023-03-09 08:59:26,111][22940] Signal inference workers to stop experience collection... (21700 times) [2023-03-09 08:59:26,127][22940] Signal inference workers to resume experience collection... (21700 times) [2023-03-09 08:59:26,186][23090] InferenceWorker_p0-w0: stopping experience collection (21700 times) [2023-03-09 08:59:26,186][23090] InferenceWorker_p0-w0: resuming experience collection (21700 times) [2023-03-09 08:59:26,753][23090] Updated weights for policy 0, policy_version 67713 (0.0016) [2023-03-09 08:59:27,415][23090] Updated weights for policy 0, policy_version 67723 (0.0016) [2023-03-09 08:59:28,424][23090] Updated weights for policy 0, policy_version 67733 (0.0021) [2023-03-09 08:59:29,059][22664] Fps is (10 sec: 196606.4, 60 sec: 198519.3, 300 sec: 198718.5). Total num frames: 1109884928. Throughput: 0: 49546.2. Samples: 277434256. Policy #0 lag: (min: 1.0, avg: 17.5, max: 34.0) [2023-03-09 08:59:29,060][22664] Avg episode reward: [(0, '54.673')] [2023-03-09 08:59:29,148][23090] Updated weights for policy 0, policy_version 67743 (0.0016) [2023-03-09 08:59:29,926][23090] Updated weights for policy 0, policy_version 67753 (0.0017) [2023-03-09 08:59:30,889][23090] Updated weights for policy 0, policy_version 67763 (0.0020) [2023-03-09 08:59:31,679][23090] Updated weights for policy 0, policy_version 67773 (0.0013) [2023-03-09 08:59:32,443][23090] Updated weights for policy 0, policy_version 67783 (0.0019) [2023-03-09 08:59:33,295][23090] Updated weights for policy 0, policy_version 67793 (0.0013) [2023-03-09 08:59:34,059][22664] Fps is (10 sec: 196604.9, 60 sec: 197973.9, 300 sec: 198662.8). Total num frames: 1110851584. Throughput: 0: 49502.0. Samples: 277729104. Policy #0 lag: (min: 1.0, avg: 17.5, max: 34.0) [2023-03-09 08:59:34,060][22664] Avg episode reward: [(0, '54.621')] [2023-03-09 08:59:34,254][23090] Updated weights for policy 0, policy_version 67804 (0.0018) [2023-03-09 08:59:34,995][23090] Updated weights for policy 0, policy_version 67814 (0.0017) [2023-03-09 08:59:35,866][23090] Updated weights for policy 0, policy_version 67824 (0.0016) [2023-03-09 08:59:36,758][23090] Updated weights for policy 0, policy_version 67834 (0.0016) [2023-03-09 08:59:37,426][22940] Signal inference workers to stop experience collection... (21750 times) [2023-03-09 08:59:37,449][22940] Signal inference workers to resume experience collection... (21750 times) [2023-03-09 08:59:37,496][23090] InferenceWorker_p0-w0: stopping experience collection (21750 times) [2023-03-09 08:59:37,496][23090] InferenceWorker_p0-w0: resuming experience collection (21750 times) [2023-03-09 08:59:37,541][23090] Updated weights for policy 0, policy_version 67844 (0.0016) [2023-03-09 08:59:38,369][23090] Updated weights for policy 0, policy_version 67854 (0.0019) [2023-03-09 08:59:39,059][22664] Fps is (10 sec: 194962.5, 60 sec: 197972.4, 300 sec: 198607.1). Total num frames: 1111834624. Throughput: 0: 49545.1. Samples: 278027984. Policy #0 lag: (min: 1.0, avg: 17.5, max: 34.0) [2023-03-09 08:59:39,061][22664] Avg episode reward: [(0, '54.318')] [2023-03-09 08:59:39,258][23090] Updated weights for policy 0, policy_version 67864 (0.0019) [2023-03-09 08:59:40,061][23090] Updated weights for policy 0, policy_version 67874 (0.0013) [2023-03-09 08:59:40,847][23090] Updated weights for policy 0, policy_version 67884 (0.0015) [2023-03-09 08:59:41,719][23090] Updated weights for policy 0, policy_version 67894 (0.0015) [2023-03-09 08:59:42,425][23090] Updated weights for policy 0, policy_version 67904 (0.0018) [2023-03-09 08:59:43,249][23090] Updated weights for policy 0, policy_version 67914 (0.0020) [2023-03-09 08:59:44,059][22664] Fps is (10 sec: 199882.9, 60 sec: 197972.4, 300 sec: 198718.3). Total num frames: 1112850432. Throughput: 0: 49543.8. Samples: 278177392. Policy #0 lag: (min: 1.0, avg: 17.5, max: 34.0) [2023-03-09 08:59:44,061][22664] Avg episode reward: [(0, '55.385')] [2023-03-09 08:59:44,166][23090] Updated weights for policy 0, policy_version 67924 (0.0013) [2023-03-09 08:59:44,978][23090] Updated weights for policy 0, policy_version 67935 (0.0025) [2023-03-09 08:59:45,742][23090] Updated weights for policy 0, policy_version 67945 (0.0012) [2023-03-09 08:59:46,664][23090] Updated weights for policy 0, policy_version 67955 (0.0014) [2023-03-09 08:59:47,519][23090] Updated weights for policy 0, policy_version 67966 (0.0019) [2023-03-09 08:59:47,833][22940] Signal inference workers to stop experience collection... (21800 times) [2023-03-09 08:59:47,846][22940] Signal inference workers to resume experience collection... (21800 times) [2023-03-09 08:59:47,878][23090] InferenceWorker_p0-w0: stopping experience collection (21800 times) [2023-03-09 08:59:47,920][23090] InferenceWorker_p0-w0: resuming experience collection (21800 times) [2023-03-09 08:59:48,328][23090] Updated weights for policy 0, policy_version 67976 (0.0013) [2023-03-09 08:59:49,059][22664] Fps is (10 sec: 201525.3, 60 sec: 198521.1, 300 sec: 198773.8). Total num frames: 1113849856. Throughput: 0: 49635.5. Samples: 278476336. Policy #0 lag: (min: 1.0, avg: 17.5, max: 34.0) [2023-03-09 08:59:49,061][22664] Avg episode reward: [(0, '54.142')] [2023-03-09 08:59:49,220][23090] Updated weights for policy 0, policy_version 67986 (0.0014) [2023-03-09 08:59:50,039][23090] Updated weights for policy 0, policy_version 67996 (0.0013) [2023-03-09 08:59:50,772][23090] Updated weights for policy 0, policy_version 68006 (0.0016) [2023-03-09 08:59:51,599][23090] Updated weights for policy 0, policy_version 68016 (0.0013) [2023-03-09 08:59:52,483][23090] Updated weights for policy 0, policy_version 68026 (0.0013) [2023-03-09 08:59:53,255][23090] Updated weights for policy 0, policy_version 68036 (0.0012) [2023-03-09 08:59:54,058][22664] Fps is (10 sec: 201527.4, 60 sec: 199066.7, 300 sec: 198829.6). Total num frames: 1114865664. Throughput: 0: 49770.7. Samples: 278779280. Policy #0 lag: (min: 1.0, avg: 17.5, max: 34.0) [2023-03-09 08:59:54,060][22664] Avg episode reward: [(0, '53.424')] [2023-03-09 08:59:54,067][23090] Updated weights for policy 0, policy_version 68046 (0.0017) [2023-03-09 08:59:54,970][23090] Updated weights for policy 0, policy_version 68056 (0.0017) [2023-03-09 08:59:55,788][23090] Updated weights for policy 0, policy_version 68066 (0.0020) [2023-03-09 08:59:56,673][23090] Updated weights for policy 0, policy_version 68076 (0.0020) [2023-03-09 08:59:57,496][23090] Updated weights for policy 0, policy_version 68086 (0.0018) [2023-03-09 08:59:58,219][23090] Updated weights for policy 0, policy_version 68096 (0.0013) [2023-03-09 08:59:58,483][22940] Signal inference workers to stop experience collection... (21850 times) [2023-03-09 08:59:58,505][22940] Signal inference workers to resume experience collection... (21850 times) [2023-03-09 08:59:58,552][23090] InferenceWorker_p0-w0: stopping experience collection (21850 times) [2023-03-09 08:59:58,552][23090] InferenceWorker_p0-w0: resuming experience collection (21850 times) [2023-03-09 08:59:59,059][22664] Fps is (10 sec: 199884.7, 60 sec: 198792.0, 300 sec: 198773.8). Total num frames: 1115848704. Throughput: 0: 49634.8. Samples: 278924656. Policy #0 lag: (min: 1.0, avg: 16.1, max: 33.0) [2023-03-09 08:59:59,061][22664] Avg episode reward: [(0, '52.025')] [2023-03-09 08:59:59,093][23090] Updated weights for policy 0, policy_version 68107 (0.0013) [2023-03-09 09:00:00,133][23090] Updated weights for policy 0, policy_version 68117 (0.0016) [2023-03-09 09:00:00,787][23090] Updated weights for policy 0, policy_version 68127 (0.0013) [2023-03-09 09:00:01,618][23090] Updated weights for policy 0, policy_version 68137 (0.0016) [2023-03-09 09:00:02,571][23090] Updated weights for policy 0, policy_version 68147 (0.0017) [2023-03-09 09:00:03,314][23090] Updated weights for policy 0, policy_version 68157 (0.0013) [2023-03-09 09:00:04,059][22664] Fps is (10 sec: 196604.5, 60 sec: 198518.7, 300 sec: 198718.5). Total num frames: 1116831744. Throughput: 0: 49589.5. Samples: 279221536. Policy #0 lag: (min: 1.0, avg: 16.1, max: 33.0) [2023-03-09 09:00:04,060][22664] Avg episode reward: [(0, '53.766')] [2023-03-09 09:00:04,091][23090] Updated weights for policy 0, policy_version 68167 (0.0014) [2023-03-09 09:00:04,970][23090] Updated weights for policy 0, policy_version 68177 (0.0015) [2023-03-09 09:00:05,779][23090] Updated weights for policy 0, policy_version 68187 (0.0021) [2023-03-09 09:00:06,558][23090] Updated weights for policy 0, policy_version 68197 (0.0016) [2023-03-09 09:00:07,387][23090] Updated weights for policy 0, policy_version 68207 (0.0013) [2023-03-09 09:00:08,278][23090] Updated weights for policy 0, policy_version 68217 (0.0013) [2023-03-09 09:00:08,964][22940] Signal inference workers to stop experience collection... (21900 times) [2023-03-09 09:00:08,966][22940] Signal inference workers to resume experience collection... (21900 times) [2023-03-09 09:00:09,032][23090] InferenceWorker_p0-w0: stopping experience collection (21900 times) [2023-03-09 09:00:09,032][23090] InferenceWorker_p0-w0: resuming experience collection (21900 times) [2023-03-09 09:00:09,058][22664] Fps is (10 sec: 196615.1, 60 sec: 198519.7, 300 sec: 198663.1). Total num frames: 1117814784. Throughput: 0: 49635.5. Samples: 279520448. Policy #0 lag: (min: 1.0, avg: 16.1, max: 33.0) [2023-03-09 09:00:09,059][22664] Avg episode reward: [(0, '52.308')] [2023-03-09 09:00:09,117][23090] Updated weights for policy 0, policy_version 68227 (0.0013) [2023-03-09 09:00:09,934][23090] Updated weights for policy 0, policy_version 68237 (0.0013) [2023-03-09 09:00:10,861][23090] Updated weights for policy 0, policy_version 68247 (0.0020) [2023-03-09 09:00:11,633][23090] Updated weights for policy 0, policy_version 68257 (0.0013) [2023-03-09 09:00:12,297][23090] Updated weights for policy 0, policy_version 68267 (0.0017) [2023-03-09 09:00:13,301][23090] Updated weights for policy 0, policy_version 68277 (0.0016) [2023-03-09 09:00:13,997][23090] Updated weights for policy 0, policy_version 68287 (0.0017) [2023-03-09 09:00:14,058][22664] Fps is (10 sec: 198250.5, 60 sec: 198247.6, 300 sec: 198718.6). Total num frames: 1118814208. Throughput: 0: 49636.0. Samples: 279667872. Policy #0 lag: (min: 1.0, avg: 16.1, max: 33.0) [2023-03-09 09:00:14,059][22664] Avg episode reward: [(0, '53.165')] [2023-03-09 09:00:14,807][23090] Updated weights for policy 0, policy_version 68297 (0.0019) [2023-03-09 09:00:15,717][23090] Updated weights for policy 0, policy_version 68307 (0.0021) [2023-03-09 09:00:16,496][23090] Updated weights for policy 0, policy_version 68317 (0.0024) [2023-03-09 09:00:17,291][23090] Updated weights for policy 0, policy_version 68327 (0.0013) [2023-03-09 09:00:18,167][23090] Updated weights for policy 0, policy_version 68337 (0.0013) [2023-03-09 09:00:18,981][23090] Updated weights for policy 0, policy_version 68347 (0.0017) [2023-03-09 09:00:19,058][22664] Fps is (10 sec: 199885.1, 60 sec: 198246.5, 300 sec: 198774.0). Total num frames: 1119813632. Throughput: 0: 49727.1. Samples: 279966816. Policy #0 lag: (min: 1.0, avg: 16.1, max: 33.0) [2023-03-09 09:00:19,061][22664] Avg episode reward: [(0, '52.568')] [2023-03-09 09:00:19,604][22940] Signal inference workers to stop experience collection... (21950 times) [2023-03-09 09:00:19,626][22940] Signal inference workers to resume experience collection... (21950 times) [2023-03-09 09:00:19,671][23090] InferenceWorker_p0-w0: stopping experience collection (21950 times) [2023-03-09 09:00:19,712][23090] InferenceWorker_p0-w0: resuming experience collection (21950 times) [2023-03-09 09:00:19,781][23090] Updated weights for policy 0, policy_version 68357 (0.0018) [2023-03-09 09:00:20,602][23090] Updated weights for policy 0, policy_version 68367 (0.0018) [2023-03-09 09:00:21,485][23090] Updated weights for policy 0, policy_version 68377 (0.0020) [2023-03-09 09:00:22,314][23090] Updated weights for policy 0, policy_version 68387 (0.0014) [2023-03-09 09:00:23,121][23090] Updated weights for policy 0, policy_version 68397 (0.0020) [2023-03-09 09:00:24,028][23090] Updated weights for policy 0, policy_version 68407 (0.0016) [2023-03-09 09:00:24,058][22664] Fps is (10 sec: 196607.8, 60 sec: 198246.3, 300 sec: 198663.1). Total num frames: 1120780288. Throughput: 0: 49728.9. Samples: 280265760. Policy #0 lag: (min: 1.0, avg: 16.1, max: 33.0) [2023-03-09 09:00:24,059][22664] Avg episode reward: [(0, '55.340')] [2023-03-09 09:00:24,785][23090] Updated weights for policy 0, policy_version 68417 (0.0014) [2023-03-09 09:00:25,499][23090] Updated weights for policy 0, policy_version 68427 (0.0017) [2023-03-09 09:00:26,465][23090] Updated weights for policy 0, policy_version 68437 (0.0015) [2023-03-09 09:00:27,268][23090] Updated weights for policy 0, policy_version 68448 (0.0013) [2023-03-09 09:00:28,034][23090] Updated weights for policy 0, policy_version 68458 (0.0016) [2023-03-09 09:00:29,004][23090] Updated weights for policy 0, policy_version 68468 (0.0019) [2023-03-09 09:00:29,059][22664] Fps is (10 sec: 196601.2, 60 sec: 198245.6, 300 sec: 198718.3). Total num frames: 1121779712. Throughput: 0: 49637.6. Samples: 280411088. Policy #0 lag: (min: 1.0, avg: 16.1, max: 33.0) [2023-03-09 09:00:29,061][22664] Avg episode reward: [(0, '53.056')] [2023-03-09 09:00:29,770][23090] Updated weights for policy 0, policy_version 68478 (0.0019) [2023-03-09 09:00:30,169][22940] Signal inference workers to stop experience collection... (22000 times) [2023-03-09 09:00:30,188][22940] Signal inference workers to resume experience collection... (22000 times) [2023-03-09 09:00:30,248][23090] InferenceWorker_p0-w0: stopping experience collection (22000 times) [2023-03-09 09:00:30,288][23090] InferenceWorker_p0-w0: resuming experience collection (22000 times) [2023-03-09 09:00:30,657][23090] Updated weights for policy 0, policy_version 68489 (0.0014) [2023-03-09 09:00:31,564][23090] Updated weights for policy 0, policy_version 68499 (0.0013) [2023-03-09 09:00:32,394][23090] Updated weights for policy 0, policy_version 68509 (0.0013) [2023-03-09 09:00:33,098][23090] Updated weights for policy 0, policy_version 68519 (0.0013) [2023-03-09 09:00:34,004][23090] Updated weights for policy 0, policy_version 68529 (0.0018) [2023-03-09 09:00:34,059][22664] Fps is (10 sec: 199883.6, 60 sec: 198792.8, 300 sec: 198774.0). Total num frames: 1122779136. Throughput: 0: 49636.6. Samples: 280709968. Policy #0 lag: (min: 1.0, avg: 16.1, max: 33.0) [2023-03-09 09:00:34,060][22664] Avg episode reward: [(0, '53.385')] [2023-03-09 09:00:34,850][23090] Updated weights for policy 0, policy_version 68539 (0.0013) [2023-03-09 09:00:35,595][23090] Updated weights for policy 0, policy_version 68549 (0.0013) [2023-03-09 09:00:36,513][23090] Updated weights for policy 0, policy_version 68560 (0.0015) [2023-03-09 09:00:37,424][23090] Updated weights for policy 0, policy_version 68570 (0.0013) [2023-03-09 09:00:38,270][23090] Updated weights for policy 0, policy_version 68581 (0.0015) [2023-03-09 09:00:39,059][22664] Fps is (10 sec: 201526.0, 60 sec: 199339.5, 300 sec: 198885.0). Total num frames: 1123794944. Throughput: 0: 49545.4. Samples: 281008832. Policy #0 lag: (min: 0.0, avg: 17.2, max: 33.0) [2023-03-09 09:00:39,060][22664] Avg episode reward: [(0, '50.486')] [2023-03-09 09:00:39,083][23090] Updated weights for policy 0, policy_version 68591 (0.0025) [2023-03-09 09:00:40,056][23090] Updated weights for policy 0, policy_version 68602 (0.0017) [2023-03-09 09:00:40,608][22940] Signal inference workers to stop experience collection... (22050 times) [2023-03-09 09:00:40,623][22940] Signal inference workers to resume experience collection... (22050 times) [2023-03-09 09:00:40,651][23090] InferenceWorker_p0-w0: stopping experience collection (22050 times) [2023-03-09 09:00:40,694][23090] InferenceWorker_p0-w0: resuming experience collection (22050 times) [2023-03-09 09:00:40,817][23090] Updated weights for policy 0, policy_version 68612 (0.0021) [2023-03-09 09:00:41,643][23090] Updated weights for policy 0, policy_version 68622 (0.0013) [2023-03-09 09:00:42,558][23090] Updated weights for policy 0, policy_version 68632 (0.0013) [2023-03-09 09:00:43,309][23090] Updated weights for policy 0, policy_version 68642 (0.0026) [2023-03-09 09:00:44,059][22664] Fps is (10 sec: 199883.1, 60 sec: 198792.8, 300 sec: 198773.9). Total num frames: 1124777984. Throughput: 0: 49636.2. Samples: 281158272. Policy #0 lag: (min: 0.0, avg: 17.2, max: 33.0) [2023-03-09 09:00:44,061][22664] Avg episode reward: [(0, '54.877')] [2023-03-09 09:00:44,174][23090] Updated weights for policy 0, policy_version 68652 (0.0015) [2023-03-09 09:00:44,989][23090] Updated weights for policy 0, policy_version 68662 (0.0016) [2023-03-09 09:00:45,714][23090] Updated weights for policy 0, policy_version 68672 (0.0017) [2023-03-09 09:00:46,501][23090] Updated weights for policy 0, policy_version 68682 (0.0017) [2023-03-09 09:00:47,570][23090] Updated weights for policy 0, policy_version 68693 (0.0013) [2023-03-09 09:00:48,389][23090] Updated weights for policy 0, policy_version 68704 (0.0013) [2023-03-09 09:00:49,059][22664] Fps is (10 sec: 198243.7, 60 sec: 198792.6, 300 sec: 198829.4). Total num frames: 1125777408. Throughput: 0: 49680.9. Samples: 281457184. Policy #0 lag: (min: 0.0, avg: 17.2, max: 33.0) [2023-03-09 09:00:49,061][22664] Avg episode reward: [(0, '52.880')] [2023-03-09 09:00:49,258][23090] Updated weights for policy 0, policy_version 68715 (0.0022) [2023-03-09 09:00:50,209][23090] Updated weights for policy 0, policy_version 68725 (0.0015) [2023-03-09 09:00:50,507][22940] Signal inference workers to stop experience collection... (22100 times) [2023-03-09 09:00:50,512][22940] Signal inference workers to resume experience collection... (22100 times) [2023-03-09 09:00:50,581][23090] InferenceWorker_p0-w0: stopping experience collection (22100 times) [2023-03-09 09:00:50,581][23090] InferenceWorker_p0-w0: resuming experience collection (22100 times) [2023-03-09 09:00:50,938][23090] Updated weights for policy 0, policy_version 68735 (0.0013) [2023-03-09 09:00:51,704][23090] Updated weights for policy 0, policy_version 68745 (0.0020) [2023-03-09 09:00:52,620][23090] Updated weights for policy 0, policy_version 68755 (0.0014) [2023-03-09 09:00:53,419][23090] Updated weights for policy 0, policy_version 68765 (0.0024) [2023-03-09 09:00:54,059][22664] Fps is (10 sec: 199883.3, 60 sec: 198518.8, 300 sec: 198774.0). Total num frames: 1126776832. Throughput: 0: 49635.3. Samples: 281754048. Policy #0 lag: (min: 0.0, avg: 17.2, max: 33.0) [2023-03-09 09:00:54,061][22664] Avg episode reward: [(0, '53.585')] [2023-03-09 09:00:54,303][23090] Updated weights for policy 0, policy_version 68776 (0.0013) [2023-03-09 09:00:55,206][23090] Updated weights for policy 0, policy_version 68786 (0.0013) [2023-03-09 09:00:56,002][23090] Updated weights for policy 0, policy_version 68796 (0.0019) [2023-03-09 09:00:56,779][23090] Updated weights for policy 0, policy_version 68806 (0.0012) [2023-03-09 09:00:57,612][23090] Updated weights for policy 0, policy_version 68816 (0.0022) [2023-03-09 09:00:58,464][23090] Updated weights for policy 0, policy_version 68826 (0.0018) [2023-03-09 09:00:59,059][22664] Fps is (10 sec: 198251.3, 60 sec: 198520.4, 300 sec: 198774.0). Total num frames: 1127759872. Throughput: 0: 49724.3. Samples: 281905472. Policy #0 lag: (min: 0.0, avg: 17.2, max: 33.0) [2023-03-09 09:00:59,060][22664] Avg episode reward: [(0, '54.324')] [2023-03-09 09:00:59,215][23090] Updated weights for policy 0, policy_version 68836 (0.0013) [2023-03-09 09:01:00,166][23090] Updated weights for policy 0, policy_version 68846 (0.0013) [2023-03-09 09:01:01,019][23090] Updated weights for policy 0, policy_version 68856 (0.0021) [2023-03-09 09:01:01,114][22940] Signal inference workers to stop experience collection... (22150 times) [2023-03-09 09:01:01,115][22940] Signal inference workers to resume experience collection... (22150 times) [2023-03-09 09:01:01,176][23090] InferenceWorker_p0-w0: stopping experience collection (22150 times) [2023-03-09 09:01:01,177][23090] InferenceWorker_p0-w0: resuming experience collection (22150 times) [2023-03-09 09:01:01,762][23090] Updated weights for policy 0, policy_version 68866 (0.0013) [2023-03-09 09:01:02,661][23090] Updated weights for policy 0, policy_version 68876 (0.0018) [2023-03-09 09:01:03,588][23090] Updated weights for policy 0, policy_version 68887 (0.0015) [2023-03-09 09:01:04,058][22664] Fps is (10 sec: 198251.0, 60 sec: 198793.2, 300 sec: 198829.6). Total num frames: 1128759296. Throughput: 0: 49724.1. Samples: 282204400. Policy #0 lag: (min: 0.0, avg: 17.2, max: 33.0) [2023-03-09 09:01:04,059][22664] Avg episode reward: [(0, '53.778')] [2023-03-09 09:01:04,318][23090] Updated weights for policy 0, policy_version 68897 (0.0016) [2023-03-09 09:01:05,036][23090] Updated weights for policy 0, policy_version 68907 (0.0013) [2023-03-09 09:01:06,023][23090] Updated weights for policy 0, policy_version 68917 (0.0014) [2023-03-09 09:01:06,726][23090] Updated weights for policy 0, policy_version 68927 (0.0017) [2023-03-09 09:01:07,504][23090] Updated weights for policy 0, policy_version 68937 (0.0018) [2023-03-09 09:01:08,459][23090] Updated weights for policy 0, policy_version 68947 (0.0016) [2023-03-09 09:01:09,058][22664] Fps is (10 sec: 199886.3, 60 sec: 199065.6, 300 sec: 198829.6). Total num frames: 1129758720. Throughput: 0: 49723.0. Samples: 282503296. Policy #0 lag: (min: 0.0, avg: 17.2, max: 33.0) [2023-03-09 09:01:09,059][22664] Avg episode reward: [(0, '53.683')] [2023-03-09 09:01:09,192][23090] Updated weights for policy 0, policy_version 68957 (0.0013) [2023-03-09 09:01:10,000][23090] Updated weights for policy 0, policy_version 68967 (0.0021) [2023-03-09 09:01:10,877][23090] Updated weights for policy 0, policy_version 68977 (0.0018) [2023-03-09 09:01:11,726][23090] Updated weights for policy 0, policy_version 68987 (0.0013) [2023-03-09 09:01:12,420][22940] Signal inference workers to stop experience collection... (22200 times) [2023-03-09 09:01:12,425][22940] Signal inference workers to resume experience collection... (22200 times) [2023-03-09 09:01:12,492][23090] InferenceWorker_p0-w0: stopping experience collection (22200 times) [2023-03-09 09:01:12,492][23090] InferenceWorker_p0-w0: resuming experience collection (22200 times) [2023-03-09 09:01:12,571][23090] Updated weights for policy 0, policy_version 68997 (0.0020) [2023-03-09 09:01:13,464][23090] Updated weights for policy 0, policy_version 69008 (0.0015) [2023-03-09 09:01:14,059][22664] Fps is (10 sec: 196603.3, 60 sec: 198518.7, 300 sec: 198718.5). Total num frames: 1130725376. Throughput: 0: 49769.4. Samples: 282650704. Policy #0 lag: (min: 0.0, avg: 17.2, max: 33.0) [2023-03-09 09:01:14,061][22664] Avg episode reward: [(0, '51.224')] [2023-03-09 09:01:14,354][23090] Updated weights for policy 0, policy_version 69018 (0.0013) [2023-03-09 09:01:15,078][23090] Updated weights for policy 0, policy_version 69028 (0.0017) [2023-03-09 09:01:15,998][23090] Updated weights for policy 0, policy_version 69038 (0.0013) [2023-03-09 09:01:16,881][23090] Updated weights for policy 0, policy_version 69049 (0.0013) [2023-03-09 09:01:17,661][23090] Updated weights for policy 0, policy_version 69059 (0.0014) [2023-03-09 09:01:18,573][23090] Updated weights for policy 0, policy_version 69070 (0.0013) [2023-03-09 09:01:19,059][22664] Fps is (10 sec: 196603.1, 60 sec: 198518.6, 300 sec: 198885.0). Total num frames: 1131724800. Throughput: 0: 49723.2. Samples: 282947520. Policy #0 lag: (min: 1.0, avg: 17.3, max: 34.0) [2023-03-09 09:01:19,060][22664] Avg episode reward: [(0, '54.316')] [2023-03-09 09:01:19,069][22940] Saving /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000069075_1131724800.pth... [2023-03-09 09:01:19,130][22940] Removing /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000066165_1084047360.pth [2023-03-09 09:01:19,509][23090] Updated weights for policy 0, policy_version 69080 (0.0017) [2023-03-09 09:01:20,238][23090] Updated weights for policy 0, policy_version 69090 (0.0013) [2023-03-09 09:01:21,122][23090] Updated weights for policy 0, policy_version 69100 (0.0015) [2023-03-09 09:01:21,997][23090] Updated weights for policy 0, policy_version 69110 (0.0017) [2023-03-09 09:01:22,695][23090] Updated weights for policy 0, policy_version 69120 (0.0013) [2023-03-09 09:01:23,492][23090] Updated weights for policy 0, policy_version 69130 (0.0022) [2023-03-09 09:01:23,892][22940] Signal inference workers to stop experience collection... (22250 times) [2023-03-09 09:01:23,896][22940] Signal inference workers to resume experience collection... (22250 times) [2023-03-09 09:01:23,957][23090] InferenceWorker_p0-w0: stopping experience collection (22250 times) [2023-03-09 09:01:23,957][23090] InferenceWorker_p0-w0: resuming experience collection (22250 times) [2023-03-09 09:01:24,059][22664] Fps is (10 sec: 199886.5, 60 sec: 199065.1, 300 sec: 198885.1). Total num frames: 1132724224. Throughput: 0: 49679.7. Samples: 283244416. Policy #0 lag: (min: 1.0, avg: 17.3, max: 34.0) [2023-03-09 09:01:24,060][22664] Avg episode reward: [(0, '56.042')] [2023-03-09 09:01:24,467][23090] Updated weights for policy 0, policy_version 69140 (0.0016) [2023-03-09 09:01:25,156][23090] Updated weights for policy 0, policy_version 69150 (0.0017) [2023-03-09 09:01:26,026][23090] Updated weights for policy 0, policy_version 69161 (0.0013) [2023-03-09 09:01:26,946][23090] Updated weights for policy 0, policy_version 69171 (0.0021) [2023-03-09 09:01:27,750][23090] Updated weights for policy 0, policy_version 69181 (0.0017) [2023-03-09 09:01:28,476][23090] Updated weights for policy 0, policy_version 69191 (0.0015) [2023-03-09 09:01:29,058][22664] Fps is (10 sec: 198251.8, 60 sec: 198793.7, 300 sec: 198774.0). Total num frames: 1133707264. Throughput: 0: 49725.7. Samples: 283395920. Policy #0 lag: (min: 1.0, avg: 17.3, max: 34.0) [2023-03-09 09:01:29,059][22664] Avg episode reward: [(0, '53.004')] [2023-03-09 09:01:29,469][23090] Updated weights for policy 0, policy_version 69202 (0.0016) [2023-03-09 09:01:30,268][23090] Updated weights for policy 0, policy_version 69212 (0.0013) [2023-03-09 09:01:31,018][23090] Updated weights for policy 0, policy_version 69222 (0.0012) [2023-03-09 09:01:31,866][23090] Updated weights for policy 0, policy_version 69232 (0.0022) [2023-03-09 09:01:32,787][23090] Updated weights for policy 0, policy_version 69242 (0.0013) [2023-03-09 09:01:33,558][23090] Updated weights for policy 0, policy_version 69252 (0.0016) [2023-03-09 09:01:34,059][22664] Fps is (10 sec: 201519.3, 60 sec: 199337.8, 300 sec: 198885.1). Total num frames: 1134739456. Throughput: 0: 49725.1. Samples: 283694816. Policy #0 lag: (min: 1.0, avg: 17.3, max: 34.0) [2023-03-09 09:01:34,061][22664] Avg episode reward: [(0, '52.699')] [2023-03-09 09:01:34,372][23090] Updated weights for policy 0, policy_version 69262 (0.0013) [2023-03-09 09:01:35,259][22940] Signal inference workers to stop experience collection... (22300 times) [2023-03-09 09:01:35,281][22940] Signal inference workers to resume experience collection... (22300 times) [2023-03-09 09:01:35,282][23090] Updated weights for policy 0, policy_version 69272 (0.0013) [2023-03-09 09:01:35,324][23090] InferenceWorker_p0-w0: stopping experience collection (22300 times) [2023-03-09 09:01:35,363][23090] InferenceWorker_p0-w0: resuming experience collection (22300 times) [2023-03-09 09:01:36,032][23090] Updated weights for policy 0, policy_version 69282 (0.0014) [2023-03-09 09:01:36,871][23090] Updated weights for policy 0, policy_version 69292 (0.0013) [2023-03-09 09:01:37,720][23090] Updated weights for policy 0, policy_version 69302 (0.0016) [2023-03-09 09:01:38,644][23090] Updated weights for policy 0, policy_version 69313 (0.0012) [2023-03-09 09:01:39,059][22664] Fps is (10 sec: 203157.9, 60 sec: 199065.7, 300 sec: 198885.0). Total num frames: 1135738880. Throughput: 0: 49771.4. Samples: 283993760. Policy #0 lag: (min: 1.0, avg: 17.3, max: 34.0) [2023-03-09 09:01:39,060][22664] Avg episode reward: [(0, '53.772')] [2023-03-09 09:01:39,311][23090] Updated weights for policy 0, policy_version 69323 (0.0016) [2023-03-09 09:01:40,304][23090] Updated weights for policy 0, policy_version 69333 (0.0016) [2023-03-09 09:01:41,010][23090] Updated weights for policy 0, policy_version 69343 (0.0014) [2023-03-09 09:01:41,815][23090] Updated weights for policy 0, policy_version 69353 (0.0014) [2023-03-09 09:01:42,742][23090] Updated weights for policy 0, policy_version 69363 (0.0016) [2023-03-09 09:01:43,520][23090] Updated weights for policy 0, policy_version 69373 (0.0016) [2023-03-09 09:01:44,059][22664] Fps is (10 sec: 196608.8, 60 sec: 198792.0, 300 sec: 198718.4). Total num frames: 1136705536. Throughput: 0: 49680.5. Samples: 284141104. Policy #0 lag: (min: 1.0, avg: 17.3, max: 34.0) [2023-03-09 09:01:44,103][22664] Avg episode reward: [(0, '53.976')] [2023-03-09 09:01:44,254][23090] Updated weights for policy 0, policy_version 69383 (0.0016) [2023-03-09 09:01:45,142][23090] Updated weights for policy 0, policy_version 69393 (0.0016) [2023-03-09 09:01:45,802][22940] Signal inference workers to stop experience collection... (22350 times) [2023-03-09 09:01:45,821][22940] Signal inference workers to resume experience collection... (22350 times) [2023-03-09 09:01:45,870][23090] InferenceWorker_p0-w0: stopping experience collection (22350 times) [2023-03-09 09:01:45,870][23090] InferenceWorker_p0-w0: resuming experience collection (22350 times) [2023-03-09 09:01:45,994][23090] Updated weights for policy 0, policy_version 69403 (0.0020) [2023-03-09 09:01:46,767][23090] Updated weights for policy 0, policy_version 69413 (0.0013) [2023-03-09 09:01:47,641][23090] Updated weights for policy 0, policy_version 69423 (0.0013) [2023-03-09 09:01:48,514][23090] Updated weights for policy 0, policy_version 69433 (0.0013) [2023-03-09 09:01:49,058][22664] Fps is (10 sec: 196611.1, 60 sec: 198793.6, 300 sec: 198774.0). Total num frames: 1137704960. Throughput: 0: 49682.1. Samples: 284440096. Policy #0 lag: (min: 1.0, avg: 17.3, max: 34.0) [2023-03-09 09:01:49,059][22664] Avg episode reward: [(0, '53.234')] [2023-03-09 09:01:49,325][23090] Updated weights for policy 0, policy_version 69443 (0.0018) [2023-03-09 09:01:50,165][23090] Updated weights for policy 0, policy_version 69453 (0.0021) [2023-03-09 09:01:51,103][23090] Updated weights for policy 0, policy_version 69463 (0.0013) [2023-03-09 09:01:51,870][23090] Updated weights for policy 0, policy_version 69473 (0.0013) [2023-03-09 09:01:52,534][23090] Updated weights for policy 0, policy_version 69483 (0.0013) [2023-03-09 09:01:53,554][23090] Updated weights for policy 0, policy_version 69493 (0.0013) [2023-03-09 09:01:54,059][22664] Fps is (10 sec: 198249.3, 60 sec: 198519.7, 300 sec: 198774.0). Total num frames: 1138688000. Throughput: 0: 49592.4. Samples: 284734960. Policy #0 lag: (min: 1.0, avg: 17.3, max: 34.0) [2023-03-09 09:01:54,060][22664] Avg episode reward: [(0, '55.663')] [2023-03-09 09:01:54,251][23090] Updated weights for policy 0, policy_version 69503 (0.0027) [2023-03-09 09:01:55,054][23090] Updated weights for policy 0, policy_version 69513 (0.0016) [2023-03-09 09:01:56,057][23090] Updated weights for policy 0, policy_version 69523 (0.0013) [2023-03-09 09:01:56,785][23090] Updated weights for policy 0, policy_version 69533 (0.0013) [2023-03-09 09:01:57,284][22940] Signal inference workers to stop experience collection... (22400 times) [2023-03-09 09:01:57,300][22940] Signal inference workers to resume experience collection... (22400 times) [2023-03-09 09:01:57,330][23090] InferenceWorker_p0-w0: stopping experience collection (22400 times) [2023-03-09 09:01:57,373][23090] InferenceWorker_p0-w0: resuming experience collection (22400 times) [2023-03-09 09:01:57,544][23090] Updated weights for policy 0, policy_version 69543 (0.0013) [2023-03-09 09:01:58,373][23090] Updated weights for policy 0, policy_version 69553 (0.0013) [2023-03-09 09:01:59,058][22664] Fps is (10 sec: 194969.8, 60 sec: 198246.7, 300 sec: 198662.9). Total num frames: 1139654656. Throughput: 0: 49592.4. Samples: 284882352. Policy #0 lag: (min: 1.0, avg: 17.3, max: 34.0) [2023-03-09 09:01:59,059][22664] Avg episode reward: [(0, '53.651')] [2023-03-09 09:01:59,232][23090] Updated weights for policy 0, policy_version 69563 (0.0016) [2023-03-09 09:01:59,996][23090] Updated weights for policy 0, policy_version 69573 (0.0029) [2023-03-09 09:02:00,838][23090] Updated weights for policy 0, policy_version 69583 (0.0018) [2023-03-09 09:02:01,723][23090] Updated weights for policy 0, policy_version 69593 (0.0018) [2023-03-09 09:02:02,574][23090] Updated weights for policy 0, policy_version 69604 (0.0013) [2023-03-09 09:02:03,450][23090] Updated weights for policy 0, policy_version 69614 (0.0019) [2023-03-09 09:02:04,059][22664] Fps is (10 sec: 198237.2, 60 sec: 198517.4, 300 sec: 198718.3). Total num frames: 1140670464. Throughput: 0: 49682.8. Samples: 285183264. Policy #0 lag: (min: 0.0, avg: 16.6, max: 33.0) [2023-03-09 09:02:04,061][22664] Avg episode reward: [(0, '53.269')] [2023-03-09 09:02:04,305][23090] Updated weights for policy 0, policy_version 69624 (0.0016) [2023-03-09 09:02:05,071][23090] Updated weights for policy 0, policy_version 69634 (0.0017) [2023-03-09 09:02:05,960][23090] Updated weights for policy 0, policy_version 69644 (0.0022) [2023-03-09 09:02:06,816][23090] Updated weights for policy 0, policy_version 69654 (0.0013) [2023-03-09 09:02:07,553][23090] Updated weights for policy 0, policy_version 69664 (0.0013) [2023-03-09 09:02:07,721][22940] Signal inference workers to stop experience collection... (22450 times) [2023-03-09 09:02:07,741][22940] Signal inference workers to resume experience collection... (22450 times) [2023-03-09 09:02:07,750][23090] InferenceWorker_p0-w0: stopping experience collection (22450 times) [2023-03-09 09:02:07,750][23090] InferenceWorker_p0-w0: resuming experience collection (22450 times) [2023-03-09 09:02:08,338][23090] Updated weights for policy 0, policy_version 69674 (0.0018) [2023-03-09 09:02:09,059][22664] Fps is (10 sec: 201520.7, 60 sec: 198519.1, 300 sec: 198774.1). Total num frames: 1141669888. Throughput: 0: 49727.7. Samples: 285482160. Policy #0 lag: (min: 0.0, avg: 16.6, max: 33.0) [2023-03-09 09:02:09,060][22664] Avg episode reward: [(0, '54.723')] [2023-03-09 09:02:09,272][23090] Updated weights for policy 0, policy_version 69684 (0.0013) [2023-03-09 09:02:10,046][23090] Updated weights for policy 0, policy_version 69694 (0.0019) [2023-03-09 09:02:10,809][23090] Updated weights for policy 0, policy_version 69704 (0.0016) [2023-03-09 09:02:11,698][23090] Updated weights for policy 0, policy_version 69714 (0.0013) [2023-03-09 09:02:12,494][23090] Updated weights for policy 0, policy_version 69724 (0.0016) [2023-03-09 09:02:13,299][23090] Updated weights for policy 0, policy_version 69734 (0.0013) [2023-03-09 09:02:14,059][22664] Fps is (10 sec: 199896.5, 60 sec: 199066.3, 300 sec: 198829.8). Total num frames: 1142669312. Throughput: 0: 49680.7. Samples: 285631552. Policy #0 lag: (min: 0.0, avg: 16.6, max: 33.0) [2023-03-09 09:02:14,059][22664] Avg episode reward: [(0, '52.193')] [2023-03-09 09:02:14,117][23090] Updated weights for policy 0, policy_version 69744 (0.0017) [2023-03-09 09:02:14,996][23090] Updated weights for policy 0, policy_version 69754 (0.0016) [2023-03-09 09:02:15,806][23090] Updated weights for policy 0, policy_version 69764 (0.0019) [2023-03-09 09:02:16,610][23090] Updated weights for policy 0, policy_version 69774 (0.0019) [2023-03-09 09:02:17,536][23090] Updated weights for policy 0, policy_version 69784 (0.0013) [2023-03-09 09:02:18,223][22940] Signal inference workers to stop experience collection... (22500 times) [2023-03-09 09:02:18,236][22940] Signal inference workers to resume experience collection... (22500 times) [2023-03-09 09:02:18,263][23090] InferenceWorker_p0-w0: stopping experience collection (22500 times) [2023-03-09 09:02:18,302][23090] InferenceWorker_p0-w0: resuming experience collection (22500 times) [2023-03-09 09:02:18,304][23090] Updated weights for policy 0, policy_version 69794 (0.0013) [2023-03-09 09:02:19,059][22664] Fps is (10 sec: 198238.9, 60 sec: 198791.7, 300 sec: 198718.3). Total num frames: 1143652352. Throughput: 0: 49634.0. Samples: 285928352. Policy #0 lag: (min: 0.0, avg: 16.6, max: 33.0) [2023-03-09 09:02:19,061][22664] Avg episode reward: [(0, '53.969')] [2023-03-09 09:02:19,165][23090] Updated weights for policy 0, policy_version 69804 (0.0016) [2023-03-09 09:02:20,056][23090] Updated weights for policy 0, policy_version 69814 (0.0017) [2023-03-09 09:02:20,775][23090] Updated weights for policy 0, policy_version 69824 (0.0016) [2023-03-09 09:02:21,529][23090] Updated weights for policy 0, policy_version 69834 (0.0013) [2023-03-09 09:02:22,480][23090] Updated weights for policy 0, policy_version 69844 (0.0013) [2023-03-09 09:02:23,224][23090] Updated weights for policy 0, policy_version 69854 (0.0013) [2023-03-09 09:02:24,022][23090] Updated weights for policy 0, policy_version 69864 (0.0013) [2023-03-09 09:02:24,059][22664] Fps is (10 sec: 198245.3, 60 sec: 198792.7, 300 sec: 198663.1). Total num frames: 1144651776. Throughput: 0: 49587.3. Samples: 286225184. Policy #0 lag: (min: 0.0, avg: 16.6, max: 33.0) [2023-03-09 09:02:24,065][22664] Avg episode reward: [(0, '52.967')] [2023-03-09 09:02:24,875][23090] Updated weights for policy 0, policy_version 69874 (0.0013) [2023-03-09 09:02:25,718][23090] Updated weights for policy 0, policy_version 69884 (0.0013) [2023-03-09 09:02:26,474][23090] Updated weights for policy 0, policy_version 69894 (0.0016) [2023-03-09 09:02:27,311][23090] Updated weights for policy 0, policy_version 69904 (0.0016) [2023-03-09 09:02:28,184][23090] Updated weights for policy 0, policy_version 69914 (0.0018) [2023-03-09 09:02:28,595][22940] Signal inference workers to stop experience collection... (22550 times) [2023-03-09 09:02:28,595][22940] Signal inference workers to resume experience collection... (22550 times) [2023-03-09 09:02:28,657][23090] InferenceWorker_p0-w0: stopping experience collection (22550 times) [2023-03-09 09:02:28,657][23090] InferenceWorker_p0-w0: resuming experience collection (22550 times) [2023-03-09 09:02:28,946][23090] Updated weights for policy 0, policy_version 69924 (0.0013) [2023-03-09 09:02:29,059][22664] Fps is (10 sec: 199892.9, 60 sec: 199065.2, 300 sec: 198718.6). Total num frames: 1145651200. Throughput: 0: 49634.0. Samples: 286374624. Policy #0 lag: (min: 0.0, avg: 16.6, max: 33.0) [2023-03-09 09:02:29,060][22664] Avg episode reward: [(0, '54.020')] [2023-03-09 09:02:29,832][23090] Updated weights for policy 0, policy_version 69934 (0.0016) [2023-03-09 09:02:30,747][23090] Updated weights for policy 0, policy_version 69944 (0.0016) [2023-03-09 09:02:31,478][23090] Updated weights for policy 0, policy_version 69954 (0.0016) [2023-03-09 09:02:32,356][23090] Updated weights for policy 0, policy_version 69964 (0.0020) [2023-03-09 09:02:33,269][23090] Updated weights for policy 0, policy_version 69974 (0.0014) [2023-03-09 09:02:33,936][23090] Updated weights for policy 0, policy_version 69984 (0.0013) [2023-03-09 09:02:34,059][22664] Fps is (10 sec: 196604.5, 60 sec: 197973.6, 300 sec: 198607.4). Total num frames: 1146617856. Throughput: 0: 49632.4. Samples: 286673568. Policy #0 lag: (min: 0.0, avg: 16.6, max: 33.0) [2023-03-09 09:02:34,060][22664] Avg episode reward: [(0, '52.107')] [2023-03-09 09:02:34,702][23090] Updated weights for policy 0, policy_version 69994 (0.0016) [2023-03-09 09:02:35,645][23090] Updated weights for policy 0, policy_version 70004 (0.0015) [2023-03-09 09:02:36,376][23090] Updated weights for policy 0, policy_version 70014 (0.0013) [2023-03-09 09:02:37,147][23090] Updated weights for policy 0, policy_version 70024 (0.0013) [2023-03-09 09:02:38,004][23090] Updated weights for policy 0, policy_version 70034 (0.0016) [2023-03-09 09:02:38,496][22940] Signal inference workers to stop experience collection... (22600 times) [2023-03-09 09:02:38,520][22940] Signal inference workers to resume experience collection... (22600 times) [2023-03-09 09:02:38,564][23090] InferenceWorker_p0-w0: stopping experience collection (22600 times) [2023-03-09 09:02:38,564][23090] InferenceWorker_p0-w0: resuming experience collection (22600 times) [2023-03-09 09:02:38,822][23090] Updated weights for policy 0, policy_version 70044 (0.0023) [2023-03-09 09:02:39,059][22664] Fps is (10 sec: 198247.6, 60 sec: 198246.9, 300 sec: 198662.9). Total num frames: 1147633664. Throughput: 0: 49768.3. Samples: 286974528. Policy #0 lag: (min: 0.0, avg: 16.6, max: 33.0) [2023-03-09 09:02:39,059][22664] Avg episode reward: [(0, '54.345')] [2023-03-09 09:02:39,625][23090] Updated weights for policy 0, policy_version 70054 (0.0019) [2023-03-09 09:02:40,455][23090] Updated weights for policy 0, policy_version 70064 (0.0018) [2023-03-09 09:02:41,373][23090] Updated weights for policy 0, policy_version 70074 (0.0016) [2023-03-09 09:02:42,110][23090] Updated weights for policy 0, policy_version 70084 (0.0016) [2023-03-09 09:02:42,960][23090] Updated weights for policy 0, policy_version 70094 (0.0016) [2023-03-09 09:02:43,873][23090] Updated weights for policy 0, policy_version 70104 (0.0013) [2023-03-09 09:02:44,058][22664] Fps is (10 sec: 201528.3, 60 sec: 198793.5, 300 sec: 198774.0). Total num frames: 1148633088. Throughput: 0: 49814.4. Samples: 287124000. Policy #0 lag: (min: 2.0, avg: 16.8, max: 33.0) [2023-03-09 09:02:44,059][22664] Avg episode reward: [(0, '55.614')] [2023-03-09 09:02:44,597][23090] Updated weights for policy 0, policy_version 70114 (0.0022) [2023-03-09 09:02:45,501][23090] Updated weights for policy 0, policy_version 70124 (0.0019) [2023-03-09 09:02:46,355][23090] Updated weights for policy 0, policy_version 70134 (0.0016) [2023-03-09 09:02:47,055][23090] Updated weights for policy 0, policy_version 70144 (0.0016) [2023-03-09 09:02:47,873][23090] Updated weights for policy 0, policy_version 70155 (0.0013) [2023-03-09 09:02:48,306][22940] Signal inference workers to stop experience collection... (22650 times) [2023-03-09 09:02:48,326][22940] Signal inference workers to resume experience collection... (22650 times) [2023-03-09 09:02:48,377][23090] InferenceWorker_p0-w0: stopping experience collection (22650 times) [2023-03-09 09:02:48,377][23090] InferenceWorker_p0-w0: resuming experience collection (22650 times) [2023-03-09 09:02:48,893][23090] Updated weights for policy 0, policy_version 70165 (0.0017) [2023-03-09 09:02:49,059][22664] Fps is (10 sec: 198240.4, 60 sec: 198518.4, 300 sec: 198662.8). Total num frames: 1149616128. Throughput: 0: 49726.2. Samples: 287420928. Policy #0 lag: (min: 2.0, avg: 16.8, max: 33.0) [2023-03-09 09:02:49,061][22664] Avg episode reward: [(0, '52.812')] [2023-03-09 09:02:49,581][23090] Updated weights for policy 0, policy_version 70175 (0.0016) [2023-03-09 09:02:50,387][23090] Updated weights for policy 0, policy_version 70185 (0.0020) [2023-03-09 09:02:51,336][23090] Updated weights for policy 0, policy_version 70195 (0.0023) [2023-03-09 09:02:52,075][23090] Updated weights for policy 0, policy_version 70205 (0.0013) [2023-03-09 09:02:52,842][23090] Updated weights for policy 0, policy_version 70215 (0.0018) [2023-03-09 09:02:53,728][23090] Updated weights for policy 0, policy_version 70225 (0.0013) [2023-03-09 09:02:54,059][22664] Fps is (10 sec: 196601.9, 60 sec: 198518.9, 300 sec: 198718.5). Total num frames: 1150599168. Throughput: 0: 49724.9. Samples: 287719792. Policy #0 lag: (min: 2.0, avg: 16.8, max: 33.0) [2023-03-09 09:02:54,061][22664] Avg episode reward: [(0, '54.814')] [2023-03-09 09:02:54,650][23090] Updated weights for policy 0, policy_version 70236 (0.0016) [2023-03-09 09:02:55,407][23090] Updated weights for policy 0, policy_version 70246 (0.0017) [2023-03-09 09:02:56,281][23090] Updated weights for policy 0, policy_version 70256 (0.0016) [2023-03-09 09:02:57,166][23090] Updated weights for policy 0, policy_version 70266 (0.0019) [2023-03-09 09:02:57,945][23090] Updated weights for policy 0, policy_version 70276 (0.0016) [2023-03-09 09:02:58,696][22940] Signal inference workers to stop experience collection... (22700 times) [2023-03-09 09:02:58,712][22940] Signal inference workers to resume experience collection... (22700 times) [2023-03-09 09:02:58,782][23090] InferenceWorker_p0-w0: stopping experience collection (22700 times) [2023-03-09 09:02:58,782][23090] InferenceWorker_p0-w0: resuming experience collection (22700 times) [2023-03-09 09:02:58,869][23090] Updated weights for policy 0, policy_version 70286 (0.0013) [2023-03-09 09:02:59,058][22664] Fps is (10 sec: 199891.6, 60 sec: 199338.7, 300 sec: 198774.3). Total num frames: 1151614976. Throughput: 0: 49727.3. Samples: 287869280. Policy #0 lag: (min: 2.0, avg: 16.8, max: 33.0) [2023-03-09 09:02:59,060][22664] Avg episode reward: [(0, '51.453')] [2023-03-09 09:02:59,679][23090] Updated weights for policy 0, policy_version 70296 (0.0013) [2023-03-09 09:03:00,467][23090] Updated weights for policy 0, policy_version 70306 (0.0017) [2023-03-09 09:03:01,323][23090] Updated weights for policy 0, policy_version 70316 (0.0013) [2023-03-09 09:03:02,183][23090] Updated weights for policy 0, policy_version 70326 (0.0013) [2023-03-09 09:03:02,888][23090] Updated weights for policy 0, policy_version 70336 (0.0014) [2023-03-09 09:03:03,682][23090] Updated weights for policy 0, policy_version 70346 (0.0013) [2023-03-09 09:03:04,059][22664] Fps is (10 sec: 199886.7, 60 sec: 198793.8, 300 sec: 198718.5). Total num frames: 1152598016. Throughput: 0: 49730.1. Samples: 288166192. Policy #0 lag: (min: 2.0, avg: 16.8, max: 33.0) [2023-03-09 09:03:04,061][22664] Avg episode reward: [(0, '52.394')] [2023-03-09 09:03:04,671][23090] Updated weights for policy 0, policy_version 70356 (0.0019) [2023-03-09 09:03:05,561][23090] Updated weights for policy 0, policy_version 70368 (0.0024) [2023-03-09 09:03:06,358][23090] Updated weights for policy 0, policy_version 70378 (0.0023) [2023-03-09 09:03:07,337][23090] Updated weights for policy 0, policy_version 70388 (0.0016) [2023-03-09 09:03:08,068][23090] Updated weights for policy 0, policy_version 70398 (0.0016) [2023-03-09 09:03:08,115][22940] Signal inference workers to stop experience collection... (22750 times) [2023-03-09 09:03:08,129][22940] Signal inference workers to resume experience collection... (22750 times) [2023-03-09 09:03:08,185][23090] InferenceWorker_p0-w0: stopping experience collection (22750 times) [2023-03-09 09:03:08,187][23090] InferenceWorker_p0-w0: resuming experience collection (22750 times) [2023-03-09 09:03:08,816][23090] Updated weights for policy 0, policy_version 70408 (0.0013) [2023-03-09 09:03:09,059][22664] Fps is (10 sec: 199877.0, 60 sec: 199064.7, 300 sec: 198774.2). Total num frames: 1153613824. Throughput: 0: 49729.8. Samples: 288463040. Policy #0 lag: (min: 2.0, avg: 16.8, max: 33.0) [2023-03-09 09:03:09,061][22664] Avg episode reward: [(0, '55.788')] [2023-03-09 09:03:09,661][23090] Updated weights for policy 0, policy_version 70418 (0.0019) [2023-03-09 09:03:10,465][23090] Updated weights for policy 0, policy_version 70428 (0.0015) [2023-03-09 09:03:11,264][23090] Updated weights for policy 0, policy_version 70438 (0.0013) [2023-03-09 09:03:12,117][23090] Updated weights for policy 0, policy_version 70448 (0.0021) [2023-03-09 09:03:13,031][23090] Updated weights for policy 0, policy_version 70458 (0.0026) [2023-03-09 09:03:13,769][23090] Updated weights for policy 0, policy_version 70468 (0.0013) [2023-03-09 09:03:14,058][22664] Fps is (10 sec: 201527.4, 60 sec: 199065.7, 300 sec: 198829.7). Total num frames: 1154613248. Throughput: 0: 49776.1. Samples: 288614544. Policy #0 lag: (min: 2.0, avg: 16.8, max: 33.0) [2023-03-09 09:03:14,060][22664] Avg episode reward: [(0, '55.628')] [2023-03-09 09:03:14,700][23090] Updated weights for policy 0, policy_version 70478 (0.0020) [2023-03-09 09:03:15,551][23090] Updated weights for policy 0, policy_version 70488 (0.0018) [2023-03-09 09:03:16,307][23090] Updated weights for policy 0, policy_version 70498 (0.0015) [2023-03-09 09:03:17,192][23090] Updated weights for policy 0, policy_version 70508 (0.0023) [2023-03-09 09:03:18,079][23090] Updated weights for policy 0, policy_version 70518 (0.0013) [2023-03-09 09:03:18,735][23090] Updated weights for policy 0, policy_version 70528 (0.0017) [2023-03-09 09:03:19,059][22664] Fps is (10 sec: 198247.6, 60 sec: 199066.2, 300 sec: 198718.5). Total num frames: 1155596288. Throughput: 0: 49683.1. Samples: 288909312. Policy #0 lag: (min: 2.0, avg: 16.8, max: 33.0) [2023-03-09 09:03:19,061][22664] Avg episode reward: [(0, '54.242')] [2023-03-09 09:03:19,091][22940] Saving /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000070533_1155612672.pth... [2023-03-09 09:03:19,164][22940] Removing /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000067622_1107918848.pth [2023-03-09 09:03:19,214][22940] Signal inference workers to stop experience collection... (22800 times) [2023-03-09 09:03:19,228][22940] Signal inference workers to resume experience collection... (22800 times) [2023-03-09 09:03:19,318][23090] InferenceWorker_p0-w0: stopping experience collection (22800 times) [2023-03-09 09:03:19,321][23090] InferenceWorker_p0-w0: resuming experience collection (22800 times) [2023-03-09 09:03:19,606][23090] Updated weights for policy 0, policy_version 70539 (0.0018) [2023-03-09 09:03:20,565][23090] Updated weights for policy 0, policy_version 70549 (0.0018) [2023-03-09 09:03:21,327][23090] Updated weights for policy 0, policy_version 70559 (0.0013) [2023-03-09 09:03:22,109][23090] Updated weights for policy 0, policy_version 70569 (0.0017) [2023-03-09 09:03:23,011][23090] Updated weights for policy 0, policy_version 70579 (0.0016) [2023-03-09 09:03:23,761][23090] Updated weights for policy 0, policy_version 70589 (0.0018) [2023-03-09 09:03:24,059][22664] Fps is (10 sec: 196602.3, 60 sec: 198791.8, 300 sec: 198662.8). Total num frames: 1156579328. Throughput: 0: 49638.5. Samples: 289208272. Policy #0 lag: (min: 2.0, avg: 16.8, max: 33.0) [2023-03-09 09:03:24,061][22664] Avg episode reward: [(0, '54.001')] [2023-03-09 09:03:24,570][23090] Updated weights for policy 0, policy_version 70599 (0.0020) [2023-03-09 09:03:25,422][23090] Updated weights for policy 0, policy_version 70609 (0.0017) [2023-03-09 09:03:26,274][23090] Updated weights for policy 0, policy_version 70619 (0.0020) [2023-03-09 09:03:27,155][23090] Updated weights for policy 0, policy_version 70630 (0.0013) [2023-03-09 09:03:27,984][23090] Updated weights for policy 0, policy_version 70640 (0.0028) [2023-03-09 09:03:28,896][23090] Updated weights for policy 0, policy_version 70650 (0.0013) [2023-03-09 09:03:29,059][22664] Fps is (10 sec: 198250.2, 60 sec: 198792.4, 300 sec: 198663.1). Total num frames: 1157578752. Throughput: 0: 49638.6. Samples: 289357744. Policy #0 lag: (min: 1.0, avg: 17.4, max: 33.0) [2023-03-09 09:03:29,060][22664] Avg episode reward: [(0, '55.594')] [2023-03-09 09:03:29,647][22940] Signal inference workers to stop experience collection... (22850 times) [2023-03-09 09:03:29,648][22940] Signal inference workers to resume experience collection... (22850 times) [2023-03-09 09:03:29,680][23090] Updated weights for policy 0, policy_version 70660 (0.0019) [2023-03-09 09:03:29,716][23090] InferenceWorker_p0-w0: stopping experience collection (22850 times) [2023-03-09 09:03:29,719][23090] InferenceWorker_p0-w0: resuming experience collection (22850 times) [2023-03-09 09:03:30,513][23090] Updated weights for policy 0, policy_version 70670 (0.0021) [2023-03-09 09:03:31,365][23090] Updated weights for policy 0, policy_version 70680 (0.0013) [2023-03-09 09:03:32,163][23090] Updated weights for policy 0, policy_version 70690 (0.0018) [2023-03-09 09:03:33,002][23090] Updated weights for policy 0, policy_version 70700 (0.0016) [2023-03-09 09:03:33,918][23090] Updated weights for policy 0, policy_version 70710 (0.0016) [2023-03-09 09:03:34,059][22664] Fps is (10 sec: 198246.5, 60 sec: 199065.5, 300 sec: 198662.9). Total num frames: 1158561792. Throughput: 0: 49637.7. Samples: 289654624. Policy #0 lag: (min: 1.0, avg: 17.4, max: 33.0) [2023-03-09 09:03:34,061][22664] Avg episode reward: [(0, '52.919')] [2023-03-09 09:03:34,570][23090] Updated weights for policy 0, policy_version 70720 (0.0016) [2023-03-09 09:03:35,374][23090] Updated weights for policy 0, policy_version 70730 (0.0017) [2023-03-09 09:03:36,330][23090] Updated weights for policy 0, policy_version 70740 (0.0018) [2023-03-09 09:03:37,132][23090] Updated weights for policy 0, policy_version 70750 (0.0016) [2023-03-09 09:03:37,841][23090] Updated weights for policy 0, policy_version 70760 (0.0017) [2023-03-09 09:03:38,711][23090] Updated weights for policy 0, policy_version 70770 (0.0013) [2023-03-09 09:03:39,058][22664] Fps is (10 sec: 194972.2, 60 sec: 198246.5, 300 sec: 198496.3). Total num frames: 1159528448. Throughput: 0: 49636.6. Samples: 289953424. Policy #0 lag: (min: 1.0, avg: 17.4, max: 33.0) [2023-03-09 09:03:39,059][22664] Avg episode reward: [(0, '52.885')] [2023-03-09 09:03:39,517][23090] Updated weights for policy 0, policy_version 70780 (0.0020) [2023-03-09 09:03:40,431][23090] Updated weights for policy 0, policy_version 70791 (0.0013) [2023-03-09 09:03:41,228][23090] Updated weights for policy 0, policy_version 70801 (0.0013) [2023-03-09 09:03:41,888][22940] Signal inference workers to stop experience collection... (22900 times) [2023-03-09 09:03:41,915][22940] Signal inference workers to resume experience collection... (22900 times) [2023-03-09 09:03:41,991][23090] InferenceWorker_p0-w0: stopping experience collection (22900 times) [2023-03-09 09:03:41,991][23090] InferenceWorker_p0-w0: resuming experience collection (22900 times) [2023-03-09 09:03:42,072][23090] Updated weights for policy 0, policy_version 70811 (0.0024) [2023-03-09 09:03:42,846][23090] Updated weights for policy 0, policy_version 70821 (0.0023) [2023-03-09 09:03:43,732][23090] Updated weights for policy 0, policy_version 70831 (0.0019) [2023-03-09 09:03:44,059][22664] Fps is (10 sec: 198249.4, 60 sec: 198519.0, 300 sec: 198663.4). Total num frames: 1160544256. Throughput: 0: 49681.3. Samples: 290104944. Policy #0 lag: (min: 1.0, avg: 17.4, max: 33.0) [2023-03-09 09:03:44,060][22664] Avg episode reward: [(0, '55.096')] [2023-03-09 09:03:44,578][23090] Updated weights for policy 0, policy_version 70841 (0.0015) [2023-03-09 09:03:45,353][23090] Updated weights for policy 0, policy_version 70851 (0.0016) [2023-03-09 09:03:46,217][23090] Updated weights for policy 0, policy_version 70861 (0.0013) [2023-03-09 09:03:47,064][23090] Updated weights for policy 0, policy_version 70871 (0.0013) [2023-03-09 09:03:47,847][23090] Updated weights for policy 0, policy_version 70881 (0.0022) [2023-03-09 09:03:48,617][23090] Updated weights for policy 0, policy_version 70891 (0.0013) [2023-03-09 09:03:49,059][22664] Fps is (10 sec: 203153.2, 60 sec: 199065.3, 300 sec: 198774.0). Total num frames: 1161560064. Throughput: 0: 49681.2. Samples: 290401856. Policy #0 lag: (min: 1.0, avg: 17.4, max: 33.0) [2023-03-09 09:03:49,061][22664] Avg episode reward: [(0, '54.629')] [2023-03-09 09:03:49,583][23090] Updated weights for policy 0, policy_version 70901 (0.0025) [2023-03-09 09:03:50,330][23090] Updated weights for policy 0, policy_version 70911 (0.0020) [2023-03-09 09:03:51,063][23090] Updated weights for policy 0, policy_version 70921 (0.0013) [2023-03-09 09:03:52,167][23090] Updated weights for policy 0, policy_version 70932 (0.0019) [2023-03-09 09:03:52,307][22940] Signal inference workers to stop experience collection... (22950 times) [2023-03-09 09:03:52,307][22940] Signal inference workers to resume experience collection... (22950 times) [2023-03-09 09:03:52,373][23090] InferenceWorker_p0-w0: stopping experience collection (22950 times) [2023-03-09 09:03:52,373][23090] InferenceWorker_p0-w0: resuming experience collection (22950 times) [2023-03-09 09:03:52,936][23090] Updated weights for policy 0, policy_version 70942 (0.0016) [2023-03-09 09:03:53,648][23090] Updated weights for policy 0, policy_version 70952 (0.0017) [2023-03-09 09:03:54,059][22664] Fps is (10 sec: 198246.3, 60 sec: 198793.1, 300 sec: 198663.0). Total num frames: 1162526720. Throughput: 0: 49682.7. Samples: 290698752. Policy #0 lag: (min: 1.0, avg: 17.4, max: 33.0) [2023-03-09 09:03:54,060][22664] Avg episode reward: [(0, '53.922')] [2023-03-09 09:03:54,661][23090] Updated weights for policy 0, policy_version 70963 (0.0021) [2023-03-09 09:03:55,393][23090] Updated weights for policy 0, policy_version 70973 (0.0016) [2023-03-09 09:03:56,229][23090] Updated weights for policy 0, policy_version 70983 (0.0016) [2023-03-09 09:03:57,045][23090] Updated weights for policy 0, policy_version 70993 (0.0016) [2023-03-09 09:03:57,997][23090] Updated weights for policy 0, policy_version 71004 (0.0013) [2023-03-09 09:03:58,763][23090] Updated weights for policy 0, policy_version 71014 (0.0022) [2023-03-09 09:03:59,059][22664] Fps is (10 sec: 199885.9, 60 sec: 199064.4, 300 sec: 198773.8). Total num frames: 1163558912. Throughput: 0: 49682.1. Samples: 290850256. Policy #0 lag: (min: 1.0, avg: 17.4, max: 33.0) [2023-03-09 09:03:59,061][22664] Avg episode reward: [(0, '52.377')] [2023-03-09 09:03:59,567][23090] Updated weights for policy 0, policy_version 71024 (0.0019) [2023-03-09 09:04:00,437][23090] Updated weights for policy 0, policy_version 71034 (0.0013) [2023-03-09 09:04:01,222][23090] Updated weights for policy 0, policy_version 71044 (0.0012) [2023-03-09 09:04:02,082][23090] Updated weights for policy 0, policy_version 71054 (0.0013) [2023-03-09 09:04:02,965][23090] Updated weights for policy 0, policy_version 71064 (0.0015) [2023-03-09 09:04:03,038][22940] Signal inference workers to stop experience collection... (23000 times) [2023-03-09 09:04:03,051][22940] Signal inference workers to resume experience collection... (23000 times) [2023-03-09 09:04:03,079][23090] InferenceWorker_p0-w0: stopping experience collection (23000 times) [2023-03-09 09:04:03,144][23090] InferenceWorker_p0-w0: resuming experience collection (23000 times) [2023-03-09 09:04:03,744][23090] Updated weights for policy 0, policy_version 71074 (0.0016) [2023-03-09 09:04:04,059][22664] Fps is (10 sec: 203164.1, 60 sec: 199339.3, 300 sec: 198829.6). Total num frames: 1164558336. Throughput: 0: 49774.2. Samples: 291149136. Policy #0 lag: (min: 1.0, avg: 17.4, max: 33.0) [2023-03-09 09:04:04,060][22664] Avg episode reward: [(0, '53.683')] [2023-03-09 09:04:04,636][23090] Updated weights for policy 0, policy_version 71084 (0.0015) [2023-03-09 09:04:05,479][23090] Updated weights for policy 0, policy_version 71094 (0.0013) [2023-03-09 09:04:06,150][23090] Updated weights for policy 0, policy_version 71104 (0.0017) [2023-03-09 09:04:06,928][23090] Updated weights for policy 0, policy_version 71114 (0.0021) [2023-03-09 09:04:07,952][23090] Updated weights for policy 0, policy_version 71124 (0.0018) [2023-03-09 09:04:08,703][23090] Updated weights for policy 0, policy_version 71134 (0.0013) [2023-03-09 09:04:09,058][22664] Fps is (10 sec: 198253.8, 60 sec: 198793.9, 300 sec: 198718.7). Total num frames: 1165541376. Throughput: 0: 49772.8. Samples: 291448032. Policy #0 lag: (min: 1.0, avg: 17.4, max: 33.0) [2023-03-09 09:04:09,059][22664] Avg episode reward: [(0, '54.994')] [2023-03-09 09:04:09,401][23090] Updated weights for policy 0, policy_version 71144 (0.0013) [2023-03-09 09:04:10,307][23090] Updated weights for policy 0, policy_version 71154 (0.0013) [2023-03-09 09:04:11,077][23090] Updated weights for policy 0, policy_version 71164 (0.0016) [2023-03-09 09:04:11,910][23090] Updated weights for policy 0, policy_version 71174 (0.0013) [2023-03-09 09:04:12,717][23090] Updated weights for policy 0, policy_version 71184 (0.0013) [2023-03-09 09:04:13,625][23090] Updated weights for policy 0, policy_version 71194 (0.0013) [2023-03-09 09:04:14,058][22664] Fps is (10 sec: 198246.5, 60 sec: 198792.5, 300 sec: 198718.5). Total num frames: 1166540800. Throughput: 0: 49771.1. Samples: 291597440. Policy #0 lag: (min: 0.0, avg: 16.8, max: 32.0) [2023-03-09 09:04:14,060][22664] Avg episode reward: [(0, '56.374')] [2023-03-09 09:04:14,353][23090] Updated weights for policy 0, policy_version 71204 (0.0023) [2023-03-09 09:04:15,225][23090] Updated weights for policy 0, policy_version 71214 (0.0019) [2023-03-09 09:04:15,271][22940] Signal inference workers to stop experience collection... (23050 times) [2023-03-09 09:04:15,284][22940] Signal inference workers to resume experience collection... (23050 times) [2023-03-09 09:04:15,341][23090] InferenceWorker_p0-w0: stopping experience collection (23050 times) [2023-03-09 09:04:15,342][23090] InferenceWorker_p0-w0: resuming experience collection (23050 times) [2023-03-09 09:04:16,119][23090] Updated weights for policy 0, policy_version 71224 (0.0013) [2023-03-09 09:04:16,850][23090] Updated weights for policy 0, policy_version 71234 (0.0014) [2023-03-09 09:04:17,771][23090] Updated weights for policy 0, policy_version 71244 (0.0013) [2023-03-09 09:04:18,644][23090] Updated weights for policy 0, policy_version 71254 (0.0020) [2023-03-09 09:04:19,059][22664] Fps is (10 sec: 199881.2, 60 sec: 199066.1, 300 sec: 198829.4). Total num frames: 1167540224. Throughput: 0: 49817.7. Samples: 291896416. Policy #0 lag: (min: 0.0, avg: 16.8, max: 32.0) [2023-03-09 09:04:19,060][22664] Avg episode reward: [(0, '54.291')] [2023-03-09 09:04:19,335][23090] Updated weights for policy 0, policy_version 71264 (0.0021) [2023-03-09 09:04:20,082][23090] Updated weights for policy 0, policy_version 71274 (0.0018) [2023-03-09 09:04:21,113][23090] Updated weights for policy 0, policy_version 71284 (0.0016) [2023-03-09 09:04:21,910][23090] Updated weights for policy 0, policy_version 71294 (0.0016) [2023-03-09 09:04:22,617][23090] Updated weights for policy 0, policy_version 71304 (0.0013) [2023-03-09 09:04:23,476][23090] Updated weights for policy 0, policy_version 71314 (0.0016) [2023-03-09 09:04:24,058][22664] Fps is (10 sec: 198247.7, 60 sec: 199066.7, 300 sec: 198774.1). Total num frames: 1168523264. Throughput: 0: 49820.5. Samples: 292195344. Policy #0 lag: (min: 0.0, avg: 16.8, max: 32.0) [2023-03-09 09:04:24,059][22664] Avg episode reward: [(0, '54.501')] [2023-03-09 09:04:24,237][23090] Updated weights for policy 0, policy_version 71324 (0.0014) [2023-03-09 09:04:25,078][23090] Updated weights for policy 0, policy_version 71334 (0.0013) [2023-03-09 09:04:25,879][23090] Updated weights for policy 0, policy_version 71344 (0.0013) [2023-03-09 09:04:26,714][22940] Signal inference workers to stop experience collection... (23100 times) [2023-03-09 09:04:26,730][22940] Signal inference workers to resume experience collection... (23100 times) [2023-03-09 09:04:26,798][23090] InferenceWorker_p0-w0: stopping experience collection (23100 times) [2023-03-09 09:04:26,798][23090] InferenceWorker_p0-w0: resuming experience collection (23100 times) [2023-03-09 09:04:26,801][23090] Updated weights for policy 0, policy_version 71354 (0.0013) [2023-03-09 09:04:27,563][23090] Updated weights for policy 0, policy_version 71364 (0.0017) [2023-03-09 09:04:28,404][23090] Updated weights for policy 0, policy_version 71374 (0.0013) [2023-03-09 09:04:29,059][22664] Fps is (10 sec: 194967.6, 60 sec: 198519.0, 300 sec: 198773.9). Total num frames: 1169489920. Throughput: 0: 49728.2. Samples: 292342720. Policy #0 lag: (min: 0.0, avg: 16.8, max: 32.0) [2023-03-09 09:04:29,060][22664] Avg episode reward: [(0, '53.095')] [2023-03-09 09:04:29,264][23090] Updated weights for policy 0, policy_version 71384 (0.0013) [2023-03-09 09:04:30,029][23090] Updated weights for policy 0, policy_version 71394 (0.0014) [2023-03-09 09:04:30,980][23090] Updated weights for policy 0, policy_version 71405 (0.0013) [2023-03-09 09:04:31,936][23090] Updated weights for policy 0, policy_version 71416 (0.0018) [2023-03-09 09:04:32,665][23090] Updated weights for policy 0, policy_version 71426 (0.0021) [2023-03-09 09:04:33,586][23090] Updated weights for policy 0, policy_version 71436 (0.0013) [2023-03-09 09:04:34,058][22664] Fps is (10 sec: 198245.9, 60 sec: 199066.6, 300 sec: 198885.4). Total num frames: 1170505728. Throughput: 0: 49819.1. Samples: 292643696. Policy #0 lag: (min: 0.0, avg: 16.8, max: 32.0) [2023-03-09 09:04:34,059][22664] Avg episode reward: [(0, '53.919')] [2023-03-09 09:04:34,439][23090] Updated weights for policy 0, policy_version 71446 (0.0013) [2023-03-09 09:04:35,242][23090] Updated weights for policy 0, policy_version 71457 (0.0013) [2023-03-09 09:04:35,983][23090] Updated weights for policy 0, policy_version 71467 (0.0013) [2023-03-09 09:04:37,005][23090] Updated weights for policy 0, policy_version 71477 (0.0017) [2023-03-09 09:04:37,781][23090] Updated weights for policy 0, policy_version 71488 (0.0013) [2023-03-09 09:04:38,538][23090] Updated weights for policy 0, policy_version 71498 (0.0015) [2023-03-09 09:04:39,059][22664] Fps is (10 sec: 203163.2, 60 sec: 199884.1, 300 sec: 198885.1). Total num frames: 1171521536. Throughput: 0: 49817.2. Samples: 292940528. Policy #0 lag: (min: 0.0, avg: 16.8, max: 32.0) [2023-03-09 09:04:39,060][22664] Avg episode reward: [(0, '53.358')] [2023-03-09 09:04:39,543][23090] Updated weights for policy 0, policy_version 71508 (0.0016) [2023-03-09 09:04:39,637][22940] Signal inference workers to stop experience collection... (23150 times) [2023-03-09 09:04:39,638][22940] Signal inference workers to resume experience collection... (23150 times) [2023-03-09 09:04:39,705][23090] InferenceWorker_p0-w0: stopping experience collection (23150 times) [2023-03-09 09:04:39,705][23090] InferenceWorker_p0-w0: resuming experience collection (23150 times) [2023-03-09 09:04:40,347][23090] Updated weights for policy 0, policy_version 71518 (0.0013) [2023-03-09 09:04:41,051][23090] Updated weights for policy 0, policy_version 71528 (0.0014) [2023-03-09 09:04:41,898][23090] Updated weights for policy 0, policy_version 71538 (0.0016) [2023-03-09 09:04:42,770][23090] Updated weights for policy 0, policy_version 71548 (0.0021) [2023-03-09 09:04:43,546][23090] Updated weights for policy 0, policy_version 71558 (0.0013) [2023-03-09 09:04:44,059][22664] Fps is (10 sec: 198239.7, 60 sec: 199065.0, 300 sec: 198774.0). Total num frames: 1172488192. Throughput: 0: 49770.7. Samples: 293089936. Policy #0 lag: (min: 0.0, avg: 16.8, max: 32.0) [2023-03-09 09:04:44,060][22664] Avg episode reward: [(0, '55.825')] [2023-03-09 09:04:44,328][23090] Updated weights for policy 0, policy_version 71568 (0.0013) [2023-03-09 09:04:45,211][23090] Updated weights for policy 0, policy_version 71578 (0.0013) [2023-03-09 09:04:45,991][23090] Updated weights for policy 0, policy_version 71588 (0.0019) [2023-03-09 09:04:46,829][23090] Updated weights for policy 0, policy_version 71598 (0.0019) [2023-03-09 09:04:47,717][23090] Updated weights for policy 0, policy_version 71608 (0.0016) [2023-03-09 09:04:48,479][23090] Updated weights for policy 0, policy_version 71618 (0.0013) [2023-03-09 09:04:49,058][22664] Fps is (10 sec: 198250.4, 60 sec: 199067.0, 300 sec: 198774.0). Total num frames: 1173504000. Throughput: 0: 49770.7. Samples: 293388816. Policy #0 lag: (min: 0.0, avg: 16.8, max: 32.0) [2023-03-09 09:04:49,059][22664] Avg episode reward: [(0, '55.230')] [2023-03-09 09:04:49,375][23090] Updated weights for policy 0, policy_version 71628 (0.0013) [2023-03-09 09:04:50,255][23090] Updated weights for policy 0, policy_version 71638 (0.0019) [2023-03-09 09:04:50,964][23090] Updated weights for policy 0, policy_version 71648 (0.0020) [2023-03-09 09:04:51,459][22940] Signal inference workers to stop experience collection... (23200 times) [2023-03-09 09:04:51,475][22940] Signal inference workers to resume experience collection... (23200 times) [2023-03-09 09:04:51,541][23090] InferenceWorker_p0-w0: stopping experience collection (23200 times) [2023-03-09 09:04:51,541][23090] InferenceWorker_p0-w0: resuming experience collection (23200 times) [2023-03-09 09:04:51,705][23090] Updated weights for policy 0, policy_version 71658 (0.0013) [2023-03-09 09:04:52,853][23090] Updated weights for policy 0, policy_version 71669 (0.0013) [2023-03-09 09:04:53,563][23090] Updated weights for policy 0, policy_version 71679 (0.0018) [2023-03-09 09:04:54,058][22664] Fps is (10 sec: 199891.6, 60 sec: 199339.2, 300 sec: 198774.3). Total num frames: 1174487040. Throughput: 0: 49726.2. Samples: 293685712. Policy #0 lag: (min: 1.0, avg: 17.0, max: 33.0) [2023-03-09 09:04:54,060][22664] Avg episode reward: [(0, '54.439')] [2023-03-09 09:04:54,276][23090] Updated weights for policy 0, policy_version 71689 (0.0016) [2023-03-09 09:04:55,269][23090] Updated weights for policy 0, policy_version 71699 (0.0015) [2023-03-09 09:04:56,016][23090] Updated weights for policy 0, policy_version 71709 (0.0017) [2023-03-09 09:04:56,825][23090] Updated weights for policy 0, policy_version 71719 (0.0021) [2023-03-09 09:04:57,611][23090] Updated weights for policy 0, policy_version 71729 (0.0020) [2023-03-09 09:04:58,508][23090] Updated weights for policy 0, policy_version 71739 (0.0013) [2023-03-09 09:04:59,058][22664] Fps is (10 sec: 198246.2, 60 sec: 198793.7, 300 sec: 198829.7). Total num frames: 1175486464. Throughput: 0: 49727.3. Samples: 293835168. Policy #0 lag: (min: 1.0, avg: 17.0, max: 33.0) [2023-03-09 09:04:59,059][22664] Avg episode reward: [(0, '54.576')] [2023-03-09 09:04:59,278][23090] Updated weights for policy 0, policy_version 71749 (0.0016) [2023-03-09 09:05:00,151][23090] Updated weights for policy 0, policy_version 71760 (0.0013) [2023-03-09 09:05:01,074][23090] Updated weights for policy 0, policy_version 71770 (0.0013) [2023-03-09 09:05:01,841][23090] Updated weights for policy 0, policy_version 71780 (0.0016) [2023-03-09 09:05:02,699][23090] Updated weights for policy 0, policy_version 71790 (0.0017) [2023-03-09 09:05:03,383][22940] Signal inference workers to stop experience collection... (23250 times) [2023-03-09 09:05:03,384][22940] Signal inference workers to resume experience collection... (23250 times) [2023-03-09 09:05:03,454][23090] InferenceWorker_p0-w0: stopping experience collection (23250 times) [2023-03-09 09:05:03,454][23090] InferenceWorker_p0-w0: resuming experience collection (23250 times) [2023-03-09 09:05:03,573][23090] Updated weights for policy 0, policy_version 71800 (0.0016) [2023-03-09 09:05:04,059][22664] Fps is (10 sec: 198245.4, 60 sec: 198519.4, 300 sec: 198829.5). Total num frames: 1176469504. Throughput: 0: 49725.7. Samples: 294134064. Policy #0 lag: (min: 1.0, avg: 17.0, max: 33.0) [2023-03-09 09:05:04,059][22664] Avg episode reward: [(0, '54.082')] [2023-03-09 09:05:04,311][23090] Updated weights for policy 0, policy_version 71810 (0.0013) [2023-03-09 09:05:05,265][23090] Updated weights for policy 0, policy_version 71820 (0.0017) [2023-03-09 09:05:06,081][23090] Updated weights for policy 0, policy_version 71830 (0.0021) [2023-03-09 09:05:06,798][23090] Updated weights for policy 0, policy_version 71840 (0.0013) [2023-03-09 09:05:07,547][23090] Updated weights for policy 0, policy_version 71850 (0.0020) [2023-03-09 09:05:08,586][23090] Updated weights for policy 0, policy_version 71860 (0.0017) [2023-03-09 09:05:09,058][22664] Fps is (10 sec: 196608.5, 60 sec: 198519.5, 300 sec: 198774.0). Total num frames: 1177452544. Throughput: 0: 49678.6. Samples: 294430880. Policy #0 lag: (min: 1.0, avg: 17.0, max: 33.0) [2023-03-09 09:05:09,059][22664] Avg episode reward: [(0, '53.396')] [2023-03-09 09:05:09,318][23090] Updated weights for policy 0, policy_version 71870 (0.0016) [2023-03-09 09:05:10,100][23090] Updated weights for policy 0, policy_version 71880 (0.0020) [2023-03-09 09:05:10,951][23090] Updated weights for policy 0, policy_version 71890 (0.0015) [2023-03-09 09:05:11,864][23090] Updated weights for policy 0, policy_version 71901 (0.0012) [2023-03-09 09:05:12,682][23090] Updated weights for policy 0, policy_version 71911 (0.0016) [2023-03-09 09:05:13,491][23090] Updated weights for policy 0, policy_version 71921 (0.0016) [2023-03-09 09:05:14,059][22664] Fps is (10 sec: 196604.0, 60 sec: 198245.7, 300 sec: 198718.3). Total num frames: 1178435584. Throughput: 0: 49679.0. Samples: 294578272. Policy #0 lag: (min: 1.0, avg: 17.0, max: 33.0) [2023-03-09 09:05:14,060][22664] Avg episode reward: [(0, '56.238')] [2023-03-09 09:05:14,105][22940] Signal inference workers to stop experience collection... (23300 times) [2023-03-09 09:05:14,107][22940] Signal inference workers to resume experience collection... (23300 times) [2023-03-09 09:05:14,170][23090] InferenceWorker_p0-w0: stopping experience collection (23300 times) [2023-03-09 09:05:14,174][23090] InferenceWorker_p0-w0: resuming experience collection (23300 times) [2023-03-09 09:05:14,381][23090] Updated weights for policy 0, policy_version 71931 (0.0021) [2023-03-09 09:05:15,188][23090] Updated weights for policy 0, policy_version 71941 (0.0017) [2023-03-09 09:05:16,037][23090] Updated weights for policy 0, policy_version 71951 (0.0017) [2023-03-09 09:05:16,956][23090] Updated weights for policy 0, policy_version 71961 (0.0025) [2023-03-09 09:05:17,738][23090] Updated weights for policy 0, policy_version 71971 (0.0020) [2023-03-09 09:05:18,540][23090] Updated weights for policy 0, policy_version 71981 (0.0017) [2023-03-09 09:05:19,059][22664] Fps is (10 sec: 196597.0, 60 sec: 197972.1, 300 sec: 198773.7). Total num frames: 1179418624. Throughput: 0: 49585.5. Samples: 294875072. Policy #0 lag: (min: 1.0, avg: 17.0, max: 33.0) [2023-03-09 09:05:19,061][22664] Avg episode reward: [(0, '55.019')] [2023-03-09 09:05:19,093][22940] Saving /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000071987_1179435008.pth... [2023-03-09 09:05:19,160][22940] Removing /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000069075_1131724800.pth [2023-03-09 09:05:19,424][23090] Updated weights for policy 0, policy_version 71991 (0.0016) [2023-03-09 09:05:20,123][23090] Updated weights for policy 0, policy_version 72001 (0.0018) [2023-03-09 09:05:20,932][23090] Updated weights for policy 0, policy_version 72011 (0.0016) [2023-03-09 09:05:21,928][23090] Updated weights for policy 0, policy_version 72021 (0.0016) [2023-03-09 09:05:22,650][23090] Updated weights for policy 0, policy_version 72031 (0.0020) [2023-03-09 09:05:23,406][23090] Updated weights for policy 0, policy_version 72041 (0.0016) [2023-03-09 09:05:24,059][22664] Fps is (10 sec: 201525.4, 60 sec: 198792.0, 300 sec: 198885.2). Total num frames: 1180450816. Throughput: 0: 49632.1. Samples: 295173968. Policy #0 lag: (min: 1.0, avg: 17.0, max: 33.0) [2023-03-09 09:05:24,061][22664] Avg episode reward: [(0, '53.115')] [2023-03-09 09:05:24,373][23090] Updated weights for policy 0, policy_version 72051 (0.0013) [2023-03-09 09:05:24,668][22940] Signal inference workers to stop experience collection... (23350 times) [2023-03-09 09:05:24,668][22940] Signal inference workers to resume experience collection... (23350 times) [2023-03-09 09:05:24,745][23090] InferenceWorker_p0-w0: stopping experience collection (23350 times) [2023-03-09 09:05:24,745][23090] InferenceWorker_p0-w0: resuming experience collection (23350 times) [2023-03-09 09:05:25,075][23090] Updated weights for policy 0, policy_version 72061 (0.0016) [2023-03-09 09:05:25,903][23090] Updated weights for policy 0, policy_version 72071 (0.0019) [2023-03-09 09:05:26,677][23090] Updated weights for policy 0, policy_version 72081 (0.0020) [2023-03-09 09:05:27,640][23090] Updated weights for policy 0, policy_version 72091 (0.0017) [2023-03-09 09:05:28,416][23090] Updated weights for policy 0, policy_version 72101 (0.0018) [2023-03-09 09:05:29,059][22664] Fps is (10 sec: 199889.2, 60 sec: 198792.4, 300 sec: 198773.9). Total num frames: 1181417472. Throughput: 0: 49632.4. Samples: 295323392. Policy #0 lag: (min: 1.0, avg: 17.0, max: 33.0) [2023-03-09 09:05:29,061][22664] Avg episode reward: [(0, '52.022')] [2023-03-09 09:05:29,295][23090] Updated weights for policy 0, policy_version 72112 (0.0014) [2023-03-09 09:05:30,198][23090] Updated weights for policy 0, policy_version 72122 (0.0016) [2023-03-09 09:05:31,022][23090] Updated weights for policy 0, policy_version 72132 (0.0013) [2023-03-09 09:05:31,896][23090] Updated weights for policy 0, policy_version 72143 (0.0013) [2023-03-09 09:05:32,811][23090] Updated weights for policy 0, policy_version 72154 (0.0013) [2023-03-09 09:05:33,596][22940] Signal inference workers to stop experience collection... (23400 times) [2023-03-09 09:05:33,597][22940] Signal inference workers to resume experience collection... (23400 times) [2023-03-09 09:05:33,664][23090] InferenceWorker_p0-w0: stopping experience collection (23400 times) [2023-03-09 09:05:33,664][23090] InferenceWorker_p0-w0: resuming experience collection (23400 times) [2023-03-09 09:05:33,666][23090] Updated weights for policy 0, policy_version 72164 (0.0023) [2023-03-09 09:05:34,059][22664] Fps is (10 sec: 198245.9, 60 sec: 198792.0, 300 sec: 198774.0). Total num frames: 1182433280. Throughput: 0: 49539.7. Samples: 295618112. Policy #0 lag: (min: 1.0, avg: 17.0, max: 33.0) [2023-03-09 09:05:34,060][22664] Avg episode reward: [(0, '54.604')] [2023-03-09 09:05:34,447][23090] Updated weights for policy 0, policy_version 72174 (0.0013) [2023-03-09 09:05:35,340][23090] Updated weights for policy 0, policy_version 72184 (0.0021) [2023-03-09 09:05:36,137][23090] Updated weights for policy 0, policy_version 72194 (0.0013) [2023-03-09 09:05:36,987][23090] Updated weights for policy 0, policy_version 72204 (0.0016) [2023-03-09 09:05:37,866][23090] Updated weights for policy 0, policy_version 72214 (0.0013) [2023-03-09 09:05:38,625][23090] Updated weights for policy 0, policy_version 72225 (0.0017) [2023-03-09 09:05:39,058][22664] Fps is (10 sec: 199890.3, 60 sec: 198246.9, 300 sec: 198774.1). Total num frames: 1183416320. Throughput: 0: 49585.0. Samples: 295917040. Policy #0 lag: (min: 2.0, avg: 16.2, max: 33.0) [2023-03-09 09:05:39,059][22664] Avg episode reward: [(0, '54.903')] [2023-03-09 09:05:39,407][23090] Updated weights for policy 0, policy_version 72235 (0.0018) [2023-03-09 09:05:40,437][23090] Updated weights for policy 0, policy_version 72245 (0.0018) [2023-03-09 09:05:41,164][23090] Updated weights for policy 0, policy_version 72255 (0.0019) [2023-03-09 09:05:41,870][23090] Updated weights for policy 0, policy_version 72265 (0.0015) [2023-03-09 09:05:42,947][23090] Updated weights for policy 0, policy_version 72276 (0.0022) [2023-03-09 09:05:43,069][22940] Signal inference workers to stop experience collection... (23450 times) [2023-03-09 09:05:43,071][22940] Signal inference workers to resume experience collection... (23450 times) [2023-03-09 09:05:43,141][23090] InferenceWorker_p0-w0: stopping experience collection (23450 times) [2023-03-09 09:05:43,141][23090] InferenceWorker_p0-w0: resuming experience collection (23450 times) [2023-03-09 09:05:43,682][23090] Updated weights for policy 0, policy_version 72286 (0.0013) [2023-03-09 09:05:44,059][22664] Fps is (10 sec: 196606.3, 60 sec: 198519.7, 300 sec: 198718.5). Total num frames: 1184399360. Throughput: 0: 49584.4. Samples: 296066480. Policy #0 lag: (min: 2.0, avg: 16.2, max: 33.0) [2023-03-09 09:05:44,060][22664] Avg episode reward: [(0, '53.347')] [2023-03-09 09:05:44,444][23090] Updated weights for policy 0, policy_version 72296 (0.0016) [2023-03-09 09:05:45,303][23090] Updated weights for policy 0, policy_version 72306 (0.0018) [2023-03-09 09:05:46,155][23090] Updated weights for policy 0, policy_version 72316 (0.0017) [2023-03-09 09:05:46,971][23090] Updated weights for policy 0, policy_version 72326 (0.0016) [2023-03-09 09:05:47,765][23090] Updated weights for policy 0, policy_version 72336 (0.0015) [2023-03-09 09:05:48,638][23090] Updated weights for policy 0, policy_version 72346 (0.0017) [2023-03-09 09:05:49,059][22664] Fps is (10 sec: 199882.1, 60 sec: 198518.9, 300 sec: 198774.1). Total num frames: 1185415168. Throughput: 0: 49539.0. Samples: 296363328. Policy #0 lag: (min: 2.0, avg: 16.2, max: 33.0) [2023-03-09 09:05:49,060][22664] Avg episode reward: [(0, '53.214')] [2023-03-09 09:05:49,480][23090] Updated weights for policy 0, policy_version 72356 (0.0013) [2023-03-09 09:05:50,301][23090] Updated weights for policy 0, policy_version 72366 (0.0014) [2023-03-09 09:05:51,259][23090] Updated weights for policy 0, policy_version 72377 (0.0013) [2023-03-09 09:05:52,075][23090] Updated weights for policy 0, policy_version 72387 (0.0024) [2023-03-09 09:05:52,291][22940] Signal inference workers to stop experience collection... (23500 times) [2023-03-09 09:05:52,295][22940] Signal inference workers to resume experience collection... (23500 times) [2023-03-09 09:05:52,362][23090] InferenceWorker_p0-w0: stopping experience collection (23500 times) [2023-03-09 09:05:52,367][23090] InferenceWorker_p0-w0: resuming experience collection (23500 times) [2023-03-09 09:05:52,849][23090] Updated weights for policy 0, policy_version 72397 (0.0013) [2023-03-09 09:05:53,711][23090] Updated weights for policy 0, policy_version 72407 (0.0013) [2023-03-09 09:05:54,059][22664] Fps is (10 sec: 199882.4, 60 sec: 198518.2, 300 sec: 198773.8). Total num frames: 1186398208. Throughput: 0: 49585.0. Samples: 296662224. Policy #0 lag: (min: 2.0, avg: 16.2, max: 33.0) [2023-03-09 09:05:54,061][22664] Avg episode reward: [(0, '56.104')] [2023-03-09 09:05:54,421][23090] Updated weights for policy 0, policy_version 72417 (0.0016) [2023-03-09 09:05:55,186][23090] Updated weights for policy 0, policy_version 72427 (0.0017) [2023-03-09 09:05:56,294][23090] Updated weights for policy 0, policy_version 72438 (0.0013) [2023-03-09 09:05:56,989][23090] Updated weights for policy 0, policy_version 72448 (0.0022) [2023-03-09 09:05:57,761][23090] Updated weights for policy 0, policy_version 72458 (0.0018) [2023-03-09 09:05:58,720][23090] Updated weights for policy 0, policy_version 72468 (0.0018) [2023-03-09 09:05:59,059][22664] Fps is (10 sec: 196608.5, 60 sec: 198245.9, 300 sec: 198718.4). Total num frames: 1187381248. Throughput: 0: 49676.9. Samples: 296813728. Policy #0 lag: (min: 2.0, avg: 16.2, max: 33.0) [2023-03-09 09:05:59,060][22664] Avg episode reward: [(0, '53.808')] [2023-03-09 09:05:59,606][23090] Updated weights for policy 0, policy_version 72479 (0.0017) [2023-03-09 09:06:00,282][23090] Updated weights for policy 0, policy_version 72489 (0.0012) [2023-03-09 09:06:01,342][23090] Updated weights for policy 0, policy_version 72500 (0.0013) [2023-03-09 09:06:01,472][22940] Signal inference workers to stop experience collection... (23550 times) [2023-03-09 09:06:01,473][22940] Signal inference workers to resume experience collection... (23550 times) [2023-03-09 09:06:01,540][23090] InferenceWorker_p0-w0: stopping experience collection (23550 times) [2023-03-09 09:06:01,540][23090] InferenceWorker_p0-w0: resuming experience collection (23550 times) [2023-03-09 09:06:02,086][23090] Updated weights for policy 0, policy_version 72510 (0.0017) [2023-03-09 09:06:02,863][23090] Updated weights for policy 0, policy_version 72520 (0.0020) [2023-03-09 09:06:03,741][23090] Updated weights for policy 0, policy_version 72530 (0.0018) [2023-03-09 09:06:04,059][22664] Fps is (10 sec: 196609.5, 60 sec: 198245.6, 300 sec: 198662.8). Total num frames: 1188364288. Throughput: 0: 49724.4. Samples: 297112656. Policy #0 lag: (min: 2.0, avg: 16.2, max: 33.0) [2023-03-09 09:06:04,061][22664] Avg episode reward: [(0, '55.426')] [2023-03-09 09:06:04,553][23090] Updated weights for policy 0, policy_version 72540 (0.0016) [2023-03-09 09:06:05,358][23090] Updated weights for policy 0, policy_version 72550 (0.0020) [2023-03-09 09:06:06,190][23090] Updated weights for policy 0, policy_version 72560 (0.0019) [2023-03-09 09:06:07,044][23090] Updated weights for policy 0, policy_version 72570 (0.0019) [2023-03-09 09:06:07,831][23090] Updated weights for policy 0, policy_version 72580 (0.0021) [2023-03-09 09:06:08,725][23090] Updated weights for policy 0, policy_version 72590 (0.0013) [2023-03-09 09:06:09,059][22664] Fps is (10 sec: 199882.3, 60 sec: 198791.5, 300 sec: 198829.5). Total num frames: 1189380096. Throughput: 0: 49723.6. Samples: 297411536. Policy #0 lag: (min: 2.0, avg: 16.2, max: 33.0) [2023-03-09 09:06:09,061][22664] Avg episode reward: [(0, '56.113')] [2023-03-09 09:06:09,498][23090] Updated weights for policy 0, policy_version 72600 (0.0016) [2023-03-09 09:06:09,643][22940] Signal inference workers to stop experience collection... (23600 times) [2023-03-09 09:06:09,644][22940] Signal inference workers to resume experience collection... (23600 times) [2023-03-09 09:06:09,728][23090] InferenceWorker_p0-w0: stopping experience collection (23600 times) [2023-03-09 09:06:09,733][23090] InferenceWorker_p0-w0: resuming experience collection (23600 times) [2023-03-09 09:06:10,427][23090] Updated weights for policy 0, policy_version 72611 (0.0016) [2023-03-09 09:06:11,273][23090] Updated weights for policy 0, policy_version 72621 (0.0019) [2023-03-09 09:06:12,113][23090] Updated weights for policy 0, policy_version 72631 (0.0018) [2023-03-09 09:06:12,855][23090] Updated weights for policy 0, policy_version 72641 (0.0016) [2023-03-09 09:06:13,616][23090] Updated weights for policy 0, policy_version 72651 (0.0013) [2023-03-09 09:06:14,059][22664] Fps is (10 sec: 201523.7, 60 sec: 199065.5, 300 sec: 198829.6). Total num frames: 1190379520. Throughput: 0: 49724.5. Samples: 297560992. Policy #0 lag: (min: 2.0, avg: 16.2, max: 33.0) [2023-03-09 09:06:14,060][22664] Avg episode reward: [(0, '55.544')] [2023-03-09 09:06:14,597][23090] Updated weights for policy 0, policy_version 72661 (0.0013) [2023-03-09 09:06:15,341][23090] Updated weights for policy 0, policy_version 72671 (0.0015) [2023-03-09 09:06:16,115][23090] Updated weights for policy 0, policy_version 72681 (0.0014) [2023-03-09 09:06:17,139][23090] Updated weights for policy 0, policy_version 72692 (0.0017) [2023-03-09 09:06:17,886][23090] Updated weights for policy 0, policy_version 72702 (0.0020) [2023-03-09 09:06:18,623][22940] Signal inference workers to stop experience collection... (23650 times) [2023-03-09 09:06:18,645][22940] Signal inference workers to resume experience collection... (23650 times) [2023-03-09 09:06:18,691][23090] InferenceWorker_p0-w0: stopping experience collection (23650 times) [2023-03-09 09:06:18,729][23090] InferenceWorker_p0-w0: resuming experience collection (23650 times) [2023-03-09 09:06:18,775][23090] Updated weights for policy 0, policy_version 72713 (0.0024) [2023-03-09 09:06:19,059][22664] Fps is (10 sec: 198246.2, 60 sec: 199066.4, 300 sec: 198773.9). Total num frames: 1191362560. Throughput: 0: 49772.7. Samples: 297857888. Policy #0 lag: (min: 2.0, avg: 16.2, max: 33.0) [2023-03-09 09:06:19,061][22664] Avg episode reward: [(0, '50.114')] [2023-03-09 09:06:19,721][23090] Updated weights for policy 0, policy_version 72723 (0.0016) [2023-03-09 09:06:20,416][23090] Updated weights for policy 0, policy_version 72733 (0.0016) [2023-03-09 09:06:21,277][23090] Updated weights for policy 0, policy_version 72743 (0.0016) [2023-03-09 09:06:22,053][23090] Updated weights for policy 0, policy_version 72753 (0.0016) [2023-03-09 09:06:22,931][23090] Updated weights for policy 0, policy_version 72763 (0.0017) [2023-03-09 09:06:23,782][23090] Updated weights for policy 0, policy_version 72773 (0.0016) [2023-03-09 09:06:24,059][22664] Fps is (10 sec: 201527.5, 60 sec: 199065.9, 300 sec: 198940.6). Total num frames: 1192394752. Throughput: 0: 49773.5. Samples: 298156848. Policy #0 lag: (min: 0.0, avg: 17.3, max: 33.0) [2023-03-09 09:06:24,060][22664] Avg episode reward: [(0, '56.090')] [2023-03-09 09:06:24,589][23090] Updated weights for policy 0, policy_version 72783 (0.0013) [2023-03-09 09:06:25,428][23090] Updated weights for policy 0, policy_version 72793 (0.0013) [2023-03-09 09:06:26,267][23090] Updated weights for policy 0, policy_version 72803 (0.0013) [2023-03-09 09:06:27,043][22940] Signal inference workers to stop experience collection... (23700 times) [2023-03-09 09:06:27,044][22940] Signal inference workers to resume experience collection... (23700 times) [2023-03-09 09:06:27,102][23090] InferenceWorker_p0-w0: stopping experience collection (23700 times) [2023-03-09 09:06:27,102][23090] InferenceWorker_p0-w0: resuming experience collection (23700 times) [2023-03-09 09:06:27,142][23090] Updated weights for policy 0, policy_version 72813 (0.0013) [2023-03-09 09:06:27,932][23090] Updated weights for policy 0, policy_version 72823 (0.0015) [2023-03-09 09:06:28,680][23090] Updated weights for policy 0, policy_version 72833 (0.0013) [2023-03-09 09:06:29,059][22664] Fps is (10 sec: 199889.5, 60 sec: 199066.5, 300 sec: 198718.7). Total num frames: 1193361408. Throughput: 0: 49773.7. Samples: 298306288. Policy #0 lag: (min: 0.0, avg: 17.3, max: 33.0) [2023-03-09 09:06:29,060][22664] Avg episode reward: [(0, '55.877')] [2023-03-09 09:06:29,440][23090] Updated weights for policy 0, policy_version 72843 (0.0013) [2023-03-09 09:06:30,442][23090] Updated weights for policy 0, policy_version 72853 (0.0016) [2023-03-09 09:06:31,145][23090] Updated weights for policy 0, policy_version 72863 (0.0025) [2023-03-09 09:06:31,937][23090] Updated weights for policy 0, policy_version 72873 (0.0013) [2023-03-09 09:06:32,856][23090] Updated weights for policy 0, policy_version 72883 (0.0015) [2023-03-09 09:06:33,695][23090] Updated weights for policy 0, policy_version 72894 (0.0016) [2023-03-09 09:06:34,059][22664] Fps is (10 sec: 196603.7, 60 sec: 198792.2, 300 sec: 198718.4). Total num frames: 1194360832. Throughput: 0: 49819.3. Samples: 298605200. Policy #0 lag: (min: 0.0, avg: 17.3, max: 33.0) [2023-03-09 09:06:34,061][22664] Avg episode reward: [(0, '53.113')] [2023-03-09 09:06:34,510][23090] Updated weights for policy 0, policy_version 72904 (0.0021) [2023-03-09 09:06:35,352][23090] Updated weights for policy 0, policy_version 72914 (0.0019) [2023-03-09 09:06:35,825][22940] Signal inference workers to stop experience collection... (23750 times) [2023-03-09 09:06:35,837][22940] Signal inference workers to resume experience collection... (23750 times) [2023-03-09 09:06:35,865][23090] InferenceWorker_p0-w0: stopping experience collection (23750 times) [2023-03-09 09:06:35,906][23090] InferenceWorker_p0-w0: resuming experience collection (23750 times) [2023-03-09 09:06:36,155][23090] Updated weights for policy 0, policy_version 72924 (0.0013) [2023-03-09 09:06:37,010][23090] Updated weights for policy 0, policy_version 72934 (0.0013) [2023-03-09 09:06:37,848][23090] Updated weights for policy 0, policy_version 72945 (0.0019) [2023-03-09 09:06:38,733][23090] Updated weights for policy 0, policy_version 72955 (0.0014) [2023-03-09 09:06:39,059][22664] Fps is (10 sec: 199879.4, 60 sec: 199064.7, 300 sec: 198829.5). Total num frames: 1195360256. Throughput: 0: 49820.1. Samples: 298904128. Policy #0 lag: (min: 0.0, avg: 17.3, max: 33.0) [2023-03-09 09:06:39,061][22664] Avg episode reward: [(0, '52.068')] [2023-03-09 09:06:39,583][23090] Updated weights for policy 0, policy_version 72965 (0.0013) [2023-03-09 09:06:40,326][23090] Updated weights for policy 0, policy_version 72975 (0.0021) [2023-03-09 09:06:41,284][23090] Updated weights for policy 0, policy_version 72986 (0.0021) [2023-03-09 09:06:42,100][23090] Updated weights for policy 0, policy_version 72996 (0.0016) [2023-03-09 09:06:42,961][23090] Updated weights for policy 0, policy_version 73006 (0.0017) [2023-03-09 09:06:43,801][23090] Updated weights for policy 0, policy_version 73016 (0.0017) [2023-03-09 09:06:44,059][22664] Fps is (10 sec: 199885.9, 60 sec: 199338.8, 300 sec: 198829.4). Total num frames: 1196359680. Throughput: 0: 49774.5. Samples: 299053584. Policy #0 lag: (min: 0.0, avg: 17.3, max: 33.0) [2023-03-09 09:06:44,060][22664] Avg episode reward: [(0, '52.508')] [2023-03-09 09:06:44,559][23090] Updated weights for policy 0, policy_version 73026 (0.0018) [2023-03-09 09:06:45,450][22940] Signal inference workers to stop experience collection... (23800 times) [2023-03-09 09:06:45,451][22940] Signal inference workers to resume experience collection... (23800 times) [2023-03-09 09:06:45,478][23090] Updated weights for policy 0, policy_version 73036 (0.0014) [2023-03-09 09:06:45,517][23090] InferenceWorker_p0-w0: stopping experience collection (23800 times) [2023-03-09 09:06:45,517][23090] InferenceWorker_p0-w0: resuming experience collection (23800 times) [2023-03-09 09:06:46,300][23090] Updated weights for policy 0, policy_version 73046 (0.0013) [2023-03-09 09:06:47,039][23090] Updated weights for policy 0, policy_version 73056 (0.0015) [2023-03-09 09:06:47,750][23090] Updated weights for policy 0, policy_version 73066 (0.0021) [2023-03-09 09:06:48,722][23090] Updated weights for policy 0, policy_version 73076 (0.0013) [2023-03-09 09:06:49,059][22664] Fps is (10 sec: 198247.5, 60 sec: 198792.2, 300 sec: 198829.5). Total num frames: 1197342720. Throughput: 0: 49771.8. Samples: 299352384. Policy #0 lag: (min: 0.0, avg: 17.3, max: 33.0) [2023-03-09 09:06:49,060][22664] Avg episode reward: [(0, '53.700')] [2023-03-09 09:06:49,482][23090] Updated weights for policy 0, policy_version 73086 (0.0013) [2023-03-09 09:06:50,301][23090] Updated weights for policy 0, policy_version 73096 (0.0013) [2023-03-09 09:06:51,357][23090] Updated weights for policy 0, policy_version 73107 (0.0019) [2023-03-09 09:06:52,019][23090] Updated weights for policy 0, policy_version 73117 (0.0023) [2023-03-09 09:06:52,926][23090] Updated weights for policy 0, policy_version 73127 (0.0013) [2023-03-09 09:06:53,658][23090] Updated weights for policy 0, policy_version 73137 (0.0017) [2023-03-09 09:06:54,059][22664] Fps is (10 sec: 196606.5, 60 sec: 198792.8, 300 sec: 198884.9). Total num frames: 1198325760. Throughput: 0: 49726.2. Samples: 299649216. Policy #0 lag: (min: 0.0, avg: 17.3, max: 33.0) [2023-03-09 09:06:54,061][22664] Avg episode reward: [(0, '52.263')] [2023-03-09 09:06:54,537][23090] Updated weights for policy 0, policy_version 73147 (0.0016) [2023-03-09 09:06:54,994][22940] Signal inference workers to stop experience collection... (23850 times) [2023-03-09 09:06:54,995][22940] Signal inference workers to resume experience collection... (23850 times) [2023-03-09 09:06:55,066][23090] InferenceWorker_p0-w0: stopping experience collection (23850 times) [2023-03-09 09:06:55,066][23090] InferenceWorker_p0-w0: resuming experience collection (23850 times) [2023-03-09 09:06:55,438][23090] Updated weights for policy 0, policy_version 73157 (0.0023) [2023-03-09 09:06:56,238][23090] Updated weights for policy 0, policy_version 73167 (0.0021) [2023-03-09 09:06:57,043][23090] Updated weights for policy 0, policy_version 73177 (0.0017) [2023-03-09 09:06:57,874][23090] Updated weights for policy 0, policy_version 73187 (0.0014) [2023-03-09 09:06:58,727][23090] Updated weights for policy 0, policy_version 73197 (0.0016) [2023-03-09 09:06:59,059][22664] Fps is (10 sec: 198244.0, 60 sec: 199064.8, 300 sec: 198829.7). Total num frames: 1199325184. Throughput: 0: 49681.3. Samples: 299796656. Policy #0 lag: (min: 0.0, avg: 17.3, max: 33.0) [2023-03-09 09:06:59,061][22664] Avg episode reward: [(0, '54.965')] [2023-03-09 09:06:59,702][23090] Updated weights for policy 0, policy_version 73208 (0.0013) [2023-03-09 09:07:00,430][23090] Updated weights for policy 0, policy_version 73218 (0.0018) [2023-03-09 09:07:01,334][23090] Updated weights for policy 0, policy_version 73228 (0.0022) [2023-03-09 09:07:02,177][23090] Updated weights for policy 0, policy_version 73238 (0.0016) [2023-03-09 09:07:02,909][23090] Updated weights for policy 0, policy_version 73248 (0.0019) [2023-03-09 09:07:03,713][23090] Updated weights for policy 0, policy_version 73259 (0.0016) [2023-03-09 09:07:04,057][22940] Signal inference workers to stop experience collection... (23900 times) [2023-03-09 09:07:04,059][22664] Fps is (10 sec: 198250.6, 60 sec: 199066.3, 300 sec: 198774.0). Total num frames: 1200308224. Throughput: 0: 49724.7. Samples: 300095488. Policy #0 lag: (min: 0.0, avg: 17.3, max: 33.0) [2023-03-09 09:07:04,059][22664] Avg episode reward: [(0, '52.182')] [2023-03-09 09:07:04,075][22940] Signal inference workers to resume experience collection... (23900 times) [2023-03-09 09:07:04,108][23090] InferenceWorker_p0-w0: stopping experience collection (23900 times) [2023-03-09 09:07:04,148][23090] InferenceWorker_p0-w0: resuming experience collection (23900 times) [2023-03-09 09:07:04,745][23090] Updated weights for policy 0, policy_version 73269 (0.0017) [2023-03-09 09:07:05,462][23090] Updated weights for policy 0, policy_version 73279 (0.0017) [2023-03-09 09:07:06,245][23090] Updated weights for policy 0, policy_version 73289 (0.0018) [2023-03-09 09:07:07,175][23090] Updated weights for policy 0, policy_version 73299 (0.0017) [2023-03-09 09:07:07,879][23090] Updated weights for policy 0, policy_version 73309 (0.0019) [2023-03-09 09:07:08,733][23090] Updated weights for policy 0, policy_version 73319 (0.0013) [2023-03-09 09:07:09,059][22664] Fps is (10 sec: 199888.9, 60 sec: 199065.9, 300 sec: 198829.5). Total num frames: 1201324032. Throughput: 0: 49675.9. Samples: 300392272. Policy #0 lag: (min: 2.0, avg: 17.7, max: 34.0) [2023-03-09 09:07:09,060][22664] Avg episode reward: [(0, '55.182')] [2023-03-09 09:07:09,491][23090] Updated weights for policy 0, policy_version 73329 (0.0015) [2023-03-09 09:07:10,333][23090] Updated weights for policy 0, policy_version 73339 (0.0018) [2023-03-09 09:07:11,261][23090] Updated weights for policy 0, policy_version 73349 (0.0016) [2023-03-09 09:07:12,121][23090] Updated weights for policy 0, policy_version 73360 (0.0022) [2023-03-09 09:07:12,960][23090] Updated weights for policy 0, policy_version 73370 (0.0020) [2023-03-09 09:07:13,804][23090] Updated weights for policy 0, policy_version 73380 (0.0016) [2023-03-09 09:07:14,059][22664] Fps is (10 sec: 199879.0, 60 sec: 198792.2, 300 sec: 198829.6). Total num frames: 1202307072. Throughput: 0: 49675.7. Samples: 300541712. Policy #0 lag: (min: 2.0, avg: 17.7, max: 34.0) [2023-03-09 09:07:14,061][22664] Avg episode reward: [(0, '55.285')] [2023-03-09 09:07:14,606][23090] Updated weights for policy 0, policy_version 73390 (0.0013) [2023-03-09 09:07:14,641][22940] Signal inference workers to stop experience collection... (23950 times) [2023-03-09 09:07:14,661][22940] Signal inference workers to resume experience collection... (23950 times) [2023-03-09 09:07:14,687][23090] InferenceWorker_p0-w0: stopping experience collection (23950 times) [2023-03-09 09:07:14,726][23090] InferenceWorker_p0-w0: resuming experience collection (23950 times) [2023-03-09 09:07:15,449][23090] Updated weights for policy 0, policy_version 73400 (0.0013) [2023-03-09 09:07:16,326][23090] Updated weights for policy 0, policy_version 73411 (0.0020) [2023-03-09 09:07:17,175][23090] Updated weights for policy 0, policy_version 73421 (0.0016) [2023-03-09 09:07:18,045][23090] Updated weights for policy 0, policy_version 73432 (0.0016) [2023-03-09 09:07:18,856][23090] Updated weights for policy 0, policy_version 73442 (0.0016) [2023-03-09 09:07:19,059][22664] Fps is (10 sec: 198244.1, 60 sec: 199065.6, 300 sec: 198829.4). Total num frames: 1203306496. Throughput: 0: 49719.8. Samples: 300842592. Policy #0 lag: (min: 2.0, avg: 17.7, max: 34.0) [2023-03-09 09:07:19,061][22664] Avg episode reward: [(0, '53.299')] [2023-03-09 09:07:19,105][22940] Saving /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000073445_1203322880.pth... [2023-03-09 09:07:19,172][22940] Removing /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000070533_1155612672.pth [2023-03-09 09:07:19,739][23090] Updated weights for policy 0, policy_version 73452 (0.0013) [2023-03-09 09:07:20,604][23090] Updated weights for policy 0, policy_version 73462 (0.0017) [2023-03-09 09:07:21,369][23090] Updated weights for policy 0, policy_version 73472 (0.0017) [2023-03-09 09:07:22,114][23090] Updated weights for policy 0, policy_version 73482 (0.0013) [2023-03-09 09:07:23,087][23090] Updated weights for policy 0, policy_version 73492 (0.0024) [2023-03-09 09:07:23,849][23090] Updated weights for policy 0, policy_version 73502 (0.0013) [2023-03-09 09:07:24,059][22664] Fps is (10 sec: 198241.0, 60 sec: 198244.5, 300 sec: 198773.7). Total num frames: 1204289536. Throughput: 0: 49626.3. Samples: 301137328. Policy #0 lag: (min: 2.0, avg: 17.7, max: 34.0) [2023-03-09 09:07:24,062][22664] Avg episode reward: [(0, '50.945')] [2023-03-09 09:07:24,623][23090] Updated weights for policy 0, policy_version 73512 (0.0013) [2023-03-09 09:07:25,227][22940] Signal inference workers to stop experience collection... (24000 times) [2023-03-09 09:07:25,254][22940] Signal inference workers to resume experience collection... (24000 times) [2023-03-09 09:07:25,301][23090] InferenceWorker_p0-w0: stopping experience collection (24000 times) [2023-03-09 09:07:25,302][23090] InferenceWorker_p0-w0: resuming experience collection (24000 times) [2023-03-09 09:07:25,505][23090] Updated weights for policy 0, policy_version 73522 (0.0021) [2023-03-09 09:07:26,311][23090] Updated weights for policy 0, policy_version 73532 (0.0013) [2023-03-09 09:07:27,174][23090] Updated weights for policy 0, policy_version 73542 (0.0024) [2023-03-09 09:07:27,964][23090] Updated weights for policy 0, policy_version 73552 (0.0021) [2023-03-09 09:07:28,835][23090] Updated weights for policy 0, policy_version 73562 (0.0018) [2023-03-09 09:07:29,059][22664] Fps is (10 sec: 198250.6, 60 sec: 198792.4, 300 sec: 198885.2). Total num frames: 1205288960. Throughput: 0: 49582.0. Samples: 301284768. Policy #0 lag: (min: 2.0, avg: 17.7, max: 34.0) [2023-03-09 09:07:29,060][22664] Avg episode reward: [(0, '53.191')] [2023-03-09 09:07:29,660][23090] Updated weights for policy 0, policy_version 73572 (0.0016) [2023-03-09 09:07:30,515][23090] Updated weights for policy 0, policy_version 73582 (0.0018) [2023-03-09 09:07:31,356][23090] Updated weights for policy 0, policy_version 73592 (0.0015) [2023-03-09 09:07:32,124][23090] Updated weights for policy 0, policy_version 73602 (0.0017) [2023-03-09 09:07:33,073][23090] Updated weights for policy 0, policy_version 73612 (0.0013) [2023-03-09 09:07:33,848][23090] Updated weights for policy 0, policy_version 73622 (0.0018) [2023-03-09 09:07:34,058][22664] Fps is (10 sec: 198259.5, 60 sec: 198520.4, 300 sec: 198774.1). Total num frames: 1206272000. Throughput: 0: 49540.2. Samples: 301581680. Policy #0 lag: (min: 2.0, avg: 17.7, max: 34.0) [2023-03-09 09:07:34,059][22664] Avg episode reward: [(0, '54.266')] [2023-03-09 09:07:34,597][22940] Signal inference workers to stop experience collection... (24050 times) [2023-03-09 09:07:34,598][22940] Signal inference workers to resume experience collection... (24050 times) [2023-03-09 09:07:34,664][23090] InferenceWorker_p0-w0: stopping experience collection (24050 times) [2023-03-09 09:07:34,666][23090] InferenceWorker_p0-w0: resuming experience collection (24050 times) [2023-03-09 09:07:34,669][23090] Updated weights for policy 0, policy_version 73632 (0.0019) [2023-03-09 09:07:35,374][23090] Updated weights for policy 0, policy_version 73642 (0.0013) [2023-03-09 09:07:36,361][23090] Updated weights for policy 0, policy_version 73652 (0.0024) [2023-03-09 09:07:37,094][23090] Updated weights for policy 0, policy_version 73662 (0.0016) [2023-03-09 09:07:37,891][23090] Updated weights for policy 0, policy_version 73672 (0.0016) [2023-03-09 09:07:38,733][23090] Updated weights for policy 0, policy_version 73682 (0.0013) [2023-03-09 09:07:39,059][22664] Fps is (10 sec: 196601.0, 60 sec: 198246.0, 300 sec: 198718.2). Total num frames: 1207255040. Throughput: 0: 49584.9. Samples: 301880544. Policy #0 lag: (min: 2.0, avg: 17.7, max: 34.0) [2023-03-09 09:07:39,061][22664] Avg episode reward: [(0, '54.468')] [2023-03-09 09:07:39,502][23090] Updated weights for policy 0, policy_version 73692 (0.0012) [2023-03-09 09:07:40,435][23090] Updated weights for policy 0, policy_version 73702 (0.0016) [2023-03-09 09:07:41,266][23090] Updated weights for policy 0, policy_version 73713 (0.0019) [2023-03-09 09:07:42,126][23090] Updated weights for policy 0, policy_version 73723 (0.0016) [2023-03-09 09:07:43,022][23090] Updated weights for policy 0, policy_version 73733 (0.0016) [2023-03-09 09:07:43,031][22940] Signal inference workers to stop experience collection... (24100 times) [2023-03-09 09:07:43,051][22940] Signal inference workers to resume experience collection... (24100 times) [2023-03-09 09:07:43,060][23090] InferenceWorker_p0-w0: stopping experience collection (24100 times) [2023-03-09 09:07:43,061][23090] InferenceWorker_p0-w0: resuming experience collection (24100 times) [2023-03-09 09:07:43,858][23090] Updated weights for policy 0, policy_version 73744 (0.0018) [2023-03-09 09:07:44,059][22664] Fps is (10 sec: 198243.2, 60 sec: 198246.7, 300 sec: 198774.2). Total num frames: 1208254464. Throughput: 0: 49629.8. Samples: 302029984. Policy #0 lag: (min: 2.0, avg: 17.7, max: 34.0) [2023-03-09 09:07:44,060][22664] Avg episode reward: [(0, '51.183')] [2023-03-09 09:07:44,663][23090] Updated weights for policy 0, policy_version 73754 (0.0016) [2023-03-09 09:07:45,474][23090] Updated weights for policy 0, policy_version 73764 (0.0023) [2023-03-09 09:07:46,402][23090] Updated weights for policy 0, policy_version 73775 (0.0013) [2023-03-09 09:07:47,246][23090] Updated weights for policy 0, policy_version 73785 (0.0013) [2023-03-09 09:07:48,020][23090] Updated weights for policy 0, policy_version 73795 (0.0018) [2023-03-09 09:07:48,932][23090] Updated weights for policy 0, policy_version 73805 (0.0020) [2023-03-09 09:07:49,058][22664] Fps is (10 sec: 199893.0, 60 sec: 198520.2, 300 sec: 198829.7). Total num frames: 1209253888. Throughput: 0: 49632.4. Samples: 302328944. Policy #0 lag: (min: 2.0, avg: 17.7, max: 34.0) [2023-03-09 09:07:49,059][22664] Avg episode reward: [(0, '52.420')] [2023-03-09 09:07:49,784][23090] Updated weights for policy 0, policy_version 73816 (0.0016) [2023-03-09 09:07:50,607][23090] Updated weights for policy 0, policy_version 73826 (0.0024) [2023-03-09 09:07:50,932][22940] Signal inference workers to stop experience collection... (24150 times) [2023-03-09 09:07:50,944][22940] Signal inference workers to resume experience collection... (24150 times) [2023-03-09 09:07:51,011][23090] InferenceWorker_p0-w0: stopping experience collection (24150 times) [2023-03-09 09:07:51,012][23090] InferenceWorker_p0-w0: resuming experience collection (24150 times) [2023-03-09 09:07:51,547][23090] Updated weights for policy 0, policy_version 73836 (0.0027) [2023-03-09 09:07:52,355][23090] Updated weights for policy 0, policy_version 73846 (0.0013) [2023-03-09 09:07:53,116][23090] Updated weights for policy 0, policy_version 73856 (0.0016) [2023-03-09 09:07:53,815][23090] Updated weights for policy 0, policy_version 73866 (0.0015) [2023-03-09 09:07:54,059][22664] Fps is (10 sec: 198242.3, 60 sec: 198519.3, 300 sec: 198718.2). Total num frames: 1210236928. Throughput: 0: 49633.6. Samples: 302625792. Policy #0 lag: (min: 2.0, avg: 16.8, max: 33.0) [2023-03-09 09:07:54,061][22664] Avg episode reward: [(0, '52.870')] [2023-03-09 09:07:54,808][23090] Updated weights for policy 0, policy_version 73876 (0.0018) [2023-03-09 09:07:55,529][23090] Updated weights for policy 0, policy_version 73886 (0.0017) [2023-03-09 09:07:56,342][23090] Updated weights for policy 0, policy_version 73896 (0.0015) [2023-03-09 09:07:57,166][23090] Updated weights for policy 0, policy_version 73906 (0.0013) [2023-03-09 09:07:58,047][23090] Updated weights for policy 0, policy_version 73917 (0.0016) [2023-03-09 09:07:58,883][22940] Signal inference workers to stop experience collection... (24200 times) [2023-03-09 09:07:58,901][22940] Signal inference workers to resume experience collection... (24200 times) [2023-03-09 09:07:58,936][23090] InferenceWorker_p0-w0: stopping experience collection (24200 times) [2023-03-09 09:07:58,939][23090] Updated weights for policy 0, policy_version 73927 (0.0013) [2023-03-09 09:07:58,975][23090] InferenceWorker_p0-w0: resuming experience collection (24200 times) [2023-03-09 09:07:59,059][22664] Fps is (10 sec: 199884.3, 60 sec: 198793.6, 300 sec: 198829.7). Total num frames: 1211252736. Throughput: 0: 49635.2. Samples: 302775280. Policy #0 lag: (min: 2.0, avg: 16.8, max: 33.0) [2023-03-09 09:07:59,060][22664] Avg episode reward: [(0, '53.565')] [2023-03-09 09:07:59,672][23090] Updated weights for policy 0, policy_version 73937 (0.0017) [2023-03-09 09:08:00,546][23090] Updated weights for policy 0, policy_version 73947 (0.0013) [2023-03-09 09:08:01,434][23090] Updated weights for policy 0, policy_version 73957 (0.0013) [2023-03-09 09:08:02,269][23090] Updated weights for policy 0, policy_version 73968 (0.0017) [2023-03-09 09:08:03,085][23090] Updated weights for policy 0, policy_version 73978 (0.0021) [2023-03-09 09:08:03,924][23090] Updated weights for policy 0, policy_version 73988 (0.0013) [2023-03-09 09:08:04,059][22664] Fps is (10 sec: 198251.3, 60 sec: 198519.4, 300 sec: 198663.1). Total num frames: 1212219392. Throughput: 0: 49591.3. Samples: 303074192. Policy #0 lag: (min: 2.0, avg: 16.8, max: 33.0) [2023-03-09 09:08:04,060][22664] Avg episode reward: [(0, '54.796')] [2023-03-09 09:08:04,849][23090] Updated weights for policy 0, policy_version 73999 (0.0021) [2023-03-09 09:08:05,693][23090] Updated weights for policy 0, policy_version 74009 (0.0013) [2023-03-09 09:08:06,530][23090] Updated weights for policy 0, policy_version 74019 (0.0020) [2023-03-09 09:08:06,808][22940] Signal inference workers to stop experience collection... (24250 times) [2023-03-09 09:08:06,827][22940] Signal inference workers to resume experience collection... (24250 times) [2023-03-09 09:08:06,849][23090] InferenceWorker_p0-w0: stopping experience collection (24250 times) [2023-03-09 09:08:06,849][23090] InferenceWorker_p0-w0: resuming experience collection (24250 times) [2023-03-09 09:08:07,367][23090] Updated weights for policy 0, policy_version 74029 (0.0013) [2023-03-09 09:08:08,279][23090] Updated weights for policy 0, policy_version 74040 (0.0017) [2023-03-09 09:08:09,007][23090] Updated weights for policy 0, policy_version 74050 (0.0020) [2023-03-09 09:08:09,059][22664] Fps is (10 sec: 198242.6, 60 sec: 198519.2, 300 sec: 198718.3). Total num frames: 1213235200. Throughput: 0: 49685.8. Samples: 303373168. Policy #0 lag: (min: 2.0, avg: 16.8, max: 33.0) [2023-03-09 09:08:09,060][22664] Avg episode reward: [(0, '51.470')] [2023-03-09 09:08:09,896][23090] Updated weights for policy 0, policy_version 74060 (0.0016) [2023-03-09 09:08:10,766][23090] Updated weights for policy 0, policy_version 74070 (0.0018) [2023-03-09 09:08:11,512][23090] Updated weights for policy 0, policy_version 74080 (0.0020) [2023-03-09 09:08:12,216][23090] Updated weights for policy 0, policy_version 74090 (0.0022) [2023-03-09 09:08:13,288][23090] Updated weights for policy 0, policy_version 74100 (0.0017) [2023-03-09 09:08:13,948][23090] Updated weights for policy 0, policy_version 74110 (0.0019) [2023-03-09 09:08:14,058][22664] Fps is (10 sec: 199886.4, 60 sec: 198520.6, 300 sec: 198718.7). Total num frames: 1214218240. Throughput: 0: 49775.0. Samples: 303524640. Policy #0 lag: (min: 2.0, avg: 16.8, max: 33.0) [2023-03-09 09:08:14,060][22664] Avg episode reward: [(0, '53.755')] [2023-03-09 09:08:14,604][22940] Signal inference workers to stop experience collection... (24300 times) [2023-03-09 09:08:14,605][22940] Signal inference workers to resume experience collection... (24300 times) [2023-03-09 09:08:14,673][23090] InferenceWorker_p0-w0: stopping experience collection (24300 times) [2023-03-09 09:08:14,673][23090] InferenceWorker_p0-w0: resuming experience collection (24300 times) [2023-03-09 09:08:14,804][23090] Updated weights for policy 0, policy_version 74120 (0.0019) [2023-03-09 09:08:15,612][23090] Updated weights for policy 0, policy_version 74130 (0.0016) [2023-03-09 09:08:16,439][23090] Updated weights for policy 0, policy_version 74140 (0.0020) [2023-03-09 09:08:17,298][23090] Updated weights for policy 0, policy_version 74150 (0.0014) [2023-03-09 09:08:18,085][23090] Updated weights for policy 0, policy_version 74160 (0.0013) [2023-03-09 09:08:18,976][23090] Updated weights for policy 0, policy_version 74170 (0.0013) [2023-03-09 09:08:19,059][22664] Fps is (10 sec: 198238.3, 60 sec: 198518.3, 300 sec: 198773.8). Total num frames: 1215217664. Throughput: 0: 49728.0. Samples: 303819472. Policy #0 lag: (min: 2.0, avg: 16.8, max: 33.0) [2023-03-09 09:08:19,061][22664] Avg episode reward: [(0, '52.590')] [2023-03-09 09:08:19,925][23090] Updated weights for policy 0, policy_version 74181 (0.0013) [2023-03-09 09:08:20,694][23090] Updated weights for policy 0, policy_version 74191 (0.0021) [2023-03-09 09:08:21,503][23090] Updated weights for policy 0, policy_version 74201 (0.0016) [2023-03-09 09:08:22,304][23090] Updated weights for policy 0, policy_version 74211 (0.0013) [2023-03-09 09:08:22,601][22940] Signal inference workers to stop experience collection... (24350 times) [2023-03-09 09:08:22,603][22940] Signal inference workers to resume experience collection... (24350 times) [2023-03-09 09:08:22,673][23090] InferenceWorker_p0-w0: stopping experience collection (24350 times) [2023-03-09 09:08:22,673][23090] InferenceWorker_p0-w0: resuming experience collection (24350 times) [2023-03-09 09:08:23,179][23090] Updated weights for policy 0, policy_version 74222 (0.0016) [2023-03-09 09:08:24,055][23090] Updated weights for policy 0, policy_version 74232 (0.0017) [2023-03-09 09:08:24,059][22664] Fps is (10 sec: 199879.9, 60 sec: 198793.8, 300 sec: 198773.9). Total num frames: 1216217088. Throughput: 0: 49731.0. Samples: 304118432. Policy #0 lag: (min: 2.0, avg: 16.8, max: 33.0) [2023-03-09 09:08:24,060][22664] Avg episode reward: [(0, '51.926')] [2023-03-09 09:08:24,822][23090] Updated weights for policy 0, policy_version 74242 (0.0025) [2023-03-09 09:08:25,817][23090] Updated weights for policy 0, policy_version 74253 (0.0013) [2023-03-09 09:08:26,620][23090] Updated weights for policy 0, policy_version 74263 (0.0015) [2023-03-09 09:08:27,386][23090] Updated weights for policy 0, policy_version 74273 (0.0016) [2023-03-09 09:08:28,154][23090] Updated weights for policy 0, policy_version 74283 (0.0013) [2023-03-09 09:08:29,059][22664] Fps is (10 sec: 196619.5, 60 sec: 198246.5, 300 sec: 198718.6). Total num frames: 1217183744. Throughput: 0: 49729.5. Samples: 304267808. Policy #0 lag: (min: 2.0, avg: 16.8, max: 33.0) [2023-03-09 09:08:29,060][22664] Avg episode reward: [(0, '52.378')] [2023-03-09 09:08:29,161][23090] Updated weights for policy 0, policy_version 74293 (0.0022) [2023-03-09 09:08:29,914][23090] Updated weights for policy 0, policy_version 74303 (0.0016) [2023-03-09 09:08:30,697][23090] Updated weights for policy 0, policy_version 74313 (0.0013) [2023-03-09 09:08:31,615][23090] Updated weights for policy 0, policy_version 74323 (0.0016) [2023-03-09 09:08:32,075][22940] Signal inference workers to stop experience collection... (24400 times) [2023-03-09 09:08:32,094][22940] Signal inference workers to resume experience collection... (24400 times) [2023-03-09 09:08:32,152][23090] InferenceWorker_p0-w0: stopping experience collection (24400 times) [2023-03-09 09:08:32,153][23090] InferenceWorker_p0-w0: resuming experience collection (24400 times) [2023-03-09 09:08:32,359][23090] Updated weights for policy 0, policy_version 74333 (0.0016) [2023-03-09 09:08:33,243][23090] Updated weights for policy 0, policy_version 74343 (0.0015) [2023-03-09 09:08:34,000][23090] Updated weights for policy 0, policy_version 74353 (0.0019) [2023-03-09 09:08:34,059][22664] Fps is (10 sec: 198250.7, 60 sec: 198792.3, 300 sec: 198885.1). Total num frames: 1218199552. Throughput: 0: 49683.2. Samples: 304564688. Policy #0 lag: (min: 2.0, avg: 16.8, max: 33.0) [2023-03-09 09:08:34,060][22664] Avg episode reward: [(0, '54.421')] [2023-03-09 09:08:34,931][23090] Updated weights for policy 0, policy_version 74364 (0.0019) [2023-03-09 09:08:35,779][23090] Updated weights for policy 0, policy_version 74374 (0.0016) [2023-03-09 09:08:36,655][23090] Updated weights for policy 0, policy_version 74385 (0.0025) [2023-03-09 09:08:37,467][23090] Updated weights for policy 0, policy_version 74395 (0.0016) [2023-03-09 09:08:38,386][23090] Updated weights for policy 0, policy_version 74405 (0.0024) [2023-03-09 09:08:39,059][22664] Fps is (10 sec: 199880.5, 60 sec: 198793.1, 300 sec: 198773.9). Total num frames: 1219182592. Throughput: 0: 49729.8. Samples: 304863632. Policy #0 lag: (min: 0.0, avg: 16.4, max: 32.0) [2023-03-09 09:08:39,060][22664] Avg episode reward: [(0, '51.905')] [2023-03-09 09:08:39,151][23090] Updated weights for policy 0, policy_version 74415 (0.0013) [2023-03-09 09:08:40,013][23090] Updated weights for policy 0, policy_version 74425 (0.0023) [2023-03-09 09:08:40,791][23090] Updated weights for policy 0, policy_version 74435 (0.0013) [2023-03-09 09:08:41,672][23090] Updated weights for policy 0, policy_version 74445 (0.0024) [2023-03-09 09:08:42,468][23090] Updated weights for policy 0, policy_version 74455 (0.0017) [2023-03-09 09:08:42,643][22940] Signal inference workers to stop experience collection... (24450 times) [2023-03-09 09:08:42,664][22940] Signal inference workers to resume experience collection... (24450 times) [2023-03-09 09:08:42,718][23090] InferenceWorker_p0-w0: stopping experience collection (24450 times) [2023-03-09 09:08:42,718][23090] InferenceWorker_p0-w0: resuming experience collection (24450 times) [2023-03-09 09:08:43,256][23090] Updated weights for policy 0, policy_version 74465 (0.0016) [2023-03-09 09:08:44,058][22664] Fps is (10 sec: 199886.3, 60 sec: 199066.2, 300 sec: 198774.3). Total num frames: 1220198400. Throughput: 0: 49683.7. Samples: 305011040. Policy #0 lag: (min: 0.0, avg: 16.4, max: 32.0) [2023-03-09 09:08:44,060][22664] Avg episode reward: [(0, '53.641')] [2023-03-09 09:08:44,293][23090] Updated weights for policy 0, policy_version 74476 (0.0023) [2023-03-09 09:08:45,058][23090] Updated weights for policy 0, policy_version 74486 (0.0016) [2023-03-09 09:08:45,860][23090] Updated weights for policy 0, policy_version 74496 (0.0017) [2023-03-09 09:08:46,546][23090] Updated weights for policy 0, policy_version 74506 (0.0016) [2023-03-09 09:08:47,577][23090] Updated weights for policy 0, policy_version 74516 (0.0026) [2023-03-09 09:08:48,286][23090] Updated weights for policy 0, policy_version 74526 (0.0015) [2023-03-09 09:08:49,059][22664] Fps is (10 sec: 199884.4, 60 sec: 198791.6, 300 sec: 198829.5). Total num frames: 1221181440. Throughput: 0: 49638.2. Samples: 305307920. Policy #0 lag: (min: 0.0, avg: 16.4, max: 32.0) [2023-03-09 09:08:49,061][22664] Avg episode reward: [(0, '52.543')] [2023-03-09 09:08:49,087][23090] Updated weights for policy 0, policy_version 74536 (0.0013) [2023-03-09 09:08:49,898][23090] Updated weights for policy 0, policy_version 74546 (0.0012) [2023-03-09 09:08:50,718][23090] Updated weights for policy 0, policy_version 74556 (0.0019) [2023-03-09 09:08:51,594][23090] Updated weights for policy 0, policy_version 74566 (0.0016) [2023-03-09 09:08:52,279][22940] Signal inference workers to stop experience collection... (24500 times) [2023-03-09 09:08:52,294][22940] Signal inference workers to resume experience collection... (24500 times) [2023-03-09 09:08:52,313][23090] InferenceWorker_p0-w0: stopping experience collection (24500 times) [2023-03-09 09:08:52,314][23090] InferenceWorker_p0-w0: resuming experience collection (24500 times) [2023-03-09 09:08:52,422][23090] Updated weights for policy 0, policy_version 74577 (0.0018) [2023-03-09 09:08:53,276][23090] Updated weights for policy 0, policy_version 74587 (0.0020) [2023-03-09 09:08:54,059][22664] Fps is (10 sec: 198242.1, 60 sec: 199066.1, 300 sec: 198718.6). Total num frames: 1222180864. Throughput: 0: 49681.1. Samples: 305608816. Policy #0 lag: (min: 0.0, avg: 16.4, max: 32.0) [2023-03-09 09:08:54,061][22664] Avg episode reward: [(0, '53.430')] [2023-03-09 09:08:54,187][23090] Updated weights for policy 0, policy_version 74597 (0.0020) [2023-03-09 09:08:54,990][23090] Updated weights for policy 0, policy_version 74608 (0.0017) [2023-03-09 09:08:55,881][23090] Updated weights for policy 0, policy_version 74618 (0.0029) [2023-03-09 09:08:56,719][23090] Updated weights for policy 0, policy_version 74628 (0.0016) [2023-03-09 09:08:57,578][23090] Updated weights for policy 0, policy_version 74638 (0.0016) [2023-03-09 09:08:58,394][23090] Updated weights for policy 0, policy_version 74648 (0.0019) [2023-03-09 09:08:59,059][22664] Fps is (10 sec: 198251.0, 60 sec: 198519.4, 300 sec: 198662.9). Total num frames: 1223163904. Throughput: 0: 49591.0. Samples: 305756240. Policy #0 lag: (min: 0.0, avg: 16.4, max: 32.0) [2023-03-09 09:08:59,060][22664] Avg episode reward: [(0, '52.129')] [2023-03-09 09:08:59,166][23090] Updated weights for policy 0, policy_version 74658 (0.0015) [2023-03-09 09:09:00,093][23090] Updated weights for policy 0, policy_version 74668 (0.0016) [2023-03-09 09:09:00,857][23090] Updated weights for policy 0, policy_version 74678 (0.0016) [2023-03-09 09:09:01,748][23090] Updated weights for policy 0, policy_version 74689 (0.0013) [2023-03-09 09:09:02,447][23090] Updated weights for policy 0, policy_version 74699 (0.0013) [2023-03-09 09:09:02,779][22940] Signal inference workers to stop experience collection... (24550 times) [2023-03-09 09:09:02,798][22940] Signal inference workers to resume experience collection... (24550 times) [2023-03-09 09:09:02,830][23090] InferenceWorker_p0-w0: stopping experience collection (24550 times) [2023-03-09 09:09:02,875][23090] InferenceWorker_p0-w0: resuming experience collection (24550 times) [2023-03-09 09:09:03,461][23090] Updated weights for policy 0, policy_version 74709 (0.0017) [2023-03-09 09:09:04,059][22664] Fps is (10 sec: 198245.6, 60 sec: 199065.2, 300 sec: 198718.3). Total num frames: 1224163328. Throughput: 0: 49637.8. Samples: 306053152. Policy #0 lag: (min: 0.0, avg: 16.4, max: 32.0) [2023-03-09 09:09:04,060][22664] Avg episode reward: [(0, '49.708')] [2023-03-09 09:09:04,215][23090] Updated weights for policy 0, policy_version 74719 (0.0013) [2023-03-09 09:09:05,014][23090] Updated weights for policy 0, policy_version 74730 (0.0022) [2023-03-09 09:09:06,066][23090] Updated weights for policy 0, policy_version 74740 (0.0022) [2023-03-09 09:09:06,747][23090] Updated weights for policy 0, policy_version 74750 (0.0015) [2023-03-09 09:09:07,568][23090] Updated weights for policy 0, policy_version 74760 (0.0022) [2023-03-09 09:09:08,398][23090] Updated weights for policy 0, policy_version 74770 (0.0016) [2023-03-09 09:09:09,059][22664] Fps is (10 sec: 198243.1, 60 sec: 198519.5, 300 sec: 198662.8). Total num frames: 1225146368. Throughput: 0: 49681.8. Samples: 306354112. Policy #0 lag: (min: 0.0, avg: 16.4, max: 32.0) [2023-03-09 09:09:09,060][22664] Avg episode reward: [(0, '51.640')] [2023-03-09 09:09:09,209][23090] Updated weights for policy 0, policy_version 74780 (0.0023) [2023-03-09 09:09:10,059][23090] Updated weights for policy 0, policy_version 74790 (0.0013) [2023-03-09 09:09:10,850][23090] Updated weights for policy 0, policy_version 74800 (0.0011) [2023-03-09 09:09:11,690][23090] Updated weights for policy 0, policy_version 74810 (0.0016) [2023-03-09 09:09:12,687][23090] Updated weights for policy 0, policy_version 74821 (0.0012) [2023-03-09 09:09:13,234][22940] Signal inference workers to stop experience collection... (24600 times) [2023-03-09 09:09:13,235][22940] Signal inference workers to resume experience collection... (24600 times) [2023-03-09 09:09:13,300][23090] InferenceWorker_p0-w0: stopping experience collection (24600 times) [2023-03-09 09:09:13,303][23090] InferenceWorker_p0-w0: resuming experience collection (24600 times) [2023-03-09 09:09:13,428][23090] Updated weights for policy 0, policy_version 74831 (0.0018) [2023-03-09 09:09:14,059][22664] Fps is (10 sec: 198249.9, 60 sec: 198792.4, 300 sec: 198663.0). Total num frames: 1226145792. Throughput: 0: 49682.2. Samples: 306503504. Policy #0 lag: (min: 0.0, avg: 16.4, max: 32.0) [2023-03-09 09:09:14,060][22664] Avg episode reward: [(0, '53.167')] [2023-03-09 09:09:14,306][23090] Updated weights for policy 0, policy_version 74841 (0.0021) [2023-03-09 09:09:15,077][23090] Updated weights for policy 0, policy_version 74851 (0.0016) [2023-03-09 09:09:15,954][23090] Updated weights for policy 0, policy_version 74861 (0.0016) [2023-03-09 09:09:16,796][23090] Updated weights for policy 0, policy_version 74871 (0.0013) [2023-03-09 09:09:17,566][23090] Updated weights for policy 0, policy_version 74881 (0.0021) [2023-03-09 09:09:18,543][23090] Updated weights for policy 0, policy_version 74892 (0.0013) [2023-03-09 09:09:19,058][22664] Fps is (10 sec: 198250.9, 60 sec: 198521.6, 300 sec: 198662.9). Total num frames: 1227128832. Throughput: 0: 49682.5. Samples: 306800400. Policy #0 lag: (min: 0.0, avg: 16.4, max: 32.0) [2023-03-09 09:09:19,059][22664] Avg episode reward: [(0, '51.927')] [2023-03-09 09:09:19,106][22940] Saving /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000074899_1227145216.pth... [2023-03-09 09:09:19,172][22940] Removing /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000071987_1179435008.pth [2023-03-09 09:09:19,358][23090] Updated weights for policy 0, policy_version 74902 (0.0022) [2023-03-09 09:09:20,164][23090] Updated weights for policy 0, policy_version 74912 (0.0018) [2023-03-09 09:09:20,865][23090] Updated weights for policy 0, policy_version 74922 (0.0022) [2023-03-09 09:09:21,845][23090] Updated weights for policy 0, policy_version 74932 (0.0021) [2023-03-09 09:09:22,545][23090] Updated weights for policy 0, policy_version 74942 (0.0020) [2023-03-09 09:09:23,198][22940] Signal inference workers to stop experience collection... (24650 times) [2023-03-09 09:09:23,199][22940] Signal inference workers to resume experience collection... (24650 times) [2023-03-09 09:09:23,273][23090] InferenceWorker_p0-w0: stopping experience collection (24650 times) [2023-03-09 09:09:23,273][23090] InferenceWorker_p0-w0: resuming experience collection (24650 times) [2023-03-09 09:09:23,403][23090] Updated weights for policy 0, policy_version 74952 (0.0013) [2023-03-09 09:09:24,059][22664] Fps is (10 sec: 198246.0, 60 sec: 198520.1, 300 sec: 198774.2). Total num frames: 1228128256. Throughput: 0: 49637.2. Samples: 307097296. Policy #0 lag: (min: 1.0, avg: 17.2, max: 33.0) [2023-03-09 09:09:24,060][22664] Avg episode reward: [(0, '53.234')] [2023-03-09 09:09:24,423][23090] Updated weights for policy 0, policy_version 74963 (0.0020) [2023-03-09 09:09:25,115][23090] Updated weights for policy 0, policy_version 74973 (0.0016) [2023-03-09 09:09:26,034][23090] Updated weights for policy 0, policy_version 74983 (0.0013) [2023-03-09 09:09:26,721][23090] Updated weights for policy 0, policy_version 74993 (0.0014) [2023-03-09 09:09:27,631][23090] Updated weights for policy 0, policy_version 75003 (0.0023) [2023-03-09 09:09:28,494][23090] Updated weights for policy 0, policy_version 75013 (0.0013) [2023-03-09 09:09:29,059][22664] Fps is (10 sec: 198240.4, 60 sec: 198791.7, 300 sec: 198662.7). Total num frames: 1229111296. Throughput: 0: 49681.7. Samples: 307246736. Policy #0 lag: (min: 1.0, avg: 17.2, max: 33.0) [2023-03-09 09:09:29,061][22664] Avg episode reward: [(0, '53.976')] [2023-03-09 09:09:29,338][23090] Updated weights for policy 0, policy_version 75024 (0.0018) [2023-03-09 09:09:30,212][23090] Updated weights for policy 0, policy_version 75034 (0.0013) [2023-03-09 09:09:31,104][23090] Updated weights for policy 0, policy_version 75044 (0.0016) [2023-03-09 09:09:31,876][23090] Updated weights for policy 0, policy_version 75054 (0.0015) [2023-03-09 09:09:31,924][22940] Signal inference workers to stop experience collection... (24700 times) [2023-03-09 09:09:31,927][22940] Signal inference workers to resume experience collection... (24700 times) [2023-03-09 09:09:31,993][23090] InferenceWorker_p0-w0: stopping experience collection (24700 times) [2023-03-09 09:09:31,994][23090] InferenceWorker_p0-w0: resuming experience collection (24700 times) [2023-03-09 09:09:32,746][23090] Updated weights for policy 0, policy_version 75064 (0.0013) [2023-03-09 09:09:33,480][23090] Updated weights for policy 0, policy_version 75074 (0.0016) [2023-03-09 09:09:34,059][22664] Fps is (10 sec: 199873.6, 60 sec: 198790.6, 300 sec: 198662.6). Total num frames: 1230127104. Throughput: 0: 49681.8. Samples: 307543616. Policy #0 lag: (min: 1.0, avg: 17.2, max: 33.0) [2023-03-09 09:09:34,062][22664] Avg episode reward: [(0, '51.754')] [2023-03-09 09:09:34,402][23090] Updated weights for policy 0, policy_version 75084 (0.0013) [2023-03-09 09:09:35,257][23090] Updated weights for policy 0, policy_version 75094 (0.0016) [2023-03-09 09:09:36,020][23090] Updated weights for policy 0, policy_version 75104 (0.0016) [2023-03-09 09:09:36,790][23090] Updated weights for policy 0, policy_version 75114 (0.0013) [2023-03-09 09:09:37,864][23090] Updated weights for policy 0, policy_version 75125 (0.0016) [2023-03-09 09:09:38,555][23090] Updated weights for policy 0, policy_version 75135 (0.0018) [2023-03-09 09:09:39,059][22664] Fps is (10 sec: 198248.7, 60 sec: 198519.7, 300 sec: 198663.0). Total num frames: 1231093760. Throughput: 0: 49592.2. Samples: 307840464. Policy #0 lag: (min: 1.0, avg: 17.2, max: 33.0) [2023-03-09 09:09:39,060][22664] Avg episode reward: [(0, '52.736')] [2023-03-09 09:09:39,345][23090] Updated weights for policy 0, policy_version 75145 (0.0014) [2023-03-09 09:09:40,361][23090] Updated weights for policy 0, policy_version 75156 (0.0013) [2023-03-09 09:09:41,058][23090] Updated weights for policy 0, policy_version 75166 (0.0017) [2023-03-09 09:09:41,989][23090] Updated weights for policy 0, policy_version 75177 (0.0014) [2023-03-09 09:09:42,364][22940] Signal inference workers to stop experience collection... (24750 times) [2023-03-09 09:09:42,384][22940] Signal inference workers to resume experience collection... (24750 times) [2023-03-09 09:09:42,428][23090] InferenceWorker_p0-w0: stopping experience collection (24750 times) [2023-03-09 09:09:42,431][23090] InferenceWorker_p0-w0: resuming experience collection (24750 times) [2023-03-09 09:09:42,901][23090] Updated weights for policy 0, policy_version 75187 (0.0013) [2023-03-09 09:09:43,622][23090] Updated weights for policy 0, policy_version 75197 (0.0016) [2023-03-09 09:09:44,058][22664] Fps is (10 sec: 196620.9, 60 sec: 198246.4, 300 sec: 198607.4). Total num frames: 1232093184. Throughput: 0: 49636.7. Samples: 307989888. Policy #0 lag: (min: 1.0, avg: 17.2, max: 33.0) [2023-03-09 09:09:44,059][22664] Avg episode reward: [(0, '52.616')] [2023-03-09 09:09:44,483][23090] Updated weights for policy 0, policy_version 75207 (0.0014) [2023-03-09 09:09:45,236][23090] Updated weights for policy 0, policy_version 75217 (0.0020) [2023-03-09 09:09:46,131][23090] Updated weights for policy 0, policy_version 75227 (0.0013) [2023-03-09 09:09:47,040][23090] Updated weights for policy 0, policy_version 75237 (0.0017) [2023-03-09 09:09:47,768][23090] Updated weights for policy 0, policy_version 75247 (0.0020) [2023-03-09 09:09:48,675][23090] Updated weights for policy 0, policy_version 75257 (0.0023) [2023-03-09 09:09:49,059][22664] Fps is (10 sec: 199883.4, 60 sec: 198519.6, 300 sec: 198662.7). Total num frames: 1233092608. Throughput: 0: 49682.1. Samples: 308288848. Policy #0 lag: (min: 1.0, avg: 17.2, max: 33.0) [2023-03-09 09:09:49,060][22664] Avg episode reward: [(0, '54.771')] [2023-03-09 09:09:49,417][23090] Updated weights for policy 0, policy_version 75267 (0.0013) [2023-03-09 09:09:50,320][23090] Updated weights for policy 0, policy_version 75277 (0.0022) [2023-03-09 09:09:51,137][23090] Updated weights for policy 0, policy_version 75287 (0.0016) [2023-03-09 09:09:51,950][23090] Updated weights for policy 0, policy_version 75297 (0.0015) [2023-03-09 09:09:52,686][23090] Updated weights for policy 0, policy_version 75307 (0.0013) [2023-03-09 09:09:53,038][22940] Signal inference workers to stop experience collection... (24800 times) [2023-03-09 09:09:53,055][22940] Signal inference workers to resume experience collection... (24800 times) [2023-03-09 09:09:53,079][23090] InferenceWorker_p0-w0: stopping experience collection (24800 times) [2023-03-09 09:09:53,117][23090] InferenceWorker_p0-w0: resuming experience collection (24800 times) [2023-03-09 09:09:53,662][23090] Updated weights for policy 0, policy_version 75317 (0.0013) [2023-03-09 09:09:54,058][22664] Fps is (10 sec: 198245.7, 60 sec: 198247.0, 300 sec: 198607.4). Total num frames: 1234075648. Throughput: 0: 49590.7. Samples: 308585680. Policy #0 lag: (min: 1.0, avg: 17.2, max: 33.0) [2023-03-09 09:09:54,059][22664] Avg episode reward: [(0, '52.376')] [2023-03-09 09:09:54,397][23090] Updated weights for policy 0, policy_version 75327 (0.0013) [2023-03-09 09:09:55,249][23090] Updated weights for policy 0, policy_version 75337 (0.0013) [2023-03-09 09:09:56,133][23090] Updated weights for policy 0, policy_version 75347 (0.0017) [2023-03-09 09:09:56,824][23090] Updated weights for policy 0, policy_version 75357 (0.0018) [2023-03-09 09:09:57,745][23090] Updated weights for policy 0, policy_version 75367 (0.0014) [2023-03-09 09:09:58,423][23090] Updated weights for policy 0, policy_version 75377 (0.0017) [2023-03-09 09:09:59,059][22664] Fps is (10 sec: 198242.6, 60 sec: 198518.2, 300 sec: 198662.7). Total num frames: 1235075072. Throughput: 0: 49592.4. Samples: 308735184. Policy #0 lag: (min: 1.0, avg: 17.2, max: 33.0) [2023-03-09 09:09:59,061][22664] Avg episode reward: [(0, '53.888')] [2023-03-09 09:09:59,342][23090] Updated weights for policy 0, policy_version 75387 (0.0013) [2023-03-09 09:10:00,230][23090] Updated weights for policy 0, policy_version 75397 (0.0013) [2023-03-09 09:10:00,965][23090] Updated weights for policy 0, policy_version 75407 (0.0015) [2023-03-09 09:10:01,885][23090] Updated weights for policy 0, policy_version 75417 (0.0013) [2023-03-09 09:10:02,630][23090] Updated weights for policy 0, policy_version 75427 (0.0018) [2023-03-09 09:10:03,551][23090] Updated weights for policy 0, policy_version 75438 (0.0013) [2023-03-09 09:10:04,058][22664] Fps is (10 sec: 198246.2, 60 sec: 198247.1, 300 sec: 198662.9). Total num frames: 1236058112. Throughput: 0: 49638.0. Samples: 309034112. Policy #0 lag: (min: 1.0, avg: 17.2, max: 33.0) [2023-03-09 09:10:04,060][22664] Avg episode reward: [(0, '53.847')] [2023-03-09 09:10:04,194][22940] Signal inference workers to stop experience collection... (24850 times) [2023-03-09 09:10:04,196][22940] Signal inference workers to resume experience collection... (24850 times) [2023-03-09 09:10:04,263][23090] InferenceWorker_p0-w0: stopping experience collection (24850 times) [2023-03-09 09:10:04,265][23090] InferenceWorker_p0-w0: resuming experience collection (24850 times) [2023-03-09 09:10:04,392][23090] Updated weights for policy 0, policy_version 75448 (0.0023) [2023-03-09 09:10:05,153][23090] Updated weights for policy 0, policy_version 75458 (0.0019) [2023-03-09 09:10:06,034][23090] Updated weights for policy 0, policy_version 75468 (0.0013) [2023-03-09 09:10:06,925][23090] Updated weights for policy 0, policy_version 75478 (0.0013) [2023-03-09 09:10:07,652][23090] Updated weights for policy 0, policy_version 75488 (0.0019) [2023-03-09 09:10:08,460][23090] Updated weights for policy 0, policy_version 75499 (0.0017) [2023-03-09 09:10:09,059][22664] Fps is (10 sec: 199882.1, 60 sec: 198791.4, 300 sec: 198773.8). Total num frames: 1237073920. Throughput: 0: 49637.5. Samples: 309331008. Policy #0 lag: (min: 2.0, avg: 17.0, max: 33.0) [2023-03-09 09:10:09,062][22664] Avg episode reward: [(0, '54.433')] [2023-03-09 09:10:09,500][23090] Updated weights for policy 0, policy_version 75509 (0.0016) [2023-03-09 09:10:10,225][23090] Updated weights for policy 0, policy_version 75519 (0.0017) [2023-03-09 09:10:11,056][23090] Updated weights for policy 0, policy_version 75529 (0.0016) [2023-03-09 09:10:11,970][23090] Updated weights for policy 0, policy_version 75539 (0.0018) [2023-03-09 09:10:12,776][23090] Updated weights for policy 0, policy_version 75550 (0.0013) [2023-03-09 09:10:13,630][23090] Updated weights for policy 0, policy_version 75560 (0.0026) [2023-03-09 09:10:14,057][22940] Signal inference workers to stop experience collection... (24900 times) [2023-03-09 09:10:14,059][22664] Fps is (10 sec: 198245.2, 60 sec: 198246.3, 300 sec: 198718.8). Total num frames: 1238040576. Throughput: 0: 49592.8. Samples: 309478400. Policy #0 lag: (min: 2.0, avg: 17.0, max: 33.0) [2023-03-09 09:10:14,059][22664] Avg episode reward: [(0, '52.263')] [2023-03-09 09:10:14,083][22940] Signal inference workers to resume experience collection... (24900 times) [2023-03-09 09:10:14,111][23090] InferenceWorker_p0-w0: stopping experience collection (24900 times) [2023-03-09 09:10:14,111][23090] InferenceWorker_p0-w0: resuming experience collection (24900 times) [2023-03-09 09:10:14,448][23090] Updated weights for policy 0, policy_version 75570 (0.0013) [2023-03-09 09:10:15,290][23090] Updated weights for policy 0, policy_version 75580 (0.0013) [2023-03-09 09:10:16,141][23090] Updated weights for policy 0, policy_version 75590 (0.0013) [2023-03-09 09:10:16,984][23090] Updated weights for policy 0, policy_version 75601 (0.0013) [2023-03-09 09:10:17,819][23090] Updated weights for policy 0, policy_version 75611 (0.0018) [2023-03-09 09:10:18,743][23090] Updated weights for policy 0, policy_version 75621 (0.0016) [2023-03-09 09:10:19,058][22664] Fps is (10 sec: 199897.1, 60 sec: 199065.7, 300 sec: 198718.6). Total num frames: 1239072768. Throughput: 0: 49638.4. Samples: 309777312. Policy #0 lag: (min: 2.0, avg: 17.0, max: 33.0) [2023-03-09 09:10:19,059][22664] Avg episode reward: [(0, '54.459')] [2023-03-09 09:10:19,506][23090] Updated weights for policy 0, policy_version 75631 (0.0016) [2023-03-09 09:10:20,372][23090] Updated weights for policy 0, policy_version 75641 (0.0017) [2023-03-09 09:10:21,110][23090] Updated weights for policy 0, policy_version 75651 (0.0013) [2023-03-09 09:10:21,996][23090] Updated weights for policy 0, policy_version 75661 (0.0024) [2023-03-09 09:10:22,833][23090] Updated weights for policy 0, policy_version 75671 (0.0013) [2023-03-09 09:10:22,957][22940] Signal inference workers to stop experience collection... (24950 times) [2023-03-09 09:10:22,969][22940] Signal inference workers to resume experience collection... (24950 times) [2023-03-09 09:10:23,031][23090] InferenceWorker_p0-w0: stopping experience collection (24950 times) [2023-03-09 09:10:23,031][23090] InferenceWorker_p0-w0: resuming experience collection (24950 times) [2023-03-09 09:10:23,565][23090] Updated weights for policy 0, policy_version 75681 (0.0016) [2023-03-09 09:10:24,059][22664] Fps is (10 sec: 201518.7, 60 sec: 198791.8, 300 sec: 198774.0). Total num frames: 1240055808. Throughput: 0: 49679.9. Samples: 310076064. Policy #0 lag: (min: 2.0, avg: 17.0, max: 33.0) [2023-03-09 09:10:24,061][22664] Avg episode reward: [(0, '51.883')] [2023-03-09 09:10:24,330][23090] Updated weights for policy 0, policy_version 75691 (0.0025) [2023-03-09 09:10:25,321][23090] Updated weights for policy 0, policy_version 75701 (0.0013) [2023-03-09 09:10:26,017][23090] Updated weights for policy 0, policy_version 75711 (0.0013) [2023-03-09 09:10:26,864][23090] Updated weights for policy 0, policy_version 75721 (0.0013) [2023-03-09 09:10:27,747][23090] Updated weights for policy 0, policy_version 75731 (0.0019) [2023-03-09 09:10:28,478][23090] Updated weights for policy 0, policy_version 75741 (0.0017) [2023-03-09 09:10:29,059][22664] Fps is (10 sec: 196600.4, 60 sec: 198792.4, 300 sec: 198662.8). Total num frames: 1241038848. Throughput: 0: 49679.9. Samples: 310225504. Policy #0 lag: (min: 2.0, avg: 17.0, max: 33.0) [2023-03-09 09:10:29,061][22664] Avg episode reward: [(0, '52.411')] [2023-03-09 09:10:29,348][23090] Updated weights for policy 0, policy_version 75751 (0.0014) [2023-03-09 09:10:30,275][23090] Updated weights for policy 0, policy_version 75762 (0.0016) [2023-03-09 09:10:31,072][23090] Updated weights for policy 0, policy_version 75772 (0.0020) [2023-03-09 09:10:31,922][23090] Updated weights for policy 0, policy_version 75782 (0.0020) [2023-03-09 09:10:32,715][23090] Updated weights for policy 0, policy_version 75792 (0.0024) [2023-03-09 09:10:33,169][22940] Signal inference workers to stop experience collection... (25000 times) [2023-03-09 09:10:33,171][22940] Signal inference workers to resume experience collection... (25000 times) [2023-03-09 09:10:33,235][23090] InferenceWorker_p0-w0: stopping experience collection (25000 times) [2023-03-09 09:10:33,277][23090] InferenceWorker_p0-w0: resuming experience collection (25000 times) [2023-03-09 09:10:33,639][23090] Updated weights for policy 0, policy_version 75802 (0.0013) [2023-03-09 09:10:34,059][22664] Fps is (10 sec: 198248.9, 60 sec: 198521.0, 300 sec: 198718.4). Total num frames: 1242038272. Throughput: 0: 49679.7. Samples: 310524432. Policy #0 lag: (min: 2.0, avg: 17.0, max: 33.0) [2023-03-09 09:10:34,060][22664] Avg episode reward: [(0, '53.178')] [2023-03-09 09:10:34,402][23090] Updated weights for policy 0, policy_version 75812 (0.0018) [2023-03-09 09:10:35,254][23090] Updated weights for policy 0, policy_version 75822 (0.0021) [2023-03-09 09:10:36,180][23090] Updated weights for policy 0, policy_version 75833 (0.0029) [2023-03-09 09:10:36,906][23090] Updated weights for policy 0, policy_version 75843 (0.0012) [2023-03-09 09:10:37,821][23090] Updated weights for policy 0, policy_version 75853 (0.0016) [2023-03-09 09:10:38,632][23090] Updated weights for policy 0, policy_version 75863 (0.0016) [2023-03-09 09:10:39,058][22664] Fps is (10 sec: 199892.4, 60 sec: 199066.3, 300 sec: 198774.2). Total num frames: 1243037696. Throughput: 0: 49681.1. Samples: 310821328. Policy #0 lag: (min: 2.0, avg: 17.0, max: 33.0) [2023-03-09 09:10:39,059][22664] Avg episode reward: [(0, '51.882')] [2023-03-09 09:10:39,396][23090] Updated weights for policy 0, policy_version 75873 (0.0023) [2023-03-09 09:10:40,164][23090] Updated weights for policy 0, policy_version 75883 (0.0021) [2023-03-09 09:10:41,122][23090] Updated weights for policy 0, policy_version 75893 (0.0016) [2023-03-09 09:10:41,850][23090] Updated weights for policy 0, policy_version 75903 (0.0018) [2023-03-09 09:10:42,673][23090] Updated weights for policy 0, policy_version 75913 (0.0013) [2023-03-09 09:10:43,621][23090] Updated weights for policy 0, policy_version 75923 (0.0020) [2023-03-09 09:10:44,059][22664] Fps is (10 sec: 198247.0, 60 sec: 198792.0, 300 sec: 198663.0). Total num frames: 1244020736. Throughput: 0: 49680.0. Samples: 310970768. Policy #0 lag: (min: 2.0, avg: 17.0, max: 33.0) [2023-03-09 09:10:44,060][22664] Avg episode reward: [(0, '55.191')] [2023-03-09 09:10:44,259][22940] Signal inference workers to stop experience collection... (25050 times) [2023-03-09 09:10:44,263][22940] Signal inference workers to resume experience collection... (25050 times) [2023-03-09 09:10:44,326][23090] InferenceWorker_p0-w0: stopping experience collection (25050 times) [2023-03-09 09:10:44,326][23090] InferenceWorker_p0-w0: resuming experience collection (25050 times) [2023-03-09 09:10:44,329][23090] Updated weights for policy 0, policy_version 75933 (0.0013) [2023-03-09 09:10:45,179][23090] Updated weights for policy 0, policy_version 75943 (0.0027) [2023-03-09 09:10:46,074][23090] Updated weights for policy 0, policy_version 75954 (0.0013) [2023-03-09 09:10:46,983][23090] Updated weights for policy 0, policy_version 75965 (0.0013) [2023-03-09 09:10:47,801][23090] Updated weights for policy 0, policy_version 75975 (0.0016) [2023-03-09 09:10:48,699][23090] Updated weights for policy 0, policy_version 75986 (0.0025) [2023-03-09 09:10:49,058][22664] Fps is (10 sec: 196608.2, 60 sec: 198520.4, 300 sec: 198663.2). Total num frames: 1245003776. Throughput: 0: 49632.4. Samples: 311267568. Policy #0 lag: (min: 2.0, avg: 17.0, max: 33.0) [2023-03-09 09:10:49,059][22664] Avg episode reward: [(0, '52.758')] [2023-03-09 09:10:49,582][23090] Updated weights for policy 0, policy_version 75996 (0.0017) [2023-03-09 09:10:50,389][23090] Updated weights for policy 0, policy_version 76006 (0.0019) [2023-03-09 09:10:51,215][23090] Updated weights for policy 0, policy_version 76017 (0.0019) [2023-03-09 09:10:52,170][23090] Updated weights for policy 0, policy_version 76028 (0.0014) [2023-03-09 09:10:53,020][23090] Updated weights for policy 0, policy_version 76038 (0.0013) [2023-03-09 09:10:53,887][23090] Updated weights for policy 0, policy_version 76049 (0.0014) [2023-03-09 09:10:54,059][22664] Fps is (10 sec: 198244.0, 60 sec: 198791.7, 300 sec: 198718.4). Total num frames: 1246003200. Throughput: 0: 49632.7. Samples: 311564464. Policy #0 lag: (min: 2.0, avg: 17.0, max: 33.0) [2023-03-09 09:10:54,060][22664] Avg episode reward: [(0, '53.119')] [2023-03-09 09:10:54,807][23090] Updated weights for policy 0, policy_version 76059 (0.0022) [2023-03-09 09:10:54,815][22940] Signal inference workers to stop experience collection... (25100 times) [2023-03-09 09:10:54,830][22940] Signal inference workers to resume experience collection... (25100 times) [2023-03-09 09:10:54,888][23090] InferenceWorker_p0-w0: stopping experience collection (25100 times) [2023-03-09 09:10:54,891][23090] InferenceWorker_p0-w0: resuming experience collection (25100 times) [2023-03-09 09:10:55,582][23090] Updated weights for policy 0, policy_version 76069 (0.0014) [2023-03-09 09:10:56,399][23090] Updated weights for policy 0, policy_version 76079 (0.0013) [2023-03-09 09:10:57,208][23090] Updated weights for policy 0, policy_version 76089 (0.0016) [2023-03-09 09:10:57,975][23090] Updated weights for policy 0, policy_version 76099 (0.0013) [2023-03-09 09:10:58,883][23090] Updated weights for policy 0, policy_version 76109 (0.0016) [2023-03-09 09:10:59,059][22664] Fps is (10 sec: 201506.7, 60 sec: 199064.5, 300 sec: 198829.2). Total num frames: 1247019008. Throughput: 0: 49723.7. Samples: 311716000. Policy #0 lag: (min: 1.0, avg: 16.1, max: 33.0) [2023-03-09 09:10:59,061][22664] Avg episode reward: [(0, '54.123')] [2023-03-09 09:10:59,724][23090] Updated weights for policy 0, policy_version 76120 (0.0016) [2023-03-09 09:11:00,535][23090] Updated weights for policy 0, policy_version 76130 (0.0023) [2023-03-09 09:11:01,526][23090] Updated weights for policy 0, policy_version 76141 (0.0013) [2023-03-09 09:11:02,341][23090] Updated weights for policy 0, policy_version 76151 (0.0020) [2023-03-09 09:11:03,092][23090] Updated weights for policy 0, policy_version 76161 (0.0017) [2023-03-09 09:11:03,865][23090] Updated weights for policy 0, policy_version 76171 (0.0016) [2023-03-09 09:11:04,059][22664] Fps is (10 sec: 199883.5, 60 sec: 199064.6, 300 sec: 198718.4). Total num frames: 1248002048. Throughput: 0: 49769.9. Samples: 312016976. Policy #0 lag: (min: 1.0, avg: 16.1, max: 33.0) [2023-03-09 09:11:04,061][22664] Avg episode reward: [(0, '54.571')] [2023-03-09 09:11:04,863][23090] Updated weights for policy 0, policy_version 76181 (0.0018) [2023-03-09 09:11:04,921][22940] Signal inference workers to stop experience collection... (25150 times) [2023-03-09 09:11:04,922][22940] Signal inference workers to resume experience collection... (25150 times) [2023-03-09 09:11:04,987][23090] InferenceWorker_p0-w0: stopping experience collection (25150 times) [2023-03-09 09:11:04,987][23090] InferenceWorker_p0-w0: resuming experience collection (25150 times) [2023-03-09 09:11:05,781][23090] Updated weights for policy 0, policy_version 76192 (0.0016) [2023-03-09 09:11:06,538][23090] Updated weights for policy 0, policy_version 76202 (0.0013) [2023-03-09 09:11:07,490][23090] Updated weights for policy 0, policy_version 76212 (0.0015) [2023-03-09 09:11:08,200][23090] Updated weights for policy 0, policy_version 76222 (0.0013) [2023-03-09 09:11:09,052][23090] Updated weights for policy 0, policy_version 76232 (0.0016) [2023-03-09 09:11:09,059][22664] Fps is (10 sec: 196615.7, 60 sec: 198520.1, 300 sec: 198662.8). Total num frames: 1248985088. Throughput: 0: 49638.6. Samples: 312309808. Policy #0 lag: (min: 1.0, avg: 16.1, max: 33.0) [2023-03-09 09:11:09,061][22664] Avg episode reward: [(0, '55.339')] [2023-03-09 09:11:09,839][23090] Updated weights for policy 0, policy_version 76242 (0.0015) [2023-03-09 09:11:10,683][23090] Updated weights for policy 0, policy_version 76252 (0.0016) [2023-03-09 09:11:11,557][23090] Updated weights for policy 0, policy_version 76262 (0.0017) [2023-03-09 09:11:12,313][23090] Updated weights for policy 0, policy_version 76272 (0.0020) [2023-03-09 09:11:13,186][23090] Updated weights for policy 0, policy_version 76282 (0.0013) [2023-03-09 09:11:13,994][23090] Updated weights for policy 0, policy_version 76292 (0.0018) [2023-03-09 09:11:14,058][22664] Fps is (10 sec: 196615.2, 60 sec: 198792.9, 300 sec: 198663.2). Total num frames: 1249968128. Throughput: 0: 49640.3. Samples: 312459296. Policy #0 lag: (min: 1.0, avg: 16.1, max: 33.0) [2023-03-09 09:11:14,059][22664] Avg episode reward: [(0, '55.350')] [2023-03-09 09:11:14,735][22940] Signal inference workers to stop experience collection... (25200 times) [2023-03-09 09:11:14,757][22940] Signal inference workers to resume experience collection... (25200 times) [2023-03-09 09:11:14,801][23090] InferenceWorker_p0-w0: stopping experience collection (25200 times) [2023-03-09 09:11:14,801][23090] InferenceWorker_p0-w0: resuming experience collection (25200 times) [2023-03-09 09:11:14,841][23090] Updated weights for policy 0, policy_version 76302 (0.0023) [2023-03-09 09:11:15,622][23090] Updated weights for policy 0, policy_version 76312 (0.0014) [2023-03-09 09:11:16,511][23090] Updated weights for policy 0, policy_version 76323 (0.0021) [2023-03-09 09:11:17,425][23090] Updated weights for policy 0, policy_version 76333 (0.0020) [2023-03-09 09:11:18,252][23090] Updated weights for policy 0, policy_version 76343 (0.0017) [2023-03-09 09:11:18,982][23090] Updated weights for policy 0, policy_version 76353 (0.0019) [2023-03-09 09:11:19,059][22664] Fps is (10 sec: 198252.6, 60 sec: 198246.0, 300 sec: 198551.8). Total num frames: 1250967552. Throughput: 0: 49595.8. Samples: 312756240. Policy #0 lag: (min: 1.0, avg: 16.1, max: 33.0) [2023-03-09 09:11:19,060][22664] Avg episode reward: [(0, '51.769')] [2023-03-09 09:11:19,064][22940] Saving /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000076354_1250983936.pth... [2023-03-09 09:11:19,134][22940] Removing /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000073445_1203322880.pth [2023-03-09 09:11:20,025][23090] Updated weights for policy 0, policy_version 76364 (0.0016) [2023-03-09 09:11:20,838][23090] Updated weights for policy 0, policy_version 76374 (0.0017) [2023-03-09 09:11:21,585][23090] Updated weights for policy 0, policy_version 76384 (0.0016) [2023-03-09 09:11:22,361][23090] Updated weights for policy 0, policy_version 76394 (0.0017) [2023-03-09 09:11:23,369][23090] Updated weights for policy 0, policy_version 76404 (0.0013) [2023-03-09 09:11:24,010][23090] Updated weights for policy 0, policy_version 76414 (0.0014) [2023-03-09 09:11:24,059][22664] Fps is (10 sec: 199879.4, 60 sec: 198519.7, 300 sec: 198662.8). Total num frames: 1251966976. Throughput: 0: 49594.7. Samples: 313053104. Policy #0 lag: (min: 1.0, avg: 16.1, max: 33.0) [2023-03-09 09:11:24,060][22664] Avg episode reward: [(0, '53.262')] [2023-03-09 09:11:24,906][23090] Updated weights for policy 0, policy_version 76424 (0.0014) [2023-03-09 09:11:24,918][22940] Signal inference workers to stop experience collection... (25250 times) [2023-03-09 09:11:24,937][22940] Signal inference workers to resume experience collection... (25250 times) [2023-03-09 09:11:24,948][23090] InferenceWorker_p0-w0: stopping experience collection (25250 times) [2023-03-09 09:11:24,948][23090] InferenceWorker_p0-w0: resuming experience collection (25250 times) [2023-03-09 09:11:25,713][23090] Updated weights for policy 0, policy_version 76434 (0.0013) [2023-03-09 09:11:26,563][23090] Updated weights for policy 0, policy_version 76444 (0.0018) [2023-03-09 09:11:27,367][23090] Updated weights for policy 0, policy_version 76454 (0.0013) [2023-03-09 09:11:28,211][23090] Updated weights for policy 0, policy_version 76465 (0.0016) [2023-03-09 09:11:29,059][22664] Fps is (10 sec: 198245.3, 60 sec: 198520.2, 300 sec: 198607.5). Total num frames: 1252950016. Throughput: 0: 49595.7. Samples: 313202576. Policy #0 lag: (min: 1.0, avg: 16.1, max: 33.0) [2023-03-09 09:11:29,060][22664] Avg episode reward: [(0, '50.810')] [2023-03-09 09:11:29,089][23090] Updated weights for policy 0, policy_version 76475 (0.0016) [2023-03-09 09:11:29,912][23090] Updated weights for policy 0, policy_version 76485 (0.0016) [2023-03-09 09:11:30,711][23090] Updated weights for policy 0, policy_version 76495 (0.0016) [2023-03-09 09:11:31,639][23090] Updated weights for policy 0, policy_version 76505 (0.0013) [2023-03-09 09:11:32,460][23090] Updated weights for policy 0, policy_version 76516 (0.0024) [2023-03-09 09:11:33,296][23090] Updated weights for policy 0, policy_version 76526 (0.0022) [2023-03-09 09:11:34,059][22664] Fps is (10 sec: 198247.8, 60 sec: 198519.5, 300 sec: 198607.5). Total num frames: 1253949440. Throughput: 0: 49638.9. Samples: 313501328. Policy #0 lag: (min: 1.0, avg: 16.1, max: 33.0) [2023-03-09 09:11:34,061][22664] Avg episode reward: [(0, '52.440')] [2023-03-09 09:11:34,103][23090] Updated weights for policy 0, policy_version 76536 (0.0013) [2023-03-09 09:11:34,941][23090] Updated weights for policy 0, policy_version 76547 (0.0013) [2023-03-09 09:11:35,499][22940] Signal inference workers to stop experience collection... (25300 times) [2023-03-09 09:11:35,499][22940] Signal inference workers to resume experience collection... (25300 times) [2023-03-09 09:11:35,524][23090] InferenceWorker_p0-w0: stopping experience collection (25300 times) [2023-03-09 09:11:35,527][23090] InferenceWorker_p0-w0: resuming experience collection (25300 times) [2023-03-09 09:11:35,867][23090] Updated weights for policy 0, policy_version 76557 (0.0022) [2023-03-09 09:11:36,683][23090] Updated weights for policy 0, policy_version 76567 (0.0019) [2023-03-09 09:11:37,472][23090] Updated weights for policy 0, policy_version 76577 (0.0015) [2023-03-09 09:11:38,215][23090] Updated weights for policy 0, policy_version 76587 (0.0017) [2023-03-09 09:11:39,059][22664] Fps is (10 sec: 198242.8, 60 sec: 198245.3, 300 sec: 198551.8). Total num frames: 1254932480. Throughput: 0: 49730.1. Samples: 313802320. Policy #0 lag: (min: 1.0, avg: 16.1, max: 33.0) [2023-03-09 09:11:39,060][22664] Avg episode reward: [(0, '50.970')] [2023-03-09 09:11:39,163][23090] Updated weights for policy 0, policy_version 76597 (0.0013) [2023-03-09 09:11:39,917][23090] Updated weights for policy 0, policy_version 76607 (0.0017) [2023-03-09 09:11:40,709][23090] Updated weights for policy 0, policy_version 76617 (0.0013) [2023-03-09 09:11:41,783][23090] Updated weights for policy 0, policy_version 76628 (0.0015) [2023-03-09 09:11:42,398][23090] Updated weights for policy 0, policy_version 76638 (0.0014) [2023-03-09 09:11:43,297][23090] Updated weights for policy 0, policy_version 76648 (0.0014) [2023-03-09 09:11:44,059][22664] Fps is (10 sec: 199886.6, 60 sec: 198792.7, 300 sec: 198663.1). Total num frames: 1255948288. Throughput: 0: 49684.0. Samples: 313951744. Policy #0 lag: (min: 0.0, avg: 16.8, max: 33.0) [2023-03-09 09:11:44,060][22664] Avg episode reward: [(0, '52.644')] [2023-03-09 09:11:44,078][23090] Updated weights for policy 0, policy_version 76658 (0.0017) [2023-03-09 09:11:44,924][23090] Updated weights for policy 0, policy_version 76668 (0.0020) [2023-03-09 09:11:45,759][23090] Updated weights for policy 0, policy_version 76678 (0.0021) [2023-03-09 09:11:45,857][22940] Signal inference workers to stop experience collection... (25350 times) [2023-03-09 09:11:45,858][22940] Signal inference workers to resume experience collection... (25350 times) [2023-03-09 09:11:45,926][23090] InferenceWorker_p0-w0: stopping experience collection (25350 times) [2023-03-09 09:11:45,926][23090] InferenceWorker_p0-w0: resuming experience collection (25350 times) [2023-03-09 09:11:46,550][23090] Updated weights for policy 0, policy_version 76688 (0.0013) [2023-03-09 09:11:47,459][23090] Updated weights for policy 0, policy_version 76698 (0.0013) [2023-03-09 09:11:48,262][23090] Updated weights for policy 0, policy_version 76708 (0.0022) [2023-03-09 09:11:49,059][22664] Fps is (10 sec: 199889.5, 60 sec: 198792.1, 300 sec: 198663.1). Total num frames: 1256931328. Throughput: 0: 49637.6. Samples: 314250656. Policy #0 lag: (min: 0.0, avg: 16.8, max: 33.0) [2023-03-09 09:11:49,060][22664] Avg episode reward: [(0, '53.527')] [2023-03-09 09:11:49,108][23090] Updated weights for policy 0, policy_version 76718 (0.0013) [2023-03-09 09:11:49,882][23090] Updated weights for policy 0, policy_version 76728 (0.0021) [2023-03-09 09:11:50,625][23090] Updated weights for policy 0, policy_version 76738 (0.0014) [2023-03-09 09:11:51,628][23090] Updated weights for policy 0, policy_version 76748 (0.0013) [2023-03-09 09:11:52,405][23090] Updated weights for policy 0, policy_version 76758 (0.0016) [2023-03-09 09:11:53,238][23090] Updated weights for policy 0, policy_version 76769 (0.0013) [2023-03-09 09:11:54,009][23090] Updated weights for policy 0, policy_version 76779 (0.0022) [2023-03-09 09:11:54,059][22664] Fps is (10 sec: 199880.4, 60 sec: 199065.5, 300 sec: 198718.5). Total num frames: 1257947136. Throughput: 0: 49773.3. Samples: 314549600. Policy #0 lag: (min: 0.0, avg: 16.8, max: 33.0) [2023-03-09 09:11:54,060][22664] Avg episode reward: [(0, '55.228')] [2023-03-09 09:11:54,992][23090] Updated weights for policy 0, policy_version 76790 (0.0018) [2023-03-09 09:11:55,091][22940] Signal inference workers to stop experience collection... (25400 times) [2023-03-09 09:11:55,092][22940] Signal inference workers to resume experience collection... (25400 times) [2023-03-09 09:11:55,152][23090] InferenceWorker_p0-w0: stopping experience collection (25400 times) [2023-03-09 09:11:55,152][23090] InferenceWorker_p0-w0: resuming experience collection (25400 times) [2023-03-09 09:11:55,764][23090] Updated weights for policy 0, policy_version 76800 (0.0020) [2023-03-09 09:11:56,558][23090] Updated weights for policy 0, policy_version 76810 (0.0018) [2023-03-09 09:11:57,526][23090] Updated weights for policy 0, policy_version 76820 (0.0013) [2023-03-09 09:11:58,236][23090] Updated weights for policy 0, policy_version 76830 (0.0013) [2023-03-09 09:11:59,059][22664] Fps is (10 sec: 201522.3, 60 sec: 198794.7, 300 sec: 198774.0). Total num frames: 1258946560. Throughput: 0: 49771.5. Samples: 314699024. Policy #0 lag: (min: 0.0, avg: 16.8, max: 33.0) [2023-03-09 09:11:59,060][22664] Avg episode reward: [(0, '54.282')] [2023-03-09 09:11:59,074][23090] Updated weights for policy 0, policy_version 76840 (0.0013) [2023-03-09 09:11:59,903][23090] Updated weights for policy 0, policy_version 76850 (0.0014) [2023-03-09 09:12:00,809][23090] Updated weights for policy 0, policy_version 76860 (0.0013) [2023-03-09 09:12:01,587][23090] Updated weights for policy 0, policy_version 76870 (0.0016) [2023-03-09 09:12:02,585][23090] Updated weights for policy 0, policy_version 76881 (0.0013) [2023-03-09 09:12:03,534][23090] Updated weights for policy 0, policy_version 76891 (0.0013) [2023-03-09 09:12:04,059][22664] Fps is (10 sec: 194970.5, 60 sec: 198246.7, 300 sec: 198551.8). Total num frames: 1259896832. Throughput: 0: 49546.8. Samples: 314985856. Policy #0 lag: (min: 0.0, avg: 16.8, max: 33.0) [2023-03-09 09:12:04,060][22664] Avg episode reward: [(0, '54.052')] [2023-03-09 09:12:04,365][23090] Updated weights for policy 0, policy_version 76901 (0.0017) [2023-03-09 09:12:04,949][22940] Signal inference workers to stop experience collection... (25450 times) [2023-03-09 09:12:04,953][22940] Signal inference workers to resume experience collection... (25450 times) [2023-03-09 09:12:05,015][23090] InferenceWorker_p0-w0: stopping experience collection (25450 times) [2023-03-09 09:12:05,016][23090] InferenceWorker_p0-w0: resuming experience collection (25450 times) [2023-03-09 09:12:05,176][23090] Updated weights for policy 0, policy_version 76912 (0.0016) [2023-03-09 09:12:06,097][23090] Updated weights for policy 0, policy_version 76922 (0.0013) [2023-03-09 09:12:06,915][23090] Updated weights for policy 0, policy_version 76932 (0.0017) [2023-03-09 09:12:07,696][23090] Updated weights for policy 0, policy_version 76942 (0.0016) [2023-03-09 09:12:08,627][23090] Updated weights for policy 0, policy_version 76953 (0.0016) [2023-03-09 09:12:09,058][22664] Fps is (10 sec: 193333.7, 60 sec: 198247.7, 300 sec: 198552.1). Total num frames: 1260879872. Throughput: 0: 49591.7. Samples: 315284720. Policy #0 lag: (min: 0.0, avg: 16.8, max: 33.0) [2023-03-09 09:12:09,059][22664] Avg episode reward: [(0, '52.703')] [2023-03-09 09:12:09,524][23090] Updated weights for policy 0, policy_version 76964 (0.0016) [2023-03-09 09:12:10,464][23090] Updated weights for policy 0, policy_version 76975 (0.0018) [2023-03-09 09:12:11,276][23090] Updated weights for policy 0, policy_version 76985 (0.0015) [2023-03-09 09:12:12,223][23090] Updated weights for policy 0, policy_version 76995 (0.0017) [2023-03-09 09:12:13,085][23090] Updated weights for policy 0, policy_version 77005 (0.0013) [2023-03-09 09:12:13,972][23090] Updated weights for policy 0, policy_version 77015 (0.0016) [2023-03-09 09:12:14,059][22664] Fps is (10 sec: 194965.2, 60 sec: 197971.6, 300 sec: 198440.7). Total num frames: 1261846528. Throughput: 0: 49545.6. Samples: 315432144. Policy #0 lag: (min: 0.0, avg: 16.8, max: 33.0) [2023-03-09 09:12:14,061][22664] Avg episode reward: [(0, '53.539')] [2023-03-09 09:12:14,715][23090] Updated weights for policy 0, policy_version 77025 (0.0016) [2023-03-09 09:12:15,266][22940] Signal inference workers to stop experience collection... (25500 times) [2023-03-09 09:12:15,288][22940] Signal inference workers to resume experience collection... (25500 times) [2023-03-09 09:12:15,332][23090] InferenceWorker_p0-w0: stopping experience collection (25500 times) [2023-03-09 09:12:15,332][23090] InferenceWorker_p0-w0: resuming experience collection (25500 times) [2023-03-09 09:12:15,495][23090] Updated weights for policy 0, policy_version 77035 (0.0020) [2023-03-09 09:12:16,450][23090] Updated weights for policy 0, policy_version 77045 (0.0018) [2023-03-09 09:12:17,205][23090] Updated weights for policy 0, policy_version 77055 (0.0018) [2023-03-09 09:12:18,049][23090] Updated weights for policy 0, policy_version 77065 (0.0018) [2023-03-09 09:12:18,942][23090] Updated weights for policy 0, policy_version 77075 (0.0016) [2023-03-09 09:12:19,058][22664] Fps is (10 sec: 193331.8, 60 sec: 197427.6, 300 sec: 198385.7). Total num frames: 1262813184. Throughput: 0: 49368.7. Samples: 315722912. Policy #0 lag: (min: 0.0, avg: 16.8, max: 33.0) [2023-03-09 09:12:19,059][22664] Avg episode reward: [(0, '53.672')] [2023-03-09 09:12:19,685][23090] Updated weights for policy 0, policy_version 77085 (0.0018) [2023-03-09 09:12:20,530][23090] Updated weights for policy 0, policy_version 77095 (0.0018) [2023-03-09 09:12:21,262][23090] Updated weights for policy 0, policy_version 77105 (0.0017) [2023-03-09 09:12:22,259][23090] Updated weights for policy 0, policy_version 77115 (0.0018) [2023-03-09 09:12:23,053][23090] Updated weights for policy 0, policy_version 77125 (0.0018) [2023-03-09 09:12:23,874][23090] Updated weights for policy 0, policy_version 77136 (0.0015) [2023-03-09 09:12:24,059][22664] Fps is (10 sec: 198250.2, 60 sec: 197700.1, 300 sec: 198440.6). Total num frames: 1263828992. Throughput: 0: 49277.2. Samples: 316019792. Policy #0 lag: (min: 0.0, avg: 16.8, max: 33.0) [2023-03-09 09:12:24,061][22664] Avg episode reward: [(0, '51.418')] [2023-03-09 09:12:24,776][23090] Updated weights for policy 0, policy_version 77146 (0.0017) [2023-03-09 09:12:24,867][22940] Signal inference workers to stop experience collection... (25550 times) [2023-03-09 09:12:24,868][22940] Signal inference workers to resume experience collection... (25550 times) [2023-03-09 09:12:24,936][23090] InferenceWorker_p0-w0: stopping experience collection (25550 times) [2023-03-09 09:12:24,936][23090] InferenceWorker_p0-w0: resuming experience collection (25550 times) [2023-03-09 09:12:25,546][23090] Updated weights for policy 0, policy_version 77156 (0.0013) [2023-03-09 09:12:26,409][23090] Updated weights for policy 0, policy_version 77166 (0.0023) [2023-03-09 09:12:27,207][23090] Updated weights for policy 0, policy_version 77176 (0.0019) [2023-03-09 09:12:28,022][23090] Updated weights for policy 0, policy_version 77186 (0.0013) [2023-03-09 09:12:28,900][23090] Updated weights for policy 0, policy_version 77196 (0.0016) [2023-03-09 09:12:29,058][22664] Fps is (10 sec: 201523.1, 60 sec: 197973.9, 300 sec: 198496.3). Total num frames: 1264828416. Throughput: 0: 49277.3. Samples: 316169216. Policy #0 lag: (min: 1.0, avg: 17.2, max: 33.0) [2023-03-09 09:12:29,059][22664] Avg episode reward: [(0, '52.148')] [2023-03-09 09:12:29,734][23090] Updated weights for policy 0, policy_version 77206 (0.0019) [2023-03-09 09:12:30,471][23090] Updated weights for policy 0, policy_version 77216 (0.0022) [2023-03-09 09:12:31,282][23090] Updated weights for policy 0, policy_version 77226 (0.0013) [2023-03-09 09:12:32,241][23090] Updated weights for policy 0, policy_version 77236 (0.0017) [2023-03-09 09:12:32,939][23090] Updated weights for policy 0, policy_version 77246 (0.0015) [2023-03-09 09:12:33,807][23090] Updated weights for policy 0, policy_version 77256 (0.0015) [2023-03-09 09:12:34,059][22664] Fps is (10 sec: 198248.0, 60 sec: 197700.1, 300 sec: 198496.5). Total num frames: 1265811456. Throughput: 0: 49277.0. Samples: 316468128. Policy #0 lag: (min: 1.0, avg: 17.2, max: 33.0) [2023-03-09 09:12:34,061][22664] Avg episode reward: [(0, '54.211')] [2023-03-09 09:12:34,590][23090] Updated weights for policy 0, policy_version 77266 (0.0023) [2023-03-09 09:12:34,921][22940] Signal inference workers to stop experience collection... (25600 times) [2023-03-09 09:12:34,922][22940] Signal inference workers to resume experience collection... (25600 times) [2023-03-09 09:12:34,988][23090] InferenceWorker_p0-w0: stopping experience collection (25600 times) [2023-03-09 09:12:34,991][23090] InferenceWorker_p0-w0: resuming experience collection (25600 times) [2023-03-09 09:12:35,451][23090] Updated weights for policy 0, policy_version 77276 (0.0013) [2023-03-09 09:12:36,266][23090] Updated weights for policy 0, policy_version 77286 (0.0018) [2023-03-09 09:12:37,037][23090] Updated weights for policy 0, policy_version 77296 (0.0016) [2023-03-09 09:12:37,944][23090] Updated weights for policy 0, policy_version 77306 (0.0021) [2023-03-09 09:12:38,756][23090] Updated weights for policy 0, policy_version 77316 (0.0023) [2023-03-09 09:12:39,059][22664] Fps is (10 sec: 198244.7, 60 sec: 197974.2, 300 sec: 198496.4). Total num frames: 1266810880. Throughput: 0: 49229.0. Samples: 316764896. Policy #0 lag: (min: 1.0, avg: 17.2, max: 33.0) [2023-03-09 09:12:39,060][22664] Avg episode reward: [(0, '54.577')] [2023-03-09 09:12:39,637][23090] Updated weights for policy 0, policy_version 77327 (0.0015) [2023-03-09 09:12:40,479][23090] Updated weights for policy 0, policy_version 77337 (0.0016) [2023-03-09 09:12:41,286][23090] Updated weights for policy 0, policy_version 77347 (0.0016) [2023-03-09 09:12:42,133][23090] Updated weights for policy 0, policy_version 77357 (0.0021) [2023-03-09 09:12:42,954][23090] Updated weights for policy 0, policy_version 77367 (0.0013) [2023-03-09 09:12:43,734][23090] Updated weights for policy 0, policy_version 77377 (0.0013) [2023-03-09 09:12:44,058][22664] Fps is (10 sec: 199889.9, 60 sec: 197700.7, 300 sec: 198496.4). Total num frames: 1267810304. Throughput: 0: 49230.4. Samples: 316914384. Policy #0 lag: (min: 1.0, avg: 17.2, max: 33.0) [2023-03-09 09:12:44,060][22664] Avg episode reward: [(0, '53.115')] [2023-03-09 09:12:44,557][23090] Updated weights for policy 0, policy_version 77387 (0.0018) [2023-03-09 09:12:45,470][23090] Updated weights for policy 0, policy_version 77397 (0.0017) [2023-03-09 09:12:45,986][22940] Signal inference workers to stop experience collection... (25650 times) [2023-03-09 09:12:46,008][22940] Signal inference workers to resume experience collection... (25650 times) [2023-03-09 09:12:46,057][23090] InferenceWorker_p0-w0: stopping experience collection (25650 times) [2023-03-09 09:12:46,057][23090] InferenceWorker_p0-w0: resuming experience collection (25650 times) [2023-03-09 09:12:46,221][23090] Updated weights for policy 0, policy_version 77407 (0.0016) [2023-03-09 09:12:47,102][23090] Updated weights for policy 0, policy_version 77417 (0.0013) [2023-03-09 09:12:48,022][23090] Updated weights for policy 0, policy_version 77427 (0.0018) [2023-03-09 09:12:48,676][23090] Updated weights for policy 0, policy_version 77437 (0.0019) [2023-03-09 09:12:49,059][22664] Fps is (10 sec: 198243.7, 60 sec: 197699.9, 300 sec: 198496.4). Total num frames: 1268793344. Throughput: 0: 49497.3. Samples: 317213232. Policy #0 lag: (min: 1.0, avg: 17.2, max: 33.0) [2023-03-09 09:12:49,060][22664] Avg episode reward: [(0, '52.056')] [2023-03-09 09:12:49,563][23090] Updated weights for policy 0, policy_version 77447 (0.0013) [2023-03-09 09:12:50,260][23090] Updated weights for policy 0, policy_version 77457 (0.0017) [2023-03-09 09:12:51,215][23090] Updated weights for policy 0, policy_version 77467 (0.0020) [2023-03-09 09:12:51,994][23090] Updated weights for policy 0, policy_version 77477 (0.0016) [2023-03-09 09:12:52,872][23090] Updated weights for policy 0, policy_version 77488 (0.0016) [2023-03-09 09:12:53,793][23090] Updated weights for policy 0, policy_version 77498 (0.0024) [2023-03-09 09:12:54,058][22664] Fps is (10 sec: 198246.3, 60 sec: 197428.3, 300 sec: 198440.8). Total num frames: 1269792768. Throughput: 0: 49453.2. Samples: 317510112. Policy #0 lag: (min: 1.0, avg: 17.2, max: 33.0) [2023-03-09 09:12:54,059][22664] Avg episode reward: [(0, '52.730')] [2023-03-09 09:12:54,609][23090] Updated weights for policy 0, policy_version 77508 (0.0022) [2023-03-09 09:12:55,434][23090] Updated weights for policy 0, policy_version 77518 (0.0016) [2023-03-09 09:12:56,265][23090] Updated weights for policy 0, policy_version 77528 (0.0014) [2023-03-09 09:12:57,020][23090] Updated weights for policy 0, policy_version 77538 (0.0016) [2023-03-09 09:12:57,506][22940] Signal inference workers to stop experience collection... (25700 times) [2023-03-09 09:12:57,529][22940] Signal inference workers to resume experience collection... (25700 times) [2023-03-09 09:12:57,607][23090] InferenceWorker_p0-w0: stopping experience collection (25700 times) [2023-03-09 09:12:57,608][23090] InferenceWorker_p0-w0: resuming experience collection (25700 times) [2023-03-09 09:12:57,921][23090] Updated weights for policy 0, policy_version 77548 (0.0022) [2023-03-09 09:12:58,727][23090] Updated weights for policy 0, policy_version 77558 (0.0017) [2023-03-09 09:12:59,059][22664] Fps is (10 sec: 198245.2, 60 sec: 197153.7, 300 sec: 198496.2). Total num frames: 1270775808. Throughput: 0: 49497.8. Samples: 317659536. Policy #0 lag: (min: 1.0, avg: 17.2, max: 33.0) [2023-03-09 09:12:59,060][22664] Avg episode reward: [(0, '52.101')] [2023-03-09 09:12:59,490][23090] Updated weights for policy 0, policy_version 77568 (0.0013) [2023-03-09 09:13:00,302][23090] Updated weights for policy 0, policy_version 77578 (0.0013) [2023-03-09 09:13:01,232][23090] Updated weights for policy 0, policy_version 77588 (0.0013) [2023-03-09 09:13:01,944][23090] Updated weights for policy 0, policy_version 77598 (0.0013) [2023-03-09 09:13:02,820][23090] Updated weights for policy 0, policy_version 77608 (0.0025) [2023-03-09 09:13:03,573][23090] Updated weights for policy 0, policy_version 77618 (0.0013) [2023-03-09 09:13:04,058][22664] Fps is (10 sec: 198245.7, 60 sec: 197974.2, 300 sec: 198441.0). Total num frames: 1271775232. Throughput: 0: 49676.8. Samples: 317958368. Policy #0 lag: (min: 1.0, avg: 17.2, max: 33.0) [2023-03-09 09:13:04,059][22664] Avg episode reward: [(0, '57.272')] [2023-03-09 09:13:04,060][22940] Saving new best policy, reward=57.272! [2023-03-09 09:13:04,494][23090] Updated weights for policy 0, policy_version 77628 (0.0013) [2023-03-09 09:13:05,251][23090] Updated weights for policy 0, policy_version 77638 (0.0016) [2023-03-09 09:13:06,070][23090] Updated weights for policy 0, policy_version 77648 (0.0016) [2023-03-09 09:13:07,048][22940] Signal inference workers to stop experience collection... (25750 times) [2023-03-09 09:13:07,049][22940] Signal inference workers to resume experience collection... (25750 times) [2023-03-09 09:13:07,076][23090] Updated weights for policy 0, policy_version 77659 (0.0019) [2023-03-09 09:13:07,113][23090] InferenceWorker_p0-w0: stopping experience collection (25750 times) [2023-03-09 09:13:07,114][23090] InferenceWorker_p0-w0: resuming experience collection (25750 times) [2023-03-09 09:13:07,901][23090] Updated weights for policy 0, policy_version 77669 (0.0018) [2023-03-09 09:13:08,696][23090] Updated weights for policy 0, policy_version 77679 (0.0021) [2023-03-09 09:13:09,059][22664] Fps is (10 sec: 196605.9, 60 sec: 197699.1, 300 sec: 198385.0). Total num frames: 1272741888. Throughput: 0: 49676.0. Samples: 318255216. Policy #0 lag: (min: 1.0, avg: 17.2, max: 33.0) [2023-03-09 09:13:09,061][22664] Avg episode reward: [(0, '54.563')] [2023-03-09 09:13:09,502][23090] Updated weights for policy 0, policy_version 77689 (0.0016) [2023-03-09 09:13:10,283][23090] Updated weights for policy 0, policy_version 77699 (0.0013) [2023-03-09 09:13:11,196][23090] Updated weights for policy 0, policy_version 77709 (0.0017) [2023-03-09 09:13:11,984][23090] Updated weights for policy 0, policy_version 77719 (0.0025) [2023-03-09 09:13:12,811][23090] Updated weights for policy 0, policy_version 77729 (0.0012) [2023-03-09 09:13:13,613][23090] Updated weights for policy 0, policy_version 77739 (0.0013) [2023-03-09 09:13:14,058][22664] Fps is (10 sec: 199885.2, 60 sec: 198794.2, 300 sec: 198496.8). Total num frames: 1273774080. Throughput: 0: 49675.4. Samples: 318404608. Policy #0 lag: (min: 1.0, avg: 17.2, max: 33.0) [2023-03-09 09:13:14,059][22664] Avg episode reward: [(0, '55.841')] [2023-03-09 09:13:14,505][23090] Updated weights for policy 0, policy_version 77749 (0.0015) [2023-03-09 09:13:15,231][23090] Updated weights for policy 0, policy_version 77759 (0.0013) [2023-03-09 09:13:16,082][23090] Updated weights for policy 0, policy_version 77769 (0.0012) [2023-03-09 09:13:17,037][23090] Updated weights for policy 0, policy_version 77779 (0.0013) [2023-03-09 09:13:17,731][23090] Updated weights for policy 0, policy_version 77789 (0.0019) [2023-03-09 09:13:18,571][22940] Signal inference workers to stop experience collection... (25800 times) [2023-03-09 09:13:18,585][22940] Signal inference workers to resume experience collection... (25800 times) [2023-03-09 09:13:18,608][23090] Updated weights for policy 0, policy_version 77799 (0.0022) [2023-03-09 09:13:18,651][23090] InferenceWorker_p0-w0: stopping experience collection (25800 times) [2023-03-09 09:13:18,651][23090] InferenceWorker_p0-w0: resuming experience collection (25800 times) [2023-03-09 09:13:19,059][22664] Fps is (10 sec: 199884.9, 60 sec: 198791.2, 300 sec: 198385.2). Total num frames: 1274740736. Throughput: 0: 49674.1. Samples: 318703472. Policy #0 lag: (min: 2.0, avg: 17.1, max: 34.0) [2023-03-09 09:13:19,061][22664] Avg episode reward: [(0, '53.160')] [2023-03-09 09:13:19,140][22940] Saving /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000077806_1274773504.pth... [2023-03-09 09:13:19,206][22940] Removing /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000074899_1227145216.pth [2023-03-09 09:13:19,378][23090] Updated weights for policy 0, policy_version 77809 (0.0022) [2023-03-09 09:13:20,244][23090] Updated weights for policy 0, policy_version 77819 (0.0013) [2023-03-09 09:13:21,016][23090] Updated weights for policy 0, policy_version 77829 (0.0021) [2023-03-09 09:13:21,833][23090] Updated weights for policy 0, policy_version 77839 (0.0013) [2023-03-09 09:13:22,684][23090] Updated weights for policy 0, policy_version 77849 (0.0018) [2023-03-09 09:13:23,432][23090] Updated weights for policy 0, policy_version 77859 (0.0013) [2023-03-09 09:13:24,059][22664] Fps is (10 sec: 198241.6, 60 sec: 198792.8, 300 sec: 198551.8). Total num frames: 1275756544. Throughput: 0: 49721.4. Samples: 319002368. Policy #0 lag: (min: 2.0, avg: 17.1, max: 34.0) [2023-03-09 09:13:24,061][22664] Avg episode reward: [(0, '52.558')] [2023-03-09 09:13:24,357][23090] Updated weights for policy 0, policy_version 77869 (0.0013) [2023-03-09 09:13:25,212][23090] Updated weights for policy 0, policy_version 77879 (0.0018) [2023-03-09 09:13:25,897][23090] Updated weights for policy 0, policy_version 77889 (0.0015) [2023-03-09 09:13:26,788][23090] Updated weights for policy 0, policy_version 77899 (0.0015) [2023-03-09 09:13:27,531][22940] Signal inference workers to stop experience collection... (25850 times) [2023-03-09 09:13:27,543][22940] Signal inference workers to resume experience collection... (25850 times) [2023-03-09 09:13:27,613][23090] InferenceWorker_p0-w0: stopping experience collection (25850 times) [2023-03-09 09:13:27,614][23090] InferenceWorker_p0-w0: resuming experience collection (25850 times) [2023-03-09 09:13:27,773][23090] Updated weights for policy 0, policy_version 77910 (0.0024) [2023-03-09 09:13:28,471][23090] Updated weights for policy 0, policy_version 77920 (0.0013) [2023-03-09 09:13:29,058][22664] Fps is (10 sec: 199892.1, 60 sec: 198519.4, 300 sec: 198440.8). Total num frames: 1276739584. Throughput: 0: 49721.2. Samples: 319151840. Policy #0 lag: (min: 2.0, avg: 17.1, max: 34.0) [2023-03-09 09:13:29,060][22664] Avg episode reward: [(0, '52.251')] [2023-03-09 09:13:29,280][23090] Updated weights for policy 0, policy_version 77930 (0.0021) [2023-03-09 09:13:30,234][23090] Updated weights for policy 0, policy_version 77940 (0.0013) [2023-03-09 09:13:30,942][23090] Updated weights for policy 0, policy_version 77950 (0.0016) [2023-03-09 09:13:31,821][23090] Updated weights for policy 0, policy_version 77960 (0.0018) [2023-03-09 09:13:32,591][23090] Updated weights for policy 0, policy_version 77970 (0.0013) [2023-03-09 09:13:33,464][23090] Updated weights for policy 0, policy_version 77980 (0.0020) [2023-03-09 09:13:34,058][22664] Fps is (10 sec: 198250.5, 60 sec: 198793.2, 300 sec: 198496.5). Total num frames: 1277739008. Throughput: 0: 49677.7. Samples: 319448720. Policy #0 lag: (min: 2.0, avg: 17.1, max: 34.0) [2023-03-09 09:13:34,059][22664] Avg episode reward: [(0, '53.470')] [2023-03-09 09:13:34,357][23090] Updated weights for policy 0, policy_version 77990 (0.0017) [2023-03-09 09:13:35,088][23090] Updated weights for policy 0, policy_version 78000 (0.0013) [2023-03-09 09:13:35,997][23090] Updated weights for policy 0, policy_version 78010 (0.0020) [2023-03-09 09:13:36,776][23090] Updated weights for policy 0, policy_version 78020 (0.0013) [2023-03-09 09:13:37,624][23090] Updated weights for policy 0, policy_version 78030 (0.0022) [2023-03-09 09:13:37,716][22940] Signal inference workers to stop experience collection... (25900 times) [2023-03-09 09:13:37,737][22940] Signal inference workers to resume experience collection... (25900 times) [2023-03-09 09:13:37,787][23090] InferenceWorker_p0-w0: stopping experience collection (25900 times) [2023-03-09 09:13:37,787][23090] InferenceWorker_p0-w0: resuming experience collection (25900 times) [2023-03-09 09:13:38,430][23090] Updated weights for policy 0, policy_version 78040 (0.0016) [2023-03-09 09:13:39,059][22664] Fps is (10 sec: 199879.3, 60 sec: 198791.8, 300 sec: 198440.6). Total num frames: 1278738432. Throughput: 0: 49677.2. Samples: 319745600. Policy #0 lag: (min: 2.0, avg: 17.1, max: 34.0) [2023-03-09 09:13:39,061][22664] Avg episode reward: [(0, '54.299')] [2023-03-09 09:13:39,204][23090] Updated weights for policy 0, policy_version 78050 (0.0016) [2023-03-09 09:13:40,119][23090] Updated weights for policy 0, policy_version 78060 (0.0013) [2023-03-09 09:13:40,995][23090] Updated weights for policy 0, policy_version 78070 (0.0013) [2023-03-09 09:13:41,785][23090] Updated weights for policy 0, policy_version 78081 (0.0016) [2023-03-09 09:13:42,641][23090] Updated weights for policy 0, policy_version 78091 (0.0014) [2023-03-09 09:13:43,632][23090] Updated weights for policy 0, policy_version 78102 (0.0018) [2023-03-09 09:13:44,059][22664] Fps is (10 sec: 198240.7, 60 sec: 198518.3, 300 sec: 198440.8). Total num frames: 1279721472. Throughput: 0: 49679.3. Samples: 319895104. Policy #0 lag: (min: 2.0, avg: 17.1, max: 34.0) [2023-03-09 09:13:44,061][22664] Avg episode reward: [(0, '52.644')] [2023-03-09 09:13:44,338][23090] Updated weights for policy 0, policy_version 78112 (0.0017) [2023-03-09 09:13:45,147][23090] Updated weights for policy 0, policy_version 78122 (0.0013) [2023-03-09 09:13:46,178][23090] Updated weights for policy 0, policy_version 78133 (0.0013) [2023-03-09 09:13:46,880][23090] Updated weights for policy 0, policy_version 78143 (0.0013) [2023-03-09 09:13:47,710][23090] Updated weights for policy 0, policy_version 78153 (0.0013) [2023-03-09 09:13:48,242][22940] Signal inference workers to stop experience collection... (25950 times) [2023-03-09 09:13:48,257][22940] Signal inference workers to resume experience collection... (25950 times) [2023-03-09 09:13:48,318][23090] InferenceWorker_p0-w0: stopping experience collection (25950 times) [2023-03-09 09:13:48,318][23090] InferenceWorker_p0-w0: resuming experience collection (25950 times) [2023-03-09 09:13:48,638][23090] Updated weights for policy 0, policy_version 78163 (0.0013) [2023-03-09 09:13:49,059][22664] Fps is (10 sec: 198244.5, 60 sec: 198792.0, 300 sec: 198440.7). Total num frames: 1280720896. Throughput: 0: 49680.3. Samples: 320194000. Policy #0 lag: (min: 2.0, avg: 17.1, max: 34.0) [2023-03-09 09:13:49,061][22664] Avg episode reward: [(0, '52.308')] [2023-03-09 09:13:49,390][23090] Updated weights for policy 0, policy_version 78173 (0.0013) [2023-03-09 09:13:50,254][23090] Updated weights for policy 0, policy_version 78183 (0.0013) [2023-03-09 09:13:50,981][23090] Updated weights for policy 0, policy_version 78193 (0.0028) [2023-03-09 09:13:51,906][23090] Updated weights for policy 0, policy_version 78203 (0.0025) [2023-03-09 09:13:52,721][23090] Updated weights for policy 0, policy_version 78213 (0.0018) [2023-03-09 09:13:53,535][23090] Updated weights for policy 0, policy_version 78223 (0.0019) [2023-03-09 09:13:54,059][22664] Fps is (10 sec: 196608.0, 60 sec: 198245.3, 300 sec: 198385.1). Total num frames: 1281687552. Throughput: 0: 49681.2. Samples: 320490864. Policy #0 lag: (min: 2.0, avg: 17.1, max: 34.0) [2023-03-09 09:13:54,061][22664] Avg episode reward: [(0, '56.212')] [2023-03-09 09:13:54,350][23090] Updated weights for policy 0, policy_version 78233 (0.0016) [2023-03-09 09:13:55,156][23090] Updated weights for policy 0, policy_version 78243 (0.0017) [2023-03-09 09:13:56,044][23090] Updated weights for policy 0, policy_version 78253 (0.0020) [2023-03-09 09:13:56,971][23090] Updated weights for policy 0, policy_version 78264 (0.0018) [2023-03-09 09:13:57,716][23090] Updated weights for policy 0, policy_version 78274 (0.0014) [2023-03-09 09:13:58,658][23090] Updated weights for policy 0, policy_version 78284 (0.0016) [2023-03-09 09:13:59,059][22664] Fps is (10 sec: 198252.6, 60 sec: 198793.2, 300 sec: 198440.9). Total num frames: 1282703360. Throughput: 0: 49636.9. Samples: 320638272. Policy #0 lag: (min: 2.0, avg: 17.1, max: 34.0) [2023-03-09 09:13:59,060][22664] Avg episode reward: [(0, '53.116')] [2023-03-09 09:13:59,512][23090] Updated weights for policy 0, policy_version 78294 (0.0016) [2023-03-09 09:13:59,595][22940] Signal inference workers to stop experience collection... (26000 times) [2023-03-09 09:13:59,599][22940] Signal inference workers to resume experience collection... (26000 times) [2023-03-09 09:13:59,676][23090] InferenceWorker_p0-w0: stopping experience collection (26000 times) [2023-03-09 09:13:59,676][23090] InferenceWorker_p0-w0: resuming experience collection (26000 times) [2023-03-09 09:14:00,282][23090] Updated weights for policy 0, policy_version 78305 (0.0020) [2023-03-09 09:14:01,137][23090] Updated weights for policy 0, policy_version 78315 (0.0019) [2023-03-09 09:14:02,098][23090] Updated weights for policy 0, policy_version 78325 (0.0021) [2023-03-09 09:14:02,761][23090] Updated weights for policy 0, policy_version 78335 (0.0019) [2023-03-09 09:14:03,606][23090] Updated weights for policy 0, policy_version 78345 (0.0017) [2023-03-09 09:14:04,058][22664] Fps is (10 sec: 201529.7, 60 sec: 198792.6, 300 sec: 198496.5). Total num frames: 1283702784. Throughput: 0: 49591.9. Samples: 320935088. Policy #0 lag: (min: 1.0, avg: 16.8, max: 33.0) [2023-03-09 09:14:04,060][22664] Avg episode reward: [(0, '55.557')] [2023-03-09 09:14:04,493][23090] Updated weights for policy 0, policy_version 78355 (0.0018) [2023-03-09 09:14:05,238][23090] Updated weights for policy 0, policy_version 78365 (0.0013) [2023-03-09 09:14:06,093][23090] Updated weights for policy 0, policy_version 78375 (0.0013) [2023-03-09 09:14:06,831][23090] Updated weights for policy 0, policy_version 78385 (0.0016) [2023-03-09 09:14:07,797][23090] Updated weights for policy 0, policy_version 78395 (0.0023) [2023-03-09 09:14:08,603][23090] Updated weights for policy 0, policy_version 78405 (0.0022) [2023-03-09 09:14:09,059][22664] Fps is (10 sec: 198238.8, 60 sec: 199065.4, 300 sec: 198440.5). Total num frames: 1284685824. Throughput: 0: 49591.6. Samples: 321234000. Policy #0 lag: (min: 1.0, avg: 16.8, max: 33.0) [2023-03-09 09:14:09,061][22664] Avg episode reward: [(0, '55.203')] [2023-03-09 09:14:09,373][23090] Updated weights for policy 0, policy_version 78415 (0.0022) [2023-03-09 09:14:10,221][23090] Updated weights for policy 0, policy_version 78425 (0.0013) [2023-03-09 09:14:10,985][23090] Updated weights for policy 0, policy_version 78435 (0.0016) [2023-03-09 09:14:11,877][22940] Signal inference workers to stop experience collection... (26050 times) [2023-03-09 09:14:11,898][22940] Signal inference workers to resume experience collection... (26050 times) [2023-03-09 09:14:11,902][23090] Updated weights for policy 0, policy_version 78445 (0.0017) [2023-03-09 09:14:11,943][23090] InferenceWorker_p0-w0: stopping experience collection (26050 times) [2023-03-09 09:14:11,943][23090] InferenceWorker_p0-w0: resuming experience collection (26050 times) [2023-03-09 09:14:12,760][23090] Updated weights for policy 0, policy_version 78455 (0.0016) [2023-03-09 09:14:13,458][23090] Updated weights for policy 0, policy_version 78465 (0.0015) [2023-03-09 09:14:14,059][22664] Fps is (10 sec: 196600.7, 60 sec: 198245.2, 300 sec: 198440.6). Total num frames: 1285668864. Throughput: 0: 49591.4. Samples: 321383472. Policy #0 lag: (min: 1.0, avg: 16.8, max: 33.0) [2023-03-09 09:14:14,061][22664] Avg episode reward: [(0, '55.827')] [2023-03-09 09:14:14,325][23090] Updated weights for policy 0, policy_version 78475 (0.0013) [2023-03-09 09:14:15,203][23090] Updated weights for policy 0, policy_version 78485 (0.0015) [2023-03-09 09:14:15,904][23090] Updated weights for policy 0, policy_version 78495 (0.0016) [2023-03-09 09:14:16,788][23090] Updated weights for policy 0, policy_version 78505 (0.0020) [2023-03-09 09:14:17,706][23090] Updated weights for policy 0, policy_version 78515 (0.0022) [2023-03-09 09:14:18,461][23090] Updated weights for policy 0, policy_version 78525 (0.0020) [2023-03-09 09:14:19,059][22664] Fps is (10 sec: 198249.4, 60 sec: 198792.8, 300 sec: 198440.6). Total num frames: 1286668288. Throughput: 0: 49636.7. Samples: 321682384. Policy #0 lag: (min: 1.0, avg: 16.8, max: 33.0) [2023-03-09 09:14:19,061][22664] Avg episode reward: [(0, '52.512')] [2023-03-09 09:14:19,308][23090] Updated weights for policy 0, policy_version 78535 (0.0019) [2023-03-09 09:14:20,164][23090] Updated weights for policy 0, policy_version 78546 (0.0029) [2023-03-09 09:14:21,063][23090] Updated weights for policy 0, policy_version 78556 (0.0018) [2023-03-09 09:14:21,880][23090] Updated weights for policy 0, policy_version 78566 (0.0016) [2023-03-09 09:14:22,640][23090] Updated weights for policy 0, policy_version 78576 (0.0016) [2023-03-09 09:14:23,584][23090] Updated weights for policy 0, policy_version 78586 (0.0022) [2023-03-09 09:14:24,035][22940] Signal inference workers to stop experience collection... (26100 times) [2023-03-09 09:14:24,036][22940] Signal inference workers to resume experience collection... (26100 times) [2023-03-09 09:14:24,059][22664] Fps is (10 sec: 198248.0, 60 sec: 198246.3, 300 sec: 198440.8). Total num frames: 1287651328. Throughput: 0: 49591.8. Samples: 321977232. Policy #0 lag: (min: 1.0, avg: 16.8, max: 33.0) [2023-03-09 09:14:24,060][22664] Avg episode reward: [(0, '55.781')] [2023-03-09 09:14:24,097][23090] InferenceWorker_p0-w0: stopping experience collection (26100 times) [2023-03-09 09:14:24,098][23090] InferenceWorker_p0-w0: resuming experience collection (26100 times) [2023-03-09 09:14:24,345][23090] Updated weights for policy 0, policy_version 78596 (0.0013) [2023-03-09 09:14:25,185][23090] Updated weights for policy 0, policy_version 78606 (0.0017) [2023-03-09 09:14:26,028][23090] Updated weights for policy 0, policy_version 78616 (0.0013) [2023-03-09 09:14:26,767][23090] Updated weights for policy 0, policy_version 78626 (0.0014) [2023-03-09 09:14:27,693][23090] Updated weights for policy 0, policy_version 78636 (0.0019) [2023-03-09 09:14:28,527][23090] Updated weights for policy 0, policy_version 78646 (0.0019) [2023-03-09 09:14:29,059][22664] Fps is (10 sec: 198248.2, 60 sec: 198518.8, 300 sec: 198385.5). Total num frames: 1288650752. Throughput: 0: 49589.8. Samples: 322126640. Policy #0 lag: (min: 1.0, avg: 16.8, max: 33.0) [2023-03-09 09:14:29,060][22664] Avg episode reward: [(0, '53.137')] [2023-03-09 09:14:29,299][23090] Updated weights for policy 0, policy_version 78656 (0.0018) [2023-03-09 09:14:30,072][23090] Updated weights for policy 0, policy_version 78666 (0.0022) [2023-03-09 09:14:31,080][23090] Updated weights for policy 0, policy_version 78677 (0.0013) [2023-03-09 09:14:31,950][23090] Updated weights for policy 0, policy_version 78688 (0.0014) [2023-03-09 09:14:32,710][23090] Updated weights for policy 0, policy_version 78698 (0.0013) [2023-03-09 09:14:33,633][23090] Updated weights for policy 0, policy_version 78708 (0.0013) [2023-03-09 09:14:34,058][22664] Fps is (10 sec: 198252.2, 60 sec: 198246.5, 300 sec: 198440.9). Total num frames: 1289633792. Throughput: 0: 49590.1. Samples: 322425536. Policy #0 lag: (min: 1.0, avg: 16.8, max: 33.0) [2023-03-09 09:14:34,059][22664] Avg episode reward: [(0, '53.886')] [2023-03-09 09:14:34,367][23090] Updated weights for policy 0, policy_version 78718 (0.0016) [2023-03-09 09:14:35,232][23090] Updated weights for policy 0, policy_version 78728 (0.0024) [2023-03-09 09:14:36,255][23090] Updated weights for policy 0, policy_version 78739 (0.0018) [2023-03-09 09:14:36,984][23090] Updated weights for policy 0, policy_version 78749 (0.0013) [2023-03-09 09:14:37,236][22940] Signal inference workers to stop experience collection... (26150 times) [2023-03-09 09:14:37,249][22940] Signal inference workers to resume experience collection... (26150 times) [2023-03-09 09:14:37,313][23090] InferenceWorker_p0-w0: stopping experience collection (26150 times) [2023-03-09 09:14:37,313][23090] InferenceWorker_p0-w0: resuming experience collection (26150 times) [2023-03-09 09:14:37,842][23090] Updated weights for policy 0, policy_version 78759 (0.0016) [2023-03-09 09:14:38,556][23090] Updated weights for policy 0, policy_version 78769 (0.0013) [2023-03-09 09:14:39,059][22664] Fps is (10 sec: 196610.2, 60 sec: 197974.0, 300 sec: 198385.2). Total num frames: 1290616832. Throughput: 0: 49590.3. Samples: 322722416. Policy #0 lag: (min: 1.0, avg: 16.8, max: 33.0) [2023-03-09 09:14:39,060][22664] Avg episode reward: [(0, '55.031')] [2023-03-09 09:14:39,526][23090] Updated weights for policy 0, policy_version 78779 (0.0013) [2023-03-09 09:14:40,332][23090] Updated weights for policy 0, policy_version 78789 (0.0019) [2023-03-09 09:14:41,102][23090] Updated weights for policy 0, policy_version 78799 (0.0013) [2023-03-09 09:14:41,982][23090] Updated weights for policy 0, policy_version 78809 (0.0013) [2023-03-09 09:14:42,721][23090] Updated weights for policy 0, policy_version 78819 (0.0013) [2023-03-09 09:14:43,603][23090] Updated weights for policy 0, policy_version 78829 (0.0013) [2023-03-09 09:14:44,059][22664] Fps is (10 sec: 198240.1, 60 sec: 198246.4, 300 sec: 198385.2). Total num frames: 1291616256. Throughput: 0: 49589.8. Samples: 322869824. Policy #0 lag: (min: 1.0, avg: 16.8, max: 33.0) [2023-03-09 09:14:44,060][22664] Avg episode reward: [(0, '54.725')] [2023-03-09 09:14:44,495][23090] Updated weights for policy 0, policy_version 78839 (0.0015) [2023-03-09 09:14:45,202][23090] Updated weights for policy 0, policy_version 78849 (0.0016) [2023-03-09 09:14:46,116][23090] Updated weights for policy 0, policy_version 78859 (0.0015) [2023-03-09 09:14:46,976][23090] Updated weights for policy 0, policy_version 78869 (0.0027) [2023-03-09 09:14:47,701][23090] Updated weights for policy 0, policy_version 78879 (0.0017) [2023-03-09 09:14:48,558][23090] Updated weights for policy 0, policy_version 78889 (0.0014) [2023-03-09 09:14:49,059][22664] Fps is (10 sec: 199872.6, 60 sec: 198245.3, 300 sec: 198440.3). Total num frames: 1292615680. Throughput: 0: 49590.3. Samples: 323166688. Policy #0 lag: (min: 1.0, avg: 16.8, max: 33.0) [2023-03-09 09:14:49,061][22664] Avg episode reward: [(0, '52.864')] [2023-03-09 09:14:49,455][23090] Updated weights for policy 0, policy_version 78899 (0.0013) [2023-03-09 09:14:50,200][23090] Updated weights for policy 0, policy_version 78909 (0.0025) [2023-03-09 09:14:50,441][22940] Signal inference workers to stop experience collection... (26200 times) [2023-03-09 09:14:50,444][22940] Signal inference workers to resume experience collection... (26200 times) [2023-03-09 09:14:50,509][23090] InferenceWorker_p0-w0: stopping experience collection (26200 times) [2023-03-09 09:14:50,512][23090] InferenceWorker_p0-w0: resuming experience collection (26200 times) [2023-03-09 09:14:51,072][23090] Updated weights for policy 0, policy_version 78919 (0.0020) [2023-03-09 09:14:51,810][23090] Updated weights for policy 0, policy_version 78929 (0.0013) [2023-03-09 09:14:52,749][23090] Updated weights for policy 0, policy_version 78939 (0.0018) [2023-03-09 09:14:53,569][23090] Updated weights for policy 0, policy_version 78949 (0.0019) [2023-03-09 09:14:54,059][22664] Fps is (10 sec: 198248.0, 60 sec: 198519.8, 300 sec: 198385.4). Total num frames: 1293598720. Throughput: 0: 49545.9. Samples: 323463552. Policy #0 lag: (min: 1.0, avg: 17.0, max: 33.0) [2023-03-09 09:14:54,060][22664] Avg episode reward: [(0, '52.412')] [2023-03-09 09:14:54,353][23090] Updated weights for policy 0, policy_version 78959 (0.0013) [2023-03-09 09:14:55,315][23090] Updated weights for policy 0, policy_version 78970 (0.0013) [2023-03-09 09:14:56,169][23090] Updated weights for policy 0, policy_version 78980 (0.0016) [2023-03-09 09:14:56,958][23090] Updated weights for policy 0, policy_version 78990 (0.0022) [2023-03-09 09:14:57,767][23090] Updated weights for policy 0, policy_version 79000 (0.0013) [2023-03-09 09:14:58,542][23090] Updated weights for policy 0, policy_version 79010 (0.0017) [2023-03-09 09:14:59,059][22664] Fps is (10 sec: 198254.3, 60 sec: 198245.6, 300 sec: 198440.6). Total num frames: 1294598144. Throughput: 0: 49545.3. Samples: 323613008. Policy #0 lag: (min: 1.0, avg: 17.0, max: 33.0) [2023-03-09 09:14:59,061][22664] Avg episode reward: [(0, '54.197')] [2023-03-09 09:14:59,423][23090] Updated weights for policy 0, policy_version 79020 (0.0016) [2023-03-09 09:15:00,312][23090] Updated weights for policy 0, policy_version 79030 (0.0013) [2023-03-09 09:15:01,067][23090] Updated weights for policy 0, policy_version 79040 (0.0013) [2023-03-09 09:15:01,895][23090] Updated weights for policy 0, policy_version 79050 (0.0019) [2023-03-09 09:15:02,794][23090] Updated weights for policy 0, policy_version 79060 (0.0016) [2023-03-09 09:15:03,340][22940] Signal inference workers to stop experience collection... (26250 times) [2023-03-09 09:15:03,344][22940] Signal inference workers to resume experience collection... (26250 times) [2023-03-09 09:15:03,407][23090] InferenceWorker_p0-w0: stopping experience collection (26250 times) [2023-03-09 09:15:03,408][23090] InferenceWorker_p0-w0: resuming experience collection (26250 times) [2023-03-09 09:15:03,533][23090] Updated weights for policy 0, policy_version 79070 (0.0013) [2023-03-09 09:15:04,059][22664] Fps is (10 sec: 196611.4, 60 sec: 197700.1, 300 sec: 198274.5). Total num frames: 1295564800. Throughput: 0: 49500.4. Samples: 323909888. Policy #0 lag: (min: 1.0, avg: 17.0, max: 33.0) [2023-03-09 09:15:04,060][22664] Avg episode reward: [(0, '55.944')] [2023-03-09 09:15:04,360][23090] Updated weights for policy 0, policy_version 79080 (0.0017) [2023-03-09 09:15:05,155][23090] Updated weights for policy 0, policy_version 79090 (0.0016) [2023-03-09 09:15:06,050][23090] Updated weights for policy 0, policy_version 79100 (0.0016) [2023-03-09 09:15:06,892][23090] Updated weights for policy 0, policy_version 79110 (0.0021) [2023-03-09 09:15:07,777][23090] Updated weights for policy 0, policy_version 79122 (0.0016) [2023-03-09 09:15:08,694][23090] Updated weights for policy 0, policy_version 79132 (0.0013) [2023-03-09 09:15:09,058][22664] Fps is (10 sec: 198252.6, 60 sec: 198247.9, 300 sec: 198440.8). Total num frames: 1296580608. Throughput: 0: 49545.2. Samples: 324206752. Policy #0 lag: (min: 1.0, avg: 17.0, max: 33.0) [2023-03-09 09:15:09,059][22664] Avg episode reward: [(0, '54.682')] [2023-03-09 09:15:09,555][23090] Updated weights for policy 0, policy_version 79142 (0.0014) [2023-03-09 09:15:10,360][23090] Updated weights for policy 0, policy_version 79153 (0.0016) [2023-03-09 09:15:11,286][23090] Updated weights for policy 0, policy_version 79163 (0.0029) [2023-03-09 09:15:12,127][23090] Updated weights for policy 0, policy_version 79173 (0.0016) [2023-03-09 09:15:12,852][23090] Updated weights for policy 0, policy_version 79183 (0.0013) [2023-03-09 09:15:13,726][23090] Updated weights for policy 0, policy_version 79193 (0.0017) [2023-03-09 09:15:14,059][22664] Fps is (10 sec: 199879.9, 60 sec: 198246.6, 300 sec: 198274.0). Total num frames: 1297563648. Throughput: 0: 49500.7. Samples: 324354176. Policy #0 lag: (min: 1.0, avg: 17.0, max: 33.0) [2023-03-09 09:15:14,061][22664] Avg episode reward: [(0, '52.833')] [2023-03-09 09:15:14,474][23090] Updated weights for policy 0, policy_version 79203 (0.0013) [2023-03-09 09:15:15,375][23090] Updated weights for policy 0, policy_version 79213 (0.0018) [2023-03-09 09:15:16,225][23090] Updated weights for policy 0, policy_version 79223 (0.0013) [2023-03-09 09:15:16,956][23090] Updated weights for policy 0, policy_version 79233 (0.0016) [2023-03-09 09:15:17,918][23090] Updated weights for policy 0, policy_version 79244 (0.0013) [2023-03-09 09:15:17,988][22940] Signal inference workers to stop experience collection... (26300 times) [2023-03-09 09:15:18,004][22940] Signal inference workers to resume experience collection... (26300 times) [2023-03-09 09:15:18,036][23090] InferenceWorker_p0-w0: stopping experience collection (26300 times) [2023-03-09 09:15:18,082][23090] InferenceWorker_p0-w0: resuming experience collection (26300 times) [2023-03-09 09:15:18,828][23090] Updated weights for policy 0, policy_version 79254 (0.0013) [2023-03-09 09:15:19,059][22664] Fps is (10 sec: 196606.2, 60 sec: 197974.0, 300 sec: 198274.3). Total num frames: 1298546688. Throughput: 0: 49547.2. Samples: 324655168. Policy #0 lag: (min: 1.0, avg: 17.0, max: 33.0) [2023-03-09 09:15:19,060][22664] Avg episode reward: [(0, '52.741')] [2023-03-09 09:15:19,070][22940] Saving /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000079258_1298563072.pth... [2023-03-09 09:15:19,167][22940] Removing /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000076354_1250983936.pth [2023-03-09 09:15:19,551][23090] Updated weights for policy 0, policy_version 79264 (0.0013) [2023-03-09 09:15:20,387][23090] Updated weights for policy 0, policy_version 79274 (0.0018) [2023-03-09 09:15:21,283][23090] Updated weights for policy 0, policy_version 79284 (0.0023) [2023-03-09 09:15:22,018][23090] Updated weights for policy 0, policy_version 79294 (0.0016) [2023-03-09 09:15:22,855][23090] Updated weights for policy 0, policy_version 79304 (0.0013) [2023-03-09 09:15:23,661][23090] Updated weights for policy 0, policy_version 79314 (0.0021) [2023-03-09 09:15:24,059][22664] Fps is (10 sec: 196607.4, 60 sec: 197973.2, 300 sec: 198274.2). Total num frames: 1299529728. Throughput: 0: 49501.3. Samples: 324949984. Policy #0 lag: (min: 1.0, avg: 17.0, max: 33.0) [2023-03-09 09:15:24,061][22664] Avg episode reward: [(0, '54.498')] [2023-03-09 09:15:24,550][23090] Updated weights for policy 0, policy_version 79324 (0.0013) [2023-03-09 09:15:25,432][23090] Updated weights for policy 0, policy_version 79335 (0.0016) [2023-03-09 09:15:26,201][23090] Updated weights for policy 0, policy_version 79345 (0.0013) [2023-03-09 09:15:27,167][23090] Updated weights for policy 0, policy_version 79355 (0.0016) [2023-03-09 09:15:27,980][23090] Updated weights for policy 0, policy_version 79365 (0.0020) [2023-03-09 09:15:28,768][23090] Updated weights for policy 0, policy_version 79376 (0.0012) [2023-03-09 09:15:29,059][22664] Fps is (10 sec: 198244.7, 60 sec: 197973.4, 300 sec: 198274.2). Total num frames: 1300529152. Throughput: 0: 49502.0. Samples: 325097408. Policy #0 lag: (min: 1.0, avg: 17.0, max: 33.0) [2023-03-09 09:15:29,060][22664] Avg episode reward: [(0, '52.854')] [2023-03-09 09:15:29,733][23090] Updated weights for policy 0, policy_version 79386 (0.0013) [2023-03-09 09:15:30,529][23090] Updated weights for policy 0, policy_version 79396 (0.0020) [2023-03-09 09:15:31,074][22940] Signal inference workers to stop experience collection... (26350 times) [2023-03-09 09:15:31,090][22940] Signal inference workers to resume experience collection... (26350 times) [2023-03-09 09:15:31,117][23090] InferenceWorker_p0-w0: stopping experience collection (26350 times) [2023-03-09 09:15:31,157][23090] InferenceWorker_p0-w0: resuming experience collection (26350 times) [2023-03-09 09:15:31,290][23090] Updated weights for policy 0, policy_version 79406 (0.0013) [2023-03-09 09:15:32,101][23090] Updated weights for policy 0, policy_version 79416 (0.0019) [2023-03-09 09:15:32,956][23090] Updated weights for policy 0, policy_version 79427 (0.0014) [2023-03-09 09:15:33,862][23090] Updated weights for policy 0, policy_version 79437 (0.0013) [2023-03-09 09:15:34,059][22664] Fps is (10 sec: 201527.8, 60 sec: 198519.1, 300 sec: 198329.6). Total num frames: 1301544960. Throughput: 0: 49592.2. Samples: 325398304. Policy #0 lag: (min: 1.0, avg: 17.0, max: 33.0) [2023-03-09 09:15:34,059][22664] Avg episode reward: [(0, '55.579')] [2023-03-09 09:15:34,717][23090] Updated weights for policy 0, policy_version 79447 (0.0016) [2023-03-09 09:15:35,561][23090] Updated weights for policy 0, policy_version 79458 (0.0014) [2023-03-09 09:15:36,446][23090] Updated weights for policy 0, policy_version 79468 (0.0013) [2023-03-09 09:15:37,283][23090] Updated weights for policy 0, policy_version 79478 (0.0016) [2023-03-09 09:15:38,096][23090] Updated weights for policy 0, policy_version 79488 (0.0017) [2023-03-09 09:15:39,011][23090] Updated weights for policy 0, policy_version 79499 (0.0019) [2023-03-09 09:15:39,059][22664] Fps is (10 sec: 199882.6, 60 sec: 198518.8, 300 sec: 198329.6). Total num frames: 1302528000. Throughput: 0: 49590.0. Samples: 325695104. Policy #0 lag: (min: 2.0, avg: 17.0, max: 33.0) [2023-03-09 09:15:39,060][22664] Avg episode reward: [(0, '54.794')] [2023-03-09 09:15:39,825][23090] Updated weights for policy 0, policy_version 79509 (0.0016) [2023-03-09 09:15:40,583][23090] Updated weights for policy 0, policy_version 79519 (0.0017) [2023-03-09 09:15:41,434][23090] Updated weights for policy 0, policy_version 79529 (0.0013) [2023-03-09 09:15:42,263][23090] Updated weights for policy 0, policy_version 79539 (0.0013) [2023-03-09 09:15:42,867][22940] Signal inference workers to stop experience collection... (26400 times) [2023-03-09 09:15:42,869][22940] Signal inference workers to resume experience collection... (26400 times) [2023-03-09 09:15:42,938][23090] InferenceWorker_p0-w0: stopping experience collection (26400 times) [2023-03-09 09:15:42,939][23090] InferenceWorker_p0-w0: resuming experience collection (26400 times) [2023-03-09 09:15:43,101][23090] Updated weights for policy 0, policy_version 79550 (0.0013) [2023-03-09 09:15:43,947][23090] Updated weights for policy 0, policy_version 79560 (0.0019) [2023-03-09 09:15:44,058][22664] Fps is (10 sec: 199887.3, 60 sec: 198793.6, 300 sec: 198440.8). Total num frames: 1303543808. Throughput: 0: 49635.2. Samples: 325846576. Policy #0 lag: (min: 2.0, avg: 17.0, max: 33.0) [2023-03-09 09:15:44,059][22664] Avg episode reward: [(0, '53.018')] [2023-03-09 09:15:44,690][23090] Updated weights for policy 0, policy_version 79570 (0.0013) [2023-03-09 09:15:45,617][23090] Updated weights for policy 0, policy_version 79580 (0.0022) [2023-03-09 09:15:46,462][23090] Updated weights for policy 0, policy_version 79590 (0.0013) [2023-03-09 09:15:47,229][23090] Updated weights for policy 0, policy_version 79601 (0.0016) [2023-03-09 09:15:48,195][23090] Updated weights for policy 0, policy_version 79611 (0.0016) [2023-03-09 09:15:48,993][23090] Updated weights for policy 0, policy_version 79621 (0.0013) [2023-03-09 09:15:49,059][22664] Fps is (10 sec: 199889.3, 60 sec: 198521.6, 300 sec: 198385.4). Total num frames: 1304526848. Throughput: 0: 49679.6. Samples: 326145472. Policy #0 lag: (min: 2.0, avg: 17.0, max: 33.0) [2023-03-09 09:15:49,060][22664] Avg episode reward: [(0, '52.877')] [2023-03-09 09:15:49,835][23090] Updated weights for policy 0, policy_version 79632 (0.0017) [2023-03-09 09:15:50,772][23090] Updated weights for policy 0, policy_version 79642 (0.0021) [2023-03-09 09:15:51,612][23090] Updated weights for policy 0, policy_version 79652 (0.0017) [2023-03-09 09:15:52,344][23090] Updated weights for policy 0, policy_version 79662 (0.0020) [2023-03-09 09:15:53,169][23090] Updated weights for policy 0, policy_version 79672 (0.0018) [2023-03-09 09:15:53,952][23090] Updated weights for policy 0, policy_version 79682 (0.0013) [2023-03-09 09:15:54,058][22664] Fps is (10 sec: 198246.0, 60 sec: 198793.3, 300 sec: 198330.3). Total num frames: 1305526272. Throughput: 0: 49725.5. Samples: 326444400. Policy #0 lag: (min: 2.0, avg: 17.0, max: 33.0) [2023-03-09 09:15:54,059][22664] Avg episode reward: [(0, '50.675')] [2023-03-09 09:15:54,589][22940] Signal inference workers to stop experience collection... (26450 times) [2023-03-09 09:15:54,591][22940] Signal inference workers to resume experience collection... (26450 times) [2023-03-09 09:15:54,672][23090] InferenceWorker_p0-w0: stopping experience collection (26450 times) [2023-03-09 09:15:54,672][23090] InferenceWorker_p0-w0: resuming experience collection (26450 times) [2023-03-09 09:15:54,920][23090] Updated weights for policy 0, policy_version 79693 (0.0021) [2023-03-09 09:15:55,770][23090] Updated weights for policy 0, policy_version 79703 (0.0022) [2023-03-09 09:15:56,574][23090] Updated weights for policy 0, policy_version 79713 (0.0020) [2023-03-09 09:15:57,428][23090] Updated weights for policy 0, policy_version 79723 (0.0017) [2023-03-09 09:15:58,279][23090] Updated weights for policy 0, policy_version 79733 (0.0014) [2023-03-09 09:15:59,017][23090] Updated weights for policy 0, policy_version 79743 (0.0021) [2023-03-09 09:15:59,059][22664] Fps is (10 sec: 198241.2, 60 sec: 198519.4, 300 sec: 198329.7). Total num frames: 1306509312. Throughput: 0: 49725.8. Samples: 326591840. Policy #0 lag: (min: 2.0, avg: 17.0, max: 33.0) [2023-03-09 09:15:59,061][22664] Avg episode reward: [(0, '52.164')] [2023-03-09 09:15:59,942][23090] Updated weights for policy 0, policy_version 79754 (0.0014) [2023-03-09 09:16:00,812][23090] Updated weights for policy 0, policy_version 79764 (0.0013) [2023-03-09 09:16:01,668][23090] Updated weights for policy 0, policy_version 79775 (0.0013) [2023-03-09 09:16:02,519][23090] Updated weights for policy 0, policy_version 79785 (0.0016) [2023-03-09 09:16:03,364][23090] Updated weights for policy 0, policy_version 79795 (0.0018) [2023-03-09 09:16:04,059][22664] Fps is (10 sec: 198244.2, 60 sec: 199065.4, 300 sec: 198385.5). Total num frames: 1307508736. Throughput: 0: 49634.5. Samples: 326888720. Policy #0 lag: (min: 2.0, avg: 17.0, max: 33.0) [2023-03-09 09:16:04,060][22664] Avg episode reward: [(0, '52.906')] [2023-03-09 09:16:04,144][23090] Updated weights for policy 0, policy_version 79805 (0.0017) [2023-03-09 09:16:05,074][23090] Updated weights for policy 0, policy_version 79816 (0.0016) [2023-03-09 09:16:05,847][23090] Updated weights for policy 0, policy_version 79826 (0.0016) [2023-03-09 09:16:06,812][23090] Updated weights for policy 0, policy_version 79837 (0.0019) [2023-03-09 09:16:06,819][22940] Signal inference workers to stop experience collection... (26500 times) [2023-03-09 09:16:06,823][22940] Signal inference workers to resume experience collection... (26500 times) [2023-03-09 09:16:06,888][23090] InferenceWorker_p0-w0: stopping experience collection (26500 times) [2023-03-09 09:16:06,889][23090] InferenceWorker_p0-w0: resuming experience collection (26500 times) [2023-03-09 09:16:07,633][23090] Updated weights for policy 0, policy_version 79847 (0.0016) [2023-03-09 09:16:08,492][23090] Updated weights for policy 0, policy_version 79858 (0.0022) [2023-03-09 09:16:09,059][22664] Fps is (10 sec: 198249.8, 60 sec: 198519.0, 300 sec: 198385.1). Total num frames: 1308491776. Throughput: 0: 49727.1. Samples: 327187696. Policy #0 lag: (min: 2.0, avg: 17.0, max: 33.0) [2023-03-09 09:16:09,060][22664] Avg episode reward: [(0, '52.619')] [2023-03-09 09:16:09,364][23090] Updated weights for policy 0, policy_version 79868 (0.0017) [2023-03-09 09:16:10,217][23090] Updated weights for policy 0, policy_version 79878 (0.0016) [2023-03-09 09:16:10,951][23090] Updated weights for policy 0, policy_version 79888 (0.0028) [2023-03-09 09:16:11,913][23090] Updated weights for policy 0, policy_version 79898 (0.0016) [2023-03-09 09:16:12,710][23090] Updated weights for policy 0, policy_version 79908 (0.0013) [2023-03-09 09:16:13,468][23090] Updated weights for policy 0, policy_version 79918 (0.0021) [2023-03-09 09:16:14,059][22664] Fps is (10 sec: 196604.3, 60 sec: 198519.5, 300 sec: 198329.6). Total num frames: 1309474816. Throughput: 0: 49771.6. Samples: 327337136. Policy #0 lag: (min: 2.0, avg: 17.0, max: 33.0) [2023-03-09 09:16:14,060][22664] Avg episode reward: [(0, '53.242')] [2023-03-09 09:16:14,303][23090] Updated weights for policy 0, policy_version 79928 (0.0018) [2023-03-09 09:16:15,095][23090] Updated weights for policy 0, policy_version 79938 (0.0015) [2023-03-09 09:16:15,978][23090] Updated weights for policy 0, policy_version 79948 (0.0016) [2023-03-09 09:16:16,832][23090] Updated weights for policy 0, policy_version 79958 (0.0013) [2023-03-09 09:16:17,651][23090] Updated weights for policy 0, policy_version 79968 (0.0013) [2023-03-09 09:16:18,454][23090] Updated weights for policy 0, policy_version 79978 (0.0013) [2023-03-09 09:16:19,059][22664] Fps is (10 sec: 199880.9, 60 sec: 199064.8, 300 sec: 198385.2). Total num frames: 1310490624. Throughput: 0: 49634.9. Samples: 327631888. Policy #0 lag: (min: 2.0, avg: 17.0, max: 33.0) [2023-03-09 09:16:19,061][22664] Avg episode reward: [(0, '54.335')] [2023-03-09 09:16:19,299][23090] Updated weights for policy 0, policy_version 79988 (0.0014) [2023-03-09 09:16:20,100][23090] Updated weights for policy 0, policy_version 79998 (0.0017) [2023-03-09 09:16:20,270][22940] Signal inference workers to stop experience collection... (26550 times) [2023-03-09 09:16:20,271][22940] Signal inference workers to resume experience collection... (26550 times) [2023-03-09 09:16:20,344][23090] InferenceWorker_p0-w0: stopping experience collection (26550 times) [2023-03-09 09:16:20,344][23090] InferenceWorker_p0-w0: resuming experience collection (26550 times) [2023-03-09 09:16:20,917][23090] Updated weights for policy 0, policy_version 80008 (0.0013) [2023-03-09 09:16:21,726][23090] Updated weights for policy 0, policy_version 80018 (0.0013) [2023-03-09 09:16:22,582][23090] Updated weights for policy 0, policy_version 80028 (0.0016) [2023-03-09 09:16:23,451][23090] Updated weights for policy 0, policy_version 80038 (0.0021) [2023-03-09 09:16:24,058][22664] Fps is (10 sec: 198251.6, 60 sec: 198793.5, 300 sec: 198329.8). Total num frames: 1311457280. Throughput: 0: 49681.7. Samples: 327930768. Policy #0 lag: (min: 2.0, avg: 17.0, max: 33.0) [2023-03-09 09:16:24,059][22664] Avg episode reward: [(0, '53.641')] [2023-03-09 09:16:24,328][23090] Updated weights for policy 0, policy_version 80049 (0.0019) [2023-03-09 09:16:25,186][23090] Updated weights for policy 0, policy_version 80059 (0.0021) [2023-03-09 09:16:25,987][23090] Updated weights for policy 0, policy_version 80069 (0.0013) [2023-03-09 09:16:26,798][23090] Updated weights for policy 0, policy_version 80079 (0.0019) [2023-03-09 09:16:27,644][23090] Updated weights for policy 0, policy_version 80089 (0.0013) [2023-03-09 09:16:28,419][23090] Updated weights for policy 0, policy_version 80099 (0.0016) [2023-03-09 09:16:29,059][22664] Fps is (10 sec: 196604.7, 60 sec: 198791.4, 300 sec: 198329.5). Total num frames: 1312456704. Throughput: 0: 49591.2. Samples: 328078208. Policy #0 lag: (min: 0.0, avg: 17.0, max: 33.0) [2023-03-09 09:16:29,061][22664] Avg episode reward: [(0, '53.943')] [2023-03-09 09:16:29,249][23090] Updated weights for policy 0, policy_version 80109 (0.0017) [2023-03-09 09:16:30,145][23090] Updated weights for policy 0, policy_version 80119 (0.0014) [2023-03-09 09:16:30,909][23090] Updated weights for policy 0, policy_version 80129 (0.0015) [2023-03-09 09:16:31,816][23090] Updated weights for policy 0, policy_version 80139 (0.0016) [2023-03-09 09:16:32,581][23090] Updated weights for policy 0, policy_version 80149 (0.0013) [2023-03-09 09:16:33,352][23090] Updated weights for policy 0, policy_version 80159 (0.0018) [2023-03-09 09:16:33,449][22940] Signal inference workers to stop experience collection... (26600 times) [2023-03-09 09:16:33,451][22940] Signal inference workers to resume experience collection... (26600 times) [2023-03-09 09:16:33,520][23090] InferenceWorker_p0-w0: stopping experience collection (26600 times) [2023-03-09 09:16:33,520][23090] InferenceWorker_p0-w0: resuming experience collection (26600 times) [2023-03-09 09:16:34,058][22664] Fps is (10 sec: 199885.3, 60 sec: 198519.8, 300 sec: 198385.5). Total num frames: 1313456128. Throughput: 0: 49639.2. Samples: 328379232. Policy #0 lag: (min: 0.0, avg: 17.0, max: 33.0) [2023-03-09 09:16:34,060][22664] Avg episode reward: [(0, '55.224')] [2023-03-09 09:16:34,202][23090] Updated weights for policy 0, policy_version 80169 (0.0021) [2023-03-09 09:16:35,081][23090] Updated weights for policy 0, policy_version 80179 (0.0022) [2023-03-09 09:16:35,843][23090] Updated weights for policy 0, policy_version 80189 (0.0018) [2023-03-09 09:16:36,649][23090] Updated weights for policy 0, policy_version 80199 (0.0024) [2023-03-09 09:16:37,450][23090] Updated weights for policy 0, policy_version 80209 (0.0013) [2023-03-09 09:16:38,342][23090] Updated weights for policy 0, policy_version 80219 (0.0016) [2023-03-09 09:16:39,059][22664] Fps is (10 sec: 198249.2, 60 sec: 198519.2, 300 sec: 198274.0). Total num frames: 1314439168. Throughput: 0: 49593.5. Samples: 328676128. Policy #0 lag: (min: 0.0, avg: 17.0, max: 33.0) [2023-03-09 09:16:39,061][22664] Avg episode reward: [(0, '53.813')] [2023-03-09 09:16:39,175][23090] Updated weights for policy 0, policy_version 80229 (0.0019) [2023-03-09 09:16:39,960][23090] Updated weights for policy 0, policy_version 80239 (0.0016) [2023-03-09 09:16:40,828][23090] Updated weights for policy 0, policy_version 80249 (0.0020) [2023-03-09 09:16:41,568][23090] Updated weights for policy 0, policy_version 80259 (0.0018) [2023-03-09 09:16:42,466][23090] Updated weights for policy 0, policy_version 80269 (0.0016) [2023-03-09 09:16:43,314][23090] Updated weights for policy 0, policy_version 80279 (0.0019) [2023-03-09 09:16:44,059][22664] Fps is (10 sec: 198240.6, 60 sec: 198245.3, 300 sec: 198329.6). Total num frames: 1315438592. Throughput: 0: 49637.7. Samples: 328825536. Policy #0 lag: (min: 0.0, avg: 17.0, max: 33.0) [2023-03-09 09:16:44,060][22664] Avg episode reward: [(0, '51.839')] [2023-03-09 09:16:44,102][23090] Updated weights for policy 0, policy_version 80289 (0.0022) [2023-03-09 09:16:44,987][23090] Updated weights for policy 0, policy_version 80299 (0.0016) [2023-03-09 09:16:45,820][23090] Updated weights for policy 0, policy_version 80309 (0.0016) [2023-03-09 09:16:46,605][23090] Updated weights for policy 0, policy_version 80319 (0.0013) [2023-03-09 09:16:47,438][23090] Updated weights for policy 0, policy_version 80329 (0.0021) [2023-03-09 09:16:47,710][22940] Signal inference workers to stop experience collection... (26650 times) [2023-03-09 09:16:47,722][22940] Signal inference workers to resume experience collection... (26650 times) [2023-03-09 09:16:47,788][23090] InferenceWorker_p0-w0: stopping experience collection (26650 times) [2023-03-09 09:16:47,788][23090] InferenceWorker_p0-w0: resuming experience collection (26650 times) [2023-03-09 09:16:48,351][23090] Updated weights for policy 0, policy_version 80339 (0.0016) [2023-03-09 09:16:49,059][22664] Fps is (10 sec: 198252.7, 60 sec: 198246.4, 300 sec: 198218.8). Total num frames: 1316421632. Throughput: 0: 49592.6. Samples: 329120384. Policy #0 lag: (min: 0.0, avg: 17.0, max: 33.0) [2023-03-09 09:16:49,060][22664] Avg episode reward: [(0, '54.345')] [2023-03-09 09:16:49,068][23090] Updated weights for policy 0, policy_version 80349 (0.0013) [2023-03-09 09:16:49,933][23090] Updated weights for policy 0, policy_version 80359 (0.0024) [2023-03-09 09:16:50,691][23090] Updated weights for policy 0, policy_version 80369 (0.0016) [2023-03-09 09:16:51,583][23090] Updated weights for policy 0, policy_version 80379 (0.0020) [2023-03-09 09:16:52,433][23090] Updated weights for policy 0, policy_version 80389 (0.0013) [2023-03-09 09:16:53,211][23090] Updated weights for policy 0, policy_version 80399 (0.0021) [2023-03-09 09:16:54,059][22664] Fps is (10 sec: 196608.9, 60 sec: 197972.5, 300 sec: 198163.0). Total num frames: 1317404672. Throughput: 0: 49545.9. Samples: 329417264. Policy #0 lag: (min: 0.0, avg: 17.0, max: 33.0) [2023-03-09 09:16:54,061][22664] Avg episode reward: [(0, '54.978')] [2023-03-09 09:16:54,092][23090] Updated weights for policy 0, policy_version 80409 (0.0017) [2023-03-09 09:16:54,841][23090] Updated weights for policy 0, policy_version 80419 (0.0018) [2023-03-09 09:16:55,732][23090] Updated weights for policy 0, policy_version 80429 (0.0017) [2023-03-09 09:16:56,575][23090] Updated weights for policy 0, policy_version 80439 (0.0017) [2023-03-09 09:16:57,348][23090] Updated weights for policy 0, policy_version 80449 (0.0019) [2023-03-09 09:16:58,224][23090] Updated weights for policy 0, policy_version 80459 (0.0016) [2023-03-09 09:16:59,048][23090] Updated weights for policy 0, policy_version 80469 (0.0020) [2023-03-09 09:16:59,059][22664] Fps is (10 sec: 198240.4, 60 sec: 198246.3, 300 sec: 198329.6). Total num frames: 1318404096. Throughput: 0: 49546.9. Samples: 329566752. Policy #0 lag: (min: 0.0, avg: 17.0, max: 33.0) [2023-03-09 09:16:59,061][22664] Avg episode reward: [(0, '55.362')] [2023-03-09 09:16:59,814][23090] Updated weights for policy 0, policy_version 80479 (0.0013) [2023-03-09 09:17:00,675][23090] Updated weights for policy 0, policy_version 80489 (0.0023) [2023-03-09 09:17:01,562][23090] Updated weights for policy 0, policy_version 80499 (0.0021) [2023-03-09 09:17:02,322][23090] Updated weights for policy 0, policy_version 80509 (0.0021) [2023-03-09 09:17:03,141][23090] Updated weights for policy 0, policy_version 80519 (0.0016) [2023-03-09 09:17:03,793][22940] Signal inference workers to stop experience collection... (26700 times) [2023-03-09 09:17:03,797][22940] Signal inference workers to resume experience collection... (26700 times) [2023-03-09 09:17:03,861][23090] InferenceWorker_p0-w0: stopping experience collection (26700 times) [2023-03-09 09:17:03,861][23090] InferenceWorker_p0-w0: resuming experience collection (26700 times) [2023-03-09 09:17:03,947][23090] Updated weights for policy 0, policy_version 80529 (0.0014) [2023-03-09 09:17:04,059][22664] Fps is (10 sec: 199888.2, 60 sec: 198246.5, 300 sec: 198385.2). Total num frames: 1319403520. Throughput: 0: 49593.9. Samples: 329863600. Policy #0 lag: (min: 0.0, avg: 17.0, max: 33.0) [2023-03-09 09:17:04,060][22664] Avg episode reward: [(0, '53.336')] [2023-03-09 09:17:04,834][23090] Updated weights for policy 0, policy_version 80539 (0.0020) [2023-03-09 09:17:05,649][23090] Updated weights for policy 0, policy_version 80549 (0.0013) [2023-03-09 09:17:06,411][23090] Updated weights for policy 0, policy_version 80559 (0.0015) [2023-03-09 09:17:07,297][23090] Updated weights for policy 0, policy_version 80569 (0.0019) [2023-03-09 09:17:08,085][23090] Updated weights for policy 0, policy_version 80579 (0.0016) [2023-03-09 09:17:08,935][23090] Updated weights for policy 0, policy_version 80589 (0.0020) [2023-03-09 09:17:09,059][22664] Fps is (10 sec: 199874.6, 60 sec: 198517.1, 300 sec: 198496.1). Total num frames: 1320402944. Throughput: 0: 49592.7. Samples: 330162480. Policy #0 lag: (min: 0.0, avg: 17.0, max: 33.0) [2023-03-09 09:17:09,061][22664] Avg episode reward: [(0, '52.501')] [2023-03-09 09:17:09,783][23090] Updated weights for policy 0, policy_version 80599 (0.0016) [2023-03-09 09:17:10,559][23090] Updated weights for policy 0, policy_version 80609 (0.0019) [2023-03-09 09:17:11,435][23090] Updated weights for policy 0, policy_version 80619 (0.0016) [2023-03-09 09:17:12,256][23090] Updated weights for policy 0, policy_version 80629 (0.0016) [2023-03-09 09:17:13,040][23090] Updated weights for policy 0, policy_version 80639 (0.0019) [2023-03-09 09:17:13,874][23090] Updated weights for policy 0, policy_version 80649 (0.0013) [2023-03-09 09:17:14,058][22664] Fps is (10 sec: 196609.1, 60 sec: 198247.3, 300 sec: 198496.3). Total num frames: 1321369600. Throughput: 0: 49593.8. Samples: 330309904. Policy #0 lag: (min: 0.0, avg: 17.0, max: 33.0) [2023-03-09 09:17:14,060][22664] Avg episode reward: [(0, '53.588')] [2023-03-09 09:17:14,792][23090] Updated weights for policy 0, policy_version 80659 (0.0019) [2023-03-09 09:17:15,530][23090] Updated weights for policy 0, policy_version 80669 (0.0017) [2023-03-09 09:17:16,387][23090] Updated weights for policy 0, policy_version 80679 (0.0016) [2023-03-09 09:17:17,245][23090] Updated weights for policy 0, policy_version 80690 (0.0019) [2023-03-09 09:17:18,105][23090] Updated weights for policy 0, policy_version 80700 (0.0016) [2023-03-09 09:17:19,031][23090] Updated weights for policy 0, policy_version 80710 (0.0019) [2023-03-09 09:17:19,059][22664] Fps is (10 sec: 196623.6, 60 sec: 197974.2, 300 sec: 198440.9). Total num frames: 1322369024. Throughput: 0: 49501.4. Samples: 330606800. Policy #0 lag: (min: 1.0, avg: 17.2, max: 33.0) [2023-03-09 09:17:19,059][22664] Avg episode reward: [(0, '53.440')] [2023-03-09 09:17:19,066][22940] Saving /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000080711_1322369024.pth... [2023-03-09 09:17:19,136][22940] Removing /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000077806_1274773504.pth [2023-03-09 09:17:19,714][23090] Updated weights for policy 0, policy_version 80720 (0.0013) [2023-03-09 09:17:20,642][23090] Updated weights for policy 0, policy_version 80730 (0.0016) [2023-03-09 09:17:21,437][23090] Updated weights for policy 0, policy_version 80740 (0.0013) [2023-03-09 09:17:21,604][22940] Signal inference workers to stop experience collection... (26750 times) [2023-03-09 09:17:21,604][22940] Signal inference workers to resume experience collection... (26750 times) [2023-03-09 09:17:21,678][23090] InferenceWorker_p0-w0: stopping experience collection (26750 times) [2023-03-09 09:17:21,679][23090] InferenceWorker_p0-w0: resuming experience collection (26750 times) [2023-03-09 09:17:22,208][23090] Updated weights for policy 0, policy_version 80750 (0.0015) [2023-03-09 09:17:23,084][23090] Updated weights for policy 0, policy_version 80760 (0.0013) [2023-03-09 09:17:23,879][23090] Updated weights for policy 0, policy_version 80770 (0.0013) [2023-03-09 09:17:24,058][22664] Fps is (10 sec: 198247.1, 60 sec: 198246.5, 300 sec: 198385.3). Total num frames: 1323352064. Throughput: 0: 49502.3. Samples: 330903712. Policy #0 lag: (min: 1.0, avg: 17.2, max: 33.0) [2023-03-09 09:17:24,059][22664] Avg episode reward: [(0, '54.310')] [2023-03-09 09:17:24,791][23090] Updated weights for policy 0, policy_version 80780 (0.0020) [2023-03-09 09:17:25,561][23090] Updated weights for policy 0, policy_version 80790 (0.0013) [2023-03-09 09:17:26,364][23090] Updated weights for policy 0, policy_version 80800 (0.0013) [2023-03-09 09:17:27,182][23090] Updated weights for policy 0, policy_version 80810 (0.0016) [2023-03-09 09:17:28,081][23090] Updated weights for policy 0, policy_version 80820 (0.0015) [2023-03-09 09:17:28,815][23090] Updated weights for policy 0, policy_version 80830 (0.0015) [2023-03-09 09:17:29,059][22664] Fps is (10 sec: 198242.3, 60 sec: 198247.2, 300 sec: 198440.7). Total num frames: 1324351488. Throughput: 0: 49502.9. Samples: 331053168. Policy #0 lag: (min: 1.0, avg: 17.2, max: 33.0) [2023-03-09 09:17:29,061][22664] Avg episode reward: [(0, '53.121')] [2023-03-09 09:17:29,650][23090] Updated weights for policy 0, policy_version 80840 (0.0013) [2023-03-09 09:17:30,428][23090] Updated weights for policy 0, policy_version 80850 (0.0014) [2023-03-09 09:17:31,352][23090] Updated weights for policy 0, policy_version 80860 (0.0016) [2023-03-09 09:17:32,194][23090] Updated weights for policy 0, policy_version 80870 (0.0016) [2023-03-09 09:17:32,962][23090] Updated weights for policy 0, policy_version 80880 (0.0013) [2023-03-09 09:17:33,823][23090] Updated weights for policy 0, policy_version 80890 (0.0013) [2023-03-09 09:17:34,059][22664] Fps is (10 sec: 199880.0, 60 sec: 198245.6, 300 sec: 198440.7). Total num frames: 1325350912. Throughput: 0: 49546.5. Samples: 331349984. Policy #0 lag: (min: 1.0, avg: 17.2, max: 33.0) [2023-03-09 09:17:34,060][22664] Avg episode reward: [(0, '52.403')] [2023-03-09 09:17:34,671][23090] Updated weights for policy 0, policy_version 80900 (0.0016) [2023-03-09 09:17:35,435][23090] Updated weights for policy 0, policy_version 80910 (0.0013) [2023-03-09 09:17:36,302][23090] Updated weights for policy 0, policy_version 80920 (0.0018) [2023-03-09 09:17:37,061][23090] Updated weights for policy 0, policy_version 80930 (0.0015) [2023-03-09 09:17:37,928][23090] Updated weights for policy 0, policy_version 80940 (0.0019) [2023-03-09 09:17:38,758][23090] Updated weights for policy 0, policy_version 80950 (0.0013) [2023-03-09 09:17:39,059][22664] Fps is (10 sec: 199878.7, 60 sec: 198518.8, 300 sec: 198440.4). Total num frames: 1326350336. Throughput: 0: 49635.9. Samples: 331650896. Policy #0 lag: (min: 1.0, avg: 17.2, max: 33.0) [2023-03-09 09:17:39,061][22664] Avg episode reward: [(0, '51.638')] [2023-03-09 09:17:39,485][23090] Updated weights for policy 0, policy_version 80960 (0.0016) [2023-03-09 09:17:40,183][22940] Signal inference workers to stop experience collection... (26800 times) [2023-03-09 09:17:40,185][22940] Signal inference workers to resume experience collection... (26800 times) [2023-03-09 09:17:40,248][23090] InferenceWorker_p0-w0: stopping experience collection (26800 times) [2023-03-09 09:17:40,248][23090] InferenceWorker_p0-w0: resuming experience collection (26800 times) [2023-03-09 09:17:40,300][23090] Updated weights for policy 0, policy_version 80970 (0.0019) [2023-03-09 09:17:41,256][23090] Updated weights for policy 0, policy_version 80981 (0.0019) [2023-03-09 09:17:42,036][23090] Updated weights for policy 0, policy_version 80991 (0.0016) [2023-03-09 09:17:42,914][23090] Updated weights for policy 0, policy_version 81001 (0.0016) [2023-03-09 09:17:43,775][23090] Updated weights for policy 0, policy_version 81011 (0.0016) [2023-03-09 09:17:44,059][22664] Fps is (10 sec: 199884.8, 60 sec: 198519.7, 300 sec: 198496.3). Total num frames: 1327349760. Throughput: 0: 49681.9. Samples: 331802432. Policy #0 lag: (min: 1.0, avg: 17.2, max: 33.0) [2023-03-09 09:17:44,061][22664] Avg episode reward: [(0, '52.387')] [2023-03-09 09:17:44,539][23090] Updated weights for policy 0, policy_version 81021 (0.0016) [2023-03-09 09:17:45,392][23090] Updated weights for policy 0, policy_version 81031 (0.0017) [2023-03-09 09:17:46,137][23090] Updated weights for policy 0, policy_version 81041 (0.0013) [2023-03-09 09:17:47,078][23090] Updated weights for policy 0, policy_version 81051 (0.0013) [2023-03-09 09:17:47,857][23090] Updated weights for policy 0, policy_version 81061 (0.0016) [2023-03-09 09:17:48,688][23090] Updated weights for policy 0, policy_version 81071 (0.0013) [2023-03-09 09:17:49,059][22664] Fps is (10 sec: 198250.2, 60 sec: 198518.4, 300 sec: 198440.5). Total num frames: 1328332800. Throughput: 0: 49679.6. Samples: 332099200. Policy #0 lag: (min: 1.0, avg: 17.2, max: 33.0) [2023-03-09 09:17:49,061][22664] Avg episode reward: [(0, '54.051')] [2023-03-09 09:17:49,560][23090] Updated weights for policy 0, policy_version 81081 (0.0013) [2023-03-09 09:17:50,324][23090] Updated weights for policy 0, policy_version 81091 (0.0013) [2023-03-09 09:17:51,160][23090] Updated weights for policy 0, policy_version 81101 (0.0016) [2023-03-09 09:17:52,076][23090] Updated weights for policy 0, policy_version 81112 (0.0013) [2023-03-09 09:17:52,846][23090] Updated weights for policy 0, policy_version 81122 (0.0017) [2023-03-09 09:17:53,778][23090] Updated weights for policy 0, policy_version 81132 (0.0023) [2023-03-09 09:17:54,059][22664] Fps is (10 sec: 198248.8, 60 sec: 198793.0, 300 sec: 198496.4). Total num frames: 1329332224. Throughput: 0: 49637.5. Samples: 332396128. Policy #0 lag: (min: 1.0, avg: 17.2, max: 33.0) [2023-03-09 09:17:54,060][22664] Avg episode reward: [(0, '51.964')] [2023-03-09 09:17:54,333][22940] Signal inference workers to stop experience collection... (26850 times) [2023-03-09 09:17:54,344][22940] Signal inference workers to resume experience collection... (26850 times) [2023-03-09 09:17:54,376][23090] InferenceWorker_p0-w0: stopping experience collection (26850 times) [2023-03-09 09:17:54,413][23090] InferenceWorker_p0-w0: resuming experience collection (26850 times) [2023-03-09 09:17:54,545][23090] Updated weights for policy 0, policy_version 81142 (0.0021) [2023-03-09 09:17:55,347][23090] Updated weights for policy 0, policy_version 81152 (0.0017) [2023-03-09 09:17:56,176][23090] Updated weights for policy 0, policy_version 81162 (0.0021) [2023-03-09 09:17:57,044][23090] Updated weights for policy 0, policy_version 81172 (0.0013) [2023-03-09 09:17:57,847][23090] Updated weights for policy 0, policy_version 81182 (0.0016) [2023-03-09 09:17:58,698][23090] Updated weights for policy 0, policy_version 81192 (0.0020) [2023-03-09 09:17:59,058][22664] Fps is (10 sec: 198254.3, 60 sec: 198520.7, 300 sec: 198440.8). Total num frames: 1330315264. Throughput: 0: 49681.4. Samples: 332545568. Policy #0 lag: (min: 1.0, avg: 17.2, max: 33.0) [2023-03-09 09:17:59,059][22664] Avg episode reward: [(0, '53.556')] [2023-03-09 09:17:59,444][23090] Updated weights for policy 0, policy_version 81202 (0.0015) [2023-03-09 09:18:00,318][23090] Updated weights for policy 0, policy_version 81212 (0.0013) [2023-03-09 09:18:01,151][23090] Updated weights for policy 0, policy_version 81222 (0.0016) [2023-03-09 09:18:01,934][23090] Updated weights for policy 0, policy_version 81232 (0.0018) [2023-03-09 09:18:02,851][23090] Updated weights for policy 0, policy_version 81242 (0.0022) [2023-03-09 09:18:03,661][23090] Updated weights for policy 0, policy_version 81252 (0.0020) [2023-03-09 09:18:04,058][22664] Fps is (10 sec: 196609.9, 60 sec: 198246.6, 300 sec: 198496.6). Total num frames: 1331298304. Throughput: 0: 49680.4. Samples: 332842416. Policy #0 lag: (min: 1.0, avg: 17.2, max: 33.0) [2023-03-09 09:18:04,059][22664] Avg episode reward: [(0, '51.772')] [2023-03-09 09:18:04,477][23090] Updated weights for policy 0, policy_version 81262 (0.0013) [2023-03-09 09:18:05,282][23090] Updated weights for policy 0, policy_version 81272 (0.0017) [2023-03-09 09:18:06,217][23090] Updated weights for policy 0, policy_version 81283 (0.0013) [2023-03-09 09:18:07,071][23090] Updated weights for policy 0, policy_version 81293 (0.0013) [2023-03-09 09:18:07,906][23090] Updated weights for policy 0, policy_version 81303 (0.0016) [2023-03-09 09:18:08,641][23090] Updated weights for policy 0, policy_version 81313 (0.0016) [2023-03-09 09:18:09,059][22664] Fps is (10 sec: 198238.0, 60 sec: 198247.9, 300 sec: 198385.0). Total num frames: 1332297728. Throughput: 0: 49678.8. Samples: 333139280. Policy #0 lag: (min: 1.0, avg: 16.6, max: 32.0) [2023-03-09 09:18:09,061][22664] Avg episode reward: [(0, '54.928')] [2023-03-09 09:18:09,550][23090] Updated weights for policy 0, policy_version 81323 (0.0015) [2023-03-09 09:18:09,631][22940] Signal inference workers to stop experience collection... (26900 times) [2023-03-09 09:18:09,644][22940] Signal inference workers to resume experience collection... (26900 times) [2023-03-09 09:18:09,699][23090] InferenceWorker_p0-w0: stopping experience collection (26900 times) [2023-03-09 09:18:09,700][23090] InferenceWorker_p0-w0: resuming experience collection (26900 times) [2023-03-09 09:18:10,339][23090] Updated weights for policy 0, policy_version 81333 (0.0016) [2023-03-09 09:18:11,079][23090] Updated weights for policy 0, policy_version 81343 (0.0022) [2023-03-09 09:18:11,968][23090] Updated weights for policy 0, policy_version 81353 (0.0017) [2023-03-09 09:18:12,807][23090] Updated weights for policy 0, policy_version 81363 (0.0013) [2023-03-09 09:18:13,628][23090] Updated weights for policy 0, policy_version 81373 (0.0014) [2023-03-09 09:18:14,059][22664] Fps is (10 sec: 199882.3, 60 sec: 198792.2, 300 sec: 198496.5). Total num frames: 1333297152. Throughput: 0: 49678.4. Samples: 333288688. Policy #0 lag: (min: 1.0, avg: 16.6, max: 32.0) [2023-03-09 09:18:14,060][22664] Avg episode reward: [(0, '53.833')] [2023-03-09 09:18:14,442][23090] Updated weights for policy 0, policy_version 81383 (0.0015) [2023-03-09 09:18:15,201][23090] Updated weights for policy 0, policy_version 81393 (0.0016) [2023-03-09 09:18:16,081][23090] Updated weights for policy 0, policy_version 81403 (0.0020) [2023-03-09 09:18:16,896][23090] Updated weights for policy 0, policy_version 81413 (0.0016) [2023-03-09 09:18:17,712][23090] Updated weights for policy 0, policy_version 81423 (0.0017) [2023-03-09 09:18:18,583][23090] Updated weights for policy 0, policy_version 81433 (0.0015) [2023-03-09 09:18:19,059][22664] Fps is (10 sec: 199890.1, 60 sec: 198792.3, 300 sec: 198440.8). Total num frames: 1334296576. Throughput: 0: 49769.7. Samples: 333589616. Policy #0 lag: (min: 1.0, avg: 16.6, max: 32.0) [2023-03-09 09:18:19,060][22664] Avg episode reward: [(0, '53.030')] [2023-03-09 09:18:19,367][23090] Updated weights for policy 0, policy_version 81443 (0.0017) [2023-03-09 09:18:20,229][23090] Updated weights for policy 0, policy_version 81453 (0.0018) [2023-03-09 09:18:21,034][23090] Updated weights for policy 0, policy_version 81463 (0.0015) [2023-03-09 09:18:21,918][23090] Updated weights for policy 0, policy_version 81473 (0.0015) [2023-03-09 09:18:22,731][23090] Updated weights for policy 0, policy_version 81483 (0.0013) [2023-03-09 09:18:23,572][23090] Updated weights for policy 0, policy_version 81493 (0.0018) [2023-03-09 09:18:24,059][22664] Fps is (10 sec: 198242.3, 60 sec: 198791.4, 300 sec: 198440.6). Total num frames: 1335279616. Throughput: 0: 49633.3. Samples: 333884384. Policy #0 lag: (min: 1.0, avg: 16.6, max: 32.0) [2023-03-09 09:18:24,087][22664] Avg episode reward: [(0, '52.519')] [2023-03-09 09:18:24,302][23090] Updated weights for policy 0, policy_version 81503 (0.0021) [2023-03-09 09:18:24,518][22940] Signal inference workers to stop experience collection... (26950 times) [2023-03-09 09:18:24,519][22940] Signal inference workers to resume experience collection... (26950 times) [2023-03-09 09:18:24,592][23090] InferenceWorker_p0-w0: stopping experience collection (26950 times) [2023-03-09 09:18:24,593][23090] InferenceWorker_p0-w0: resuming experience collection (26950 times) [2023-03-09 09:18:25,234][23090] Updated weights for policy 0, policy_version 81513 (0.0018) [2023-03-09 09:18:26,057][23090] Updated weights for policy 0, policy_version 81523 (0.0013) [2023-03-09 09:18:26,836][23090] Updated weights for policy 0, policy_version 81533 (0.0025) [2023-03-09 09:18:27,661][23090] Updated weights for policy 0, policy_version 81543 (0.0013) [2023-03-09 09:18:28,500][23090] Updated weights for policy 0, policy_version 81553 (0.0013) [2023-03-09 09:18:29,059][22664] Fps is (10 sec: 196607.8, 60 sec: 198519.9, 300 sec: 198385.2). Total num frames: 1336262656. Throughput: 0: 49540.7. Samples: 334031760. Policy #0 lag: (min: 1.0, avg: 16.6, max: 32.0) [2023-03-09 09:18:29,060][22664] Avg episode reward: [(0, '56.404')] [2023-03-09 09:18:29,336][23090] Updated weights for policy 0, policy_version 81563 (0.0013) [2023-03-09 09:18:30,228][23090] Updated weights for policy 0, policy_version 81573 (0.0020) [2023-03-09 09:18:30,944][23090] Updated weights for policy 0, policy_version 81583 (0.0015) [2023-03-09 09:18:31,841][23090] Updated weights for policy 0, policy_version 81593 (0.0016) [2023-03-09 09:18:32,627][23090] Updated weights for policy 0, policy_version 81603 (0.0017) [2023-03-09 09:18:33,507][23090] Updated weights for policy 0, policy_version 81614 (0.0016) [2023-03-09 09:18:34,058][22664] Fps is (10 sec: 196615.1, 60 sec: 198247.2, 300 sec: 198329.9). Total num frames: 1337245696. Throughput: 0: 49590.1. Samples: 334330736. Policy #0 lag: (min: 1.0, avg: 16.6, max: 32.0) [2023-03-09 09:18:34,059][22664] Avg episode reward: [(0, '53.186')] [2023-03-09 09:18:34,411][23090] Updated weights for policy 0, policy_version 81624 (0.0013) [2023-03-09 09:18:35,179][23090] Updated weights for policy 0, policy_version 81634 (0.0016) [2023-03-09 09:18:36,088][23090] Updated weights for policy 0, policy_version 81644 (0.0019) [2023-03-09 09:18:36,842][23090] Updated weights for policy 0, policy_version 81654 (0.0015) [2023-03-09 09:18:37,659][23090] Updated weights for policy 0, policy_version 81664 (0.0016) [2023-03-09 09:18:38,510][23090] Updated weights for policy 0, policy_version 81674 (0.0016) [2023-03-09 09:18:39,045][22940] Signal inference workers to stop experience collection... (27000 times) [2023-03-09 09:18:39,048][22940] Signal inference workers to resume experience collection... (27000 times) [2023-03-09 09:18:39,058][22664] Fps is (10 sec: 199888.1, 60 sec: 198521.4, 300 sec: 198441.0). Total num frames: 1338261504. Throughput: 0: 49589.1. Samples: 334627632. Policy #0 lag: (min: 1.0, avg: 16.6, max: 32.0) [2023-03-09 09:18:39,059][22664] Avg episode reward: [(0, '53.563')] [2023-03-09 09:18:39,109][23090] InferenceWorker_p0-w0: stopping experience collection (27000 times) [2023-03-09 09:18:39,109][23090] InferenceWorker_p0-w0: resuming experience collection (27000 times) [2023-03-09 09:18:39,340][23090] Updated weights for policy 0, policy_version 81684 (0.0022) [2023-03-09 09:18:40,119][23090] Updated weights for policy 0, policy_version 81694 (0.0018) [2023-03-09 09:18:40,936][23090] Updated weights for policy 0, policy_version 81704 (0.0013) [2023-03-09 09:18:41,724][23090] Updated weights for policy 0, policy_version 81714 (0.0013) [2023-03-09 09:18:42,583][23090] Updated weights for policy 0, policy_version 81724 (0.0016) [2023-03-09 09:18:43,442][23090] Updated weights for policy 0, policy_version 81734 (0.0015) [2023-03-09 09:18:44,059][22664] Fps is (10 sec: 199882.1, 60 sec: 198246.8, 300 sec: 198385.4). Total num frames: 1339244544. Throughput: 0: 49589.2. Samples: 334777088. Policy #0 lag: (min: 1.0, avg: 16.6, max: 32.0) [2023-03-09 09:18:44,060][22664] Avg episode reward: [(0, '54.215')] [2023-03-09 09:18:44,196][23090] Updated weights for policy 0, policy_version 81744 (0.0016) [2023-03-09 09:18:45,146][23090] Updated weights for policy 0, policy_version 81754 (0.0013) [2023-03-09 09:18:45,918][23090] Updated weights for policy 0, policy_version 81764 (0.0013) [2023-03-09 09:18:46,710][23090] Updated weights for policy 0, policy_version 81774 (0.0014) [2023-03-09 09:18:47,587][23090] Updated weights for policy 0, policy_version 81784 (0.0013) [2023-03-09 09:18:48,356][23090] Updated weights for policy 0, policy_version 81794 (0.0028) [2023-03-09 09:18:49,059][22664] Fps is (10 sec: 198241.3, 60 sec: 198519.9, 300 sec: 198496.4). Total num frames: 1340243968. Throughput: 0: 49634.2. Samples: 335075968. Policy #0 lag: (min: 1.0, avg: 16.6, max: 32.0) [2023-03-09 09:18:49,060][22664] Avg episode reward: [(0, '52.542')] [2023-03-09 09:18:49,243][23090] Updated weights for policy 0, policy_version 81804 (0.0013) [2023-03-09 09:18:50,027][23090] Updated weights for policy 0, policy_version 81814 (0.0013) [2023-03-09 09:18:50,796][23090] Updated weights for policy 0, policy_version 81824 (0.0015) [2023-03-09 09:18:51,787][23090] Updated weights for policy 0, policy_version 81835 (0.0017) [2023-03-09 09:18:52,007][22940] Signal inference workers to stop experience collection... (27050 times) [2023-03-09 09:18:52,008][22940] Signal inference workers to resume experience collection... (27050 times) [2023-03-09 09:18:52,072][23090] InferenceWorker_p0-w0: stopping experience collection (27050 times) [2023-03-09 09:18:52,072][23090] InferenceWorker_p0-w0: resuming experience collection (27050 times) [2023-03-09 09:18:52,601][23090] Updated weights for policy 0, policy_version 81845 (0.0017) [2023-03-09 09:18:53,355][23090] Updated weights for policy 0, policy_version 81855 (0.0020) [2023-03-09 09:18:54,059][22664] Fps is (10 sec: 199882.2, 60 sec: 198519.0, 300 sec: 198440.7). Total num frames: 1341243392. Throughput: 0: 49631.5. Samples: 335372688. Policy #0 lag: (min: 1.0, avg: 16.6, max: 32.0) [2023-03-09 09:18:54,060][22664] Avg episode reward: [(0, '54.109')] [2023-03-09 09:18:54,248][23090] Updated weights for policy 0, policy_version 81865 (0.0018) [2023-03-09 09:18:55,187][23090] Updated weights for policy 0, policy_version 81876 (0.0016) [2023-03-09 09:18:55,959][23090] Updated weights for policy 0, policy_version 81886 (0.0014) [2023-03-09 09:18:56,785][23090] Updated weights for policy 0, policy_version 81896 (0.0018) [2023-03-09 09:18:57,620][23090] Updated weights for policy 0, policy_version 81906 (0.0013) [2023-03-09 09:18:58,462][23090] Updated weights for policy 0, policy_version 81916 (0.0015) [2023-03-09 09:18:59,059][22664] Fps is (10 sec: 198245.5, 60 sec: 198518.4, 300 sec: 198385.0). Total num frames: 1342226432. Throughput: 0: 49632.9. Samples: 335522176. Policy #0 lag: (min: 1.0, avg: 17.5, max: 34.0) [2023-03-09 09:18:59,061][22664] Avg episode reward: [(0, '52.245')] [2023-03-09 09:18:59,327][23090] Updated weights for policy 0, policy_version 81926 (0.0020) [2023-03-09 09:19:00,194][23090] Updated weights for policy 0, policy_version 81937 (0.0017) [2023-03-09 09:19:01,055][23090] Updated weights for policy 0, policy_version 81947 (0.0016) [2023-03-09 09:19:01,848][23090] Updated weights for policy 0, policy_version 81957 (0.0012) [2023-03-09 09:19:02,657][23090] Updated weights for policy 0, policy_version 81967 (0.0016) [2023-03-09 09:19:03,507][23090] Updated weights for policy 0, policy_version 81977 (0.0013) [2023-03-09 09:19:04,059][22664] Fps is (10 sec: 196611.8, 60 sec: 198519.3, 300 sec: 198385.5). Total num frames: 1343209472. Throughput: 0: 49542.9. Samples: 335819040. Policy #0 lag: (min: 1.0, avg: 17.5, max: 34.0) [2023-03-09 09:19:04,059][22664] Avg episode reward: [(0, '54.843')] [2023-03-09 09:19:04,310][23090] Updated weights for policy 0, policy_version 81987 (0.0016) [2023-03-09 09:19:05,220][23090] Updated weights for policy 0, policy_version 81997 (0.0013) [2023-03-09 09:19:05,985][23090] Updated weights for policy 0, policy_version 82007 (0.0024) [2023-03-09 09:19:06,354][22940] Signal inference workers to stop experience collection... (27100 times) [2023-03-09 09:19:06,371][22940] Signal inference workers to resume experience collection... (27100 times) [2023-03-09 09:19:06,426][23090] InferenceWorker_p0-w0: stopping experience collection (27100 times) [2023-03-09 09:19:06,427][23090] InferenceWorker_p0-w0: resuming experience collection (27100 times) [2023-03-09 09:19:06,799][23090] Updated weights for policy 0, policy_version 82017 (0.0019) [2023-03-09 09:19:07,731][23090] Updated weights for policy 0, policy_version 82028 (0.0014) [2023-03-09 09:19:08,590][23090] Updated weights for policy 0, policy_version 82038 (0.0013) [2023-03-09 09:19:09,059][22664] Fps is (10 sec: 196610.9, 60 sec: 198247.2, 300 sec: 198385.4). Total num frames: 1344192512. Throughput: 0: 49590.2. Samples: 336115936. Policy #0 lag: (min: 1.0, avg: 17.5, max: 34.0) [2023-03-09 09:19:09,060][22664] Avg episode reward: [(0, '53.433')] [2023-03-09 09:19:09,373][23090] Updated weights for policy 0, policy_version 82048 (0.0013) [2023-03-09 09:19:10,261][23090] Updated weights for policy 0, policy_version 82058 (0.0013) [2023-03-09 09:19:11,160][23090] Updated weights for policy 0, policy_version 82069 (0.0021) [2023-03-09 09:19:11,977][23090] Updated weights for policy 0, policy_version 82079 (0.0017) [2023-03-09 09:19:12,829][23090] Updated weights for policy 0, policy_version 82089 (0.0013) [2023-03-09 09:19:13,643][23090] Updated weights for policy 0, policy_version 82099 (0.0020) [2023-03-09 09:19:14,059][22664] Fps is (10 sec: 196608.3, 60 sec: 197973.6, 300 sec: 198329.9). Total num frames: 1345175552. Throughput: 0: 49545.4. Samples: 336261296. Policy #0 lag: (min: 1.0, avg: 17.5, max: 34.0) [2023-03-09 09:19:14,060][22664] Avg episode reward: [(0, '54.090')] [2023-03-09 09:19:14,474][23090] Updated weights for policy 0, policy_version 82109 (0.0017) [2023-03-09 09:19:15,254][23090] Updated weights for policy 0, policy_version 82119 (0.0016) [2023-03-09 09:19:16,035][23090] Updated weights for policy 0, policy_version 82129 (0.0016) [2023-03-09 09:19:16,987][23090] Updated weights for policy 0, policy_version 82139 (0.0015) [2023-03-09 09:19:17,800][23090] Updated weights for policy 0, policy_version 82149 (0.0021) [2023-03-09 09:19:18,418][22940] Signal inference workers to stop experience collection... (27150 times) [2023-03-09 09:19:18,436][22940] Signal inference workers to resume experience collection... (27150 times) [2023-03-09 09:19:18,469][23090] InferenceWorker_p0-w0: stopping experience collection (27150 times) [2023-03-09 09:19:18,509][23090] InferenceWorker_p0-w0: resuming experience collection (27150 times) [2023-03-09 09:19:18,556][23090] Updated weights for policy 0, policy_version 82159 (0.0016) [2023-03-09 09:19:19,059][22664] Fps is (10 sec: 198247.8, 60 sec: 197973.5, 300 sec: 198385.4). Total num frames: 1346174976. Throughput: 0: 49544.1. Samples: 336560224. Policy #0 lag: (min: 1.0, avg: 17.5, max: 34.0) [2023-03-09 09:19:19,060][22664] Avg episode reward: [(0, '54.117')] [2023-03-09 09:19:19,137][22940] Saving /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000082166_1346207744.pth... [2023-03-09 09:19:19,196][22940] Removing /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000079258_1298563072.pth [2023-03-09 09:19:19,410][23090] Updated weights for policy 0, policy_version 82169 (0.0020) [2023-03-09 09:19:20,331][23090] Updated weights for policy 0, policy_version 82180 (0.0016) [2023-03-09 09:19:21,149][23090] Updated weights for policy 0, policy_version 82190 (0.0017) [2023-03-09 09:19:21,984][23090] Updated weights for policy 0, policy_version 82200 (0.0016) [2023-03-09 09:19:22,746][23090] Updated weights for policy 0, policy_version 82210 (0.0013) [2023-03-09 09:19:23,759][23090] Updated weights for policy 0, policy_version 82221 (0.0013) [2023-03-09 09:19:24,059][22664] Fps is (10 sec: 199879.8, 60 sec: 198246.6, 300 sec: 198385.2). Total num frames: 1347174400. Throughput: 0: 49541.4. Samples: 336857008. Policy #0 lag: (min: 1.0, avg: 17.5, max: 34.0) [2023-03-09 09:19:24,061][22664] Avg episode reward: [(0, '55.087')] [2023-03-09 09:19:24,552][23090] Updated weights for policy 0, policy_version 82231 (0.0019) [2023-03-09 09:19:25,342][23090] Updated weights for policy 0, policy_version 82241 (0.0020) [2023-03-09 09:19:26,266][23090] Updated weights for policy 0, policy_version 82251 (0.0013) [2023-03-09 09:19:27,088][23090] Updated weights for policy 0, policy_version 82261 (0.0017) [2023-03-09 09:19:27,830][23090] Updated weights for policy 0, policy_version 82271 (0.0020) [2023-03-09 09:19:28,758][23090] Updated weights for policy 0, policy_version 82281 (0.0014) [2023-03-09 09:19:29,059][22664] Fps is (10 sec: 198244.7, 60 sec: 198246.4, 300 sec: 198385.1). Total num frames: 1348157440. Throughput: 0: 49496.8. Samples: 337004448. Policy #0 lag: (min: 1.0, avg: 17.5, max: 34.0) [2023-03-09 09:19:29,060][22664] Avg episode reward: [(0, '55.455')] [2023-03-09 09:19:29,556][23090] Updated weights for policy 0, policy_version 82291 (0.0017) [2023-03-09 09:19:30,350][23090] Updated weights for policy 0, policy_version 82301 (0.0014) [2023-03-09 09:19:31,125][23090] Updated weights for policy 0, policy_version 82311 (0.0013) [2023-03-09 09:19:31,558][22940] Signal inference workers to stop experience collection... (27200 times) [2023-03-09 09:19:31,573][22940] Signal inference workers to resume experience collection... (27200 times) [2023-03-09 09:19:31,639][23090] InferenceWorker_p0-w0: stopping experience collection (27200 times) [2023-03-09 09:19:31,639][23090] InferenceWorker_p0-w0: resuming experience collection (27200 times) [2023-03-09 09:19:31,890][23090] Updated weights for policy 0, policy_version 82321 (0.0013) [2023-03-09 09:19:32,845][23090] Updated weights for policy 0, policy_version 82331 (0.0013) [2023-03-09 09:19:33,657][23090] Updated weights for policy 0, policy_version 82341 (0.0014) [2023-03-09 09:19:34,059][22664] Fps is (10 sec: 198245.1, 60 sec: 198518.2, 300 sec: 198440.6). Total num frames: 1349156864. Throughput: 0: 49496.4. Samples: 337303312. Policy #0 lag: (min: 1.0, avg: 17.5, max: 34.0) [2023-03-09 09:19:34,108][22664] Avg episode reward: [(0, '53.705')] [2023-03-09 09:19:34,395][23090] Updated weights for policy 0, policy_version 82351 (0.0013) [2023-03-09 09:19:35,282][23090] Updated weights for policy 0, policy_version 82361 (0.0037) [2023-03-09 09:19:36,117][23090] Updated weights for policy 0, policy_version 82371 (0.0015) [2023-03-09 09:19:36,976][23090] Updated weights for policy 0, policy_version 82381 (0.0021) [2023-03-09 09:19:37,762][23090] Updated weights for policy 0, policy_version 82391 (0.0016) [2023-03-09 09:19:38,614][23090] Updated weights for policy 0, policy_version 82401 (0.0021) [2023-03-09 09:19:39,059][22664] Fps is (10 sec: 199879.4, 60 sec: 198244.9, 300 sec: 198440.7). Total num frames: 1350156288. Throughput: 0: 49499.5. Samples: 337600176. Policy #0 lag: (min: 1.0, avg: 17.5, max: 34.0) [2023-03-09 09:19:39,061][22664] Avg episode reward: [(0, '52.529')] [2023-03-09 09:19:39,456][23090] Updated weights for policy 0, policy_version 82411 (0.0020) [2023-03-09 09:19:40,288][23090] Updated weights for policy 0, policy_version 82422 (0.0017) [2023-03-09 09:19:41,136][23090] Updated weights for policy 0, policy_version 82432 (0.0013) [2023-03-09 09:19:42,008][23090] Updated weights for policy 0, policy_version 82442 (0.0017) [2023-03-09 09:19:42,824][23090] Updated weights for policy 0, policy_version 82452 (0.0018) [2023-03-09 09:19:43,577][23090] Updated weights for policy 0, policy_version 82462 (0.0018) [2023-03-09 09:19:44,059][22664] Fps is (10 sec: 198251.1, 60 sec: 198246.4, 300 sec: 198385.7). Total num frames: 1351139328. Throughput: 0: 49499.2. Samples: 337749632. Policy #0 lag: (min: 1.0, avg: 17.5, max: 34.0) [2023-03-09 09:19:44,060][22664] Avg episode reward: [(0, '54.493')] [2023-03-09 09:19:44,408][23090] Updated weights for policy 0, policy_version 82472 (0.0017) [2023-03-09 09:19:45,362][23090] Updated weights for policy 0, policy_version 82483 (0.0017) [2023-03-09 09:19:46,183][23090] Updated weights for policy 0, policy_version 82493 (0.0013) [2023-03-09 09:19:46,871][22940] Signal inference workers to stop experience collection... (27250 times) [2023-03-09 09:19:46,872][22940] Signal inference workers to resume experience collection... (27250 times) [2023-03-09 09:19:46,940][23090] InferenceWorker_p0-w0: stopping experience collection (27250 times) [2023-03-09 09:19:46,940][23090] InferenceWorker_p0-w0: resuming experience collection (27250 times) [2023-03-09 09:19:46,985][23090] Updated weights for policy 0, policy_version 82503 (0.0016) [2023-03-09 09:19:47,903][23090] Updated weights for policy 0, policy_version 82514 (0.0017) [2023-03-09 09:19:48,768][23090] Updated weights for policy 0, policy_version 82524 (0.0024) [2023-03-09 09:19:49,059][22664] Fps is (10 sec: 196611.6, 60 sec: 197973.3, 300 sec: 198385.2). Total num frames: 1352122368. Throughput: 0: 49499.9. Samples: 338046544. Policy #0 lag: (min: 1.0, avg: 16.7, max: 33.0) [2023-03-09 09:19:49,061][22664] Avg episode reward: [(0, '53.923')] [2023-03-09 09:19:49,591][23090] Updated weights for policy 0, policy_version 82534 (0.0019) [2023-03-09 09:19:50,389][23090] Updated weights for policy 0, policy_version 82544 (0.0029) [2023-03-09 09:19:51,294][23090] Updated weights for policy 0, policy_version 82554 (0.0014) [2023-03-09 09:19:52,105][23090] Updated weights for policy 0, policy_version 82564 (0.0020) [2023-03-09 09:19:52,923][23090] Updated weights for policy 0, policy_version 82574 (0.0022) [2023-03-09 09:19:53,763][23090] Updated weights for policy 0, policy_version 82584 (0.0017) [2023-03-09 09:19:54,059][22664] Fps is (10 sec: 196605.1, 60 sec: 197700.2, 300 sec: 198329.8). Total num frames: 1353105408. Throughput: 0: 49453.8. Samples: 338341360. Policy #0 lag: (min: 1.0, avg: 16.7, max: 33.0) [2023-03-09 09:19:54,060][22664] Avg episode reward: [(0, '51.464')] [2023-03-09 09:19:54,546][23090] Updated weights for policy 0, policy_version 82594 (0.0017) [2023-03-09 09:19:55,481][23090] Updated weights for policy 0, policy_version 82604 (0.0013) [2023-03-09 09:19:56,241][23090] Updated weights for policy 0, policy_version 82614 (0.0013) [2023-03-09 09:19:57,021][23090] Updated weights for policy 0, policy_version 82624 (0.0020) [2023-03-09 09:19:57,918][23090] Updated weights for policy 0, policy_version 82634 (0.0013) [2023-03-09 09:19:58,795][23090] Updated weights for policy 0, policy_version 82644 (0.0017) [2023-03-09 09:19:59,059][22664] Fps is (10 sec: 198250.0, 60 sec: 197974.1, 300 sec: 198440.8). Total num frames: 1354104832. Throughput: 0: 49545.6. Samples: 338490848. Policy #0 lag: (min: 1.0, avg: 16.7, max: 33.0) [2023-03-09 09:19:59,060][22664] Avg episode reward: [(0, '53.130')] [2023-03-09 09:19:59,509][23090] Updated weights for policy 0, policy_version 82654 (0.0014) [2023-03-09 09:20:00,340][23090] Updated weights for policy 0, policy_version 82664 (0.0020) [2023-03-09 09:20:01,163][23090] Updated weights for policy 0, policy_version 82674 (0.0015) [2023-03-09 09:20:02,117][23090] Updated weights for policy 0, policy_version 82685 (0.0020) [2023-03-09 09:20:02,910][23090] Updated weights for policy 0, policy_version 82695 (0.0025) [2023-03-09 09:20:03,478][22940] Signal inference workers to stop experience collection... (27300 times) [2023-03-09 09:20:03,497][22940] Signal inference workers to resume experience collection... (27300 times) [2023-03-09 09:20:03,548][23090] InferenceWorker_p0-w0: stopping experience collection (27300 times) [2023-03-09 09:20:03,551][23090] InferenceWorker_p0-w0: resuming experience collection (27300 times) [2023-03-09 09:20:03,714][23090] Updated weights for policy 0, policy_version 82705 (0.0013) [2023-03-09 09:20:04,058][22664] Fps is (10 sec: 196613.6, 60 sec: 197700.5, 300 sec: 198274.2). Total num frames: 1355071488. Throughput: 0: 49501.3. Samples: 338787776. Policy #0 lag: (min: 1.0, avg: 16.7, max: 33.0) [2023-03-09 09:20:04,059][22664] Avg episode reward: [(0, '56.459')] [2023-03-09 09:20:04,693][23090] Updated weights for policy 0, policy_version 82715 (0.0021) [2023-03-09 09:20:05,441][23090] Updated weights for policy 0, policy_version 82725 (0.0013) [2023-03-09 09:20:06,265][23090] Updated weights for policy 0, policy_version 82735 (0.0016) [2023-03-09 09:20:07,114][23090] Updated weights for policy 0, policy_version 82745 (0.0020) [2023-03-09 09:20:07,918][23090] Updated weights for policy 0, policy_version 82755 (0.0013) [2023-03-09 09:20:08,777][23090] Updated weights for policy 0, policy_version 82765 (0.0024) [2023-03-09 09:20:09,059][22664] Fps is (10 sec: 198241.1, 60 sec: 198245.8, 300 sec: 198385.2). Total num frames: 1356087296. Throughput: 0: 49458.8. Samples: 339082656. Policy #0 lag: (min: 1.0, avg: 16.7, max: 33.0) [2023-03-09 09:20:09,061][22664] Avg episode reward: [(0, '52.885')] [2023-03-09 09:20:09,560][23090] Updated weights for policy 0, policy_version 82775 (0.0013) [2023-03-09 09:20:10,350][23090] Updated weights for policy 0, policy_version 82785 (0.0013) [2023-03-09 09:20:11,274][23090] Updated weights for policy 0, policy_version 82795 (0.0022) [2023-03-09 09:20:12,060][23090] Updated weights for policy 0, policy_version 82805 (0.0013) [2023-03-09 09:20:12,993][23090] Updated weights for policy 0, policy_version 82816 (0.0019) [2023-03-09 09:20:13,848][23090] Updated weights for policy 0, policy_version 82826 (0.0015) [2023-03-09 09:20:14,059][22664] Fps is (10 sec: 198232.9, 60 sec: 197971.3, 300 sec: 198329.3). Total num frames: 1357053952. Throughput: 0: 49502.0. Samples: 339232064. Policy #0 lag: (min: 1.0, avg: 16.7, max: 33.0) [2023-03-09 09:20:14,061][22664] Avg episode reward: [(0, '55.473')] [2023-03-09 09:20:14,681][23090] Updated weights for policy 0, policy_version 82836 (0.0013) [2023-03-09 09:20:15,458][23090] Updated weights for policy 0, policy_version 82846 (0.0013) [2023-03-09 09:20:16,292][23090] Updated weights for policy 0, policy_version 82856 (0.0013) [2023-03-09 09:20:16,819][22940] Signal inference workers to stop experience collection... (27350 times) [2023-03-09 09:20:16,838][22940] Signal inference workers to resume experience collection... (27350 times) [2023-03-09 09:20:16,862][23090] InferenceWorker_p0-w0: stopping experience collection (27350 times) [2023-03-09 09:20:16,862][23090] InferenceWorker_p0-w0: resuming experience collection (27350 times) [2023-03-09 09:20:17,103][23090] Updated weights for policy 0, policy_version 82866 (0.0023) [2023-03-09 09:20:17,982][23090] Updated weights for policy 0, policy_version 82876 (0.0013) [2023-03-09 09:20:18,751][23090] Updated weights for policy 0, policy_version 82886 (0.0020) [2023-03-09 09:20:19,059][22664] Fps is (10 sec: 196607.8, 60 sec: 197972.5, 300 sec: 198385.2). Total num frames: 1358053376. Throughput: 0: 49456.0. Samples: 339528832. Policy #0 lag: (min: 1.0, avg: 16.7, max: 33.0) [2023-03-09 09:20:19,061][22664] Avg episode reward: [(0, '52.483')] [2023-03-09 09:20:19,543][23090] Updated weights for policy 0, policy_version 82896 (0.0016) [2023-03-09 09:20:20,478][23090] Updated weights for policy 0, policy_version 82906 (0.0018) [2023-03-09 09:20:21,320][23090] Updated weights for policy 0, policy_version 82916 (0.0020) [2023-03-09 09:20:22,066][23090] Updated weights for policy 0, policy_version 82926 (0.0024) [2023-03-09 09:20:22,905][23090] Updated weights for policy 0, policy_version 82936 (0.0013) [2023-03-09 09:20:23,692][23090] Updated weights for policy 0, policy_version 82946 (0.0013) [2023-03-09 09:20:24,059][22664] Fps is (10 sec: 199893.1, 60 sec: 197973.5, 300 sec: 198385.2). Total num frames: 1359052800. Throughput: 0: 49455.5. Samples: 339825664. Policy #0 lag: (min: 1.0, avg: 16.7, max: 33.0) [2023-03-09 09:20:24,061][22664] Avg episode reward: [(0, '53.710')] [2023-03-09 09:20:24,619][23090] Updated weights for policy 0, policy_version 82956 (0.0017) [2023-03-09 09:20:25,382][23090] Updated weights for policy 0, policy_version 82966 (0.0016) [2023-03-09 09:20:26,178][23090] Updated weights for policy 0, policy_version 82976 (0.0013) [2023-03-09 09:20:27,059][23090] Updated weights for policy 0, policy_version 82986 (0.0017) [2023-03-09 09:20:27,871][23090] Updated weights for policy 0, policy_version 82996 (0.0014) [2023-03-09 09:20:28,446][22940] Signal inference workers to stop experience collection... (27400 times) [2023-03-09 09:20:28,464][22940] Signal inference workers to resume experience collection... (27400 times) [2023-03-09 09:20:28,514][23090] InferenceWorker_p0-w0: stopping experience collection (27400 times) [2023-03-09 09:20:28,514][23090] InferenceWorker_p0-w0: resuming experience collection (27400 times) [2023-03-09 09:20:28,638][23090] Updated weights for policy 0, policy_version 83006 (0.0016) [2023-03-09 09:20:29,058][22664] Fps is (10 sec: 198253.2, 60 sec: 197973.9, 300 sec: 198274.2). Total num frames: 1360035840. Throughput: 0: 49455.4. Samples: 339975120. Policy #0 lag: (min: 1.0, avg: 16.7, max: 33.0) [2023-03-09 09:20:29,060][22664] Avg episode reward: [(0, '53.187')] [2023-03-09 09:20:29,474][23090] Updated weights for policy 0, policy_version 83016 (0.0015) [2023-03-09 09:20:30,292][23090] Updated weights for policy 0, policy_version 83026 (0.0013) [2023-03-09 09:20:31,160][23090] Updated weights for policy 0, policy_version 83036 (0.0019) [2023-03-09 09:20:31,952][23090] Updated weights for policy 0, policy_version 83046 (0.0016) [2023-03-09 09:20:32,722][23090] Updated weights for policy 0, policy_version 83056 (0.0015) [2023-03-09 09:20:33,651][23090] Updated weights for policy 0, policy_version 83066 (0.0018) [2023-03-09 09:20:34,059][22664] Fps is (10 sec: 198245.5, 60 sec: 197973.5, 300 sec: 198329.7). Total num frames: 1361035264. Throughput: 0: 49499.7. Samples: 340274032. Policy #0 lag: (min: 1.0, avg: 16.7, max: 33.0) [2023-03-09 09:20:34,061][22664] Avg episode reward: [(0, '53.602')] [2023-03-09 09:20:34,499][23090] Updated weights for policy 0, policy_version 83076 (0.0021) [2023-03-09 09:20:35,271][23090] Updated weights for policy 0, policy_version 83086 (0.0016) [2023-03-09 09:20:36,048][23090] Updated weights for policy 0, policy_version 83096 (0.0013) [2023-03-09 09:20:36,887][23090] Updated weights for policy 0, policy_version 83106 (0.0013) [2023-03-09 09:20:37,733][23090] Updated weights for policy 0, policy_version 83116 (0.0013) [2023-03-09 09:20:38,482][22940] Signal inference workers to stop experience collection... (27450 times) [2023-03-09 09:20:38,495][22940] Signal inference workers to resume experience collection... (27450 times) [2023-03-09 09:20:38,561][23090] InferenceWorker_p0-w0: stopping experience collection (27450 times) [2023-03-09 09:20:38,562][23090] InferenceWorker_p0-w0: resuming experience collection (27450 times) [2023-03-09 09:20:38,606][23090] Updated weights for policy 0, policy_version 83127 (0.0013) [2023-03-09 09:20:39,059][22664] Fps is (10 sec: 198239.4, 60 sec: 197700.5, 300 sec: 198218.4). Total num frames: 1362018304. Throughput: 0: 49589.2. Samples: 340572880. Policy #0 lag: (min: 1.0, avg: 17.1, max: 33.0) [2023-03-09 09:20:39,061][22664] Avg episode reward: [(0, '54.809')] [2023-03-09 09:20:39,416][23090] Updated weights for policy 0, policy_version 83137 (0.0013) [2023-03-09 09:20:40,309][23090] Updated weights for policy 0, policy_version 83147 (0.0013) [2023-03-09 09:20:41,125][23090] Updated weights for policy 0, policy_version 83157 (0.0026) [2023-03-09 09:20:41,875][23090] Updated weights for policy 0, policy_version 83167 (0.0013) [2023-03-09 09:20:42,718][23090] Updated weights for policy 0, policy_version 83177 (0.0013) [2023-03-09 09:20:43,689][23090] Updated weights for policy 0, policy_version 83188 (0.0013) [2023-03-09 09:20:44,058][22664] Fps is (10 sec: 198251.8, 60 sec: 197973.7, 300 sec: 198274.2). Total num frames: 1363017728. Throughput: 0: 49588.3. Samples: 340722320. Policy #0 lag: (min: 1.0, avg: 17.1, max: 33.0) [2023-03-09 09:20:44,060][22664] Avg episode reward: [(0, '52.467')] [2023-03-09 09:20:44,473][23090] Updated weights for policy 0, policy_version 83198 (0.0017) [2023-03-09 09:20:45,304][23090] Updated weights for policy 0, policy_version 83208 (0.0013) [2023-03-09 09:20:46,189][23090] Updated weights for policy 0, policy_version 83218 (0.0016) [2023-03-09 09:20:47,022][23090] Updated weights for policy 0, policy_version 83228 (0.0013) [2023-03-09 09:20:47,826][23090] Updated weights for policy 0, policy_version 83238 (0.0013) [2023-03-09 09:20:48,563][23090] Updated weights for policy 0, policy_version 83248 (0.0013) [2023-03-09 09:20:49,059][22664] Fps is (10 sec: 199888.3, 60 sec: 198246.6, 300 sec: 198274.0). Total num frames: 1364017152. Throughput: 0: 49585.9. Samples: 341019152. Policy #0 lag: (min: 1.0, avg: 17.1, max: 33.0) [2023-03-09 09:20:49,060][22664] Avg episode reward: [(0, '53.362')] [2023-03-09 09:20:49,510][23090] Updated weights for policy 0, policy_version 83258 (0.0018) [2023-03-09 09:20:49,939][22940] Signal inference workers to stop experience collection... (27500 times) [2023-03-09 09:20:49,940][22940] Signal inference workers to resume experience collection... (27500 times) [2023-03-09 09:20:50,000][23090] InferenceWorker_p0-w0: stopping experience collection (27500 times) [2023-03-09 09:20:50,001][23090] InferenceWorker_p0-w0: resuming experience collection (27500 times) [2023-03-09 09:20:50,284][23090] Updated weights for policy 0, policy_version 83268 (0.0024) [2023-03-09 09:20:51,093][23090] Updated weights for policy 0, policy_version 83278 (0.0013) [2023-03-09 09:20:51,944][23090] Updated weights for policy 0, policy_version 83288 (0.0019) [2023-03-09 09:20:52,739][23090] Updated weights for policy 0, policy_version 83298 (0.0018) [2023-03-09 09:20:53,647][23090] Updated weights for policy 0, policy_version 83308 (0.0017) [2023-03-09 09:20:54,059][22664] Fps is (10 sec: 199876.4, 60 sec: 198518.9, 300 sec: 198329.6). Total num frames: 1365016576. Throughput: 0: 49628.3. Samples: 341315936. Policy #0 lag: (min: 1.0, avg: 17.1, max: 33.0) [2023-03-09 09:20:54,061][22664] Avg episode reward: [(0, '53.422')] [2023-03-09 09:20:54,400][23090] Updated weights for policy 0, policy_version 83318 (0.0019) [2023-03-09 09:20:55,196][23090] Updated weights for policy 0, policy_version 83328 (0.0021) [2023-03-09 09:20:56,042][23090] Updated weights for policy 0, policy_version 83338 (0.0013) [2023-03-09 09:20:56,869][23090] Updated weights for policy 0, policy_version 83348 (0.0013) [2023-03-09 09:20:57,691][23090] Updated weights for policy 0, policy_version 83358 (0.0013) [2023-03-09 09:20:58,467][23090] Updated weights for policy 0, policy_version 83368 (0.0013) [2023-03-09 09:20:59,058][22664] Fps is (10 sec: 199888.8, 60 sec: 198519.7, 300 sec: 198329.8). Total num frames: 1366016000. Throughput: 0: 49675.7. Samples: 341467440. Policy #0 lag: (min: 1.0, avg: 17.1, max: 33.0) [2023-03-09 09:20:59,059][22664] Avg episode reward: [(0, '55.612')] [2023-03-09 09:20:59,301][23090] Updated weights for policy 0, policy_version 83378 (0.0019) [2023-03-09 09:21:00,191][23090] Updated weights for policy 0, policy_version 83388 (0.0014) [2023-03-09 09:21:00,983][23090] Updated weights for policy 0, policy_version 83398 (0.0017) [2023-03-09 09:21:01,630][22940] Signal inference workers to stop experience collection... (27550 times) [2023-03-09 09:21:01,650][22940] Signal inference workers to resume experience collection... (27550 times) [2023-03-09 09:21:01,713][23090] InferenceWorker_p0-w0: stopping experience collection (27550 times) [2023-03-09 09:21:01,713][23090] InferenceWorker_p0-w0: resuming experience collection (27550 times) [2023-03-09 09:21:01,716][23090] Updated weights for policy 0, policy_version 83408 (0.0013) [2023-03-09 09:21:02,694][23090] Updated weights for policy 0, policy_version 83418 (0.0015) [2023-03-09 09:21:03,565][23090] Updated weights for policy 0, policy_version 83429 (0.0013) [2023-03-09 09:21:04,059][22664] Fps is (10 sec: 198248.7, 60 sec: 198791.4, 300 sec: 198329.6). Total num frames: 1366999040. Throughput: 0: 49678.3. Samples: 341764352. Policy #0 lag: (min: 1.0, avg: 17.1, max: 33.0) [2023-03-09 09:21:04,061][22664] Avg episode reward: [(0, '53.374')] [2023-03-09 09:21:04,304][23090] Updated weights for policy 0, policy_version 83439 (0.0025) [2023-03-09 09:21:05,209][23090] Updated weights for policy 0, policy_version 83449 (0.0016) [2023-03-09 09:21:05,979][23090] Updated weights for policy 0, policy_version 83459 (0.0016) [2023-03-09 09:21:06,816][23090] Updated weights for policy 0, policy_version 83469 (0.0013) [2023-03-09 09:21:07,593][23090] Updated weights for policy 0, policy_version 83479 (0.0017) [2023-03-09 09:21:08,418][23090] Updated weights for policy 0, policy_version 83489 (0.0017) [2023-03-09 09:21:09,059][22664] Fps is (10 sec: 198237.5, 60 sec: 198519.1, 300 sec: 198385.1). Total num frames: 1367998464. Throughput: 0: 49769.4. Samples: 342065296. Policy #0 lag: (min: 1.0, avg: 17.1, max: 33.0) [2023-03-09 09:21:09,106][22664] Avg episode reward: [(0, '54.019')] [2023-03-09 09:21:09,269][23090] Updated weights for policy 0, policy_version 83499 (0.0016) [2023-03-09 09:21:10,121][23090] Updated weights for policy 0, policy_version 83509 (0.0013) [2023-03-09 09:21:11,041][23090] Updated weights for policy 0, policy_version 83520 (0.0017) [2023-03-09 09:21:11,846][23090] Updated weights for policy 0, policy_version 83530 (0.0020) [2023-03-09 09:21:12,668][23090] Updated weights for policy 0, policy_version 83540 (0.0013) [2023-03-09 09:21:13,303][22940] Signal inference workers to stop experience collection... (27600 times) [2023-03-09 09:21:13,304][22940] Signal inference workers to resume experience collection... (27600 times) [2023-03-09 09:21:13,383][23090] InferenceWorker_p0-w0: stopping experience collection (27600 times) [2023-03-09 09:21:13,383][23090] InferenceWorker_p0-w0: resuming experience collection (27600 times) [2023-03-09 09:21:13,470][23090] Updated weights for policy 0, policy_version 83550 (0.0017) [2023-03-09 09:21:14,059][22664] Fps is (10 sec: 198243.0, 60 sec: 198793.1, 300 sec: 198274.1). Total num frames: 1368981504. Throughput: 0: 49723.6. Samples: 342212704. Policy #0 lag: (min: 1.0, avg: 17.1, max: 33.0) [2023-03-09 09:21:14,061][22664] Avg episode reward: [(0, '54.889')] [2023-03-09 09:21:14,265][23090] Updated weights for policy 0, policy_version 83560 (0.0015) [2023-03-09 09:21:15,097][23090] Updated weights for policy 0, policy_version 83570 (0.0017) [2023-03-09 09:21:15,957][23090] Updated weights for policy 0, policy_version 83580 (0.0022) [2023-03-09 09:21:16,795][23090] Updated weights for policy 0, policy_version 83590 (0.0013) [2023-03-09 09:21:17,617][23090] Updated weights for policy 0, policy_version 83601 (0.0013) [2023-03-09 09:21:18,575][23090] Updated weights for policy 0, policy_version 83611 (0.0013) [2023-03-09 09:21:19,058][22664] Fps is (10 sec: 199893.6, 60 sec: 199066.8, 300 sec: 198440.8). Total num frames: 1369997312. Throughput: 0: 49724.4. Samples: 342511616. Policy #0 lag: (min: 1.0, avg: 17.1, max: 33.0) [2023-03-09 09:21:19,059][22664] Avg episode reward: [(0, '52.589')] [2023-03-09 09:21:19,107][22940] Saving /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000083618_1369997312.pth... [2023-03-09 09:21:19,170][22940] Removing /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000080711_1322369024.pth [2023-03-09 09:21:19,389][23090] Updated weights for policy 0, policy_version 83621 (0.0013) [2023-03-09 09:21:20,112][23090] Updated weights for policy 0, policy_version 83631 (0.0016) [2023-03-09 09:21:21,034][23090] Updated weights for policy 0, policy_version 83641 (0.0013) [2023-03-09 09:21:21,821][23090] Updated weights for policy 0, policy_version 83651 (0.0015) [2023-03-09 09:21:22,632][23090] Updated weights for policy 0, policy_version 83661 (0.0022) [2023-03-09 09:21:23,443][23090] Updated weights for policy 0, policy_version 83671 (0.0013) [2023-03-09 09:21:24,059][22664] Fps is (10 sec: 201528.0, 60 sec: 199065.6, 300 sec: 198441.0). Total num frames: 1370996736. Throughput: 0: 49724.2. Samples: 342810464. Policy #0 lag: (min: 1.0, avg: 17.1, max: 33.0) [2023-03-09 09:21:24,061][22664] Avg episode reward: [(0, '54.466')] [2023-03-09 09:21:24,229][23090] Updated weights for policy 0, policy_version 83681 (0.0018) [2023-03-09 09:21:25,090][23090] Updated weights for policy 0, policy_version 83691 (0.0016) [2023-03-09 09:21:25,177][22940] Signal inference workers to stop experience collection... (27650 times) [2023-03-09 09:21:25,193][22940] Signal inference workers to resume experience collection... (27650 times) [2023-03-09 09:21:25,251][23090] InferenceWorker_p0-w0: stopping experience collection (27650 times) [2023-03-09 09:21:25,254][23090] InferenceWorker_p0-w0: resuming experience collection (27650 times) [2023-03-09 09:21:25,888][23090] Updated weights for policy 0, policy_version 83701 (0.0017) [2023-03-09 09:21:26,696][23090] Updated weights for policy 0, policy_version 83711 (0.0015) [2023-03-09 09:21:27,572][23090] Updated weights for policy 0, policy_version 83721 (0.0020) [2023-03-09 09:21:28,390][23090] Updated weights for policy 0, policy_version 83731 (0.0015) [2023-03-09 09:21:29,058][22664] Fps is (10 sec: 196607.4, 60 sec: 198792.5, 300 sec: 198329.7). Total num frames: 1371963392. Throughput: 0: 49724.8. Samples: 342959936. Policy #0 lag: (min: 2.0, avg: 18.0, max: 34.0) [2023-03-09 09:21:29,060][22664] Avg episode reward: [(0, '51.539')] [2023-03-09 09:21:29,231][23090] Updated weights for policy 0, policy_version 83741 (0.0016) [2023-03-09 09:21:30,032][23090] Updated weights for policy 0, policy_version 83751 (0.0016) [2023-03-09 09:21:30,947][23090] Updated weights for policy 0, policy_version 83762 (0.0014) [2023-03-09 09:21:31,860][23090] Updated weights for policy 0, policy_version 83773 (0.0013) [2023-03-09 09:21:32,683][23090] Updated weights for policy 0, policy_version 83783 (0.0013) [2023-03-09 09:21:33,440][23090] Updated weights for policy 0, policy_version 83793 (0.0022) [2023-03-09 09:21:34,059][22664] Fps is (10 sec: 196607.9, 60 sec: 198792.6, 300 sec: 198385.3). Total num frames: 1372962816. Throughput: 0: 49726.1. Samples: 343256832. Policy #0 lag: (min: 2.0, avg: 18.0, max: 34.0) [2023-03-09 09:21:34,061][22664] Avg episode reward: [(0, '52.603')] [2023-03-09 09:21:34,416][23090] Updated weights for policy 0, policy_version 83803 (0.0019) [2023-03-09 09:21:35,219][23090] Updated weights for policy 0, policy_version 83813 (0.0013) [2023-03-09 09:21:35,960][23090] Updated weights for policy 0, policy_version 83823 (0.0019) [2023-03-09 09:21:36,882][23090] Updated weights for policy 0, policy_version 83833 (0.0019) [2023-03-09 09:21:37,614][23090] Updated weights for policy 0, policy_version 83843 (0.0013) [2023-03-09 09:21:38,410][22940] Signal inference workers to stop experience collection... (27700 times) [2023-03-09 09:21:38,435][22940] Signal inference workers to resume experience collection... (27700 times) [2023-03-09 09:21:38,439][23090] Updated weights for policy 0, policy_version 83853 (0.0020) [2023-03-09 09:21:38,476][23090] InferenceWorker_p0-w0: stopping experience collection (27700 times) [2023-03-09 09:21:38,483][23090] InferenceWorker_p0-w0: resuming experience collection (27700 times) [2023-03-09 09:21:39,059][22664] Fps is (10 sec: 199878.2, 60 sec: 199065.6, 300 sec: 198385.2). Total num frames: 1373962240. Throughput: 0: 49772.2. Samples: 343555680. Policy #0 lag: (min: 2.0, avg: 18.0, max: 34.0) [2023-03-09 09:21:39,061][22664] Avg episode reward: [(0, '53.614')] [2023-03-09 09:21:39,263][23090] Updated weights for policy 0, policy_version 83863 (0.0020) [2023-03-09 09:21:40,160][23090] Updated weights for policy 0, policy_version 83874 (0.0016) [2023-03-09 09:21:41,048][23090] Updated weights for policy 0, policy_version 83884 (0.0023) [2023-03-09 09:21:41,849][23090] Updated weights for policy 0, policy_version 83894 (0.0016) [2023-03-09 09:21:42,624][23090] Updated weights for policy 0, policy_version 83904 (0.0016) [2023-03-09 09:21:43,500][23090] Updated weights for policy 0, policy_version 83914 (0.0016) [2023-03-09 09:21:44,058][22664] Fps is (10 sec: 199889.6, 60 sec: 199065.6, 300 sec: 198440.8). Total num frames: 1374961664. Throughput: 0: 49681.4. Samples: 343703104. Policy #0 lag: (min: 2.0, avg: 18.0, max: 34.0) [2023-03-09 09:21:44,060][22664] Avg episode reward: [(0, '54.472')] [2023-03-09 09:21:44,323][23090] Updated weights for policy 0, policy_version 83924 (0.0016) [2023-03-09 09:21:45,148][23090] Updated weights for policy 0, policy_version 83934 (0.0017) [2023-03-09 09:21:45,991][23090] Updated weights for policy 0, policy_version 83944 (0.0018) [2023-03-09 09:21:46,794][23090] Updated weights for policy 0, policy_version 83954 (0.0013) [2023-03-09 09:21:47,681][23090] Updated weights for policy 0, policy_version 83964 (0.0017) [2023-03-09 09:21:48,493][23090] Updated weights for policy 0, policy_version 83974 (0.0013) [2023-03-09 09:21:49,058][22664] Fps is (10 sec: 198253.4, 60 sec: 198793.1, 300 sec: 198440.9). Total num frames: 1375944704. Throughput: 0: 49681.4. Samples: 344000000. Policy #0 lag: (min: 2.0, avg: 18.0, max: 34.0) [2023-03-09 09:21:49,060][22664] Avg episode reward: [(0, '55.961')] [2023-03-09 09:21:49,222][23090] Updated weights for policy 0, policy_version 83984 (0.0016) [2023-03-09 09:21:50,242][23090] Updated weights for policy 0, policy_version 83994 (0.0016) [2023-03-09 09:21:51,005][23090] Updated weights for policy 0, policy_version 84004 (0.0019) [2023-03-09 09:21:51,801][23090] Updated weights for policy 0, policy_version 84014 (0.0015) [2023-03-09 09:21:52,622][23090] Updated weights for policy 0, policy_version 84024 (0.0013) [2023-03-09 09:21:53,408][23090] Updated weights for policy 0, policy_version 84034 (0.0017) [2023-03-09 09:21:53,648][22940] Signal inference workers to stop experience collection... (27750 times) [2023-03-09 09:21:53,661][22940] Signal inference workers to resume experience collection... (27750 times) [2023-03-09 09:21:53,721][23090] InferenceWorker_p0-w0: stopping experience collection (27750 times) [2023-03-09 09:21:53,721][23090] InferenceWorker_p0-w0: resuming experience collection (27750 times) [2023-03-09 09:21:54,059][22664] Fps is (10 sec: 196602.8, 60 sec: 198519.9, 300 sec: 198385.3). Total num frames: 1376927744. Throughput: 0: 49592.7. Samples: 344296960. Policy #0 lag: (min: 2.0, avg: 18.0, max: 34.0) [2023-03-09 09:21:54,061][22664] Avg episode reward: [(0, '53.283')] [2023-03-09 09:21:54,262][23090] Updated weights for policy 0, policy_version 84044 (0.0013) [2023-03-09 09:21:55,193][23090] Updated weights for policy 0, policy_version 84055 (0.0017) [2023-03-09 09:21:55,979][23090] Updated weights for policy 0, policy_version 84065 (0.0013) [2023-03-09 09:21:56,982][23090] Updated weights for policy 0, policy_version 84076 (0.0016) [2023-03-09 09:21:57,764][23090] Updated weights for policy 0, policy_version 84086 (0.0013) [2023-03-09 09:21:58,562][23090] Updated weights for policy 0, policy_version 84096 (0.0015) [2023-03-09 09:21:59,059][22664] Fps is (10 sec: 196602.3, 60 sec: 198245.4, 300 sec: 198329.6). Total num frames: 1377910784. Throughput: 0: 49593.8. Samples: 344444416. Policy #0 lag: (min: 2.0, avg: 18.0, max: 34.0) [2023-03-09 09:21:59,061][22664] Avg episode reward: [(0, '53.940')] [2023-03-09 09:21:59,414][23090] Updated weights for policy 0, policy_version 84106 (0.0013) [2023-03-09 09:22:00,231][23090] Updated weights for policy 0, policy_version 84116 (0.0020) [2023-03-09 09:22:01,060][23090] Updated weights for policy 0, policy_version 84126 (0.0016) [2023-03-09 09:22:01,833][23090] Updated weights for policy 0, policy_version 84136 (0.0016) [2023-03-09 09:22:02,777][23090] Updated weights for policy 0, policy_version 84147 (0.0018) [2023-03-09 09:22:03,669][23090] Updated weights for policy 0, policy_version 84158 (0.0013) [2023-03-09 09:22:04,059][22664] Fps is (10 sec: 198247.9, 60 sec: 198519.8, 300 sec: 198330.1). Total num frames: 1378910208. Throughput: 0: 49594.1. Samples: 344743360. Policy #0 lag: (min: 2.0, avg: 18.0, max: 34.0) [2023-03-09 09:22:04,060][22664] Avg episode reward: [(0, '54.969')] [2023-03-09 09:22:04,493][23090] Updated weights for policy 0, policy_version 84168 (0.0021) [2023-03-09 09:22:05,432][23090] Updated weights for policy 0, policy_version 84179 (0.0016) [2023-03-09 09:22:06,285][23090] Updated weights for policy 0, policy_version 84189 (0.0013) [2023-03-09 09:22:07,072][23090] Updated weights for policy 0, policy_version 84199 (0.0020) [2023-03-09 09:22:07,282][22940] Signal inference workers to stop experience collection... (27800 times) [2023-03-09 09:22:07,286][22940] Signal inference workers to resume experience collection... (27800 times) [2023-03-09 09:22:07,348][23090] InferenceWorker_p0-w0: stopping experience collection (27800 times) [2023-03-09 09:22:07,348][23090] InferenceWorker_p0-w0: resuming experience collection (27800 times) [2023-03-09 09:22:07,803][23090] Updated weights for policy 0, policy_version 84209 (0.0024) [2023-03-09 09:22:08,815][23090] Updated weights for policy 0, policy_version 84219 (0.0018) [2023-03-09 09:22:09,059][22664] Fps is (10 sec: 199888.5, 60 sec: 198520.5, 300 sec: 198440.7). Total num frames: 1379909632. Throughput: 0: 49551.1. Samples: 345040256. Policy #0 lag: (min: 2.0, avg: 18.0, max: 34.0) [2023-03-09 09:22:09,060][22664] Avg episode reward: [(0, '54.160')] [2023-03-09 09:22:09,588][23090] Updated weights for policy 0, policy_version 84229 (0.0020) [2023-03-09 09:22:10,300][23090] Updated weights for policy 0, policy_version 84239 (0.0013) [2023-03-09 09:22:11,244][23090] Updated weights for policy 0, policy_version 84249 (0.0014) [2023-03-09 09:22:12,037][23090] Updated weights for policy 0, policy_version 84259 (0.0016) [2023-03-09 09:22:12,874][23090] Updated weights for policy 0, policy_version 84269 (0.0016) [2023-03-09 09:22:13,688][23090] Updated weights for policy 0, policy_version 84279 (0.0016) [2023-03-09 09:22:14,058][22664] Fps is (10 sec: 196612.7, 60 sec: 198248.1, 300 sec: 198329.8). Total num frames: 1380876288. Throughput: 0: 49551.7. Samples: 345189760. Policy #0 lag: (min: 2.0, avg: 18.0, max: 34.0) [2023-03-09 09:22:14,059][22664] Avg episode reward: [(0, '52.556')] [2023-03-09 09:22:14,487][23090] Updated weights for policy 0, policy_version 84289 (0.0018) [2023-03-09 09:22:15,340][23090] Updated weights for policy 0, policy_version 84299 (0.0019) [2023-03-09 09:22:16,144][23090] Updated weights for policy 0, policy_version 84309 (0.0013) [2023-03-09 09:22:16,949][23090] Updated weights for policy 0, policy_version 84319 (0.0018) [2023-03-09 09:22:17,872][23090] Updated weights for policy 0, policy_version 84329 (0.0013) [2023-03-09 09:22:18,631][23090] Updated weights for policy 0, policy_version 84339 (0.0013) [2023-03-09 09:22:19,059][22664] Fps is (10 sec: 196607.1, 60 sec: 197972.8, 300 sec: 198385.1). Total num frames: 1381875712. Throughput: 0: 49597.3. Samples: 345488704. Policy #0 lag: (min: 0.0, avg: 16.8, max: 33.0) [2023-03-09 09:22:19,060][22664] Avg episode reward: [(0, '53.069')] [2023-03-09 09:22:19,451][23090] Updated weights for policy 0, policy_version 84349 (0.0019) [2023-03-09 09:22:20,298][23090] Updated weights for policy 0, policy_version 84359 (0.0017) [2023-03-09 09:22:20,712][22940] Signal inference workers to stop experience collection... (27850 times) [2023-03-09 09:22:20,713][22940] Signal inference workers to resume experience collection... (27850 times) [2023-03-09 09:22:20,779][23090] InferenceWorker_p0-w0: stopping experience collection (27850 times) [2023-03-09 09:22:20,782][23090] InferenceWorker_p0-w0: resuming experience collection (27850 times) [2023-03-09 09:22:21,028][23090] Updated weights for policy 0, policy_version 84369 (0.0013) [2023-03-09 09:22:22,024][23090] Updated weights for policy 0, policy_version 84379 (0.0017) [2023-03-09 09:22:22,796][23090] Updated weights for policy 0, policy_version 84389 (0.0018) [2023-03-09 09:22:23,525][23090] Updated weights for policy 0, policy_version 84399 (0.0022) [2023-03-09 09:22:24,059][22664] Fps is (10 sec: 199877.7, 60 sec: 197973.1, 300 sec: 198385.2). Total num frames: 1382875136. Throughput: 0: 49506.9. Samples: 345783488. Policy #0 lag: (min: 0.0, avg: 16.8, max: 33.0) [2023-03-09 09:22:24,061][22664] Avg episode reward: [(0, '50.697')] [2023-03-09 09:22:24,496][23090] Updated weights for policy 0, policy_version 84409 (0.0015) [2023-03-09 09:22:25,414][23090] Updated weights for policy 0, policy_version 84420 (0.0015) [2023-03-09 09:22:26,153][23090] Updated weights for policy 0, policy_version 84430 (0.0017) [2023-03-09 09:22:27,027][23090] Updated weights for policy 0, policy_version 84440 (0.0019) [2023-03-09 09:22:27,795][23090] Updated weights for policy 0, policy_version 84450 (0.0013) [2023-03-09 09:22:28,681][23090] Updated weights for policy 0, policy_version 84460 (0.0016) [2023-03-09 09:22:29,059][22664] Fps is (10 sec: 199882.8, 60 sec: 198518.7, 300 sec: 198385.2). Total num frames: 1383874560. Throughput: 0: 49550.7. Samples: 345932896. Policy #0 lag: (min: 0.0, avg: 16.8, max: 33.0) [2023-03-09 09:22:29,061][22664] Avg episode reward: [(0, '55.325')] [2023-03-09 09:22:29,461][23090] Updated weights for policy 0, policy_version 84470 (0.0013) [2023-03-09 09:22:30,256][23090] Updated weights for policy 0, policy_version 84480 (0.0022) [2023-03-09 09:22:31,173][23090] Updated weights for policy 0, policy_version 84490 (0.0013) [2023-03-09 09:22:31,971][23090] Updated weights for policy 0, policy_version 84500 (0.0015) [2023-03-09 09:22:32,842][23090] Updated weights for policy 0, policy_version 84511 (0.0016) [2023-03-09 09:22:33,307][22940] Signal inference workers to stop experience collection... (27900 times) [2023-03-09 09:22:33,308][22940] Signal inference workers to resume experience collection... (27900 times) [2023-03-09 09:22:33,367][23090] InferenceWorker_p0-w0: stopping experience collection (27900 times) [2023-03-09 09:22:33,368][23090] InferenceWorker_p0-w0: resuming experience collection (27900 times) [2023-03-09 09:22:33,697][23090] Updated weights for policy 0, policy_version 84521 (0.0013) [2023-03-09 09:22:34,058][22664] Fps is (10 sec: 199891.8, 60 sec: 198520.4, 300 sec: 198385.7). Total num frames: 1384873984. Throughput: 0: 49548.8. Samples: 346229696. Policy #0 lag: (min: 0.0, avg: 16.8, max: 33.0) [2023-03-09 09:22:34,059][22664] Avg episode reward: [(0, '54.400')] [2023-03-09 09:22:34,480][23090] Updated weights for policy 0, policy_version 84531 (0.0016) [2023-03-09 09:22:35,364][23090] Updated weights for policy 0, policy_version 84541 (0.0018) [2023-03-09 09:22:36,104][23090] Updated weights for policy 0, policy_version 84551 (0.0021) [2023-03-09 09:22:36,906][23090] Updated weights for policy 0, policy_version 84561 (0.0013) [2023-03-09 09:22:37,897][23090] Updated weights for policy 0, policy_version 84571 (0.0013) [2023-03-09 09:22:38,706][23090] Updated weights for policy 0, policy_version 84581 (0.0015) [2023-03-09 09:22:39,059][22664] Fps is (10 sec: 196604.4, 60 sec: 197973.0, 300 sec: 198274.0). Total num frames: 1385840640. Throughput: 0: 49546.8. Samples: 346526576. Policy #0 lag: (min: 0.0, avg: 16.8, max: 33.0) [2023-03-09 09:22:39,061][22664] Avg episode reward: [(0, '55.936')] [2023-03-09 09:22:39,436][23090] Updated weights for policy 0, policy_version 84591 (0.0018) [2023-03-09 09:22:40,486][23090] Updated weights for policy 0, policy_version 84602 (0.0013) [2023-03-09 09:22:41,255][23090] Updated weights for policy 0, policy_version 84612 (0.0020) [2023-03-09 09:22:42,024][23090] Updated weights for policy 0, policy_version 84622 (0.0022) [2023-03-09 09:22:42,875][23090] Updated weights for policy 0, policy_version 84632 (0.0016) [2023-03-09 09:22:43,683][23090] Updated weights for policy 0, policy_version 84642 (0.0016) [2023-03-09 09:22:44,059][22664] Fps is (10 sec: 196601.2, 60 sec: 197972.3, 300 sec: 198329.8). Total num frames: 1386840064. Throughput: 0: 49592.5. Samples: 346676080. Policy #0 lag: (min: 0.0, avg: 16.8, max: 33.0) [2023-03-09 09:22:44,061][22664] Avg episode reward: [(0, '51.803')] [2023-03-09 09:22:44,538][23090] Updated weights for policy 0, policy_version 84652 (0.0019) [2023-03-09 09:22:45,428][23090] Updated weights for policy 0, policy_version 84663 (0.0017) [2023-03-09 09:22:45,877][22940] Signal inference workers to stop experience collection... (27950 times) [2023-03-09 09:22:45,878][22940] Signal inference workers to resume experience collection... (27950 times) [2023-03-09 09:22:45,943][23090] InferenceWorker_p0-w0: stopping experience collection (27950 times) [2023-03-09 09:22:45,943][23090] InferenceWorker_p0-w0: resuming experience collection (27950 times) [2023-03-09 09:22:46,205][23090] Updated weights for policy 0, policy_version 84673 (0.0016) [2023-03-09 09:22:47,110][23090] Updated weights for policy 0, policy_version 84683 (0.0012) [2023-03-09 09:22:47,923][23090] Updated weights for policy 0, policy_version 84693 (0.0013) [2023-03-09 09:22:48,778][23090] Updated weights for policy 0, policy_version 84704 (0.0019) [2023-03-09 09:22:49,058][22664] Fps is (10 sec: 198255.1, 60 sec: 197973.3, 300 sec: 198274.2). Total num frames: 1387823104. Throughput: 0: 49545.1. Samples: 346972880. Policy #0 lag: (min: 0.0, avg: 16.8, max: 33.0) [2023-03-09 09:22:49,060][22664] Avg episode reward: [(0, '53.079')] [2023-03-09 09:22:49,680][23090] Updated weights for policy 0, policy_version 84714 (0.0013) [2023-03-09 09:22:50,499][23090] Updated weights for policy 0, policy_version 84724 (0.0013) [2023-03-09 09:22:51,353][23090] Updated weights for policy 0, policy_version 84734 (0.0020) [2023-03-09 09:22:52,287][23090] Updated weights for policy 0, policy_version 84745 (0.0017) [2023-03-09 09:22:53,066][23090] Updated weights for policy 0, policy_version 84755 (0.0017) [2023-03-09 09:22:53,953][23090] Updated weights for policy 0, policy_version 84765 (0.0014) [2023-03-09 09:22:54,058][22664] Fps is (10 sec: 198252.4, 60 sec: 198247.3, 300 sec: 198329.7). Total num frames: 1388822528. Throughput: 0: 49498.8. Samples: 347267696. Policy #0 lag: (min: 0.0, avg: 16.8, max: 33.0) [2023-03-09 09:22:54,060][22664] Avg episode reward: [(0, '56.032')] [2023-03-09 09:22:54,766][23090] Updated weights for policy 0, policy_version 84775 (0.0013) [2023-03-09 09:22:55,526][23090] Updated weights for policy 0, policy_version 84785 (0.0013) [2023-03-09 09:22:56,449][23090] Updated weights for policy 0, policy_version 84795 (0.0012) [2023-03-09 09:22:57,379][23090] Updated weights for policy 0, policy_version 84806 (0.0016) [2023-03-09 09:22:58,095][23090] Updated weights for policy 0, policy_version 84816 (0.0012) [2023-03-09 09:22:59,056][23090] Updated weights for policy 0, policy_version 84826 (0.0017) [2023-03-09 09:22:59,059][22664] Fps is (10 sec: 196601.6, 60 sec: 197973.2, 300 sec: 198273.9). Total num frames: 1389789184. Throughput: 0: 49449.6. Samples: 347415008. Policy #0 lag: (min: 0.0, avg: 16.8, max: 33.0) [2023-03-09 09:22:59,061][22664] Avg episode reward: [(0, '53.076')] [2023-03-09 09:22:59,784][23090] Updated weights for policy 0, policy_version 84836 (0.0013) [2023-03-09 09:22:59,967][22940] Signal inference workers to stop experience collection... (28000 times) [2023-03-09 09:22:59,969][22940] Signal inference workers to resume experience collection... (28000 times) [2023-03-09 09:23:00,029][23090] InferenceWorker_p0-w0: stopping experience collection (28000 times) [2023-03-09 09:23:00,029][23090] InferenceWorker_p0-w0: resuming experience collection (28000 times) [2023-03-09 09:23:00,547][23090] Updated weights for policy 0, policy_version 84846 (0.0020) [2023-03-09 09:23:01,429][23090] Updated weights for policy 0, policy_version 84856 (0.0014) [2023-03-09 09:23:02,260][23090] Updated weights for policy 0, policy_version 84866 (0.0016) [2023-03-09 09:23:03,084][23090] Updated weights for policy 0, policy_version 84876 (0.0015) [2023-03-09 09:23:03,919][23090] Updated weights for policy 0, policy_version 84886 (0.0021) [2023-03-09 09:23:04,058][22664] Fps is (10 sec: 196608.2, 60 sec: 197974.0, 300 sec: 198274.4). Total num frames: 1390788608. Throughput: 0: 49448.7. Samples: 347713888. Policy #0 lag: (min: 0.0, avg: 16.8, max: 33.0) [2023-03-09 09:23:04,059][22664] Avg episode reward: [(0, '53.283')] [2023-03-09 09:23:04,696][23090] Updated weights for policy 0, policy_version 84896 (0.0013) [2023-03-09 09:23:05,572][23090] Updated weights for policy 0, policy_version 84906 (0.0016) [2023-03-09 09:23:06,387][23090] Updated weights for policy 0, policy_version 84916 (0.0013) [2023-03-09 09:23:07,207][23090] Updated weights for policy 0, policy_version 84926 (0.0021) [2023-03-09 09:23:08,109][23090] Updated weights for policy 0, policy_version 84937 (0.0014) [2023-03-09 09:23:08,988][23090] Updated weights for policy 0, policy_version 84947 (0.0016) [2023-03-09 09:23:09,058][22664] Fps is (10 sec: 199891.2, 60 sec: 197973.6, 300 sec: 198274.2). Total num frames: 1391788032. Throughput: 0: 49542.0. Samples: 348012864. Policy #0 lag: (min: 1.0, avg: 16.5, max: 33.0) [2023-03-09 09:23:09,060][22664] Avg episode reward: [(0, '55.488')] [2023-03-09 09:23:09,746][23090] Updated weights for policy 0, policy_version 84957 (0.0017) [2023-03-09 09:23:10,585][23090] Updated weights for policy 0, policy_version 84967 (0.0013) [2023-03-09 09:23:11,292][22940] Signal inference workers to stop experience collection... (28050 times) [2023-03-09 09:23:11,292][22940] Signal inference workers to resume experience collection... (28050 times) [2023-03-09 09:23:11,355][23090] InferenceWorker_p0-w0: stopping experience collection (28050 times) [2023-03-09 09:23:11,356][23090] InferenceWorker_p0-w0: resuming experience collection (28050 times) [2023-03-09 09:23:11,477][23090] Updated weights for policy 0, policy_version 84978 (0.0013) [2023-03-09 09:23:12,361][23090] Updated weights for policy 0, policy_version 84988 (0.0017) [2023-03-09 09:23:13,136][23090] Updated weights for policy 0, policy_version 84998 (0.0017) [2023-03-09 09:23:13,906][23090] Updated weights for policy 0, policy_version 85008 (0.0016) [2023-03-09 09:23:14,059][22664] Fps is (10 sec: 199882.1, 60 sec: 198518.9, 300 sec: 198274.2). Total num frames: 1392787456. Throughput: 0: 49543.2. Samples: 348162336. Policy #0 lag: (min: 1.0, avg: 16.5, max: 33.0) [2023-03-09 09:23:14,060][22664] Avg episode reward: [(0, '52.957')] [2023-03-09 09:23:14,866][23090] Updated weights for policy 0, policy_version 85018 (0.0013) [2023-03-09 09:23:15,729][23090] Updated weights for policy 0, policy_version 85029 (0.0012) [2023-03-09 09:23:16,484][23090] Updated weights for policy 0, policy_version 85039 (0.0013) [2023-03-09 09:23:17,411][23090] Updated weights for policy 0, policy_version 85049 (0.0013) [2023-03-09 09:23:18,254][23090] Updated weights for policy 0, policy_version 85059 (0.0013) [2023-03-09 09:23:19,035][23090] Updated weights for policy 0, policy_version 85069 (0.0022) [2023-03-09 09:23:19,058][22664] Fps is (10 sec: 199884.9, 60 sec: 198520.0, 300 sec: 198329.9). Total num frames: 1393786880. Throughput: 0: 49544.1. Samples: 348459184. Policy #0 lag: (min: 1.0, avg: 16.5, max: 33.0) [2023-03-09 09:23:19,059][22664] Avg episode reward: [(0, '54.427')] [2023-03-09 09:23:19,098][22940] Saving /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000085071_1393803264.pth... [2023-03-09 09:23:19,152][22940] Removing /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000082166_1346207744.pth [2023-03-09 09:23:19,816][23090] Updated weights for policy 0, policy_version 85079 (0.0013) [2023-03-09 09:23:20,741][23090] Updated weights for policy 0, policy_version 85090 (0.0016) [2023-03-09 09:23:21,599][23090] Updated weights for policy 0, policy_version 85100 (0.0018) [2023-03-09 09:23:22,430][23090] Updated weights for policy 0, policy_version 85110 (0.0016) [2023-03-09 09:23:23,198][23090] Updated weights for policy 0, policy_version 85120 (0.0016) [2023-03-09 09:23:24,059][22664] Fps is (10 sec: 196604.0, 60 sec: 197973.3, 300 sec: 198274.0). Total num frames: 1394753536. Throughput: 0: 49497.4. Samples: 348753952. Policy #0 lag: (min: 1.0, avg: 16.5, max: 33.0) [2023-03-09 09:23:24,061][22664] Avg episode reward: [(0, '55.611')] [2023-03-09 09:23:24,087][23090] Updated weights for policy 0, policy_version 85130 (0.0025) [2023-03-09 09:23:24,512][22940] Signal inference workers to stop experience collection... (28100 times) [2023-03-09 09:23:24,512][22940] Signal inference workers to resume experience collection... (28100 times) [2023-03-09 09:23:24,578][23090] InferenceWorker_p0-w0: stopping experience collection (28100 times) [2023-03-09 09:23:24,578][23090] InferenceWorker_p0-w0: resuming experience collection (28100 times) [2023-03-09 09:23:24,907][23090] Updated weights for policy 0, policy_version 85140 (0.0013) [2023-03-09 09:23:25,744][23090] Updated weights for policy 0, policy_version 85150 (0.0013) [2023-03-09 09:23:26,686][23090] Updated weights for policy 0, policy_version 85161 (0.0013) [2023-03-09 09:23:27,601][23090] Updated weights for policy 0, policy_version 85172 (0.0016) [2023-03-09 09:23:28,431][23090] Updated weights for policy 0, policy_version 85182 (0.0018) [2023-03-09 09:23:29,059][22664] Fps is (10 sec: 194964.3, 60 sec: 197700.2, 300 sec: 198274.0). Total num frames: 1395736576. Throughput: 0: 49451.1. Samples: 348901376. Policy #0 lag: (min: 1.0, avg: 16.5, max: 33.0) [2023-03-09 09:23:29,061][22664] Avg episode reward: [(0, '55.623')] [2023-03-09 09:23:29,209][23090] Updated weights for policy 0, policy_version 85192 (0.0016) [2023-03-09 09:23:30,177][23090] Updated weights for policy 0, policy_version 85203 (0.0013) [2023-03-09 09:23:30,992][23090] Updated weights for policy 0, policy_version 85213 (0.0017) [2023-03-09 09:23:31,798][23090] Updated weights for policy 0, policy_version 85223 (0.0018) [2023-03-09 09:23:32,566][23090] Updated weights for policy 0, policy_version 85233 (0.0019) [2023-03-09 09:23:33,535][23090] Updated weights for policy 0, policy_version 85243 (0.0013) [2023-03-09 09:23:34,059][22664] Fps is (10 sec: 198247.1, 60 sec: 197699.2, 300 sec: 198218.4). Total num frames: 1396736000. Throughput: 0: 49452.5. Samples: 349198256. Policy #0 lag: (min: 1.0, avg: 16.5, max: 33.0) [2023-03-09 09:23:34,061][22664] Avg episode reward: [(0, '56.401')] [2023-03-09 09:23:34,329][23090] Updated weights for policy 0, policy_version 85253 (0.0013) [2023-03-09 09:23:35,035][23090] Updated weights for policy 0, policy_version 85263 (0.0018) [2023-03-09 09:23:36,035][23090] Updated weights for policy 0, policy_version 85273 (0.0017) [2023-03-09 09:23:36,788][23090] Updated weights for policy 0, policy_version 85283 (0.0017) [2023-03-09 09:23:37,088][22940] Signal inference workers to stop experience collection... (28150 times) [2023-03-09 09:23:37,090][22940] Signal inference workers to resume experience collection... (28150 times) [2023-03-09 09:23:37,153][23090] InferenceWorker_p0-w0: stopping experience collection (28150 times) [2023-03-09 09:23:37,154][23090] InferenceWorker_p0-w0: resuming experience collection (28150 times) [2023-03-09 09:23:37,601][23090] Updated weights for policy 0, policy_version 85294 (0.0014) [2023-03-09 09:23:38,488][23090] Updated weights for policy 0, policy_version 85304 (0.0018) [2023-03-09 09:23:39,059][22664] Fps is (10 sec: 199884.5, 60 sec: 198246.9, 300 sec: 198274.0). Total num frames: 1397735424. Throughput: 0: 49543.2. Samples: 349497152. Policy #0 lag: (min: 1.0, avg: 16.5, max: 33.0) [2023-03-09 09:23:39,060][22664] Avg episode reward: [(0, '54.234')] [2023-03-09 09:23:39,285][23090] Updated weights for policy 0, policy_version 85314 (0.0013) [2023-03-09 09:23:40,115][23090] Updated weights for policy 0, policy_version 85324 (0.0013) [2023-03-09 09:23:41,012][23090] Updated weights for policy 0, policy_version 85335 (0.0019) [2023-03-09 09:23:41,927][23090] Updated weights for policy 0, policy_version 85346 (0.0016) [2023-03-09 09:23:42,748][23090] Updated weights for policy 0, policy_version 85356 (0.0013) [2023-03-09 09:23:43,592][23090] Updated weights for policy 0, policy_version 85366 (0.0014) [2023-03-09 09:23:44,059][22664] Fps is (10 sec: 196612.0, 60 sec: 197701.0, 300 sec: 198163.2). Total num frames: 1398702080. Throughput: 0: 49591.4. Samples: 349646608. Policy #0 lag: (min: 1.0, avg: 16.5, max: 33.0) [2023-03-09 09:23:44,060][22664] Avg episode reward: [(0, '53.800')] [2023-03-09 09:23:44,364][23090] Updated weights for policy 0, policy_version 85376 (0.0013) [2023-03-09 09:23:45,222][23090] Updated weights for policy 0, policy_version 85386 (0.0014) [2023-03-09 09:23:46,198][23090] Updated weights for policy 0, policy_version 85397 (0.0016) [2023-03-09 09:23:46,928][23090] Updated weights for policy 0, policy_version 85407 (0.0013) [2023-03-09 09:23:47,806][23090] Updated weights for policy 0, policy_version 85417 (0.0013) [2023-03-09 09:23:48,630][23090] Updated weights for policy 0, policy_version 85427 (0.0016) [2023-03-09 09:23:49,059][22664] Fps is (10 sec: 196605.9, 60 sec: 197972.0, 300 sec: 198163.0). Total num frames: 1399701504. Throughput: 0: 49546.9. Samples: 349943520. Policy #0 lag: (min: 1.0, avg: 16.5, max: 33.0) [2023-03-09 09:23:49,061][22664] Avg episode reward: [(0, '54.434')] [2023-03-09 09:23:49,457][22940] Signal inference workers to stop experience collection... (28200 times) [2023-03-09 09:23:49,471][22940] Signal inference workers to resume experience collection... (28200 times) [2023-03-09 09:23:49,499][23090] InferenceWorker_p0-w0: stopping experience collection (28200 times) [2023-03-09 09:23:49,499][23090] InferenceWorker_p0-w0: resuming experience collection (28200 times) [2023-03-09 09:23:49,502][23090] Updated weights for policy 0, policy_version 85437 (0.0013) [2023-03-09 09:23:50,292][23090] Updated weights for policy 0, policy_version 85447 (0.0013) [2023-03-09 09:23:51,047][23090] Updated weights for policy 0, policy_version 85457 (0.0014) [2023-03-09 09:23:52,081][23090] Updated weights for policy 0, policy_version 85468 (0.0013) [2023-03-09 09:23:52,894][23090] Updated weights for policy 0, policy_version 85478 (0.0025) [2023-03-09 09:23:53,661][23090] Updated weights for policy 0, policy_version 85488 (0.0013) [2023-03-09 09:23:54,058][22664] Fps is (10 sec: 199887.8, 60 sec: 197973.5, 300 sec: 198218.9). Total num frames: 1400700928. Throughput: 0: 49455.7. Samples: 350238368. Policy #0 lag: (min: 1.0, avg: 16.5, max: 33.0) [2023-03-09 09:23:54,059][22664] Avg episode reward: [(0, '54.782')] [2023-03-09 09:23:54,671][23090] Updated weights for policy 0, policy_version 85498 (0.0026) [2023-03-09 09:23:55,436][23090] Updated weights for policy 0, policy_version 85508 (0.0013) [2023-03-09 09:23:56,185][23090] Updated weights for policy 0, policy_version 85518 (0.0016) [2023-03-09 09:23:57,101][23090] Updated weights for policy 0, policy_version 85528 (0.0019) [2023-03-09 09:23:57,986][23090] Updated weights for policy 0, policy_version 85539 (0.0018) [2023-03-09 09:23:58,801][23090] Updated weights for policy 0, policy_version 85549 (0.0024) [2023-03-09 09:23:59,059][22664] Fps is (10 sec: 198244.8, 60 sec: 198245.9, 300 sec: 198218.3). Total num frames: 1401683968. Throughput: 0: 49409.4. Samples: 350385776. Policy #0 lag: (min: 1.0, avg: 16.5, max: 33.0) [2023-03-09 09:23:59,061][22664] Avg episode reward: [(0, '53.845')] [2023-03-09 09:23:59,625][23090] Updated weights for policy 0, policy_version 85559 (0.0013) [2023-03-09 09:24:00,513][23090] Updated weights for policy 0, policy_version 85569 (0.0013) [2023-03-09 09:24:01,337][23090] Updated weights for policy 0, policy_version 85579 (0.0015) [2023-03-09 09:24:02,119][23090] Updated weights for policy 0, policy_version 85589 (0.0019) [2023-03-09 09:24:02,717][22940] Signal inference workers to stop experience collection... (28250 times) [2023-03-09 09:24:02,721][22940] Signal inference workers to resume experience collection... (28250 times) [2023-03-09 09:24:02,795][23090] InferenceWorker_p0-w0: stopping experience collection (28250 times) [2023-03-09 09:24:02,796][23090] InferenceWorker_p0-w0: resuming experience collection (28250 times) [2023-03-09 09:24:02,881][23090] Updated weights for policy 0, policy_version 85599 (0.0013) [2023-03-09 09:24:03,738][23090] Updated weights for policy 0, policy_version 85609 (0.0013) [2023-03-09 09:24:04,059][22664] Fps is (10 sec: 198244.1, 60 sec: 198246.2, 300 sec: 198274.2). Total num frames: 1402683392. Throughput: 0: 49411.8. Samples: 350682720. Policy #0 lag: (min: 1.0, avg: 16.8, max: 33.0) [2023-03-09 09:24:04,061][22664] Avg episode reward: [(0, '54.977')] [2023-03-09 09:24:04,557][23090] Updated weights for policy 0, policy_version 85619 (0.0017) [2023-03-09 09:24:05,433][23090] Updated weights for policy 0, policy_version 85629 (0.0013) [2023-03-09 09:24:06,205][23090] Updated weights for policy 0, policy_version 85639 (0.0016) [2023-03-09 09:24:07,093][23090] Updated weights for policy 0, policy_version 85650 (0.0017) [2023-03-09 09:24:08,059][23090] Updated weights for policy 0, policy_version 85660 (0.0013) [2023-03-09 09:24:08,792][23090] Updated weights for policy 0, policy_version 85670 (0.0016) [2023-03-09 09:24:09,059][22664] Fps is (10 sec: 198251.8, 60 sec: 197972.7, 300 sec: 198274.0). Total num frames: 1403666432. Throughput: 0: 49505.9. Samples: 350981712. Policy #0 lag: (min: 1.0, avg: 16.8, max: 33.0) [2023-03-09 09:24:09,060][22664] Avg episode reward: [(0, '54.310')] [2023-03-09 09:24:09,544][23090] Updated weights for policy 0, policy_version 85680 (0.0020) [2023-03-09 09:24:10,578][23090] Updated weights for policy 0, policy_version 85690 (0.0014) [2023-03-09 09:24:11,315][23090] Updated weights for policy 0, policy_version 85700 (0.0013) [2023-03-09 09:24:12,050][23090] Updated weights for policy 0, policy_version 85710 (0.0021) [2023-03-09 09:24:12,966][23090] Updated weights for policy 0, policy_version 85720 (0.0019) [2023-03-09 09:24:13,747][23090] Updated weights for policy 0, policy_version 85730 (0.0015) [2023-03-09 09:24:14,059][22664] Fps is (10 sec: 196595.1, 60 sec: 197698.3, 300 sec: 198218.2). Total num frames: 1404649472. Throughput: 0: 49504.9. Samples: 351129120. Policy #0 lag: (min: 1.0, avg: 16.8, max: 33.0) [2023-03-09 09:24:14,062][22664] Avg episode reward: [(0, '54.071')] [2023-03-09 09:24:14,188][22940] Signal inference workers to stop experience collection... (28300 times) [2023-03-09 09:24:14,189][22940] Signal inference workers to resume experience collection... (28300 times) [2023-03-09 09:24:14,253][23090] InferenceWorker_p0-w0: stopping experience collection (28300 times) [2023-03-09 09:24:14,255][23090] InferenceWorker_p0-w0: resuming experience collection (28300 times) [2023-03-09 09:24:14,591][23090] Updated weights for policy 0, policy_version 85740 (0.0017) [2023-03-09 09:24:15,411][23090] Updated weights for policy 0, policy_version 85750 (0.0016) [2023-03-09 09:24:16,253][23090] Updated weights for policy 0, policy_version 85760 (0.0020) [2023-03-09 09:24:17,072][23090] Updated weights for policy 0, policy_version 85770 (0.0017) [2023-03-09 09:24:17,860][23090] Updated weights for policy 0, policy_version 85780 (0.0014) [2023-03-09 09:24:18,712][23090] Updated weights for policy 0, policy_version 85790 (0.0013) [2023-03-09 09:24:19,059][22664] Fps is (10 sec: 198247.7, 60 sec: 197699.8, 300 sec: 198218.7). Total num frames: 1405648896. Throughput: 0: 49505.2. Samples: 351425984. Policy #0 lag: (min: 1.0, avg: 16.8, max: 33.0) [2023-03-09 09:24:19,060][22664] Avg episode reward: [(0, '52.953')] [2023-03-09 09:24:19,523][23090] Updated weights for policy 0, policy_version 85800 (0.0023) [2023-03-09 09:24:20,336][23090] Updated weights for policy 0, policy_version 85810 (0.0016) [2023-03-09 09:24:21,271][23090] Updated weights for policy 0, policy_version 85820 (0.0018) [2023-03-09 09:24:22,041][23090] Updated weights for policy 0, policy_version 85830 (0.0014) [2023-03-09 09:24:22,810][23090] Updated weights for policy 0, policy_version 85840 (0.0015) [2023-03-09 09:24:23,825][23090] Updated weights for policy 0, policy_version 85850 (0.0013) [2023-03-09 09:24:24,058][22664] Fps is (10 sec: 198261.4, 60 sec: 197974.6, 300 sec: 198218.8). Total num frames: 1406631936. Throughput: 0: 49459.2. Samples: 351722800. Policy #0 lag: (min: 1.0, avg: 16.8, max: 33.0) [2023-03-09 09:24:24,059][22664] Avg episode reward: [(0, '56.114')] [2023-03-09 09:24:24,561][23090] Updated weights for policy 0, policy_version 85860 (0.0016) [2023-03-09 09:24:25,344][23090] Updated weights for policy 0, policy_version 85870 (0.0019) [2023-03-09 09:24:26,230][23090] Updated weights for policy 0, policy_version 85880 (0.0018) [2023-03-09 09:24:26,482][22940] Signal inference workers to stop experience collection... (28350 times) [2023-03-09 09:24:26,496][22940] Signal inference workers to resume experience collection... (28350 times) [2023-03-09 09:24:26,555][23090] InferenceWorker_p0-w0: stopping experience collection (28350 times) [2023-03-09 09:24:26,555][23090] InferenceWorker_p0-w0: resuming experience collection (28350 times) [2023-03-09 09:24:27,033][23090] Updated weights for policy 0, policy_version 85890 (0.0016) [2023-03-09 09:24:27,902][23090] Updated weights for policy 0, policy_version 85900 (0.0024) [2023-03-09 09:24:28,700][23090] Updated weights for policy 0, policy_version 85910 (0.0018) [2023-03-09 09:24:29,059][22664] Fps is (10 sec: 194965.7, 60 sec: 197700.1, 300 sec: 198107.6). Total num frames: 1407598592. Throughput: 0: 49413.1. Samples: 351870208. Policy #0 lag: (min: 1.0, avg: 16.8, max: 33.0) [2023-03-09 09:24:29,061][22664] Avg episode reward: [(0, '54.931')] [2023-03-09 09:24:29,509][23090] Updated weights for policy 0, policy_version 85920 (0.0016) [2023-03-09 09:24:30,329][23090] Updated weights for policy 0, policy_version 85930 (0.0018) [2023-03-09 09:24:31,183][23090] Updated weights for policy 0, policy_version 85940 (0.0013) [2023-03-09 09:24:32,019][23090] Updated weights for policy 0, policy_version 85950 (0.0017) [2023-03-09 09:24:32,837][23090] Updated weights for policy 0, policy_version 85960 (0.0013) [2023-03-09 09:24:33,649][23090] Updated weights for policy 0, policy_version 85970 (0.0020) [2023-03-09 09:24:34,059][22664] Fps is (10 sec: 196602.3, 60 sec: 197700.4, 300 sec: 198107.7). Total num frames: 1408598016. Throughput: 0: 49412.8. Samples: 352167088. Policy #0 lag: (min: 1.0, avg: 16.8, max: 33.0) [2023-03-09 09:24:34,060][22664] Avg episode reward: [(0, '53.725')] [2023-03-09 09:24:34,589][23090] Updated weights for policy 0, policy_version 85980 (0.0017) [2023-03-09 09:24:35,440][23090] Updated weights for policy 0, policy_version 85991 (0.0013) [2023-03-09 09:24:36,289][23090] Updated weights for policy 0, policy_version 86002 (0.0013) [2023-03-09 09:24:37,200][23090] Updated weights for policy 0, policy_version 86012 (0.0015) [2023-03-09 09:24:38,011][23090] Updated weights for policy 0, policy_version 86022 (0.0016) [2023-03-09 09:24:38,519][22940] Signal inference workers to stop experience collection... (28400 times) [2023-03-09 09:24:38,539][22940] Signal inference workers to resume experience collection... (28400 times) [2023-03-09 09:24:38,585][23090] InferenceWorker_p0-w0: stopping experience collection (28400 times) [2023-03-09 09:24:38,586][23090] InferenceWorker_p0-w0: resuming experience collection (28400 times) [2023-03-09 09:24:38,871][23090] Updated weights for policy 0, policy_version 86033 (0.0018) [2023-03-09 09:24:39,059][22664] Fps is (10 sec: 198251.7, 60 sec: 197427.9, 300 sec: 198107.6). Total num frames: 1409581056. Throughput: 0: 49412.1. Samples: 352461920. Policy #0 lag: (min: 1.0, avg: 16.8, max: 33.0) [2023-03-09 09:24:39,059][22664] Avg episode reward: [(0, '54.193')] [2023-03-09 09:24:39,808][23090] Updated weights for policy 0, policy_version 86043 (0.0015) [2023-03-09 09:24:40,678][23090] Updated weights for policy 0, policy_version 86054 (0.0018) [2023-03-09 09:24:41,428][23090] Updated weights for policy 0, policy_version 86064 (0.0013) [2023-03-09 09:24:42,399][23090] Updated weights for policy 0, policy_version 86074 (0.0016) [2023-03-09 09:24:43,164][23090] Updated weights for policy 0, policy_version 86084 (0.0018) [2023-03-09 09:24:43,945][23090] Updated weights for policy 0, policy_version 86094 (0.0016) [2023-03-09 09:24:44,058][22664] Fps is (10 sec: 199890.4, 60 sec: 198246.8, 300 sec: 198218.8). Total num frames: 1410596864. Throughput: 0: 49411.8. Samples: 352609280. Policy #0 lag: (min: 1.0, avg: 16.8, max: 33.0) [2023-03-09 09:24:44,060][22664] Avg episode reward: [(0, '54.331')] [2023-03-09 09:24:44,811][23090] Updated weights for policy 0, policy_version 86104 (0.0019) [2023-03-09 09:24:45,605][23090] Updated weights for policy 0, policy_version 86114 (0.0020) [2023-03-09 09:24:46,447][23090] Updated weights for policy 0, policy_version 86124 (0.0016) [2023-03-09 09:24:47,272][23090] Updated weights for policy 0, policy_version 86134 (0.0019) [2023-03-09 09:24:48,083][23090] Updated weights for policy 0, policy_version 86144 (0.0020) [2023-03-09 09:24:48,933][23090] Updated weights for policy 0, policy_version 86154 (0.0020) [2023-03-09 09:24:49,059][22664] Fps is (10 sec: 198240.6, 60 sec: 197700.4, 300 sec: 198163.0). Total num frames: 1411563520. Throughput: 0: 49409.1. Samples: 352906144. Policy #0 lag: (min: 1.0, avg: 16.8, max: 33.0) [2023-03-09 09:24:49,061][22664] Avg episode reward: [(0, '55.396')] [2023-03-09 09:24:49,750][23090] Updated weights for policy 0, policy_version 86164 (0.0015) [2023-03-09 09:24:50,568][23090] Updated weights for policy 0, policy_version 86174 (0.0016) [2023-03-09 09:24:50,646][22940] Signal inference workers to stop experience collection... (28450 times) [2023-03-09 09:24:50,658][22940] Signal inference workers to resume experience collection... (28450 times) [2023-03-09 09:24:50,753][23090] InferenceWorker_p0-w0: stopping experience collection (28450 times) [2023-03-09 09:24:50,754][23090] InferenceWorker_p0-w0: resuming experience collection (28450 times) [2023-03-09 09:24:51,407][23090] Updated weights for policy 0, policy_version 86184 (0.0013) [2023-03-09 09:24:52,200][23090] Updated weights for policy 0, policy_version 86194 (0.0016) [2023-03-09 09:24:53,150][23090] Updated weights for policy 0, policy_version 86204 (0.0015) [2023-03-09 09:24:53,999][23090] Updated weights for policy 0, policy_version 86215 (0.0018) [2023-03-09 09:24:54,059][22664] Fps is (10 sec: 194964.1, 60 sec: 197426.2, 300 sec: 198107.4). Total num frames: 1412546560. Throughput: 0: 49362.8. Samples: 353203040. Policy #0 lag: (min: 1.0, avg: 17.2, max: 33.0) [2023-03-09 09:24:54,060][22664] Avg episode reward: [(0, '53.977')] [2023-03-09 09:24:54,768][23090] Updated weights for policy 0, policy_version 86225 (0.0015) [2023-03-09 09:24:55,732][23090] Updated weights for policy 0, policy_version 86235 (0.0018) [2023-03-09 09:24:56,501][23090] Updated weights for policy 0, policy_version 86245 (0.0013) [2023-03-09 09:24:57,247][23090] Updated weights for policy 0, policy_version 86255 (0.0017) [2023-03-09 09:24:58,271][23090] Updated weights for policy 0, policy_version 86265 (0.0019) [2023-03-09 09:24:59,003][23090] Updated weights for policy 0, policy_version 86275 (0.0016) [2023-03-09 09:24:59,059][22664] Fps is (10 sec: 198245.8, 60 sec: 197700.6, 300 sec: 198218.3). Total num frames: 1413545984. Throughput: 0: 49408.7. Samples: 353352496. Policy #0 lag: (min: 1.0, avg: 17.2, max: 33.0) [2023-03-09 09:24:59,061][22664] Avg episode reward: [(0, '55.243')] [2023-03-09 09:24:59,814][23090] Updated weights for policy 0, policy_version 86285 (0.0013) [2023-03-09 09:25:00,600][23090] Updated weights for policy 0, policy_version 86295 (0.0013) [2023-03-09 09:25:01,416][23090] Updated weights for policy 0, policy_version 86305 (0.0019) [2023-03-09 09:25:02,344][23090] Updated weights for policy 0, policy_version 86315 (0.0017) [2023-03-09 09:25:02,408][22940] Signal inference workers to stop experience collection... (28500 times) [2023-03-09 09:25:02,429][22940] Signal inference workers to resume experience collection... (28500 times) [2023-03-09 09:25:02,470][23090] InferenceWorker_p0-w0: stopping experience collection (28500 times) [2023-03-09 09:25:02,470][23090] InferenceWorker_p0-w0: resuming experience collection (28500 times) [2023-03-09 09:25:03,112][23090] Updated weights for policy 0, policy_version 86325 (0.0019) [2023-03-09 09:25:03,905][23090] Updated weights for policy 0, policy_version 86335 (0.0016) [2023-03-09 09:25:04,058][22664] Fps is (10 sec: 198252.2, 60 sec: 197427.5, 300 sec: 198107.8). Total num frames: 1414529024. Throughput: 0: 49407.8. Samples: 353649328. Policy #0 lag: (min: 1.0, avg: 17.2, max: 33.0) [2023-03-09 09:25:04,059][22664] Avg episode reward: [(0, '55.416')] [2023-03-09 09:25:04,736][23090] Updated weights for policy 0, policy_version 86345 (0.0018) [2023-03-09 09:25:05,582][23090] Updated weights for policy 0, policy_version 86355 (0.0017) [2023-03-09 09:25:06,447][23090] Updated weights for policy 0, policy_version 86365 (0.0015) [2023-03-09 09:25:07,229][23090] Updated weights for policy 0, policy_version 86375 (0.0018) [2023-03-09 09:25:07,996][23090] Updated weights for policy 0, policy_version 86385 (0.0013) [2023-03-09 09:25:08,964][23090] Updated weights for policy 0, policy_version 86395 (0.0016) [2023-03-09 09:25:09,059][22664] Fps is (10 sec: 196612.5, 60 sec: 197427.3, 300 sec: 198163.4). Total num frames: 1415512064. Throughput: 0: 49364.4. Samples: 353944208. Policy #0 lag: (min: 1.0, avg: 17.2, max: 33.0) [2023-03-09 09:25:09,060][22664] Avg episode reward: [(0, '53.776')] [2023-03-09 09:25:09,778][23090] Updated weights for policy 0, policy_version 86405 (0.0019) [2023-03-09 09:25:10,513][23090] Updated weights for policy 0, policy_version 86415 (0.0016) [2023-03-09 09:25:11,530][23090] Updated weights for policy 0, policy_version 86425 (0.0016) [2023-03-09 09:25:12,270][23090] Updated weights for policy 0, policy_version 86435 (0.0015) [2023-03-09 09:25:13,096][23090] Updated weights for policy 0, policy_version 86445 (0.0013) [2023-03-09 09:25:13,891][23090] Updated weights for policy 0, policy_version 86455 (0.0017) [2023-03-09 09:25:14,059][22664] Fps is (10 sec: 196599.2, 60 sec: 197428.2, 300 sec: 198107.5). Total num frames: 1416495104. Throughput: 0: 49410.8. Samples: 354093696. Policy #0 lag: (min: 1.0, avg: 17.2, max: 33.0) [2023-03-09 09:25:14,061][22664] Avg episode reward: [(0, '53.869')] [2023-03-09 09:25:14,702][23090] Updated weights for policy 0, policy_version 86465 (0.0019) [2023-03-09 09:25:15,577][23090] Updated weights for policy 0, policy_version 86475 (0.0018) [2023-03-09 09:25:15,594][22940] Signal inference workers to stop experience collection... (28550 times) [2023-03-09 09:25:15,624][22940] Signal inference workers to resume experience collection... (28550 times) [2023-03-09 09:25:15,699][23090] InferenceWorker_p0-w0: stopping experience collection (28550 times) [2023-03-09 09:25:15,699][23090] InferenceWorker_p0-w0: resuming experience collection (28550 times) [2023-03-09 09:25:16,391][23090] Updated weights for policy 0, policy_version 86485 (0.0018) [2023-03-09 09:25:17,278][23090] Updated weights for policy 0, policy_version 86496 (0.0018) [2023-03-09 09:25:18,094][23090] Updated weights for policy 0, policy_version 86506 (0.0013) [2023-03-09 09:25:18,946][23090] Updated weights for policy 0, policy_version 86516 (0.0013) [2023-03-09 09:25:19,059][22664] Fps is (10 sec: 198247.6, 60 sec: 197427.3, 300 sec: 198107.6). Total num frames: 1417494528. Throughput: 0: 49365.2. Samples: 354388512. Policy #0 lag: (min: 1.0, avg: 17.2, max: 33.0) [2023-03-09 09:25:19,060][22664] Avg episode reward: [(0, '54.745')] [2023-03-09 09:25:19,087][22940] Saving /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000086518_1417510912.pth... [2023-03-09 09:25:19,143][22940] Removing /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000083618_1369997312.pth [2023-03-09 09:25:19,750][23090] Updated weights for policy 0, policy_version 86526 (0.0014) [2023-03-09 09:25:20,567][23090] Updated weights for policy 0, policy_version 86536 (0.0013) [2023-03-09 09:25:21,384][23090] Updated weights for policy 0, policy_version 86546 (0.0018) [2023-03-09 09:25:22,266][23090] Updated weights for policy 0, policy_version 86556 (0.0013) [2023-03-09 09:25:23,095][23090] Updated weights for policy 0, policy_version 86566 (0.0013) [2023-03-09 09:25:23,873][23090] Updated weights for policy 0, policy_version 86576 (0.0013) [2023-03-09 09:25:24,058][22664] Fps is (10 sec: 199893.7, 60 sec: 197700.3, 300 sec: 198163.1). Total num frames: 1418493952. Throughput: 0: 49411.0. Samples: 354685408. Policy #0 lag: (min: 1.0, avg: 17.2, max: 33.0) [2023-03-09 09:25:24,059][22664] Avg episode reward: [(0, '52.908')] [2023-03-09 09:25:24,835][23090] Updated weights for policy 0, policy_version 86586 (0.0020) [2023-03-09 09:25:25,676][23090] Updated weights for policy 0, policy_version 86597 (0.0018) [2023-03-09 09:25:26,418][23090] Updated weights for policy 0, policy_version 86607 (0.0013) [2023-03-09 09:25:27,460][22940] Signal inference workers to stop experience collection... (28600 times) [2023-03-09 09:25:27,472][22940] Signal inference workers to resume experience collection... (28600 times) [2023-03-09 09:25:27,493][23090] Updated weights for policy 0, policy_version 86618 (0.0015) [2023-03-09 09:25:27,530][23090] InferenceWorker_p0-w0: stopping experience collection (28600 times) [2023-03-09 09:25:27,531][23090] InferenceWorker_p0-w0: resuming experience collection (28600 times) [2023-03-09 09:25:28,223][23090] Updated weights for policy 0, policy_version 86628 (0.0019) [2023-03-09 09:25:29,059][22664] Fps is (10 sec: 198247.8, 60 sec: 197974.4, 300 sec: 198107.7). Total num frames: 1419476992. Throughput: 0: 49456.7. Samples: 354834832. Policy #0 lag: (min: 1.0, avg: 17.2, max: 33.0) [2023-03-09 09:25:29,060][22664] Avg episode reward: [(0, '54.252')] [2023-03-09 09:25:29,064][23090] Updated weights for policy 0, policy_version 86639 (0.0022) [2023-03-09 09:25:30,056][23090] Updated weights for policy 0, policy_version 86649 (0.0013) [2023-03-09 09:25:30,798][23090] Updated weights for policy 0, policy_version 86659 (0.0022) [2023-03-09 09:25:31,642][23090] Updated weights for policy 0, policy_version 86669 (0.0017) [2023-03-09 09:25:32,417][23090] Updated weights for policy 0, policy_version 86679 (0.0013) [2023-03-09 09:25:33,227][23090] Updated weights for policy 0, policy_version 86689 (0.0013) [2023-03-09 09:25:34,059][22664] Fps is (10 sec: 196603.2, 60 sec: 197700.4, 300 sec: 198107.6). Total num frames: 1420460032. Throughput: 0: 49457.6. Samples: 355131728. Policy #0 lag: (min: 1.0, avg: 17.2, max: 33.0) [2023-03-09 09:25:34,060][22664] Avg episode reward: [(0, '52.613')] [2023-03-09 09:25:34,215][23090] Updated weights for policy 0, policy_version 86700 (0.0013) [2023-03-09 09:25:34,964][23090] Updated weights for policy 0, policy_version 86710 (0.0013) [2023-03-09 09:25:35,876][23090] Updated weights for policy 0, policy_version 86721 (0.0013) [2023-03-09 09:25:36,756][23090] Updated weights for policy 0, policy_version 86731 (0.0017) [2023-03-09 09:25:37,531][23090] Updated weights for policy 0, policy_version 86741 (0.0015) [2023-03-09 09:25:38,394][23090] Updated weights for policy 0, policy_version 86751 (0.0015) [2023-03-09 09:25:39,058][22664] Fps is (10 sec: 198247.2, 60 sec: 197973.6, 300 sec: 198107.6). Total num frames: 1421459456. Throughput: 0: 49456.7. Samples: 355428576. Policy #0 lag: (min: 1.0, avg: 17.2, max: 33.0) [2023-03-09 09:25:39,060][22664] Avg episode reward: [(0, '53.347')] [2023-03-09 09:25:39,190][23090] Updated weights for policy 0, policy_version 86761 (0.0016) [2023-03-09 09:25:40,010][23090] Updated weights for policy 0, policy_version 86771 (0.0013) [2023-03-09 09:25:40,608][22940] Signal inference workers to stop experience collection... (28650 times) [2023-03-09 09:25:40,623][22940] Signal inference workers to resume experience collection... (28650 times) [2023-03-09 09:25:40,692][23090] InferenceWorker_p0-w0: stopping experience collection (28650 times) [2023-03-09 09:25:40,692][23090] InferenceWorker_p0-w0: resuming experience collection (28650 times) [2023-03-09 09:25:40,865][23090] Updated weights for policy 0, policy_version 86781 (0.0020) [2023-03-09 09:25:41,691][23090] Updated weights for policy 0, policy_version 86791 (0.0022) [2023-03-09 09:25:42,422][23090] Updated weights for policy 0, policy_version 86801 (0.0019) [2023-03-09 09:25:43,406][23090] Updated weights for policy 0, policy_version 86811 (0.0013) [2023-03-09 09:25:44,059][22664] Fps is (10 sec: 198243.9, 60 sec: 197426.0, 300 sec: 198051.9). Total num frames: 1422442496. Throughput: 0: 49456.4. Samples: 355578032. Policy #0 lag: (min: 0.0, avg: 17.0, max: 33.0) [2023-03-09 09:25:44,061][22664] Avg episode reward: [(0, '54.442')] [2023-03-09 09:25:44,174][23090] Updated weights for policy 0, policy_version 86821 (0.0013) [2023-03-09 09:25:44,929][23090] Updated weights for policy 0, policy_version 86831 (0.0012) [2023-03-09 09:25:45,854][23090] Updated weights for policy 0, policy_version 86841 (0.0013) [2023-03-09 09:25:46,777][23090] Updated weights for policy 0, policy_version 86852 (0.0013) [2023-03-09 09:25:47,476][23090] Updated weights for policy 0, policy_version 86862 (0.0016) [2023-03-09 09:25:48,325][23090] Updated weights for policy 0, policy_version 86872 (0.0016) [2023-03-09 09:25:49,059][22664] Fps is (10 sec: 199880.7, 60 sec: 198247.0, 300 sec: 198107.7). Total num frames: 1423458304. Throughput: 0: 49501.3. Samples: 355876896. Policy #0 lag: (min: 0.0, avg: 17.0, max: 33.0) [2023-03-09 09:25:49,060][22664] Avg episode reward: [(0, '54.760')] [2023-03-09 09:25:49,125][23090] Updated weights for policy 0, policy_version 86882 (0.0017) [2023-03-09 09:25:50,007][23090] Updated weights for policy 0, policy_version 86892 (0.0013) [2023-03-09 09:25:50,800][23090] Updated weights for policy 0, policy_version 86902 (0.0020) [2023-03-09 09:25:51,240][22940] Signal inference workers to stop experience collection... (28700 times) [2023-03-09 09:25:51,242][22940] Signal inference workers to resume experience collection... (28700 times) [2023-03-09 09:25:51,329][23090] InferenceWorker_p0-w0: stopping experience collection (28700 times) [2023-03-09 09:25:51,331][23090] InferenceWorker_p0-w0: resuming experience collection (28700 times) [2023-03-09 09:25:51,606][23090] Updated weights for policy 0, policy_version 86912 (0.0013) [2023-03-09 09:25:52,413][23090] Updated weights for policy 0, policy_version 86922 (0.0016) [2023-03-09 09:25:53,232][23090] Updated weights for policy 0, policy_version 86932 (0.0020) [2023-03-09 09:25:54,059][22664] Fps is (10 sec: 199887.3, 60 sec: 198246.6, 300 sec: 198051.9). Total num frames: 1424441344. Throughput: 0: 49591.4. Samples: 356175824. Policy #0 lag: (min: 0.0, avg: 17.0, max: 33.0) [2023-03-09 09:25:54,060][22664] Avg episode reward: [(0, '54.856')] [2023-03-09 09:25:54,081][23090] Updated weights for policy 0, policy_version 86942 (0.0013) [2023-03-09 09:25:54,910][23090] Updated weights for policy 0, policy_version 86952 (0.0013) [2023-03-09 09:25:55,768][23090] Updated weights for policy 0, policy_version 86962 (0.0016) [2023-03-09 09:25:56,578][23090] Updated weights for policy 0, policy_version 86972 (0.0017) [2023-03-09 09:25:57,451][23090] Updated weights for policy 0, policy_version 86982 (0.0020) [2023-03-09 09:25:58,156][23090] Updated weights for policy 0, policy_version 86992 (0.0013) [2023-03-09 09:25:59,059][22664] Fps is (10 sec: 194964.7, 60 sec: 197700.1, 300 sec: 197996.4). Total num frames: 1425408000. Throughput: 0: 49545.2. Samples: 356323232. Policy #0 lag: (min: 0.0, avg: 17.0, max: 33.0) [2023-03-09 09:25:59,061][22664] Avg episode reward: [(0, '55.241')] [2023-03-09 09:25:59,139][23090] Updated weights for policy 0, policy_version 87002 (0.0013) [2023-03-09 09:25:59,922][23090] Updated weights for policy 0, policy_version 87012 (0.0013) [2023-03-09 09:26:00,659][23090] Updated weights for policy 0, policy_version 87022 (0.0016) [2023-03-09 09:26:01,532][23090] Updated weights for policy 0, policy_version 87032 (0.0020) [2023-03-09 09:26:02,270][22940] Signal inference workers to stop experience collection... (28750 times) [2023-03-09 09:26:02,271][22940] Signal inference workers to resume experience collection... (28750 times) [2023-03-09 09:26:02,333][23090] InferenceWorker_p0-w0: stopping experience collection (28750 times) [2023-03-09 09:26:02,333][23090] InferenceWorker_p0-w0: resuming experience collection (28750 times) [2023-03-09 09:26:02,336][23090] Updated weights for policy 0, policy_version 87042 (0.0013) [2023-03-09 09:26:03,189][23090] Updated weights for policy 0, policy_version 87052 (0.0013) [2023-03-09 09:26:04,006][23090] Updated weights for policy 0, policy_version 87062 (0.0016) [2023-03-09 09:26:04,059][22664] Fps is (10 sec: 199882.5, 60 sec: 198518.3, 300 sec: 198107.6). Total num frames: 1426440192. Throughput: 0: 49633.2. Samples: 356622016. Policy #0 lag: (min: 0.0, avg: 17.0, max: 33.0) [2023-03-09 09:26:04,061][22664] Avg episode reward: [(0, '53.345')] [2023-03-09 09:26:04,820][23090] Updated weights for policy 0, policy_version 87072 (0.0013) [2023-03-09 09:26:05,644][23090] Updated weights for policy 0, policy_version 87082 (0.0012) [2023-03-09 09:26:06,430][23090] Updated weights for policy 0, policy_version 87092 (0.0017) [2023-03-09 09:26:07,392][23090] Updated weights for policy 0, policy_version 87103 (0.0017) [2023-03-09 09:26:08,221][23090] Updated weights for policy 0, policy_version 87113 (0.0017) [2023-03-09 09:26:09,006][23090] Updated weights for policy 0, policy_version 87123 (0.0017) [2023-03-09 09:26:09,059][22664] Fps is (10 sec: 201523.3, 60 sec: 198518.6, 300 sec: 198107.6). Total num frames: 1427423232. Throughput: 0: 49631.5. Samples: 356918848. Policy #0 lag: (min: 0.0, avg: 17.0, max: 33.0) [2023-03-09 09:26:09,061][22664] Avg episode reward: [(0, '50.964')] [2023-03-09 09:26:09,925][23090] Updated weights for policy 0, policy_version 87133 (0.0016) [2023-03-09 09:26:10,721][23090] Updated weights for policy 0, policy_version 87143 (0.0012) [2023-03-09 09:26:11,447][23090] Updated weights for policy 0, policy_version 87153 (0.0018) [2023-03-09 09:26:12,420][23090] Updated weights for policy 0, policy_version 87163 (0.0019) [2023-03-09 09:26:13,268][22940] Signal inference workers to stop experience collection... (28800 times) [2023-03-09 09:26:13,289][22940] Signal inference workers to resume experience collection... (28800 times) [2023-03-09 09:26:13,306][23090] Updated weights for policy 0, policy_version 87174 (0.0013) [2023-03-09 09:26:13,343][23090] InferenceWorker_p0-w0: stopping experience collection (28800 times) [2023-03-09 09:26:13,343][23090] InferenceWorker_p0-w0: resuming experience collection (28800 times) [2023-03-09 09:26:13,995][23090] Updated weights for policy 0, policy_version 87184 (0.0022) [2023-03-09 09:26:14,058][22664] Fps is (10 sec: 198253.2, 60 sec: 198794.0, 300 sec: 198052.0). Total num frames: 1428422656. Throughput: 0: 49632.8. Samples: 357068304. Policy #0 lag: (min: 0.0, avg: 17.0, max: 33.0) [2023-03-09 09:26:14,059][22664] Avg episode reward: [(0, '53.939')] [2023-03-09 09:26:15,004][23090] Updated weights for policy 0, policy_version 87194 (0.0028) [2023-03-09 09:26:15,752][23090] Updated weights for policy 0, policy_version 87204 (0.0016) [2023-03-09 09:26:16,496][23090] Updated weights for policy 0, policy_version 87214 (0.0013) [2023-03-09 09:26:17,379][23090] Updated weights for policy 0, policy_version 87224 (0.0015) [2023-03-09 09:26:18,196][23090] Updated weights for policy 0, policy_version 87234 (0.0013) [2023-03-09 09:26:19,059][22664] Fps is (10 sec: 198254.1, 60 sec: 198519.6, 300 sec: 197996.6). Total num frames: 1429405696. Throughput: 0: 49679.1. Samples: 357367280. Policy #0 lag: (min: 0.0, avg: 17.0, max: 33.0) [2023-03-09 09:26:19,060][22664] Avg episode reward: [(0, '56.008')] [2023-03-09 09:26:19,066][23090] Updated weights for policy 0, policy_version 87244 (0.0013) [2023-03-09 09:26:19,865][23090] Updated weights for policy 0, policy_version 87254 (0.0017) [2023-03-09 09:26:20,675][23090] Updated weights for policy 0, policy_version 87264 (0.0013) [2023-03-09 09:26:21,525][23090] Updated weights for policy 0, policy_version 87274 (0.0013) [2023-03-09 09:26:22,347][23090] Updated weights for policy 0, policy_version 87284 (0.0016) [2023-03-09 09:26:23,183][23090] Updated weights for policy 0, policy_version 87294 (0.0020) [2023-03-09 09:26:23,996][23090] Updated weights for policy 0, policy_version 87304 (0.0013) [2023-03-09 09:26:24,058][22664] Fps is (10 sec: 196608.1, 60 sec: 198246.4, 300 sec: 198052.0). Total num frames: 1430388736. Throughput: 0: 49635.2. Samples: 357662160. Policy #0 lag: (min: 0.0, avg: 17.0, max: 33.0) [2023-03-09 09:26:24,059][22664] Avg episode reward: [(0, '52.283')] [2023-03-09 09:26:24,335][22940] Signal inference workers to stop experience collection... (28850 times) [2023-03-09 09:26:24,337][22940] Signal inference workers to resume experience collection... (28850 times) [2023-03-09 09:26:24,406][23090] InferenceWorker_p0-w0: stopping experience collection (28850 times) [2023-03-09 09:26:24,406][23090] InferenceWorker_p0-w0: resuming experience collection (28850 times) [2023-03-09 09:26:24,805][23090] Updated weights for policy 0, policy_version 87314 (0.0013) [2023-03-09 09:26:25,728][23090] Updated weights for policy 0, policy_version 87324 (0.0015) [2023-03-09 09:26:26,490][23090] Updated weights for policy 0, policy_version 87334 (0.0013) [2023-03-09 09:26:27,297][23090] Updated weights for policy 0, policy_version 87345 (0.0019) [2023-03-09 09:26:28,255][23090] Updated weights for policy 0, policy_version 87355 (0.0013) [2023-03-09 09:26:29,059][23090] Updated weights for policy 0, policy_version 87365 (0.0015) [2023-03-09 09:26:29,059][22664] Fps is (10 sec: 198240.0, 60 sec: 198518.3, 300 sec: 198051.9). Total num frames: 1431388160. Throughput: 0: 49681.0. Samples: 357813680. Policy #0 lag: (min: 0.0, avg: 17.0, max: 33.0) [2023-03-09 09:26:29,062][22664] Avg episode reward: [(0, '54.856')] [2023-03-09 09:26:29,767][23090] Updated weights for policy 0, policy_version 87375 (0.0013) [2023-03-09 09:26:30,750][23090] Updated weights for policy 0, policy_version 87385 (0.0016) [2023-03-09 09:26:31,612][23090] Updated weights for policy 0, policy_version 87396 (0.0013) [2023-03-09 09:26:32,386][23090] Updated weights for policy 0, policy_version 87406 (0.0017) [2023-03-09 09:26:33,224][23090] Updated weights for policy 0, policy_version 87416 (0.0013) [2023-03-09 09:26:34,034][23090] Updated weights for policy 0, policy_version 87426 (0.0017) [2023-03-09 09:26:34,058][22664] Fps is (10 sec: 199885.1, 60 sec: 198793.4, 300 sec: 198052.3). Total num frames: 1432387584. Throughput: 0: 49636.9. Samples: 358110544. Policy #0 lag: (min: 0.0, avg: 17.0, max: 33.0) [2023-03-09 09:26:34,059][22664] Avg episode reward: [(0, '53.345')] [2023-03-09 09:26:34,901][23090] Updated weights for policy 0, policy_version 87436 (0.0016) [2023-03-09 09:26:35,591][22940] Signal inference workers to stop experience collection... (28900 times) [2023-03-09 09:26:35,605][22940] Signal inference workers to resume experience collection... (28900 times) [2023-03-09 09:26:35,668][23090] InferenceWorker_p0-w0: stopping experience collection (28900 times) [2023-03-09 09:26:35,671][23090] InferenceWorker_p0-w0: resuming experience collection (28900 times) [2023-03-09 09:26:35,675][23090] Updated weights for policy 0, policy_version 87446 (0.0018) [2023-03-09 09:26:36,549][23090] Updated weights for policy 0, policy_version 87456 (0.0017) [2023-03-09 09:26:37,350][23090] Updated weights for policy 0, policy_version 87466 (0.0016) [2023-03-09 09:26:38,115][23090] Updated weights for policy 0, policy_version 87476 (0.0017) [2023-03-09 09:26:38,969][23090] Updated weights for policy 0, policy_version 87486 (0.0016) [2023-03-09 09:26:39,063][22664] Fps is (10 sec: 199794.7, 60 sec: 198776.3, 300 sec: 198048.7). Total num frames: 1433387008. Throughput: 0: 49631.1. Samples: 358409456. Policy #0 lag: (min: 0.0, avg: 16.8, max: 34.0) [2023-03-09 09:26:39,065][22664] Avg episode reward: [(0, '53.955')] [2023-03-09 09:26:39,766][23090] Updated weights for policy 0, policy_version 87496 (0.0017) [2023-03-09 09:26:40,654][23090] Updated weights for policy 0, policy_version 87506 (0.0016) [2023-03-09 09:26:41,505][23090] Updated weights for policy 0, policy_version 87516 (0.0014) [2023-03-09 09:26:42,304][23090] Updated weights for policy 0, policy_version 87526 (0.0013) [2023-03-09 09:26:42,997][23090] Updated weights for policy 0, policy_version 87536 (0.0016) [2023-03-09 09:26:44,015][23090] Updated weights for policy 0, policy_version 87546 (0.0017) [2023-03-09 09:26:44,058][22664] Fps is (10 sec: 198245.8, 60 sec: 198793.7, 300 sec: 198052.0). Total num frames: 1434370048. Throughput: 0: 49682.6. Samples: 358558928. Policy #0 lag: (min: 0.0, avg: 16.8, max: 34.0) [2023-03-09 09:26:44,061][22664] Avg episode reward: [(0, '54.667')] [2023-03-09 09:26:44,758][23090] Updated weights for policy 0, policy_version 87556 (0.0018) [2023-03-09 09:26:45,571][23090] Updated weights for policy 0, policy_version 87566 (0.0013) [2023-03-09 09:26:46,376][23090] Updated weights for policy 0, policy_version 87576 (0.0013) [2023-03-09 09:26:46,623][22940] Signal inference workers to stop experience collection... (28950 times) [2023-03-09 09:26:46,626][22940] Signal inference workers to resume experience collection... (28950 times) [2023-03-09 09:26:46,696][23090] InferenceWorker_p0-w0: stopping experience collection (28950 times) [2023-03-09 09:26:46,697][23090] InferenceWorker_p0-w0: resuming experience collection (28950 times) [2023-03-09 09:26:47,190][23090] Updated weights for policy 0, policy_version 87586 (0.0013) [2023-03-09 09:26:48,071][23090] Updated weights for policy 0, policy_version 87596 (0.0013) [2023-03-09 09:26:48,862][23090] Updated weights for policy 0, policy_version 87606 (0.0013) [2023-03-09 09:26:49,058][22664] Fps is (10 sec: 198343.6, 60 sec: 198520.2, 300 sec: 198107.8). Total num frames: 1435369472. Throughput: 0: 49685.4. Samples: 358857840. Policy #0 lag: (min: 0.0, avg: 16.8, max: 34.0) [2023-03-09 09:26:49,059][22664] Avg episode reward: [(0, '50.856')] [2023-03-09 09:26:49,674][23090] Updated weights for policy 0, policy_version 87616 (0.0013) [2023-03-09 09:26:50,561][23090] Updated weights for policy 0, policy_version 87626 (0.0018) [2023-03-09 09:26:51,341][23090] Updated weights for policy 0, policy_version 87636 (0.0018) [2023-03-09 09:26:52,185][23090] Updated weights for policy 0, policy_version 87646 (0.0013) [2023-03-09 09:26:53,016][23090] Updated weights for policy 0, policy_version 87656 (0.0021) [2023-03-09 09:26:53,964][23090] Updated weights for policy 0, policy_version 87667 (0.0017) [2023-03-09 09:26:54,059][22664] Fps is (10 sec: 198241.1, 60 sec: 198519.3, 300 sec: 198107.6). Total num frames: 1436352512. Throughput: 0: 49595.6. Samples: 359150640. Policy #0 lag: (min: 0.0, avg: 16.8, max: 34.0) [2023-03-09 09:26:54,061][22664] Avg episode reward: [(0, '52.659')] [2023-03-09 09:26:54,816][23090] Updated weights for policy 0, policy_version 87677 (0.0012) [2023-03-09 09:26:55,615][23090] Updated weights for policy 0, policy_version 87687 (0.0013) [2023-03-09 09:26:56,351][23090] Updated weights for policy 0, policy_version 87697 (0.0018) [2023-03-09 09:26:57,318][23090] Updated weights for policy 0, policy_version 87707 (0.0013) [2023-03-09 09:26:58,109][23090] Updated weights for policy 0, policy_version 87717 (0.0013) [2023-03-09 09:26:58,648][22940] Signal inference workers to stop experience collection... (29000 times) [2023-03-09 09:26:58,672][22940] Signal inference workers to resume experience collection... (29000 times) [2023-03-09 09:26:58,718][23090] InferenceWorker_p0-w0: stopping experience collection (29000 times) [2023-03-09 09:26:58,718][23090] InferenceWorker_p0-w0: resuming experience collection (29000 times) [2023-03-09 09:26:58,843][23090] Updated weights for policy 0, policy_version 87727 (0.0021) [2023-03-09 09:26:59,059][22664] Fps is (10 sec: 198239.7, 60 sec: 199066.0, 300 sec: 198107.5). Total num frames: 1437351936. Throughput: 0: 49640.5. Samples: 359302144. Policy #0 lag: (min: 0.0, avg: 16.8, max: 34.0) [2023-03-09 09:26:59,061][22664] Avg episode reward: [(0, '52.897')] [2023-03-09 09:26:59,874][23090] Updated weights for policy 0, policy_version 87737 (0.0017) [2023-03-09 09:27:00,565][23090] Updated weights for policy 0, policy_version 87747 (0.0017) [2023-03-09 09:27:01,410][23090] Updated weights for policy 0, policy_version 87758 (0.0012) [2023-03-09 09:27:02,242][23090] Updated weights for policy 0, policy_version 87768 (0.0013) [2023-03-09 09:27:03,059][23090] Updated weights for policy 0, policy_version 87778 (0.0013) [2023-03-09 09:27:03,907][23090] Updated weights for policy 0, policy_version 87788 (0.0020) [2023-03-09 09:27:04,059][22664] Fps is (10 sec: 201527.7, 60 sec: 198793.5, 300 sec: 198163.1). Total num frames: 1438367744. Throughput: 0: 49683.6. Samples: 359603040. Policy #0 lag: (min: 0.0, avg: 16.8, max: 34.0) [2023-03-09 09:27:04,059][22664] Avg episode reward: [(0, '54.440')] [2023-03-09 09:27:04,660][23090] Updated weights for policy 0, policy_version 87798 (0.0021) [2023-03-09 09:27:05,499][23090] Updated weights for policy 0, policy_version 87808 (0.0018) [2023-03-09 09:27:06,339][23090] Updated weights for policy 0, policy_version 87818 (0.0021) [2023-03-09 09:27:07,142][23090] Updated weights for policy 0, policy_version 87828 (0.0015) [2023-03-09 09:27:07,995][23090] Updated weights for policy 0, policy_version 87838 (0.0020) [2023-03-09 09:27:08,822][23090] Updated weights for policy 0, policy_version 87848 (0.0018) [2023-03-09 09:27:09,059][22664] Fps is (10 sec: 198250.6, 60 sec: 198520.6, 300 sec: 198163.0). Total num frames: 1439334400. Throughput: 0: 49725.4. Samples: 359899808. Policy #0 lag: (min: 0.0, avg: 16.8, max: 34.0) [2023-03-09 09:27:09,060][22664] Avg episode reward: [(0, '53.133')] [2023-03-09 09:27:09,168][22940] Signal inference workers to stop experience collection... (29050 times) [2023-03-09 09:27:09,191][22940] Signal inference workers to resume experience collection... (29050 times) [2023-03-09 09:27:09,236][23090] InferenceWorker_p0-w0: stopping experience collection (29050 times) [2023-03-09 09:27:09,281][23090] InferenceWorker_p0-w0: resuming experience collection (29050 times) [2023-03-09 09:27:09,683][23090] Updated weights for policy 0, policy_version 87858 (0.0016) [2023-03-09 09:27:10,563][23090] Updated weights for policy 0, policy_version 87868 (0.0016) [2023-03-09 09:27:11,368][23090] Updated weights for policy 0, policy_version 87878 (0.0020) [2023-03-09 09:27:12,061][23090] Updated weights for policy 0, policy_version 87888 (0.0017) [2023-03-09 09:27:13,071][23090] Updated weights for policy 0, policy_version 87898 (0.0013) [2023-03-09 09:27:13,832][23090] Updated weights for policy 0, policy_version 87908 (0.0018) [2023-03-09 09:27:14,059][22664] Fps is (10 sec: 196604.6, 60 sec: 198518.7, 300 sec: 198163.1). Total num frames: 1440333824. Throughput: 0: 49634.3. Samples: 360047216. Policy #0 lag: (min: 0.0, avg: 16.8, max: 34.0) [2023-03-09 09:27:14,060][22664] Avg episode reward: [(0, '54.491')] [2023-03-09 09:27:14,613][23090] Updated weights for policy 0, policy_version 87918 (0.0019) [2023-03-09 09:27:15,478][23090] Updated weights for policy 0, policy_version 87928 (0.0013) [2023-03-09 09:27:16,252][23090] Updated weights for policy 0, policy_version 87938 (0.0020) [2023-03-09 09:27:17,144][23090] Updated weights for policy 0, policy_version 87948 (0.0013) [2023-03-09 09:27:18,021][23090] Updated weights for policy 0, policy_version 87959 (0.0016) [2023-03-09 09:27:18,788][23090] Updated weights for policy 0, policy_version 87969 (0.0013) [2023-03-09 09:27:19,059][22664] Fps is (10 sec: 198243.4, 60 sec: 198518.8, 300 sec: 198107.6). Total num frames: 1441316864. Throughput: 0: 49680.8. Samples: 360346192. Policy #0 lag: (min: 0.0, avg: 16.8, max: 34.0) [2023-03-09 09:27:19,061][22664] Avg episode reward: [(0, '53.523')] [2023-03-09 09:27:19,124][22940] Saving /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000087972_1441333248.pth... [2023-03-09 09:27:19,185][22940] Removing /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000085071_1393803264.pth [2023-03-09 09:27:19,304][22940] Signal inference workers to stop experience collection... (29100 times) [2023-03-09 09:27:19,322][22940] Signal inference workers to resume experience collection... (29100 times) [2023-03-09 09:27:19,383][23090] InferenceWorker_p0-w0: stopping experience collection (29100 times) [2023-03-09 09:27:19,425][23090] InferenceWorker_p0-w0: resuming experience collection (29100 times) [2023-03-09 09:27:19,826][23090] Updated weights for policy 0, policy_version 87980 (0.0013) [2023-03-09 09:27:20,567][23090] Updated weights for policy 0, policy_version 87990 (0.0017) [2023-03-09 09:27:21,434][23090] Updated weights for policy 0, policy_version 88000 (0.0013) [2023-03-09 09:27:22,320][23090] Updated weights for policy 0, policy_version 88010 (0.0022) [2023-03-09 09:27:23,090][23090] Updated weights for policy 0, policy_version 88020 (0.0019) [2023-03-09 09:27:23,856][23090] Updated weights for policy 0, policy_version 88030 (0.0013) [2023-03-09 09:27:24,058][22664] Fps is (10 sec: 196611.7, 60 sec: 198519.3, 300 sec: 198052.2). Total num frames: 1442299904. Throughput: 0: 49638.8. Samples: 360642960. Policy #0 lag: (min: 0.0, avg: 16.8, max: 34.0) [2023-03-09 09:27:24,060][22664] Avg episode reward: [(0, '55.270')] [2023-03-09 09:27:24,680][23090] Updated weights for policy 0, policy_version 88040 (0.0018) [2023-03-09 09:27:25,542][23090] Updated weights for policy 0, policy_version 88050 (0.0012) [2023-03-09 09:27:26,388][23090] Updated weights for policy 0, policy_version 88060 (0.0023) [2023-03-09 09:27:27,202][23090] Updated weights for policy 0, policy_version 88070 (0.0021) [2023-03-09 09:27:27,899][23090] Updated weights for policy 0, policy_version 88080 (0.0020) [2023-03-09 09:27:28,340][22940] Signal inference workers to stop experience collection... (29150 times) [2023-03-09 09:27:28,343][22940] Signal inference workers to resume experience collection... (29150 times) [2023-03-09 09:27:28,410][23090] InferenceWorker_p0-w0: stopping experience collection (29150 times) [2023-03-09 09:27:28,411][23090] InferenceWorker_p0-w0: resuming experience collection (29150 times) [2023-03-09 09:27:28,917][23090] Updated weights for policy 0, policy_version 88090 (0.0016) [2023-03-09 09:27:29,059][22664] Fps is (10 sec: 198248.6, 60 sec: 198520.2, 300 sec: 198051.9). Total num frames: 1443299328. Throughput: 0: 49632.9. Samples: 360792416. Policy #0 lag: (min: 0.0, avg: 16.8, max: 34.0) [2023-03-09 09:27:29,060][22664] Avg episode reward: [(0, '54.058')] [2023-03-09 09:27:29,656][23090] Updated weights for policy 0, policy_version 88100 (0.0015) [2023-03-09 09:27:30,477][23090] Updated weights for policy 0, policy_version 88110 (0.0016) [2023-03-09 09:27:31,314][23090] Updated weights for policy 0, policy_version 88120 (0.0013) [2023-03-09 09:27:32,226][23090] Updated weights for policy 0, policy_version 88131 (0.0013) [2023-03-09 09:27:33,039][23090] Updated weights for policy 0, policy_version 88141 (0.0022) [2023-03-09 09:27:33,882][23090] Updated weights for policy 0, policy_version 88151 (0.0020) [2023-03-09 09:27:34,059][22664] Fps is (10 sec: 198245.7, 60 sec: 198246.1, 300 sec: 198107.8). Total num frames: 1444282368. Throughput: 0: 49632.6. Samples: 361091312. Policy #0 lag: (min: 1.0, avg: 16.9, max: 33.0) [2023-03-09 09:27:34,059][22664] Avg episode reward: [(0, '55.833')] [2023-03-09 09:27:34,667][23090] Updated weights for policy 0, policy_version 88161 (0.0013) [2023-03-09 09:27:35,514][23090] Updated weights for policy 0, policy_version 88171 (0.0013) [2023-03-09 09:27:36,044][22940] Signal inference workers to stop experience collection... (29200 times) [2023-03-09 09:27:36,046][22940] Signal inference workers to resume experience collection... (29200 times) [2023-03-09 09:27:36,108][23090] InferenceWorker_p0-w0: stopping experience collection (29200 times) [2023-03-09 09:27:36,108][23090] InferenceWorker_p0-w0: resuming experience collection (29200 times) [2023-03-09 09:27:36,272][23090] Updated weights for policy 0, policy_version 88181 (0.0015) [2023-03-09 09:27:37,064][23090] Updated weights for policy 0, policy_version 88191 (0.0015) [2023-03-09 09:27:37,875][23090] Updated weights for policy 0, policy_version 88201 (0.0017) [2023-03-09 09:27:38,716][23090] Updated weights for policy 0, policy_version 88211 (0.0019) [2023-03-09 09:27:39,059][22664] Fps is (10 sec: 199883.7, 60 sec: 198535.0, 300 sec: 198163.2). Total num frames: 1445298176. Throughput: 0: 49813.4. Samples: 361392240. Policy #0 lag: (min: 1.0, avg: 16.9, max: 33.0) [2023-03-09 09:27:39,061][22664] Avg episode reward: [(0, '54.560')] [2023-03-09 09:27:39,553][23090] Updated weights for policy 0, policy_version 88221 (0.0017) [2023-03-09 09:27:40,366][23090] Updated weights for policy 0, policy_version 88231 (0.0019) [2023-03-09 09:27:41,291][23090] Updated weights for policy 0, policy_version 88242 (0.0012) [2023-03-09 09:27:42,205][23090] Updated weights for policy 0, policy_version 88253 (0.0019) [2023-03-09 09:27:43,014][23090] Updated weights for policy 0, policy_version 88263 (0.0016) [2023-03-09 09:27:43,747][23090] Updated weights for policy 0, policy_version 88273 (0.0013) [2023-03-09 09:27:43,942][22940] Signal inference workers to stop experience collection... (29250 times) [2023-03-09 09:27:43,955][22940] Signal inference workers to resume experience collection... (29250 times) [2023-03-09 09:27:44,015][23090] InferenceWorker_p0-w0: stopping experience collection (29250 times) [2023-03-09 09:27:44,018][23090] InferenceWorker_p0-w0: resuming experience collection (29250 times) [2023-03-09 09:27:44,059][22664] Fps is (10 sec: 201519.0, 60 sec: 198791.6, 300 sec: 198218.5). Total num frames: 1446297600. Throughput: 0: 49767.9. Samples: 361541696. Policy #0 lag: (min: 1.0, avg: 16.9, max: 33.0) [2023-03-09 09:27:44,060][22664] Avg episode reward: [(0, '53.390')] [2023-03-09 09:27:44,709][23090] Updated weights for policy 0, policy_version 88283 (0.0013) [2023-03-09 09:27:45,525][23090] Updated weights for policy 0, policy_version 88293 (0.0023) [2023-03-09 09:27:46,313][23090] Updated weights for policy 0, policy_version 88303 (0.0017) [2023-03-09 09:27:47,221][23090] Updated weights for policy 0, policy_version 88313 (0.0015) [2023-03-09 09:27:47,984][23090] Updated weights for policy 0, policy_version 88323 (0.0013) [2023-03-09 09:27:48,805][23090] Updated weights for policy 0, policy_version 88333 (0.0013) [2023-03-09 09:27:49,059][22664] Fps is (10 sec: 201522.5, 60 sec: 199064.8, 300 sec: 198274.0). Total num frames: 1447313408. Throughput: 0: 49677.3. Samples: 361838528. Policy #0 lag: (min: 1.0, avg: 16.9, max: 33.0) [2023-03-09 09:27:49,061][22664] Avg episode reward: [(0, '54.269')] [2023-03-09 09:27:49,652][23090] Updated weights for policy 0, policy_version 88343 (0.0018) [2023-03-09 09:27:50,449][23090] Updated weights for policy 0, policy_version 88353 (0.0016) [2023-03-09 09:27:51,303][23090] Updated weights for policy 0, policy_version 88363 (0.0022) [2023-03-09 09:27:52,106][23090] Updated weights for policy 0, policy_version 88373 (0.0013) [2023-03-09 09:27:52,503][22940] Signal inference workers to stop experience collection... (29300 times) [2023-03-09 09:27:52,503][22940] Signal inference workers to resume experience collection... (29300 times) [2023-03-09 09:27:52,572][23090] InferenceWorker_p0-w0: stopping experience collection (29300 times) [2023-03-09 09:27:52,573][23090] InferenceWorker_p0-w0: resuming experience collection (29300 times) [2023-03-09 09:27:52,862][23090] Updated weights for policy 0, policy_version 88383 (0.0021) [2023-03-09 09:27:53,684][23090] Updated weights for policy 0, policy_version 88393 (0.0016) [2023-03-09 09:27:54,059][22664] Fps is (10 sec: 199883.6, 60 sec: 199065.4, 300 sec: 198329.7). Total num frames: 1448296448. Throughput: 0: 49724.6. Samples: 362137424. Policy #0 lag: (min: 1.0, avg: 16.9, max: 33.0) [2023-03-09 09:27:54,061][22664] Avg episode reward: [(0, '53.081')] [2023-03-09 09:27:54,537][23090] Updated weights for policy 0, policy_version 88403 (0.0020) [2023-03-09 09:27:55,383][23090] Updated weights for policy 0, policy_version 88413 (0.0020) [2023-03-09 09:27:56,198][23090] Updated weights for policy 0, policy_version 88423 (0.0016) [2023-03-09 09:27:56,920][23090] Updated weights for policy 0, policy_version 88433 (0.0013) [2023-03-09 09:27:57,870][23090] Updated weights for policy 0, policy_version 88443 (0.0017) [2023-03-09 09:27:58,708][23090] Updated weights for policy 0, policy_version 88453 (0.0016) [2023-03-09 09:27:59,058][22664] Fps is (10 sec: 196613.0, 60 sec: 198793.6, 300 sec: 198274.2). Total num frames: 1449279488. Throughput: 0: 49770.9. Samples: 362286896. Policy #0 lag: (min: 1.0, avg: 16.9, max: 33.0) [2023-03-09 09:27:59,059][22664] Avg episode reward: [(0, '54.141')] [2023-03-09 09:27:59,447][23090] Updated weights for policy 0, policy_version 88463 (0.0013) [2023-03-09 09:28:00,150][22940] Signal inference workers to stop experience collection... (29350 times) [2023-03-09 09:28:00,151][22940] Signal inference workers to resume experience collection... (29350 times) [2023-03-09 09:28:00,244][23090] InferenceWorker_p0-w0: stopping experience collection (29350 times) [2023-03-09 09:28:00,245][23090] InferenceWorker_p0-w0: resuming experience collection (29350 times) [2023-03-09 09:28:00,405][23090] Updated weights for policy 0, policy_version 88473 (0.0021) [2023-03-09 09:28:01,133][23090] Updated weights for policy 0, policy_version 88483 (0.0013) [2023-03-09 09:28:01,952][23090] Updated weights for policy 0, policy_version 88493 (0.0016) [2023-03-09 09:28:02,857][23090] Updated weights for policy 0, policy_version 88504 (0.0016) [2023-03-09 09:28:03,672][23090] Updated weights for policy 0, policy_version 88514 (0.0015) [2023-03-09 09:28:04,058][22664] Fps is (10 sec: 198252.7, 60 sec: 198519.6, 300 sec: 198274.2). Total num frames: 1450278912. Throughput: 0: 49769.9. Samples: 362585824. Policy #0 lag: (min: 1.0, avg: 16.9, max: 33.0) [2023-03-09 09:28:04,059][22664] Avg episode reward: [(0, '55.309')] [2023-03-09 09:28:04,555][23090] Updated weights for policy 0, policy_version 88524 (0.0018) [2023-03-09 09:28:05,322][23090] Updated weights for policy 0, policy_version 88534 (0.0016) [2023-03-09 09:28:06,163][23090] Updated weights for policy 0, policy_version 88544 (0.0017) [2023-03-09 09:28:07,060][23090] Updated weights for policy 0, policy_version 88554 (0.0016) [2023-03-09 09:28:07,911][22940] Signal inference workers to stop experience collection... (29400 times) [2023-03-09 09:28:07,933][22940] Signal inference workers to resume experience collection... (29400 times) [2023-03-09 09:28:07,934][23090] Updated weights for policy 0, policy_version 88565 (0.0016) [2023-03-09 09:28:07,983][23090] InferenceWorker_p0-w0: stopping experience collection (29400 times) [2023-03-09 09:28:08,019][23090] InferenceWorker_p0-w0: resuming experience collection (29400 times) [2023-03-09 09:28:08,682][23090] Updated weights for policy 0, policy_version 88575 (0.0016) [2023-03-09 09:28:09,059][22664] Fps is (10 sec: 199879.7, 60 sec: 199065.2, 300 sec: 198274.1). Total num frames: 1451278336. Throughput: 0: 49770.1. Samples: 362882624. Policy #0 lag: (min: 1.0, avg: 16.9, max: 33.0) [2023-03-09 09:28:09,060][22664] Avg episode reward: [(0, '56.789')] [2023-03-09 09:28:09,517][23090] Updated weights for policy 0, policy_version 88585 (0.0013) [2023-03-09 09:28:10,372][23090] Updated weights for policy 0, policy_version 88595 (0.0018) [2023-03-09 09:28:11,305][23090] Updated weights for policy 0, policy_version 88606 (0.0014) [2023-03-09 09:28:12,105][23090] Updated weights for policy 0, policy_version 88616 (0.0013) [2023-03-09 09:28:12,984][23090] Updated weights for policy 0, policy_version 88626 (0.0013) [2023-03-09 09:28:13,793][23090] Updated weights for policy 0, policy_version 88636 (0.0013) [2023-03-09 09:28:14,059][22664] Fps is (10 sec: 198245.4, 60 sec: 198793.0, 300 sec: 198218.6). Total num frames: 1452261376. Throughput: 0: 49767.9. Samples: 363031968. Policy #0 lag: (min: 1.0, avg: 16.9, max: 33.0) [2023-03-09 09:28:14,060][22664] Avg episode reward: [(0, '53.425')] [2023-03-09 09:28:14,650][23090] Updated weights for policy 0, policy_version 88646 (0.0017) [2023-03-09 09:28:15,322][23090] Updated weights for policy 0, policy_version 88656 (0.0013) [2023-03-09 09:28:16,244][23090] Updated weights for policy 0, policy_version 88666 (0.0014) [2023-03-09 09:28:17,063][23090] Updated weights for policy 0, policy_version 88676 (0.0021) [2023-03-09 09:28:17,234][22940] Signal inference workers to stop experience collection... (29450 times) [2023-03-09 09:28:17,238][22940] Signal inference workers to resume experience collection... (29450 times) [2023-03-09 09:28:17,308][23090] InferenceWorker_p0-w0: stopping experience collection (29450 times) [2023-03-09 09:28:17,308][23090] InferenceWorker_p0-w0: resuming experience collection (29450 times) [2023-03-09 09:28:17,830][23090] Updated weights for policy 0, policy_version 88686 (0.0013) [2023-03-09 09:28:18,693][23090] Updated weights for policy 0, policy_version 88696 (0.0018) [2023-03-09 09:28:19,059][22664] Fps is (10 sec: 199885.3, 60 sec: 199338.8, 300 sec: 198385.3). Total num frames: 1453277184. Throughput: 0: 49767.3. Samples: 363330848. Policy #0 lag: (min: 1.0, avg: 16.9, max: 33.0) [2023-03-09 09:28:19,060][22664] Avg episode reward: [(0, '54.822')] [2023-03-09 09:28:19,482][23090] Updated weights for policy 0, policy_version 88706 (0.0012) [2023-03-09 09:28:20,294][23090] Updated weights for policy 0, policy_version 88716 (0.0016) [2023-03-09 09:28:21,267][23090] Updated weights for policy 0, policy_version 88727 (0.0016) [2023-03-09 09:28:21,994][23090] Updated weights for policy 0, policy_version 88737 (0.0017) [2023-03-09 09:28:22,925][23090] Updated weights for policy 0, policy_version 88748 (0.0023) [2023-03-09 09:28:23,718][23090] Updated weights for policy 0, policy_version 88758 (0.0019) [2023-03-09 09:28:24,059][22664] Fps is (10 sec: 199882.7, 60 sec: 199338.2, 300 sec: 198385.3). Total num frames: 1454260224. Throughput: 0: 49764.7. Samples: 363631648. Policy #0 lag: (min: 1.0, avg: 17.1, max: 33.0) [2023-03-09 09:28:24,060][22664] Avg episode reward: [(0, '56.154')] [2023-03-09 09:28:24,559][23090] Updated weights for policy 0, policy_version 88768 (0.0016) [2023-03-09 09:28:25,412][23090] Updated weights for policy 0, policy_version 88778 (0.0013) [2023-03-09 09:28:26,222][23090] Updated weights for policy 0, policy_version 88788 (0.0017) [2023-03-09 09:28:26,649][22940] Signal inference workers to stop experience collection... (29500 times) [2023-03-09 09:28:26,662][22940] Signal inference workers to resume experience collection... (29500 times) [2023-03-09 09:28:26,689][23090] InferenceWorker_p0-w0: stopping experience collection (29500 times) [2023-03-09 09:28:26,729][23090] InferenceWorker_p0-w0: resuming experience collection (29500 times) [2023-03-09 09:28:27,001][23090] Updated weights for policy 0, policy_version 88798 (0.0018) [2023-03-09 09:28:27,824][23090] Updated weights for policy 0, policy_version 88808 (0.0013) [2023-03-09 09:28:28,646][23090] Updated weights for policy 0, policy_version 88818 (0.0017) [2023-03-09 09:28:29,059][22664] Fps is (10 sec: 198242.3, 60 sec: 199337.8, 300 sec: 198385.2). Total num frames: 1455259648. Throughput: 0: 49809.3. Samples: 363783120. Policy #0 lag: (min: 1.0, avg: 17.1, max: 33.0) [2023-03-09 09:28:29,061][22664] Avg episode reward: [(0, '52.265')] [2023-03-09 09:28:29,604][23090] Updated weights for policy 0, policy_version 88829 (0.0012) [2023-03-09 09:28:30,420][23090] Updated weights for policy 0, policy_version 88839 (0.0013) [2023-03-09 09:28:31,117][23090] Updated weights for policy 0, policy_version 88849 (0.0018) [2023-03-09 09:28:32,103][23090] Updated weights for policy 0, policy_version 88859 (0.0016) [2023-03-09 09:28:32,885][23090] Updated weights for policy 0, policy_version 88869 (0.0020) [2023-03-09 09:28:33,634][23090] Updated weights for policy 0, policy_version 88879 (0.0022) [2023-03-09 09:28:34,059][22664] Fps is (10 sec: 199882.9, 60 sec: 199611.1, 300 sec: 198385.3). Total num frames: 1456259072. Throughput: 0: 49810.1. Samples: 364079984. Policy #0 lag: (min: 1.0, avg: 17.1, max: 33.0) [2023-03-09 09:28:34,060][22664] Avg episode reward: [(0, '54.675')] [2023-03-09 09:28:34,558][23090] Updated weights for policy 0, policy_version 88889 (0.0016) [2023-03-09 09:28:35,343][23090] Updated weights for policy 0, policy_version 88899 (0.0017) [2023-03-09 09:28:36,188][23090] Updated weights for policy 0, policy_version 88909 (0.0016) [2023-03-09 09:28:37,007][23090] Updated weights for policy 0, policy_version 88919 (0.0016) [2023-03-09 09:28:37,342][22940] Signal inference workers to stop experience collection... (29550 times) [2023-03-09 09:28:37,352][22940] Signal inference workers to resume experience collection... (29550 times) [2023-03-09 09:28:37,412][23090] InferenceWorker_p0-w0: stopping experience collection (29550 times) [2023-03-09 09:28:37,412][23090] InferenceWorker_p0-w0: resuming experience collection (29550 times) [2023-03-09 09:28:37,798][23090] Updated weights for policy 0, policy_version 88929 (0.0019) [2023-03-09 09:28:38,667][23090] Updated weights for policy 0, policy_version 88939 (0.0017) [2023-03-09 09:28:39,058][22664] Fps is (10 sec: 201531.7, 60 sec: 199612.4, 300 sec: 198551.9). Total num frames: 1457274880. Throughput: 0: 49810.9. Samples: 364378896. Policy #0 lag: (min: 1.0, avg: 17.1, max: 33.0) [2023-03-09 09:28:39,059][22664] Avg episode reward: [(0, '55.578')] [2023-03-09 09:28:39,470][23090] Updated weights for policy 0, policy_version 88949 (0.0016) [2023-03-09 09:28:40,238][23090] Updated weights for policy 0, policy_version 88959 (0.0016) [2023-03-09 09:28:41,098][23090] Updated weights for policy 0, policy_version 88969 (0.0013) [2023-03-09 09:28:41,896][23090] Updated weights for policy 0, policy_version 88979 (0.0019) [2023-03-09 09:28:42,728][23090] Updated weights for policy 0, policy_version 88989 (0.0015) [2023-03-09 09:28:43,602][23090] Updated weights for policy 0, policy_version 88999 (0.0013) [2023-03-09 09:28:44,059][22664] Fps is (10 sec: 199884.5, 60 sec: 199338.6, 300 sec: 198496.4). Total num frames: 1458257920. Throughput: 0: 49808.0. Samples: 364528272. Policy #0 lag: (min: 1.0, avg: 17.1, max: 33.0) [2023-03-09 09:28:44,061][22664] Avg episode reward: [(0, '55.348')] [2023-03-09 09:28:44,302][23090] Updated weights for policy 0, policy_version 89009 (0.0016) [2023-03-09 09:28:45,287][23090] Updated weights for policy 0, policy_version 89020 (0.0017) [2023-03-09 09:28:46,200][23090] Updated weights for policy 0, policy_version 89030 (0.0013) [2023-03-09 09:28:46,880][23090] Updated weights for policy 0, policy_version 89040 (0.0019) [2023-03-09 09:28:47,841][23090] Updated weights for policy 0, policy_version 89050 (0.0019) [2023-03-09 09:28:48,761][23090] Updated weights for policy 0, policy_version 89061 (0.0016) [2023-03-09 09:28:49,059][22664] Fps is (10 sec: 196602.9, 60 sec: 198792.5, 300 sec: 198440.6). Total num frames: 1459240960. Throughput: 0: 49762.2. Samples: 364825136. Policy #0 lag: (min: 1.0, avg: 17.1, max: 33.0) [2023-03-09 09:28:49,060][22664] Avg episode reward: [(0, '54.244')] [2023-03-09 09:28:49,304][22940] Signal inference workers to stop experience collection... (29600 times) [2023-03-09 09:28:49,329][22940] Signal inference workers to resume experience collection... (29600 times) [2023-03-09 09:28:49,376][23090] InferenceWorker_p0-w0: stopping experience collection (29600 times) [2023-03-09 09:28:49,414][23090] InferenceWorker_p0-w0: resuming experience collection (29600 times) [2023-03-09 09:28:49,509][23090] Updated weights for policy 0, policy_version 89071 (0.0020) [2023-03-09 09:28:50,415][23090] Updated weights for policy 0, policy_version 89081 (0.0013) [2023-03-09 09:28:51,227][23090] Updated weights for policy 0, policy_version 89091 (0.0014) [2023-03-09 09:28:52,004][23090] Updated weights for policy 0, policy_version 89101 (0.0019) [2023-03-09 09:28:52,901][23090] Updated weights for policy 0, policy_version 89111 (0.0021) [2023-03-09 09:28:53,637][23090] Updated weights for policy 0, policy_version 89121 (0.0022) [2023-03-09 09:28:54,059][22664] Fps is (10 sec: 196610.4, 60 sec: 198793.1, 300 sec: 198441.0). Total num frames: 1460224000. Throughput: 0: 49809.5. Samples: 365124048. Policy #0 lag: (min: 1.0, avg: 17.1, max: 33.0) [2023-03-09 09:28:54,060][22664] Avg episode reward: [(0, '53.510')] [2023-03-09 09:28:54,524][23090] Updated weights for policy 0, policy_version 89131 (0.0013) [2023-03-09 09:28:55,331][23090] Updated weights for policy 0, policy_version 89141 (0.0020) [2023-03-09 09:28:56,099][23090] Updated weights for policy 0, policy_version 89151 (0.0022) [2023-03-09 09:28:56,953][23090] Updated weights for policy 0, policy_version 89161 (0.0013) [2023-03-09 09:28:57,785][23090] Updated weights for policy 0, policy_version 89171 (0.0013) [2023-03-09 09:28:58,581][23090] Updated weights for policy 0, policy_version 89181 (0.0013) [2023-03-09 09:28:59,059][22664] Fps is (10 sec: 198244.3, 60 sec: 199064.4, 300 sec: 198440.6). Total num frames: 1461223424. Throughput: 0: 49766.4. Samples: 365271472. Policy #0 lag: (min: 1.0, avg: 17.1, max: 33.0) [2023-03-09 09:28:59,061][22664] Avg episode reward: [(0, '55.023')] [2023-03-09 09:28:59,455][23090] Updated weights for policy 0, policy_version 89191 (0.0016) [2023-03-09 09:29:00,371][22940] Signal inference workers to stop experience collection... (29650 times) [2023-03-09 09:29:00,385][22940] Signal inference workers to resume experience collection... (29650 times) [2023-03-09 09:29:00,413][23090] InferenceWorker_p0-w0: stopping experience collection (29650 times) [2023-03-09 09:29:00,415][23090] Updated weights for policy 0, policy_version 89202 (0.0022) [2023-03-09 09:29:00,450][23090] InferenceWorker_p0-w0: resuming experience collection (29650 times) [2023-03-09 09:29:01,223][23090] Updated weights for policy 0, policy_version 89212 (0.0013) [2023-03-09 09:29:02,022][23090] Updated weights for policy 0, policy_version 89222 (0.0020) [2023-03-09 09:29:02,821][23090] Updated weights for policy 0, policy_version 89233 (0.0016) [2023-03-09 09:29:03,764][23090] Updated weights for policy 0, policy_version 89243 (0.0013) [2023-03-09 09:29:04,059][22664] Fps is (10 sec: 199876.5, 60 sec: 199063.8, 300 sec: 198496.1). Total num frames: 1462222848. Throughput: 0: 49720.5. Samples: 365568288. Policy #0 lag: (min: 1.0, avg: 17.1, max: 33.0) [2023-03-09 09:29:04,061][22664] Avg episode reward: [(0, '55.191')] [2023-03-09 09:29:04,539][23090] Updated weights for policy 0, policy_version 89253 (0.0017) [2023-03-09 09:29:05,283][23090] Updated weights for policy 0, policy_version 89263 (0.0013) [2023-03-09 09:29:06,299][23090] Updated weights for policy 0, policy_version 89274 (0.0013) [2023-03-09 09:29:07,078][23090] Updated weights for policy 0, policy_version 89284 (0.0022) [2023-03-09 09:29:07,859][23090] Updated weights for policy 0, policy_version 89294 (0.0013) [2023-03-09 09:29:08,723][23090] Updated weights for policy 0, policy_version 89304 (0.0013) [2023-03-09 09:29:09,059][22664] Fps is (10 sec: 199884.9, 60 sec: 199065.2, 300 sec: 198552.1). Total num frames: 1463222272. Throughput: 0: 49724.6. Samples: 365869264. Policy #0 lag: (min: 1.0, avg: 17.1, max: 33.0) [2023-03-09 09:29:09,061][22664] Avg episode reward: [(0, '53.700')] [2023-03-09 09:29:09,572][23090] Updated weights for policy 0, policy_version 89314 (0.0019) [2023-03-09 09:29:10,372][23090] Updated weights for policy 0, policy_version 89324 (0.0017) [2023-03-09 09:29:11,126][23090] Updated weights for policy 0, policy_version 89334 (0.0016) [2023-03-09 09:29:11,996][23090] Updated weights for policy 0, policy_version 89344 (0.0013) [2023-03-09 09:29:12,173][22940] Signal inference workers to stop experience collection... (29700 times) [2023-03-09 09:29:12,175][22940] Signal inference workers to resume experience collection... (29700 times) [2023-03-09 09:29:12,234][23090] InferenceWorker_p0-w0: stopping experience collection (29700 times) [2023-03-09 09:29:12,237][23090] InferenceWorker_p0-w0: resuming experience collection (29700 times) [2023-03-09 09:29:12,819][23090] Updated weights for policy 0, policy_version 89354 (0.0013) [2023-03-09 09:29:13,668][23090] Updated weights for policy 0, policy_version 89364 (0.0016) [2023-03-09 09:29:14,059][22664] Fps is (10 sec: 198254.5, 60 sec: 199065.3, 300 sec: 198496.3). Total num frames: 1464205312. Throughput: 0: 49726.2. Samples: 366020784. Policy #0 lag: (min: 1.0, avg: 17.1, max: 33.0) [2023-03-09 09:29:14,060][22664] Avg episode reward: [(0, '56.838')] [2023-03-09 09:29:14,420][23090] Updated weights for policy 0, policy_version 89374 (0.0022) [2023-03-09 09:29:15,266][23090] Updated weights for policy 0, policy_version 89384 (0.0013) [2023-03-09 09:29:16,134][23090] Updated weights for policy 0, policy_version 89394 (0.0020) [2023-03-09 09:29:16,896][23090] Updated weights for policy 0, policy_version 89404 (0.0017) [2023-03-09 09:29:17,732][23090] Updated weights for policy 0, policy_version 89414 (0.0018) [2023-03-09 09:29:18,431][23090] Updated weights for policy 0, policy_version 89424 (0.0016) [2023-03-09 09:29:19,058][22664] Fps is (10 sec: 199891.3, 60 sec: 199066.2, 300 sec: 198607.4). Total num frames: 1465221120. Throughput: 0: 49771.6. Samples: 366319696. Policy #0 lag: (min: 1.0, avg: 16.8, max: 33.0) [2023-03-09 09:29:19,059][22664] Avg episode reward: [(0, '54.129')] [2023-03-09 09:29:19,109][22940] Saving /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000089431_1465237504.pth... [2023-03-09 09:29:19,173][22940] Removing /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000086518_1417510912.pth [2023-03-09 09:29:19,453][23090] Updated weights for policy 0, policy_version 89434 (0.0017) [2023-03-09 09:29:20,221][23090] Updated weights for policy 0, policy_version 89444 (0.0017) [2023-03-09 09:29:21,008][23090] Updated weights for policy 0, policy_version 89455 (0.0013) [2023-03-09 09:29:22,006][23090] Updated weights for policy 0, policy_version 89465 (0.0020) [2023-03-09 09:29:22,844][23090] Updated weights for policy 0, policy_version 89476 (0.0016) [2023-03-09 09:29:23,624][23090] Updated weights for policy 0, policy_version 89486 (0.0018) [2023-03-09 09:29:24,059][22664] Fps is (10 sec: 201511.3, 60 sec: 199336.7, 300 sec: 198718.2). Total num frames: 1466220544. Throughput: 0: 49724.7. Samples: 366616544. Policy #0 lag: (min: 1.0, avg: 16.8, max: 33.0) [2023-03-09 09:29:24,061][22664] Avg episode reward: [(0, '53.734')] [2023-03-09 09:29:24,408][22940] Signal inference workers to stop experience collection... (29750 times) [2023-03-09 09:29:24,423][22940] Signal inference workers to resume experience collection... (29750 times) [2023-03-09 09:29:24,486][23090] InferenceWorker_p0-w0: stopping experience collection (29750 times) [2023-03-09 09:29:24,489][23090] InferenceWorker_p0-w0: resuming experience collection (29750 times) [2023-03-09 09:29:24,493][23090] Updated weights for policy 0, policy_version 89496 (0.0019) [2023-03-09 09:29:25,301][23090] Updated weights for policy 0, policy_version 89506 (0.0013) [2023-03-09 09:29:26,148][23090] Updated weights for policy 0, policy_version 89516 (0.0013) [2023-03-09 09:29:26,911][23090] Updated weights for policy 0, policy_version 89526 (0.0013) [2023-03-09 09:29:27,747][23090] Updated weights for policy 0, policy_version 89536 (0.0015) [2023-03-09 09:29:28,634][23090] Updated weights for policy 0, policy_version 89546 (0.0013) [2023-03-09 09:29:29,059][22664] Fps is (10 sec: 201518.8, 60 sec: 199612.3, 300 sec: 198774.0). Total num frames: 1467236352. Throughput: 0: 49772.8. Samples: 366768048. Policy #0 lag: (min: 1.0, avg: 16.8, max: 33.0) [2023-03-09 09:29:29,060][22664] Avg episode reward: [(0, '54.827')] [2023-03-09 09:29:29,446][23090] Updated weights for policy 0, policy_version 89556 (0.0020) [2023-03-09 09:29:30,203][23090] Updated weights for policy 0, policy_version 89566 (0.0013) [2023-03-09 09:29:31,067][23090] Updated weights for policy 0, policy_version 89576 (0.0013) [2023-03-09 09:29:31,933][23090] Updated weights for policy 0, policy_version 89586 (0.0018) [2023-03-09 09:29:32,768][23090] Updated weights for policy 0, policy_version 89597 (0.0024) [2023-03-09 09:29:33,622][23090] Updated weights for policy 0, policy_version 89607 (0.0017) [2023-03-09 09:29:34,059][22664] Fps is (10 sec: 198260.3, 60 sec: 199066.3, 300 sec: 198718.5). Total num frames: 1468203008. Throughput: 0: 49772.7. Samples: 367064896. Policy #0 lag: (min: 1.0, avg: 16.8, max: 33.0) [2023-03-09 09:29:34,060][22664] Avg episode reward: [(0, '54.690')] [2023-03-09 09:29:34,582][23090] Updated weights for policy 0, policy_version 89618 (0.0020) [2023-03-09 09:29:35,390][23090] Updated weights for policy 0, policy_version 89628 (0.0016) [2023-03-09 09:29:36,173][23090] Updated weights for policy 0, policy_version 89638 (0.0022) [2023-03-09 09:29:36,903][23090] Updated weights for policy 0, policy_version 89648 (0.0023) [2023-03-09 09:29:37,572][22940] Signal inference workers to stop experience collection... (29800 times) [2023-03-09 09:29:37,581][22940] Signal inference workers to resume experience collection... (29800 times) [2023-03-09 09:29:37,610][23090] InferenceWorker_p0-w0: stopping experience collection (29800 times) [2023-03-09 09:29:37,647][23090] InferenceWorker_p0-w0: resuming experience collection (29800 times) [2023-03-09 09:29:37,856][23090] Updated weights for policy 0, policy_version 89658 (0.0013) [2023-03-09 09:29:38,665][23090] Updated weights for policy 0, policy_version 89668 (0.0020) [2023-03-09 09:29:39,058][22664] Fps is (10 sec: 194974.6, 60 sec: 198519.5, 300 sec: 198607.4). Total num frames: 1469186048. Throughput: 0: 49772.6. Samples: 367363808. Policy #0 lag: (min: 1.0, avg: 16.8, max: 33.0) [2023-03-09 09:29:39,059][22664] Avg episode reward: [(0, '54.483')] [2023-03-09 09:29:39,408][23090] Updated weights for policy 0, policy_version 89678 (0.0016) [2023-03-09 09:29:40,287][23090] Updated weights for policy 0, policy_version 89688 (0.0014) [2023-03-09 09:29:41,118][23090] Updated weights for policy 0, policy_version 89698 (0.0019) [2023-03-09 09:29:41,943][23090] Updated weights for policy 0, policy_version 89708 (0.0020) [2023-03-09 09:29:42,783][23090] Updated weights for policy 0, policy_version 89718 (0.0016) [2023-03-09 09:29:43,626][23090] Updated weights for policy 0, policy_version 89728 (0.0016) [2023-03-09 09:29:44,059][22664] Fps is (10 sec: 198246.9, 60 sec: 198793.4, 300 sec: 198718.7). Total num frames: 1470185472. Throughput: 0: 49817.6. Samples: 367513248. Policy #0 lag: (min: 1.0, avg: 16.8, max: 33.0) [2023-03-09 09:29:44,060][22664] Avg episode reward: [(0, '54.251')] [2023-03-09 09:29:44,488][23090] Updated weights for policy 0, policy_version 89738 (0.0016) [2023-03-09 09:29:45,304][23090] Updated weights for policy 0, policy_version 89748 (0.0016) [2023-03-09 09:29:46,104][23090] Updated weights for policy 0, policy_version 89758 (0.0020) [2023-03-09 09:29:46,922][23090] Updated weights for policy 0, policy_version 89768 (0.0013) [2023-03-09 09:29:47,792][23090] Updated weights for policy 0, policy_version 89778 (0.0015) [2023-03-09 09:29:48,607][23090] Updated weights for policy 0, policy_version 89788 (0.0014) [2023-03-09 09:29:49,059][22664] Fps is (10 sec: 198244.6, 60 sec: 198793.1, 300 sec: 198718.6). Total num frames: 1471168512. Throughput: 0: 49819.9. Samples: 367810160. Policy #0 lag: (min: 1.0, avg: 16.8, max: 33.0) [2023-03-09 09:29:49,060][22664] Avg episode reward: [(0, '54.724')] [2023-03-09 09:29:49,405][23090] Updated weights for policy 0, policy_version 89798 (0.0018) [2023-03-09 09:29:50,147][23090] Updated weights for policy 0, policy_version 89808 (0.0013) [2023-03-09 09:29:50,638][22940] Signal inference workers to stop experience collection... (29850 times) [2023-03-09 09:29:50,657][22940] Signal inference workers to resume experience collection... (29850 times) [2023-03-09 09:29:50,736][23090] InferenceWorker_p0-w0: stopping experience collection (29850 times) [2023-03-09 09:29:50,736][23090] InferenceWorker_p0-w0: resuming experience collection (29850 times) [2023-03-09 09:29:51,110][23090] Updated weights for policy 0, policy_version 89818 (0.0016) [2023-03-09 09:29:51,890][23090] Updated weights for policy 0, policy_version 89828 (0.0016) [2023-03-09 09:29:52,696][23090] Updated weights for policy 0, policy_version 89838 (0.0017) [2023-03-09 09:29:53,526][23090] Updated weights for policy 0, policy_version 89848 (0.0017) [2023-03-09 09:29:54,058][22664] Fps is (10 sec: 198247.0, 60 sec: 199066.1, 300 sec: 198718.8). Total num frames: 1472167936. Throughput: 0: 49684.0. Samples: 368105024. Policy #0 lag: (min: 1.0, avg: 16.8, max: 33.0) [2023-03-09 09:29:54,059][22664] Avg episode reward: [(0, '53.459')] [2023-03-09 09:29:54,374][23090] Updated weights for policy 0, policy_version 89858 (0.0019) [2023-03-09 09:29:55,212][23090] Updated weights for policy 0, policy_version 89868 (0.0018) [2023-03-09 09:29:56,072][23090] Updated weights for policy 0, policy_version 89878 (0.0018) [2023-03-09 09:29:56,935][23090] Updated weights for policy 0, policy_version 89889 (0.0014) [2023-03-09 09:29:57,768][23090] Updated weights for policy 0, policy_version 89899 (0.0014) [2023-03-09 09:29:58,653][23090] Updated weights for policy 0, policy_version 89909 (0.0016) [2023-03-09 09:29:59,059][22664] Fps is (10 sec: 196602.6, 60 sec: 198519.5, 300 sec: 198662.7). Total num frames: 1473134592. Throughput: 0: 49632.1. Samples: 368254240. Policy #0 lag: (min: 1.0, avg: 16.8, max: 33.0) [2023-03-09 09:29:59,061][22664] Avg episode reward: [(0, '56.847')] [2023-03-09 09:29:59,390][23090] Updated weights for policy 0, policy_version 89919 (0.0022) [2023-03-09 09:30:00,310][23090] Updated weights for policy 0, policy_version 89929 (0.0017) [2023-03-09 09:30:01,249][23090] Updated weights for policy 0, policy_version 89940 (0.0013) [2023-03-09 09:30:02,010][23090] Updated weights for policy 0, policy_version 89950 (0.0019) [2023-03-09 09:30:02,881][23090] Updated weights for policy 0, policy_version 89960 (0.0017) [2023-03-09 09:30:03,680][23090] Updated weights for policy 0, policy_version 89970 (0.0016) [2023-03-09 09:30:04,059][22664] Fps is (10 sec: 196601.9, 60 sec: 198520.4, 300 sec: 198718.4). Total num frames: 1474134016. Throughput: 0: 49541.0. Samples: 368549056. Policy #0 lag: (min: 1.0, avg: 16.8, max: 33.0) [2023-03-09 09:30:04,061][22664] Avg episode reward: [(0, '54.154')] [2023-03-09 09:30:04,540][23090] Updated weights for policy 0, policy_version 89980 (0.0017) [2023-03-09 09:30:05,383][23090] Updated weights for policy 0, policy_version 89990 (0.0020) [2023-03-09 09:30:05,716][22940] Signal inference workers to stop experience collection... (29900 times) [2023-03-09 09:30:05,717][22940] Signal inference workers to resume experience collection... (29900 times) [2023-03-09 09:30:05,785][23090] InferenceWorker_p0-w0: stopping experience collection (29900 times) [2023-03-09 09:30:05,786][23090] InferenceWorker_p0-w0: resuming experience collection (29900 times) [2023-03-09 09:30:06,088][23090] Updated weights for policy 0, policy_version 90000 (0.0019) [2023-03-09 09:30:07,036][23090] Updated weights for policy 0, policy_version 90010 (0.0018) [2023-03-09 09:30:07,843][23090] Updated weights for policy 0, policy_version 90020 (0.0014) [2023-03-09 09:30:08,649][23090] Updated weights for policy 0, policy_version 90030 (0.0018) [2023-03-09 09:30:09,059][22664] Fps is (10 sec: 198250.7, 60 sec: 198247.1, 300 sec: 198718.7). Total num frames: 1475117056. Throughput: 0: 49539.2. Samples: 368845776. Policy #0 lag: (min: 1.0, avg: 16.8, max: 33.0) [2023-03-09 09:30:09,060][22664] Avg episode reward: [(0, '53.614')] [2023-03-09 09:30:09,492][23090] Updated weights for policy 0, policy_version 90040 (0.0017) [2023-03-09 09:30:10,327][23090] Updated weights for policy 0, policy_version 90050 (0.0020) [2023-03-09 09:30:11,170][23090] Updated weights for policy 0, policy_version 90060 (0.0017) [2023-03-09 09:30:11,993][23090] Updated weights for policy 0, policy_version 90070 (0.0013) [2023-03-09 09:30:12,838][23090] Updated weights for policy 0, policy_version 90080 (0.0013) [2023-03-09 09:30:13,683][23090] Updated weights for policy 0, policy_version 90090 (0.0020) [2023-03-09 09:30:14,059][22664] Fps is (10 sec: 198245.3, 60 sec: 198518.8, 300 sec: 198718.3). Total num frames: 1476116480. Throughput: 0: 49491.1. Samples: 368995152. Policy #0 lag: (min: 0.0, avg: 17.2, max: 33.0) [2023-03-09 09:30:14,061][22664] Avg episode reward: [(0, '52.872')] [2023-03-09 09:30:14,535][23090] Updated weights for policy 0, policy_version 90100 (0.0019) [2023-03-09 09:30:15,273][23090] Updated weights for policy 0, policy_version 90110 (0.0017) [2023-03-09 09:30:16,202][23090] Updated weights for policy 0, policy_version 90120 (0.0015) [2023-03-09 09:30:16,981][23090] Updated weights for policy 0, policy_version 90130 (0.0024) [2023-03-09 09:30:17,862][23090] Updated weights for policy 0, policy_version 90141 (0.0017) [2023-03-09 09:30:18,732][23090] Updated weights for policy 0, policy_version 90151 (0.0016) [2023-03-09 09:30:19,059][22664] Fps is (10 sec: 196605.8, 60 sec: 197699.5, 300 sec: 198607.2). Total num frames: 1477083136. Throughput: 0: 49444.4. Samples: 369289904. Policy #0 lag: (min: 0.0, avg: 17.2, max: 33.0) [2023-03-09 09:30:19,060][22664] Avg episode reward: [(0, '55.039')] [2023-03-09 09:30:19,148][22940] Signal inference workers to stop experience collection... (29950 times) [2023-03-09 09:30:19,171][22940] Signal inference workers to resume experience collection... (29950 times) [2023-03-09 09:30:19,214][23090] InferenceWorker_p0-w0: stopping experience collection (29950 times) [2023-03-09 09:30:19,215][23090] InferenceWorker_p0-w0: resuming experience collection (29950 times) [2023-03-09 09:30:19,464][23090] Updated weights for policy 0, policy_version 90161 (0.0024) [2023-03-09 09:30:20,408][23090] Updated weights for policy 0, policy_version 90171 (0.0020) [2023-03-09 09:30:21,220][23090] Updated weights for policy 0, policy_version 90181 (0.0014) [2023-03-09 09:30:21,977][23090] Updated weights for policy 0, policy_version 90191 (0.0016) [2023-03-09 09:30:22,898][23090] Updated weights for policy 0, policy_version 90201 (0.0015) [2023-03-09 09:30:23,663][23090] Updated weights for policy 0, policy_version 90211 (0.0020) [2023-03-09 09:30:24,058][22664] Fps is (10 sec: 196614.9, 60 sec: 197702.7, 300 sec: 198663.0). Total num frames: 1478082560. Throughput: 0: 49398.7. Samples: 369586752. Policy #0 lag: (min: 0.0, avg: 17.2, max: 33.0) [2023-03-09 09:30:24,059][22664] Avg episode reward: [(0, '55.106')] [2023-03-09 09:30:24,571][23090] Updated weights for policy 0, policy_version 90222 (0.0019) [2023-03-09 09:30:25,421][23090] Updated weights for policy 0, policy_version 90232 (0.0015) [2023-03-09 09:30:26,286][23090] Updated weights for policy 0, policy_version 90242 (0.0013) [2023-03-09 09:30:27,144][23090] Updated weights for policy 0, policy_version 90252 (0.0014) [2023-03-09 09:30:27,938][23090] Updated weights for policy 0, policy_version 90262 (0.0015) [2023-03-09 09:30:28,758][23090] Updated weights for policy 0, policy_version 90272 (0.0016) [2023-03-09 09:30:29,058][22664] Fps is (10 sec: 198251.7, 60 sec: 197155.0, 300 sec: 198663.1). Total num frames: 1479065600. Throughput: 0: 49307.4. Samples: 369732080. Policy #0 lag: (min: 0.0, avg: 17.2, max: 33.0) [2023-03-09 09:30:29,059][22664] Avg episode reward: [(0, '56.541')] [2023-03-09 09:30:29,674][23090] Updated weights for policy 0, policy_version 90282 (0.0017) [2023-03-09 09:30:30,492][23090] Updated weights for policy 0, policy_version 90292 (0.0022) [2023-03-09 09:30:31,284][23090] Updated weights for policy 0, policy_version 90302 (0.0016) [2023-03-09 09:30:32,121][23090] Updated weights for policy 0, policy_version 90312 (0.0013) [2023-03-09 09:30:32,980][23090] Updated weights for policy 0, policy_version 90322 (0.0016) [2023-03-09 09:30:33,584][22940] Signal inference workers to stop experience collection... (30000 times) [2023-03-09 09:30:33,586][22940] Signal inference workers to resume experience collection... (30000 times) [2023-03-09 09:30:33,652][23090] InferenceWorker_p0-w0: stopping experience collection (30000 times) [2023-03-09 09:30:33,653][23090] InferenceWorker_p0-w0: resuming experience collection (30000 times) [2023-03-09 09:30:33,782][23090] Updated weights for policy 0, policy_version 90332 (0.0013) [2023-03-09 09:30:34,059][22664] Fps is (10 sec: 196607.3, 60 sec: 197427.2, 300 sec: 198607.4). Total num frames: 1480048640. Throughput: 0: 49260.1. Samples: 370026864. Policy #0 lag: (min: 0.0, avg: 17.2, max: 33.0) [2023-03-09 09:30:34,059][22664] Avg episode reward: [(0, '54.794')] [2023-03-09 09:30:34,610][23090] Updated weights for policy 0, policy_version 90342 (0.0018) [2023-03-09 09:30:35,334][23090] Updated weights for policy 0, policy_version 90352 (0.0023) [2023-03-09 09:30:36,307][23090] Updated weights for policy 0, policy_version 90362 (0.0017) [2023-03-09 09:30:37,108][23090] Updated weights for policy 0, policy_version 90372 (0.0013) [2023-03-09 09:30:37,925][23090] Updated weights for policy 0, policy_version 90382 (0.0017) [2023-03-09 09:30:38,869][23090] Updated weights for policy 0, policy_version 90393 (0.0013) [2023-03-09 09:30:39,058][22664] Fps is (10 sec: 196607.9, 60 sec: 197427.2, 300 sec: 198607.6). Total num frames: 1481031680. Throughput: 0: 49349.7. Samples: 370325760. Policy #0 lag: (min: 0.0, avg: 17.2, max: 33.0) [2023-03-09 09:30:39,059][22664] Avg episode reward: [(0, '55.141')] [2023-03-09 09:30:39,665][23090] Updated weights for policy 0, policy_version 90403 (0.0017) [2023-03-09 09:30:40,455][23090] Updated weights for policy 0, policy_version 90413 (0.0018) [2023-03-09 09:30:41,329][23090] Updated weights for policy 0, policy_version 90423 (0.0013) [2023-03-09 09:30:42,097][23090] Updated weights for policy 0, policy_version 90433 (0.0013) [2023-03-09 09:30:42,959][23090] Updated weights for policy 0, policy_version 90443 (0.0016) [2023-03-09 09:30:43,800][23090] Updated weights for policy 0, policy_version 90453 (0.0015) [2023-03-09 09:30:44,059][22664] Fps is (10 sec: 198242.1, 60 sec: 197426.4, 300 sec: 198551.8). Total num frames: 1482031104. Throughput: 0: 49310.0. Samples: 370473184. Policy #0 lag: (min: 0.0, avg: 17.2, max: 33.0) [2023-03-09 09:30:44,061][22664] Avg episode reward: [(0, '54.024')] [2023-03-09 09:30:44,574][23090] Updated weights for policy 0, policy_version 90463 (0.0013) [2023-03-09 09:30:45,460][23090] Updated weights for policy 0, policy_version 90473 (0.0013) [2023-03-09 09:30:46,255][23090] Updated weights for policy 0, policy_version 90483 (0.0018) [2023-03-09 09:30:47,113][22940] Signal inference workers to stop experience collection... (30050 times) [2023-03-09 09:30:47,115][22940] Signal inference workers to resume experience collection... (30050 times) [2023-03-09 09:30:47,144][23090] Updated weights for policy 0, policy_version 90493 (0.0013) [2023-03-09 09:30:47,191][23090] InferenceWorker_p0-w0: stopping experience collection (30050 times) [2023-03-09 09:30:47,234][23090] InferenceWorker_p0-w0: resuming experience collection (30050 times) [2023-03-09 09:30:47,936][23090] Updated weights for policy 0, policy_version 90503 (0.0016) [2023-03-09 09:30:48,843][23090] Updated weights for policy 0, policy_version 90514 (0.0019) [2023-03-09 09:30:49,059][22664] Fps is (10 sec: 199881.5, 60 sec: 197700.0, 300 sec: 198607.4). Total num frames: 1483030528. Throughput: 0: 49355.5. Samples: 370770048. Policy #0 lag: (min: 0.0, avg: 17.2, max: 33.0) [2023-03-09 09:30:49,060][22664] Avg episode reward: [(0, '56.054')] [2023-03-09 09:30:49,671][23090] Updated weights for policy 0, policy_version 90524 (0.0013) [2023-03-09 09:30:50,485][23090] Updated weights for policy 0, policy_version 90534 (0.0013) [2023-03-09 09:30:51,296][23090] Updated weights for policy 0, policy_version 90545 (0.0013) [2023-03-09 09:30:52,214][23090] Updated weights for policy 0, policy_version 90555 (0.0020) [2023-03-09 09:30:53,028][23090] Updated weights for policy 0, policy_version 90565 (0.0013) [2023-03-09 09:30:53,851][23090] Updated weights for policy 0, policy_version 90576 (0.0017) [2023-03-09 09:30:54,059][22664] Fps is (10 sec: 198246.1, 60 sec: 197426.3, 300 sec: 198663.1). Total num frames: 1484013568. Throughput: 0: 49357.0. Samples: 371066848. Policy #0 lag: (min: 0.0, avg: 17.2, max: 33.0) [2023-03-09 09:30:54,061][22664] Avg episode reward: [(0, '54.987')] [2023-03-09 09:30:54,808][23090] Updated weights for policy 0, policy_version 90586 (0.0018) [2023-03-09 09:30:55,592][23090] Updated weights for policy 0, policy_version 90596 (0.0014) [2023-03-09 09:30:56,376][23090] Updated weights for policy 0, policy_version 90606 (0.0017) [2023-03-09 09:30:57,262][23090] Updated weights for policy 0, policy_version 90616 (0.0016) [2023-03-09 09:30:58,073][23090] Updated weights for policy 0, policy_version 90626 (0.0022) [2023-03-09 09:30:58,931][23090] Updated weights for policy 0, policy_version 90636 (0.0012) [2023-03-09 09:30:59,058][22664] Fps is (10 sec: 198249.7, 60 sec: 197974.5, 300 sec: 198552.1). Total num frames: 1485012992. Throughput: 0: 49360.0. Samples: 371216336. Policy #0 lag: (min: 0.0, avg: 17.2, max: 33.0) [2023-03-09 09:30:59,060][22664] Avg episode reward: [(0, '56.116')] [2023-03-09 09:30:59,753][23090] Updated weights for policy 0, policy_version 90646 (0.0013) [2023-03-09 09:31:00,082][22940] Signal inference workers to stop experience collection... (30100 times) [2023-03-09 09:31:00,083][22940] Signal inference workers to resume experience collection... (30100 times) [2023-03-09 09:31:00,148][23090] InferenceWorker_p0-w0: stopping experience collection (30100 times) [2023-03-09 09:31:00,148][23090] InferenceWorker_p0-w0: resuming experience collection (30100 times) [2023-03-09 09:31:00,604][23090] Updated weights for policy 0, policy_version 90656 (0.0019) [2023-03-09 09:31:01,515][23090] Updated weights for policy 0, policy_version 90666 (0.0017) [2023-03-09 09:31:02,273][23090] Updated weights for policy 0, policy_version 90676 (0.0013) [2023-03-09 09:31:03,102][23090] Updated weights for policy 0, policy_version 90686 (0.0019) [2023-03-09 09:31:03,926][23090] Updated weights for policy 0, policy_version 90696 (0.0013) [2023-03-09 09:31:04,059][22664] Fps is (10 sec: 196607.1, 60 sec: 197427.1, 300 sec: 198496.4). Total num frames: 1485979648. Throughput: 0: 49358.9. Samples: 371511056. Policy #0 lag: (min: 0.0, avg: 17.2, max: 33.0) [2023-03-09 09:31:04,061][22664] Avg episode reward: [(0, '53.775')] [2023-03-09 09:31:04,765][23090] Updated weights for policy 0, policy_version 90706 (0.0013) [2023-03-09 09:31:05,584][23090] Updated weights for policy 0, policy_version 90716 (0.0020) [2023-03-09 09:31:06,469][23090] Updated weights for policy 0, policy_version 90726 (0.0023) [2023-03-09 09:31:07,157][23090] Updated weights for policy 0, policy_version 90736 (0.0016) [2023-03-09 09:31:08,142][23090] Updated weights for policy 0, policy_version 90746 (0.0022) [2023-03-09 09:31:08,923][23090] Updated weights for policy 0, policy_version 90756 (0.0016) [2023-03-09 09:31:09,059][22664] Fps is (10 sec: 196602.0, 60 sec: 197699.8, 300 sec: 198496.1). Total num frames: 1486979072. Throughput: 0: 49359.3. Samples: 371807936. Policy #0 lag: (min: 1.0, avg: 16.3, max: 33.0) [2023-03-09 09:31:09,060][22664] Avg episode reward: [(0, '53.521')] [2023-03-09 09:31:09,702][23090] Updated weights for policy 0, policy_version 90766 (0.0018) [2023-03-09 09:31:10,541][23090] Updated weights for policy 0, policy_version 90776 (0.0017) [2023-03-09 09:31:11,347][23090] Updated weights for policy 0, policy_version 90786 (0.0013) [2023-03-09 09:31:12,236][23090] Updated weights for policy 0, policy_version 90796 (0.0013) [2023-03-09 09:31:12,366][22940] Signal inference workers to stop experience collection... (30150 times) [2023-03-09 09:31:12,387][22940] Signal inference workers to resume experience collection... (30150 times) [2023-03-09 09:31:12,406][23090] InferenceWorker_p0-w0: stopping experience collection (30150 times) [2023-03-09 09:31:12,407][23090] InferenceWorker_p0-w0: resuming experience collection (30150 times) [2023-03-09 09:31:12,969][23090] Updated weights for policy 0, policy_version 90806 (0.0013) [2023-03-09 09:31:13,924][23090] Updated weights for policy 0, policy_version 90817 (0.0015) [2023-03-09 09:31:14,059][22664] Fps is (10 sec: 198247.3, 60 sec: 197427.5, 300 sec: 198496.2). Total num frames: 1487962112. Throughput: 0: 49452.1. Samples: 371957440. Policy #0 lag: (min: 1.0, avg: 16.3, max: 33.0) [2023-03-09 09:31:14,061][22664] Avg episode reward: [(0, '54.652')] [2023-03-09 09:31:14,783][23090] Updated weights for policy 0, policy_version 90827 (0.0017) [2023-03-09 09:31:15,598][23090] Updated weights for policy 0, policy_version 90837 (0.0019) [2023-03-09 09:31:16,420][23090] Updated weights for policy 0, policy_version 90847 (0.0023) [2023-03-09 09:31:17,268][23090] Updated weights for policy 0, policy_version 90857 (0.0013) [2023-03-09 09:31:18,096][23090] Updated weights for policy 0, policy_version 90867 (0.0017) [2023-03-09 09:31:18,945][23090] Updated weights for policy 0, policy_version 90877 (0.0016) [2023-03-09 09:31:19,059][22664] Fps is (10 sec: 196607.3, 60 sec: 197700.0, 300 sec: 198496.1). Total num frames: 1488945152. Throughput: 0: 49453.5. Samples: 372252288. Policy #0 lag: (min: 1.0, avg: 16.3, max: 33.0) [2023-03-09 09:31:19,060][22664] Avg episode reward: [(0, '55.963')] [2023-03-09 09:31:19,097][22940] Saving /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000090879_1488961536.pth... [2023-03-09 09:31:19,170][22940] Removing /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000087972_1441333248.pth [2023-03-09 09:31:19,786][23090] Updated weights for policy 0, policy_version 90887 (0.0015) [2023-03-09 09:31:20,450][23090] Updated weights for policy 0, policy_version 90897 (0.0016) [2023-03-09 09:31:21,480][23090] Updated weights for policy 0, policy_version 90907 (0.0020) [2023-03-09 09:31:22,299][23090] Updated weights for policy 0, policy_version 90917 (0.0015) [2023-03-09 09:31:23,045][23090] Updated weights for policy 0, policy_version 90927 (0.0019) [2023-03-09 09:31:23,934][23090] Updated weights for policy 0, policy_version 90937 (0.0016) [2023-03-09 09:31:24,059][22664] Fps is (10 sec: 196609.8, 60 sec: 197426.6, 300 sec: 198440.9). Total num frames: 1489928192. Throughput: 0: 49406.7. Samples: 372549072. Policy #0 lag: (min: 1.0, avg: 16.3, max: 33.0) [2023-03-09 09:31:24,060][22664] Avg episode reward: [(0, '52.044')] [2023-03-09 09:31:24,256][22940] Signal inference workers to stop experience collection... (30200 times) [2023-03-09 09:31:24,257][22940] Signal inference workers to resume experience collection... (30200 times) [2023-03-09 09:31:24,321][23090] InferenceWorker_p0-w0: stopping experience collection (30200 times) [2023-03-09 09:31:24,324][23090] InferenceWorker_p0-w0: resuming experience collection (30200 times) [2023-03-09 09:31:24,744][23090] Updated weights for policy 0, policy_version 90947 (0.0019) [2023-03-09 09:31:25,567][23090] Updated weights for policy 0, policy_version 90957 (0.0016) [2023-03-09 09:31:26,488][23090] Updated weights for policy 0, policy_version 90968 (0.0019) [2023-03-09 09:31:27,329][23090] Updated weights for policy 0, policy_version 90978 (0.0016) [2023-03-09 09:31:28,182][23090] Updated weights for policy 0, policy_version 90988 (0.0021) [2023-03-09 09:31:28,954][23090] Updated weights for policy 0, policy_version 90998 (0.0016) [2023-03-09 09:31:29,059][22664] Fps is (10 sec: 198247.2, 60 sec: 197699.2, 300 sec: 198440.6). Total num frames: 1490927616. Throughput: 0: 49405.8. Samples: 372696448. Policy #0 lag: (min: 1.0, avg: 16.3, max: 33.0) [2023-03-09 09:31:29,061][22664] Avg episode reward: [(0, '54.378')] [2023-03-09 09:31:29,826][23090] Updated weights for policy 0, policy_version 91008 (0.0014) [2023-03-09 09:31:30,662][23090] Updated weights for policy 0, policy_version 91018 (0.0014) [2023-03-09 09:31:31,499][23090] Updated weights for policy 0, policy_version 91028 (0.0016) [2023-03-09 09:31:32,278][23090] Updated weights for policy 0, policy_version 91038 (0.0018) [2023-03-09 09:31:33,171][23090] Updated weights for policy 0, policy_version 91048 (0.0025) [2023-03-09 09:31:34,008][23090] Updated weights for policy 0, policy_version 91058 (0.0013) [2023-03-09 09:31:34,059][22664] Fps is (10 sec: 198244.2, 60 sec: 197699.4, 300 sec: 198388.3). Total num frames: 1491910656. Throughput: 0: 49360.6. Samples: 372991280. Policy #0 lag: (min: 1.0, avg: 16.3, max: 33.0) [2023-03-09 09:31:34,060][22664] Avg episode reward: [(0, '54.327')] [2023-03-09 09:31:34,784][23090] Updated weights for policy 0, policy_version 91068 (0.0021) [2023-03-09 09:31:35,635][23090] Updated weights for policy 0, policy_version 91078 (0.0013) [2023-03-09 09:31:36,330][23090] Updated weights for policy 0, policy_version 91088 (0.0015) [2023-03-09 09:31:37,387][23090] Updated weights for policy 0, policy_version 91099 (0.0016) [2023-03-09 09:31:37,489][22940] Signal inference workers to stop experience collection... (30250 times) [2023-03-09 09:31:37,489][22940] Signal inference workers to resume experience collection... (30250 times) [2023-03-09 09:31:37,553][23090] InferenceWorker_p0-w0: stopping experience collection (30250 times) [2023-03-09 09:31:37,553][23090] InferenceWorker_p0-w0: resuming experience collection (30250 times) [2023-03-09 09:31:38,168][23090] Updated weights for policy 0, policy_version 91109 (0.0019) [2023-03-09 09:31:38,961][23090] Updated weights for policy 0, policy_version 91119 (0.0017) [2023-03-09 09:31:39,059][22664] Fps is (10 sec: 198246.8, 60 sec: 197972.4, 300 sec: 198440.6). Total num frames: 1492910080. Throughput: 0: 49405.5. Samples: 373290096. Policy #0 lag: (min: 1.0, avg: 16.3, max: 33.0) [2023-03-09 09:31:39,061][22664] Avg episode reward: [(0, '54.870')] [2023-03-09 09:31:39,873][23090] Updated weights for policy 0, policy_version 91129 (0.0015) [2023-03-09 09:31:40,654][23090] Updated weights for policy 0, policy_version 91139 (0.0013) [2023-03-09 09:31:41,493][23090] Updated weights for policy 0, policy_version 91149 (0.0012) [2023-03-09 09:31:42,306][23090] Updated weights for policy 0, policy_version 91159 (0.0013) [2023-03-09 09:31:43,115][23090] Updated weights for policy 0, policy_version 91169 (0.0015) [2023-03-09 09:31:44,031][23090] Updated weights for policy 0, policy_version 91179 (0.0017) [2023-03-09 09:31:44,058][22664] Fps is (10 sec: 196614.3, 60 sec: 197428.2, 300 sec: 198329.7). Total num frames: 1493876736. Throughput: 0: 49359.0. Samples: 373437488. Policy #0 lag: (min: 1.0, avg: 16.3, max: 33.0) [2023-03-09 09:31:44,059][22664] Avg episode reward: [(0, '56.184')] [2023-03-09 09:31:44,773][23090] Updated weights for policy 0, policy_version 91189 (0.0018) [2023-03-09 09:31:45,590][23090] Updated weights for policy 0, policy_version 91199 (0.0018) [2023-03-09 09:31:46,487][23090] Updated weights for policy 0, policy_version 91209 (0.0016) [2023-03-09 09:31:47,304][23090] Updated weights for policy 0, policy_version 91219 (0.0016) [2023-03-09 09:31:48,183][23090] Updated weights for policy 0, policy_version 91230 (0.0018) [2023-03-09 09:31:49,052][23090] Updated weights for policy 0, policy_version 91240 (0.0013) [2023-03-09 09:31:49,059][22664] Fps is (10 sec: 196607.9, 60 sec: 197426.8, 300 sec: 198385.2). Total num frames: 1494876160. Throughput: 0: 49406.6. Samples: 373734352. Policy #0 lag: (min: 1.0, avg: 16.3, max: 33.0) [2023-03-09 09:31:49,060][22664] Avg episode reward: [(0, '55.741')] [2023-03-09 09:31:49,966][23090] Updated weights for policy 0, policy_version 91251 (0.0013) [2023-03-09 09:31:50,605][22940] Signal inference workers to stop experience collection... (30300 times) [2023-03-09 09:31:50,623][22940] Signal inference workers to resume experience collection... (30300 times) [2023-03-09 09:31:50,655][23090] InferenceWorker_p0-w0: stopping experience collection (30300 times) [2023-03-09 09:31:50,694][23090] InferenceWorker_p0-w0: resuming experience collection (30300 times) [2023-03-09 09:31:50,745][23090] Updated weights for policy 0, policy_version 91261 (0.0013) [2023-03-09 09:31:51,620][23090] Updated weights for policy 0, policy_version 91271 (0.0013) [2023-03-09 09:31:52,334][23090] Updated weights for policy 0, policy_version 91281 (0.0015) [2023-03-09 09:31:53,333][23090] Updated weights for policy 0, policy_version 91291 (0.0013) [2023-03-09 09:31:54,059][22664] Fps is (10 sec: 198243.2, 60 sec: 197427.7, 300 sec: 198329.8). Total num frames: 1495859200. Throughput: 0: 49406.8. Samples: 374031232. Policy #0 lag: (min: 1.0, avg: 16.3, max: 33.0) [2023-03-09 09:31:54,059][22664] Avg episode reward: [(0, '55.684')] [2023-03-09 09:31:54,114][23090] Updated weights for policy 0, policy_version 91301 (0.0013) [2023-03-09 09:31:54,865][23090] Updated weights for policy 0, policy_version 91311 (0.0020) [2023-03-09 09:31:55,769][23090] Updated weights for policy 0, policy_version 91321 (0.0013) [2023-03-09 09:31:56,540][23090] Updated weights for policy 0, policy_version 91331 (0.0013) [2023-03-09 09:31:57,410][23090] Updated weights for policy 0, policy_version 91341 (0.0017) [2023-03-09 09:31:58,291][23090] Updated weights for policy 0, policy_version 91352 (0.0013) [2023-03-09 09:31:59,059][22664] Fps is (10 sec: 198244.1, 60 sec: 197425.9, 300 sec: 198273.9). Total num frames: 1496858624. Throughput: 0: 49405.0. Samples: 374180672. Policy #0 lag: (min: 1.0, avg: 16.3, max: 33.0) [2023-03-09 09:31:59,106][22664] Avg episode reward: [(0, '54.798')] [2023-03-09 09:31:59,138][23090] Updated weights for policy 0, policy_version 91362 (0.0018) [2023-03-09 09:31:59,997][23090] Updated weights for policy 0, policy_version 91372 (0.0018) [2023-03-09 09:32:00,766][23090] Updated weights for policy 0, policy_version 91382 (0.0019) [2023-03-09 09:32:01,609][23090] Updated weights for policy 0, policy_version 91392 (0.0016) [2023-03-09 09:32:02,498][23090] Updated weights for policy 0, policy_version 91402 (0.0016) [2023-03-09 09:32:03,277][23090] Updated weights for policy 0, policy_version 91412 (0.0016) [2023-03-09 09:32:04,059][22664] Fps is (10 sec: 198243.0, 60 sec: 197700.3, 300 sec: 198329.6). Total num frames: 1497841664. Throughput: 0: 49404.8. Samples: 374475504. Policy #0 lag: (min: 1.0, avg: 17.1, max: 33.0) [2023-03-09 09:32:04,061][22664] Avg episode reward: [(0, '54.744')] [2023-03-09 09:32:04,097][23090] Updated weights for policy 0, policy_version 91422 (0.0016) [2023-03-09 09:32:04,958][23090] Updated weights for policy 0, policy_version 91432 (0.0023) [2023-03-09 09:32:05,411][22940] Signal inference workers to stop experience collection... (30350 times) [2023-03-09 09:32:05,433][22940] Signal inference workers to resume experience collection... (30350 times) [2023-03-09 09:32:05,442][23090] InferenceWorker_p0-w0: stopping experience collection (30350 times) [2023-03-09 09:32:05,442][23090] InferenceWorker_p0-w0: resuming experience collection (30350 times) [2023-03-09 09:32:05,800][23090] Updated weights for policy 0, policy_version 91442 (0.0019) [2023-03-09 09:32:06,612][23090] Updated weights for policy 0, policy_version 91452 (0.0016) [2023-03-09 09:32:07,438][23090] Updated weights for policy 0, policy_version 91462 (0.0017) [2023-03-09 09:32:08,248][23090] Updated weights for policy 0, policy_version 91473 (0.0013) [2023-03-09 09:32:09,059][22664] Fps is (10 sec: 196607.0, 60 sec: 197426.7, 300 sec: 198274.0). Total num frames: 1498824704. Throughput: 0: 49407.0. Samples: 374772400. Policy #0 lag: (min: 1.0, avg: 17.1, max: 33.0) [2023-03-09 09:32:09,061][22664] Avg episode reward: [(0, '52.498')] [2023-03-09 09:32:09,218][23090] Updated weights for policy 0, policy_version 91483 (0.0013) [2023-03-09 09:32:10,010][23090] Updated weights for policy 0, policy_version 91493 (0.0023) [2023-03-09 09:32:10,792][23090] Updated weights for policy 0, policy_version 91504 (0.0016) [2023-03-09 09:32:11,788][23090] Updated weights for policy 0, policy_version 91514 (0.0012) [2023-03-09 09:32:12,579][23090] Updated weights for policy 0, policy_version 91524 (0.0021) [2023-03-09 09:32:13,398][23090] Updated weights for policy 0, policy_version 91535 (0.0016) [2023-03-09 09:32:14,059][22664] Fps is (10 sec: 198249.6, 60 sec: 197700.7, 300 sec: 198329.8). Total num frames: 1499824128. Throughput: 0: 49453.7. Samples: 374921856. Policy #0 lag: (min: 1.0, avg: 17.1, max: 33.0) [2023-03-09 09:32:14,060][22664] Avg episode reward: [(0, '54.839')] [2023-03-09 09:32:14,329][23090] Updated weights for policy 0, policy_version 91545 (0.0016) [2023-03-09 09:32:15,269][23090] Updated weights for policy 0, policy_version 91556 (0.0013) [2023-03-09 09:32:16,062][23090] Updated weights for policy 0, policy_version 91566 (0.0013) [2023-03-09 09:32:16,904][23090] Updated weights for policy 0, policy_version 91576 (0.0021) [2023-03-09 09:32:17,715][23090] Updated weights for policy 0, policy_version 91586 (0.0017) [2023-03-09 09:32:18,641][23090] Updated weights for policy 0, policy_version 91596 (0.0016) [2023-03-09 09:32:19,059][22664] Fps is (10 sec: 196613.0, 60 sec: 197427.7, 300 sec: 198274.1). Total num frames: 1500790784. Throughput: 0: 49408.5. Samples: 375214656. Policy #0 lag: (min: 1.0, avg: 17.1, max: 33.0) [2023-03-09 09:32:19,060][22664] Avg episode reward: [(0, '54.866')] [2023-03-09 09:32:19,370][23090] Updated weights for policy 0, policy_version 91606 (0.0013) [2023-03-09 09:32:19,838][22940] Signal inference workers to stop experience collection... (30400 times) [2023-03-09 09:32:19,860][22940] Signal inference workers to resume experience collection... (30400 times) [2023-03-09 09:32:19,915][23090] InferenceWorker_p0-w0: stopping experience collection (30400 times) [2023-03-09 09:32:19,915][23090] InferenceWorker_p0-w0: resuming experience collection (30400 times) [2023-03-09 09:32:20,270][23090] Updated weights for policy 0, policy_version 91616 (0.0017) [2023-03-09 09:32:21,088][23090] Updated weights for policy 0, policy_version 91626 (0.0026) [2023-03-09 09:32:21,967][23090] Updated weights for policy 0, policy_version 91637 (0.0013) [2023-03-09 09:32:22,791][23090] Updated weights for policy 0, policy_version 91647 (0.0020) [2023-03-09 09:32:23,806][23090] Updated weights for policy 0, policy_version 91658 (0.0019) [2023-03-09 09:32:24,059][22664] Fps is (10 sec: 196608.2, 60 sec: 197700.4, 300 sec: 198274.2). Total num frames: 1501790208. Throughput: 0: 49320.3. Samples: 375509504. Policy #0 lag: (min: 1.0, avg: 17.1, max: 33.0) [2023-03-09 09:32:24,060][22664] Avg episode reward: [(0, '53.305')] [2023-03-09 09:32:24,590][23090] Updated weights for policy 0, policy_version 91668 (0.0018) [2023-03-09 09:32:25,366][23090] Updated weights for policy 0, policy_version 91678 (0.0015) [2023-03-09 09:32:26,278][23090] Updated weights for policy 0, policy_version 91688 (0.0013) [2023-03-09 09:32:27,062][23090] Updated weights for policy 0, policy_version 91698 (0.0016) [2023-03-09 09:32:27,955][23090] Updated weights for policy 0, policy_version 91709 (0.0014) [2023-03-09 09:32:28,796][23090] Updated weights for policy 0, policy_version 91719 (0.0013) [2023-03-09 09:32:29,059][22664] Fps is (10 sec: 198237.7, 60 sec: 197426.1, 300 sec: 198273.8). Total num frames: 1502773248. Throughput: 0: 49365.3. Samples: 375658960. Policy #0 lag: (min: 1.0, avg: 17.1, max: 33.0) [2023-03-09 09:32:29,061][22664] Avg episode reward: [(0, '52.112')] [2023-03-09 09:32:29,709][23090] Updated weights for policy 0, policy_version 91730 (0.0013) [2023-03-09 09:32:30,522][23090] Updated weights for policy 0, policy_version 91740 (0.0021) [2023-03-09 09:32:31,336][23090] Updated weights for policy 0, policy_version 91750 (0.0019) [2023-03-09 09:32:32,072][23090] Updated weights for policy 0, policy_version 91760 (0.0020) [2023-03-09 09:32:32,365][22940] Signal inference workers to stop experience collection... (30450 times) [2023-03-09 09:32:32,365][22940] Signal inference workers to resume experience collection... (30450 times) [2023-03-09 09:32:32,428][23090] InferenceWorker_p0-w0: stopping experience collection (30450 times) [2023-03-09 09:32:32,428][23090] InferenceWorker_p0-w0: resuming experience collection (30450 times) [2023-03-09 09:32:33,078][23090] Updated weights for policy 0, policy_version 91770 (0.0013) [2023-03-09 09:32:33,967][23090] Updated weights for policy 0, policy_version 91781 (0.0013) [2023-03-09 09:32:34,059][22664] Fps is (10 sec: 196606.1, 60 sec: 197427.4, 300 sec: 198163.1). Total num frames: 1503756288. Throughput: 0: 49409.1. Samples: 375957760. Policy #0 lag: (min: 1.0, avg: 17.1, max: 33.0) [2023-03-09 09:32:34,060][22664] Avg episode reward: [(0, '53.009')] [2023-03-09 09:32:34,660][23090] Updated weights for policy 0, policy_version 91791 (0.0015) [2023-03-09 09:32:35,578][23090] Updated weights for policy 0, policy_version 91801 (0.0015) [2023-03-09 09:32:36,361][23090] Updated weights for policy 0, policy_version 91811 (0.0015) [2023-03-09 09:32:37,202][23090] Updated weights for policy 0, policy_version 91821 (0.0019) [2023-03-09 09:32:38,014][23090] Updated weights for policy 0, policy_version 91831 (0.0019) [2023-03-09 09:32:38,865][23090] Updated weights for policy 0, policy_version 91841 (0.0017) [2023-03-09 09:32:39,058][22664] Fps is (10 sec: 198259.0, 60 sec: 197428.1, 300 sec: 198163.3). Total num frames: 1504755712. Throughput: 0: 49406.7. Samples: 376254528. Policy #0 lag: (min: 1.0, avg: 17.1, max: 33.0) [2023-03-09 09:32:39,059][22664] Avg episode reward: [(0, '57.417')] [2023-03-09 09:32:39,063][22940] Saving new best policy, reward=57.417! [2023-03-09 09:32:39,692][23090] Updated weights for policy 0, policy_version 91851 (0.0017) [2023-03-09 09:32:40,530][23090] Updated weights for policy 0, policy_version 91861 (0.0022) [2023-03-09 09:32:41,312][23090] Updated weights for policy 0, policy_version 91871 (0.0017) [2023-03-09 09:32:42,229][23090] Updated weights for policy 0, policy_version 91881 (0.0013) [2023-03-09 09:32:43,000][23090] Updated weights for policy 0, policy_version 91891 (0.0017) [2023-03-09 09:32:43,079][22940] Signal inference workers to stop experience collection... (30500 times) [2023-03-09 09:32:43,092][22940] Signal inference workers to resume experience collection... (30500 times) [2023-03-09 09:32:43,123][23090] InferenceWorker_p0-w0: stopping experience collection (30500 times) [2023-03-09 09:32:43,161][23090] InferenceWorker_p0-w0: resuming experience collection (30500 times) [2023-03-09 09:32:43,835][23090] Updated weights for policy 0, policy_version 91901 (0.0028) [2023-03-09 09:32:44,059][22664] Fps is (10 sec: 198248.6, 60 sec: 197699.8, 300 sec: 198052.1). Total num frames: 1505738752. Throughput: 0: 49361.7. Samples: 376401936. Policy #0 lag: (min: 1.0, avg: 17.1, max: 33.0) [2023-03-09 09:32:44,060][22664] Avg episode reward: [(0, '57.074')] [2023-03-09 09:32:44,654][23090] Updated weights for policy 0, policy_version 91911 (0.0013) [2023-03-09 09:32:45,426][23090] Updated weights for policy 0, policy_version 91921 (0.0018) [2023-03-09 09:32:46,348][23090] Updated weights for policy 0, policy_version 91931 (0.0017) [2023-03-09 09:32:47,173][23090] Updated weights for policy 0, policy_version 91941 (0.0014) [2023-03-09 09:32:47,871][23090] Updated weights for policy 0, policy_version 91951 (0.0018) [2023-03-09 09:32:48,783][23090] Updated weights for policy 0, policy_version 91961 (0.0018) [2023-03-09 09:32:49,058][22664] Fps is (10 sec: 198245.9, 60 sec: 197701.1, 300 sec: 198107.8). Total num frames: 1506738176. Throughput: 0: 49451.0. Samples: 376700784. Policy #0 lag: (min: 1.0, avg: 17.1, max: 33.0) [2023-03-09 09:32:49,059][22664] Avg episode reward: [(0, '54.283')] [2023-03-09 09:32:49,588][23090] Updated weights for policy 0, policy_version 91971 (0.0017) [2023-03-09 09:32:50,446][23090] Updated weights for policy 0, policy_version 91981 (0.0014) [2023-03-09 09:32:51,263][23090] Updated weights for policy 0, policy_version 91991 (0.0013) [2023-03-09 09:32:52,091][23090] Updated weights for policy 0, policy_version 92001 (0.0022) [2023-03-09 09:32:52,191][22940] Signal inference workers to stop experience collection... (30550 times) [2023-03-09 09:32:52,192][22940] Signal inference workers to resume experience collection... (30550 times) [2023-03-09 09:32:52,250][23090] InferenceWorker_p0-w0: stopping experience collection (30550 times) [2023-03-09 09:32:52,250][23090] InferenceWorker_p0-w0: resuming experience collection (30550 times) [2023-03-09 09:32:52,981][23090] Updated weights for policy 0, policy_version 92011 (0.0016) [2023-03-09 09:32:53,782][23090] Updated weights for policy 0, policy_version 92021 (0.0014) [2023-03-09 09:32:54,058][22664] Fps is (10 sec: 198248.5, 60 sec: 197700.7, 300 sec: 198107.5). Total num frames: 1507721216. Throughput: 0: 49406.0. Samples: 376995648. Policy #0 lag: (min: 1.0, avg: 17.1, max: 33.0) [2023-03-09 09:32:54,059][22664] Avg episode reward: [(0, '56.254')] [2023-03-09 09:32:54,584][23090] Updated weights for policy 0, policy_version 92031 (0.0017) [2023-03-09 09:32:55,485][23090] Updated weights for policy 0, policy_version 92041 (0.0020) [2023-03-09 09:32:56,416][23090] Updated weights for policy 0, policy_version 92052 (0.0016) [2023-03-09 09:32:57,267][23090] Updated weights for policy 0, policy_version 92063 (0.0022) [2023-03-09 09:32:58,149][23090] Updated weights for policy 0, policy_version 92073 (0.0016) [2023-03-09 09:32:59,024][23090] Updated weights for policy 0, policy_version 92084 (0.0013) [2023-03-09 09:32:59,059][22664] Fps is (10 sec: 196607.0, 60 sec: 197428.3, 300 sec: 198052.0). Total num frames: 1508704256. Throughput: 0: 49360.4. Samples: 377143072. Policy #0 lag: (min: 0.0, avg: 16.6, max: 33.0) [2023-03-09 09:32:59,070][22664] Avg episode reward: [(0, '53.650')] [2023-03-09 09:32:59,838][23090] Updated weights for policy 0, policy_version 92094 (0.0018) [2023-03-09 09:33:00,708][23090] Updated weights for policy 0, policy_version 92104 (0.0013) [2023-03-09 09:33:00,976][22940] Signal inference workers to stop experience collection... (30600 times) [2023-03-09 09:33:00,997][22940] Signal inference workers to resume experience collection... (30600 times) [2023-03-09 09:33:01,039][23090] InferenceWorker_p0-w0: stopping experience collection (30600 times) [2023-03-09 09:33:01,041][23090] InferenceWorker_p0-w0: resuming experience collection (30600 times) [2023-03-09 09:33:01,527][23090] Updated weights for policy 0, policy_version 92114 (0.0013) [2023-03-09 09:33:02,361][23090] Updated weights for policy 0, policy_version 92124 (0.0015) [2023-03-09 09:33:03,166][23090] Updated weights for policy 0, policy_version 92134 (0.0016) [2023-03-09 09:33:03,978][23090] Updated weights for policy 0, policy_version 92145 (0.0016) [2023-03-09 09:33:04,059][22664] Fps is (10 sec: 198235.5, 60 sec: 197699.4, 300 sec: 198051.8). Total num frames: 1509703680. Throughput: 0: 49450.6. Samples: 377439952. Policy #0 lag: (min: 0.0, avg: 16.6, max: 33.0) [2023-03-09 09:33:04,061][22664] Avg episode reward: [(0, '55.027')] [2023-03-09 09:33:04,884][23090] Updated weights for policy 0, policy_version 92155 (0.0013) [2023-03-09 09:33:05,701][23090] Updated weights for policy 0, policy_version 92165 (0.0013) [2023-03-09 09:33:06,421][23090] Updated weights for policy 0, policy_version 92175 (0.0016) [2023-03-09 09:33:07,326][23090] Updated weights for policy 0, policy_version 92185 (0.0013) [2023-03-09 09:33:08,164][23090] Updated weights for policy 0, policy_version 92195 (0.0016) [2023-03-09 09:33:08,989][23090] Updated weights for policy 0, policy_version 92205 (0.0017) [2023-03-09 09:33:09,059][22664] Fps is (10 sec: 199885.3, 60 sec: 197974.7, 300 sec: 198107.6). Total num frames: 1510703104. Throughput: 0: 49540.4. Samples: 377738816. Policy #0 lag: (min: 0.0, avg: 16.6, max: 33.0) [2023-03-09 09:33:09,059][22664] Avg episode reward: [(0, '52.299')] [2023-03-09 09:33:09,898][23090] Updated weights for policy 0, policy_version 92216 (0.0013) [2023-03-09 09:33:10,767][23090] Updated weights for policy 0, policy_version 92226 (0.0016) [2023-03-09 09:33:11,093][22940] Signal inference workers to stop experience collection... (30650 times) [2023-03-09 09:33:11,094][22940] Signal inference workers to resume experience collection... (30650 times) [2023-03-09 09:33:11,163][23090] InferenceWorker_p0-w0: stopping experience collection (30650 times) [2023-03-09 09:33:11,163][23090] InferenceWorker_p0-w0: resuming experience collection (30650 times) [2023-03-09 09:33:11,548][23090] Updated weights for policy 0, policy_version 92236 (0.0013) [2023-03-09 09:33:12,382][23090] Updated weights for policy 0, policy_version 92246 (0.0018) [2023-03-09 09:33:13,194][23090] Updated weights for policy 0, policy_version 92256 (0.0013) [2023-03-09 09:33:14,058][22664] Fps is (10 sec: 196619.5, 60 sec: 197427.7, 300 sec: 197941.1). Total num frames: 1511669760. Throughput: 0: 49495.8. Samples: 377886240. Policy #0 lag: (min: 0.0, avg: 16.6, max: 33.0) [2023-03-09 09:33:14,059][22664] Avg episode reward: [(0, '57.980')] [2023-03-09 09:33:14,074][23090] Updated weights for policy 0, policy_version 92266 (0.0013) [2023-03-09 09:33:14,076][22940] Saving new best policy, reward=57.980! [2023-03-09 09:33:14,850][23090] Updated weights for policy 0, policy_version 92276 (0.0013) [2023-03-09 09:33:15,662][23090] Updated weights for policy 0, policy_version 92286 (0.0017) [2023-03-09 09:33:16,528][23090] Updated weights for policy 0, policy_version 92296 (0.0016) [2023-03-09 09:33:17,321][23090] Updated weights for policy 0, policy_version 92306 (0.0017) [2023-03-09 09:33:18,152][23090] Updated weights for policy 0, policy_version 92316 (0.0013) [2023-03-09 09:33:19,059][22664] Fps is (10 sec: 198245.3, 60 sec: 198246.7, 300 sec: 198052.1). Total num frames: 1512685568. Throughput: 0: 49497.4. Samples: 378185136. Policy #0 lag: (min: 0.0, avg: 16.6, max: 33.0) [2023-03-09 09:33:19,060][22664] Avg episode reward: [(0, '55.047')] [2023-03-09 09:33:19,065][22940] Saving /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000092327_1512685568.pth... [2023-03-09 09:33:19,078][23090] Updated weights for policy 0, policy_version 92327 (0.0018) [2023-03-09 09:33:19,122][22940] Removing /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000089431_1465237504.pth [2023-03-09 09:33:19,662][22940] Signal inference workers to stop experience collection... (30700 times) [2023-03-09 09:33:19,663][22940] Signal inference workers to resume experience collection... (30700 times) [2023-03-09 09:33:19,726][23090] InferenceWorker_p0-w0: stopping experience collection (30700 times) [2023-03-09 09:33:19,726][23090] InferenceWorker_p0-w0: resuming experience collection (30700 times) [2023-03-09 09:33:19,813][23090] Updated weights for policy 0, policy_version 92337 (0.0014) [2023-03-09 09:33:20,765][23090] Updated weights for policy 0, policy_version 92347 (0.0014) [2023-03-09 09:33:21,576][23090] Updated weights for policy 0, policy_version 92357 (0.0017) [2023-03-09 09:33:22,287][23090] Updated weights for policy 0, policy_version 92367 (0.0020) [2023-03-09 09:33:23,366][23090] Updated weights for policy 0, policy_version 92378 (0.0016) [2023-03-09 09:33:24,059][22664] Fps is (10 sec: 199880.6, 60 sec: 197973.2, 300 sec: 197996.6). Total num frames: 1513668608. Throughput: 0: 49498.1. Samples: 378481952. Policy #0 lag: (min: 0.0, avg: 16.6, max: 33.0) [2023-03-09 09:33:24,061][22664] Avg episode reward: [(0, '54.731')] [2023-03-09 09:33:24,180][23090] Updated weights for policy 0, policy_version 92388 (0.0015) [2023-03-09 09:33:24,964][23090] Updated weights for policy 0, policy_version 92399 (0.0020) [2023-03-09 09:33:25,835][23090] Updated weights for policy 0, policy_version 92409 (0.0018) [2023-03-09 09:33:26,686][23090] Updated weights for policy 0, policy_version 92419 (0.0015) [2023-03-09 09:33:27,501][23090] Updated weights for policy 0, policy_version 92429 (0.0013) [2023-03-09 09:33:28,377][23090] Updated weights for policy 0, policy_version 92439 (0.0013) [2023-03-09 09:33:29,059][22664] Fps is (10 sec: 196608.9, 60 sec: 197975.2, 300 sec: 197941.1). Total num frames: 1514651648. Throughput: 0: 49498.0. Samples: 378629344. Policy #0 lag: (min: 0.0, avg: 16.6, max: 33.0) [2023-03-09 09:33:29,059][22664] Avg episode reward: [(0, '53.704')] [2023-03-09 09:33:29,154][23090] Updated weights for policy 0, policy_version 92449 (0.0013) [2023-03-09 09:33:30,033][23090] Updated weights for policy 0, policy_version 92459 (0.0016) [2023-03-09 09:33:30,133][22940] Signal inference workers to stop experience collection... (30750 times) [2023-03-09 09:33:30,157][22940] Signal inference workers to resume experience collection... (30750 times) [2023-03-09 09:33:30,199][23090] InferenceWorker_p0-w0: stopping experience collection (30750 times) [2023-03-09 09:33:30,200][23090] InferenceWorker_p0-w0: resuming experience collection (30750 times) [2023-03-09 09:33:30,799][23090] Updated weights for policy 0, policy_version 92469 (0.0023) [2023-03-09 09:33:31,646][23090] Updated weights for policy 0, policy_version 92479 (0.0019) [2023-03-09 09:33:32,511][23090] Updated weights for policy 0, policy_version 92489 (0.0013) [2023-03-09 09:33:33,306][23090] Updated weights for policy 0, policy_version 92499 (0.0016) [2023-03-09 09:33:34,059][22664] Fps is (10 sec: 198236.6, 60 sec: 198244.9, 300 sec: 197884.9). Total num frames: 1515651072. Throughput: 0: 49451.4. Samples: 378926128. Policy #0 lag: (min: 0.0, avg: 16.6, max: 33.0) [2023-03-09 09:33:34,061][22664] Avg episode reward: [(0, '52.909')] [2023-03-09 09:33:34,126][23090] Updated weights for policy 0, policy_version 92509 (0.0017) [2023-03-09 09:33:35,045][23090] Updated weights for policy 0, policy_version 92519 (0.0016) [2023-03-09 09:33:35,709][23090] Updated weights for policy 0, policy_version 92529 (0.0015) [2023-03-09 09:33:36,656][23090] Updated weights for policy 0, policy_version 92539 (0.0016) [2023-03-09 09:33:37,471][23090] Updated weights for policy 0, policy_version 92549 (0.0013) [2023-03-09 09:33:38,239][23090] Updated weights for policy 0, policy_version 92559 (0.0029) [2023-03-09 09:33:39,059][22664] Fps is (10 sec: 198243.8, 60 sec: 197972.7, 300 sec: 197885.5). Total num frames: 1516634112. Throughput: 0: 49495.6. Samples: 379222960. Policy #0 lag: (min: 0.0, avg: 16.6, max: 33.0) [2023-03-09 09:33:39,060][22664] Avg episode reward: [(0, '56.529')] [2023-03-09 09:33:39,086][23090] Updated weights for policy 0, policy_version 92569 (0.0013) [2023-03-09 09:33:39,957][23090] Updated weights for policy 0, policy_version 92579 (0.0013) [2023-03-09 09:33:40,778][23090] Updated weights for policy 0, policy_version 92589 (0.0016) [2023-03-09 09:33:41,152][22940] Signal inference workers to stop experience collection... (30800 times) [2023-03-09 09:33:41,153][22940] Signal inference workers to resume experience collection... (30800 times) [2023-03-09 09:33:41,214][23090] InferenceWorker_p0-w0: stopping experience collection (30800 times) [2023-03-09 09:33:41,217][23090] InferenceWorker_p0-w0: resuming experience collection (30800 times) [2023-03-09 09:33:41,604][23090] Updated weights for policy 0, policy_version 92599 (0.0013) [2023-03-09 09:33:42,382][23090] Updated weights for policy 0, policy_version 92609 (0.0013) [2023-03-09 09:33:43,235][23090] Updated weights for policy 0, policy_version 92619 (0.0013) [2023-03-09 09:33:44,037][23090] Updated weights for policy 0, policy_version 92629 (0.0018) [2023-03-09 09:33:44,058][22664] Fps is (10 sec: 198260.2, 60 sec: 198246.8, 300 sec: 197941.1). Total num frames: 1517633536. Throughput: 0: 49540.7. Samples: 379372400. Policy #0 lag: (min: 0.0, avg: 16.6, max: 33.0) [2023-03-09 09:33:44,059][22664] Avg episode reward: [(0, '55.173')] [2023-03-09 09:33:44,852][23090] Updated weights for policy 0, policy_version 92639 (0.0013) [2023-03-09 09:33:45,717][23090] Updated weights for policy 0, policy_version 92649 (0.0013) [2023-03-09 09:33:46,491][23090] Updated weights for policy 0, policy_version 92659 (0.0016) [2023-03-09 09:33:47,319][23090] Updated weights for policy 0, policy_version 92669 (0.0013) [2023-03-09 09:33:48,226][23090] Updated weights for policy 0, policy_version 92679 (0.0020) [2023-03-09 09:33:48,954][23090] Updated weights for policy 0, policy_version 92689 (0.0018) [2023-03-09 09:33:49,058][22664] Fps is (10 sec: 198250.2, 60 sec: 197973.4, 300 sec: 197941.0). Total num frames: 1518616576. Throughput: 0: 49586.4. Samples: 379671312. Policy #0 lag: (min: 0.0, avg: 16.6, max: 33.0) [2023-03-09 09:33:49,059][22664] Avg episode reward: [(0, '56.115')] [2023-03-09 09:33:49,829][23090] Updated weights for policy 0, policy_version 92699 (0.0013) [2023-03-09 09:33:50,693][23090] Updated weights for policy 0, policy_version 92709 (0.0016) [2023-03-09 09:33:51,200][22940] Signal inference workers to stop experience collection... (30850 times) [2023-03-09 09:33:51,223][22940] Signal inference workers to resume experience collection... (30850 times) [2023-03-09 09:33:51,264][23090] InferenceWorker_p0-w0: stopping experience collection (30850 times) [2023-03-09 09:33:51,310][23090] InferenceWorker_p0-w0: resuming experience collection (30850 times) [2023-03-09 09:33:51,489][23090] Updated weights for policy 0, policy_version 92719 (0.0023) [2023-03-09 09:33:52,331][23090] Updated weights for policy 0, policy_version 92729 (0.0016) [2023-03-09 09:33:53,166][23090] Updated weights for policy 0, policy_version 92739 (0.0020) [2023-03-09 09:33:53,989][23090] Updated weights for policy 0, policy_version 92749 (0.0016) [2023-03-09 09:33:54,059][22664] Fps is (10 sec: 198245.3, 60 sec: 198246.3, 300 sec: 197941.1). Total num frames: 1519616000. Throughput: 0: 49542.4. Samples: 379968224. Policy #0 lag: (min: 0.0, avg: 17.4, max: 34.0) [2023-03-09 09:33:54,059][22664] Avg episode reward: [(0, '53.130')] [2023-03-09 09:33:54,821][23090] Updated weights for policy 0, policy_version 92759 (0.0025) [2023-03-09 09:33:55,646][23090] Updated weights for policy 0, policy_version 92769 (0.0013) [2023-03-09 09:33:56,523][23090] Updated weights for policy 0, policy_version 92779 (0.0016) [2023-03-09 09:33:57,256][23090] Updated weights for policy 0, policy_version 92789 (0.0015) [2023-03-09 09:33:58,097][23090] Updated weights for policy 0, policy_version 92799 (0.0013) [2023-03-09 09:33:58,950][23090] Updated weights for policy 0, policy_version 92809 (0.0020) [2023-03-09 09:33:59,059][22664] Fps is (10 sec: 196601.0, 60 sec: 197972.4, 300 sec: 197830.0). Total num frames: 1520582656. Throughput: 0: 49542.0. Samples: 380115648. Policy #0 lag: (min: 0.0, avg: 17.4, max: 34.0) [2023-03-09 09:33:59,106][22664] Avg episode reward: [(0, '54.244')] [2023-03-09 09:33:59,755][23090] Updated weights for policy 0, policy_version 92819 (0.0013) [2023-03-09 09:34:00,556][23090] Updated weights for policy 0, policy_version 92829 (0.0016) [2023-03-09 09:34:01,474][23090] Updated weights for policy 0, policy_version 92839 (0.0017) [2023-03-09 09:34:01,769][22940] Signal inference workers to stop experience collection... (30900 times) [2023-03-09 09:34:01,795][22940] Signal inference workers to resume experience collection... (30900 times) [2023-03-09 09:34:01,799][23090] InferenceWorker_p0-w0: stopping experience collection (30900 times) [2023-03-09 09:34:01,799][23090] InferenceWorker_p0-w0: resuming experience collection (30900 times) [2023-03-09 09:34:02,175][23090] Updated weights for policy 0, policy_version 92849 (0.0018) [2023-03-09 09:34:03,089][23090] Updated weights for policy 0, policy_version 92859 (0.0021) [2023-03-09 09:34:03,939][23090] Updated weights for policy 0, policy_version 92869 (0.0013) [2023-03-09 09:34:04,059][22664] Fps is (10 sec: 196600.1, 60 sec: 197973.7, 300 sec: 197829.8). Total num frames: 1521582080. Throughput: 0: 49496.5. Samples: 380412496. Policy #0 lag: (min: 0.0, avg: 17.4, max: 34.0) [2023-03-09 09:34:04,106][22664] Avg episode reward: [(0, '55.191')] [2023-03-09 09:34:04,967][23090] Updated weights for policy 0, policy_version 92881 (0.0012) [2023-03-09 09:34:05,924][23090] Updated weights for policy 0, policy_version 92891 (0.0015) [2023-03-09 09:34:06,769][23090] Updated weights for policy 0, policy_version 92901 (0.0012) [2023-03-09 09:34:07,617][23090] Updated weights for policy 0, policy_version 92912 (0.0023) [2023-03-09 09:34:08,531][23090] Updated weights for policy 0, policy_version 92922 (0.0016) [2023-03-09 09:34:09,059][22664] Fps is (10 sec: 194974.2, 60 sec: 197153.9, 300 sec: 197718.8). Total num frames: 1522532352. Throughput: 0: 49271.9. Samples: 380699184. Policy #0 lag: (min: 0.0, avg: 17.4, max: 34.0) [2023-03-09 09:34:09,060][22664] Avg episode reward: [(0, '53.141')] [2023-03-09 09:34:09,361][23090] Updated weights for policy 0, policy_version 92932 (0.0013) [2023-03-09 09:34:10,156][23090] Updated weights for policy 0, policy_version 92942 (0.0013) [2023-03-09 09:34:11,049][23090] Updated weights for policy 0, policy_version 92952 (0.0015) [2023-03-09 09:34:11,844][23090] Updated weights for policy 0, policy_version 92962 (0.0021) [2023-03-09 09:34:12,708][23090] Updated weights for policy 0, policy_version 92972 (0.0016) [2023-03-09 09:34:13,487][23090] Updated weights for policy 0, policy_version 92982 (0.0013) [2023-03-09 09:34:13,978][22940] Signal inference workers to stop experience collection... (30950 times) [2023-03-09 09:34:13,979][22940] Signal inference workers to resume experience collection... (30950 times) [2023-03-09 09:34:14,049][23090] InferenceWorker_p0-w0: stopping experience collection (30950 times) [2023-03-09 09:34:14,051][23090] InferenceWorker_p0-w0: resuming experience collection (30950 times) [2023-03-09 09:34:14,059][22664] Fps is (10 sec: 193334.9, 60 sec: 197426.3, 300 sec: 197607.6). Total num frames: 1523515392. Throughput: 0: 49271.3. Samples: 380846560. Policy #0 lag: (min: 0.0, avg: 17.4, max: 34.0) [2023-03-09 09:34:14,060][22664] Avg episode reward: [(0, '55.908')] [2023-03-09 09:34:14,413][23090] Updated weights for policy 0, policy_version 92992 (0.0017) [2023-03-09 09:34:15,225][23090] Updated weights for policy 0, policy_version 93002 (0.0016) [2023-03-09 09:34:16,017][23090] Updated weights for policy 0, policy_version 93012 (0.0017) [2023-03-09 09:34:16,835][23090] Updated weights for policy 0, policy_version 93022 (0.0016) [2023-03-09 09:34:17,725][23090] Updated weights for policy 0, policy_version 93032 (0.0017) [2023-03-09 09:34:18,512][23090] Updated weights for policy 0, policy_version 93042 (0.0014) [2023-03-09 09:34:19,058][22664] Fps is (10 sec: 194972.2, 60 sec: 196608.4, 300 sec: 197497.1). Total num frames: 1524482048. Throughput: 0: 49182.6. Samples: 381139312. Policy #0 lag: (min: 0.0, avg: 17.4, max: 34.0) [2023-03-09 09:34:19,059][22664] Avg episode reward: [(0, '55.020')] [2023-03-09 09:34:19,398][23090] Updated weights for policy 0, policy_version 93052 (0.0016) [2023-03-09 09:34:20,285][23090] Updated weights for policy 0, policy_version 93062 (0.0017) [2023-03-09 09:34:20,911][23090] Updated weights for policy 0, policy_version 93072 (0.0016) [2023-03-09 09:34:21,867][23090] Updated weights for policy 0, policy_version 93082 (0.0023) [2023-03-09 09:34:22,790][23090] Updated weights for policy 0, policy_version 93092 (0.0013) [2023-03-09 09:34:23,585][23090] Updated weights for policy 0, policy_version 93102 (0.0023) [2023-03-09 09:34:24,058][22664] Fps is (10 sec: 194974.9, 60 sec: 196608.7, 300 sec: 197385.7). Total num frames: 1525465088. Throughput: 0: 49092.8. Samples: 381432128. Policy #0 lag: (min: 0.0, avg: 17.4, max: 34.0) [2023-03-09 09:34:24,059][22664] Avg episode reward: [(0, '52.900')] [2023-03-09 09:34:24,457][23090] Updated weights for policy 0, policy_version 93112 (0.0013) [2023-03-09 09:34:25,298][23090] Updated weights for policy 0, policy_version 93122 (0.0016) [2023-03-09 09:34:26,104][23090] Updated weights for policy 0, policy_version 93132 (0.0017) [2023-03-09 09:34:26,275][22940] Signal inference workers to stop experience collection... (31000 times) [2023-03-09 09:34:26,275][22940] Signal inference workers to resume experience collection... (31000 times) [2023-03-09 09:34:26,344][23090] InferenceWorker_p0-w0: stopping experience collection (31000 times) [2023-03-09 09:34:26,345][23090] InferenceWorker_p0-w0: resuming experience collection (31000 times) [2023-03-09 09:34:26,881][23090] Updated weights for policy 0, policy_version 93142 (0.0013) [2023-03-09 09:34:27,764][23090] Updated weights for policy 0, policy_version 93152 (0.0016) [2023-03-09 09:34:28,645][23090] Updated weights for policy 0, policy_version 93162 (0.0017) [2023-03-09 09:34:29,059][22664] Fps is (10 sec: 198238.8, 60 sec: 196880.0, 300 sec: 197496.4). Total num frames: 1526464512. Throughput: 0: 49047.8. Samples: 381579568. Policy #0 lag: (min: 0.0, avg: 17.4, max: 34.0) [2023-03-09 09:34:29,061][22664] Avg episode reward: [(0, '55.396')] [2023-03-09 09:34:29,493][23090] Updated weights for policy 0, policy_version 93173 (0.0012) [2023-03-09 09:34:30,303][23090] Updated weights for policy 0, policy_version 93183 (0.0016) [2023-03-09 09:34:31,153][23090] Updated weights for policy 0, policy_version 93193 (0.0013) [2023-03-09 09:34:31,956][23090] Updated weights for policy 0, policy_version 93203 (0.0016) [2023-03-09 09:34:32,781][23090] Updated weights for policy 0, policy_version 93213 (0.0016) [2023-03-09 09:34:33,721][23090] Updated weights for policy 0, policy_version 93223 (0.0018) [2023-03-09 09:34:34,059][22664] Fps is (10 sec: 196602.4, 60 sec: 196336.3, 300 sec: 197440.9). Total num frames: 1527431168. Throughput: 0: 49003.1. Samples: 381876464. Policy #0 lag: (min: 0.0, avg: 17.4, max: 34.0) [2023-03-09 09:34:34,061][22664] Avg episode reward: [(0, '55.675')] [2023-03-09 09:34:34,428][23090] Updated weights for policy 0, policy_version 93233 (0.0020) [2023-03-09 09:34:35,399][23090] Updated weights for policy 0, policy_version 93244 (0.0013) [2023-03-09 09:34:36,306][23090] Updated weights for policy 0, policy_version 93254 (0.0015) [2023-03-09 09:34:37,016][23090] Updated weights for policy 0, policy_version 93264 (0.0016) [2023-03-09 09:34:37,930][23090] Updated weights for policy 0, policy_version 93274 (0.0023) [2023-03-09 09:34:38,747][23090] Updated weights for policy 0, policy_version 93284 (0.0013) [2023-03-09 09:34:39,059][22664] Fps is (10 sec: 194973.2, 60 sec: 196334.9, 300 sec: 197385.4). Total num frames: 1528414208. Throughput: 0: 48955.2. Samples: 382171216. Policy #0 lag: (min: 0.0, avg: 17.4, max: 34.0) [2023-03-09 09:34:39,060][22664] Avg episode reward: [(0, '54.848')] [2023-03-09 09:34:39,564][23090] Updated weights for policy 0, policy_version 93294 (0.0014) [2023-03-09 09:34:40,022][22940] Signal inference workers to stop experience collection... (31050 times) [2023-03-09 09:34:40,024][22940] Signal inference workers to resume experience collection... (31050 times) [2023-03-09 09:34:40,097][23090] InferenceWorker_p0-w0: stopping experience collection (31050 times) [2023-03-09 09:34:40,100][23090] InferenceWorker_p0-w0: resuming experience collection (31050 times) [2023-03-09 09:34:40,469][23090] Updated weights for policy 0, policy_version 93304 (0.0020) [2023-03-09 09:34:41,333][23090] Updated weights for policy 0, policy_version 93314 (0.0021) [2023-03-09 09:34:42,085][23090] Updated weights for policy 0, policy_version 93324 (0.0017) [2023-03-09 09:34:42,881][23090] Updated weights for policy 0, policy_version 93334 (0.0013) [2023-03-09 09:34:43,748][23090] Updated weights for policy 0, policy_version 93344 (0.0013) [2023-03-09 09:34:44,059][22664] Fps is (10 sec: 196606.8, 60 sec: 196060.8, 300 sec: 197385.4). Total num frames: 1529397248. Throughput: 0: 48955.8. Samples: 382318656. Policy #0 lag: (min: 0.0, avg: 17.4, max: 34.0) [2023-03-09 09:34:44,061][22664] Avg episode reward: [(0, '54.934')] [2023-03-09 09:34:44,705][23090] Updated weights for policy 0, policy_version 93355 (0.0013) [2023-03-09 09:34:45,470][23090] Updated weights for policy 0, policy_version 93365 (0.0015) [2023-03-09 09:34:46,322][23090] Updated weights for policy 0, policy_version 93375 (0.0013) [2023-03-09 09:34:47,162][23090] Updated weights for policy 0, policy_version 93385 (0.0013) [2023-03-09 09:34:48,037][23090] Updated weights for policy 0, policy_version 93395 (0.0023) [2023-03-09 09:34:48,786][23090] Updated weights for policy 0, policy_version 93405 (0.0019) [2023-03-09 09:34:49,058][22664] Fps is (10 sec: 196611.7, 60 sec: 196061.9, 300 sec: 197330.0). Total num frames: 1530380288. Throughput: 0: 48867.0. Samples: 382611488. Policy #0 lag: (min: 1.0, avg: 16.9, max: 33.0) [2023-03-09 09:34:49,059][22664] Avg episode reward: [(0, '54.043')] [2023-03-09 09:34:49,679][23090] Updated weights for policy 0, policy_version 93415 (0.0013) [2023-03-09 09:34:50,407][23090] Updated weights for policy 0, policy_version 93425 (0.0017) [2023-03-09 09:34:51,297][23090] Updated weights for policy 0, policy_version 93435 (0.0017) [2023-03-09 09:34:51,930][22940] Signal inference workers to stop experience collection... (31100 times) [2023-03-09 09:34:51,930][22940] Signal inference workers to resume experience collection... (31100 times) [2023-03-09 09:34:51,991][23090] InferenceWorker_p0-w0: stopping experience collection (31100 times) [2023-03-09 09:34:51,991][23090] InferenceWorker_p0-w0: resuming experience collection (31100 times) [2023-03-09 09:34:52,119][23090] Updated weights for policy 0, policy_version 93445 (0.0013) [2023-03-09 09:34:52,870][23090] Updated weights for policy 0, policy_version 93455 (0.0016) [2023-03-09 09:34:53,773][23090] Updated weights for policy 0, policy_version 93465 (0.0016) [2023-03-09 09:34:54,059][22664] Fps is (10 sec: 199889.5, 60 sec: 196334.8, 300 sec: 197496.8). Total num frames: 1531396096. Throughput: 0: 49138.2. Samples: 382910400. Policy #0 lag: (min: 1.0, avg: 16.9, max: 33.0) [2023-03-09 09:34:54,060][22664] Avg episode reward: [(0, '53.601')] [2023-03-09 09:34:54,655][23090] Updated weights for policy 0, policy_version 93475 (0.0015) [2023-03-09 09:34:55,437][23090] Updated weights for policy 0, policy_version 93485 (0.0018) [2023-03-09 09:34:56,274][23090] Updated weights for policy 0, policy_version 93495 (0.0023) [2023-03-09 09:34:57,088][23090] Updated weights for policy 0, policy_version 93505 (0.0013) [2023-03-09 09:34:57,931][23090] Updated weights for policy 0, policy_version 93515 (0.0018) [2023-03-09 09:34:58,709][23090] Updated weights for policy 0, policy_version 93525 (0.0013) [2023-03-09 09:34:59,058][22664] Fps is (10 sec: 198246.1, 60 sec: 196336.1, 300 sec: 197385.7). Total num frames: 1532362752. Throughput: 0: 49185.0. Samples: 383059872. Policy #0 lag: (min: 1.0, avg: 16.9, max: 33.0) [2023-03-09 09:34:59,059][22664] Avg episode reward: [(0, '54.684')] [2023-03-09 09:34:59,570][23090] Updated weights for policy 0, policy_version 93535 (0.0016) [2023-03-09 09:35:00,457][23090] Updated weights for policy 0, policy_version 93545 (0.0013) [2023-03-09 09:35:01,233][23090] Updated weights for policy 0, policy_version 93555 (0.0015) [2023-03-09 09:35:02,053][23090] Updated weights for policy 0, policy_version 93565 (0.0019) [2023-03-09 09:35:02,978][23090] Updated weights for policy 0, policy_version 93575 (0.0020) [2023-03-09 09:35:03,193][22940] Signal inference workers to stop experience collection... (31150 times) [2023-03-09 09:35:03,194][22940] Signal inference workers to resume experience collection... (31150 times) [2023-03-09 09:35:03,258][23090] InferenceWorker_p0-w0: stopping experience collection (31150 times) [2023-03-09 09:35:03,261][23090] InferenceWorker_p0-w0: resuming experience collection (31150 times) [2023-03-09 09:35:03,635][23090] Updated weights for policy 0, policy_version 93585 (0.0028) [2023-03-09 09:35:04,059][22664] Fps is (10 sec: 196608.9, 60 sec: 196336.3, 300 sec: 197441.2). Total num frames: 1533362176. Throughput: 0: 49229.4. Samples: 383354640. Policy #0 lag: (min: 1.0, avg: 16.9, max: 33.0) [2023-03-09 09:35:04,060][22664] Avg episode reward: [(0, '56.711')] [2023-03-09 09:35:04,541][23090] Updated weights for policy 0, policy_version 93595 (0.0013) [2023-03-09 09:35:05,356][23090] Updated weights for policy 0, policy_version 93605 (0.0013) [2023-03-09 09:35:06,142][23090] Updated weights for policy 0, policy_version 93615 (0.0019) [2023-03-09 09:35:07,017][23090] Updated weights for policy 0, policy_version 93625 (0.0012) [2023-03-09 09:35:07,873][23090] Updated weights for policy 0, policy_version 93635 (0.0022) [2023-03-09 09:35:08,662][23090] Updated weights for policy 0, policy_version 93645 (0.0020) [2023-03-09 09:35:09,058][22664] Fps is (10 sec: 199885.4, 60 sec: 197154.6, 300 sec: 197441.3). Total num frames: 1534361600. Throughput: 0: 49362.5. Samples: 383653440. Policy #0 lag: (min: 1.0, avg: 16.9, max: 33.0) [2023-03-09 09:35:09,059][22664] Avg episode reward: [(0, '54.257')] [2023-03-09 09:35:09,489][23090] Updated weights for policy 0, policy_version 93655 (0.0016) [2023-03-09 09:35:10,343][23090] Updated weights for policy 0, policy_version 93665 (0.0019) [2023-03-09 09:35:11,164][23090] Updated weights for policy 0, policy_version 93675 (0.0017) [2023-03-09 09:35:12,026][23090] Updated weights for policy 0, policy_version 93686 (0.0016) [2023-03-09 09:35:12,919][23090] Updated weights for policy 0, policy_version 93696 (0.0015) [2023-03-09 09:35:13,846][23090] Updated weights for policy 0, policy_version 93707 (0.0013) [2023-03-09 09:35:13,996][22940] Signal inference workers to stop experience collection... (31200 times) [2023-03-09 09:35:14,016][22940] Signal inference workers to resume experience collection... (31200 times) [2023-03-09 09:35:14,047][23090] InferenceWorker_p0-w0: stopping experience collection (31200 times) [2023-03-09 09:35:14,059][22664] Fps is (10 sec: 198241.7, 60 sec: 197154.1, 300 sec: 197496.6). Total num frames: 1535344640. Throughput: 0: 49361.9. Samples: 383800848. Policy #0 lag: (min: 1.0, avg: 16.9, max: 33.0) [2023-03-09 09:35:14,061][22664] Avg episode reward: [(0, '53.126')] [2023-03-09 09:35:14,089][23090] InferenceWorker_p0-w0: resuming experience collection (31200 times) [2023-03-09 09:35:14,633][23090] Updated weights for policy 0, policy_version 93717 (0.0018) [2023-03-09 09:35:15,480][23090] Updated weights for policy 0, policy_version 93727 (0.0016) [2023-03-09 09:35:16,350][23090] Updated weights for policy 0, policy_version 93737 (0.0016) [2023-03-09 09:35:17,130][23090] Updated weights for policy 0, policy_version 93747 (0.0013) [2023-03-09 09:35:17,939][23090] Updated weights for policy 0, policy_version 93757 (0.0023) [2023-03-09 09:35:18,822][23090] Updated weights for policy 0, policy_version 93767 (0.0016) [2023-03-09 09:35:19,059][22664] Fps is (10 sec: 194967.0, 60 sec: 197153.7, 300 sec: 197385.5). Total num frames: 1536311296. Throughput: 0: 49314.7. Samples: 384095616. Policy #0 lag: (min: 1.0, avg: 16.9, max: 33.0) [2023-03-09 09:35:19,060][22664] Avg episode reward: [(0, '54.926')] [2023-03-09 09:35:19,076][22940] Saving /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000093770_1536327680.pth... [2023-03-09 09:35:19,134][22940] Removing /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000090879_1488961536.pth [2023-03-09 09:35:19,989][23090] Updated weights for policy 0, policy_version 93779 (0.0012) [2023-03-09 09:35:20,827][23090] Updated weights for policy 0, policy_version 93789 (0.0022) [2023-03-09 09:35:21,679][23090] Updated weights for policy 0, policy_version 93799 (0.0015) [2023-03-09 09:35:22,426][23090] Updated weights for policy 0, policy_version 93809 (0.0019) [2023-03-09 09:35:23,335][23090] Updated weights for policy 0, policy_version 93819 (0.0013) [2023-03-09 09:35:24,058][22664] Fps is (10 sec: 191698.7, 60 sec: 196608.0, 300 sec: 197274.5). Total num frames: 1537261568. Throughput: 0: 49177.8. Samples: 384384208. Policy #0 lag: (min: 1.0, avg: 16.9, max: 33.0) [2023-03-09 09:35:24,059][22664] Avg episode reward: [(0, '56.679')] [2023-03-09 09:35:24,190][23090] Updated weights for policy 0, policy_version 93829 (0.0031) [2023-03-09 09:35:24,943][23090] Updated weights for policy 0, policy_version 93839 (0.0013) [2023-03-09 09:35:25,403][22940] Signal inference workers to stop experience collection... (31250 times) [2023-03-09 09:35:25,408][22940] Signal inference workers to resume experience collection... (31250 times) [2023-03-09 09:35:25,471][23090] InferenceWorker_p0-w0: stopping experience collection (31250 times) [2023-03-09 09:35:25,472][23090] InferenceWorker_p0-w0: resuming experience collection (31250 times) [2023-03-09 09:35:25,847][23090] Updated weights for policy 0, policy_version 93849 (0.0020) [2023-03-09 09:35:26,705][23090] Updated weights for policy 0, policy_version 93859 (0.0013) [2023-03-09 09:35:27,500][23090] Updated weights for policy 0, policy_version 93869 (0.0013) [2023-03-09 09:35:28,353][23090] Updated weights for policy 0, policy_version 93879 (0.0018) [2023-03-09 09:35:29,059][22664] Fps is (10 sec: 193330.3, 60 sec: 196335.6, 300 sec: 197274.4). Total num frames: 1538244608. Throughput: 0: 49131.2. Samples: 384529552. Policy #0 lag: (min: 1.0, avg: 16.9, max: 33.0) [2023-03-09 09:35:29,060][22664] Avg episode reward: [(0, '55.279')] [2023-03-09 09:35:29,164][23090] Updated weights for policy 0, policy_version 93889 (0.0013) [2023-03-09 09:35:30,040][23090] Updated weights for policy 0, policy_version 93899 (0.0020) [2023-03-09 09:35:30,792][23090] Updated weights for policy 0, policy_version 93909 (0.0021) [2023-03-09 09:35:31,628][23090] Updated weights for policy 0, policy_version 93919 (0.0016) [2023-03-09 09:35:32,512][23090] Updated weights for policy 0, policy_version 93929 (0.0013) [2023-03-09 09:35:33,298][23090] Updated weights for policy 0, policy_version 93939 (0.0016) [2023-03-09 09:35:34,059][22664] Fps is (10 sec: 199883.4, 60 sec: 197154.9, 300 sec: 197385.5). Total num frames: 1539260416. Throughput: 0: 49129.5. Samples: 384822320. Policy #0 lag: (min: 1.0, avg: 16.9, max: 33.0) [2023-03-09 09:35:34,060][22664] Avg episode reward: [(0, '55.651')] [2023-03-09 09:35:34,063][23090] Updated weights for policy 0, policy_version 93949 (0.0019) [2023-03-09 09:35:35,061][23090] Updated weights for policy 0, policy_version 93959 (0.0013) [2023-03-09 09:35:35,746][23090] Updated weights for policy 0, policy_version 93969 (0.0013) [2023-03-09 09:35:36,642][23090] Updated weights for policy 0, policy_version 93979 (0.0018) [2023-03-09 09:35:37,391][22940] Signal inference workers to stop experience collection... (31300 times) [2023-03-09 09:35:37,392][22940] Signal inference workers to resume experience collection... (31300 times) [2023-03-09 09:35:37,462][23090] InferenceWorker_p0-w0: stopping experience collection (31300 times) [2023-03-09 09:35:37,463][23090] InferenceWorker_p0-w0: resuming experience collection (31300 times) [2023-03-09 09:35:37,465][23090] Updated weights for policy 0, policy_version 93989 (0.0014) [2023-03-09 09:35:38,224][23090] Updated weights for policy 0, policy_version 93999 (0.0021) [2023-03-09 09:35:39,059][22664] Fps is (10 sec: 198248.3, 60 sec: 196881.5, 300 sec: 197274.6). Total num frames: 1540227072. Throughput: 0: 49173.4. Samples: 385123200. Policy #0 lag: (min: 1.0, avg: 16.9, max: 33.0) [2023-03-09 09:35:39,060][22664] Avg episode reward: [(0, '52.541')] [2023-03-09 09:35:39,104][23090] Updated weights for policy 0, policy_version 94009 (0.0024) [2023-03-09 09:35:39,958][23090] Updated weights for policy 0, policy_version 94019 (0.0013) [2023-03-09 09:35:40,792][23090] Updated weights for policy 0, policy_version 94029 (0.0022) [2023-03-09 09:35:41,589][23090] Updated weights for policy 0, policy_version 94039 (0.0013) [2023-03-09 09:35:42,444][23090] Updated weights for policy 0, policy_version 94049 (0.0017) [2023-03-09 09:35:43,289][23090] Updated weights for policy 0, policy_version 94059 (0.0018) [2023-03-09 09:35:44,059][22664] Fps is (10 sec: 196606.2, 60 sec: 197154.8, 300 sec: 197274.5). Total num frames: 1541226496. Throughput: 0: 49126.6. Samples: 385270576. Policy #0 lag: (min: 1.0, avg: 16.9, max: 33.0) [2023-03-09 09:35:44,060][22664] Avg episode reward: [(0, '56.194')] [2023-03-09 09:35:44,079][23090] Updated weights for policy 0, policy_version 94069 (0.0013) [2023-03-09 09:35:44,930][23090] Updated weights for policy 0, policy_version 94079 (0.0029) [2023-03-09 09:35:45,779][23090] Updated weights for policy 0, policy_version 94089 (0.0020) [2023-03-09 09:35:46,599][23090] Updated weights for policy 0, policy_version 94099 (0.0023) [2023-03-09 09:35:47,356][23090] Updated weights for policy 0, policy_version 94109 (0.0014) [2023-03-09 09:35:48,031][22940] Signal inference workers to stop experience collection... (31350 times) [2023-03-09 09:35:48,032][22940] Signal inference workers to resume experience collection... (31350 times) [2023-03-09 09:35:48,091][23090] InferenceWorker_p0-w0: stopping experience collection (31350 times) [2023-03-09 09:35:48,091][23090] InferenceWorker_p0-w0: resuming experience collection (31350 times) [2023-03-09 09:35:48,302][23090] Updated weights for policy 0, policy_version 94119 (0.0017) [2023-03-09 09:35:49,009][23090] Updated weights for policy 0, policy_version 94129 (0.0024) [2023-03-09 09:35:49,059][22664] Fps is (10 sec: 198230.2, 60 sec: 197151.2, 300 sec: 197274.1). Total num frames: 1542209536. Throughput: 0: 49127.6. Samples: 385565424. Policy #0 lag: (min: 0.0, avg: 15.9, max: 33.0) [2023-03-09 09:35:49,061][22664] Avg episode reward: [(0, '53.887')] [2023-03-09 09:35:49,978][23090] Updated weights for policy 0, policy_version 94140 (0.0016) [2023-03-09 09:35:50,849][23090] Updated weights for policy 0, policy_version 94150 (0.0016) [2023-03-09 09:35:51,885][23090] Updated weights for policy 0, policy_version 94162 (0.0016) [2023-03-09 09:35:52,727][23090] Updated weights for policy 0, policy_version 94172 (0.0013) [2023-03-09 09:35:53,648][23090] Updated weights for policy 0, policy_version 94182 (0.0013) [2023-03-09 09:35:54,059][22664] Fps is (10 sec: 193327.2, 60 sec: 196061.0, 300 sec: 197107.6). Total num frames: 1543159808. Throughput: 0: 48948.2. Samples: 385856128. Policy #0 lag: (min: 0.0, avg: 15.9, max: 33.0) [2023-03-09 09:35:54,061][22664] Avg episode reward: [(0, '56.161')] [2023-03-09 09:35:54,316][23090] Updated weights for policy 0, policy_version 94192 (0.0018) [2023-03-09 09:35:55,308][23090] Updated weights for policy 0, policy_version 94202 (0.0014) [2023-03-09 09:35:56,111][23090] Updated weights for policy 0, policy_version 94212 (0.0013) [2023-03-09 09:35:56,897][23090] Updated weights for policy 0, policy_version 94222 (0.0015) [2023-03-09 09:35:57,758][22940] Signal inference workers to stop experience collection... (31400 times) [2023-03-09 09:35:57,760][22940] Signal inference workers to resume experience collection... (31400 times) [2023-03-09 09:35:57,819][23090] Updated weights for policy 0, policy_version 94233 (0.0016) [2023-03-09 09:35:57,856][23090] InferenceWorker_p0-w0: stopping experience collection (31400 times) [2023-03-09 09:35:57,857][23090] InferenceWorker_p0-w0: resuming experience collection (31400 times) [2023-03-09 09:35:58,677][23090] Updated weights for policy 0, policy_version 94243 (0.0021) [2023-03-09 09:35:59,058][22664] Fps is (10 sec: 193348.4, 60 sec: 196335.0, 300 sec: 197163.6). Total num frames: 1544142848. Throughput: 0: 48904.1. Samples: 386001520. Policy #0 lag: (min: 0.0, avg: 15.9, max: 33.0) [2023-03-09 09:35:59,059][22664] Avg episode reward: [(0, '54.117')] [2023-03-09 09:35:59,472][23090] Updated weights for policy 0, policy_version 94253 (0.0017) [2023-03-09 09:36:00,307][23090] Updated weights for policy 0, policy_version 94263 (0.0016) [2023-03-09 09:36:01,183][23090] Updated weights for policy 0, policy_version 94273 (0.0018) [2023-03-09 09:36:02,006][23090] Updated weights for policy 0, policy_version 94283 (0.0016) [2023-03-09 09:36:02,768][23090] Updated weights for policy 0, policy_version 94293 (0.0016) [2023-03-09 09:36:03,610][23090] Updated weights for policy 0, policy_version 94303 (0.0017) [2023-03-09 09:36:04,058][22664] Fps is (10 sec: 198252.3, 60 sec: 196334.9, 300 sec: 197163.6). Total num frames: 1545142272. Throughput: 0: 48996.3. Samples: 386300448. Policy #0 lag: (min: 0.0, avg: 15.9, max: 33.0) [2023-03-09 09:36:04,060][22664] Avg episode reward: [(0, '56.259')] [2023-03-09 09:36:04,439][23090] Updated weights for policy 0, policy_version 94313 (0.0016) [2023-03-09 09:36:05,267][23090] Updated weights for policy 0, policy_version 94323 (0.0013) [2023-03-09 09:36:06,003][23090] Updated weights for policy 0, policy_version 94333 (0.0016) [2023-03-09 09:36:07,022][23090] Updated weights for policy 0, policy_version 94344 (0.0026) [2023-03-09 09:36:07,482][22940] Signal inference workers to stop experience collection... (31450 times) [2023-03-09 09:36:07,494][22940] Signal inference workers to resume experience collection... (31450 times) [2023-03-09 09:36:07,523][23090] InferenceWorker_p0-w0: stopping experience collection (31450 times) [2023-03-09 09:36:07,523][23090] InferenceWorker_p0-w0: resuming experience collection (31450 times) [2023-03-09 09:36:07,788][23090] Updated weights for policy 0, policy_version 94354 (0.0016) [2023-03-09 09:36:08,624][23090] Updated weights for policy 0, policy_version 94364 (0.0015) [2023-03-09 09:36:09,058][22664] Fps is (10 sec: 198246.0, 60 sec: 196061.8, 300 sec: 197163.6). Total num frames: 1546125312. Throughput: 0: 49225.2. Samples: 386599344. Policy #0 lag: (min: 0.0, avg: 15.9, max: 33.0) [2023-03-09 09:36:09,059][22664] Avg episode reward: [(0, '54.453')] [2023-03-09 09:36:09,513][23090] Updated weights for policy 0, policy_version 94374 (0.0017) [2023-03-09 09:36:10,225][23090] Updated weights for policy 0, policy_version 94384 (0.0015) [2023-03-09 09:36:11,103][23090] Updated weights for policy 0, policy_version 94394 (0.0013) [2023-03-09 09:36:11,961][23090] Updated weights for policy 0, policy_version 94404 (0.0013) [2023-03-09 09:36:12,779][23090] Updated weights for policy 0, policy_version 94414 (0.0013) [2023-03-09 09:36:13,679][23090] Updated weights for policy 0, policy_version 94424 (0.0013) [2023-03-09 09:36:14,059][22664] Fps is (10 sec: 199879.8, 60 sec: 196607.9, 300 sec: 197274.5). Total num frames: 1547141120. Throughput: 0: 49316.5. Samples: 386748800. Policy #0 lag: (min: 0.0, avg: 15.9, max: 33.0) [2023-03-09 09:36:14,061][22664] Avg episode reward: [(0, '54.535')] [2023-03-09 09:36:14,485][23090] Updated weights for policy 0, policy_version 94434 (0.0016) [2023-03-09 09:36:15,308][23090] Updated weights for policy 0, policy_version 94444 (0.0016) [2023-03-09 09:36:16,064][23090] Updated weights for policy 0, policy_version 94454 (0.0019) [2023-03-09 09:36:16,915][23090] Updated weights for policy 0, policy_version 94464 (0.0021) [2023-03-09 09:36:17,787][23090] Updated weights for policy 0, policy_version 94474 (0.0018) [2023-03-09 09:36:18,066][22940] Signal inference workers to stop experience collection... (31500 times) [2023-03-09 09:36:18,085][22940] Signal inference workers to resume experience collection... (31500 times) [2023-03-09 09:36:18,117][23090] InferenceWorker_p0-w0: stopping experience collection (31500 times) [2023-03-09 09:36:18,157][23090] InferenceWorker_p0-w0: resuming experience collection (31500 times) [2023-03-09 09:36:18,562][23090] Updated weights for policy 0, policy_version 94484 (0.0013) [2023-03-09 09:36:19,059][22664] Fps is (10 sec: 199878.5, 60 sec: 196880.4, 300 sec: 197274.4). Total num frames: 1548124160. Throughput: 0: 49361.8. Samples: 387043616. Policy #0 lag: (min: 0.0, avg: 15.9, max: 33.0) [2023-03-09 09:36:19,061][22664] Avg episode reward: [(0, '53.819')] [2023-03-09 09:36:19,297][23090] Updated weights for policy 0, policy_version 94494 (0.0016) [2023-03-09 09:36:20,268][23090] Updated weights for policy 0, policy_version 94504 (0.0020) [2023-03-09 09:36:21,035][23090] Updated weights for policy 0, policy_version 94514 (0.0016) [2023-03-09 09:36:21,840][23090] Updated weights for policy 0, policy_version 94524 (0.0013) [2023-03-09 09:36:22,759][23090] Updated weights for policy 0, policy_version 94534 (0.0018) [2023-03-09 09:36:23,464][23090] Updated weights for policy 0, policy_version 94544 (0.0022) [2023-03-09 09:36:24,059][22664] Fps is (10 sec: 196612.8, 60 sec: 197426.9, 300 sec: 197219.1). Total num frames: 1549107200. Throughput: 0: 49315.6. Samples: 387342400. Policy #0 lag: (min: 0.0, avg: 15.9, max: 33.0) [2023-03-09 09:36:24,059][22664] Avg episode reward: [(0, '56.185')] [2023-03-09 09:36:24,404][23090] Updated weights for policy 0, policy_version 94554 (0.0022) [2023-03-09 09:36:25,213][23090] Updated weights for policy 0, policy_version 94564 (0.0013) [2023-03-09 09:36:26,036][23090] Updated weights for policy 0, policy_version 94574 (0.0016) [2023-03-09 09:36:26,958][23090] Updated weights for policy 0, policy_version 94585 (0.0013) [2023-03-09 09:36:27,858][23090] Updated weights for policy 0, policy_version 94595 (0.0020) [2023-03-09 09:36:28,680][23090] Updated weights for policy 0, policy_version 94605 (0.0013) [2023-03-09 09:36:28,944][22940] Signal inference workers to stop experience collection... (31550 times) [2023-03-09 09:36:28,945][22940] Signal inference workers to resume experience collection... (31550 times) [2023-03-09 09:36:29,009][23090] InferenceWorker_p0-w0: stopping experience collection (31550 times) [2023-03-09 09:36:29,010][23090] InferenceWorker_p0-w0: resuming experience collection (31550 times) [2023-03-09 09:36:29,059][22664] Fps is (10 sec: 196609.1, 60 sec: 197426.8, 300 sec: 197218.9). Total num frames: 1550090240. Throughput: 0: 49315.8. Samples: 387489792. Policy #0 lag: (min: 0.0, avg: 15.9, max: 33.0) [2023-03-09 09:36:29,060][22664] Avg episode reward: [(0, '55.236')] [2023-03-09 09:36:29,559][23090] Updated weights for policy 0, policy_version 94616 (0.0014) [2023-03-09 09:36:30,404][23090] Updated weights for policy 0, policy_version 94626 (0.0013) [2023-03-09 09:36:31,209][23090] Updated weights for policy 0, policy_version 94636 (0.0013) [2023-03-09 09:36:31,919][23090] Updated weights for policy 0, policy_version 94646 (0.0014) [2023-03-09 09:36:32,833][23090] Updated weights for policy 0, policy_version 94656 (0.0018) [2023-03-09 09:36:33,660][23090] Updated weights for policy 0, policy_version 94666 (0.0019) [2023-03-09 09:36:34,059][22664] Fps is (10 sec: 198246.4, 60 sec: 197154.1, 300 sec: 197219.1). Total num frames: 1551089664. Throughput: 0: 49360.2. Samples: 387786592. Policy #0 lag: (min: 0.0, avg: 15.9, max: 33.0) [2023-03-09 09:36:34,059][22664] Avg episode reward: [(0, '54.603')] [2023-03-09 09:36:34,488][23090] Updated weights for policy 0, policy_version 94676 (0.0020) [2023-03-09 09:36:35,243][23090] Updated weights for policy 0, policy_version 94686 (0.0024) [2023-03-09 09:36:36,208][23090] Updated weights for policy 0, policy_version 94696 (0.0020) [2023-03-09 09:36:37,160][23090] Updated weights for policy 0, policy_version 94707 (0.0013) [2023-03-09 09:36:37,892][23090] Updated weights for policy 0, policy_version 94717 (0.0015) [2023-03-09 09:36:38,805][23090] Updated weights for policy 0, policy_version 94727 (0.0017) [2023-03-09 09:36:38,964][22940] Signal inference workers to stop experience collection... (31600 times) [2023-03-09 09:36:38,964][22940] Signal inference workers to resume experience collection... (31600 times) [2023-03-09 09:36:39,049][23090] InferenceWorker_p0-w0: stopping experience collection (31600 times) [2023-03-09 09:36:39,049][23090] InferenceWorker_p0-w0: resuming experience collection (31600 times) [2023-03-09 09:36:39,059][22664] Fps is (10 sec: 196607.7, 60 sec: 197153.4, 300 sec: 197218.7). Total num frames: 1552056320. Throughput: 0: 49397.8. Samples: 388079024. Policy #0 lag: (min: 0.0, avg: 15.9, max: 33.0) [2023-03-09 09:36:39,061][22664] Avg episode reward: [(0, '55.384')] [2023-03-09 09:36:39,559][23090] Updated weights for policy 0, policy_version 94737 (0.0020) [2023-03-09 09:36:40,407][23090] Updated weights for policy 0, policy_version 94747 (0.0012) [2023-03-09 09:36:41,299][23090] Updated weights for policy 0, policy_version 94757 (0.0013) [2023-03-09 09:36:42,022][23090] Updated weights for policy 0, policy_version 94767 (0.0018) [2023-03-09 09:36:42,982][23090] Updated weights for policy 0, policy_version 94777 (0.0022) [2023-03-09 09:36:43,757][23090] Updated weights for policy 0, policy_version 94787 (0.0017) [2023-03-09 09:36:44,058][22664] Fps is (10 sec: 193332.1, 60 sec: 196608.4, 300 sec: 197108.0). Total num frames: 1553022976. Throughput: 0: 49488.0. Samples: 388228480. Policy #0 lag: (min: 0.0, avg: 17.1, max: 33.0) [2023-03-09 09:36:44,060][22664] Avg episode reward: [(0, '57.528')] [2023-03-09 09:36:44,592][23090] Updated weights for policy 0, policy_version 94797 (0.0013) [2023-03-09 09:36:45,451][23090] Updated weights for policy 0, policy_version 94808 (0.0013) [2023-03-09 09:36:46,305][23090] Updated weights for policy 0, policy_version 94818 (0.0013) [2023-03-09 09:36:47,133][23090] Updated weights for policy 0, policy_version 94828 (0.0013) [2023-03-09 09:36:47,895][23090] Updated weights for policy 0, policy_version 94838 (0.0016) [2023-03-09 09:36:48,397][22940] Signal inference workers to stop experience collection... (31650 times) [2023-03-09 09:36:48,419][22940] Signal inference workers to resume experience collection... (31650 times) [2023-03-09 09:36:48,461][23090] InferenceWorker_p0-w0: stopping experience collection (31650 times) [2023-03-09 09:36:48,461][23090] InferenceWorker_p0-w0: resuming experience collection (31650 times) [2023-03-09 09:36:48,748][23090] Updated weights for policy 0, policy_version 94848 (0.0017) [2023-03-09 09:36:49,059][22664] Fps is (10 sec: 198248.0, 60 sec: 197156.4, 300 sec: 197218.9). Total num frames: 1554038784. Throughput: 0: 49443.0. Samples: 388525392. Policy #0 lag: (min: 0.0, avg: 17.1, max: 33.0) [2023-03-09 09:36:49,060][22664] Avg episode reward: [(0, '53.934')] [2023-03-09 09:36:49,586][23090] Updated weights for policy 0, policy_version 94858 (0.0013) [2023-03-09 09:36:50,451][23090] Updated weights for policy 0, policy_version 94868 (0.0016) [2023-03-09 09:36:51,207][23090] Updated weights for policy 0, policy_version 94878 (0.0019) [2023-03-09 09:36:52,124][23090] Updated weights for policy 0, policy_version 94888 (0.0016) [2023-03-09 09:36:52,860][23090] Updated weights for policy 0, policy_version 94898 (0.0017) [2023-03-09 09:36:53,735][23090] Updated weights for policy 0, policy_version 94908 (0.0021) [2023-03-09 09:36:54,059][22664] Fps is (10 sec: 199881.9, 60 sec: 197700.9, 300 sec: 197163.6). Total num frames: 1555021824. Throughput: 0: 49351.7. Samples: 388820176. Policy #0 lag: (min: 0.0, avg: 17.1, max: 33.0) [2023-03-09 09:36:54,060][22664] Avg episode reward: [(0, '53.050')] [2023-03-09 09:36:54,648][23090] Updated weights for policy 0, policy_version 94918 (0.0013) [2023-03-09 09:36:55,341][23090] Updated weights for policy 0, policy_version 94928 (0.0013) [2023-03-09 09:36:56,260][23090] Updated weights for policy 0, policy_version 94938 (0.0013) [2023-03-09 09:36:57,084][23090] Updated weights for policy 0, policy_version 94948 (0.0015) [2023-03-09 09:36:57,897][23090] Updated weights for policy 0, policy_version 94958 (0.0021) [2023-03-09 09:36:58,709][23090] Updated weights for policy 0, policy_version 94968 (0.0013) [2023-03-09 09:36:59,059][22664] Fps is (10 sec: 198247.5, 60 sec: 197972.8, 300 sec: 197219.0). Total num frames: 1556021248. Throughput: 0: 49397.9. Samples: 388971696. Policy #0 lag: (min: 0.0, avg: 17.1, max: 33.0) [2023-03-09 09:36:59,060][22664] Avg episode reward: [(0, '53.939')] [2023-03-09 09:36:59,629][23090] Updated weights for policy 0, policy_version 94978 (0.0018) [2023-03-09 09:36:59,971][22940] Signal inference workers to stop experience collection... (31700 times) [2023-03-09 09:36:59,972][22940] Signal inference workers to resume experience collection... (31700 times) [2023-03-09 09:37:00,039][23090] InferenceWorker_p0-w0: stopping experience collection (31700 times) [2023-03-09 09:37:00,039][23090] InferenceWorker_p0-w0: resuming experience collection (31700 times) [2023-03-09 09:37:00,417][23090] Updated weights for policy 0, policy_version 94988 (0.0013) [2023-03-09 09:37:01,187][23090] Updated weights for policy 0, policy_version 94998 (0.0013) [2023-03-09 09:37:02,039][23090] Updated weights for policy 0, policy_version 95008 (0.0020) [2023-03-09 09:37:02,885][23090] Updated weights for policy 0, policy_version 95018 (0.0015) [2023-03-09 09:37:03,737][23090] Updated weights for policy 0, policy_version 95028 (0.0025) [2023-03-09 09:37:04,058][22664] Fps is (10 sec: 198249.5, 60 sec: 197700.4, 300 sec: 197219.2). Total num frames: 1557004288. Throughput: 0: 49397.7. Samples: 389266496. Policy #0 lag: (min: 0.0, avg: 17.1, max: 33.0) [2023-03-09 09:37:04,059][22664] Avg episode reward: [(0, '53.885')] [2023-03-09 09:37:04,480][23090] Updated weights for policy 0, policy_version 95038 (0.0017) [2023-03-09 09:37:05,373][23090] Updated weights for policy 0, policy_version 95048 (0.0024) [2023-03-09 09:37:06,251][23090] Updated weights for policy 0, policy_version 95059 (0.0013) [2023-03-09 09:37:07,027][23090] Updated weights for policy 0, policy_version 95069 (0.0016) [2023-03-09 09:37:07,995][23090] Updated weights for policy 0, policy_version 95079 (0.0013) [2023-03-09 09:37:08,728][23090] Updated weights for policy 0, policy_version 95089 (0.0013) [2023-03-09 09:37:09,058][22664] Fps is (10 sec: 198249.5, 60 sec: 197973.4, 300 sec: 197219.0). Total num frames: 1558003712. Throughput: 0: 49354.4. Samples: 389563344. Policy #0 lag: (min: 0.0, avg: 17.1, max: 33.0) [2023-03-09 09:37:09,061][22664] Avg episode reward: [(0, '53.904')] [2023-03-09 09:37:09,594][23090] Updated weights for policy 0, policy_version 95099 (0.0013) [2023-03-09 09:37:10,435][23090] Updated weights for policy 0, policy_version 95109 (0.0015) [2023-03-09 09:37:11,131][22940] Signal inference workers to stop experience collection... (31750 times) [2023-03-09 09:37:11,150][22940] Signal inference workers to resume experience collection... (31750 times) [2023-03-09 09:37:11,167][23090] InferenceWorker_p0-w0: stopping experience collection (31750 times) [2023-03-09 09:37:11,167][23090] InferenceWorker_p0-w0: resuming experience collection (31750 times) [2023-03-09 09:37:11,218][23090] Updated weights for policy 0, policy_version 95119 (0.0016) [2023-03-09 09:37:12,182][23090] Updated weights for policy 0, policy_version 95129 (0.0013) [2023-03-09 09:37:12,992][23090] Updated weights for policy 0, policy_version 95139 (0.0021) [2023-03-09 09:37:13,800][23090] Updated weights for policy 0, policy_version 95149 (0.0013) [2023-03-09 09:37:14,059][22664] Fps is (10 sec: 196602.4, 60 sec: 197154.2, 300 sec: 197218.9). Total num frames: 1558970368. Throughput: 0: 49308.8. Samples: 389708688. Policy #0 lag: (min: 0.0, avg: 17.1, max: 33.0) [2023-03-09 09:37:14,061][22664] Avg episode reward: [(0, '55.123')] [2023-03-09 09:37:14,621][23090] Updated weights for policy 0, policy_version 95159 (0.0016) [2023-03-09 09:37:15,472][23090] Updated weights for policy 0, policy_version 95169 (0.0017) [2023-03-09 09:37:16,311][23090] Updated weights for policy 0, policy_version 95179 (0.0013) [2023-03-09 09:37:17,111][23090] Updated weights for policy 0, policy_version 95189 (0.0018) [2023-03-09 09:37:17,902][23090] Updated weights for policy 0, policy_version 95199 (0.0013) [2023-03-09 09:37:18,791][23090] Updated weights for policy 0, policy_version 95209 (0.0016) [2023-03-09 09:37:19,059][22664] Fps is (10 sec: 194955.2, 60 sec: 197152.8, 300 sec: 197163.0). Total num frames: 1559953408. Throughput: 0: 49264.3. Samples: 390003520. Policy #0 lag: (min: 0.0, avg: 17.1, max: 33.0) [2023-03-09 09:37:19,062][22664] Avg episode reward: [(0, '56.593')] [2023-03-09 09:37:19,095][22940] Saving /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000095213_1559969792.pth... [2023-03-09 09:37:19,155][22940] Removing /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000092327_1512685568.pth [2023-03-09 09:37:19,579][23090] Updated weights for policy 0, policy_version 95219 (0.0019) [2023-03-09 09:37:20,381][23090] Updated weights for policy 0, policy_version 95229 (0.0017) [2023-03-09 09:37:21,334][23090] Updated weights for policy 0, policy_version 95239 (0.0017) [2023-03-09 09:37:22,032][23090] Updated weights for policy 0, policy_version 95249 (0.0017) [2023-03-09 09:37:22,938][23090] Updated weights for policy 0, policy_version 95259 (0.0013) [2023-03-09 09:37:23,842][23090] Updated weights for policy 0, policy_version 95269 (0.0018) [2023-03-09 09:37:24,059][22664] Fps is (10 sec: 196607.0, 60 sec: 197153.2, 300 sec: 197163.6). Total num frames: 1560936448. Throughput: 0: 49363.9. Samples: 390300400. Policy #0 lag: (min: 0.0, avg: 17.1, max: 33.0) [2023-03-09 09:37:24,061][22664] Avg episode reward: [(0, '53.729')] [2023-03-09 09:37:24,265][22940] Signal inference workers to stop experience collection... (31800 times) [2023-03-09 09:37:24,278][22940] Signal inference workers to resume experience collection... (31800 times) [2023-03-09 09:37:24,347][23090] InferenceWorker_p0-w0: stopping experience collection (31800 times) [2023-03-09 09:37:24,348][23090] InferenceWorker_p0-w0: resuming experience collection (31800 times) [2023-03-09 09:37:24,586][23090] Updated weights for policy 0, policy_version 95280 (0.0019) [2023-03-09 09:37:25,530][23090] Updated weights for policy 0, policy_version 95290 (0.0019) [2023-03-09 09:37:26,406][23090] Updated weights for policy 0, policy_version 95300 (0.0020) [2023-03-09 09:37:27,149][23090] Updated weights for policy 0, policy_version 95310 (0.0016) [2023-03-09 09:37:27,949][23090] Updated weights for policy 0, policy_version 95320 (0.0016) [2023-03-09 09:37:28,991][23090] Updated weights for policy 0, policy_version 95331 (0.0016) [2023-03-09 09:37:29,058][22664] Fps is (10 sec: 196622.2, 60 sec: 197155.0, 300 sec: 197163.5). Total num frames: 1561919488. Throughput: 0: 49318.0. Samples: 390447792. Policy #0 lag: (min: 0.0, avg: 17.1, max: 33.0) [2023-03-09 09:37:29,059][22664] Avg episode reward: [(0, '56.434')] [2023-03-09 09:37:29,705][23090] Updated weights for policy 0, policy_version 95341 (0.0015) [2023-03-09 09:37:30,506][23090] Updated weights for policy 0, policy_version 95351 (0.0013) [2023-03-09 09:37:31,358][23090] Updated weights for policy 0, policy_version 95361 (0.0013) [2023-03-09 09:37:32,231][23090] Updated weights for policy 0, policy_version 95371 (0.0018) [2023-03-09 09:37:32,976][23090] Updated weights for policy 0, policy_version 95381 (0.0018) [2023-03-09 09:37:33,942][23090] Updated weights for policy 0, policy_version 95392 (0.0013) [2023-03-09 09:37:34,058][22664] Fps is (10 sec: 198253.1, 60 sec: 197154.3, 300 sec: 197163.4). Total num frames: 1562918912. Throughput: 0: 49359.2. Samples: 390746544. Policy #0 lag: (min: 0.0, avg: 17.1, max: 33.0) [2023-03-09 09:37:34,060][22664] Avg episode reward: [(0, '56.654')] [2023-03-09 09:37:34,877][23090] Updated weights for policy 0, policy_version 95403 (0.0022) [2023-03-09 09:37:35,586][22940] Signal inference workers to stop experience collection... (31850 times) [2023-03-09 09:37:35,587][22940] Signal inference workers to resume experience collection... (31850 times) [2023-03-09 09:37:35,651][23090] InferenceWorker_p0-w0: stopping experience collection (31850 times) [2023-03-09 09:37:35,651][23090] InferenceWorker_p0-w0: resuming experience collection (31850 times) [2023-03-09 09:37:35,654][23090] Updated weights for policy 0, policy_version 95413 (0.0016) [2023-03-09 09:37:36,449][23090] Updated weights for policy 0, policy_version 95423 (0.0013) [2023-03-09 09:37:37,376][23090] Updated weights for policy 0, policy_version 95433 (0.0015) [2023-03-09 09:37:38,268][23090] Updated weights for policy 0, policy_version 95444 (0.0013) [2023-03-09 09:37:39,040][23090] Updated weights for policy 0, policy_version 95454 (0.0013) [2023-03-09 09:37:39,059][22664] Fps is (10 sec: 199883.5, 60 sec: 197701.0, 300 sec: 197219.0). Total num frames: 1563918336. Throughput: 0: 49360.1. Samples: 391041376. Policy #0 lag: (min: 0.0, avg: 17.1, max: 33.0) [2023-03-09 09:37:39,060][22664] Avg episode reward: [(0, '54.160')] [2023-03-09 09:37:39,953][23090] Updated weights for policy 0, policy_version 95464 (0.0015) [2023-03-09 09:37:40,711][23090] Updated weights for policy 0, policy_version 95474 (0.0014) [2023-03-09 09:37:41,523][23090] Updated weights for policy 0, policy_version 95484 (0.0016) [2023-03-09 09:37:42,451][23090] Updated weights for policy 0, policy_version 95494 (0.0020) [2023-03-09 09:37:43,169][23090] Updated weights for policy 0, policy_version 95504 (0.0013) [2023-03-09 09:37:44,059][22664] Fps is (10 sec: 198238.5, 60 sec: 197972.1, 300 sec: 197163.1). Total num frames: 1564901376. Throughput: 0: 49268.7. Samples: 391188800. Policy #0 lag: (min: 1.0, avg: 16.4, max: 33.0) [2023-03-09 09:37:44,061][22664] Avg episode reward: [(0, '54.174')] [2023-03-09 09:37:44,093][23090] Updated weights for policy 0, policy_version 95514 (0.0016) [2023-03-09 09:37:44,936][23090] Updated weights for policy 0, policy_version 95524 (0.0017) [2023-03-09 09:37:45,711][23090] Updated weights for policy 0, policy_version 95534 (0.0015) [2023-03-09 09:37:46,551][23090] Updated weights for policy 0, policy_version 95544 (0.0013) [2023-03-09 09:37:47,366][23090] Updated weights for policy 0, policy_version 95554 (0.0013) [2023-03-09 09:37:48,212][22940] Signal inference workers to stop experience collection... (31900 times) [2023-03-09 09:37:48,237][22940] Signal inference workers to resume experience collection... (31900 times) [2023-03-09 09:37:48,243][23090] Updated weights for policy 0, policy_version 95564 (0.0023) [2023-03-09 09:37:48,280][23090] InferenceWorker_p0-w0: stopping experience collection (31900 times) [2023-03-09 09:37:48,280][23090] InferenceWorker_p0-w0: resuming experience collection (31900 times) [2023-03-09 09:37:48,946][23090] Updated weights for policy 0, policy_version 95574 (0.0018) [2023-03-09 09:37:49,059][22664] Fps is (10 sec: 196608.2, 60 sec: 197427.6, 300 sec: 197163.4). Total num frames: 1565884416. Throughput: 0: 49359.6. Samples: 391487680. Policy #0 lag: (min: 1.0, avg: 16.4, max: 33.0) [2023-03-09 09:37:49,060][22664] Avg episode reward: [(0, '55.913')] [2023-03-09 09:37:49,857][23090] Updated weights for policy 0, policy_version 95584 (0.0016) [2023-03-09 09:37:50,678][23090] Updated weights for policy 0, policy_version 95594 (0.0016) [2023-03-09 09:37:51,457][23090] Updated weights for policy 0, policy_version 95604 (0.0018) [2023-03-09 09:37:52,250][23090] Updated weights for policy 0, policy_version 95614 (0.0013) [2023-03-09 09:37:53,177][23090] Updated weights for policy 0, policy_version 95624 (0.0013) [2023-03-09 09:37:53,963][23090] Updated weights for policy 0, policy_version 95634 (0.0013) [2023-03-09 09:37:54,059][22664] Fps is (10 sec: 198247.3, 60 sec: 197699.6, 300 sec: 197218.7). Total num frames: 1566883840. Throughput: 0: 49312.7. Samples: 391782432. Policy #0 lag: (min: 1.0, avg: 16.4, max: 33.0) [2023-03-09 09:37:54,061][22664] Avg episode reward: [(0, '55.407')] [2023-03-09 09:37:54,828][23090] Updated weights for policy 0, policy_version 95644 (0.0016) [2023-03-09 09:37:55,708][23090] Updated weights for policy 0, policy_version 95654 (0.0014) [2023-03-09 09:37:56,532][23090] Updated weights for policy 0, policy_version 95665 (0.0019) [2023-03-09 09:37:57,420][23090] Updated weights for policy 0, policy_version 95675 (0.0023) [2023-03-09 09:37:58,279][23090] Updated weights for policy 0, policy_version 95685 (0.0013) [2023-03-09 09:37:59,001][23090] Updated weights for policy 0, policy_version 95695 (0.0018) [2023-03-09 09:37:59,059][22664] Fps is (10 sec: 198236.8, 60 sec: 197425.9, 300 sec: 197163.4). Total num frames: 1567866880. Throughput: 0: 49358.6. Samples: 391929840. Policy #0 lag: (min: 1.0, avg: 16.4, max: 33.0) [2023-03-09 09:37:59,061][22664] Avg episode reward: [(0, '53.619')] [2023-03-09 09:37:59,895][23090] Updated weights for policy 0, policy_version 95705 (0.0017) [2023-03-09 09:38:00,832][23090] Updated weights for policy 0, policy_version 95715 (0.0013) [2023-03-09 09:38:01,143][22940] Signal inference workers to stop experience collection... (31950 times) [2023-03-09 09:38:01,144][22940] Signal inference workers to resume experience collection... (31950 times) [2023-03-09 09:38:01,204][23090] InferenceWorker_p0-w0: stopping experience collection (31950 times) [2023-03-09 09:38:01,205][23090] InferenceWorker_p0-w0: resuming experience collection (31950 times) [2023-03-09 09:38:01,621][23090] Updated weights for policy 0, policy_version 95725 (0.0014) [2023-03-09 09:38:02,394][23090] Updated weights for policy 0, policy_version 95735 (0.0013) [2023-03-09 09:38:03,245][23090] Updated weights for policy 0, policy_version 95745 (0.0021) [2023-03-09 09:38:04,059][22664] Fps is (10 sec: 194971.4, 60 sec: 197153.3, 300 sec: 197052.2). Total num frames: 1568833536. Throughput: 0: 49359.1. Samples: 392224656. Policy #0 lag: (min: 1.0, avg: 16.4, max: 33.0) [2023-03-09 09:38:04,060][22664] Avg episode reward: [(0, '54.843')] [2023-03-09 09:38:04,128][23090] Updated weights for policy 0, policy_version 95755 (0.0024) [2023-03-09 09:38:04,889][23090] Updated weights for policy 0, policy_version 95765 (0.0013) [2023-03-09 09:38:05,753][23090] Updated weights for policy 0, policy_version 95775 (0.0013) [2023-03-09 09:38:06,569][23090] Updated weights for policy 0, policy_version 95785 (0.0023) [2023-03-09 09:38:07,344][23090] Updated weights for policy 0, policy_version 95795 (0.0015) [2023-03-09 09:38:08,225][23090] Updated weights for policy 0, policy_version 95806 (0.0019) [2023-03-09 09:38:09,058][22664] Fps is (10 sec: 194980.5, 60 sec: 196881.1, 300 sec: 197107.8). Total num frames: 1569816576. Throughput: 0: 49403.0. Samples: 392523520. Policy #0 lag: (min: 1.0, avg: 16.4, max: 33.0) [2023-03-09 09:38:09,059][22664] Avg episode reward: [(0, '53.852')] [2023-03-09 09:38:09,147][23090] Updated weights for policy 0, policy_version 95816 (0.0014) [2023-03-09 09:38:09,919][23090] Updated weights for policy 0, policy_version 95826 (0.0020) [2023-03-09 09:38:10,773][23090] Updated weights for policy 0, policy_version 95836 (0.0019) [2023-03-09 09:38:11,625][23090] Updated weights for policy 0, policy_version 95846 (0.0016) [2023-03-09 09:38:12,471][23090] Updated weights for policy 0, policy_version 95857 (0.0017) [2023-03-09 09:38:13,191][22940] Signal inference workers to stop experience collection... (32000 times) [2023-03-09 09:38:13,208][22940] Signal inference workers to resume experience collection... (32000 times) [2023-03-09 09:38:13,274][23090] InferenceWorker_p0-w0: stopping experience collection (32000 times) [2023-03-09 09:38:13,276][23090] InferenceWorker_p0-w0: resuming experience collection (32000 times) [2023-03-09 09:38:13,364][23090] Updated weights for policy 0, policy_version 95867 (0.0013) [2023-03-09 09:38:14,059][22664] Fps is (10 sec: 198248.6, 60 sec: 197427.7, 300 sec: 197052.3). Total num frames: 1570816000. Throughput: 0: 49448.0. Samples: 392672960. Policy #0 lag: (min: 1.0, avg: 16.4, max: 33.0) [2023-03-09 09:38:14,060][22664] Avg episode reward: [(0, '53.739')] [2023-03-09 09:38:14,202][23090] Updated weights for policy 0, policy_version 95877 (0.0017) [2023-03-09 09:38:14,941][23090] Updated weights for policy 0, policy_version 95887 (0.0017) [2023-03-09 09:38:15,896][23090] Updated weights for policy 0, policy_version 95897 (0.0013) [2023-03-09 09:38:16,732][23090] Updated weights for policy 0, policy_version 95907 (0.0015) [2023-03-09 09:38:17,501][23090] Updated weights for policy 0, policy_version 95917 (0.0016) [2023-03-09 09:38:18,270][23090] Updated weights for policy 0, policy_version 95927 (0.0016) [2023-03-09 09:38:19,059][22664] Fps is (10 sec: 198245.3, 60 sec: 197429.5, 300 sec: 197052.4). Total num frames: 1571799040. Throughput: 0: 49359.2. Samples: 392967712. Policy #0 lag: (min: 1.0, avg: 16.4, max: 33.0) [2023-03-09 09:38:19,059][22664] Avg episode reward: [(0, '55.797')] [2023-03-09 09:38:19,189][23090] Updated weights for policy 0, policy_version 95937 (0.0020) [2023-03-09 09:38:20,003][23090] Updated weights for policy 0, policy_version 95947 (0.0021) [2023-03-09 09:38:20,769][23090] Updated weights for policy 0, policy_version 95957 (0.0017) [2023-03-09 09:38:21,579][23090] Updated weights for policy 0, policy_version 95967 (0.0017) [2023-03-09 09:38:22,490][23090] Updated weights for policy 0, policy_version 95977 (0.0016) [2023-03-09 09:38:23,230][23090] Updated weights for policy 0, policy_version 95987 (0.0025) [2023-03-09 09:38:24,059][22664] Fps is (10 sec: 199880.2, 60 sec: 197973.2, 300 sec: 197163.2). Total num frames: 1572814848. Throughput: 0: 49404.5. Samples: 393264592. Policy #0 lag: (min: 1.0, avg: 16.4, max: 33.0) [2023-03-09 09:38:24,061][22664] Avg episode reward: [(0, '55.043')] [2023-03-09 09:38:24,131][23090] Updated weights for policy 0, policy_version 95998 (0.0016) [2023-03-09 09:38:24,942][22940] Signal inference workers to stop experience collection... (32050 times) [2023-03-09 09:38:24,945][22940] Signal inference workers to resume experience collection... (32050 times) [2023-03-09 09:38:25,017][23090] InferenceWorker_p0-w0: stopping experience collection (32050 times) [2023-03-09 09:38:25,017][23090] InferenceWorker_p0-w0: resuming experience collection (32050 times) [2023-03-09 09:38:25,061][23090] Updated weights for policy 0, policy_version 96008 (0.0013) [2023-03-09 09:38:25,797][23090] Updated weights for policy 0, policy_version 96018 (0.0017) [2023-03-09 09:38:26,722][23090] Updated weights for policy 0, policy_version 96028 (0.0017) [2023-03-09 09:38:27,614][23090] Updated weights for policy 0, policy_version 96038 (0.0014) [2023-03-09 09:38:28,384][23090] Updated weights for policy 0, policy_version 96049 (0.0018) [2023-03-09 09:38:29,058][22664] Fps is (10 sec: 198247.0, 60 sec: 197700.2, 300 sec: 197052.8). Total num frames: 1573781504. Throughput: 0: 49404.9. Samples: 393412000. Policy #0 lag: (min: 1.0, avg: 16.4, max: 33.0) [2023-03-09 09:38:29,059][22664] Avg episode reward: [(0, '54.025')] [2023-03-09 09:38:29,295][23090] Updated weights for policy 0, policy_version 96059 (0.0023) [2023-03-09 09:38:30,149][23090] Updated weights for policy 0, policy_version 96069 (0.0018) [2023-03-09 09:38:30,896][23090] Updated weights for policy 0, policy_version 96079 (0.0013) [2023-03-09 09:38:31,791][23090] Updated weights for policy 0, policy_version 96089 (0.0022) [2023-03-09 09:38:32,716][23090] Updated weights for policy 0, policy_version 96100 (0.0016) [2023-03-09 09:38:33,503][23090] Updated weights for policy 0, policy_version 96110 (0.0019) [2023-03-09 09:38:34,059][22664] Fps is (10 sec: 196614.1, 60 sec: 197700.0, 300 sec: 197107.9). Total num frames: 1574780928. Throughput: 0: 49360.0. Samples: 393708880. Policy #0 lag: (min: 1.0, avg: 16.4, max: 33.0) [2023-03-09 09:38:34,060][22664] Avg episode reward: [(0, '53.621')] [2023-03-09 09:38:34,352][23090] Updated weights for policy 0, policy_version 96120 (0.0020) [2023-03-09 09:38:34,722][22940] Signal inference workers to stop experience collection... (32100 times) [2023-03-09 09:38:34,741][22940] Signal inference workers to resume experience collection... (32100 times) [2023-03-09 09:38:34,763][23090] InferenceWorker_p0-w0: stopping experience collection (32100 times) [2023-03-09 09:38:34,763][23090] InferenceWorker_p0-w0: resuming experience collection (32100 times) [2023-03-09 09:38:35,211][23090] Updated weights for policy 0, policy_version 96130 (0.0019) [2023-03-09 09:38:36,042][23090] Updated weights for policy 0, policy_version 96140 (0.0013) [2023-03-09 09:38:36,823][23090] Updated weights for policy 0, policy_version 96150 (0.0016) [2023-03-09 09:38:37,670][23090] Updated weights for policy 0, policy_version 96160 (0.0020) [2023-03-09 09:38:38,530][23090] Updated weights for policy 0, policy_version 96170 (0.0017) [2023-03-09 09:38:39,059][22664] Fps is (10 sec: 198238.9, 60 sec: 197426.2, 300 sec: 197052.0). Total num frames: 1575763968. Throughput: 0: 49360.3. Samples: 394003648. Policy #0 lag: (min: 2.0, avg: 16.4, max: 33.0) [2023-03-09 09:38:39,061][22664] Avg episode reward: [(0, '52.590')] [2023-03-09 09:38:39,332][23090] Updated weights for policy 0, policy_version 96180 (0.0022) [2023-03-09 09:38:40,117][23090] Updated weights for policy 0, policy_version 96190 (0.0013) [2023-03-09 09:38:41,027][23090] Updated weights for policy 0, policy_version 96200 (0.0016) [2023-03-09 09:38:41,761][23090] Updated weights for policy 0, policy_version 96210 (0.0013) [2023-03-09 09:38:42,623][23090] Updated weights for policy 0, policy_version 96220 (0.0016) [2023-03-09 09:38:43,586][23090] Updated weights for policy 0, policy_version 96230 (0.0013) [2023-03-09 09:38:44,059][22664] Fps is (10 sec: 194965.6, 60 sec: 197154.6, 300 sec: 196996.6). Total num frames: 1576730624. Throughput: 0: 49361.0. Samples: 394151072. Policy #0 lag: (min: 2.0, avg: 16.4, max: 33.0) [2023-03-09 09:38:44,061][22664] Avg episode reward: [(0, '55.701')] [2023-03-09 09:38:44,251][23090] Updated weights for policy 0, policy_version 96240 (0.0016) [2023-03-09 09:38:45,223][23090] Updated weights for policy 0, policy_version 96251 (0.0023) [2023-03-09 09:38:46,078][23090] Updated weights for policy 0, policy_version 96261 (0.0017) [2023-03-09 09:38:46,813][23090] Updated weights for policy 0, policy_version 96271 (0.0019) [2023-03-09 09:38:47,747][23090] Updated weights for policy 0, policy_version 96281 (0.0018) [2023-03-09 09:38:47,880][22940] Signal inference workers to stop experience collection... (32150 times) [2023-03-09 09:38:47,907][22940] Signal inference workers to resume experience collection... (32150 times) [2023-03-09 09:38:47,954][23090] InferenceWorker_p0-w0: stopping experience collection (32150 times) [2023-03-09 09:38:47,954][23090] InferenceWorker_p0-w0: resuming experience collection (32150 times) [2023-03-09 09:38:48,640][23090] Updated weights for policy 0, policy_version 96291 (0.0016) [2023-03-09 09:38:49,059][22664] Fps is (10 sec: 194973.7, 60 sec: 197153.8, 300 sec: 196941.1). Total num frames: 1577713664. Throughput: 0: 49407.4. Samples: 394447984. Policy #0 lag: (min: 2.0, avg: 16.4, max: 33.0) [2023-03-09 09:38:49,060][22664] Avg episode reward: [(0, '53.331')] [2023-03-09 09:38:49,387][23090] Updated weights for policy 0, policy_version 96301 (0.0021) [2023-03-09 09:38:50,184][23090] Updated weights for policy 0, policy_version 96311 (0.0016) [2023-03-09 09:38:51,102][23090] Updated weights for policy 0, policy_version 96321 (0.0013) [2023-03-09 09:38:51,921][23090] Updated weights for policy 0, policy_version 96331 (0.0017) [2023-03-09 09:38:52,803][23090] Updated weights for policy 0, policy_version 96342 (0.0023) [2023-03-09 09:38:53,639][23090] Updated weights for policy 0, policy_version 96352 (0.0023) [2023-03-09 09:38:54,059][22664] Fps is (10 sec: 196610.2, 60 sec: 196881.7, 300 sec: 196996.9). Total num frames: 1578696704. Throughput: 0: 49270.9. Samples: 394740720. Policy #0 lag: (min: 2.0, avg: 16.4, max: 33.0) [2023-03-09 09:38:54,060][22664] Avg episode reward: [(0, '53.165')] [2023-03-09 09:38:54,484][23090] Updated weights for policy 0, policy_version 96362 (0.0013) [2023-03-09 09:38:55,265][23090] Updated weights for policy 0, policy_version 96372 (0.0013) [2023-03-09 09:38:56,073][23090] Updated weights for policy 0, policy_version 96382 (0.0016) [2023-03-09 09:38:57,003][23090] Updated weights for policy 0, policy_version 96392 (0.0016) [2023-03-09 09:38:57,751][23090] Updated weights for policy 0, policy_version 96402 (0.0013) [2023-03-09 09:38:58,669][23090] Updated weights for policy 0, policy_version 96412 (0.0019) [2023-03-09 09:38:59,058][22664] Fps is (10 sec: 196611.6, 60 sec: 196882.9, 300 sec: 196941.5). Total num frames: 1579679744. Throughput: 0: 49270.9. Samples: 394890144. Policy #0 lag: (min: 2.0, avg: 16.4, max: 33.0) [2023-03-09 09:38:59,059][22664] Avg episode reward: [(0, '52.460')] [2023-03-09 09:38:59,517][23090] Updated weights for policy 0, policy_version 96422 (0.0021) [2023-03-09 09:39:00,251][23090] Updated weights for policy 0, policy_version 96432 (0.0013) [2023-03-09 09:39:01,164][23090] Updated weights for policy 0, policy_version 96442 (0.0021) [2023-03-09 09:39:02,006][23090] Updated weights for policy 0, policy_version 96452 (0.0014) [2023-03-09 09:39:02,308][22940] Signal inference workers to stop experience collection... (32200 times) [2023-03-09 09:39:02,309][22940] Signal inference workers to resume experience collection... (32200 times) [2023-03-09 09:39:02,375][23090] InferenceWorker_p0-w0: stopping experience collection (32200 times) [2023-03-09 09:39:02,376][23090] InferenceWorker_p0-w0: resuming experience collection (32200 times) [2023-03-09 09:39:02,759][23090] Updated weights for policy 0, policy_version 96462 (0.0013) [2023-03-09 09:39:03,641][23090] Updated weights for policy 0, policy_version 96472 (0.0018) [2023-03-09 09:39:04,059][22664] Fps is (10 sec: 198242.3, 60 sec: 197426.8, 300 sec: 197107.7). Total num frames: 1580679168. Throughput: 0: 49226.3. Samples: 395182912. Policy #0 lag: (min: 2.0, avg: 16.4, max: 33.0) [2023-03-09 09:39:04,061][22664] Avg episode reward: [(0, '53.617')] [2023-03-09 09:39:04,495][23090] Updated weights for policy 0, policy_version 96482 (0.0016) [2023-03-09 09:39:05,330][23090] Updated weights for policy 0, policy_version 96492 (0.0016) [2023-03-09 09:39:06,095][23090] Updated weights for policy 0, policy_version 96502 (0.0016) [2023-03-09 09:39:06,953][23090] Updated weights for policy 0, policy_version 96512 (0.0013) [2023-03-09 09:39:07,851][23090] Updated weights for policy 0, policy_version 96522 (0.0013) [2023-03-09 09:39:08,639][23090] Updated weights for policy 0, policy_version 96532 (0.0013) [2023-03-09 09:39:09,059][22664] Fps is (10 sec: 196606.1, 60 sec: 197153.8, 300 sec: 197052.4). Total num frames: 1581645824. Throughput: 0: 49181.5. Samples: 395477744. Policy #0 lag: (min: 2.0, avg: 16.4, max: 33.0) [2023-03-09 09:39:09,060][22664] Avg episode reward: [(0, '52.718')] [2023-03-09 09:39:09,441][23090] Updated weights for policy 0, policy_version 96542 (0.0021) [2023-03-09 09:39:10,370][23090] Updated weights for policy 0, policy_version 96552 (0.0013) [2023-03-09 09:39:11,270][23090] Updated weights for policy 0, policy_version 96563 (0.0015) [2023-03-09 09:39:12,014][23090] Updated weights for policy 0, policy_version 96573 (0.0016) [2023-03-09 09:39:12,959][23090] Updated weights for policy 0, policy_version 96583 (0.0013) [2023-03-09 09:39:13,667][23090] Updated weights for policy 0, policy_version 96593 (0.0013) [2023-03-09 09:39:14,058][22664] Fps is (10 sec: 196615.4, 60 sec: 197154.6, 300 sec: 197163.4). Total num frames: 1582645248. Throughput: 0: 49181.5. Samples: 395625168. Policy #0 lag: (min: 2.0, avg: 16.4, max: 33.0) [2023-03-09 09:39:14,059][22664] Avg episode reward: [(0, '54.969')] [2023-03-09 09:39:14,582][23090] Updated weights for policy 0, policy_version 96603 (0.0018) [2023-03-09 09:39:15,442][23090] Updated weights for policy 0, policy_version 96613 (0.0013) [2023-03-09 09:39:16,163][23090] Updated weights for policy 0, policy_version 96623 (0.0019) [2023-03-09 09:39:16,546][22940] Signal inference workers to stop experience collection... (32250 times) [2023-03-09 09:39:16,546][22940] Signal inference workers to resume experience collection... (32250 times) [2023-03-09 09:39:16,612][23090] InferenceWorker_p0-w0: stopping experience collection (32250 times) [2023-03-09 09:39:16,612][23090] InferenceWorker_p0-w0: resuming experience collection (32250 times) [2023-03-09 09:39:17,107][23090] Updated weights for policy 0, policy_version 96633 (0.0023) [2023-03-09 09:39:17,884][23090] Updated weights for policy 0, policy_version 96643 (0.0013) [2023-03-09 09:39:18,690][23090] Updated weights for policy 0, policy_version 96653 (0.0014) [2023-03-09 09:39:19,059][22664] Fps is (10 sec: 199873.4, 60 sec: 197425.1, 300 sec: 197218.5). Total num frames: 1583644672. Throughput: 0: 49180.1. Samples: 395922016. Policy #0 lag: (min: 2.0, avg: 16.4, max: 33.0) [2023-03-09 09:39:19,061][22664] Avg episode reward: [(0, '55.086')] [2023-03-09 09:39:19,071][22940] Saving /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000096658_1583644672.pth... [2023-03-09 09:39:19,126][22940] Removing /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000093770_1536327680.pth [2023-03-09 09:39:19,497][23090] Updated weights for policy 0, policy_version 96663 (0.0017) [2023-03-09 09:39:20,409][23090] Updated weights for policy 0, policy_version 96673 (0.0026) [2023-03-09 09:39:21,199][23090] Updated weights for policy 0, policy_version 96683 (0.0015) [2023-03-09 09:39:21,956][23090] Updated weights for policy 0, policy_version 96693 (0.0019) [2023-03-09 09:39:22,952][23090] Updated weights for policy 0, policy_version 96704 (0.0013) [2023-03-09 09:39:23,787][23090] Updated weights for policy 0, policy_version 96714 (0.0025) [2023-03-09 09:39:24,058][22664] Fps is (10 sec: 196607.8, 60 sec: 196609.2, 300 sec: 197108.1). Total num frames: 1584611328. Throughput: 0: 49227.8. Samples: 396218880. Policy #0 lag: (min: 2.0, avg: 16.4, max: 33.0) [2023-03-09 09:39:24,060][22664] Avg episode reward: [(0, '56.475')] [2023-03-09 09:39:24,578][23090] Updated weights for policy 0, policy_version 96724 (0.0022) [2023-03-09 09:39:25,381][23090] Updated weights for policy 0, policy_version 96734 (0.0013) [2023-03-09 09:39:26,338][23090] Updated weights for policy 0, policy_version 96744 (0.0017) [2023-03-09 09:39:27,037][23090] Updated weights for policy 0, policy_version 96754 (0.0013) [2023-03-09 09:39:27,903][23090] Updated weights for policy 0, policy_version 96764 (0.0017) [2023-03-09 09:39:28,807][23090] Updated weights for policy 0, policy_version 96774 (0.0015) [2023-03-09 09:39:29,059][22664] Fps is (10 sec: 194975.2, 60 sec: 196879.9, 300 sec: 197163.3). Total num frames: 1585594368. Throughput: 0: 49227.3. Samples: 396366304. Policy #0 lag: (min: 2.0, avg: 16.4, max: 33.0) [2023-03-09 09:39:29,061][22664] Avg episode reward: [(0, '54.546')] [2023-03-09 09:39:29,318][22940] Signal inference workers to stop experience collection... (32300 times) [2023-03-09 09:39:29,335][22940] Signal inference workers to resume experience collection... (32300 times) [2023-03-09 09:39:29,410][23090] InferenceWorker_p0-w0: stopping experience collection (32300 times) [2023-03-09 09:39:29,411][23090] InferenceWorker_p0-w0: resuming experience collection (32300 times) [2023-03-09 09:39:29,540][23090] Updated weights for policy 0, policy_version 96784 (0.0016) [2023-03-09 09:39:30,467][23090] Updated weights for policy 0, policy_version 96794 (0.0013) [2023-03-09 09:39:31,275][23090] Updated weights for policy 0, policy_version 96804 (0.0013) [2023-03-09 09:39:32,032][23090] Updated weights for policy 0, policy_version 96814 (0.0018) [2023-03-09 09:39:32,860][23090] Updated weights for policy 0, policy_version 96824 (0.0022) [2023-03-09 09:39:33,884][23090] Updated weights for policy 0, policy_version 96835 (0.0015) [2023-03-09 09:39:34,059][22664] Fps is (10 sec: 196602.5, 60 sec: 196607.3, 300 sec: 197163.3). Total num frames: 1586577408. Throughput: 0: 49224.1. Samples: 396663072. Policy #0 lag: (min: 2.0, avg: 16.4, max: 33.0) [2023-03-09 09:39:34,061][22664] Avg episode reward: [(0, '56.768')] [2023-03-09 09:39:34,659][23090] Updated weights for policy 0, policy_version 96845 (0.0015) [2023-03-09 09:39:35,432][23090] Updated weights for policy 0, policy_version 96855 (0.0019) [2023-03-09 09:39:36,361][23090] Updated weights for policy 0, policy_version 96865 (0.0013) [2023-03-09 09:39:37,126][23090] Updated weights for policy 0, policy_version 96875 (0.0018) [2023-03-09 09:39:37,922][23090] Updated weights for policy 0, policy_version 96885 (0.0013) [2023-03-09 09:39:38,690][23090] Updated weights for policy 0, policy_version 96895 (0.0014) [2023-03-09 09:39:39,059][22664] Fps is (10 sec: 198252.0, 60 sec: 196882.0, 300 sec: 197219.1). Total num frames: 1587576832. Throughput: 0: 49311.4. Samples: 396959728. Policy #0 lag: (min: 0.0, avg: 16.5, max: 33.0) [2023-03-09 09:39:39,060][22664] Avg episode reward: [(0, '55.440')] [2023-03-09 09:39:39,600][23090] Updated weights for policy 0, policy_version 96905 (0.0018) [2023-03-09 09:39:40,383][23090] Updated weights for policy 0, policy_version 96915 (0.0018) [2023-03-09 09:39:41,034][22940] Signal inference workers to stop experience collection... (32350 times) [2023-03-09 09:39:41,035][22940] Signal inference workers to resume experience collection... (32350 times) [2023-03-09 09:39:41,102][23090] InferenceWorker_p0-w0: stopping experience collection (32350 times) [2023-03-09 09:39:41,103][23090] InferenceWorker_p0-w0: resuming experience collection (32350 times) [2023-03-09 09:39:41,236][23090] Updated weights for policy 0, policy_version 96925 (0.0013) [2023-03-09 09:39:42,198][23090] Updated weights for policy 0, policy_version 96935 (0.0016) [2023-03-09 09:39:42,809][23090] Updated weights for policy 0, policy_version 96945 (0.0017) [2023-03-09 09:39:43,685][23090] Updated weights for policy 0, policy_version 96955 (0.0017) [2023-03-09 09:39:44,059][22664] Fps is (10 sec: 199885.6, 60 sec: 197427.3, 300 sec: 197274.3). Total num frames: 1588576256. Throughput: 0: 49311.7. Samples: 397109184. Policy #0 lag: (min: 0.0, avg: 16.5, max: 33.0) [2023-03-09 09:39:44,061][22664] Avg episode reward: [(0, '53.024')] [2023-03-09 09:39:44,578][23090] Updated weights for policy 0, policy_version 96965 (0.0016) [2023-03-09 09:39:45,393][23090] Updated weights for policy 0, policy_version 96976 (0.0013) [2023-03-09 09:39:46,295][23090] Updated weights for policy 0, policy_version 96986 (0.0013) [2023-03-09 09:39:47,177][23090] Updated weights for policy 0, policy_version 96996 (0.0013) [2023-03-09 09:39:47,913][23090] Updated weights for policy 0, policy_version 97006 (0.0013) [2023-03-09 09:39:48,809][23090] Updated weights for policy 0, policy_version 97016 (0.0020) [2023-03-09 09:39:49,059][22664] Fps is (10 sec: 198241.2, 60 sec: 197426.6, 300 sec: 197163.2). Total num frames: 1589559296. Throughput: 0: 49403.4. Samples: 397406064. Policy #0 lag: (min: 0.0, avg: 16.5, max: 33.0) [2023-03-09 09:39:49,061][22664] Avg episode reward: [(0, '55.377')] [2023-03-09 09:39:49,662][23090] Updated weights for policy 0, policy_version 97026 (0.0025) [2023-03-09 09:39:50,513][23090] Updated weights for policy 0, policy_version 97037 (0.0016) [2023-03-09 09:39:51,331][23090] Updated weights for policy 0, policy_version 97047 (0.0016) [2023-03-09 09:39:52,282][23090] Updated weights for policy 0, policy_version 97057 (0.0021) [2023-03-09 09:39:53,004][23090] Updated weights for policy 0, policy_version 97067 (0.0016) [2023-03-09 09:39:53,808][23090] Updated weights for policy 0, policy_version 97077 (0.0016) [2023-03-09 09:39:54,059][22664] Fps is (10 sec: 196607.0, 60 sec: 197426.8, 300 sec: 197218.7). Total num frames: 1590542336. Throughput: 0: 49403.2. Samples: 397700896. Policy #0 lag: (min: 0.0, avg: 16.5, max: 33.0) [2023-03-09 09:39:54,081][22664] Avg episode reward: [(0, '56.262')] [2023-03-09 09:39:54,623][23090] Updated weights for policy 0, policy_version 97087 (0.0017) [2023-03-09 09:39:55,543][23090] Updated weights for policy 0, policy_version 97097 (0.0018) [2023-03-09 09:39:55,556][22940] Signal inference workers to stop experience collection... (32400 times) [2023-03-09 09:39:55,557][22940] Signal inference workers to resume experience collection... (32400 times) [2023-03-09 09:39:55,625][23090] InferenceWorker_p0-w0: stopping experience collection (32400 times) [2023-03-09 09:39:55,626][23090] InferenceWorker_p0-w0: resuming experience collection (32400 times) [2023-03-09 09:39:56,330][23090] Updated weights for policy 0, policy_version 97107 (0.0033) [2023-03-09 09:39:57,124][23090] Updated weights for policy 0, policy_version 97117 (0.0014) [2023-03-09 09:39:58,055][23090] Updated weights for policy 0, policy_version 97127 (0.0018) [2023-03-09 09:39:58,862][23090] Updated weights for policy 0, policy_version 97138 (0.0020) [2023-03-09 09:39:59,058][22664] Fps is (10 sec: 198253.6, 60 sec: 197700.3, 300 sec: 197219.0). Total num frames: 1591541760. Throughput: 0: 49446.4. Samples: 397850256. Policy #0 lag: (min: 0.0, avg: 16.5, max: 33.0) [2023-03-09 09:39:59,059][22664] Avg episode reward: [(0, '54.299')] [2023-03-09 09:39:59,719][23090] Updated weights for policy 0, policy_version 97148 (0.0021) [2023-03-09 09:40:00,622][23090] Updated weights for policy 0, policy_version 97158 (0.0018) [2023-03-09 09:40:01,388][23090] Updated weights for policy 0, policy_version 97169 (0.0019) [2023-03-09 09:40:02,289][23090] Updated weights for policy 0, policy_version 97179 (0.0013) [2023-03-09 09:40:03,168][23090] Updated weights for policy 0, policy_version 97189 (0.0017) [2023-03-09 09:40:03,917][23090] Updated weights for policy 0, policy_version 97199 (0.0013) [2023-03-09 09:40:04,059][22664] Fps is (10 sec: 199886.4, 60 sec: 197700.8, 300 sec: 197218.8). Total num frames: 1592541184. Throughput: 0: 49445.5. Samples: 398147040. Policy #0 lag: (min: 0.0, avg: 16.5, max: 33.0) [2023-03-09 09:40:04,060][22664] Avg episode reward: [(0, '56.206')] [2023-03-09 09:40:04,817][23090] Updated weights for policy 0, policy_version 97209 (0.0013) [2023-03-09 09:40:05,704][23090] Updated weights for policy 0, policy_version 97219 (0.0013) [2023-03-09 09:40:06,454][23090] Updated weights for policy 0, policy_version 97229 (0.0017) [2023-03-09 09:40:07,221][23090] Updated weights for policy 0, policy_version 97239 (0.0017) [2023-03-09 09:40:08,236][23090] Updated weights for policy 0, policy_version 97249 (0.0026) [2023-03-09 09:40:08,988][23090] Updated weights for policy 0, policy_version 97259 (0.0019) [2023-03-09 09:40:09,058][22664] Fps is (10 sec: 196608.0, 60 sec: 197700.6, 300 sec: 197163.6). Total num frames: 1593507840. Throughput: 0: 49398.4. Samples: 398441808. Policy #0 lag: (min: 0.0, avg: 16.5, max: 33.0) [2023-03-09 09:40:09,059][22664] Avg episode reward: [(0, '52.277')] [2023-03-09 09:40:09,109][22940] Signal inference workers to stop experience collection... (32450 times) [2023-03-09 09:40:09,109][22940] Signal inference workers to resume experience collection... (32450 times) [2023-03-09 09:40:09,194][23090] InferenceWorker_p0-w0: stopping experience collection (32450 times) [2023-03-09 09:40:09,194][23090] InferenceWorker_p0-w0: resuming experience collection (32450 times) [2023-03-09 09:40:09,727][23090] Updated weights for policy 0, policy_version 97269 (0.0020) [2023-03-09 09:40:10,548][23090] Updated weights for policy 0, policy_version 97279 (0.0018) [2023-03-09 09:40:11,500][23090] Updated weights for policy 0, policy_version 97289 (0.0013) [2023-03-09 09:40:12,314][23090] Updated weights for policy 0, policy_version 97299 (0.0013) [2023-03-09 09:40:13,111][23090] Updated weights for policy 0, policy_version 97310 (0.0016) [2023-03-09 09:40:14,035][23090] Updated weights for policy 0, policy_version 97320 (0.0022) [2023-03-09 09:40:14,058][22664] Fps is (10 sec: 194973.8, 60 sec: 197427.2, 300 sec: 197219.0). Total num frames: 1594490880. Throughput: 0: 49443.6. Samples: 398591248. Policy #0 lag: (min: 0.0, avg: 16.5, max: 33.0) [2023-03-09 09:40:14,059][22664] Avg episode reward: [(0, '56.076')] [2023-03-09 09:40:14,810][23090] Updated weights for policy 0, policy_version 97330 (0.0022) [2023-03-09 09:40:15,652][23090] Updated weights for policy 0, policy_version 97340 (0.0013) [2023-03-09 09:40:16,584][23090] Updated weights for policy 0, policy_version 97350 (0.0016) [2023-03-09 09:40:17,248][23090] Updated weights for policy 0, policy_version 97360 (0.0020) [2023-03-09 09:40:18,202][23090] Updated weights for policy 0, policy_version 97370 (0.0013) [2023-03-09 09:40:19,027][23090] Updated weights for policy 0, policy_version 97380 (0.0018) [2023-03-09 09:40:19,059][22664] Fps is (10 sec: 196606.7, 60 sec: 197156.1, 300 sec: 197329.9). Total num frames: 1595473920. Throughput: 0: 49400.4. Samples: 398886080. Policy #0 lag: (min: 0.0, avg: 16.5, max: 33.0) [2023-03-09 09:40:19,059][22664] Avg episode reward: [(0, '55.716')] [2023-03-09 09:40:19,830][23090] Updated weights for policy 0, policy_version 97390 (0.0013) [2023-03-09 09:40:19,882][22940] Signal inference workers to stop experience collection... (32500 times) [2023-03-09 09:40:19,883][22940] Signal inference workers to resume experience collection... (32500 times) [2023-03-09 09:40:19,948][23090] InferenceWorker_p0-w0: stopping experience collection (32500 times) [2023-03-09 09:40:19,950][23090] InferenceWorker_p0-w0: resuming experience collection (32500 times) [2023-03-09 09:40:20,643][23090] Updated weights for policy 0, policy_version 97400 (0.0014) [2023-03-09 09:40:21,602][23090] Updated weights for policy 0, policy_version 97411 (0.0013) [2023-03-09 09:40:22,460][23090] Updated weights for policy 0, policy_version 97422 (0.0013) [2023-03-09 09:40:23,328][23090] Updated weights for policy 0, policy_version 97432 (0.0016) [2023-03-09 09:40:24,059][22664] Fps is (10 sec: 196601.6, 60 sec: 197426.1, 300 sec: 197329.9). Total num frames: 1596456960. Throughput: 0: 49313.5. Samples: 399178848. Policy #0 lag: (min: 0.0, avg: 16.5, max: 33.0) [2023-03-09 09:40:24,061][22664] Avg episode reward: [(0, '54.347')] [2023-03-09 09:40:24,330][23090] Updated weights for policy 0, policy_version 97443 (0.0016) [2023-03-09 09:40:25,079][23090] Updated weights for policy 0, policy_version 97453 (0.0013) [2023-03-09 09:40:25,857][23090] Updated weights for policy 0, policy_version 97463 (0.0016) [2023-03-09 09:40:26,779][23090] Updated weights for policy 0, policy_version 97473 (0.0017) [2023-03-09 09:40:27,589][23090] Updated weights for policy 0, policy_version 97483 (0.0013) [2023-03-09 09:40:28,324][23090] Updated weights for policy 0, policy_version 97493 (0.0013) [2023-03-09 09:40:29,059][22664] Fps is (10 sec: 199878.7, 60 sec: 197973.4, 300 sec: 197329.8). Total num frames: 1597472768. Throughput: 0: 49360.2. Samples: 399330400. Policy #0 lag: (min: 0.0, avg: 16.5, max: 33.0) [2023-03-09 09:40:29,061][22664] Avg episode reward: [(0, '55.272')] [2023-03-09 09:40:29,166][23090] Updated weights for policy 0, policy_version 97503 (0.0021) [2023-03-09 09:40:30,097][23090] Updated weights for policy 0, policy_version 97513 (0.0016) [2023-03-09 09:40:30,925][22940] Signal inference workers to stop experience collection... (32550 times) [2023-03-09 09:40:30,949][22940] Signal inference workers to resume experience collection... (32550 times) [2023-03-09 09:40:30,986][23090] InferenceWorker_p0-w0: stopping experience collection (32550 times) [2023-03-09 09:40:30,989][23090] Updated weights for policy 0, policy_version 97524 (0.0016) [2023-03-09 09:40:31,035][23090] InferenceWorker_p0-w0: resuming experience collection (32550 times) [2023-03-09 09:40:31,701][23090] Updated weights for policy 0, policy_version 97534 (0.0023) [2023-03-09 09:40:32,664][23090] Updated weights for policy 0, policy_version 97544 (0.0017) [2023-03-09 09:40:33,531][23090] Updated weights for policy 0, policy_version 97555 (0.0013) [2023-03-09 09:40:34,058][22664] Fps is (10 sec: 198252.6, 60 sec: 197701.2, 300 sec: 197330.0). Total num frames: 1598439424. Throughput: 0: 49314.2. Samples: 399625184. Policy #0 lag: (min: 0.0, avg: 16.5, max: 33.0) [2023-03-09 09:40:34,060][22664] Avg episode reward: [(0, '54.869')] [2023-03-09 09:40:34,344][23090] Updated weights for policy 0, policy_version 97565 (0.0016) [2023-03-09 09:40:35,253][23090] Updated weights for policy 0, policy_version 97575 (0.0013) [2023-03-09 09:40:35,957][23090] Updated weights for policy 0, policy_version 97585 (0.0013) [2023-03-09 09:40:36,870][23090] Updated weights for policy 0, policy_version 97595 (0.0016) [2023-03-09 09:40:37,729][23090] Updated weights for policy 0, policy_version 97605 (0.0016) [2023-03-09 09:40:38,455][23090] Updated weights for policy 0, policy_version 97615 (0.0018) [2023-03-09 09:40:39,058][22664] Fps is (10 sec: 196615.1, 60 sec: 197700.6, 300 sec: 197330.1). Total num frames: 1599438848. Throughput: 0: 49357.1. Samples: 399921952. Policy #0 lag: (min: 1.0, avg: 16.3, max: 33.0) [2023-03-09 09:40:39,059][22664] Avg episode reward: [(0, '54.736')] [2023-03-09 09:40:39,342][23090] Updated weights for policy 0, policy_version 97625 (0.0015) [2023-03-09 09:40:40,235][23090] Updated weights for policy 0, policy_version 97635 (0.0016) [2023-03-09 09:40:40,889][22940] Signal inference workers to stop experience collection... (32600 times) [2023-03-09 09:40:40,904][22940] Signal inference workers to resume experience collection... (32600 times) [2023-03-09 09:40:40,951][23090] InferenceWorker_p0-w0: stopping experience collection (32600 times) [2023-03-09 09:40:40,951][23090] InferenceWorker_p0-w0: resuming experience collection (32600 times) [2023-03-09 09:40:41,037][23090] Updated weights for policy 0, policy_version 97646 (0.0015) [2023-03-09 09:40:41,890][23090] Updated weights for policy 0, policy_version 97656 (0.0014) [2023-03-09 09:40:42,767][23090] Updated weights for policy 0, policy_version 97666 (0.0012) [2023-03-09 09:40:43,562][23090] Updated weights for policy 0, policy_version 97676 (0.0016) [2023-03-09 09:40:44,059][22664] Fps is (10 sec: 198238.2, 60 sec: 197426.6, 300 sec: 197330.3). Total num frames: 1600421888. Throughput: 0: 49313.0. Samples: 400069360. Policy #0 lag: (min: 1.0, avg: 16.3, max: 33.0) [2023-03-09 09:40:44,061][22664] Avg episode reward: [(0, '54.093')] [2023-03-09 09:40:44,386][23090] Updated weights for policy 0, policy_version 97687 (0.0013) [2023-03-09 09:40:45,307][23090] Updated weights for policy 0, policy_version 97697 (0.0013) [2023-03-09 09:40:46,142][23090] Updated weights for policy 0, policy_version 97707 (0.0016) [2023-03-09 09:40:46,849][23090] Updated weights for policy 0, policy_version 97717 (0.0013) [2023-03-09 09:40:47,800][23090] Updated weights for policy 0, policy_version 97728 (0.0023) [2023-03-09 09:40:48,696][23090] Updated weights for policy 0, policy_version 97738 (0.0017) [2023-03-09 09:40:49,058][22664] Fps is (10 sec: 199885.3, 60 sec: 197974.6, 300 sec: 197552.4). Total num frames: 1601437696. Throughput: 0: 49406.1. Samples: 400370304. Policy #0 lag: (min: 1.0, avg: 16.3, max: 33.0) [2023-03-09 09:40:49,060][22664] Avg episode reward: [(0, '55.513')] [2023-03-09 09:40:49,437][23090] Updated weights for policy 0, policy_version 97748 (0.0017) [2023-03-09 09:40:50,195][23090] Updated weights for policy 0, policy_version 97758 (0.0013) [2023-03-09 09:40:51,176][23090] Updated weights for policy 0, policy_version 97768 (0.0027) [2023-03-09 09:40:51,905][23090] Updated weights for policy 0, policy_version 97778 (0.0013) [2023-03-09 09:40:52,779][23090] Updated weights for policy 0, policy_version 97788 (0.0017) [2023-03-09 09:40:53,615][23090] Updated weights for policy 0, policy_version 97798 (0.0015) [2023-03-09 09:40:54,059][22664] Fps is (10 sec: 198249.8, 60 sec: 197700.4, 300 sec: 197496.4). Total num frames: 1602404352. Throughput: 0: 49450.7. Samples: 400667104. Policy #0 lag: (min: 1.0, avg: 16.3, max: 33.0) [2023-03-09 09:40:54,060][22664] Avg episode reward: [(0, '53.813')] [2023-03-09 09:40:54,087][22940] Signal inference workers to stop experience collection... (32650 times) [2023-03-09 09:40:54,089][22940] Signal inference workers to resume experience collection... (32650 times) [2023-03-09 09:40:54,159][23090] InferenceWorker_p0-w0: stopping experience collection (32650 times) [2023-03-09 09:40:54,201][23090] InferenceWorker_p0-w0: resuming experience collection (32650 times) [2023-03-09 09:40:54,359][23090] Updated weights for policy 0, policy_version 97808 (0.0013) [2023-03-09 09:40:55,274][23090] Updated weights for policy 0, policy_version 97818 (0.0021) [2023-03-09 09:40:56,080][23090] Updated weights for policy 0, policy_version 97828 (0.0018) [2023-03-09 09:40:56,856][23090] Updated weights for policy 0, policy_version 97838 (0.0013) [2023-03-09 09:40:57,680][23090] Updated weights for policy 0, policy_version 97848 (0.0018) [2023-03-09 09:40:58,603][23090] Updated weights for policy 0, policy_version 97858 (0.0020) [2023-03-09 09:40:59,059][22664] Fps is (10 sec: 194957.2, 60 sec: 197425.2, 300 sec: 197440.7). Total num frames: 1603387392. Throughput: 0: 49450.7. Samples: 400816560. Policy #0 lag: (min: 1.0, avg: 16.3, max: 33.0) [2023-03-09 09:40:59,061][22664] Avg episode reward: [(0, '54.312')] [2023-03-09 09:40:59,419][23090] Updated weights for policy 0, policy_version 97868 (0.0013) [2023-03-09 09:41:00,140][23090] Updated weights for policy 0, policy_version 97878 (0.0013) [2023-03-09 09:41:00,990][23090] Updated weights for policy 0, policy_version 97888 (0.0019) [2023-03-09 09:41:01,961][23090] Updated weights for policy 0, policy_version 97899 (0.0013) [2023-03-09 09:41:02,682][23090] Updated weights for policy 0, policy_version 97909 (0.0016) [2023-03-09 09:41:03,500][23090] Updated weights for policy 0, policy_version 97919 (0.0014) [2023-03-09 09:41:04,059][22664] Fps is (10 sec: 198245.6, 60 sec: 197426.9, 300 sec: 197496.4). Total num frames: 1604386816. Throughput: 0: 49496.6. Samples: 401113440. Policy #0 lag: (min: 1.0, avg: 16.3, max: 33.0) [2023-03-09 09:41:04,061][22664] Avg episode reward: [(0, '55.990')] [2023-03-09 09:41:04,423][23090] Updated weights for policy 0, policy_version 97929 (0.0013) [2023-03-09 09:41:05,212][23090] Updated weights for policy 0, policy_version 97939 (0.0016) [2023-03-09 09:41:06,001][23090] Updated weights for policy 0, policy_version 97950 (0.0027) [2023-03-09 09:41:07,001][23090] Updated weights for policy 0, policy_version 97960 (0.0025) [2023-03-09 09:41:07,180][22940] Signal inference workers to stop experience collection... (32700 times) [2023-03-09 09:41:07,185][22940] Signal inference workers to resume experience collection... (32700 times) [2023-03-09 09:41:07,251][23090] InferenceWorker_p0-w0: stopping experience collection (32700 times) [2023-03-09 09:41:07,251][23090] InferenceWorker_p0-w0: resuming experience collection (32700 times) [2023-03-09 09:41:07,699][23090] Updated weights for policy 0, policy_version 97970 (0.0017) [2023-03-09 09:41:08,615][23090] Updated weights for policy 0, policy_version 97980 (0.0020) [2023-03-09 09:41:09,059][22664] Fps is (10 sec: 199887.4, 60 sec: 197971.7, 300 sec: 197441.0). Total num frames: 1605386240. Throughput: 0: 49631.8. Samples: 401412288. Policy #0 lag: (min: 1.0, avg: 16.3, max: 33.0) [2023-03-09 09:41:09,061][22664] Avg episode reward: [(0, '55.416')] [2023-03-09 09:41:09,473][23090] Updated weights for policy 0, policy_version 97990 (0.0018) [2023-03-09 09:41:10,192][23090] Updated weights for policy 0, policy_version 98000 (0.0019) [2023-03-09 09:41:11,123][23090] Updated weights for policy 0, policy_version 98010 (0.0017) [2023-03-09 09:41:11,952][23090] Updated weights for policy 0, policy_version 98020 (0.0020) [2023-03-09 09:41:12,748][23090] Updated weights for policy 0, policy_version 98030 (0.0015) [2023-03-09 09:41:13,529][23090] Updated weights for policy 0, policy_version 98040 (0.0022) [2023-03-09 09:41:14,059][22664] Fps is (10 sec: 201527.5, 60 sec: 198519.2, 300 sec: 197552.3). Total num frames: 1606402048. Throughput: 0: 49583.3. Samples: 401561632. Policy #0 lag: (min: 1.0, avg: 16.3, max: 33.0) [2023-03-09 09:41:14,060][22664] Avg episode reward: [(0, '54.542')] [2023-03-09 09:41:14,470][23090] Updated weights for policy 0, policy_version 98050 (0.0013) [2023-03-09 09:41:15,262][23090] Updated weights for policy 0, policy_version 98060 (0.0013) [2023-03-09 09:41:15,986][23090] Updated weights for policy 0, policy_version 98070 (0.0016) [2023-03-09 09:41:16,855][23090] Updated weights for policy 0, policy_version 98080 (0.0014) [2023-03-09 09:41:17,786][23090] Updated weights for policy 0, policy_version 98090 (0.0018) [2023-03-09 09:41:18,481][23090] Updated weights for policy 0, policy_version 98100 (0.0013) [2023-03-09 09:41:19,059][22664] Fps is (10 sec: 198249.6, 60 sec: 198245.5, 300 sec: 197496.4). Total num frames: 1607368704. Throughput: 0: 49582.9. Samples: 401856432. Policy #0 lag: (min: 1.0, avg: 16.3, max: 33.0) [2023-03-09 09:41:19,061][22664] Avg episode reward: [(0, '58.519')] [2023-03-09 09:41:19,125][22940] Saving /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000098107_1607385088.pth... [2023-03-09 09:41:19,195][22940] Removing /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000095213_1559969792.pth [2023-03-09 09:41:19,199][22940] Saving new best policy, reward=58.519! [2023-03-09 09:41:19,449][23090] Updated weights for policy 0, policy_version 98110 (0.0013) [2023-03-09 09:41:20,250][23090] Updated weights for policy 0, policy_version 98120 (0.0016) [2023-03-09 09:41:20,957][23090] Updated weights for policy 0, policy_version 98130 (0.0016) [2023-03-09 09:41:21,721][22940] Signal inference workers to stop experience collection... (32750 times) [2023-03-09 09:41:21,723][22940] Signal inference workers to resume experience collection... (32750 times) [2023-03-09 09:41:21,791][23090] InferenceWorker_p0-w0: stopping experience collection (32750 times) [2023-03-09 09:41:21,791][23090] InferenceWorker_p0-w0: resuming experience collection (32750 times) [2023-03-09 09:41:21,870][23090] Updated weights for policy 0, policy_version 98140 (0.0013) [2023-03-09 09:41:22,763][23090] Updated weights for policy 0, policy_version 98150 (0.0016) [2023-03-09 09:41:23,538][23090] Updated weights for policy 0, policy_version 98160 (0.0016) [2023-03-09 09:41:24,058][22664] Fps is (10 sec: 194970.9, 60 sec: 198247.4, 300 sec: 197496.8). Total num frames: 1608351744. Throughput: 0: 49538.5. Samples: 402151184. Policy #0 lag: (min: 1.0, avg: 16.3, max: 33.0) [2023-03-09 09:41:24,059][22664] Avg episode reward: [(0, '53.332')] [2023-03-09 09:41:24,447][23090] Updated weights for policy 0, policy_version 98170 (0.0018) [2023-03-09 09:41:25,265][23090] Updated weights for policy 0, policy_version 98180 (0.0016) [2023-03-09 09:41:26,061][23090] Updated weights for policy 0, policy_version 98190 (0.0014) [2023-03-09 09:41:26,983][23090] Updated weights for policy 0, policy_version 98201 (0.0013) [2023-03-09 09:41:27,873][23090] Updated weights for policy 0, policy_version 98211 (0.0017) [2023-03-09 09:41:28,642][23090] Updated weights for policy 0, policy_version 98221 (0.0017) [2023-03-09 09:41:29,059][22664] Fps is (10 sec: 196607.0, 60 sec: 197700.2, 300 sec: 197440.9). Total num frames: 1609334784. Throughput: 0: 49537.8. Samples: 402298560. Policy #0 lag: (min: 1.0, avg: 16.3, max: 33.0) [2023-03-09 09:41:29,061][22664] Avg episode reward: [(0, '55.548')] [2023-03-09 09:41:29,396][23090] Updated weights for policy 0, policy_version 98231 (0.0019) [2023-03-09 09:41:30,461][23090] Updated weights for policy 0, policy_version 98242 (0.0013) [2023-03-09 09:41:31,255][23090] Updated weights for policy 0, policy_version 98252 (0.0016) [2023-03-09 09:41:32,063][23090] Updated weights for policy 0, policy_version 98263 (0.0019) [2023-03-09 09:41:33,003][23090] Updated weights for policy 0, policy_version 98273 (0.0014) [2023-03-09 09:41:33,827][23090] Updated weights for policy 0, policy_version 98283 (0.0016) [2023-03-09 09:41:33,885][22940] Signal inference workers to stop experience collection... (32800 times) [2023-03-09 09:41:33,900][22940] Signal inference workers to resume experience collection... (32800 times) [2023-03-09 09:41:33,983][23090] InferenceWorker_p0-w0: stopping experience collection (32800 times) [2023-03-09 09:41:33,984][23090] InferenceWorker_p0-w0: resuming experience collection (32800 times) [2023-03-09 09:41:34,059][22664] Fps is (10 sec: 196607.1, 60 sec: 197973.2, 300 sec: 197496.8). Total num frames: 1610317824. Throughput: 0: 49446.3. Samples: 402595392. Policy #0 lag: (min: 2.0, avg: 17.3, max: 34.0) [2023-03-09 09:41:34,060][22664] Avg episode reward: [(0, '54.798')] [2023-03-09 09:41:34,641][23090] Updated weights for policy 0, policy_version 98294 (0.0018) [2023-03-09 09:41:35,648][23090] Updated weights for policy 0, policy_version 98305 (0.0015) [2023-03-09 09:41:36,514][23090] Updated weights for policy 0, policy_version 98315 (0.0013) [2023-03-09 09:41:37,246][23090] Updated weights for policy 0, policy_version 98325 (0.0016) [2023-03-09 09:41:38,151][23090] Updated weights for policy 0, policy_version 98336 (0.0013) [2023-03-09 09:41:39,027][23090] Updated weights for policy 0, policy_version 98346 (0.0014) [2023-03-09 09:41:39,058][22664] Fps is (10 sec: 196615.2, 60 sec: 197700.3, 300 sec: 197552.2). Total num frames: 1611300864. Throughput: 0: 49491.8. Samples: 402894224. Policy #0 lag: (min: 2.0, avg: 17.3, max: 34.0) [2023-03-09 09:41:39,073][22664] Avg episode reward: [(0, '55.124')] [2023-03-09 09:41:39,747][23090] Updated weights for policy 0, policy_version 98356 (0.0016) [2023-03-09 09:41:40,520][23090] Updated weights for policy 0, policy_version 98366 (0.0019) [2023-03-09 09:41:41,512][23090] Updated weights for policy 0, policy_version 98376 (0.0018) [2023-03-09 09:41:42,184][23090] Updated weights for policy 0, policy_version 98386 (0.0017) [2023-03-09 09:41:43,072][23090] Updated weights for policy 0, policy_version 98396 (0.0016) [2023-03-09 09:41:43,966][23090] Updated weights for policy 0, policy_version 98406 (0.0015) [2023-03-09 09:41:44,059][22664] Fps is (10 sec: 196608.3, 60 sec: 197701.5, 300 sec: 197441.2). Total num frames: 1612283904. Throughput: 0: 49447.0. Samples: 403041648. Policy #0 lag: (min: 2.0, avg: 17.3, max: 34.0) [2023-03-09 09:41:44,060][22664] Avg episode reward: [(0, '54.718')] [2023-03-09 09:41:44,714][23090] Updated weights for policy 0, policy_version 98416 (0.0016) [2023-03-09 09:41:45,659][23090] Updated weights for policy 0, policy_version 98426 (0.0016) [2023-03-09 09:41:46,319][22940] Signal inference workers to stop experience collection... (32850 times) [2023-03-09 09:41:46,320][22940] Signal inference workers to resume experience collection... (32850 times) [2023-03-09 09:41:46,387][23090] InferenceWorker_p0-w0: stopping experience collection (32850 times) [2023-03-09 09:41:46,387][23090] InferenceWorker_p0-w0: resuming experience collection (32850 times) [2023-03-09 09:41:46,435][23090] Updated weights for policy 0, policy_version 98436 (0.0021) [2023-03-09 09:41:47,222][23090] Updated weights for policy 0, policy_version 98446 (0.0015) [2023-03-09 09:41:48,052][23090] Updated weights for policy 0, policy_version 98456 (0.0016) [2023-03-09 09:41:48,981][23090] Updated weights for policy 0, policy_version 98466 (0.0015) [2023-03-09 09:41:49,059][22664] Fps is (10 sec: 198241.8, 60 sec: 197426.3, 300 sec: 197496.6). Total num frames: 1613283328. Throughput: 0: 49445.0. Samples: 403338464. Policy #0 lag: (min: 2.0, avg: 17.3, max: 34.0) [2023-03-09 09:41:49,061][22664] Avg episode reward: [(0, '53.177')] [2023-03-09 09:41:49,757][23090] Updated weights for policy 0, policy_version 98476 (0.0025) [2023-03-09 09:41:50,493][23090] Updated weights for policy 0, policy_version 98486 (0.0016) [2023-03-09 09:41:51,372][23090] Updated weights for policy 0, policy_version 98496 (0.0013) [2023-03-09 09:41:52,268][23090] Updated weights for policy 0, policy_version 98506 (0.0020) [2023-03-09 09:41:52,960][23090] Updated weights for policy 0, policy_version 98516 (0.0016) [2023-03-09 09:41:53,807][23090] Updated weights for policy 0, policy_version 98526 (0.0016) [2023-03-09 09:41:54,059][22664] Fps is (10 sec: 199879.6, 60 sec: 197973.2, 300 sec: 197496.5). Total num frames: 1614282752. Throughput: 0: 49399.3. Samples: 403635248. Policy #0 lag: (min: 2.0, avg: 17.3, max: 34.0) [2023-03-09 09:41:54,061][22664] Avg episode reward: [(0, '55.801')] [2023-03-09 09:41:54,742][23090] Updated weights for policy 0, policy_version 98536 (0.0013) [2023-03-09 09:41:55,547][23090] Updated weights for policy 0, policy_version 98547 (0.0018) [2023-03-09 09:41:56,404][23090] Updated weights for policy 0, policy_version 98557 (0.0013) [2023-03-09 09:41:57,356][23090] Updated weights for policy 0, policy_version 98567 (0.0016) [2023-03-09 09:41:58,038][22940] Signal inference workers to stop experience collection... (32900 times) [2023-03-09 09:41:58,038][22940] Signal inference workers to resume experience collection... (32900 times) [2023-03-09 09:41:58,057][23090] Updated weights for policy 0, policy_version 98577 (0.0016) [2023-03-09 09:41:58,093][23090] InferenceWorker_p0-w0: stopping experience collection (32900 times) [2023-03-09 09:41:58,093][23090] InferenceWorker_p0-w0: resuming experience collection (32900 times) [2023-03-09 09:41:58,931][23090] Updated weights for policy 0, policy_version 98587 (0.0013) [2023-03-09 09:41:59,059][22664] Fps is (10 sec: 199873.8, 60 sec: 198245.8, 300 sec: 197551.6). Total num frames: 1615282176. Throughput: 0: 49399.7. Samples: 403784656. Policy #0 lag: (min: 2.0, avg: 17.3, max: 34.0) [2023-03-09 09:41:59,061][22664] Avg episode reward: [(0, '49.541')] [2023-03-09 09:41:59,864][23090] Updated weights for policy 0, policy_version 98598 (0.0021) [2023-03-09 09:42:00,605][23090] Updated weights for policy 0, policy_version 98608 (0.0013) [2023-03-09 09:42:01,513][23090] Updated weights for policy 0, policy_version 98618 (0.0016) [2023-03-09 09:42:02,361][23090] Updated weights for policy 0, policy_version 98628 (0.0022) [2023-03-09 09:42:03,145][23090] Updated weights for policy 0, policy_version 98638 (0.0016) [2023-03-09 09:42:03,991][23090] Updated weights for policy 0, policy_version 98648 (0.0013) [2023-03-09 09:42:04,058][22664] Fps is (10 sec: 196614.4, 60 sec: 197701.3, 300 sec: 197441.1). Total num frames: 1616248832. Throughput: 0: 49400.2. Samples: 404079424. Policy #0 lag: (min: 2.0, avg: 17.3, max: 34.0) [2023-03-09 09:42:04,059][22664] Avg episode reward: [(0, '55.109')] [2023-03-09 09:42:04,883][23090] Updated weights for policy 0, policy_version 98658 (0.0013) [2023-03-09 09:42:05,730][23090] Updated weights for policy 0, policy_version 98668 (0.0021) [2023-03-09 09:42:06,439][23090] Updated weights for policy 0, policy_version 98678 (0.0024) [2023-03-09 09:42:07,288][23090] Updated weights for policy 0, policy_version 98688 (0.0016) [2023-03-09 09:42:08,208][23090] Updated weights for policy 0, policy_version 98698 (0.0021) [2023-03-09 09:42:08,923][23090] Updated weights for policy 0, policy_version 98708 (0.0018) [2023-03-09 09:42:09,059][22664] Fps is (10 sec: 196617.6, 60 sec: 197700.9, 300 sec: 197552.1). Total num frames: 1617248256. Throughput: 0: 49400.6. Samples: 404374224. Policy #0 lag: (min: 2.0, avg: 17.3, max: 34.0) [2023-03-09 09:42:09,061][22664] Avg episode reward: [(0, '54.455')] [2023-03-09 09:42:09,723][23090] Updated weights for policy 0, policy_version 98718 (0.0018) [2023-03-09 09:42:10,683][23090] Updated weights for policy 0, policy_version 98728 (0.0016) [2023-03-09 09:42:10,948][22940] Signal inference workers to stop experience collection... (32950 times) [2023-03-09 09:42:10,970][22940] Signal inference workers to resume experience collection... (32950 times) [2023-03-09 09:42:11,042][23090] InferenceWorker_p0-w0: stopping experience collection (32950 times) [2023-03-09 09:42:11,042][23090] InferenceWorker_p0-w0: resuming experience collection (32950 times) [2023-03-09 09:42:11,421][23090] Updated weights for policy 0, policy_version 98738 (0.0013) [2023-03-09 09:42:12,286][23090] Updated weights for policy 0, policy_version 98748 (0.0013) [2023-03-09 09:42:13,233][23090] Updated weights for policy 0, policy_version 98758 (0.0019) [2023-03-09 09:42:13,893][23090] Updated weights for policy 0, policy_version 98768 (0.0013) [2023-03-09 09:42:14,059][22664] Fps is (10 sec: 199871.8, 60 sec: 197425.4, 300 sec: 197607.8). Total num frames: 1618247680. Throughput: 0: 49446.8. Samples: 404523680. Policy #0 lag: (min: 2.0, avg: 17.3, max: 34.0) [2023-03-09 09:42:14,061][22664] Avg episode reward: [(0, '55.972')] [2023-03-09 09:42:14,857][23090] Updated weights for policy 0, policy_version 98778 (0.0013) [2023-03-09 09:42:15,674][23090] Updated weights for policy 0, policy_version 98788 (0.0013) [2023-03-09 09:42:16,463][23090] Updated weights for policy 0, policy_version 98798 (0.0013) [2023-03-09 09:42:17,232][23090] Updated weights for policy 0, policy_version 98808 (0.0015) [2023-03-09 09:42:18,160][23090] Updated weights for policy 0, policy_version 98818 (0.0015) [2023-03-09 09:42:18,895][23090] Updated weights for policy 0, policy_version 98828 (0.0015) [2023-03-09 09:42:19,059][22664] Fps is (10 sec: 198251.7, 60 sec: 197701.2, 300 sec: 197607.9). Total num frames: 1619230720. Throughput: 0: 49446.1. Samples: 404820464. Policy #0 lag: (min: 2.0, avg: 17.3, max: 34.0) [2023-03-09 09:42:19,060][22664] Avg episode reward: [(0, '55.245')] [2023-03-09 09:42:19,642][23090] Updated weights for policy 0, policy_version 98838 (0.0013) [2023-03-09 09:42:20,526][23090] Updated weights for policy 0, policy_version 98848 (0.0015) [2023-03-09 09:42:21,414][23090] Updated weights for policy 0, policy_version 98858 (0.0022) [2023-03-09 09:42:22,136][23090] Updated weights for policy 0, policy_version 98868 (0.0013) [2023-03-09 09:42:22,717][22940] Signal inference workers to stop experience collection... (33000 times) [2023-03-09 09:42:22,719][22940] Signal inference workers to resume experience collection... (33000 times) [2023-03-09 09:42:22,787][23090] InferenceWorker_p0-w0: stopping experience collection (33000 times) [2023-03-09 09:42:22,787][23090] InferenceWorker_p0-w0: resuming experience collection (33000 times) [2023-03-09 09:42:22,947][23090] Updated weights for policy 0, policy_version 98878 (0.0014) [2023-03-09 09:42:23,986][23090] Updated weights for policy 0, policy_version 98889 (0.0013) [2023-03-09 09:42:24,058][22664] Fps is (10 sec: 194982.3, 60 sec: 197427.3, 300 sec: 197552.2). Total num frames: 1620197376. Throughput: 0: 49446.4. Samples: 405119312. Policy #0 lag: (min: 2.0, avg: 17.3, max: 34.0) [2023-03-09 09:42:24,059][22664] Avg episode reward: [(0, '52.646')] [2023-03-09 09:42:24,684][23090] Updated weights for policy 0, policy_version 98899 (0.0020) [2023-03-09 09:42:25,542][23090] Updated weights for policy 0, policy_version 98909 (0.0020) [2023-03-09 09:42:26,447][23090] Updated weights for policy 0, policy_version 98919 (0.0013) [2023-03-09 09:42:27,134][23090] Updated weights for policy 0, policy_version 98929 (0.0013) [2023-03-09 09:42:28,070][23090] Updated weights for policy 0, policy_version 98939 (0.0013) [2023-03-09 09:42:28,909][23090] Updated weights for policy 0, policy_version 98949 (0.0019) [2023-03-09 09:42:29,059][22664] Fps is (10 sec: 196607.4, 60 sec: 197701.3, 300 sec: 197552.1). Total num frames: 1621196800. Throughput: 0: 49490.1. Samples: 405268704. Policy #0 lag: (min: 2.0, avg: 17.3, max: 34.0) [2023-03-09 09:42:29,059][22664] Avg episode reward: [(0, '56.449')] [2023-03-09 09:42:29,654][23090] Updated weights for policy 0, policy_version 98959 (0.0022) [2023-03-09 09:42:30,529][23090] Updated weights for policy 0, policy_version 98969 (0.0013) [2023-03-09 09:42:31,411][23090] Updated weights for policy 0, policy_version 98979 (0.0013) [2023-03-09 09:42:32,189][23090] Updated weights for policy 0, policy_version 98989 (0.0018) [2023-03-09 09:42:32,920][23090] Updated weights for policy 0, policy_version 98999 (0.0016) [2023-03-09 09:42:33,371][22940] Signal inference workers to stop experience collection... (33050 times) [2023-03-09 09:42:33,390][22940] Signal inference workers to resume experience collection... (33050 times) [2023-03-09 09:42:33,426][23090] InferenceWorker_p0-w0: stopping experience collection (33050 times) [2023-03-09 09:42:33,493][23090] InferenceWorker_p0-w0: resuming experience collection (33050 times) [2023-03-09 09:42:34,035][23090] Updated weights for policy 0, policy_version 99010 (0.0013) [2023-03-09 09:42:34,058][22664] Fps is (10 sec: 199884.1, 60 sec: 197973.5, 300 sec: 197552.2). Total num frames: 1622196224. Throughput: 0: 49489.3. Samples: 405565472. Policy #0 lag: (min: 2.0, avg: 18.3, max: 34.0) [2023-03-09 09:42:34,060][22664] Avg episode reward: [(0, '50.723')] [2023-03-09 09:42:34,774][23090] Updated weights for policy 0, policy_version 99020 (0.0016) [2023-03-09 09:42:35,569][23090] Updated weights for policy 0, policy_version 99031 (0.0019) [2023-03-09 09:42:36,439][23090] Updated weights for policy 0, policy_version 99041 (0.0021) [2023-03-09 09:42:37,361][23090] Updated weights for policy 0, policy_version 99051 (0.0021) [2023-03-09 09:42:38,020][23090] Updated weights for policy 0, policy_version 99061 (0.0014) [2023-03-09 09:42:38,907][23090] Updated weights for policy 0, policy_version 99071 (0.0019) [2023-03-09 09:42:39,058][22664] Fps is (10 sec: 199885.9, 60 sec: 198246.4, 300 sec: 197608.0). Total num frames: 1623195648. Throughput: 0: 49533.8. Samples: 405864256. Policy #0 lag: (min: 2.0, avg: 18.3, max: 34.0) [2023-03-09 09:42:39,059][22664] Avg episode reward: [(0, '54.387')] [2023-03-09 09:42:39,813][23090] Updated weights for policy 0, policy_version 99081 (0.0016) [2023-03-09 09:42:40,538][23090] Updated weights for policy 0, policy_version 99091 (0.0013) [2023-03-09 09:42:41,313][23090] Updated weights for policy 0, policy_version 99101 (0.0018) [2023-03-09 09:42:42,387][23090] Updated weights for policy 0, policy_version 99112 (0.0022) [2023-03-09 09:42:43,112][23090] Updated weights for policy 0, policy_version 99122 (0.0013) [2023-03-09 09:42:43,792][22940] Signal inference workers to stop experience collection... (33100 times) [2023-03-09 09:42:43,807][22940] Signal inference workers to resume experience collection... (33100 times) [2023-03-09 09:42:43,878][23090] InferenceWorker_p0-w0: stopping experience collection (33100 times) [2023-03-09 09:42:43,878][23090] InferenceWorker_p0-w0: resuming experience collection (33100 times) [2023-03-09 09:42:43,968][23090] Updated weights for policy 0, policy_version 99132 (0.0019) [2023-03-09 09:42:44,059][22664] Fps is (10 sec: 201521.0, 60 sec: 198792.3, 300 sec: 197718.7). Total num frames: 1624211456. Throughput: 0: 49535.0. Samples: 406013696. Policy #0 lag: (min: 2.0, avg: 18.3, max: 34.0) [2023-03-09 09:42:44,060][22664] Avg episode reward: [(0, '54.155')] [2023-03-09 09:42:44,976][23090] Updated weights for policy 0, policy_version 99143 (0.0012) [2023-03-09 09:42:45,678][23090] Updated weights for policy 0, policy_version 99153 (0.0016) [2023-03-09 09:42:46,528][23090] Updated weights for policy 0, policy_version 99163 (0.0018) [2023-03-09 09:42:47,395][23090] Updated weights for policy 0, policy_version 99173 (0.0014) [2023-03-09 09:42:48,139][23090] Updated weights for policy 0, policy_version 99183 (0.0021) [2023-03-09 09:42:49,008][23090] Updated weights for policy 0, policy_version 99193 (0.0013) [2023-03-09 09:42:49,059][22664] Fps is (10 sec: 198240.1, 60 sec: 198246.1, 300 sec: 197607.7). Total num frames: 1625178112. Throughput: 0: 49580.4. Samples: 406310560. Policy #0 lag: (min: 2.0, avg: 18.3, max: 34.0) [2023-03-09 09:42:49,061][22664] Avg episode reward: [(0, '51.502')] [2023-03-09 09:42:49,944][23090] Updated weights for policy 0, policy_version 99204 (0.0017) [2023-03-09 09:42:50,753][23090] Updated weights for policy 0, policy_version 99215 (0.0013) [2023-03-09 09:42:51,621][23090] Updated weights for policy 0, policy_version 99225 (0.0022) [2023-03-09 09:42:52,506][23090] Updated weights for policy 0, policy_version 99235 (0.0013) [2023-03-09 09:42:53,306][23090] Updated weights for policy 0, policy_version 99245 (0.0016) [2023-03-09 09:42:54,008][23090] Updated weights for policy 0, policy_version 99255 (0.0018) [2023-03-09 09:42:54,059][22664] Fps is (10 sec: 198238.4, 60 sec: 198518.7, 300 sec: 197718.8). Total num frames: 1626193920. Throughput: 0: 49668.7. Samples: 406609328. Policy #0 lag: (min: 2.0, avg: 18.3, max: 34.0) [2023-03-09 09:42:54,060][22664] Avg episode reward: [(0, '53.408')] [2023-03-09 09:42:54,462][22940] Signal inference workers to stop experience collection... (33150 times) [2023-03-09 09:42:54,486][22940] Signal inference workers to resume experience collection... (33150 times) [2023-03-09 09:42:54,530][23090] InferenceWorker_p0-w0: stopping experience collection (33150 times) [2023-03-09 09:42:54,531][23090] InferenceWorker_p0-w0: resuming experience collection (33150 times) [2023-03-09 09:42:54,959][23090] Updated weights for policy 0, policy_version 99265 (0.0019) [2023-03-09 09:42:55,815][23090] Updated weights for policy 0, policy_version 99275 (0.0013) [2023-03-09 09:42:56,482][23090] Updated weights for policy 0, policy_version 99285 (0.0019) [2023-03-09 09:42:57,364][23090] Updated weights for policy 0, policy_version 99295 (0.0016) [2023-03-09 09:42:58,437][23090] Updated weights for policy 0, policy_version 99306 (0.0013) [2023-03-09 09:42:59,059][22664] Fps is (10 sec: 199884.2, 60 sec: 198247.8, 300 sec: 197774.3). Total num frames: 1627176960. Throughput: 0: 49668.9. Samples: 406758768. Policy #0 lag: (min: 2.0, avg: 18.3, max: 34.0) [2023-03-09 09:42:59,061][22664] Avg episode reward: [(0, '54.865')] [2023-03-09 09:42:59,095][23090] Updated weights for policy 0, policy_version 99316 (0.0016) [2023-03-09 09:43:00,167][23090] Updated weights for policy 0, policy_version 99327 (0.0016) [2023-03-09 09:43:01,087][23090] Updated weights for policy 0, policy_version 99337 (0.0018) [2023-03-09 09:43:01,770][23090] Updated weights for policy 0, policy_version 99347 (0.0013) [2023-03-09 09:43:02,585][23090] Updated weights for policy 0, policy_version 99357 (0.0019) [2023-03-09 09:43:03,546][23090] Updated weights for policy 0, policy_version 99367 (0.0017) [2023-03-09 09:43:04,059][22664] Fps is (10 sec: 194973.2, 60 sec: 198245.2, 300 sec: 197718.5). Total num frames: 1628143616. Throughput: 0: 49563.7. Samples: 407050848. Policy #0 lag: (min: 2.0, avg: 18.3, max: 34.0) [2023-03-09 09:43:04,106][22664] Avg episode reward: [(0, '55.027')] [2023-03-09 09:43:04,291][23090] Updated weights for policy 0, policy_version 99377 (0.0013) [2023-03-09 09:43:05,180][23090] Updated weights for policy 0, policy_version 99387 (0.0017) [2023-03-09 09:43:06,030][23090] Updated weights for policy 0, policy_version 99397 (0.0016) [2023-03-09 09:43:06,473][22940] Signal inference workers to stop experience collection... (33200 times) [2023-03-09 09:43:06,496][22940] Signal inference workers to resume experience collection... (33200 times) [2023-03-09 09:43:06,542][23090] InferenceWorker_p0-w0: stopping experience collection (33200 times) [2023-03-09 09:43:06,543][23090] InferenceWorker_p0-w0: resuming experience collection (33200 times) [2023-03-09 09:43:06,806][23090] Updated weights for policy 0, policy_version 99407 (0.0017) [2023-03-09 09:43:07,662][23090] Updated weights for policy 0, policy_version 99417 (0.0013) [2023-03-09 09:43:08,613][23090] Updated weights for policy 0, policy_version 99428 (0.0019) [2023-03-09 09:43:09,059][22664] Fps is (10 sec: 191695.0, 60 sec: 197427.4, 300 sec: 197552.1). Total num frames: 1629093888. Throughput: 0: 49474.6. Samples: 407345680. Policy #0 lag: (min: 2.0, avg: 18.3, max: 34.0) [2023-03-09 09:43:09,106][22664] Avg episode reward: [(0, '53.886')] [2023-03-09 09:43:09,359][23090] Updated weights for policy 0, policy_version 99438 (0.0020) [2023-03-09 09:43:10,202][23090] Updated weights for policy 0, policy_version 99448 (0.0017) [2023-03-09 09:43:11,089][23090] Updated weights for policy 0, policy_version 99458 (0.0016) [2023-03-09 09:43:11,909][23090] Updated weights for policy 0, policy_version 99468 (0.0024) [2023-03-09 09:43:12,654][23090] Updated weights for policy 0, policy_version 99478 (0.0013) [2023-03-09 09:43:13,474][23090] Updated weights for policy 0, policy_version 99488 (0.0016) [2023-03-09 09:43:14,058][22664] Fps is (10 sec: 194976.7, 60 sec: 197429.3, 300 sec: 197607.7). Total num frames: 1630093312. Throughput: 0: 49477.1. Samples: 407495168. Policy #0 lag: (min: 2.0, avg: 18.3, max: 34.0) [2023-03-09 09:43:14,060][22664] Avg episode reward: [(0, '53.605')] [2023-03-09 09:43:14,538][23090] Updated weights for policy 0, policy_version 99499 (0.0013) [2023-03-09 09:43:15,236][23090] Updated weights for policy 0, policy_version 99509 (0.0016) [2023-03-09 09:43:16,004][23090] Updated weights for policy 0, policy_version 99519 (0.0013) [2023-03-09 09:43:16,991][23090] Updated weights for policy 0, policy_version 99529 (0.0019) [2023-03-09 09:43:17,001][22940] Signal inference workers to stop experience collection... (33250 times) [2023-03-09 09:43:17,003][22940] Signal inference workers to resume experience collection... (33250 times) [2023-03-09 09:43:17,074][23090] InferenceWorker_p0-w0: stopping experience collection (33250 times) [2023-03-09 09:43:17,076][23090] InferenceWorker_p0-w0: resuming experience collection (33250 times) [2023-03-09 09:43:17,753][23090] Updated weights for policy 0, policy_version 99540 (0.0014) [2023-03-09 09:43:18,563][23090] Updated weights for policy 0, policy_version 99550 (0.0020) [2023-03-09 09:43:19,059][22664] Fps is (10 sec: 199885.5, 60 sec: 197699.7, 300 sec: 197552.3). Total num frames: 1631092736. Throughput: 0: 49476.8. Samples: 407791936. Policy #0 lag: (min: 2.0, avg: 18.3, max: 34.0) [2023-03-09 09:43:19,060][22664] Avg episode reward: [(0, '52.301')] [2023-03-09 09:43:19,108][22940] Saving /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000099555_1631109120.pth... [2023-03-09 09:43:19,162][22940] Removing /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000096658_1583644672.pth [2023-03-09 09:43:19,495][23090] Updated weights for policy 0, policy_version 99560 (0.0018) [2023-03-09 09:43:20,302][23090] Updated weights for policy 0, policy_version 99571 (0.0013) [2023-03-09 09:43:21,146][23090] Updated weights for policy 0, policy_version 99581 (0.0013) [2023-03-09 09:43:22,091][23090] Updated weights for policy 0, policy_version 99591 (0.0013) [2023-03-09 09:43:22,855][23090] Updated weights for policy 0, policy_version 99602 (0.0022) [2023-03-09 09:43:23,726][23090] Updated weights for policy 0, policy_version 99612 (0.0016) [2023-03-09 09:43:24,058][22664] Fps is (10 sec: 201523.1, 60 sec: 198519.4, 300 sec: 197718.8). Total num frames: 1632108544. Throughput: 0: 49432.9. Samples: 408088736. Policy #0 lag: (min: 2.0, avg: 18.3, max: 34.0) [2023-03-09 09:43:24,059][22664] Avg episode reward: [(0, '52.168')] [2023-03-09 09:43:24,679][23090] Updated weights for policy 0, policy_version 99622 (0.0018) [2023-03-09 09:43:25,452][23090] Updated weights for policy 0, policy_version 99633 (0.0021) [2023-03-09 09:43:26,336][23090] Updated weights for policy 0, policy_version 99643 (0.0017) [2023-03-09 09:43:27,207][23090] Updated weights for policy 0, policy_version 99653 (0.0023) [2023-03-09 09:43:27,742][22940] Signal inference workers to stop experience collection... (33300 times) [2023-03-09 09:43:27,755][22940] Signal inference workers to resume experience collection... (33300 times) [2023-03-09 09:43:27,826][23090] InferenceWorker_p0-w0: stopping experience collection (33300 times) [2023-03-09 09:43:27,826][23090] InferenceWorker_p0-w0: resuming experience collection (33300 times) [2023-03-09 09:43:27,951][23090] Updated weights for policy 0, policy_version 99663 (0.0023) [2023-03-09 09:43:28,961][23090] Updated weights for policy 0, policy_version 99674 (0.0023) [2023-03-09 09:43:29,059][22664] Fps is (10 sec: 199874.8, 60 sec: 198244.3, 300 sec: 197662.8). Total num frames: 1633091584. Throughput: 0: 49388.2. Samples: 408236192. Policy #0 lag: (min: 2.0, avg: 18.3, max: 34.0) [2023-03-09 09:43:29,061][22664] Avg episode reward: [(0, '53.474')] [2023-03-09 09:43:29,780][23090] Updated weights for policy 0, policy_version 99684 (0.0013) [2023-03-09 09:43:30,619][23090] Updated weights for policy 0, policy_version 99695 (0.0020) [2023-03-09 09:43:31,432][23090] Updated weights for policy 0, policy_version 99705 (0.0016) [2023-03-09 09:43:32,310][23090] Updated weights for policy 0, policy_version 99715 (0.0013) [2023-03-09 09:43:33,148][23090] Updated weights for policy 0, policy_version 99725 (0.0022) [2023-03-09 09:43:33,985][23090] Updated weights for policy 0, policy_version 99736 (0.0013) [2023-03-09 09:43:34,059][22664] Fps is (10 sec: 196606.3, 60 sec: 197973.1, 300 sec: 197663.5). Total num frames: 1634074624. Throughput: 0: 49434.2. Samples: 408535088. Policy #0 lag: (min: 1.0, avg: 17.4, max: 33.0) [2023-03-09 09:43:34,059][22664] Avg episode reward: [(0, '53.678')] [2023-03-09 09:43:34,892][23090] Updated weights for policy 0, policy_version 99746 (0.0012) [2023-03-09 09:43:35,687][23090] Updated weights for policy 0, policy_version 99756 (0.0017) [2023-03-09 09:43:36,490][23090] Updated weights for policy 0, policy_version 99767 (0.0013) [2023-03-09 09:43:37,367][23090] Updated weights for policy 0, policy_version 99777 (0.0015) [2023-03-09 09:43:38,283][23090] Updated weights for policy 0, policy_version 99787 (0.0016) [2023-03-09 09:43:38,352][22940] Signal inference workers to stop experience collection... (33350 times) [2023-03-09 09:43:38,374][22940] Signal inference workers to resume experience collection... (33350 times) [2023-03-09 09:43:38,409][23090] InferenceWorker_p0-w0: stopping experience collection (33350 times) [2023-03-09 09:43:38,446][23090] InferenceWorker_p0-w0: resuming experience collection (33350 times) [2023-03-09 09:43:38,934][23090] Updated weights for policy 0, policy_version 99797 (0.0013) [2023-03-09 09:43:39,059][22664] Fps is (10 sec: 201530.4, 60 sec: 198518.4, 300 sec: 197885.3). Total num frames: 1635106816. Throughput: 0: 49435.9. Samples: 408833936. Policy #0 lag: (min: 1.0, avg: 17.4, max: 33.0) [2023-03-09 09:43:39,061][22664] Avg episode reward: [(0, '53.351')] [2023-03-09 09:43:39,851][23090] Updated weights for policy 0, policy_version 99807 (0.0012) [2023-03-09 09:43:40,743][23090] Updated weights for policy 0, policy_version 99817 (0.0017) [2023-03-09 09:43:41,460][23090] Updated weights for policy 0, policy_version 99827 (0.0016) [2023-03-09 09:43:42,380][23090] Updated weights for policy 0, policy_version 99838 (0.0016) [2023-03-09 09:43:43,314][23090] Updated weights for policy 0, policy_version 99848 (0.0013) [2023-03-09 09:43:44,022][23090] Updated weights for policy 0, policy_version 99858 (0.0018) [2023-03-09 09:43:44,059][22664] Fps is (10 sec: 199880.5, 60 sec: 197699.7, 300 sec: 197829.8). Total num frames: 1636073472. Throughput: 0: 49434.7. Samples: 408983328. Policy #0 lag: (min: 1.0, avg: 17.4, max: 33.0) [2023-03-09 09:43:44,060][22664] Avg episode reward: [(0, '54.744')] [2023-03-09 09:43:44,903][23090] Updated weights for policy 0, policy_version 99868 (0.0013) [2023-03-09 09:43:45,823][23090] Updated weights for policy 0, policy_version 99878 (0.0016) [2023-03-09 09:43:46,523][23090] Updated weights for policy 0, policy_version 99888 (0.0023) [2023-03-09 09:43:47,379][23090] Updated weights for policy 0, policy_version 99898 (0.0022) [2023-03-09 09:43:48,263][23090] Updated weights for policy 0, policy_version 99908 (0.0018) [2023-03-09 09:43:49,043][23090] Updated weights for policy 0, policy_version 99918 (0.0013) [2023-03-09 09:43:49,059][22664] Fps is (10 sec: 194975.3, 60 sec: 197974.2, 300 sec: 197829.9). Total num frames: 1637056512. Throughput: 0: 49495.1. Samples: 409278112. Policy #0 lag: (min: 1.0, avg: 17.4, max: 33.0) [2023-03-09 09:43:49,060][22664] Avg episode reward: [(0, '52.711')] [2023-03-09 09:43:49,840][23090] Updated weights for policy 0, policy_version 99928 (0.0013) [2023-03-09 09:43:50,422][22940] Signal inference workers to stop experience collection... (33400 times) [2023-03-09 09:43:50,425][22940] Signal inference workers to resume experience collection... (33400 times) [2023-03-09 09:43:50,491][23090] InferenceWorker_p0-w0: stopping experience collection (33400 times) [2023-03-09 09:43:50,491][23090] InferenceWorker_p0-w0: resuming experience collection (33400 times) [2023-03-09 09:43:50,758][23090] Updated weights for policy 0, policy_version 99938 (0.0013) [2023-03-09 09:43:51,606][23090] Updated weights for policy 0, policy_version 99948 (0.0013) [2023-03-09 09:43:52,256][23090] Updated weights for policy 0, policy_version 99958 (0.0018) [2023-03-09 09:43:53,130][23090] Updated weights for policy 0, policy_version 99968 (0.0013) [2023-03-09 09:43:54,059][22664] Fps is (10 sec: 194972.2, 60 sec: 197155.4, 300 sec: 197774.2). Total num frames: 1638023168. Throughput: 0: 49537.5. Samples: 409574864. Policy #0 lag: (min: 1.0, avg: 17.4, max: 33.0) [2023-03-09 09:43:54,060][22664] Avg episode reward: [(0, '54.811')] [2023-03-09 09:43:54,126][23090] Updated weights for policy 0, policy_version 99978 (0.0019) [2023-03-09 09:43:54,794][23090] Updated weights for policy 0, policy_version 99988 (0.0013) [2023-03-09 09:43:55,609][23090] Updated weights for policy 0, policy_version 99998 (0.0024) [2023-03-09 09:43:56,654][23090] Updated weights for policy 0, policy_version 100009 (0.0013) [2023-03-09 09:43:57,352][23090] Updated weights for policy 0, policy_version 100019 (0.0016) [2023-03-09 09:43:58,186][23090] Updated weights for policy 0, policy_version 100029 (0.0020) [2023-03-09 09:43:59,059][22664] Fps is (10 sec: 196602.4, 60 sec: 197427.3, 300 sec: 197774.3). Total num frames: 1639022592. Throughput: 0: 49536.7. Samples: 409724336. Policy #0 lag: (min: 1.0, avg: 17.4, max: 33.0) [2023-03-09 09:43:59,061][22664] Avg episode reward: [(0, '54.306')] [2023-03-09 09:43:59,097][23090] Updated weights for policy 0, policy_version 100039 (0.0015) [2023-03-09 09:43:59,865][23090] Updated weights for policy 0, policy_version 100049 (0.0021) [2023-03-09 09:44:00,674][23090] Updated weights for policy 0, policy_version 100059 (0.0018) [2023-03-09 09:44:01,678][23090] Updated weights for policy 0, policy_version 100070 (0.0019) [2023-03-09 09:44:02,364][23090] Updated weights for policy 0, policy_version 100080 (0.0020) [2023-03-09 09:44:03,261][23090] Updated weights for policy 0, policy_version 100090 (0.0012) [2023-03-09 09:44:04,058][22664] Fps is (10 sec: 199887.4, 60 sec: 197974.4, 300 sec: 197885.4). Total num frames: 1640022016. Throughput: 0: 49582.8. Samples: 410023152. Policy #0 lag: (min: 1.0, avg: 17.4, max: 33.0) [2023-03-09 09:44:04,059][22664] Avg episode reward: [(0, '54.329')] [2023-03-09 09:44:04,073][23090] Updated weights for policy 0, policy_version 100100 (0.0021) [2023-03-09 09:44:04,378][22940] Signal inference workers to stop experience collection... (33450 times) [2023-03-09 09:44:04,379][22940] Signal inference workers to resume experience collection... (33450 times) [2023-03-09 09:44:04,465][23090] InferenceWorker_p0-w0: stopping experience collection (33450 times) [2023-03-09 09:44:04,467][23090] InferenceWorker_p0-w0: resuming experience collection (33450 times) [2023-03-09 09:44:04,921][23090] Updated weights for policy 0, policy_version 100110 (0.0021) [2023-03-09 09:44:05,665][23090] Updated weights for policy 0, policy_version 100120 (0.0013) [2023-03-09 09:44:06,713][23090] Updated weights for policy 0, policy_version 100131 (0.0013) [2023-03-09 09:44:07,539][23090] Updated weights for policy 0, policy_version 100141 (0.0014) [2023-03-09 09:44:08,351][23090] Updated weights for policy 0, policy_version 100152 (0.0016) [2023-03-09 09:44:09,058][22664] Fps is (10 sec: 199891.7, 60 sec: 198793.4, 300 sec: 197885.4). Total num frames: 1641021440. Throughput: 0: 49537.8. Samples: 410317936. Policy #0 lag: (min: 1.0, avg: 17.4, max: 33.0) [2023-03-09 09:44:09,059][22664] Avg episode reward: [(0, '54.125')] [2023-03-09 09:44:09,350][23090] Updated weights for policy 0, policy_version 100163 (0.0020) [2023-03-09 09:44:10,205][23090] Updated weights for policy 0, policy_version 100173 (0.0018) [2023-03-09 09:44:10,871][23090] Updated weights for policy 0, policy_version 100183 (0.0021) [2023-03-09 09:44:11,822][23090] Updated weights for policy 0, policy_version 100193 (0.0013) [2023-03-09 09:44:12,732][23090] Updated weights for policy 0, policy_version 100203 (0.0019) [2023-03-09 09:44:13,391][23090] Updated weights for policy 0, policy_version 100213 (0.0021) [2023-03-09 09:44:14,059][22664] Fps is (10 sec: 199880.8, 60 sec: 198791.7, 300 sec: 197885.7). Total num frames: 1642020864. Throughput: 0: 49582.7. Samples: 410467392. Policy #0 lag: (min: 1.0, avg: 17.4, max: 33.0) [2023-03-09 09:44:14,061][22664] Avg episode reward: [(0, '54.431')] [2023-03-09 09:44:14,247][23090] Updated weights for policy 0, policy_version 100223 (0.0013) [2023-03-09 09:44:15,243][23090] Updated weights for policy 0, policy_version 100233 (0.0013) [2023-03-09 09:44:15,435][22940] Signal inference workers to stop experience collection... (33500 times) [2023-03-09 09:44:15,455][22940] Signal inference workers to resume experience collection... (33500 times) [2023-03-09 09:44:15,486][23090] InferenceWorker_p0-w0: stopping experience collection (33500 times) [2023-03-09 09:44:15,532][23090] InferenceWorker_p0-w0: resuming experience collection (33500 times) [2023-03-09 09:44:15,955][23090] Updated weights for policy 0, policy_version 100243 (0.0015) [2023-03-09 09:44:16,752][23090] Updated weights for policy 0, policy_version 100253 (0.0018) [2023-03-09 09:44:17,684][23090] Updated weights for policy 0, policy_version 100263 (0.0013) [2023-03-09 09:44:18,462][23090] Updated weights for policy 0, policy_version 100273 (0.0013) [2023-03-09 09:44:19,058][22664] Fps is (10 sec: 196607.2, 60 sec: 198247.0, 300 sec: 197885.4). Total num frames: 1642987520. Throughput: 0: 49492.0. Samples: 410762224. Policy #0 lag: (min: 1.0, avg: 17.4, max: 33.0) [2023-03-09 09:44:19,060][22664] Avg episode reward: [(0, '52.192')] [2023-03-09 09:44:19,272][23090] Updated weights for policy 0, policy_version 100283 (0.0013) [2023-03-09 09:44:20,172][23090] Updated weights for policy 0, policy_version 100293 (0.0021) [2023-03-09 09:44:20,916][23090] Updated weights for policy 0, policy_version 100303 (0.0017) [2023-03-09 09:44:21,886][23090] Updated weights for policy 0, policy_version 100314 (0.0015) [2023-03-09 09:44:22,702][23090] Updated weights for policy 0, policy_version 100324 (0.0013) [2023-03-09 09:44:23,595][23090] Updated weights for policy 0, policy_version 100335 (0.0016) [2023-03-09 09:44:24,059][22664] Fps is (10 sec: 196609.1, 60 sec: 197972.7, 300 sec: 197941.1). Total num frames: 1643986944. Throughput: 0: 49401.4. Samples: 411056992. Policy #0 lag: (min: 1.0, avg: 17.4, max: 33.0) [2023-03-09 09:44:24,060][22664] Avg episode reward: [(0, '53.060')] [2023-03-09 09:44:24,443][23090] Updated weights for policy 0, policy_version 100345 (0.0016) [2023-03-09 09:44:25,370][23090] Updated weights for policy 0, policy_version 100356 (0.0016) [2023-03-09 09:44:25,877][22940] Signal inference workers to stop experience collection... (33550 times) [2023-03-09 09:44:25,893][22940] Signal inference workers to resume experience collection... (33550 times) [2023-03-09 09:44:25,923][23090] InferenceWorker_p0-w0: stopping experience collection (33550 times) [2023-03-09 09:44:25,965][23090] InferenceWorker_p0-w0: resuming experience collection (33550 times) [2023-03-09 09:44:26,188][23090] Updated weights for policy 0, policy_version 100366 (0.0013) [2023-03-09 09:44:26,936][23090] Updated weights for policy 0, policy_version 100376 (0.0016) [2023-03-09 09:44:27,915][23090] Updated weights for policy 0, policy_version 100386 (0.0013) [2023-03-09 09:44:28,769][23090] Updated weights for policy 0, policy_version 100396 (0.0022) [2023-03-09 09:44:29,059][22664] Fps is (10 sec: 198239.1, 60 sec: 197974.3, 300 sec: 197940.9). Total num frames: 1644969984. Throughput: 0: 49402.9. Samples: 411206464. Policy #0 lag: (min: 1.0, avg: 17.4, max: 33.0) [2023-03-09 09:44:29,061][22664] Avg episode reward: [(0, '52.190')] [2023-03-09 09:44:29,394][23090] Updated weights for policy 0, policy_version 100406 (0.0013) [2023-03-09 09:44:30,294][23090] Updated weights for policy 0, policy_version 100416 (0.0016) [2023-03-09 09:44:31,263][23090] Updated weights for policy 0, policy_version 100426 (0.0013) [2023-03-09 09:44:31,900][23090] Updated weights for policy 0, policy_version 100436 (0.0013) [2023-03-09 09:44:32,731][23090] Updated weights for policy 0, policy_version 100446 (0.0024) [2023-03-09 09:44:33,671][23090] Updated weights for policy 0, policy_version 100456 (0.0018) [2023-03-09 09:44:34,059][22664] Fps is (10 sec: 194971.0, 60 sec: 197700.2, 300 sec: 197829.9). Total num frames: 1645936640. Throughput: 0: 49448.8. Samples: 411503312. Policy #0 lag: (min: 1.0, avg: 16.2, max: 32.0) [2023-03-09 09:44:34,060][22664] Avg episode reward: [(0, '55.441')] [2023-03-09 09:44:34,478][23090] Updated weights for policy 0, policy_version 100467 (0.0020) [2023-03-09 09:44:35,263][23090] Updated weights for policy 0, policy_version 100477 (0.0019) [2023-03-09 09:44:36,292][23090] Updated weights for policy 0, policy_version 100487 (0.0017) [2023-03-09 09:44:36,501][22940] Signal inference workers to stop experience collection... (33600 times) [2023-03-09 09:44:36,503][22940] Signal inference workers to resume experience collection... (33600 times) [2023-03-09 09:44:36,573][23090] InferenceWorker_p0-w0: stopping experience collection (33600 times) [2023-03-09 09:44:36,574][23090] InferenceWorker_p0-w0: resuming experience collection (33600 times) [2023-03-09 09:44:36,985][23090] Updated weights for policy 0, policy_version 100497 (0.0017) [2023-03-09 09:44:37,834][23090] Updated weights for policy 0, policy_version 100507 (0.0021) [2023-03-09 09:44:38,719][23090] Updated weights for policy 0, policy_version 100517 (0.0020) [2023-03-09 09:44:39,058][22664] Fps is (10 sec: 194977.2, 60 sec: 196882.2, 300 sec: 197774.5). Total num frames: 1646919680. Throughput: 0: 49450.1. Samples: 411800112. Policy #0 lag: (min: 1.0, avg: 16.2, max: 32.0) [2023-03-09 09:44:39,059][22664] Avg episode reward: [(0, '52.956')] [2023-03-09 09:44:39,541][23090] Updated weights for policy 0, policy_version 100528 (0.0016) [2023-03-09 09:44:40,363][23090] Updated weights for policy 0, policy_version 100538 (0.0013) [2023-03-09 09:44:41,281][23090] Updated weights for policy 0, policy_version 100548 (0.0016) [2023-03-09 09:44:42,095][23090] Updated weights for policy 0, policy_version 100558 (0.0014) [2023-03-09 09:44:42,797][23090] Updated weights for policy 0, policy_version 100568 (0.0017) [2023-03-09 09:44:43,731][23090] Updated weights for policy 0, policy_version 100578 (0.0015) [2023-03-09 09:44:44,059][22664] Fps is (10 sec: 198243.8, 60 sec: 197427.4, 300 sec: 197829.9). Total num frames: 1647919104. Throughput: 0: 49447.9. Samples: 411949488. Policy #0 lag: (min: 1.0, avg: 16.2, max: 32.0) [2023-03-09 09:44:44,061][22664] Avg episode reward: [(0, '52.674')] [2023-03-09 09:44:44,583][23090] Updated weights for policy 0, policy_version 100588 (0.0015) [2023-03-09 09:44:45,318][23090] Updated weights for policy 0, policy_version 100599 (0.0019) [2023-03-09 09:44:46,247][23090] Updated weights for policy 0, policy_version 100609 (0.0013) [2023-03-09 09:44:47,218][23090] Updated weights for policy 0, policy_version 100619 (0.0018) [2023-03-09 09:44:47,275][22940] Signal inference workers to stop experience collection... (33650 times) [2023-03-09 09:44:47,292][22940] Signal inference workers to resume experience collection... (33650 times) [2023-03-09 09:44:47,342][23090] InferenceWorker_p0-w0: stopping experience collection (33650 times) [2023-03-09 09:44:47,344][23090] InferenceWorker_p0-w0: resuming experience collection (33650 times) [2023-03-09 09:44:47,914][23090] Updated weights for policy 0, policy_version 100630 (0.0015) [2023-03-09 09:44:48,923][23090] Updated weights for policy 0, policy_version 100641 (0.0016) [2023-03-09 09:44:49,059][22664] Fps is (10 sec: 199881.0, 60 sec: 197699.8, 300 sec: 197885.5). Total num frames: 1648918528. Throughput: 0: 49403.9. Samples: 412246336. Policy #0 lag: (min: 1.0, avg: 16.2, max: 32.0) [2023-03-09 09:44:49,060][22664] Avg episode reward: [(0, '55.541')] [2023-03-09 09:44:49,848][23090] Updated weights for policy 0, policy_version 100651 (0.0014) [2023-03-09 09:44:50,485][23090] Updated weights for policy 0, policy_version 100661 (0.0016) [2023-03-09 09:44:51,298][23090] Updated weights for policy 0, policy_version 100671 (0.0016) [2023-03-09 09:44:52,328][23090] Updated weights for policy 0, policy_version 100681 (0.0019) [2023-03-09 09:44:52,976][23090] Updated weights for policy 0, policy_version 100691 (0.0015) [2023-03-09 09:44:53,767][23090] Updated weights for policy 0, policy_version 100701 (0.0021) [2023-03-09 09:44:54,059][22664] Fps is (10 sec: 201519.8, 60 sec: 198518.7, 300 sec: 197940.7). Total num frames: 1649934336. Throughput: 0: 49494.3. Samples: 412545200. Policy #0 lag: (min: 1.0, avg: 16.2, max: 32.0) [2023-03-09 09:44:54,061][22664] Avg episode reward: [(0, '55.045')] [2023-03-09 09:44:54,736][23090] Updated weights for policy 0, policy_version 100711 (0.0013) [2023-03-09 09:44:55,463][23090] Updated weights for policy 0, policy_version 100721 (0.0015) [2023-03-09 09:44:56,318][23090] Updated weights for policy 0, policy_version 100731 (0.0016) [2023-03-09 09:44:57,196][23090] Updated weights for policy 0, policy_version 100741 (0.0017) [2023-03-09 09:44:57,946][23090] Updated weights for policy 0, policy_version 100751 (0.0013) [2023-03-09 09:44:58,326][22940] Signal inference workers to stop experience collection... (33700 times) [2023-03-09 09:44:58,327][22940] Signal inference workers to resume experience collection... (33700 times) [2023-03-09 09:44:58,394][23090] InferenceWorker_p0-w0: stopping experience collection (33700 times) [2023-03-09 09:44:58,394][23090] InferenceWorker_p0-w0: resuming experience collection (33700 times) [2023-03-09 09:44:58,823][23090] Updated weights for policy 0, policy_version 100761 (0.0016) [2023-03-09 09:44:59,058][22664] Fps is (10 sec: 199888.7, 60 sec: 198247.5, 300 sec: 197885.5). Total num frames: 1650917376. Throughput: 0: 49495.4. Samples: 412694672. Policy #0 lag: (min: 1.0, avg: 16.2, max: 32.0) [2023-03-09 09:44:59,059][22664] Avg episode reward: [(0, '52.283')] [2023-03-09 09:44:59,683][23090] Updated weights for policy 0, policy_version 100771 (0.0017) [2023-03-09 09:45:00,531][23090] Updated weights for policy 0, policy_version 100781 (0.0015) [2023-03-09 09:45:01,184][23090] Updated weights for policy 0, policy_version 100791 (0.0013) [2023-03-09 09:45:02,144][23090] Updated weights for policy 0, policy_version 100801 (0.0013) [2023-03-09 09:45:03,044][23090] Updated weights for policy 0, policy_version 100811 (0.0022) [2023-03-09 09:45:03,777][23090] Updated weights for policy 0, policy_version 100822 (0.0016) [2023-03-09 09:45:04,059][22664] Fps is (10 sec: 196609.5, 60 sec: 197972.4, 300 sec: 197940.7). Total num frames: 1651900416. Throughput: 0: 49539.6. Samples: 412991520. Policy #0 lag: (min: 1.0, avg: 16.2, max: 32.0) [2023-03-09 09:45:04,061][22664] Avg episode reward: [(0, '56.217')] [2023-03-09 09:45:04,626][23090] Updated weights for policy 0, policy_version 100832 (0.0013) [2023-03-09 09:45:05,660][23090] Updated weights for policy 0, policy_version 100842 (0.0013) [2023-03-09 09:45:06,295][23090] Updated weights for policy 0, policy_version 100852 (0.0013) [2023-03-09 09:45:07,131][23090] Updated weights for policy 0, policy_version 100862 (0.0018) [2023-03-09 09:45:08,110][23090] Updated weights for policy 0, policy_version 100872 (0.0017) [2023-03-09 09:45:08,845][23090] Updated weights for policy 0, policy_version 100882 (0.0021) [2023-03-09 09:45:09,059][22664] Fps is (10 sec: 198238.2, 60 sec: 197971.9, 300 sec: 197996.2). Total num frames: 1652899840. Throughput: 0: 49495.2. Samples: 413284288. Policy #0 lag: (min: 1.0, avg: 16.2, max: 32.0) [2023-03-09 09:45:09,061][22664] Avg episode reward: [(0, '53.576')] [2023-03-09 09:45:09,645][22940] Signal inference workers to stop experience collection... (33750 times) [2023-03-09 09:45:09,666][22940] Signal inference workers to resume experience collection... (33750 times) [2023-03-09 09:45:09,699][23090] InferenceWorker_p0-w0: stopping experience collection (33750 times) [2023-03-09 09:45:09,701][23090] Updated weights for policy 0, policy_version 100892 (0.0022) [2023-03-09 09:45:09,738][23090] InferenceWorker_p0-w0: resuming experience collection (33750 times) [2023-03-09 09:45:10,603][23090] Updated weights for policy 0, policy_version 100902 (0.0019) [2023-03-09 09:45:11,451][23090] Updated weights for policy 0, policy_version 100913 (0.0016) [2023-03-09 09:45:12,285][23090] Updated weights for policy 0, policy_version 100923 (0.0012) [2023-03-09 09:45:13,178][23090] Updated weights for policy 0, policy_version 100933 (0.0013) [2023-03-09 09:45:13,977][23090] Updated weights for policy 0, policy_version 100944 (0.0013) [2023-03-09 09:45:14,059][22664] Fps is (10 sec: 196604.6, 60 sec: 197426.3, 300 sec: 197940.6). Total num frames: 1653866496. Throughput: 0: 49495.4. Samples: 413433760. Policy #0 lag: (min: 1.0, avg: 16.2, max: 32.0) [2023-03-09 09:45:14,061][22664] Avg episode reward: [(0, '52.945')] [2023-03-09 09:45:14,866][23090] Updated weights for policy 0, policy_version 100954 (0.0020) [2023-03-09 09:45:15,676][23090] Updated weights for policy 0, policy_version 100964 (0.0019) [2023-03-09 09:45:16,491][23090] Updated weights for policy 0, policy_version 100974 (0.0013) [2023-03-09 09:45:17,222][23090] Updated weights for policy 0, policy_version 100984 (0.0013) [2023-03-09 09:45:18,170][23090] Updated weights for policy 0, policy_version 100994 (0.0013) [2023-03-09 09:45:19,015][23090] Updated weights for policy 0, policy_version 101004 (0.0016) [2023-03-09 09:45:19,059][22664] Fps is (10 sec: 196609.2, 60 sec: 197972.3, 300 sec: 197996.4). Total num frames: 1654865920. Throughput: 0: 49541.4. Samples: 413732688. Policy #0 lag: (min: 1.0, avg: 16.2, max: 32.0) [2023-03-09 09:45:19,061][22664] Avg episode reward: [(0, '53.866')] [2023-03-09 09:45:19,092][22940] Saving /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000101006_1654882304.pth... [2023-03-09 09:45:19,157][22940] Removing /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000098107_1607385088.pth [2023-03-09 09:45:19,406][22940] Signal inference workers to stop experience collection... (33800 times) [2023-03-09 09:45:19,422][22940] Signal inference workers to resume experience collection... (33800 times) [2023-03-09 09:45:19,476][23090] InferenceWorker_p0-w0: stopping experience collection (33800 times) [2023-03-09 09:45:19,479][23090] InferenceWorker_p0-w0: resuming experience collection (33800 times) [2023-03-09 09:45:19,649][23090] Updated weights for policy 0, policy_version 101014 (0.0014) [2023-03-09 09:45:20,557][23090] Updated weights for policy 0, policy_version 101024 (0.0015) [2023-03-09 09:45:21,533][23090] Updated weights for policy 0, policy_version 101034 (0.0013) [2023-03-09 09:45:22,267][23090] Updated weights for policy 0, policy_version 101045 (0.0016) [2023-03-09 09:45:23,077][23090] Updated weights for policy 0, policy_version 101055 (0.0017) [2023-03-09 09:45:24,059][22664] Fps is (10 sec: 196609.8, 60 sec: 197426.4, 300 sec: 197829.8). Total num frames: 1655832576. Throughput: 0: 49497.2. Samples: 414027504. Policy #0 lag: (min: 1.0, avg: 16.2, max: 32.0) [2023-03-09 09:45:24,061][22664] Avg episode reward: [(0, '55.789')] [2023-03-09 09:45:24,168][23090] Updated weights for policy 0, policy_version 101065 (0.0016) [2023-03-09 09:45:24,790][23090] Updated weights for policy 0, policy_version 101075 (0.0013) [2023-03-09 09:45:25,605][23090] Updated weights for policy 0, policy_version 101085 (0.0013) [2023-03-09 09:45:26,614][23090] Updated weights for policy 0, policy_version 101095 (0.0013) [2023-03-09 09:45:27,429][23090] Updated weights for policy 0, policy_version 101106 (0.0013) [2023-03-09 09:45:28,242][23090] Updated weights for policy 0, policy_version 101116 (0.0013) [2023-03-09 09:45:29,059][22664] Fps is (10 sec: 194970.7, 60 sec: 197427.5, 300 sec: 197885.2). Total num frames: 1656815616. Throughput: 0: 49498.9. Samples: 414176944. Policy #0 lag: (min: 1.0, avg: 16.2, max: 32.0) [2023-03-09 09:45:29,060][22664] Avg episode reward: [(0, '55.508')] [2023-03-09 09:45:29,168][23090] Updated weights for policy 0, policy_version 101126 (0.0017) [2023-03-09 09:45:29,502][22940] Signal inference workers to stop experience collection... (33850 times) [2023-03-09 09:45:29,525][22940] Signal inference workers to resume experience collection... (33850 times) [2023-03-09 09:45:29,570][23090] InferenceWorker_p0-w0: stopping experience collection (33850 times) [2023-03-09 09:45:29,613][23090] InferenceWorker_p0-w0: resuming experience collection (33850 times) [2023-03-09 09:45:29,869][23090] Updated weights for policy 0, policy_version 101136 (0.0016) [2023-03-09 09:45:30,776][23090] Updated weights for policy 0, policy_version 101146 (0.0015) [2023-03-09 09:45:31,622][23090] Updated weights for policy 0, policy_version 101156 (0.0013) [2023-03-09 09:45:32,391][23090] Updated weights for policy 0, policy_version 101166 (0.0013) [2023-03-09 09:45:33,165][23090] Updated weights for policy 0, policy_version 101176 (0.0017) [2023-03-09 09:45:34,059][22664] Fps is (10 sec: 198253.6, 60 sec: 197973.5, 300 sec: 197885.4). Total num frames: 1657815040. Throughput: 0: 49453.0. Samples: 414471712. Policy #0 lag: (min: 1.0, avg: 17.8, max: 33.0) [2023-03-09 09:45:34,059][22664] Avg episode reward: [(0, '55.547')] [2023-03-09 09:45:34,070][23090] Updated weights for policy 0, policy_version 101186 (0.0013) [2023-03-09 09:45:34,908][23090] Updated weights for policy 0, policy_version 101196 (0.0018) [2023-03-09 09:45:35,605][23090] Updated weights for policy 0, policy_version 101206 (0.0021) [2023-03-09 09:45:36,417][23090] Updated weights for policy 0, policy_version 101216 (0.0013) [2023-03-09 09:45:37,449][23090] Updated weights for policy 0, policy_version 101226 (0.0017) [2023-03-09 09:45:38,107][23090] Updated weights for policy 0, policy_version 101236 (0.0013) [2023-03-09 09:45:38,925][23090] Updated weights for policy 0, policy_version 101246 (0.0018) [2023-03-09 09:45:39,059][22664] Fps is (10 sec: 201521.7, 60 sec: 198518.3, 300 sec: 197996.5). Total num frames: 1658830848. Throughput: 0: 49362.5. Samples: 414766512. Policy #0 lag: (min: 1.0, avg: 17.8, max: 33.0) [2023-03-09 09:45:39,060][22664] Avg episode reward: [(0, '54.308')] [2023-03-09 09:45:39,878][23090] Updated weights for policy 0, policy_version 101256 (0.0018) [2023-03-09 09:45:40,048][22940] Signal inference workers to stop experience collection... (33900 times) [2023-03-09 09:45:40,072][22940] Signal inference workers to resume experience collection... (33900 times) [2023-03-09 09:45:40,114][23090] InferenceWorker_p0-w0: stopping experience collection (33900 times) [2023-03-09 09:45:40,115][23090] InferenceWorker_p0-w0: resuming experience collection (33900 times) [2023-03-09 09:45:40,610][23090] Updated weights for policy 0, policy_version 101266 (0.0025) [2023-03-09 09:45:41,433][23090] Updated weights for policy 0, policy_version 101276 (0.0014) [2023-03-09 09:45:42,358][23090] Updated weights for policy 0, policy_version 101286 (0.0016) [2023-03-09 09:45:43,033][23090] Updated weights for policy 0, policy_version 101296 (0.0020) [2023-03-09 09:45:43,924][23090] Updated weights for policy 0, policy_version 101306 (0.0017) [2023-03-09 09:45:44,059][22664] Fps is (10 sec: 203156.3, 60 sec: 198792.3, 300 sec: 197996.3). Total num frames: 1659846656. Throughput: 0: 49498.7. Samples: 414922128. Policy #0 lag: (min: 1.0, avg: 17.8, max: 33.0) [2023-03-09 09:45:44,061][22664] Avg episode reward: [(0, '56.034')] [2023-03-09 09:45:44,802][23090] Updated weights for policy 0, policy_version 101316 (0.0013) [2023-03-09 09:45:45,578][23090] Updated weights for policy 0, policy_version 101326 (0.0023) [2023-03-09 09:45:46,314][23090] Updated weights for policy 0, policy_version 101336 (0.0017) [2023-03-09 09:45:47,349][23090] Updated weights for policy 0, policy_version 101347 (0.0013) [2023-03-09 09:45:48,123][23090] Updated weights for policy 0, policy_version 101357 (0.0027) [2023-03-09 09:45:48,818][23090] Updated weights for policy 0, policy_version 101367 (0.0026) [2023-03-09 09:45:49,059][22664] Fps is (10 sec: 198246.4, 60 sec: 198245.8, 300 sec: 197996.4). Total num frames: 1660813312. Throughput: 0: 49545.5. Samples: 415221072. Policy #0 lag: (min: 1.0, avg: 17.8, max: 33.0) [2023-03-09 09:45:49,061][22664] Avg episode reward: [(0, '55.346')] [2023-03-09 09:45:49,279][22940] Signal inference workers to stop experience collection... (33950 times) [2023-03-09 09:45:49,302][22940] Signal inference workers to resume experience collection... (33950 times) [2023-03-09 09:45:49,348][23090] InferenceWorker_p0-w0: stopping experience collection (33950 times) [2023-03-09 09:45:49,348][23090] InferenceWorker_p0-w0: resuming experience collection (33950 times) [2023-03-09 09:45:49,751][23090] Updated weights for policy 0, policy_version 101377 (0.0025) [2023-03-09 09:45:50,699][23090] Updated weights for policy 0, policy_version 101387 (0.0020) [2023-03-09 09:45:51,303][23090] Updated weights for policy 0, policy_version 101397 (0.0018) [2023-03-09 09:45:52,162][23090] Updated weights for policy 0, policy_version 101407 (0.0025) [2023-03-09 09:45:53,211][23090] Updated weights for policy 0, policy_version 101417 (0.0015) [2023-03-09 09:45:53,890][23090] Updated weights for policy 0, policy_version 101427 (0.0019) [2023-03-09 09:45:54,059][22664] Fps is (10 sec: 198245.3, 60 sec: 198246.5, 300 sec: 198107.7). Total num frames: 1661829120. Throughput: 0: 49590.1. Samples: 415515840. Policy #0 lag: (min: 1.0, avg: 17.8, max: 33.0) [2023-03-09 09:45:54,061][22664] Avg episode reward: [(0, '57.139')] [2023-03-09 09:45:54,748][23090] Updated weights for policy 0, policy_version 101438 (0.0020) [2023-03-09 09:45:55,727][23090] Updated weights for policy 0, policy_version 101448 (0.0018) [2023-03-09 09:45:56,561][23090] Updated weights for policy 0, policy_version 101459 (0.0013) [2023-03-09 09:45:57,346][23090] Updated weights for policy 0, policy_version 101469 (0.0021) [2023-03-09 09:45:58,295][23090] Updated weights for policy 0, policy_version 101479 (0.0013) [2023-03-09 09:45:59,035][23090] Updated weights for policy 0, policy_version 101489 (0.0013) [2023-03-09 09:45:59,058][22664] Fps is (10 sec: 198253.8, 60 sec: 197973.3, 300 sec: 197996.7). Total num frames: 1662795776. Throughput: 0: 49544.4. Samples: 415663232. Policy #0 lag: (min: 1.0, avg: 17.8, max: 33.0) [2023-03-09 09:45:59,059][22664] Avg episode reward: [(0, '55.990')] [2023-03-09 09:45:59,908][23090] Updated weights for policy 0, policy_version 101500 (0.0013) [2023-03-09 09:46:00,876][23090] Updated weights for policy 0, policy_version 101510 (0.0016) [2023-03-09 09:46:01,179][22940] Signal inference workers to stop experience collection... (34000 times) [2023-03-09 09:46:01,203][22940] Signal inference workers to resume experience collection... (34000 times) [2023-03-09 09:46:01,245][23090] InferenceWorker_p0-w0: stopping experience collection (34000 times) [2023-03-09 09:46:01,285][23090] InferenceWorker_p0-w0: resuming experience collection (34000 times) [2023-03-09 09:46:01,597][23090] Updated weights for policy 0, policy_version 101520 (0.0016) [2023-03-09 09:46:02,461][23090] Updated weights for policy 0, policy_version 101530 (0.0022) [2023-03-09 09:46:03,324][23090] Updated weights for policy 0, policy_version 101540 (0.0015) [2023-03-09 09:46:04,058][22664] Fps is (10 sec: 194976.9, 60 sec: 197974.5, 300 sec: 197941.3). Total num frames: 1663778816. Throughput: 0: 49498.0. Samples: 415960080. Policy #0 lag: (min: 1.0, avg: 17.8, max: 33.0) [2023-03-09 09:46:04,059][22664] Avg episode reward: [(0, '54.341')] [2023-03-09 09:46:04,073][23090] Updated weights for policy 0, policy_version 101550 (0.0015) [2023-03-09 09:46:04,860][23090] Updated weights for policy 0, policy_version 101560 (0.0012) [2023-03-09 09:46:05,748][23090] Updated weights for policy 0, policy_version 101570 (0.0017) [2023-03-09 09:46:06,613][23090] Updated weights for policy 0, policy_version 101580 (0.0013) [2023-03-09 09:46:07,362][23090] Updated weights for policy 0, policy_version 101591 (0.0020) [2023-03-09 09:46:08,246][23090] Updated weights for policy 0, policy_version 101601 (0.0013) [2023-03-09 09:46:09,059][22664] Fps is (10 sec: 194967.4, 60 sec: 197428.2, 300 sec: 197774.3). Total num frames: 1664745472. Throughput: 0: 49634.4. Samples: 416261040. Policy #0 lag: (min: 1.0, avg: 17.8, max: 33.0) [2023-03-09 09:46:09,060][22664] Avg episode reward: [(0, '54.421')] [2023-03-09 09:46:09,207][23090] Updated weights for policy 0, policy_version 101611 (0.0017) [2023-03-09 09:46:09,864][23090] Updated weights for policy 0, policy_version 101621 (0.0016) [2023-03-09 09:46:10,715][23090] Updated weights for policy 0, policy_version 101631 (0.0013) [2023-03-09 09:46:11,718][23090] Updated weights for policy 0, policy_version 101641 (0.0013) [2023-03-09 09:46:11,787][22940] Signal inference workers to stop experience collection... (34050 times) [2023-03-09 09:46:11,811][22940] Signal inference workers to resume experience collection... (34050 times) [2023-03-09 09:46:11,842][23090] InferenceWorker_p0-w0: stopping experience collection (34050 times) [2023-03-09 09:46:11,884][23090] InferenceWorker_p0-w0: resuming experience collection (34050 times) [2023-03-09 09:46:12,457][23090] Updated weights for policy 0, policy_version 101651 (0.0020) [2023-03-09 09:46:13,146][23090] Updated weights for policy 0, policy_version 101661 (0.0013) [2023-03-09 09:46:14,058][22664] Fps is (10 sec: 198245.9, 60 sec: 198248.0, 300 sec: 197941.1). Total num frames: 1665761280. Throughput: 0: 49541.7. Samples: 416406304. Policy #0 lag: (min: 1.0, avg: 17.8, max: 33.0) [2023-03-09 09:46:14,059][22664] Avg episode reward: [(0, '54.619')] [2023-03-09 09:46:14,158][23090] Updated weights for policy 0, policy_version 101671 (0.0015) [2023-03-09 09:46:14,886][23090] Updated weights for policy 0, policy_version 101681 (0.0016) [2023-03-09 09:46:15,707][23090] Updated weights for policy 0, policy_version 101691 (0.0018) [2023-03-09 09:46:16,685][23090] Updated weights for policy 0, policy_version 101702 (0.0019) [2023-03-09 09:46:17,425][23090] Updated weights for policy 0, policy_version 101712 (0.0019) [2023-03-09 09:46:18,339][23090] Updated weights for policy 0, policy_version 101723 (0.0017) [2023-03-09 09:46:19,059][22664] Fps is (10 sec: 201519.5, 60 sec: 198246.6, 300 sec: 197996.3). Total num frames: 1666760704. Throughput: 0: 49677.9. Samples: 416707232. Policy #0 lag: (min: 1.0, avg: 17.8, max: 33.0) [2023-03-09 09:46:19,060][22664] Avg episode reward: [(0, '54.553')] [2023-03-09 09:46:19,256][23090] Updated weights for policy 0, policy_version 101733 (0.0013) [2023-03-09 09:46:20,022][23090] Updated weights for policy 0, policy_version 101743 (0.0016) [2023-03-09 09:46:20,799][23090] Updated weights for policy 0, policy_version 101753 (0.0018) [2023-03-09 09:46:21,718][23090] Updated weights for policy 0, policy_version 101763 (0.0015) [2023-03-09 09:46:22,310][22940] Signal inference workers to stop experience collection... (34100 times) [2023-03-09 09:46:22,332][22940] Signal inference workers to resume experience collection... (34100 times) [2023-03-09 09:46:22,375][23090] InferenceWorker_p0-w0: stopping experience collection (34100 times) [2023-03-09 09:46:22,375][23090] InferenceWorker_p0-w0: resuming experience collection (34100 times) [2023-03-09 09:46:22,547][23090] Updated weights for policy 0, policy_version 101774 (0.0013) [2023-03-09 09:46:23,485][23090] Updated weights for policy 0, policy_version 101785 (0.0013) [2023-03-09 09:46:24,059][22664] Fps is (10 sec: 199879.4, 60 sec: 198793.0, 300 sec: 198052.1). Total num frames: 1667760128. Throughput: 0: 49677.6. Samples: 417002000. Policy #0 lag: (min: 1.0, avg: 17.8, max: 33.0) [2023-03-09 09:46:24,061][22664] Avg episode reward: [(0, '50.691')] [2023-03-09 09:46:24,369][23090] Updated weights for policy 0, policy_version 101795 (0.0013) [2023-03-09 09:46:25,235][23090] Updated weights for policy 0, policy_version 101805 (0.0020) [2023-03-09 09:46:25,901][23090] Updated weights for policy 0, policy_version 101815 (0.0022) [2023-03-09 09:46:26,858][23090] Updated weights for policy 0, policy_version 101825 (0.0013) [2023-03-09 09:46:27,707][23090] Updated weights for policy 0, policy_version 101835 (0.0016) [2023-03-09 09:46:28,466][23090] Updated weights for policy 0, policy_version 101845 (0.0015) [2023-03-09 09:46:29,059][22664] Fps is (10 sec: 199884.8, 60 sec: 199065.6, 300 sec: 198107.4). Total num frames: 1668759552. Throughput: 0: 49495.1. Samples: 417149408. Policy #0 lag: (min: 1.0, avg: 17.8, max: 33.0) [2023-03-09 09:46:29,061][22664] Avg episode reward: [(0, '54.065')] [2023-03-09 09:46:29,246][23090] Updated weights for policy 0, policy_version 101855 (0.0016) [2023-03-09 09:46:30,273][23090] Updated weights for policy 0, policy_version 101865 (0.0013) [2023-03-09 09:46:30,978][23090] Updated weights for policy 0, policy_version 101875 (0.0015) [2023-03-09 09:46:31,736][23090] Updated weights for policy 0, policy_version 101885 (0.0013) [2023-03-09 09:46:32,716][23090] Updated weights for policy 0, policy_version 101895 (0.0013) [2023-03-09 09:46:32,884][22940] Signal inference workers to stop experience collection... (34150 times) [2023-03-09 09:46:32,887][22940] Signal inference workers to resume experience collection... (34150 times) [2023-03-09 09:46:32,962][23090] InferenceWorker_p0-w0: stopping experience collection (34150 times) [2023-03-09 09:46:32,965][23090] InferenceWorker_p0-w0: resuming experience collection (34150 times) [2023-03-09 09:46:33,492][23090] Updated weights for policy 0, policy_version 101905 (0.0019) [2023-03-09 09:46:34,058][22664] Fps is (10 sec: 196613.4, 60 sec: 198519.6, 300 sec: 198052.0). Total num frames: 1669726208. Throughput: 0: 49496.2. Samples: 417448384. Policy #0 lag: (min: 1.0, avg: 18.2, max: 33.0) [2023-03-09 09:46:34,059][22664] Avg episode reward: [(0, '54.171')] [2023-03-09 09:46:34,282][23090] Updated weights for policy 0, policy_version 101915 (0.0022) [2023-03-09 09:46:35,216][23090] Updated weights for policy 0, policy_version 101925 (0.0023) [2023-03-09 09:46:35,956][23090] Updated weights for policy 0, policy_version 101935 (0.0014) [2023-03-09 09:46:36,745][23090] Updated weights for policy 0, policy_version 101945 (0.0013) [2023-03-09 09:46:37,621][23090] Updated weights for policy 0, policy_version 101955 (0.0016) [2023-03-09 09:46:38,454][23090] Updated weights for policy 0, policy_version 101965 (0.0016) [2023-03-09 09:46:39,059][22664] Fps is (10 sec: 198247.0, 60 sec: 198519.8, 300 sec: 198162.9). Total num frames: 1670742016. Throughput: 0: 49540.0. Samples: 417745136. Policy #0 lag: (min: 1.0, avg: 18.2, max: 33.0) [2023-03-09 09:46:39,061][22664] Avg episode reward: [(0, '54.921')] [2023-03-09 09:46:39,128][23090] Updated weights for policy 0, policy_version 101975 (0.0023) [2023-03-09 09:46:40,215][23090] Updated weights for policy 0, policy_version 101986 (0.0017) [2023-03-09 09:46:41,060][23090] Updated weights for policy 0, policy_version 101996 (0.0017) [2023-03-09 09:46:41,560][22940] Signal inference workers to stop experience collection... (34200 times) [2023-03-09 09:46:41,581][22940] Signal inference workers to resume experience collection... (34200 times) [2023-03-09 09:46:41,667][23090] InferenceWorker_p0-w0: stopping experience collection (34200 times) [2023-03-09 09:46:41,669][23090] InferenceWorker_p0-w0: resuming experience collection (34200 times) [2023-03-09 09:46:41,785][23090] Updated weights for policy 0, policy_version 102007 (0.0017) [2023-03-09 09:46:42,669][23090] Updated weights for policy 0, policy_version 102017 (0.0019) [2023-03-09 09:46:43,608][23090] Updated weights for policy 0, policy_version 102027 (0.0016) [2023-03-09 09:46:44,059][22664] Fps is (10 sec: 199882.1, 60 sec: 197973.9, 300 sec: 198107.6). Total num frames: 1671725056. Throughput: 0: 49540.8. Samples: 417892576. Policy #0 lag: (min: 1.0, avg: 18.2, max: 33.0) [2023-03-09 09:46:44,060][22664] Avg episode reward: [(0, '55.899')] [2023-03-09 09:46:44,331][23090] Updated weights for policy 0, policy_version 102037 (0.0017) [2023-03-09 09:46:45,110][23090] Updated weights for policy 0, policy_version 102047 (0.0013) [2023-03-09 09:46:46,171][23090] Updated weights for policy 0, policy_version 102057 (0.0017) [2023-03-09 09:46:46,837][23090] Updated weights for policy 0, policy_version 102067 (0.0013) [2023-03-09 09:46:47,645][23090] Updated weights for policy 0, policy_version 102077 (0.0024) [2023-03-09 09:46:48,609][23090] Updated weights for policy 0, policy_version 102087 (0.0016) [2023-03-09 09:46:49,059][22664] Fps is (10 sec: 196608.4, 60 sec: 198246.8, 300 sec: 198052.1). Total num frames: 1672708096. Throughput: 0: 49540.0. Samples: 418189392. Policy #0 lag: (min: 1.0, avg: 18.2, max: 33.0) [2023-03-09 09:46:49,061][22664] Avg episode reward: [(0, '51.569')] [2023-03-09 09:46:49,332][23090] Updated weights for policy 0, policy_version 102097 (0.0012) [2023-03-09 09:46:50,133][23090] Updated weights for policy 0, policy_version 102107 (0.0017) [2023-03-09 09:46:51,056][23090] Updated weights for policy 0, policy_version 102117 (0.0018) [2023-03-09 09:46:51,401][22940] Signal inference workers to stop experience collection... (34250 times) [2023-03-09 09:46:51,426][22940] Signal inference workers to resume experience collection... (34250 times) [2023-03-09 09:46:51,457][23090] InferenceWorker_p0-w0: stopping experience collection (34250 times) [2023-03-09 09:46:51,503][23090] InferenceWorker_p0-w0: resuming experience collection (34250 times) [2023-03-09 09:46:51,761][23090] Updated weights for policy 0, policy_version 102127 (0.0017) [2023-03-09 09:46:52,559][23090] Updated weights for policy 0, policy_version 102137 (0.0017) [2023-03-09 09:46:53,490][23090] Updated weights for policy 0, policy_version 102147 (0.0013) [2023-03-09 09:46:54,059][22664] Fps is (10 sec: 193327.4, 60 sec: 197154.2, 300 sec: 197885.7). Total num frames: 1673658368. Throughput: 0: 49493.5. Samples: 418488256. Policy #0 lag: (min: 1.0, avg: 18.2, max: 33.0) [2023-03-09 09:46:54,061][22664] Avg episode reward: [(0, '52.607')] [2023-03-09 09:46:54,300][23090] Updated weights for policy 0, policy_version 102157 (0.0016) [2023-03-09 09:46:54,957][23090] Updated weights for policy 0, policy_version 102167 (0.0016) [2023-03-09 09:46:55,915][23090] Updated weights for policy 0, policy_version 102177 (0.0015) [2023-03-09 09:46:56,876][23090] Updated weights for policy 0, policy_version 102187 (0.0028) [2023-03-09 09:46:57,638][23090] Updated weights for policy 0, policy_version 102198 (0.0013) [2023-03-09 09:46:58,508][23090] Updated weights for policy 0, policy_version 102208 (0.0013) [2023-03-09 09:46:59,059][22664] Fps is (10 sec: 194972.9, 60 sec: 197700.0, 300 sec: 197996.4). Total num frames: 1674657792. Throughput: 0: 49541.6. Samples: 418635680. Policy #0 lag: (min: 1.0, avg: 18.2, max: 33.0) [2023-03-09 09:46:59,060][22664] Avg episode reward: [(0, '52.834')] [2023-03-09 09:46:59,485][23090] Updated weights for policy 0, policy_version 102218 (0.0013) [2023-03-09 09:46:59,919][22940] Signal inference workers to stop experience collection... (34300 times) [2023-03-09 09:46:59,940][22940] Signal inference workers to resume experience collection... (34300 times) [2023-03-09 09:46:59,995][23090] InferenceWorker_p0-w0: stopping experience collection (34300 times) [2023-03-09 09:46:59,995][23090] InferenceWorker_p0-w0: resuming experience collection (34300 times) [2023-03-09 09:47:00,155][23090] Updated weights for policy 0, policy_version 102228 (0.0013) [2023-03-09 09:47:00,948][23090] Updated weights for policy 0, policy_version 102238 (0.0021) [2023-03-09 09:47:01,915][23090] Updated weights for policy 0, policy_version 102248 (0.0013) [2023-03-09 09:47:02,628][23090] Updated weights for policy 0, policy_version 102258 (0.0018) [2023-03-09 09:47:03,435][23090] Updated weights for policy 0, policy_version 102268 (0.0016) [2023-03-09 09:47:04,059][22664] Fps is (10 sec: 199888.7, 60 sec: 197972.8, 300 sec: 197996.6). Total num frames: 1675657216. Throughput: 0: 49448.0. Samples: 418932384. Policy #0 lag: (min: 1.0, avg: 18.2, max: 33.0) [2023-03-09 09:47:04,060][22664] Avg episode reward: [(0, '53.248')] [2023-03-09 09:47:04,398][23090] Updated weights for policy 0, policy_version 102278 (0.0013) [2023-03-09 09:47:05,170][23090] Updated weights for policy 0, policy_version 102288 (0.0013) [2023-03-09 09:47:06,015][23090] Updated weights for policy 0, policy_version 102298 (0.0022) [2023-03-09 09:47:06,897][23090] Updated weights for policy 0, policy_version 102308 (0.0024) [2023-03-09 09:47:07,598][23090] Updated weights for policy 0, policy_version 102318 (0.0016) [2023-03-09 09:47:08,355][23090] Updated weights for policy 0, policy_version 102328 (0.0019) [2023-03-09 09:47:09,059][22664] Fps is (10 sec: 201516.9, 60 sec: 198791.6, 300 sec: 198052.2). Total num frames: 1676673024. Throughput: 0: 49493.9. Samples: 419229232. Policy #0 lag: (min: 1.0, avg: 18.2, max: 33.0) [2023-03-09 09:47:09,061][22664] Avg episode reward: [(0, '54.513')] [2023-03-09 09:47:09,291][23090] Updated weights for policy 0, policy_version 102338 (0.0016) [2023-03-09 09:47:10,180][23090] Updated weights for policy 0, policy_version 102348 (0.0021) [2023-03-09 09:47:10,838][23090] Updated weights for policy 0, policy_version 102358 (0.0013) [2023-03-09 09:47:11,718][23090] Updated weights for policy 0, policy_version 102368 (0.0016) [2023-03-09 09:47:12,724][22940] Signal inference workers to stop experience collection... (34350 times) [2023-03-09 09:47:12,747][22940] Signal inference workers to resume experience collection... (34350 times) [2023-03-09 09:47:12,755][23090] InferenceWorker_p0-w0: stopping experience collection (34350 times) [2023-03-09 09:47:12,757][23090] InferenceWorker_p0-w0: resuming experience collection (34350 times) [2023-03-09 09:47:12,761][23090] Updated weights for policy 0, policy_version 102378 (0.0018) [2023-03-09 09:47:13,485][23090] Updated weights for policy 0, policy_version 102389 (0.0022) [2023-03-09 09:47:14,059][22664] Fps is (10 sec: 198248.1, 60 sec: 197973.2, 300 sec: 197996.5). Total num frames: 1677639680. Throughput: 0: 49539.8. Samples: 419378688. Policy #0 lag: (min: 1.0, avg: 18.2, max: 33.0) [2023-03-09 09:47:14,060][22664] Avg episode reward: [(0, '55.287')] [2023-03-09 09:47:14,280][23090] Updated weights for policy 0, policy_version 102399 (0.0013) [2023-03-09 09:47:15,363][23090] Updated weights for policy 0, policy_version 102409 (0.0020) [2023-03-09 09:47:15,991][23090] Updated weights for policy 0, policy_version 102419 (0.0019) [2023-03-09 09:47:16,823][23090] Updated weights for policy 0, policy_version 102429 (0.0013) [2023-03-09 09:47:17,763][23090] Updated weights for policy 0, policy_version 102439 (0.0016) [2023-03-09 09:47:18,531][23090] Updated weights for policy 0, policy_version 102449 (0.0023) [2023-03-09 09:47:19,059][22664] Fps is (10 sec: 196611.3, 60 sec: 197973.6, 300 sec: 198107.4). Total num frames: 1678639104. Throughput: 0: 49400.3. Samples: 419671408. Policy #0 lag: (min: 1.0, avg: 18.2, max: 33.0) [2023-03-09 09:47:19,060][22664] Avg episode reward: [(0, '54.012')] [2023-03-09 09:47:19,071][22940] Saving /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000102456_1678639104.pth... [2023-03-09 09:47:19,128][22940] Removing /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000099555_1631109120.pth [2023-03-09 09:47:19,348][23090] Updated weights for policy 0, policy_version 102459 (0.0017) [2023-03-09 09:47:20,272][23090] Updated weights for policy 0, policy_version 102469 (0.0013) [2023-03-09 09:47:21,005][23090] Updated weights for policy 0, policy_version 102479 (0.0017) [2023-03-09 09:47:21,845][23090] Updated weights for policy 0, policy_version 102489 (0.0019) [2023-03-09 09:47:22,737][23090] Updated weights for policy 0, policy_version 102499 (0.0024) [2023-03-09 09:47:23,614][23090] Updated weights for policy 0, policy_version 102510 (0.0013) [2023-03-09 09:47:24,058][22664] Fps is (10 sec: 198247.8, 60 sec: 197701.2, 300 sec: 198052.1). Total num frames: 1679622144. Throughput: 0: 49357.5. Samples: 419966208. Policy #0 lag: (min: 1.0, avg: 18.2, max: 33.0) [2023-03-09 09:47:24,059][22664] Avg episode reward: [(0, '52.643')] [2023-03-09 09:47:24,349][23090] Updated weights for policy 0, policy_version 102520 (0.0014) [2023-03-09 09:47:25,290][23090] Updated weights for policy 0, policy_version 102530 (0.0017) [2023-03-09 09:47:25,930][22940] Signal inference workers to stop experience collection... (34400 times) [2023-03-09 09:47:25,945][22940] Signal inference workers to resume experience collection... (34400 times) [2023-03-09 09:47:25,978][23090] InferenceWorker_p0-w0: stopping experience collection (34400 times) [2023-03-09 09:47:26,026][23090] InferenceWorker_p0-w0: resuming experience collection (34400 times) [2023-03-09 09:47:26,158][23090] Updated weights for policy 0, policy_version 102541 (0.0013) [2023-03-09 09:47:27,013][23090] Updated weights for policy 0, policy_version 102552 (0.0017) [2023-03-09 09:47:27,938][23090] Updated weights for policy 0, policy_version 102562 (0.0016) [2023-03-09 09:47:28,768][23090] Updated weights for policy 0, policy_version 102572 (0.0013) [2023-03-09 09:47:29,059][22664] Fps is (10 sec: 196603.8, 60 sec: 197426.7, 300 sec: 197996.2). Total num frames: 1680605184. Throughput: 0: 49355.0. Samples: 420113568. Policy #0 lag: (min: 1.0, avg: 18.2, max: 33.0) [2023-03-09 09:47:29,061][22664] Avg episode reward: [(0, '52.316')] [2023-03-09 09:47:29,466][23090] Updated weights for policy 0, policy_version 102582 (0.0014) [2023-03-09 09:47:30,356][23090] Updated weights for policy 0, policy_version 102592 (0.0013) [2023-03-09 09:47:31,323][23090] Updated weights for policy 0, policy_version 102602 (0.0016) [2023-03-09 09:47:31,966][23090] Updated weights for policy 0, policy_version 102612 (0.0013) [2023-03-09 09:47:32,784][23090] Updated weights for policy 0, policy_version 102622 (0.0018) [2023-03-09 09:47:33,781][23090] Updated weights for policy 0, policy_version 102632 (0.0015) [2023-03-09 09:47:34,059][22664] Fps is (10 sec: 194968.7, 60 sec: 197427.1, 300 sec: 197885.4). Total num frames: 1681571840. Throughput: 0: 49404.0. Samples: 420412560. Policy #0 lag: (min: 1.0, avg: 18.2, max: 33.0) [2023-03-09 09:47:34,060][22664] Avg episode reward: [(0, '55.358')] [2023-03-09 09:47:34,501][23090] Updated weights for policy 0, policy_version 102642 (0.0016) [2023-03-09 09:47:35,330][23090] Updated weights for policy 0, policy_version 102652 (0.0016) [2023-03-09 09:47:36,281][23090] Updated weights for policy 0, policy_version 102662 (0.0013) [2023-03-09 09:47:37,030][23090] Updated weights for policy 0, policy_version 102672 (0.0016) [2023-03-09 09:47:37,247][22940] Signal inference workers to stop experience collection... (34450 times) [2023-03-09 09:47:37,248][22940] Signal inference workers to resume experience collection... (34450 times) [2023-03-09 09:47:37,337][23090] InferenceWorker_p0-w0: stopping experience collection (34450 times) [2023-03-09 09:47:37,337][23090] InferenceWorker_p0-w0: resuming experience collection (34450 times) [2023-03-09 09:47:37,867][23090] Updated weights for policy 0, policy_version 102682 (0.0016) [2023-03-09 09:47:38,754][23090] Updated weights for policy 0, policy_version 102692 (0.0014) [2023-03-09 09:47:39,058][22664] Fps is (10 sec: 193339.6, 60 sec: 196608.9, 300 sec: 197718.9). Total num frames: 1682538496. Throughput: 0: 49356.4. Samples: 420709280. Policy #0 lag: (min: 3.0, avg: 16.7, max: 34.0) [2023-03-09 09:47:39,059][22664] Avg episode reward: [(0, '54.643')] [2023-03-09 09:47:39,522][23090] Updated weights for policy 0, policy_version 102702 (0.0017) [2023-03-09 09:47:40,289][23090] Updated weights for policy 0, policy_version 102712 (0.0016) [2023-03-09 09:47:41,232][23090] Updated weights for policy 0, policy_version 102722 (0.0016) [2023-03-09 09:47:42,088][23090] Updated weights for policy 0, policy_version 102732 (0.0021) [2023-03-09 09:47:42,769][23090] Updated weights for policy 0, policy_version 102742 (0.0023) [2023-03-09 09:47:43,659][23090] Updated weights for policy 0, policy_version 102752 (0.0020) [2023-03-09 09:47:44,059][22664] Fps is (10 sec: 196604.1, 60 sec: 196880.8, 300 sec: 197829.9). Total num frames: 1683537920. Throughput: 0: 49310.8. Samples: 420854672. Policy #0 lag: (min: 3.0, avg: 16.7, max: 34.0) [2023-03-09 09:47:44,061][22664] Avg episode reward: [(0, '55.253')] [2023-03-09 09:47:44,625][23090] Updated weights for policy 0, policy_version 102762 (0.0019) [2023-03-09 09:47:45,266][23090] Updated weights for policy 0, policy_version 102772 (0.0014) [2023-03-09 09:47:46,076][23090] Updated weights for policy 0, policy_version 102782 (0.0017) [2023-03-09 09:47:47,070][23090] Updated weights for policy 0, policy_version 102792 (0.0013) [2023-03-09 09:47:47,763][23090] Updated weights for policy 0, policy_version 102802 (0.0012) [2023-03-09 09:47:48,551][23090] Updated weights for policy 0, policy_version 102812 (0.0015) [2023-03-09 09:47:49,058][22664] Fps is (10 sec: 201523.0, 60 sec: 197428.0, 300 sec: 197830.2). Total num frames: 1684553728. Throughput: 0: 49359.8. Samples: 421153568. Policy #0 lag: (min: 3.0, avg: 16.7, max: 34.0) [2023-03-09 09:47:49,059][22664] Avg episode reward: [(0, '53.323')] [2023-03-09 09:47:49,485][23090] Updated weights for policy 0, policy_version 102822 (0.0019) [2023-03-09 09:47:49,771][22940] Signal inference workers to stop experience collection... (34500 times) [2023-03-09 09:47:49,773][22940] Signal inference workers to resume experience collection... (34500 times) [2023-03-09 09:47:49,843][23090] InferenceWorker_p0-w0: stopping experience collection (34500 times) [2023-03-09 09:47:49,843][23090] InferenceWorker_p0-w0: resuming experience collection (34500 times) [2023-03-09 09:47:50,288][23090] Updated weights for policy 0, policy_version 102832 (0.0015) [2023-03-09 09:47:51,087][23090] Updated weights for policy 0, policy_version 102842 (0.0013) [2023-03-09 09:47:51,970][23090] Updated weights for policy 0, policy_version 102852 (0.0013) [2023-03-09 09:47:52,892][23090] Updated weights for policy 0, policy_version 102864 (0.0013) [2023-03-09 09:47:53,668][23090] Updated weights for policy 0, policy_version 102874 (0.0020) [2023-03-09 09:47:54,059][22664] Fps is (10 sec: 203160.5, 60 sec: 198519.6, 300 sec: 197941.0). Total num frames: 1685569536. Throughput: 0: 49405.6. Samples: 421452480. Policy #0 lag: (min: 3.0, avg: 16.7, max: 34.0) [2023-03-09 09:47:54,060][22664] Avg episode reward: [(0, '54.495')] [2023-03-09 09:47:54,637][23090] Updated weights for policy 0, policy_version 102884 (0.0016) [2023-03-09 09:47:55,410][23090] Updated weights for policy 0, policy_version 102894 (0.0018) [2023-03-09 09:47:56,254][23090] Updated weights for policy 0, policy_version 102905 (0.0013) [2023-03-09 09:47:57,169][23090] Updated weights for policy 0, policy_version 102915 (0.0013) [2023-03-09 09:47:57,931][23090] Updated weights for policy 0, policy_version 102925 (0.0017) [2023-03-09 09:47:58,631][23090] Updated weights for policy 0, policy_version 102935 (0.0017) [2023-03-09 09:47:58,998][22940] Signal inference workers to stop experience collection... (34550 times) [2023-03-09 09:47:59,015][22940] Signal inference workers to resume experience collection... (34550 times) [2023-03-09 09:47:59,059][22664] Fps is (10 sec: 199882.8, 60 sec: 198246.3, 300 sec: 197996.6). Total num frames: 1686552576. Throughput: 0: 49405.4. Samples: 421601936. Policy #0 lag: (min: 3.0, avg: 16.7, max: 34.0) [2023-03-09 09:47:59,060][22664] Avg episode reward: [(0, '53.710')] [2023-03-09 09:47:59,070][23090] InferenceWorker_p0-w0: stopping experience collection (34550 times) [2023-03-09 09:47:59,070][23090] InferenceWorker_p0-w0: resuming experience collection (34550 times) [2023-03-09 09:47:59,565][23090] Updated weights for policy 0, policy_version 102945 (0.0017) [2023-03-09 09:48:00,524][23090] Updated weights for policy 0, policy_version 102955 (0.0017) [2023-03-09 09:48:01,144][23090] Updated weights for policy 0, policy_version 102965 (0.0018) [2023-03-09 09:48:02,026][23090] Updated weights for policy 0, policy_version 102975 (0.0014) [2023-03-09 09:48:03,017][23090] Updated weights for policy 0, policy_version 102985 (0.0013) [2023-03-09 09:48:03,711][23090] Updated weights for policy 0, policy_version 102995 (0.0016) [2023-03-09 09:48:04,058][22664] Fps is (10 sec: 196613.9, 60 sec: 197973.9, 300 sec: 198107.7). Total num frames: 1687535616. Throughput: 0: 49497.9. Samples: 421898800. Policy #0 lag: (min: 3.0, avg: 16.7, max: 34.0) [2023-03-09 09:48:04,059][22664] Avg episode reward: [(0, '55.103')] [2023-03-09 09:48:04,479][23090] Updated weights for policy 0, policy_version 103005 (0.0013) [2023-03-09 09:48:05,471][23090] Updated weights for policy 0, policy_version 103015 (0.0021) [2023-03-09 09:48:06,195][23090] Updated weights for policy 0, policy_version 103025 (0.0016) [2023-03-09 09:48:07,004][23090] Updated weights for policy 0, policy_version 103035 (0.0013) [2023-03-09 09:48:07,902][23090] Updated weights for policy 0, policy_version 103045 (0.0016) [2023-03-09 09:48:08,839][23090] Updated weights for policy 0, policy_version 103056 (0.0013) [2023-03-09 09:48:09,059][22664] Fps is (10 sec: 198247.4, 60 sec: 197701.3, 300 sec: 198107.5). Total num frames: 1688535040. Throughput: 0: 49498.9. Samples: 422193664. Policy #0 lag: (min: 3.0, avg: 16.7, max: 34.0) [2023-03-09 09:48:09,060][22664] Avg episode reward: [(0, '54.237')] [2023-03-09 09:48:09,613][23090] Updated weights for policy 0, policy_version 103066 (0.0016) [2023-03-09 09:48:09,692][22940] Signal inference workers to stop experience collection... (34600 times) [2023-03-09 09:48:09,710][22940] Signal inference workers to resume experience collection... (34600 times) [2023-03-09 09:48:09,733][23090] InferenceWorker_p0-w0: stopping experience collection (34600 times) [2023-03-09 09:48:09,733][23090] InferenceWorker_p0-w0: resuming experience collection (34600 times) [2023-03-09 09:48:10,533][23090] Updated weights for policy 0, policy_version 103076 (0.0016) [2023-03-09 09:48:11,267][23090] Updated weights for policy 0, policy_version 103086 (0.0015) [2023-03-09 09:48:12,097][23090] Updated weights for policy 0, policy_version 103096 (0.0016) [2023-03-09 09:48:13,021][23090] Updated weights for policy 0, policy_version 103106 (0.0016) [2023-03-09 09:48:13,883][23090] Updated weights for policy 0, policy_version 103116 (0.0019) [2023-03-09 09:48:14,059][22664] Fps is (10 sec: 194964.1, 60 sec: 197426.5, 300 sec: 197940.9). Total num frames: 1689485312. Throughput: 0: 49544.4. Samples: 422343056. Policy #0 lag: (min: 3.0, avg: 16.7, max: 34.0) [2023-03-09 09:48:14,060][22664] Avg episode reward: [(0, '54.107')] [2023-03-09 09:48:14,553][23090] Updated weights for policy 0, policy_version 103126 (0.0016) [2023-03-09 09:48:15,428][23090] Updated weights for policy 0, policy_version 103136 (0.0019) [2023-03-09 09:48:16,403][23090] Updated weights for policy 0, policy_version 103146 (0.0018) [2023-03-09 09:48:17,051][23090] Updated weights for policy 0, policy_version 103156 (0.0017) [2023-03-09 09:48:17,858][23090] Updated weights for policy 0, policy_version 103166 (0.0016) [2023-03-09 09:48:18,885][23090] Updated weights for policy 0, policy_version 103176 (0.0017) [2023-03-09 09:48:19,059][22664] Fps is (10 sec: 193326.7, 60 sec: 197153.9, 300 sec: 197829.6). Total num frames: 1690468352. Throughput: 0: 49406.6. Samples: 422635872. Policy #0 lag: (min: 3.0, avg: 16.7, max: 34.0) [2023-03-09 09:48:19,060][22664] Avg episode reward: [(0, '55.114')] [2023-03-09 09:48:19,667][23090] Updated weights for policy 0, policy_version 103187 (0.0017) [2023-03-09 09:48:20,299][22940] Signal inference workers to stop experience collection... (34650 times) [2023-03-09 09:48:20,319][22940] Signal inference workers to resume experience collection... (34650 times) [2023-03-09 09:48:20,347][23090] InferenceWorker_p0-w0: stopping experience collection (34650 times) [2023-03-09 09:48:20,396][23090] InferenceWorker_p0-w0: resuming experience collection (34650 times) [2023-03-09 09:48:20,434][23090] Updated weights for policy 0, policy_version 103197 (0.0019) [2023-03-09 09:48:21,428][23090] Updated weights for policy 0, policy_version 103207 (0.0020) [2023-03-09 09:48:22,204][23090] Updated weights for policy 0, policy_version 103217 (0.0013) [2023-03-09 09:48:23,047][23090] Updated weights for policy 0, policy_version 103228 (0.0017) [2023-03-09 09:48:24,018][23090] Updated weights for policy 0, policy_version 103238 (0.0022) [2023-03-09 09:48:24,059][22664] Fps is (10 sec: 196606.5, 60 sec: 197153.0, 300 sec: 197830.1). Total num frames: 1691451392. Throughput: 0: 49409.8. Samples: 422932736. Policy #0 lag: (min: 3.0, avg: 16.7, max: 34.0) [2023-03-09 09:48:24,061][22664] Avg episode reward: [(0, '55.124')] [2023-03-09 09:48:24,797][23090] Updated weights for policy 0, policy_version 103248 (0.0020) [2023-03-09 09:48:25,572][23090] Updated weights for policy 0, policy_version 103258 (0.0018) [2023-03-09 09:48:26,488][23090] Updated weights for policy 0, policy_version 103268 (0.0016) [2023-03-09 09:48:27,228][23090] Updated weights for policy 0, policy_version 103278 (0.0019) [2023-03-09 09:48:28,027][23090] Updated weights for policy 0, policy_version 103288 (0.0015) [2023-03-09 09:48:28,880][23090] Updated weights for policy 0, policy_version 103298 (0.0018) [2023-03-09 09:48:29,059][22664] Fps is (10 sec: 198251.5, 60 sec: 197428.5, 300 sec: 197885.4). Total num frames: 1692450816. Throughput: 0: 49500.6. Samples: 423082192. Policy #0 lag: (min: 3.0, avg: 16.7, max: 34.0) [2023-03-09 09:48:29,059][22664] Avg episode reward: [(0, '56.429')] [2023-03-09 09:48:29,780][23090] Updated weights for policy 0, policy_version 103309 (0.0018) [2023-03-09 09:48:30,511][23090] Updated weights for policy 0, policy_version 103319 (0.0012) [2023-03-09 09:48:30,957][22940] Signal inference workers to stop experience collection... (34700 times) [2023-03-09 09:48:30,974][22940] Signal inference workers to resume experience collection... (34700 times) [2023-03-09 09:48:30,997][23090] InferenceWorker_p0-w0: stopping experience collection (34700 times) [2023-03-09 09:48:31,037][23090] InferenceWorker_p0-w0: resuming experience collection (34700 times) [2023-03-09 09:48:31,404][23090] Updated weights for policy 0, policy_version 103329 (0.0015) [2023-03-09 09:48:32,393][23090] Updated weights for policy 0, policy_version 103340 (0.0013) [2023-03-09 09:48:33,110][23090] Updated weights for policy 0, policy_version 103350 (0.0016) [2023-03-09 09:48:33,942][23090] Updated weights for policy 0, policy_version 103360 (0.0013) [2023-03-09 09:48:34,058][22664] Fps is (10 sec: 199891.3, 60 sec: 197973.4, 300 sec: 197774.5). Total num frames: 1693450240. Throughput: 0: 49457.1. Samples: 423379136. Policy #0 lag: (min: 3.0, avg: 16.7, max: 34.0) [2023-03-09 09:48:34,059][22664] Avg episode reward: [(0, '55.508')] [2023-03-09 09:48:34,945][23090] Updated weights for policy 0, policy_version 103371 (0.0018) [2023-03-09 09:48:35,685][23090] Updated weights for policy 0, policy_version 103381 (0.0017) [2023-03-09 09:48:36,484][23090] Updated weights for policy 0, policy_version 103391 (0.0022) [2023-03-09 09:48:37,482][23090] Updated weights for policy 0, policy_version 103401 (0.0013) [2023-03-09 09:48:38,174][23090] Updated weights for policy 0, policy_version 103411 (0.0027) [2023-03-09 09:48:38,925][23090] Updated weights for policy 0, policy_version 103421 (0.0017) [2023-03-09 09:48:39,059][22664] Fps is (10 sec: 201515.4, 60 sec: 198791.1, 300 sec: 197940.8). Total num frames: 1694466048. Throughput: 0: 49409.3. Samples: 423675904. Policy #0 lag: (min: 0.0, avg: 16.2, max: 33.0) [2023-03-09 09:48:39,061][22664] Avg episode reward: [(0, '53.745')] [2023-03-09 09:48:39,939][23090] Updated weights for policy 0, policy_version 103431 (0.0016) [2023-03-09 09:48:40,753][23090] Updated weights for policy 0, policy_version 103441 (0.0016) [2023-03-09 09:48:41,373][22940] Signal inference workers to stop experience collection... (34750 times) [2023-03-09 09:48:41,375][22940] Signal inference workers to resume experience collection... (34750 times) [2023-03-09 09:48:41,439][23090] InferenceWorker_p0-w0: stopping experience collection (34750 times) [2023-03-09 09:48:41,440][23090] InferenceWorker_p0-w0: resuming experience collection (34750 times) [2023-03-09 09:48:41,488][23090] Updated weights for policy 0, policy_version 103451 (0.0016) [2023-03-09 09:48:42,469][23090] Updated weights for policy 0, policy_version 103461 (0.0013) [2023-03-09 09:48:43,162][23090] Updated weights for policy 0, policy_version 103471 (0.0013) [2023-03-09 09:48:44,006][23090] Updated weights for policy 0, policy_version 103481 (0.0014) [2023-03-09 09:48:44,059][22664] Fps is (10 sec: 198245.6, 60 sec: 198247.0, 300 sec: 197885.4). Total num frames: 1695432704. Throughput: 0: 49408.8. Samples: 423825328. Policy #0 lag: (min: 0.0, avg: 16.2, max: 33.0) [2023-03-09 09:48:44,060][22664] Avg episode reward: [(0, '53.766')] [2023-03-09 09:48:44,962][23090] Updated weights for policy 0, policy_version 103491 (0.0017) [2023-03-09 09:48:45,646][23090] Updated weights for policy 0, policy_version 103501 (0.0013) [2023-03-09 09:48:46,354][23090] Updated weights for policy 0, policy_version 103511 (0.0016) [2023-03-09 09:48:47,239][23090] Updated weights for policy 0, policy_version 103521 (0.0013) [2023-03-09 09:48:48,231][23090] Updated weights for policy 0, policy_version 103532 (0.0013) [2023-03-09 09:48:48,889][23090] Updated weights for policy 0, policy_version 103542 (0.0023) [2023-03-09 09:48:49,059][22664] Fps is (10 sec: 198252.6, 60 sec: 198246.1, 300 sec: 198052.0). Total num frames: 1696448512. Throughput: 0: 49453.0. Samples: 424124192. Policy #0 lag: (min: 0.0, avg: 16.2, max: 33.0) [2023-03-09 09:48:49,060][22664] Avg episode reward: [(0, '55.209')] [2023-03-09 09:48:49,727][23090] Updated weights for policy 0, policy_version 103552 (0.0018) [2023-03-09 09:48:50,720][23090] Updated weights for policy 0, policy_version 103562 (0.0019) [2023-03-09 09:48:50,768][22940] Signal inference workers to stop experience collection... (34800 times) [2023-03-09 09:48:50,771][22940] Signal inference workers to resume experience collection... (34800 times) [2023-03-09 09:48:50,842][23090] InferenceWorker_p0-w0: stopping experience collection (34800 times) [2023-03-09 09:48:50,842][23090] InferenceWorker_p0-w0: resuming experience collection (34800 times) [2023-03-09 09:48:51,423][23090] Updated weights for policy 0, policy_version 103572 (0.0020) [2023-03-09 09:48:52,196][23090] Updated weights for policy 0, policy_version 103582 (0.0016) [2023-03-09 09:48:53,225][23090] Updated weights for policy 0, policy_version 103592 (0.0017) [2023-03-09 09:48:54,033][23090] Updated weights for policy 0, policy_version 103602 (0.0013) [2023-03-09 09:48:54,058][22664] Fps is (10 sec: 199886.0, 60 sec: 197701.2, 300 sec: 197996.7). Total num frames: 1697431552. Throughput: 0: 49498.4. Samples: 424421088. Policy #0 lag: (min: 0.0, avg: 16.2, max: 33.0) [2023-03-09 09:48:54,059][22664] Avg episode reward: [(0, '55.077')] [2023-03-09 09:48:54,793][23090] Updated weights for policy 0, policy_version 103613 (0.0016) [2023-03-09 09:48:55,790][23090] Updated weights for policy 0, policy_version 103623 (0.0013) [2023-03-09 09:48:56,567][23090] Updated weights for policy 0, policy_version 103633 (0.0013) [2023-03-09 09:48:57,413][23090] Updated weights for policy 0, policy_version 103644 (0.0015) [2023-03-09 09:48:58,329][23090] Updated weights for policy 0, policy_version 103654 (0.0016) [2023-03-09 09:48:59,059][22664] Fps is (10 sec: 196607.3, 60 sec: 197700.2, 300 sec: 197940.9). Total num frames: 1698414592. Throughput: 0: 49454.3. Samples: 424568496. Policy #0 lag: (min: 0.0, avg: 16.2, max: 33.0) [2023-03-09 09:48:59,060][22664] Avg episode reward: [(0, '56.829')] [2023-03-09 09:48:59,202][23090] Updated weights for policy 0, policy_version 103664 (0.0013) [2023-03-09 09:48:59,941][23090] Updated weights for policy 0, policy_version 103674 (0.0021) [2023-03-09 09:48:59,946][22940] Signal inference workers to stop experience collection... (34850 times) [2023-03-09 09:48:59,948][22940] Signal inference workers to resume experience collection... (34850 times) [2023-03-09 09:49:00,021][23090] InferenceWorker_p0-w0: stopping experience collection (34850 times) [2023-03-09 09:49:00,022][23090] InferenceWorker_p0-w0: resuming experience collection (34850 times) [2023-03-09 09:49:00,844][23090] Updated weights for policy 0, policy_version 103684 (0.0017) [2023-03-09 09:49:01,585][23090] Updated weights for policy 0, policy_version 103694 (0.0015) [2023-03-09 09:49:02,505][23090] Updated weights for policy 0, policy_version 103705 (0.0013) [2023-03-09 09:49:03,475][23090] Updated weights for policy 0, policy_version 103715 (0.0016) [2023-03-09 09:49:04,059][22664] Fps is (10 sec: 198230.8, 60 sec: 197970.7, 300 sec: 197940.4). Total num frames: 1699414016. Throughput: 0: 49589.2. Samples: 424867408. Policy #0 lag: (min: 0.0, avg: 16.2, max: 33.0) [2023-03-09 09:49:04,062][22664] Avg episode reward: [(0, '55.635')] [2023-03-09 09:49:04,261][23090] Updated weights for policy 0, policy_version 103726 (0.0016) [2023-03-09 09:49:05,042][23090] Updated weights for policy 0, policy_version 103736 (0.0013) [2023-03-09 09:49:05,985][23090] Updated weights for policy 0, policy_version 103746 (0.0016) [2023-03-09 09:49:06,739][23090] Updated weights for policy 0, policy_version 103756 (0.0013) [2023-03-09 09:49:07,397][23090] Updated weights for policy 0, policy_version 103766 (0.0015) [2023-03-09 09:49:08,275][23090] Updated weights for policy 0, policy_version 103776 (0.0017) [2023-03-09 09:49:09,058][22664] Fps is (10 sec: 196610.6, 60 sec: 197427.4, 300 sec: 197830.0). Total num frames: 1700380672. Throughput: 0: 49634.1. Samples: 425166256. Policy #0 lag: (min: 0.0, avg: 16.2, max: 33.0) [2023-03-09 09:49:09,059][22664] Avg episode reward: [(0, '54.950')] [2023-03-09 09:49:09,256][23090] Updated weights for policy 0, policy_version 103786 (0.0016) [2023-03-09 09:49:09,303][22940] Signal inference workers to stop experience collection... (34900 times) [2023-03-09 09:49:09,307][22940] Signal inference workers to resume experience collection... (34900 times) [2023-03-09 09:49:09,386][23090] InferenceWorker_p0-w0: stopping experience collection (34900 times) [2023-03-09 09:49:09,387][23090] InferenceWorker_p0-w0: resuming experience collection (34900 times) [2023-03-09 09:49:09,975][23090] Updated weights for policy 0, policy_version 103796 (0.0014) [2023-03-09 09:49:10,850][23090] Updated weights for policy 0, policy_version 103807 (0.0019) [2023-03-09 09:49:11,859][23090] Updated weights for policy 0, policy_version 103817 (0.0019) [2023-03-09 09:49:12,574][23090] Updated weights for policy 0, policy_version 103827 (0.0013) [2023-03-09 09:49:13,380][23090] Updated weights for policy 0, policy_version 103837 (0.0021) [2023-03-09 09:49:14,059][22664] Fps is (10 sec: 194973.7, 60 sec: 197972.3, 300 sec: 197885.0). Total num frames: 1701363712. Throughput: 0: 49587.0. Samples: 425313632. Policy #0 lag: (min: 0.0, avg: 16.2, max: 33.0) [2023-03-09 09:49:14,062][22664] Avg episode reward: [(0, '55.457')] [2023-03-09 09:49:14,365][23090] Updated weights for policy 0, policy_version 103847 (0.0016) [2023-03-09 09:49:15,085][23090] Updated weights for policy 0, policy_version 103857 (0.0012) [2023-03-09 09:49:15,852][23090] Updated weights for policy 0, policy_version 103867 (0.0014) [2023-03-09 09:49:16,801][23090] Updated weights for policy 0, policy_version 103877 (0.0020) [2023-03-09 09:49:17,505][23090] Updated weights for policy 0, policy_version 103887 (0.0013) [2023-03-09 09:49:18,343][23090] Updated weights for policy 0, policy_version 103897 (0.0013) [2023-03-09 09:49:18,431][22940] Signal inference workers to stop experience collection... (34950 times) [2023-03-09 09:49:18,432][22940] Signal inference workers to resume experience collection... (34950 times) [2023-03-09 09:49:18,503][23090] InferenceWorker_p0-w0: stopping experience collection (34950 times) [2023-03-09 09:49:18,504][23090] InferenceWorker_p0-w0: resuming experience collection (34950 times) [2023-03-09 09:49:19,059][22664] Fps is (10 sec: 199877.1, 60 sec: 198519.1, 300 sec: 197940.8). Total num frames: 1702379520. Throughput: 0: 49581.4. Samples: 425610320. Policy #0 lag: (min: 0.0, avg: 16.2, max: 33.0) [2023-03-09 09:49:19,061][22664] Avg episode reward: [(0, '53.831')] [2023-03-09 09:49:19,118][22940] Saving /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000103906_1702395904.pth... [2023-03-09 09:49:19,172][22940] Removing /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000101006_1654882304.pth [2023-03-09 09:49:19,296][23090] Updated weights for policy 0, policy_version 103907 (0.0020) [2023-03-09 09:49:19,985][23090] Updated weights for policy 0, policy_version 103917 (0.0017) [2023-03-09 09:49:20,679][23090] Updated weights for policy 0, policy_version 103927 (0.0019) [2023-03-09 09:49:21,587][23090] Updated weights for policy 0, policy_version 103937 (0.0024) [2023-03-09 09:49:22,476][23090] Updated weights for policy 0, policy_version 103947 (0.0013) [2023-03-09 09:49:23,174][23090] Updated weights for policy 0, policy_version 103957 (0.0018) [2023-03-09 09:49:24,059][22664] Fps is (10 sec: 203167.8, 60 sec: 199065.8, 300 sec: 198052.1). Total num frames: 1703395328. Throughput: 0: 49628.3. Samples: 425909168. Policy #0 lag: (min: 0.0, avg: 16.2, max: 33.0) [2023-03-09 09:49:24,060][22664] Avg episode reward: [(0, '50.157')] [2023-03-09 09:49:24,086][23090] Updated weights for policy 0, policy_version 103967 (0.0016) [2023-03-09 09:49:25,027][23090] Updated weights for policy 0, policy_version 103977 (0.0015) [2023-03-09 09:49:25,752][23090] Updated weights for policy 0, policy_version 103987 (0.0017) [2023-03-09 09:49:26,477][23090] Updated weights for policy 0, policy_version 103997 (0.0013) [2023-03-09 09:49:26,694][22940] Signal inference workers to stop experience collection... (35000 times) [2023-03-09 09:49:26,695][22940] Signal inference workers to resume experience collection... (35000 times) [2023-03-09 09:49:26,758][23090] InferenceWorker_p0-w0: stopping experience collection (35000 times) [2023-03-09 09:49:26,761][23090] InferenceWorker_p0-w0: resuming experience collection (35000 times) [2023-03-09 09:49:27,489][23090] Updated weights for policy 0, policy_version 104007 (0.0018) [2023-03-09 09:49:28,230][23090] Updated weights for policy 0, policy_version 104017 (0.0013) [2023-03-09 09:49:29,037][23090] Updated weights for policy 0, policy_version 104027 (0.0017) [2023-03-09 09:49:29,059][22664] Fps is (10 sec: 201530.0, 60 sec: 199065.5, 300 sec: 198163.1). Total num frames: 1704394752. Throughput: 0: 49628.8. Samples: 426058624. Policy #0 lag: (min: 0.0, avg: 16.2, max: 33.0) [2023-03-09 09:49:29,060][22664] Avg episode reward: [(0, '54.537')] [2023-03-09 09:49:29,960][23090] Updated weights for policy 0, policy_version 104037 (0.0018) [2023-03-09 09:49:30,726][23090] Updated weights for policy 0, policy_version 104047 (0.0019) [2023-03-09 09:49:31,503][23090] Updated weights for policy 0, policy_version 104057 (0.0021) [2023-03-09 09:49:32,506][23090] Updated weights for policy 0, policy_version 104067 (0.0016) [2023-03-09 09:49:33,164][23090] Updated weights for policy 0, policy_version 104077 (0.0017) [2023-03-09 09:49:33,903][23090] Updated weights for policy 0, policy_version 104087 (0.0015) [2023-03-09 09:49:34,058][22664] Fps is (10 sec: 198251.0, 60 sec: 198792.5, 300 sec: 198163.1). Total num frames: 1705377792. Throughput: 0: 49631.0. Samples: 426357584. Policy #0 lag: (min: 0.0, avg: 16.2, max: 33.0) [2023-03-09 09:49:34,060][22664] Avg episode reward: [(0, '52.434')] [2023-03-09 09:49:34,778][23090] Updated weights for policy 0, policy_version 104097 (0.0021) [2023-03-09 09:49:35,658][23090] Updated weights for policy 0, policy_version 104107 (0.0020) [2023-03-09 09:49:36,081][22940] Signal inference workers to stop experience collection... (35050 times) [2023-03-09 09:49:36,081][22940] Signal inference workers to resume experience collection... (35050 times) [2023-03-09 09:49:36,149][23090] InferenceWorker_p0-w0: stopping experience collection (35050 times) [2023-03-09 09:49:36,152][23090] InferenceWorker_p0-w0: resuming experience collection (35050 times) [2023-03-09 09:49:36,359][23090] Updated weights for policy 0, policy_version 104117 (0.0013) [2023-03-09 09:49:37,278][23090] Updated weights for policy 0, policy_version 104127 (0.0013) [2023-03-09 09:49:38,270][23090] Updated weights for policy 0, policy_version 104138 (0.0013) [2023-03-09 09:49:39,017][23090] Updated weights for policy 0, policy_version 104148 (0.0016) [2023-03-09 09:49:39,059][22664] Fps is (10 sec: 198242.7, 60 sec: 198520.1, 300 sec: 198163.1). Total num frames: 1706377216. Throughput: 0: 49583.7. Samples: 426652368. Policy #0 lag: (min: 1.0, avg: 17.8, max: 33.0) [2023-03-09 09:49:39,060][22664] Avg episode reward: [(0, '54.077')] [2023-03-09 09:49:39,766][23090] Updated weights for policy 0, policy_version 104158 (0.0015) [2023-03-09 09:49:40,792][23090] Updated weights for policy 0, policy_version 104168 (0.0013) [2023-03-09 09:49:41,561][23090] Updated weights for policy 0, policy_version 104179 (0.0015) [2023-03-09 09:49:42,363][23090] Updated weights for policy 0, policy_version 104189 (0.0016) [2023-03-09 09:49:43,298][23090] Updated weights for policy 0, policy_version 104199 (0.0016) [2023-03-09 09:49:44,059][22664] Fps is (10 sec: 196606.7, 60 sec: 198519.3, 300 sec: 198052.1). Total num frames: 1707343872. Throughput: 0: 49629.2. Samples: 426801808. Policy #0 lag: (min: 1.0, avg: 17.8, max: 33.0) [2023-03-09 09:49:44,060][22664] Avg episode reward: [(0, '54.409')] [2023-03-09 09:49:44,103][23090] Updated weights for policy 0, policy_version 104209 (0.0021) [2023-03-09 09:49:44,829][23090] Updated weights for policy 0, policy_version 104219 (0.0016) [2023-03-09 09:49:45,784][23090] Updated weights for policy 0, policy_version 104229 (0.0023) [2023-03-09 09:49:46,540][23090] Updated weights for policy 0, policy_version 104239 (0.0022) [2023-03-09 09:49:46,747][22940] Signal inference workers to stop experience collection... (35100 times) [2023-03-09 09:49:46,766][22940] Signal inference workers to resume experience collection... (35100 times) [2023-03-09 09:49:46,787][23090] InferenceWorker_p0-w0: stopping experience collection (35100 times) [2023-03-09 09:49:46,787][23090] InferenceWorker_p0-w0: resuming experience collection (35100 times) [2023-03-09 09:49:47,326][23090] Updated weights for policy 0, policy_version 104249 (0.0032) [2023-03-09 09:49:48,286][23090] Updated weights for policy 0, policy_version 104259 (0.0018) [2023-03-09 09:49:49,058][22664] Fps is (10 sec: 196612.7, 60 sec: 198246.7, 300 sec: 197996.7). Total num frames: 1708343296. Throughput: 0: 49675.9. Samples: 427102784. Policy #0 lag: (min: 1.0, avg: 17.8, max: 33.0) [2023-03-09 09:49:49,059][22664] Avg episode reward: [(0, '54.315')] [2023-03-09 09:49:49,077][23090] Updated weights for policy 0, policy_version 104270 (0.0017) [2023-03-09 09:49:49,807][23090] Updated weights for policy 0, policy_version 104280 (0.0016) [2023-03-09 09:49:50,761][23090] Updated weights for policy 0, policy_version 104290 (0.0016) [2023-03-09 09:49:51,518][23090] Updated weights for policy 0, policy_version 104300 (0.0020) [2023-03-09 09:49:52,225][23090] Updated weights for policy 0, policy_version 104310 (0.0018) [2023-03-09 09:49:53,083][23090] Updated weights for policy 0, policy_version 104320 (0.0016) [2023-03-09 09:49:54,007][23090] Updated weights for policy 0, policy_version 104330 (0.0013) [2023-03-09 09:49:54,059][22664] Fps is (10 sec: 199881.5, 60 sec: 198518.6, 300 sec: 198051.8). Total num frames: 1709342720. Throughput: 0: 49718.5. Samples: 427403600. Policy #0 lag: (min: 1.0, avg: 17.8, max: 33.0) [2023-03-09 09:49:54,061][22664] Avg episode reward: [(0, '54.869')] [2023-03-09 09:49:54,778][23090] Updated weights for policy 0, policy_version 104340 (0.0016) [2023-03-09 09:49:55,383][22940] Signal inference workers to stop experience collection... (35150 times) [2023-03-09 09:49:55,402][22940] Signal inference workers to resume experience collection... (35150 times) [2023-03-09 09:49:55,462][23090] InferenceWorker_p0-w0: stopping experience collection (35150 times) [2023-03-09 09:49:55,462][23090] InferenceWorker_p0-w0: resuming experience collection (35150 times) [2023-03-09 09:49:55,574][23090] Updated weights for policy 0, policy_version 104350 (0.0017) [2023-03-09 09:49:56,534][23090] Updated weights for policy 0, policy_version 104360 (0.0016) [2023-03-09 09:49:57,290][23090] Updated weights for policy 0, policy_version 104370 (0.0017) [2023-03-09 09:49:58,078][23090] Updated weights for policy 0, policy_version 104380 (0.0013) [2023-03-09 09:49:59,024][23090] Updated weights for policy 0, policy_version 104390 (0.0016) [2023-03-09 09:49:59,059][22664] Fps is (10 sec: 198245.7, 60 sec: 198519.8, 300 sec: 198052.2). Total num frames: 1710325760. Throughput: 0: 49764.8. Samples: 427553024. Policy #0 lag: (min: 1.0, avg: 17.8, max: 33.0) [2023-03-09 09:49:59,060][22664] Avg episode reward: [(0, '54.673')] [2023-03-09 09:49:59,720][23090] Updated weights for policy 0, policy_version 104400 (0.0019) [2023-03-09 09:50:00,573][23090] Updated weights for policy 0, policy_version 104410 (0.0014) [2023-03-09 09:50:01,437][23090] Updated weights for policy 0, policy_version 104420 (0.0018) [2023-03-09 09:50:02,189][23090] Updated weights for policy 0, policy_version 104430 (0.0017) [2023-03-09 09:50:02,923][23090] Updated weights for policy 0, policy_version 104440 (0.0013) [2023-03-09 09:50:03,877][23090] Updated weights for policy 0, policy_version 104450 (0.0014) [2023-03-09 09:50:03,994][22940] Signal inference workers to stop experience collection... (35200 times) [2023-03-09 09:50:04,006][22940] Signal inference workers to resume experience collection... (35200 times) [2023-03-09 09:50:04,058][22664] Fps is (10 sec: 199889.5, 60 sec: 198795.0, 300 sec: 198107.8). Total num frames: 1711341568. Throughput: 0: 49812.0. Samples: 427851840. Policy #0 lag: (min: 1.0, avg: 17.8, max: 33.0) [2023-03-09 09:50:04,059][22664] Avg episode reward: [(0, '54.417')] [2023-03-09 09:50:04,062][23090] InferenceWorker_p0-w0: stopping experience collection (35200 times) [2023-03-09 09:50:04,062][23090] InferenceWorker_p0-w0: resuming experience collection (35200 times) [2023-03-09 09:50:04,672][23090] Updated weights for policy 0, policy_version 104460 (0.0017) [2023-03-09 09:50:05,359][23090] Updated weights for policy 0, policy_version 104470 (0.0013) [2023-03-09 09:50:06,201][23090] Updated weights for policy 0, policy_version 104480 (0.0016) [2023-03-09 09:50:07,184][23090] Updated weights for policy 0, policy_version 104490 (0.0016) [2023-03-09 09:50:07,877][23090] Updated weights for policy 0, policy_version 104500 (0.0013) [2023-03-09 09:50:08,657][23090] Updated weights for policy 0, policy_version 104510 (0.0013) [2023-03-09 09:50:09,059][22664] Fps is (10 sec: 201523.2, 60 sec: 199338.6, 300 sec: 198218.9). Total num frames: 1712340992. Throughput: 0: 49813.2. Samples: 428150752. Policy #0 lag: (min: 1.0, avg: 17.8, max: 33.0) [2023-03-09 09:50:09,060][22664] Avg episode reward: [(0, '54.623')] [2023-03-09 09:50:09,652][23090] Updated weights for policy 0, policy_version 104520 (0.0013) [2023-03-09 09:50:10,383][23090] Updated weights for policy 0, policy_version 104530 (0.0016) [2023-03-09 09:50:11,214][23090] Updated weights for policy 0, policy_version 104540 (0.0013) [2023-03-09 09:50:12,159][23090] Updated weights for policy 0, policy_version 104550 (0.0029) [2023-03-09 09:50:12,370][22940] Signal inference workers to stop experience collection... (35250 times) [2023-03-09 09:50:12,371][22940] Signal inference workers to resume experience collection... (35250 times) [2023-03-09 09:50:12,439][23090] InferenceWorker_p0-w0: stopping experience collection (35250 times) [2023-03-09 09:50:12,439][23090] InferenceWorker_p0-w0: resuming experience collection (35250 times) [2023-03-09 09:50:12,848][23090] Updated weights for policy 0, policy_version 104560 (0.0016) [2023-03-09 09:50:13,705][23090] Updated weights for policy 0, policy_version 104570 (0.0020) [2023-03-09 09:50:14,059][22664] Fps is (10 sec: 201517.1, 60 sec: 199885.6, 300 sec: 198274.2). Total num frames: 1713356800. Throughput: 0: 49857.8. Samples: 428302240. Policy #0 lag: (min: 1.0, avg: 17.8, max: 33.0) [2023-03-09 09:50:14,061][22664] Avg episode reward: [(0, '53.141')] [2023-03-09 09:50:14,569][23090] Updated weights for policy 0, policy_version 104580 (0.0016) [2023-03-09 09:50:15,304][23090] Updated weights for policy 0, policy_version 104590 (0.0015) [2023-03-09 09:50:16,064][23090] Updated weights for policy 0, policy_version 104600 (0.0016) [2023-03-09 09:50:16,985][23090] Updated weights for policy 0, policy_version 104610 (0.0016) [2023-03-09 09:50:17,830][23090] Updated weights for policy 0, policy_version 104620 (0.0018) [2023-03-09 09:50:18,533][23090] Updated weights for policy 0, policy_version 104630 (0.0013) [2023-03-09 09:50:19,058][22664] Fps is (10 sec: 199886.0, 60 sec: 199340.0, 300 sec: 198330.0). Total num frames: 1714339840. Throughput: 0: 49856.4. Samples: 428601120. Policy #0 lag: (min: 1.0, avg: 17.8, max: 33.0) [2023-03-09 09:50:19,059][22664] Avg episode reward: [(0, '53.923')] [2023-03-09 09:50:19,363][23090] Updated weights for policy 0, policy_version 104640 (0.0021) [2023-03-09 09:50:20,342][23090] Updated weights for policy 0, policy_version 104650 (0.0018) [2023-03-09 09:50:20,447][22940] Signal inference workers to stop experience collection... (35300 times) [2023-03-09 09:50:20,448][22940] Signal inference workers to resume experience collection... (35300 times) [2023-03-09 09:50:20,469][23090] InferenceWorker_p0-w0: stopping experience collection (35300 times) [2023-03-09 09:50:20,469][23090] InferenceWorker_p0-w0: resuming experience collection (35300 times) [2023-03-09 09:50:21,032][23090] Updated weights for policy 0, policy_version 104660 (0.0017) [2023-03-09 09:50:21,832][23090] Updated weights for policy 0, policy_version 104670 (0.0016) [2023-03-09 09:50:22,800][23090] Updated weights for policy 0, policy_version 104680 (0.0023) [2023-03-09 09:50:23,610][23090] Updated weights for policy 0, policy_version 104690 (0.0014) [2023-03-09 09:50:24,059][22664] Fps is (10 sec: 198247.9, 60 sec: 199065.6, 300 sec: 198385.3). Total num frames: 1715339264. Throughput: 0: 49901.5. Samples: 428897936. Policy #0 lag: (min: 1.0, avg: 17.8, max: 33.0) [2023-03-09 09:50:24,060][22664] Avg episode reward: [(0, '53.996')] [2023-03-09 09:50:24,390][23090] Updated weights for policy 0, policy_version 104701 (0.0016) [2023-03-09 09:50:25,416][23090] Updated weights for policy 0, policy_version 104711 (0.0013) [2023-03-09 09:50:26,166][23090] Updated weights for policy 0, policy_version 104721 (0.0018) [2023-03-09 09:50:26,963][23090] Updated weights for policy 0, policy_version 104731 (0.0018) [2023-03-09 09:50:27,884][23090] Updated weights for policy 0, policy_version 104741 (0.0020) [2023-03-09 09:50:28,763][23090] Updated weights for policy 0, policy_version 104752 (0.0013) [2023-03-09 09:50:28,883][22940] Signal inference workers to stop experience collection... (35350 times) [2023-03-09 09:50:28,903][22940] Signal inference workers to resume experience collection... (35350 times) [2023-03-09 09:50:28,923][23090] InferenceWorker_p0-w0: stopping experience collection (35350 times) [2023-03-09 09:50:28,923][23090] InferenceWorker_p0-w0: resuming experience collection (35350 times) [2023-03-09 09:50:29,059][22664] Fps is (10 sec: 199872.4, 60 sec: 199063.8, 300 sec: 198384.9). Total num frames: 1716338688. Throughput: 0: 49856.5. Samples: 429045376. Policy #0 lag: (min: 1.0, avg: 17.8, max: 33.0) [2023-03-09 09:50:29,062][22664] Avg episode reward: [(0, '52.448')] [2023-03-09 09:50:29,505][23090] Updated weights for policy 0, policy_version 104762 (0.0016) [2023-03-09 09:50:30,421][23090] Updated weights for policy 0, policy_version 104772 (0.0016) [2023-03-09 09:50:31,165][23090] Updated weights for policy 0, policy_version 104782 (0.0013) [2023-03-09 09:50:31,949][23090] Updated weights for policy 0, policy_version 104792 (0.0017) [2023-03-09 09:50:32,904][23090] Updated weights for policy 0, policy_version 104802 (0.0013) [2023-03-09 09:50:33,684][23090] Updated weights for policy 0, policy_version 104812 (0.0018) [2023-03-09 09:50:34,059][22664] Fps is (10 sec: 196606.8, 60 sec: 198791.6, 300 sec: 198218.7). Total num frames: 1717305344. Throughput: 0: 49811.6. Samples: 429344320. Policy #0 lag: (min: 1.0, avg: 17.8, max: 33.0) [2023-03-09 09:50:34,060][22664] Avg episode reward: [(0, '53.424')] [2023-03-09 09:50:34,349][23090] Updated weights for policy 0, policy_version 104822 (0.0013) [2023-03-09 09:50:35,226][23090] Updated weights for policy 0, policy_version 104832 (0.0020) [2023-03-09 09:50:36,257][23090] Updated weights for policy 0, policy_version 104843 (0.0015) [2023-03-09 09:50:36,965][23090] Updated weights for policy 0, policy_version 104853 (0.0017) [2023-03-09 09:50:37,460][22940] Signal inference workers to stop experience collection... (35400 times) [2023-03-09 09:50:37,463][22940] Signal inference workers to resume experience collection... (35400 times) [2023-03-09 09:50:37,530][23090] InferenceWorker_p0-w0: stopping experience collection (35400 times) [2023-03-09 09:50:37,530][23090] InferenceWorker_p0-w0: resuming experience collection (35400 times) [2023-03-09 09:50:37,865][23090] Updated weights for policy 0, policy_version 104864 (0.0013) [2023-03-09 09:50:38,820][23090] Updated weights for policy 0, policy_version 104874 (0.0016) [2023-03-09 09:50:39,059][22664] Fps is (10 sec: 196612.8, 60 sec: 198792.2, 300 sec: 198163.1). Total num frames: 1718304768. Throughput: 0: 49723.6. Samples: 429641168. Policy #0 lag: (min: 1.0, avg: 18.1, max: 33.0) [2023-03-09 09:50:39,061][22664] Avg episode reward: [(0, '54.607')] [2023-03-09 09:50:39,556][23090] Updated weights for policy 0, policy_version 104884 (0.0016) [2023-03-09 09:50:40,323][23090] Updated weights for policy 0, policy_version 104894 (0.0013) [2023-03-09 09:50:41,412][23090] Updated weights for policy 0, policy_version 104904 (0.0017) [2023-03-09 09:50:42,115][23090] Updated weights for policy 0, policy_version 104914 (0.0013) [2023-03-09 09:50:42,908][23090] Updated weights for policy 0, policy_version 104924 (0.0020) [2023-03-09 09:50:43,843][23090] Updated weights for policy 0, policy_version 104934 (0.0013) [2023-03-09 09:50:44,059][22664] Fps is (10 sec: 196609.5, 60 sec: 198792.1, 300 sec: 198163.2). Total num frames: 1719271424. Throughput: 0: 49723.2. Samples: 429790576. Policy #0 lag: (min: 1.0, avg: 18.1, max: 33.0) [2023-03-09 09:50:44,061][22664] Avg episode reward: [(0, '51.011')] [2023-03-09 09:50:44,653][23090] Updated weights for policy 0, policy_version 104944 (0.0013) [2023-03-09 09:50:45,470][23090] Updated weights for policy 0, policy_version 104954 (0.0023) [2023-03-09 09:50:46,311][23090] Updated weights for policy 0, policy_version 104964 (0.0017) [2023-03-09 09:50:46,694][22940] Signal inference workers to stop experience collection... (35450 times) [2023-03-09 09:50:46,695][22940] Signal inference workers to resume experience collection... (35450 times) [2023-03-09 09:50:46,764][23090] InferenceWorker_p0-w0: stopping experience collection (35450 times) [2023-03-09 09:50:46,764][23090] InferenceWorker_p0-w0: resuming experience collection (35450 times) [2023-03-09 09:50:47,058][23090] Updated weights for policy 0, policy_version 104974 (0.0013) [2023-03-09 09:50:47,796][23090] Updated weights for policy 0, policy_version 104984 (0.0013) [2023-03-09 09:50:48,849][23090] Updated weights for policy 0, policy_version 104995 (0.0013) [2023-03-09 09:50:49,059][22664] Fps is (10 sec: 196607.2, 60 sec: 198791.2, 300 sec: 198107.5). Total num frames: 1720270848. Throughput: 0: 49678.9. Samples: 430087408. Policy #0 lag: (min: 1.0, avg: 18.1, max: 33.0) [2023-03-09 09:50:49,061][22664] Avg episode reward: [(0, '53.686')] [2023-03-09 09:50:49,697][23090] Updated weights for policy 0, policy_version 105006 (0.0012) [2023-03-09 09:50:50,445][23090] Updated weights for policy 0, policy_version 105016 (0.0016) [2023-03-09 09:50:51,388][23090] Updated weights for policy 0, policy_version 105026 (0.0018) [2023-03-09 09:50:52,202][23090] Updated weights for policy 0, policy_version 105036 (0.0022) [2023-03-09 09:50:52,894][23090] Updated weights for policy 0, policy_version 105046 (0.0013) [2023-03-09 09:50:53,726][23090] Updated weights for policy 0, policy_version 105056 (0.0027) [2023-03-09 09:50:54,059][22664] Fps is (10 sec: 199883.9, 60 sec: 198792.5, 300 sec: 198218.4). Total num frames: 1721270272. Throughput: 0: 49632.1. Samples: 430384208. Policy #0 lag: (min: 1.0, avg: 18.1, max: 33.0) [2023-03-09 09:50:54,061][22664] Avg episode reward: [(0, '53.097')] [2023-03-09 09:50:54,735][23090] Updated weights for policy 0, policy_version 105066 (0.0015) [2023-03-09 09:50:54,800][22940] Signal inference workers to stop experience collection... (35500 times) [2023-03-09 09:50:54,820][22940] Signal inference workers to resume experience collection... (35500 times) [2023-03-09 09:50:54,853][23090] InferenceWorker_p0-w0: stopping experience collection (35500 times) [2023-03-09 09:50:54,897][23090] InferenceWorker_p0-w0: resuming experience collection (35500 times) [2023-03-09 09:50:55,395][23090] Updated weights for policy 0, policy_version 105076 (0.0013) [2023-03-09 09:50:56,191][23090] Updated weights for policy 0, policy_version 105086 (0.0026) [2023-03-09 09:50:57,190][23090] Updated weights for policy 0, policy_version 105096 (0.0013) [2023-03-09 09:50:57,968][23090] Updated weights for policy 0, policy_version 105107 (0.0013) [2023-03-09 09:50:58,819][23090] Updated weights for policy 0, policy_version 105118 (0.0012) [2023-03-09 09:50:59,059][22664] Fps is (10 sec: 201524.3, 60 sec: 199337.7, 300 sec: 198329.5). Total num frames: 1722286080. Throughput: 0: 49633.1. Samples: 430535728. Policy #0 lag: (min: 1.0, avg: 18.1, max: 33.0) [2023-03-09 09:50:59,061][22664] Avg episode reward: [(0, '52.469')] [2023-03-09 09:50:59,828][23090] Updated weights for policy 0, policy_version 105128 (0.0016) [2023-03-09 09:51:00,602][23090] Updated weights for policy 0, policy_version 105138 (0.0016) [2023-03-09 09:51:01,378][23090] Updated weights for policy 0, policy_version 105148 (0.0016) [2023-03-09 09:51:02,416][23090] Updated weights for policy 0, policy_version 105159 (0.0013) [2023-03-09 09:51:03,104][22940] Signal inference workers to stop experience collection... (35550 times) [2023-03-09 09:51:03,105][22940] Signal inference workers to resume experience collection... (35550 times) [2023-03-09 09:51:03,172][23090] InferenceWorker_p0-w0: stopping experience collection (35550 times) [2023-03-09 09:51:03,172][23090] InferenceWorker_p0-w0: resuming experience collection (35550 times) [2023-03-09 09:51:03,174][23090] Updated weights for policy 0, policy_version 105169 (0.0013) [2023-03-09 09:51:03,935][23090] Updated weights for policy 0, policy_version 105179 (0.0018) [2023-03-09 09:51:04,059][22664] Fps is (10 sec: 201520.3, 60 sec: 199064.3, 300 sec: 198440.6). Total num frames: 1723285504. Throughput: 0: 49541.9. Samples: 430830528. Policy #0 lag: (min: 1.0, avg: 18.1, max: 33.0) [2023-03-09 09:51:04,061][22664] Avg episode reward: [(0, '50.343')] [2023-03-09 09:51:04,879][23090] Updated weights for policy 0, policy_version 105189 (0.0013) [2023-03-09 09:51:05,626][23090] Updated weights for policy 0, policy_version 105199 (0.0025) [2023-03-09 09:51:06,500][23090] Updated weights for policy 0, policy_version 105209 (0.0013) [2023-03-09 09:51:07,311][23090] Updated weights for policy 0, policy_version 105219 (0.0018) [2023-03-09 09:51:08,043][23090] Updated weights for policy 0, policy_version 105229 (0.0021) [2023-03-09 09:51:08,805][23090] Updated weights for policy 0, policy_version 105239 (0.0018) [2023-03-09 09:51:09,059][22664] Fps is (10 sec: 196613.4, 60 sec: 198519.4, 300 sec: 198274.1). Total num frames: 1724252160. Throughput: 0: 49588.1. Samples: 431129392. Policy #0 lag: (min: 1.0, avg: 18.1, max: 33.0) [2023-03-09 09:51:09,060][22664] Avg episode reward: [(0, '52.643')] [2023-03-09 09:51:09,654][23090] Updated weights for policy 0, policy_version 105249 (0.0019) [2023-03-09 09:51:10,612][23090] Updated weights for policy 0, policy_version 105259 (0.0016) [2023-03-09 09:51:10,826][22940] Signal inference workers to stop experience collection... (35600 times) [2023-03-09 09:51:10,827][22940] Signal inference workers to resume experience collection... (35600 times) [2023-03-09 09:51:10,890][23090] InferenceWorker_p0-w0: stopping experience collection (35600 times) [2023-03-09 09:51:10,890][23090] InferenceWorker_p0-w0: resuming experience collection (35600 times) [2023-03-09 09:51:11,270][23090] Updated weights for policy 0, policy_version 105269 (0.0021) [2023-03-09 09:51:12,075][23090] Updated weights for policy 0, policy_version 105279 (0.0019) [2023-03-09 09:51:13,103][23090] Updated weights for policy 0, policy_version 105289 (0.0013) [2023-03-09 09:51:13,790][23090] Updated weights for policy 0, policy_version 105299 (0.0013) [2023-03-09 09:51:14,059][22664] Fps is (10 sec: 199884.8, 60 sec: 198792.2, 300 sec: 198385.2). Total num frames: 1725284352. Throughput: 0: 49633.3. Samples: 431278864. Policy #0 lag: (min: 1.0, avg: 18.1, max: 33.0) [2023-03-09 09:51:14,061][22664] Avg episode reward: [(0, '55.034')] [2023-03-09 09:51:14,587][23090] Updated weights for policy 0, policy_version 105309 (0.0021) [2023-03-09 09:51:15,695][23090] Updated weights for policy 0, policy_version 105320 (0.0015) [2023-03-09 09:51:16,401][23090] Updated weights for policy 0, policy_version 105330 (0.0017) [2023-03-09 09:51:17,155][23090] Updated weights for policy 0, policy_version 105340 (0.0012) [2023-03-09 09:51:18,143][23090] Updated weights for policy 0, policy_version 105350 (0.0020) [2023-03-09 09:51:18,685][22940] Signal inference workers to stop experience collection... (35650 times) [2023-03-09 09:51:18,686][22940] Signal inference workers to resume experience collection... (35650 times) [2023-03-09 09:51:18,744][23090] InferenceWorker_p0-w0: stopping experience collection (35650 times) [2023-03-09 09:51:18,745][23090] InferenceWorker_p0-w0: resuming experience collection (35650 times) [2023-03-09 09:51:18,876][23090] Updated weights for policy 0, policy_version 105360 (0.0013) [2023-03-09 09:51:19,059][22664] Fps is (10 sec: 201517.7, 60 sec: 198791.3, 300 sec: 198329.7). Total num frames: 1726267392. Throughput: 0: 49677.5. Samples: 431579808. Policy #0 lag: (min: 1.0, avg: 18.1, max: 33.0) [2023-03-09 09:51:19,106][22664] Avg episode reward: [(0, '54.064')] [2023-03-09 09:51:19,144][22940] Saving /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000105365_1726300160.pth... [2023-03-09 09:51:19,179][22940] Removing /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000102456_1678639104.pth [2023-03-09 09:51:19,672][23090] Updated weights for policy 0, policy_version 105370 (0.0013) [2023-03-09 09:51:20,520][23090] Updated weights for policy 0, policy_version 105380 (0.0022) [2023-03-09 09:51:21,397][23090] Updated weights for policy 0, policy_version 105391 (0.0016) [2023-03-09 09:51:22,243][23090] Updated weights for policy 0, policy_version 105401 (0.0017) [2023-03-09 09:51:23,080][23090] Updated weights for policy 0, policy_version 105411 (0.0017) [2023-03-09 09:51:23,821][23090] Updated weights for policy 0, policy_version 105421 (0.0013) [2023-03-09 09:51:24,059][22664] Fps is (10 sec: 196603.4, 60 sec: 198518.1, 300 sec: 198273.9). Total num frames: 1727250432. Throughput: 0: 49722.0. Samples: 431878672. Policy #0 lag: (min: 1.0, avg: 18.1, max: 33.0) [2023-03-09 09:51:24,061][22664] Avg episode reward: [(0, '53.966')] [2023-03-09 09:51:24,689][23090] Updated weights for policy 0, policy_version 105432 (0.0029) [2023-03-09 09:51:25,576][23090] Updated weights for policy 0, policy_version 105442 (0.0017) [2023-03-09 09:51:26,386][23090] Updated weights for policy 0, policy_version 105452 (0.0019) [2023-03-09 09:51:26,872][22940] Signal inference workers to stop experience collection... (35700 times) [2023-03-09 09:51:26,877][22940] Signal inference workers to resume experience collection... (35700 times) [2023-03-09 09:51:26,944][23090] InferenceWorker_p0-w0: stopping experience collection (35700 times) [2023-03-09 09:51:26,945][23090] InferenceWorker_p0-w0: resuming experience collection (35700 times) [2023-03-09 09:51:27,107][23090] Updated weights for policy 0, policy_version 105462 (0.0016) [2023-03-09 09:51:27,945][23090] Updated weights for policy 0, policy_version 105472 (0.0017) [2023-03-09 09:51:28,915][23090] Updated weights for policy 0, policy_version 105482 (0.0024) [2023-03-09 09:51:29,059][22664] Fps is (10 sec: 198252.0, 60 sec: 198521.3, 300 sec: 198385.2). Total num frames: 1728249856. Throughput: 0: 49724.3. Samples: 432028160. Policy #0 lag: (min: 1.0, avg: 18.1, max: 33.0) [2023-03-09 09:51:29,059][22664] Avg episode reward: [(0, '53.996')] [2023-03-09 09:51:29,615][23090] Updated weights for policy 0, policy_version 105492 (0.0018) [2023-03-09 09:51:30,447][23090] Updated weights for policy 0, policy_version 105502 (0.0023) [2023-03-09 09:51:31,408][23090] Updated weights for policy 0, policy_version 105512 (0.0018) [2023-03-09 09:51:32,212][23090] Updated weights for policy 0, policy_version 105523 (0.0022) [2023-03-09 09:51:33,074][23090] Updated weights for policy 0, policy_version 105534 (0.0013) [2023-03-09 09:51:34,049][23090] Updated weights for policy 0, policy_version 105544 (0.0016) [2023-03-09 09:51:34,059][22664] Fps is (10 sec: 198254.3, 60 sec: 198792.7, 300 sec: 198274.2). Total num frames: 1729232896. Throughput: 0: 49771.5. Samples: 432327120. Policy #0 lag: (min: 1.0, avg: 18.1, max: 33.0) [2023-03-09 09:51:34,060][22664] Avg episode reward: [(0, '53.470')] [2023-03-09 09:51:34,752][23090] Updated weights for policy 0, policy_version 105554 (0.0013) [2023-03-09 09:51:35,560][22940] Signal inference workers to stop experience collection... (35750 times) [2023-03-09 09:51:35,573][22940] Signal inference workers to resume experience collection... (35750 times) [2023-03-09 09:51:35,592][23090] InferenceWorker_p0-w0: stopping experience collection (35750 times) [2023-03-09 09:51:35,592][23090] InferenceWorker_p0-w0: resuming experience collection (35750 times) [2023-03-09 09:51:35,632][23090] Updated weights for policy 0, policy_version 105565 (0.0019) [2023-03-09 09:51:36,664][23090] Updated weights for policy 0, policy_version 105575 (0.0017) [2023-03-09 09:51:37,357][23090] Updated weights for policy 0, policy_version 105585 (0.0023) [2023-03-09 09:51:38,189][23090] Updated weights for policy 0, policy_version 105595 (0.0013) [2023-03-09 09:51:39,058][22664] Fps is (10 sec: 196609.2, 60 sec: 198520.7, 300 sec: 198274.3). Total num frames: 1730215936. Throughput: 0: 49817.6. Samples: 432625984. Policy #0 lag: (min: 2.0, avg: 17.2, max: 34.0) [2023-03-09 09:51:39,059][22664] Avg episode reward: [(0, '56.290')] [2023-03-09 09:51:39,115][23090] Updated weights for policy 0, policy_version 105605 (0.0014) [2023-03-09 09:51:39,813][23090] Updated weights for policy 0, policy_version 105615 (0.0013) [2023-03-09 09:51:40,719][23090] Updated weights for policy 0, policy_version 105626 (0.0015) [2023-03-09 09:51:41,557][23090] Updated weights for policy 0, policy_version 105636 (0.0015) [2023-03-09 09:51:42,352][23090] Updated weights for policy 0, policy_version 105646 (0.0019) [2023-03-09 09:51:43,138][23090] Updated weights for policy 0, policy_version 105656 (0.0017) [2023-03-09 09:51:44,059][22664] Fps is (10 sec: 199882.9, 60 sec: 199338.3, 300 sec: 198385.2). Total num frames: 1731231744. Throughput: 0: 49770.7. Samples: 432775408. Policy #0 lag: (min: 2.0, avg: 17.2, max: 34.0) [2023-03-09 09:51:44,061][22664] Avg episode reward: [(0, '54.905')] [2023-03-09 09:51:44,129][23090] Updated weights for policy 0, policy_version 105667 (0.0016) [2023-03-09 09:51:44,755][22940] Signal inference workers to stop experience collection... (35800 times) [2023-03-09 09:51:44,774][22940] Signal inference workers to resume experience collection... (35800 times) [2023-03-09 09:51:44,807][23090] InferenceWorker_p0-w0: stopping experience collection (35800 times) [2023-03-09 09:51:44,857][23090] InferenceWorker_p0-w0: resuming experience collection (35800 times) [2023-03-09 09:51:44,898][23090] Updated weights for policy 0, policy_version 105677 (0.0013) [2023-03-09 09:51:45,596][23090] Updated weights for policy 0, policy_version 105687 (0.0013) [2023-03-09 09:51:46,472][23090] Updated weights for policy 0, policy_version 105697 (0.0016) [2023-03-09 09:51:47,408][23090] Updated weights for policy 0, policy_version 105707 (0.0021) [2023-03-09 09:51:48,133][23090] Updated weights for policy 0, policy_version 105717 (0.0017) [2023-03-09 09:51:48,932][23090] Updated weights for policy 0, policy_version 105727 (0.0021) [2023-03-09 09:51:49,059][22664] Fps is (10 sec: 203152.8, 60 sec: 199611.6, 300 sec: 198607.3). Total num frames: 1732247552. Throughput: 0: 49818.0. Samples: 433072336. Policy #0 lag: (min: 2.0, avg: 17.2, max: 34.0) [2023-03-09 09:51:49,060][22664] Avg episode reward: [(0, '55.274')] [2023-03-09 09:51:49,920][23090] Updated weights for policy 0, policy_version 105737 (0.0013) [2023-03-09 09:51:50,624][23090] Updated weights for policy 0, policy_version 105747 (0.0015) [2023-03-09 09:51:51,420][23090] Updated weights for policy 0, policy_version 105757 (0.0014) [2023-03-09 09:51:52,416][23090] Updated weights for policy 0, policy_version 105767 (0.0013) [2023-03-09 09:51:53,158][23090] Updated weights for policy 0, policy_version 105777 (0.0027) [2023-03-09 09:51:53,352][22940] Signal inference workers to stop experience collection... (35850 times) [2023-03-09 09:51:53,353][22940] Signal inference workers to resume experience collection... (35850 times) [2023-03-09 09:51:53,400][23090] InferenceWorker_p0-w0: stopping experience collection (35850 times) [2023-03-09 09:51:53,403][23090] InferenceWorker_p0-w0: resuming experience collection (35850 times) [2023-03-09 09:51:53,978][23090] Updated weights for policy 0, policy_version 105788 (0.0018) [2023-03-09 09:51:54,059][22664] Fps is (10 sec: 201524.5, 60 sec: 199611.7, 300 sec: 198607.3). Total num frames: 1733246976. Throughput: 0: 49817.7. Samples: 433371200. Policy #0 lag: (min: 2.0, avg: 17.2, max: 34.0) [2023-03-09 09:51:54,061][22664] Avg episode reward: [(0, '52.880')] [2023-03-09 09:51:54,990][23090] Updated weights for policy 0, policy_version 105798 (0.0013) [2023-03-09 09:51:55,730][23090] Updated weights for policy 0, policy_version 105808 (0.0018) [2023-03-09 09:51:56,526][23090] Updated weights for policy 0, policy_version 105818 (0.0018) [2023-03-09 09:51:57,412][23090] Updated weights for policy 0, policy_version 105828 (0.0013) [2023-03-09 09:51:58,288][23090] Updated weights for policy 0, policy_version 105839 (0.0017) [2023-03-09 09:51:59,058][22664] Fps is (10 sec: 196616.1, 60 sec: 198793.6, 300 sec: 198496.4). Total num frames: 1734213632. Throughput: 0: 49818.8. Samples: 433520688. Policy #0 lag: (min: 2.0, avg: 17.2, max: 34.0) [2023-03-09 09:51:59,060][22664] Avg episode reward: [(0, '53.819')] [2023-03-09 09:51:59,114][23090] Updated weights for policy 0, policy_version 105849 (0.0016) [2023-03-09 09:51:59,998][23090] Updated weights for policy 0, policy_version 105859 (0.0013) [2023-03-09 09:52:00,709][23090] Updated weights for policy 0, policy_version 105869 (0.0013) [2023-03-09 09:52:01,448][23090] Updated weights for policy 0, policy_version 105879 (0.0016) [2023-03-09 09:52:01,796][22940] Signal inference workers to stop experience collection... (35900 times) [2023-03-09 09:52:01,822][22940] Signal inference workers to resume experience collection... (35900 times) [2023-03-09 09:52:01,863][23090] InferenceWorker_p0-w0: stopping experience collection (35900 times) [2023-03-09 09:52:01,902][23090] InferenceWorker_p0-w0: resuming experience collection (35900 times) [2023-03-09 09:52:02,271][23090] Updated weights for policy 0, policy_version 105889 (0.0019) [2023-03-09 09:52:03,253][23090] Updated weights for policy 0, policy_version 105899 (0.0018) [2023-03-09 09:52:03,922][23090] Updated weights for policy 0, policy_version 105909 (0.0013) [2023-03-09 09:52:04,059][22664] Fps is (10 sec: 198251.4, 60 sec: 199066.9, 300 sec: 198496.6). Total num frames: 1735229440. Throughput: 0: 49773.1. Samples: 433819584. Policy #0 lag: (min: 2.0, avg: 17.2, max: 34.0) [2023-03-09 09:52:04,060][22664] Avg episode reward: [(0, '53.849')] [2023-03-09 09:52:04,848][23090] Updated weights for policy 0, policy_version 105920 (0.0018) [2023-03-09 09:52:05,799][23090] Updated weights for policy 0, policy_version 105930 (0.0016) [2023-03-09 09:52:06,499][23090] Updated weights for policy 0, policy_version 105940 (0.0013) [2023-03-09 09:52:07,307][23090] Updated weights for policy 0, policy_version 105950 (0.0016) [2023-03-09 09:52:08,291][23090] Updated weights for policy 0, policy_version 105960 (0.0019) [2023-03-09 09:52:09,015][23090] Updated weights for policy 0, policy_version 105970 (0.0018) [2023-03-09 09:52:09,059][22664] Fps is (10 sec: 201511.6, 60 sec: 199610.0, 300 sec: 198607.0). Total num frames: 1736228864. Throughput: 0: 49771.4. Samples: 434118384. Policy #0 lag: (min: 2.0, avg: 17.2, max: 34.0) [2023-03-09 09:52:09,061][22664] Avg episode reward: [(0, '54.030')] [2023-03-09 09:52:09,801][23090] Updated weights for policy 0, policy_version 105980 (0.0013) [2023-03-09 09:52:10,753][23090] Updated weights for policy 0, policy_version 105990 (0.0017) [2023-03-09 09:52:11,489][23090] Updated weights for policy 0, policy_version 106000 (0.0013) [2023-03-09 09:52:11,666][22940] Signal inference workers to stop experience collection... (35950 times) [2023-03-09 09:52:11,683][22940] Signal inference workers to resume experience collection... (35950 times) [2023-03-09 09:52:11,733][23090] InferenceWorker_p0-w0: stopping experience collection (35950 times) [2023-03-09 09:52:11,734][23090] InferenceWorker_p0-w0: resuming experience collection (35950 times) [2023-03-09 09:52:12,304][23090] Updated weights for policy 0, policy_version 106010 (0.0016) [2023-03-09 09:52:13,208][23090] Updated weights for policy 0, policy_version 106020 (0.0012) [2023-03-09 09:52:14,058][22664] Fps is (10 sec: 198247.4, 60 sec: 198794.0, 300 sec: 198552.0). Total num frames: 1737211904. Throughput: 0: 49771.5. Samples: 434267872. Policy #0 lag: (min: 2.0, avg: 17.2, max: 34.0) [2023-03-09 09:52:14,059][22664] Avg episode reward: [(0, '53.921')] [2023-03-09 09:52:14,064][23090] Updated weights for policy 0, policy_version 106031 (0.0019) [2023-03-09 09:52:14,860][23090] Updated weights for policy 0, policy_version 106041 (0.0016) [2023-03-09 09:52:15,741][23090] Updated weights for policy 0, policy_version 106051 (0.0013) [2023-03-09 09:52:16,503][23090] Updated weights for policy 0, policy_version 106061 (0.0018) [2023-03-09 09:52:17,245][23090] Updated weights for policy 0, policy_version 106071 (0.0021) [2023-03-09 09:52:18,101][23090] Updated weights for policy 0, policy_version 106081 (0.0023) [2023-03-09 09:52:19,059][22664] Fps is (10 sec: 198254.3, 60 sec: 199066.1, 300 sec: 198607.3). Total num frames: 1738211328. Throughput: 0: 49723.8. Samples: 434564688. Policy #0 lag: (min: 2.0, avg: 17.2, max: 34.0) [2023-03-09 09:52:19,061][22664] Avg episode reward: [(0, '51.396')] [2023-03-09 09:52:19,064][23090] Updated weights for policy 0, policy_version 106092 (0.0020) [2023-03-09 09:52:19,781][23090] Updated weights for policy 0, policy_version 106102 (0.0015) [2023-03-09 09:52:20,625][23090] Updated weights for policy 0, policy_version 106112 (0.0016) [2023-03-09 09:52:21,629][23090] Updated weights for policy 0, policy_version 106122 (0.0019) [2023-03-09 09:52:22,364][22940] Signal inference workers to stop experience collection... (36000 times) [2023-03-09 09:52:22,365][23090] Updated weights for policy 0, policy_version 106132 (0.0013) [2023-03-09 09:52:22,383][22940] Signal inference workers to resume experience collection... (36000 times) [2023-03-09 09:52:22,408][23090] InferenceWorker_p0-w0: stopping experience collection (36000 times) [2023-03-09 09:52:22,408][23090] InferenceWorker_p0-w0: resuming experience collection (36000 times) [2023-03-09 09:52:23,104][23090] Updated weights for policy 0, policy_version 106142 (0.0016) [2023-03-09 09:52:24,059][22664] Fps is (10 sec: 194958.9, 60 sec: 198519.9, 300 sec: 198496.3). Total num frames: 1739161600. Throughput: 0: 49723.5. Samples: 434863568. Policy #0 lag: (min: 2.0, avg: 17.2, max: 34.0) [2023-03-09 09:52:24,061][22664] Avg episode reward: [(0, '54.233')] [2023-03-09 09:52:24,141][23090] Updated weights for policy 0, policy_version 106152 (0.0017) [2023-03-09 09:52:24,841][23090] Updated weights for policy 0, policy_version 106162 (0.0016) [2023-03-09 09:52:25,649][23090] Updated weights for policy 0, policy_version 106172 (0.0023) [2023-03-09 09:52:26,722][23090] Updated weights for policy 0, policy_version 106183 (0.0020) [2023-03-09 09:52:27,377][23090] Updated weights for policy 0, policy_version 106193 (0.0013) [2023-03-09 09:52:28,229][23090] Updated weights for policy 0, policy_version 106203 (0.0017) [2023-03-09 09:52:29,059][22664] Fps is (10 sec: 196609.9, 60 sec: 198792.4, 300 sec: 198662.9). Total num frames: 1740177408. Throughput: 0: 49725.1. Samples: 435013024. Policy #0 lag: (min: 2.0, avg: 17.2, max: 34.0) [2023-03-09 09:52:29,060][22664] Avg episode reward: [(0, '52.562')] [2023-03-09 09:52:29,153][23090] Updated weights for policy 0, policy_version 106213 (0.0021) [2023-03-09 09:52:29,929][23090] Updated weights for policy 0, policy_version 106223 (0.0021) [2023-03-09 09:52:30,779][23090] Updated weights for policy 0, policy_version 106234 (0.0013) [2023-03-09 09:52:31,689][23090] Updated weights for policy 0, policy_version 106244 (0.0016) [2023-03-09 09:52:32,424][23090] Updated weights for policy 0, policy_version 106254 (0.0016) [2023-03-09 09:52:33,235][23090] Updated weights for policy 0, policy_version 106264 (0.0018) [2023-03-09 09:52:33,447][22940] Signal inference workers to stop experience collection... (36050 times) [2023-03-09 09:52:33,457][22940] Signal inference workers to resume experience collection... (36050 times) [2023-03-09 09:52:33,523][23090] InferenceWorker_p0-w0: stopping experience collection (36050 times) [2023-03-09 09:52:33,523][23090] InferenceWorker_p0-w0: resuming experience collection (36050 times) [2023-03-09 09:52:34,059][22664] Fps is (10 sec: 201525.2, 60 sec: 199065.0, 300 sec: 198773.7). Total num frames: 1741176832. Throughput: 0: 49768.9. Samples: 435311936. Policy #0 lag: (min: 2.0, avg: 17.2, max: 34.0) [2023-03-09 09:52:34,061][22664] Avg episode reward: [(0, '50.892')] [2023-03-09 09:52:34,132][23090] Updated weights for policy 0, policy_version 106274 (0.0014) [2023-03-09 09:52:34,945][23090] Updated weights for policy 0, policy_version 106284 (0.0016) [2023-03-09 09:52:35,646][23090] Updated weights for policy 0, policy_version 106294 (0.0018) [2023-03-09 09:52:36,492][23090] Updated weights for policy 0, policy_version 106304 (0.0021) [2023-03-09 09:52:37,468][23090] Updated weights for policy 0, policy_version 106314 (0.0013) [2023-03-09 09:52:38,180][23090] Updated weights for policy 0, policy_version 106324 (0.0015) [2023-03-09 09:52:38,950][23090] Updated weights for policy 0, policy_version 106334 (0.0018) [2023-03-09 09:52:39,058][22664] Fps is (10 sec: 201525.1, 60 sec: 199611.7, 300 sec: 198829.7). Total num frames: 1742192640. Throughput: 0: 49723.0. Samples: 435608720. Policy #0 lag: (min: 1.0, avg: 16.7, max: 33.0) [2023-03-09 09:52:39,059][22664] Avg episode reward: [(0, '50.846')] [2023-03-09 09:52:39,985][23090] Updated weights for policy 0, policy_version 106344 (0.0016) [2023-03-09 09:52:40,688][23090] Updated weights for policy 0, policy_version 106354 (0.0013) [2023-03-09 09:52:41,509][23090] Updated weights for policy 0, policy_version 106364 (0.0016) [2023-03-09 09:52:42,466][23090] Updated weights for policy 0, policy_version 106374 (0.0016) [2023-03-09 09:52:43,240][23090] Updated weights for policy 0, policy_version 106384 (0.0020) [2023-03-09 09:52:43,968][22940] Signal inference workers to stop experience collection... (36100 times) [2023-03-09 09:52:43,981][22940] Signal inference workers to resume experience collection... (36100 times) [2023-03-09 09:52:44,047][23090] InferenceWorker_p0-w0: stopping experience collection (36100 times) [2023-03-09 09:52:44,050][23090] InferenceWorker_p0-w0: resuming experience collection (36100 times) [2023-03-09 09:52:44,053][23090] Updated weights for policy 0, policy_version 106394 (0.0019) [2023-03-09 09:52:44,059][22664] Fps is (10 sec: 198248.5, 60 sec: 198792.6, 300 sec: 198662.7). Total num frames: 1743159296. Throughput: 0: 49675.7. Samples: 435756112. Policy #0 lag: (min: 1.0, avg: 16.7, max: 33.0) [2023-03-09 09:52:44,060][22664] Avg episode reward: [(0, '50.919')] [2023-03-09 09:52:44,937][23090] Updated weights for policy 0, policy_version 106404 (0.0026) [2023-03-09 09:52:45,708][23090] Updated weights for policy 0, policy_version 106414 (0.0018) [2023-03-09 09:52:46,481][23090] Updated weights for policy 0, policy_version 106424 (0.0021) [2023-03-09 09:52:47,341][23090] Updated weights for policy 0, policy_version 106434 (0.0019) [2023-03-09 09:52:48,176][23090] Updated weights for policy 0, policy_version 106444 (0.0018) [2023-03-09 09:52:48,889][23090] Updated weights for policy 0, policy_version 106454 (0.0024) [2023-03-09 09:52:49,059][22664] Fps is (10 sec: 196597.5, 60 sec: 198519.1, 300 sec: 198607.2). Total num frames: 1744158720. Throughput: 0: 49629.3. Samples: 436052928. Policy #0 lag: (min: 1.0, avg: 16.7, max: 33.0) [2023-03-09 09:52:49,061][22664] Avg episode reward: [(0, '51.123')] [2023-03-09 09:52:49,728][23090] Updated weights for policy 0, policy_version 106464 (0.0021) [2023-03-09 09:52:50,741][23090] Updated weights for policy 0, policy_version 106474 (0.0017) [2023-03-09 09:52:51,493][23090] Updated weights for policy 0, policy_version 106485 (0.0016) [2023-03-09 09:52:52,262][23090] Updated weights for policy 0, policy_version 106495 (0.0015) [2023-03-09 09:52:53,284][23090] Updated weights for policy 0, policy_version 106505 (0.0013) [2023-03-09 09:52:53,332][22940] Signal inference workers to stop experience collection... (36150 times) [2023-03-09 09:52:53,334][22940] Signal inference workers to resume experience collection... (36150 times) [2023-03-09 09:52:53,425][23090] InferenceWorker_p0-w0: stopping experience collection (36150 times) [2023-03-09 09:52:53,425][23090] InferenceWorker_p0-w0: resuming experience collection (36150 times) [2023-03-09 09:52:54,027][23090] Updated weights for policy 0, policy_version 106515 (0.0019) [2023-03-09 09:52:54,059][22664] Fps is (10 sec: 199888.2, 60 sec: 198519.9, 300 sec: 198662.9). Total num frames: 1745158144. Throughput: 0: 49586.6. Samples: 436349760. Policy #0 lag: (min: 1.0, avg: 16.7, max: 33.0) [2023-03-09 09:52:54,060][22664] Avg episode reward: [(0, '52.600')] [2023-03-09 09:52:54,801][23090] Updated weights for policy 0, policy_version 106525 (0.0013) [2023-03-09 09:52:55,882][23090] Updated weights for policy 0, policy_version 106535 (0.0016) [2023-03-09 09:52:56,509][23090] Updated weights for policy 0, policy_version 106545 (0.0016) [2023-03-09 09:52:57,364][23090] Updated weights for policy 0, policy_version 106556 (0.0014) [2023-03-09 09:52:58,394][23090] Updated weights for policy 0, policy_version 106566 (0.0022) [2023-03-09 09:52:59,058][22664] Fps is (10 sec: 196618.6, 60 sec: 198519.5, 300 sec: 198607.4). Total num frames: 1746124800. Throughput: 0: 49540.6. Samples: 436497200. Policy #0 lag: (min: 1.0, avg: 16.7, max: 33.0) [2023-03-09 09:52:59,059][22664] Avg episode reward: [(0, '52.988')] [2023-03-09 09:52:59,112][23090] Updated weights for policy 0, policy_version 106576 (0.0019) [2023-03-09 09:52:59,923][23090] Updated weights for policy 0, policy_version 106586 (0.0013) [2023-03-09 09:53:00,923][23090] Updated weights for policy 0, policy_version 106597 (0.0013) [2023-03-09 09:53:01,701][23090] Updated weights for policy 0, policy_version 106607 (0.0016) [2023-03-09 09:53:02,535][23090] Updated weights for policy 0, policy_version 106617 (0.0019) [2023-03-09 09:53:02,545][22940] Signal inference workers to stop experience collection... (36200 times) [2023-03-09 09:53:02,566][22940] Signal inference workers to resume experience collection... (36200 times) [2023-03-09 09:53:02,617][23090] InferenceWorker_p0-w0: stopping experience collection (36200 times) [2023-03-09 09:53:02,618][23090] InferenceWorker_p0-w0: resuming experience collection (36200 times) [2023-03-09 09:53:03,352][23090] Updated weights for policy 0, policy_version 106627 (0.0021) [2023-03-09 09:53:04,059][22664] Fps is (10 sec: 196609.6, 60 sec: 198246.3, 300 sec: 198607.4). Total num frames: 1747124224. Throughput: 0: 49538.6. Samples: 436793920. Policy #0 lag: (min: 1.0, avg: 16.7, max: 33.0) [2023-03-09 09:53:04,060][22664] Avg episode reward: [(0, '53.975')] [2023-03-09 09:53:04,149][23090] Updated weights for policy 0, policy_version 106637 (0.0013) [2023-03-09 09:53:04,825][23090] Updated weights for policy 0, policy_version 106647 (0.0014) [2023-03-09 09:53:05,683][23090] Updated weights for policy 0, policy_version 106657 (0.0016) [2023-03-09 09:53:06,651][23090] Updated weights for policy 0, policy_version 106667 (0.0017) [2023-03-09 09:53:07,305][23090] Updated weights for policy 0, policy_version 106677 (0.0017) [2023-03-09 09:53:08,175][23090] Updated weights for policy 0, policy_version 106687 (0.0017) [2023-03-09 09:53:09,059][22664] Fps is (10 sec: 196599.2, 60 sec: 197700.8, 300 sec: 198662.8). Total num frames: 1748090880. Throughput: 0: 49582.7. Samples: 437094784. Policy #0 lag: (min: 1.0, avg: 16.7, max: 33.0) [2023-03-09 09:53:09,061][22664] Avg episode reward: [(0, '51.744')] [2023-03-09 09:53:09,140][23090] Updated weights for policy 0, policy_version 106697 (0.0013) [2023-03-09 09:53:09,903][23090] Updated weights for policy 0, policy_version 106708 (0.0023) [2023-03-09 09:53:10,680][23090] Updated weights for policy 0, policy_version 106718 (0.0015) [2023-03-09 09:53:11,757][23090] Updated weights for policy 0, policy_version 106728 (0.0019) [2023-03-09 09:53:12,238][22940] Signal inference workers to stop experience collection... (36250 times) [2023-03-09 09:53:12,239][22940] Signal inference workers to resume experience collection... (36250 times) [2023-03-09 09:53:12,303][23090] InferenceWorker_p0-w0: stopping experience collection (36250 times) [2023-03-09 09:53:12,304][23090] InferenceWorker_p0-w0: resuming experience collection (36250 times) [2023-03-09 09:53:12,470][23090] Updated weights for policy 0, policy_version 106738 (0.0015) [2023-03-09 09:53:13,274][23090] Updated weights for policy 0, policy_version 106748 (0.0016) [2023-03-09 09:53:14,059][22664] Fps is (10 sec: 196609.0, 60 sec: 197973.2, 300 sec: 198718.7). Total num frames: 1749090304. Throughput: 0: 49537.1. Samples: 437242192. Policy #0 lag: (min: 1.0, avg: 16.7, max: 33.0) [2023-03-09 09:53:14,059][22664] Avg episode reward: [(0, '53.087')] [2023-03-09 09:53:14,234][23090] Updated weights for policy 0, policy_version 106758 (0.0015) [2023-03-09 09:53:15,025][23090] Updated weights for policy 0, policy_version 106769 (0.0012) [2023-03-09 09:53:15,845][23090] Updated weights for policy 0, policy_version 106779 (0.0013) [2023-03-09 09:53:16,879][23090] Updated weights for policy 0, policy_version 106790 (0.0013) [2023-03-09 09:53:17,660][23090] Updated weights for policy 0, policy_version 106800 (0.0019) [2023-03-09 09:53:18,444][23090] Updated weights for policy 0, policy_version 106810 (0.0013) [2023-03-09 09:53:19,058][22664] Fps is (10 sec: 199893.3, 60 sec: 197973.9, 300 sec: 198774.2). Total num frames: 1750089728. Throughput: 0: 49492.0. Samples: 437539056. Policy #0 lag: (min: 1.0, avg: 16.7, max: 33.0) [2023-03-09 09:53:19,060][22664] Avg episode reward: [(0, '52.958')] [2023-03-09 09:53:19,074][22940] Saving /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000106818_1750106112.pth... [2023-03-09 09:53:19,137][22940] Removing /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000103906_1702395904.pth [2023-03-09 09:53:19,290][23090] Updated weights for policy 0, policy_version 106820 (0.0013) [2023-03-09 09:53:20,069][23090] Updated weights for policy 0, policy_version 106830 (0.0013) [2023-03-09 09:53:20,865][23090] Updated weights for policy 0, policy_version 106840 (0.0019) [2023-03-09 09:53:21,747][23090] Updated weights for policy 0, policy_version 106850 (0.0017) [2023-03-09 09:53:22,558][23090] Updated weights for policy 0, policy_version 106860 (0.0016) [2023-03-09 09:53:22,901][22940] Signal inference workers to stop experience collection... (36300 times) [2023-03-09 09:53:22,901][22940] Signal inference workers to resume experience collection... (36300 times) [2023-03-09 09:53:22,971][23090] InferenceWorker_p0-w0: stopping experience collection (36300 times) [2023-03-09 09:53:22,971][23090] InferenceWorker_p0-w0: resuming experience collection (36300 times) [2023-03-09 09:53:23,259][23090] Updated weights for policy 0, policy_version 106870 (0.0014) [2023-03-09 09:53:24,059][22664] Fps is (10 sec: 201518.7, 60 sec: 199066.6, 300 sec: 198829.4). Total num frames: 1751105536. Throughput: 0: 49539.3. Samples: 437838000. Policy #0 lag: (min: 1.0, avg: 16.7, max: 33.0) [2023-03-09 09:53:24,060][22664] Avg episode reward: [(0, '53.989')] [2023-03-09 09:53:24,102][23090] Updated weights for policy 0, policy_version 106880 (0.0017) [2023-03-09 09:53:25,071][23090] Updated weights for policy 0, policy_version 106891 (0.0017) [2023-03-09 09:53:25,838][23090] Updated weights for policy 0, policy_version 106901 (0.0027) [2023-03-09 09:53:26,619][23090] Updated weights for policy 0, policy_version 106911 (0.0016) [2023-03-09 09:53:27,655][23090] Updated weights for policy 0, policy_version 106921 (0.0013) [2023-03-09 09:53:28,348][23090] Updated weights for policy 0, policy_version 106931 (0.0020) [2023-03-09 09:53:29,059][22664] Fps is (10 sec: 199878.4, 60 sec: 198518.7, 300 sec: 198773.8). Total num frames: 1752088576. Throughput: 0: 49585.8. Samples: 437987472. Policy #0 lag: (min: 1.0, avg: 16.7, max: 33.0) [2023-03-09 09:53:29,061][22664] Avg episode reward: [(0, '51.738')] [2023-03-09 09:53:29,142][23090] Updated weights for policy 0, policy_version 106941 (0.0017) [2023-03-09 09:53:30,179][23090] Updated weights for policy 0, policy_version 106951 (0.0016) [2023-03-09 09:53:30,878][23090] Updated weights for policy 0, policy_version 106961 (0.0016) [2023-03-09 09:53:31,661][23090] Updated weights for policy 0, policy_version 106971 (0.0016) [2023-03-09 09:53:32,612][23090] Updated weights for policy 0, policy_version 106981 (0.0018) [2023-03-09 09:53:33,385][23090] Updated weights for policy 0, policy_version 106991 (0.0014) [2023-03-09 09:53:33,691][22940] Signal inference workers to stop experience collection... (36350 times) [2023-03-09 09:53:33,692][22940] Signal inference workers to resume experience collection... (36350 times) [2023-03-09 09:53:33,761][23090] InferenceWorker_p0-w0: stopping experience collection (36350 times) [2023-03-09 09:53:33,762][23090] InferenceWorker_p0-w0: resuming experience collection (36350 times) [2023-03-09 09:53:34,059][22664] Fps is (10 sec: 196606.7, 60 sec: 198246.8, 300 sec: 198663.0). Total num frames: 1753071616. Throughput: 0: 49587.4. Samples: 438284352. Policy #0 lag: (min: 1.0, avg: 16.7, max: 33.0) [2023-03-09 09:53:34,061][22664] Avg episode reward: [(0, '54.831')] [2023-03-09 09:53:34,219][23090] Updated weights for policy 0, policy_version 107001 (0.0013) [2023-03-09 09:53:35,077][23090] Updated weights for policy 0, policy_version 107011 (0.0023) [2023-03-09 09:53:35,855][23090] Updated weights for policy 0, policy_version 107021 (0.0018) [2023-03-09 09:53:36,599][23090] Updated weights for policy 0, policy_version 107031 (0.0016) [2023-03-09 09:53:37,460][23090] Updated weights for policy 0, policy_version 107041 (0.0018) [2023-03-09 09:53:38,421][23090] Updated weights for policy 0, policy_version 107051 (0.0019) [2023-03-09 09:53:39,059][22664] Fps is (10 sec: 196607.7, 60 sec: 197699.1, 300 sec: 198718.3). Total num frames: 1754054656. Throughput: 0: 49497.4. Samples: 438577152. Policy #0 lag: (min: 2.0, avg: 18.3, max: 34.0) [2023-03-09 09:53:39,061][22664] Avg episode reward: [(0, '52.468')] [2023-03-09 09:53:39,174][23090] Updated weights for policy 0, policy_version 107061 (0.0013) [2023-03-09 09:53:39,943][23090] Updated weights for policy 0, policy_version 107071 (0.0018) [2023-03-09 09:53:40,981][23090] Updated weights for policy 0, policy_version 107081 (0.0013) [2023-03-09 09:53:41,639][23090] Updated weights for policy 0, policy_version 107091 (0.0016) [2023-03-09 09:53:42,495][23090] Updated weights for policy 0, policy_version 107102 (0.0023) [2023-03-09 09:53:43,554][23090] Updated weights for policy 0, policy_version 107112 (0.0014) [2023-03-09 09:53:44,059][22664] Fps is (10 sec: 196608.4, 60 sec: 197973.5, 300 sec: 198607.3). Total num frames: 1755037696. Throughput: 0: 49542.1. Samples: 438726608. Policy #0 lag: (min: 2.0, avg: 18.3, max: 34.0) [2023-03-09 09:53:44,061][22664] Avg episode reward: [(0, '53.452')] [2023-03-09 09:53:44,277][23090] Updated weights for policy 0, policy_version 107122 (0.0017) [2023-03-09 09:53:44,869][22940] Signal inference workers to stop experience collection... (36400 times) [2023-03-09 09:53:44,870][22940] Signal inference workers to resume experience collection... (36400 times) [2023-03-09 09:53:44,940][23090] InferenceWorker_p0-w0: stopping experience collection (36400 times) [2023-03-09 09:53:44,940][23090] InferenceWorker_p0-w0: resuming experience collection (36400 times) [2023-03-09 09:53:45,073][23090] Updated weights for policy 0, policy_version 107132 (0.0013) [2023-03-09 09:53:46,058][23090] Updated weights for policy 0, policy_version 107142 (0.0016) [2023-03-09 09:53:46,808][23090] Updated weights for policy 0, policy_version 107152 (0.0013) [2023-03-09 09:53:47,617][23090] Updated weights for policy 0, policy_version 107162 (0.0016) [2023-03-09 09:53:48,464][23090] Updated weights for policy 0, policy_version 107172 (0.0016) [2023-03-09 09:53:49,058][22664] Fps is (10 sec: 196615.0, 60 sec: 197702.0, 300 sec: 198607.4). Total num frames: 1756020736. Throughput: 0: 49500.5. Samples: 439021440. Policy #0 lag: (min: 2.0, avg: 18.3, max: 34.0) [2023-03-09 09:53:49,060][22664] Avg episode reward: [(0, '53.131')] [2023-03-09 09:53:49,260][23090] Updated weights for policy 0, policy_version 107182 (0.0013) [2023-03-09 09:53:50,016][23090] Updated weights for policy 0, policy_version 107192 (0.0018) [2023-03-09 09:53:50,878][23090] Updated weights for policy 0, policy_version 107202 (0.0017) [2023-03-09 09:53:51,737][23090] Updated weights for policy 0, policy_version 107212 (0.0028) [2023-03-09 09:53:52,509][23090] Updated weights for policy 0, policy_version 107222 (0.0018) [2023-03-09 09:53:53,364][23090] Updated weights for policy 0, policy_version 107232 (0.0018) [2023-03-09 09:53:54,059][22664] Fps is (10 sec: 194974.3, 60 sec: 197154.5, 300 sec: 198551.9). Total num frames: 1756987392. Throughput: 0: 49458.2. Samples: 439320384. Policy #0 lag: (min: 2.0, avg: 18.3, max: 34.0) [2023-03-09 09:53:54,059][22664] Avg episode reward: [(0, '51.771')] [2023-03-09 09:53:54,334][23090] Updated weights for policy 0, policy_version 107243 (0.0014) [2023-03-09 09:53:55,028][23090] Updated weights for policy 0, policy_version 107253 (0.0016) [2023-03-09 09:53:55,558][22940] Signal inference workers to stop experience collection... (36450 times) [2023-03-09 09:53:55,559][22940] Signal inference workers to resume experience collection... (36450 times) [2023-03-09 09:53:55,629][23090] InferenceWorker_p0-w0: stopping experience collection (36450 times) [2023-03-09 09:53:55,629][23090] InferenceWorker_p0-w0: resuming experience collection (36450 times) [2023-03-09 09:53:55,798][23090] Updated weights for policy 0, policy_version 107263 (0.0013) [2023-03-09 09:53:56,884][23090] Updated weights for policy 0, policy_version 107273 (0.0016) [2023-03-09 09:53:57,608][23090] Updated weights for policy 0, policy_version 107284 (0.0018) [2023-03-09 09:53:58,414][23090] Updated weights for policy 0, policy_version 107294 (0.0013) [2023-03-09 09:53:59,059][22664] Fps is (10 sec: 198240.0, 60 sec: 197972.3, 300 sec: 198607.7). Total num frames: 1758003200. Throughput: 0: 49456.0. Samples: 439467728. Policy #0 lag: (min: 2.0, avg: 18.3, max: 34.0) [2023-03-09 09:53:59,061][22664] Avg episode reward: [(0, '49.131')] [2023-03-09 09:53:59,441][23090] Updated weights for policy 0, policy_version 107304 (0.0013) [2023-03-09 09:54:00,142][23090] Updated weights for policy 0, policy_version 107314 (0.0013) [2023-03-09 09:54:00,924][23090] Updated weights for policy 0, policy_version 107324 (0.0016) [2023-03-09 09:54:01,910][23090] Updated weights for policy 0, policy_version 107334 (0.0013) [2023-03-09 09:54:02,667][23090] Updated weights for policy 0, policy_version 107344 (0.0013) [2023-03-09 09:54:03,447][23090] Updated weights for policy 0, policy_version 107354 (0.0023) [2023-03-09 09:54:04,059][22664] Fps is (10 sec: 201514.1, 60 sec: 197971.9, 300 sec: 198718.2). Total num frames: 1759002624. Throughput: 0: 49455.1. Samples: 439764560. Policy #0 lag: (min: 2.0, avg: 18.3, max: 34.0) [2023-03-09 09:54:04,061][22664] Avg episode reward: [(0, '50.902')] [2023-03-09 09:54:04,325][23090] Updated weights for policy 0, policy_version 107364 (0.0026) [2023-03-09 09:54:05,129][23090] Updated weights for policy 0, policy_version 107374 (0.0020) [2023-03-09 09:54:05,476][22940] Signal inference workers to stop experience collection... (36500 times) [2023-03-09 09:54:05,477][22940] Signal inference workers to resume experience collection... (36500 times) [2023-03-09 09:54:05,542][23090] InferenceWorker_p0-w0: stopping experience collection (36500 times) [2023-03-09 09:54:05,542][23090] InferenceWorker_p0-w0: resuming experience collection (36500 times) [2023-03-09 09:54:05,852][23090] Updated weights for policy 0, policy_version 107384 (0.0011) [2023-03-09 09:54:06,767][23090] Updated weights for policy 0, policy_version 107394 (0.0013) [2023-03-09 09:54:07,567][23090] Updated weights for policy 0, policy_version 107404 (0.0017) [2023-03-09 09:54:08,292][23090] Updated weights for policy 0, policy_version 107414 (0.0013) [2023-03-09 09:54:09,059][22664] Fps is (10 sec: 201522.9, 60 sec: 198792.9, 300 sec: 198829.7). Total num frames: 1760018432. Throughput: 0: 49498.9. Samples: 440065456. Policy #0 lag: (min: 2.0, avg: 18.3, max: 34.0) [2023-03-09 09:54:09,061][22664] Avg episode reward: [(0, '50.798')] [2023-03-09 09:54:09,095][23090] Updated weights for policy 0, policy_version 107424 (0.0013) [2023-03-09 09:54:10,138][23090] Updated weights for policy 0, policy_version 107434 (0.0023) [2023-03-09 09:54:10,813][23090] Updated weights for policy 0, policy_version 107444 (0.0013) [2023-03-09 09:54:11,590][23090] Updated weights for policy 0, policy_version 107454 (0.0013) [2023-03-09 09:54:12,648][23090] Updated weights for policy 0, policy_version 107464 (0.0029) [2023-03-09 09:54:13,375][23090] Updated weights for policy 0, policy_version 107474 (0.0023) [2023-03-09 09:54:14,022][22940] Signal inference workers to stop experience collection... (36550 times) [2023-03-09 09:54:14,036][22940] Signal inference workers to resume experience collection... (36550 times) [2023-03-09 09:54:14,058][22664] Fps is (10 sec: 199894.8, 60 sec: 198519.5, 300 sec: 198718.7). Total num frames: 1761001472. Throughput: 0: 49499.7. Samples: 440214944. Policy #0 lag: (min: 2.0, avg: 18.3, max: 34.0) [2023-03-09 09:54:14,060][22664] Avg episode reward: [(0, '51.170')] [2023-03-09 09:54:14,106][23090] InferenceWorker_p0-w0: stopping experience collection (36550 times) [2023-03-09 09:54:14,106][23090] InferenceWorker_p0-w0: resuming experience collection (36550 times) [2023-03-09 09:54:14,108][23090] Updated weights for policy 0, policy_version 107484 (0.0016) [2023-03-09 09:54:15,131][23090] Updated weights for policy 0, policy_version 107494 (0.0013) [2023-03-09 09:54:15,824][23090] Updated weights for policy 0, policy_version 107504 (0.0013) [2023-03-09 09:54:16,595][23090] Updated weights for policy 0, policy_version 107514 (0.0016) [2023-03-09 09:54:17,579][23090] Updated weights for policy 0, policy_version 107525 (0.0014) [2023-03-09 09:54:18,353][23090] Updated weights for policy 0, policy_version 107535 (0.0016) [2023-03-09 09:54:19,059][22664] Fps is (10 sec: 198247.2, 60 sec: 198518.6, 300 sec: 198662.9). Total num frames: 1762000896. Throughput: 0: 49543.5. Samples: 440513808. Policy #0 lag: (min: 2.0, avg: 18.3, max: 34.0) [2023-03-09 09:54:19,060][22664] Avg episode reward: [(0, '52.973')] [2023-03-09 09:54:19,126][23090] Updated weights for policy 0, policy_version 107545 (0.0016) [2023-03-09 09:54:20,043][23090] Updated weights for policy 0, policy_version 107555 (0.0017) [2023-03-09 09:54:20,807][23090] Updated weights for policy 0, policy_version 107565 (0.0017) [2023-03-09 09:54:21,472][23090] Updated weights for policy 0, policy_version 107575 (0.0013) [2023-03-09 09:54:22,079][22940] Signal inference workers to stop experience collection... (36600 times) [2023-03-09 09:54:22,080][22940] Signal inference workers to resume experience collection... (36600 times) [2023-03-09 09:54:22,146][23090] InferenceWorker_p0-w0: stopping experience collection (36600 times) [2023-03-09 09:54:22,146][23090] InferenceWorker_p0-w0: resuming experience collection (36600 times) [2023-03-09 09:54:22,373][23090] Updated weights for policy 0, policy_version 107585 (0.0013) [2023-03-09 09:54:23,357][23090] Updated weights for policy 0, policy_version 107595 (0.0017) [2023-03-09 09:54:24,017][23090] Updated weights for policy 0, policy_version 107605 (0.0019) [2023-03-09 09:54:24,059][22664] Fps is (10 sec: 201521.4, 60 sec: 198520.0, 300 sec: 198718.5). Total num frames: 1763016704. Throughput: 0: 49679.6. Samples: 440812720. Policy #0 lag: (min: 2.0, avg: 18.3, max: 34.0) [2023-03-09 09:54:24,060][22664] Avg episode reward: [(0, '53.003')] [2023-03-09 09:54:24,811][23090] Updated weights for policy 0, policy_version 107615 (0.0016) [2023-03-09 09:54:25,879][23090] Updated weights for policy 0, policy_version 107625 (0.0015) [2023-03-09 09:54:26,535][23090] Updated weights for policy 0, policy_version 107635 (0.0016) [2023-03-09 09:54:27,305][23090] Updated weights for policy 0, policy_version 107645 (0.0013) [2023-03-09 09:54:28,393][23090] Updated weights for policy 0, policy_version 107655 (0.0019) [2023-03-09 09:54:29,006][23090] Updated weights for policy 0, policy_version 107665 (0.0013) [2023-03-09 09:54:29,059][22664] Fps is (10 sec: 198246.9, 60 sec: 198246.6, 300 sec: 198662.8). Total num frames: 1763983360. Throughput: 0: 49680.0. Samples: 440962208. Policy #0 lag: (min: 2.0, avg: 18.3, max: 34.0) [2023-03-09 09:54:29,060][22664] Avg episode reward: [(0, '53.594')] [2023-03-09 09:54:29,815][23090] Updated weights for policy 0, policy_version 107675 (0.0013) [2023-03-09 09:54:30,776][23090] Updated weights for policy 0, policy_version 107685 (0.0018) [2023-03-09 09:54:31,065][22940] Signal inference workers to stop experience collection... (36650 times) [2023-03-09 09:54:31,085][22940] Signal inference workers to resume experience collection... (36650 times) [2023-03-09 09:54:31,135][23090] InferenceWorker_p0-w0: stopping experience collection (36650 times) [2023-03-09 09:54:31,136][23090] InferenceWorker_p0-w0: resuming experience collection (36650 times) [2023-03-09 09:54:31,553][23090] Updated weights for policy 0, policy_version 107695 (0.0019) [2023-03-09 09:54:32,349][23090] Updated weights for policy 0, policy_version 107705 (0.0021) [2023-03-09 09:54:33,223][23090] Updated weights for policy 0, policy_version 107715 (0.0018) [2023-03-09 09:54:33,992][23090] Updated weights for policy 0, policy_version 107725 (0.0014) [2023-03-09 09:54:34,059][22664] Fps is (10 sec: 194964.9, 60 sec: 198246.3, 300 sec: 198607.3). Total num frames: 1764966400. Throughput: 0: 49724.4. Samples: 441259056. Policy #0 lag: (min: 2.0, avg: 18.3, max: 34.0) [2023-03-09 09:54:34,061][22664] Avg episode reward: [(0, '52.663')] [2023-03-09 09:54:34,670][23090] Updated weights for policy 0, policy_version 107735 (0.0016) [2023-03-09 09:54:35,606][23090] Updated weights for policy 0, policy_version 107745 (0.0016) [2023-03-09 09:54:36,530][23090] Updated weights for policy 0, policy_version 107755 (0.0014) [2023-03-09 09:54:37,222][23090] Updated weights for policy 0, policy_version 107765 (0.0018) [2023-03-09 09:54:38,101][23090] Updated weights for policy 0, policy_version 107776 (0.0016) [2023-03-09 09:54:39,058][22664] Fps is (10 sec: 196613.1, 60 sec: 198247.5, 300 sec: 198663.0). Total num frames: 1765949440. Throughput: 0: 49722.7. Samples: 441557904. Policy #0 lag: (min: 2.0, avg: 17.4, max: 33.0) [2023-03-09 09:54:39,060][22664] Avg episode reward: [(0, '55.201')] [2023-03-09 09:54:39,110][23090] Updated weights for policy 0, policy_version 107786 (0.0018) [2023-03-09 09:54:39,876][23090] Updated weights for policy 0, policy_version 107797 (0.0016) [2023-03-09 09:54:40,707][23090] Updated weights for policy 0, policy_version 107807 (0.0021) [2023-03-09 09:54:41,652][22940] Signal inference workers to stop experience collection... (36700 times) [2023-03-09 09:54:41,672][22940] Signal inference workers to resume experience collection... (36700 times) [2023-03-09 09:54:41,713][23090] InferenceWorker_p0-w0: stopping experience collection (36700 times) [2023-03-09 09:54:41,716][23090] Updated weights for policy 0, policy_version 107817 (0.0013) [2023-03-09 09:54:41,755][23090] InferenceWorker_p0-w0: resuming experience collection (36700 times) [2023-03-09 09:54:42,373][23090] Updated weights for policy 0, policy_version 107827 (0.0013) [2023-03-09 09:54:43,120][23090] Updated weights for policy 0, policy_version 107837 (0.0016) [2023-03-09 09:54:44,058][22664] Fps is (10 sec: 196613.8, 60 sec: 198247.2, 300 sec: 198607.4). Total num frames: 1766932480. Throughput: 0: 49725.1. Samples: 441705344. Policy #0 lag: (min: 2.0, avg: 17.4, max: 33.0) [2023-03-09 09:54:44,059][22664] Avg episode reward: [(0, '52.831')] [2023-03-09 09:54:44,236][23090] Updated weights for policy 0, policy_version 107847 (0.0016) [2023-03-09 09:54:44,898][23090] Updated weights for policy 0, policy_version 107857 (0.0016) [2023-03-09 09:54:45,698][23090] Updated weights for policy 0, policy_version 107867 (0.0013) [2023-03-09 09:54:46,588][23090] Updated weights for policy 0, policy_version 107877 (0.0017) [2023-03-09 09:54:47,391][23090] Updated weights for policy 0, policy_version 107887 (0.0016) [2023-03-09 09:54:48,167][23090] Updated weights for policy 0, policy_version 107897 (0.0016) [2023-03-09 09:54:49,057][23090] Updated weights for policy 0, policy_version 107907 (0.0013) [2023-03-09 09:54:49,059][22664] Fps is (10 sec: 199878.2, 60 sec: 198791.4, 300 sec: 198662.9). Total num frames: 1767948288. Throughput: 0: 49727.1. Samples: 442002272. Policy #0 lag: (min: 2.0, avg: 17.4, max: 33.0) [2023-03-09 09:54:49,060][22664] Avg episode reward: [(0, '51.973')] [2023-03-09 09:54:49,839][23090] Updated weights for policy 0, policy_version 107917 (0.0013) [2023-03-09 09:54:50,523][23090] Updated weights for policy 0, policy_version 107927 (0.0015) [2023-03-09 09:54:51,416][23090] Updated weights for policy 0, policy_version 107937 (0.0017) [2023-03-09 09:54:52,227][22940] Signal inference workers to stop experience collection... (36750 times) [2023-03-09 09:54:52,245][22940] Signal inference workers to resume experience collection... (36750 times) [2023-03-09 09:54:52,285][23090] InferenceWorker_p0-w0: stopping experience collection (36750 times) [2023-03-09 09:54:52,327][23090] InferenceWorker_p0-w0: resuming experience collection (36750 times) [2023-03-09 09:54:52,369][23090] Updated weights for policy 0, policy_version 107947 (0.0013) [2023-03-09 09:54:53,080][23090] Updated weights for policy 0, policy_version 107957 (0.0016) [2023-03-09 09:54:53,890][23090] Updated weights for policy 0, policy_version 107967 (0.0013) [2023-03-09 09:54:54,059][22664] Fps is (10 sec: 201519.1, 60 sec: 199338.0, 300 sec: 198718.3). Total num frames: 1768947712. Throughput: 0: 49637.4. Samples: 442299136. Policy #0 lag: (min: 2.0, avg: 17.4, max: 33.0) [2023-03-09 09:54:54,060][22664] Avg episode reward: [(0, '51.735')] [2023-03-09 09:54:54,958][23090] Updated weights for policy 0, policy_version 107977 (0.0016) [2023-03-09 09:54:55,628][23090] Updated weights for policy 0, policy_version 107987 (0.0018) [2023-03-09 09:54:56,380][23090] Updated weights for policy 0, policy_version 107997 (0.0016) [2023-03-09 09:54:57,460][23090] Updated weights for policy 0, policy_version 108007 (0.0019) [2023-03-09 09:54:58,167][23090] Updated weights for policy 0, policy_version 108017 (0.0013) [2023-03-09 09:54:58,943][23090] Updated weights for policy 0, policy_version 108027 (0.0014) [2023-03-09 09:54:59,058][22664] Fps is (10 sec: 199891.6, 60 sec: 199066.7, 300 sec: 198663.0). Total num frames: 1769947136. Throughput: 0: 49637.0. Samples: 442448608. Policy #0 lag: (min: 2.0, avg: 17.4, max: 33.0) [2023-03-09 09:54:59,059][22664] Avg episode reward: [(0, '52.908')] [2023-03-09 09:54:59,861][23090] Updated weights for policy 0, policy_version 108037 (0.0013) [2023-03-09 09:55:00,639][23090] Updated weights for policy 0, policy_version 108047 (0.0013) [2023-03-09 09:55:01,559][23090] Updated weights for policy 0, policy_version 108058 (0.0017) [2023-03-09 09:55:02,406][23090] Updated weights for policy 0, policy_version 108068 (0.0017) [2023-03-09 09:55:03,303][23090] Updated weights for policy 0, policy_version 108079 (0.0016) [2023-03-09 09:55:04,059][22664] Fps is (10 sec: 196607.7, 60 sec: 198520.3, 300 sec: 198551.7). Total num frames: 1770913792. Throughput: 0: 49591.5. Samples: 442745424. Policy #0 lag: (min: 2.0, avg: 17.4, max: 33.0) [2023-03-09 09:55:04,061][22664] Avg episode reward: [(0, '53.979')] [2023-03-09 09:55:04,088][23090] Updated weights for policy 0, policy_version 108089 (0.0013) [2023-03-09 09:55:04,307][22940] Signal inference workers to stop experience collection... (36800 times) [2023-03-09 09:55:04,308][22940] Signal inference workers to resume experience collection... (36800 times) [2023-03-09 09:55:04,375][23090] InferenceWorker_p0-w0: stopping experience collection (36800 times) [2023-03-09 09:55:04,375][23090] InferenceWorker_p0-w0: resuming experience collection (36800 times) [2023-03-09 09:55:05,046][23090] Updated weights for policy 0, policy_version 108099 (0.0013) [2023-03-09 09:55:05,833][23090] Updated weights for policy 0, policy_version 108109 (0.0013) [2023-03-09 09:55:06,536][23090] Updated weights for policy 0, policy_version 108119 (0.0017) [2023-03-09 09:55:07,416][23090] Updated weights for policy 0, policy_version 108129 (0.0013) [2023-03-09 09:55:08,344][23090] Updated weights for policy 0, policy_version 108139 (0.0018) [2023-03-09 09:55:09,052][23090] Updated weights for policy 0, policy_version 108149 (0.0021) [2023-03-09 09:55:09,059][22664] Fps is (10 sec: 196601.4, 60 sec: 198246.4, 300 sec: 198496.3). Total num frames: 1771913216. Throughput: 0: 49456.1. Samples: 443038256. Policy #0 lag: (min: 2.0, avg: 17.4, max: 33.0) [2023-03-09 09:55:09,061][22664] Avg episode reward: [(0, '54.708')] [2023-03-09 09:55:09,852][23090] Updated weights for policy 0, policy_version 108159 (0.0018) [2023-03-09 09:55:10,887][23090] Updated weights for policy 0, policy_version 108169 (0.0013) [2023-03-09 09:55:11,588][23090] Updated weights for policy 0, policy_version 108179 (0.0018) [2023-03-09 09:55:12,362][23090] Updated weights for policy 0, policy_version 108189 (0.0015) [2023-03-09 09:55:13,439][23090] Updated weights for policy 0, policy_version 108199 (0.0013) [2023-03-09 09:55:14,059][22664] Fps is (10 sec: 196608.1, 60 sec: 197972.5, 300 sec: 198440.6). Total num frames: 1772879872. Throughput: 0: 49455.7. Samples: 443187712. Policy #0 lag: (min: 2.0, avg: 17.4, max: 33.0) [2023-03-09 09:55:14,061][22664] Avg episode reward: [(0, '53.342')] [2023-03-09 09:55:14,100][23090] Updated weights for policy 0, policy_version 108209 (0.0019) [2023-03-09 09:55:14,911][23090] Updated weights for policy 0, policy_version 108219 (0.0016) [2023-03-09 09:55:15,849][23090] Updated weights for policy 0, policy_version 108229 (0.0017) [2023-03-09 09:55:16,409][22940] Signal inference workers to stop experience collection... (36850 times) [2023-03-09 09:55:16,410][22940] Signal inference workers to resume experience collection... (36850 times) [2023-03-09 09:55:16,470][23090] InferenceWorker_p0-w0: stopping experience collection (36850 times) [2023-03-09 09:55:16,471][23090] InferenceWorker_p0-w0: resuming experience collection (36850 times) [2023-03-09 09:55:16,598][23090] Updated weights for policy 0, policy_version 108239 (0.0012) [2023-03-09 09:55:17,368][23090] Updated weights for policy 0, policy_version 108249 (0.0016) [2023-03-09 09:55:18,288][23090] Updated weights for policy 0, policy_version 108259 (0.0017) [2023-03-09 09:55:19,058][22664] Fps is (10 sec: 194975.5, 60 sec: 197701.1, 300 sec: 198385.4). Total num frames: 1773862912. Throughput: 0: 49455.6. Samples: 443484544. Policy #0 lag: (min: 2.0, avg: 17.4, max: 33.0) [2023-03-09 09:55:19,059][22664] Avg episode reward: [(0, '51.908')] [2023-03-09 09:55:19,075][22940] Saving /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000108269_1773879296.pth... [2023-03-09 09:55:19,102][23090] Updated weights for policy 0, policy_version 108269 (0.0013) [2023-03-09 09:55:19,137][22940] Removing /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000105365_1726300160.pth [2023-03-09 09:55:19,904][23090] Updated weights for policy 0, policy_version 108280 (0.0018) [2023-03-09 09:55:20,794][23090] Updated weights for policy 0, policy_version 108290 (0.0013) [2023-03-09 09:55:21,674][23090] Updated weights for policy 0, policy_version 108300 (0.0021) [2023-03-09 09:55:22,329][23090] Updated weights for policy 0, policy_version 108310 (0.0026) [2023-03-09 09:55:23,221][23090] Updated weights for policy 0, policy_version 108320 (0.0017) [2023-03-09 09:55:24,059][22664] Fps is (10 sec: 194968.5, 60 sec: 196880.3, 300 sec: 198274.4). Total num frames: 1774829568. Throughput: 0: 49365.4. Samples: 443779360. Policy #0 lag: (min: 2.0, avg: 17.4, max: 33.0) [2023-03-09 09:55:24,061][22664] Avg episode reward: [(0, '54.177')] [2023-03-09 09:55:24,233][23090] Updated weights for policy 0, policy_version 108330 (0.0027) [2023-03-09 09:55:24,982][23090] Updated weights for policy 0, policy_version 108341 (0.0016) [2023-03-09 09:55:25,761][23090] Updated weights for policy 0, policy_version 108351 (0.0020) [2023-03-09 09:55:26,802][23090] Updated weights for policy 0, policy_version 108361 (0.0022) [2023-03-09 09:55:27,533][23090] Updated weights for policy 0, policy_version 108371 (0.0013) [2023-03-09 09:55:27,553][22940] Signal inference workers to stop experience collection... (36900 times) [2023-03-09 09:55:27,575][22940] Signal inference workers to resume experience collection... (36900 times) [2023-03-09 09:55:27,620][23090] InferenceWorker_p0-w0: stopping experience collection (36900 times) [2023-03-09 09:55:27,620][23090] InferenceWorker_p0-w0: resuming experience collection (36900 times) [2023-03-09 09:55:28,273][23090] Updated weights for policy 0, policy_version 108381 (0.0016) [2023-03-09 09:55:29,059][22664] Fps is (10 sec: 196602.6, 60 sec: 197427.0, 300 sec: 198385.2). Total num frames: 1775828992. Throughput: 0: 49363.6. Samples: 443926720. Policy #0 lag: (min: 2.0, avg: 17.4, max: 33.0) [2023-03-09 09:55:29,106][22664] Avg episode reward: [(0, '53.276')] [2023-03-09 09:55:29,324][23090] Updated weights for policy 0, policy_version 108391 (0.0020) [2023-03-09 09:55:30,033][23090] Updated weights for policy 0, policy_version 108401 (0.0014) [2023-03-09 09:55:30,835][23090] Updated weights for policy 0, policy_version 108411 (0.0019) [2023-03-09 09:55:31,759][23090] Updated weights for policy 0, policy_version 108421 (0.0016) [2023-03-09 09:55:32,530][23090] Updated weights for policy 0, policy_version 108431 (0.0019) [2023-03-09 09:55:33,308][23090] Updated weights for policy 0, policy_version 108441 (0.0016) [2023-03-09 09:55:34,058][22664] Fps is (10 sec: 199890.8, 60 sec: 197701.3, 300 sec: 198385.5). Total num frames: 1776828416. Throughput: 0: 49409.4. Samples: 444225680. Policy #0 lag: (min: 2.0, avg: 17.4, max: 33.0) [2023-03-09 09:55:34,060][22664] Avg episode reward: [(0, '53.231')] [2023-03-09 09:55:34,180][23090] Updated weights for policy 0, policy_version 108451 (0.0015) [2023-03-09 09:55:35,001][23090] Updated weights for policy 0, policy_version 108461 (0.0018) [2023-03-09 09:55:35,825][23090] Updated weights for policy 0, policy_version 108472 (0.0014) [2023-03-09 09:55:36,707][23090] Updated weights for policy 0, policy_version 108482 (0.0020) [2023-03-09 09:55:37,569][23090] Updated weights for policy 0, policy_version 108492 (0.0019) [2023-03-09 09:55:38,086][22940] Signal inference workers to stop experience collection... (36950 times) [2023-03-09 09:55:38,096][22940] Signal inference workers to resume experience collection... (36950 times) [2023-03-09 09:55:38,128][23090] InferenceWorker_p0-w0: stopping experience collection (36950 times) [2023-03-09 09:55:38,172][23090] InferenceWorker_p0-w0: resuming experience collection (36950 times) [2023-03-09 09:55:38,257][23090] Updated weights for policy 0, policy_version 108502 (0.0019) [2023-03-09 09:55:39,059][22664] Fps is (10 sec: 201524.5, 60 sec: 198245.6, 300 sec: 198551.9). Total num frames: 1777844224. Throughput: 0: 49406.9. Samples: 444522448. Policy #0 lag: (min: 1.0, avg: 16.7, max: 33.0) [2023-03-09 09:55:39,060][22664] Avg episode reward: [(0, '54.258')] [2023-03-09 09:55:39,121][23090] Updated weights for policy 0, policy_version 108512 (0.0016) [2023-03-09 09:55:40,128][23090] Updated weights for policy 0, policy_version 108522 (0.0016) [2023-03-09 09:55:40,858][23090] Updated weights for policy 0, policy_version 108532 (0.0019) [2023-03-09 09:55:41,596][23090] Updated weights for policy 0, policy_version 108542 (0.0023) [2023-03-09 09:55:42,608][23090] Updated weights for policy 0, policy_version 108552 (0.0022) [2023-03-09 09:55:43,427][23090] Updated weights for policy 0, policy_version 108563 (0.0019) [2023-03-09 09:55:44,059][22664] Fps is (10 sec: 199881.4, 60 sec: 198245.9, 300 sec: 198496.5). Total num frames: 1778827264. Throughput: 0: 49407.1. Samples: 444671936. Policy #0 lag: (min: 1.0, avg: 16.7, max: 33.0) [2023-03-09 09:55:44,061][22664] Avg episode reward: [(0, '54.861')] [2023-03-09 09:55:44,178][23090] Updated weights for policy 0, policy_version 108573 (0.0015) [2023-03-09 09:55:45,226][23090] Updated weights for policy 0, policy_version 108583 (0.0018) [2023-03-09 09:55:45,854][23090] Updated weights for policy 0, policy_version 108593 (0.0013) [2023-03-09 09:55:46,684][23090] Updated weights for policy 0, policy_version 108603 (0.0015) [2023-03-09 09:55:47,558][23090] Updated weights for policy 0, policy_version 108613 (0.0017) [2023-03-09 09:55:48,433][23090] Updated weights for policy 0, policy_version 108624 (0.0015) [2023-03-09 09:55:49,058][22664] Fps is (10 sec: 198251.5, 60 sec: 197974.5, 300 sec: 198496.5). Total num frames: 1779826688. Throughput: 0: 49423.9. Samples: 444969488. Policy #0 lag: (min: 1.0, avg: 16.7, max: 33.0) [2023-03-09 09:55:49,059][22664] Avg episode reward: [(0, '53.852')] [2023-03-09 09:55:49,125][22940] Signal inference workers to stop experience collection... (37000 times) [2023-03-09 09:55:49,126][22940] Signal inference workers to resume experience collection... (37000 times) [2023-03-09 09:55:49,197][23090] InferenceWorker_p0-w0: stopping experience collection (37000 times) [2023-03-09 09:55:49,197][23090] InferenceWorker_p0-w0: resuming experience collection (37000 times) [2023-03-09 09:55:49,200][23090] Updated weights for policy 0, policy_version 108634 (0.0020) [2023-03-09 09:55:50,105][23090] Updated weights for policy 0, policy_version 108644 (0.0020) [2023-03-09 09:55:50,885][23090] Updated weights for policy 0, policy_version 108654 (0.0017) [2023-03-09 09:55:51,645][23090] Updated weights for policy 0, policy_version 108664 (0.0013) [2023-03-09 09:55:52,561][23090] Updated weights for policy 0, policy_version 108674 (0.0019) [2023-03-09 09:55:53,388][23090] Updated weights for policy 0, policy_version 108685 (0.0015) [2023-03-09 09:55:54,059][22664] Fps is (10 sec: 201514.8, 60 sec: 198245.2, 300 sec: 198496.2). Total num frames: 1780842496. Throughput: 0: 49558.1. Samples: 445268384. Policy #0 lag: (min: 1.0, avg: 16.7, max: 33.0) [2023-03-09 09:55:54,061][22664] Avg episode reward: [(0, '54.583')] [2023-03-09 09:55:54,157][23090] Updated weights for policy 0, policy_version 108695 (0.0013) [2023-03-09 09:55:55,025][23090] Updated weights for policy 0, policy_version 108705 (0.0013) [2023-03-09 09:55:55,891][23090] Updated weights for policy 0, policy_version 108715 (0.0012) [2023-03-09 09:55:56,651][23090] Updated weights for policy 0, policy_version 108725 (0.0021) [2023-03-09 09:55:57,388][23090] Updated weights for policy 0, policy_version 108735 (0.0019) [2023-03-09 09:55:58,471][23090] Updated weights for policy 0, policy_version 108745 (0.0016) [2023-03-09 09:55:59,059][22664] Fps is (10 sec: 198240.7, 60 sec: 197699.4, 300 sec: 198385.3). Total num frames: 1781809152. Throughput: 0: 49603.9. Samples: 445419888. Policy #0 lag: (min: 1.0, avg: 16.7, max: 33.0) [2023-03-09 09:55:59,060][22664] Avg episode reward: [(0, '53.112')] [2023-03-09 09:55:59,125][23090] Updated weights for policy 0, policy_version 108755 (0.0016) [2023-03-09 09:55:59,916][23090] Updated weights for policy 0, policy_version 108765 (0.0020) [2023-03-09 09:56:00,984][23090] Updated weights for policy 0, policy_version 108775 (0.0013) [2023-03-09 09:56:01,491][22940] Signal inference workers to stop experience collection... (37050 times) [2023-03-09 09:56:01,504][22940] Signal inference workers to resume experience collection... (37050 times) [2023-03-09 09:56:01,564][23090] InferenceWorker_p0-w0: stopping experience collection (37050 times) [2023-03-09 09:56:01,564][23090] InferenceWorker_p0-w0: resuming experience collection (37050 times) [2023-03-09 09:56:01,644][23090] Updated weights for policy 0, policy_version 108785 (0.0017) [2023-03-09 09:56:02,402][23090] Updated weights for policy 0, policy_version 108795 (0.0021) [2023-03-09 09:56:03,366][23090] Updated weights for policy 0, policy_version 108805 (0.0020) [2023-03-09 09:56:04,059][22664] Fps is (10 sec: 194975.7, 60 sec: 197973.2, 300 sec: 198440.6). Total num frames: 1782792192. Throughput: 0: 49604.0. Samples: 445716736. Policy #0 lag: (min: 1.0, avg: 16.7, max: 33.0) [2023-03-09 09:56:04,061][22664] Avg episode reward: [(0, '53.038')] [2023-03-09 09:56:04,221][23090] Updated weights for policy 0, policy_version 108816 (0.0016) [2023-03-09 09:56:04,986][23090] Updated weights for policy 0, policy_version 108826 (0.0014) [2023-03-09 09:56:05,892][23090] Updated weights for policy 0, policy_version 108836 (0.0013) [2023-03-09 09:56:06,710][23090] Updated weights for policy 0, policy_version 108846 (0.0019) [2023-03-09 09:56:07,434][23090] Updated weights for policy 0, policy_version 108856 (0.0016) [2023-03-09 09:56:08,368][23090] Updated weights for policy 0, policy_version 108866 (0.0018) [2023-03-09 09:56:09,059][22664] Fps is (10 sec: 198250.7, 60 sec: 197974.3, 300 sec: 198330.0). Total num frames: 1783791616. Throughput: 0: 49695.6. Samples: 446015648. Policy #0 lag: (min: 1.0, avg: 16.7, max: 33.0) [2023-03-09 09:56:09,060][22664] Avg episode reward: [(0, '53.558')] [2023-03-09 09:56:09,146][23090] Updated weights for policy 0, policy_version 108876 (0.0016) [2023-03-09 09:56:09,892][23090] Updated weights for policy 0, policy_version 108886 (0.0022) [2023-03-09 09:56:10,710][23090] Updated weights for policy 0, policy_version 108896 (0.0019) [2023-03-09 09:56:11,702][23090] Updated weights for policy 0, policy_version 108906 (0.0017) [2023-03-09 09:56:12,485][23090] Updated weights for policy 0, policy_version 108917 (0.0016) [2023-03-09 09:56:13,453][23090] Updated weights for policy 0, policy_version 108928 (0.0016) [2023-03-09 09:56:14,059][22664] Fps is (10 sec: 196605.6, 60 sec: 197972.8, 300 sec: 198274.1). Total num frames: 1784758272. Throughput: 0: 49740.7. Samples: 446165056. Policy #0 lag: (min: 1.0, avg: 16.7, max: 33.0) [2023-03-09 09:56:14,061][22664] Avg episode reward: [(0, '55.079')] [2023-03-09 09:56:14,237][22940] Signal inference workers to stop experience collection... (37100 times) [2023-03-09 09:56:14,255][22940] Signal inference workers to resume experience collection... (37100 times) [2023-03-09 09:56:14,320][23090] InferenceWorker_p0-w0: stopping experience collection (37100 times) [2023-03-09 09:56:14,366][23090] InferenceWorker_p0-w0: resuming experience collection (37100 times) [2023-03-09 09:56:14,412][23090] Updated weights for policy 0, policy_version 108939 (0.0020) [2023-03-09 09:56:15,203][23090] Updated weights for policy 0, policy_version 108949 (0.0018) [2023-03-09 09:56:15,939][23090] Updated weights for policy 0, policy_version 108959 (0.0016) [2023-03-09 09:56:17,012][23090] Updated weights for policy 0, policy_version 108969 (0.0016) [2023-03-09 09:56:17,675][23090] Updated weights for policy 0, policy_version 108979 (0.0013) [2023-03-09 09:56:18,478][23090] Updated weights for policy 0, policy_version 108989 (0.0021) [2023-03-09 09:56:19,058][22664] Fps is (10 sec: 196608.8, 60 sec: 198246.5, 300 sec: 198330.1). Total num frames: 1785757696. Throughput: 0: 49603.6. Samples: 446457840. Policy #0 lag: (min: 1.0, avg: 16.7, max: 33.0) [2023-03-09 09:56:19,059][22664] Avg episode reward: [(0, '54.596')] [2023-03-09 09:56:19,511][23090] Updated weights for policy 0, policy_version 108999 (0.0013) [2023-03-09 09:56:20,219][23090] Updated weights for policy 0, policy_version 109009 (0.0018) [2023-03-09 09:56:20,991][23090] Updated weights for policy 0, policy_version 109019 (0.0012) [2023-03-09 09:56:21,946][23090] Updated weights for policy 0, policy_version 109029 (0.0017) [2023-03-09 09:56:22,778][23090] Updated weights for policy 0, policy_version 109040 (0.0019) [2023-03-09 09:56:23,540][23090] Updated weights for policy 0, policy_version 109050 (0.0016) [2023-03-09 09:56:24,059][22664] Fps is (10 sec: 201527.8, 60 sec: 199066.1, 300 sec: 198385.2). Total num frames: 1786773504. Throughput: 0: 49605.8. Samples: 446754704. Policy #0 lag: (min: 1.0, avg: 16.7, max: 33.0) [2023-03-09 09:56:24,060][22664] Avg episode reward: [(0, '54.239')] [2023-03-09 09:56:24,473][23090] Updated weights for policy 0, policy_version 109060 (0.0019) [2023-03-09 09:56:24,803][22940] Signal inference workers to stop experience collection... (37150 times) [2023-03-09 09:56:24,824][22940] Signal inference workers to resume experience collection... (37150 times) [2023-03-09 09:56:24,903][23090] InferenceWorker_p0-w0: stopping experience collection (37150 times) [2023-03-09 09:56:24,903][23090] InferenceWorker_p0-w0: resuming experience collection (37150 times) [2023-03-09 09:56:25,329][23090] Updated weights for policy 0, policy_version 109070 (0.0013) [2023-03-09 09:56:26,018][23090] Updated weights for policy 0, policy_version 109080 (0.0017) [2023-03-09 09:56:26,975][23090] Updated weights for policy 0, policy_version 109090 (0.0019) [2023-03-09 09:56:27,758][23090] Updated weights for policy 0, policy_version 109100 (0.0013) [2023-03-09 09:56:28,531][23090] Updated weights for policy 0, policy_version 109110 (0.0019) [2023-03-09 09:56:29,059][22664] Fps is (10 sec: 201515.7, 60 sec: 199065.4, 300 sec: 198440.7). Total num frames: 1787772928. Throughput: 0: 49558.9. Samples: 446902096. Policy #0 lag: (min: 1.0, avg: 16.7, max: 33.0) [2023-03-09 09:56:29,060][22664] Avg episode reward: [(0, '53.047')] [2023-03-09 09:56:29,370][23090] Updated weights for policy 0, policy_version 109120 (0.0013) [2023-03-09 09:56:30,350][23090] Updated weights for policy 0, policy_version 109131 (0.0013) [2023-03-09 09:56:31,122][23090] Updated weights for policy 0, policy_version 109141 (0.0015) [2023-03-09 09:56:31,858][23090] Updated weights for policy 0, policy_version 109151 (0.0016) [2023-03-09 09:56:32,936][23090] Updated weights for policy 0, policy_version 109161 (0.0015) [2023-03-09 09:56:33,607][23090] Updated weights for policy 0, policy_version 109171 (0.0019) [2023-03-09 09:56:34,059][22664] Fps is (10 sec: 196608.7, 60 sec: 198519.0, 300 sec: 198385.1). Total num frames: 1788739584. Throughput: 0: 49542.6. Samples: 447198912. Policy #0 lag: (min: 1.0, avg: 16.7, max: 33.0) [2023-03-09 09:56:34,060][22664] Avg episode reward: [(0, '53.747')] [2023-03-09 09:56:34,407][23090] Updated weights for policy 0, policy_version 109181 (0.0013) [2023-03-09 09:56:35,446][23090] Updated weights for policy 0, policy_version 109191 (0.0016) [2023-03-09 09:56:35,569][22940] Signal inference workers to stop experience collection... (37200 times) [2023-03-09 09:56:35,596][22940] Signal inference workers to resume experience collection... (37200 times) [2023-03-09 09:56:35,622][23090] InferenceWorker_p0-w0: stopping experience collection (37200 times) [2023-03-09 09:56:35,623][23090] InferenceWorker_p0-w0: resuming experience collection (37200 times) [2023-03-09 09:56:36,136][23090] Updated weights for policy 0, policy_version 109201 (0.0016) [2023-03-09 09:56:36,900][23090] Updated weights for policy 0, policy_version 109211 (0.0013) [2023-03-09 09:56:37,859][23090] Updated weights for policy 0, policy_version 109221 (0.0014) [2023-03-09 09:56:38,627][23090] Updated weights for policy 0, policy_version 109231 (0.0025) [2023-03-09 09:56:39,058][22664] Fps is (10 sec: 196615.4, 60 sec: 198247.2, 300 sec: 198329.9). Total num frames: 1789739008. Throughput: 0: 49542.7. Samples: 447497776. Policy #0 lag: (min: 1.0, avg: 16.2, max: 32.0) [2023-03-09 09:56:39,059][22664] Avg episode reward: [(0, '56.400')] [2023-03-09 09:56:39,420][23090] Updated weights for policy 0, policy_version 109241 (0.0019) [2023-03-09 09:56:40,269][23090] Updated weights for policy 0, policy_version 109251 (0.0014) [2023-03-09 09:56:41,295][23090] Updated weights for policy 0, policy_version 109262 (0.0019) [2023-03-09 09:56:41,993][23090] Updated weights for policy 0, policy_version 109272 (0.0013) [2023-03-09 09:56:43,031][23090] Updated weights for policy 0, policy_version 109283 (0.0016) [2023-03-09 09:56:43,854][23090] Updated weights for policy 0, policy_version 109293 (0.0016) [2023-03-09 09:56:44,059][22664] Fps is (10 sec: 196600.2, 60 sec: 197972.2, 300 sec: 198163.0). Total num frames: 1790705664. Throughput: 0: 49361.1. Samples: 447641152. Policy #0 lag: (min: 1.0, avg: 16.2, max: 32.0) [2023-03-09 09:56:44,061][22664] Avg episode reward: [(0, '56.447')] [2023-03-09 09:56:44,590][23090] Updated weights for policy 0, policy_version 109303 (0.0016) [2023-03-09 09:56:45,444][23090] Updated weights for policy 0, policy_version 109313 (0.0016) [2023-03-09 09:56:46,340][23090] Updated weights for policy 0, policy_version 109323 (0.0017) [2023-03-09 09:56:47,102][23090] Updated weights for policy 0, policy_version 109333 (0.0013) [2023-03-09 09:56:47,115][22940] Signal inference workers to stop experience collection... (37250 times) [2023-03-09 09:56:47,116][22940] Signal inference workers to resume experience collection... (37250 times) [2023-03-09 09:56:47,178][23090] InferenceWorker_p0-w0: stopping experience collection (37250 times) [2023-03-09 09:56:47,179][23090] InferenceWorker_p0-w0: resuming experience collection (37250 times) [2023-03-09 09:56:47,845][23090] Updated weights for policy 0, policy_version 109343 (0.0016) [2023-03-09 09:56:48,915][23090] Updated weights for policy 0, policy_version 109353 (0.0013) [2023-03-09 09:56:49,059][22664] Fps is (10 sec: 194966.3, 60 sec: 197699.7, 300 sec: 198107.6). Total num frames: 1791688704. Throughput: 0: 49316.0. Samples: 447935952. Policy #0 lag: (min: 1.0, avg: 16.2, max: 32.0) [2023-03-09 09:56:49,060][22664] Avg episode reward: [(0, '54.100')] [2023-03-09 09:56:49,659][23090] Updated weights for policy 0, policy_version 109364 (0.0024) [2023-03-09 09:56:50,417][23090] Updated weights for policy 0, policy_version 109374 (0.0013) [2023-03-09 09:56:51,452][23090] Updated weights for policy 0, policy_version 109384 (0.0015) [2023-03-09 09:56:52,187][23090] Updated weights for policy 0, policy_version 109394 (0.0013) [2023-03-09 09:56:52,949][23090] Updated weights for policy 0, policy_version 109405 (0.0016) [2023-03-09 09:56:54,044][23090] Updated weights for policy 0, policy_version 109415 (0.0022) [2023-03-09 09:56:54,059][22664] Fps is (10 sec: 194974.9, 60 sec: 196882.2, 300 sec: 198107.4). Total num frames: 1792655360. Throughput: 0: 49314.6. Samples: 448234816. Policy #0 lag: (min: 1.0, avg: 16.2, max: 32.0) [2023-03-09 09:56:54,060][22664] Avg episode reward: [(0, '53.525')] [2023-03-09 09:56:54,724][23090] Updated weights for policy 0, policy_version 109425 (0.0013) [2023-03-09 09:56:55,492][23090] Updated weights for policy 0, policy_version 109435 (0.0021) [2023-03-09 09:56:56,480][23090] Updated weights for policy 0, policy_version 109445 (0.0017) [2023-03-09 09:56:57,271][23090] Updated weights for policy 0, policy_version 109455 (0.0019) [2023-03-09 09:56:57,839][22940] Signal inference workers to stop experience collection... (37300 times) [2023-03-09 09:56:57,839][22940] Signal inference workers to resume experience collection... (37300 times) [2023-03-09 09:56:57,899][23090] InferenceWorker_p0-w0: stopping experience collection (37300 times) [2023-03-09 09:56:57,899][23090] InferenceWorker_p0-w0: resuming experience collection (37300 times) [2023-03-09 09:56:58,102][23090] Updated weights for policy 0, policy_version 109466 (0.0016) [2023-03-09 09:56:58,997][23090] Updated weights for policy 0, policy_version 109476 (0.0013) [2023-03-09 09:56:59,059][22664] Fps is (10 sec: 196610.9, 60 sec: 197428.0, 300 sec: 198052.0). Total num frames: 1793654784. Throughput: 0: 49316.3. Samples: 448384272. Policy #0 lag: (min: 1.0, avg: 16.2, max: 32.0) [2023-03-09 09:56:59,060][22664] Avg episode reward: [(0, '53.433')] [2023-03-09 09:56:59,813][23090] Updated weights for policy 0, policy_version 109486 (0.0016) [2023-03-09 09:57:00,557][23090] Updated weights for policy 0, policy_version 109496 (0.0013) [2023-03-09 09:57:01,488][23090] Updated weights for policy 0, policy_version 109506 (0.0021) [2023-03-09 09:57:02,422][23090] Updated weights for policy 0, policy_version 109517 (0.0013) [2023-03-09 09:57:03,132][23090] Updated weights for policy 0, policy_version 109527 (0.0015) [2023-03-09 09:57:04,015][23090] Updated weights for policy 0, policy_version 109537 (0.0015) [2023-03-09 09:57:04,059][22664] Fps is (10 sec: 199878.5, 60 sec: 197699.3, 300 sec: 198052.0). Total num frames: 1794654208. Throughput: 0: 49360.1. Samples: 448679072. Policy #0 lag: (min: 1.0, avg: 16.2, max: 32.0) [2023-03-09 09:57:04,061][22664] Avg episode reward: [(0, '54.079')] [2023-03-09 09:57:04,907][23090] Updated weights for policy 0, policy_version 109547 (0.0016) [2023-03-09 09:57:05,660][23090] Updated weights for policy 0, policy_version 109557 (0.0028) [2023-03-09 09:57:06,567][23090] Updated weights for policy 0, policy_version 109568 (0.0020) [2023-03-09 09:57:07,511][23090] Updated weights for policy 0, policy_version 109578 (0.0015) [2023-03-09 09:57:08,221][23090] Updated weights for policy 0, policy_version 109588 (0.0016) [2023-03-09 09:57:08,438][22940] Signal inference workers to stop experience collection... (37350 times) [2023-03-09 09:57:08,439][22940] Signal inference workers to resume experience collection... (37350 times) [2023-03-09 09:57:08,503][23090] InferenceWorker_p0-w0: stopping experience collection (37350 times) [2023-03-09 09:57:08,505][23090] InferenceWorker_p0-w0: resuming experience collection (37350 times) [2023-03-09 09:57:08,957][23090] Updated weights for policy 0, policy_version 109598 (0.0016) [2023-03-09 09:57:09,058][22664] Fps is (10 sec: 199885.4, 60 sec: 197700.5, 300 sec: 198107.5). Total num frames: 1795653632. Throughput: 0: 49359.8. Samples: 448975888. Policy #0 lag: (min: 1.0, avg: 16.2, max: 32.0) [2023-03-09 09:57:09,059][22664] Avg episode reward: [(0, '53.590')] [2023-03-09 09:57:10,065][23090] Updated weights for policy 0, policy_version 109608 (0.0016) [2023-03-09 09:57:10,740][23090] Updated weights for policy 0, policy_version 109618 (0.0014) [2023-03-09 09:57:11,533][23090] Updated weights for policy 0, policy_version 109628 (0.0017) [2023-03-09 09:57:12,618][23090] Updated weights for policy 0, policy_version 109638 (0.0015) [2023-03-09 09:57:13,302][23090] Updated weights for policy 0, policy_version 109648 (0.0014) [2023-03-09 09:57:14,058][22664] Fps is (10 sec: 198258.3, 60 sec: 197974.7, 300 sec: 198052.2). Total num frames: 1796636672. Throughput: 0: 49359.0. Samples: 449123232. Policy #0 lag: (min: 1.0, avg: 16.2, max: 32.0) [2023-03-09 09:57:14,059][22664] Avg episode reward: [(0, '54.878')] [2023-03-09 09:57:14,066][23090] Updated weights for policy 0, policy_version 109658 (0.0019) [2023-03-09 09:57:14,929][23090] Updated weights for policy 0, policy_version 109668 (0.0020) [2023-03-09 09:57:15,851][23090] Updated weights for policy 0, policy_version 109679 (0.0017) [2023-03-09 09:57:16,627][23090] Updated weights for policy 0, policy_version 109689 (0.0013) [2023-03-09 09:57:17,475][23090] Updated weights for policy 0, policy_version 109699 (0.0022) [2023-03-09 09:57:17,961][22940] Signal inference workers to stop experience collection... (37400 times) [2023-03-09 09:57:17,976][22940] Signal inference workers to resume experience collection... (37400 times) [2023-03-09 09:57:18,007][23090] InferenceWorker_p0-w0: stopping experience collection (37400 times) [2023-03-09 09:57:18,048][23090] InferenceWorker_p0-w0: resuming experience collection (37400 times) [2023-03-09 09:57:18,336][23090] Updated weights for policy 0, policy_version 109709 (0.0018) [2023-03-09 09:57:19,050][23090] Updated weights for policy 0, policy_version 109719 (0.0013) [2023-03-09 09:57:19,059][22664] Fps is (10 sec: 198238.3, 60 sec: 197972.1, 300 sec: 198218.7). Total num frames: 1797636096. Throughput: 0: 49359.0. Samples: 449420080. Policy #0 lag: (min: 1.0, avg: 16.2, max: 32.0) [2023-03-09 09:57:19,061][22664] Avg episode reward: [(0, '56.257')] [2023-03-09 09:57:19,111][22940] Saving /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000109720_1797652480.pth... [2023-03-09 09:57:19,163][22940] Removing /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000106818_1750106112.pth [2023-03-09 09:57:19,931][23090] Updated weights for policy 0, policy_version 109729 (0.0013) [2023-03-09 09:57:20,790][23090] Updated weights for policy 0, policy_version 109739 (0.0020) [2023-03-09 09:57:21,628][23090] Updated weights for policy 0, policy_version 109749 (0.0019) [2023-03-09 09:57:22,474][23090] Updated weights for policy 0, policy_version 109760 (0.0015) [2023-03-09 09:57:23,414][23090] Updated weights for policy 0, policy_version 109770 (0.0013) [2023-03-09 09:57:24,058][22664] Fps is (10 sec: 198246.3, 60 sec: 197427.8, 300 sec: 198107.6). Total num frames: 1798619136. Throughput: 0: 49358.6. Samples: 449718912. Policy #0 lag: (min: 1.0, avg: 16.2, max: 32.0) [2023-03-09 09:57:24,059][22664] Avg episode reward: [(0, '55.503')] [2023-03-09 09:57:24,074][23090] Updated weights for policy 0, policy_version 109780 (0.0013) [2023-03-09 09:57:24,877][23090] Updated weights for policy 0, policy_version 109790 (0.0013) [2023-03-09 09:57:25,875][23090] Updated weights for policy 0, policy_version 109800 (0.0020) [2023-03-09 09:57:26,612][23090] Updated weights for policy 0, policy_version 109810 (0.0017) [2023-03-09 09:57:26,868][22940] Signal inference workers to stop experience collection... (37450 times) [2023-03-09 09:57:26,869][22940] Signal inference workers to resume experience collection... (37450 times) [2023-03-09 09:57:26,933][23090] InferenceWorker_p0-w0: stopping experience collection (37450 times) [2023-03-09 09:57:26,935][23090] InferenceWorker_p0-w0: resuming experience collection (37450 times) [2023-03-09 09:57:27,372][23090] Updated weights for policy 0, policy_version 109820 (0.0013) [2023-03-09 09:57:28,420][23090] Updated weights for policy 0, policy_version 109830 (0.0013) [2023-03-09 09:57:29,059][22664] Fps is (10 sec: 196610.0, 60 sec: 197154.4, 300 sec: 198052.1). Total num frames: 1799602176. Throughput: 0: 49448.1. Samples: 449866304. Policy #0 lag: (min: 1.0, avg: 16.2, max: 32.0) [2023-03-09 09:57:29,060][22664] Avg episode reward: [(0, '52.928')] [2023-03-09 09:57:29,120][23090] Updated weights for policy 0, policy_version 109840 (0.0013) [2023-03-09 09:57:29,870][23090] Updated weights for policy 0, policy_version 109850 (0.0016) [2023-03-09 09:57:30,755][23090] Updated weights for policy 0, policy_version 109860 (0.0016) [2023-03-09 09:57:31,627][23090] Updated weights for policy 0, policy_version 109871 (0.0017) [2023-03-09 09:57:32,433][23090] Updated weights for policy 0, policy_version 109881 (0.0021) [2023-03-09 09:57:33,277][23090] Updated weights for policy 0, policy_version 109891 (0.0014) [2023-03-09 09:57:34,059][22664] Fps is (10 sec: 198238.5, 60 sec: 197699.5, 300 sec: 197996.2). Total num frames: 1800601600. Throughput: 0: 49584.5. Samples: 450167264. Policy #0 lag: (min: 1.0, avg: 16.2, max: 32.0) [2023-03-09 09:57:34,061][22664] Avg episode reward: [(0, '55.363')] [2023-03-09 09:57:34,167][23090] Updated weights for policy 0, policy_version 109901 (0.0013) [2023-03-09 09:57:34,886][23090] Updated weights for policy 0, policy_version 109912 (0.0021) [2023-03-09 09:57:35,052][22940] Signal inference workers to stop experience collection... (37500 times) [2023-03-09 09:57:35,052][22940] Signal inference workers to resume experience collection... (37500 times) [2023-03-09 09:57:35,120][23090] InferenceWorker_p0-w0: stopping experience collection (37500 times) [2023-03-09 09:57:35,121][23090] InferenceWorker_p0-w0: resuming experience collection (37500 times) [2023-03-09 09:57:35,822][23090] Updated weights for policy 0, policy_version 109922 (0.0016) [2023-03-09 09:57:36,624][23090] Updated weights for policy 0, policy_version 109932 (0.0017) [2023-03-09 09:57:37,397][23090] Updated weights for policy 0, policy_version 109942 (0.0017) [2023-03-09 09:57:38,323][23090] Updated weights for policy 0, policy_version 109953 (0.0013) [2023-03-09 09:57:39,058][22664] Fps is (10 sec: 198252.4, 60 sec: 197427.2, 300 sec: 198052.2). Total num frames: 1801584640. Throughput: 0: 49586.8. Samples: 450466208. Policy #0 lag: (min: 1.0, avg: 16.2, max: 32.0) [2023-03-09 09:57:39,059][22664] Avg episode reward: [(0, '55.169')] [2023-03-09 09:57:39,200][23090] Updated weights for policy 0, policy_version 109963 (0.0016) [2023-03-09 09:57:40,021][23090] Updated weights for policy 0, policy_version 109973 (0.0020) [2023-03-09 09:57:40,906][23090] Updated weights for policy 0, policy_version 109984 (0.0013) [2023-03-09 09:57:41,804][23090] Updated weights for policy 0, policy_version 109994 (0.0017) [2023-03-09 09:57:42,537][23090] Updated weights for policy 0, policy_version 110004 (0.0013) [2023-03-09 09:57:43,313][23090] Updated weights for policy 0, policy_version 110014 (0.0013) [2023-03-09 09:57:44,058][22664] Fps is (10 sec: 196615.5, 60 sec: 197702.0, 300 sec: 197996.8). Total num frames: 1802567680. Throughput: 0: 49542.1. Samples: 450613664. Policy #0 lag: (min: 3.0, avg: 17.3, max: 35.0) [2023-03-09 09:57:44,060][22664] Avg episode reward: [(0, '55.675')] [2023-03-09 09:57:44,191][22940] Signal inference workers to stop experience collection... (37550 times) [2023-03-09 09:57:44,204][22940] Signal inference workers to resume experience collection... (37550 times) [2023-03-09 09:57:44,266][23090] InferenceWorker_p0-w0: stopping experience collection (37550 times) [2023-03-09 09:57:44,267][23090] InferenceWorker_p0-w0: resuming experience collection (37550 times) [2023-03-09 09:57:44,353][23090] Updated weights for policy 0, policy_version 110024 (0.0013) [2023-03-09 09:57:45,006][23090] Updated weights for policy 0, policy_version 110034 (0.0017) [2023-03-09 09:57:45,801][23090] Updated weights for policy 0, policy_version 110044 (0.0014) [2023-03-09 09:57:46,801][23090] Updated weights for policy 0, policy_version 110054 (0.0017) [2023-03-09 09:57:47,597][23090] Updated weights for policy 0, policy_version 110065 (0.0027) [2023-03-09 09:57:48,363][23090] Updated weights for policy 0, policy_version 110075 (0.0020) [2023-03-09 09:57:49,059][22664] Fps is (10 sec: 199883.7, 60 sec: 198246.8, 300 sec: 198052.1). Total num frames: 1803583488. Throughput: 0: 49632.6. Samples: 450912512. Policy #0 lag: (min: 3.0, avg: 17.3, max: 35.0) [2023-03-09 09:57:49,060][22664] Avg episode reward: [(0, '55.528')] [2023-03-09 09:57:49,352][23090] Updated weights for policy 0, policy_version 110085 (0.0013) [2023-03-09 09:57:50,050][23090] Updated weights for policy 0, policy_version 110095 (0.0017) [2023-03-09 09:57:50,835][23090] Updated weights for policy 0, policy_version 110105 (0.0013) [2023-03-09 09:57:51,838][23090] Updated weights for policy 0, policy_version 110116 (0.0016) [2023-03-09 09:57:52,652][23090] Updated weights for policy 0, policy_version 110126 (0.0026) [2023-03-09 09:57:53,170][22940] Signal inference workers to stop experience collection... (37600 times) [2023-03-09 09:57:53,178][22940] Signal inference workers to resume experience collection... (37600 times) [2023-03-09 09:57:53,252][23090] InferenceWorker_p0-w0: stopping experience collection (37600 times) [2023-03-09 09:57:53,252][23090] InferenceWorker_p0-w0: resuming experience collection (37600 times) [2023-03-09 09:57:53,343][23090] Updated weights for policy 0, policy_version 110136 (0.0013) [2023-03-09 09:57:54,059][22664] Fps is (10 sec: 201522.3, 60 sec: 198793.3, 300 sec: 198163.1). Total num frames: 1804582912. Throughput: 0: 49632.7. Samples: 451209360. Policy #0 lag: (min: 3.0, avg: 17.3, max: 35.0) [2023-03-09 09:57:54,059][22664] Avg episode reward: [(0, '56.362')] [2023-03-09 09:57:54,275][23090] Updated weights for policy 0, policy_version 110146 (0.0015) [2023-03-09 09:57:55,096][23090] Updated weights for policy 0, policy_version 110156 (0.0018) [2023-03-09 09:57:55,882][23090] Updated weights for policy 0, policy_version 110166 (0.0016) [2023-03-09 09:57:56,796][23090] Updated weights for policy 0, policy_version 110177 (0.0016) [2023-03-09 09:57:57,681][23090] Updated weights for policy 0, policy_version 110187 (0.0020) [2023-03-09 09:57:58,481][23090] Updated weights for policy 0, policy_version 110197 (0.0016) [2023-03-09 09:57:59,059][22664] Fps is (10 sec: 201517.4, 60 sec: 199064.6, 300 sec: 198218.5). Total num frames: 1805598720. Throughput: 0: 49724.1. Samples: 451360832. Policy #0 lag: (min: 3.0, avg: 17.3, max: 35.0) [2023-03-09 09:57:59,061][22664] Avg episode reward: [(0, '54.772')] [2023-03-09 09:57:59,205][23090] Updated weights for policy 0, policy_version 110207 (0.0013) [2023-03-09 09:58:00,209][23090] Updated weights for policy 0, policy_version 110217 (0.0021) [2023-03-09 09:58:00,902][23090] Updated weights for policy 0, policy_version 110227 (0.0016) [2023-03-09 09:58:01,755][23090] Updated weights for policy 0, policy_version 110238 (0.0013) [2023-03-09 09:58:02,328][22940] Signal inference workers to stop experience collection... (37650 times) [2023-03-09 09:58:02,329][22940] Signal inference workers to resume experience collection... (37650 times) [2023-03-09 09:58:02,388][23090] InferenceWorker_p0-w0: stopping experience collection (37650 times) [2023-03-09 09:58:02,389][23090] InferenceWorker_p0-w0: resuming experience collection (37650 times) [2023-03-09 09:58:02,797][23090] Updated weights for policy 0, policy_version 110248 (0.0021) [2023-03-09 09:58:03,471][23090] Updated weights for policy 0, policy_version 110258 (0.0014) [2023-03-09 09:58:04,059][22664] Fps is (10 sec: 199884.7, 60 sec: 198794.3, 300 sec: 198274.4). Total num frames: 1806581760. Throughput: 0: 49724.1. Samples: 451657648. Policy #0 lag: (min: 3.0, avg: 17.3, max: 35.0) [2023-03-09 09:58:04,060][22664] Avg episode reward: [(0, '56.526')] [2023-03-09 09:58:04,285][23090] Updated weights for policy 0, policy_version 110268 (0.0013) [2023-03-09 09:58:05,319][23090] Updated weights for policy 0, policy_version 110278 (0.0020) [2023-03-09 09:58:06,000][23090] Updated weights for policy 0, policy_version 110288 (0.0023) [2023-03-09 09:58:06,736][23090] Updated weights for policy 0, policy_version 110298 (0.0015) [2023-03-09 09:58:07,657][23090] Updated weights for policy 0, policy_version 110308 (0.0013) [2023-03-09 09:58:08,457][23090] Updated weights for policy 0, policy_version 110318 (0.0015) [2023-03-09 09:58:09,059][22664] Fps is (10 sec: 198246.3, 60 sec: 198791.4, 300 sec: 198274.0). Total num frames: 1807581184. Throughput: 0: 49723.3. Samples: 451956480. Policy #0 lag: (min: 3.0, avg: 17.3, max: 35.0) [2023-03-09 09:58:09,061][22664] Avg episode reward: [(0, '54.980')] [2023-03-09 09:58:09,144][23090] Updated weights for policy 0, policy_version 110328 (0.0013) [2023-03-09 09:58:10,078][23090] Updated weights for policy 0, policy_version 110338 (0.0022) [2023-03-09 09:58:10,922][23090] Updated weights for policy 0, policy_version 110348 (0.0016) [2023-03-09 09:58:11,257][22940] Signal inference workers to stop experience collection... (37700 times) [2023-03-09 09:58:11,269][22940] Signal inference workers to resume experience collection... (37700 times) [2023-03-09 09:58:11,334][23090] InferenceWorker_p0-w0: stopping experience collection (37700 times) [2023-03-09 09:58:11,334][23090] InferenceWorker_p0-w0: resuming experience collection (37700 times) [2023-03-09 09:58:11,744][23090] Updated weights for policy 0, policy_version 110358 (0.0021) [2023-03-09 09:58:12,552][23090] Updated weights for policy 0, policy_version 110368 (0.0018) [2023-03-09 09:58:13,465][23090] Updated weights for policy 0, policy_version 110378 (0.0016) [2023-03-09 09:58:14,059][22664] Fps is (10 sec: 198245.9, 60 sec: 198792.2, 300 sec: 198218.6). Total num frames: 1808564224. Throughput: 0: 49768.8. Samples: 452105888. Policy #0 lag: (min: 3.0, avg: 17.3, max: 35.0) [2023-03-09 09:58:14,060][22664] Avg episode reward: [(0, '53.239')] [2023-03-09 09:58:14,182][23090] Updated weights for policy 0, policy_version 110388 (0.0013) [2023-03-09 09:58:14,955][23090] Updated weights for policy 0, policy_version 110398 (0.0013) [2023-03-09 09:58:15,994][23090] Updated weights for policy 0, policy_version 110408 (0.0017) [2023-03-09 09:58:16,646][23090] Updated weights for policy 0, policy_version 110418 (0.0013) [2023-03-09 09:58:17,467][23090] Updated weights for policy 0, policy_version 110428 (0.0019) [2023-03-09 09:58:18,484][23090] Updated weights for policy 0, policy_version 110438 (0.0018) [2023-03-09 09:58:19,059][22664] Fps is (10 sec: 196608.1, 60 sec: 198519.7, 300 sec: 198107.5). Total num frames: 1809547264. Throughput: 0: 49678.3. Samples: 452402784. Policy #0 lag: (min: 3.0, avg: 17.3, max: 35.0) [2023-03-09 09:58:19,060][22664] Avg episode reward: [(0, '54.728')] [2023-03-09 09:58:19,141][23090] Updated weights for policy 0, policy_version 110448 (0.0016) [2023-03-09 09:58:19,957][23090] Updated weights for policy 0, policy_version 110458 (0.0016) [2023-03-09 09:58:20,991][23090] Updated weights for policy 0, policy_version 110469 (0.0020) [2023-03-09 09:58:21,652][22940] Signal inference workers to stop experience collection... (37750 times) [2023-03-09 09:58:21,666][22940] Signal inference workers to resume experience collection... (37750 times) [2023-03-09 09:58:21,733][23090] InferenceWorker_p0-w0: stopping experience collection (37750 times) [2023-03-09 09:58:21,733][23090] InferenceWorker_p0-w0: resuming experience collection (37750 times) [2023-03-09 09:58:21,736][23090] Updated weights for policy 0, policy_version 110479 (0.0016) [2023-03-09 09:58:22,503][23090] Updated weights for policy 0, policy_version 110489 (0.0018) [2023-03-09 09:58:23,423][23090] Updated weights for policy 0, policy_version 110499 (0.0013) [2023-03-09 09:58:24,059][22664] Fps is (10 sec: 196607.1, 60 sec: 198519.0, 300 sec: 198107.7). Total num frames: 1810530304. Throughput: 0: 49674.2. Samples: 452701552. Policy #0 lag: (min: 3.0, avg: 17.3, max: 35.0) [2023-03-09 09:58:24,060][22664] Avg episode reward: [(0, '53.760')] [2023-03-09 09:58:24,511][23090] Updated weights for policy 0, policy_version 110511 (0.0016) [2023-03-09 09:58:25,276][23090] Updated weights for policy 0, policy_version 110521 (0.0018) [2023-03-09 09:58:26,239][23090] Updated weights for policy 0, policy_version 110532 (0.0021) [2023-03-09 09:58:27,086][23090] Updated weights for policy 0, policy_version 110542 (0.0015) [2023-03-09 09:58:27,767][23090] Updated weights for policy 0, policy_version 110552 (0.0021) [2023-03-09 09:58:28,619][23090] Updated weights for policy 0, policy_version 110562 (0.0016) [2023-03-09 09:58:29,059][22664] Fps is (10 sec: 194972.1, 60 sec: 198246.7, 300 sec: 198052.1). Total num frames: 1811496960. Throughput: 0: 49582.0. Samples: 452844864. Policy #0 lag: (min: 3.0, avg: 17.3, max: 35.0) [2023-03-09 09:58:29,061][22664] Avg episode reward: [(0, '55.009')] [2023-03-09 09:58:29,518][23090] Updated weights for policy 0, policy_version 110572 (0.0013) [2023-03-09 09:58:30,349][23090] Updated weights for policy 0, policy_version 110582 (0.0025) [2023-03-09 09:58:31,146][23090] Updated weights for policy 0, policy_version 110592 (0.0013) [2023-03-09 09:58:32,112][23090] Updated weights for policy 0, policy_version 110602 (0.0016) [2023-03-09 09:58:32,796][23090] Updated weights for policy 0, policy_version 110612 (0.0011) [2023-03-09 09:58:33,581][23090] Updated weights for policy 0, policy_version 110622 (0.0017) [2023-03-09 09:58:34,059][22664] Fps is (10 sec: 198243.1, 60 sec: 198519.8, 300 sec: 198163.1). Total num frames: 1812512768. Throughput: 0: 49583.0. Samples: 453143760. Policy #0 lag: (min: 3.0, avg: 17.3, max: 35.0) [2023-03-09 09:58:34,061][22664] Avg episode reward: [(0, '54.929')] [2023-03-09 09:58:34,423][22940] Signal inference workers to stop experience collection... (37800 times) [2023-03-09 09:58:34,425][22940] Signal inference workers to resume experience collection... (37800 times) [2023-03-09 09:58:34,494][23090] InferenceWorker_p0-w0: stopping experience collection (37800 times) [2023-03-09 09:58:34,495][23090] InferenceWorker_p0-w0: resuming experience collection (37800 times) [2023-03-09 09:58:34,579][23090] Updated weights for policy 0, policy_version 110632 (0.0016) [2023-03-09 09:58:35,329][23090] Updated weights for policy 0, policy_version 110643 (0.0013) [2023-03-09 09:58:36,062][23090] Updated weights for policy 0, policy_version 110653 (0.0013) [2023-03-09 09:58:37,121][23090] Updated weights for policy 0, policy_version 110663 (0.0021) [2023-03-09 09:58:37,830][23090] Updated weights for policy 0, policy_version 110673 (0.0016) [2023-03-09 09:58:38,630][23090] Updated weights for policy 0, policy_version 110683 (0.0016) [2023-03-09 09:58:39,058][22664] Fps is (10 sec: 201527.4, 60 sec: 198792.5, 300 sec: 198218.8). Total num frames: 1813512192. Throughput: 0: 49625.7. Samples: 453442512. Policy #0 lag: (min: 3.0, avg: 17.3, max: 35.0) [2023-03-09 09:58:39,060][22664] Avg episode reward: [(0, '54.909')] [2023-03-09 09:58:39,582][23090] Updated weights for policy 0, policy_version 110693 (0.0017) [2023-03-09 09:58:40,605][23090] Updated weights for policy 0, policy_version 110705 (0.0028) [2023-03-09 09:58:41,340][23090] Updated weights for policy 0, policy_version 110715 (0.0013) [2023-03-09 09:58:42,333][23090] Updated weights for policy 0, policy_version 110725 (0.0014) [2023-03-09 09:58:43,099][23090] Updated weights for policy 0, policy_version 110735 (0.0032) [2023-03-09 09:58:43,310][22940] Signal inference workers to stop experience collection... (37850 times) [2023-03-09 09:58:43,311][22940] Signal inference workers to resume experience collection... (37850 times) [2023-03-09 09:58:43,390][23090] InferenceWorker_p0-w0: stopping experience collection (37850 times) [2023-03-09 09:58:43,390][23090] InferenceWorker_p0-w0: resuming experience collection (37850 times) [2023-03-09 09:58:43,840][23090] Updated weights for policy 0, policy_version 110745 (0.0013) [2023-03-09 09:58:44,059][22664] Fps is (10 sec: 196613.1, 60 sec: 198519.4, 300 sec: 198163.1). Total num frames: 1814478848. Throughput: 0: 49400.5. Samples: 453583840. Policy #0 lag: (min: 3.0, avg: 16.9, max: 34.0) [2023-03-09 09:58:44,060][22664] Avg episode reward: [(0, '54.778')] [2023-03-09 09:58:44,736][23090] Updated weights for policy 0, policy_version 110755 (0.0016) [2023-03-09 09:58:45,835][23090] Updated weights for policy 0, policy_version 110767 (0.0020) [2023-03-09 09:58:46,594][23090] Updated weights for policy 0, policy_version 110777 (0.0019) [2023-03-09 09:58:47,478][23090] Updated weights for policy 0, policy_version 110787 (0.0018) [2023-03-09 09:58:48,445][23090] Updated weights for policy 0, policy_version 110798 (0.0017) [2023-03-09 09:58:49,059][22664] Fps is (10 sec: 194967.1, 60 sec: 197973.1, 300 sec: 198218.6). Total num frames: 1815461888. Throughput: 0: 49353.5. Samples: 453878560. Policy #0 lag: (min: 3.0, avg: 16.9, max: 34.0) [2023-03-09 09:58:49,060][22664] Avg episode reward: [(0, '55.890')] [2023-03-09 09:58:49,108][23090] Updated weights for policy 0, policy_version 110808 (0.0014) [2023-03-09 09:58:50,007][23090] Updated weights for policy 0, policy_version 110818 (0.0013) [2023-03-09 09:58:50,847][23090] Updated weights for policy 0, policy_version 110828 (0.0020) [2023-03-09 09:58:51,670][23090] Updated weights for policy 0, policy_version 110838 (0.0017) [2023-03-09 09:58:52,483][23090] Updated weights for policy 0, policy_version 110848 (0.0022) [2023-03-09 09:58:53,171][22940] Signal inference workers to stop experience collection... (37900 times) [2023-03-09 09:58:53,172][22940] Signal inference workers to resume experience collection... (37900 times) [2023-03-09 09:58:53,236][23090] InferenceWorker_p0-w0: stopping experience collection (37900 times) [2023-03-09 09:58:53,236][23090] InferenceWorker_p0-w0: resuming experience collection (37900 times) [2023-03-09 09:58:53,445][23090] Updated weights for policy 0, policy_version 110858 (0.0016) [2023-03-09 09:58:54,059][22664] Fps is (10 sec: 196599.4, 60 sec: 197698.9, 300 sec: 198107.5). Total num frames: 1816444928. Throughput: 0: 49219.8. Samples: 454171376. Policy #0 lag: (min: 3.0, avg: 16.9, max: 34.0) [2023-03-09 09:58:54,061][22664] Avg episode reward: [(0, '54.746')] [2023-03-09 09:58:54,176][23090] Updated weights for policy 0, policy_version 110868 (0.0013) [2023-03-09 09:58:54,919][23090] Updated weights for policy 0, policy_version 110878 (0.0014) [2023-03-09 09:58:55,956][23090] Updated weights for policy 0, policy_version 110888 (0.0013) [2023-03-09 09:58:56,604][23090] Updated weights for policy 0, policy_version 110898 (0.0013) [2023-03-09 09:58:57,481][23090] Updated weights for policy 0, policy_version 110908 (0.0013) [2023-03-09 09:58:58,504][23090] Updated weights for policy 0, policy_version 110918 (0.0021) [2023-03-09 09:58:59,059][22664] Fps is (10 sec: 194969.3, 60 sec: 196881.7, 300 sec: 197996.7). Total num frames: 1817411584. Throughput: 0: 49221.6. Samples: 454320864. Policy #0 lag: (min: 3.0, avg: 16.9, max: 34.0) [2023-03-09 09:58:59,060][22664] Avg episode reward: [(0, '53.402')] [2023-03-09 09:58:59,163][23090] Updated weights for policy 0, policy_version 110928 (0.0021) [2023-03-09 09:58:59,963][23090] Updated weights for policy 0, policy_version 110938 (0.0016) [2023-03-09 09:59:00,805][23090] Updated weights for policy 0, policy_version 110948 (0.0021) [2023-03-09 09:59:01,123][22940] Signal inference workers to stop experience collection... (37950 times) [2023-03-09 09:59:01,136][22940] Signal inference workers to resume experience collection... (37950 times) [2023-03-09 09:59:01,187][23090] InferenceWorker_p0-w0: stopping experience collection (37950 times) [2023-03-09 09:59:01,188][23090] InferenceWorker_p0-w0: resuming experience collection (37950 times) [2023-03-09 09:59:01,684][23090] Updated weights for policy 0, policy_version 110958 (0.0013) [2023-03-09 09:59:02,384][23090] Updated weights for policy 0, policy_version 110968 (0.0016) [2023-03-09 09:59:03,260][23090] Updated weights for policy 0, policy_version 110978 (0.0018) [2023-03-09 09:59:04,058][22664] Fps is (10 sec: 196617.5, 60 sec: 197154.4, 300 sec: 197941.2). Total num frames: 1818411008. Throughput: 0: 49266.5. Samples: 454619760. Policy #0 lag: (min: 3.0, avg: 16.9, max: 34.0) [2023-03-09 09:59:04,059][22664] Avg episode reward: [(0, '55.989')] [2023-03-09 09:59:04,078][23090] Updated weights for policy 0, policy_version 110988 (0.0013) [2023-03-09 09:59:04,911][23090] Updated weights for policy 0, policy_version 110998 (0.0018) [2023-03-09 09:59:05,693][23090] Updated weights for policy 0, policy_version 111008 (0.0013) [2023-03-09 09:59:06,658][23090] Updated weights for policy 0, policy_version 111018 (0.0014) [2023-03-09 09:59:07,391][23090] Updated weights for policy 0, policy_version 111028 (0.0022) [2023-03-09 09:59:08,164][23090] Updated weights for policy 0, policy_version 111038 (0.0013) [2023-03-09 09:59:09,059][22664] Fps is (10 sec: 196604.4, 60 sec: 196608.0, 300 sec: 197885.2). Total num frames: 1819377664. Throughput: 0: 49176.0. Samples: 454914480. Policy #0 lag: (min: 3.0, avg: 16.9, max: 34.0) [2023-03-09 09:59:09,061][22664] Avg episode reward: [(0, '54.989')] [2023-03-09 09:59:09,206][22940] Signal inference workers to stop experience collection... (38000 times) [2023-03-09 09:59:09,211][23090] Updated weights for policy 0, policy_version 111048 (0.0013) [2023-03-09 09:59:09,231][22940] Signal inference workers to resume experience collection... (38000 times) [2023-03-09 09:59:09,254][23090] InferenceWorker_p0-w0: stopping experience collection (38000 times) [2023-03-09 09:59:09,254][23090] InferenceWorker_p0-w0: resuming experience collection (38000 times) [2023-03-09 09:59:09,872][23090] Updated weights for policy 0, policy_version 111058 (0.0020) [2023-03-09 09:59:10,712][23090] Updated weights for policy 0, policy_version 111068 (0.0013) [2023-03-09 09:59:11,699][23090] Updated weights for policy 0, policy_version 111078 (0.0024) [2023-03-09 09:59:12,439][23090] Updated weights for policy 0, policy_version 111088 (0.0017) [2023-03-09 09:59:13,181][23090] Updated weights for policy 0, policy_version 111098 (0.0016) [2023-03-09 09:59:14,059][22664] Fps is (10 sec: 196601.3, 60 sec: 196880.3, 300 sec: 197885.4). Total num frames: 1820377088. Throughput: 0: 49312.9. Samples: 455063952. Policy #0 lag: (min: 3.0, avg: 16.9, max: 34.0) [2023-03-09 09:59:14,061][22664] Avg episode reward: [(0, '54.108')] [2023-03-09 09:59:14,092][23090] Updated weights for policy 0, policy_version 111108 (0.0020) [2023-03-09 09:59:14,935][23090] Updated weights for policy 0, policy_version 111118 (0.0016) [2023-03-09 09:59:15,651][23090] Updated weights for policy 0, policy_version 111128 (0.0016) [2023-03-09 09:59:16,502][23090] Updated weights for policy 0, policy_version 111138 (0.0013) [2023-03-09 09:59:17,331][23090] Updated weights for policy 0, policy_version 111148 (0.0016) [2023-03-09 09:59:18,172][23090] Updated weights for policy 0, policy_version 111158 (0.0017) [2023-03-09 09:59:18,628][22940] Signal inference workers to stop experience collection... (38050 times) [2023-03-09 09:59:18,641][22940] Signal inference workers to resume experience collection... (38050 times) [2023-03-09 09:59:18,664][23090] InferenceWorker_p0-w0: stopping experience collection (38050 times) [2023-03-09 09:59:18,665][23090] InferenceWorker_p0-w0: resuming experience collection (38050 times) [2023-03-09 09:59:18,982][23090] Updated weights for policy 0, policy_version 111168 (0.0016) [2023-03-09 09:59:19,059][22664] Fps is (10 sec: 199887.3, 60 sec: 197154.6, 300 sec: 197829.8). Total num frames: 1821376512. Throughput: 0: 49222.5. Samples: 455358768. Policy #0 lag: (min: 3.0, avg: 16.9, max: 34.0) [2023-03-09 09:59:19,060][22664] Avg episode reward: [(0, '53.971')] [2023-03-09 09:59:19,070][22940] Saving /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000111169_1821392896.pth... [2023-03-09 09:59:19,129][22940] Removing /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000108269_1773879296.pth [2023-03-09 09:59:19,908][23090] Updated weights for policy 0, policy_version 111178 (0.0022) [2023-03-09 09:59:20,725][23090] Updated weights for policy 0, policy_version 111189 (0.0019) [2023-03-09 09:59:21,488][23090] Updated weights for policy 0, policy_version 111199 (0.0019) [2023-03-09 09:59:22,501][23090] Updated weights for policy 0, policy_version 111209 (0.0016) [2023-03-09 09:59:23,327][23090] Updated weights for policy 0, policy_version 111220 (0.0013) [2023-03-09 09:59:24,059][22664] Fps is (10 sec: 199890.4, 60 sec: 197427.5, 300 sec: 197941.1). Total num frames: 1822375936. Throughput: 0: 49225.5. Samples: 455657664. Policy #0 lag: (min: 3.0, avg: 16.9, max: 34.0) [2023-03-09 09:59:24,060][22664] Avg episode reward: [(0, '55.911')] [2023-03-09 09:59:24,076][23090] Updated weights for policy 0, policy_version 111230 (0.0014) [2023-03-09 09:59:25,080][23090] Updated weights for policy 0, policy_version 111240 (0.0013) [2023-03-09 09:59:25,765][23090] Updated weights for policy 0, policy_version 111250 (0.0016) [2023-03-09 09:59:26,590][23090] Updated weights for policy 0, policy_version 111260 (0.0022) [2023-03-09 09:59:27,523][23090] Updated weights for policy 0, policy_version 111270 (0.0015) [2023-03-09 09:59:28,269][23090] Updated weights for policy 0, policy_version 111280 (0.0013) [2023-03-09 09:59:28,642][22940] Signal inference workers to stop experience collection... (38100 times) [2023-03-09 09:59:28,644][22940] Signal inference workers to resume experience collection... (38100 times) [2023-03-09 09:59:28,713][23090] InferenceWorker_p0-w0: stopping experience collection (38100 times) [2023-03-09 09:59:28,713][23090] InferenceWorker_p0-w0: resuming experience collection (38100 times) [2023-03-09 09:59:29,023][23090] Updated weights for policy 0, policy_version 111290 (0.0015) [2023-03-09 09:59:29,059][22664] Fps is (10 sec: 199886.0, 60 sec: 197973.5, 300 sec: 197996.6). Total num frames: 1823375360. Throughput: 0: 49406.1. Samples: 455807120. Policy #0 lag: (min: 3.0, avg: 16.9, max: 34.0) [2023-03-09 09:59:29,061][22664] Avg episode reward: [(0, '54.433')] [2023-03-09 09:59:29,920][23090] Updated weights for policy 0, policy_version 111300 (0.0019) [2023-03-09 09:59:30,797][23090] Updated weights for policy 0, policy_version 111310 (0.0013) [2023-03-09 09:59:31,446][23090] Updated weights for policy 0, policy_version 111320 (0.0013) [2023-03-09 09:59:32,357][23090] Updated weights for policy 0, policy_version 111330 (0.0018) [2023-03-09 09:59:33,221][23090] Updated weights for policy 0, policy_version 111340 (0.0018) [2023-03-09 09:59:33,992][23090] Updated weights for policy 0, policy_version 111350 (0.0016) [2023-03-09 09:59:34,058][22664] Fps is (10 sec: 199885.2, 60 sec: 197701.1, 300 sec: 198052.0). Total num frames: 1824374784. Throughput: 0: 49452.9. Samples: 456103936. Policy #0 lag: (min: 3.0, avg: 16.9, max: 34.0) [2023-03-09 09:59:34,059][22664] Avg episode reward: [(0, '52.810')] [2023-03-09 09:59:34,805][23090] Updated weights for policy 0, policy_version 111360 (0.0016) [2023-03-09 09:59:35,773][23090] Updated weights for policy 0, policy_version 111370 (0.0017) [2023-03-09 09:59:36,490][23090] Updated weights for policy 0, policy_version 111380 (0.0020) [2023-03-09 09:59:37,276][23090] Updated weights for policy 0, policy_version 111390 (0.0017) [2023-03-09 09:59:38,287][23090] Updated weights for policy 0, policy_version 111400 (0.0013) [2023-03-09 09:59:38,936][22940] Signal inference workers to stop experience collection... (38150 times) [2023-03-09 09:59:38,953][22940] Signal inference workers to resume experience collection... (38150 times) [2023-03-09 09:59:38,976][23090] InferenceWorker_p0-w0: stopping experience collection (38150 times) [2023-03-09 09:59:39,019][23090] InferenceWorker_p0-w0: resuming experience collection (38150 times) [2023-03-09 09:59:39,021][23090] Updated weights for policy 0, policy_version 111410 (0.0013) [2023-03-09 09:59:39,059][22664] Fps is (10 sec: 198242.3, 60 sec: 197426.0, 300 sec: 198051.8). Total num frames: 1825357824. Throughput: 0: 49543.2. Samples: 456400816. Policy #0 lag: (min: 3.0, avg: 16.9, max: 34.0) [2023-03-09 09:59:39,061][22664] Avg episode reward: [(0, '54.442')] [2023-03-09 09:59:39,807][23090] Updated weights for policy 0, policy_version 111420 (0.0019) [2023-03-09 09:59:40,858][23090] Updated weights for policy 0, policy_version 111431 (0.0012) [2023-03-09 09:59:41,599][23090] Updated weights for policy 0, policy_version 111441 (0.0021) [2023-03-09 09:59:42,414][23090] Updated weights for policy 0, policy_version 111451 (0.0013) [2023-03-09 09:59:43,343][23090] Updated weights for policy 0, policy_version 111461 (0.0017) [2023-03-09 09:59:44,058][22664] Fps is (10 sec: 194970.1, 60 sec: 197427.3, 300 sec: 197885.6). Total num frames: 1826324480. Throughput: 0: 49541.5. Samples: 456550224. Policy #0 lag: (min: 1.0, avg: 15.1, max: 33.0) [2023-03-09 09:59:44,060][22664] Avg episode reward: [(0, '54.681')] [2023-03-09 09:59:44,195][23090] Updated weights for policy 0, policy_version 111472 (0.0017) [2023-03-09 09:59:44,958][23090] Updated weights for policy 0, policy_version 111482 (0.0025) [2023-03-09 09:59:45,803][23090] Updated weights for policy 0, policy_version 111492 (0.0013) [2023-03-09 09:59:46,663][23090] Updated weights for policy 0, policy_version 111502 (0.0023) [2023-03-09 09:59:47,379][23090] Updated weights for policy 0, policy_version 111512 (0.0016) [2023-03-09 09:59:48,282][23090] Updated weights for policy 0, policy_version 111522 (0.0013) [2023-03-09 09:59:49,058][22664] Fps is (10 sec: 196614.6, 60 sec: 197700.6, 300 sec: 197885.5). Total num frames: 1827323904. Throughput: 0: 49450.3. Samples: 456845024. Policy #0 lag: (min: 1.0, avg: 15.1, max: 33.0) [2023-03-09 09:59:49,059][22664] Avg episode reward: [(0, '53.216')] [2023-03-09 09:59:49,118][23090] Updated weights for policy 0, policy_version 111532 (0.0013) [2023-03-09 09:59:49,895][23090] Updated weights for policy 0, policy_version 111542 (0.0013) [2023-03-09 09:59:50,772][23090] Updated weights for policy 0, policy_version 111552 (0.0017) [2023-03-09 09:59:51,453][22940] Signal inference workers to stop experience collection... (38200 times) [2023-03-09 09:59:51,467][22940] Signal inference workers to resume experience collection... (38200 times) [2023-03-09 09:59:51,538][23090] InferenceWorker_p0-w0: stopping experience collection (38200 times) [2023-03-09 09:59:51,538][23090] InferenceWorker_p0-w0: resuming experience collection (38200 times) [2023-03-09 09:59:51,670][23090] Updated weights for policy 0, policy_version 111562 (0.0018) [2023-03-09 09:59:52,458][23090] Updated weights for policy 0, policy_version 111573 (0.0016) [2023-03-09 09:59:53,238][23090] Updated weights for policy 0, policy_version 111583 (0.0016) [2023-03-09 09:59:54,058][22664] Fps is (10 sec: 196608.2, 60 sec: 197428.8, 300 sec: 197774.3). Total num frames: 1828290560. Throughput: 0: 49542.1. Samples: 457143856. Policy #0 lag: (min: 1.0, avg: 15.1, max: 33.0) [2023-03-09 09:59:54,059][22664] Avg episode reward: [(0, '54.513')] [2023-03-09 09:59:54,242][23090] Updated weights for policy 0, policy_version 111593 (0.0013) [2023-03-09 09:59:54,938][23090] Updated weights for policy 0, policy_version 111603 (0.0018) [2023-03-09 09:59:55,860][23090] Updated weights for policy 0, policy_version 111614 (0.0020) [2023-03-09 09:59:56,832][23090] Updated weights for policy 0, policy_version 111624 (0.0016) [2023-03-09 09:59:57,540][23090] Updated weights for policy 0, policy_version 111634 (0.0020) [2023-03-09 09:59:58,349][23090] Updated weights for policy 0, policy_version 111644 (0.0016) [2023-03-09 09:59:59,059][22664] Fps is (10 sec: 198243.1, 60 sec: 198246.3, 300 sec: 197941.0). Total num frames: 1829306368. Throughput: 0: 49541.1. Samples: 457293296. Policy #0 lag: (min: 1.0, avg: 15.1, max: 33.0) [2023-03-09 09:59:59,060][22664] Avg episode reward: [(0, '53.499')] [2023-03-09 09:59:59,319][23090] Updated weights for policy 0, policy_version 111654 (0.0017) [2023-03-09 10:00:00,040][23090] Updated weights for policy 0, policy_version 111664 (0.0013) [2023-03-09 10:00:00,808][23090] Updated weights for policy 0, policy_version 111674 (0.0019) [2023-03-09 10:00:01,653][23090] Updated weights for policy 0, policy_version 111684 (0.0020) [2023-03-09 10:00:02,524][23090] Updated weights for policy 0, policy_version 111694 (0.0023) [2023-03-09 10:00:03,250][23090] Updated weights for policy 0, policy_version 111704 (0.0016) [2023-03-09 10:00:04,059][22664] Fps is (10 sec: 201518.6, 60 sec: 198245.6, 300 sec: 197941.0). Total num frames: 1830305792. Throughput: 0: 49585.0. Samples: 457590096. Policy #0 lag: (min: 1.0, avg: 15.1, max: 33.0) [2023-03-09 10:00:04,060][22664] Avg episode reward: [(0, '53.136')] [2023-03-09 10:00:04,138][23090] Updated weights for policy 0, policy_version 111714 (0.0016) [2023-03-09 10:00:04,861][22940] Signal inference workers to stop experience collection... (38250 times) [2023-03-09 10:00:04,887][22940] Signal inference workers to resume experience collection... (38250 times) [2023-03-09 10:00:04,906][23090] InferenceWorker_p0-w0: stopping experience collection (38250 times) [2023-03-09 10:00:04,907][23090] InferenceWorker_p0-w0: resuming experience collection (38250 times) [2023-03-09 10:00:05,067][23090] Updated weights for policy 0, policy_version 111724 (0.0017) [2023-03-09 10:00:05,757][23090] Updated weights for policy 0, policy_version 111734 (0.0020) [2023-03-09 10:00:06,655][23090] Updated weights for policy 0, policy_version 111744 (0.0013) [2023-03-09 10:00:07,547][23090] Updated weights for policy 0, policy_version 111754 (0.0022) [2023-03-09 10:00:08,299][23090] Updated weights for policy 0, policy_version 111764 (0.0013) [2023-03-09 10:00:09,038][23090] Updated weights for policy 0, policy_version 111774 (0.0013) [2023-03-09 10:00:09,059][22664] Fps is (10 sec: 199886.6, 60 sec: 198793.3, 300 sec: 198052.1). Total num frames: 1831305216. Throughput: 0: 49539.5. Samples: 457886944. Policy #0 lag: (min: 1.0, avg: 15.1, max: 33.0) [2023-03-09 10:00:09,060][22664] Avg episode reward: [(0, '53.689')] [2023-03-09 10:00:10,112][23090] Updated weights for policy 0, policy_version 111784 (0.0022) [2023-03-09 10:00:10,778][23090] Updated weights for policy 0, policy_version 111794 (0.0013) [2023-03-09 10:00:11,550][23090] Updated weights for policy 0, policy_version 111804 (0.0013) [2023-03-09 10:00:12,554][23090] Updated weights for policy 0, policy_version 111814 (0.0013) [2023-03-09 10:00:13,295][23090] Updated weights for policy 0, policy_version 111824 (0.0020) [2023-03-09 10:00:14,059][22664] Fps is (10 sec: 196599.2, 60 sec: 198245.3, 300 sec: 197996.1). Total num frames: 1832271872. Throughput: 0: 49493.1. Samples: 458034336. Policy #0 lag: (min: 1.0, avg: 15.1, max: 33.0) [2023-03-09 10:00:14,061][22664] Avg episode reward: [(0, '55.055')] [2023-03-09 10:00:14,098][23090] Updated weights for policy 0, policy_version 111834 (0.0025) [2023-03-09 10:00:14,956][23090] Updated weights for policy 0, policy_version 111844 (0.0014) [2023-03-09 10:00:15,687][22940] Signal inference workers to stop experience collection... (38300 times) [2023-03-09 10:00:15,688][22940] Signal inference workers to resume experience collection... (38300 times) [2023-03-09 10:00:15,747][23090] InferenceWorker_p0-w0: stopping experience collection (38300 times) [2023-03-09 10:00:15,747][23090] InferenceWorker_p0-w0: resuming experience collection (38300 times) [2023-03-09 10:00:15,797][23090] Updated weights for policy 0, policy_version 111854 (0.0018) [2023-03-09 10:00:16,501][23090] Updated weights for policy 0, policy_version 111864 (0.0013) [2023-03-09 10:00:17,400][23090] Updated weights for policy 0, policy_version 111874 (0.0017) [2023-03-09 10:00:18,350][23090] Updated weights for policy 0, policy_version 111885 (0.0013) [2023-03-09 10:00:19,059][22664] Fps is (10 sec: 196599.6, 60 sec: 198245.4, 300 sec: 198107.4). Total num frames: 1833271296. Throughput: 0: 49493.9. Samples: 458331184. Policy #0 lag: (min: 1.0, avg: 15.1, max: 33.0) [2023-03-09 10:00:19,061][22664] Avg episode reward: [(0, '54.755')] [2023-03-09 10:00:19,099][23090] Updated weights for policy 0, policy_version 111895 (0.0013) [2023-03-09 10:00:19,988][23090] Updated weights for policy 0, policy_version 111905 (0.0016) [2023-03-09 10:00:20,843][23090] Updated weights for policy 0, policy_version 111915 (0.0013) [2023-03-09 10:00:21,650][23090] Updated weights for policy 0, policy_version 111925 (0.0016) [2023-03-09 10:00:22,384][23090] Updated weights for policy 0, policy_version 111935 (0.0018) [2023-03-09 10:00:23,394][23090] Updated weights for policy 0, policy_version 111945 (0.0013) [2023-03-09 10:00:24,059][22664] Fps is (10 sec: 198251.1, 60 sec: 197972.1, 300 sec: 198051.9). Total num frames: 1834254336. Throughput: 0: 49448.4. Samples: 458626000. Policy #0 lag: (min: 1.0, avg: 15.1, max: 33.0) [2023-03-09 10:00:24,061][22664] Avg episode reward: [(0, '55.159')] [2023-03-09 10:00:24,212][23090] Updated weights for policy 0, policy_version 111956 (0.0018) [2023-03-09 10:00:24,947][23090] Updated weights for policy 0, policy_version 111966 (0.0016) [2023-03-09 10:00:26,033][23090] Updated weights for policy 0, policy_version 111977 (0.0015) [2023-03-09 10:00:26,360][22940] Signal inference workers to stop experience collection... (38350 times) [2023-03-09 10:00:26,363][22940] Signal inference workers to resume experience collection... (38350 times) [2023-03-09 10:00:26,425][23090] InferenceWorker_p0-w0: stopping experience collection (38350 times) [2023-03-09 10:00:26,429][23090] InferenceWorker_p0-w0: resuming experience collection (38350 times) [2023-03-09 10:00:26,760][23090] Updated weights for policy 0, policy_version 111987 (0.0016) [2023-03-09 10:00:27,531][23090] Updated weights for policy 0, policy_version 111997 (0.0019) [2023-03-09 10:00:28,532][23090] Updated weights for policy 0, policy_version 112007 (0.0021) [2023-03-09 10:00:29,059][22664] Fps is (10 sec: 196617.3, 60 sec: 197700.6, 300 sec: 197996.5). Total num frames: 1835237376. Throughput: 0: 49449.9. Samples: 458775472. Policy #0 lag: (min: 1.0, avg: 15.1, max: 33.0) [2023-03-09 10:00:29,060][22664] Avg episode reward: [(0, '53.838')] [2023-03-09 10:00:29,287][23090] Updated weights for policy 0, policy_version 112017 (0.0016) [2023-03-09 10:00:30,129][23090] Updated weights for policy 0, policy_version 112028 (0.0016) [2023-03-09 10:00:31,103][23090] Updated weights for policy 0, policy_version 112038 (0.0018) [2023-03-09 10:00:31,954][23090] Updated weights for policy 0, policy_version 112049 (0.0020) [2023-03-09 10:00:32,732][23090] Updated weights for policy 0, policy_version 112059 (0.0016) [2023-03-09 10:00:33,760][23090] Updated weights for policy 0, policy_version 112069 (0.0020) [2023-03-09 10:00:34,059][22664] Fps is (10 sec: 196609.5, 60 sec: 197426.1, 300 sec: 197885.3). Total num frames: 1836220416. Throughput: 0: 49495.1. Samples: 459072320. Policy #0 lag: (min: 1.0, avg: 15.1, max: 33.0) [2023-03-09 10:00:34,062][22664] Avg episode reward: [(0, '54.383')] [2023-03-09 10:00:34,417][23090] Updated weights for policy 0, policy_version 112079 (0.0023) [2023-03-09 10:00:35,147][23090] Updated weights for policy 0, policy_version 112089 (0.0014) [2023-03-09 10:00:36,109][23090] Updated weights for policy 0, policy_version 112099 (0.0016) [2023-03-09 10:00:36,917][23090] Updated weights for policy 0, policy_version 112109 (0.0016) [2023-03-09 10:00:37,222][22940] Signal inference workers to stop experience collection... (38400 times) [2023-03-09 10:00:37,223][22940] Signal inference workers to resume experience collection... (38400 times) [2023-03-09 10:00:37,275][23090] InferenceWorker_p0-w0: stopping experience collection (38400 times) [2023-03-09 10:00:37,275][23090] InferenceWorker_p0-w0: resuming experience collection (38400 times) [2023-03-09 10:00:37,624][23090] Updated weights for policy 0, policy_version 112119 (0.0013) [2023-03-09 10:00:38,514][23090] Updated weights for policy 0, policy_version 112129 (0.0016) [2023-03-09 10:00:39,059][22664] Fps is (10 sec: 196604.3, 60 sec: 197427.6, 300 sec: 197885.4). Total num frames: 1837203456. Throughput: 0: 49538.9. Samples: 459373120. Policy #0 lag: (min: 1.0, avg: 15.1, max: 33.0) [2023-03-09 10:00:39,061][22664] Avg episode reward: [(0, '52.857')] [2023-03-09 10:00:39,340][23090] Updated weights for policy 0, policy_version 112139 (0.0016) [2023-03-09 10:00:40,233][23090] Updated weights for policy 0, policy_version 112150 (0.0018) [2023-03-09 10:00:41,051][23090] Updated weights for policy 0, policy_version 112160 (0.0016) [2023-03-09 10:00:41,938][23090] Updated weights for policy 0, policy_version 112170 (0.0018) [2023-03-09 10:00:42,731][23090] Updated weights for policy 0, policy_version 112180 (0.0013) [2023-03-09 10:00:43,453][23090] Updated weights for policy 0, policy_version 112190 (0.0017) [2023-03-09 10:00:44,059][22664] Fps is (10 sec: 199885.3, 60 sec: 198245.3, 300 sec: 197940.7). Total num frames: 1838219264. Throughput: 0: 49494.6. Samples: 459520560. Policy #0 lag: (min: 0.0, avg: 15.9, max: 33.0) [2023-03-09 10:00:44,060][22664] Avg episode reward: [(0, '51.338')] [2023-03-09 10:00:44,439][23090] Updated weights for policy 0, policy_version 112200 (0.0013) [2023-03-09 10:00:45,167][23090] Updated weights for policy 0, policy_version 112210 (0.0016) [2023-03-09 10:00:45,943][23090] Updated weights for policy 0, policy_version 112220 (0.0016) [2023-03-09 10:00:46,976][23090] Updated weights for policy 0, policy_version 112230 (0.0013) [2023-03-09 10:00:47,557][22940] Signal inference workers to stop experience collection... (38450 times) [2023-03-09 10:00:47,559][22940] Signal inference workers to resume experience collection... (38450 times) [2023-03-09 10:00:47,627][23090] InferenceWorker_p0-w0: stopping experience collection (38450 times) [2023-03-09 10:00:47,628][23090] InferenceWorker_p0-w0: resuming experience collection (38450 times) [2023-03-09 10:00:47,673][23090] Updated weights for policy 0, policy_version 112240 (0.0014) [2023-03-09 10:00:48,430][23090] Updated weights for policy 0, policy_version 112250 (0.0022) [2023-03-09 10:00:49,059][22664] Fps is (10 sec: 199882.6, 60 sec: 197972.2, 300 sec: 197830.0). Total num frames: 1839202304. Throughput: 0: 49542.6. Samples: 459819520. Policy #0 lag: (min: 0.0, avg: 15.9, max: 33.0) [2023-03-09 10:00:49,060][22664] Avg episode reward: [(0, '53.407')] [2023-03-09 10:00:49,321][23090] Updated weights for policy 0, policy_version 112260 (0.0021) [2023-03-09 10:00:50,188][23090] Updated weights for policy 0, policy_version 112270 (0.0015) [2023-03-09 10:00:50,840][23090] Updated weights for policy 0, policy_version 112280 (0.0016) [2023-03-09 10:00:51,739][23090] Updated weights for policy 0, policy_version 112290 (0.0016) [2023-03-09 10:00:52,754][23090] Updated weights for policy 0, policy_version 112301 (0.0014) [2023-03-09 10:00:53,473][23090] Updated weights for policy 0, policy_version 112311 (0.0016) [2023-03-09 10:00:54,058][22664] Fps is (10 sec: 199891.4, 60 sec: 198792.5, 300 sec: 197996.7). Total num frames: 1840218112. Throughput: 0: 49495.2. Samples: 460114224. Policy #0 lag: (min: 0.0, avg: 15.9, max: 33.0) [2023-03-09 10:00:54,060][22664] Avg episode reward: [(0, '53.288')] [2023-03-09 10:00:54,400][23090] Updated weights for policy 0, policy_version 112321 (0.0017) [2023-03-09 10:00:55,216][23090] Updated weights for policy 0, policy_version 112331 (0.0016) [2023-03-09 10:00:56,017][23090] Updated weights for policy 0, policy_version 112341 (0.0025) [2023-03-09 10:00:56,790][23090] Updated weights for policy 0, policy_version 112351 (0.0016) [2023-03-09 10:00:57,498][22940] Signal inference workers to stop experience collection... (38500 times) [2023-03-09 10:00:57,509][22940] Signal inference workers to resume experience collection... (38500 times) [2023-03-09 10:00:57,568][23090] InferenceWorker_p0-w0: stopping experience collection (38500 times) [2023-03-09 10:00:57,568][23090] InferenceWorker_p0-w0: resuming experience collection (38500 times) [2023-03-09 10:00:57,732][23090] Updated weights for policy 0, policy_version 112361 (0.0019) [2023-03-09 10:00:58,507][23090] Updated weights for policy 0, policy_version 112371 (0.0013) [2023-03-09 10:00:59,059][22664] Fps is (10 sec: 199876.4, 60 sec: 198244.5, 300 sec: 197996.2). Total num frames: 1841201152. Throughput: 0: 49495.7. Samples: 460261648. Policy #0 lag: (min: 0.0, avg: 15.9, max: 33.0) [2023-03-09 10:00:59,062][22664] Avg episode reward: [(0, '55.112')] [2023-03-09 10:00:59,301][23090] Updated weights for policy 0, policy_version 112381 (0.0019) [2023-03-09 10:01:00,263][23090] Updated weights for policy 0, policy_version 112391 (0.0017) [2023-03-09 10:01:00,963][23090] Updated weights for policy 0, policy_version 112401 (0.0018) [2023-03-09 10:01:01,696][23090] Updated weights for policy 0, policy_version 112411 (0.0013) [2023-03-09 10:01:02,727][23090] Updated weights for policy 0, policy_version 112421 (0.0013) [2023-03-09 10:01:03,485][23090] Updated weights for policy 0, policy_version 112431 (0.0013) [2023-03-09 10:01:04,059][22664] Fps is (10 sec: 198245.4, 60 sec: 198247.0, 300 sec: 197996.5). Total num frames: 1842200576. Throughput: 0: 49587.4. Samples: 460562592. Policy #0 lag: (min: 0.0, avg: 15.9, max: 33.0) [2023-03-09 10:01:04,060][22664] Avg episode reward: [(0, '51.808')] [2023-03-09 10:01:04,200][23090] Updated weights for policy 0, policy_version 112441 (0.0013) [2023-03-09 10:01:05,090][23090] Updated weights for policy 0, policy_version 112451 (0.0014) [2023-03-09 10:01:05,975][23090] Updated weights for policy 0, policy_version 112461 (0.0018) [2023-03-09 10:01:06,416][22940] Signal inference workers to stop experience collection... (38550 times) [2023-03-09 10:01:06,417][22940] Signal inference workers to resume experience collection... (38550 times) [2023-03-09 10:01:06,494][23090] InferenceWorker_p0-w0: stopping experience collection (38550 times) [2023-03-09 10:01:06,494][23090] InferenceWorker_p0-w0: resuming experience collection (38550 times) [2023-03-09 10:01:06,661][23090] Updated weights for policy 0, policy_version 112471 (0.0019) [2023-03-09 10:01:07,531][23090] Updated weights for policy 0, policy_version 112481 (0.0013) [2023-03-09 10:01:08,378][23090] Updated weights for policy 0, policy_version 112491 (0.0013) [2023-03-09 10:01:09,059][22664] Fps is (10 sec: 198260.8, 60 sec: 197973.5, 300 sec: 198052.3). Total num frames: 1843183616. Throughput: 0: 49676.5. Samples: 460861424. Policy #0 lag: (min: 0.0, avg: 15.9, max: 33.0) [2023-03-09 10:01:09,059][22664] Avg episode reward: [(0, '54.668')] [2023-03-09 10:01:09,163][23090] Updated weights for policy 0, policy_version 112501 (0.0020) [2023-03-09 10:01:10,082][23090] Updated weights for policy 0, policy_version 112512 (0.0017) [2023-03-09 10:01:10,977][23090] Updated weights for policy 0, policy_version 112522 (0.0016) [2023-03-09 10:01:11,755][23090] Updated weights for policy 0, policy_version 112532 (0.0016) [2023-03-09 10:01:12,518][23090] Updated weights for policy 0, policy_version 112542 (0.0018) [2023-03-09 10:01:13,526][23090] Updated weights for policy 0, policy_version 112552 (0.0013) [2023-03-09 10:01:14,059][22664] Fps is (10 sec: 196602.3, 60 sec: 198247.5, 300 sec: 197996.3). Total num frames: 1844166656. Throughput: 0: 49629.2. Samples: 461008800. Policy #0 lag: (min: 0.0, avg: 15.9, max: 33.0) [2023-03-09 10:01:14,061][22664] Avg episode reward: [(0, '54.956')] [2023-03-09 10:01:14,221][23090] Updated weights for policy 0, policy_version 112562 (0.0013) [2023-03-09 10:01:14,966][22940] Signal inference workers to stop experience collection... (38600 times) [2023-03-09 10:01:14,967][22940] Signal inference workers to resume experience collection... (38600 times) [2023-03-09 10:01:15,030][23090] InferenceWorker_p0-w0: stopping experience collection (38600 times) [2023-03-09 10:01:15,030][23090] InferenceWorker_p0-w0: resuming experience collection (38600 times) [2023-03-09 10:01:15,037][23090] Updated weights for policy 0, policy_version 112572 (0.0017) [2023-03-09 10:01:16,061][23090] Updated weights for policy 0, policy_version 112582 (0.0013) [2023-03-09 10:01:16,862][23090] Updated weights for policy 0, policy_version 112593 (0.0012) [2023-03-09 10:01:17,639][23090] Updated weights for policy 0, policy_version 112603 (0.0013) [2023-03-09 10:01:18,599][23090] Updated weights for policy 0, policy_version 112613 (0.0016) [2023-03-09 10:01:19,059][22664] Fps is (10 sec: 196601.2, 60 sec: 197973.8, 300 sec: 197885.3). Total num frames: 1845149696. Throughput: 0: 49630.2. Samples: 461305680. Policy #0 lag: (min: 0.0, avg: 15.9, max: 33.0) [2023-03-09 10:01:19,060][22664] Avg episode reward: [(0, '55.316')] [2023-03-09 10:01:19,106][22940] Saving /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000112620_1845166080.pth... [2023-03-09 10:01:19,172][22940] Removing /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000109720_1797652480.pth [2023-03-09 10:01:19,359][23090] Updated weights for policy 0, policy_version 112623 (0.0017) [2023-03-09 10:01:20,184][23090] Updated weights for policy 0, policy_version 112634 (0.0016) [2023-03-09 10:01:21,042][23090] Updated weights for policy 0, policy_version 112644 (0.0012) [2023-03-09 10:01:21,978][23090] Updated weights for policy 0, policy_version 112655 (0.0019) [2023-03-09 10:01:22,684][23090] Updated weights for policy 0, policy_version 112665 (0.0019) [2023-03-09 10:01:23,599][23090] Updated weights for policy 0, policy_version 112675 (0.0025) [2023-03-09 10:01:24,059][22664] Fps is (10 sec: 196613.1, 60 sec: 197974.5, 300 sec: 197830.1). Total num frames: 1846132736. Throughput: 0: 49585.6. Samples: 461604464. Policy #0 lag: (min: 0.0, avg: 15.9, max: 33.0) [2023-03-09 10:01:24,060][22664] Avg episode reward: [(0, '56.469')] [2023-03-09 10:01:24,493][23090] Updated weights for policy 0, policy_version 112685 (0.0013) [2023-03-09 10:01:24,514][22940] Signal inference workers to stop experience collection... (38650 times) [2023-03-09 10:01:24,515][22940] Signal inference workers to resume experience collection... (38650 times) [2023-03-09 10:01:24,577][23090] InferenceWorker_p0-w0: stopping experience collection (38650 times) [2023-03-09 10:01:24,577][23090] InferenceWorker_p0-w0: resuming experience collection (38650 times) [2023-03-09 10:01:25,262][23090] Updated weights for policy 0, policy_version 112696 (0.0013) [2023-03-09 10:01:26,155][23090] Updated weights for policy 0, policy_version 112706 (0.0018) [2023-03-09 10:01:27,031][23090] Updated weights for policy 0, policy_version 112716 (0.0021) [2023-03-09 10:01:27,775][23090] Updated weights for policy 0, policy_version 112726 (0.0016) [2023-03-09 10:01:28,592][23090] Updated weights for policy 0, policy_version 112736 (0.0021) [2023-03-09 10:01:29,059][22664] Fps is (10 sec: 198253.3, 60 sec: 198246.4, 300 sec: 197941.0). Total num frames: 1847132160. Throughput: 0: 49584.7. Samples: 461751856. Policy #0 lag: (min: 0.0, avg: 15.9, max: 33.0) [2023-03-09 10:01:29,060][22664] Avg episode reward: [(0, '55.504')] [2023-03-09 10:01:29,525][23090] Updated weights for policy 0, policy_version 112746 (0.0019) [2023-03-09 10:01:30,289][23090] Updated weights for policy 0, policy_version 112756 (0.0013) [2023-03-09 10:01:31,021][23090] Updated weights for policy 0, policy_version 112766 (0.0013) [2023-03-09 10:01:32,023][23090] Updated weights for policy 0, policy_version 112776 (0.0022) [2023-03-09 10:01:32,702][23090] Updated weights for policy 0, policy_version 112786 (0.0017) [2023-03-09 10:01:32,911][22940] Signal inference workers to stop experience collection... (38700 times) [2023-03-09 10:01:32,913][22940] Signal inference workers to resume experience collection... (38700 times) [2023-03-09 10:01:32,990][23090] InferenceWorker_p0-w0: stopping experience collection (38700 times) [2023-03-09 10:01:32,990][23090] InferenceWorker_p0-w0: resuming experience collection (38700 times) [2023-03-09 10:01:33,523][23090] Updated weights for policy 0, policy_version 112796 (0.0013) [2023-03-09 10:01:34,058][22664] Fps is (10 sec: 199885.8, 60 sec: 198520.5, 300 sec: 197940.9). Total num frames: 1848131584. Throughput: 0: 49583.6. Samples: 462050768. Policy #0 lag: (min: 0.0, avg: 15.9, max: 33.0) [2023-03-09 10:01:34,060][22664] Avg episode reward: [(0, '55.926')] [2023-03-09 10:01:34,549][23090] Updated weights for policy 0, policy_version 112806 (0.0014) [2023-03-09 10:01:35,259][23090] Updated weights for policy 0, policy_version 112816 (0.0016) [2023-03-09 10:01:35,996][23090] Updated weights for policy 0, policy_version 112826 (0.0016) [2023-03-09 10:01:36,879][23090] Updated weights for policy 0, policy_version 112836 (0.0017) [2023-03-09 10:01:37,763][23090] Updated weights for policy 0, policy_version 112846 (0.0016) [2023-03-09 10:01:38,476][23090] Updated weights for policy 0, policy_version 112856 (0.0019) [2023-03-09 10:01:39,059][22664] Fps is (10 sec: 201513.7, 60 sec: 199064.7, 300 sec: 198107.6). Total num frames: 1849147392. Throughput: 0: 49630.0. Samples: 462347600. Policy #0 lag: (min: 0.0, avg: 15.9, max: 33.0) [2023-03-09 10:01:39,061][22664] Avg episode reward: [(0, '53.386')] [2023-03-09 10:01:39,335][23090] Updated weights for policy 0, policy_version 112866 (0.0016) [2023-03-09 10:01:40,212][23090] Updated weights for policy 0, policy_version 112876 (0.0017) [2023-03-09 10:01:40,936][23090] Updated weights for policy 0, policy_version 112886 (0.0013) [2023-03-09 10:01:41,897][23090] Updated weights for policy 0, policy_version 112897 (0.0019) [2023-03-09 10:01:42,754][23090] Updated weights for policy 0, policy_version 112907 (0.0027) [2023-03-09 10:01:42,945][22940] Signal inference workers to stop experience collection... (38750 times) [2023-03-09 10:01:42,957][22940] Signal inference workers to resume experience collection... (38750 times) [2023-03-09 10:01:42,986][23090] InferenceWorker_p0-w0: stopping experience collection (38750 times) [2023-03-09 10:01:43,028][23090] InferenceWorker_p0-w0: resuming experience collection (38750 times) [2023-03-09 10:01:43,515][23090] Updated weights for policy 0, policy_version 112917 (0.0013) [2023-03-09 10:01:44,059][22664] Fps is (10 sec: 201519.0, 60 sec: 198792.8, 300 sec: 198163.0). Total num frames: 1850146816. Throughput: 0: 49676.0. Samples: 462497040. Policy #0 lag: (min: 2.0, avg: 15.9, max: 33.0) [2023-03-09 10:01:44,061][22664] Avg episode reward: [(0, '49.681')] [2023-03-09 10:01:44,276][23090] Updated weights for policy 0, policy_version 112927 (0.0013) [2023-03-09 10:01:45,319][23090] Updated weights for policy 0, policy_version 112938 (0.0020) [2023-03-09 10:01:46,142][23090] Updated weights for policy 0, policy_version 112948 (0.0017) [2023-03-09 10:01:46,841][23090] Updated weights for policy 0, policy_version 112958 (0.0021) [2023-03-09 10:01:47,881][23090] Updated weights for policy 0, policy_version 112968 (0.0016) [2023-03-09 10:01:48,539][23090] Updated weights for policy 0, policy_version 112978 (0.0014) [2023-03-09 10:01:49,058][22664] Fps is (10 sec: 198256.9, 60 sec: 198793.7, 300 sec: 198218.8). Total num frames: 1851129856. Throughput: 0: 49538.6. Samples: 462791824. Policy #0 lag: (min: 2.0, avg: 15.9, max: 33.0) [2023-03-09 10:01:49,059][22664] Avg episode reward: [(0, '55.196')] [2023-03-09 10:01:49,381][23090] Updated weights for policy 0, policy_version 112988 (0.0013) [2023-03-09 10:01:50,405][23090] Updated weights for policy 0, policy_version 112998 (0.0020) [2023-03-09 10:01:51,114][23090] Updated weights for policy 0, policy_version 113008 (0.0017) [2023-03-09 10:01:51,841][23090] Updated weights for policy 0, policy_version 113018 (0.0016) [2023-03-09 10:01:52,716][23090] Updated weights for policy 0, policy_version 113028 (0.0013) [2023-03-09 10:01:52,964][22940] Signal inference workers to stop experience collection... (38800 times) [2023-03-09 10:01:52,965][22940] Signal inference workers to resume experience collection... (38800 times) [2023-03-09 10:01:53,028][23090] InferenceWorker_p0-w0: stopping experience collection (38800 times) [2023-03-09 10:01:53,028][23090] InferenceWorker_p0-w0: resuming experience collection (38800 times) [2023-03-09 10:01:53,617][23090] Updated weights for policy 0, policy_version 113038 (0.0020) [2023-03-09 10:01:54,058][22664] Fps is (10 sec: 196612.6, 60 sec: 198246.4, 300 sec: 198163.1). Total num frames: 1852112896. Throughput: 0: 49584.0. Samples: 463092704. Policy #0 lag: (min: 2.0, avg: 15.9, max: 33.0) [2023-03-09 10:01:54,060][22664] Avg episode reward: [(0, '54.554')] [2023-03-09 10:01:54,331][23090] Updated weights for policy 0, policy_version 113048 (0.0016) [2023-03-09 10:01:55,239][23090] Updated weights for policy 0, policy_version 113058 (0.0013) [2023-03-09 10:01:56,087][23090] Updated weights for policy 0, policy_version 113068 (0.0015) [2023-03-09 10:01:56,774][23090] Updated weights for policy 0, policy_version 113078 (0.0020) [2023-03-09 10:01:57,627][23090] Updated weights for policy 0, policy_version 113088 (0.0017) [2023-03-09 10:01:58,625][23090] Updated weights for policy 0, policy_version 113099 (0.0016) [2023-03-09 10:01:59,059][22664] Fps is (10 sec: 196606.9, 60 sec: 198248.8, 300 sec: 198107.9). Total num frames: 1853095936. Throughput: 0: 49581.8. Samples: 463239968. Policy #0 lag: (min: 2.0, avg: 15.9, max: 33.0) [2023-03-09 10:01:59,059][22664] Avg episode reward: [(0, '53.140')] [2023-03-09 10:01:59,405][23090] Updated weights for policy 0, policy_version 113109 (0.0014) [2023-03-09 10:02:00,140][23090] Updated weights for policy 0, policy_version 113119 (0.0017) [2023-03-09 10:02:01,134][23090] Updated weights for policy 0, policy_version 113129 (0.0020) [2023-03-09 10:02:01,868][23090] Updated weights for policy 0, policy_version 113139 (0.0019) [2023-03-09 10:02:02,006][22940] Signal inference workers to stop experience collection... (38850 times) [2023-03-09 10:02:02,026][22940] Signal inference workers to resume experience collection... (38850 times) [2023-03-09 10:02:02,081][23090] InferenceWorker_p0-w0: stopping experience collection (38850 times) [2023-03-09 10:02:02,081][23090] InferenceWorker_p0-w0: resuming experience collection (38850 times) [2023-03-09 10:02:02,707][23090] Updated weights for policy 0, policy_version 113149 (0.0020) [2023-03-09 10:02:03,655][23090] Updated weights for policy 0, policy_version 113159 (0.0013) [2023-03-09 10:02:04,059][22664] Fps is (10 sec: 196602.6, 60 sec: 197972.6, 300 sec: 198051.8). Total num frames: 1854078976. Throughput: 0: 49628.2. Samples: 463538944. Policy #0 lag: (min: 2.0, avg: 15.9, max: 33.0) [2023-03-09 10:02:04,061][22664] Avg episode reward: [(0, '53.534')] [2023-03-09 10:02:04,353][23090] Updated weights for policy 0, policy_version 113169 (0.0013) [2023-03-09 10:02:05,124][23090] Updated weights for policy 0, policy_version 113179 (0.0013) [2023-03-09 10:02:06,139][23090] Updated weights for policy 0, policy_version 113189 (0.0019) [2023-03-09 10:02:06,875][23090] Updated weights for policy 0, policy_version 113199 (0.0016) [2023-03-09 10:02:07,576][23090] Updated weights for policy 0, policy_version 113209 (0.0018) [2023-03-09 10:02:08,457][23090] Updated weights for policy 0, policy_version 113219 (0.0013) [2023-03-09 10:02:09,059][22664] Fps is (10 sec: 198240.5, 60 sec: 198245.4, 300 sec: 198107.3). Total num frames: 1855078400. Throughput: 0: 49629.2. Samples: 463837792. Policy #0 lag: (min: 2.0, avg: 15.9, max: 33.0) [2023-03-09 10:02:09,061][22664] Avg episode reward: [(0, '53.998')] [2023-03-09 10:02:09,368][23090] Updated weights for policy 0, policy_version 113229 (0.0013) [2023-03-09 10:02:10,061][23090] Updated weights for policy 0, policy_version 113239 (0.0013) [2023-03-09 10:02:10,923][23090] Updated weights for policy 0, policy_version 113249 (0.0013) [2023-03-09 10:02:11,803][23090] Updated weights for policy 0, policy_version 113259 (0.0013) [2023-03-09 10:02:12,631][23090] Updated weights for policy 0, policy_version 113269 (0.0016) [2023-03-09 10:02:12,640][22940] Signal inference workers to stop experience collection... (38900 times) [2023-03-09 10:02:12,659][22940] Signal inference workers to resume experience collection... (38900 times) [2023-03-09 10:02:12,670][23090] InferenceWorker_p0-w0: stopping experience collection (38900 times) [2023-03-09 10:02:12,671][23090] InferenceWorker_p0-w0: resuming experience collection (38900 times) [2023-03-09 10:02:13,366][23090] Updated weights for policy 0, policy_version 113279 (0.0013) [2023-03-09 10:02:14,058][22664] Fps is (10 sec: 196614.2, 60 sec: 197974.6, 300 sec: 197996.8). Total num frames: 1856045056. Throughput: 0: 49629.2. Samples: 463985168. Policy #0 lag: (min: 2.0, avg: 15.9, max: 33.0) [2023-03-09 10:02:14,059][22664] Avg episode reward: [(0, '54.501')] [2023-03-09 10:02:14,375][23090] Updated weights for policy 0, policy_version 113289 (0.0013) [2023-03-09 10:02:15,099][23090] Updated weights for policy 0, policy_version 113299 (0.0023) [2023-03-09 10:02:15,879][23090] Updated weights for policy 0, policy_version 113309 (0.0013) [2023-03-09 10:02:16,895][23090] Updated weights for policy 0, policy_version 113319 (0.0013) [2023-03-09 10:02:17,660][23090] Updated weights for policy 0, policy_version 113330 (0.0021) [2023-03-09 10:02:18,449][23090] Updated weights for policy 0, policy_version 113340 (0.0022) [2023-03-09 10:02:19,059][22664] Fps is (10 sec: 198252.3, 60 sec: 198520.6, 300 sec: 198107.5). Total num frames: 1857060864. Throughput: 0: 49584.7. Samples: 464282080. Policy #0 lag: (min: 2.0, avg: 15.9, max: 33.0) [2023-03-09 10:02:19,060][22664] Avg episode reward: [(0, '53.588')] [2023-03-09 10:02:19,470][23090] Updated weights for policy 0, policy_version 113350 (0.0013) [2023-03-09 10:02:20,183][23090] Updated weights for policy 0, policy_version 113360 (0.0016) [2023-03-09 10:02:20,949][23090] Updated weights for policy 0, policy_version 113370 (0.0016) [2023-03-09 10:02:21,850][23090] Updated weights for policy 0, policy_version 113380 (0.0013) [2023-03-09 10:02:22,708][23090] Updated weights for policy 0, policy_version 113390 (0.0021) [2023-03-09 10:02:22,877][22940] Signal inference workers to stop experience collection... (38950 times) [2023-03-09 10:02:22,879][22940] Signal inference workers to resume experience collection... (38950 times) [2023-03-09 10:02:22,955][23090] InferenceWorker_p0-w0: stopping experience collection (38950 times) [2023-03-09 10:02:22,955][23090] InferenceWorker_p0-w0: resuming experience collection (38950 times) [2023-03-09 10:02:23,447][23090] Updated weights for policy 0, policy_version 113400 (0.0013) [2023-03-09 10:02:24,059][22664] Fps is (10 sec: 201519.2, 60 sec: 198792.3, 300 sec: 198163.2). Total num frames: 1858060288. Throughput: 0: 49539.9. Samples: 464576880. Policy #0 lag: (min: 2.0, avg: 15.9, max: 33.0) [2023-03-09 10:02:24,060][22664] Avg episode reward: [(0, '54.322')] [2023-03-09 10:02:24,321][23090] Updated weights for policy 0, policy_version 113410 (0.0017) [2023-03-09 10:02:25,188][23090] Updated weights for policy 0, policy_version 113420 (0.0013) [2023-03-09 10:02:25,933][23090] Updated weights for policy 0, policy_version 113430 (0.0022) [2023-03-09 10:02:26,712][23090] Updated weights for policy 0, policy_version 113440 (0.0017) [2023-03-09 10:02:27,681][23090] Updated weights for policy 0, policy_version 113451 (0.0013) [2023-03-09 10:02:28,543][23090] Updated weights for policy 0, policy_version 113462 (0.0019) [2023-03-09 10:02:29,059][22664] Fps is (10 sec: 199884.2, 60 sec: 198792.4, 300 sec: 198163.3). Total num frames: 1859059712. Throughput: 0: 49586.0. Samples: 464728400. Policy #0 lag: (min: 2.0, avg: 15.9, max: 33.0) [2023-03-09 10:02:29,059][22664] Avg episode reward: [(0, '51.696')] [2023-03-09 10:02:29,425][23090] Updated weights for policy 0, policy_version 113472 (0.0013) [2023-03-09 10:02:30,353][23090] Updated weights for policy 0, policy_version 113482 (0.0016) [2023-03-09 10:02:31,094][23090] Updated weights for policy 0, policy_version 113492 (0.0012) [2023-03-09 10:02:31,832][23090] Updated weights for policy 0, policy_version 113502 (0.0013) [2023-03-09 10:02:32,854][23090] Updated weights for policy 0, policy_version 113512 (0.0014) [2023-03-09 10:02:33,548][23090] Updated weights for policy 0, policy_version 113522 (0.0029) [2023-03-09 10:02:34,059][22664] Fps is (10 sec: 198245.1, 60 sec: 198518.8, 300 sec: 198162.9). Total num frames: 1860042752. Throughput: 0: 49539.3. Samples: 465021104. Policy #0 lag: (min: 2.0, avg: 15.9, max: 33.0) [2023-03-09 10:02:34,060][22664] Avg episode reward: [(0, '52.329')] [2023-03-09 10:02:34,352][23090] Updated weights for policy 0, policy_version 113532 (0.0017) [2023-03-09 10:02:34,878][22940] Signal inference workers to stop experience collection... (39000 times) [2023-03-09 10:02:34,879][22940] Signal inference workers to resume experience collection... (39000 times) [2023-03-09 10:02:34,939][23090] InferenceWorker_p0-w0: stopping experience collection (39000 times) [2023-03-09 10:02:34,939][23090] InferenceWorker_p0-w0: resuming experience collection (39000 times) [2023-03-09 10:02:35,397][23090] Updated weights for policy 0, policy_version 113542 (0.0017) [2023-03-09 10:02:36,148][23090] Updated weights for policy 0, policy_version 113552 (0.0023) [2023-03-09 10:02:36,942][23090] Updated weights for policy 0, policy_version 113562 (0.0025) [2023-03-09 10:02:37,743][23090] Updated weights for policy 0, policy_version 113572 (0.0013) [2023-03-09 10:02:38,653][23090] Updated weights for policy 0, policy_version 113583 (0.0025) [2023-03-09 10:02:39,059][22664] Fps is (10 sec: 196602.6, 60 sec: 197973.9, 300 sec: 198162.9). Total num frames: 1861025792. Throughput: 0: 49496.2. Samples: 465320048. Policy #0 lag: (min: 2.0, avg: 15.9, max: 33.0) [2023-03-09 10:02:39,061][22664] Avg episode reward: [(0, '53.464')] [2023-03-09 10:02:39,392][23090] Updated weights for policy 0, policy_version 113593 (0.0016) [2023-03-09 10:02:40,272][23090] Updated weights for policy 0, policy_version 113603 (0.0015) [2023-03-09 10:02:41,168][23090] Updated weights for policy 0, policy_version 113613 (0.0014) [2023-03-09 10:02:41,884][23090] Updated weights for policy 0, policy_version 113623 (0.0019) [2023-03-09 10:02:42,811][23090] Updated weights for policy 0, policy_version 113633 (0.0013) [2023-03-09 10:02:43,609][23090] Updated weights for policy 0, policy_version 113643 (0.0013) [2023-03-09 10:02:44,059][22664] Fps is (10 sec: 196606.7, 60 sec: 197700.1, 300 sec: 198051.9). Total num frames: 1862008832. Throughput: 0: 49499.5. Samples: 465467456. Policy #0 lag: (min: 2.0, avg: 16.6, max: 34.0) [2023-03-09 10:02:44,061][22664] Avg episode reward: [(0, '54.444')] [2023-03-09 10:02:44,414][23090] Updated weights for policy 0, policy_version 113653 (0.0016) [2023-03-09 10:02:45,165][23090] Updated weights for policy 0, policy_version 113663 (0.0014) [2023-03-09 10:02:46,109][22940] Signal inference workers to stop experience collection... (39050 times) [2023-03-09 10:02:46,127][22940] Signal inference workers to resume experience collection... (39050 times) [2023-03-09 10:02:46,147][23090] InferenceWorker_p0-w0: stopping experience collection (39050 times) [2023-03-09 10:02:46,147][23090] InferenceWorker_p0-w0: resuming experience collection (39050 times) [2023-03-09 10:02:46,152][23090] Updated weights for policy 0, policy_version 113673 (0.0016) [2023-03-09 10:02:46,917][23090] Updated weights for policy 0, policy_version 113683 (0.0013) [2023-03-09 10:02:47,700][23090] Updated weights for policy 0, policy_version 113694 (0.0012) [2023-03-09 10:02:48,700][23090] Updated weights for policy 0, policy_version 113704 (0.0020) [2023-03-09 10:02:49,059][22664] Fps is (10 sec: 198240.7, 60 sec: 197971.2, 300 sec: 198051.6). Total num frames: 1863008256. Throughput: 0: 49543.4. Samples: 465768416. Policy #0 lag: (min: 2.0, avg: 16.6, max: 34.0) [2023-03-09 10:02:49,061][22664] Avg episode reward: [(0, '55.415')] [2023-03-09 10:02:49,393][23090] Updated weights for policy 0, policy_version 113714 (0.0013) [2023-03-09 10:02:50,176][23090] Updated weights for policy 0, policy_version 113724 (0.0020) [2023-03-09 10:02:51,197][23090] Updated weights for policy 0, policy_version 113734 (0.0016) [2023-03-09 10:02:51,990][23090] Updated weights for policy 0, policy_version 113745 (0.0022) [2023-03-09 10:02:52,742][23090] Updated weights for policy 0, policy_version 113755 (0.0013) [2023-03-09 10:02:53,729][23090] Updated weights for policy 0, policy_version 113765 (0.0022) [2023-03-09 10:02:54,058][22664] Fps is (10 sec: 199890.2, 60 sec: 198246.3, 300 sec: 197996.7). Total num frames: 1864007680. Throughput: 0: 49545.2. Samples: 466067312. Policy #0 lag: (min: 2.0, avg: 16.6, max: 34.0) [2023-03-09 10:02:54,060][22664] Avg episode reward: [(0, '54.606')] [2023-03-09 10:02:54,472][23090] Updated weights for policy 0, policy_version 113775 (0.0026) [2023-03-09 10:02:55,167][23090] Updated weights for policy 0, policy_version 113785 (0.0012) [2023-03-09 10:02:55,521][22940] Signal inference workers to stop experience collection... (39100 times) [2023-03-09 10:02:55,524][22940] Signal inference workers to resume experience collection... (39100 times) [2023-03-09 10:02:55,590][23090] InferenceWorker_p0-w0: stopping experience collection (39100 times) [2023-03-09 10:02:55,591][23090] InferenceWorker_p0-w0: resuming experience collection (39100 times) [2023-03-09 10:02:56,071][23090] Updated weights for policy 0, policy_version 113795 (0.0013) [2023-03-09 10:02:56,968][23090] Updated weights for policy 0, policy_version 113805 (0.0019) [2023-03-09 10:02:57,739][23090] Updated weights for policy 0, policy_version 113816 (0.0013) [2023-03-09 10:02:58,656][23090] Updated weights for policy 0, policy_version 113826 (0.0013) [2023-03-09 10:02:59,059][22664] Fps is (10 sec: 196615.3, 60 sec: 197972.6, 300 sec: 197940.8). Total num frames: 1864974336. Throughput: 0: 49589.4. Samples: 466216704. Policy #0 lag: (min: 2.0, avg: 16.6, max: 34.0) [2023-03-09 10:02:59,061][22664] Avg episode reward: [(0, '53.744')] [2023-03-09 10:02:59,499][23090] Updated weights for policy 0, policy_version 113836 (0.0013) [2023-03-09 10:03:00,239][23090] Updated weights for policy 0, policy_version 113846 (0.0016) [2023-03-09 10:03:01,042][23090] Updated weights for policy 0, policy_version 113856 (0.0018) [2023-03-09 10:03:01,970][23090] Updated weights for policy 0, policy_version 113866 (0.0013) [2023-03-09 10:03:02,841][23090] Updated weights for policy 0, policy_version 113877 (0.0017) [2023-03-09 10:03:03,581][23090] Updated weights for policy 0, policy_version 113887 (0.0021) [2023-03-09 10:03:04,059][22664] Fps is (10 sec: 199881.4, 60 sec: 198792.8, 300 sec: 198052.1). Total num frames: 1866006528. Throughput: 0: 49588.5. Samples: 466513568. Policy #0 lag: (min: 2.0, avg: 16.6, max: 34.0) [2023-03-09 10:03:04,061][22664] Avg episode reward: [(0, '51.860')] [2023-03-09 10:03:04,570][23090] Updated weights for policy 0, policy_version 113897 (0.0017) [2023-03-09 10:03:04,994][22940] Signal inference workers to stop experience collection... (39150 times) [2023-03-09 10:03:05,011][22940] Signal inference workers to resume experience collection... (39150 times) [2023-03-09 10:03:05,038][23090] InferenceWorker_p0-w0: stopping experience collection (39150 times) [2023-03-09 10:03:05,079][23090] InferenceWorker_p0-w0: resuming experience collection (39150 times) [2023-03-09 10:03:05,294][23090] Updated weights for policy 0, policy_version 113907 (0.0022) [2023-03-09 10:03:06,041][23090] Updated weights for policy 0, policy_version 113917 (0.0016) [2023-03-09 10:03:07,082][23090] Updated weights for policy 0, policy_version 113927 (0.0024) [2023-03-09 10:03:07,852][23090] Updated weights for policy 0, policy_version 113938 (0.0018) [2023-03-09 10:03:08,630][23090] Updated weights for policy 0, policy_version 113948 (0.0020) [2023-03-09 10:03:09,059][22664] Fps is (10 sec: 201520.5, 60 sec: 198519.3, 300 sec: 198051.8). Total num frames: 1866989568. Throughput: 0: 49636.0. Samples: 466810512. Policy #0 lag: (min: 2.0, avg: 16.6, max: 34.0) [2023-03-09 10:03:09,061][22664] Avg episode reward: [(0, '52.358')] [2023-03-09 10:03:09,743][23090] Updated weights for policy 0, policy_version 113959 (0.0020) [2023-03-09 10:03:10,446][23090] Updated weights for policy 0, policy_version 113969 (0.0016) [2023-03-09 10:03:11,223][23090] Updated weights for policy 0, policy_version 113979 (0.0022) [2023-03-09 10:03:12,227][23090] Updated weights for policy 0, policy_version 113989 (0.0017) [2023-03-09 10:03:13,062][23090] Updated weights for policy 0, policy_version 114000 (0.0018) [2023-03-09 10:03:13,811][23090] Updated weights for policy 0, policy_version 114010 (0.0013) [2023-03-09 10:03:14,059][22664] Fps is (10 sec: 198245.5, 60 sec: 199064.7, 300 sec: 198107.6). Total num frames: 1867988992. Throughput: 0: 49590.2. Samples: 466959968. Policy #0 lag: (min: 2.0, avg: 16.6, max: 34.0) [2023-03-09 10:03:14,060][22664] Avg episode reward: [(0, '54.782')] [2023-03-09 10:03:14,683][23090] Updated weights for policy 0, policy_version 114020 (0.0013) [2023-03-09 10:03:15,072][22940] Signal inference workers to stop experience collection... (39200 times) [2023-03-09 10:03:15,092][22940] Signal inference workers to resume experience collection... (39200 times) [2023-03-09 10:03:15,121][23090] InferenceWorker_p0-w0: stopping experience collection (39200 times) [2023-03-09 10:03:15,169][23090] InferenceWorker_p0-w0: resuming experience collection (39200 times) [2023-03-09 10:03:15,575][23090] Updated weights for policy 0, policy_version 114030 (0.0021) [2023-03-09 10:03:16,360][23090] Updated weights for policy 0, policy_version 114041 (0.0017) [2023-03-09 10:03:17,259][23090] Updated weights for policy 0, policy_version 114051 (0.0018) [2023-03-09 10:03:18,165][23090] Updated weights for policy 0, policy_version 114061 (0.0015) [2023-03-09 10:03:18,912][23090] Updated weights for policy 0, policy_version 114072 (0.0025) [2023-03-09 10:03:19,058][22664] Fps is (10 sec: 198253.7, 60 sec: 198519.5, 300 sec: 198107.6). Total num frames: 1868972032. Throughput: 0: 49638.3. Samples: 467254816. Policy #0 lag: (min: 2.0, avg: 16.6, max: 34.0) [2023-03-09 10:03:19,059][22664] Avg episode reward: [(0, '53.997')] [2023-03-09 10:03:19,063][22940] Saving /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000114073_1868972032.pth... [2023-03-09 10:03:19,131][22940] Removing /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000111169_1821392896.pth [2023-03-09 10:03:19,812][23090] Updated weights for policy 0, policy_version 114082 (0.0021) [2023-03-09 10:03:20,734][23090] Updated weights for policy 0, policy_version 114092 (0.0013) [2023-03-09 10:03:21,453][23090] Updated weights for policy 0, policy_version 114102 (0.0014) [2023-03-09 10:03:22,296][23090] Updated weights for policy 0, policy_version 114112 (0.0018) [2023-03-09 10:03:23,192][23090] Updated weights for policy 0, policy_version 114122 (0.0016) [2023-03-09 10:03:23,994][23090] Updated weights for policy 0, policy_version 114132 (0.0013) [2023-03-09 10:03:24,058][22664] Fps is (10 sec: 194974.2, 60 sec: 197973.9, 300 sec: 198107.7). Total num frames: 1869938688. Throughput: 0: 49592.9. Samples: 467551712. Policy #0 lag: (min: 2.0, avg: 16.6, max: 34.0) [2023-03-09 10:03:24,059][22664] Avg episode reward: [(0, '55.183')] [2023-03-09 10:03:24,459][22940] Signal inference workers to stop experience collection... (39250 times) [2023-03-09 10:03:24,459][22940] Signal inference workers to resume experience collection... (39250 times) [2023-03-09 10:03:24,527][23090] InferenceWorker_p0-w0: stopping experience collection (39250 times) [2023-03-09 10:03:24,529][23090] InferenceWorker_p0-w0: resuming experience collection (39250 times) [2023-03-09 10:03:24,738][23090] Updated weights for policy 0, policy_version 114142 (0.0016) [2023-03-09 10:03:25,772][23090] Updated weights for policy 0, policy_version 114152 (0.0021) [2023-03-09 10:03:26,441][23090] Updated weights for policy 0, policy_version 114162 (0.0013) [2023-03-09 10:03:27,248][23090] Updated weights for policy 0, policy_version 114172 (0.0017) [2023-03-09 10:03:28,254][23090] Updated weights for policy 0, policy_version 114182 (0.0016) [2023-03-09 10:03:29,012][23090] Updated weights for policy 0, policy_version 114192 (0.0016) [2023-03-09 10:03:29,059][22664] Fps is (10 sec: 196592.7, 60 sec: 197970.9, 300 sec: 198051.7). Total num frames: 1870938112. Throughput: 0: 49545.4. Samples: 467697024. Policy #0 lag: (min: 2.0, avg: 16.6, max: 34.0) [2023-03-09 10:03:29,062][22664] Avg episode reward: [(0, '53.494')] [2023-03-09 10:03:29,756][23090] Updated weights for policy 0, policy_version 114202 (0.0020) [2023-03-09 10:03:30,608][23090] Updated weights for policy 0, policy_version 114212 (0.0021) [2023-03-09 10:03:31,519][23090] Updated weights for policy 0, policy_version 114222 (0.0027) [2023-03-09 10:03:32,223][23090] Updated weights for policy 0, policy_version 114232 (0.0016) [2023-03-09 10:03:33,104][23090] Updated weights for policy 0, policy_version 114242 (0.0016) [2023-03-09 10:03:34,021][23090] Updated weights for policy 0, policy_version 114252 (0.0018) [2023-03-09 10:03:34,058][22664] Fps is (10 sec: 196608.0, 60 sec: 197701.0, 300 sec: 197940.9). Total num frames: 1871904768. Throughput: 0: 49500.4. Samples: 467995904. Policy #0 lag: (min: 2.0, avg: 16.6, max: 34.0) [2023-03-09 10:03:34,059][22664] Avg episode reward: [(0, '54.672')] [2023-03-09 10:03:34,570][22940] Signal inference workers to stop experience collection... (39300 times) [2023-03-09 10:03:34,571][22940] Signal inference workers to resume experience collection... (39300 times) [2023-03-09 10:03:34,632][23090] InferenceWorker_p0-w0: stopping experience collection (39300 times) [2023-03-09 10:03:34,634][23090] InferenceWorker_p0-w0: resuming experience collection (39300 times) [2023-03-09 10:03:34,680][23090] Updated weights for policy 0, policy_version 114262 (0.0026) [2023-03-09 10:03:35,525][23090] Updated weights for policy 0, policy_version 114272 (0.0015) [2023-03-09 10:03:36,388][23090] Updated weights for policy 0, policy_version 114282 (0.0015) [2023-03-09 10:03:37,197][23090] Updated weights for policy 0, policy_version 114292 (0.0013) [2023-03-09 10:03:37,900][23090] Updated weights for policy 0, policy_version 114302 (0.0013) [2023-03-09 10:03:38,937][23090] Updated weights for policy 0, policy_version 114312 (0.0014) [2023-03-09 10:03:39,058][22664] Fps is (10 sec: 199901.2, 60 sec: 198520.7, 300 sec: 198163.1). Total num frames: 1872936960. Throughput: 0: 49544.9. Samples: 468296832. Policy #0 lag: (min: 2.0, avg: 16.6, max: 34.0) [2023-03-09 10:03:39,060][22664] Avg episode reward: [(0, '56.162')] [2023-03-09 10:03:39,643][23090] Updated weights for policy 0, policy_version 114322 (0.0017) [2023-03-09 10:03:40,441][23090] Updated weights for policy 0, policy_version 114332 (0.0013) [2023-03-09 10:03:41,446][23090] Updated weights for policy 0, policy_version 114342 (0.0018) [2023-03-09 10:03:42,184][23090] Updated weights for policy 0, policy_version 114352 (0.0015) [2023-03-09 10:03:42,921][23090] Updated weights for policy 0, policy_version 114362 (0.0017) [2023-03-09 10:03:43,802][23090] Updated weights for policy 0, policy_version 114372 (0.0019) [2023-03-09 10:03:44,058][22664] Fps is (10 sec: 198246.6, 60 sec: 197974.3, 300 sec: 198052.1). Total num frames: 1873887232. Throughput: 0: 49547.0. Samples: 468446304. Policy #0 lag: (min: 2.0, avg: 16.6, max: 34.0) [2023-03-09 10:03:44,059][22664] Avg episode reward: [(0, '52.835')] [2023-03-09 10:03:44,643][23090] Updated weights for policy 0, policy_version 114382 (0.0013) [2023-03-09 10:03:45,147][22940] Signal inference workers to stop experience collection... (39350 times) [2023-03-09 10:03:45,168][22940] Signal inference workers to resume experience collection... (39350 times) [2023-03-09 10:03:45,180][23090] InferenceWorker_p0-w0: stopping experience collection (39350 times) [2023-03-09 10:03:45,180][23090] InferenceWorker_p0-w0: resuming experience collection (39350 times) [2023-03-09 10:03:45,377][23090] Updated weights for policy 0, policy_version 114392 (0.0022) [2023-03-09 10:03:46,308][23090] Updated weights for policy 0, policy_version 114402 (0.0015) [2023-03-09 10:03:47,150][23090] Updated weights for policy 0, policy_version 114412 (0.0013) [2023-03-09 10:03:47,880][23090] Updated weights for policy 0, policy_version 114422 (0.0017) [2023-03-09 10:03:48,698][23090] Updated weights for policy 0, policy_version 114432 (0.0013) [2023-03-09 10:03:49,059][22664] Fps is (10 sec: 196603.5, 60 sec: 198247.8, 300 sec: 198163.3). Total num frames: 1874903040. Throughput: 0: 49500.8. Samples: 468741104. Policy #0 lag: (min: 0.0, avg: 16.6, max: 33.0) [2023-03-09 10:03:49,060][22664] Avg episode reward: [(0, '52.289')] [2023-03-09 10:03:49,631][23090] Updated weights for policy 0, policy_version 114442 (0.0013) [2023-03-09 10:03:50,450][23090] Updated weights for policy 0, policy_version 114452 (0.0013) [2023-03-09 10:03:51,169][23090] Updated weights for policy 0, policy_version 114462 (0.0016) [2023-03-09 10:03:52,135][23090] Updated weights for policy 0, policy_version 114472 (0.0018) [2023-03-09 10:03:53,027][23090] Updated weights for policy 0, policy_version 114483 (0.0017) [2023-03-09 10:03:53,837][23090] Updated weights for policy 0, policy_version 114494 (0.0016) [2023-03-09 10:03:54,059][22664] Fps is (10 sec: 201520.4, 60 sec: 198246.0, 300 sec: 198274.2). Total num frames: 1875902464. Throughput: 0: 49453.8. Samples: 469035920. Policy #0 lag: (min: 0.0, avg: 16.6, max: 33.0) [2023-03-09 10:03:54,060][22664] Avg episode reward: [(0, '55.186')] [2023-03-09 10:03:54,841][23090] Updated weights for policy 0, policy_version 114504 (0.0013) [2023-03-09 10:03:55,567][23090] Updated weights for policy 0, policy_version 114514 (0.0014) [2023-03-09 10:03:56,368][23090] Updated weights for policy 0, policy_version 114524 (0.0013) [2023-03-09 10:03:56,418][22940] Signal inference workers to stop experience collection... (39400 times) [2023-03-09 10:03:56,420][22940] Signal inference workers to resume experience collection... (39400 times) [2023-03-09 10:03:56,488][23090] InferenceWorker_p0-w0: stopping experience collection (39400 times) [2023-03-09 10:03:56,488][23090] InferenceWorker_p0-w0: resuming experience collection (39400 times) [2023-03-09 10:03:57,389][23090] Updated weights for policy 0, policy_version 114534 (0.0013) [2023-03-09 10:03:58,138][23090] Updated weights for policy 0, policy_version 114544 (0.0016) [2023-03-09 10:03:58,867][23090] Updated weights for policy 0, policy_version 114554 (0.0022) [2023-03-09 10:03:59,059][22664] Fps is (10 sec: 198249.0, 60 sec: 198520.1, 300 sec: 198218.6). Total num frames: 1876885504. Throughput: 0: 49453.3. Samples: 469185360. Policy #0 lag: (min: 0.0, avg: 16.6, max: 33.0) [2023-03-09 10:03:59,060][22664] Avg episode reward: [(0, '55.632')] [2023-03-09 10:03:59,731][23090] Updated weights for policy 0, policy_version 114564 (0.0014) [2023-03-09 10:04:00,641][23090] Updated weights for policy 0, policy_version 114574 (0.0020) [2023-03-09 10:04:01,441][23090] Updated weights for policy 0, policy_version 114585 (0.0016) [2023-03-09 10:04:02,285][23090] Updated weights for policy 0, policy_version 114595 (0.0016) [2023-03-09 10:04:03,234][23090] Updated weights for policy 0, policy_version 114605 (0.0016) [2023-03-09 10:04:04,040][23090] Updated weights for policy 0, policy_version 114616 (0.0020) [2023-03-09 10:04:04,058][22664] Fps is (10 sec: 196610.5, 60 sec: 197700.9, 300 sec: 198274.4). Total num frames: 1877868544. Throughput: 0: 49451.0. Samples: 469480112. Policy #0 lag: (min: 0.0, avg: 16.6, max: 33.0) [2023-03-09 10:04:04,059][22664] Avg episode reward: [(0, '54.948')] [2023-03-09 10:04:04,872][23090] Updated weights for policy 0, policy_version 114626 (0.0022) [2023-03-09 10:04:05,747][23090] Updated weights for policy 0, policy_version 114636 (0.0016) [2023-03-09 10:04:06,486][23090] Updated weights for policy 0, policy_version 114646 (0.0013) [2023-03-09 10:04:06,621][22940] Signal inference workers to stop experience collection... (39450 times) [2023-03-09 10:04:06,622][22940] Signal inference workers to resume experience collection... (39450 times) [2023-03-09 10:04:06,686][23090] InferenceWorker_p0-w0: stopping experience collection (39450 times) [2023-03-09 10:04:06,686][23090] InferenceWorker_p0-w0: resuming experience collection (39450 times) [2023-03-09 10:04:07,316][23090] Updated weights for policy 0, policy_version 114656 (0.0017) [2023-03-09 10:04:08,218][23090] Updated weights for policy 0, policy_version 114666 (0.0022) [2023-03-09 10:04:09,056][23090] Updated weights for policy 0, policy_version 114676 (0.0017) [2023-03-09 10:04:09,059][22664] Fps is (10 sec: 196595.9, 60 sec: 197699.3, 300 sec: 198218.4). Total num frames: 1878851584. Throughput: 0: 49450.6. Samples: 469777024. Policy #0 lag: (min: 0.0, avg: 16.6, max: 33.0) [2023-03-09 10:04:09,061][22664] Avg episode reward: [(0, '55.605')] [2023-03-09 10:04:09,741][23090] Updated weights for policy 0, policy_version 114686 (0.0018) [2023-03-09 10:04:10,719][23090] Updated weights for policy 0, policy_version 114696 (0.0017) [2023-03-09 10:04:11,488][23090] Updated weights for policy 0, policy_version 114706 (0.0012) [2023-03-09 10:04:12,347][23090] Updated weights for policy 0, policy_version 114717 (0.0021) [2023-03-09 10:04:13,347][23090] Updated weights for policy 0, policy_version 114727 (0.0016) [2023-03-09 10:04:14,059][22664] Fps is (10 sec: 196603.2, 60 sec: 197427.1, 300 sec: 198163.1). Total num frames: 1879834624. Throughput: 0: 49543.7. Samples: 469926464. Policy #0 lag: (min: 0.0, avg: 16.6, max: 33.0) [2023-03-09 10:04:14,061][22664] Avg episode reward: [(0, '55.578')] [2023-03-09 10:04:14,091][23090] Updated weights for policy 0, policy_version 114737 (0.0016) [2023-03-09 10:04:14,873][23090] Updated weights for policy 0, policy_version 114747 (0.0014) [2023-03-09 10:04:15,854][23090] Updated weights for policy 0, policy_version 114757 (0.0016) [2023-03-09 10:04:16,150][22940] Signal inference workers to stop experience collection... (39500 times) [2023-03-09 10:04:16,151][22940] Signal inference workers to resume experience collection... (39500 times) [2023-03-09 10:04:16,181][23090] InferenceWorker_p0-w0: stopping experience collection (39500 times) [2023-03-09 10:04:16,181][23090] InferenceWorker_p0-w0: resuming experience collection (39500 times) [2023-03-09 10:04:16,618][23090] Updated weights for policy 0, policy_version 114767 (0.0016) [2023-03-09 10:04:17,316][23090] Updated weights for policy 0, policy_version 114777 (0.0014) [2023-03-09 10:04:18,217][23090] Updated weights for policy 0, policy_version 114787 (0.0013) [2023-03-09 10:04:19,059][22664] Fps is (10 sec: 196616.4, 60 sec: 197426.4, 300 sec: 198107.4). Total num frames: 1880817664. Throughput: 0: 49497.3. Samples: 470223296. Policy #0 lag: (min: 0.0, avg: 16.6, max: 33.0) [2023-03-09 10:04:19,061][22664] Avg episode reward: [(0, '56.927')] [2023-03-09 10:04:19,142][23090] Updated weights for policy 0, policy_version 114797 (0.0013) [2023-03-09 10:04:19,880][23090] Updated weights for policy 0, policy_version 114807 (0.0016) [2023-03-09 10:04:20,688][23090] Updated weights for policy 0, policy_version 114817 (0.0020) [2023-03-09 10:04:21,502][23090] Updated weights for policy 0, policy_version 114827 (0.0020) [2023-03-09 10:04:22,361][23090] Updated weights for policy 0, policy_version 114837 (0.0023) [2023-03-09 10:04:23,049][23090] Updated weights for policy 0, policy_version 114847 (0.0013) [2023-03-09 10:04:24,047][23090] Updated weights for policy 0, policy_version 114857 (0.0019) [2023-03-09 10:04:24,059][22664] Fps is (10 sec: 198249.0, 60 sec: 197972.9, 300 sec: 198107.6). Total num frames: 1881817088. Throughput: 0: 49406.1. Samples: 470520112. Policy #0 lag: (min: 0.0, avg: 16.6, max: 33.0) [2023-03-09 10:04:24,060][22664] Avg episode reward: [(0, '55.120')] [2023-03-09 10:04:24,827][22940] Signal inference workers to stop experience collection... (39550 times) [2023-03-09 10:04:24,839][22940] Signal inference workers to resume experience collection... (39550 times) [2023-03-09 10:04:24,860][23090] Updated weights for policy 0, policy_version 114867 (0.0016) [2023-03-09 10:04:24,904][23090] InferenceWorker_p0-w0: stopping experience collection (39550 times) [2023-03-09 10:04:24,904][23090] InferenceWorker_p0-w0: resuming experience collection (39550 times) [2023-03-09 10:04:25,562][23090] Updated weights for policy 0, policy_version 114877 (0.0013) [2023-03-09 10:04:26,545][23090] Updated weights for policy 0, policy_version 114887 (0.0013) [2023-03-09 10:04:27,343][23090] Updated weights for policy 0, policy_version 114898 (0.0017) [2023-03-09 10:04:28,163][23090] Updated weights for policy 0, policy_version 114909 (0.0018) [2023-03-09 10:04:29,059][22664] Fps is (10 sec: 198247.4, 60 sec: 197702.2, 300 sec: 198051.9). Total num frames: 1882800128. Throughput: 0: 49450.4. Samples: 470671584. Policy #0 lag: (min: 0.0, avg: 16.6, max: 33.0) [2023-03-09 10:04:29,060][22664] Avg episode reward: [(0, '53.242')] [2023-03-09 10:04:29,204][23090] Updated weights for policy 0, policy_version 114919 (0.0016) [2023-03-09 10:04:29,981][23090] Updated weights for policy 0, policy_version 114929 (0.0019) [2023-03-09 10:04:30,683][23090] Updated weights for policy 0, policy_version 114939 (0.0022) [2023-03-09 10:04:31,715][23090] Updated weights for policy 0, policy_version 114949 (0.0016) [2023-03-09 10:04:32,527][23090] Updated weights for policy 0, policy_version 114959 (0.0013) [2023-03-09 10:04:33,184][23090] Updated weights for policy 0, policy_version 114969 (0.0021) [2023-03-09 10:04:34,042][23090] Updated weights for policy 0, policy_version 114979 (0.0024) [2023-03-09 10:04:34,059][22664] Fps is (10 sec: 199883.5, 60 sec: 198518.9, 300 sec: 198163.2). Total num frames: 1883815936. Throughput: 0: 49451.8. Samples: 470966432. Policy #0 lag: (min: 0.0, avg: 16.6, max: 33.0) [2023-03-09 10:04:34,060][22664] Avg episode reward: [(0, '56.571')] [2023-03-09 10:04:34,493][22940] Signal inference workers to stop experience collection... (39600 times) [2023-03-09 10:04:34,510][22940] Signal inference workers to resume experience collection... (39600 times) [2023-03-09 10:04:34,537][23090] InferenceWorker_p0-w0: stopping experience collection (39600 times) [2023-03-09 10:04:34,579][23090] InferenceWorker_p0-w0: resuming experience collection (39600 times) [2023-03-09 10:04:34,976][23090] Updated weights for policy 0, policy_version 114989 (0.0013) [2023-03-09 10:04:35,676][23090] Updated weights for policy 0, policy_version 114999 (0.0019) [2023-03-09 10:04:36,535][23090] Updated weights for policy 0, policy_version 115009 (0.0013) [2023-03-09 10:04:37,370][23090] Updated weights for policy 0, policy_version 115019 (0.0016) [2023-03-09 10:04:38,200][23090] Updated weights for policy 0, policy_version 115029 (0.0018) [2023-03-09 10:04:38,928][23090] Updated weights for policy 0, policy_version 115039 (0.0019) [2023-03-09 10:04:39,059][22664] Fps is (10 sec: 201524.4, 60 sec: 197972.8, 300 sec: 198274.1). Total num frames: 1884815360. Throughput: 0: 49541.7. Samples: 471265296. Policy #0 lag: (min: 0.0, avg: 16.6, max: 33.0) [2023-03-09 10:04:39,060][22664] Avg episode reward: [(0, '55.266')] [2023-03-09 10:04:39,891][23090] Updated weights for policy 0, policy_version 115049 (0.0016) [2023-03-09 10:04:40,657][23090] Updated weights for policy 0, policy_version 115059 (0.0016) [2023-03-09 10:04:41,477][23090] Updated weights for policy 0, policy_version 115070 (0.0017) [2023-03-09 10:04:42,493][23090] Updated weights for policy 0, policy_version 115080 (0.0017) [2023-03-09 10:04:43,254][23090] Updated weights for policy 0, policy_version 115090 (0.0019) [2023-03-09 10:04:43,996][23090] Updated weights for policy 0, policy_version 115100 (0.0017) [2023-03-09 10:04:44,058][22664] Fps is (10 sec: 199888.7, 60 sec: 198792.5, 300 sec: 198274.2). Total num frames: 1885814784. Throughput: 0: 49495.9. Samples: 471412672. Policy #0 lag: (min: 0.0, avg: 16.6, max: 33.0) [2023-03-09 10:04:44,059][22664] Avg episode reward: [(0, '53.587')] [2023-03-09 10:04:45,011][22940] Signal inference workers to stop experience collection... (39650 times) [2023-03-09 10:04:45,027][22940] Signal inference workers to resume experience collection... (39650 times) [2023-03-09 10:04:45,055][23090] Updated weights for policy 0, policy_version 115110 (0.0019) [2023-03-09 10:04:45,099][23090] InferenceWorker_p0-w0: stopping experience collection (39650 times) [2023-03-09 10:04:45,103][23090] InferenceWorker_p0-w0: resuming experience collection (39650 times) [2023-03-09 10:04:45,790][23090] Updated weights for policy 0, policy_version 115120 (0.0013) [2023-03-09 10:04:46,450][23090] Updated weights for policy 0, policy_version 115130 (0.0015) [2023-03-09 10:04:47,379][23090] Updated weights for policy 0, policy_version 115140 (0.0016) [2023-03-09 10:04:48,297][23090] Updated weights for policy 0, policy_version 115150 (0.0019) [2023-03-09 10:04:49,034][23090] Updated weights for policy 0, policy_version 115161 (0.0020) [2023-03-09 10:04:49,059][22664] Fps is (10 sec: 198245.7, 60 sec: 198246.5, 300 sec: 198329.6). Total num frames: 1886797824. Throughput: 0: 49585.6. Samples: 471711472. Policy #0 lag: (min: 1.0, avg: 16.2, max: 33.0) [2023-03-09 10:04:49,060][22664] Avg episode reward: [(0, '56.193')] [2023-03-09 10:04:49,915][23090] Updated weights for policy 0, policy_version 115171 (0.0018) [2023-03-09 10:04:50,828][23090] Updated weights for policy 0, policy_version 115181 (0.0014) [2023-03-09 10:04:51,621][23090] Updated weights for policy 0, policy_version 115192 (0.0017) [2023-03-09 10:04:52,523][23090] Updated weights for policy 0, policy_version 115202 (0.0013) [2023-03-09 10:04:53,449][23090] Updated weights for policy 0, policy_version 115212 (0.0020) [2023-03-09 10:04:54,058][22664] Fps is (10 sec: 196608.4, 60 sec: 197973.9, 300 sec: 198218.8). Total num frames: 1887780864. Throughput: 0: 49586.9. Samples: 472008400. Policy #0 lag: (min: 1.0, avg: 16.2, max: 33.0) [2023-03-09 10:04:54,060][22664] Avg episode reward: [(0, '54.516')] [2023-03-09 10:04:54,189][23090] Updated weights for policy 0, policy_version 115223 (0.0016) [2023-03-09 10:04:54,561][22940] Signal inference workers to stop experience collection... (39700 times) [2023-03-09 10:04:54,574][22940] Signal inference workers to resume experience collection... (39700 times) [2023-03-09 10:04:54,636][23090] InferenceWorker_p0-w0: stopping experience collection (39700 times) [2023-03-09 10:04:54,639][23090] InferenceWorker_p0-w0: resuming experience collection (39700 times) [2023-03-09 10:04:55,060][23090] Updated weights for policy 0, policy_version 115233 (0.0016) [2023-03-09 10:04:55,915][23090] Updated weights for policy 0, policy_version 115243 (0.0017) [2023-03-09 10:04:56,729][23090] Updated weights for policy 0, policy_version 115254 (0.0013) [2023-03-09 10:04:57,544][23090] Updated weights for policy 0, policy_version 115264 (0.0020) [2023-03-09 10:04:58,471][23090] Updated weights for policy 0, policy_version 115274 (0.0017) [2023-03-09 10:04:59,059][22664] Fps is (10 sec: 196607.3, 60 sec: 197972.9, 300 sec: 198163.1). Total num frames: 1888763904. Throughput: 0: 49541.0. Samples: 472155808. Policy #0 lag: (min: 1.0, avg: 16.2, max: 33.0) [2023-03-09 10:04:59,060][22664] Avg episode reward: [(0, '57.207')] [2023-03-09 10:04:59,346][23090] Updated weights for policy 0, policy_version 115285 (0.0013) [2023-03-09 10:05:00,082][23090] Updated weights for policy 0, policy_version 115295 (0.0014) [2023-03-09 10:05:01,079][23090] Updated weights for policy 0, policy_version 115305 (0.0015) [2023-03-09 10:05:01,812][23090] Updated weights for policy 0, policy_version 115315 (0.0015) [2023-03-09 10:05:02,568][23090] Updated weights for policy 0, policy_version 115325 (0.0013) [2023-03-09 10:05:03,560][23090] Updated weights for policy 0, policy_version 115335 (0.0016) [2023-03-09 10:05:04,059][22664] Fps is (10 sec: 196606.3, 60 sec: 197973.2, 300 sec: 198107.6). Total num frames: 1889746944. Throughput: 0: 49587.4. Samples: 472454720. Policy #0 lag: (min: 1.0, avg: 16.2, max: 33.0) [2023-03-09 10:05:04,060][22664] Avg episode reward: [(0, '53.312')] [2023-03-09 10:05:04,274][23090] Updated weights for policy 0, policy_version 115345 (0.0016) [2023-03-09 10:05:04,741][22940] Signal inference workers to stop experience collection... (39750 times) [2023-03-09 10:05:04,742][22940] Signal inference workers to resume experience collection... (39750 times) [2023-03-09 10:05:04,800][23090] InferenceWorker_p0-w0: stopping experience collection (39750 times) [2023-03-09 10:05:04,801][23090] InferenceWorker_p0-w0: resuming experience collection (39750 times) [2023-03-09 10:05:05,013][23090] Updated weights for policy 0, policy_version 115355 (0.0015) [2023-03-09 10:05:06,024][23090] Updated weights for policy 0, policy_version 115365 (0.0023) [2023-03-09 10:05:06,865][23090] Updated weights for policy 0, policy_version 115376 (0.0012) [2023-03-09 10:05:07,566][23090] Updated weights for policy 0, policy_version 115386 (0.0018) [2023-03-09 10:05:08,477][23090] Updated weights for policy 0, policy_version 115396 (0.0015) [2023-03-09 10:05:09,059][22664] Fps is (10 sec: 199885.9, 60 sec: 198521.2, 300 sec: 198274.5). Total num frames: 1890762752. Throughput: 0: 49679.2. Samples: 472755680. Policy #0 lag: (min: 1.0, avg: 16.2, max: 33.0) [2023-03-09 10:05:09,060][22664] Avg episode reward: [(0, '54.617')] [2023-03-09 10:05:09,373][23090] Updated weights for policy 0, policy_version 115406 (0.0018) [2023-03-09 10:05:10,093][23090] Updated weights for policy 0, policy_version 115417 (0.0016) [2023-03-09 10:05:10,982][23090] Updated weights for policy 0, policy_version 115427 (0.0012) [2023-03-09 10:05:11,903][23090] Updated weights for policy 0, policy_version 115437 (0.0017) [2023-03-09 10:05:12,652][23090] Updated weights for policy 0, policy_version 115447 (0.0022) [2023-03-09 10:05:13,473][23090] Updated weights for policy 0, policy_version 115457 (0.0017) [2023-03-09 10:05:14,059][22664] Fps is (10 sec: 198243.3, 60 sec: 198246.5, 300 sec: 198163.3). Total num frames: 1891729408. Throughput: 0: 49633.4. Samples: 472905088. Policy #0 lag: (min: 1.0, avg: 16.2, max: 33.0) [2023-03-09 10:05:14,061][22664] Avg episode reward: [(0, '53.774')] [2023-03-09 10:05:14,343][23090] Updated weights for policy 0, policy_version 115467 (0.0016) [2023-03-09 10:05:15,102][23090] Updated weights for policy 0, policy_version 115477 (0.0022) [2023-03-09 10:05:15,869][23090] Updated weights for policy 0, policy_version 115487 (0.0019) [2023-03-09 10:05:16,791][22940] Signal inference workers to stop experience collection... (39800 times) [2023-03-09 10:05:16,805][22940] Signal inference workers to resume experience collection... (39800 times) [2023-03-09 10:05:16,830][23090] InferenceWorker_p0-w0: stopping experience collection (39800 times) [2023-03-09 10:05:16,830][23090] InferenceWorker_p0-w0: resuming experience collection (39800 times) [2023-03-09 10:05:16,835][23090] Updated weights for policy 0, policy_version 115497 (0.0020) [2023-03-09 10:05:17,656][23090] Updated weights for policy 0, policy_version 115508 (0.0018) [2023-03-09 10:05:18,443][23090] Updated weights for policy 0, policy_version 115518 (0.0013) [2023-03-09 10:05:19,059][22664] Fps is (10 sec: 198243.3, 60 sec: 198792.3, 300 sec: 198274.2). Total num frames: 1892745216. Throughput: 0: 49675.9. Samples: 473201856. Policy #0 lag: (min: 1.0, avg: 16.2, max: 33.0) [2023-03-09 10:05:19,061][22664] Avg episode reward: [(0, '54.369')] [2023-03-09 10:05:19,066][22940] Saving /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000115524_1892745216.pth... [2023-03-09 10:05:19,118][22940] Removing /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000112620_1845166080.pth [2023-03-09 10:05:19,445][23090] Updated weights for policy 0, policy_version 115528 (0.0013) [2023-03-09 10:05:20,170][23090] Updated weights for policy 0, policy_version 115538 (0.0013) [2023-03-09 10:05:20,918][23090] Updated weights for policy 0, policy_version 115548 (0.0017) [2023-03-09 10:05:21,982][23090] Updated weights for policy 0, policy_version 115558 (0.0013) [2023-03-09 10:05:22,710][23090] Updated weights for policy 0, policy_version 115568 (0.0016) [2023-03-09 10:05:23,432][23090] Updated weights for policy 0, policy_version 115578 (0.0024) [2023-03-09 10:05:24,059][22664] Fps is (10 sec: 201527.1, 60 sec: 198792.9, 300 sec: 198329.7). Total num frames: 1893744640. Throughput: 0: 49630.0. Samples: 473498640. Policy #0 lag: (min: 1.0, avg: 16.2, max: 33.0) [2023-03-09 10:05:24,060][22664] Avg episode reward: [(0, '53.506')] [2023-03-09 10:05:24,315][23090] Updated weights for policy 0, policy_version 115588 (0.0018) [2023-03-09 10:05:25,240][23090] Updated weights for policy 0, policy_version 115598 (0.0017) [2023-03-09 10:05:25,938][23090] Updated weights for policy 0, policy_version 115608 (0.0020) [2023-03-09 10:05:26,772][23090] Updated weights for policy 0, policy_version 115618 (0.0013) [2023-03-09 10:05:27,661][23090] Updated weights for policy 0, policy_version 115628 (0.0015) [2023-03-09 10:05:28,274][22940] Signal inference workers to stop experience collection... (39850 times) [2023-03-09 10:05:28,296][22940] Signal inference workers to resume experience collection... (39850 times) [2023-03-09 10:05:28,335][23090] InferenceWorker_p0-w0: stopping experience collection (39850 times) [2023-03-09 10:05:28,374][23090] InferenceWorker_p0-w0: resuming experience collection (39850 times) [2023-03-09 10:05:28,421][23090] Updated weights for policy 0, policy_version 115638 (0.0024) [2023-03-09 10:05:29,059][22664] Fps is (10 sec: 199890.7, 60 sec: 199066.2, 300 sec: 198385.5). Total num frames: 1894744064. Throughput: 0: 49676.4. Samples: 473648112. Policy #0 lag: (min: 1.0, avg: 16.2, max: 33.0) [2023-03-09 10:05:29,060][22664] Avg episode reward: [(0, '55.214')] [2023-03-09 10:05:29,169][23090] Updated weights for policy 0, policy_version 115648 (0.0013) [2023-03-09 10:05:30,243][23090] Updated weights for policy 0, policy_version 115659 (0.0016) [2023-03-09 10:05:31,021][23090] Updated weights for policy 0, policy_version 115669 (0.0018) [2023-03-09 10:05:31,748][23090] Updated weights for policy 0, policy_version 115679 (0.0020) [2023-03-09 10:05:32,757][23090] Updated weights for policy 0, policy_version 115690 (0.0015) [2023-03-09 10:05:33,603][23090] Updated weights for policy 0, policy_version 115700 (0.0024) [2023-03-09 10:05:34,059][22664] Fps is (10 sec: 198242.0, 60 sec: 198519.3, 300 sec: 198385.2). Total num frames: 1895727104. Throughput: 0: 49678.9. Samples: 473947024. Policy #0 lag: (min: 1.0, avg: 16.2, max: 33.0) [2023-03-09 10:05:34,061][22664] Avg episode reward: [(0, '53.793')] [2023-03-09 10:05:34,296][23090] Updated weights for policy 0, policy_version 115710 (0.0022) [2023-03-09 10:05:35,346][23090] Updated weights for policy 0, policy_version 115721 (0.0013) [2023-03-09 10:05:36,174][23090] Updated weights for policy 0, policy_version 115731 (0.0021) [2023-03-09 10:05:36,870][23090] Updated weights for policy 0, policy_version 115741 (0.0016) [2023-03-09 10:05:37,899][23090] Updated weights for policy 0, policy_version 115751 (0.0013) [2023-03-09 10:05:38,633][23090] Updated weights for policy 0, policy_version 115761 (0.0022) [2023-03-09 10:05:39,059][22664] Fps is (10 sec: 196608.0, 60 sec: 198246.8, 300 sec: 198274.4). Total num frames: 1896710144. Throughput: 0: 49631.9. Samples: 474241840. Policy #0 lag: (min: 1.0, avg: 16.2, max: 33.0) [2023-03-09 10:05:39,060][22664] Avg episode reward: [(0, '55.145')] [2023-03-09 10:05:39,399][22940] Signal inference workers to stop experience collection... (39900 times) [2023-03-09 10:05:39,413][22940] Signal inference workers to resume experience collection... (39900 times) [2023-03-09 10:05:39,435][23090] Updated weights for policy 0, policy_version 115771 (0.0018) [2023-03-09 10:05:39,472][23090] InferenceWorker_p0-w0: stopping experience collection (39900 times) [2023-03-09 10:05:39,472][23090] InferenceWorker_p0-w0: resuming experience collection (39900 times) [2023-03-09 10:05:40,361][23090] Updated weights for policy 0, policy_version 115781 (0.0021) [2023-03-09 10:05:41,122][23090] Updated weights for policy 0, policy_version 115791 (0.0013) [2023-03-09 10:05:41,865][23090] Updated weights for policy 0, policy_version 115801 (0.0013) [2023-03-09 10:05:42,748][23090] Updated weights for policy 0, policy_version 115811 (0.0019) [2023-03-09 10:05:43,651][23090] Updated weights for policy 0, policy_version 115821 (0.0024) [2023-03-09 10:05:44,059][22664] Fps is (10 sec: 196608.5, 60 sec: 197972.6, 300 sec: 198274.3). Total num frames: 1897693184. Throughput: 0: 49678.6. Samples: 474391344. Policy #0 lag: (min: 1.0, avg: 16.2, max: 33.0) [2023-03-09 10:05:44,060][22664] Avg episode reward: [(0, '55.752')] [2023-03-09 10:05:44,356][23090] Updated weights for policy 0, policy_version 115831 (0.0016) [2023-03-09 10:05:45,219][23090] Updated weights for policy 0, policy_version 115841 (0.0015) [2023-03-09 10:05:46,071][23090] Updated weights for policy 0, policy_version 115851 (0.0013) [2023-03-09 10:05:46,883][23090] Updated weights for policy 0, policy_version 115861 (0.0018) [2023-03-09 10:05:47,592][23090] Updated weights for policy 0, policy_version 115871 (0.0019) [2023-03-09 10:05:48,625][23090] Updated weights for policy 0, policy_version 115882 (0.0016) [2023-03-09 10:05:49,058][22664] Fps is (10 sec: 198247.0, 60 sec: 198247.0, 300 sec: 198218.6). Total num frames: 1898692608. Throughput: 0: 49677.9. Samples: 474690224. Policy #0 lag: (min: 0.0, avg: 16.5, max: 33.0) [2023-03-09 10:05:49,059][22664] Avg episode reward: [(0, '55.534')] [2023-03-09 10:05:49,448][23090] Updated weights for policy 0, policy_version 115892 (0.0017) [2023-03-09 10:05:50,179][23090] Updated weights for policy 0, policy_version 115902 (0.0013) [2023-03-09 10:05:51,135][22940] Signal inference workers to stop experience collection... (39950 times) [2023-03-09 10:05:51,158][22940] Signal inference workers to resume experience collection... (39950 times) [2023-03-09 10:05:51,186][23090] InferenceWorker_p0-w0: stopping experience collection (39950 times) [2023-03-09 10:05:51,192][23090] Updated weights for policy 0, policy_version 115912 (0.0020) [2023-03-09 10:05:51,233][23090] InferenceWorker_p0-w0: resuming experience collection (39950 times) [2023-03-09 10:05:52,044][23090] Updated weights for policy 0, policy_version 115923 (0.0013) [2023-03-09 10:05:52,771][23090] Updated weights for policy 0, policy_version 115933 (0.0018) [2023-03-09 10:05:53,773][23090] Updated weights for policy 0, policy_version 115943 (0.0017) [2023-03-09 10:05:54,059][22664] Fps is (10 sec: 198244.4, 60 sec: 198245.2, 300 sec: 198218.9). Total num frames: 1899675648. Throughput: 0: 49496.4. Samples: 474983024. Policy #0 lag: (min: 0.0, avg: 16.5, max: 33.0) [2023-03-09 10:05:54,061][22664] Avg episode reward: [(0, '55.175')] [2023-03-09 10:05:54,585][23090] Updated weights for policy 0, policy_version 115954 (0.0023) [2023-03-09 10:05:55,372][23090] Updated weights for policy 0, policy_version 115964 (0.0018) [2023-03-09 10:05:56,402][23090] Updated weights for policy 0, policy_version 115974 (0.0019) [2023-03-09 10:05:57,110][23090] Updated weights for policy 0, policy_version 115984 (0.0016) [2023-03-09 10:05:57,904][23090] Updated weights for policy 0, policy_version 115994 (0.0012) [2023-03-09 10:05:58,766][23090] Updated weights for policy 0, policy_version 116004 (0.0021) [2023-03-09 10:05:59,059][22664] Fps is (10 sec: 194963.7, 60 sec: 197973.1, 300 sec: 198107.4). Total num frames: 1900642304. Throughput: 0: 49497.9. Samples: 475132496. Policy #0 lag: (min: 0.0, avg: 16.5, max: 33.0) [2023-03-09 10:05:59,061][22664] Avg episode reward: [(0, '56.387')] [2023-03-09 10:05:59,684][23090] Updated weights for policy 0, policy_version 116014 (0.0016) [2023-03-09 10:06:00,357][23090] Updated weights for policy 0, policy_version 116024 (0.0020) [2023-03-09 10:06:01,209][23090] Updated weights for policy 0, policy_version 116034 (0.0019) [2023-03-09 10:06:02,131][23090] Updated weights for policy 0, policy_version 116044 (0.0013) [2023-03-09 10:06:02,872][23090] Updated weights for policy 0, policy_version 116054 (0.0017) [2023-03-09 10:06:03,644][23090] Updated weights for policy 0, policy_version 116064 (0.0020) [2023-03-09 10:06:04,058][22664] Fps is (10 sec: 196614.7, 60 sec: 198246.6, 300 sec: 198163.1). Total num frames: 1901641728. Throughput: 0: 49500.8. Samples: 475429376. Policy #0 lag: (min: 0.0, avg: 16.5, max: 33.0) [2023-03-09 10:06:04,059][22664] Avg episode reward: [(0, '52.986')] [2023-03-09 10:06:04,360][22940] Signal inference workers to stop experience collection... (40000 times) [2023-03-09 10:06:04,375][22940] Signal inference workers to resume experience collection... (40000 times) [2023-03-09 10:06:04,434][23090] InferenceWorker_p0-w0: stopping experience collection (40000 times) [2023-03-09 10:06:04,477][23090] InferenceWorker_p0-w0: resuming experience collection (40000 times) [2023-03-09 10:06:04,561][23090] Updated weights for policy 0, policy_version 116074 (0.0013) [2023-03-09 10:06:05,376][23090] Updated weights for policy 0, policy_version 116084 (0.0018) [2023-03-09 10:06:06,114][23090] Updated weights for policy 0, policy_version 116094 (0.0022) [2023-03-09 10:06:07,102][23090] Updated weights for policy 0, policy_version 116104 (0.0013) [2023-03-09 10:06:07,863][23090] Updated weights for policy 0, policy_version 116114 (0.0021) [2023-03-09 10:06:08,671][23090] Updated weights for policy 0, policy_version 116124 (0.0013) [2023-03-09 10:06:09,058][22664] Fps is (10 sec: 199890.5, 60 sec: 197973.8, 300 sec: 198218.8). Total num frames: 1902641152. Throughput: 0: 49502.2. Samples: 475726240. Policy #0 lag: (min: 0.0, avg: 16.5, max: 33.0) [2023-03-09 10:06:09,059][22664] Avg episode reward: [(0, '55.144')] [2023-03-09 10:06:09,663][23090] Updated weights for policy 0, policy_version 116134 (0.0018) [2023-03-09 10:06:10,386][23090] Updated weights for policy 0, policy_version 116144 (0.0024) [2023-03-09 10:06:11,123][23090] Updated weights for policy 0, policy_version 116154 (0.0016) [2023-03-09 10:06:12,050][23090] Updated weights for policy 0, policy_version 116164 (0.0015) [2023-03-09 10:06:12,949][23090] Updated weights for policy 0, policy_version 116174 (0.0019) [2023-03-09 10:06:13,674][23090] Updated weights for policy 0, policy_version 116184 (0.0025) [2023-03-09 10:06:14,058][22664] Fps is (10 sec: 199884.9, 60 sec: 198520.2, 300 sec: 198274.4). Total num frames: 1903640576. Throughput: 0: 49456.8. Samples: 475873664. Policy #0 lag: (min: 0.0, avg: 16.5, max: 33.0) [2023-03-09 10:06:14,060][22664] Avg episode reward: [(0, '55.115')] [2023-03-09 10:06:14,567][23090] Updated weights for policy 0, policy_version 116194 (0.0013) [2023-03-09 10:06:15,396][23090] Updated weights for policy 0, policy_version 116204 (0.0017) [2023-03-09 10:06:15,629][22940] Signal inference workers to stop experience collection... (40050 times) [2023-03-09 10:06:15,649][22940] Signal inference workers to resume experience collection... (40050 times) [2023-03-09 10:06:15,686][23090] InferenceWorker_p0-w0: stopping experience collection (40050 times) [2023-03-09 10:06:15,686][23090] InferenceWorker_p0-w0: resuming experience collection (40050 times) [2023-03-09 10:06:16,182][23090] Updated weights for policy 0, policy_version 116214 (0.0021) [2023-03-09 10:06:16,902][23090] Updated weights for policy 0, policy_version 116224 (0.0017) [2023-03-09 10:06:17,981][23090] Updated weights for policy 0, policy_version 116235 (0.0021) [2023-03-09 10:06:18,747][23090] Updated weights for policy 0, policy_version 116245 (0.0013) [2023-03-09 10:06:19,059][22664] Fps is (10 sec: 198245.6, 60 sec: 197974.2, 300 sec: 198274.2). Total num frames: 1904623616. Throughput: 0: 49365.2. Samples: 476168448. Policy #0 lag: (min: 0.0, avg: 16.5, max: 33.0) [2023-03-09 10:06:19,060][22664] Avg episode reward: [(0, '53.874')] [2023-03-09 10:06:19,451][23090] Updated weights for policy 0, policy_version 116255 (0.0013) [2023-03-09 10:06:20,410][23090] Updated weights for policy 0, policy_version 116265 (0.0020) [2023-03-09 10:06:21,282][23090] Updated weights for policy 0, policy_version 116275 (0.0013) [2023-03-09 10:06:21,971][23090] Updated weights for policy 0, policy_version 116285 (0.0013) [2023-03-09 10:06:22,935][23090] Updated weights for policy 0, policy_version 116295 (0.0013) [2023-03-09 10:06:23,687][23090] Updated weights for policy 0, policy_version 116305 (0.0016) [2023-03-09 10:06:24,059][22664] Fps is (10 sec: 196602.7, 60 sec: 197699.5, 300 sec: 198218.5). Total num frames: 1905606656. Throughput: 0: 49454.0. Samples: 476467280. Policy #0 lag: (min: 0.0, avg: 16.5, max: 33.0) [2023-03-09 10:06:24,060][22664] Avg episode reward: [(0, '54.408')] [2023-03-09 10:06:24,415][23090] Updated weights for policy 0, policy_version 116315 (0.0015) [2023-03-09 10:06:25,393][23090] Updated weights for policy 0, policy_version 116325 (0.0016) [2023-03-09 10:06:26,159][22940] Signal inference workers to stop experience collection... (40100 times) [2023-03-09 10:06:26,190][22940] Signal inference workers to resume experience collection... (40100 times) [2023-03-09 10:06:26,216][23090] InferenceWorker_p0-w0: stopping experience collection (40100 times) [2023-03-09 10:06:26,222][23090] Updated weights for policy 0, policy_version 116335 (0.0017) [2023-03-09 10:06:26,263][23090] InferenceWorker_p0-w0: resuming experience collection (40100 times) [2023-03-09 10:06:26,882][23090] Updated weights for policy 0, policy_version 116345 (0.0013) [2023-03-09 10:06:27,796][23090] Updated weights for policy 0, policy_version 116355 (0.0013) [2023-03-09 10:06:28,635][23090] Updated weights for policy 0, policy_version 116365 (0.0013) [2023-03-09 10:06:29,058][22664] Fps is (10 sec: 198247.5, 60 sec: 197700.4, 300 sec: 198218.6). Total num frames: 1906606080. Throughput: 0: 49452.7. Samples: 476616704. Policy #0 lag: (min: 0.0, avg: 16.5, max: 33.0) [2023-03-09 10:06:29,059][22664] Avg episode reward: [(0, '54.977')] [2023-03-09 10:06:29,430][23090] Updated weights for policy 0, policy_version 116375 (0.0013) [2023-03-09 10:06:30,207][23090] Updated weights for policy 0, policy_version 116385 (0.0018) [2023-03-09 10:06:31,200][23090] Updated weights for policy 0, policy_version 116396 (0.0013) [2023-03-09 10:06:31,943][23090] Updated weights for policy 0, policy_version 116406 (0.0013) [2023-03-09 10:06:32,707][23090] Updated weights for policy 0, policy_version 116416 (0.0016) [2023-03-09 10:06:33,635][23090] Updated weights for policy 0, policy_version 116426 (0.0013) [2023-03-09 10:06:34,059][22664] Fps is (10 sec: 198244.7, 60 sec: 197700.0, 300 sec: 198107.7). Total num frames: 1907589120. Throughput: 0: 49451.7. Samples: 476915568. Policy #0 lag: (min: 0.0, avg: 16.5, max: 33.0) [2023-03-09 10:06:34,061][22664] Avg episode reward: [(0, '54.687')] [2023-03-09 10:06:34,518][23090] Updated weights for policy 0, policy_version 116436 (0.0013) [2023-03-09 10:06:35,217][22940] Signal inference workers to stop experience collection... (40150 times) [2023-03-09 10:06:35,217][22940] Signal inference workers to resume experience collection... (40150 times) [2023-03-09 10:06:35,240][23090] Updated weights for policy 0, policy_version 116446 (0.0017) [2023-03-09 10:06:35,273][23090] InferenceWorker_p0-w0: stopping experience collection (40150 times) [2023-03-09 10:06:35,274][23090] InferenceWorker_p0-w0: resuming experience collection (40150 times) [2023-03-09 10:06:36,119][23090] Updated weights for policy 0, policy_version 116456 (0.0018) [2023-03-09 10:06:36,926][23090] Updated weights for policy 0, policy_version 116466 (0.0013) [2023-03-09 10:06:37,709][23090] Updated weights for policy 0, policy_version 116476 (0.0021) [2023-03-09 10:06:38,686][23090] Updated weights for policy 0, policy_version 116486 (0.0013) [2023-03-09 10:06:39,059][22664] Fps is (10 sec: 198239.4, 60 sec: 197972.3, 300 sec: 198107.5). Total num frames: 1908588544. Throughput: 0: 49585.7. Samples: 477214384. Policy #0 lag: (min: 0.0, avg: 16.5, max: 33.0) [2023-03-09 10:06:39,061][22664] Avg episode reward: [(0, '54.766')] [2023-03-09 10:06:39,488][23090] Updated weights for policy 0, policy_version 116497 (0.0019) [2023-03-09 10:06:40,261][23090] Updated weights for policy 0, policy_version 116507 (0.0016) [2023-03-09 10:06:41,223][23090] Updated weights for policy 0, policy_version 116517 (0.0018) [2023-03-09 10:06:42,024][23090] Updated weights for policy 0, policy_version 116527 (0.0016) [2023-03-09 10:06:42,680][23090] Updated weights for policy 0, policy_version 116537 (0.0026) [2023-03-09 10:06:43,578][23090] Updated weights for policy 0, policy_version 116547 (0.0013) [2023-03-09 10:06:44,059][22664] Fps is (10 sec: 201521.9, 60 sec: 198518.9, 300 sec: 198218.4). Total num frames: 1909604352. Throughput: 0: 49585.3. Samples: 477363840. Policy #0 lag: (min: 0.0, avg: 16.5, max: 33.0) [2023-03-09 10:06:44,061][22664] Avg episode reward: [(0, '54.014')] [2023-03-09 10:06:44,406][23090] Updated weights for policy 0, policy_version 116557 (0.0013) [2023-03-09 10:06:44,539][22940] Signal inference workers to stop experience collection... (40200 times) [2023-03-09 10:06:44,540][22940] Signal inference workers to resume experience collection... (40200 times) [2023-03-09 10:06:44,614][23090] InferenceWorker_p0-w0: stopping experience collection (40200 times) [2023-03-09 10:06:44,615][23090] InferenceWorker_p0-w0: resuming experience collection (40200 times) [2023-03-09 10:06:45,150][23090] Updated weights for policy 0, policy_version 116567 (0.0015) [2023-03-09 10:06:46,103][23090] Updated weights for policy 0, policy_version 116578 (0.0013) [2023-03-09 10:06:47,026][23090] Updated weights for policy 0, policy_version 116588 (0.0016) [2023-03-09 10:06:47,736][23090] Updated weights for policy 0, policy_version 116598 (0.0015) [2023-03-09 10:06:48,539][23090] Updated weights for policy 0, policy_version 116608 (0.0019) [2023-03-09 10:06:49,059][22664] Fps is (10 sec: 198247.4, 60 sec: 197972.3, 300 sec: 198162.9). Total num frames: 1910571008. Throughput: 0: 49629.9. Samples: 477662736. Policy #0 lag: (min: 1.0, avg: 17.6, max: 33.0) [2023-03-09 10:06:49,061][22664] Avg episode reward: [(0, '54.028')] [2023-03-09 10:06:49,506][23090] Updated weights for policy 0, policy_version 116618 (0.0019) [2023-03-09 10:06:50,406][23090] Updated weights for policy 0, policy_version 116629 (0.0023) [2023-03-09 10:06:51,133][23090] Updated weights for policy 0, policy_version 116639 (0.0013) [2023-03-09 10:06:52,091][23090] Updated weights for policy 0, policy_version 116649 (0.0019) [2023-03-09 10:06:52,971][23090] Updated weights for policy 0, policy_version 116660 (0.0013) [2023-03-09 10:06:53,087][22940] Signal inference workers to stop experience collection... (40250 times) [2023-03-09 10:06:53,097][22940] Signal inference workers to resume experience collection... (40250 times) [2023-03-09 10:06:53,129][23090] InferenceWorker_p0-w0: stopping experience collection (40250 times) [2023-03-09 10:06:53,174][23090] InferenceWorker_p0-w0: resuming experience collection (40250 times) [2023-03-09 10:06:53,680][23090] Updated weights for policy 0, policy_version 116670 (0.0025) [2023-03-09 10:06:54,059][22664] Fps is (10 sec: 196613.5, 60 sec: 198247.1, 300 sec: 198218.6). Total num frames: 1911570432. Throughput: 0: 49581.4. Samples: 477957408. Policy #0 lag: (min: 1.0, avg: 17.6, max: 33.0) [2023-03-09 10:06:54,060][22664] Avg episode reward: [(0, '53.763')] [2023-03-09 10:06:54,726][23090] Updated weights for policy 0, policy_version 116680 (0.0018) [2023-03-09 10:06:55,447][23090] Updated weights for policy 0, policy_version 116690 (0.0014) [2023-03-09 10:06:56,246][23090] Updated weights for policy 0, policy_version 116701 (0.0017) [2023-03-09 10:06:57,251][23090] Updated weights for policy 0, policy_version 116711 (0.0016) [2023-03-09 10:06:57,982][23090] Updated weights for policy 0, policy_version 116721 (0.0011) [2023-03-09 10:06:58,763][23090] Updated weights for policy 0, policy_version 116731 (0.0020) [2023-03-09 10:06:59,059][22664] Fps is (10 sec: 201521.7, 60 sec: 199065.4, 300 sec: 198329.6). Total num frames: 1912586240. Throughput: 0: 49623.7. Samples: 478106752. Policy #0 lag: (min: 1.0, avg: 17.6, max: 33.0) [2023-03-09 10:06:59,061][22664] Avg episode reward: [(0, '53.708')] [2023-03-09 10:06:59,718][23090] Updated weights for policy 0, policy_version 116741 (0.0016) [2023-03-09 10:07:00,540][23090] Updated weights for policy 0, policy_version 116751 (0.0016) [2023-03-09 10:07:01,330][23090] Updated weights for policy 0, policy_version 116762 (0.0013) [2023-03-09 10:07:01,469][22940] Signal inference workers to stop experience collection... (40300 times) [2023-03-09 10:07:01,493][22940] Signal inference workers to resume experience collection... (40300 times) [2023-03-09 10:07:01,543][23090] InferenceWorker_p0-w0: stopping experience collection (40300 times) [2023-03-09 10:07:01,546][23090] InferenceWorker_p0-w0: resuming experience collection (40300 times) [2023-03-09 10:07:02,364][23090] Updated weights for policy 0, policy_version 116773 (0.0022) [2023-03-09 10:07:03,201][23090] Updated weights for policy 0, policy_version 116783 (0.0017) [2023-03-09 10:07:03,881][23090] Updated weights for policy 0, policy_version 116793 (0.0017) [2023-03-09 10:07:04,058][22664] Fps is (10 sec: 198248.4, 60 sec: 198519.3, 300 sec: 198218.8). Total num frames: 1913552896. Throughput: 0: 49669.4. Samples: 478403568. Policy #0 lag: (min: 1.0, avg: 17.6, max: 33.0) [2023-03-09 10:07:04,059][22664] Avg episode reward: [(0, '53.532')] [2023-03-09 10:07:04,821][23090] Updated weights for policy 0, policy_version 116803 (0.0016) [2023-03-09 10:07:05,700][23090] Updated weights for policy 0, policy_version 116813 (0.0021) [2023-03-09 10:07:06,452][23090] Updated weights for policy 0, policy_version 116823 (0.0013) [2023-03-09 10:07:07,265][23090] Updated weights for policy 0, policy_version 116833 (0.0014) [2023-03-09 10:07:08,207][23090] Updated weights for policy 0, policy_version 116843 (0.0021) [2023-03-09 10:07:08,919][23090] Updated weights for policy 0, policy_version 116853 (0.0018) [2023-03-09 10:07:09,059][22664] Fps is (10 sec: 194971.2, 60 sec: 198245.5, 300 sec: 198273.9). Total num frames: 1914535936. Throughput: 0: 49625.2. Samples: 478700416. Policy #0 lag: (min: 1.0, avg: 17.6, max: 33.0) [2023-03-09 10:07:09,060][22664] Avg episode reward: [(0, '52.339')] [2023-03-09 10:07:09,687][23090] Updated weights for policy 0, policy_version 116863 (0.0015) [2023-03-09 10:07:10,546][22940] Signal inference workers to stop experience collection... (40350 times) [2023-03-09 10:07:10,570][22940] Signal inference workers to resume experience collection... (40350 times) [2023-03-09 10:07:10,574][23090] InferenceWorker_p0-w0: stopping experience collection (40350 times) [2023-03-09 10:07:10,577][23090] InferenceWorker_p0-w0: resuming experience collection (40350 times) [2023-03-09 10:07:10,625][23090] Updated weights for policy 0, policy_version 116873 (0.0016) [2023-03-09 10:07:11,486][23090] Updated weights for policy 0, policy_version 116883 (0.0021) [2023-03-09 10:07:12,234][23090] Updated weights for policy 0, policy_version 116894 (0.0013) [2023-03-09 10:07:13,241][23090] Updated weights for policy 0, policy_version 116904 (0.0016) [2023-03-09 10:07:14,002][23090] Updated weights for policy 0, policy_version 116914 (0.0014) [2023-03-09 10:07:14,059][22664] Fps is (10 sec: 196607.7, 60 sec: 197973.2, 300 sec: 198163.1). Total num frames: 1915518976. Throughput: 0: 49581.1. Samples: 478847856. Policy #0 lag: (min: 1.0, avg: 17.6, max: 33.0) [2023-03-09 10:07:14,060][22664] Avg episode reward: [(0, '53.386')] [2023-03-09 10:07:14,784][23090] Updated weights for policy 0, policy_version 116924 (0.0015) [2023-03-09 10:07:15,817][23090] Updated weights for policy 0, policy_version 116934 (0.0013) [2023-03-09 10:07:16,586][23090] Updated weights for policy 0, policy_version 116944 (0.0019) [2023-03-09 10:07:17,254][23090] Updated weights for policy 0, policy_version 116954 (0.0021) [2023-03-09 10:07:18,156][23090] Updated weights for policy 0, policy_version 116964 (0.0013) [2023-03-09 10:07:19,059][22664] Fps is (10 sec: 194969.9, 60 sec: 197699.5, 300 sec: 198051.9). Total num frames: 1916485632. Throughput: 0: 49492.7. Samples: 479142736. Policy #0 lag: (min: 1.0, avg: 17.6, max: 33.0) [2023-03-09 10:07:19,060][22664] Avg episode reward: [(0, '52.837')] [2023-03-09 10:07:19,096][22940] Saving /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000116974_1916502016.pth... [2023-03-09 10:07:19,122][23090] Updated weights for policy 0, policy_version 116974 (0.0022) [2023-03-09 10:07:19,154][22940] Removing /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000114073_1868972032.pth [2023-03-09 10:07:19,533][22940] Signal inference workers to stop experience collection... (40400 times) [2023-03-09 10:07:19,551][22940] Signal inference workers to resume experience collection... (40400 times) [2023-03-09 10:07:19,584][23090] InferenceWorker_p0-w0: stopping experience collection (40400 times) [2023-03-09 10:07:19,624][23090] InferenceWorker_p0-w0: resuming experience collection (40400 times) [2023-03-09 10:07:19,797][23090] Updated weights for policy 0, policy_version 116984 (0.0015) [2023-03-09 10:07:20,725][23090] Updated weights for policy 0, policy_version 116994 (0.0019) [2023-03-09 10:07:21,578][23090] Updated weights for policy 0, policy_version 117004 (0.0015) [2023-03-09 10:07:22,431][23090] Updated weights for policy 0, policy_version 117015 (0.0015) [2023-03-09 10:07:23,241][23090] Updated weights for policy 0, policy_version 117025 (0.0016) [2023-03-09 10:07:24,059][22664] Fps is (10 sec: 196603.8, 60 sec: 197973.3, 300 sec: 198051.9). Total num frames: 1917485056. Throughput: 0: 49404.2. Samples: 479437568. Policy #0 lag: (min: 1.0, avg: 17.6, max: 33.0) [2023-03-09 10:07:24,060][22664] Avg episode reward: [(0, '54.367')] [2023-03-09 10:07:24,172][23090] Updated weights for policy 0, policy_version 117035 (0.0016) [2023-03-09 10:07:25,029][23090] Updated weights for policy 0, policy_version 117046 (0.0020) [2023-03-09 10:07:25,777][23090] Updated weights for policy 0, policy_version 117056 (0.0013) [2023-03-09 10:07:26,695][23090] Updated weights for policy 0, policy_version 117066 (0.0013) [2023-03-09 10:07:27,586][23090] Updated weights for policy 0, policy_version 117077 (0.0018) [2023-03-09 10:07:27,801][22940] Signal inference workers to stop experience collection... (40450 times) [2023-03-09 10:07:27,815][22940] Signal inference workers to resume experience collection... (40450 times) [2023-03-09 10:07:27,835][23090] InferenceWorker_p0-w0: stopping experience collection (40450 times) [2023-03-09 10:07:27,838][23090] InferenceWorker_p0-w0: resuming experience collection (40450 times) [2023-03-09 10:07:28,340][23090] Updated weights for policy 0, policy_version 117087 (0.0013) [2023-03-09 10:07:29,059][22664] Fps is (10 sec: 196606.4, 60 sec: 197426.0, 300 sec: 197996.4). Total num frames: 1918451712. Throughput: 0: 49359.0. Samples: 479584992. Policy #0 lag: (min: 1.0, avg: 17.6, max: 33.0) [2023-03-09 10:07:29,061][22664] Avg episode reward: [(0, '54.276')] [2023-03-09 10:07:29,301][23090] Updated weights for policy 0, policy_version 117097 (0.0014) [2023-03-09 10:07:30,092][23090] Updated weights for policy 0, policy_version 117107 (0.0013) [2023-03-09 10:07:30,824][23090] Updated weights for policy 0, policy_version 117117 (0.0013) [2023-03-09 10:07:31,854][23090] Updated weights for policy 0, policy_version 117127 (0.0017) [2023-03-09 10:07:32,673][23090] Updated weights for policy 0, policy_version 117138 (0.0020) [2023-03-09 10:07:33,465][23090] Updated weights for policy 0, policy_version 117148 (0.0013) [2023-03-09 10:07:34,059][22664] Fps is (10 sec: 194973.4, 60 sec: 197428.2, 300 sec: 197996.7). Total num frames: 1919434752. Throughput: 0: 49224.1. Samples: 479877808. Policy #0 lag: (min: 1.0, avg: 17.6, max: 33.0) [2023-03-09 10:07:34,060][22664] Avg episode reward: [(0, '52.131')] [2023-03-09 10:07:34,491][23090] Updated weights for policy 0, policy_version 117158 (0.0020) [2023-03-09 10:07:35,235][23090] Updated weights for policy 0, policy_version 117168 (0.0017) [2023-03-09 10:07:35,896][23090] Updated weights for policy 0, policy_version 117178 (0.0019) [2023-03-09 10:07:36,810][23090] Updated weights for policy 0, policy_version 117188 (0.0016) [2023-03-09 10:07:37,201][22940] Signal inference workers to stop experience collection... (40500 times) [2023-03-09 10:07:37,222][22940] Signal inference workers to resume experience collection... (40500 times) [2023-03-09 10:07:37,256][23090] InferenceWorker_p0-w0: stopping experience collection (40500 times) [2023-03-09 10:07:37,301][23090] InferenceWorker_p0-w0: resuming experience collection (40500 times) [2023-03-09 10:07:37,774][23090] Updated weights for policy 0, policy_version 117198 (0.0013) [2023-03-09 10:07:38,580][23090] Updated weights for policy 0, policy_version 117209 (0.0017) [2023-03-09 10:07:39,059][22664] Fps is (10 sec: 199884.6, 60 sec: 197700.2, 300 sec: 198107.5). Total num frames: 1920450560. Throughput: 0: 49226.4. Samples: 480172608. Policy #0 lag: (min: 1.0, avg: 17.6, max: 33.0) [2023-03-09 10:07:39,061][22664] Avg episode reward: [(0, '53.779')] [2023-03-09 10:07:39,469][23090] Updated weights for policy 0, policy_version 117219 (0.0013) [2023-03-09 10:07:40,328][23090] Updated weights for policy 0, policy_version 117229 (0.0013) [2023-03-09 10:07:41,231][23090] Updated weights for policy 0, policy_version 117240 (0.0019) [2023-03-09 10:07:42,110][23090] Updated weights for policy 0, policy_version 117250 (0.0018) [2023-03-09 10:07:43,005][23090] Updated weights for policy 0, policy_version 117260 (0.0016) [2023-03-09 10:07:43,801][23090] Updated weights for policy 0, policy_version 117270 (0.0019) [2023-03-09 10:07:44,059][22664] Fps is (10 sec: 198246.5, 60 sec: 196882.2, 300 sec: 197996.9). Total num frames: 1921417216. Throughput: 0: 49182.6. Samples: 480319952. Policy #0 lag: (min: 1.0, avg: 17.6, max: 33.0) [2023-03-09 10:07:44,059][22664] Avg episode reward: [(0, '55.332')] [2023-03-09 10:07:44,542][23090] Updated weights for policy 0, policy_version 117280 (0.0013) [2023-03-09 10:07:45,198][22940] Signal inference workers to stop experience collection... (40550 times) [2023-03-09 10:07:45,200][22940] Signal inference workers to resume experience collection... (40550 times) [2023-03-09 10:07:45,270][23090] InferenceWorker_p0-w0: stopping experience collection (40550 times) [2023-03-09 10:07:45,270][23090] InferenceWorker_p0-w0: resuming experience collection (40550 times) [2023-03-09 10:07:45,437][23090] Updated weights for policy 0, policy_version 117290 (0.0013) [2023-03-09 10:07:46,292][23090] Updated weights for policy 0, policy_version 117300 (0.0016) [2023-03-09 10:07:47,031][23090] Updated weights for policy 0, policy_version 117310 (0.0017) [2023-03-09 10:07:48,061][23090] Updated weights for policy 0, policy_version 117320 (0.0023) [2023-03-09 10:07:48,811][23090] Updated weights for policy 0, policy_version 117330 (0.0016) [2023-03-09 10:07:49,059][22664] Fps is (10 sec: 191695.2, 60 sec: 196608.2, 300 sec: 197829.7). Total num frames: 1922367488. Throughput: 0: 49000.6. Samples: 480608608. Policy #0 lag: (min: 1.0, avg: 17.6, max: 33.0) [2023-03-09 10:07:49,061][22664] Avg episode reward: [(0, '54.588')] [2023-03-09 10:07:49,570][23090] Updated weights for policy 0, policy_version 117340 (0.0014) [2023-03-09 10:07:50,583][23090] Updated weights for policy 0, policy_version 117350 (0.0016) [2023-03-09 10:07:51,350][23090] Updated weights for policy 0, policy_version 117360 (0.0014) [2023-03-09 10:07:52,125][23090] Updated weights for policy 0, policy_version 117370 (0.0013) [2023-03-09 10:07:52,571][22940] Signal inference workers to stop experience collection... (40600 times) [2023-03-09 10:07:52,571][22940] Signal inference workers to resume experience collection... (40600 times) [2023-03-09 10:07:52,643][23090] InferenceWorker_p0-w0: stopping experience collection (40600 times) [2023-03-09 10:07:52,643][23090] InferenceWorker_p0-w0: resuming experience collection (40600 times) [2023-03-09 10:07:53,213][23090] Updated weights for policy 0, policy_version 117381 (0.0018) [2023-03-09 10:07:54,010][23090] Updated weights for policy 0, policy_version 117391 (0.0014) [2023-03-09 10:07:54,059][22664] Fps is (10 sec: 193325.4, 60 sec: 196334.2, 300 sec: 197885.3). Total num frames: 1923350528. Throughput: 0: 48908.4. Samples: 480901296. Policy #0 lag: (min: 2.0, avg: 17.3, max: 34.0) [2023-03-09 10:07:54,061][22664] Avg episode reward: [(0, '55.588')] [2023-03-09 10:07:54,774][23090] Updated weights for policy 0, policy_version 117401 (0.0013) [2023-03-09 10:07:55,610][23090] Updated weights for policy 0, policy_version 117411 (0.0016) [2023-03-09 10:07:56,511][23090] Updated weights for policy 0, policy_version 117421 (0.0020) [2023-03-09 10:07:57,244][23090] Updated weights for policy 0, policy_version 117431 (0.0016) [2023-03-09 10:07:58,018][23090] Updated weights for policy 0, policy_version 117441 (0.0023) [2023-03-09 10:07:59,007][23090] Updated weights for policy 0, policy_version 117451 (0.0016) [2023-03-09 10:07:59,059][22664] Fps is (10 sec: 196599.1, 60 sec: 195787.7, 300 sec: 197718.4). Total num frames: 1924333568. Throughput: 0: 48951.4. Samples: 481050704. Policy #0 lag: (min: 2.0, avg: 17.3, max: 34.0) [2023-03-09 10:07:59,062][22664] Avg episode reward: [(0, '51.481')] [2023-03-09 10:07:59,738][23090] Updated weights for policy 0, policy_version 117461 (0.0016) [2023-03-09 10:08:00,481][23090] Updated weights for policy 0, policy_version 117471 (0.0013) [2023-03-09 10:08:00,806][22940] Signal inference workers to stop experience collection... (40650 times) [2023-03-09 10:08:00,822][22940] Signal inference workers to resume experience collection... (40650 times) [2023-03-09 10:08:00,888][23090] InferenceWorker_p0-w0: stopping experience collection (40650 times) [2023-03-09 10:08:00,888][23090] InferenceWorker_p0-w0: resuming experience collection (40650 times) [2023-03-09 10:08:01,426][23090] Updated weights for policy 0, policy_version 117481 (0.0013) [2023-03-09 10:08:02,225][23090] Updated weights for policy 0, policy_version 117491 (0.0017) [2023-03-09 10:08:02,936][23090] Updated weights for policy 0, policy_version 117501 (0.0016) [2023-03-09 10:08:03,947][23090] Updated weights for policy 0, policy_version 117511 (0.0020) [2023-03-09 10:08:04,058][22664] Fps is (10 sec: 196614.3, 60 sec: 196061.9, 300 sec: 197719.0). Total num frames: 1925316608. Throughput: 0: 48996.2. Samples: 481347552. Policy #0 lag: (min: 2.0, avg: 17.3, max: 34.0) [2023-03-09 10:08:04,059][22664] Avg episode reward: [(0, '53.723')] [2023-03-09 10:08:04,709][23090] Updated weights for policy 0, policy_version 117521 (0.0016) [2023-03-09 10:08:05,460][23090] Updated weights for policy 0, policy_version 117531 (0.0021) [2023-03-09 10:08:06,448][23090] Updated weights for policy 0, policy_version 117541 (0.0013) [2023-03-09 10:08:07,251][23090] Updated weights for policy 0, policy_version 117552 (0.0020) [2023-03-09 10:08:08,035][23090] Updated weights for policy 0, policy_version 117562 (0.0017) [2023-03-09 10:08:08,934][23090] Updated weights for policy 0, policy_version 117572 (0.0013) [2023-03-09 10:08:09,059][22664] Fps is (10 sec: 196616.3, 60 sec: 196061.9, 300 sec: 197663.2). Total num frames: 1926299648. Throughput: 0: 49041.7. Samples: 481644448. Policy #0 lag: (min: 2.0, avg: 17.3, max: 34.0) [2023-03-09 10:08:09,061][22664] Avg episode reward: [(0, '55.522')] [2023-03-09 10:08:09,223][22940] Signal inference workers to stop experience collection... (40700 times) [2023-03-09 10:08:09,239][22940] Signal inference workers to resume experience collection... (40700 times) [2023-03-09 10:08:09,336][23090] InferenceWorker_p0-w0: stopping experience collection (40700 times) [2023-03-09 10:08:09,338][23090] InferenceWorker_p0-w0: resuming experience collection (40700 times) [2023-03-09 10:08:09,912][23090] Updated weights for policy 0, policy_version 117583 (0.0016) [2023-03-09 10:08:10,670][23090] Updated weights for policy 0, policy_version 117593 (0.0013) [2023-03-09 10:08:11,557][23090] Updated weights for policy 0, policy_version 117603 (0.0013) [2023-03-09 10:08:12,452][23090] Updated weights for policy 0, policy_version 117613 (0.0013) [2023-03-09 10:08:13,228][23090] Updated weights for policy 0, policy_version 117623 (0.0013) [2023-03-09 10:08:14,044][23090] Updated weights for policy 0, policy_version 117633 (0.0013) [2023-03-09 10:08:14,059][22664] Fps is (10 sec: 198240.6, 60 sec: 196334.0, 300 sec: 197718.6). Total num frames: 1927299072. Throughput: 0: 48996.0. Samples: 481789808. Policy #0 lag: (min: 2.0, avg: 17.3, max: 34.0) [2023-03-09 10:08:14,061][22664] Avg episode reward: [(0, '53.627')] [2023-03-09 10:08:14,983][23090] Updated weights for policy 0, policy_version 117643 (0.0019) [2023-03-09 10:08:15,759][23090] Updated weights for policy 0, policy_version 117653 (0.0015) [2023-03-09 10:08:16,491][23090] Updated weights for policy 0, policy_version 117663 (0.0016) [2023-03-09 10:08:17,462][23090] Updated weights for policy 0, policy_version 117673 (0.0019) [2023-03-09 10:08:17,863][22940] Signal inference workers to stop experience collection... (40750 times) [2023-03-09 10:08:17,878][22940] Signal inference workers to resume experience collection... (40750 times) [2023-03-09 10:08:17,941][23090] InferenceWorker_p0-w0: stopping experience collection (40750 times) [2023-03-09 10:08:17,942][23090] InferenceWorker_p0-w0: resuming experience collection (40750 times) [2023-03-09 10:08:18,271][23090] Updated weights for policy 0, policy_version 117683 (0.0019) [2023-03-09 10:08:19,044][23090] Updated weights for policy 0, policy_version 117694 (0.0017) [2023-03-09 10:08:19,059][22664] Fps is (10 sec: 199885.4, 60 sec: 196881.2, 300 sec: 197829.7). Total num frames: 1928298496. Throughput: 0: 49041.9. Samples: 482084704. Policy #0 lag: (min: 2.0, avg: 17.3, max: 34.0) [2023-03-09 10:08:19,060][22664] Avg episode reward: [(0, '55.462')] [2023-03-09 10:08:20,011][23090] Updated weights for policy 0, policy_version 117704 (0.0016) [2023-03-09 10:08:20,813][23090] Updated weights for policy 0, policy_version 117714 (0.0014) [2023-03-09 10:08:21,607][23090] Updated weights for policy 0, policy_version 117724 (0.0016) [2023-03-09 10:08:22,575][23090] Updated weights for policy 0, policy_version 117734 (0.0016) [2023-03-09 10:08:23,377][23090] Updated weights for policy 0, policy_version 117744 (0.0022) [2023-03-09 10:08:24,059][22664] Fps is (10 sec: 198251.8, 60 sec: 196608.7, 300 sec: 197774.8). Total num frames: 1929281536. Throughput: 0: 49042.2. Samples: 482379488. Policy #0 lag: (min: 2.0, avg: 17.3, max: 34.0) [2023-03-09 10:08:24,060][22664] Avg episode reward: [(0, '56.190')] [2023-03-09 10:08:24,074][23090] Updated weights for policy 0, policy_version 117754 (0.0013) [2023-03-09 10:08:25,022][23090] Updated weights for policy 0, policy_version 117764 (0.0016) [2023-03-09 10:08:25,884][23090] Updated weights for policy 0, policy_version 117774 (0.0014) [2023-03-09 10:08:26,570][22940] Signal inference workers to stop experience collection... (40800 times) [2023-03-09 10:08:26,590][22940] Signal inference workers to resume experience collection... (40800 times) [2023-03-09 10:08:26,656][23090] InferenceWorker_p0-w0: stopping experience collection (40800 times) [2023-03-09 10:08:26,657][23090] InferenceWorker_p0-w0: resuming experience collection (40800 times) [2023-03-09 10:08:26,660][23090] Updated weights for policy 0, policy_version 117784 (0.0019) [2023-03-09 10:08:27,513][23090] Updated weights for policy 0, policy_version 117794 (0.0014) [2023-03-09 10:08:28,502][23090] Updated weights for policy 0, policy_version 117804 (0.0024) [2023-03-09 10:08:29,059][22664] Fps is (10 sec: 193335.3, 60 sec: 196336.0, 300 sec: 197718.8). Total num frames: 1930231808. Throughput: 0: 48997.3. Samples: 482524832. Policy #0 lag: (min: 2.0, avg: 17.3, max: 34.0) [2023-03-09 10:08:29,060][22664] Avg episode reward: [(0, '56.349')] [2023-03-09 10:08:29,198][23090] Updated weights for policy 0, policy_version 117814 (0.0013) [2023-03-09 10:08:29,976][23090] Updated weights for policy 0, policy_version 117824 (0.0013) [2023-03-09 10:08:31,080][23090] Updated weights for policy 0, policy_version 117835 (0.0016) [2023-03-09 10:08:31,840][23090] Updated weights for policy 0, policy_version 117845 (0.0016) [2023-03-09 10:08:32,620][23090] Updated weights for policy 0, policy_version 117855 (0.0021) [2023-03-09 10:08:33,615][23090] Updated weights for policy 0, policy_version 117865 (0.0018) [2023-03-09 10:08:34,059][22664] Fps is (10 sec: 191690.0, 60 sec: 196061.4, 300 sec: 197496.5). Total num frames: 1931198464. Throughput: 0: 49042.6. Samples: 482815520. Policy #0 lag: (min: 2.0, avg: 17.3, max: 34.0) [2023-03-09 10:08:34,060][22664] Avg episode reward: [(0, '54.082')] [2023-03-09 10:08:34,521][23090] Updated weights for policy 0, policy_version 117876 (0.0017) [2023-03-09 10:08:35,239][23090] Updated weights for policy 0, policy_version 117886 (0.0015) [2023-03-09 10:08:36,292][23090] Updated weights for policy 0, policy_version 117896 (0.0013) [2023-03-09 10:08:36,605][22940] Signal inference workers to stop experience collection... (40850 times) [2023-03-09 10:08:36,606][22940] Signal inference workers to resume experience collection... (40850 times) [2023-03-09 10:08:36,667][23090] InferenceWorker_p0-w0: stopping experience collection (40850 times) [2023-03-09 10:08:36,667][23090] InferenceWorker_p0-w0: resuming experience collection (40850 times) [2023-03-09 10:08:37,020][23090] Updated weights for policy 0, policy_version 117906 (0.0013) [2023-03-09 10:08:37,814][23090] Updated weights for policy 0, policy_version 117916 (0.0017) [2023-03-09 10:08:38,899][23090] Updated weights for policy 0, policy_version 117926 (0.0020) [2023-03-09 10:08:39,059][22664] Fps is (10 sec: 191691.8, 60 sec: 194970.5, 300 sec: 197496.6). Total num frames: 1932148736. Throughput: 0: 48953.2. Samples: 483104176. Policy #0 lag: (min: 2.0, avg: 17.3, max: 34.0) [2023-03-09 10:08:39,060][22664] Avg episode reward: [(0, '55.452')] [2023-03-09 10:08:39,664][23090] Updated weights for policy 0, policy_version 117936 (0.0021) [2023-03-09 10:08:40,390][23090] Updated weights for policy 0, policy_version 117946 (0.0013) [2023-03-09 10:08:41,336][23090] Updated weights for policy 0, policy_version 117956 (0.0014) [2023-03-09 10:08:42,221][23090] Updated weights for policy 0, policy_version 117966 (0.0018) [2023-03-09 10:08:42,930][23090] Updated weights for policy 0, policy_version 117976 (0.0019) [2023-03-09 10:08:43,861][23090] Updated weights for policy 0, policy_version 117986 (0.0014) [2023-03-09 10:08:44,059][22664] Fps is (10 sec: 191695.7, 60 sec: 194969.6, 300 sec: 197330.1). Total num frames: 1933115392. Throughput: 0: 48815.3. Samples: 483247360. Policy #0 lag: (min: 2.0, avg: 17.3, max: 34.0) [2023-03-09 10:08:44,060][22664] Avg episode reward: [(0, '54.742')] [2023-03-09 10:08:44,809][23090] Updated weights for policy 0, policy_version 117997 (0.0021) [2023-03-09 10:08:44,981][22940] Signal inference workers to stop experience collection... (40900 times) [2023-03-09 10:08:44,996][22940] Signal inference workers to resume experience collection... (40900 times) [2023-03-09 10:08:45,084][23090] InferenceWorker_p0-w0: stopping experience collection (40900 times) [2023-03-09 10:08:45,084][23090] InferenceWorker_p0-w0: resuming experience collection (40900 times) [2023-03-09 10:08:45,584][23090] Updated weights for policy 0, policy_version 118007 (0.0016) [2023-03-09 10:08:46,404][23090] Updated weights for policy 0, policy_version 118017 (0.0025) [2023-03-09 10:08:47,462][23090] Updated weights for policy 0, policy_version 118028 (0.0013) [2023-03-09 10:08:48,267][23090] Updated weights for policy 0, policy_version 118038 (0.0016) [2023-03-09 10:08:48,990][23090] Updated weights for policy 0, policy_version 118048 (0.0013) [2023-03-09 10:08:49,058][22664] Fps is (10 sec: 194971.6, 60 sec: 195516.6, 300 sec: 197274.6). Total num frames: 1934098432. Throughput: 0: 48677.7. Samples: 483538048. Policy #0 lag: (min: 2.0, avg: 17.3, max: 34.0) [2023-03-09 10:08:49,059][22664] Avg episode reward: [(0, '53.938')] [2023-03-09 10:08:49,965][23090] Updated weights for policy 0, policy_version 118058 (0.0017) [2023-03-09 10:08:50,788][23090] Updated weights for policy 0, policy_version 118068 (0.0023) [2023-03-09 10:08:51,528][23090] Updated weights for policy 0, policy_version 118078 (0.0017) [2023-03-09 10:08:52,583][23090] Updated weights for policy 0, policy_version 118089 (0.0013) [2023-03-09 10:08:53,454][23090] Updated weights for policy 0, policy_version 118099 (0.0013) [2023-03-09 10:08:53,712][22940] Signal inference workers to stop experience collection... (40950 times) [2023-03-09 10:08:53,713][22940] Signal inference workers to resume experience collection... (40950 times) [2023-03-09 10:08:53,780][23090] InferenceWorker_p0-w0: stopping experience collection (40950 times) [2023-03-09 10:08:53,784][23090] InferenceWorker_p0-w0: resuming experience collection (40950 times) [2023-03-09 10:08:54,059][22664] Fps is (10 sec: 194964.3, 60 sec: 195242.8, 300 sec: 197218.8). Total num frames: 1935065088. Throughput: 0: 48448.3. Samples: 483824624. Policy #0 lag: (min: 2.0, avg: 16.3, max: 33.0) [2023-03-09 10:08:54,061][22664] Avg episode reward: [(0, '53.938')] [2023-03-09 10:08:54,197][23090] Updated weights for policy 0, policy_version 118109 (0.0015) [2023-03-09 10:08:55,227][23090] Updated weights for policy 0, policy_version 118119 (0.0014) [2023-03-09 10:08:56,065][23090] Updated weights for policy 0, policy_version 118130 (0.0013) [2023-03-09 10:08:56,825][23090] Updated weights for policy 0, policy_version 118140 (0.0019) [2023-03-09 10:08:57,871][23090] Updated weights for policy 0, policy_version 118150 (0.0024) [2023-03-09 10:08:58,637][23090] Updated weights for policy 0, policy_version 118160 (0.0017) [2023-03-09 10:08:59,059][22664] Fps is (10 sec: 191676.0, 60 sec: 194696.0, 300 sec: 197107.3). Total num frames: 1936015360. Throughput: 0: 48492.9. Samples: 483972016. Policy #0 lag: (min: 2.0, avg: 16.3, max: 33.0) [2023-03-09 10:08:59,061][22664] Avg episode reward: [(0, '54.898')] [2023-03-09 10:08:59,345][23090] Updated weights for policy 0, policy_version 118170 (0.0018) [2023-03-09 10:09:00,311][23090] Updated weights for policy 0, policy_version 118180 (0.0019) [2023-03-09 10:09:01,194][23090] Updated weights for policy 0, policy_version 118190 (0.0016) [2023-03-09 10:09:02,041][23090] Updated weights for policy 0, policy_version 118201 (0.0016) [2023-03-09 10:09:02,264][22940] Signal inference workers to stop experience collection... (41000 times) [2023-03-09 10:09:02,265][22940] Signal inference workers to resume experience collection... (41000 times) [2023-03-09 10:09:02,330][23090] InferenceWorker_p0-w0: stopping experience collection (41000 times) [2023-03-09 10:09:02,330][23090] InferenceWorker_p0-w0: resuming experience collection (41000 times) [2023-03-09 10:09:02,943][23090] Updated weights for policy 0, policy_version 118211 (0.0017) [2023-03-09 10:09:03,918][23090] Updated weights for policy 0, policy_version 118222 (0.0019) [2023-03-09 10:09:04,059][22664] Fps is (10 sec: 191694.2, 60 sec: 194422.8, 300 sec: 197052.6). Total num frames: 1936982016. Throughput: 0: 48401.1. Samples: 484262752. Policy #0 lag: (min: 2.0, avg: 16.3, max: 33.0) [2023-03-09 10:09:04,060][22664] Avg episode reward: [(0, '55.972')] [2023-03-09 10:09:04,636][23090] Updated weights for policy 0, policy_version 118232 (0.0016) [2023-03-09 10:09:05,656][23090] Updated weights for policy 0, policy_version 118243 (0.0016) [2023-03-09 10:09:06,564][23090] Updated weights for policy 0, policy_version 118253 (0.0017) [2023-03-09 10:09:07,274][23090] Updated weights for policy 0, policy_version 118263 (0.0017) [2023-03-09 10:09:08,123][23090] Updated weights for policy 0, policy_version 118273 (0.0013) [2023-03-09 10:09:09,046][23090] Updated weights for policy 0, policy_version 118283 (0.0017) [2023-03-09 10:09:09,059][22664] Fps is (10 sec: 193339.5, 60 sec: 194149.9, 300 sec: 196996.6). Total num frames: 1937948672. Throughput: 0: 48310.0. Samples: 484553456. Policy #0 lag: (min: 2.0, avg: 16.3, max: 33.0) [2023-03-09 10:09:09,061][22664] Avg episode reward: [(0, '54.968')] [2023-03-09 10:09:09,833][23090] Updated weights for policy 0, policy_version 118293 (0.0013) [2023-03-09 10:09:10,594][23090] Updated weights for policy 0, policy_version 118303 (0.0019) [2023-03-09 10:09:11,538][22940] Signal inference workers to stop experience collection... (41050 times) [2023-03-09 10:09:11,560][22940] Signal inference workers to resume experience collection... (41050 times) [2023-03-09 10:09:11,586][23090] InferenceWorker_p0-w0: stopping experience collection (41050 times) [2023-03-09 10:09:11,587][23090] InferenceWorker_p0-w0: resuming experience collection (41050 times) [2023-03-09 10:09:11,592][23090] Updated weights for policy 0, policy_version 118313 (0.0015) [2023-03-09 10:09:12,473][23090] Updated weights for policy 0, policy_version 118323 (0.0017) [2023-03-09 10:09:13,166][23090] Updated weights for policy 0, policy_version 118333 (0.0013) [2023-03-09 10:09:14,059][22664] Fps is (10 sec: 191693.5, 60 sec: 193331.6, 300 sec: 196885.7). Total num frames: 1938898944. Throughput: 0: 48310.2. Samples: 484698800. Policy #0 lag: (min: 2.0, avg: 16.3, max: 33.0) [2023-03-09 10:09:14,061][22664] Avg episode reward: [(0, '54.795')] [2023-03-09 10:09:14,230][23090] Updated weights for policy 0, policy_version 118343 (0.0014) [2023-03-09 10:09:14,971][23090] Updated weights for policy 0, policy_version 118353 (0.0016) [2023-03-09 10:09:15,847][23090] Updated weights for policy 0, policy_version 118364 (0.0016) [2023-03-09 10:09:16,917][23090] Updated weights for policy 0, policy_version 118374 (0.0017) [2023-03-09 10:09:17,614][23090] Updated weights for policy 0, policy_version 118384 (0.0013) [2023-03-09 10:09:18,497][23090] Updated weights for policy 0, policy_version 118395 (0.0017) [2023-03-09 10:09:19,059][22664] Fps is (10 sec: 193338.1, 60 sec: 193058.7, 300 sec: 196830.2). Total num frames: 1939881984. Throughput: 0: 48265.3. Samples: 484987456. Policy #0 lag: (min: 2.0, avg: 16.3, max: 33.0) [2023-03-09 10:09:19,059][22664] Avg episode reward: [(0, '55.360')] [2023-03-09 10:09:19,105][22940] Saving /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000118402_1939898368.pth... [2023-03-09 10:09:19,169][22940] Removing /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000115524_1892745216.pth [2023-03-09 10:09:19,482][23090] Updated weights for policy 0, policy_version 118405 (0.0022) [2023-03-09 10:09:20,310][23090] Updated weights for policy 0, policy_version 118415 (0.0018) [2023-03-09 10:09:20,616][22940] Signal inference workers to stop experience collection... (41100 times) [2023-03-09 10:09:20,617][22940] Signal inference workers to resume experience collection... (41100 times) [2023-03-09 10:09:20,687][23090] InferenceWorker_p0-w0: stopping experience collection (41100 times) [2023-03-09 10:09:20,690][23090] InferenceWorker_p0-w0: resuming experience collection (41100 times) [2023-03-09 10:09:21,025][23090] Updated weights for policy 0, policy_version 118425 (0.0020) [2023-03-09 10:09:22,006][23090] Updated weights for policy 0, policy_version 118435 (0.0014) [2023-03-09 10:09:22,869][23090] Updated weights for policy 0, policy_version 118445 (0.0019) [2023-03-09 10:09:23,672][23090] Updated weights for policy 0, policy_version 118456 (0.0019) [2023-03-09 10:09:24,059][22664] Fps is (10 sec: 196606.2, 60 sec: 193057.3, 300 sec: 196830.1). Total num frames: 1940865024. Throughput: 0: 48265.4. Samples: 485276128. Policy #0 lag: (min: 2.0, avg: 16.3, max: 33.0) [2023-03-09 10:09:24,061][22664] Avg episode reward: [(0, '56.461')] [2023-03-09 10:09:24,561][23090] Updated weights for policy 0, policy_version 118466 (0.0018) [2023-03-09 10:09:25,558][23090] Updated weights for policy 0, policy_version 118476 (0.0014) [2023-03-09 10:09:26,288][23090] Updated weights for policy 0, policy_version 118486 (0.0013) [2023-03-09 10:09:27,059][23090] Updated weights for policy 0, policy_version 118496 (0.0016) [2023-03-09 10:09:28,187][23090] Updated weights for policy 0, policy_version 118507 (0.0013) [2023-03-09 10:09:28,956][23090] Updated weights for policy 0, policy_version 118517 (0.0019) [2023-03-09 10:09:29,059][22664] Fps is (10 sec: 191688.7, 60 sec: 192784.2, 300 sec: 196552.4). Total num frames: 1941798912. Throughput: 0: 48223.0. Samples: 485417408. Policy #0 lag: (min: 2.0, avg: 16.3, max: 33.0) [2023-03-09 10:09:29,061][22664] Avg episode reward: [(0, '53.561')] [2023-03-09 10:09:29,668][23090] Updated weights for policy 0, policy_version 118527 (0.0017) [2023-03-09 10:09:30,670][23090] Updated weights for policy 0, policy_version 118537 (0.0019) [2023-03-09 10:09:30,963][22940] Signal inference workers to stop experience collection... (41150 times) [2023-03-09 10:09:30,965][22940] Signal inference workers to resume experience collection... (41150 times) [2023-03-09 10:09:31,036][23090] InferenceWorker_p0-w0: stopping experience collection (41150 times) [2023-03-09 10:09:31,041][23090] InferenceWorker_p0-w0: resuming experience collection (41150 times) [2023-03-09 10:09:31,494][23090] Updated weights for policy 0, policy_version 118547 (0.0022) [2023-03-09 10:09:32,228][23090] Updated weights for policy 0, policy_version 118557 (0.0018) [2023-03-09 10:09:33,234][23090] Updated weights for policy 0, policy_version 118567 (0.0013) [2023-03-09 10:09:34,059][22664] Fps is (10 sec: 190052.4, 60 sec: 192784.4, 300 sec: 196441.2). Total num frames: 1942765568. Throughput: 0: 48268.4. Samples: 485710144. Policy #0 lag: (min: 2.0, avg: 16.3, max: 33.0) [2023-03-09 10:09:34,061][22664] Avg episode reward: [(0, '55.047')] [2023-03-09 10:09:34,094][23090] Updated weights for policy 0, policy_version 118578 (0.0013) [2023-03-09 10:09:34,904][23090] Updated weights for policy 0, policy_version 118588 (0.0013) [2023-03-09 10:09:35,892][23090] Updated weights for policy 0, policy_version 118598 (0.0015) [2023-03-09 10:09:36,612][23090] Updated weights for policy 0, policy_version 118608 (0.0019) [2023-03-09 10:09:37,373][23090] Updated weights for policy 0, policy_version 118618 (0.0018) [2023-03-09 10:09:38,315][23090] Updated weights for policy 0, policy_version 118628 (0.0012) [2023-03-09 10:09:39,059][22664] Fps is (10 sec: 193331.9, 60 sec: 193057.6, 300 sec: 196330.1). Total num frames: 1943732224. Throughput: 0: 48405.0. Samples: 486002848. Policy #0 lag: (min: 2.0, avg: 16.3, max: 33.0) [2023-03-09 10:09:39,060][22664] Avg episode reward: [(0, '55.126')] [2023-03-09 10:09:39,133][23090] Updated weights for policy 0, policy_version 118638 (0.0016) [2023-03-09 10:09:39,870][23090] Updated weights for policy 0, policy_version 118648 (0.0014) [2023-03-09 10:09:40,430][22940] Signal inference workers to stop experience collection... (41200 times) [2023-03-09 10:09:40,431][22940] Signal inference workers to resume experience collection... (41200 times) [2023-03-09 10:09:40,493][23090] InferenceWorker_p0-w0: stopping experience collection (41200 times) [2023-03-09 10:09:40,496][23090] InferenceWorker_p0-w0: resuming experience collection (41200 times) [2023-03-09 10:09:40,736][23090] Updated weights for policy 0, policy_version 118658 (0.0013) [2023-03-09 10:09:41,680][23090] Updated weights for policy 0, policy_version 118668 (0.0013) [2023-03-09 10:09:42,428][23090] Updated weights for policy 0, policy_version 118678 (0.0013) [2023-03-09 10:09:43,122][23090] Updated weights for policy 0, policy_version 118688 (0.0017) [2023-03-09 10:09:44,058][22664] Fps is (10 sec: 196616.2, 60 sec: 193604.5, 300 sec: 196386.0). Total num frames: 1944731648. Throughput: 0: 48405.6. Samples: 486150224. Policy #0 lag: (min: 2.0, avg: 16.3, max: 33.0) [2023-03-09 10:09:44,060][22664] Avg episode reward: [(0, '57.185')] [2023-03-09 10:09:44,076][23090] Updated weights for policy 0, policy_version 118698 (0.0022) [2023-03-09 10:09:44,897][23090] Updated weights for policy 0, policy_version 118708 (0.0019) [2023-03-09 10:09:45,612][23090] Updated weights for policy 0, policy_version 118718 (0.0013) [2023-03-09 10:09:46,660][23090] Updated weights for policy 0, policy_version 118728 (0.0020) [2023-03-09 10:09:47,401][23090] Updated weights for policy 0, policy_version 118738 (0.0016) [2023-03-09 10:09:48,182][23090] Updated weights for policy 0, policy_version 118748 (0.0013) [2023-03-09 10:09:49,059][22664] Fps is (10 sec: 196610.3, 60 sec: 193330.7, 300 sec: 196330.2). Total num frames: 1945698304. Throughput: 0: 48495.7. Samples: 486445056. Policy #0 lag: (min: 2.0, avg: 16.3, max: 33.0) [2023-03-09 10:09:49,060][22664] Avg episode reward: [(0, '56.384')] [2023-03-09 10:09:49,208][23090] Updated weights for policy 0, policy_version 118758 (0.0024) [2023-03-09 10:09:50,013][23090] Updated weights for policy 0, policy_version 118769 (0.0022) [2023-03-09 10:09:50,180][22940] Signal inference workers to stop experience collection... (41250 times) [2023-03-09 10:09:50,182][22940] Signal inference workers to resume experience collection... (41250 times) [2023-03-09 10:09:50,257][23090] InferenceWorker_p0-w0: stopping experience collection (41250 times) [2023-03-09 10:09:50,257][23090] InferenceWorker_p0-w0: resuming experience collection (41250 times) [2023-03-09 10:09:50,833][23090] Updated weights for policy 0, policy_version 118779 (0.0013) [2023-03-09 10:09:51,743][23090] Updated weights for policy 0, policy_version 118789 (0.0017) [2023-03-09 10:09:52,644][23090] Updated weights for policy 0, policy_version 118800 (0.0018) [2023-03-09 10:09:53,425][23090] Updated weights for policy 0, policy_version 118810 (0.0015) [2023-03-09 10:09:54,058][22664] Fps is (10 sec: 196607.6, 60 sec: 193878.3, 300 sec: 196386.0). Total num frames: 1946697728. Throughput: 0: 48497.6. Samples: 486735824. Policy #0 lag: (min: 1.0, avg: 16.6, max: 33.0) [2023-03-09 10:09:54,059][22664] Avg episode reward: [(0, '55.205')] [2023-03-09 10:09:54,350][23090] Updated weights for policy 0, policy_version 118820 (0.0018) [2023-03-09 10:09:55,169][23090] Updated weights for policy 0, policy_version 118830 (0.0022) [2023-03-09 10:09:55,915][23090] Updated weights for policy 0, policy_version 118840 (0.0013) [2023-03-09 10:09:56,790][23090] Updated weights for policy 0, policy_version 118850 (0.0018) [2023-03-09 10:09:57,728][23090] Updated weights for policy 0, policy_version 118860 (0.0013) [2023-03-09 10:09:58,388][23090] Updated weights for policy 0, policy_version 118870 (0.0013) [2023-03-09 10:09:59,059][22664] Fps is (10 sec: 199886.4, 60 sec: 194699.2, 300 sec: 196441.4). Total num frames: 1947697152. Throughput: 0: 48633.0. Samples: 486887280. Policy #0 lag: (min: 1.0, avg: 16.6, max: 33.0) [2023-03-09 10:09:59,059][22664] Avg episode reward: [(0, '55.038')] [2023-03-09 10:09:59,159][23090] Updated weights for policy 0, policy_version 118880 (0.0013) [2023-03-09 10:10:00,001][22940] Signal inference workers to stop experience collection... (41300 times) [2023-03-09 10:10:00,023][22940] Signal inference workers to resume experience collection... (41300 times) [2023-03-09 10:10:00,046][23090] InferenceWorker_p0-w0: stopping experience collection (41300 times) [2023-03-09 10:10:00,047][23090] InferenceWorker_p0-w0: resuming experience collection (41300 times) [2023-03-09 10:10:00,091][23090] Updated weights for policy 0, policy_version 118890 (0.0013) [2023-03-09 10:10:00,893][23090] Updated weights for policy 0, policy_version 118900 (0.0013) [2023-03-09 10:10:01,744][23090] Updated weights for policy 0, policy_version 118911 (0.0012) [2023-03-09 10:10:02,686][23090] Updated weights for policy 0, policy_version 118921 (0.0016) [2023-03-09 10:10:03,547][23090] Updated weights for policy 0, policy_version 118931 (0.0018) [2023-03-09 10:10:04,059][22664] Fps is (10 sec: 198240.7, 60 sec: 194969.4, 300 sec: 196330.2). Total num frames: 1948680192. Throughput: 0: 48721.9. Samples: 487179952. Policy #0 lag: (min: 1.0, avg: 16.6, max: 33.0) [2023-03-09 10:10:04,061][22664] Avg episode reward: [(0, '54.923')] [2023-03-09 10:10:04,308][23090] Updated weights for policy 0, policy_version 118941 (0.0024) [2023-03-09 10:10:05,325][23090] Updated weights for policy 0, policy_version 118951 (0.0018) [2023-03-09 10:10:06,063][23090] Updated weights for policy 0, policy_version 118961 (0.0022) [2023-03-09 10:10:06,897][23090] Updated weights for policy 0, policy_version 118971 (0.0020) [2023-03-09 10:10:07,826][23090] Updated weights for policy 0, policy_version 118981 (0.0017) [2023-03-09 10:10:08,647][23090] Updated weights for policy 0, policy_version 118991 (0.0019) [2023-03-09 10:10:09,059][22664] Fps is (10 sec: 194965.3, 60 sec: 194970.1, 300 sec: 196330.3). Total num frames: 1949646848. Throughput: 0: 48858.3. Samples: 487474752. Policy #0 lag: (min: 1.0, avg: 16.6, max: 33.0) [2023-03-09 10:10:09,060][22664] Avg episode reward: [(0, '55.513')] [2023-03-09 10:10:09,438][23090] Updated weights for policy 0, policy_version 119002 (0.0013) [2023-03-09 10:10:10,363][23090] Updated weights for policy 0, policy_version 119012 (0.0024) [2023-03-09 10:10:11,287][23090] Updated weights for policy 0, policy_version 119022 (0.0019) [2023-03-09 10:10:11,505][22940] Signal inference workers to stop experience collection... (41350 times) [2023-03-09 10:10:11,505][22940] Signal inference workers to resume experience collection... (41350 times) [2023-03-09 10:10:11,571][23090] InferenceWorker_p0-w0: stopping experience collection (41350 times) [2023-03-09 10:10:11,571][23090] InferenceWorker_p0-w0: resuming experience collection (41350 times) [2023-03-09 10:10:12,011][23090] Updated weights for policy 0, policy_version 119032 (0.0019) [2023-03-09 10:10:12,866][23090] Updated weights for policy 0, policy_version 119042 (0.0013) [2023-03-09 10:10:13,765][23090] Updated weights for policy 0, policy_version 119052 (0.0020) [2023-03-09 10:10:14,059][22664] Fps is (10 sec: 193332.4, 60 sec: 195242.6, 300 sec: 196163.8). Total num frames: 1950613504. Throughput: 0: 48993.9. Samples: 487622128. Policy #0 lag: (min: 1.0, avg: 16.6, max: 33.0) [2023-03-09 10:10:14,061][22664] Avg episode reward: [(0, '53.832')] [2023-03-09 10:10:14,468][23090] Updated weights for policy 0, policy_version 119062 (0.0019) [2023-03-09 10:10:15,242][23090] Updated weights for policy 0, policy_version 119072 (0.0020) [2023-03-09 10:10:16,169][23090] Updated weights for policy 0, policy_version 119082 (0.0016) [2023-03-09 10:10:16,968][23090] Updated weights for policy 0, policy_version 119092 (0.0017) [2023-03-09 10:10:17,735][23090] Updated weights for policy 0, policy_version 119102 (0.0034) [2023-03-09 10:10:18,666][23090] Updated weights for policy 0, policy_version 119112 (0.0013) [2023-03-09 10:10:19,058][22664] Fps is (10 sec: 193336.7, 60 sec: 194969.9, 300 sec: 196052.6). Total num frames: 1951580160. Throughput: 0: 49040.8. Samples: 487916960. Policy #0 lag: (min: 1.0, avg: 16.6, max: 33.0) [2023-03-09 10:10:19,059][22664] Avg episode reward: [(0, '55.633')] [2023-03-09 10:10:19,524][23090] Updated weights for policy 0, policy_version 119122 (0.0016) [2023-03-09 10:10:20,292][23090] Updated weights for policy 0, policy_version 119132 (0.0013) [2023-03-09 10:10:21,226][23090] Updated weights for policy 0, policy_version 119142 (0.0017) [2023-03-09 10:10:21,965][22940] Signal inference workers to stop experience collection... (41400 times) [2023-03-09 10:10:21,979][22940] Signal inference workers to resume experience collection... (41400 times) [2023-03-09 10:10:22,032][23090] InferenceWorker_p0-w0: stopping experience collection (41400 times) [2023-03-09 10:10:22,032][23090] InferenceWorker_p0-w0: resuming experience collection (41400 times) [2023-03-09 10:10:22,034][23090] Updated weights for policy 0, policy_version 119152 (0.0014) [2023-03-09 10:10:22,734][23090] Updated weights for policy 0, policy_version 119162 (0.0014) [2023-03-09 10:10:23,719][23090] Updated weights for policy 0, policy_version 119172 (0.0018) [2023-03-09 10:10:24,059][22664] Fps is (10 sec: 196607.1, 60 sec: 195242.7, 300 sec: 196052.5). Total num frames: 1952579584. Throughput: 0: 49041.4. Samples: 488209712. Policy #0 lag: (min: 1.0, avg: 16.6, max: 33.0) [2023-03-09 10:10:24,061][22664] Avg episode reward: [(0, '54.713')] [2023-03-09 10:10:24,585][23090] Updated weights for policy 0, policy_version 119182 (0.0013) [2023-03-09 10:10:25,334][23090] Updated weights for policy 0, policy_version 119192 (0.0020) [2023-03-09 10:10:26,181][23090] Updated weights for policy 0, policy_version 119202 (0.0026) [2023-03-09 10:10:27,149][23090] Updated weights for policy 0, policy_version 119212 (0.0016) [2023-03-09 10:10:27,863][23090] Updated weights for policy 0, policy_version 119222 (0.0016) [2023-03-09 10:10:28,564][23090] Updated weights for policy 0, policy_version 119232 (0.0013) [2023-03-09 10:10:29,059][22664] Fps is (10 sec: 196607.1, 60 sec: 195789.6, 300 sec: 195997.2). Total num frames: 1953546240. Throughput: 0: 49041.7. Samples: 488357104. Policy #0 lag: (min: 1.0, avg: 16.6, max: 33.0) [2023-03-09 10:10:29,060][22664] Avg episode reward: [(0, '54.696')] [2023-03-09 10:10:29,536][23090] Updated weights for policy 0, policy_version 119242 (0.0018) [2023-03-09 10:10:30,384][23090] Updated weights for policy 0, policy_version 119252 (0.0014) [2023-03-09 10:10:31,202][23090] Updated weights for policy 0, policy_version 119262 (0.0020) [2023-03-09 10:10:31,716][22940] Signal inference workers to stop experience collection... (41450 times) [2023-03-09 10:10:31,717][22940] Signal inference workers to resume experience collection... (41450 times) [2023-03-09 10:10:31,776][23090] InferenceWorker_p0-w0: stopping experience collection (41450 times) [2023-03-09 10:10:31,776][23090] InferenceWorker_p0-w0: resuming experience collection (41450 times) [2023-03-09 10:10:32,128][23090] Updated weights for policy 0, policy_version 119272 (0.0016) [2023-03-09 10:10:33,070][23090] Updated weights for policy 0, policy_version 119283 (0.0021) [2023-03-09 10:10:33,792][23090] Updated weights for policy 0, policy_version 119293 (0.0020) [2023-03-09 10:10:34,059][22664] Fps is (10 sec: 196608.0, 60 sec: 196335.3, 300 sec: 196052.5). Total num frames: 1954545664. Throughput: 0: 48991.9. Samples: 488649696. Policy #0 lag: (min: 1.0, avg: 16.6, max: 33.0) [2023-03-09 10:10:34,060][22664] Avg episode reward: [(0, '54.804')] [2023-03-09 10:10:34,812][23090] Updated weights for policy 0, policy_version 119303 (0.0020) [2023-03-09 10:10:35,651][23090] Updated weights for policy 0, policy_version 119313 (0.0017) [2023-03-09 10:10:36,366][23090] Updated weights for policy 0, policy_version 119323 (0.0018) [2023-03-09 10:10:37,295][23090] Updated weights for policy 0, policy_version 119333 (0.0014) [2023-03-09 10:10:38,134][23090] Updated weights for policy 0, policy_version 119343 (0.0022) [2023-03-09 10:10:38,877][23090] Updated weights for policy 0, policy_version 119353 (0.0013) [2023-03-09 10:10:39,059][22664] Fps is (10 sec: 196605.6, 60 sec: 196335.3, 300 sec: 195997.1). Total num frames: 1955512320. Throughput: 0: 48942.0. Samples: 488938224. Policy #0 lag: (min: 1.0, avg: 16.6, max: 33.0) [2023-03-09 10:10:39,060][22664] Avg episode reward: [(0, '54.159')] [2023-03-09 10:10:39,823][23090] Updated weights for policy 0, policy_version 119363 (0.0016) [2023-03-09 10:10:40,551][22940] Signal inference workers to stop experience collection... (41500 times) [2023-03-09 10:10:40,570][22940] Signal inference workers to resume experience collection... (41500 times) [2023-03-09 10:10:40,624][23090] InferenceWorker_p0-w0: stopping experience collection (41500 times) [2023-03-09 10:10:40,624][23090] InferenceWorker_p0-w0: resuming experience collection (41500 times) [2023-03-09 10:10:40,627][23090] Updated weights for policy 0, policy_version 119373 (0.0013) [2023-03-09 10:10:41,383][23090] Updated weights for policy 0, policy_version 119383 (0.0020) [2023-03-09 10:10:42,210][23090] Updated weights for policy 0, policy_version 119393 (0.0016) [2023-03-09 10:10:43,228][23090] Updated weights for policy 0, policy_version 119403 (0.0017) [2023-03-09 10:10:43,991][23090] Updated weights for policy 0, policy_version 119413 (0.0014) [2023-03-09 10:10:44,059][22664] Fps is (10 sec: 193335.2, 60 sec: 195788.5, 300 sec: 195886.0). Total num frames: 1956478976. Throughput: 0: 48898.9. Samples: 489087728. Policy #0 lag: (min: 1.0, avg: 16.6, max: 33.0) [2023-03-09 10:10:44,060][22664] Avg episode reward: [(0, '54.637')] [2023-03-09 10:10:44,653][23090] Updated weights for policy 0, policy_version 119423 (0.0014) [2023-03-09 10:10:45,594][23090] Updated weights for policy 0, policy_version 119433 (0.0016) [2023-03-09 10:10:46,504][23090] Updated weights for policy 0, policy_version 119443 (0.0014) [2023-03-09 10:10:47,238][23090] Updated weights for policy 0, policy_version 119453 (0.0016) [2023-03-09 10:10:48,177][23090] Updated weights for policy 0, policy_version 119463 (0.0018) [2023-03-09 10:10:48,233][22940] Signal inference workers to stop experience collection... (41550 times) [2023-03-09 10:10:48,234][22940] Signal inference workers to resume experience collection... (41550 times) [2023-03-09 10:10:48,324][23090] InferenceWorker_p0-w0: stopping experience collection (41550 times) [2023-03-09 10:10:48,324][23090] InferenceWorker_p0-w0: resuming experience collection (41550 times) [2023-03-09 10:10:48,982][23090] Updated weights for policy 0, policy_version 119473 (0.0017) [2023-03-09 10:10:49,059][22664] Fps is (10 sec: 193333.2, 60 sec: 195789.1, 300 sec: 195830.6). Total num frames: 1957445632. Throughput: 0: 48898.0. Samples: 489380352. Policy #0 lag: (min: 1.0, avg: 16.6, max: 33.0) [2023-03-09 10:10:49,059][22664] Avg episode reward: [(0, '56.363')] [2023-03-09 10:10:49,784][23090] Updated weights for policy 0, policy_version 119483 (0.0013) [2023-03-09 10:10:50,699][23090] Updated weights for policy 0, policy_version 119493 (0.0013) [2023-03-09 10:10:51,505][23090] Updated weights for policy 0, policy_version 119503 (0.0019) [2023-03-09 10:10:52,238][23090] Updated weights for policy 0, policy_version 119513 (0.0013) [2023-03-09 10:10:53,221][23090] Updated weights for policy 0, policy_version 119524 (0.0016) [2023-03-09 10:10:54,059][22664] Fps is (10 sec: 194965.4, 60 sec: 195514.8, 300 sec: 195886.0). Total num frames: 1958428672. Throughput: 0: 48898.1. Samples: 489675168. Policy #0 lag: (min: 0.0, avg: 17.4, max: 32.0) [2023-03-09 10:10:54,061][22664] Avg episode reward: [(0, '52.727')] [2023-03-09 10:10:54,096][23090] Updated weights for policy 0, policy_version 119534 (0.0019) [2023-03-09 10:10:54,840][23090] Updated weights for policy 0, policy_version 119544 (0.0014) [2023-03-09 10:10:55,733][23090] Updated weights for policy 0, policy_version 119554 (0.0016) [2023-03-09 10:10:56,667][23090] Updated weights for policy 0, policy_version 119564 (0.0013) [2023-03-09 10:10:56,802][22940] Signal inference workers to stop experience collection... (41600 times) [2023-03-09 10:10:56,803][22940] Signal inference workers to resume experience collection... (41600 times) [2023-03-09 10:10:56,872][23090] InferenceWorker_p0-w0: stopping experience collection (41600 times) [2023-03-09 10:10:56,872][23090] InferenceWorker_p0-w0: resuming experience collection (41600 times) [2023-03-09 10:10:57,419][23090] Updated weights for policy 0, policy_version 119574 (0.0013) [2023-03-09 10:10:58,381][23090] Updated weights for policy 0, policy_version 119585 (0.0013) [2023-03-09 10:10:59,059][22664] Fps is (10 sec: 196608.2, 60 sec: 195242.7, 300 sec: 195830.4). Total num frames: 1959411712. Throughput: 0: 48898.7. Samples: 489822560. Policy #0 lag: (min: 0.0, avg: 17.4, max: 32.0) [2023-03-09 10:10:59,060][22664] Avg episode reward: [(0, '57.490')] [2023-03-09 10:10:59,242][23090] Updated weights for policy 0, policy_version 119595 (0.0017) [2023-03-09 10:11:00,009][23090] Updated weights for policy 0, policy_version 119605 (0.0013) [2023-03-09 10:11:00,708][23090] Updated weights for policy 0, policy_version 119615 (0.0013) [2023-03-09 10:11:01,600][23090] Updated weights for policy 0, policy_version 119625 (0.0014) [2023-03-09 10:11:02,477][23090] Updated weights for policy 0, policy_version 119635 (0.0017) [2023-03-09 10:11:03,237][23090] Updated weights for policy 0, policy_version 119645 (0.0019) [2023-03-09 10:11:04,058][22664] Fps is (10 sec: 196612.7, 60 sec: 195243.5, 300 sec: 195774.9). Total num frames: 1960394752. Throughput: 0: 48897.7. Samples: 490117360. Policy #0 lag: (min: 0.0, avg: 17.4, max: 32.0) [2023-03-09 10:11:04,059][22664] Avg episode reward: [(0, '57.274')] [2023-03-09 10:11:04,159][23090] Updated weights for policy 0, policy_version 119655 (0.0016) [2023-03-09 10:11:04,947][23090] Updated weights for policy 0, policy_version 119665 (0.0013) [2023-03-09 10:11:05,798][23090] Updated weights for policy 0, policy_version 119675 (0.0020) [2023-03-09 10:11:05,885][22940] Signal inference workers to stop experience collection... (41650 times) [2023-03-09 10:11:05,897][22940] Signal inference workers to resume experience collection... (41650 times) [2023-03-09 10:11:05,970][23090] InferenceWorker_p0-w0: stopping experience collection (41650 times) [2023-03-09 10:11:05,970][23090] InferenceWorker_p0-w0: resuming experience collection (41650 times) [2023-03-09 10:11:06,669][23090] Updated weights for policy 0, policy_version 119685 (0.0019) [2023-03-09 10:11:07,485][23090] Updated weights for policy 0, policy_version 119695 (0.0021) [2023-03-09 10:11:08,186][23090] Updated weights for policy 0, policy_version 119705 (0.0013) [2023-03-09 10:11:09,059][22664] Fps is (10 sec: 198243.8, 60 sec: 195789.1, 300 sec: 195774.8). Total num frames: 1961394176. Throughput: 0: 48988.2. Samples: 490414176. Policy #0 lag: (min: 0.0, avg: 17.4, max: 32.0) [2023-03-09 10:11:09,060][22664] Avg episode reward: [(0, '55.754')] [2023-03-09 10:11:09,120][23090] Updated weights for policy 0, policy_version 119715 (0.0019) [2023-03-09 10:11:09,996][23090] Updated weights for policy 0, policy_version 119725 (0.0013) [2023-03-09 10:11:10,852][23090] Updated weights for policy 0, policy_version 119736 (0.0019) [2023-03-09 10:11:11,707][23090] Updated weights for policy 0, policy_version 119746 (0.0014) [2023-03-09 10:11:12,620][23090] Updated weights for policy 0, policy_version 119756 (0.0021) [2023-03-09 10:11:13,396][23090] Updated weights for policy 0, policy_version 119766 (0.0013) [2023-03-09 10:11:14,059][22664] Fps is (10 sec: 199873.9, 60 sec: 196333.7, 300 sec: 195830.1). Total num frames: 1962393600. Throughput: 0: 48987.5. Samples: 490561568. Policy #0 lag: (min: 0.0, avg: 17.4, max: 32.0) [2023-03-09 10:11:14,061][22664] Avg episode reward: [(0, '56.344')] [2023-03-09 10:11:14,092][23090] Updated weights for policy 0, policy_version 119776 (0.0018) [2023-03-09 10:11:15,070][23090] Updated weights for policy 0, policy_version 119786 (0.0016) [2023-03-09 10:11:15,849][23090] Updated weights for policy 0, policy_version 119796 (0.0014) [2023-03-09 10:11:16,676][23090] Updated weights for policy 0, policy_version 119807 (0.0013) [2023-03-09 10:11:17,720][23090] Updated weights for policy 0, policy_version 119817 (0.0017) [2023-03-09 10:11:18,499][22940] Signal inference workers to stop experience collection... (41700 times) [2023-03-09 10:11:18,517][22940] Signal inference workers to resume experience collection... (41700 times) [2023-03-09 10:11:18,544][23090] Updated weights for policy 0, policy_version 119827 (0.0025) [2023-03-09 10:11:18,584][23090] InferenceWorker_p0-w0: stopping experience collection (41700 times) [2023-03-09 10:11:18,585][23090] InferenceWorker_p0-w0: resuming experience collection (41700 times) [2023-03-09 10:11:19,059][22664] Fps is (10 sec: 196604.9, 60 sec: 196333.8, 300 sec: 195774.9). Total num frames: 1963360256. Throughput: 0: 48946.0. Samples: 490852272. Policy #0 lag: (min: 0.0, avg: 17.4, max: 32.0) [2023-03-09 10:11:19,061][22664] Avg episode reward: [(0, '55.774')] [2023-03-09 10:11:19,109][22940] Saving /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000119834_1963360256.pth... [2023-03-09 10:11:19,175][22940] Removing /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000116974_1916502016.pth [2023-03-09 10:11:19,379][23090] Updated weights for policy 0, policy_version 119837 (0.0019) [2023-03-09 10:11:20,349][23090] Updated weights for policy 0, policy_version 119848 (0.0021) [2023-03-09 10:11:21,174][23090] Updated weights for policy 0, policy_version 119858 (0.0018) [2023-03-09 10:11:21,941][23090] Updated weights for policy 0, policy_version 119868 (0.0019) [2023-03-09 10:11:22,967][23090] Updated weights for policy 0, policy_version 119878 (0.0014) [2023-03-09 10:11:23,875][23090] Updated weights for policy 0, policy_version 119889 (0.0016) [2023-03-09 10:11:24,059][22664] Fps is (10 sec: 191699.3, 60 sec: 195515.8, 300 sec: 195608.1). Total num frames: 1964310528. Throughput: 0: 48947.5. Samples: 491140864. Policy #0 lag: (min: 0.0, avg: 17.4, max: 32.0) [2023-03-09 10:11:24,060][22664] Avg episode reward: [(0, '55.282')] [2023-03-09 10:11:24,636][23090] Updated weights for policy 0, policy_version 119899 (0.0022) [2023-03-09 10:11:25,573][23090] Updated weights for policy 0, policy_version 119909 (0.0016) [2023-03-09 10:11:26,460][23090] Updated weights for policy 0, policy_version 119920 (0.0014) [2023-03-09 10:11:27,239][23090] Updated weights for policy 0, policy_version 119930 (0.0024) [2023-03-09 10:11:28,178][23090] Updated weights for policy 0, policy_version 119940 (0.0023) [2023-03-09 10:11:29,059][22940] Signal inference workers to stop experience collection... (41750 times) [2023-03-09 10:11:29,059][22664] Fps is (10 sec: 190060.1, 60 sec: 195242.6, 300 sec: 195497.4). Total num frames: 1965260800. Throughput: 0: 48810.3. Samples: 491284192. Policy #0 lag: (min: 0.0, avg: 17.4, max: 32.0) [2023-03-09 10:11:29,060][22940] Signal inference workers to resume experience collection... (41750 times) [2023-03-09 10:11:29,060][22664] Avg episode reward: [(0, '54.965')] [2023-03-09 10:11:29,123][23090] InferenceWorker_p0-w0: stopping experience collection (41750 times) [2023-03-09 10:11:29,123][23090] InferenceWorker_p0-w0: resuming experience collection (41750 times) [2023-03-09 10:11:29,129][23090] Updated weights for policy 0, policy_version 119951 (0.0020) [2023-03-09 10:11:29,875][23090] Updated weights for policy 0, policy_version 119961 (0.0016) [2023-03-09 10:11:30,802][23090] Updated weights for policy 0, policy_version 119971 (0.0019) [2023-03-09 10:11:31,626][23090] Updated weights for policy 0, policy_version 119981 (0.0013) [2023-03-09 10:11:32,405][23090] Updated weights for policy 0, policy_version 119991 (0.0018) [2023-03-09 10:11:33,256][23090] Updated weights for policy 0, policy_version 120001 (0.0021) [2023-03-09 10:11:34,059][22664] Fps is (10 sec: 193330.8, 60 sec: 194969.6, 300 sec: 195441.7). Total num frames: 1966243840. Throughput: 0: 48811.9. Samples: 491576896. Policy #0 lag: (min: 0.0, avg: 17.4, max: 32.0) [2023-03-09 10:11:34,060][22664] Avg episode reward: [(0, '53.870')] [2023-03-09 10:11:34,181][23090] Updated weights for policy 0, policy_version 120011 (0.0021) [2023-03-09 10:11:34,911][23090] Updated weights for policy 0, policy_version 120021 (0.0015) [2023-03-09 10:11:35,631][23090] Updated weights for policy 0, policy_version 120031 (0.0018) [2023-03-09 10:11:36,595][23090] Updated weights for policy 0, policy_version 120041 (0.0021) [2023-03-09 10:11:37,372][23090] Updated weights for policy 0, policy_version 120051 (0.0013) [2023-03-09 10:11:38,148][23090] Updated weights for policy 0, policy_version 120061 (0.0016) [2023-03-09 10:11:39,058][22664] Fps is (10 sec: 196609.1, 60 sec: 195243.2, 300 sec: 195330.9). Total num frames: 1967226880. Throughput: 0: 48903.8. Samples: 491875824. Policy #0 lag: (min: 0.0, avg: 17.4, max: 32.0) [2023-03-09 10:11:39,059][22664] Avg episode reward: [(0, '56.379')] [2023-03-09 10:11:39,112][23090] Updated weights for policy 0, policy_version 120071 (0.0017) [2023-03-09 10:11:39,847][23090] Updated weights for policy 0, policy_version 120081 (0.0015) [2023-03-09 10:11:40,407][22940] Signal inference workers to stop experience collection... (41800 times) [2023-03-09 10:11:40,408][22940] Signal inference workers to resume experience collection... (41800 times) [2023-03-09 10:11:40,474][23090] InferenceWorker_p0-w0: stopping experience collection (41800 times) [2023-03-09 10:11:40,474][23090] InferenceWorker_p0-w0: resuming experience collection (41800 times) [2023-03-09 10:11:40,664][23090] Updated weights for policy 0, policy_version 120091 (0.0016) [2023-03-09 10:11:41,549][23090] Updated weights for policy 0, policy_version 120101 (0.0013) [2023-03-09 10:11:42,392][23090] Updated weights for policy 0, policy_version 120111 (0.0017) [2023-03-09 10:11:43,125][23090] Updated weights for policy 0, policy_version 120121 (0.0016) [2023-03-09 10:11:44,052][23090] Updated weights for policy 0, policy_version 120131 (0.0016) [2023-03-09 10:11:44,059][22664] Fps is (10 sec: 198246.1, 60 sec: 195788.1, 300 sec: 195441.7). Total num frames: 1968226304. Throughput: 0: 48904.6. Samples: 492023280. Policy #0 lag: (min: 0.0, avg: 17.4, max: 32.0) [2023-03-09 10:11:44,061][22664] Avg episode reward: [(0, '55.472')] [2023-03-09 10:11:44,874][23090] Updated weights for policy 0, policy_version 120141 (0.0025) [2023-03-09 10:11:45,662][23090] Updated weights for policy 0, policy_version 120151 (0.0018) [2023-03-09 10:11:46,550][23090] Updated weights for policy 0, policy_version 120161 (0.0018) [2023-03-09 10:11:47,560][23090] Updated weights for policy 0, policy_version 120172 (0.0013) [2023-03-09 10:11:48,316][23090] Updated weights for policy 0, policy_version 120182 (0.0017) [2023-03-09 10:11:48,992][23090] Updated weights for policy 0, policy_version 120192 (0.0016) [2023-03-09 10:11:49,059][22664] Fps is (10 sec: 199883.1, 60 sec: 196334.9, 300 sec: 195441.7). Total num frames: 1969225728. Throughput: 0: 48905.2. Samples: 492318096. Policy #0 lag: (min: 0.0, avg: 17.4, max: 32.0) [2023-03-09 10:11:49,060][22664] Avg episode reward: [(0, '56.695')] [2023-03-09 10:11:49,984][23090] Updated weights for policy 0, policy_version 120202 (0.0020) [2023-03-09 10:11:50,394][22940] Signal inference workers to stop experience collection... (41850 times) [2023-03-09 10:11:50,397][22940] Signal inference workers to resume experience collection... (41850 times) [2023-03-09 10:11:50,475][23090] InferenceWorker_p0-w0: stopping experience collection (41850 times) [2023-03-09 10:11:50,475][23090] InferenceWorker_p0-w0: resuming experience collection (41850 times) [2023-03-09 10:11:50,768][23090] Updated weights for policy 0, policy_version 120212 (0.0012) [2023-03-09 10:11:51,603][23090] Updated weights for policy 0, policy_version 120223 (0.0022) [2023-03-09 10:11:52,649][23090] Updated weights for policy 0, policy_version 120234 (0.0018) [2023-03-09 10:11:53,449][23090] Updated weights for policy 0, policy_version 120244 (0.0020) [2023-03-09 10:11:54,059][22664] Fps is (10 sec: 196612.6, 60 sec: 196062.6, 300 sec: 195275.3). Total num frames: 1970192384. Throughput: 0: 48859.5. Samples: 492612848. Policy #0 lag: (min: 0.0, avg: 17.4, max: 32.0) [2023-03-09 10:11:54,060][22664] Avg episode reward: [(0, '56.638')] [2023-03-09 10:11:54,230][23090] Updated weights for policy 0, policy_version 120254 (0.0013) [2023-03-09 10:11:55,151][23090] Updated weights for policy 0, policy_version 120264 (0.0016) [2023-03-09 10:11:55,931][23090] Updated weights for policy 0, policy_version 120274 (0.0013) [2023-03-09 10:11:56,773][23090] Updated weights for policy 0, policy_version 120284 (0.0016) [2023-03-09 10:11:57,717][23090] Updated weights for policy 0, policy_version 120294 (0.0016) [2023-03-09 10:11:58,486][23090] Updated weights for policy 0, policy_version 120304 (0.0019) [2023-03-09 10:11:59,058][22664] Fps is (10 sec: 194970.7, 60 sec: 196062.0, 300 sec: 195330.6). Total num frames: 1971175424. Throughput: 0: 48815.2. Samples: 492758224. Policy #0 lag: (min: 2.0, avg: 18.7, max: 34.0) [2023-03-09 10:11:59,059][22664] Avg episode reward: [(0, '53.417')] [2023-03-09 10:11:59,073][22940] Signal inference workers to stop experience collection... (41900 times) [2023-03-09 10:11:59,074][22940] Signal inference workers to resume experience collection... (41900 times) [2023-03-09 10:11:59,158][23090] InferenceWorker_p0-w0: stopping experience collection (41900 times) [2023-03-09 10:11:59,158][23090] InferenceWorker_p0-w0: resuming experience collection (41900 times) [2023-03-09 10:11:59,248][23090] Updated weights for policy 0, policy_version 120314 (0.0021) [2023-03-09 10:12:00,180][23090] Updated weights for policy 0, policy_version 120324 (0.0017) [2023-03-09 10:12:01,031][23090] Updated weights for policy 0, policy_version 120334 (0.0017) [2023-03-09 10:12:01,786][23090] Updated weights for policy 0, policy_version 120344 (0.0018) [2023-03-09 10:12:02,677][23090] Updated weights for policy 0, policy_version 120354 (0.0023) [2023-03-09 10:12:03,579][23090] Updated weights for policy 0, policy_version 120364 (0.0016) [2023-03-09 10:12:04,059][22664] Fps is (10 sec: 196606.0, 60 sec: 196061.5, 300 sec: 195330.7). Total num frames: 1972158464. Throughput: 0: 48905.5. Samples: 493053008. Policy #0 lag: (min: 2.0, avg: 18.7, max: 34.0) [2023-03-09 10:12:04,060][22664] Avg episode reward: [(0, '52.847')] [2023-03-09 10:12:04,316][23090] Updated weights for policy 0, policy_version 120374 (0.0020) [2023-03-09 10:12:05,068][23090] Updated weights for policy 0, policy_version 120384 (0.0024) [2023-03-09 10:12:06,003][23090] Updated weights for policy 0, policy_version 120394 (0.0013) [2023-03-09 10:12:06,918][23090] Updated weights for policy 0, policy_version 120405 (0.0013) [2023-03-09 10:12:07,410][22940] Signal inference workers to stop experience collection... (41950 times) [2023-03-09 10:12:07,425][22940] Signal inference workers to resume experience collection... (41950 times) [2023-03-09 10:12:07,522][23090] InferenceWorker_p0-w0: stopping experience collection (41950 times) [2023-03-09 10:12:07,522][23090] InferenceWorker_p0-w0: resuming experience collection (41950 times) [2023-03-09 10:12:07,743][23090] Updated weights for policy 0, policy_version 120416 (0.0019) [2023-03-09 10:12:08,716][23090] Updated weights for policy 0, policy_version 120426 (0.0016) [2023-03-09 10:12:09,059][22664] Fps is (10 sec: 194964.7, 60 sec: 195515.4, 300 sec: 195274.9). Total num frames: 1973125120. Throughput: 0: 49044.2. Samples: 493347856. Policy #0 lag: (min: 2.0, avg: 18.7, max: 34.0) [2023-03-09 10:12:09,061][22664] Avg episode reward: [(0, '56.897')] [2023-03-09 10:12:09,471][23090] Updated weights for policy 0, policy_version 120436 (0.0021) [2023-03-09 10:12:10,363][23090] Updated weights for policy 0, policy_version 120447 (0.0029) [2023-03-09 10:12:11,372][23090] Updated weights for policy 0, policy_version 120457 (0.0013) [2023-03-09 10:12:12,122][23090] Updated weights for policy 0, policy_version 120467 (0.0014) [2023-03-09 10:12:13,038][23090] Updated weights for policy 0, policy_version 120478 (0.0013) [2023-03-09 10:12:13,937][23090] Updated weights for policy 0, policy_version 120488 (0.0019) [2023-03-09 10:12:14,059][22664] Fps is (10 sec: 193324.2, 60 sec: 194969.8, 300 sec: 195274.9). Total num frames: 1974091776. Throughput: 0: 49088.6. Samples: 493493200. Policy #0 lag: (min: 2.0, avg: 18.7, max: 34.0) [2023-03-09 10:12:14,061][22664] Avg episode reward: [(0, '56.780')] [2023-03-09 10:12:14,750][23090] Updated weights for policy 0, policy_version 120498 (0.0013) [2023-03-09 10:12:15,587][23090] Updated weights for policy 0, policy_version 120508 (0.0021) [2023-03-09 10:12:16,524][23090] Updated weights for policy 0, policy_version 120518 (0.0022) [2023-03-09 10:12:16,538][22940] Signal inference workers to stop experience collection... (42000 times) [2023-03-09 10:12:16,569][22940] Signal inference workers to resume experience collection... (42000 times) [2023-03-09 10:12:16,651][23090] InferenceWorker_p0-w0: stopping experience collection (42000 times) [2023-03-09 10:12:16,651][23090] InferenceWorker_p0-w0: resuming experience collection (42000 times) [2023-03-09 10:12:17,265][23090] Updated weights for policy 0, policy_version 120528 (0.0021) [2023-03-09 10:12:18,098][23090] Updated weights for policy 0, policy_version 120538 (0.0020) [2023-03-09 10:12:18,963][23090] Updated weights for policy 0, policy_version 120548 (0.0015) [2023-03-09 10:12:19,059][22664] Fps is (10 sec: 193334.2, 60 sec: 194970.3, 300 sec: 195164.1). Total num frames: 1975058432. Throughput: 0: 49045.8. Samples: 493783952. Policy #0 lag: (min: 2.0, avg: 18.7, max: 34.0) [2023-03-09 10:12:19,060][22664] Avg episode reward: [(0, '54.931')] [2023-03-09 10:12:19,853][23090] Updated weights for policy 0, policy_version 120558 (0.0014) [2023-03-09 10:12:20,572][23090] Updated weights for policy 0, policy_version 120568 (0.0020) [2023-03-09 10:12:21,453][23090] Updated weights for policy 0, policy_version 120578 (0.0016) [2023-03-09 10:12:22,389][23090] Updated weights for policy 0, policy_version 120588 (0.0019) [2023-03-09 10:12:23,111][23090] Updated weights for policy 0, policy_version 120598 (0.0022) [2023-03-09 10:12:23,850][23090] Updated weights for policy 0, policy_version 120608 (0.0017) [2023-03-09 10:12:24,059][22664] Fps is (10 sec: 196612.9, 60 sec: 195788.7, 300 sec: 195275.1). Total num frames: 1976057856. Throughput: 0: 48951.9. Samples: 494078672. Policy #0 lag: (min: 2.0, avg: 18.7, max: 34.0) [2023-03-09 10:12:24,060][22664] Avg episode reward: [(0, '53.257')] [2023-03-09 10:12:24,781][23090] Updated weights for policy 0, policy_version 120618 (0.0021) [2023-03-09 10:12:24,952][22940] Signal inference workers to stop experience collection... (42050 times) [2023-03-09 10:12:24,953][22940] Signal inference workers to resume experience collection... (42050 times) [2023-03-09 10:12:25,023][23090] InferenceWorker_p0-w0: stopping experience collection (42050 times) [2023-03-09 10:12:25,024][23090] InferenceWorker_p0-w0: resuming experience collection (42050 times) [2023-03-09 10:12:25,558][23090] Updated weights for policy 0, policy_version 120628 (0.0016) [2023-03-09 10:12:26,376][23090] Updated weights for policy 0, policy_version 120638 (0.0016) [2023-03-09 10:12:27,250][23090] Updated weights for policy 0, policy_version 120648 (0.0019) [2023-03-09 10:12:28,096][23090] Updated weights for policy 0, policy_version 120658 (0.0022) [2023-03-09 10:12:28,914][23090] Updated weights for policy 0, policy_version 120669 (0.0021) [2023-03-09 10:12:29,059][22664] Fps is (10 sec: 199880.3, 60 sec: 196607.0, 300 sec: 195330.4). Total num frames: 1977057280. Throughput: 0: 48995.8. Samples: 494228096. Policy #0 lag: (min: 2.0, avg: 18.7, max: 34.0) [2023-03-09 10:12:29,061][22664] Avg episode reward: [(0, '52.742')] [2023-03-09 10:12:29,899][23090] Updated weights for policy 0, policy_version 120679 (0.0018) [2023-03-09 10:12:30,675][23090] Updated weights for policy 0, policy_version 120689 (0.0018) [2023-03-09 10:12:31,501][23090] Updated weights for policy 0, policy_version 120699 (0.0017) [2023-03-09 10:12:32,405][23090] Updated weights for policy 0, policy_version 120709 (0.0014) [2023-03-09 10:12:33,211][23090] Updated weights for policy 0, policy_version 120719 (0.0026) [2023-03-09 10:12:33,217][22940] Signal inference workers to stop experience collection... (42100 times) [2023-03-09 10:12:33,243][22940] Signal inference workers to resume experience collection... (42100 times) [2023-03-09 10:12:33,306][23090] InferenceWorker_p0-w0: stopping experience collection (42100 times) [2023-03-09 10:12:33,309][23090] InferenceWorker_p0-w0: resuming experience collection (42100 times) [2023-03-09 10:12:33,991][23090] Updated weights for policy 0, policy_version 120729 (0.0013) [2023-03-09 10:12:34,058][22664] Fps is (10 sec: 196613.6, 60 sec: 196335.9, 300 sec: 195164.3). Total num frames: 1978023936. Throughput: 0: 48949.8. Samples: 494520832. Policy #0 lag: (min: 2.0, avg: 18.7, max: 34.0) [2023-03-09 10:12:34,059][22664] Avg episode reward: [(0, '52.648')] [2023-03-09 10:12:34,904][23090] Updated weights for policy 0, policy_version 120739 (0.0026) [2023-03-09 10:12:35,764][23090] Updated weights for policy 0, policy_version 120749 (0.0027) [2023-03-09 10:12:36,625][23090] Updated weights for policy 0, policy_version 120760 (0.0017) [2023-03-09 10:12:37,476][23090] Updated weights for policy 0, policy_version 120770 (0.0023) [2023-03-09 10:12:38,408][23090] Updated weights for policy 0, policy_version 120780 (0.0020) [2023-03-09 10:12:39,059][22664] Fps is (10 sec: 193336.2, 60 sec: 196061.6, 300 sec: 195164.0). Total num frames: 1978990592. Throughput: 0: 48952.1. Samples: 494815696. Policy #0 lag: (min: 2.0, avg: 18.7, max: 34.0) [2023-03-09 10:12:39,060][22664] Avg episode reward: [(0, '54.742')] [2023-03-09 10:12:39,158][23090] Updated weights for policy 0, policy_version 120790 (0.0018) [2023-03-09 10:12:39,851][23090] Updated weights for policy 0, policy_version 120800 (0.0016) [2023-03-09 10:12:40,830][23090] Updated weights for policy 0, policy_version 120810 (0.0016) [2023-03-09 10:12:41,621][23090] Updated weights for policy 0, policy_version 120820 (0.0017) [2023-03-09 10:12:41,885][22940] Signal inference workers to stop experience collection... (42150 times) [2023-03-09 10:12:41,886][22940] Signal inference workers to resume experience collection... (42150 times) [2023-03-09 10:12:41,963][23090] InferenceWorker_p0-w0: stopping experience collection (42150 times) [2023-03-09 10:12:41,964][23090] InferenceWorker_p0-w0: resuming experience collection (42150 times) [2023-03-09 10:12:42,432][23090] Updated weights for policy 0, policy_version 120830 (0.0017) [2023-03-09 10:12:43,364][23090] Updated weights for policy 0, policy_version 120840 (0.0021) [2023-03-09 10:12:44,059][22664] Fps is (10 sec: 194965.3, 60 sec: 195789.1, 300 sec: 195275.1). Total num frames: 1979973632. Throughput: 0: 48951.6. Samples: 494961056. Policy #0 lag: (min: 2.0, avg: 18.7, max: 34.0) [2023-03-09 10:12:44,061][22664] Avg episode reward: [(0, '57.541')] [2023-03-09 10:12:44,249][23090] Updated weights for policy 0, policy_version 120850 (0.0024) [2023-03-09 10:12:44,990][23090] Updated weights for policy 0, policy_version 120860 (0.0017) [2023-03-09 10:12:45,865][23090] Updated weights for policy 0, policy_version 120870 (0.0018) [2023-03-09 10:12:46,674][23090] Updated weights for policy 0, policy_version 120880 (0.0019) [2023-03-09 10:12:47,478][23090] Updated weights for policy 0, policy_version 120890 (0.0018) [2023-03-09 10:12:48,361][23090] Updated weights for policy 0, policy_version 120900 (0.0013) [2023-03-09 10:12:49,059][22664] Fps is (10 sec: 194964.4, 60 sec: 195241.8, 300 sec: 195219.5). Total num frames: 1980940288. Throughput: 0: 48952.0. Samples: 495255856. Policy #0 lag: (min: 2.0, avg: 18.7, max: 34.0) [2023-03-09 10:12:49,105][22664] Avg episode reward: [(0, '53.937')] [2023-03-09 10:12:49,224][23090] Updated weights for policy 0, policy_version 120910 (0.0016) [2023-03-09 10:12:49,953][23090] Updated weights for policy 0, policy_version 120920 (0.0022) [2023-03-09 10:12:50,494][22940] Signal inference workers to stop experience collection... (42200 times) [2023-03-09 10:12:50,495][22940] Signal inference workers to resume experience collection... (42200 times) [2023-03-09 10:12:50,567][23090] InferenceWorker_p0-w0: stopping experience collection (42200 times) [2023-03-09 10:12:50,568][23090] InferenceWorker_p0-w0: resuming experience collection (42200 times) [2023-03-09 10:12:50,856][23090] Updated weights for policy 0, policy_version 120930 (0.0019) [2023-03-09 10:12:51,798][23090] Updated weights for policy 0, policy_version 120940 (0.0017) [2023-03-09 10:12:52,539][23090] Updated weights for policy 0, policy_version 120950 (0.0021) [2023-03-09 10:12:53,236][23090] Updated weights for policy 0, policy_version 120960 (0.0015) [2023-03-09 10:12:54,059][22664] Fps is (10 sec: 196611.2, 60 sec: 195788.8, 300 sec: 195275.5). Total num frames: 1981939712. Throughput: 0: 48951.0. Samples: 495550640. Policy #0 lag: (min: 2.0, avg: 18.7, max: 34.0) [2023-03-09 10:12:54,060][22664] Avg episode reward: [(0, '55.298')] [2023-03-09 10:12:54,198][23090] Updated weights for policy 0, policy_version 120970 (0.0013) [2023-03-09 10:12:54,984][23090] Updated weights for policy 0, policy_version 120980 (0.0015) [2023-03-09 10:12:55,833][23090] Updated weights for policy 0, policy_version 120991 (0.0019) [2023-03-09 10:12:56,771][23090] Updated weights for policy 0, policy_version 121001 (0.0018) [2023-03-09 10:12:57,612][23090] Updated weights for policy 0, policy_version 121011 (0.0016) [2023-03-09 10:12:58,389][23090] Updated weights for policy 0, policy_version 121021 (0.0023) [2023-03-09 10:12:59,059][22664] Fps is (10 sec: 198250.7, 60 sec: 195788.5, 300 sec: 195275.0). Total num frames: 1982922752. Throughput: 0: 48950.5. Samples: 495695952. Policy #0 lag: (min: 2.0, avg: 17.9, max: 33.0) [2023-03-09 10:12:59,060][22664] Avg episode reward: [(0, '54.910')] [2023-03-09 10:12:59,303][23090] Updated weights for policy 0, policy_version 121031 (0.0019) [2023-03-09 10:13:00,110][23090] Updated weights for policy 0, policy_version 121041 (0.0017) [2023-03-09 10:13:00,924][23090] Updated weights for policy 0, policy_version 121051 (0.0019) [2023-03-09 10:13:01,059][22940] Signal inference workers to stop experience collection... (42250 times) [2023-03-09 10:13:01,060][22940] Signal inference workers to resume experience collection... (42250 times) [2023-03-09 10:13:01,124][23090] InferenceWorker_p0-w0: stopping experience collection (42250 times) [2023-03-09 10:13:01,124][23090] InferenceWorker_p0-w0: resuming experience collection (42250 times) [2023-03-09 10:13:01,816][23090] Updated weights for policy 0, policy_version 121061 (0.0016) [2023-03-09 10:13:02,606][23090] Updated weights for policy 0, policy_version 121071 (0.0013) [2023-03-09 10:13:03,378][23090] Updated weights for policy 0, policy_version 121081 (0.0017) [2023-03-09 10:13:04,058][22664] Fps is (10 sec: 196608.3, 60 sec: 195789.2, 300 sec: 195275.2). Total num frames: 1983905792. Throughput: 0: 49039.4. Samples: 495990720. Policy #0 lag: (min: 2.0, avg: 17.9, max: 33.0) [2023-03-09 10:13:04,060][22664] Avg episode reward: [(0, '54.602')] [2023-03-09 10:13:04,285][23090] Updated weights for policy 0, policy_version 121091 (0.0013) [2023-03-09 10:13:05,212][23090] Updated weights for policy 0, policy_version 121101 (0.0016) [2023-03-09 10:13:05,913][23090] Updated weights for policy 0, policy_version 121111 (0.0013) [2023-03-09 10:13:06,768][23090] Updated weights for policy 0, policy_version 121121 (0.0017) [2023-03-09 10:13:07,784][23090] Updated weights for policy 0, policy_version 121132 (0.0013) [2023-03-09 10:13:08,536][23090] Updated weights for policy 0, policy_version 121142 (0.0020) [2023-03-09 10:13:09,059][22664] Fps is (10 sec: 196605.1, 60 sec: 196061.9, 300 sec: 195219.5). Total num frames: 1984888832. Throughput: 0: 49042.1. Samples: 496285568. Policy #0 lag: (min: 2.0, avg: 17.9, max: 33.0) [2023-03-09 10:13:09,060][22664] Avg episode reward: [(0, '57.408')] [2023-03-09 10:13:09,304][23090] Updated weights for policy 0, policy_version 121152 (0.0017) [2023-03-09 10:13:10,266][23090] Updated weights for policy 0, policy_version 121162 (0.0020) [2023-03-09 10:13:11,033][23090] Updated weights for policy 0, policy_version 121172 (0.0014) [2023-03-09 10:13:11,176][22940] Signal inference workers to stop experience collection... (42300 times) [2023-03-09 10:13:11,198][22940] Signal inference workers to resume experience collection... (42300 times) [2023-03-09 10:13:11,233][23090] InferenceWorker_p0-w0: stopping experience collection (42300 times) [2023-03-09 10:13:11,278][23090] InferenceWorker_p0-w0: resuming experience collection (42300 times) [2023-03-09 10:13:11,805][23090] Updated weights for policy 0, policy_version 121182 (0.0017) [2023-03-09 10:13:12,722][23090] Updated weights for policy 0, policy_version 121192 (0.0016) [2023-03-09 10:13:13,598][23090] Updated weights for policy 0, policy_version 121203 (0.0020) [2023-03-09 10:13:14,059][22664] Fps is (10 sec: 198238.9, 60 sec: 196608.4, 300 sec: 195219.4). Total num frames: 1985888256. Throughput: 0: 48998.0. Samples: 496433008. Policy #0 lag: (min: 2.0, avg: 17.9, max: 33.0) [2023-03-09 10:13:14,061][22664] Avg episode reward: [(0, '53.934')] [2023-03-09 10:13:14,385][23090] Updated weights for policy 0, policy_version 121213 (0.0018) [2023-03-09 10:13:15,322][23090] Updated weights for policy 0, policy_version 121223 (0.0016) [2023-03-09 10:13:16,166][23090] Updated weights for policy 0, policy_version 121233 (0.0016) [2023-03-09 10:13:16,950][23090] Updated weights for policy 0, policy_version 121243 (0.0013) [2023-03-09 10:13:17,831][23090] Updated weights for policy 0, policy_version 121253 (0.0013) [2023-03-09 10:13:18,615][23090] Updated weights for policy 0, policy_version 121263 (0.0013) [2023-03-09 10:13:19,059][22664] Fps is (10 sec: 196610.1, 60 sec: 196607.8, 300 sec: 195163.9). Total num frames: 1986854912. Throughput: 0: 49088.1. Samples: 496729808. Policy #0 lag: (min: 2.0, avg: 17.9, max: 33.0) [2023-03-09 10:13:19,060][22664] Avg episode reward: [(0, '55.481')] [2023-03-09 10:13:19,064][22940] Saving /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000121268_1986854912.pth... [2023-03-09 10:13:19,131][22940] Removing /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000118402_1939898368.pth [2023-03-09 10:13:19,426][23090] Updated weights for policy 0, policy_version 121273 (0.0013) [2023-03-09 10:13:20,277][23090] Updated weights for policy 0, policy_version 121283 (0.0016) [2023-03-09 10:13:21,164][23090] Updated weights for policy 0, policy_version 121293 (0.0017) [2023-03-09 10:13:21,502][22940] Signal inference workers to stop experience collection... (42350 times) [2023-03-09 10:13:21,503][22940] Signal inference workers to resume experience collection... (42350 times) [2023-03-09 10:13:21,569][23090] InferenceWorker_p0-w0: stopping experience collection (42350 times) [2023-03-09 10:13:21,570][23090] InferenceWorker_p0-w0: resuming experience collection (42350 times) [2023-03-09 10:13:21,916][23090] Updated weights for policy 0, policy_version 121303 (0.0015) [2023-03-09 10:13:22,790][23090] Updated weights for policy 0, policy_version 121313 (0.0019) [2023-03-09 10:13:23,739][23090] Updated weights for policy 0, policy_version 121323 (0.0018) [2023-03-09 10:13:24,058][22664] Fps is (10 sec: 193338.8, 60 sec: 196062.7, 300 sec: 195219.6). Total num frames: 1987821568. Throughput: 0: 49041.9. Samples: 497022576. Policy #0 lag: (min: 2.0, avg: 17.9, max: 33.0) [2023-03-09 10:13:24,059][22664] Avg episode reward: [(0, '57.628')] [2023-03-09 10:13:24,555][23090] Updated weights for policy 0, policy_version 121334 (0.0016) [2023-03-09 10:13:25,261][23090] Updated weights for policy 0, policy_version 121344 (0.0018) [2023-03-09 10:13:26,246][23090] Updated weights for policy 0, policy_version 121354 (0.0016) [2023-03-09 10:13:27,053][23090] Updated weights for policy 0, policy_version 121364 (0.0013) [2023-03-09 10:13:27,837][23090] Updated weights for policy 0, policy_version 121374 (0.0019) [2023-03-09 10:13:28,700][23090] Updated weights for policy 0, policy_version 121384 (0.0012) [2023-03-09 10:13:29,059][22664] Fps is (10 sec: 194971.3, 60 sec: 195789.6, 300 sec: 195275.1). Total num frames: 1988804608. Throughput: 0: 49087.4. Samples: 497169984. Policy #0 lag: (min: 2.0, avg: 17.9, max: 33.0) [2023-03-09 10:13:29,060][22664] Avg episode reward: [(0, '53.111')] [2023-03-09 10:13:29,603][23090] Updated weights for policy 0, policy_version 121395 (0.0016) [2023-03-09 10:13:30,424][23090] Updated weights for policy 0, policy_version 121405 (0.0017) [2023-03-09 10:13:31,313][23090] Updated weights for policy 0, policy_version 121415 (0.0013) [2023-03-09 10:13:31,823][22940] Signal inference workers to stop experience collection... (42400 times) [2023-03-09 10:13:31,824][22940] Signal inference workers to resume experience collection... (42400 times) [2023-03-09 10:13:31,898][23090] InferenceWorker_p0-w0: stopping experience collection (42400 times) [2023-03-09 10:13:31,901][23090] InferenceWorker_p0-w0: resuming experience collection (42400 times) [2023-03-09 10:13:32,188][23090] Updated weights for policy 0, policy_version 121425 (0.0019) [2023-03-09 10:13:32,917][23090] Updated weights for policy 0, policy_version 121435 (0.0022) [2023-03-09 10:13:33,829][23090] Updated weights for policy 0, policy_version 121445 (0.0016) [2023-03-09 10:13:34,058][22664] Fps is (10 sec: 198246.9, 60 sec: 196334.9, 300 sec: 195441.8). Total num frames: 1989804032. Throughput: 0: 49179.1. Samples: 497468896. Policy #0 lag: (min: 2.0, avg: 17.9, max: 33.0) [2023-03-09 10:13:34,059][22664] Avg episode reward: [(0, '53.046')] [2023-03-09 10:13:34,649][23090] Updated weights for policy 0, policy_version 121455 (0.0020) [2023-03-09 10:13:35,390][23090] Updated weights for policy 0, policy_version 121465 (0.0013) [2023-03-09 10:13:36,272][23090] Updated weights for policy 0, policy_version 121475 (0.0013) [2023-03-09 10:13:37,134][23090] Updated weights for policy 0, policy_version 121485 (0.0016) [2023-03-09 10:13:37,982][23090] Updated weights for policy 0, policy_version 121496 (0.0013) [2023-03-09 10:13:38,863][23090] Updated weights for policy 0, policy_version 121506 (0.0019) [2023-03-09 10:13:39,059][22664] Fps is (10 sec: 198244.9, 60 sec: 196607.7, 300 sec: 195497.1). Total num frames: 1990787072. Throughput: 0: 49133.7. Samples: 497761664. Policy #0 lag: (min: 2.0, avg: 17.9, max: 33.0) [2023-03-09 10:13:39,060][22664] Avg episode reward: [(0, '54.923')] [2023-03-09 10:13:39,793][23090] Updated weights for policy 0, policy_version 121516 (0.0016) [2023-03-09 10:13:40,539][23090] Updated weights for policy 0, policy_version 121526 (0.0020) [2023-03-09 10:13:41,270][23090] Updated weights for policy 0, policy_version 121536 (0.0019) [2023-03-09 10:13:42,212][23090] Updated weights for policy 0, policy_version 121546 (0.0017) [2023-03-09 10:13:43,056][23090] Updated weights for policy 0, policy_version 121556 (0.0013) [2023-03-09 10:13:43,162][22940] Signal inference workers to stop experience collection... (42450 times) [2023-03-09 10:13:43,164][22940] Signal inference workers to resume experience collection... (42450 times) [2023-03-09 10:13:43,226][23090] InferenceWorker_p0-w0: stopping experience collection (42450 times) [2023-03-09 10:13:43,226][23090] InferenceWorker_p0-w0: resuming experience collection (42450 times) [2023-03-09 10:13:43,808][23090] Updated weights for policy 0, policy_version 121566 (0.0016) [2023-03-09 10:13:44,059][22664] Fps is (10 sec: 196601.8, 60 sec: 196607.7, 300 sec: 195497.0). Total num frames: 1991770112. Throughput: 0: 49134.8. Samples: 497907024. Policy #0 lag: (min: 2.0, avg: 17.9, max: 33.0) [2023-03-09 10:13:44,061][22664] Avg episode reward: [(0, '55.519')] [2023-03-09 10:13:44,726][23090] Updated weights for policy 0, policy_version 121576 (0.0013) [2023-03-09 10:13:45,579][23090] Updated weights for policy 0, policy_version 121586 (0.0013) [2023-03-09 10:13:46,359][23090] Updated weights for policy 0, policy_version 121596 (0.0016) [2023-03-09 10:13:47,274][23090] Updated weights for policy 0, policy_version 121606 (0.0016) [2023-03-09 10:13:48,010][23090] Updated weights for policy 0, policy_version 121616 (0.0032) [2023-03-09 10:13:48,947][23090] Updated weights for policy 0, policy_version 121627 (0.0014) [2023-03-09 10:13:49,059][22664] Fps is (10 sec: 198247.0, 60 sec: 197154.8, 300 sec: 195608.4). Total num frames: 1992769536. Throughput: 0: 49180.0. Samples: 498203824. Policy #0 lag: (min: 2.0, avg: 17.9, max: 33.0) [2023-03-09 10:13:49,060][22664] Avg episode reward: [(0, '53.882')] [2023-03-09 10:13:49,873][23090] Updated weights for policy 0, policy_version 121637 (0.0023) [2023-03-09 10:13:50,631][23090] Updated weights for policy 0, policy_version 121647 (0.0016) [2023-03-09 10:13:51,428][23090] Updated weights for policy 0, policy_version 121657 (0.0017) [2023-03-09 10:13:52,298][23090] Updated weights for policy 0, policy_version 121667 (0.0019) [2023-03-09 10:13:53,184][23090] Updated weights for policy 0, policy_version 121677 (0.0019) [2023-03-09 10:13:53,941][23090] Updated weights for policy 0, policy_version 121687 (0.0013) [2023-03-09 10:13:54,059][22664] Fps is (10 sec: 196613.4, 60 sec: 196608.1, 300 sec: 195664.4). Total num frames: 1993736192. Throughput: 0: 49134.1. Samples: 498496592. Policy #0 lag: (min: 2.0, avg: 17.9, max: 33.0) [2023-03-09 10:13:54,060][22664] Avg episode reward: [(0, '55.527')] [2023-03-09 10:13:54,461][22940] Signal inference workers to stop experience collection... (42500 times) [2023-03-09 10:13:54,463][22940] Signal inference workers to resume experience collection... (42500 times) [2023-03-09 10:13:54,515][23090] InferenceWorker_p0-w0: stopping experience collection (42500 times) [2023-03-09 10:13:54,558][23090] InferenceWorker_p0-w0: resuming experience collection (42500 times) [2023-03-09 10:13:54,847][23090] Updated weights for policy 0, policy_version 121697 (0.0016) [2023-03-09 10:13:55,765][23090] Updated weights for policy 0, policy_version 121707 (0.0017) [2023-03-09 10:13:56,558][23090] Updated weights for policy 0, policy_version 121717 (0.0016) [2023-03-09 10:13:57,274][23090] Updated weights for policy 0, policy_version 121727 (0.0019) [2023-03-09 10:13:58,203][23090] Updated weights for policy 0, policy_version 121737 (0.0015) [2023-03-09 10:13:59,059][22664] Fps is (10 sec: 193316.5, 60 sec: 196332.4, 300 sec: 195663.4). Total num frames: 1994702848. Throughput: 0: 49086.8. Samples: 498641936. Policy #0 lag: (min: 2.0, avg: 18.1, max: 34.0) [2023-03-09 10:13:59,058][23090] Updated weights for policy 0, policy_version 121747 (0.0013) [2023-03-09 10:13:59,061][22664] Avg episode reward: [(0, '54.954')] [2023-03-09 10:13:59,852][23090] Updated weights for policy 0, policy_version 121757 (0.0016) [2023-03-09 10:14:00,762][23090] Updated weights for policy 0, policy_version 121767 (0.0013) [2023-03-09 10:14:01,688][23090] Updated weights for policy 0, policy_version 121778 (0.0013) [2023-03-09 10:14:02,516][23090] Updated weights for policy 0, policy_version 121788 (0.0025) [2023-03-09 10:14:03,402][23090] Updated weights for policy 0, policy_version 121798 (0.0017) [2023-03-09 10:14:04,059][22664] Fps is (10 sec: 193324.1, 60 sec: 196060.7, 300 sec: 195663.9). Total num frames: 1995669504. Throughput: 0: 48998.2. Samples: 498934736. Policy #0 lag: (min: 2.0, avg: 18.1, max: 34.0) [2023-03-09 10:14:04,061][22664] Avg episode reward: [(0, '56.127')] [2023-03-09 10:14:04,206][23090] Updated weights for policy 0, policy_version 121808 (0.0013) [2023-03-09 10:14:04,384][22940] Signal inference workers to stop experience collection... (42550 times) [2023-03-09 10:14:04,386][22940] Signal inference workers to resume experience collection... (42550 times) [2023-03-09 10:14:04,453][23090] InferenceWorker_p0-w0: stopping experience collection (42550 times) [2023-03-09 10:14:04,454][23090] InferenceWorker_p0-w0: resuming experience collection (42550 times) [2023-03-09 10:14:05,070][23090] Updated weights for policy 0, policy_version 121818 (0.0017) [2023-03-09 10:14:05,812][23090] Updated weights for policy 0, policy_version 121828 (0.0026) [2023-03-09 10:14:06,673][23090] Updated weights for policy 0, policy_version 121838 (0.0022) [2023-03-09 10:14:07,461][23090] Updated weights for policy 0, policy_version 121848 (0.0017) [2023-03-09 10:14:08,328][23090] Updated weights for policy 0, policy_version 121858 (0.0013) [2023-03-09 10:14:09,059][22664] Fps is (10 sec: 194986.3, 60 sec: 196062.7, 300 sec: 195775.0). Total num frames: 1996652544. Throughput: 0: 49044.6. Samples: 499229584. Policy #0 lag: (min: 2.0, avg: 18.1, max: 34.0) [2023-03-09 10:14:09,059][22664] Avg episode reward: [(0, '56.040')] [2023-03-09 10:14:09,263][23090] Updated weights for policy 0, policy_version 121868 (0.0017) [2023-03-09 10:14:10,013][23090] Updated weights for policy 0, policy_version 121878 (0.0021) [2023-03-09 10:14:10,777][23090] Updated weights for policy 0, policy_version 121888 (0.0013) [2023-03-09 10:14:11,681][23090] Updated weights for policy 0, policy_version 121898 (0.0013) [2023-03-09 10:14:12,540][23090] Updated weights for policy 0, policy_version 121908 (0.0019) [2023-03-09 10:14:13,365][23090] Updated weights for policy 0, policy_version 121918 (0.0013) [2023-03-09 10:14:14,059][22664] Fps is (10 sec: 194962.3, 60 sec: 195514.6, 300 sec: 195718.9). Total num frames: 1997619200. Throughput: 0: 48998.7. Samples: 499374960. Policy #0 lag: (min: 2.0, avg: 18.1, max: 34.0) [2023-03-09 10:14:14,062][22664] Avg episode reward: [(0, '54.233')] [2023-03-09 10:14:14,223][23090] Updated weights for policy 0, policy_version 121928 (0.0016) [2023-03-09 10:14:14,601][22940] Signal inference workers to stop experience collection... (42600 times) [2023-03-09 10:14:14,602][22940] Signal inference workers to resume experience collection... (42600 times) [2023-03-09 10:14:14,676][23090] InferenceWorker_p0-w0: stopping experience collection (42600 times) [2023-03-09 10:14:14,718][23090] InferenceWorker_p0-w0: resuming experience collection (42600 times) [2023-03-09 10:14:15,118][23090] Updated weights for policy 0, policy_version 121938 (0.0017) [2023-03-09 10:14:15,877][23090] Updated weights for policy 0, policy_version 121948 (0.0017) [2023-03-09 10:14:16,806][23090] Updated weights for policy 0, policy_version 121958 (0.0013) [2023-03-09 10:14:17,585][23090] Updated weights for policy 0, policy_version 121968 (0.0013) [2023-03-09 10:14:18,488][23090] Updated weights for policy 0, policy_version 121978 (0.0029) [2023-03-09 10:14:19,058][22664] Fps is (10 sec: 194970.5, 60 sec: 195789.4, 300 sec: 195719.6). Total num frames: 1998602240. Throughput: 0: 48864.3. Samples: 499667792. Policy #0 lag: (min: 2.0, avg: 18.1, max: 34.0) [2023-03-09 10:14:19,059][22664] Avg episode reward: [(0, '55.119')] [2023-03-09 10:14:19,271][23090] Updated weights for policy 0, policy_version 121988 (0.0016) [2023-03-09 10:14:20,113][23090] Updated weights for policy 0, policy_version 121998 (0.0013) [2023-03-09 10:14:20,865][23090] Updated weights for policy 0, policy_version 122008 (0.0018) [2023-03-09 10:14:21,736][23090] Updated weights for policy 0, policy_version 122018 (0.0021) [2023-03-09 10:14:22,715][23090] Updated weights for policy 0, policy_version 122028 (0.0020) [2023-03-09 10:14:23,484][23090] Updated weights for policy 0, policy_version 122039 (0.0016) [2023-03-09 10:14:23,983][22940] Signal inference workers to stop experience collection... (42650 times) [2023-03-09 10:14:23,985][22940] Signal inference workers to resume experience collection... (42650 times) [2023-03-09 10:14:24,014][23090] InferenceWorker_p0-w0: stopping experience collection (42650 times) [2023-03-09 10:14:24,014][23090] InferenceWorker_p0-w0: resuming experience collection (42650 times) [2023-03-09 10:14:24,058][22664] Fps is (10 sec: 198261.6, 60 sec: 196335.0, 300 sec: 195941.7). Total num frames: 1999601664. Throughput: 0: 48864.9. Samples: 499960576. Policy #0 lag: (min: 2.0, avg: 18.1, max: 34.0) [2023-03-09 10:14:24,059][22664] Avg episode reward: [(0, '56.177')] [2023-03-09 10:14:24,345][23090] Updated weights for policy 0, policy_version 122049 (0.0013) [2023-03-09 10:14:25,252][23090] Updated weights for policy 0, policy_version 122059 (0.0020) [2023-03-09 10:14:26,028][23090] Updated weights for policy 0, policy_version 122069 (0.0016) [2023-03-09 10:14:26,225][22940] Saving /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000122072_2000027648.pth... [2023-03-09 10:14:26,275][22940] Stopping Batcher_0... [2023-03-09 10:14:26,276][22940] Loop batcher_evt_loop terminating... [2023-03-09 10:14:26,276][22664] Component Batcher_0 stopped! [2023-03-09 10:14:26,293][23090] Weights refcount: 2 0 [2023-03-09 10:14:26,354][23090] Stopping InferenceWorker_p0-w0... [2023-03-09 10:14:26,355][23090] Loop inference_proc0-0_evt_loop terminating... [2023-03-09 10:14:26,375][22940] Removing /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000119834_1963360256.pth [2023-03-09 10:14:26,382][22940] Saving /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000122072_2000027648.pth... [2023-03-09 10:14:26,384][22664] Component InferenceWorker_p0-w0 stopped! [2023-03-09 10:14:26,526][22664] Component LearnerWorker_p0 stopped! [2023-03-09 10:14:26,502][22940] Stopping LearnerWorker_p0... [2023-03-09 10:14:26,580][22940] Loop learner_proc0_evt_loop terminating... [2023-03-09 10:14:28,326][23234] Stopping RolloutWorker_w58... [2023-03-09 10:14:28,327][23234] Loop rollout_proc58_evt_loop terminating... [2023-03-09 10:14:28,329][22664] Component RolloutWorker_w58 stopped! [2023-03-09 10:14:28,378][24120] Stopping RolloutWorker_w97... [2023-03-09 10:14:28,378][23217] Stopping RolloutWorker_w86... [2023-03-09 10:14:28,378][24120] Loop rollout_proc97_evt_loop terminating... [2023-03-09 10:14:28,378][23217] Loop rollout_proc86_evt_loop terminating... [2023-03-09 10:14:28,379][23096] Stopping RolloutWorker_w23... [2023-03-09 10:14:28,380][23096] Loop rollout_proc23_evt_loop terminating... [2023-03-09 10:14:28,380][23865] Stopping RolloutWorker_w102... [2023-03-09 10:14:28,380][23185] Stopping RolloutWorker_w45... [2023-03-09 10:14:28,380][23169] Stopping RolloutWorker_w44... [2023-03-09 10:14:28,380][23202] Stopping RolloutWorker_w43... [2023-03-09 10:14:28,381][23865] Loop rollout_proc102_evt_loop terminating... [2023-03-09 10:14:28,381][23169] Loop rollout_proc44_evt_loop terminating... [2023-03-09 10:14:28,381][23185] Loop rollout_proc45_evt_loop terminating... [2023-03-09 10:14:28,380][23093] Stopping RolloutWorker_w17... [2023-03-09 10:14:28,381][23202] Loop rollout_proc43_evt_loop terminating... [2023-03-09 10:14:28,381][23093] Loop rollout_proc17_evt_loop terminating... [2023-03-09 10:14:28,381][23094] Stopping RolloutWorker_w20... [2023-03-09 10:14:28,381][23094] Loop rollout_proc20_evt_loop terminating... [2023-03-09 10:14:28,381][23092] Stopping RolloutWorker_w14... [2023-03-09 10:14:28,381][23092] Loop rollout_proc14_evt_loop terminating... [2023-03-09 10:14:28,381][23183] Stopping RolloutWorker_w42... [2023-03-09 10:14:28,381][23961] Stopping RolloutWorker_w120... [2023-03-09 10:14:28,381][24818] Stopping RolloutWorker_w115... [2023-03-09 10:14:28,381][23207] Stopping RolloutWorker_w62... [2023-03-09 10:14:28,382][23197] Stopping RolloutWorker_w37... [2023-03-09 10:14:28,382][23193] Stopping RolloutWorker_w22... [2023-03-09 10:14:28,382][23183] Loop rollout_proc42_evt_loop terminating... [2023-03-09 10:14:28,382][23961] Loop rollout_proc120_evt_loop terminating... [2023-03-09 10:14:28,382][23197] Loop rollout_proc37_evt_loop terminating... [2023-03-09 10:14:28,382][24818] Loop rollout_proc115_evt_loop terminating... [2023-03-09 10:14:28,382][23207] Loop rollout_proc62_evt_loop terminating... [2023-03-09 10:14:28,382][23193] Loop rollout_proc22_evt_loop terminating... [2023-03-09 10:14:28,382][23172] Stopping RolloutWorker_w9... [2023-03-09 10:14:28,383][23227] Stopping RolloutWorker_w81... [2023-03-09 10:14:28,383][23172] Loop rollout_proc9_evt_loop terminating... [2023-03-09 10:14:28,383][23485] Stopping RolloutWorker_w110... [2023-03-09 10:14:28,383][23243] Stopping RolloutWorker_w82... [2023-03-09 10:14:28,383][23227] Loop rollout_proc81_evt_loop terminating... [2023-03-09 10:14:28,383][23485] Loop rollout_proc110_evt_loop terminating... [2023-03-09 10:14:28,383][23243] Loop rollout_proc82_evt_loop terminating... [2023-03-09 10:14:28,387][23181] Stopping RolloutWorker_w39... [2023-03-09 10:14:28,387][23089] Stopping RolloutWorker_w8... [2023-03-09 10:14:28,387][23103] Stopping RolloutWorker_w38... [2023-03-09 10:14:28,387][23637] Stopping RolloutWorker_w96... [2023-03-09 10:14:28,387][24025] Stopping RolloutWorker_w114... [2023-03-09 10:14:28,387][23211] Stopping RolloutWorker_w74... [2023-03-09 10:14:28,387][23091] Stopping RolloutWorker_w11... [2023-03-09 10:14:28,387][33428] Stopping RolloutWorker_w1... [2023-03-09 10:14:28,387][23194] Stopping RolloutWorker_w25... [2023-03-09 10:14:28,387][23233] Stopping RolloutWorker_w78... [2023-03-09 10:14:28,387][24793] Stopping RolloutWorker_w121... [2023-03-09 10:14:28,387][23181] Loop rollout_proc39_evt_loop terminating... [2023-03-09 10:14:28,387][23089] Loop rollout_proc8_evt_loop terminating... [2023-03-09 10:14:28,387][23637] Loop rollout_proc96_evt_loop terminating... [2023-03-09 10:14:28,387][23103] Loop rollout_proc38_evt_loop terminating... [2023-03-09 10:14:28,387][24025] Loop rollout_proc114_evt_loop terminating... [2023-03-09 10:14:28,387][23091] Loop rollout_proc11_evt_loop terminating... [2023-03-09 10:14:28,387][33428] Loop rollout_proc1_evt_loop terminating... [2023-03-09 10:14:28,387][23211] Loop rollout_proc74_evt_loop terminating... [2023-03-09 10:14:28,388][24793] Loop rollout_proc121_evt_loop terminating... [2023-03-09 10:14:28,388][23233] Loop rollout_proc78_evt_loop terminating... [2023-03-09 10:14:28,387][23194] Loop rollout_proc25_evt_loop terminating... [2023-03-09 10:14:28,385][22664] Component RolloutWorker_w101 stopped! [2023-03-09 10:14:28,391][22664] Component RolloutWorker_w97 stopped! [2023-03-09 10:14:28,398][22664] Component RolloutWorker_w86 stopped! [2023-03-09 10:14:28,402][22664] Component RolloutWorker_w23 stopped! [2023-03-09 10:14:28,403][22664] Component RolloutWorker_w17 stopped! [2023-03-09 10:14:28,404][22664] Component RolloutWorker_w102 stopped! [2023-03-09 10:14:28,409][22664] Component RolloutWorker_w45 stopped! [2023-03-09 10:14:28,410][22664] Component RolloutWorker_w44 stopped! [2023-03-09 10:14:28,411][22664] Component RolloutWorker_w43 stopped! [2023-03-09 10:14:28,412][22664] Component RolloutWorker_w20 stopped! [2023-03-09 10:14:28,413][22664] Component RolloutWorker_w14 stopped! [2023-03-09 10:14:28,415][23189] Stopping RolloutWorker_w16... [2023-03-09 10:14:28,415][23189] Loop rollout_proc16_evt_loop terminating... [2023-03-09 10:14:28,378][23314] Stopping RolloutWorker_w101... [2023-03-09 10:14:28,414][22664] Component RolloutWorker_w42 stopped! [2023-03-09 10:14:28,417][22664] Component RolloutWorker_w62 stopped! [2023-03-09 10:14:28,418][22664] Component RolloutWorker_w120 stopped! [2023-03-09 10:14:28,423][23179] Stopping RolloutWorker_w33... [2023-03-09 10:14:28,423][23230] Stopping RolloutWorker_w52... [2023-03-09 10:14:28,424][23179] Loop rollout_proc33_evt_loop terminating... [2023-03-09 10:14:28,424][23230] Loop rollout_proc52_evt_loop terminating... [2023-03-09 10:14:28,424][23182] Stopping RolloutWorker_w36... [2023-03-09 10:14:28,424][23182] Loop rollout_proc36_evt_loop terminating... [2023-03-09 10:14:28,424][23098] Stopping RolloutWorker_w32... [2023-03-09 10:14:28,424][23232] Stopping RolloutWorker_w49... [2023-03-09 10:14:28,425][23098] Loop rollout_proc32_evt_loop terminating... [2023-03-09 10:14:28,425][23232] Loop rollout_proc49_evt_loop terminating... [2023-03-09 10:14:28,425][23206] Stopping RolloutWorker_w65... [2023-03-09 10:14:28,425][23239] Stopping RolloutWorker_w88... [2023-03-09 10:14:28,425][23244] Stopping RolloutWorker_w76... [2023-03-09 10:14:28,425][23636] Stopping RolloutWorker_w122... [2023-03-09 10:14:28,425][23657] Stopping RolloutWorker_w93... [2023-03-09 10:14:28,425][23231] Stopping RolloutWorker_w60... [2023-03-09 10:14:28,425][23204] Stopping RolloutWorker_w56... [2023-03-09 10:14:28,423][22664] Component RolloutWorker_w115 stopped! [2023-03-09 10:14:28,425][23239] Loop rollout_proc88_evt_loop terminating... [2023-03-09 10:14:28,425][23206] Loop rollout_proc65_evt_loop terminating... [2023-03-09 10:14:28,425][23244] Loop rollout_proc76_evt_loop terminating... [2023-03-09 10:14:28,425][23657] Loop rollout_proc93_evt_loop terminating... [2023-03-09 10:14:28,425][23636] Loop rollout_proc122_evt_loop terminating... [2023-03-09 10:14:28,425][23231] Loop rollout_proc60_evt_loop terminating... [2023-03-09 10:14:28,425][23204] Loop rollout_proc56_evt_loop terminating... [2023-03-09 10:14:28,425][23867] Stopping RolloutWorker_w117... [2023-03-09 10:14:28,425][23201] Stopping RolloutWorker_w50... [2023-03-09 10:14:28,426][23867] Loop rollout_proc117_evt_loop terminating... [2023-03-09 10:14:28,426][23201] Loop rollout_proc50_evt_loop terminating... [2023-03-09 10:14:28,427][23177] Stopping RolloutWorker_w27... [2023-03-09 10:14:28,427][24156] Stopping RolloutWorker_w103... [2023-03-09 10:14:28,427][23177] Loop rollout_proc27_evt_loop terminating... [2023-03-09 10:14:28,427][23823] Stopping RolloutWorker_w105... [2023-03-09 10:14:28,428][24156] Loop rollout_proc103_evt_loop terminating... [2023-03-09 10:14:28,428][23212] Stopping RolloutWorker_w77... [2023-03-09 10:14:28,428][23441] Stopping RolloutWorker_w107... [2023-03-09 10:14:28,428][23823] Loop rollout_proc105_evt_loop terminating... [2023-03-09 10:14:28,428][23174] Stopping RolloutWorker_w15... [2023-03-09 10:14:28,428][23097] Stopping RolloutWorker_w29... [2023-03-09 10:14:28,428][23623] Stopping RolloutWorker_w116... [2023-03-09 10:14:28,428][23178] Stopping RolloutWorker_w24... [2023-03-09 10:14:28,428][23226] Stopping RolloutWorker_w87... [2023-03-09 10:14:28,428][32460] Stopping RolloutWorker_w0... [2023-03-09 10:14:28,428][23237] Stopping RolloutWorker_w73... [2023-03-09 10:14:28,428][24666] Stopping RolloutWorker_w127... [2023-03-09 10:14:28,428][23212] Loop rollout_proc77_evt_loop terminating... [2023-03-09 10:14:28,428][23441] Loop rollout_proc107_evt_loop terminating... [2023-03-09 10:14:28,428][23174] Loop rollout_proc15_evt_loop terminating... [2023-03-09 10:14:28,428][23097] Loop rollout_proc29_evt_loop terminating... [2023-03-09 10:14:28,428][23623] Loop rollout_proc116_evt_loop terminating... [2023-03-09 10:14:28,428][23178] Loop rollout_proc24_evt_loop terminating... [2023-03-09 10:14:28,428][23226] Loop rollout_proc87_evt_loop terminating... [2023-03-09 10:14:28,428][32460] Loop rollout_proc0_evt_loop terminating... [2023-03-09 10:14:28,428][23222] Stopping RolloutWorker_w72... [2023-03-09 10:14:28,428][24666] Loop rollout_proc127_evt_loop terminating... [2023-03-09 10:14:28,428][23221] Stopping RolloutWorker_w84... [2023-03-09 10:14:28,428][23237] Loop rollout_proc73_evt_loop terminating... [2023-03-09 10:14:28,428][24121] Stopping RolloutWorker_w94... [2023-03-09 10:14:28,428][23228] Stopping RolloutWorker_w54... [2023-03-09 10:14:28,428][24434] Stopping RolloutWorker_w100... [2023-03-09 10:14:28,428][23240] Stopping RolloutWorker_w64... [2023-03-09 10:14:28,428][23216] Stopping RolloutWorker_w51... [2023-03-09 10:14:28,428][23247] Stopping RolloutWorker_w91... [2023-03-09 10:14:28,428][23173] Stopping RolloutWorker_w12... [2023-03-09 10:14:28,428][24858] Stopping RolloutWorker_w124... [2023-03-09 10:14:28,428][23190] Stopping RolloutWorker_w13... [2023-03-09 10:14:28,428][23186] Stopping RolloutWorker_w4... [2023-03-09 10:14:28,428][23188] Stopping RolloutWorker_w10... [2023-03-09 10:14:28,428][23866] Stopping RolloutWorker_w111... [2023-03-09 10:14:28,428][23525] Stopping RolloutWorker_w104... [2023-03-09 10:14:28,428][23817] Stopping RolloutWorker_w108... [2023-03-09 10:14:28,428][23191] Stopping RolloutWorker_w19... [2023-03-09 10:14:28,428][23213] Stopping RolloutWorker_w80... [2023-03-09 10:14:28,428][23203] Stopping RolloutWorker_w40... [2023-03-09 10:14:28,428][23634] Stopping RolloutWorker_w113... [2023-03-09 10:14:28,428][23088] Stopping RolloutWorker_w5... [2023-03-09 10:14:28,429][23222] Loop rollout_proc72_evt_loop terminating... [2023-03-09 10:14:28,429][23221] Loop rollout_proc84_evt_loop terminating... [2023-03-09 10:14:28,429][24121] Loop rollout_proc94_evt_loop terminating... [2023-03-09 10:14:28,429][23228] Loop rollout_proc54_evt_loop terminating... [2023-03-09 10:14:28,429][23242] Stopping RolloutWorker_w92... [2023-03-09 10:14:28,429][24434] Loop rollout_proc100_evt_loop terminating... [2023-03-09 10:14:28,429][23216] Loop rollout_proc51_evt_loop terminating... [2023-03-09 10:14:28,429][23240] Loop rollout_proc64_evt_loop terminating... [2023-03-09 10:14:28,429][23247] Loop rollout_proc91_evt_loop terminating... [2023-03-09 10:14:28,429][23200] Stopping RolloutWorker_w47... [2023-03-09 10:14:28,429][23173] Loop rollout_proc12_evt_loop terminating... [2023-03-09 10:14:28,429][23190] Loop rollout_proc13_evt_loop terminating... [2023-03-09 10:14:28,429][23188] Loop rollout_proc10_evt_loop terminating... [2023-03-09 10:14:28,429][24858] Loop rollout_proc124_evt_loop terminating... [2023-03-09 10:14:28,429][23186] Loop rollout_proc4_evt_loop terminating... [2023-03-09 10:14:28,429][23817] Loop rollout_proc108_evt_loop terminating... [2023-03-09 10:14:28,429][23191] Loop rollout_proc19_evt_loop terminating... [2023-03-09 10:14:28,429][23866] Loop rollout_proc111_evt_loop terminating... [2023-03-09 10:14:28,429][23213] Loop rollout_proc80_evt_loop terminating... [2023-03-09 10:14:28,429][23525] Loop rollout_proc104_evt_loop terminating... [2023-03-09 10:14:28,429][23088] Loop rollout_proc5_evt_loop terminating... [2023-03-09 10:14:28,429][23634] Loop rollout_proc113_evt_loop terminating... [2023-03-09 10:14:28,429][23203] Loop rollout_proc40_evt_loop terminating... [2023-03-09 10:14:28,429][23242] Loop rollout_proc92_evt_loop terminating... [2023-03-09 10:14:28,429][23218] Stopping RolloutWorker_w57... [2023-03-09 10:14:28,429][23200] Loop rollout_proc47_evt_loop terminating... [2023-03-09 10:14:28,429][23249] Stopping RolloutWorker_w98... [2023-03-09 10:14:28,429][23218] Loop rollout_proc57_evt_loop terminating... [2023-03-09 10:14:28,430][23249] Loop rollout_proc98_evt_loop terminating... [2023-03-09 10:14:28,430][24539] Stopping RolloutWorker_w118... [2023-03-09 10:14:28,430][23235] Stopping RolloutWorker_w90... [2023-03-09 10:14:28,431][24539] Loop rollout_proc118_evt_loop terminating... [2023-03-09 10:14:28,431][23235] Loop rollout_proc90_evt_loop terminating... [2023-03-09 10:14:28,439][22664] Component RolloutWorker_w37 stopped! [2023-03-09 10:14:28,416][23314] Loop rollout_proc101_evt_loop terminating... [2023-03-09 10:14:28,449][24352] Stopping RolloutWorker_w109... [2023-03-09 10:14:28,449][24118] Stopping RolloutWorker_w126... [2023-03-09 10:14:28,449][23192] Stopping RolloutWorker_w28... [2023-03-09 10:14:28,449][24352] Loop rollout_proc109_evt_loop terminating... [2023-03-09 10:14:28,449][24118] Loop rollout_proc126_evt_loop terminating... [2023-03-09 10:14:28,449][23246] Stopping RolloutWorker_w61... [2023-03-09 10:14:28,449][23099] Stopping RolloutWorker_w35... [2023-03-09 10:14:28,449][23662] Stopping RolloutWorker_w99... [2023-03-09 10:14:28,449][23118] Stopping RolloutWorker_w41... [2023-03-09 10:14:28,449][23192] Loop rollout_proc28_evt_loop terminating... [2023-03-09 10:14:28,449][23087] Stopping RolloutWorker_w2... [2023-03-09 10:14:28,449][23225] Stopping RolloutWorker_w69... [2023-03-09 10:14:28,449][23241] Stopping RolloutWorker_w70... [2023-03-09 10:14:28,449][23236] Stopping RolloutWorker_w85... [2023-03-09 10:14:28,450][23246] Loop rollout_proc61_evt_loop terminating... [2023-03-09 10:14:28,450][23118] Loop rollout_proc41_evt_loop terminating... [2023-03-09 10:14:28,450][23087] Loop rollout_proc2_evt_loop terminating... [2023-03-09 10:14:28,450][23662] Loop rollout_proc99_evt_loop terminating... [2023-03-09 10:14:28,450][23099] Loop rollout_proc35_evt_loop terminating... [2023-03-09 10:14:28,450][23225] Loop rollout_proc69_evt_loop terminating... [2023-03-09 10:14:28,450][23241] Loop rollout_proc70_evt_loop terminating... [2023-03-09 10:14:28,450][23236] Loop rollout_proc85_evt_loop terminating... [2023-03-09 10:14:28,442][22664] Component RolloutWorker_w22 stopped! [2023-03-09 10:14:28,451][23229] Stopping RolloutWorker_w75... [2023-03-09 10:14:28,451][23195] Stopping RolloutWorker_w34... [2023-03-09 10:14:28,451][23638] Stopping RolloutWorker_w125... [2023-03-09 10:14:28,451][23205] Stopping RolloutWorker_w53... [2023-03-09 10:14:28,451][23224] Stopping RolloutWorker_w63... [2023-03-09 10:14:28,452][23229] Loop rollout_proc75_evt_loop terminating... [2023-03-09 10:14:28,452][23176] Stopping RolloutWorker_w21... [2023-03-09 10:14:28,452][23219] Stopping RolloutWorker_w89... [2023-03-09 10:14:28,452][23214] Stopping RolloutWorker_w83... [2023-03-09 10:14:28,452][23224] Loop rollout_proc63_evt_loop terminating... [2023-03-09 10:14:28,452][23638] Loop rollout_proc125_evt_loop terminating... [2023-03-09 10:14:28,452][23205] Loop rollout_proc53_evt_loop terminating... [2023-03-09 10:14:28,452][23195] Loop rollout_proc34_evt_loop terminating... [2023-03-09 10:14:28,452][23219] Loop rollout_proc89_evt_loop terminating... [2023-03-09 10:14:28,452][23214] Loop rollout_proc83_evt_loop terminating... [2023-03-09 10:14:28,452][23176] Loop rollout_proc21_evt_loop terminating... [2023-03-09 10:14:28,453][23199] Stopping RolloutWorker_w46... [2023-03-09 10:14:28,454][23199] Loop rollout_proc46_evt_loop terminating... [2023-03-09 10:14:28,457][22664] Component RolloutWorker_w9 stopped! [2023-03-09 10:14:28,459][23095] Stopping RolloutWorker_w26... [2023-03-09 10:14:28,460][23095] Loop rollout_proc26_evt_loop terminating... [2023-03-09 10:14:28,459][22664] Component RolloutWorker_w81 stopped! [2023-03-09 10:14:28,461][23238] Stopping RolloutWorker_w67... [2023-03-09 10:14:28,461][24089] Stopping RolloutWorker_w123... [2023-03-09 10:14:28,462][23238] Loop rollout_proc67_evt_loop terminating... [2023-03-09 10:14:28,462][23250] Stopping RolloutWorker_w79... [2023-03-09 10:14:28,462][24157] Stopping RolloutWorker_w106... [2023-03-09 10:14:28,462][24089] Loop rollout_proc123_evt_loop terminating... [2023-03-09 10:14:28,462][23180] Stopping RolloutWorker_w30... [2023-03-09 10:14:28,462][23250] Loop rollout_proc79_evt_loop terminating... [2023-03-09 10:14:28,463][24157] Loop rollout_proc106_evt_loop terminating... [2023-03-09 10:14:28,463][23180] Loop rollout_proc30_evt_loop terminating... [2023-03-09 10:14:28,463][23196] Stopping RolloutWorker_w31... [2023-03-09 10:14:28,463][23196] Loop rollout_proc31_evt_loop terminating... [2023-03-09 10:14:28,469][23175] Stopping RolloutWorker_w18... [2023-03-09 10:14:28,469][23223] Stopping RolloutWorker_w66... [2023-03-09 10:14:28,469][23210] Stopping RolloutWorker_w71... [2023-03-09 10:14:28,470][23175] Loop rollout_proc18_evt_loop terminating... [2023-03-09 10:14:28,470][23223] Loop rollout_proc66_evt_loop terminating... [2023-03-09 10:14:28,470][23208] Stopping RolloutWorker_w59... [2023-03-09 10:14:28,470][23210] Loop rollout_proc71_evt_loop terminating... [2023-03-09 10:14:28,470][23208] Loop rollout_proc59_evt_loop terminating... [2023-03-09 10:14:28,470][23187] Stopping RolloutWorker_w7... [2023-03-09 10:14:28,471][23187] Loop rollout_proc7_evt_loop terminating... [2023-03-09 10:14:28,470][22664] Component RolloutWorker_w110 stopped! [2023-03-09 10:14:28,473][22664] Component RolloutWorker_w82 stopped! [2023-03-09 10:14:28,474][23209] Stopping RolloutWorker_w68... [2023-03-09 10:14:28,474][22664] Component RolloutWorker_w11 stopped! [2023-03-09 10:14:28,479][23209] Loop rollout_proc68_evt_loop terminating... [2023-03-09 10:14:28,481][22664] Component RolloutWorker_w39 stopped! [2023-03-09 10:14:28,483][22664] Component RolloutWorker_w38 stopped! [2023-03-09 10:14:28,484][22664] Component RolloutWorker_w96 stopped! [2023-03-09 10:14:28,485][22664] Component RolloutWorker_w8 stopped! [2023-03-09 10:14:28,486][22664] Component RolloutWorker_w114 stopped! [2023-03-09 10:14:28,487][22664] Component RolloutWorker_w25 stopped! [2023-03-09 10:14:28,488][22664] Component RolloutWorker_w78 stopped! [2023-03-09 10:14:28,489][22664] Component RolloutWorker_w1 stopped! [2023-03-09 10:14:28,490][22664] Component RolloutWorker_w74 stopped! [2023-03-09 10:14:28,490][23171] Stopping RolloutWorker_w3... [2023-03-09 10:14:28,492][23171] Loop rollout_proc3_evt_loop terminating... [2023-03-09 10:14:28,497][22664] Component RolloutWorker_w121 stopped! [2023-03-09 10:14:28,500][22664] Component RolloutWorker_w16 stopped! [2023-03-09 10:14:28,502][22664] Component RolloutWorker_w52 stopped! [2023-03-09 10:14:28,504][22664] Component RolloutWorker_w33 stopped! [2023-03-09 10:14:28,505][22664] Component RolloutWorker_w36 stopped! [2023-03-09 10:14:28,506][22664] Component RolloutWorker_w32 stopped! [2023-03-09 10:14:28,507][22664] Component RolloutWorker_w49 stopped! [2023-03-09 10:14:28,509][22664] Component RolloutWorker_w56 stopped! [2023-03-09 10:14:28,509][23245] Stopping RolloutWorker_w55... [2023-03-09 10:14:28,510][23245] Loop rollout_proc55_evt_loop terminating... [2023-03-09 10:14:28,510][22664] Component RolloutWorker_w60 stopped! [2023-03-09 10:14:28,511][22664] Component RolloutWorker_w65 stopped! [2023-03-09 10:14:28,513][22664] Component RolloutWorker_w88 stopped! [2023-03-09 10:14:28,514][22664] Component RolloutWorker_w76 stopped! [2023-03-09 10:14:28,515][22664] Component RolloutWorker_w93 stopped! [2023-03-09 10:14:28,516][22664] Component RolloutWorker_w122 stopped! [2023-03-09 10:14:28,517][22664] Component RolloutWorker_w50 stopped! [2023-03-09 10:14:28,519][22664] Component RolloutWorker_w117 stopped! [2023-03-09 10:14:28,519][24158] Stopping RolloutWorker_w112... [2023-03-09 10:14:28,520][24158] Loop rollout_proc112_evt_loop terminating... [2023-03-09 10:14:28,520][22664] Component RolloutWorker_w27 stopped! [2023-03-09 10:14:28,521][22664] Component RolloutWorker_w103 stopped! [2023-03-09 10:14:28,523][22664] Component RolloutWorker_w105 stopped! [2023-03-09 10:14:28,524][22664] Component RolloutWorker_w77 stopped! [2023-03-09 10:14:28,525][23635] Stopping RolloutWorker_w119... [2023-03-09 10:14:28,525][23635] Loop rollout_proc119_evt_loop terminating... [2023-03-09 10:14:28,525][22664] Component RolloutWorker_w107 stopped! [2023-03-09 10:14:28,526][22664] Component RolloutWorker_w29 stopped! [2023-03-09 10:14:28,527][22664] Component RolloutWorker_w15 stopped! [2023-03-09 10:14:28,529][22664] Component RolloutWorker_w116 stopped! [2023-03-09 10:14:28,529][22664] Component RolloutWorker_w24 stopped! [2023-03-09 10:14:28,531][22664] Component RolloutWorker_w87 stopped! [2023-03-09 10:14:28,532][22664] Component RolloutWorker_w0 stopped! [2023-03-09 10:14:28,533][22664] Component RolloutWorker_w73 stopped! [2023-03-09 10:14:28,534][22664] Component RolloutWorker_w127 stopped! [2023-03-09 10:14:28,535][22664] Component RolloutWorker_w84 stopped! [2023-03-09 10:14:28,536][22664] Component RolloutWorker_w72 stopped! [2023-03-09 10:14:28,537][22664] Component RolloutWorker_w94 stopped! [2023-03-09 10:14:28,538][22664] Component RolloutWorker_w100 stopped! [2023-03-09 10:14:28,539][22664] Component RolloutWorker_w91 stopped! [2023-03-09 10:14:28,540][22664] Component RolloutWorker_w64 stopped! [2023-03-09 10:14:28,541][22664] Component RolloutWorker_w54 stopped! [2023-03-09 10:14:28,542][22664] Component RolloutWorker_w51 stopped! [2023-03-09 10:14:28,543][22664] Component RolloutWorker_w4 stopped! [2023-03-09 10:14:28,544][22664] Component RolloutWorker_w12 stopped! [2023-03-09 10:14:28,545][22664] Component RolloutWorker_w13 stopped! [2023-03-09 10:14:28,546][22664] Component RolloutWorker_w124 stopped! [2023-03-09 10:14:28,547][22664] Component RolloutWorker_w111 stopped! [2023-03-09 10:14:28,548][22664] Component RolloutWorker_w10 stopped! [2023-03-09 10:14:28,550][22664] Component RolloutWorker_w80 stopped! [2023-03-09 10:14:28,551][22664] Component RolloutWorker_w104 stopped! [2023-03-09 10:14:28,552][22664] Component RolloutWorker_w108 stopped! [2023-03-09 10:14:28,553][22664] Component RolloutWorker_w113 stopped! [2023-03-09 10:14:28,554][22664] Component RolloutWorker_w40 stopped! [2023-03-09 10:14:28,555][22664] Component RolloutWorker_w19 stopped! [2023-03-09 10:14:28,556][22664] Component RolloutWorker_w5 stopped! [2023-03-09 10:14:28,557][22664] Component RolloutWorker_w47 stopped! [2023-03-09 10:14:28,558][22664] Component RolloutWorker_w92 stopped! [2023-03-09 10:14:28,559][22664] Component RolloutWorker_w57 stopped! [2023-03-09 10:14:28,560][22664] Component RolloutWorker_w98 stopped! [2023-03-09 10:14:28,561][22664] Component RolloutWorker_w118 stopped! [2023-03-09 10:14:28,562][22664] Component RolloutWorker_w90 stopped! [2023-03-09 10:14:28,563][22664] Component RolloutWorker_w126 stopped! [2023-03-09 10:14:28,564][22664] Component RolloutWorker_w109 stopped! [2023-03-09 10:14:28,565][22664] Component RolloutWorker_w28 stopped! [2023-03-09 10:14:28,560][23215] Stopping RolloutWorker_w48... [2023-03-09 10:14:28,566][22664] Component RolloutWorker_w61 stopped! [2023-03-09 10:14:28,566][23170] Stopping RolloutWorker_w6... [2023-03-09 10:14:28,567][22664] Component RolloutWorker_w99 stopped! [2023-03-09 10:14:28,568][22664] Component RolloutWorker_w35 stopped! [2023-03-09 10:14:28,568][23170] Loop rollout_proc6_evt_loop terminating... [2023-03-09 10:14:28,570][22664] Component RolloutWorker_w41 stopped! [2023-03-09 10:14:28,571][22664] Component RolloutWorker_w2 stopped! [2023-03-09 10:14:28,572][22664] Component RolloutWorker_w70 stopped! [2023-03-09 10:14:28,573][22664] Component RolloutWorker_w69 stopped! [2023-03-09 10:14:28,574][22664] Component RolloutWorker_w85 stopped! [2023-03-09 10:14:28,575][22664] Component RolloutWorker_w75 stopped! [2023-03-09 10:14:28,575][23248] Stopping RolloutWorker_w95... [2023-03-09 10:14:28,576][23248] Loop rollout_proc95_evt_loop terminating... [2023-03-09 10:14:28,576][22664] Component RolloutWorker_w63 stopped! [2023-03-09 10:14:28,577][22664] Component RolloutWorker_w34 stopped! [2023-03-09 10:14:28,578][22664] Component RolloutWorker_w53 stopped! [2023-03-09 10:14:28,572][23215] Loop rollout_proc48_evt_loop terminating... [2023-03-09 10:14:28,579][22664] Component RolloutWorker_w125 stopped! [2023-03-09 10:14:28,580][22664] Component RolloutWorker_w21 stopped! [2023-03-09 10:14:28,581][22664] Component RolloutWorker_w83 stopped! [2023-03-09 10:14:28,582][22664] Component RolloutWorker_w89 stopped! [2023-03-09 10:14:28,583][22664] Component RolloutWorker_w46 stopped! [2023-03-09 10:14:28,584][22664] Component RolloutWorker_w26 stopped! [2023-03-09 10:14:28,585][22664] Component RolloutWorker_w67 stopped! [2023-03-09 10:14:28,586][22664] Component RolloutWorker_w123 stopped! [2023-03-09 10:14:28,586][22664] Component RolloutWorker_w79 stopped! [2023-03-09 10:14:28,587][22664] Component RolloutWorker_w30 stopped! [2023-03-09 10:14:28,588][22664] Component RolloutWorker_w106 stopped! [2023-03-09 10:14:28,589][22664] Component RolloutWorker_w31 stopped! [2023-03-09 10:14:28,590][22664] Component RolloutWorker_w66 stopped! [2023-03-09 10:14:28,591][22664] Component RolloutWorker_w18 stopped! [2023-03-09 10:14:28,592][22664] Component RolloutWorker_w71 stopped! [2023-03-09 10:14:28,593][22664] Component RolloutWorker_w59 stopped! [2023-03-09 10:14:28,593][22664] Component RolloutWorker_w7 stopped! [2023-03-09 10:14:28,594][22664] Component RolloutWorker_w68 stopped! [2023-03-09 10:14:28,595][22664] Component RolloutWorker_w3 stopped! [2023-03-09 10:14:28,597][22664] Component RolloutWorker_w55 stopped! [2023-03-09 10:14:28,597][22664] Component RolloutWorker_w112 stopped! [2023-03-09 10:14:28,598][22664] Component RolloutWorker_w119 stopped! [2023-03-09 10:14:28,599][22664] Component RolloutWorker_w48 stopped! [2023-03-09 10:14:28,599][22664] Component RolloutWorker_w6 stopped! [2023-03-09 10:14:28,600][22664] Component RolloutWorker_w95 stopped! [2023-03-09 10:14:28,601][22664] Waiting for process learner_proc0 to stop... [2023-03-09 10:14:31,466][22664] Waiting for process inference_proc0-0 to join... [2023-03-09 10:14:31,467][22664] Waiting for process rollout_proc0 to join... [2023-03-09 10:14:31,468][22664] Waiting for process rollout_proc1 to join... [2023-03-09 10:14:31,469][22664] Waiting for process rollout_proc2 to join... [2023-03-09 10:14:31,470][22664] Waiting for process rollout_proc3 to join... [2023-03-09 10:14:31,471][22664] Waiting for process rollout_proc4 to join... [2023-03-09 10:14:31,472][22664] Waiting for process rollout_proc5 to join... [2023-03-09 10:14:31,472][22664] Waiting for process rollout_proc6 to join... [2023-03-09 10:14:31,473][22664] Waiting for process rollout_proc7 to join... [2023-03-09 10:14:31,474][22664] Waiting for process rollout_proc8 to join... [2023-03-09 10:14:31,475][22664] Waiting for process rollout_proc9 to join... [2023-03-09 10:14:31,476][22664] Waiting for process rollout_proc10 to join... [2023-03-09 10:14:31,476][22664] Waiting for process rollout_proc11 to join... [2023-03-09 10:14:31,477][22664] Waiting for process rollout_proc12 to join... [2023-03-09 10:14:31,478][22664] Waiting for process rollout_proc13 to join... [2023-03-09 10:14:31,479][22664] Waiting for process rollout_proc14 to join... [2023-03-09 10:14:31,480][22664] Waiting for process rollout_proc15 to join... [2023-03-09 10:14:31,480][22664] Waiting for process rollout_proc16 to join... [2023-03-09 10:14:31,481][22664] Waiting for process rollout_proc17 to join... [2023-03-09 10:14:31,482][22664] Waiting for process rollout_proc18 to join... [2023-03-09 10:14:31,483][22664] Waiting for process rollout_proc19 to join... [2023-03-09 10:14:31,483][22664] Waiting for process rollout_proc20 to join... [2023-03-09 10:14:31,484][22664] Waiting for process rollout_proc21 to join... [2023-03-09 10:14:31,485][22664] Waiting for process rollout_proc22 to join... [2023-03-09 10:14:31,486][22664] Waiting for process rollout_proc23 to join... [2023-03-09 10:14:31,487][22664] Waiting for process rollout_proc24 to join... [2023-03-09 10:14:31,487][22664] Waiting for process rollout_proc25 to join... [2023-03-09 10:14:31,488][22664] Waiting for process rollout_proc26 to join... [2023-03-09 10:14:31,489][22664] Waiting for process rollout_proc27 to join... [2023-03-09 10:14:31,490][22664] Waiting for process rollout_proc28 to join... [2023-03-09 10:14:31,490][22664] Waiting for process rollout_proc29 to join... [2023-03-09 10:14:31,491][22664] Waiting for process rollout_proc30 to join... [2023-03-09 10:14:31,492][22664] Waiting for process rollout_proc31 to join... [2023-03-09 10:14:31,493][22664] Waiting for process rollout_proc32 to join... [2023-03-09 10:14:31,493][22664] Waiting for process rollout_proc33 to join... [2023-03-09 10:14:31,494][22664] Waiting for process rollout_proc34 to join... [2023-03-09 10:14:31,495][22664] Waiting for process rollout_proc35 to join... [2023-03-09 10:14:31,496][22664] Waiting for process rollout_proc36 to join... [2023-03-09 10:14:31,497][22664] Waiting for process rollout_proc37 to join... [2023-03-09 10:14:31,497][22664] Waiting for process rollout_proc38 to join... [2023-03-09 10:14:31,498][22664] Waiting for process rollout_proc39 to join... [2023-03-09 10:14:31,499][22664] Waiting for process rollout_proc40 to join... [2023-03-09 10:14:31,500][22664] Waiting for process rollout_proc41 to join... [2023-03-09 10:14:31,500][22664] Waiting for process rollout_proc42 to join... [2023-03-09 10:14:31,501][22664] Waiting for process rollout_proc43 to join... [2023-03-09 10:14:31,502][22664] Waiting for process rollout_proc44 to join... [2023-03-09 10:14:31,503][22664] Waiting for process rollout_proc45 to join... [2023-03-09 10:14:31,503][22664] Waiting for process rollout_proc46 to join... [2023-03-09 10:14:31,506][22664] Waiting for process rollout_proc47 to join... [2023-03-09 10:14:31,507][22664] Waiting for process rollout_proc48 to join... [2023-03-09 10:14:31,507][22664] Waiting for process rollout_proc49 to join... [2023-03-09 10:14:31,508][22664] Waiting for process rollout_proc50 to join... [2023-03-09 10:14:31,509][22664] Waiting for process rollout_proc51 to join... [2023-03-09 10:14:31,510][22664] Waiting for process rollout_proc52 to join... [2023-03-09 10:14:31,511][22664] Waiting for process rollout_proc53 to join... [2023-03-09 10:14:31,511][22664] Waiting for process rollout_proc54 to join... [2023-03-09 10:14:31,512][22664] Waiting for process rollout_proc55 to join... [2023-03-09 10:14:31,513][22664] Waiting for process rollout_proc56 to join... [2023-03-09 10:14:31,514][22664] Waiting for process rollout_proc57 to join... [2023-03-09 10:14:31,515][22664] Waiting for process rollout_proc58 to join... [2023-03-09 10:14:31,516][22664] Waiting for process rollout_proc59 to join... [2023-03-09 10:14:31,518][22664] Waiting for process rollout_proc60 to join... [2023-03-09 10:14:31,519][22664] Waiting for process rollout_proc61 to join... [2023-03-09 10:14:31,520][22664] Waiting for process rollout_proc62 to join... [2023-03-09 10:14:31,521][22664] Waiting for process rollout_proc63 to join... [2023-03-09 10:14:31,521][22664] Waiting for process rollout_proc64 to join... [2023-03-09 10:14:31,522][22664] Waiting for process rollout_proc65 to join... [2023-03-09 10:14:31,523][22664] Waiting for process rollout_proc66 to join... [2023-03-09 10:14:31,524][22664] Waiting for process rollout_proc67 to join... [2023-03-09 10:14:31,524][22664] Waiting for process rollout_proc68 to join... [2023-03-09 10:14:31,525][22664] Waiting for process rollout_proc69 to join... [2023-03-09 10:14:31,526][22664] Waiting for process rollout_proc70 to join... [2023-03-09 10:14:31,526][22664] Waiting for process rollout_proc71 to join... [2023-03-09 10:14:31,527][22664] Waiting for process rollout_proc72 to join... [2023-03-09 10:14:31,528][22664] Waiting for process rollout_proc73 to join... [2023-03-09 10:14:31,529][22664] Waiting for process rollout_proc74 to join... [2023-03-09 10:14:31,529][22664] Waiting for process rollout_proc75 to join... [2023-03-09 10:14:31,530][22664] Waiting for process rollout_proc76 to join... [2023-03-09 10:14:31,531][22664] Waiting for process rollout_proc77 to join... [2023-03-09 10:14:31,532][22664] Waiting for process rollout_proc78 to join... [2023-03-09 10:14:31,532][22664] Waiting for process rollout_proc79 to join... [2023-03-09 10:14:31,533][22664] Waiting for process rollout_proc80 to join... [2023-03-09 10:14:31,534][22664] Waiting for process rollout_proc81 to join... [2023-03-09 10:14:31,535][22664] Waiting for process rollout_proc82 to join... [2023-03-09 10:14:31,535][22664] Waiting for process rollout_proc83 to join... [2023-03-09 10:14:31,536][22664] Waiting for process rollout_proc84 to join... [2023-03-09 10:14:31,537][22664] Waiting for process rollout_proc85 to join... [2023-03-09 10:14:31,538][22664] Waiting for process rollout_proc86 to join... [2023-03-09 10:14:31,538][22664] Waiting for process rollout_proc87 to join... [2023-03-09 10:14:31,539][22664] Waiting for process rollout_proc88 to join... [2023-03-09 10:14:31,540][22664] Waiting for process rollout_proc89 to join... [2023-03-09 10:14:31,540][22664] Waiting for process rollout_proc90 to join... [2023-03-09 10:14:31,541][22664] Waiting for process rollout_proc91 to join... [2023-03-09 10:14:31,542][22664] Waiting for process rollout_proc92 to join... [2023-03-09 10:14:31,543][22664] Waiting for process rollout_proc93 to join... [2023-03-09 10:14:31,544][22664] Waiting for process rollout_proc94 to join... [2023-03-09 10:14:31,548][22664] Waiting for process rollout_proc95 to join... [2023-03-09 10:14:31,549][22664] Waiting for process rollout_proc96 to join... [2023-03-09 10:14:31,549][22664] Waiting for process rollout_proc97 to join... [2023-03-09 10:14:31,550][22664] Waiting for process rollout_proc98 to join... [2023-03-09 10:14:31,551][22664] Waiting for process rollout_proc99 to join... [2023-03-09 10:14:31,552][22664] Waiting for process rollout_proc100 to join... [2023-03-09 10:14:31,555][22664] Waiting for process rollout_proc101 to join... [2023-03-09 10:14:31,556][22664] Waiting for process rollout_proc102 to join... [2023-03-09 10:14:31,557][22664] Waiting for process rollout_proc103 to join... [2023-03-09 10:14:31,558][22664] Waiting for process rollout_proc104 to join... [2023-03-09 10:14:31,559][22664] Waiting for process rollout_proc105 to join... [2023-03-09 10:14:31,560][22664] Waiting for process rollout_proc106 to join... [2023-03-09 10:14:31,561][22664] Waiting for process rollout_proc107 to join... [2023-03-09 10:14:31,561][22664] Waiting for process rollout_proc108 to join... [2023-03-09 10:14:31,562][22664] Waiting for process rollout_proc109 to join... [2023-03-09 10:14:31,563][22664] Waiting for process rollout_proc110 to join... [2023-03-09 10:14:31,564][22664] Waiting for process rollout_proc111 to join... [2023-03-09 10:14:31,566][22664] Waiting for process rollout_proc112 to join... [2023-03-09 10:14:31,566][22664] Waiting for process rollout_proc113 to join... [2023-03-09 10:14:31,567][22664] Waiting for process rollout_proc114 to join... [2023-03-09 10:14:31,568][22664] Waiting for process rollout_proc115 to join... [2023-03-09 10:14:31,569][22664] Waiting for process rollout_proc116 to join... [2023-03-09 10:14:31,569][22664] Waiting for process rollout_proc117 to join... [2023-03-09 10:14:31,570][22664] Waiting for process rollout_proc118 to join... [2023-03-09 10:14:31,571][22664] Waiting for process rollout_proc119 to join... [2023-03-09 10:14:31,572][22664] Waiting for process rollout_proc120 to join... [2023-03-09 10:14:31,575][22664] Waiting for process rollout_proc121 to join... [2023-03-09 10:14:31,576][22664] Waiting for process rollout_proc122 to join... [2023-03-09 10:14:31,576][22664] Waiting for process rollout_proc123 to join... [2023-03-09 10:14:31,577][22664] Waiting for process rollout_proc124 to join... [2023-03-09 10:14:31,578][22664] Waiting for process rollout_proc125 to join... [2023-03-09 10:14:31,579][22664] Waiting for process rollout_proc126 to join... [2023-03-09 10:14:31,580][22664] Waiting for process rollout_proc127 to join... [2023-03-09 10:14:31,583][22664] Batcher 0 profile tree view: batching: 2742.8135, releasing_batches: 143.5254 [2023-03-09 10:14:31,584][22664] InferenceWorker_p0-w0 profile tree view: wait_policy: 0.0005 wait_policy_total: 267.2242 update_model: 227.2763 weight_update: 0.0016 one_step: 0.0462 handle_policy_step: 9572.9953 deserialize: 4699.4361, stack: 11.7560, obs_to_device_normalize: 2201.6907, forward: 350.7292, send_messages: 645.4250 prepare_outputs: 1539.1866 to_cpu: 905.8869 [2023-03-09 10:14:31,584][22664] Learner 0 profile tree view: misc: 0.5993, prepare_batch: 1194.8507 train: 4150.8316 epoch_init: 0.7705, minibatch_init: 0.7566, losses_postprocess: 39.0192, kl_divergence: 42.9128, after_optimizer: 1051.7356 calculate_losses: 1690.3505 losses_init: 0.5207, forward_head: 158.0041, bptt_initial: 1063.1735, tail: 86.7248, advantages_returns: 23.7173, losses: 149.1722 bptt: 185.4911 bptt_forward_core: 178.1105 update: 1273.4316 clip: 202.0435 [2023-03-09 10:14:31,585][22664] RolloutWorker_w0 profile tree view: wait_for_trajectories: 2.9783, enqueue_policy_requests: 157.6141, env_step: 4208.4656, overhead: 371.2717, complete_rollouts: 1.3259 save_policy_outputs: 526.5193 split_output_tensors: 247.7296 [2023-03-09 10:14:31,586][22664] RolloutWorker_w127 profile tree view: wait_for_trajectories: 2.9139, enqueue_policy_requests: 161.6105, env_step: 4214.3953, overhead: 376.0761, complete_rollouts: 1.2166 save_policy_outputs: 536.5171 split_output_tensors: 251.8584 [2023-03-09 10:14:31,586][22664] Loop Runner_EvtLoop terminating... [2023-03-09 10:14:31,591][22664] Runner profile tree view: main_loop: 10148.0063 [2023-03-09 10:14:31,592][22664] Collected {0: 2000027648}, FPS: 197085.8 [2023-03-09 10:14:31,677][22664] Loading existing experiment configuration from /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/config.json [2023-03-09 10:14:31,678][22664] Adding new argument 'no_render'=True that is not in the saved config file! [2023-03-09 10:14:31,678][22664] Adding new argument 'save_video'=True that is not in the saved config file! [2023-03-09 10:14:31,679][22664] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file! [2023-03-09 10:14:31,680][22664] Adding new argument 'video_name'=None that is not in the saved config file! [2023-03-09 10:14:31,680][22664] Adding new argument 'max_num_frames'=1000000000.0 that is not in the saved config file! [2023-03-09 10:14:31,681][22664] Adding new argument 'max_num_episodes'=10 that is not in the saved config file! [2023-03-09 10:14:31,681][22664] Adding new argument 'push_to_hub'=False that is not in the saved config file! [2023-03-09 10:14:31,682][22664] Adding new argument 'hf_repository'=None that is not in the saved config file! [2023-03-09 10:14:31,682][22664] Adding new argument 'policy_index'=0 that is not in the saved config file! [2023-03-09 10:14:31,683][22664] Adding new argument 'eval_deterministic'=False that is not in the saved config file! [2023-03-09 10:14:31,683][22664] Adding new argument 'train_script'=None that is not in the saved config file! [2023-03-09 10:14:31,684][22664] Adding new argument 'enjoy_script'=None that is not in the saved config file! [2023-03-09 10:14:31,684][22664] Using frameskip 1 and render_action_repeat=4 for evaluation [2023-03-09 10:14:31,692][22664] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:14:31,694][22664] RunningMeanStd input shape: (3, 72, 128) [2023-03-09 10:14:31,695][22664] RunningMeanStd input shape: (1,) [2023-03-09 10:14:31,706][22664] ConvEncoder: input_channels=3 [2023-03-09 10:14:31,798][22664] Conv encoder output size: 512 [2023-03-09 10:14:31,798][22664] Policy head output size: 512 [2023-03-09 10:14:33,539][22664] Loading state from checkpoint /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000122072_2000027648.pth... [2023-03-09 10:14:34,505][22664] Num frames 100... [2023-03-09 10:14:34,584][22664] Num frames 200... [2023-03-09 10:14:34,662][22664] Num frames 300... [2023-03-09 10:14:34,740][22664] Num frames 400... [2023-03-09 10:14:34,818][22664] Num frames 500... [2023-03-09 10:14:34,896][22664] Num frames 600... [2023-03-09 10:14:34,974][22664] Num frames 700... [2023-03-09 10:14:35,066][22664] Num frames 800... [2023-03-09 10:14:35,158][22664] Num frames 900... [2023-03-09 10:14:35,254][22664] Num frames 1000... [2023-03-09 10:14:35,347][22664] Num frames 1100... [2023-03-09 10:14:35,436][22664] Num frames 1200... [2023-03-09 10:14:35,528][22664] Num frames 1300... [2023-03-09 10:14:35,623][22664] Num frames 1400... [2023-03-09 10:14:35,711][22664] Num frames 1500... [2023-03-09 10:14:35,805][22664] Num frames 1600... [2023-03-09 10:14:35,895][22664] Num frames 1700... [2023-03-09 10:14:35,986][22664] Num frames 1800... [2023-03-09 10:14:36,075][22664] Num frames 1900... [2023-03-09 10:14:36,163][22664] Num frames 2000... [2023-03-09 10:14:36,254][22664] Num frames 2100... [2023-03-09 10:14:36,305][22664] Avg episode rewards: #0: 56.999, true rewards: #0: 21.000 [2023-03-09 10:14:36,306][22664] Avg episode reward: 56.999, avg true_objective: 21.000 [2023-03-09 10:14:36,404][22664] Num frames 2200... [2023-03-09 10:14:36,492][22664] Num frames 2300... [2023-03-09 10:14:36,579][22664] Num frames 2400... [2023-03-09 10:14:36,664][22664] Num frames 2500... [2023-03-09 10:14:36,750][22664] Num frames 2600... [2023-03-09 10:14:36,838][22664] Num frames 2700... [2023-03-09 10:14:36,927][22664] Num frames 2800... [2023-03-09 10:14:37,015][22664] Num frames 2900... [2023-03-09 10:14:37,103][22664] Num frames 3000... [2023-03-09 10:14:37,189][22664] Num frames 3100... [2023-03-09 10:14:37,276][22664] Num frames 3200... [2023-03-09 10:14:37,364][22664] Num frames 3300... [2023-03-09 10:14:37,451][22664] Num frames 3400... [2023-03-09 10:14:37,537][22664] Num frames 3500... [2023-03-09 10:14:37,627][22664] Num frames 3600... [2023-03-09 10:14:37,716][22664] Num frames 3700... [2023-03-09 10:14:37,805][22664] Num frames 3800... [2023-03-09 10:14:37,893][22664] Num frames 3900... [2023-03-09 10:14:37,982][22664] Num frames 4000... [2023-03-09 10:14:38,070][22664] Num frames 4100... [2023-03-09 10:14:38,160][22664] Num frames 4200... [2023-03-09 10:14:38,211][22664] Avg episode rewards: #0: 58.999, true rewards: #0: 21.000 [2023-03-09 10:14:38,212][22664] Avg episode reward: 58.999, avg true_objective: 21.000 [2023-03-09 10:14:38,298][22664] Num frames 4300... [2023-03-09 10:14:38,384][22664] Num frames 4400... [2023-03-09 10:14:38,471][22664] Num frames 4500... [2023-03-09 10:14:38,558][22664] Num frames 4600... [2023-03-09 10:14:38,643][22664] Num frames 4700... [2023-03-09 10:14:38,730][22664] Num frames 4800... [2023-03-09 10:14:38,818][22664] Num frames 4900... [2023-03-09 10:14:38,907][22664] Num frames 5000... [2023-03-09 10:14:38,993][22664] Num frames 5100... [2023-03-09 10:14:39,082][22664] Num frames 5200... [2023-03-09 10:14:39,173][22664] Num frames 5300... [2023-03-09 10:14:39,260][22664] Num frames 5400... [2023-03-09 10:14:39,348][22664] Num frames 5500... [2023-03-09 10:14:39,435][22664] Num frames 5600... [2023-03-09 10:14:39,523][22664] Num frames 5700... [2023-03-09 10:14:39,614][22664] Num frames 5800... [2023-03-09 10:14:39,703][22664] Num frames 5900... [2023-03-09 10:14:39,792][22664] Num frames 6000... [2023-03-09 10:14:39,879][22664] Num frames 6100... [2023-03-09 10:14:39,966][22664] Num frames 6200... [2023-03-09 10:14:40,057][22664] Num frames 6300... [2023-03-09 10:14:40,109][22664] Avg episode rewards: #0: 60.665, true rewards: #0: 21.000 [2023-03-09 10:14:40,110][22664] Avg episode reward: 60.665, avg true_objective: 21.000 [2023-03-09 10:14:40,197][22664] Num frames 6400... [2023-03-09 10:14:40,283][22664] Num frames 6500... [2023-03-09 10:14:40,371][22664] Num frames 6600... [2023-03-09 10:14:40,459][22664] Num frames 6700... [2023-03-09 10:14:40,546][22664] Num frames 6800... [2023-03-09 10:14:40,633][22664] Num frames 6900... [2023-03-09 10:14:40,719][22664] Num frames 7000... [2023-03-09 10:14:40,806][22664] Num frames 7100... [2023-03-09 10:14:40,895][22664] Num frames 7200... [2023-03-09 10:14:40,983][22664] Num frames 7300... [2023-03-09 10:14:41,072][22664] Num frames 7400... [2023-03-09 10:14:41,159][22664] Num frames 7500... [2023-03-09 10:14:41,247][22664] Num frames 7600... [2023-03-09 10:14:41,334][22664] Num frames 7700... [2023-03-09 10:14:41,421][22664] Num frames 7800... [2023-03-09 10:14:41,508][22664] Num frames 7900... [2023-03-09 10:14:41,596][22664] Num frames 8000... [2023-03-09 10:14:41,685][22664] Num frames 8100... [2023-03-09 10:14:41,772][22664] Num frames 8200... [2023-03-09 10:14:41,859][22664] Num frames 8300... [2023-03-09 10:14:41,949][22664] Num frames 8400... [2023-03-09 10:14:42,001][22664] Avg episode rewards: #0: 60.499, true rewards: #0: 21.000 [2023-03-09 10:14:42,001][22664] Avg episode reward: 60.499, avg true_objective: 21.000 [2023-03-09 10:14:42,088][22664] Num frames 8500... [2023-03-09 10:14:42,175][22664] Num frames 8600... [2023-03-09 10:14:42,261][22664] Num frames 8700... [2023-03-09 10:14:42,347][22664] Num frames 8800... [2023-03-09 10:14:42,434][22664] Num frames 8900... [2023-03-09 10:14:42,522][22664] Num frames 9000... [2023-03-09 10:14:42,609][22664] Num frames 9100... [2023-03-09 10:14:42,696][22664] Num frames 9200... [2023-03-09 10:14:42,785][22664] Num frames 9300... [2023-03-09 10:14:42,873][22664] Num frames 9400... [2023-03-09 10:14:42,962][22664] Num frames 9500... [2023-03-09 10:14:43,049][22664] Num frames 9600... [2023-03-09 10:14:43,136][22664] Num frames 9700... [2023-03-09 10:14:43,225][22664] Num frames 9800... [2023-03-09 10:14:43,315][22664] Num frames 9900... [2023-03-09 10:14:43,404][22664] Num frames 10000... [2023-03-09 10:14:43,491][22664] Num frames 10100... [2023-03-09 10:14:43,578][22664] Num frames 10200... [2023-03-09 10:14:43,667][22664] Num frames 10300... [2023-03-09 10:14:43,755][22664] Num frames 10400... [2023-03-09 10:14:43,847][22664] Num frames 10500... [2023-03-09 10:14:43,898][22664] Avg episode rewards: #0: 60.399, true rewards: #0: 21.000 [2023-03-09 10:14:43,899][22664] Avg episode reward: 60.399, avg true_objective: 21.000 [2023-03-09 10:14:43,999][22664] Num frames 10600... [2023-03-09 10:14:44,086][22664] Num frames 10700... [2023-03-09 10:14:44,171][22664] Num frames 10800... [2023-03-09 10:14:44,260][22664] Num frames 10900... [2023-03-09 10:14:44,347][22664] Num frames 11000... [2023-03-09 10:14:44,435][22664] Num frames 11100... [2023-03-09 10:14:44,521][22664] Num frames 11200... [2023-03-09 10:14:44,609][22664] Num frames 11300... [2023-03-09 10:14:44,698][22664] Num frames 11400... [2023-03-09 10:14:44,785][22664] Num frames 11500... [2023-03-09 10:14:44,873][22664] Num frames 11600... [2023-03-09 10:14:44,959][22664] Num frames 11700... [2023-03-09 10:14:45,046][22664] Num frames 11800... [2023-03-09 10:14:45,134][22664] Num frames 11900... [2023-03-09 10:14:45,222][22664] Num frames 12000... [2023-03-09 10:14:45,311][22664] Num frames 12100... [2023-03-09 10:14:45,399][22664] Num frames 12200... [2023-03-09 10:14:45,485][22664] Num frames 12300... [2023-03-09 10:14:45,570][22664] Num frames 12400... [2023-03-09 10:14:45,659][22664] Num frames 12500... [2023-03-09 10:14:45,749][22664] Num frames 12600... [2023-03-09 10:14:45,801][22664] Avg episode rewards: #0: 60.665, true rewards: #0: 21.000 [2023-03-09 10:14:45,802][22664] Avg episode reward: 60.665, avg true_objective: 21.000 [2023-03-09 10:14:45,915][22664] Num frames 12700... [2023-03-09 10:14:46,003][22664] Num frames 12800... [2023-03-09 10:14:46,090][22664] Num frames 12900... [2023-03-09 10:14:46,175][22664] Num frames 13000... [2023-03-09 10:14:46,261][22664] Num frames 13100... [2023-03-09 10:14:46,349][22664] Num frames 13200... [2023-03-09 10:14:46,436][22664] Num frames 13300... [2023-03-09 10:14:46,523][22664] Num frames 13400... [2023-03-09 10:14:46,610][22664] Num frames 13500... [2023-03-09 10:14:46,697][22664] Num frames 13600... [2023-03-09 10:14:46,783][22664] Num frames 13700... [2023-03-09 10:14:46,869][22664] Num frames 13800... [2023-03-09 10:14:46,957][22664] Num frames 13900... [2023-03-09 10:14:47,046][22664] Num frames 14000... [2023-03-09 10:14:47,135][22664] Num frames 14100... [2023-03-09 10:14:47,223][22664] Num frames 14200... [2023-03-09 10:14:47,310][22664] Num frames 14300... [2023-03-09 10:14:47,397][22664] Num frames 14400... [2023-03-09 10:14:47,487][22664] Num frames 14500... [2023-03-09 10:14:47,575][22664] Num frames 14600... [2023-03-09 10:14:47,668][22664] Num frames 14700... [2023-03-09 10:14:47,719][22664] Avg episode rewards: #0: 60.427, true rewards: #0: 21.000 [2023-03-09 10:14:47,720][22664] Avg episode reward: 60.427, avg true_objective: 21.000 [2023-03-09 10:14:47,828][22664] Num frames 14800... [2023-03-09 10:14:47,914][22664] Num frames 14900... [2023-03-09 10:14:48,000][22664] Num frames 15000... [2023-03-09 10:14:48,086][22664] Num frames 15100... [2023-03-09 10:14:48,172][22664] Num frames 15200... [2023-03-09 10:14:48,260][22664] Num frames 15300... [2023-03-09 10:14:48,347][22664] Num frames 15400... [2023-03-09 10:14:48,434][22664] Num frames 15500... [2023-03-09 10:14:48,520][22664] Num frames 15600... [2023-03-09 10:14:48,608][22664] Num frames 15700... [2023-03-09 10:14:48,695][22664] Num frames 15800... [2023-03-09 10:14:48,781][22664] Num frames 15900... [2023-03-09 10:14:48,868][22664] Num frames 16000... [2023-03-09 10:14:48,955][22664] Num frames 16100... [2023-03-09 10:14:49,080][22664] Avg episode rewards: #0: 57.471, true rewards: #0: 20.223 [2023-03-09 10:14:49,081][22664] Avg episode reward: 57.471, avg true_objective: 20.223 [2023-03-09 10:14:49,101][22664] Num frames 16200... [2023-03-09 10:14:49,193][22664] Num frames 16300... [2023-03-09 10:14:49,280][22664] Num frames 16400... [2023-03-09 10:14:49,366][22664] Num frames 16500... [2023-03-09 10:14:49,453][22664] Num frames 16600... [2023-03-09 10:14:49,541][22664] Num frames 16700... [2023-03-09 10:14:49,626][22664] Num frames 16800... [2023-03-09 10:14:49,714][22664] Num frames 16900... [2023-03-09 10:14:49,800][22664] Num frames 17000... [2023-03-09 10:14:49,888][22664] Num frames 17100... [2023-03-09 10:14:49,975][22664] Num frames 17200... [2023-03-09 10:14:50,061][22664] Num frames 17300... [2023-03-09 10:14:50,149][22664] Num frames 17400... [2023-03-09 10:14:50,237][22664] Num frames 17500... [2023-03-09 10:14:50,338][22664] Avg episode rewards: #0: 54.615, true rewards: #0: 19.504 [2023-03-09 10:14:50,339][22664] Avg episode reward: 54.615, avg true_objective: 19.504 [2023-03-09 10:14:50,399][22664] Num frames 17600... [2023-03-09 10:14:50,489][22664] Num frames 17700... [2023-03-09 10:14:50,575][22664] Num frames 17800... [2023-03-09 10:14:50,660][22664] Num frames 17900... [2023-03-09 10:14:50,747][22664] Num frames 18000... [2023-03-09 10:14:50,834][22664] Num frames 18100... [2023-03-09 10:14:50,920][22664] Num frames 18200... [2023-03-09 10:14:51,008][22664] Num frames 18300... [2023-03-09 10:14:51,095][22664] Num frames 18400... [2023-03-09 10:14:51,182][22664] Num frames 18500... [2023-03-09 10:14:51,271][22664] Num frames 18600... [2023-03-09 10:14:51,359][22664] Num frames 18700... [2023-03-09 10:14:51,446][22664] Num frames 18800... [2023-03-09 10:14:51,533][22664] Num frames 18900... [2023-03-09 10:14:51,621][22664] Num frames 19000... [2023-03-09 10:14:51,709][22664] Num frames 19100... [2023-03-09 10:14:51,795][22664] Num frames 19200... [2023-03-09 10:14:51,881][22664] Num frames 19300... [2023-03-09 10:14:51,967][22664] Num frames 19400... [2023-03-09 10:14:52,057][22664] Num frames 19500... [2023-03-09 10:14:52,144][22664] Num frames 19600... [2023-03-09 10:14:52,246][22664] Avg episode rewards: #0: 55.753, true rewards: #0: 19.654 [2023-03-09 10:14:52,246][22664] Avg episode reward: 55.753, avg true_objective: 19.654 [2023-03-09 10:15:17,348][22664] Replay video saved to /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/replay.mp4! [2023-03-09 10:15:17,638][22664] Loading existing experiment configuration from /mnt/Lata/projects/samplefactory/train_dir/default_experiment/config.json [2023-03-09 10:15:17,639][22664] Overriding arg 'num_workers' with value 1 passed from command line [2023-03-09 10:15:17,639][22664] Adding new argument 'no_render'=True that is not in the saved config file! [2023-03-09 10:15:17,640][22664] Adding new argument 'save_video'=True that is not in the saved config file! [2023-03-09 10:15:17,641][22664] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file! [2023-03-09 10:15:17,641][22664] Adding new argument 'video_name'=None that is not in the saved config file! [2023-03-09 10:15:17,642][22664] Adding new argument 'max_num_frames'=100000 that is not in the saved config file! [2023-03-09 10:15:17,643][22664] Adding new argument 'max_num_episodes'=10 that is not in the saved config file! [2023-03-09 10:15:17,644][22664] Adding new argument 'push_to_hub'=True that is not in the saved config file! [2023-03-09 10:15:17,644][22664] Adding new argument 'hf_repository'='Rolo/doom_health_w128-epw64-r32_b4096-2b' that is not in the saved config file! [2023-03-09 10:15:17,645][22664] Adding new argument 'policy_index'=0 that is not in the saved config file! [2023-03-09 10:15:17,645][22664] Adding new argument 'eval_deterministic'=False that is not in the saved config file! [2023-03-09 10:15:17,647][22664] Adding new argument 'train_script'=None that is not in the saved config file! [2023-03-09 10:15:17,647][22664] Adding new argument 'enjoy_script'=None that is not in the saved config file! [2023-03-09 10:15:17,648][22664] Using frameskip 1 and render_action_repeat=4 for evaluation [2023-03-09 10:15:17,712][22664] RunningMeanStd input shape: (3, 72, 128) [2023-03-09 10:15:17,713][22664] RunningMeanStd input shape: (1,) [2023-03-09 10:15:17,722][22664] ConvEncoder: input_channels=3 [2023-03-09 10:15:17,752][22664] Conv encoder output size: 512 [2023-03-09 10:15:17,753][22664] Policy head output size: 512 [2023-03-09 10:15:17,778][22664] Loading state from checkpoint /mnt/Lata/projects/samplefactory/train_dir/default_experiment/checkpoint_p0/checkpoint_000000983_4026368.pth... [2023-03-09 10:15:18,447][22664] Num frames 100... [2023-03-09 10:15:18,532][22664] Num frames 200... [2023-03-09 10:15:18,621][22664] Num frames 300... [2023-03-09 10:15:18,746][22664] Avg episode rewards: #0: 3.840, true rewards: #0: 3.840 [2023-03-09 10:15:18,746][22664] Avg episode reward: 3.840, avg true_objective: 3.840 [2023-03-09 10:15:18,761][22664] Num frames 400... [2023-03-09 10:15:18,854][22664] Num frames 500... [2023-03-09 10:15:18,940][22664] Num frames 600... [2023-03-09 10:15:19,023][22664] Num frames 700... [2023-03-09 10:15:19,110][22664] Num frames 800... [2023-03-09 10:15:19,161][22664] Avg episode rewards: #0: 5.000, true rewards: #0: 4.000 [2023-03-09 10:15:19,162][22664] Avg episode reward: 5.000, avg true_objective: 4.000 [2023-03-09 10:15:19,247][22664] Num frames 900... [2023-03-09 10:15:19,332][22664] Num frames 1000... [2023-03-09 10:15:19,416][22664] Num frames 1100... [2023-03-09 10:15:19,502][22664] Num frames 1200... [2023-03-09 10:15:19,588][22664] Num frames 1300... [2023-03-09 10:15:19,680][22664] Avg episode rewards: #0: 6.147, true rewards: #0: 4.480 [2023-03-09 10:15:19,680][22664] Avg episode reward: 6.147, avg true_objective: 4.480 [2023-03-09 10:15:19,737][22664] Num frames 1400... [2023-03-09 10:15:19,826][22664] Num frames 1500... [2023-03-09 10:15:19,911][22664] Num frames 1600... [2023-03-09 10:15:19,997][22664] Num frames 1700... [2023-03-09 10:15:20,075][22664] Avg episode rewards: #0: 5.570, true rewards: #0: 4.320 [2023-03-09 10:15:20,076][22664] Avg episode reward: 5.570, avg true_objective: 4.320 [2023-03-09 10:15:20,157][22664] Num frames 1800... [2023-03-09 10:15:20,241][22664] Num frames 1900... [2023-03-09 10:15:20,364][22664] Avg episode rewards: #0: 4.968, true rewards: #0: 3.968 [2023-03-09 10:15:20,366][22664] Avg episode reward: 4.968, avg true_objective: 3.968 [2023-03-09 10:15:20,430][22664] Num frames 2000... [2023-03-09 10:15:20,538][22664] Num frames 2100... [2023-03-09 10:15:20,625][22664] Num frames 2200... [2023-03-09 10:15:20,711][22664] Num frames 2300... [2023-03-09 10:15:20,797][22664] Num frames 2400... [2023-03-09 10:15:20,879][22664] Avg episode rewards: #0: 5.053, true rewards: #0: 4.053 [2023-03-09 10:15:20,880][22664] Avg episode reward: 5.053, avg true_objective: 4.053 [2023-03-09 10:15:20,949][22664] Num frames 2500... [2023-03-09 10:15:21,032][22664] Num frames 2600... [2023-03-09 10:15:21,116][22664] Num frames 2700... [2023-03-09 10:15:21,200][22664] Num frames 2800... [2023-03-09 10:15:21,322][22664] Avg episode rewards: #0: 5.114, true rewards: #0: 4.114 [2023-03-09 10:15:21,323][22664] Avg episode reward: 5.114, avg true_objective: 4.114 [2023-03-09 10:15:21,347][22664] Num frames 2900... [2023-03-09 10:15:21,443][22664] Num frames 3000... [2023-03-09 10:15:21,528][22664] Num frames 3100... [2023-03-09 10:15:21,613][22664] Num frames 3200... [2023-03-09 10:15:21,698][22664] Num frames 3300... [2023-03-09 10:15:21,785][22664] Num frames 3400... [2023-03-09 10:15:21,859][22664] Avg episode rewards: #0: 5.405, true rewards: #0: 4.280 [2023-03-09 10:15:21,861][22664] Avg episode reward: 5.405, avg true_objective: 4.280 [2023-03-09 10:15:21,946][22664] Num frames 3500... [2023-03-09 10:15:22,032][22664] Num frames 3600... [2023-03-09 10:15:22,119][22664] Num frames 3700... [2023-03-09 10:15:22,206][22664] Num frames 3800... [2023-03-09 10:15:22,295][22664] Num frames 3900... [2023-03-09 10:15:22,382][22664] Num frames 4000... [2023-03-09 10:15:22,471][22664] Num frames 4100... [2023-03-09 10:15:22,550][22664] Avg episode rewards: #0: 6.031, true rewards: #0: 4.587 [2023-03-09 10:15:22,551][22664] Avg episode reward: 6.031, avg true_objective: 4.587 [2023-03-09 10:15:22,613][22664] Num frames 4200... [2023-03-09 10:15:22,699][22664] Num frames 4300... [2023-03-09 10:15:22,784][22664] Num frames 4400... [2023-03-09 10:15:22,870][22664] Num frames 4500... [2023-03-09 10:15:22,955][22664] Num frames 4600... [2023-03-09 10:15:23,043][22664] Avg episode rewards: #0: 6.340, true rewards: #0: 4.640 [2023-03-09 10:15:23,044][22664] Avg episode reward: 6.340, avg true_objective: 4.640 [2023-03-09 10:15:28,619][22664] Replay video saved to /mnt/Lata/projects/samplefactory/train_dir/default_experiment/replay.mp4! [2023-03-09 10:16:02,805][22664] The model has been pushed to https://huggingface.co/Rolo/doom_health_w128-epw64-r32_b4096-2b [2023-03-09 10:31:25,871][118949] Saving configuration to /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/config.json... [2023-03-09 10:31:25,873][118949] Rollout worker 0 uses device cpu [2023-03-09 10:31:25,873][118949] Rollout worker 1 uses device cpu [2023-03-09 10:31:25,874][118949] Rollout worker 2 uses device cpu [2023-03-09 10:31:25,874][118949] Rollout worker 3 uses device cpu [2023-03-09 10:31:25,875][118949] Rollout worker 4 uses device cpu [2023-03-09 10:31:25,876][118949] Rollout worker 5 uses device cpu [2023-03-09 10:31:25,877][118949] Rollout worker 6 uses device cpu [2023-03-09 10:31:25,878][118949] Rollout worker 7 uses device cpu [2023-03-09 10:31:25,879][118949] Rollout worker 8 uses device cpu [2023-03-09 10:31:25,879][118949] Rollout worker 9 uses device cpu [2023-03-09 10:31:25,880][118949] Rollout worker 10 uses device cpu [2023-03-09 10:31:25,881][118949] Rollout worker 11 uses device cpu [2023-03-09 10:31:25,882][118949] Rollout worker 12 uses device cpu [2023-03-09 10:31:25,883][118949] Rollout worker 13 uses device cpu [2023-03-09 10:31:25,884][118949] Rollout worker 14 uses device cpu [2023-03-09 10:31:25,885][118949] Rollout worker 15 uses device cpu [2023-03-09 10:31:25,886][118949] Rollout worker 16 uses device cpu [2023-03-09 10:31:25,887][118949] Rollout worker 17 uses device cpu [2023-03-09 10:31:25,888][118949] Rollout worker 18 uses device cpu [2023-03-09 10:31:25,889][118949] Rollout worker 19 uses device cpu [2023-03-09 10:31:25,889][118949] Rollout worker 20 uses device cpu [2023-03-09 10:31:25,890][118949] Rollout worker 21 uses device cpu [2023-03-09 10:31:25,891][118949] Rollout worker 22 uses device cpu [2023-03-09 10:31:25,891][118949] Rollout worker 23 uses device cpu [2023-03-09 10:31:25,892][118949] Rollout worker 24 uses device cpu [2023-03-09 10:31:25,894][118949] Rollout worker 25 uses device cpu [2023-03-09 10:31:25,894][118949] Rollout worker 26 uses device cpu [2023-03-09 10:31:25,895][118949] Rollout worker 27 uses device cpu [2023-03-09 10:31:25,896][118949] Rollout worker 28 uses device cpu [2023-03-09 10:31:25,897][118949] Rollout worker 29 uses device cpu [2023-03-09 10:31:25,898][118949] Rollout worker 30 uses device cpu [2023-03-09 10:31:25,898][118949] Rollout worker 31 uses device cpu [2023-03-09 10:31:25,900][118949] Rollout worker 32 uses device cpu [2023-03-09 10:31:25,901][118949] Rollout worker 33 uses device cpu [2023-03-09 10:31:25,902][118949] Rollout worker 34 uses device cpu [2023-03-09 10:31:25,902][118949] Rollout worker 35 uses device cpu [2023-03-09 10:31:25,903][118949] Rollout worker 36 uses device cpu [2023-03-09 10:31:25,904][118949] Rollout worker 37 uses device cpu [2023-03-09 10:31:25,905][118949] Rollout worker 38 uses device cpu [2023-03-09 10:31:25,906][118949] Rollout worker 39 uses device cpu [2023-03-09 10:31:25,906][118949] Rollout worker 40 uses device cpu [2023-03-09 10:31:25,907][118949] Rollout worker 41 uses device cpu [2023-03-09 10:31:25,908][118949] Rollout worker 42 uses device cpu [2023-03-09 10:31:25,909][118949] Rollout worker 43 uses device cpu [2023-03-09 10:31:25,910][118949] Rollout worker 44 uses device cpu [2023-03-09 10:31:25,911][118949] Rollout worker 45 uses device cpu [2023-03-09 10:31:25,912][118949] Rollout worker 46 uses device cpu [2023-03-09 10:31:25,913][118949] Rollout worker 47 uses device cpu [2023-03-09 10:31:25,913][118949] Rollout worker 48 uses device cpu [2023-03-09 10:31:25,914][118949] Rollout worker 49 uses device cpu [2023-03-09 10:31:25,915][118949] Rollout worker 50 uses device cpu [2023-03-09 10:31:25,916][118949] Rollout worker 51 uses device cpu [2023-03-09 10:31:25,917][118949] Rollout worker 52 uses device cpu [2023-03-09 10:31:25,918][118949] Rollout worker 53 uses device cpu [2023-03-09 10:31:25,918][118949] Rollout worker 54 uses device cpu [2023-03-09 10:31:25,919][118949] Rollout worker 55 uses device cpu [2023-03-09 10:31:25,920][118949] Rollout worker 56 uses device cpu [2023-03-09 10:31:25,921][118949] Rollout worker 57 uses device cpu [2023-03-09 10:31:25,922][118949] Rollout worker 58 uses device cpu [2023-03-09 10:31:25,923][118949] Rollout worker 59 uses device cpu [2023-03-09 10:31:25,923][118949] Rollout worker 60 uses device cpu [2023-03-09 10:31:25,924][118949] Rollout worker 61 uses device cpu [2023-03-09 10:31:25,926][118949] Rollout worker 62 uses device cpu [2023-03-09 10:31:25,927][118949] Rollout worker 63 uses device cpu [2023-03-09 10:31:25,927][118949] Rollout worker 64 uses device cpu [2023-03-09 10:31:25,928][118949] Rollout worker 65 uses device cpu [2023-03-09 10:31:25,929][118949] Rollout worker 66 uses device cpu [2023-03-09 10:31:25,930][118949] Rollout worker 67 uses device cpu [2023-03-09 10:31:25,931][118949] Rollout worker 68 uses device cpu [2023-03-09 10:31:25,931][118949] Rollout worker 69 uses device cpu [2023-03-09 10:31:25,932][118949] Rollout worker 70 uses device cpu [2023-03-09 10:31:25,933][118949] Rollout worker 71 uses device cpu [2023-03-09 10:31:25,934][118949] Rollout worker 72 uses device cpu [2023-03-09 10:31:25,935][118949] Rollout worker 73 uses device cpu [2023-03-09 10:31:25,935][118949] Rollout worker 74 uses device cpu [2023-03-09 10:31:25,936][118949] Rollout worker 75 uses device cpu [2023-03-09 10:31:25,938][118949] Rollout worker 76 uses device cpu [2023-03-09 10:31:25,938][118949] Rollout worker 77 uses device cpu [2023-03-09 10:31:25,939][118949] Rollout worker 78 uses device cpu [2023-03-09 10:31:25,940][118949] Rollout worker 79 uses device cpu [2023-03-09 10:31:25,941][118949] Rollout worker 80 uses device cpu [2023-03-09 10:31:25,942][118949] Rollout worker 81 uses device cpu [2023-03-09 10:31:25,943][118949] Rollout worker 82 uses device cpu [2023-03-09 10:31:25,943][118949] Rollout worker 83 uses device cpu [2023-03-09 10:31:25,944][118949] Rollout worker 84 uses device cpu [2023-03-09 10:31:25,945][118949] Rollout worker 85 uses device cpu [2023-03-09 10:31:25,946][118949] Rollout worker 86 uses device cpu [2023-03-09 10:31:25,947][118949] Rollout worker 87 uses device cpu [2023-03-09 10:31:25,947][118949] Rollout worker 88 uses device cpu [2023-03-09 10:31:25,949][118949] Rollout worker 89 uses device cpu [2023-03-09 10:31:25,950][118949] Rollout worker 90 uses device cpu [2023-03-09 10:31:25,951][118949] Rollout worker 91 uses device cpu [2023-03-09 10:31:25,951][118949] Rollout worker 92 uses device cpu [2023-03-09 10:31:25,952][118949] Rollout worker 93 uses device cpu [2023-03-09 10:31:25,953][118949] Rollout worker 94 uses device cpu [2023-03-09 10:31:25,954][118949] Rollout worker 95 uses device cpu [2023-03-09 10:31:25,955][118949] Rollout worker 96 uses device cpu [2023-03-09 10:31:25,955][118949] Rollout worker 97 uses device cpu [2023-03-09 10:31:25,956][118949] Rollout worker 98 uses device cpu [2023-03-09 10:31:25,958][118949] Rollout worker 99 uses device cpu [2023-03-09 10:31:25,958][118949] Rollout worker 100 uses device cpu [2023-03-09 10:31:25,959][118949] Rollout worker 101 uses device cpu [2023-03-09 10:31:25,960][118949] Rollout worker 102 uses device cpu [2023-03-09 10:31:25,961][118949] Rollout worker 103 uses device cpu [2023-03-09 10:31:25,962][118949] Rollout worker 104 uses device cpu [2023-03-09 10:31:25,963][118949] Rollout worker 105 uses device cpu [2023-03-09 10:31:25,963][118949] Rollout worker 106 uses device cpu [2023-03-09 10:31:25,964][118949] Rollout worker 107 uses device cpu [2023-03-09 10:31:25,965][118949] Rollout worker 108 uses device cpu [2023-03-09 10:31:25,966][118949] Rollout worker 109 uses device cpu [2023-03-09 10:31:25,967][118949] Rollout worker 110 uses device cpu [2023-03-09 10:31:25,967][118949] Rollout worker 111 uses device cpu [2023-03-09 10:31:25,969][118949] Rollout worker 112 uses device cpu [2023-03-09 10:31:25,970][118949] Rollout worker 113 uses device cpu [2023-03-09 10:31:25,970][118949] Rollout worker 114 uses device cpu [2023-03-09 10:31:25,971][118949] Rollout worker 115 uses device cpu [2023-03-09 10:31:25,972][118949] Rollout worker 116 uses device cpu [2023-03-09 10:31:25,973][118949] Rollout worker 117 uses device cpu [2023-03-09 10:31:25,974][118949] Rollout worker 118 uses device cpu [2023-03-09 10:31:25,975][118949] Rollout worker 119 uses device cpu [2023-03-09 10:31:25,975][118949] Rollout worker 120 uses device cpu [2023-03-09 10:31:25,976][118949] Rollout worker 121 uses device cpu [2023-03-09 10:31:25,977][118949] Rollout worker 122 uses device cpu [2023-03-09 10:31:25,978][118949] Rollout worker 123 uses device cpu [2023-03-09 10:31:25,979][118949] Rollout worker 124 uses device cpu [2023-03-09 10:31:25,980][118949] Rollout worker 125 uses device cpu [2023-03-09 10:31:25,981][118949] Rollout worker 126 uses device cpu [2023-03-09 10:31:25,981][118949] Rollout worker 127 uses device cpu [2023-03-09 10:31:28,229][118949] Using GPUs [0] for process 0 (actually maps to GPUs [0]) [2023-03-09 10:31:28,230][118949] InferenceWorker_p0-w0: min num requests: 42 [2023-03-09 10:31:28,567][118949] Starting all processes... [2023-03-09 10:31:28,568][118949] Starting process learner_proc0 [2023-03-09 10:31:29,471][118949] Starting all processes... [2023-03-09 10:31:29,473][119240] Using GPUs [0] for process 0 (actually maps to GPUs [0]) [2023-03-09 10:31:29,473][119240] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0 [2023-03-09 10:31:29,478][118949] Starting process inference_proc0-0 [2023-03-09 10:31:29,482][119240] Num visible devices: 1 [2023-03-09 10:31:29,479][118949] Starting process rollout_proc2 [2023-03-09 10:31:29,479][118949] Starting process rollout_proc5 [2023-03-09 10:31:29,487][119240] Starting seed is not provided [2023-03-09 10:31:29,487][119240] Using GPUs [0] for process 0 (actually maps to GPUs [0]) [2023-03-09 10:31:29,487][119240] Initializing actor-critic model on device cuda:0 [2023-03-09 10:31:29,487][119240] RunningMeanStd input shape: (3, 72, 128) [2023-03-09 10:31:29,480][118949] Starting process rollout_proc8 [2023-03-09 10:31:29,488][119240] RunningMeanStd input shape: (1,) [2023-03-09 10:31:29,480][118949] Starting process rollout_proc11 [2023-03-09 10:31:29,485][118949] Starting process rollout_proc14 [2023-03-09 10:31:29,498][119240] ConvEncoder: input_channels=3 [2023-03-09 10:31:29,486][118949] Starting process rollout_proc17 [2023-03-09 10:31:29,487][118949] Starting process rollout_proc20 [2023-03-09 10:31:29,488][118949] Starting process rollout_proc23 [2023-03-09 10:31:29,488][118949] Starting process rollout_proc26 [2023-03-09 10:31:29,489][118949] Starting process rollout_proc29 [2023-03-09 10:31:29,489][118949] Starting process rollout_proc32 [2023-03-09 10:31:29,490][118949] Starting process rollout_proc35 [2023-03-09 10:31:29,490][118949] Starting process rollout_proc38 [2023-03-09 10:31:29,491][118949] Starting process rollout_proc41 [2023-03-09 10:31:29,493][118949] Starting process rollout_proc44 [2023-03-09 10:31:29,521][118949] Starting process rollout_proc9 [2023-03-09 10:31:29,522][118949] Starting process rollout_proc3 [2023-03-09 10:31:29,526][118949] Starting process rollout_proc6 [2023-03-09 10:31:29,530][118949] Starting process rollout_proc18 [2023-03-09 10:31:29,535][118949] Starting process rollout_proc15 [2023-03-09 10:31:29,537][118949] Starting process rollout_proc21 [2023-03-09 10:31:29,545][118949] Starting process rollout_proc24 [2023-03-09 10:31:29,551][118949] Starting process rollout_proc27 [2023-03-09 10:31:29,553][118949] Starting process rollout_proc12 [2023-03-09 10:31:29,560][118949] Starting process rollout_proc33 [2023-03-09 10:31:29,560][118949] Starting process rollout_proc30 [2023-03-09 10:31:29,569][118949] Starting process rollout_proc36 [2023-03-09 10:31:29,576][118949] Starting process rollout_proc42 [2023-03-09 10:31:29,602][119240] Conv encoder output size: 512 [2023-03-09 10:31:29,603][119240] Policy head output size: 512 [2023-03-09 10:31:29,582][118949] Starting process rollout_proc39 [2023-03-09 10:31:29,595][118949] Starting process rollout_proc45 [2023-03-09 10:31:29,614][119240] Created Actor Critic model with architecture: [2023-03-09 10:31:29,614][119240] ActorCriticSharedWeights( (obs_normalizer): ObservationNormalizer( (running_mean_std): RunningMeanStdDictInPlace( (running_mean_std): ModuleDict( (obs): RunningMeanStdInPlace() ) ) ) (returns_normalizer): RecursiveScriptModule(original_name=RunningMeanStdInPlace) (encoder): VizdoomEncoder( (basic_encoder): ConvEncoder( (enc): RecursiveScriptModule( original_name=ConvEncoderImpl (conv_head): RecursiveScriptModule( original_name=Sequential (0): RecursiveScriptModule(original_name=Conv2d) (1): RecursiveScriptModule(original_name=ELU) (2): RecursiveScriptModule(original_name=Conv2d) (3): RecursiveScriptModule(original_name=ELU) (4): RecursiveScriptModule(original_name=Conv2d) (5): RecursiveScriptModule(original_name=ELU) ) (mlp_layers): RecursiveScriptModule( original_name=Sequential (0): RecursiveScriptModule(original_name=Linear) (1): RecursiveScriptModule(original_name=ELU) ) ) ) ) (core): ModelCoreRNN( (core): GRU(512, 512) ) (decoder): MlpDecoder( (mlp): Identity() ) (critic_linear): Linear(in_features=512, out_features=1, bias=True) (action_parameterization): ActionParameterizationDefault( (distribution_linear): Linear(in_features=512, out_features=5, bias=True) ) ) [2023-03-09 10:31:29,597][118949] Starting process rollout_proc10 [2023-03-09 10:31:29,599][118949] Starting process rollout_proc4 [2023-03-09 10:31:29,604][118949] Starting process rollout_proc7 [2023-03-09 10:31:29,616][118949] Starting process rollout_proc16 [2023-03-09 10:31:29,619][118949] Starting process rollout_proc19 [2023-03-09 10:31:29,624][118949] Starting process rollout_proc25 [2023-03-09 10:31:29,631][118949] Starting process rollout_proc22 [2023-03-09 10:31:29,638][118949] Starting process rollout_proc34 [2023-03-09 10:31:29,640][118949] Starting process rollout_proc13 [2023-03-09 10:31:29,645][118949] Starting process rollout_proc28 [2023-03-09 10:31:29,651][118949] Starting process rollout_proc31 [2023-03-09 10:31:29,654][118949] Starting process rollout_proc37 [2023-03-09 10:31:29,658][118949] Starting process rollout_proc40 [2023-03-09 10:31:29,661][118949] Starting process rollout_proc43 [2023-03-09 10:31:29,666][118949] Starting process rollout_proc46 [2023-03-09 10:31:29,676][118949] Starting process rollout_proc47 [2023-03-09 10:31:29,678][118949] Starting process rollout_proc50 [2023-03-09 10:31:29,678][118949] Starting process rollout_proc53 [2023-03-09 10:31:29,680][118949] Starting process rollout_proc56 [2023-03-09 10:31:29,686][118949] Starting process rollout_proc59 [2023-03-09 10:31:29,686][118949] Starting process rollout_proc62 [2023-03-09 10:31:29,693][118949] Starting process rollout_proc65 [2023-03-09 10:31:29,707][118949] Starting process rollout_proc68 [2023-03-09 10:31:29,709][118949] Starting process rollout_proc71 [2023-03-09 10:31:29,709][118949] Starting process rollout_proc74 [2023-03-09 10:31:29,714][118949] Starting process rollout_proc77 [2023-03-09 10:31:29,715][118949] Starting process rollout_proc80 [2023-03-09 10:31:29,725][118949] Starting process rollout_proc83 [2023-03-09 10:31:29,728][118949] Starting process rollout_proc86 [2023-03-09 10:31:29,733][118949] Starting process rollout_proc89 [2023-03-09 10:31:29,748][118949] Starting process rollout_proc48 [2023-03-09 10:31:29,753][118949] Starting process rollout_proc51 [2023-03-09 10:31:29,754][118949] Starting process rollout_proc54 [2023-03-09 10:31:29,767][118949] Starting process rollout_proc60 [2023-03-09 10:31:29,771][118949] Starting process rollout_proc63 [2023-03-09 10:31:29,773][118949] Starting process rollout_proc57 [2023-03-09 10:31:29,783][118949] Starting process rollout_proc69 [2023-03-09 10:31:29,784][118949] Starting process rollout_proc66 [2023-03-09 10:31:29,800][118949] Starting process rollout_proc75 [2023-03-09 10:31:29,803][118949] Starting process rollout_proc81 [2023-03-09 10:31:29,806][118949] Starting process rollout_proc78 [2023-03-09 10:31:29,814][118949] Starting process rollout_proc72 [2023-03-09 10:31:29,815][118949] Starting process rollout_proc84 [2023-03-09 10:31:29,824][118949] Starting process rollout_proc90 [2023-03-09 10:31:29,834][118949] Starting process rollout_proc87 [2023-03-09 10:31:29,846][118949] Starting process rollout_proc61 [2023-03-09 10:31:29,866][118949] Starting process rollout_proc55 [2023-03-09 10:31:29,910][118949] Starting process rollout_proc82 [2023-03-09 10:31:29,914][118949] Starting process rollout_proc52 [2023-03-09 10:31:29,915][118949] Starting process rollout_proc91 [2023-03-09 10:31:29,918][118949] Starting process rollout_proc73 [2023-03-09 10:31:29,919][118949] Starting process rollout_proc85 [2023-03-09 10:31:29,919][118949] Starting process rollout_proc76 [2023-03-09 10:31:29,923][118949] Starting process rollout_proc79 [2023-03-09 10:31:29,925][118949] Starting process rollout_proc64 [2023-03-09 10:31:29,926][118949] Starting process rollout_proc67 [2023-03-09 10:31:29,929][118949] Starting process rollout_proc88 [2023-03-09 10:31:29,930][118949] Starting process rollout_proc49 [2023-03-09 10:31:29,931][118949] Starting process rollout_proc70 [2023-03-09 10:31:29,934][118949] Starting process rollout_proc58 [2023-03-09 10:31:29,941][118949] Starting process rollout_proc92 [2023-03-09 10:31:29,945][118949] Starting process rollout_proc95 [2023-03-09 10:31:29,970][118949] Starting process rollout_proc98 [2023-03-09 10:31:29,986][118949] Starting process rollout_proc101 [2023-03-09 10:31:29,992][118949] Starting process rollout_proc104 [2023-03-09 10:31:30,018][118949] Starting process rollout_proc107 [2023-03-09 10:31:30,024][118949] Starting process rollout_proc110 [2023-03-09 10:31:30,027][118949] Starting process rollout_proc113 [2023-03-09 10:31:30,030][118949] Starting process rollout_proc116 [2023-03-09 10:31:30,039][118949] Starting process rollout_proc119 [2023-03-09 10:31:30,048][118949] Starting process rollout_proc122 [2023-03-09 10:31:30,069][118949] Starting process rollout_proc125 [2023-03-09 10:31:30,082][118949] Starting process rollout_proc93 [2023-03-09 10:31:30,096][118949] Starting process rollout_proc96 [2023-03-09 10:31:30,135][118949] Starting process rollout_proc102 [2023-03-09 10:31:30,136][118949] Starting process rollout_proc105 [2023-03-09 10:31:30,167][118949] Starting process rollout_proc99 [2023-03-09 10:31:30,202][118949] Starting process rollout_proc108 [2023-03-09 10:31:30,212][118949] Starting process rollout_proc111 [2023-03-09 10:31:30,222][118949] Starting process rollout_proc114 [2023-03-09 10:31:30,241][118949] Starting process rollout_proc120 [2023-03-09 10:31:30,241][118949] Starting process rollout_proc126 [2023-03-09 10:31:30,241][118949] Starting process rollout_proc123 [2023-03-09 10:31:30,241][118949] Starting process rollout_proc97 [2023-03-09 10:31:30,270][118949] Starting process rollout_proc94 [2023-03-09 10:31:30,270][118949] Starting process rollout_proc117 [2023-03-09 10:31:30,284][118949] Starting process rollout_proc103 [2023-03-09 10:31:30,321][118949] Starting process rollout_proc100 [2023-03-09 10:31:30,321][118949] Starting process rollout_proc115 [2023-03-09 10:31:30,334][118949] Starting process rollout_proc112 [2023-03-09 10:31:30,340][118949] Starting process rollout_proc106 [2023-03-09 10:31:30,348][118949] Starting process rollout_proc121 [2023-03-09 10:31:30,349][118949] Starting process rollout_proc109 [2023-03-09 10:31:30,447][118949] Starting process rollout_proc127 [2023-03-09 10:31:30,481][118949] Starting process rollout_proc124 [2023-03-09 10:31:30,542][118949] Starting process rollout_proc118 [2023-03-09 10:31:31,624][119390] Worker 5 uses CPU cores [5] [2023-03-09 10:31:32,072][119394] Worker 23 uses CPU cores [23] [2023-03-09 10:31:32,106][118949] Starting process rollout_proc0 [2023-03-09 10:31:32,130][119383] Using GPUs [0] for process 0 (actually maps to GPUs [0]) [2023-03-09 10:31:32,130][119383] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0 [2023-03-09 10:31:32,150][119389] Worker 2 uses CPU cores [2] [2023-03-09 10:31:32,164][119383] Num visible devices: 1 [2023-03-09 10:31:32,208][119395] Worker 11 uses CPU cores [11] [2023-03-09 10:31:32,210][119478] Worker 12 uses CPU cores [12] [2023-03-09 10:31:32,228][119474] Worker 18 uses CPU cores [18] [2023-03-09 10:31:32,254][119388] Worker 8 uses CPU cores [8] [2023-03-09 10:31:32,260][119477] Worker 33 uses CPU cores [33] [2023-03-09 10:31:32,275][118949] Starting process rollout_proc1 [2023-03-09 10:31:32,365][119501] Worker 46 uses CPU cores [46] [2023-03-09 10:31:32,429][119489] Worker 10 uses CPU cores [10] [2023-03-09 10:31:32,456][119481] Worker 39 uses CPU cores [39] [2023-03-09 10:31:32,460][119392] Worker 14 uses CPU cores [14] [2023-03-09 10:31:32,485][119399] Worker 35 uses CPU cores [35] [2023-03-09 10:31:32,498][119464] Worker 41 uses CPU cores [41] [2023-03-09 10:31:32,558][119396] Worker 26 uses CPU cores [26] [2023-03-09 10:31:32,588][119466] Worker 44 uses CPU cores [44] [2023-03-09 10:31:32,623][119484] Worker 45 uses CPU cores [45] [2023-03-09 10:31:32,666][119485] Worker 42 uses CPU cores [42] [2023-03-09 10:31:32,690][119393] Worker 20 uses CPU cores [20] [2023-03-09 10:31:32,716][119499] Worker 40 uses CPU cores [40] [2023-03-09 10:31:32,716][119496] Worker 37 uses CPU cores [37] [2023-03-09 10:31:32,716][119503] Worker 50 uses CPU cores [50] [2023-03-09 10:31:32,728][119480] Worker 30 uses CPU cores [30] [2023-03-09 10:31:32,741][119491] Worker 25 uses CPU cores [25] [2023-03-09 10:31:32,759][119508] Worker 68 uses CPU cores [68] [2023-03-09 10:31:32,788][119490] Worker 19 uses CPU cores [19] [2023-03-09 10:31:32,798][119479] Worker 27 uses CPU cores [27] [2023-03-09 10:31:32,799][119462] Worker 38 uses CPU cores [38] [2023-03-09 10:31:32,812][119476] Worker 21 uses CPU cores [21] [2023-03-09 10:31:32,820][119495] Worker 34 uses CPU cores [34] [2023-03-09 10:31:32,836][119497] Worker 13 uses CPU cores [13] [2023-03-09 10:31:32,844][119475] Worker 24 uses CPU cores [24] [2023-03-09 10:31:32,860][119506] Worker 62 uses CPU cores [62] [2023-03-09 10:31:32,868][119511] Worker 80 uses CPU cores [80] [2023-03-09 10:31:32,880][119533] Worker 55 uses CPU cores [55] [2023-03-09 10:31:32,885][119504] Worker 53 uses CPU cores [53] [2023-03-09 10:31:32,900][119515] Worker 89 uses CPU cores [89] [2023-03-09 10:31:32,904][119397] Worker 29 uses CPU cores [29] [2023-03-09 10:31:32,904][119473] Worker 15 uses CPU cores [15] [2023-03-09 10:31:32,910][119494] Worker 31 uses CPU cores [31] [2023-03-09 10:31:32,916][119502] Worker 47 uses CPU cores [47] [2023-03-09 10:31:32,928][119488] Worker 16 uses CPU cores [16] [2023-03-09 10:31:32,931][119510] Worker 74 uses CPU cores [74] [2023-03-09 10:31:32,939][119483] Worker 36 uses CPU cores [36] [2023-03-09 10:31:32,940][119512] Worker 77 uses CPU cores [77] [2023-03-09 10:31:32,980][119391] Worker 17 uses CPU cores [17] [2023-03-09 10:31:32,993][119487] Worker 7 uses CPU cores [7] [2023-03-09 10:31:33,020][119469] Worker 9 uses CPU cores [9] [2023-03-09 10:31:33,032][119509] Worker 65 uses CPU cores [65] [2023-03-09 10:31:33,038][119534] Worker 82 uses CPU cores [82] [2023-03-09 10:31:33,049][119493] Worker 22 uses CPU cores [22] [2023-03-09 10:31:33,060][119398] Worker 32 uses CPU cores [32] [2023-03-09 10:31:33,070][119505] Worker 59 uses CPU cores [59] [2023-03-09 10:31:33,080][119514] Worker 83 uses CPU cores [83] [2023-03-09 10:31:33,080][119507] Worker 56 uses CPU cores [56] [2023-03-09 10:31:33,104][119516] Worker 86 uses CPU cores [86] [2023-03-09 10:31:33,128][119523] Worker 84 uses CPU cores [84] [2023-03-09 10:31:33,132][119500] Worker 43 uses CPU cores [43] [2023-03-09 10:31:33,134][119486] Worker 4 uses CPU cores [4] [2023-03-09 10:31:33,148][119520] Worker 51 uses CPU cores [51] [2023-03-09 10:31:33,152][119521] Worker 90 uses CPU cores [90] [2023-03-09 10:31:33,153][119498] Worker 28 uses CPU cores [28] [2023-03-09 10:31:33,180][119851] Worker 125 uses CPU cores [125] [2023-03-09 10:31:33,200][119518] Worker 54 uses CPU cores [54] [2023-03-09 10:31:33,204][119526] Worker 66 uses CPU cores [66] [2023-03-09 10:31:33,208][119525] Worker 78 uses CPU cores [78] [2023-03-09 10:31:33,224][119470] Worker 3 uses CPU cores [3] [2023-03-09 10:31:33,243][119472] Worker 6 uses CPU cores [6] [2023-03-09 10:31:33,244][119529] Worker 69 uses CPU cores [69] [2023-03-09 10:31:33,248][120904] Worker 124 uses CPU cores [124] [2023-03-09 10:31:33,256][119548] Worker 58 uses CPU cores [58] [2023-03-09 10:31:33,264][119517] Worker 60 uses CPU cores [60] [2023-03-09 10:31:33,274][119547] Worker 95 uses CPU cores [95] [2023-03-09 10:31:33,280][119543] Worker 67 uses CPU cores [67] [2023-03-09 10:31:33,288][119937] Worker 93 uses CPU cores [93] [2023-03-09 10:31:33,292][119527] Worker 63 uses CPU cores [63] [2023-03-09 10:31:33,296][119522] Worker 72 uses CPU cores [72] [2023-03-09 10:31:33,304][119530] Worker 48 uses CPU cores [48] [2023-03-09 10:31:33,305][119531] Worker 57 uses CPU cores [57] [2023-03-09 10:31:33,309][119519] Worker 81 uses CPU cores [81] [2023-03-09 10:31:33,312][119528] Worker 87 uses CPU cores [87] [2023-03-09 10:31:33,316][119540] Worker 76 uses CPU cores [76] [2023-03-09 10:31:33,320][119807] Worker 116 uses CPU cores [116] [2023-03-09 10:31:33,323][119546] Worker 92 uses CPU cores [92] [2023-03-09 10:31:33,330][120005] Worker 108 uses CPU cores [108] [2023-03-09 10:31:33,336][119808] Worker 119 uses CPU cores [119] [2023-03-09 10:31:33,344][119532] Worker 61 uses CPU cores [61] [2023-03-09 10:31:33,372][119537] Worker 73 uses CPU cores [73] [2023-03-09 10:31:33,376][119545] Worker 49 uses CPU cores [49] [2023-03-09 10:31:33,380][120615] Worker 117 uses CPU cores [117] [2023-03-09 10:31:33,392][119900] Worker 122 uses CPU cores [122] [2023-03-09 10:31:33,394][119680] Worker 113 uses CPU cores [113] [2023-03-09 10:31:33,441][120648] Worker 100 uses CPU cores [100] [2023-03-09 10:31:33,448][119524] Worker 75 uses CPU cores [75] [2023-03-09 10:31:33,451][120002] Worker 102 uses CPU cores [102] [2023-03-09 10:31:33,452][119513] Worker 71 uses CPU cores [71] [2023-03-09 10:31:33,452][119538] Worker 85 uses CPU cores [85] [2023-03-09 10:31:33,453][119539] Worker 79 uses CPU cores [79] [2023-03-09 10:31:33,465][119536] Worker 91 uses CPU cores [91] [2023-03-09 10:31:33,467][119541] Worker 88 uses CPU cores [88] [2023-03-09 10:31:33,476][119535] Worker 52 uses CPU cores [52] [2023-03-09 10:31:33,476][119655] Worker 110 uses CPU cores [110] [2023-03-09 10:31:33,480][120134] Worker 120 uses CPU cores [120] [2023-03-09 10:31:33,487][119550] Worker 98 uses CPU cores [98] [2023-03-09 10:31:33,498][119542] Worker 64 uses CPU cores [64] [2023-03-09 10:31:33,498][119544] Worker 70 uses CPU cores [70] [2023-03-09 10:31:33,509][119946] Worker 96 uses CPU cores [96] [2023-03-09 10:31:33,529][120896] Worker 127 uses CPU cores [127] [2023-03-09 10:31:33,544][120004] Worker 99 uses CPU cores [99] [2023-03-09 10:31:33,544][120003] Worker 105 uses CPU cores [105] [2023-03-09 10:31:33,552][121015] Worker 118 uses CPU cores [118] [2023-03-09 10:31:33,558][120652] Worker 112 uses CPU cores [112] [2023-03-09 10:31:33,567][120653] Worker 115 uses CPU cores [115] [2023-03-09 10:31:33,583][119614] Worker 104 uses CPU cores [104] [2023-03-09 10:31:33,587][120717] Worker 106 uses CPU cores [106] [2023-03-09 10:31:33,587][120263] Worker 97 uses CPU cores [97] [2023-03-09 10:31:33,588][119615] Worker 107 uses CPU cores [107] [2023-03-09 10:31:33,588][120040] Worker 111 uses CPU cores [111] [2023-03-09 10:31:33,610][120199] Worker 123 uses CPU cores [123] [2023-03-09 10:31:33,620][120135] Worker 126 uses CPU cores [126] [2023-03-09 10:31:33,668][119549] Worker 101 uses CPU cores [101] [2023-03-09 10:31:33,702][120073] Worker 114 uses CPU cores [114] [2023-03-09 10:31:33,720][120629] Worker 103 uses CPU cores [103] [2023-03-09 10:31:33,720][119240] Using optimizer [2023-03-09 10:31:33,721][119240] Loading state from checkpoint /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000122072_2000027648.pth... [2023-03-09 10:31:33,723][120778] Worker 121 uses CPU cores [121] [2023-03-09 10:31:33,741][119240] Loading model from checkpoint [2023-03-09 10:31:33,744][119240] Loaded experiment state at self.train_step=122072, self.env_steps=2000027648 [2023-03-09 10:31:33,745][119240] Initialized policy 0 weights for model version 122072 [2023-03-09 10:31:33,746][119240] LearnerWorker_p0 finished initialization! [2023-03-09 10:31:33,746][119240] Using GPUs [0] for process 0 (actually maps to GPUs [0]) [2023-03-09 10:31:33,767][120877] Worker 109 uses CPU cores [109] [2023-03-09 10:31:33,771][120550] Worker 94 uses CPU cores [94] [2023-03-09 10:31:33,810][119383] RunningMeanStd input shape: (3, 72, 128) [2023-03-09 10:31:33,810][119383] RunningMeanStd input shape: (1,) [2023-03-09 10:31:33,822][119383] ConvEncoder: input_channels=3 [2023-03-09 10:31:33,898][119383] Conv encoder output size: 512 [2023-03-09 10:31:33,898][119383] Policy head output size: 512 [2023-03-09 10:31:33,902][118949] Fps is (10 sec: nan, 60 sec: nan, 300 sec: nan). Total num frames: 2000027648. Throughput: 0: nan. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) [2023-03-09 10:31:33,926][126685] Worker 1 uses CPU cores [1] [2023-03-09 10:31:33,930][125883] Worker 0 uses CPU cores [0] [2023-03-09 10:31:34,751][118949] Inference worker 0-0 is ready! [2023-03-09 10:31:34,752][118949] All inference workers are ready! Signal rollout workers to start! [2023-03-09 10:31:34,872][125883] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:34,874][120135] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:34,875][120263] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:34,875][119522] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:34,876][120778] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:34,876][119462] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:34,877][119397] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:34,878][119530] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:34,879][119504] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:34,880][119494] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:34,881][119541] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:34,881][119389] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:34,882][119470] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:34,882][119545] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:34,882][119537] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:34,883][119393] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:34,883][120896] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:34,883][119544] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:34,884][119529] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:34,884][119498] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:34,884][119481] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:34,884][119469] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:34,885][119524] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:34,885][119466] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:34,885][119473] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:34,886][119540] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:34,886][119477] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:34,886][120004] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:34,886][119390] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:34,887][119655] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:34,887][119488] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:34,887][119394] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:34,887][120629] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:34,887][119503] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:34,888][119517] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:34,888][119496] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:34,888][119501] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:34,888][119491] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:34,888][119543] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:34,888][119614] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:34,888][119493] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:34,888][119900] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:34,888][119515] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:34,889][120134] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:34,889][119521] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:34,889][119538] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:34,889][119518] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:34,889][120005] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:34,889][119523] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:34,889][120653] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:34,889][119531] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:34,890][119485] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:34,890][119476] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:34,890][119516] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:34,890][119535] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:34,890][119511] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:34,890][119549] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:34,891][119478] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:34,891][119472] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:34,891][120040] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:34,892][120717] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:34,892][119542] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:34,892][119509] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:34,893][119512] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:34,893][119807] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:34,893][119500] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:34,893][120002] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:34,893][119528] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:34,893][119525] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:34,894][119527] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:34,894][119474] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:34,894][120652] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:34,894][119508] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:34,895][119534] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:34,896][119546] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:34,895][119937] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:34,896][120550] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:34,896][121015] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:34,896][119615] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:34,897][120073] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:34,897][119550] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:34,897][119539] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:34,897][119532] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:34,897][119483] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:34,897][119464] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:34,897][119526] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:34,897][119487] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:34,897][119507] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:34,898][119505] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:34,897][120199] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:34,898][119480] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:34,898][119484] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:34,898][119514] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:34,898][119548] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:34,898][119533] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:34,898][120003] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:34,898][119497] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:34,899][119519] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:34,899][119499] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:34,899][119536] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:34,899][119851] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:34,899][119680] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:34,899][119808] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:34,900][119506] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:34,899][120904] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:34,900][119946] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:34,899][119475] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:34,900][119547] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:34,900][119399] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:34,900][119490] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:34,901][119502] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:34,901][120648] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:34,901][119520] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:34,904][119495] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:34,905][119510] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:34,905][119388] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:34,905][119486] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:34,906][119489] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:34,907][119392] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:34,908][119513] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:34,909][120877] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:34,909][119398] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:34,909][119479] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:34,910][119395] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:34,913][119391] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:34,914][119396] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:34,937][120615] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:34,991][126685] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 10:31:35,937][120652] Decorrelating experience for 0 frames... [2023-03-09 10:31:35,944][119389] Decorrelating experience for 0 frames... [2023-03-09 10:31:35,953][119526] Decorrelating experience for 0 frames... [2023-03-09 10:31:36,003][119491] Decorrelating experience for 0 frames... [2023-03-09 10:31:36,006][119477] Decorrelating experience for 0 frames... [2023-03-09 10:31:36,006][120134] Decorrelating experience for 0 frames... [2023-03-09 10:31:36,006][119615] Decorrelating experience for 0 frames... [2023-03-09 10:31:36,007][119528] Decorrelating experience for 0 frames... [2023-03-09 10:31:36,007][120629] Decorrelating experience for 0 frames... [2023-03-09 10:31:36,008][119530] Decorrelating experience for 0 frames... [2023-03-09 10:31:36,108][119527] Decorrelating experience for 0 frames... [2023-03-09 10:31:36,118][119503] Decorrelating experience for 0 frames... [2023-03-09 10:31:36,128][119480] Decorrelating experience for 0 frames... [2023-03-09 10:31:36,180][119491] Decorrelating experience for 32 frames... [2023-03-09 10:31:36,187][119506] Decorrelating experience for 0 frames... [2023-03-09 10:31:36,187][120648] Decorrelating experience for 0 frames... [2023-03-09 10:31:36,189][119529] Decorrelating experience for 0 frames... [2023-03-09 10:31:36,189][119508] Decorrelating experience for 0 frames... [2023-03-09 10:31:36,191][119474] Decorrelating experience for 0 frames... [2023-03-09 10:31:36,192][119499] Decorrelating experience for 0 frames... [2023-03-09 10:31:36,280][119532] Decorrelating experience for 0 frames... [2023-03-09 10:31:36,293][119533] Decorrelating experience for 0 frames... [2023-03-09 10:31:36,358][120904] Decorrelating experience for 0 frames... [2023-03-09 10:31:36,358][120778] Decorrelating experience for 0 frames... [2023-03-09 10:31:36,368][119523] Decorrelating experience for 0 frames... [2023-03-09 10:31:36,370][119474] Decorrelating experience for 32 frames... [2023-03-09 10:31:36,372][119491] Decorrelating experience for 64 frames... [2023-03-09 10:31:36,374][119496] Decorrelating experience for 0 frames... [2023-03-09 10:31:36,375][119900] Decorrelating experience for 0 frames... [2023-03-09 10:31:36,412][119517] Decorrelating experience for 0 frames... [2023-03-09 10:31:36,451][121015] Decorrelating experience for 0 frames... [2023-03-09 10:31:36,464][119533] Decorrelating experience for 32 frames... [2023-03-09 10:31:36,531][120134] Decorrelating experience for 32 frames... [2023-03-09 10:31:36,545][119486] Decorrelating experience for 0 frames... [2023-03-09 10:31:36,556][119537] Decorrelating experience for 0 frames... [2023-03-09 10:31:36,577][119462] Decorrelating experience for 0 frames... [2023-03-09 10:31:36,586][119519] Decorrelating experience for 0 frames... [2023-03-09 10:31:36,623][119515] Decorrelating experience for 0 frames... [2023-03-09 10:31:36,634][119391] Decorrelating experience for 0 frames... [2023-03-09 10:31:36,634][119501] Decorrelating experience for 0 frames... [2023-03-09 10:31:36,635][119655] Decorrelating experience for 0 frames... [2023-03-09 10:31:36,638][120717] Decorrelating experience for 0 frames... [2023-03-09 10:31:36,721][119499] Decorrelating experience for 32 frames... [2023-03-09 10:31:36,722][119513] Decorrelating experience for 0 frames... [2023-03-09 10:31:36,732][119537] Decorrelating experience for 32 frames... [2023-03-09 10:31:36,748][119533] Decorrelating experience for 64 frames... [2023-03-09 10:31:36,763][119489] Decorrelating experience for 0 frames... [2023-03-09 10:31:36,800][119900] Decorrelating experience for 32 frames... [2023-03-09 10:31:36,811][119391] Decorrelating experience for 32 frames... [2023-03-09 10:31:36,813][120717] Decorrelating experience for 32 frames... [2023-03-09 10:31:36,816][120652] Decorrelating experience for 32 frames... [2023-03-09 10:31:36,825][121015] Decorrelating experience for 32 frames... [2023-03-09 10:31:36,897][119513] Decorrelating experience for 32 frames... [2023-03-09 10:31:36,900][119496] Decorrelating experience for 32 frames... [2023-03-09 10:31:36,904][119499] Decorrelating experience for 64 frames... [2023-03-09 10:31:36,930][119536] Decorrelating experience for 0 frames... [2023-03-09 10:31:36,938][119851] Decorrelating experience for 0 frames... [2023-03-09 10:31:36,973][119389] Decorrelating experience for 32 frames... [2023-03-09 10:31:36,987][120199] Decorrelating experience for 0 frames... [2023-03-09 10:31:36,996][119490] Decorrelating experience for 0 frames... [2023-03-09 10:31:36,997][119493] Decorrelating experience for 0 frames... [2023-03-09 10:31:37,009][121015] Decorrelating experience for 64 frames... [2023-03-09 10:31:37,097][120717] Decorrelating experience for 64 frames... [2023-03-09 10:31:37,099][120652] Decorrelating experience for 64 frames... [2023-03-09 10:31:37,100][120615] Decorrelating experience for 0 frames... [2023-03-09 10:31:37,104][119536] Decorrelating experience for 32 frames... [2023-03-09 10:31:37,143][119481] Decorrelating experience for 0 frames... [2023-03-09 10:31:37,157][119389] Decorrelating experience for 64 frames... [2023-03-09 10:31:37,198][119397] Decorrelating experience for 0 frames... [2023-03-09 10:31:37,199][120134] Decorrelating experience for 64 frames... [2023-03-09 10:31:37,201][119503] Decorrelating experience for 32 frames... [2023-03-09 10:31:37,201][119542] Decorrelating experience for 0 frames... [2023-03-09 10:31:37,272][119493] Decorrelating experience for 32 frames... [2023-03-09 10:31:37,298][120717] Decorrelating experience for 96 frames... [2023-03-09 10:31:37,300][119390] Decorrelating experience for 0 frames... [2023-03-09 10:31:37,301][119391] Decorrelating experience for 64 frames... [2023-03-09 10:31:37,347][119462] Decorrelating experience for 32 frames... [2023-03-09 10:31:37,356][119487] Decorrelating experience for 0 frames... [2023-03-09 10:31:37,374][119542] Decorrelating experience for 32 frames... [2023-03-09 10:31:37,391][119536] Decorrelating experience for 64 frames... [2023-03-09 10:31:37,393][119515] Decorrelating experience for 32 frames... [2023-03-09 10:31:37,434][119504] Decorrelating experience for 0 frames... [2023-03-09 10:31:37,445][119523] Decorrelating experience for 32 frames... [2023-03-09 10:31:37,472][119397] Decorrelating experience for 32 frames... [2023-03-09 10:31:37,504][119513] Decorrelating experience for 64 frames... [2023-03-09 10:31:37,512][120615] Decorrelating experience for 32 frames... [2023-03-09 10:31:37,550][119655] Decorrelating experience for 32 frames... [2023-03-09 10:31:37,551][119480] Decorrelating experience for 32 frames... [2023-03-09 10:31:37,552][119469] Decorrelating experience for 0 frames... [2023-03-09 10:31:37,595][119506] Decorrelating experience for 32 frames... [2023-03-09 10:31:37,599][119851] Decorrelating experience for 32 frames... [2023-03-09 10:31:37,618][119481] Decorrelating experience for 32 frames... [2023-03-09 10:31:37,650][119508] Decorrelating experience for 32 frames... [2023-03-09 10:31:37,690][119487] Decorrelating experience for 32 frames... [2023-03-09 10:31:37,697][119615] Decorrelating experience for 32 frames... [2023-03-09 10:31:37,713][119532] Decorrelating experience for 32 frames... [2023-03-09 10:31:37,752][119543] Decorrelating experience for 0 frames... [2023-03-09 10:31:37,753][119548] Decorrelating experience for 0 frames... [2023-03-09 10:31:37,755][120896] Decorrelating experience for 0 frames... [2023-03-09 10:31:37,776][119390] Decorrelating experience for 32 frames... [2023-03-09 10:31:37,798][119474] Decorrelating experience for 64 frames... [2023-03-09 10:31:37,820][119851] Decorrelating experience for 64 frames... [2023-03-09 10:31:37,848][119937] Decorrelating experience for 0 frames... [2023-03-09 10:31:37,873][119490] Decorrelating experience for 32 frames... [2023-03-09 10:31:37,878][119469] Decorrelating experience for 32 frames... [2023-03-09 10:31:37,889][119503] Decorrelating experience for 64 frames... [2023-03-09 10:31:37,934][119506] Decorrelating experience for 64 frames... [2023-03-09 10:31:37,950][120003] Decorrelating experience for 0 frames... [2023-03-09 10:31:37,951][120005] Decorrelating experience for 0 frames... [2023-03-09 10:31:37,955][119615] Decorrelating experience for 64 frames... [2023-03-09 10:31:37,980][120896] Decorrelating experience for 32 frames... [2023-03-09 10:31:38,021][125883] Decorrelating experience for 0 frames... [2023-03-09 10:31:38,051][120615] Decorrelating experience for 64 frames... [2023-03-09 10:31:38,061][119490] Decorrelating experience for 64 frames... [2023-03-09 10:31:38,068][119469] Decorrelating experience for 64 frames... [2023-03-09 10:31:38,120][119500] Decorrelating experience for 0 frames... [2023-03-09 10:31:38,134][119542] Decorrelating experience for 64 frames... [2023-03-09 10:31:38,145][120005] Decorrelating experience for 32 frames... [2023-03-09 10:31:38,155][119808] Decorrelating experience for 0 frames... [2023-03-09 10:31:38,156][120004] Decorrelating experience for 0 frames... [2023-03-09 10:31:38,196][119615] Decorrelating experience for 96 frames... [2023-03-09 10:31:38,205][119393] Decorrelating experience for 0 frames... [2023-03-09 10:31:38,239][119480] Decorrelating experience for 64 frames... [2023-03-09 10:31:38,251][119527] Decorrelating experience for 32 frames... [2023-03-09 10:31:38,273][119466] Decorrelating experience for 0 frames... [2023-03-09 10:31:38,302][119511] Decorrelating experience for 0 frames... [2023-03-09 10:31:38,330][120004] Decorrelating experience for 32 frames... [2023-03-09 10:31:38,331][119487] Decorrelating experience for 64 frames... [2023-03-09 10:31:38,352][119526] Decorrelating experience for 32 frames... [2023-03-09 10:31:38,354][119507] Decorrelating experience for 0 frames... [2023-03-09 10:31:38,379][119393] Decorrelating experience for 32 frames... [2023-03-09 10:31:38,388][119503] Decorrelating experience for 96 frames... [2023-03-09 10:31:38,427][120003] Decorrelating experience for 32 frames... [2023-03-09 10:31:38,430][119808] Decorrelating experience for 32 frames... [2023-03-09 10:31:38,444][119466] Decorrelating experience for 32 frames... [2023-03-09 10:31:38,475][119511] Decorrelating experience for 32 frames... [2023-03-09 10:31:38,502][120648] Decorrelating experience for 32 frames... [2023-03-09 10:31:38,513][120717] Decorrelating experience for 128 frames... [2023-03-09 10:31:38,557][119525] Decorrelating experience for 0 frames... [2023-03-09 10:31:38,558][119516] Decorrelating experience for 0 frames... [2023-03-09 10:31:38,565][119522] Decorrelating experience for 0 frames... [2023-03-09 10:31:38,570][119527] Decorrelating experience for 64 frames... [2023-03-09 10:31:38,605][120134] Decorrelating experience for 96 frames... [2023-03-09 10:31:38,607][119470] Decorrelating experience for 0 frames... [2023-03-09 10:31:38,655][119540] Decorrelating experience for 0 frames... [2023-03-09 10:31:38,664][120896] Decorrelating experience for 64 frames... [2023-03-09 10:31:38,733][119525] Decorrelating experience for 32 frames... [2023-03-09 10:31:38,738][119515] Decorrelating experience for 64 frames... [2023-03-09 10:31:38,741][119526] Decorrelating experience for 64 frames... [2023-03-09 10:31:38,748][119542] Decorrelating experience for 96 frames... [2023-03-09 10:31:38,754][119494] Decorrelating experience for 0 frames... [2023-03-09 10:31:38,766][125883] Decorrelating experience for 32 frames... [2023-03-09 10:31:38,781][119466] Decorrelating experience for 64 frames... [2023-03-09 10:31:38,789][119523] Decorrelating experience for 64 frames... [2023-03-09 10:31:38,858][119483] Decorrelating experience for 0 frames... [2023-03-09 10:31:38,859][120550] Decorrelating experience for 0 frames... [2023-03-09 10:31:38,902][118949] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 2000027648. Throughput: 0: 0.0. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) [2023-03-09 10:31:38,909][119391] Decorrelating experience for 96 frames... [2023-03-09 10:31:38,917][120003] Decorrelating experience for 64 frames... [2023-03-09 10:31:38,919][119390] Decorrelating experience for 64 frames... [2023-03-09 10:31:38,935][120717] Decorrelating experience for 160 frames... [2023-03-09 10:31:38,951][119516] Decorrelating experience for 32 frames... [2023-03-09 10:31:38,957][119512] Decorrelating experience for 0 frames... [2023-03-09 10:31:38,963][119490] Decorrelating experience for 96 frames... [2023-03-09 10:31:38,969][119807] Decorrelating experience for 0 frames... [2023-03-09 10:31:39,031][119483] Decorrelating experience for 32 frames... [2023-03-09 10:31:39,085][119493] Decorrelating experience for 64 frames... [2023-03-09 10:31:39,096][119508] Decorrelating experience for 64 frames... [2023-03-09 10:31:39,097][119655] Decorrelating experience for 64 frames... [2023-03-09 10:31:39,109][119475] Decorrelating experience for 0 frames... [2023-03-09 10:31:39,112][119532] Decorrelating experience for 64 frames... [2023-03-09 10:31:39,133][119512] Decorrelating experience for 32 frames... [2023-03-09 10:31:39,137][119515] Decorrelating experience for 96 frames... [2023-03-09 10:31:39,146][119462] Decorrelating experience for 64 frames... [2023-03-09 10:31:39,156][119495] Decorrelating experience for 0 frames... [2023-03-09 10:31:39,208][120135] Decorrelating experience for 0 frames... [2023-03-09 10:31:39,266][120003] Decorrelating experience for 96 frames... [2023-03-09 10:31:39,268][119499] Decorrelating experience for 96 frames... [2023-03-09 10:31:39,279][119527] Decorrelating experience for 96 frames... [2023-03-09 10:31:39,291][120648] Decorrelating experience for 64 frames... [2023-03-09 10:31:39,310][120073] Decorrelating experience for 0 frames... [2023-03-09 10:31:39,312][119521] Decorrelating experience for 0 frames... [2023-03-09 10:31:39,321][119525] Decorrelating experience for 64 frames... [2023-03-09 10:31:39,330][119494] Decorrelating experience for 32 frames... [2023-03-09 10:31:39,357][120904] Decorrelating experience for 32 frames... [2023-03-09 10:31:39,382][119475] Decorrelating experience for 32 frames... [2023-03-09 10:31:39,461][119491] Decorrelating experience for 96 frames... [2023-03-09 10:31:39,462][119476] Decorrelating experience for 0 frames... [2023-03-09 10:31:39,473][120004] Decorrelating experience for 64 frames... [2023-03-09 10:31:39,476][119513] Decorrelating experience for 96 frames... [2023-03-09 10:31:39,487][120550] Decorrelating experience for 32 frames... [2023-03-09 10:31:39,489][120648] Decorrelating experience for 96 frames... [2023-03-09 10:31:39,502][119500] Decorrelating experience for 32 frames... [2023-03-09 10:31:39,511][119472] Decorrelating experience for 0 frames... [2023-03-09 10:31:39,538][119527] Decorrelating experience for 128 frames... [2023-03-09 10:31:39,558][119530] Decorrelating experience for 32 frames... [2023-03-09 10:31:39,641][119526] Decorrelating experience for 96 frames... [2023-03-09 10:31:39,657][119487] Decorrelating experience for 96 frames... [2023-03-09 10:31:39,663][119531] Decorrelating experience for 0 frames... [2023-03-09 10:31:39,665][119473] Decorrelating experience for 0 frames... [2023-03-09 10:31:39,670][119475] Decorrelating experience for 64 frames... [2023-03-09 10:31:39,680][120003] Decorrelating experience for 128 frames... [2023-03-09 10:31:39,685][119937] Decorrelating experience for 32 frames... [2023-03-09 10:31:39,686][119540] Decorrelating experience for 32 frames... [2023-03-09 10:31:39,715][119484] Decorrelating experience for 0 frames... [2023-03-09 10:31:39,731][119495] Decorrelating experience for 32 frames... [2023-03-09 10:31:39,813][119615] Decorrelating experience for 128 frames... [2023-03-09 10:31:39,834][119466] Decorrelating experience for 96 frames... [2023-03-09 10:31:39,847][119480] Decorrelating experience for 96 frames... [2023-03-09 10:31:39,854][119536] Decorrelating experience for 96 frames... [2023-03-09 10:31:39,859][119474] Decorrelating experience for 96 frames... [2023-03-09 10:31:39,865][119537] Decorrelating experience for 64 frames... [2023-03-09 10:31:39,872][119487] Decorrelating experience for 128 frames... [2023-03-09 10:31:39,873][119937] Decorrelating experience for 64 frames... [2023-03-09 10:31:39,894][120904] Decorrelating experience for 64 frames... [2023-03-09 10:31:39,911][119399] Decorrelating experience for 0 frames... [2023-03-09 10:31:40,007][119500] Decorrelating experience for 64 frames... [2023-03-09 10:31:40,015][119547] Decorrelating experience for 0 frames... [2023-03-09 10:31:40,023][120134] Decorrelating experience for 128 frames... [2023-03-09 10:31:40,042][120135] Decorrelating experience for 32 frames... [2023-03-09 10:31:40,044][119531] Decorrelating experience for 32 frames... [2023-03-09 10:31:40,045][119476] Decorrelating experience for 32 frames... [2023-03-09 10:31:40,052][119515] Decorrelating experience for 128 frames... [2023-03-09 10:31:40,071][119466] Decorrelating experience for 128 frames... [2023-03-09 10:31:40,089][119521] Decorrelating experience for 32 frames... [2023-03-09 10:31:40,099][119513] Decorrelating experience for 128 frames... [2023-03-09 10:31:40,192][119470] Decorrelating experience for 32 frames... [2023-03-09 10:31:40,193][119473] Decorrelating experience for 32 frames... [2023-03-09 10:31:40,200][119522] Decorrelating experience for 32 frames... [2023-03-09 10:31:40,223][120896] Decorrelating experience for 96 frames... [2023-03-09 10:31:40,225][119483] Decorrelating experience for 64 frames... [2023-03-09 10:31:40,226][120004] Decorrelating experience for 96 frames... [2023-03-09 10:31:40,227][119808] Decorrelating experience for 64 frames... [2023-03-09 10:31:40,264][120002] Decorrelating experience for 0 frames... [2023-03-09 10:31:40,280][119476] Decorrelating experience for 64 frames... [2023-03-09 10:31:40,331][119615] Decorrelating experience for 160 frames... [2023-03-09 10:31:40,371][119510] Decorrelating experience for 0 frames... [2023-03-09 10:31:40,376][120040] Decorrelating experience for 0 frames... [2023-03-09 10:31:40,377][119512] Decorrelating experience for 64 frames... [2023-03-09 10:31:40,413][120615] Decorrelating experience for 96 frames... [2023-03-09 10:31:40,421][119537] Decorrelating experience for 96 frames... [2023-03-09 10:31:40,424][119527] Decorrelating experience for 160 frames... [2023-03-09 10:31:40,441][119547] Decorrelating experience for 32 frames... [2023-03-09 10:31:40,461][119500] Decorrelating experience for 96 frames... [2023-03-09 10:31:40,490][119472] Decorrelating experience for 32 frames... [2023-03-09 10:31:40,515][119680] Decorrelating experience for 0 frames... [2023-03-09 10:31:40,553][119508] Decorrelating experience for 96 frames... [2023-03-09 10:31:40,555][119526] Decorrelating experience for 128 frames... [2023-03-09 10:31:40,571][119502] Decorrelating experience for 0 frames... [2023-03-09 10:31:40,599][119516] Decorrelating experience for 64 frames... [2023-03-09 10:31:40,599][119523] Decorrelating experience for 96 frames... [2023-03-09 10:31:40,620][119541] Decorrelating experience for 0 frames... [2023-03-09 10:31:40,621][119509] Decorrelating experience for 0 frames... [2023-03-09 10:31:40,636][120004] Decorrelating experience for 128 frames... [2023-03-09 10:31:40,674][119512] Decorrelating experience for 96 frames... [2023-03-09 10:31:40,718][119550] Decorrelating experience for 0 frames... [2023-03-09 10:31:40,727][119808] Decorrelating experience for 96 frames... [2023-03-09 10:31:40,731][119542] Decorrelating experience for 128 frames... [2023-03-09 10:31:40,758][119527] Decorrelating experience for 192 frames... [2023-03-09 10:31:40,775][119937] Decorrelating experience for 96 frames... [2023-03-09 10:31:40,777][119521] Decorrelating experience for 64 frames... [2023-03-09 10:31:40,797][119484] Decorrelating experience for 32 frames... [2023-03-09 10:31:40,814][119508] Decorrelating experience for 128 frames... [2023-03-09 10:31:40,820][119478] Decorrelating experience for 0 frames... [2023-03-09 10:31:40,860][119523] Decorrelating experience for 128 frames... [2023-03-09 10:31:40,930][119522] Decorrelating experience for 64 frames... [2023-03-09 10:31:40,935][119509] Decorrelating experience for 32 frames... [2023-03-09 10:31:40,937][119851] Decorrelating experience for 96 frames... [2023-03-09 10:31:40,977][119521] Decorrelating experience for 96 frames... [2023-03-09 10:31:40,985][119490] Decorrelating experience for 128 frames... [2023-03-09 10:31:40,988][119531] Decorrelating experience for 64 frames... [2023-03-09 10:31:40,992][119399] Decorrelating experience for 32 frames... [2023-03-09 10:31:41,035][119544] Decorrelating experience for 0 frames... [2023-03-09 10:31:41,038][119484] Decorrelating experience for 64 frames... [2023-03-09 10:31:41,044][119485] Decorrelating experience for 0 frames... [2023-03-09 10:31:41,130][119522] Decorrelating experience for 96 frames... [2023-03-09 10:31:41,133][120134] Decorrelating experience for 160 frames... [2023-03-09 10:31:41,144][120004] Decorrelating experience for 160 frames... [2023-03-09 10:31:41,173][119509] Decorrelating experience for 64 frames... [2023-03-09 10:31:41,181][119543] Decorrelating experience for 32 frames... [2023-03-09 10:31:41,183][119512] Decorrelating experience for 128 frames... [2023-03-09 10:31:41,234][120135] Decorrelating experience for 64 frames... [2023-03-09 10:31:41,236][119396] Decorrelating experience for 0 frames... [2023-03-09 10:31:41,248][120717] Decorrelating experience for 192 frames... [2023-03-09 10:31:41,289][119485] Decorrelating experience for 32 frames... [2023-03-09 10:31:41,334][119535] Decorrelating experience for 0 frames... [2023-03-09 10:31:41,336][120896] Decorrelating experience for 128 frames... [2023-03-09 10:31:41,347][119498] Decorrelating experience for 0 frames... [2023-03-09 10:31:41,359][119490] Decorrelating experience for 160 frames... [2023-03-09 10:31:41,363][119544] Decorrelating experience for 32 frames... [2023-03-09 10:31:41,369][119509] Decorrelating experience for 96 frames... [2023-03-09 10:31:41,410][119396] Decorrelating experience for 32 frames... [2023-03-09 10:31:41,419][120134] Decorrelating experience for 192 frames... [2023-03-09 10:31:41,431][119680] Decorrelating experience for 32 frames... [2023-03-09 10:31:41,482][120135] Decorrelating experience for 96 frames... [2023-03-09 10:31:41,539][119530] Decorrelating experience for 64 frames... [2023-03-09 10:31:41,541][119503] Decorrelating experience for 128 frames... [2023-03-09 10:31:41,541][119516] Decorrelating experience for 96 frames... [2023-03-09 10:31:41,557][119514] Decorrelating experience for 0 frames... [2023-03-09 10:31:41,563][120896] Decorrelating experience for 160 frames... [2023-03-09 10:31:41,571][119498] Decorrelating experience for 32 frames... [2023-03-09 10:31:41,583][119495] Decorrelating experience for 64 frames... [2023-03-09 10:31:41,622][119512] Decorrelating experience for 160 frames... [2023-03-09 10:31:41,659][119507] Decorrelating experience for 32 frames... [2023-03-09 10:31:41,663][120717] Decorrelating experience for 224 frames... [2023-03-09 10:31:41,736][119514] Decorrelating experience for 32 frames... [2023-03-09 10:31:41,739][119513] Decorrelating experience for 160 frames... [2023-03-09 10:31:41,742][119484] Decorrelating experience for 96 frames... [2023-03-09 10:31:41,780][119497] Decorrelating experience for 0 frames... [2023-03-09 10:31:41,796][120134] Decorrelating experience for 224 frames... [2023-03-09 10:31:41,801][119807] Decorrelating experience for 32 frames... [2023-03-09 10:31:41,808][119498] Decorrelating experience for 64 frames... [2023-03-09 10:31:41,824][119535] Decorrelating experience for 32 frames... [2023-03-09 10:31:41,837][119474] Decorrelating experience for 128 frames... [2023-03-09 10:31:41,841][119937] Decorrelating experience for 128 frames... [2023-03-09 10:31:41,929][119503] Decorrelating experience for 160 frames... [2023-03-09 10:31:41,938][119539] Decorrelating experience for 0 frames... [2023-03-09 10:31:41,939][119536] Decorrelating experience for 128 frames... [2023-03-09 10:31:41,975][120717] Decorrelating experience for 256 frames... [2023-03-09 10:31:41,976][119514] Decorrelating experience for 64 frames... [2023-03-09 10:31:41,985][119495] Decorrelating experience for 96 frames... [2023-03-09 10:31:41,987][120003] Decorrelating experience for 160 frames... [2023-03-09 10:31:42,001][119516] Decorrelating experience for 128 frames... [2023-03-09 10:31:42,038][120199] Decorrelating experience for 32 frames... [2023-03-09 10:31:42,078][120073] Decorrelating experience for 32 frames... [2023-03-09 10:31:42,107][119484] Decorrelating experience for 128 frames... [2023-03-09 10:31:42,115][119937] Decorrelating experience for 160 frames... [2023-03-09 10:31:42,124][119513] Decorrelating experience for 192 frames... [2023-03-09 10:31:42,152][119507] Decorrelating experience for 64 frames... [2023-03-09 10:31:42,163][119535] Decorrelating experience for 64 frames... [2023-03-09 10:31:42,172][119680] Decorrelating experience for 64 frames... [2023-03-09 10:31:42,187][120648] Decorrelating experience for 128 frames... [2023-03-09 10:31:42,215][119512] Decorrelating experience for 192 frames... [2023-03-09 10:31:42,219][120003] Decorrelating experience for 192 frames... [2023-03-09 10:31:42,290][126685] Decorrelating experience for 0 frames... [2023-03-09 10:31:42,297][119495] Decorrelating experience for 128 frames... [2023-03-09 10:31:42,309][119498] Decorrelating experience for 96 frames... [2023-03-09 10:31:42,319][119497] Decorrelating experience for 32 frames... [2023-03-09 10:31:42,340][119510] Decorrelating experience for 32 frames... [2023-03-09 10:31:42,340][119485] Decorrelating experience for 64 frames... [2023-03-09 10:31:42,363][120073] Decorrelating experience for 64 frames... [2023-03-09 10:31:42,385][120004] Decorrelating experience for 192 frames... [2023-03-09 10:31:42,390][119475] Decorrelating experience for 96 frames... [2023-03-09 10:31:42,403][119478] Decorrelating experience for 32 frames... [2023-03-09 10:31:42,480][119542] Decorrelating experience for 160 frames... [2023-03-09 10:31:42,483][119484] Decorrelating experience for 160 frames... [2023-03-09 10:31:42,498][120135] Decorrelating experience for 128 frames... [2023-03-09 10:31:42,513][119527] Decorrelating experience for 224 frames... [2023-03-09 10:31:42,516][120003] Decorrelating experience for 224 frames... [2023-03-09 10:31:42,527][119516] Decorrelating experience for 160 frames... [2023-03-09 10:31:42,536][119512] Decorrelating experience for 224 frames... [2023-03-09 10:31:42,571][119498] Decorrelating experience for 128 frames... [2023-03-09 10:31:42,573][119680] Decorrelating experience for 96 frames... [2023-03-09 10:31:42,637][119544] Decorrelating experience for 64 frames... [2023-03-09 10:31:42,665][120073] Decorrelating experience for 96 frames... [2023-03-09 10:31:42,667][119536] Decorrelating experience for 160 frames... [2023-03-09 10:31:42,693][119537] Decorrelating experience for 128 frames... [2023-03-09 10:31:42,709][120134] Decorrelating experience for 256 frames... [2023-03-09 10:31:42,711][120648] Decorrelating experience for 160 frames... [2023-03-09 10:31:42,720][119495] Decorrelating experience for 160 frames... [2023-03-09 10:31:42,741][119472] Decorrelating experience for 64 frames... [2023-03-09 10:31:42,748][119521] Decorrelating experience for 128 frames... [2023-03-09 10:31:42,788][119807] Decorrelating experience for 64 frames... [2023-03-09 10:31:42,842][119485] Decorrelating experience for 96 frames... [2023-03-09 10:31:42,843][119506] Decorrelating experience for 96 frames... [2023-03-09 10:31:42,861][119535] Decorrelating experience for 96 frames... [2023-03-09 10:31:42,897][119615] Decorrelating experience for 192 frames... [2023-03-09 10:31:42,898][119462] Decorrelating experience for 96 frames... [2023-03-09 10:31:42,900][119487] Decorrelating experience for 160 frames... [2023-03-09 10:31:42,908][119544] Decorrelating experience for 96 frames... [2023-03-09 10:31:42,918][119539] Decorrelating experience for 32 frames... [2023-03-09 10:31:42,926][119543] Decorrelating experience for 64 frames... [2023-03-09 10:31:42,990][119550] Decorrelating experience for 32 frames... [2023-03-09 10:31:43,020][119521] Decorrelating experience for 160 frames... [2023-03-09 10:31:43,066][119490] Decorrelating experience for 192 frames... [2023-03-09 10:31:43,081][120134] Decorrelating experience for 288 frames... [2023-03-09 10:31:43,089][119680] Decorrelating experience for 128 frames... [2023-03-09 10:31:43,101][119389] Decorrelating experience for 96 frames... [2023-03-09 10:31:43,105][119502] Decorrelating experience for 32 frames... [2023-03-09 10:31:43,106][119513] Decorrelating experience for 224 frames... [2023-03-09 10:31:43,107][119506] Decorrelating experience for 128 frames... [2023-03-09 10:31:43,152][119514] Decorrelating experience for 96 frames... [2023-03-09 10:31:43,197][119532] Decorrelating experience for 96 frames... [2023-03-09 10:31:43,198][119388] Decorrelating experience for 0 frames... [2023-03-09 10:31:43,243][119512] Decorrelating experience for 256 frames... [2023-03-09 10:31:43,268][119537] Decorrelating experience for 160 frames... [2023-03-09 10:31:43,271][119544] Decorrelating experience for 128 frames... [2023-03-09 10:31:43,277][119543] Decorrelating experience for 96 frames... [2023-03-09 10:31:43,294][119503] Decorrelating experience for 192 frames... [2023-03-09 10:31:43,297][119615] Decorrelating experience for 224 frames... [2023-03-09 10:31:43,298][119502] Decorrelating experience for 64 frames... [2023-03-09 10:31:43,327][119550] Decorrelating experience for 64 frames... [2023-03-09 10:31:43,394][119545] Decorrelating experience for 0 frames... [2023-03-09 10:31:43,399][120135] Decorrelating experience for 160 frames... [2023-03-09 10:31:43,451][119808] Decorrelating experience for 128 frames... [2023-03-09 10:31:43,453][126685] Decorrelating experience for 32 frames... [2023-03-09 10:31:43,480][119484] Decorrelating experience for 192 frames... [2023-03-09 10:31:43,486][119807] Decorrelating experience for 96 frames... [2023-03-09 10:31:43,490][119543] Decorrelating experience for 128 frames... [2023-03-09 10:31:43,494][119490] Decorrelating experience for 224 frames... [2023-03-09 10:31:43,531][119506] Decorrelating experience for 160 frames... [2023-03-09 10:31:43,574][119535] Decorrelating experience for 128 frames... [2023-03-09 10:31:43,577][120003] Decorrelating experience for 256 frames... [2023-03-09 10:31:43,595][120615] Decorrelating experience for 128 frames... [2023-03-09 10:31:43,630][120073] Decorrelating experience for 128 frames... [2023-03-09 10:31:43,661][119521] Decorrelating experience for 192 frames... [2023-03-09 10:31:43,662][119495] Decorrelating experience for 192 frames... [2023-03-09 10:31:43,667][120134] Decorrelating experience for 320 frames... [2023-03-09 10:31:43,670][119516] Decorrelating experience for 192 frames... [2023-03-09 10:31:43,704][119537] Decorrelating experience for 192 frames... [2023-03-09 10:31:43,707][119655] Decorrelating experience for 96 frames... [2023-03-09 10:31:43,748][119548] Decorrelating experience for 32 frames... [2023-03-09 10:31:43,749][119531] Decorrelating experience for 96 frames... [2023-03-09 10:31:43,798][120002] Decorrelating experience for 32 frames... [2023-03-09 10:31:43,808][119485] Decorrelating experience for 128 frames... [2023-03-09 10:31:43,843][126685] Decorrelating experience for 64 frames... [2023-03-09 10:31:43,849][119544] Decorrelating experience for 160 frames... [2023-03-09 10:31:43,855][119490] Decorrelating experience for 256 frames... [2023-03-09 10:31:43,891][119503] Decorrelating experience for 224 frames... [2023-03-09 10:31:43,902][118949] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 2000027648. Throughput: 0: 0.0. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) [2023-03-09 10:31:43,914][119807] Decorrelating experience for 128 frames... [2023-03-09 10:31:43,923][119808] Decorrelating experience for 160 frames... [2023-03-09 10:31:43,938][120004] Decorrelating experience for 224 frames... [2023-03-09 10:31:43,963][119535] Decorrelating experience for 160 frames... [2023-03-09 10:31:43,985][119548] Decorrelating experience for 64 frames... [2023-03-09 10:31:44,000][119397] Decorrelating experience for 64 frames... [2023-03-09 10:31:44,030][119388] Decorrelating experience for 32 frames... [2023-03-09 10:31:44,032][119485] Decorrelating experience for 160 frames... [2023-03-09 10:31:44,058][119507] Decorrelating experience for 96 frames... [2023-03-09 10:31:44,073][119542] Decorrelating experience for 192 frames... [2023-03-09 10:31:44,101][119534] Decorrelating experience for 0 frames... [2023-03-09 10:31:44,110][119495] Decorrelating experience for 224 frames... [2023-03-09 10:31:44,117][119506] Decorrelating experience for 192 frames... [2023-03-09 10:31:44,153][119537] Decorrelating experience for 224 frames... [2023-03-09 10:31:44,168][119508] Decorrelating experience for 160 frames... [2023-03-09 10:31:44,192][126685] Decorrelating experience for 96 frames... [2023-03-09 10:31:44,219][119680] Decorrelating experience for 160 frames... [2023-03-09 10:31:44,229][120717] Decorrelating experience for 288 frames... [2023-03-09 10:31:44,238][119544] Decorrelating experience for 192 frames... [2023-03-09 10:31:44,250][119540] Decorrelating experience for 64 frames... [2023-03-09 10:31:44,298][120004] Decorrelating experience for 256 frames... [2023-03-09 10:31:44,304][119493] Decorrelating experience for 96 frames... [2023-03-09 10:31:44,318][119507] Decorrelating experience for 128 frames... [2023-03-09 10:31:44,331][119484] Decorrelating experience for 224 frames... [2023-03-09 10:31:44,351][119547] Decorrelating experience for 64 frames... [2023-03-09 10:31:44,400][119490] Decorrelating experience for 288 frames... [2023-03-09 10:31:44,406][119525] Decorrelating experience for 96 frames... [2023-03-09 10:31:44,407][120648] Decorrelating experience for 192 frames... [2023-03-09 10:31:44,433][119545] Decorrelating experience for 32 frames... [2023-03-09 10:31:44,443][119396] Decorrelating experience for 64 frames... [2023-03-09 10:31:44,500][119540] Decorrelating experience for 96 frames... [2023-03-09 10:31:44,504][120003] Decorrelating experience for 288 frames... [2023-03-09 10:31:44,536][119548] Decorrelating experience for 96 frames... [2023-03-09 10:31:44,545][119514] Decorrelating experience for 128 frames... [2023-03-09 10:31:44,551][119521] Decorrelating experience for 224 frames... [2023-03-09 10:31:44,584][119509] Decorrelating experience for 128 frames... [2023-03-09 10:31:44,589][120002] Decorrelating experience for 64 frames... [2023-03-09 10:31:44,602][119397] Decorrelating experience for 96 frames... [2023-03-09 10:31:44,612][119488] Decorrelating experience for 0 frames... [2023-03-09 10:31:44,617][119543] Decorrelating experience for 160 frames... [2023-03-09 10:31:44,717][119491] Decorrelating experience for 128 frames... [2023-03-09 10:31:44,721][119512] Decorrelating experience for 288 frames... [2023-03-09 10:31:44,740][119485] Decorrelating experience for 192 frames... [2023-03-09 10:31:44,755][119474] Decorrelating experience for 160 frames... [2023-03-09 10:31:44,756][119534] Decorrelating experience for 32 frames... [2023-03-09 10:31:44,763][119535] Decorrelating experience for 192 frames... [2023-03-09 10:31:44,768][119525] Decorrelating experience for 128 frames... [2023-03-09 10:31:44,791][119507] Decorrelating experience for 160 frames... [2023-03-09 10:31:44,803][119503] Decorrelating experience for 256 frames... [2023-03-09 10:31:44,807][119509] Decorrelating experience for 160 frames... [2023-03-09 10:31:44,904][119396] Decorrelating experience for 96 frames... [2023-03-09 10:31:44,907][119526] Decorrelating experience for 160 frames... [2023-03-09 10:31:44,940][120003] Decorrelating experience for 320 frames... [2023-03-09 10:31:44,943][120199] Decorrelating experience for 64 frames... [2023-03-09 10:31:44,946][119548] Decorrelating experience for 128 frames... [2023-03-09 10:31:44,953][119543] Decorrelating experience for 192 frames... [2023-03-09 10:31:44,968][119506] Decorrelating experience for 224 frames... [2023-03-09 10:31:44,975][119655] Decorrelating experience for 128 frames... [2023-03-09 10:31:44,991][119491] Decorrelating experience for 160 frames... [2023-03-09 10:31:44,997][119534] Decorrelating experience for 64 frames... [2023-03-09 10:31:45,090][120002] Decorrelating experience for 96 frames... [2023-03-09 10:31:45,093][119484] Decorrelating experience for 256 frames... [2023-03-09 10:31:45,118][119396] Decorrelating experience for 128 frames... [2023-03-09 10:31:45,123][119503] Decorrelating experience for 288 frames... [2023-03-09 10:31:45,126][120615] Decorrelating experience for 160 frames... [2023-03-09 10:31:45,156][119547] Decorrelating experience for 96 frames... [2023-03-09 10:31:45,159][126685] Decorrelating experience for 128 frames... [2023-03-09 10:31:45,171][119548] Decorrelating experience for 160 frames... [2023-03-09 10:31:45,172][120134] Decorrelating experience for 352 frames... [2023-03-09 10:31:45,184][119526] Decorrelating experience for 192 frames... [2023-03-09 10:31:45,267][119937] Decorrelating experience for 192 frames... [2023-03-09 10:31:45,280][119516] Decorrelating experience for 224 frames... [2023-03-09 10:31:45,344][119474] Decorrelating experience for 192 frames... [2023-03-09 10:31:45,363][120615] Decorrelating experience for 192 frames... [2023-03-09 10:31:45,365][120778] Decorrelating experience for 32 frames... [2023-03-09 10:31:45,386][119483] Decorrelating experience for 96 frames... [2023-03-09 10:31:45,387][120648] Decorrelating experience for 224 frames... [2023-03-09 10:31:45,413][120003] Decorrelating experience for 352 frames... [2023-03-09 10:31:45,417][119534] Decorrelating experience for 96 frames... [2023-03-09 10:31:45,428][119464] Decorrelating experience for 0 frames... [2023-03-09 10:31:45,456][119548] Decorrelating experience for 192 frames... [2023-03-09 10:31:45,464][119488] Decorrelating experience for 32 frames... [2023-03-09 10:31:45,519][119549] Decorrelating experience for 0 frames... [2023-03-09 10:31:45,546][119510] Decorrelating experience for 64 frames... [2023-03-09 10:31:45,565][119479] Decorrelating experience for 0 frames... [2023-03-09 10:31:45,576][119491] Decorrelating experience for 192 frames... [2023-03-09 10:31:45,588][119511] Decorrelating experience for 64 frames... [2023-03-09 10:31:45,594][119509] Decorrelating experience for 192 frames... [2023-03-09 10:31:45,599][119543] Decorrelating experience for 224 frames... [2023-03-09 10:31:45,642][119544] Decorrelating experience for 224 frames... [2023-03-09 10:31:45,651][119464] Decorrelating experience for 32 frames... [2023-03-09 10:31:45,687][120877] Decorrelating experience for 0 frames... [2023-03-09 10:31:45,692][119525] Decorrelating experience for 160 frames... [2023-03-09 10:31:45,730][119526] Decorrelating experience for 224 frames... [2023-03-09 10:31:45,762][120648] Decorrelating experience for 256 frames... [2023-03-09 10:31:45,776][119514] Decorrelating experience for 160 frames... [2023-03-09 10:31:45,813][119484] Decorrelating experience for 288 frames... [2023-03-09 10:31:45,826][119515] Decorrelating experience for 160 frames... [2023-03-09 10:31:45,855][120134] Decorrelating experience for 384 frames... [2023-03-09 10:31:45,855][119507] Decorrelating experience for 192 frames... [2023-03-09 10:31:45,863][120629] Decorrelating experience for 32 frames... [2023-03-09 10:31:45,878][119393] Decorrelating experience for 64 frames... [2023-03-09 10:31:45,929][119523] Decorrelating experience for 160 frames... [2023-03-09 10:31:45,977][120877] Decorrelating experience for 32 frames... [2023-03-09 10:31:45,985][119511] Decorrelating experience for 96 frames... [2023-03-09 10:31:45,986][119503] Decorrelating experience for 320 frames... [2023-03-09 10:31:46,042][119509] Decorrelating experience for 224 frames... [2023-03-09 10:31:46,043][119548] Decorrelating experience for 224 frames... [2023-03-09 10:31:46,044][119464] Decorrelating experience for 64 frames... [2023-03-09 10:31:46,045][119479] Decorrelating experience for 32 frames... [2023-03-09 10:31:46,086][119549] Decorrelating experience for 32 frames... [2023-03-09 10:31:46,088][119516] Decorrelating experience for 256 frames... [2023-03-09 10:31:46,131][120648] Decorrelating experience for 288 frames... [2023-03-09 10:31:46,162][120877] Decorrelating experience for 64 frames... [2023-03-09 10:31:46,186][120002] Decorrelating experience for 128 frames... [2023-03-09 10:31:46,188][119524] Decorrelating experience for 0 frames... [2023-03-09 10:31:46,240][119508] Decorrelating experience for 192 frames... [2023-03-09 10:31:46,243][119470] Decorrelating experience for 64 frames... [2023-03-09 10:31:46,243][119485] Decorrelating experience for 224 frames... [2023-03-09 10:31:46,244][119534] Decorrelating experience for 128 frames... [2023-03-09 10:31:46,273][119549] Decorrelating experience for 64 frames... [2023-03-09 10:31:46,285][120263] Decorrelating experience for 0 frames... [2023-03-09 10:31:46,335][119527] Decorrelating experience for 256 frames... [2023-03-09 10:31:46,338][119475] Decorrelating experience for 128 frames... [2023-03-09 10:31:46,384][119479] Decorrelating experience for 64 frames... [2023-03-09 10:31:46,391][119526] Decorrelating experience for 256 frames... [2023-03-09 10:31:46,442][119546] Decorrelating experience for 0 frames... [2023-03-09 10:31:46,442][119510] Decorrelating experience for 96 frames... [2023-03-09 10:31:46,454][119535] Decorrelating experience for 224 frames... [2023-03-09 10:31:46,485][119481] Decorrelating experience for 64 frames... [2023-03-09 10:31:46,507][119503] Decorrelating experience for 352 frames... [2023-03-09 10:31:46,508][120073] Decorrelating experience for 160 frames... [2023-03-09 10:31:46,511][120263] Decorrelating experience for 32 frames... [2023-03-09 10:31:46,534][119507] Decorrelating experience for 224 frames... [2023-03-09 10:31:46,562][120877] Decorrelating experience for 96 frames... [2023-03-09 10:31:46,614][119516] Decorrelating experience for 288 frames... [2023-03-09 10:31:46,640][119488] Decorrelating experience for 64 frames... [2023-03-09 10:31:46,641][119480] Decorrelating experience for 128 frames... [2023-03-09 10:31:46,643][119542] Decorrelating experience for 224 frames... [2023-03-09 10:31:46,697][119531] Decorrelating experience for 128 frames... [2023-03-09 10:31:46,700][119393] Decorrelating experience for 96 frames... [2023-03-09 10:31:46,701][119466] Decorrelating experience for 160 frames... [2023-03-09 10:31:46,701][119550] Decorrelating experience for 96 frames... [2023-03-09 10:31:46,735][119479] Decorrelating experience for 96 frames... [2023-03-09 10:31:46,739][119520] Decorrelating experience for 0 frames... [2023-03-09 10:31:46,790][119507] Decorrelating experience for 256 frames... [2023-03-09 10:31:46,821][119515] Decorrelating experience for 192 frames... [2023-03-09 10:31:46,821][119534] Decorrelating experience for 160 frames... [2023-03-09 10:31:46,828][120073] Decorrelating experience for 192 frames... [2023-03-09 10:31:46,874][119549] Decorrelating experience for 96 frames... [2023-03-09 10:31:46,891][119517] Decorrelating experience for 32 frames... [2023-03-09 10:31:46,892][119498] Decorrelating experience for 160 frames... [2023-03-09 10:31:46,896][119470] Decorrelating experience for 96 frames... [2023-03-09 10:31:46,913][119393] Decorrelating experience for 128 frames... [2023-03-09 10:31:46,916][120648] Decorrelating experience for 320 frames... [2023-03-09 10:31:46,970][119531] Decorrelating experience for 160 frames... [2023-03-09 10:31:47,000][120896] Decorrelating experience for 192 frames... [2023-03-09 10:31:47,008][119548] Decorrelating experience for 256 frames... [2023-03-09 10:31:47,010][120629] Decorrelating experience for 64 frames... [2023-03-09 10:31:47,050][119511] Decorrelating experience for 128 frames... [2023-03-09 10:31:47,067][119478] Decorrelating experience for 64 frames... [2023-03-09 10:31:47,095][119529] Decorrelating experience for 32 frames... [2023-03-09 10:31:47,095][119397] Decorrelating experience for 128 frames... [2023-03-09 10:31:47,099][119503] Decorrelating experience for 384 frames... [2023-03-09 10:31:47,104][119542] Decorrelating experience for 256 frames... [2023-03-09 10:31:47,163][119526] Decorrelating experience for 288 frames... [2023-03-09 10:31:47,192][119549] Decorrelating experience for 128 frames... [2023-03-09 10:31:47,193][119393] Decorrelating experience for 160 frames... [2023-03-09 10:31:47,195][119466] Decorrelating experience for 192 frames... [2023-03-09 10:31:47,239][119498] Decorrelating experience for 192 frames... [2023-03-09 10:31:47,244][126685] Decorrelating experience for 160 frames... [2023-03-09 10:31:47,278][119548] Decorrelating experience for 288 frames... [2023-03-09 10:31:47,298][119506] Decorrelating experience for 256 frames... [2023-03-09 10:31:47,299][119504] Decorrelating experience for 32 frames... [2023-03-09 10:31:47,300][120896] Decorrelating experience for 224 frames... [2023-03-09 10:31:47,338][119481] Decorrelating experience for 96 frames... [2023-03-09 10:31:47,370][119480] Decorrelating experience for 160 frames... [2023-03-09 10:31:47,376][119511] Decorrelating experience for 160 frames... [2023-03-09 10:31:47,412][119546] Decorrelating experience for 32 frames... [2023-03-09 10:31:47,416][119503] Decorrelating experience for 416 frames... [2023-03-09 10:31:47,420][119397] Decorrelating experience for 160 frames... [2023-03-09 10:31:47,456][119531] Decorrelating experience for 192 frames... [2023-03-09 10:31:47,495][119490] Decorrelating experience for 320 frames... [2023-03-09 10:31:47,497][119476] Decorrelating experience for 96 frames... [2023-03-09 10:31:47,505][119464] Decorrelating experience for 96 frames... [2023-03-09 10:31:47,556][120263] Decorrelating experience for 64 frames... [2023-03-09 10:31:47,602][119546] Decorrelating experience for 64 frames... [2023-03-09 10:31:47,606][119516] Decorrelating experience for 320 frames... [2023-03-09 10:31:47,610][120615] Decorrelating experience for 224 frames... [2023-03-09 10:31:47,617][119470] Decorrelating experience for 128 frames... [2023-03-09 10:31:47,635][119529] Decorrelating experience for 64 frames... [2023-03-09 10:31:47,662][119543] Decorrelating experience for 256 frames... [2023-03-09 10:31:47,695][119807] Decorrelating experience for 160 frames... [2023-03-09 10:31:47,702][119481] Decorrelating experience for 128 frames... [2023-03-09 10:31:47,708][119476] Decorrelating experience for 128 frames... [2023-03-09 10:31:47,783][119504] Decorrelating experience for 64 frames... [2023-03-09 10:31:47,804][120904] Decorrelating experience for 96 frames... [2023-03-09 10:31:47,805][120135] Decorrelating experience for 192 frames... [2023-03-09 10:31:47,805][119533] Decorrelating experience for 96 frames... [2023-03-09 10:31:47,807][119546] Decorrelating experience for 96 frames... [2023-03-09 10:31:47,813][119510] Decorrelating experience for 128 frames... [2023-03-09 10:31:47,842][119503] Decorrelating experience for 448 frames... [2023-03-09 10:31:47,895][121015] Decorrelating experience for 96 frames... [2023-03-09 10:31:47,920][119470] Decorrelating experience for 160 frames... [2023-03-09 10:31:47,961][119527] Decorrelating experience for 288 frames... [2023-03-09 10:31:47,988][120877] Decorrelating experience for 128 frames... [2023-03-09 10:31:48,004][120615] Decorrelating experience for 256 frames... [2023-03-09 10:31:48,007][120717] Decorrelating experience for 320 frames... [2023-03-09 10:31:48,009][126685] Decorrelating experience for 192 frames... [2023-03-09 10:31:48,011][119512] Decorrelating experience for 320 frames... [2023-03-09 10:31:48,020][119546] Decorrelating experience for 128 frames... [2023-03-09 10:31:48,040][120896] Decorrelating experience for 256 frames... [2023-03-09 10:31:48,094][119535] Decorrelating experience for 256 frames... [2023-03-09 10:31:48,151][119543] Decorrelating experience for 288 frames... [2023-03-09 10:31:48,158][119509] Decorrelating experience for 256 frames... [2023-03-09 10:31:48,171][120002] Decorrelating experience for 160 frames... [2023-03-09 10:31:48,190][119517] Decorrelating experience for 64 frames... [2023-03-09 10:31:48,201][119477] Decorrelating experience for 32 frames... [2023-03-09 10:31:48,206][119513] Decorrelating experience for 256 frames... [2023-03-09 10:31:48,208][119489] Decorrelating experience for 32 frames... [2023-03-09 10:31:48,216][120629] Decorrelating experience for 96 frames... [2023-03-09 10:31:48,224][118949] Heartbeat connected on Batcher_0 [2023-03-09 10:31:48,227][118949] Heartbeat connected on LearnerWorker_p0 [2023-03-09 10:31:48,246][119807] Decorrelating experience for 192 frames... [2023-03-09 10:31:48,272][118949] Heartbeat connected on InferenceWorker_p0-w0 [2023-03-09 10:31:48,295][120003] Decorrelating experience for 384 frames... [2023-03-09 10:31:48,326][119523] Decorrelating experience for 192 frames... [2023-03-09 10:31:48,334][119503] Decorrelating experience for 480 frames... [2023-03-09 10:31:48,350][119469] Decorrelating experience for 96 frames... [2023-03-09 10:31:48,368][119540] Decorrelating experience for 128 frames... [2023-03-09 10:31:48,385][119476] Decorrelating experience for 160 frames... [2023-03-09 10:31:48,397][119490] Decorrelating experience for 352 frames... [2023-03-09 10:31:48,398][119510] Decorrelating experience for 160 frames... [2023-03-09 10:31:48,401][125883] Decorrelating experience for 64 frames... [2023-03-09 10:31:48,432][119543] Decorrelating experience for 320 frames... [2023-03-09 10:31:48,476][120629] Decorrelating experience for 128 frames... [2023-03-09 10:31:48,517][120904] Decorrelating experience for 128 frames... [2023-03-09 10:31:48,521][119549] Decorrelating experience for 160 frames... [2023-03-09 10:31:48,551][120778] Decorrelating experience for 64 frames... [2023-03-09 10:31:48,553][119491] Decorrelating experience for 224 frames... [2023-03-09 10:31:48,580][119520] Decorrelating experience for 32 frames... [2023-03-09 10:31:48,583][119524] Decorrelating experience for 32 frames... [2023-03-09 10:31:48,615][119480] Decorrelating experience for 192 frames... [2023-03-09 10:31:48,621][119533] Decorrelating experience for 128 frames... [2023-03-09 10:31:48,665][120550] Decorrelating experience for 64 frames... [2023-03-09 10:31:48,667][119614] Decorrelating experience for 0 frames... [2023-03-09 10:31:48,702][119535] Decorrelating experience for 288 frames... [2023-03-09 10:31:48,704][119489] Decorrelating experience for 64 frames... [2023-03-09 10:31:48,728][119507] Decorrelating experience for 288 frames... [2023-03-09 10:31:48,752][119474] Decorrelating experience for 224 frames... [2023-03-09 10:31:48,757][119479] Decorrelating experience for 128 frames... [2023-03-09 10:31:48,761][119512] Decorrelating experience for 352 frames... [2023-03-09 10:31:48,791][119517] Decorrelating experience for 96 frames... [2023-03-09 10:31:48,802][119516] Decorrelating experience for 352 frames... [2023-03-09 10:31:48,852][119505] Decorrelating experience for 0 frames... [2023-03-09 10:31:48,852][120778] Decorrelating experience for 96 frames... [2023-03-09 10:31:48,883][119481] Decorrelating experience for 160 frames... [2023-03-09 10:31:48,889][120896] Decorrelating experience for 288 frames... [2023-03-09 10:31:48,902][118949] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 2000027648. Throughput: 0: 0.0. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) [2023-03-09 10:31:48,907][119549] Decorrelating experience for 192 frames... [2023-03-09 10:31:48,937][119480] Decorrelating experience for 224 frames... [2023-03-09 10:31:48,948][119540] Decorrelating experience for 160 frames... [2023-03-09 10:31:48,963][119808] Decorrelating experience for 192 frames... [2023-03-09 10:31:48,983][119479] Decorrelating experience for 160 frames... [2023-03-09 10:31:48,985][119534] Decorrelating experience for 192 frames... [2023-03-09 10:31:49,036][119509] Decorrelating experience for 288 frames... [2023-03-09 10:31:49,040][119464] Decorrelating experience for 128 frames... [2023-03-09 10:31:49,068][119491] Decorrelating experience for 256 frames... [2023-03-09 10:31:49,087][119542] Decorrelating experience for 288 frames... [2023-03-09 10:31:49,115][119470] Decorrelating experience for 192 frames... [2023-03-09 10:31:49,140][119533] Decorrelating experience for 160 frames... [2023-03-09 10:31:49,155][119545] Decorrelating experience for 64 frames... [2023-03-09 10:31:49,155][120550] Decorrelating experience for 96 frames... [2023-03-09 10:31:49,171][119497] Decorrelating experience for 64 frames... [2023-03-09 10:31:49,189][119510] Decorrelating experience for 192 frames... [2023-03-09 10:31:49,223][120877] Decorrelating experience for 160 frames... [2023-03-09 10:31:49,232][119534] Decorrelating experience for 224 frames... [2023-03-09 10:31:49,246][120904] Decorrelating experience for 160 frames... [2023-03-09 10:31:49,267][119485] Decorrelating experience for 256 frames... [2023-03-09 10:31:49,292][119527] Decorrelating experience for 320 frames... [2023-03-09 10:31:49,352][119546] Decorrelating experience for 160 frames... [2023-03-09 10:31:49,361][120629] Decorrelating experience for 160 frames... [2023-03-09 10:31:49,362][119391] Decorrelating experience for 128 frames... [2023-03-09 10:31:49,364][125883] Decorrelating experience for 96 frames... [2023-03-09 10:31:49,366][120550] Decorrelating experience for 128 frames... [2023-03-09 10:31:49,406][119900] Decorrelating experience for 64 frames... [2023-03-09 10:31:49,417][119390] Decorrelating experience for 96 frames... [2023-03-09 10:31:49,425][119523] Decorrelating experience for 224 frames... [2023-03-09 10:31:49,459][119541] Decorrelating experience for 32 frames... [2023-03-09 10:31:49,477][119524] Decorrelating experience for 64 frames... [2023-03-09 10:31:49,532][119506] Decorrelating experience for 288 frames... [2023-03-09 10:31:49,549][119477] Decorrelating experience for 64 frames... [2023-03-09 10:31:49,566][119525] Decorrelating experience for 192 frames... [2023-03-09 10:31:49,567][119472] Decorrelating experience for 96 frames... [2023-03-09 10:31:49,567][119490] Decorrelating experience for 384 frames... [2023-03-09 10:31:49,596][119510] Decorrelating experience for 224 frames... [2023-03-09 10:31:49,607][119545] Decorrelating experience for 96 frames... [2023-03-09 10:31:49,611][119487] Decorrelating experience for 192 frames... [2023-03-09 10:31:49,635][120615] Decorrelating experience for 288 frames... [2023-03-09 10:31:49,656][119483] Decorrelating experience for 128 frames... [2023-03-09 10:31:49,706][119526] Decorrelating experience for 320 frames... [2023-03-09 10:31:49,739][119485] Decorrelating experience for 288 frames... [2023-03-09 10:31:49,750][120629] Decorrelating experience for 192 frames... [2023-03-09 10:31:49,758][119900] Decorrelating experience for 96 frames... [2023-03-09 10:31:49,766][120002] Decorrelating experience for 192 frames... [2023-03-09 10:31:49,778][120134] Decorrelating experience for 416 frames... [2023-03-09 10:31:49,781][119505] Decorrelating experience for 32 frames... [2023-03-09 10:31:49,794][119540] Decorrelating experience for 192 frames... [2023-03-09 10:31:49,812][119549] Decorrelating experience for 224 frames... [2023-03-09 10:31:49,832][120003] Decorrelating experience for 416 frames... [2023-03-09 10:31:49,886][119543] Decorrelating experience for 352 frames... [2023-03-09 10:31:49,914][120615] Decorrelating experience for 320 frames... [2023-03-09 10:31:49,929][120648] Decorrelating experience for 352 frames... [2023-03-09 10:31:49,934][120904] Decorrelating experience for 192 frames... [2023-03-09 10:31:49,964][119487] Decorrelating experience for 224 frames... [2023-03-09 10:31:49,971][119545] Decorrelating experience for 128 frames... [2023-03-09 10:31:49,972][119495] Decorrelating experience for 256 frames... [2023-03-09 10:31:49,984][119462] Decorrelating experience for 128 frames... [2023-03-09 10:31:49,987][119391] Decorrelating experience for 160 frames... [2023-03-09 10:31:50,008][119807] Decorrelating experience for 224 frames... [2023-03-09 10:31:50,071][119900] Decorrelating experience for 128 frames... [2023-03-09 10:31:50,115][119528] Decorrelating experience for 32 frames... [2023-03-09 10:31:50,116][119494] Decorrelating experience for 64 frames... [2023-03-09 10:31:50,143][119546] Decorrelating experience for 192 frames... [2023-03-09 10:31:50,170][119851] Decorrelating experience for 128 frames... [2023-03-09 10:31:50,171][119516] Decorrelating experience for 384 frames... [2023-03-09 10:31:50,176][119680] Decorrelating experience for 192 frames... [2023-03-09 10:31:50,188][119550] Decorrelating experience for 128 frames... [2023-03-09 10:31:50,192][119475] Decorrelating experience for 160 frames... [2023-03-09 10:31:50,225][119391] Decorrelating experience for 192 frames... [2023-03-09 10:31:50,246][119504] Decorrelating experience for 96 frames... [2023-03-09 10:31:50,295][119900] Decorrelating experience for 160 frames... [2023-03-09 10:31:50,313][119937] Decorrelating experience for 224 frames... [2023-03-09 10:31:50,319][119470] Decorrelating experience for 224 frames... [2023-03-09 10:31:50,351][119540] Decorrelating experience for 224 frames... [2023-03-09 10:31:50,353][119534] Decorrelating experience for 256 frames... [2023-03-09 10:31:50,355][119528] Decorrelating experience for 64 frames... [2023-03-09 10:31:50,377][120263] Decorrelating experience for 96 frames... [2023-03-09 10:31:50,378][119479] Decorrelating experience for 192 frames... [2023-03-09 10:31:50,431][119509] Decorrelating experience for 320 frames... [2023-03-09 10:31:50,439][119546] Decorrelating experience for 224 frames... [2023-03-09 10:31:50,472][119505] Decorrelating experience for 64 frames... [2023-03-09 10:31:50,490][119523] Decorrelating experience for 256 frames... [2023-03-09 10:31:50,505][120629] Decorrelating experience for 224 frames... [2023-03-09 10:31:50,536][119475] Decorrelating experience for 192 frames... [2023-03-09 10:31:50,536][119511] Decorrelating experience for 192 frames... [2023-03-09 10:31:50,539][119533] Decorrelating experience for 192 frames... [2023-03-09 10:31:50,555][119528] Decorrelating experience for 96 frames... [2023-03-09 10:31:50,563][119521] Decorrelating experience for 256 frames... [2023-03-09 10:31:50,611][119462] Decorrelating experience for 160 frames... [2023-03-09 10:31:50,623][119937] Decorrelating experience for 256 frames... [2023-03-09 10:31:50,661][119545] Decorrelating experience for 160 frames... [2023-03-09 10:31:50,670][120135] Decorrelating experience for 224 frames... [2023-03-09 10:31:50,688][119516] Decorrelating experience for 416 frames... [2023-03-09 10:31:50,716][120134] Decorrelating experience for 448 frames... [2023-03-09 10:31:50,719][119500] Decorrelating experience for 128 frames... [2023-03-09 10:31:50,724][119486] Decorrelating experience for 32 frames... [2023-03-09 10:31:50,745][119474] Decorrelating experience for 256 frames... [2023-03-09 10:31:50,761][119808] Decorrelating experience for 224 frames... [2023-03-09 10:31:50,795][119390] Decorrelating experience for 128 frames... [2023-03-09 10:31:50,810][119504] Decorrelating experience for 128 frames... [2023-03-09 10:31:50,843][120263] Decorrelating experience for 128 frames... [2023-03-09 10:31:50,850][119851] Decorrelating experience for 160 frames... [2023-03-09 10:31:50,866][119510] Decorrelating experience for 256 frames... [2023-03-09 10:31:50,897][119472] Decorrelating experience for 128 frames... [2023-03-09 10:31:50,900][119546] Decorrelating experience for 256 frames... [2023-03-09 10:31:50,918][119655] Decorrelating experience for 160 frames... [2023-03-09 10:31:50,929][119497] Decorrelating experience for 96 frames... [2023-03-09 10:31:50,986][119515] Decorrelating experience for 224 frames... [2023-03-09 10:31:50,988][126685] Decorrelating experience for 224 frames... [2023-03-09 10:31:51,038][119528] Decorrelating experience for 128 frames... [2023-03-09 10:31:51,042][119542] Decorrelating experience for 320 frames... [2023-03-09 10:31:51,090][119483] Decorrelating experience for 160 frames... [2023-03-09 10:31:51,091][119478] Decorrelating experience for 96 frames... [2023-03-09 10:31:51,092][119937] Decorrelating experience for 288 frames... [2023-03-09 10:31:51,116][119474] Decorrelating experience for 288 frames... [2023-03-09 10:31:51,134][119514] Decorrelating experience for 192 frames... [2023-03-09 10:31:51,151][120648] Decorrelating experience for 384 frames... [2023-03-09 10:31:51,186][119545] Decorrelating experience for 192 frames... [2023-03-09 10:31:51,187][119503] Decorrelating experience for 512 frames... [2023-03-09 10:31:51,222][119516] Decorrelating experience for 448 frames... [2023-03-09 10:31:51,223][119546] Decorrelating experience for 288 frames... [2023-03-09 10:31:51,271][120263] Decorrelating experience for 160 frames... [2023-03-09 10:31:51,290][119614] Decorrelating experience for 32 frames... [2023-03-09 10:31:51,291][119538] Decorrelating experience for 0 frames... [2023-03-09 10:31:51,323][119390] Decorrelating experience for 160 frames... [2023-03-09 10:31:51,337][119525] Decorrelating experience for 224 frames... [2023-03-09 10:31:51,337][119540] Decorrelating experience for 256 frames... [2023-03-09 10:31:51,392][119491] Decorrelating experience for 288 frames... [2023-03-09 10:31:51,394][119523] Decorrelating experience for 288 frames... [2023-03-09 10:31:51,399][126685] Decorrelating experience for 256 frames... [2023-03-09 10:31:51,410][120904] Decorrelating experience for 224 frames... [2023-03-09 10:31:51,480][119614] Decorrelating experience for 64 frames... [2023-03-09 10:31:51,485][119545] Decorrelating experience for 224 frames... [2023-03-09 10:31:51,489][119518] Decorrelating experience for 0 frames... [2023-03-09 10:31:51,531][119937] Decorrelating experience for 320 frames... [2023-03-09 10:31:51,533][119472] Decorrelating experience for 160 frames... [2023-03-09 10:31:51,538][119481] Decorrelating experience for 192 frames... [2023-03-09 10:31:51,594][119488] Decorrelating experience for 96 frames... [2023-03-09 10:31:51,596][119541] Decorrelating experience for 64 frames... [2023-03-09 10:31:51,597][119533] Decorrelating experience for 224 frames... [2023-03-09 10:31:51,657][119655] Decorrelating experience for 192 frames... [2023-03-09 10:31:51,677][119491] Decorrelating experience for 320 frames... [2023-03-09 10:31:51,681][119614] Decorrelating experience for 96 frames... [2023-03-09 10:31:51,689][119542] Decorrelating experience for 352 frames... [2023-03-09 10:31:51,715][119518] Decorrelating experience for 32 frames... [2023-03-09 10:31:51,736][119514] Decorrelating experience for 224 frames... [2023-03-09 10:31:51,741][119680] Decorrelating experience for 224 frames... [2023-03-09 10:31:51,792][119393] Decorrelating experience for 192 frames... [2023-03-09 10:31:51,794][120717] Decorrelating experience for 352 frames... [2023-03-09 10:31:51,808][119808] Decorrelating experience for 256 frames... [2023-03-09 10:31:51,839][119498] Decorrelating experience for 224 frames... [2023-03-09 10:31:51,859][119390] Decorrelating experience for 192 frames... [2023-03-09 10:31:51,890][119535] Decorrelating experience for 320 frames... [2023-03-09 10:31:51,902][119474] Decorrelating experience for 320 frames... [2023-03-09 10:31:51,945][119500] Decorrelating experience for 160 frames... [2023-03-09 10:31:51,946][120778] Decorrelating experience for 128 frames... [2023-03-09 10:31:51,971][119538] Decorrelating experience for 32 frames... [2023-03-09 10:31:51,981][119937] Decorrelating experience for 352 frames... [2023-03-09 10:31:51,991][119496] Decorrelating experience for 64 frames... [2023-03-09 10:31:52,023][119491] Decorrelating experience for 352 frames... [2023-03-09 10:31:52,035][119481] Decorrelating experience for 224 frames... [2023-03-09 10:31:52,094][119477] Decorrelating experience for 96 frames... [2023-03-09 10:31:52,094][119399] Decorrelating experience for 64 frames... [2023-03-09 10:31:52,148][119470] Decorrelating experience for 256 frames... [2023-03-09 10:31:52,149][120896] Decorrelating experience for 320 frames... [2023-03-09 10:31:52,165][120134] Decorrelating experience for 480 frames... [2023-03-09 10:31:52,168][119528] Decorrelating experience for 160 frames... [2023-03-09 10:31:52,188][119533] Decorrelating experience for 256 frames... [2023-03-09 10:31:52,242][119462] Decorrelating experience for 192 frames... [2023-03-09 10:31:52,252][119515] Decorrelating experience for 256 frames... [2023-03-09 10:31:52,300][120550] Decorrelating experience for 160 frames... [2023-03-09 10:31:52,301][120652] Decorrelating experience for 96 frames... [2023-03-09 10:31:52,335][119500] Decorrelating experience for 192 frames... [2023-03-09 10:31:52,338][119535] Decorrelating experience for 352 frames... [2023-03-09 10:31:52,345][119393] Decorrelating experience for 224 frames... [2023-03-09 10:31:52,349][119398] Decorrelating experience for 0 frames... [2023-03-09 10:31:52,392][119495] Decorrelating experience for 288 frames... [2023-03-09 10:31:52,451][120003] Decorrelating experience for 448 frames... [2023-03-09 10:31:52,454][119512] Decorrelating experience for 384 frames... [2023-03-09 10:31:52,454][120896] Decorrelating experience for 352 frames... [2023-03-09 10:31:52,495][119519] Decorrelating experience for 32 frames... [2023-03-09 10:31:52,509][119477] Decorrelating experience for 128 frames... [2023-03-09 10:31:52,527][119470] Decorrelating experience for 288 frames... [2023-03-09 10:31:52,528][120778] Decorrelating experience for 160 frames... [2023-03-09 10:31:52,535][119808] Decorrelating experience for 288 frames... [2023-03-09 10:31:52,597][119489] Decorrelating experience for 96 frames... [2023-03-09 10:31:52,601][119523] Decorrelating experience for 320 frames... [2023-03-09 10:31:52,635][119500] Decorrelating experience for 224 frames... [2023-03-09 10:31:52,646][120629] Decorrelating experience for 256 frames... [2023-03-09 10:31:52,681][119478] Decorrelating experience for 128 frames... [2023-03-09 10:31:52,702][119393] Decorrelating experience for 256 frames... [2023-03-09 10:31:52,713][119390] Decorrelating experience for 224 frames... [2023-03-09 10:31:52,717][120134] Decorrelating experience for 512 frames... [2023-03-09 10:31:52,745][119509] Decorrelating experience for 352 frames... [2023-03-09 10:31:52,760][119533] Decorrelating experience for 288 frames... [2023-03-09 10:31:52,788][120648] Decorrelating experience for 416 frames... [2023-03-09 10:31:52,803][119466] Decorrelating experience for 224 frames... [2023-03-09 10:31:52,814][120652] Decorrelating experience for 128 frames... [2023-03-09 10:31:52,824][119515] Decorrelating experience for 288 frames... [2023-03-09 10:31:52,864][119546] Decorrelating experience for 320 frames... [2023-03-09 10:31:52,883][119519] Decorrelating experience for 64 frames... [2023-03-09 10:31:52,898][119389] Decorrelating experience for 128 frames... [2023-03-09 10:31:52,922][119512] Decorrelating experience for 416 frames... [2023-03-09 10:31:52,951][119535] Decorrelating experience for 384 frames... [2023-03-09 10:31:52,977][119808] Decorrelating experience for 320 frames... [2023-03-09 10:31:52,994][119393] Decorrelating experience for 288 frames... [2023-03-09 10:31:53,004][119542] Decorrelating experience for 384 frames... [2023-03-09 10:31:53,011][119507] Decorrelating experience for 320 frames... [2023-03-09 10:31:53,018][120629] Decorrelating experience for 288 frames... [2023-03-09 10:31:53,100][119399] Decorrelating experience for 96 frames... [2023-03-09 10:31:53,114][119527] Decorrelating experience for 352 frames... [2023-03-09 10:31:53,133][120896] Decorrelating experience for 384 frames... [2023-03-09 10:31:53,149][119533] Decorrelating experience for 320 frames... [2023-03-09 10:31:53,190][119477] Decorrelating experience for 160 frames... [2023-03-09 10:31:53,192][119491] Decorrelating experience for 384 frames... [2023-03-09 10:31:53,199][119462] Decorrelating experience for 224 frames... [2023-03-09 10:31:53,201][119500] Decorrelating experience for 256 frames... [2023-03-09 10:31:53,226][119515] Decorrelating experience for 320 frames... [2023-03-09 10:31:53,284][119519] Decorrelating experience for 96 frames... [2023-03-09 10:31:53,303][119394] Decorrelating experience for 0 frames... [2023-03-09 10:31:53,318][119538] Decorrelating experience for 64 frames... [2023-03-09 10:31:53,341][120652] Decorrelating experience for 160 frames... [2023-03-09 10:31:53,376][119542] Decorrelating experience for 416 frames... [2023-03-09 10:31:53,382][120134] Decorrelating experience for 544 frames... [2023-03-09 10:31:53,383][119516] Decorrelating experience for 480 frames... [2023-03-09 10:31:53,403][119481] Decorrelating experience for 256 frames... [2023-03-09 10:31:53,413][119399] Decorrelating experience for 128 frames... [2023-03-09 10:31:53,480][119394] Decorrelating experience for 32 frames... [2023-03-09 10:31:53,499][119519] Decorrelating experience for 128 frames... [2023-03-09 10:31:53,504][120135] Decorrelating experience for 256 frames... [2023-03-09 10:31:53,505][120002] Decorrelating experience for 224 frames... [2023-03-09 10:31:53,520][119483] Decorrelating experience for 192 frames... [2023-03-09 10:31:53,555][119512] Decorrelating experience for 448 frames... [2023-03-09 10:31:53,564][119546] Decorrelating experience for 352 frames... [2023-03-09 10:31:53,565][119510] Decorrelating experience for 288 frames... [2023-03-09 10:31:53,593][119533] Decorrelating experience for 352 frames... [2023-03-09 10:31:53,607][119474] Decorrelating experience for 352 frames... [2023-03-09 10:31:53,665][120896] Decorrelating experience for 416 frames... [2023-03-09 10:31:53,678][119486] Decorrelating experience for 64 frames... [2023-03-09 10:31:53,700][120003] Decorrelating experience for 480 frames... [2023-03-09 10:31:53,706][119550] Decorrelating experience for 160 frames... [2023-03-09 10:31:53,708][119531] Decorrelating experience for 224 frames... [2023-03-09 10:31:53,760][119532] Decorrelating experience for 128 frames... [2023-03-09 10:31:53,761][119511] Decorrelating experience for 224 frames... [2023-03-09 10:31:53,770][119483] Decorrelating experience for 224 frames... [2023-03-09 10:31:53,779][119807] Decorrelating experience for 256 frames... [2023-03-09 10:31:53,811][119542] Decorrelating experience for 448 frames... [2023-03-09 10:31:53,857][120040] Decorrelating experience for 32 frames... [2023-03-09 10:31:53,881][119515] Decorrelating experience for 352 frames... [2023-03-09 10:31:53,888][119516] Decorrelating experience for 512 frames... [2023-03-09 10:31:53,902][118949] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 2000027648. Throughput: 0: 0.0. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) [2023-03-09 10:31:53,904][119539] Decorrelating experience for 64 frames... [2023-03-09 10:31:53,940][119535] Decorrelating experience for 416 frames... [2023-03-09 10:31:53,949][119472] Decorrelating experience for 192 frames... [2023-03-09 10:31:53,956][119510] Decorrelating experience for 320 frames... [2023-03-09 10:31:53,965][119614] Decorrelating experience for 128 frames... [2023-03-09 10:31:53,966][120629] Decorrelating experience for 320 frames... [2023-03-09 10:31:53,992][119550] Decorrelating experience for 192 frames... [2023-03-09 10:31:54,036][119393] Decorrelating experience for 320 frames... [2023-03-09 10:31:54,088][119486] Decorrelating experience for 96 frames... [2023-03-09 10:31:54,091][119532] Decorrelating experience for 160 frames... [2023-03-09 10:31:54,112][120877] Decorrelating experience for 192 frames... [2023-03-09 10:31:54,119][119528] Decorrelating experience for 192 frames... [2023-03-09 10:31:54,128][119525] Decorrelating experience for 256 frames... [2023-03-09 10:31:54,138][119398] Decorrelating experience for 32 frames... [2023-03-09 10:31:54,156][119506] Decorrelating experience for 320 frames... [2023-03-09 10:31:54,204][120648] Decorrelating experience for 448 frames... [2023-03-09 10:31:54,218][119531] Decorrelating experience for 256 frames... [2023-03-09 10:31:54,288][120778] Decorrelating experience for 192 frames... [2023-03-09 10:31:54,291][119614] Decorrelating experience for 160 frames... [2023-03-09 10:31:54,310][119533] Decorrelating experience for 384 frames... [2023-03-09 10:31:54,328][119655] Decorrelating experience for 224 frames... [2023-03-09 10:31:54,336][119390] Decorrelating experience for 256 frames... [2023-03-09 10:31:54,357][119483] Decorrelating experience for 256 frames... [2023-03-09 10:31:54,369][120550] Decorrelating experience for 192 frames... [2023-03-09 10:31:54,375][119480] Decorrelating experience for 256 frames... [2023-03-09 10:31:54,409][120135] Decorrelating experience for 288 frames... [2023-03-09 10:31:54,425][119503] Decorrelating experience for 544 frames... [2023-03-09 10:31:54,477][119528] Decorrelating experience for 224 frames... [2023-03-09 10:31:54,510][119900] Decorrelating experience for 192 frames... [2023-03-09 10:31:54,515][125883] Decorrelating experience for 128 frames... [2023-03-09 10:31:54,527][119488] Decorrelating experience for 128 frames... [2023-03-09 10:31:54,536][119808] Decorrelating experience for 352 frames... [2023-03-09 10:31:54,538][119807] Decorrelating experience for 288 frames... [2023-03-09 10:31:54,603][119486] Decorrelating experience for 128 frames... [2023-03-09 10:31:54,619][119937] Decorrelating experience for 384 frames... [2023-03-09 10:31:54,626][119397] Decorrelating experience for 192 frames... [2023-03-09 10:31:54,653][120003] Decorrelating experience for 512 frames... [2023-03-09 10:31:54,665][119394] Decorrelating experience for 64 frames... [2023-03-09 10:31:54,714][119499] Decorrelating experience for 128 frames... [2023-03-09 10:31:54,716][119504] Decorrelating experience for 160 frames... [2023-03-09 10:31:54,719][119479] Decorrelating experience for 224 frames... [2023-03-09 10:31:54,729][119542] Decorrelating experience for 480 frames... [2023-03-09 10:31:54,732][119531] Decorrelating experience for 288 frames... [2023-03-09 10:31:54,782][119519] Decorrelating experience for 160 frames... [2023-03-09 10:31:54,804][119483] Decorrelating experience for 288 frames... [2023-03-09 10:31:54,809][120896] Decorrelating experience for 448 frames... [2023-03-09 10:31:54,829][119532] Decorrelating experience for 192 frames... [2023-03-09 10:31:54,882][119398] Decorrelating experience for 64 frames... [2023-03-09 10:31:54,919][119488] Decorrelating experience for 160 frames... [2023-03-09 10:31:54,919][120550] Decorrelating experience for 224 frames... [2023-03-09 10:31:54,920][119503] Decorrelating experience for 576 frames... [2023-03-09 10:31:54,922][119390] Decorrelating experience for 288 frames... [2023-03-09 10:31:54,954][120040] Decorrelating experience for 64 frames... [2023-03-09 10:31:54,962][119900] Decorrelating experience for 224 frames... [2023-03-09 10:31:54,985][119393] Decorrelating experience for 352 frames... [2023-03-09 10:31:54,996][119470] Decorrelating experience for 320 frames... [2023-03-09 10:31:55,038][120648] Decorrelating experience for 480 frames... [2023-03-09 10:31:55,061][119397] Decorrelating experience for 224 frames... [2023-03-09 10:31:55,102][119504] Decorrelating experience for 192 frames... [2023-03-09 10:31:55,113][119473] Decorrelating experience for 64 frames... [2023-03-09 10:31:55,117][119464] Decorrelating experience for 160 frames... [2023-03-09 10:31:55,129][119532] Decorrelating experience for 224 frames... [2023-03-09 10:31:55,161][125883] Decorrelating experience for 160 frames... [2023-03-09 10:31:55,165][120778] Decorrelating experience for 224 frames... [2023-03-09 10:31:55,167][119490] Decorrelating experience for 416 frames... [2023-03-09 10:31:55,177][119546] Decorrelating experience for 384 frames... [2023-03-09 10:31:55,215][119396] Decorrelating experience for 160 frames... [2023-03-09 10:31:55,243][119515] Decorrelating experience for 384 frames... [2023-03-09 10:31:55,305][119393] Decorrelating experience for 384 frames... [2023-03-09 10:31:55,310][119488] Decorrelating experience for 192 frames... [2023-03-09 10:31:55,319][121015] Decorrelating experience for 128 frames... [2023-03-09 10:31:55,320][119473] Decorrelating experience for 96 frames... [2023-03-09 10:31:55,346][119475] Decorrelating experience for 224 frames... [2023-03-09 10:31:55,363][119390] Decorrelating experience for 320 frames... [2023-03-09 10:31:55,394][119483] Decorrelating experience for 320 frames... [2023-03-09 10:31:55,422][120896] Decorrelating experience for 480 frames... [2023-03-09 10:31:55,424][119519] Decorrelating experience for 192 frames... [2023-03-09 10:31:55,462][119527] Decorrelating experience for 384 frames... [2023-03-09 10:31:55,503][119490] Decorrelating experience for 448 frames... [2023-03-09 10:31:55,510][119464] Decorrelating experience for 192 frames... [2023-03-09 10:31:55,520][119946] Decorrelating experience for 0 frames... [2023-03-09 10:31:55,523][119491] Decorrelating experience for 416 frames... [2023-03-09 10:31:55,525][119536] Decorrelating experience for 192 frames... [2023-03-09 10:31:55,568][119510] Decorrelating experience for 352 frames... [2023-03-09 10:31:55,576][119462] Decorrelating experience for 256 frames... [2023-03-09 10:31:55,603][119396] Decorrelating experience for 192 frames... [2023-03-09 10:31:55,617][119523] Decorrelating experience for 352 frames... [2023-03-09 10:31:55,643][120652] Decorrelating experience for 192 frames... [2023-03-09 10:31:55,695][119532] Decorrelating experience for 256 frames... [2023-03-09 10:31:55,699][121015] Decorrelating experience for 160 frames... [2023-03-09 10:31:55,704][119399] Decorrelating experience for 160 frames... [2023-03-09 10:31:55,709][119525] Decorrelating experience for 288 frames... [2023-03-09 10:31:55,721][119537] Decorrelating experience for 256 frames... [2023-03-09 10:31:55,743][119392] Another process currently holds the lock /tmp/sf2_rolo/doom_006.lockfile, attempt: 1 [2023-03-09 10:31:55,771][119503] Decorrelating experience for 608 frames... [2023-03-09 10:31:55,785][120550] Decorrelating experience for 256 frames... [2023-03-09 10:31:55,804][120135] Decorrelating experience for 320 frames... [2023-03-09 10:31:55,808][120653] Another process currently holds the lock /tmp/sf2_rolo/doom_006.lockfile, attempt: 1 [2023-03-09 10:31:55,810][119528] Decorrelating experience for 256 frames... [2023-03-09 10:31:55,839][119479] Decorrelating experience for 256 frames... [2023-03-09 10:31:55,892][119481] Decorrelating experience for 288 frames... [2023-03-09 10:31:55,892][120263] Decorrelating experience for 192 frames... [2023-03-09 10:31:55,907][119491] Decorrelating experience for 448 frames... [2023-03-09 10:31:55,921][119395] Decorrelating experience for 0 frames... [2023-03-09 10:31:55,941][119394] Decorrelating experience for 96 frames... [2023-03-09 10:31:55,993][119532] Decorrelating experience for 288 frames... [2023-03-09 10:31:55,994][119398] Decorrelating experience for 96 frames... [2023-03-09 10:31:55,995][119399] Decorrelating experience for 192 frames... [2023-03-09 10:31:56,042][119490] Decorrelating experience for 480 frames... [2023-03-09 10:31:56,042][119483] Decorrelating experience for 352 frames... [2023-03-09 10:31:56,093][119389] Decorrelating experience for 160 frames... [2023-03-09 10:31:56,093][126685] Decorrelating experience for 288 frames... [2023-03-09 10:31:56,094][119900] Decorrelating experience for 256 frames... [2023-03-09 10:31:56,099][120135] Decorrelating experience for 352 frames... [2023-03-09 10:31:56,134][119533] Decorrelating experience for 416 frames... [2023-03-09 10:31:56,195][119519] Decorrelating experience for 224 frames... [2023-03-09 10:31:56,197][119485] Decorrelating experience for 320 frames... [2023-03-09 10:31:56,197][119397] Decorrelating experience for 256 frames... [2023-03-09 10:31:56,238][119535] Decorrelating experience for 448 frames... [2023-03-09 10:31:56,242][119515] Decorrelating experience for 416 frames... [2023-03-09 10:31:56,278][119481] Decorrelating experience for 320 frames... [2023-03-09 10:31:56,292][120652] Decorrelating experience for 224 frames... [2023-03-09 10:31:56,293][119500] Decorrelating experience for 288 frames... [2023-03-09 10:31:56,296][119390] Decorrelating experience for 352 frames... [2023-03-09 10:31:56,338][119499] Decorrelating experience for 160 frames... [2023-03-09 10:31:56,396][119388] Decorrelating experience for 64 frames... [2023-03-09 10:31:56,397][119473] Decorrelating experience for 128 frames... [2023-03-09 10:31:56,400][120040] Decorrelating experience for 96 frames... [2023-03-09 10:31:56,431][119532] Decorrelating experience for 320 frames... [2023-03-09 10:31:56,433][119389] Decorrelating experience for 192 frames... [2023-03-09 10:31:56,477][119503] Decorrelating experience for 640 frames... [2023-03-09 10:31:56,490][119462] Decorrelating experience for 288 frames... [2023-03-09 10:31:56,525][126685] Decorrelating experience for 320 frames... [2023-03-09 10:31:56,533][120629] Decorrelating experience for 352 frames... [2023-03-09 10:31:56,593][119496] Decorrelating experience for 96 frames... [2023-03-09 10:31:56,595][119510] Decorrelating experience for 384 frames... [2023-03-09 10:31:56,601][119525] Decorrelating experience for 320 frames... [2023-03-09 10:31:56,604][119509] Decorrelating experience for 384 frames... [2023-03-09 10:31:56,619][119533] Decorrelating experience for 448 frames... [2023-03-09 10:31:56,637][119523] Decorrelating experience for 384 frames... [2023-03-09 10:31:56,664][119501] Another process currently holds the lock /tmp/sf2_rolo/doom_003.lockfile, attempt: 1 [2023-03-09 10:31:56,673][119499] Decorrelating experience for 192 frames... [2023-03-09 10:31:56,713][119519] Decorrelating experience for 256 frames... [2023-03-09 10:31:56,725][119481] Decorrelating experience for 352 frames... [2023-03-09 10:31:56,750][120550] Decorrelating experience for 288 frames... [2023-03-09 10:31:56,796][119498] Decorrelating experience for 256 frames... [2023-03-09 10:31:56,799][120717] Decorrelating experience for 384 frames... [2023-03-09 10:31:56,801][121015] Decorrelating experience for 192 frames... [2023-03-09 10:31:56,812][119395] Decorrelating experience for 32 frames... [2023-03-09 10:31:56,864][119480] Decorrelating experience for 288 frames... [2023-03-09 10:31:56,871][119946] Decorrelating experience for 32 frames... [2023-03-09 10:31:56,880][119535] Decorrelating experience for 480 frames... [2023-03-09 10:31:56,891][119540] Decorrelating experience for 288 frames... [2023-03-09 10:31:56,908][119496] Decorrelating experience for 128 frames... [2023-03-09 10:31:56,966][119398] Decorrelating experience for 128 frames... [2023-03-09 10:31:56,978][119515] Decorrelating experience for 448 frames... [2023-03-09 10:31:56,994][119503] Decorrelating experience for 672 frames... [2023-03-09 10:31:56,996][119527] Decorrelating experience for 416 frames... [2023-03-09 10:31:57,044][119519] Decorrelating experience for 288 frames... [2023-03-09 10:31:57,050][120263] Decorrelating experience for 224 frames... [2023-03-09 10:31:57,055][119509] Decorrelating experience for 416 frames... [2023-03-09 10:31:57,072][119900] Decorrelating experience for 288 frames... [2023-03-09 10:31:57,091][119808] Decorrelating experience for 384 frames... [2023-03-09 10:31:57,147][119501] Decorrelating experience for 32 frames... [2023-03-09 10:31:57,164][119807] Decorrelating experience for 320 frames... [2023-03-09 10:31:57,175][119528] Decorrelating experience for 288 frames... [2023-03-09 10:31:57,192][119512] Decorrelating experience for 480 frames... [2023-03-09 10:31:57,226][119491] Decorrelating experience for 480 frames... [2023-03-09 10:31:57,246][125883] Decorrelating experience for 192 frames... [2023-03-09 10:31:57,256][119399] Decorrelating experience for 224 frames... [2023-03-09 10:31:57,258][121015] Decorrelating experience for 224 frames... [2023-03-09 10:31:57,294][119392] Decorrelating experience for 0 frames... [2023-03-09 10:31:57,306][119477] Decorrelating experience for 192 frames... [2023-03-09 10:31:57,324][119397] Decorrelating experience for 288 frames... [2023-03-09 10:31:57,348][119548] Decorrelating experience for 320 frames... [2023-03-09 10:31:57,353][119388] Decorrelating experience for 96 frames... [2023-03-09 10:31:57,408][119523] Decorrelating experience for 416 frames... [2023-03-09 10:31:57,430][119527] Decorrelating experience for 448 frames... [2023-03-09 10:31:57,438][120263] Decorrelating experience for 256 frames... [2023-03-09 10:31:57,451][119485] Decorrelating experience for 352 frames... [2023-03-09 10:31:57,473][119946] Decorrelating experience for 64 frames... [2023-03-09 10:31:57,475][119392] Decorrelating experience for 32 frames... [2023-03-09 10:31:57,489][119389] Decorrelating experience for 224 frames... [2023-03-09 10:31:57,505][119535] Decorrelating experience for 512 frames... [2023-03-09 10:31:57,527][126685] Decorrelating experience for 352 frames... [2023-03-09 10:31:57,582][119481] Decorrelating experience for 384 frames... [2023-03-09 10:31:57,619][120652] Decorrelating experience for 256 frames... [2023-03-09 10:31:57,634][119519] Decorrelating experience for 320 frames... [2023-03-09 10:31:57,654][120629] Decorrelating experience for 384 frames... [2023-03-09 10:31:57,661][119537] Decorrelating experience for 288 frames... [2023-03-09 10:31:57,665][119394] Decorrelating experience for 128 frames... [2023-03-09 10:31:57,676][119498] Decorrelating experience for 288 frames... [2023-03-09 10:31:57,692][119477] Decorrelating experience for 224 frames... [2023-03-09 10:31:57,711][119484] Decorrelating experience for 320 frames... [2023-03-09 10:31:57,740][119807] Decorrelating experience for 352 frames... [2023-03-09 10:31:57,761][119483] Decorrelating experience for 384 frames... [2023-03-09 10:31:57,797][120778] Decorrelating experience for 256 frames... [2023-03-09 10:31:57,815][119392] Decorrelating experience for 64 frames... [2023-03-09 10:31:57,833][126685] Decorrelating experience for 384 frames... [2023-03-09 10:31:57,870][120717] Decorrelating experience for 416 frames... [2023-03-09 10:31:57,877][119499] Decorrelating experience for 224 frames... [2023-03-09 10:31:57,900][119615] Decorrelating experience for 256 frames... [2023-03-09 10:31:57,905][119389] Decorrelating experience for 256 frames... [2023-03-09 10:31:57,922][119399] Decorrelating experience for 256 frames... [2023-03-09 10:31:57,947][119398] Decorrelating experience for 160 frames... [2023-03-09 10:31:57,957][119500] Decorrelating experience for 320 frames... [2023-03-09 10:31:57,978][119491] Decorrelating experience for 512 frames... [2023-03-09 10:31:57,998][119548] Decorrelating experience for 352 frames... [2023-03-09 10:31:58,013][119488] Decorrelating experience for 224 frames... [2023-03-09 10:31:58,054][119537] Decorrelating experience for 320 frames... [2023-03-09 10:31:58,071][119395] Decorrelating experience for 64 frames... [2023-03-09 10:31:58,079][119388] Decorrelating experience for 128 frames... [2023-03-09 10:31:58,109][119655] Decorrelating experience for 256 frames... [2023-03-09 10:31:58,109][119807] Decorrelating experience for 384 frames... [2023-03-09 10:31:58,128][120040] Decorrelating experience for 128 frames... [2023-03-09 10:31:58,136][119532] Decorrelating experience for 352 frames... [2023-03-09 10:31:58,180][119946] Decorrelating experience for 96 frames... [2023-03-09 10:31:58,227][119528] Decorrelating experience for 320 frames... [2023-03-09 10:31:58,243][119523] Decorrelating experience for 448 frames... [2023-03-09 10:31:58,261][119493] Decorrelating experience for 128 frames... [2023-03-09 10:31:58,261][119394] Decorrelating experience for 160 frames... [2023-03-09 10:31:58,267][120005] Decorrelating experience for 64 frames... [2023-03-09 10:31:58,299][119546] Decorrelating experience for 416 frames... [2023-03-09 10:31:58,324][119517] Decorrelating experience for 128 frames... [2023-03-09 10:31:58,329][119503] Decorrelating experience for 704 frames... [2023-03-09 10:31:58,336][119484] Decorrelating experience for 352 frames... [2023-03-09 10:31:58,360][119490] Decorrelating experience for 512 frames... [2023-03-09 10:31:58,412][120040] Decorrelating experience for 160 frames... [2023-03-09 10:31:58,424][120778] Decorrelating experience for 288 frames... [2023-03-09 10:31:58,442][119515] Decorrelating experience for 480 frames... [2023-03-09 10:31:58,458][119525] Decorrelating experience for 352 frames... [2023-03-09 10:31:58,480][119527] Decorrelating experience for 480 frames... [2023-03-09 10:31:58,480][119535] Decorrelating experience for 544 frames... [2023-03-09 10:31:58,504][119680] Decorrelating experience for 256 frames... [2023-03-09 10:31:58,508][119478] Decorrelating experience for 160 frames... [2023-03-09 10:31:58,600][120652] Decorrelating experience for 288 frames... [2023-03-09 10:31:58,600][119807] Decorrelating experience for 416 frames... [2023-03-09 10:31:58,612][119388] Decorrelating experience for 160 frames... [2023-03-09 10:31:58,626][119808] Decorrelating experience for 416 frames... [2023-03-09 10:31:58,629][120073] Decorrelating experience for 224 frames... [2023-03-09 10:31:58,639][119493] Decorrelating experience for 160 frames... [2023-03-09 10:31:58,671][119900] Decorrelating experience for 320 frames... [2023-03-09 10:31:58,685][119397] Decorrelating experience for 320 frames... [2023-03-09 10:31:58,690][119390] Decorrelating experience for 384 frames... [2023-03-09 10:31:58,692][119462] Decorrelating experience for 320 frames... [2023-03-09 10:31:58,785][119546] Decorrelating experience for 448 frames... [2023-03-09 10:31:58,798][119532] Decorrelating experience for 384 frames... [2023-03-09 10:31:58,825][119525] Decorrelating experience for 384 frames... [2023-03-09 10:31:58,826][120135] Decorrelating experience for 384 frames... [2023-03-09 10:31:58,833][120005] Decorrelating experience for 96 frames... [2023-03-09 10:31:58,856][119470] Decorrelating experience for 352 frames... [2023-03-09 10:31:58,869][120778] Decorrelating experience for 320 frames... [2023-03-09 10:31:58,877][119937] Decorrelating experience for 416 frames... [2023-03-09 10:31:58,881][119493] Decorrelating experience for 192 frames... [2023-03-09 10:31:58,883][119490] Decorrelating experience for 544 frames... [2023-03-09 10:31:58,902][118949] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 2000027648. Throughput: 0: 0.0. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) [2023-03-09 10:31:58,971][119615] Decorrelating experience for 288 frames... [2023-03-09 10:31:59,011][120073] Decorrelating experience for 256 frames... [2023-03-09 10:31:59,013][119808] Decorrelating experience for 448 frames... [2023-03-09 10:31:59,058][119539] Decorrelating experience for 96 frames... [2023-03-09 10:31:59,059][120005] Decorrelating experience for 128 frames... [2023-03-09 10:31:59,064][119477] Decorrelating experience for 256 frames... [2023-03-09 10:31:59,070][120134] Decorrelating experience for 576 frames... [2023-03-09 10:31:59,101][119397] Decorrelating experience for 352 frames... [2023-03-09 10:31:59,106][119540] Decorrelating experience for 320 frames... [2023-03-09 10:31:59,119][119478] Decorrelating experience for 192 frames... [2023-03-09 10:31:59,148][119509] Decorrelating experience for 448 frames... [2023-03-09 10:31:59,195][119525] Decorrelating experience for 416 frames... [2023-03-09 10:31:59,209][119499] Decorrelating experience for 256 frames... [2023-03-09 10:31:59,251][120135] Decorrelating experience for 416 frames... [2023-03-09 10:31:59,258][119946] Decorrelating experience for 128 frames... [2023-03-09 10:31:59,266][119503] Decorrelating experience for 736 frames... [2023-03-09 10:31:59,286][119510] Decorrelating experience for 416 frames... [2023-03-09 10:31:59,294][119527] Decorrelating experience for 512 frames... [2023-03-09 10:31:59,307][125883] Decorrelating experience for 224 frames... [2023-03-09 10:31:59,324][119937] Decorrelating experience for 448 frames... [2023-03-09 10:31:59,339][120652] Decorrelating experience for 320 frames... [2023-03-09 10:31:59,390][119500] Decorrelating experience for 352 frames... [2023-03-09 10:31:59,395][119519] Decorrelating experience for 352 frames... [2023-03-09 10:31:59,434][119479] Decorrelating experience for 288 frames... [2023-03-09 10:31:59,441][119477] Decorrelating experience for 288 frames... [2023-03-09 10:31:59,453][119655] Decorrelating experience for 288 frames... [2023-03-09 10:31:59,497][119392] Decorrelating experience for 96 frames... [2023-03-09 10:31:59,535][119546] Decorrelating experience for 480 frames... [2023-03-09 10:31:59,542][119539] Decorrelating experience for 128 frames... [2023-03-09 10:31:59,542][119540] Decorrelating experience for 352 frames... [2023-03-09 10:31:59,559][119473] Decorrelating experience for 160 frames... [2023-03-09 10:31:59,572][119484] Decorrelating experience for 384 frames... [2023-03-09 10:31:59,622][119526] Decorrelating experience for 352 frames... [2023-03-09 10:31:59,623][119508] Decorrelating experience for 224 frames... [2023-03-09 10:31:59,625][119532] Decorrelating experience for 416 frames... [2023-03-09 10:31:59,646][119509] Decorrelating experience for 480 frames... [2023-03-09 10:31:59,677][120629] Decorrelating experience for 416 frames... [2023-03-09 10:31:59,724][119503] Decorrelating experience for 768 frames... [2023-03-09 10:31:59,728][119477] Decorrelating experience for 320 frames... [2023-03-09 10:31:59,745][120005] Decorrelating experience for 160 frames... [2023-03-09 10:31:59,759][119808] Decorrelating experience for 480 frames... [2023-03-09 10:31:59,808][119535] Decorrelating experience for 576 frames... [2023-03-09 10:31:59,811][119525] Decorrelating experience for 448 frames... [2023-03-09 10:31:59,813][119549] Decorrelating experience for 256 frames... [2023-03-09 10:31:59,893][119484] Decorrelating experience for 416 frames... [2023-03-09 10:31:59,910][119478] Decorrelating experience for 224 frames... [2023-03-09 10:31:59,913][119655] Decorrelating experience for 320 frames... [2023-03-09 10:31:59,925][119501] Decorrelating experience for 64 frames... [2023-03-09 10:31:59,947][119680] Decorrelating experience for 288 frames... [2023-03-09 10:31:59,948][119389] Decorrelating experience for 288 frames... [2023-03-09 10:31:59,960][119481] Decorrelating experience for 416 frames... [2023-03-09 10:31:59,992][119394] Decorrelating experience for 192 frames... [2023-03-09 10:31:59,994][119946] Decorrelating experience for 160 frames... [2023-03-09 10:32:00,016][120615] Decorrelating experience for 352 frames... [2023-03-09 10:32:00,077][119477] Decorrelating experience for 352 frames... [2023-03-09 10:32:00,103][119462] Decorrelating experience for 352 frames... [2023-03-09 10:32:00,107][119509] Decorrelating experience for 512 frames... [2023-03-09 10:32:00,109][119548] Decorrelating experience for 384 frames... [2023-03-09 10:32:00,151][119533] Decorrelating experience for 480 frames... [2023-03-09 10:32:00,152][119395] Decorrelating experience for 96 frames... [2023-03-09 10:32:00,173][119807] Decorrelating experience for 448 frames... [2023-03-09 10:32:00,180][120199] Decorrelating experience for 96 frames... [2023-03-09 10:32:00,182][119513] Decorrelating experience for 288 frames... [2023-03-09 10:32:00,212][119494] Decorrelating experience for 96 frames... [2023-03-09 10:32:00,259][119525] Decorrelating experience for 480 frames... [2023-03-09 10:32:00,293][119503] Decorrelating experience for 800 frames... [2023-03-09 10:32:00,294][120134] Decorrelating experience for 608 frames... [2023-03-09 10:32:00,306][119540] Decorrelating experience for 384 frames... [2023-03-09 10:32:00,348][119483] Decorrelating experience for 416 frames... [2023-03-09 10:32:00,367][119519] Decorrelating experience for 384 frames... [2023-03-09 10:32:00,367][119851] Decorrelating experience for 192 frames... [2023-03-09 10:32:00,380][119484] Decorrelating experience for 448 frames... [2023-03-09 10:32:00,384][120002] Decorrelating experience for 256 frames... [2023-03-09 10:32:00,390][119946] Decorrelating experience for 192 frames... [2023-03-09 10:32:00,442][120629] Decorrelating experience for 448 frames... [2023-03-09 10:32:00,479][119470] Decorrelating experience for 384 frames... [2023-03-09 10:32:00,521][119900] Decorrelating experience for 352 frames... [2023-03-09 10:32:00,526][119527] Decorrelating experience for 544 frames... [2023-03-09 10:32:00,550][120199] Decorrelating experience for 128 frames... [2023-03-09 10:32:00,556][119499] Decorrelating experience for 288 frames... [2023-03-09 10:32:00,572][119514] Decorrelating experience for 256 frames... [2023-03-09 10:32:00,577][119472] Decorrelating experience for 224 frames... [2023-03-09 10:32:00,580][119390] Decorrelating experience for 416 frames... [2023-03-09 10:32:00,602][119548] Decorrelating experience for 416 frames... [2023-03-09 10:32:00,627][119513] Decorrelating experience for 320 frames... [2023-03-09 10:32:00,662][119515] Decorrelating experience for 512 frames... [2023-03-09 10:32:00,711][120002] Decorrelating experience for 288 frames... [2023-03-09 10:32:00,711][119496] Decorrelating experience for 160 frames... [2023-03-09 10:32:00,734][119476] Decorrelating experience for 192 frames... [2023-03-09 10:32:00,740][119680] Decorrelating experience for 320 frames... [2023-03-09 10:32:00,762][119533] Decorrelating experience for 512 frames... [2023-03-09 10:32:00,770][119525] Decorrelating experience for 512 frames... [2023-03-09 10:32:00,783][119543] Decorrelating experience for 384 frames... [2023-03-09 10:32:00,801][119481] Decorrelating experience for 448 frames... [2023-03-09 10:32:00,810][119394] Decorrelating experience for 224 frames... [2023-03-09 10:32:00,858][120134] Decorrelating experience for 640 frames... [2023-03-09 10:32:00,901][119472] Decorrelating experience for 256 frames... [2023-03-09 10:32:00,902][119546] Decorrelating experience for 512 frames... [2023-03-09 10:32:00,924][119536] Decorrelating experience for 224 frames... [2023-03-09 10:32:00,926][119504] Decorrelating experience for 224 frames... [2023-03-09 10:32:01,007][120263] Decorrelating experience for 288 frames... [2023-03-09 10:32:01,008][119900] Decorrelating experience for 384 frames... [2023-03-09 10:32:01,008][120073] Decorrelating experience for 288 frames... [2023-03-09 10:32:01,009][119508] Decorrelating experience for 256 frames... [2023-03-09 10:32:01,009][119478] Decorrelating experience for 256 frames... [2023-03-09 10:32:01,094][119615] Decorrelating experience for 320 frames... [2023-03-09 10:32:01,095][119488] Decorrelating experience for 256 frames... [2023-03-09 10:32:01,111][120629] Decorrelating experience for 480 frames... [2023-03-09 10:32:01,140][120135] Decorrelating experience for 448 frames... [2023-03-09 10:32:01,140][120896] Decorrelating experience for 512 frames... [2023-03-09 10:32:01,204][119470] Decorrelating experience for 416 frames... [2023-03-09 10:32:01,208][119549] Decorrelating experience for 288 frames... [2023-03-09 10:32:01,209][119536] Decorrelating experience for 256 frames... [2023-03-09 10:32:01,209][119515] Decorrelating experience for 544 frames... [2023-03-09 10:32:01,210][120002] Decorrelating experience for 320 frames... [2023-03-09 10:32:01,210][119522] Another process currently holds the lock /tmp/sf2_rolo/doom_007.lockfile, attempt: 1 [2023-03-09 10:32:01,293][119523] Decorrelating experience for 480 frames... [2023-03-09 10:32:01,294][119397] Decorrelating experience for 384 frames... [2023-03-09 10:32:01,335][120134] Decorrelating experience for 672 frames... [2023-03-09 10:32:01,336][119472] Decorrelating experience for 288 frames... [2023-03-09 10:32:01,338][119508] Decorrelating experience for 288 frames... [2023-03-09 10:32:01,402][119505] Decorrelating experience for 96 frames... [2023-03-09 10:32:01,408][119477] Decorrelating experience for 384 frames... [2023-03-09 10:32:01,409][119513] Decorrelating experience for 352 frames... [2023-03-09 10:32:01,410][119493] Decorrelating experience for 224 frames... [2023-03-09 10:32:01,443][119527] Decorrelating experience for 576 frames... [2023-03-09 10:32:01,485][119536] Decorrelating experience for 288 frames... [2023-03-09 10:32:01,490][119542] Decorrelating experience for 512 frames... [2023-03-09 10:32:01,549][119510] Decorrelating experience for 448 frames... [2023-03-09 10:32:01,550][119499] Decorrelating experience for 320 frames... [2023-03-09 10:32:01,567][119530] Another process currently holds the lock /tmp/sf2_rolo/doom_006.lockfile, attempt: 1 [2023-03-09 10:32:01,583][119528] Decorrelating experience for 352 frames... [2023-03-09 10:32:01,593][119470] Decorrelating experience for 448 frames... [2023-03-09 10:32:01,595][119548] Decorrelating experience for 448 frames... [2023-03-09 10:32:01,678][119505] Decorrelating experience for 128 frames... [2023-03-09 10:32:01,681][119680] Decorrelating experience for 352 frames... [2023-03-09 10:32:01,681][119508] Decorrelating experience for 320 frames... [2023-03-09 10:32:01,681][119545] Decorrelating experience for 256 frames... [2023-03-09 10:32:01,695][119394] Decorrelating experience for 256 frames... [2023-03-09 10:32:01,749][119808] Decorrelating experience for 512 frames... [2023-03-09 10:32:01,764][119397] Decorrelating experience for 416 frames... [2023-03-09 10:32:01,779][119472] Decorrelating experience for 320 frames... [2023-03-09 10:32:01,790][119478] Decorrelating experience for 288 frames... [2023-03-09 10:32:01,792][120550] Decorrelating experience for 320 frames... [2023-03-09 10:32:01,864][120896] Decorrelating experience for 544 frames... [2023-03-09 10:32:01,874][119481] Decorrelating experience for 480 frames... [2023-03-09 10:32:01,894][119503] Decorrelating experience for 832 frames... [2023-03-09 10:32:01,910][119541] Decorrelating experience for 96 frames... [2023-03-09 10:32:01,960][119533] Decorrelating experience for 544 frames... [2023-03-09 10:32:01,964][119542] Decorrelating experience for 544 frames... [2023-03-09 10:32:01,964][119543] Decorrelating experience for 416 frames... [2023-03-09 10:32:01,988][119475] Decorrelating experience for 256 frames... [2023-03-09 10:32:01,996][119946] Decorrelating experience for 224 frames... [2023-03-09 10:32:01,997][119496] Decorrelating experience for 192 frames... [2023-03-09 10:32:02,043][120652] Decorrelating experience for 352 frames... [2023-03-09 10:32:02,076][119478] Decorrelating experience for 320 frames... [2023-03-09 10:32:02,091][119548] Decorrelating experience for 480 frames... [2023-03-09 10:32:02,095][119485] Decorrelating experience for 384 frames... [2023-03-09 10:32:02,146][119464] Decorrelating experience for 224 frames... [2023-03-09 10:32:02,153][119395] Decorrelating experience for 128 frames... [2023-03-09 10:32:02,181][119508] Decorrelating experience for 352 frames... [2023-03-09 10:32:02,194][119394] Decorrelating experience for 288 frames... [2023-03-09 10:32:02,195][119516] Decorrelating experience for 544 frames... [2023-03-09 10:32:02,224][119488] Decorrelating experience for 288 frames... [2023-03-09 10:32:02,256][119541] Decorrelating experience for 128 frames... [2023-03-09 10:32:02,329][119536] Decorrelating experience for 320 frames... [2023-03-09 10:32:02,341][119398] Decorrelating experience for 192 frames... [2023-03-09 10:32:02,352][119475] Decorrelating experience for 288 frames... [2023-03-09 10:32:02,354][120615] Decorrelating experience for 384 frames... [2023-03-09 10:32:02,366][119900] Decorrelating experience for 416 frames... [2023-03-09 10:32:02,402][120877] Decorrelating experience for 224 frames... [2023-03-09 10:32:02,406][119549] Decorrelating experience for 320 frames... [2023-03-09 10:32:02,426][119946] Decorrelating experience for 256 frames... [2023-03-09 10:32:02,453][119480] Decorrelating experience for 320 frames... [2023-03-09 10:32:02,505][120550] Decorrelating experience for 352 frames... [2023-03-09 10:32:02,533][119478] Decorrelating experience for 352 frames... [2023-03-09 10:32:02,534][119472] Decorrelating experience for 352 frames... [2023-03-09 10:32:02,549][119511] Decorrelating experience for 256 frames... [2023-03-09 10:32:02,552][119615] Decorrelating experience for 352 frames... [2023-03-09 10:32:02,563][119505] Decorrelating experience for 160 frames... [2023-03-09 10:32:02,593][119470] Decorrelating experience for 480 frames... [2023-03-09 10:32:02,598][119391] Decorrelating experience for 224 frames... [2023-03-09 10:32:02,615][119485] Decorrelating experience for 416 frames... [2023-03-09 10:32:02,655][119484] Decorrelating experience for 480 frames... [2023-03-09 10:32:02,693][119508] Decorrelating experience for 384 frames... [2023-03-09 10:32:02,720][119548] Decorrelating experience for 512 frames... [2023-03-09 10:32:02,737][119394] Decorrelating experience for 320 frames... [2023-03-09 10:32:02,738][119481] Decorrelating experience for 512 frames... [2023-03-09 10:32:02,745][119395] Decorrelating experience for 160 frames... [2023-03-09 10:32:02,763][119464] Decorrelating experience for 256 frames... [2023-03-09 10:32:02,779][119396] Decorrelating experience for 224 frames... [2023-03-09 10:32:02,798][119808] Decorrelating experience for 544 frames... [2023-03-09 10:32:02,803][119474] Decorrelating experience for 384 frames... [2023-03-09 10:32:02,849][119490] Decorrelating experience for 576 frames... [2023-03-09 10:32:02,881][119536] Decorrelating experience for 352 frames... [2023-03-09 10:32:02,947][119527] Decorrelating experience for 608 frames... [2023-03-09 10:32:02,950][119472] Decorrelating experience for 384 frames... [2023-03-09 10:32:02,958][119504] Decorrelating experience for 256 frames... [2023-03-09 10:32:03,001][119521] Decorrelating experience for 288 frames... [2023-03-09 10:32:03,003][120615] Decorrelating experience for 416 frames... [2023-03-09 10:32:03,003][119614] Decorrelating experience for 192 frames... [2023-03-09 10:32:03,009][120877] Decorrelating experience for 256 frames... [2023-03-09 10:32:03,018][119486] Decorrelating experience for 160 frames... [2023-03-09 10:32:03,064][119615] Decorrelating experience for 384 frames... [2023-03-09 10:32:03,106][119508] Decorrelating experience for 416 frames... [2023-03-09 10:32:03,133][119513] Decorrelating experience for 384 frames... [2023-03-09 10:32:03,138][119394] Decorrelating experience for 352 frames... [2023-03-09 10:32:03,143][119395] Decorrelating experience for 192 frames... [2023-03-09 10:32:03,183][119493] Decorrelating experience for 256 frames... [2023-03-09 10:32:03,198][119548] Decorrelating experience for 544 frames... [2023-03-09 10:32:03,198][119464] Decorrelating experience for 288 frames... [2023-03-09 10:32:03,205][119937] Decorrelating experience for 480 frames... [2023-03-09 10:32:03,206][119526] Decorrelating experience for 384 frames... [2023-03-09 10:32:03,243][119490] Decorrelating experience for 608 frames... [2023-03-09 10:32:03,314][119484] Decorrelating experience for 512 frames... [2023-03-09 10:32:03,317][119391] Decorrelating experience for 256 frames... [2023-03-09 10:32:03,323][119398] Decorrelating experience for 224 frames... [2023-03-09 10:32:03,325][119502] Another process currently holds the lock /tmp/sf2_rolo/doom_007.lockfile, attempt: 1 [2023-03-09 10:32:03,366][119530] Decorrelating experience for 96 frames... [2023-03-09 10:32:03,368][119500] Decorrelating experience for 384 frames... [2023-03-09 10:32:03,400][119395] Decorrelating experience for 224 frames... [2023-03-09 10:32:03,407][119486] Decorrelating experience for 192 frames... [2023-03-09 10:32:03,420][119528] Decorrelating experience for 384 frames... [2023-03-09 10:32:03,459][120877] Decorrelating experience for 288 frames... [2023-03-09 10:32:03,466][119808] Decorrelating experience for 576 frames... [2023-03-09 10:32:03,504][119470] Decorrelating experience for 512 frames... [2023-03-09 10:32:03,543][120896] Decorrelating experience for 576 frames... [2023-03-09 10:32:03,557][119473] Decorrelating experience for 192 frames... [2023-03-09 10:32:03,561][119487] Decorrelating experience for 256 frames... [2023-03-09 10:32:03,584][119533] Decorrelating experience for 576 frames... [2023-03-09 10:32:03,613][119542] Decorrelating experience for 576 frames... [2023-03-09 10:32:03,613][119538] Decorrelating experience for 96 frames... [2023-03-09 10:32:03,656][120199] Decorrelating experience for 160 frames... [2023-03-09 10:32:03,667][119388] Decorrelating experience for 192 frames... [2023-03-09 10:32:03,677][119527] Decorrelating experience for 640 frames... [2023-03-09 10:32:03,703][119485] Decorrelating experience for 448 frames... [2023-03-09 10:32:03,739][119500] Decorrelating experience for 416 frames... [2023-03-09 10:32:03,746][119477] Decorrelating experience for 416 frames... [2023-03-09 10:32:03,754][119490] Decorrelating experience for 640 frames... [2023-03-09 10:32:03,778][120134] Decorrelating experience for 704 frames... [2023-03-09 10:32:03,812][119496] Decorrelating experience for 224 frames... [2023-03-09 10:32:03,851][119522] Decorrelating experience for 128 frames... [2023-03-09 10:32:03,867][120073] Decorrelating experience for 320 frames... [2023-03-09 10:32:03,868][120135] Decorrelating experience for 480 frames... [2023-03-09 10:32:03,868][119851] Decorrelating experience for 224 frames... [2023-03-09 10:32:03,902][118949] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 2000027648. Throughput: 0: 0.0. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) [2023-03-09 10:32:03,910][119510] Decorrelating experience for 480 frames... [2023-03-09 10:32:03,937][119538] Decorrelating experience for 128 frames... [2023-03-09 10:32:03,939][120877] Decorrelating experience for 320 frames... [2023-03-09 10:32:03,956][119474] Decorrelating experience for 416 frames... [2023-03-09 10:32:03,979][120002] Decorrelating experience for 352 frames... [2023-03-09 10:32:03,998][120199] Decorrelating experience for 192 frames... [2023-03-09 10:32:04,059][119808] Decorrelating experience for 608 frames... [2023-03-09 10:32:04,064][119519] Decorrelating experience for 416 frames... [2023-03-09 10:32:04,087][119528] Decorrelating experience for 416 frames... [2023-03-09 10:32:04,113][120550] Decorrelating experience for 384 frames... [2023-03-09 10:32:04,127][119534] Decorrelating experience for 288 frames... [2023-03-09 10:32:04,142][119530] Decorrelating experience for 128 frames... [2023-03-09 10:32:04,142][119851] Decorrelating experience for 256 frames... [2023-03-09 10:32:04,166][119538] Decorrelating experience for 160 frames... [2023-03-09 10:32:04,181][119548] Decorrelating experience for 576 frames... [2023-03-09 10:32:04,188][119394] Decorrelating experience for 384 frames... [2023-03-09 10:32:04,263][119542] Decorrelating experience for 608 frames... [2023-03-09 10:32:04,264][119494] Decorrelating experience for 128 frames... [2023-03-09 10:32:04,268][119512] Decorrelating experience for 512 frames... [2023-03-09 10:32:04,316][120040] Decorrelating experience for 192 frames... [2023-03-09 10:32:04,317][119473] Decorrelating experience for 224 frames... [2023-03-09 10:32:04,326][119470] Decorrelating experience for 544 frames... [2023-03-09 10:32:04,355][119388] Decorrelating experience for 224 frames... [2023-03-09 10:32:04,356][119475] Decorrelating experience for 320 frames... [2023-03-09 10:32:04,376][120134] Decorrelating experience for 736 frames... [2023-03-09 10:32:04,376][120073] Decorrelating experience for 352 frames... [2023-03-09 10:32:04,431][120004] Another process currently holds the lock /tmp/sf2_rolo/doom_006.lockfile, attempt: 1 [2023-03-09 10:32:04,456][119485] Decorrelating experience for 480 frames... [2023-03-09 10:32:04,467][120005] Decorrelating experience for 192 frames... [2023-03-09 10:32:04,470][119493] Decorrelating experience for 288 frames... [2023-03-09 10:32:04,502][119474] Decorrelating experience for 448 frames... [2023-03-09 10:32:04,518][119501] Decorrelating experience for 96 frames... [2023-03-09 10:32:04,519][119538] Decorrelating experience for 192 frames... [2023-03-09 10:32:04,538][120629] Decorrelating experience for 512 frames... [2023-03-09 10:32:04,559][119680] Decorrelating experience for 384 frames... [2023-03-09 10:32:04,563][120003] Decorrelating experience for 544 frames... [2023-03-09 10:32:04,574][119500] Decorrelating experience for 448 frames... [2023-03-09 10:32:04,666][119532] Decorrelating experience for 448 frames... [2023-03-09 10:32:04,668][119389] Decorrelating experience for 320 frames... [2023-03-09 10:32:04,684][119472] Decorrelating experience for 416 frames... [2023-03-09 10:32:04,689][119394] Decorrelating experience for 416 frames... [2023-03-09 10:32:04,703][120199] Decorrelating experience for 224 frames... [2023-03-09 10:32:04,714][119397] Decorrelating experience for 448 frames... [2023-03-09 10:32:04,720][119530] Decorrelating experience for 160 frames... [2023-03-09 10:32:04,760][119475] Decorrelating experience for 352 frames... [2023-03-09 10:32:04,799][120002] Decorrelating experience for 384 frames... [2023-03-09 10:32:04,807][119528] Decorrelating experience for 448 frames... [2023-03-09 10:32:04,849][119474] Decorrelating experience for 480 frames... [2023-03-09 10:32:04,868][119529] Decorrelating experience for 96 frames... [2023-03-09 10:32:04,872][119517] Decorrelating experience for 160 frames... [2023-03-09 10:32:04,882][119490] Decorrelating experience for 672 frames... [2023-03-09 10:32:04,900][120877] Decorrelating experience for 352 frames... [2023-03-09 10:32:04,902][119546] Decorrelating experience for 544 frames... [2023-03-09 10:32:04,908][119493] Decorrelating experience for 320 frames... [2023-03-09 10:32:04,964][120629] Decorrelating experience for 544 frames... [2023-03-09 10:32:04,999][119521] Decorrelating experience for 320 frames... [2023-03-09 10:32:05,003][119487] Decorrelating experience for 288 frames... [2023-03-09 10:32:05,030][119680] Decorrelating experience for 416 frames... [2023-03-09 10:32:05,063][119470] Decorrelating experience for 576 frames... [2023-03-09 10:32:05,067][119398] Decorrelating experience for 256 frames... [2023-03-09 10:32:05,071][120199] Decorrelating experience for 256 frames... [2023-03-09 10:32:05,090][119496] Decorrelating experience for 256 frames... [2023-03-09 10:32:05,091][119488] Decorrelating experience for 320 frames... [2023-03-09 10:32:05,095][119464] Decorrelating experience for 320 frames... [2023-03-09 10:32:05,164][119397] Decorrelating experience for 480 frames... [2023-03-09 10:32:05,204][119536] Decorrelating experience for 384 frames... [2023-03-09 10:32:05,220][119499] Decorrelating experience for 352 frames... [2023-03-09 10:32:05,226][119472] Decorrelating experience for 448 frames... [2023-03-09 10:32:05,237][119547] Another process currently holds the lock /tmp/sf2_rolo/doom_006.lockfile, attempt: 1 [2023-03-09 10:32:05,269][119517] Decorrelating experience for 192 frames... [2023-03-09 10:32:05,278][119502] Decorrelating experience for 96 frames... [2023-03-09 10:32:05,284][126685] Decorrelating experience for 416 frames... [2023-03-09 10:32:05,284][120653] Decorrelating experience for 0 frames... [2023-03-09 10:32:05,286][119519] Decorrelating experience for 448 frames... [2023-03-09 10:32:05,288][119526] Decorrelating experience for 416 frames... [2023-03-09 10:32:05,349][120263] Decorrelating experience for 320 frames... [2023-03-09 10:32:05,455][120199] Decorrelating experience for 288 frames... [2023-03-09 10:32:05,460][120003] Decorrelating experience for 576 frames... [2023-03-09 10:32:05,476][119470] Decorrelating experience for 608 frames... [2023-03-09 10:32:05,482][119527] Decorrelating experience for 672 frames... [2023-03-09 10:32:05,482][119532] Decorrelating experience for 480 frames... [2023-03-09 10:32:05,483][119808] Decorrelating experience for 640 frames... [2023-03-09 10:32:05,483][119391] Decorrelating experience for 288 frames... [2023-03-09 10:32:05,487][120904] Decorrelating experience for 256 frames... [2023-03-09 10:32:05,517][119464] Decorrelating experience for 352 frames... [2023-03-09 10:32:05,530][119548] Decorrelating experience for 608 frames... [2023-03-09 10:32:05,643][119504] Decorrelating experience for 288 frames... [2023-03-09 10:32:05,645][119522] Decorrelating experience for 160 frames... [2023-03-09 10:32:05,684][119530] Decorrelating experience for 192 frames... [2023-03-09 10:32:05,686][119478] Decorrelating experience for 384 frames... [2023-03-09 10:32:05,687][120653] Decorrelating experience for 32 frames... [2023-03-09 10:32:05,688][119539] Decorrelating experience for 160 frames... [2023-03-09 10:32:05,688][120877] Decorrelating experience for 384 frames... [2023-03-09 10:32:05,689][119526] Decorrelating experience for 448 frames... [2023-03-09 10:32:05,722][119392] Decorrelating experience for 128 frames... [2023-03-09 10:32:05,739][119544] Another process currently holds the lock /tmp/sf2_rolo/doom_002.lockfile, attempt: 1 [2023-03-09 10:32:05,826][120002] Decorrelating experience for 416 frames... [2023-03-09 10:32:05,831][120040] Decorrelating experience for 224 frames... [2023-03-09 10:32:05,896][126685] Decorrelating experience for 448 frames... [2023-03-09 10:32:05,897][119514] Decorrelating experience for 288 frames... [2023-03-09 10:32:05,898][120778] Decorrelating experience for 352 frames... [2023-03-09 10:32:05,898][119513] Decorrelating experience for 416 frames... [2023-03-09 10:32:05,898][119391] Decorrelating experience for 320 frames... [2023-03-09 10:32:05,903][119521] Decorrelating experience for 352 frames... [2023-03-09 10:32:05,931][120003] Decorrelating experience for 608 frames... [2023-03-09 10:32:05,941][119389] Decorrelating experience for 352 frames... [2023-03-09 10:32:06,030][119900] Decorrelating experience for 448 frames... [2023-03-09 10:32:06,031][119475] Decorrelating experience for 384 frames... [2023-03-09 10:32:06,099][125883] Decorrelating experience for 256 frames... [2023-03-09 10:32:06,101][119508] Decorrelating experience for 448 frames... [2023-03-09 10:32:06,101][120653] Decorrelating experience for 64 frames... [2023-03-09 10:32:06,102][119504] Decorrelating experience for 320 frames... [2023-03-09 10:32:06,103][119530] Decorrelating experience for 224 frames... [2023-03-09 10:32:06,128][120005] Decorrelating experience for 224 frames... [2023-03-09 10:32:06,144][120040] Decorrelating experience for 256 frames... [2023-03-09 10:32:06,153][119487] Decorrelating experience for 320 frames... [2023-03-09 10:32:06,239][119514] Decorrelating experience for 320 frames... [2023-03-09 10:32:06,244][119528] Decorrelating experience for 480 frames... [2023-03-09 10:32:06,295][119680] Decorrelating experience for 448 frames... [2023-03-09 10:32:06,296][119499] Decorrelating experience for 384 frames... [2023-03-09 10:32:06,298][119395] Decorrelating experience for 256 frames... [2023-03-09 10:32:06,333][120615] Decorrelating experience for 448 frames... [2023-03-09 10:32:06,342][119500] Decorrelating experience for 480 frames... [2023-03-09 10:32:06,352][120263] Decorrelating experience for 352 frames... [2023-03-09 10:32:06,359][120778] Decorrelating experience for 384 frames... [2023-03-09 10:32:06,381][119615] Decorrelating experience for 416 frames... [2023-03-09 10:32:06,430][119900] Decorrelating experience for 480 frames... [2023-03-09 10:32:06,443][120135] Decorrelating experience for 512 frames... [2023-03-09 10:32:06,488][119472] Decorrelating experience for 480 frames... [2023-03-09 10:32:06,489][119485] Decorrelating experience for 512 frames... [2023-03-09 10:32:06,510][119479] Decorrelating experience for 320 frames... [2023-03-09 10:32:06,529][119397] Decorrelating experience for 512 frames... [2023-03-09 10:32:06,531][119486] Decorrelating experience for 224 frames... [2023-03-09 10:32:06,588][119514] Decorrelating experience for 352 frames... [2023-03-09 10:32:06,596][119504] Decorrelating experience for 352 frames... [2023-03-09 10:32:06,660][119546] Decorrelating experience for 576 frames... [2023-03-09 10:32:06,661][119526] Decorrelating experience for 480 frames... [2023-03-09 10:32:06,662][119536] Decorrelating experience for 416 frames... [2023-03-09 10:32:06,675][120904] Decorrelating experience for 288 frames... [2023-03-09 10:32:06,678][120040] Decorrelating experience for 288 frames... [2023-03-09 10:32:06,695][119522] Decorrelating experience for 192 frames... [2023-03-09 10:32:06,716][120263] Decorrelating experience for 384 frames... [2023-03-09 10:32:06,732][119549] Decorrelating experience for 352 frames... [2023-03-09 10:32:06,796][119680] Decorrelating experience for 480 frames... [2023-03-09 10:32:06,831][120615] Decorrelating experience for 480 frames... [2023-03-09 10:32:06,855][119486] Decorrelating experience for 256 frames... [2023-03-09 10:32:06,866][119391] Decorrelating experience for 352 frames... [2023-03-09 10:32:06,867][120629] Decorrelating experience for 576 frames... [2023-03-09 10:32:06,869][120002] Decorrelating experience for 448 frames... [2023-03-09 10:32:06,879][119520] Decorrelating experience for 64 frames... [2023-03-09 10:32:06,912][119615] Decorrelating experience for 448 frames... [2023-03-09 10:32:06,915][119479] Decorrelating experience for 352 frames... [2023-03-09 10:32:06,934][121015] Decorrelating experience for 256 frames... [2023-03-09 10:32:06,991][119900] Decorrelating experience for 512 frames... [2023-03-09 10:32:07,052][119549] Decorrelating experience for 384 frames... [2023-03-09 10:32:07,068][119488] Decorrelating experience for 352 frames... [2023-03-09 10:32:07,069][119394] Decorrelating experience for 448 frames... [2023-03-09 10:32:07,069][119397] Decorrelating experience for 544 frames... [2023-03-09 10:32:07,100][119501] Decorrelating experience for 128 frames... [2023-03-09 10:32:07,107][119392] Decorrelating experience for 160 frames... [2023-03-09 10:32:07,115][119500] Decorrelating experience for 512 frames... [2023-03-09 10:32:07,154][119504] Decorrelating experience for 384 frames... [2023-03-09 10:32:07,172][119474] Decorrelating experience for 512 frames... [2023-03-09 10:32:07,202][119525] Decorrelating experience for 544 frames... [2023-03-09 10:32:07,262][120005] Decorrelating experience for 256 frames... [2023-03-09 10:32:07,266][119514] Decorrelating experience for 384 frames... [2023-03-09 10:32:07,267][119398] Decorrelating experience for 288 frames... [2023-03-09 10:32:07,268][119680] Decorrelating experience for 512 frames... [2023-03-09 10:32:07,281][119543] Decorrelating experience for 448 frames... [2023-03-09 10:32:07,291][119399] Decorrelating experience for 288 frames... [2023-03-09 10:32:07,306][119536] Decorrelating experience for 448 frames... [2023-03-09 10:32:07,339][120263] Decorrelating experience for 416 frames... [2023-03-09 10:32:07,365][119503] Decorrelating experience for 864 frames... [2023-03-09 10:32:07,397][119532] Decorrelating experience for 512 frames... [2023-03-09 10:32:07,459][119396] Decorrelating experience for 256 frames... [2023-03-09 10:32:07,460][119529] Decorrelating experience for 128 frames... [2023-03-09 10:32:07,464][119472] Decorrelating experience for 512 frames... [2023-03-09 10:32:07,467][119487] Decorrelating experience for 352 frames... [2023-03-09 10:32:07,480][119493] Decorrelating experience for 352 frames... [2023-03-09 10:32:07,480][119499] Decorrelating experience for 416 frames... [2023-03-09 10:32:07,540][120005] Decorrelating experience for 288 frames... [2023-03-09 10:32:07,552][119522] Decorrelating experience for 224 frames... [2023-03-09 10:32:07,561][119389] Decorrelating experience for 384 frames... [2023-03-09 10:32:07,579][119504] Decorrelating experience for 416 frames... [2023-03-09 10:32:07,652][119514] Decorrelating experience for 416 frames... [2023-03-09 10:32:07,653][119523] Decorrelating experience for 512 frames... [2023-03-09 10:32:07,659][119536] Decorrelating experience for 480 frames... [2023-03-09 10:32:07,674][119533] Decorrelating experience for 608 frames... [2023-03-09 10:32:07,676][119512] Decorrelating experience for 544 frames... [2023-03-09 10:32:07,680][119545] Decorrelating experience for 288 frames... [2023-03-09 10:32:07,742][119529] Decorrelating experience for 160 frames... [2023-03-09 10:32:07,763][119502] Decorrelating experience for 128 frames... [2023-03-09 10:32:07,765][119475] Decorrelating experience for 416 frames... [2023-03-09 10:32:07,818][119680] Decorrelating experience for 544 frames... [2023-03-09 10:32:07,848][119488] Decorrelating experience for 384 frames... [2023-03-09 10:32:07,849][119506] Decorrelating experience for 352 frames... [2023-03-09 10:32:07,852][120778] Decorrelating experience for 416 frames... [2023-03-09 10:32:07,870][119517] Decorrelating experience for 224 frames... [2023-03-09 10:32:07,871][119542] Decorrelating experience for 640 frames... [2023-03-09 10:32:07,874][120629] Decorrelating experience for 608 frames... [2023-03-09 10:32:07,930][120005] Decorrelating experience for 320 frames... [2023-03-09 10:32:07,957][119397] Decorrelating experience for 576 frames... [2023-03-09 10:32:07,968][119546] Decorrelating experience for 608 frames... [2023-03-09 10:32:08,012][119398] Decorrelating experience for 320 frames... [2023-03-09 10:32:08,039][119501] Decorrelating experience for 160 frames... [2023-03-09 10:32:08,044][119472] Decorrelating experience for 544 frames... [2023-03-09 10:32:08,062][126685] Decorrelating experience for 480 frames... [2023-03-09 10:32:08,064][119473] Decorrelating experience for 256 frames... [2023-03-09 10:32:08,128][119532] Decorrelating experience for 544 frames... [2023-03-09 10:32:08,131][119474] Decorrelating experience for 544 frames... [2023-03-09 10:32:08,132][119534] Decorrelating experience for 320 frames... [2023-03-09 10:32:08,167][121015] Decorrelating experience for 288 frames... [2023-03-09 10:32:08,221][119516] Decorrelating experience for 576 frames... [2023-03-09 10:32:08,234][119900] Decorrelating experience for 544 frames... [2023-03-09 10:32:08,250][119388] Decorrelating experience for 256 frames... [2023-03-09 10:32:08,251][119538] Decorrelating experience for 224 frames... [2023-03-09 10:32:08,260][119493] Decorrelating experience for 384 frames... [2023-03-09 10:32:08,291][119498] Decorrelating experience for 320 frames... [2023-03-09 10:32:08,330][120199] Decorrelating experience for 320 frames... [2023-03-09 10:32:08,331][119506] Decorrelating experience for 384 frames... [2023-03-09 10:32:08,331][119499] Decorrelating experience for 448 frames... [2023-03-09 10:32:08,375][119394] Decorrelating experience for 480 frames... [2023-03-09 10:32:08,413][119469] Another process currently holds the lock /tmp/sf2_rolo/doom_006.lockfile, attempt: 1 [2023-03-09 10:32:08,416][120550] Decorrelating experience for 416 frames... [2023-03-09 10:32:08,430][119488] Decorrelating experience for 416 frames... [2023-03-09 10:32:08,441][120629] Decorrelating experience for 640 frames... [2023-03-09 10:32:08,445][119543] Decorrelating experience for 480 frames... [2023-03-09 10:32:08,474][119503] Decorrelating experience for 896 frames... [2023-03-09 10:32:08,484][120134] Decorrelating experience for 768 frames... [2023-03-09 10:32:08,514][119545] Decorrelating experience for 320 frames... [2023-03-09 10:32:08,523][119512] Decorrelating experience for 576 frames... [2023-03-09 10:32:08,525][119536] Decorrelating experience for 512 frames... [2023-03-09 10:32:08,574][126685] Decorrelating experience for 512 frames... [2023-03-09 10:32:08,634][119522] Decorrelating experience for 256 frames... [2023-03-09 10:32:08,635][119474] Decorrelating experience for 576 frames... [2023-03-09 10:32:08,638][125883] Decorrelating experience for 288 frames... [2023-03-09 10:32:08,670][119548] Decorrelating experience for 640 frames... [2023-03-09 10:32:08,675][119808] Decorrelating experience for 672 frames... [2023-03-09 10:32:08,680][119511] Decorrelating experience for 288 frames... [2023-03-09 10:32:08,700][119516] Decorrelating experience for 608 frames... [2023-03-09 10:32:08,710][119506] Decorrelating experience for 416 frames... [2023-03-09 10:32:08,771][119470] Decorrelating experience for 640 frames... [2023-03-09 10:32:08,792][119517] Decorrelating experience for 256 frames... [2023-03-09 10:32:08,832][119398] Decorrelating experience for 352 frames... [2023-03-09 10:32:08,857][119535] Decorrelating experience for 608 frames... [2023-03-09 10:32:08,896][119392] Decorrelating experience for 192 frames... [2023-03-09 10:32:08,896][120002] Decorrelating experience for 480 frames... [2023-03-09 10:32:08,897][119494] Decorrelating experience for 160 frames... [2023-03-09 10:32:08,902][120040] Decorrelating experience for 320 frames... [2023-03-09 10:32:08,902][118949] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 2000027648. Throughput: 0: 0.0. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) [2023-03-09 10:32:08,918][119532] Decorrelating experience for 576 frames... [2023-03-09 10:32:08,922][119502] Decorrelating experience for 160 frames... [2023-03-09 10:32:08,956][119480] Decorrelating experience for 352 frames... [2023-03-09 10:32:09,009][120134] Decorrelating experience for 800 frames... [2023-03-09 10:32:09,022][119477] Decorrelating experience for 448 frames... [2023-03-09 10:32:09,047][119541] Decorrelating experience for 160 frames... [2023-03-09 10:32:09,085][119523] Decorrelating experience for 544 frames... [2023-03-09 10:32:09,090][120877] Decorrelating experience for 416 frames... [2023-03-09 10:32:09,105][119506] Decorrelating experience for 448 frames... [2023-03-09 10:32:09,114][126685] Decorrelating experience for 544 frames... [2023-03-09 10:32:09,115][119513] Decorrelating experience for 448 frames... [2023-03-09 10:32:09,131][119473] Decorrelating experience for 288 frames... [2023-03-09 10:32:09,139][119533] Decorrelating experience for 640 frames... [2023-03-09 10:32:09,239][119527] Decorrelating experience for 704 frames... [2023-03-09 10:32:09,274][119539] Decorrelating experience for 192 frames... [2023-03-09 10:32:09,291][119388] Decorrelating experience for 288 frames... [2023-03-09 10:32:09,305][119398] Decorrelating experience for 384 frames... [2023-03-09 10:32:09,313][121015] Decorrelating experience for 320 frames... [2023-03-09 10:32:09,322][120629] Decorrelating experience for 672 frames... [2023-03-09 10:32:09,332][119511] Decorrelating experience for 320 frames... [2023-03-09 10:32:09,352][120135] Decorrelating experience for 544 frames... [2023-03-09 10:32:09,388][119393] Decorrelating experience for 416 frames... [2023-03-09 10:32:09,426][119480] Decorrelating experience for 384 frames... [2023-03-09 10:32:09,455][119540] Decorrelating experience for 416 frames... [2023-03-09 10:32:09,487][119615] Decorrelating experience for 480 frames... [2023-03-09 10:32:09,494][120199] Decorrelating experience for 352 frames... [2023-03-09 10:32:09,497][119503] Decorrelating experience for 928 frames... [2023-03-09 10:32:09,510][119493] Decorrelating experience for 416 frames... [2023-03-09 10:32:09,515][119524] Another process currently holds the lock /tmp/sf2_rolo/doom_006.lockfile, attempt: 1 [2023-03-09 10:32:09,530][119538] Decorrelating experience for 256 frames... [2023-03-09 10:32:09,540][119549] Decorrelating experience for 416 frames... [2023-03-09 10:32:09,579][119388] Decorrelating experience for 320 frames... [2023-03-09 10:32:09,608][119396] Decorrelating experience for 288 frames... [2023-03-09 10:32:09,639][120134] Decorrelating experience for 832 frames... [2023-03-09 10:32:09,671][119535] Decorrelating experience for 640 frames... [2023-03-09 10:32:09,690][125883] Decorrelating experience for 320 frames... [2023-03-09 10:32:09,691][119527] Decorrelating experience for 736 frames... [2023-03-09 10:32:09,726][119477] Decorrelating experience for 480 frames... [2023-03-09 10:32:09,763][120629] Decorrelating experience for 704 frames... [2023-03-09 10:32:09,771][120002] Decorrelating experience for 512 frames... [2023-03-09 10:32:09,772][119533] Decorrelating experience for 672 frames... [2023-03-09 10:32:09,775][119516] Decorrelating experience for 640 frames... [2023-03-09 10:32:09,827][119393] Decorrelating experience for 448 frames... [2023-03-09 10:32:09,844][119521] Decorrelating experience for 384 frames... [2023-03-09 10:32:09,862][119480] Decorrelating experience for 416 frames... [2023-03-09 10:32:09,872][119545] Decorrelating experience for 352 frames... [2023-03-09 10:32:09,919][119543] Decorrelating experience for 512 frames... [2023-03-09 10:32:09,945][119498] Decorrelating experience for 352 frames... [2023-03-09 10:32:09,973][119538] Decorrelating experience for 288 frames... [2023-03-09 10:32:09,974][120199] Decorrelating experience for 384 frames... [2023-03-09 10:32:10,018][119491] Decorrelating experience for 544 frames... [2023-03-09 10:32:10,038][119481] Decorrelating experience for 544 frames... [2023-03-09 10:32:10,049][119394] Decorrelating experience for 512 frames... [2023-03-09 10:32:10,055][119396] Decorrelating experience for 320 frames... [2023-03-09 10:32:10,074][119522] Decorrelating experience for 288 frames... [2023-03-09 10:32:10,090][119523] Decorrelating experience for 576 frames... [2023-03-09 10:32:10,122][119532] Decorrelating experience for 608 frames... [2023-03-09 10:32:10,136][120877] Decorrelating experience for 448 frames... [2023-03-09 10:32:10,175][119397] Decorrelating experience for 608 frames... [2023-03-09 10:32:10,196][119535] Decorrelating experience for 672 frames... [2023-03-09 10:32:10,203][119531] Decorrelating experience for 320 frames... [2023-03-09 10:32:10,246][119472] Decorrelating experience for 576 frames... [2023-03-09 10:32:10,247][119478] Decorrelating experience for 416 frames... [2023-03-09 10:32:10,273][119498] Decorrelating experience for 384 frames... [2023-03-09 10:32:10,274][119475] Decorrelating experience for 448 frames... [2023-03-09 10:32:10,304][119533] Decorrelating experience for 704 frames... [2023-03-09 10:32:10,372][120629] Decorrelating experience for 736 frames... [2023-03-09 10:32:10,373][121015] Decorrelating experience for 352 frames... [2023-03-09 10:32:10,387][119545] Decorrelating experience for 384 frames... [2023-03-09 10:32:10,391][119808] Decorrelating experience for 704 frames... [2023-03-09 10:32:10,404][119516] Decorrelating experience for 672 frames... [2023-03-09 10:32:10,440][119477] Decorrelating experience for 512 frames... [2023-03-09 10:32:10,445][119526] Decorrelating experience for 512 frames... [2023-03-09 10:32:10,457][119396] Decorrelating experience for 352 frames... [2023-03-09 10:32:10,502][119394] Decorrelating experience for 544 frames... [2023-03-09 10:32:10,570][119538] Decorrelating experience for 320 frames... [2023-03-09 10:32:10,574][119494] Decorrelating experience for 192 frames... [2023-03-09 10:32:10,578][119532] Decorrelating experience for 640 frames... [2023-03-09 10:32:10,632][119508] Decorrelating experience for 480 frames... [2023-03-09 10:32:10,640][119535] Decorrelating experience for 704 frames... [2023-03-09 10:32:10,644][119511] Decorrelating experience for 352 frames... [2023-03-09 10:32:10,648][119528] Decorrelating experience for 512 frames... [2023-03-09 10:32:10,656][119522] Decorrelating experience for 320 frames... [2023-03-09 10:32:10,690][121015] Decorrelating experience for 384 frames... [2023-03-09 10:32:10,759][119462] Decorrelating experience for 384 frames... [2023-03-09 10:32:10,762][119388] Decorrelating experience for 352 frames... [2023-03-09 10:32:10,776][119513] Decorrelating experience for 480 frames... [2023-03-09 10:32:10,819][119480] Decorrelating experience for 448 frames... [2023-03-09 10:32:10,824][119519] Decorrelating experience for 480 frames... [2023-03-09 10:32:10,834][120653] Decorrelating experience for 96 frames... [2023-03-09 10:32:10,858][120896] Decorrelating experience for 608 frames... [2023-03-09 10:32:10,866][119526] Decorrelating experience for 544 frames... [2023-03-09 10:32:10,877][120629] Decorrelating experience for 768 frames... [2023-03-09 10:32:10,948][120263] Decorrelating experience for 448 frames... [2023-03-09 10:32:10,957][125883] Decorrelating experience for 352 frames... [2023-03-09 10:32:10,990][119497] Another process currently holds the lock /tmp/sf2_rolo/doom_001.lockfile, attempt: 1 [2023-03-09 10:32:11,002][119532] Decorrelating experience for 672 frames... [2023-03-09 10:32:11,018][120615] Decorrelating experience for 512 frames... [2023-03-09 10:32:11,020][119544] Decorrelating experience for 256 frames... [2023-03-09 10:32:11,025][119473] Decorrelating experience for 320 frames... [2023-03-09 10:32:11,033][119527] Decorrelating experience for 768 frames... [2023-03-09 10:32:11,042][120904] Decorrelating experience for 320 frames... [2023-03-09 10:32:11,071][121015] Decorrelating experience for 416 frames... [2023-03-09 10:32:11,090][119522] Decorrelating experience for 352 frames... [2023-03-09 10:32:11,133][119503] Decorrelating experience for 960 frames... [2023-03-09 10:32:11,143][119393] Decorrelating experience for 480 frames... [2023-03-09 10:32:11,208][119543] Decorrelating experience for 544 frames... [2023-03-09 10:32:11,212][119529] Decorrelating experience for 192 frames... [2023-03-09 10:32:11,215][119511] Decorrelating experience for 384 frames... [2023-03-09 10:32:11,224][119480] Decorrelating experience for 480 frames... [2023-03-09 10:32:11,278][119528] Decorrelating experience for 544 frames... [2023-03-09 10:32:11,289][119388] Decorrelating experience for 384 frames... [2023-03-09 10:32:11,293][119521] Decorrelating experience for 416 frames... [2023-03-09 10:32:11,321][119536] Decorrelating experience for 544 frames... [2023-03-09 10:32:11,340][119396] Decorrelating experience for 384 frames... [2023-03-09 10:32:11,341][119517] Decorrelating experience for 288 frames... [2023-03-09 10:32:11,403][119499] Decorrelating experience for 480 frames... [2023-03-09 10:32:11,412][119516] Decorrelating experience for 704 frames... [2023-03-09 10:32:11,417][119615] Decorrelating experience for 512 frames... [2023-03-09 10:32:11,418][120002] Decorrelating experience for 544 frames... [2023-03-09 10:32:11,503][119519] Decorrelating experience for 512 frames... [2023-03-09 10:32:11,504][119512] Decorrelating experience for 608 frames... [2023-03-09 10:32:11,504][120615] Decorrelating experience for 544 frames... [2023-03-09 10:32:11,526][125883] Decorrelating experience for 384 frames... [2023-03-09 10:32:11,542][119470] Decorrelating experience for 672 frames... [2023-03-09 10:32:11,548][119513] Decorrelating experience for 512 frames... [2023-03-09 10:32:11,622][119474] Decorrelating experience for 608 frames... [2023-03-09 10:32:11,623][119530] Decorrelating experience for 256 frames... [2023-03-09 10:32:11,625][119541] Decorrelating experience for 192 frames... [2023-03-09 10:32:11,626][119655] Decorrelating experience for 352 frames... [2023-03-09 10:32:11,691][119535] Decorrelating experience for 736 frames... [2023-03-09 10:32:11,715][119536] Decorrelating experience for 576 frames... [2023-03-09 10:32:11,726][119680] Decorrelating experience for 576 frames... [2023-03-09 10:32:11,735][119518] Another process currently holds the lock /tmp/sf2_rolo/doom_006.lockfile, attempt: 1 [2023-03-09 10:32:11,760][119522] Decorrelating experience for 384 frames... [2023-03-09 10:32:11,769][119462] Decorrelating experience for 416 frames... [2023-03-09 10:32:11,769][119504] Decorrelating experience for 448 frames... [2023-03-09 10:32:11,813][119393] Decorrelating experience for 512 frames... [2023-03-09 10:32:11,814][120653] Decorrelating experience for 128 frames... [2023-03-09 10:32:11,834][119498] Decorrelating experience for 416 frames... [2023-03-09 10:32:11,834][119483] Decorrelating experience for 448 frames... [2023-03-09 10:32:11,881][119541] Decorrelating experience for 224 frames... [2023-03-09 10:32:11,912][120199] Decorrelating experience for 416 frames... [2023-03-09 10:32:11,919][119512] Decorrelating experience for 640 frames... [2023-03-09 10:32:11,946][119615] Decorrelating experience for 544 frames... [2023-03-09 10:32:11,959][119521] Decorrelating experience for 448 frames... [2023-03-09 10:32:12,015][119530] Decorrelating experience for 288 frames... [2023-03-09 10:32:12,016][119472] Decorrelating experience for 608 frames... [2023-03-09 10:32:12,027][119513] Decorrelating experience for 544 frames... [2023-03-09 10:32:12,041][119394] Decorrelating experience for 576 frames... [2023-03-09 10:32:12,041][120002] Decorrelating experience for 576 frames... [2023-03-09 10:32:12,067][119499] Decorrelating experience for 512 frames... [2023-03-09 10:32:12,102][119397] Decorrelating experience for 640 frames... [2023-03-09 10:32:12,130][119543] Decorrelating experience for 576 frames... [2023-03-09 10:32:12,154][119485] Decorrelating experience for 544 frames... [2023-03-09 10:32:12,155][119541] Decorrelating experience for 256 frames... [2023-03-09 10:32:12,212][119535] Decorrelating experience for 768 frames... [2023-03-09 10:32:12,217][119501] Decorrelating experience for 192 frames... [2023-03-09 10:32:12,217][119493] Decorrelating experience for 448 frames... [2023-03-09 10:32:12,242][119393] Decorrelating experience for 544 frames... [2023-03-09 10:32:12,250][119478] Decorrelating experience for 448 frames... [2023-03-09 10:32:12,289][120073] Decorrelating experience for 384 frames... [2023-03-09 10:32:12,317][119398] Decorrelating experience for 416 frames... [2023-03-09 10:32:12,325][119544] Decorrelating experience for 288 frames... [2023-03-09 10:32:12,343][119483] Decorrelating experience for 480 frames... [2023-03-09 10:32:12,403][120199] Decorrelating experience for 448 frames... [2023-03-09 10:32:12,420][119462] Decorrelating experience for 448 frames... [2023-03-09 10:32:12,456][119499] Decorrelating experience for 544 frames... [2023-03-09 10:32:12,459][119539] Decorrelating experience for 224 frames... [2023-03-09 10:32:12,460][120040] Decorrelating experience for 352 frames... [2023-03-09 10:32:12,465][120629] Decorrelating experience for 800 frames... [2023-03-09 10:32:12,475][119476] Decorrelating experience for 224 frames... [2023-03-09 10:32:12,499][119495] Another process currently holds the lock /tmp/sf2_rolo/doom_006.lockfile, attempt: 1 [2023-03-09 10:32:12,514][120263] Decorrelating experience for 480 frames... [2023-03-09 10:32:12,564][119503] Decorrelating experience for 992 frames... [2023-03-09 10:32:12,589][119502] Decorrelating experience for 192 frames... [2023-03-09 10:32:12,590][119475] Decorrelating experience for 480 frames... [2023-03-09 10:32:12,607][119488] Decorrelating experience for 448 frames... [2023-03-09 10:32:12,643][119546] Decorrelating experience for 640 frames... [2023-03-09 10:32:12,646][119489] Another process currently holds the lock /tmp/sf2_rolo/doom_006.lockfile, attempt: 1 [2023-03-09 10:32:12,652][119900] Decorrelating experience for 576 frames... [2023-03-09 10:32:12,668][119544] Decorrelating experience for 320 frames... [2023-03-09 10:32:12,674][119520] Decorrelating experience for 96 frames... [2023-03-09 10:32:12,682][119397] Decorrelating experience for 672 frames... [2023-03-09 10:32:12,729][119680] Decorrelating experience for 608 frames... [2023-03-09 10:32:12,751][119808] Decorrelating experience for 736 frames... [2023-03-09 10:32:12,777][119513] Decorrelating experience for 576 frames... [2023-03-09 10:32:12,795][119396] Decorrelating experience for 416 frames... [2023-03-09 10:32:12,803][120005] Decorrelating experience for 352 frames... [2023-03-09 10:32:12,833][119501] Decorrelating experience for 224 frames... [2023-03-09 10:32:12,864][119549] Decorrelating experience for 448 frames... [2023-03-09 10:32:12,864][125883] Decorrelating experience for 416 frames... [2023-03-09 10:32:12,880][119462] Decorrelating experience for 480 frames... [2023-03-09 10:32:12,889][119543] Decorrelating experience for 608 frames... [2023-03-09 10:32:12,913][119466] Another process currently holds the lock /tmp/sf2_rolo/doom_006.lockfile, attempt: 1 [2023-03-09 10:32:12,919][119502] Decorrelating experience for 224 frames... [2023-03-09 10:32:12,944][118949] Heartbeat connected on RolloutWorker_w50 [2023-03-09 10:32:12,949][119474] Decorrelating experience for 640 frames... [2023-03-09 10:32:12,993][120648] Decorrelating experience for 512 frames... [2023-03-09 10:32:12,997][119615] Decorrelating experience for 576 frames... [2023-03-09 10:32:13,038][119521] Decorrelating experience for 480 frames... [2023-03-09 10:32:13,053][119655] Decorrelating experience for 384 frames... [2023-03-09 10:32:13,058][119900] Decorrelating experience for 608 frames... [2023-03-09 10:32:13,062][119478] Decorrelating experience for 480 frames... [2023-03-09 10:32:13,102][119485] Decorrelating experience for 576 frames... [2023-03-09 10:32:13,134][119544] Decorrelating experience for 352 frames... [2023-03-09 10:32:13,141][119388] Decorrelating experience for 416 frames... [2023-03-09 10:32:13,146][119680] Decorrelating experience for 640 frames... [2023-03-09 10:32:13,157][119507] Another process currently holds the lock /tmp/sf2_rolo/doom_006.lockfile, attempt: 1 [2023-03-09 10:32:13,180][126685] Decorrelating experience for 576 frames... [2023-03-09 10:32:13,194][119502] Decorrelating experience for 256 frames... [2023-03-09 10:32:13,224][120877] Decorrelating experience for 480 frames... [2023-03-09 10:32:13,242][119538] Decorrelating experience for 352 frames... [2023-03-09 10:32:13,248][119494] Decorrelating experience for 224 frames... [2023-03-09 10:32:13,259][119475] Decorrelating experience for 512 frames... [2023-03-09 10:32:13,332][119528] Decorrelating experience for 576 frames... [2023-03-09 10:32:13,345][119513] Decorrelating experience for 608 frames... [2023-03-09 10:32:13,347][119470] Decorrelating experience for 704 frames... [2023-03-09 10:32:13,360][119396] Decorrelating experience for 448 frames... [2023-03-09 10:32:13,368][120002] Decorrelating experience for 608 frames... [2023-03-09 10:32:13,411][120653] Decorrelating experience for 160 frames... [2023-03-09 10:32:13,425][119523] Decorrelating experience for 608 frames... [2023-03-09 10:32:13,429][119937] Decorrelating experience for 512 frames... [2023-03-09 10:32:13,463][119497] Decorrelating experience for 128 frames... [2023-03-09 10:32:13,468][119508] Decorrelating experience for 512 frames... [2023-03-09 10:32:13,520][119540] Decorrelating experience for 448 frames... [2023-03-09 10:32:13,547][119499] Decorrelating experience for 576 frames... [2023-03-09 10:32:13,575][120199] Decorrelating experience for 480 frames... [2023-03-09 10:32:13,578][119680] Decorrelating experience for 672 frames... [2023-03-09 10:32:13,608][119544] Decorrelating experience for 384 frames... [2023-03-09 10:32:13,630][119521] Decorrelating experience for 512 frames... [2023-03-09 10:32:13,631][119494] Decorrelating experience for 256 frames... [2023-03-09 10:32:13,634][119900] Decorrelating experience for 640 frames... [2023-03-09 10:32:13,653][119480] Decorrelating experience for 512 frames... [2023-03-09 10:32:13,659][119502] Decorrelating experience for 288 frames... [2023-03-09 10:32:13,746][119543] Decorrelating experience for 640 frames... [2023-03-09 10:32:13,752][119394] Decorrelating experience for 608 frames... [2023-03-09 10:32:13,768][119504] Decorrelating experience for 480 frames... [2023-03-09 10:32:13,778][120648] Decorrelating experience for 544 frames... [2023-03-09 10:32:13,826][119808] Decorrelating experience for 768 frames... [2023-03-09 10:32:13,833][119509] Decorrelating experience for 544 frames... [2023-03-09 10:32:13,837][119536] Decorrelating experience for 608 frames... [2023-03-09 10:32:13,860][119519] Decorrelating experience for 544 frames... [2023-03-09 10:32:13,860][119475] Decorrelating experience for 544 frames... [2023-03-09 10:32:13,860][119497] Decorrelating experience for 160 frames... [2023-03-09 10:32:13,902][118949] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 2000027648. Throughput: 0: 16.0. Samples: 640. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) [2023-03-09 10:32:13,903][118949] Avg episode reward: [(0, '0.533')] [2023-03-09 10:32:13,940][119544] Decorrelating experience for 416 frames... [2023-03-09 10:32:13,959][119466] Decorrelating experience for 256 frames... [2023-03-09 10:32:13,965][119462] Decorrelating experience for 512 frames... [2023-03-09 10:32:13,968][119513] Decorrelating experience for 640 frames... [2023-03-09 10:32:14,039][119537] Decorrelating experience for 352 frames... [2023-03-09 10:32:14,049][119488] Decorrelating experience for 480 frames... [2023-03-09 10:32:14,065][119494] Decorrelating experience for 288 frames... [2023-03-09 10:32:14,067][119937] Decorrelating experience for 544 frames... [2023-03-09 10:32:14,073][119398] Decorrelating experience for 448 frames... [2023-03-09 10:32:14,099][120615] Decorrelating experience for 576 frames... [2023-03-09 10:32:14,114][119550] Another process currently holds the lock /tmp/sf2_rolo/doom_006.lockfile, attempt: 1 [2023-03-09 10:32:14,129][120629] Decorrelating experience for 832 frames... [2023-03-09 10:32:14,161][119506] Decorrelating experience for 480 frames... [2023-03-09 10:32:14,163][119497] Decorrelating experience for 192 frames... [2023-03-09 10:32:14,170][119394] Decorrelating experience for 640 frames... [2023-03-09 10:32:14,241][120040] Decorrelating experience for 384 frames... [2023-03-09 10:32:14,271][119538] Decorrelating experience for 384 frames... [2023-03-09 10:32:14,273][119517] Decorrelating experience for 320 frames... [2023-03-09 10:32:14,281][119549] Decorrelating experience for 480 frames... [2023-03-09 10:32:14,307][119397] Decorrelating experience for 704 frames... [2023-03-09 10:32:14,310][119475] Decorrelating experience for 576 frames... [2023-03-09 10:32:14,320][120134] Decorrelating experience for 864 frames... [2023-03-09 10:32:14,355][120550] Decorrelating experience for 448 frames... [2023-03-09 10:32:14,356][120199] Decorrelating experience for 512 frames... [2023-03-09 10:32:14,363][119519] Decorrelating experience for 576 frames... [2023-03-09 10:32:14,442][119498] Decorrelating experience for 448 frames... [2023-03-09 10:32:14,476][119680] Decorrelating experience for 704 frames... [2023-03-09 10:32:14,482][119543] Decorrelating experience for 672 frames... [2023-03-09 10:32:14,490][119530] Decorrelating experience for 320 frames... [2023-03-09 10:32:14,496][119851] Decorrelating experience for 288 frames... [2023-03-09 10:32:14,515][119537] Decorrelating experience for 384 frames... [2023-03-09 10:32:14,539][119502] Decorrelating experience for 320 frames... [2023-03-09 10:32:14,542][120005] Decorrelating experience for 384 frames... [2023-03-09 10:32:14,551][119523] Decorrelating experience for 640 frames... [2023-03-09 10:32:14,571][119396] Decorrelating experience for 480 frames... [2023-03-09 10:32:14,641][120629] Decorrelating experience for 864 frames... [2023-03-09 10:32:14,690][119526] Decorrelating experience for 576 frames... [2023-03-09 10:32:14,693][119539] Decorrelating experience for 256 frames... [2023-03-09 10:32:14,703][120615] Decorrelating experience for 608 frames... [2023-03-09 10:32:14,706][120135] Decorrelating experience for 576 frames... [2023-03-09 10:32:14,732][119399] Decorrelating experience for 320 frames... [2023-03-09 10:32:14,743][126685] Decorrelating experience for 608 frames... [2023-03-09 10:32:14,806][119516] Decorrelating experience for 736 frames... [2023-03-09 10:32:14,810][119493] Decorrelating experience for 480 frames... [2023-03-09 10:32:14,849][119506] Decorrelating experience for 512 frames... [2023-03-09 10:32:14,856][119522] Decorrelating experience for 416 frames... [2023-03-09 10:32:14,899][119614] Decorrelating experience for 224 frames... [2023-03-09 10:32:14,900][120134] Decorrelating experience for 896 frames... [2023-03-09 10:32:14,903][119851] Decorrelating experience for 320 frames... [2023-03-09 10:32:14,911][119462] Decorrelating experience for 544 frames... [2023-03-09 10:32:14,920][119488] Decorrelating experience for 512 frames... [2023-03-09 10:32:14,934][119680] Decorrelating experience for 736 frames... [2023-03-09 10:32:14,992][119544] Decorrelating experience for 448 frames... [2023-03-09 10:32:15,062][119541] Decorrelating experience for 288 frames... [2023-03-09 10:32:15,069][119519] Decorrelating experience for 608 frames... [2023-03-09 10:32:15,082][119509] Decorrelating experience for 576 frames... [2023-03-09 10:32:15,096][120778] Decorrelating experience for 448 frames... [2023-03-09 10:32:15,107][119550] Decorrelating experience for 224 frames... [2023-03-09 10:32:15,119][120615] Decorrelating experience for 640 frames... [2023-03-09 10:32:15,146][119532] Decorrelating experience for 704 frames... [2023-03-09 10:32:15,159][119391] Decorrelating experience for 384 frames... [2023-03-09 10:32:15,198][119478] Decorrelating experience for 512 frames... [2023-03-09 10:32:15,248][119540] Decorrelating experience for 480 frames... [2023-03-09 10:32:15,281][120005] Decorrelating experience for 416 frames... [2023-03-09 10:32:15,290][119900] Decorrelating experience for 672 frames... [2023-03-09 10:32:15,295][119483] Decorrelating experience for 512 frames... [2023-03-09 10:32:15,323][119535] Decorrelating experience for 800 frames... [2023-03-09 10:32:15,352][119528] Decorrelating experience for 608 frames... [2023-03-09 10:32:15,352][119493] Decorrelating experience for 512 frames... [2023-03-09 10:32:15,354][119510] Decorrelating experience for 512 frames... [2023-03-09 10:32:15,362][119807] Decorrelating experience for 480 frames... [2023-03-09 10:32:15,401][120002] Decorrelating experience for 640 frames... [2023-03-09 10:32:15,438][119397] Decorrelating experience for 736 frames... [2023-03-09 10:32:15,482][119506] Decorrelating experience for 544 frames... [2023-03-09 10:32:15,494][119480] Decorrelating experience for 544 frames... [2023-03-09 10:32:15,509][120778] Decorrelating experience for 480 frames... [2023-03-09 10:32:15,519][119476] Decorrelating experience for 256 frames... [2023-03-09 10:32:15,548][119399] Decorrelating experience for 352 frames... [2023-03-09 10:32:15,552][119395] Decorrelating experience for 288 frames... [2023-03-09 10:32:15,569][119534] Decorrelating experience for 352 frames... [2023-03-09 10:32:15,602][120615] Decorrelating experience for 672 frames... [2023-03-09 10:32:15,648][120648] Decorrelating experience for 576 frames... [2023-03-09 10:32:15,676][119504] Decorrelating experience for 512 frames... [2023-03-09 10:32:15,714][120040] Decorrelating experience for 416 frames... [2023-03-09 10:32:15,720][119519] Decorrelating experience for 640 frames... [2023-03-09 10:32:15,728][119512] Decorrelating experience for 672 frames... [2023-03-09 10:32:15,736][119540] Decorrelating experience for 512 frames... [2023-03-09 10:32:15,757][119495] Decorrelating experience for 320 frames... [2023-03-09 10:32:15,765][119474] Decorrelating experience for 672 frames... [2023-03-09 10:32:15,807][119655] Decorrelating experience for 416 frames... [2023-03-09 10:32:15,831][119391] Decorrelating experience for 416 frames... [2023-03-09 10:32:15,842][119527] Decorrelating experience for 800 frames... [2023-03-09 10:32:15,862][119508] Decorrelating experience for 544 frames... [2023-03-09 10:32:15,911][119513] Decorrelating experience for 672 frames... [2023-03-09 10:32:15,923][119494] Decorrelating experience for 320 frames... [2023-03-09 10:32:15,927][120653] Decorrelating experience for 192 frames... [2023-03-09 10:32:15,945][119389] Decorrelating experience for 416 frames... [2023-03-09 10:32:15,952][119522] Decorrelating experience for 448 frames... [2023-03-09 10:32:16,031][119807] Decorrelating experience for 512 frames... [2023-03-09 10:32:16,038][121015] Decorrelating experience for 448 frames... [2023-03-09 10:32:16,061][119462] Decorrelating experience for 576 frames... [2023-03-09 10:32:16,065][119501] Decorrelating experience for 256 frames... [2023-03-09 10:32:16,100][120648] Decorrelating experience for 608 frames... [2023-03-09 10:32:16,116][119491] Decorrelating experience for 576 frames... [2023-03-09 10:32:16,179][120073] Decorrelating experience for 416 frames... [2023-03-09 10:32:16,209][119534] Decorrelating experience for 384 frames... [2023-03-09 10:32:16,221][119487] Decorrelating experience for 384 frames... [2023-03-09 10:32:16,225][119614] Decorrelating experience for 256 frames... [2023-03-09 10:32:16,258][119391] Decorrelating experience for 448 frames... [2023-03-09 10:32:16,258][120615] Decorrelating experience for 704 frames... [2023-03-09 10:32:16,273][119537] Decorrelating experience for 416 frames... [2023-03-09 10:32:16,289][119510] Decorrelating experience for 544 frames... [2023-03-09 10:32:16,299][119474] Decorrelating experience for 704 frames... [2023-03-09 10:32:16,303][119395] Decorrelating experience for 320 frames... [2023-03-09 10:32:16,380][119527] Decorrelating experience for 832 frames... [2023-03-09 10:32:16,418][119388] Decorrelating experience for 448 frames... [2023-03-09 10:32:16,475][120040] Decorrelating experience for 448 frames... [2023-03-09 10:32:16,479][119495] Decorrelating experience for 352 frames... [2023-03-09 10:32:16,484][119519] Decorrelating experience for 672 frames... [2023-03-09 10:32:16,484][119469] Decorrelating experience for 128 frames... [2023-03-09 10:32:16,504][120653] Decorrelating experience for 224 frames... [2023-03-09 10:32:16,504][119389] Decorrelating experience for 448 frames... [2023-03-09 10:32:16,504][119535] Decorrelating experience for 832 frames... [2023-03-09 10:32:16,514][120648] Decorrelating experience for 640 frames... [2023-03-09 10:32:16,585][120134] Decorrelating experience for 928 frames... [2023-03-09 10:32:16,602][119544] Decorrelating experience for 480 frames... [2023-03-09 10:32:16,667][119851] Decorrelating experience for 352 frames... [2023-03-09 10:32:16,672][119538] Decorrelating experience for 416 frames... [2023-03-09 10:32:16,684][119506] Decorrelating experience for 576 frames... [2023-03-09 10:32:16,685][119549] Decorrelating experience for 512 frames... [2023-03-09 10:32:16,701][119480] Decorrelating experience for 576 frames... [2023-03-09 10:32:16,703][119501] Decorrelating experience for 288 frames... [2023-03-09 10:32:16,720][119395] Decorrelating experience for 352 frames... [2023-03-09 10:32:16,753][119534] Decorrelating experience for 416 frames... [2023-03-09 10:32:16,796][119550] Decorrelating experience for 256 frames... [2023-03-09 10:32:16,860][119483] Decorrelating experience for 544 frames... [2023-03-09 10:32:16,864][119389] Decorrelating experience for 480 frames... [2023-03-09 10:32:16,880][119528] Decorrelating experience for 640 frames... [2023-03-09 10:32:16,890][119543] Decorrelating experience for 704 frames... [2023-03-09 10:32:16,927][119491] Decorrelating experience for 608 frames... [2023-03-09 10:32:16,937][119496] Decorrelating experience for 288 frames... [2023-03-09 10:32:16,949][119474] Decorrelating experience for 736 frames... [2023-03-09 10:32:16,952][119476] Decorrelating experience for 288 frames... [2023-03-09 10:32:16,990][119900] Decorrelating experience for 704 frames... [2023-03-09 10:32:16,996][119495] Decorrelating experience for 384 frames... [2023-03-09 10:32:17,046][119540] Decorrelating experience for 544 frames... [2023-03-09 10:32:17,084][120653] Decorrelating experience for 256 frames... [2023-03-09 10:32:17,088][119466] Decorrelating experience for 288 frames... [2023-03-09 10:32:17,094][120550] Decorrelating experience for 480 frames... [2023-03-09 10:32:17,122][119544] Decorrelating experience for 512 frames... [2023-03-09 10:32:17,133][119490] Decorrelating experience for 704 frames... [2023-03-09 10:32:17,143][119494] Decorrelating experience for 352 frames... [2023-03-09 10:32:17,146][119395] Decorrelating experience for 384 frames... [2023-03-09 10:32:17,196][119506] Decorrelating experience for 608 frames... [2023-03-09 10:32:17,208][120134] Decorrelating experience for 960 frames... [2023-03-09 10:32:17,240][119512] Decorrelating experience for 704 frames... [2023-03-09 10:32:17,286][119537] Decorrelating experience for 448 frames... [2023-03-09 10:32:17,289][120896] Decorrelating experience for 640 frames... [2023-03-09 10:32:17,292][119549] Decorrelating experience for 544 frames... [2023-03-09 10:32:17,344][119388] Decorrelating experience for 480 frames... [2023-03-09 10:32:17,353][119543] Decorrelating experience for 736 frames... [2023-03-09 10:32:17,396][119507] Decorrelating experience for 352 frames... [2023-03-09 10:32:17,412][119476] Decorrelating experience for 320 frames... [2023-03-09 10:32:17,412][119485] Decorrelating experience for 608 frames... [2023-03-09 10:32:17,415][120073] Decorrelating experience for 448 frames... [2023-03-09 10:32:17,426][119391] Decorrelating experience for 480 frames... [2023-03-09 10:32:17,478][120653] Decorrelating experience for 288 frames... [2023-03-09 10:32:17,489][119472] Decorrelating experience for 640 frames... [2023-03-09 10:32:17,563][119491] Decorrelating experience for 640 frames... [2023-03-09 10:32:17,570][119527] Decorrelating experience for 864 frames... [2023-03-09 10:32:17,592][119498] Decorrelating experience for 480 frames... [2023-03-09 10:32:17,608][120002] Decorrelating experience for 672 frames... [2023-03-09 10:32:17,628][119534] Decorrelating experience for 448 frames... [2023-03-09 10:32:17,628][120648] Decorrelating experience for 672 frames... [2023-03-09 10:32:17,628][119680] Decorrelating experience for 768 frames... [2023-03-09 10:32:17,684][120550] Decorrelating experience for 512 frames... [2023-03-09 10:32:17,697][119807] Decorrelating experience for 544 frames... [2023-03-09 10:32:17,784][119494] Decorrelating experience for 384 frames... [2023-03-09 10:32:17,786][119476] Decorrelating experience for 352 frames... [2023-03-09 10:32:17,788][119520] Decorrelating experience for 128 frames... [2023-03-09 10:32:17,796][119537] Decorrelating experience for 480 frames... [2023-03-09 10:32:17,832][119508] Decorrelating experience for 576 frames... [2023-03-09 10:32:17,833][120615] Decorrelating experience for 736 frames... [2023-03-09 10:32:17,836][120904] Decorrelating experience for 352 frames... [2023-03-09 10:32:17,841][119538] Decorrelating experience for 448 frames... [2023-03-09 10:32:17,871][120263] Decorrelating experience for 512 frames... [2023-03-09 10:32:17,891][119389] Decorrelating experience for 512 frames... [2023-03-09 10:32:17,977][120877] Decorrelating experience for 512 frames... [2023-03-09 10:32:18,015][119491] Decorrelating experience for 672 frames... [2023-03-09 10:32:18,015][120778] Decorrelating experience for 512 frames... [2023-03-09 10:32:18,020][119493] Decorrelating experience for 544 frames... [2023-03-09 10:32:18,030][119498] Decorrelating experience for 512 frames... [2023-03-09 10:32:18,040][119520] Decorrelating experience for 160 frames... [2023-03-09 10:32:18,046][119513] Decorrelating experience for 704 frames... [2023-03-09 10:32:18,046][119462] Decorrelating experience for 608 frames... [2023-03-09 10:32:18,068][120717] Another process currently holds the lock /tmp/sf2_rolo/doom_006.lockfile, attempt: 1 [2023-03-09 10:32:18,070][119937] Decorrelating experience for 576 frames... [2023-03-09 10:32:18,093][119530] Decorrelating experience for 352 frames... [2023-03-09 10:32:18,163][119525] Decorrelating experience for 576 frames... [2023-03-09 10:32:18,207][119499] Decorrelating experience for 608 frames... [2023-03-09 10:32:18,212][119501] Decorrelating experience for 320 frames... [2023-03-09 10:32:18,220][119537] Decorrelating experience for 512 frames... [2023-03-09 10:32:18,242][119519] Decorrelating experience for 704 frames... [2023-03-09 10:32:18,251][119807] Decorrelating experience for 576 frames... [2023-03-09 10:32:18,257][119532] Decorrelating experience for 736 frames... [2023-03-09 10:32:18,303][119490] Decorrelating experience for 736 frames... [2023-03-09 10:32:18,306][119397] Decorrelating experience for 768 frames... [2023-03-09 10:32:18,315][119531] Decorrelating experience for 352 frames... [2023-03-09 10:32:18,399][119512] Decorrelating experience for 736 frames... [2023-03-09 10:32:18,422][119851] Decorrelating experience for 384 frames... [2023-03-09 10:32:18,423][119388] Decorrelating experience for 512 frames... [2023-03-09 10:32:18,436][119474] Decorrelating experience for 768 frames... [2023-03-09 10:32:18,468][119462] Decorrelating experience for 640 frames... [2023-03-09 10:32:18,493][119549] Decorrelating experience for 576 frames... [2023-03-09 10:32:18,499][120134] Decorrelating experience for 992 frames... [2023-03-09 10:32:18,500][120073] Decorrelating experience for 480 frames... [2023-03-09 10:32:18,548][120778] Decorrelating experience for 544 frames... [2023-03-09 10:32:18,572][119496] Decorrelating experience for 320 frames... [2023-03-09 10:32:18,614][119505] Decorrelating experience for 192 frames... [2023-03-09 10:32:18,630][119389] Decorrelating experience for 544 frames... [2023-03-09 10:32:18,647][119391] Decorrelating experience for 512 frames... [2023-03-09 10:32:18,695][119536] Decorrelating experience for 640 frames... [2023-03-09 10:32:18,701][119522] Decorrelating experience for 480 frames... [2023-03-09 10:32:18,704][119541] Decorrelating experience for 320 frames... [2023-03-09 10:32:18,715][119537] Decorrelating experience for 544 frames... [2023-03-09 10:32:18,718][119543] Decorrelating experience for 768 frames... [2023-03-09 10:32:18,753][119478] Decorrelating experience for 544 frames... [2023-03-09 10:32:18,809][119513] Decorrelating experience for 736 frames... [2023-03-09 10:32:18,832][119470] Decorrelating experience for 736 frames... [2023-03-09 10:32:18,858][119807] Decorrelating experience for 608 frames... [2023-03-09 10:32:18,863][120550] Decorrelating experience for 544 frames... [2023-03-09 10:32:18,879][118949] Heartbeat connected on RolloutWorker_w120 [2023-03-09 10:32:18,883][120653] Decorrelating experience for 320 frames... [2023-03-09 10:32:18,902][118949] Fps is (10 sec: 1638.4, 60 sec: 364.1, 300 sec: 364.1). Total num frames: 2000044032. Throughput: 0: 83.9. Samples: 3776. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 10:32:18,903][118949] Avg episode reward: [(0, '3.545')] [2023-03-09 10:32:18,910][119397] Decorrelating experience for 800 frames... [2023-03-09 10:32:18,915][119510] Decorrelating experience for 576 frames... [2023-03-09 10:32:18,955][119496] Decorrelating experience for 352 frames... [2023-03-09 10:32:18,979][119519] Decorrelating experience for 736 frames... [2023-03-09 10:32:18,999][119495] Decorrelating experience for 416 frames... [2023-03-09 10:32:19,006][119480] Decorrelating experience for 608 frames... [2023-03-09 10:32:19,033][119490] Decorrelating experience for 768 frames... [2023-03-09 10:32:19,053][119538] Decorrelating experience for 480 frames... [2023-03-09 10:32:19,063][119527] Decorrelating experience for 896 frames... [2023-03-09 10:32:19,075][119680] Decorrelating experience for 800 frames... [2023-03-09 10:32:19,107][120778] Decorrelating experience for 576 frames... [2023-03-09 10:32:19,150][119462] Decorrelating experience for 672 frames... [2023-03-09 10:32:19,165][120073] Decorrelating experience for 512 frames... [2023-03-09 10:32:19,189][119485] Decorrelating experience for 640 frames... [2023-03-09 10:32:19,225][119549] Decorrelating experience for 608 frames... [2023-03-09 10:32:19,251][120653] Decorrelating experience for 352 frames... [2023-03-09 10:32:19,258][119487] Decorrelating experience for 416 frames... [2023-03-09 10:32:19,272][120629] Decorrelating experience for 896 frames... [2023-03-09 10:32:19,276][119474] Decorrelating experience for 800 frames... [2023-03-09 10:32:19,296][119391] Decorrelating experience for 544 frames... [2023-03-09 10:32:19,313][119509] Decorrelating experience for 608 frames... [2023-03-09 10:32:19,369][119466] Decorrelating experience for 320 frames... [2023-03-09 10:32:19,379][119518] Decorrelating experience for 64 frames... [2023-03-09 10:32:19,418][119531] Decorrelating experience for 384 frames... [2023-03-09 10:32:19,421][119537] Decorrelating experience for 576 frames... [2023-03-09 10:32:19,454][119478] Decorrelating experience for 576 frames... [2023-03-09 10:32:19,456][119395] Decorrelating experience for 416 frames... [2023-03-09 10:32:19,479][119491] Decorrelating experience for 704 frames... [2023-03-09 10:32:19,502][119532] Decorrelating experience for 768 frames... [2023-03-09 10:32:19,507][119475] Decorrelating experience for 608 frames... [2023-03-09 10:32:19,511][119900] Decorrelating experience for 736 frames... [2023-03-09 10:32:19,577][119493] Decorrelating experience for 576 frames... [2023-03-09 10:32:19,642][120005] Decorrelating experience for 448 frames... [2023-03-09 10:32:19,648][119548] Decorrelating experience for 672 frames... [2023-03-09 10:32:19,650][119399] Decorrelating experience for 384 frames... [2023-03-09 10:32:19,659][119527] Decorrelating experience for 928 frames... [2023-03-09 10:32:19,692][120778] Decorrelating experience for 608 frames... [2023-03-09 10:32:19,698][119518] Decorrelating experience for 96 frames... [2023-03-09 10:32:19,702][119495] Decorrelating experience for 448 frames... [2023-03-09 10:32:19,718][120073] Decorrelating experience for 544 frames... [2023-03-09 10:32:19,753][119507] Decorrelating experience for 384 frames... [2023-03-09 10:32:19,843][119388] Decorrelating experience for 544 frames... [2023-03-09 10:32:19,857][119472] Decorrelating experience for 672 frames... [2023-03-09 10:32:19,857][119481] Decorrelating experience for 576 frames... [2023-03-09 10:32:19,863][119508] Decorrelating experience for 608 frames... [2023-03-09 10:32:19,867][119851] Decorrelating experience for 416 frames... [2023-03-09 10:32:19,903][119396] Decorrelating experience for 512 frames... [2023-03-09 10:32:19,907][119549] Decorrelating experience for 640 frames... [2023-03-09 10:32:19,913][119395] Decorrelating experience for 448 frames... [2023-03-09 10:32:19,928][120904] Decorrelating experience for 384 frames... [2023-03-09 10:32:19,941][119469] Decorrelating experience for 160 frames... [2023-03-09 10:32:20,037][119399] Decorrelating experience for 416 frames... [2023-03-09 10:32:20,064][119515] Decorrelating experience for 576 frames... [2023-03-09 10:32:20,069][119464] Decorrelating experience for 384 frames... [2023-03-09 10:32:20,069][119498] Decorrelating experience for 544 frames... [2023-03-09 10:32:20,069][119495] Decorrelating experience for 480 frames... [2023-03-09 10:32:20,110][120550] Decorrelating experience for 576 frames... [2023-03-09 10:32:20,113][119462] Decorrelating experience for 704 frames... [2023-03-09 10:32:20,137][119538] Decorrelating experience for 512 frames... [2023-03-09 10:32:20,138][119680] Decorrelating experience for 832 frames... [2023-03-09 10:32:20,153][119532] Decorrelating experience for 800 frames... [2023-03-09 10:32:20,230][119541] Decorrelating experience for 352 frames... [2023-03-09 10:32:20,285][119537] Decorrelating experience for 608 frames... [2023-03-09 10:32:20,301][119496] Decorrelating experience for 384 frames... [2023-03-09 10:32:20,310][119527] Decorrelating experience for 960 frames... [2023-03-09 10:32:20,320][119478] Decorrelating experience for 608 frames... [2023-03-09 10:32:20,332][119533] Decorrelating experience for 736 frames... [2023-03-09 10:32:20,333][119808] Decorrelating experience for 800 frames... [2023-03-09 10:32:20,337][119474] Decorrelating experience for 832 frames... [2023-03-09 10:32:20,390][119900] Decorrelating experience for 768 frames... [2023-03-09 10:32:20,409][119476] Decorrelating experience for 384 frames... [2023-03-09 10:32:20,437][119466] Decorrelating experience for 352 frames... [2023-03-09 10:32:20,496][119388] Decorrelating experience for 576 frames... [2023-03-09 10:32:20,514][120550] Decorrelating experience for 608 frames... [2023-03-09 10:32:20,567][119807] Decorrelating experience for 640 frames... [2023-03-09 10:32:20,568][119484] Decorrelating experience for 544 frames... [2023-03-09 10:32:20,568][119391] Decorrelating experience for 576 frames... [2023-03-09 10:32:20,569][119487] Decorrelating experience for 448 frames... [2023-03-09 10:32:20,588][119475] Decorrelating experience for 640 frames... [2023-03-09 10:32:20,589][119491] Decorrelating experience for 736 frames... [2023-03-09 10:32:20,652][119470] Decorrelating experience for 768 frames... [2023-03-09 10:32:20,697][119515] Decorrelating experience for 608 frames... [2023-03-09 10:32:20,698][120648] Decorrelating experience for 704 frames... [2023-03-09 10:32:20,710][119537] Decorrelating experience for 640 frames... [2023-03-09 10:32:20,754][119390] Another process currently holds the lock /tmp/sf2_rolo/doom_006.lockfile, attempt: 1 [2023-03-09 10:32:20,772][120629] Decorrelating experience for 928 frames... [2023-03-09 10:32:20,806][119478] Decorrelating experience for 640 frames... [2023-03-09 10:32:20,815][119485] Decorrelating experience for 672 frames... [2023-03-09 10:32:20,816][119615] Decorrelating experience for 608 frames... [2023-03-09 10:32:20,816][119508] Decorrelating experience for 640 frames... [2023-03-09 10:32:20,840][120904] Decorrelating experience for 416 frames... [2023-03-09 10:32:20,867][119543] Decorrelating experience for 800 frames... [2023-03-09 10:32:20,900][119534] Decorrelating experience for 480 frames... [2023-03-09 10:32:20,907][120199] Decorrelating experience for 544 frames... [2023-03-09 10:32:20,907][119532] Decorrelating experience for 832 frames... [2023-03-09 10:32:20,991][119496] Decorrelating experience for 416 frames... [2023-03-09 10:32:21,029][119466] Decorrelating experience for 384 frames... [2023-03-09 10:32:21,029][119541] Decorrelating experience for 384 frames... [2023-03-09 10:32:21,031][119498] Decorrelating experience for 576 frames... [2023-03-09 10:32:21,038][120550] Decorrelating experience for 640 frames... [2023-03-09 10:32:21,047][119487] Decorrelating experience for 480 frames... [2023-03-09 10:32:21,099][119399] Decorrelating experience for 448 frames... [2023-03-09 10:32:21,103][119535] Decorrelating experience for 864 frames... [2023-03-09 10:32:21,112][119388] Decorrelating experience for 608 frames... [2023-03-09 10:32:21,137][119481] Decorrelating experience for 608 frames... [2023-03-09 10:32:21,194][119491] Decorrelating experience for 768 frames... [2023-03-09 10:32:21,223][119484] Decorrelating experience for 576 frames... [2023-03-09 10:32:21,236][119900] Decorrelating experience for 800 frames... [2023-03-09 10:32:21,237][119462] Decorrelating experience for 736 frames... [2023-03-09 10:32:21,250][119483] Decorrelating experience for 576 frames... [2023-03-09 10:32:21,253][119395] Decorrelating experience for 480 frames... [2023-03-09 10:32:21,297][119537] Decorrelating experience for 672 frames... [2023-03-09 10:32:21,315][119519] Decorrelating experience for 768 frames... [2023-03-09 10:32:21,338][119464] Decorrelating experience for 416 frames... [2023-03-09 10:32:21,379][119807] Decorrelating experience for 672 frames... [2023-03-09 10:32:21,420][119485] Decorrelating experience for 704 frames... [2023-03-09 10:32:21,437][120904] Decorrelating experience for 448 frames... [2023-03-09 10:32:21,457][119496] Decorrelating experience for 448 frames... [2023-03-09 10:32:21,458][119615] Decorrelating experience for 640 frames... [2023-03-09 10:32:21,459][119505] Decorrelating experience for 224 frames... [2023-03-09 10:32:21,511][119391] Decorrelating experience for 608 frames... [2023-03-09 10:32:21,549][119513] Decorrelating experience for 768 frames... [2023-03-09 10:32:21,569][119517] Decorrelating experience for 352 frames... [2023-03-09 10:32:21,588][119515] Decorrelating experience for 640 frames... [2023-03-09 10:32:21,601][120629] Decorrelating experience for 960 frames... [2023-03-09 10:32:21,628][119534] Decorrelating experience for 512 frames... [2023-03-09 10:32:21,675][119473] Decorrelating experience for 352 frames... [2023-03-09 10:32:21,676][119546] Decorrelating experience for 672 frames... [2023-03-09 10:32:21,676][119389] Decorrelating experience for 576 frames... [2023-03-09 10:32:21,677][119533] Decorrelating experience for 768 frames... [2023-03-09 10:32:21,766][119538] Decorrelating experience for 544 frames... [2023-03-09 10:32:21,770][119536] Decorrelating experience for 672 frames... [2023-03-09 10:32:21,774][119481] Decorrelating experience for 640 frames... [2023-03-09 10:32:21,808][119540] Decorrelating experience for 576 frames... [2023-03-09 10:32:21,809][119397] Decorrelating experience for 832 frames... [2023-03-09 10:32:21,839][119900] Decorrelating experience for 832 frames... [2023-03-09 10:32:21,890][119466] Decorrelating experience for 416 frames... [2023-03-09 10:32:21,890][120003] Decorrelating experience for 640 frames... [2023-03-09 10:32:21,891][119541] Decorrelating experience for 416 frames... [2023-03-09 10:32:21,896][120904] Decorrelating experience for 480 frames... [2023-03-09 10:32:21,966][119614] Decorrelating experience for 288 frames... [2023-03-09 10:32:21,969][120199] Decorrelating experience for 576 frames... [2023-03-09 10:32:21,979][120550] Decorrelating experience for 672 frames... [2023-03-09 10:32:22,009][120896] Decorrelating experience for 672 frames... [2023-03-09 10:32:22,009][119494] Decorrelating experience for 416 frames... [2023-03-09 10:32:22,038][119807] Decorrelating experience for 704 frames... [2023-03-09 10:32:22,087][119515] Decorrelating experience for 672 frames... [2023-03-09 10:32:22,095][119484] Decorrelating experience for 608 frames... [2023-03-09 10:32:22,098][119395] Decorrelating experience for 512 frames... [2023-03-09 10:32:22,170][119493] Decorrelating experience for 608 frames... [2023-03-09 10:32:22,178][119483] Decorrelating experience for 608 frames... [2023-03-09 10:32:22,181][119464] Decorrelating experience for 448 frames... [2023-03-09 10:32:22,184][119538] Decorrelating experience for 576 frames... [2023-03-09 10:32:22,204][119550] Decorrelating experience for 288 frames... [2023-03-09 10:32:22,207][119502] Decorrelating experience for 352 frames... [2023-03-09 10:32:22,214][120652] Another process currently holds the lock /tmp/sf2_rolo/doom_002.lockfile, attempt: 1 [2023-03-09 10:32:22,247][119466] Decorrelating experience for 448 frames... [2023-03-09 10:32:22,297][119389] Decorrelating experience for 608 frames... [2023-03-09 10:32:22,329][119505] Decorrelating experience for 256 frames... [2023-03-09 10:32:22,354][120073] Decorrelating experience for 576 frames... [2023-03-09 10:32:22,386][119486] Decorrelating experience for 288 frames... [2023-03-09 10:32:22,388][119394] Decorrelating experience for 672 frames... [2023-03-09 10:32:22,392][119522] Decorrelating experience for 512 frames... [2023-03-09 10:32:22,393][119399] Decorrelating experience for 480 frames... [2023-03-09 10:32:22,398][119541] Decorrelating experience for 448 frames... [2023-03-09 10:32:22,404][119520] Decorrelating experience for 192 frames... [2023-03-09 10:32:22,468][119513] Decorrelating experience for 800 frames... [2023-03-09 10:32:22,502][119537] Decorrelating experience for 704 frames... [2023-03-09 10:32:22,520][119536] Decorrelating experience for 704 frames... [2023-03-09 10:32:22,554][119807] Decorrelating experience for 736 frames... [2023-03-09 10:32:22,573][119946] Another process currently holds the lock /tmp/sf2_rolo/doom_006.lockfile, attempt: 1 [2023-03-09 10:32:22,580][119543] Decorrelating experience for 832 frames... [2023-03-09 10:32:22,586][119546] Decorrelating experience for 704 frames... [2023-03-09 10:32:22,600][119483] Decorrelating experience for 640 frames... [2023-03-09 10:32:22,634][119538] Decorrelating experience for 608 frames... [2023-03-09 10:32:22,648][119526] Decorrelating experience for 608 frames... [2023-03-09 10:32:22,661][119550] Decorrelating experience for 320 frames... [2023-03-09 10:32:22,664][119487] Decorrelating experience for 512 frames... [2023-03-09 10:32:22,756][120652] Decorrelating experience for 384 frames... [2023-03-09 10:32:22,794][119398] Decorrelating experience for 480 frames... [2023-03-09 10:32:22,798][119535] Decorrelating experience for 896 frames... [2023-03-09 10:32:22,798][119476] Decorrelating experience for 416 frames... [2023-03-09 10:32:22,800][119485] Decorrelating experience for 736 frames... [2023-03-09 10:32:22,800][119491] Decorrelating experience for 800 frames... [2023-03-09 10:32:22,868][119525] Decorrelating experience for 608 frames... [2023-03-09 10:32:22,873][119517] Decorrelating experience for 384 frames... [2023-03-09 10:32:22,873][119478] Decorrelating experience for 672 frames... [2023-03-09 10:32:22,874][120003] Decorrelating experience for 672 frames... [2023-03-09 10:32:22,999][119532] Decorrelating experience for 864 frames... [2023-03-09 10:32:23,007][119394] Decorrelating experience for 704 frames... [2023-03-09 10:32:23,010][120073] Decorrelating experience for 608 frames... [2023-03-09 10:32:23,020][119462] Decorrelating experience for 768 frames... [2023-03-09 10:32:23,053][119534] Decorrelating experience for 544 frames... [2023-03-09 10:32:23,061][119900] Decorrelating experience for 864 frames... [2023-03-09 10:32:23,071][119494] Decorrelating experience for 448 frames... [2023-03-09 10:32:23,073][119388] Decorrelating experience for 640 frames... [2023-03-09 10:32:23,089][119474] Decorrelating experience for 864 frames... [2023-03-09 10:32:23,091][119399] Decorrelating experience for 512 frames... [2023-03-09 10:32:23,197][119513] Decorrelating experience for 832 frames... [2023-03-09 10:32:23,214][119476] Decorrelating experience for 448 frames... [2023-03-09 10:32:23,217][119389] Decorrelating experience for 640 frames... [2023-03-09 10:32:23,262][119615] Decorrelating experience for 672 frames... [2023-03-09 10:32:23,266][119539] Decorrelating experience for 288 frames... [2023-03-09 10:32:23,297][119541] Decorrelating experience for 480 frames... [2023-03-09 10:32:23,297][119505] Decorrelating experience for 288 frames... [2023-03-09 10:32:23,297][119484] Decorrelating experience for 640 frames... [2023-03-09 10:32:23,300][120629] Decorrelating experience for 992 frames... [2023-03-09 10:32:23,346][119481] Decorrelating experience for 672 frames... [2023-03-09 10:32:23,394][119546] Decorrelating experience for 736 frames... [2023-03-09 10:32:23,407][119549] Decorrelating experience for 672 frames... [2023-03-09 10:32:23,421][119680] Decorrelating experience for 864 frames... [2023-03-09 10:32:23,464][119655] Decorrelating experience for 448 frames... [2023-03-09 10:32:23,468][120005] Decorrelating experience for 480 frames... [2023-03-09 10:32:23,503][119543] Decorrelating experience for 864 frames... [2023-03-09 10:32:23,503][120652] Decorrelating experience for 416 frames... [2023-03-09 10:32:23,532][119532] Decorrelating experience for 896 frames... [2023-03-09 10:32:23,539][119396] Decorrelating experience for 544 frames... [2023-03-09 10:32:23,549][119522] Decorrelating experience for 544 frames... [2023-03-09 10:32:23,612][120003] Decorrelating experience for 704 frames... [2023-03-09 10:32:23,622][120778] Decorrelating experience for 640 frames... [2023-03-09 10:32:23,669][119506] Decorrelating experience for 640 frames... [2023-03-09 10:32:23,669][119937] Decorrelating experience for 608 frames... [2023-03-09 10:32:23,690][119498] Decorrelating experience for 608 frames... [2023-03-09 10:32:23,700][119525] Decorrelating experience for 640 frames... [2023-03-09 10:32:23,744][119808] Decorrelating experience for 832 frames... [2023-03-09 10:32:23,757][119535] Decorrelating experience for 928 frames... [2023-03-09 10:32:23,782][119476] Decorrelating experience for 480 frames... [2023-03-09 10:32:23,782][120073] Decorrelating experience for 640 frames... [2023-03-09 10:32:23,837][118949] Heartbeat connected on RolloutWorker_w103 [2023-03-09 10:32:23,850][119466] Decorrelating experience for 480 frames... [2023-03-09 10:32:23,878][119615] Decorrelating experience for 704 frames... [2023-03-09 10:32:23,879][119542] Decorrelating experience for 672 frames... [2023-03-09 10:32:23,885][119550] Decorrelating experience for 352 frames... [2023-03-09 10:32:23,887][119538] Decorrelating experience for 640 frames... [2023-03-09 10:32:23,902][118949] Fps is (10 sec: 4915.3, 60 sec: 983.0, 300 sec: 983.0). Total num frames: 2000076800. Throughput: 0: 309.0. Samples: 13904. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 10:32:23,903][118949] Avg episode reward: [(0, '2.234')] [2023-03-09 10:32:23,912][119462] Decorrelating experience for 800 frames... [2023-03-09 10:32:23,957][119491] Decorrelating experience for 832 frames... [2023-03-09 10:32:23,985][119485] Decorrelating experience for 768 frames... [2023-03-09 10:32:23,990][119398] Decorrelating experience for 512 frames... [2023-03-09 10:32:24,030][119481] Decorrelating experience for 704 frames... [2023-03-09 10:32:24,052][119502] Decorrelating experience for 384 frames... [2023-03-09 10:32:24,073][121015] Decorrelating experience for 480 frames... [2023-03-09 10:32:24,089][119391] Decorrelating experience for 640 frames... [2023-03-09 10:32:24,090][119543] Decorrelating experience for 896 frames... [2023-03-09 10:32:24,090][119541] Decorrelating experience for 512 frames... [2023-03-09 10:32:24,121][119517] Decorrelating experience for 416 frames... [2023-03-09 10:32:24,167][119532] Decorrelating experience for 928 frames... [2023-03-09 10:32:24,179][120003] Decorrelating experience for 736 frames... [2023-03-09 10:32:24,191][119399] Decorrelating experience for 544 frames... [2023-03-09 10:32:24,242][119496] Decorrelating experience for 480 frames... [2023-03-09 10:32:24,250][119540] Decorrelating experience for 608 frames... [2023-03-09 10:32:24,265][119550] Decorrelating experience for 384 frames... [2023-03-09 10:32:24,288][119466] Decorrelating experience for 512 frames... [2023-03-09 10:32:24,291][119394] Decorrelating experience for 736 frames... [2023-03-09 10:32:24,325][119501] Decorrelating experience for 352 frames... [2023-03-09 10:32:24,362][120904] Decorrelating experience for 512 frames... [2023-03-09 10:32:24,386][119520] Decorrelating experience for 224 frames... [2023-03-09 10:32:24,394][119536] Decorrelating experience for 736 frames... [2023-03-09 10:32:24,418][119535] Decorrelating experience for 960 frames... [2023-03-09 10:32:24,444][119527] Decorrelating experience for 992 frames... [2023-03-09 10:32:24,459][119486] Decorrelating experience for 320 frames... [2023-03-09 10:32:24,469][119500] Decorrelating experience for 544 frames... [2023-03-09 10:32:24,478][120004] Another process currently holds the lock /tmp/sf2_rolo/doom_006.lockfile, attempt: 2 [2023-03-09 10:32:24,483][119614] Decorrelating experience for 320 frames... [2023-03-09 10:32:24,497][119484] Decorrelating experience for 672 frames... [2023-03-09 10:32:24,527][119544] Decorrelating experience for 544 frames... [2023-03-09 10:32:24,560][121015] Decorrelating experience for 512 frames... [2023-03-09 10:32:24,589][119526] Decorrelating experience for 640 frames... [2023-03-09 10:32:24,595][119494] Decorrelating experience for 480 frames... [2023-03-09 10:32:24,626][119539] Decorrelating experience for 320 frames... [2023-03-09 10:32:24,649][119502] Decorrelating experience for 416 frames... [2023-03-09 10:32:24,657][119550] Decorrelating experience for 416 frames... [2023-03-09 10:32:24,668][119520] Decorrelating experience for 256 frames... [2023-03-09 10:32:24,682][119531] Decorrelating experience for 416 frames... [2023-03-09 10:32:24,700][120550] Decorrelating experience for 704 frames... [2023-03-09 10:32:24,731][119469] Decorrelating experience for 192 frames... [2023-03-09 10:32:24,756][120199] Decorrelating experience for 608 frames... [2023-03-09 10:32:24,807][119396] Decorrelating experience for 576 frames... [2023-03-09 10:32:24,811][119540] Decorrelating experience for 640 frames... [2023-03-09 10:32:24,827][119532] Decorrelating experience for 960 frames... [2023-03-09 10:32:24,870][119501] Decorrelating experience for 384 frames... [2023-03-09 10:32:24,872][118949] Heartbeat connected on RolloutWorker_w63 [2023-03-09 10:32:24,887][119500] Decorrelating experience for 576 frames... [2023-03-09 10:32:24,888][119808] Decorrelating experience for 864 frames... [2023-03-09 10:32:24,891][119549] Decorrelating experience for 704 frames... [2023-03-09 10:32:24,951][119614] Decorrelating experience for 352 frames... [2023-03-09 10:32:24,994][120896] Decorrelating experience for 704 frames... [2023-03-09 10:32:24,998][119538] Decorrelating experience for 672 frames... [2023-03-09 10:32:25,014][119499] Decorrelating experience for 640 frames... [2023-03-09 10:32:25,074][119507] Decorrelating experience for 416 frames... [2023-03-09 10:32:25,074][120002] Decorrelating experience for 704 frames... [2023-03-09 10:32:25,105][119466] Decorrelating experience for 544 frames... [2023-03-09 10:32:25,105][119391] Decorrelating experience for 672 frames... [2023-03-09 10:32:25,108][125883] Decorrelating experience for 448 frames... [2023-03-09 10:32:25,111][119496] Decorrelating experience for 512 frames... [2023-03-09 10:32:25,143][119544] Decorrelating experience for 576 frames... [2023-03-09 10:32:25,194][119517] Decorrelating experience for 448 frames... [2023-03-09 10:32:25,207][119502] Decorrelating experience for 448 frames... [2023-03-09 10:32:25,213][119520] Decorrelating experience for 288 frames... [2023-03-09 10:32:25,238][119547] Another process currently holds the lock /tmp/sf2_rolo/doom_006.lockfile, attempt: 2 [2023-03-09 10:32:25,287][121015] Decorrelating experience for 544 frames... [2023-03-09 10:32:25,287][120004] Decorrelating experience for 288 frames... [2023-03-09 10:32:25,312][119484] Decorrelating experience for 704 frames... [2023-03-09 10:32:25,315][119388] Decorrelating experience for 672 frames... [2023-03-09 10:32:25,361][119481] Decorrelating experience for 736 frames... [2023-03-09 10:32:25,422][119808] Decorrelating experience for 896 frames... [2023-03-09 10:32:25,426][119501] Decorrelating experience for 416 frames... [2023-03-09 10:32:25,428][119506] Decorrelating experience for 672 frames... [2023-03-09 10:32:25,459][119655] Decorrelating experience for 480 frames... [2023-03-09 10:32:25,475][119528] Decorrelating experience for 672 frames... [2023-03-09 10:32:25,492][119488] Decorrelating experience for 544 frames... [2023-03-09 10:32:25,518][119396] Decorrelating experience for 608 frames... [2023-03-09 10:32:25,530][120904] Decorrelating experience for 544 frames... [2023-03-09 10:32:25,565][119399] Decorrelating experience for 576 frames... [2023-03-09 10:32:25,620][119534] Decorrelating experience for 576 frames... [2023-03-09 10:32:25,633][119548] Decorrelating experience for 704 frames... [2023-03-09 10:32:25,636][119523] Decorrelating experience for 672 frames... [2023-03-09 10:32:25,649][119807] Decorrelating experience for 768 frames... [2023-03-09 10:32:25,676][119524] Decorrelating experience for 96 frames... [2023-03-09 10:32:25,692][119543] Decorrelating experience for 928 frames... [2023-03-09 10:32:25,754][119462] Decorrelating experience for 832 frames... [2023-03-09 10:32:25,778][119484] Decorrelating experience for 736 frames... [2023-03-09 10:32:25,803][119394] Decorrelating experience for 768 frames... [2023-03-09 10:32:25,824][120073] Decorrelating experience for 672 frames... [2023-03-09 10:32:25,841][120778] Decorrelating experience for 672 frames... [2023-03-09 10:32:25,844][120263] Decorrelating experience for 544 frames... [2023-03-09 10:32:25,845][119537] Decorrelating experience for 736 frames... [2023-03-09 10:32:25,879][120040] Decorrelating experience for 480 frames... [2023-03-09 10:32:25,899][119397] Decorrelating experience for 864 frames... [2023-03-09 10:32:25,924][120002] Decorrelating experience for 736 frames... [2023-03-09 10:32:25,950][119395] Decorrelating experience for 544 frames... [2023-03-09 10:32:26,017][120003] Decorrelating experience for 768 frames... [2023-03-09 10:32:26,036][119486] Decorrelating experience for 352 frames... [2023-03-09 10:32:26,047][119542] Decorrelating experience for 704 frames... [2023-03-09 10:32:26,066][119531] Decorrelating experience for 448 frames... [2023-03-09 10:32:26,079][119494] Decorrelating experience for 512 frames... [2023-03-09 10:32:26,109][119481] Decorrelating experience for 768 frames... [2023-03-09 10:32:26,112][119548] Decorrelating experience for 736 frames... [2023-03-09 10:32:26,144][119398] Decorrelating experience for 544 frames... [2023-03-09 10:32:26,182][119470] Decorrelating experience for 800 frames... [2023-03-09 10:32:26,221][119550] Decorrelating experience for 448 frames... [2023-03-09 10:32:26,234][119513] Decorrelating experience for 864 frames... [2023-03-09 10:32:26,248][119499] Decorrelating experience for 672 frames... [2023-03-09 10:32:26,288][119521] Decorrelating experience for 544 frames... [2023-03-09 10:32:26,296][119517] Decorrelating experience for 480 frames... [2023-03-09 10:32:26,304][119394] Decorrelating experience for 800 frames... [2023-03-09 10:32:26,308][119525] Decorrelating experience for 672 frames... [2023-03-09 10:32:26,339][119534] Decorrelating experience for 608 frames... [2023-03-09 10:32:26,364][120896] Decorrelating experience for 736 frames... [2023-03-09 10:32:26,398][119472] Decorrelating experience for 704 frames... [2023-03-09 10:32:26,435][120652] Decorrelating experience for 448 frames... [2023-03-09 10:32:26,458][119508] Decorrelating experience for 672 frames... [2023-03-09 10:32:26,473][120073] Decorrelating experience for 704 frames... [2023-03-09 10:32:26,487][120717] Decorrelating experience for 448 frames... [2023-03-09 10:32:26,501][120002] Decorrelating experience for 768 frames... [2023-03-09 10:32:26,508][119500] Decorrelating experience for 608 frames... [2023-03-09 10:32:26,541][119536] Decorrelating experience for 768 frames... [2023-03-09 10:32:26,576][119395] Decorrelating experience for 576 frames... [2023-03-09 10:32:26,599][119523] Decorrelating experience for 704 frames... [2023-03-09 10:32:26,632][119524] Decorrelating experience for 128 frames... [2023-03-09 10:32:26,640][119522] Decorrelating experience for 576 frames... [2023-03-09 10:32:26,666][119469] Decorrelating experience for 224 frames... [2023-03-09 10:32:26,685][119470] Decorrelating experience for 832 frames... [2023-03-09 10:32:26,702][121015] Decorrelating experience for 576 frames... [2023-03-09 10:32:26,716][119487] Decorrelating experience for 544 frames... [2023-03-09 10:32:26,727][119496] Decorrelating experience for 544 frames... [2023-03-09 10:32:26,740][119526] Decorrelating experience for 672 frames... [2023-03-09 10:32:26,809][119499] Decorrelating experience for 704 frames... [2023-03-09 10:32:26,826][119509] Decorrelating experience for 640 frames... [2023-03-09 10:32:26,840][120550] Decorrelating experience for 736 frames... [2023-03-09 10:32:26,881][119397] Decorrelating experience for 896 frames... [2023-03-09 10:32:26,909][119528] Decorrelating experience for 704 frames... [2023-03-09 10:32:26,916][119537] Decorrelating experience for 768 frames... [2023-03-09 10:32:26,917][119501] Decorrelating experience for 448 frames... [2023-03-09 10:32:26,933][119544] Decorrelating experience for 608 frames... [2023-03-09 10:32:26,936][119500] Decorrelating experience for 640 frames... [2023-03-09 10:32:26,996][120896] Decorrelating experience for 768 frames... [2023-03-09 10:32:27,006][120778] Decorrelating experience for 704 frames... [2023-03-09 10:32:27,021][119476] Decorrelating experience for 512 frames... [2023-03-09 10:32:27,047][119479] Another process currently holds the lock /tmp/sf2_rolo/doom_006.lockfile, attempt: 1 [2023-03-09 10:32:27,065][120003] Decorrelating experience for 800 frames... [2023-03-09 10:32:27,075][119490] Decorrelating experience for 800 frames... [2023-03-09 10:32:27,108][120652] Decorrelating experience for 480 frames... [2023-03-09 10:32:27,118][119900] Decorrelating experience for 896 frames... [2023-03-09 10:32:27,138][119396] Decorrelating experience for 640 frames... [2023-03-09 10:32:27,146][119487] Decorrelating experience for 576 frames... [2023-03-09 10:32:27,147][119498] Decorrelating experience for 640 frames... [2023-03-09 10:32:27,204][120002] Decorrelating experience for 800 frames... [2023-03-09 10:32:27,227][119508] Decorrelating experience for 704 frames... [2023-03-09 10:32:27,228][121015] Decorrelating experience for 608 frames... [2023-03-09 10:32:27,272][119523] Decorrelating experience for 736 frames... [2023-03-09 10:32:27,277][119483] Decorrelating experience for 672 frames... [2023-03-09 10:32:27,318][119484] Decorrelating experience for 768 frames... [2023-03-09 10:32:27,328][119509] Decorrelating experience for 672 frames... [2023-03-09 10:32:27,335][119540] Decorrelating experience for 672 frames... [2023-03-09 10:32:27,345][119493] Decorrelating experience for 640 frames... [2023-03-09 10:32:27,358][119496] Decorrelating experience for 576 frames... [2023-03-09 10:32:27,406][119470] Decorrelating experience for 864 frames... [2023-03-09 10:32:27,436][119544] Decorrelating experience for 640 frames... [2023-03-09 10:32:27,462][119388] Decorrelating experience for 704 frames... [2023-03-09 10:32:27,473][119391] Decorrelating experience for 704 frames... [2023-03-09 10:32:27,477][119515] Decorrelating experience for 704 frames... [2023-03-09 10:32:27,539][119500] Decorrelating experience for 672 frames... [2023-03-09 10:32:27,540][120778] Decorrelating experience for 736 frames... [2023-03-09 10:32:27,543][119510] Decorrelating experience for 608 frames... [2023-03-09 10:32:27,560][119521] Decorrelating experience for 576 frames... [2023-03-09 10:32:27,596][119522] Decorrelating experience for 608 frames... [2023-03-09 10:32:27,612][119539] Decorrelating experience for 352 frames... [2023-03-09 10:32:27,642][120652] Decorrelating experience for 512 frames... [2023-03-09 10:32:27,659][119807] Decorrelating experience for 800 frames... [2023-03-09 10:32:27,700][119946] Decorrelating experience for 288 frames... [2023-03-09 10:32:27,705][119526] Decorrelating experience for 704 frames... [2023-03-09 10:32:27,739][119520] Decorrelating experience for 320 frames... [2023-03-09 10:32:27,743][119480] Decorrelating experience for 640 frames... [2023-03-09 10:32:27,759][119495] Decorrelating experience for 512 frames... [2023-03-09 10:32:27,760][119523] Decorrelating experience for 768 frames... [2023-03-09 10:32:27,808][119514] Another process currently holds the lock /tmp/sf2_rolo/doom_006.lockfile, attempt: 1 [2023-03-09 10:32:27,819][119488] Decorrelating experience for 576 frames... [2023-03-09 10:32:27,857][119546] Decorrelating experience for 768 frames... [2023-03-09 10:32:27,860][120896] Decorrelating experience for 800 frames... [2023-03-09 10:32:27,873][119537] Decorrelating experience for 800 frames... [2023-03-09 10:32:27,893][120877] Decorrelating experience for 544 frames... [2023-03-09 10:32:27,934][119496] Decorrelating experience for 608 frames... [2023-03-09 10:32:27,961][119524] Decorrelating experience for 160 frames... [2023-03-09 10:32:27,961][125883] Decorrelating experience for 480 frames... [2023-03-09 10:32:27,974][119501] Decorrelating experience for 480 frames... [2023-03-09 10:32:28,053][120778] Decorrelating experience for 768 frames... [2023-03-09 10:32:28,054][119946] Decorrelating experience for 320 frames... [2023-03-09 10:32:28,097][120002] Decorrelating experience for 832 frames... [2023-03-09 10:32:28,098][119474] Decorrelating experience for 896 frames... [2023-03-09 10:32:28,105][119655] Decorrelating experience for 512 frames... [2023-03-09 10:32:28,106][119478] Decorrelating experience for 704 frames... [2023-03-09 10:32:28,171][119526] Decorrelating experience for 736 frames... [2023-03-09 10:32:28,188][119511] Decorrelating experience for 416 frames... [2023-03-09 10:32:28,194][119525] Decorrelating experience for 704 frames... [2023-03-09 10:32:28,219][119531] Decorrelating experience for 480 frames... [2023-03-09 10:32:28,277][119472] Decorrelating experience for 736 frames... [2023-03-09 10:32:28,298][119515] Decorrelating experience for 736 frames... [2023-03-09 10:32:28,312][119508] Decorrelating experience for 736 frames... [2023-03-09 10:32:28,320][119398] Decorrelating experience for 576 frames... [2023-03-09 10:32:28,376][120717] Decorrelating experience for 480 frames... [2023-03-09 10:32:28,380][119392] Decorrelating experience for 224 frames... [2023-03-09 10:32:28,385][119900] Decorrelating experience for 928 frames... [2023-03-09 10:32:28,391][119395] Decorrelating experience for 608 frames... [2023-03-09 10:32:28,414][119484] Decorrelating experience for 800 frames... [2023-03-09 10:32:28,486][119480] Decorrelating experience for 672 frames... [2023-03-09 10:32:28,524][119522] Decorrelating experience for 640 frames... [2023-03-09 10:32:28,528][119615] Decorrelating experience for 736 frames... [2023-03-09 10:32:28,563][120896] Decorrelating experience for 832 frames... [2023-03-09 10:32:28,578][119390] Decorrelating experience for 448 frames... [2023-03-09 10:32:28,614][119499] Decorrelating experience for 736 frames... [2023-03-09 10:32:28,615][120003] Decorrelating experience for 832 frames... [2023-03-09 10:32:28,617][119397] Decorrelating experience for 928 frames... [2023-03-09 10:32:28,629][120002] Decorrelating experience for 864 frames... [2023-03-09 10:32:28,689][119501] Decorrelating experience for 512 frames... [2023-03-09 10:32:28,693][119548] Decorrelating experience for 768 frames... [2023-03-09 10:32:28,736][119521] Decorrelating experience for 608 frames... [2023-03-09 10:32:28,786][119807] Decorrelating experience for 832 frames... [2023-03-09 10:32:28,794][119937] Decorrelating experience for 640 frames... [2023-03-09 10:32:28,820][119532] Decorrelating experience for 992 frames... [2023-03-09 10:32:28,823][119524] Decorrelating experience for 192 frames... [2023-03-09 10:32:28,836][120778] Decorrelating experience for 800 frames... [2023-03-09 10:32:28,849][119462] Decorrelating experience for 864 frames... [2023-03-09 10:32:28,902][118949] Fps is (10 sec: 9830.4, 60 sec: 2085.2, 300 sec: 2085.2). Total num frames: 2000142336. Throughput: 0: 776.5. Samples: 34944. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 10:32:28,903][119526] Decorrelating experience for 768 frames... [2023-03-09 10:32:28,903][118949] Avg episode reward: [(0, '21.055')] [2023-03-09 10:32:28,905][119536] Decorrelating experience for 800 frames... [2023-03-09 10:32:28,927][119388] Decorrelating experience for 736 frames... [2023-03-09 10:32:28,981][119537] Decorrelating experience for 832 frames... [2023-03-09 10:32:28,992][119490] Decorrelating experience for 832 frames... [2023-03-09 10:32:29,005][119389] Decorrelating experience for 672 frames... [2023-03-09 10:32:29,021][119520] Decorrelating experience for 352 frames... [2023-03-09 10:32:29,025][119615] Decorrelating experience for 768 frames... [2023-03-09 10:32:29,045][119509] Decorrelating experience for 704 frames... [2023-03-09 10:32:29,086][120073] Decorrelating experience for 736 frames... [2023-03-09 10:32:29,101][119391] Decorrelating experience for 736 frames... [2023-03-09 10:32:29,169][120717] Decorrelating experience for 512 frames... [2023-03-09 10:32:29,169][119480] Decorrelating experience for 704 frames... [2023-03-09 10:32:29,219][118949] Heartbeat connected on RolloutWorker_w61 [2023-03-09 10:32:29,228][119395] Decorrelating experience for 640 frames... [2023-03-09 10:32:29,229][119542] Decorrelating experience for 736 frames... [2023-03-09 10:32:29,240][119464] Decorrelating experience for 480 frames... [2023-03-09 10:32:29,288][119484] Decorrelating experience for 832 frames... [2023-03-09 10:32:29,288][119472] Decorrelating experience for 768 frames... [2023-03-09 10:32:29,289][119541] Decorrelating experience for 544 frames... [2023-03-09 10:32:29,319][119478] Decorrelating experience for 736 frames... [2023-03-09 10:32:29,319][119548] Decorrelating experience for 800 frames... [2023-03-09 10:32:29,365][121015] Decorrelating experience for 640 frames... [2023-03-09 10:32:29,437][120003] Decorrelating experience for 864 frames... [2023-03-09 10:32:29,449][120005] Decorrelating experience for 512 frames... [2023-03-09 10:32:29,499][119537] Decorrelating experience for 864 frames... [2023-03-09 10:32:29,519][119528] Decorrelating experience for 736 frames... [2023-03-09 10:32:29,528][119531] Decorrelating experience for 512 frames... [2023-03-09 10:32:29,531][120550] Decorrelating experience for 768 frames... [2023-03-09 10:32:29,562][119392] Decorrelating experience for 256 frames... [2023-03-09 10:32:29,584][119807] Decorrelating experience for 864 frames... [2023-03-09 10:32:29,592][119535] Decorrelating experience for 992 frames... [2023-03-09 10:32:29,593][120778] Decorrelating experience for 832 frames... [2023-03-09 10:32:29,662][119490] Decorrelating experience for 864 frames... [2023-03-09 10:32:29,691][120002] Decorrelating experience for 896 frames... [2023-03-09 10:32:29,719][119508] Decorrelating experience for 768 frames... [2023-03-09 10:32:29,731][119655] Decorrelating experience for 544 frames... [2023-03-09 10:32:29,783][119513] Decorrelating experience for 896 frames... [2023-03-09 10:32:29,785][119389] Decorrelating experience for 704 frames... [2023-03-09 10:32:29,789][119529] Decorrelating experience for 224 frames... [2023-03-09 10:32:29,792][119462] Decorrelating experience for 896 frames... [2023-03-09 10:32:29,816][119937] Decorrelating experience for 672 frames... [2023-03-09 10:32:29,848][119526] Decorrelating experience for 800 frames... [2023-03-09 10:32:29,916][119500] Decorrelating experience for 704 frames... [2023-03-09 10:32:29,924][119541] Decorrelating experience for 576 frames... [2023-03-09 10:32:29,939][119464] Decorrelating experience for 512 frames... [2023-03-09 10:32:29,991][119391] Decorrelating experience for 768 frames... [2023-03-09 10:32:30,018][120005] Decorrelating experience for 544 frames... [2023-03-09 10:32:30,021][119392] Decorrelating experience for 288 frames... [2023-03-09 10:32:30,021][119388] Decorrelating experience for 768 frames... [2023-03-09 10:32:30,023][119397] Decorrelating experience for 960 frames... [2023-03-09 10:32:30,054][120896] Decorrelating experience for 864 frames... [2023-03-09 10:32:30,070][119538] Decorrelating experience for 704 frames... [2023-03-09 10:32:30,120][120877] Decorrelating experience for 576 frames... [2023-03-09 10:32:30,132][119655] Decorrelating experience for 576 frames... [2023-03-09 10:32:30,157][118949] Heartbeat connected on RolloutWorker_w52 [2023-03-09 10:32:30,169][119493] Decorrelating experience for 672 frames... [2023-03-09 10:32:30,231][119530] Decorrelating experience for 384 frames... [2023-03-09 10:32:30,241][119536] Decorrelating experience for 832 frames... [2023-03-09 10:32:30,242][119396] Decorrelating experience for 672 frames... [2023-03-09 10:32:30,242][119524] Decorrelating experience for 224 frames... [2023-03-09 10:32:30,247][119478] Decorrelating experience for 768 frames... [2023-03-09 10:32:30,298][119522] Decorrelating experience for 672 frames... [2023-03-09 10:32:30,320][119807] Decorrelating experience for 896 frames... [2023-03-09 10:32:30,342][119541] Decorrelating experience for 608 frames... [2023-03-09 10:32:30,361][119507] Decorrelating experience for 448 frames... [2023-03-09 10:32:30,367][119399] Decorrelating experience for 608 frames... [2023-03-09 10:32:30,427][119511] Decorrelating experience for 448 frames... [2023-03-09 10:32:30,452][119490] Decorrelating experience for 896 frames... [2023-03-09 10:32:30,453][120904] Decorrelating experience for 576 frames... [2023-03-09 10:32:30,464][119526] Decorrelating experience for 832 frames... [2023-03-09 10:32:30,478][119900] Decorrelating experience for 960 frames... [2023-03-09 10:32:30,529][119470] Decorrelating experience for 896 frames... [2023-03-09 10:32:30,530][119484] Decorrelating experience for 864 frames... [2023-03-09 10:32:30,539][120002] Decorrelating experience for 928 frames... [2023-03-09 10:32:30,540][119545] Another process currently holds the lock /tmp/sf2_rolo/doom_006.lockfile, attempt: 1 [2023-03-09 10:32:30,588][119537] Decorrelating experience for 896 frames... [2023-03-09 10:32:30,618][119383] Updated weights for policy 0, policy_version 122082 (0.0012) [2023-03-09 10:32:30,621][119394] Decorrelating experience for 832 frames... [2023-03-09 10:32:30,640][119540] Decorrelating experience for 704 frames... [2023-03-09 10:32:30,662][119655] Decorrelating experience for 608 frames... [2023-03-09 10:32:30,666][119531] Decorrelating experience for 544 frames... [2023-03-09 10:32:30,680][119477] Another process currently holds the lock /tmp/sf2_rolo/doom_006.lockfile, attempt: 1 [2023-03-09 10:32:30,681][119615] Decorrelating experience for 800 frames... [2023-03-09 10:32:30,735][119808] Decorrelating experience for 928 frames... [2023-03-09 10:32:30,735][119483] Decorrelating experience for 704 frames... [2023-03-09 10:32:30,753][119389] Decorrelating experience for 736 frames... [2023-03-09 10:32:30,805][119480] Decorrelating experience for 736 frames... [2023-03-09 10:32:30,824][120004] Decorrelating experience for 320 frames... [2023-03-09 10:32:30,834][119391] Decorrelating experience for 800 frames... [2023-03-09 10:32:30,846][119462] Decorrelating experience for 928 frames... [2023-03-09 10:32:30,870][119520] Decorrelating experience for 384 frames... [2023-03-09 10:32:30,874][119508] Decorrelating experience for 800 frames... [2023-03-09 10:32:30,936][119398] Decorrelating experience for 608 frames... [2023-03-09 10:32:30,994][120073] Decorrelating experience for 768 frames... [2023-03-09 10:32:30,996][120877] Decorrelating experience for 608 frames... [2023-03-09 10:32:31,025][119525] Decorrelating experience for 736 frames... [2023-03-09 10:32:31,043][119548] Decorrelating experience for 832 frames... [2023-03-09 10:32:31,082][119542] Decorrelating experience for 768 frames... [2023-03-09 10:32:31,088][121015] Decorrelating experience for 672 frames... [2023-03-09 10:32:31,106][119937] Decorrelating experience for 704 frames... [2023-03-09 10:32:31,143][119464] Decorrelating experience for 544 frames... [2023-03-09 10:32:31,148][120004] Decorrelating experience for 352 frames... [2023-03-09 10:32:31,229][119501] Decorrelating experience for 544 frames... [2023-03-09 10:32:31,261][120778] Decorrelating experience for 864 frames... [2023-03-09 10:32:31,265][119397] Decorrelating experience for 992 frames... [2023-03-09 10:32:31,309][119509] Decorrelating experience for 736 frames... [2023-03-09 10:32:31,309][119544] Decorrelating experience for 672 frames... [2023-03-09 10:32:31,309][119389] Decorrelating experience for 768 frames... [2023-03-09 10:32:31,312][119519] Decorrelating experience for 800 frames... [2023-03-09 10:32:31,365][119520] Decorrelating experience for 416 frames... [2023-03-09 10:32:31,377][119484] Decorrelating experience for 896 frames... [2023-03-09 10:32:31,417][120003] Decorrelating experience for 896 frames... [2023-03-09 10:32:31,464][119511] Decorrelating experience for 480 frames... [2023-03-09 10:32:31,482][119391] Decorrelating experience for 832 frames... [2023-03-09 10:32:31,522][119522] Decorrelating experience for 704 frames... [2023-03-09 10:32:31,535][119476] Decorrelating experience for 544 frames... [2023-03-09 10:32:31,535][119540] Decorrelating experience for 736 frames... [2023-03-09 10:32:31,535][119398] Decorrelating experience for 640 frames... [2023-03-09 10:32:31,545][120877] Decorrelating experience for 640 frames... [2023-03-09 10:32:31,589][119394] Decorrelating experience for 864 frames... [2023-03-09 10:32:31,603][119525] Decorrelating experience for 768 frames... [2023-03-09 10:32:31,629][120004] Decorrelating experience for 384 frames... [2023-03-09 10:32:31,664][119900] Decorrelating experience for 992 frames... [2023-03-09 10:32:31,686][119550] Decorrelating experience for 480 frames... [2023-03-09 10:32:31,744][119518] Decorrelating experience for 128 frames... [2023-03-09 10:32:31,747][119393] Decorrelating experience for 576 frames... [2023-03-09 10:32:31,749][118949] Heartbeat connected on RolloutWorker_w29 [2023-03-09 10:32:31,752][119499] Decorrelating experience for 768 frames... [2023-03-09 10:32:31,779][119462] Decorrelating experience for 960 frames... [2023-03-09 10:32:31,801][119501] Decorrelating experience for 576 frames... [2023-03-09 10:32:31,804][119464] Decorrelating experience for 576 frames... [2023-03-09 10:32:31,847][125883] Decorrelating experience for 512 frames... [2023-03-09 10:32:31,885][119536] Decorrelating experience for 864 frames... [2023-03-09 10:32:31,889][119937] Decorrelating experience for 736 frames... [2023-03-09 10:32:31,894][119395] Decorrelating experience for 672 frames... [2023-03-09 10:32:31,942][119537] Decorrelating experience for 928 frames... [2023-03-09 10:32:31,948][119506] Decorrelating experience for 704 frames... [2023-03-09 10:32:32,005][119538] Decorrelating experience for 736 frames... [2023-03-09 10:32:32,008][119519] Decorrelating experience for 832 frames... [2023-03-09 10:32:32,051][119542] Decorrelating experience for 800 frames... [2023-03-09 10:32:32,057][118949] Heartbeat connected on RolloutWorker_w122 [2023-03-09 10:32:32,064][120615] Decorrelating experience for 768 frames... [2023-03-09 10:32:32,083][120002] Decorrelating experience for 960 frames... [2023-03-09 10:32:32,085][119515] Decorrelating experience for 768 frames... [2023-03-09 10:32:32,136][119495] Decorrelating experience for 544 frames... [2023-03-09 10:32:32,144][119533] Decorrelating experience for 800 frames... [2023-03-09 10:32:32,165][119524] Decorrelating experience for 256 frames... [2023-03-09 10:32:32,215][119484] Decorrelating experience for 928 frames... [2023-03-09 10:32:32,225][119394] Decorrelating experience for 896 frames... [2023-03-09 10:32:32,247][119509] Decorrelating experience for 768 frames... [2023-03-09 10:32:32,264][119396] Decorrelating experience for 704 frames... [2023-03-09 10:32:32,351][119526] Decorrelating experience for 864 frames... [2023-03-09 10:32:32,363][119498] Decorrelating experience for 672 frames... [2023-03-09 10:32:32,363][119946] Decorrelating experience for 352 frames... [2023-03-09 10:32:32,372][119469] Decorrelating experience for 256 frames... [2023-03-09 10:32:32,385][119544] Decorrelating experience for 704 frames... [2023-03-09 10:32:32,423][119540] Decorrelating experience for 768 frames... [2023-03-09 10:32:32,435][119485] Decorrelating experience for 800 frames... [2023-03-09 10:32:32,516][125883] Decorrelating experience for 544 frames... [2023-03-09 10:32:32,528][119389] Decorrelating experience for 800 frames... [2023-03-09 10:32:32,565][119474] Decorrelating experience for 928 frames... [2023-03-09 10:32:32,571][119483] Decorrelating experience for 736 frames... [2023-03-09 10:32:32,597][119470] Decorrelating experience for 928 frames... [2023-03-09 10:32:32,602][119522] Decorrelating experience for 736 frames... [2023-03-09 10:32:32,631][119520] Decorrelating experience for 448 frames... [2023-03-09 10:32:32,640][119510] Decorrelating experience for 640 frames... [2023-03-09 10:32:32,646][119528] Decorrelating experience for 768 frames... [2023-03-09 10:32:32,694][119489] Another process currently holds the lock /tmp/sf2_rolo/doom_006.lockfile, attempt: 2 [2023-03-09 10:32:32,753][119393] Decorrelating experience for 608 frames... [2023-03-09 10:32:32,753][119521] Decorrelating experience for 640 frames... [2023-03-09 10:32:32,782][119509] Decorrelating experience for 800 frames... [2023-03-09 10:32:32,786][119533] Decorrelating experience for 832 frames... [2023-03-09 10:32:32,787][119469] Decorrelating experience for 288 frames... [2023-03-09 10:32:32,817][119508] Decorrelating experience for 832 frames... [2023-03-09 10:32:32,821][120550] Decorrelating experience for 800 frames... [2023-03-09 10:32:32,842][120004] Decorrelating experience for 416 frames... [2023-03-09 10:32:32,855][119477] Decorrelating experience for 544 frames... [2023-03-09 10:32:32,887][120717] Decorrelating experience for 544 frames... [2023-03-09 10:32:32,955][119530] Decorrelating experience for 416 frames... [2023-03-09 10:32:32,988][119544] Decorrelating experience for 736 frames... [2023-03-09 10:32:32,994][119515] Decorrelating experience for 800 frames... [2023-03-09 10:32:33,023][119484] Decorrelating experience for 960 frames... [2023-03-09 10:32:33,057][119548] Decorrelating experience for 864 frames... [2023-03-09 10:32:33,070][119392] Decorrelating experience for 320 frames... [2023-03-09 10:32:33,070][119497] Decorrelating experience for 224 frames... [2023-03-09 10:32:33,071][119946] Decorrelating experience for 384 frames... [2023-03-09 10:32:33,080][119542] Decorrelating experience for 832 frames... [2023-03-09 10:32:33,091][119808] Decorrelating experience for 960 frames... [2023-03-09 10:32:33,157][120003] Decorrelating experience for 928 frames... [2023-03-09 10:32:33,187][119393] Decorrelating experience for 640 frames... [2023-03-09 10:32:33,219][119483] Decorrelating experience for 768 frames... [2023-03-09 10:32:33,253][119526] Decorrelating experience for 896 frames... [2023-03-09 10:32:33,257][119500] Decorrelating experience for 736 frames... [2023-03-09 10:32:33,272][119477] Decorrelating experience for 576 frames... [2023-03-09 10:32:33,301][119396] Decorrelating experience for 736 frames... [2023-03-09 10:32:33,308][119539] Decorrelating experience for 384 frames... [2023-03-09 10:32:33,309][120005] Decorrelating experience for 576 frames... [2023-03-09 10:32:33,316][119851] Decorrelating experience for 448 frames... [2023-03-09 10:32:33,365][119399] Decorrelating experience for 640 frames... [2023-03-09 10:32:33,385][119501] Decorrelating experience for 608 frames... [2023-03-09 10:32:33,461][119528] Decorrelating experience for 800 frames... [2023-03-09 10:32:33,496][119544] Decorrelating experience for 768 frames... [2023-03-09 10:32:33,504][120550] Decorrelating experience for 832 frames... [2023-03-09 10:32:33,528][119493] Decorrelating experience for 704 frames... [2023-03-09 10:32:33,531][119549] Decorrelating experience for 736 frames... [2023-03-09 10:32:33,532][119470] Decorrelating experience for 960 frames... [2023-03-09 10:32:33,535][119499] Decorrelating experience for 800 frames... [2023-03-09 10:32:33,573][119495] Decorrelating experience for 576 frames... [2023-03-09 10:32:33,582][119614] Decorrelating experience for 384 frames... [2023-03-09 10:32:33,596][119538] Decorrelating experience for 768 frames... [2023-03-09 10:32:33,657][119539] Decorrelating experience for 416 frames... [2023-03-09 10:32:33,712][119513] Decorrelating experience for 928 frames... [2023-03-09 10:32:33,724][120003] Decorrelating experience for 960 frames... [2023-03-09 10:32:33,745][120002] Decorrelating experience for 992 frames... [2023-03-09 10:32:33,746][119533] Decorrelating experience for 864 frames... [2023-03-09 10:32:33,753][119500] Decorrelating experience for 768 frames... [2023-03-09 10:32:33,759][119390] Decorrelating experience for 480 frames... [2023-03-09 10:32:33,782][119483] Decorrelating experience for 800 frames... [2023-03-09 10:32:33,789][120778] Decorrelating experience for 896 frames... [2023-03-09 10:32:33,799][119469] Decorrelating experience for 320 frames... [2023-03-09 10:32:33,859][119521] Decorrelating experience for 672 frames... [2023-03-09 10:32:33,902][118949] Fps is (10 sec: 19660.6, 60 sec: 4096.0, 300 sec: 4096.0). Total num frames: 2000273408. Throughput: 0: 1128.9. Samples: 50800. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 10:32:33,903][118949] Avg episode reward: [(0, '22.479')] [2023-03-09 10:32:33,912][125883] Decorrelating experience for 576 frames... [2023-03-09 10:32:33,944][120005] Decorrelating experience for 608 frames... [2023-03-09 10:32:33,970][120877] Decorrelating experience for 672 frames... [2023-03-09 10:32:33,978][119391] Decorrelating experience for 864 frames... [2023-03-09 10:32:33,981][119486] Decorrelating experience for 384 frames... [2023-03-09 10:32:34,014][119498] Decorrelating experience for 704 frames... [2023-03-09 10:32:34,015][119506] Decorrelating experience for 736 frames... [2023-03-09 10:32:34,017][120073] Decorrelating experience for 800 frames... [2023-03-09 10:32:34,022][119544] Decorrelating experience for 800 frames... [2023-03-09 10:32:34,115][119476] Decorrelating experience for 576 frames... [2023-03-09 10:32:34,149][118949] Heartbeat connected on RolloutWorker_w102 [2023-03-09 10:32:34,151][119808] Decorrelating experience for 992 frames... [2023-03-09 10:32:34,172][119549] Decorrelating experience for 768 frames... [2023-03-09 10:32:34,252][119539] Decorrelating experience for 448 frames... [2023-03-09 10:32:34,260][119469] Decorrelating experience for 352 frames... [2023-03-09 10:32:34,260][119395] Decorrelating experience for 704 frames... [2023-03-09 10:32:34,261][119540] Decorrelating experience for 800 frames... [2023-03-09 10:32:34,261][120199] Decorrelating experience for 640 frames... [2023-03-09 10:32:34,268][119542] Decorrelating experience for 864 frames... [2023-03-09 10:32:34,276][120615] Decorrelating experience for 800 frames... [2023-03-09 10:32:34,331][119470] Decorrelating experience for 992 frames... [2023-03-09 10:32:34,366][119493] Decorrelating experience for 736 frames... [2023-03-09 10:32:34,401][119513] Decorrelating experience for 960 frames... [2023-03-09 10:32:34,465][119500] Decorrelating experience for 800 frames... [2023-03-09 10:32:34,471][119541] Decorrelating experience for 640 frames... [2023-03-09 10:32:34,481][119526] Decorrelating experience for 928 frames... [2023-03-09 10:32:34,512][119464] Decorrelating experience for 608 frames... [2023-03-09 10:32:34,528][119937] Decorrelating experience for 768 frames... [2023-03-09 10:32:34,528][119946] Decorrelating experience for 416 frames... [2023-03-09 10:32:34,556][119533] Decorrelating experience for 896 frames... [2023-03-09 10:32:34,601][119501] Decorrelating experience for 640 frames... [2023-03-09 10:32:34,617][119528] Decorrelating experience for 832 frames... [2023-03-09 10:32:34,628][120003] Decorrelating experience for 992 frames... [2023-03-09 10:32:34,665][118949] Heartbeat connected on RolloutWorker_w119 [2023-03-09 10:32:34,669][119399] Decorrelating experience for 672 frames... [2023-03-09 10:32:34,688][120005] Decorrelating experience for 640 frames... [2023-03-09 10:32:34,716][119506] Decorrelating experience for 768 frames... [2023-03-09 10:32:34,725][119521] Decorrelating experience for 704 frames... [2023-03-09 10:32:34,733][118949] Heartbeat connected on RolloutWorker_w3 [2023-03-09 10:32:34,739][119655] Decorrelating experience for 640 frames... [2023-03-09 10:32:34,762][119537] Decorrelating experience for 960 frames... [2023-03-09 10:32:34,823][119495] Decorrelating experience for 608 frames... [2023-03-09 10:32:34,831][119539] Decorrelating experience for 480 frames... [2023-03-09 10:32:34,881][120199] Decorrelating experience for 672 frames... [2023-03-09 10:32:34,891][120877] Decorrelating experience for 704 frames... [2023-03-09 10:32:34,921][119614] Decorrelating experience for 416 frames... [2023-03-09 10:32:34,946][119505] Decorrelating experience for 320 frames... [2023-03-09 10:32:34,948][119486] Decorrelating experience for 416 frames... [2023-03-09 10:32:34,969][119534] Decorrelating experience for 640 frames... [2023-03-09 10:32:35,025][126685] Another process currently holds the lock /tmp/sf2_rolo/doom_006.lockfile, attempt: 1 [2023-03-09 10:32:35,025][120135] Another process currently holds the lock /tmp/sf2_rolo/doom_006.lockfile, attempt: 1 [2023-03-09 10:32:35,030][125883] Decorrelating experience for 608 frames... [2023-03-09 10:32:35,071][120717] Decorrelating experience for 576 frames... [2023-03-09 10:32:35,096][119395] Decorrelating experience for 736 frames... [2023-03-09 10:32:35,123][119393] Decorrelating experience for 672 frames... [2023-03-09 10:32:35,137][119528] Decorrelating experience for 864 frames... [2023-03-09 10:32:35,158][120615] Decorrelating experience for 832 frames... [2023-03-09 10:32:35,160][119526] Decorrelating experience for 960 frames... [2023-03-09 10:32:35,163][118949] Heartbeat connected on RolloutWorker_w105 [2023-03-09 10:32:35,173][119516] Decorrelating experience for 768 frames... [2023-03-09 10:32:35,179][119464] Decorrelating experience for 640 frames... [2023-03-09 10:32:35,195][119521] Decorrelating experience for 736 frames... [2023-03-09 10:32:35,246][119476] Decorrelating experience for 608 frames... [2023-03-09 10:32:35,300][119390] Decorrelating experience for 512 frames... [2023-03-09 10:32:35,304][119946] Decorrelating experience for 448 frames... [2023-03-09 10:32:35,326][119506] Decorrelating experience for 800 frames... [2023-03-09 10:32:35,380][119495] Decorrelating experience for 640 frames... [2023-03-09 10:32:35,395][120877] Decorrelating experience for 736 frames... [2023-03-09 10:32:35,395][119391] Decorrelating experience for 896 frames... [2023-03-09 10:32:35,396][119479] Decorrelating experience for 384 frames... [2023-03-09 10:32:35,398][119486] Decorrelating experience for 448 frames... [2023-03-09 10:32:35,446][119537] Decorrelating experience for 992 frames... [2023-03-09 10:32:35,500][119533] Decorrelating experience for 928 frames... [2023-03-09 10:32:35,518][119655] Decorrelating experience for 672 frames... [2023-03-09 10:32:35,544][119524] Decorrelating experience for 288 frames... [2023-03-09 10:32:35,571][119851] Decorrelating experience for 480 frames... [2023-03-09 10:32:35,587][119393] Decorrelating experience for 704 frames... [2023-03-09 10:32:35,600][120005] Decorrelating experience for 672 frames... [2023-03-09 10:32:35,627][119525] Decorrelating experience for 800 frames... [2023-03-09 10:32:35,654][119937] Decorrelating experience for 800 frames... [2023-03-09 10:32:35,688][119521] Decorrelating experience for 768 frames... [2023-03-09 10:32:35,691][119469] Decorrelating experience for 384 frames... [2023-03-09 10:32:35,729][120199] Decorrelating experience for 704 frames... [2023-03-09 10:32:35,763][119390] Decorrelating experience for 544 frames... [2023-03-09 10:32:35,778][125883] Decorrelating experience for 640 frames... [2023-03-09 10:32:35,782][119464] Decorrelating experience for 672 frames... [2023-03-09 10:32:35,794][120615] Decorrelating experience for 864 frames... [2023-03-09 10:32:35,825][120004] Decorrelating experience for 448 frames... [2023-03-09 10:32:35,893][120778] Decorrelating experience for 928 frames... [2023-03-09 10:32:35,895][119478] Decorrelating experience for 800 frames... [2023-03-09 10:32:35,898][119526] Decorrelating experience for 992 frames... [2023-03-09 10:32:35,931][119531] Decorrelating experience for 576 frames... [2023-03-09 10:32:35,952][119486] Decorrelating experience for 480 frames... [2023-03-09 10:32:35,972][118949] Heartbeat connected on RolloutWorker_w73 [2023-03-09 10:32:35,984][119504] Another process currently holds the lock /tmp/sf2_rolo/doom_006.lockfile, attempt: 1 [2023-03-09 10:32:35,989][119484] Decorrelating experience for 992 frames... [2023-03-09 10:32:35,990][120040] Decorrelating experience for 512 frames... [2023-03-09 10:32:35,999][119479] Decorrelating experience for 416 frames... [2023-03-09 10:32:36,022][119501] Decorrelating experience for 672 frames... [2023-03-09 10:32:36,030][119490] Decorrelating experience for 928 frames... [2023-03-09 10:32:36,098][119506] Decorrelating experience for 832 frames... [2023-03-09 10:32:36,100][119476] Decorrelating experience for 640 frames... [2023-03-09 10:32:36,125][120005] Decorrelating experience for 704 frames... [2023-03-09 10:32:36,134][119473] Decorrelating experience for 384 frames... [2023-03-09 10:32:36,192][119528] Decorrelating experience for 896 frames... [2023-03-09 10:32:36,207][119391] Decorrelating experience for 928 frames... [2023-03-09 10:32:36,208][119505] Decorrelating experience for 352 frames... [2023-03-09 10:32:36,246][119517] Decorrelating experience for 512 frames... [2023-03-09 10:32:36,246][119521] Decorrelating experience for 800 frames... [2023-03-09 10:32:36,306][118949] Heartbeat connected on RolloutWorker_w66 [2023-03-09 10:32:36,338][119515] Decorrelating experience for 832 frames... [2023-03-09 10:32:36,362][119533] Decorrelating experience for 960 frames... [2023-03-09 10:32:36,370][119464] Decorrelating experience for 704 frames... [2023-03-09 10:32:36,399][119614] Decorrelating experience for 448 frames... [2023-03-09 10:32:36,399][118949] Heartbeat connected on RolloutWorker_w45 [2023-03-09 10:32:36,438][119478] Decorrelating experience for 832 frames... [2023-03-09 10:32:36,440][119513] Decorrelating experience for 992 frames... [2023-03-09 10:32:36,442][119655] Decorrelating experience for 704 frames... [2023-03-09 10:32:36,471][120652] Decorrelating experience for 544 frames... [2023-03-09 10:32:36,479][119473] Decorrelating experience for 416 frames... [2023-03-09 10:32:36,517][119383] Updated weights for policy 0, policy_version 122092 (0.0013) [2023-03-09 10:32:36,534][119546] Decorrelating experience for 800 frames... [2023-03-09 10:32:36,613][119501] Decorrelating experience for 704 frames... [2023-03-09 10:32:36,649][120778] Decorrelating experience for 960 frames... [2023-03-09 10:32:36,652][119530] Decorrelating experience for 448 frames... [2023-03-09 10:32:36,662][119483] Decorrelating experience for 832 frames... [2023-03-09 10:32:36,662][120040] Decorrelating experience for 544 frames... [2023-03-09 10:32:36,667][119499] Decorrelating experience for 832 frames... [2023-03-09 10:32:36,726][120896] Decorrelating experience for 896 frames... [2023-03-09 10:32:36,744][119519] Decorrelating experience for 864 frames... [2023-03-09 10:32:36,839][118949] Heartbeat connected on RolloutWorker_w71 [2023-03-09 10:32:36,847][119525] Decorrelating experience for 832 frames... [2023-03-09 10:32:36,873][119395] Decorrelating experience for 768 frames... [2023-03-09 10:32:36,873][119517] Decorrelating experience for 544 frames... [2023-03-09 10:32:36,886][119807] Decorrelating experience for 928 frames... [2023-03-09 10:32:36,897][119495] Decorrelating experience for 672 frames... [2023-03-09 10:32:36,899][119505] Decorrelating experience for 384 frames... [2023-03-09 10:32:36,952][119474] Decorrelating experience for 960 frames... [2023-03-09 10:32:36,987][119507] Decorrelating experience for 480 frames... [2023-03-09 10:32:37,039][120652] Decorrelating experience for 576 frames... [2023-03-09 10:32:37,081][120877] Decorrelating experience for 768 frames... [2023-03-09 10:32:37,111][119476] Decorrelating experience for 672 frames... [2023-03-09 10:32:37,183][119390] Decorrelating experience for 576 frames... [2023-03-09 10:32:37,200][119534] Decorrelating experience for 672 frames... [2023-03-09 10:32:37,208][119536] Decorrelating experience for 896 frames... [2023-03-09 10:32:37,209][119550] Decorrelating experience for 512 frames... [2023-03-09 10:32:37,211][119530] Decorrelating experience for 480 frames... [2023-03-09 10:32:37,212][119506] Decorrelating experience for 864 frames... [2023-03-09 10:32:37,246][119499] Decorrelating experience for 864 frames... [2023-03-09 10:32:37,261][119505] Decorrelating experience for 416 frames... [2023-03-09 10:32:37,287][119531] Decorrelating experience for 608 frames... [2023-03-09 10:32:37,315][120005] Decorrelating experience for 736 frames... [2023-03-09 10:32:37,405][119508] Decorrelating experience for 864 frames... [2023-03-09 10:32:37,427][120004] Decorrelating experience for 480 frames... [2023-03-09 10:32:37,427][120717] Decorrelating experience for 608 frames... [2023-03-09 10:32:37,433][119478] Decorrelating experience for 864 frames... [2023-03-09 10:32:37,444][119395] Decorrelating experience for 800 frames... [2023-03-09 10:32:37,494][119523] Decorrelating experience for 800 frames... [2023-03-09 10:32:37,527][120135] Decorrelating experience for 608 frames... [2023-03-09 10:32:37,548][119507] Decorrelating experience for 512 frames... [2023-03-09 10:32:37,587][119519] Decorrelating experience for 896 frames... [2023-03-09 10:32:37,626][119549] Decorrelating experience for 800 frames... [2023-03-09 10:32:37,647][119655] Decorrelating experience for 736 frames... [2023-03-09 10:32:37,651][120199] Decorrelating experience for 736 frames... [2023-03-09 10:32:37,703][119483] Decorrelating experience for 864 frames... [2023-03-09 10:32:37,716][119391] Decorrelating experience for 960 frames... [2023-03-09 10:32:37,718][120778] Decorrelating experience for 992 frames... [2023-03-09 10:32:37,726][119476] Decorrelating experience for 704 frames... [2023-03-09 10:32:37,767][119534] Decorrelating experience for 704 frames... [2023-03-09 10:32:37,837][119521] Decorrelating experience for 832 frames... [2023-03-09 10:32:37,853][119499] Decorrelating experience for 896 frames... [2023-03-09 10:32:37,863][119505] Decorrelating experience for 448 frames... [2023-03-09 10:32:37,879][120717] Decorrelating experience for 640 frames... [2023-03-09 10:32:37,899][120073] Decorrelating experience for 832 frames... [2023-03-09 10:32:37,956][120615] Decorrelating experience for 896 frames... [2023-03-09 10:32:37,956][119493] Decorrelating experience for 768 frames... [2023-03-09 10:32:37,957][120005] Decorrelating experience for 768 frames... [2023-03-09 10:32:37,960][119539] Decorrelating experience for 512 frames... [2023-03-09 10:32:37,983][119536] Decorrelating experience for 928 frames... [2023-03-09 10:32:38,053][119472] Decorrelating experience for 800 frames... [2023-03-09 10:32:38,064][119506] Decorrelating experience for 896 frames... [2023-03-09 10:32:38,082][119478] Decorrelating experience for 896 frames... [2023-03-09 10:32:38,154][119548] Decorrelating experience for 896 frames... [2023-03-09 10:32:38,195][118949] Heartbeat connected on RolloutWorker_w121 [2023-03-09 10:32:38,201][119530] Decorrelating experience for 512 frames... [2023-03-09 10:32:38,201][119494] Decorrelating experience for 544 frames... [2023-03-09 10:32:38,202][119549] Decorrelating experience for 832 frames... [2023-03-09 10:32:38,205][120004] Decorrelating experience for 512 frames... [2023-03-09 10:32:38,243][119531] Decorrelating experience for 640 frames... [2023-03-09 10:32:38,277][119501] Decorrelating experience for 736 frames... [2023-03-09 10:32:38,280][119517] Decorrelating experience for 576 frames... [2023-03-09 10:32:38,304][119495] Decorrelating experience for 704 frames... [2023-03-09 10:32:38,345][120717] Decorrelating experience for 672 frames... [2023-03-09 10:32:38,416][119534] Decorrelating experience for 736 frames... [2023-03-09 10:32:38,451][119516] Decorrelating experience for 800 frames... [2023-03-09 10:32:38,455][119399] Decorrelating experience for 704 frames... [2023-03-09 10:32:38,462][119511] Decorrelating experience for 512 frames... [2023-03-09 10:32:38,462][120877] Decorrelating experience for 800 frames... [2023-03-09 10:32:38,486][120005] Decorrelating experience for 800 frames... [2023-03-09 10:32:38,487][119525] Decorrelating experience for 864 frames... [2023-03-09 10:32:38,549][120652] Decorrelating experience for 608 frames... [2023-03-09 10:32:38,624][119505] Decorrelating experience for 480 frames... [2023-03-09 10:32:38,641][119478] Decorrelating experience for 928 frames... [2023-03-09 10:32:38,658][119519] Decorrelating experience for 928 frames... [2023-03-09 10:32:38,699][119512] Another process currently holds the lock /tmp/sf2_rolo/doom_006.lockfile, attempt: 1 [2023-03-09 10:32:38,765][120615] Decorrelating experience for 928 frames... [2023-03-09 10:32:38,774][119477] Decorrelating experience for 608 frames... [2023-03-09 10:32:38,778][119549] Decorrelating experience for 864 frames... [2023-03-09 10:32:38,778][119539] Decorrelating experience for 544 frames... [2023-03-09 10:32:38,779][120263] Decorrelating experience for 576 frames... [2023-03-09 10:32:38,785][119499] Decorrelating experience for 928 frames... [2023-03-09 10:32:38,789][119473] Decorrelating experience for 448 frames... [2023-03-09 10:32:38,866][119529] Decorrelating experience for 256 frames... [2023-03-09 10:32:38,867][120717] Decorrelating experience for 704 frames... [2023-03-09 10:32:38,902][118949] Fps is (10 sec: 32768.3, 60 sec: 7372.8, 300 sec: 6805.7). Total num frames: 2000470016. Throughput: 0: 2385.1. Samples: 107328. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 10:32:38,903][118949] Avg episode reward: [(0, '22.064')] [2023-03-09 10:32:38,921][120199] Decorrelating experience for 768 frames... [2023-03-09 10:32:38,978][119475] Decorrelating experience for 672 frames... [2023-03-09 10:32:38,999][119946] Decorrelating experience for 480 frames... [2023-03-09 10:32:39,009][119395] Decorrelating experience for 832 frames... [2023-03-09 10:32:39,009][119472] Decorrelating experience for 832 frames... [2023-03-09 10:32:39,018][119516] Decorrelating experience for 832 frames... [2023-03-09 10:32:39,033][119521] Decorrelating experience for 864 frames... [2023-03-09 10:32:39,089][119534] Decorrelating experience for 768 frames... [2023-03-09 10:32:39,089][119486] Decorrelating experience for 512 frames... [2023-03-09 10:32:39,173][119495] Decorrelating experience for 736 frames... [2023-03-09 10:32:39,249][119478] Decorrelating experience for 960 frames... [2023-03-09 10:32:39,274][119501] Decorrelating experience for 768 frames... [2023-03-09 10:32:39,274][119399] Decorrelating experience for 736 frames... [2023-03-09 10:32:39,274][119519] Decorrelating experience for 960 frames... [2023-03-09 10:32:39,275][119388] Decorrelating experience for 800 frames... [2023-03-09 10:32:39,281][120073] Decorrelating experience for 864 frames... [2023-03-09 10:32:39,329][120652] Decorrelating experience for 640 frames... [2023-03-09 10:32:39,330][120040] Decorrelating experience for 576 frames... [2023-03-09 10:32:39,424][120653] Another process currently holds the lock /tmp/sf2_rolo/doom_005.lockfile, attempt: 1 [2023-03-09 10:32:39,425][119494] Decorrelating experience for 576 frames... [2023-03-09 10:32:39,475][119523] Decorrelating experience for 832 frames... [2023-03-09 10:32:39,481][119480] Decorrelating experience for 768 frames... [2023-03-09 10:32:39,498][120199] Decorrelating experience for 800 frames... [2023-03-09 10:32:39,524][119515] Decorrelating experience for 864 frames... [2023-03-09 10:32:39,530][119477] Decorrelating experience for 640 frames... [2023-03-09 10:32:39,556][119539] Decorrelating experience for 576 frames... [2023-03-09 10:32:39,560][119383] Updated weights for policy 0, policy_version 122102 (0.0012) [2023-03-09 10:32:39,577][119473] Decorrelating experience for 480 frames... [2023-03-09 10:32:39,699][119521] Decorrelating experience for 896 frames... [2023-03-09 10:32:39,722][119464] Decorrelating experience for 736 frames... [2023-03-09 10:32:39,776][119395] Decorrelating experience for 864 frames... [2023-03-09 10:32:39,776][120040] Decorrelating experience for 608 frames... [2023-03-09 10:32:39,785][119501] Decorrelating experience for 800 frames... [2023-03-09 10:32:39,795][119398] Decorrelating experience for 672 frames... [2023-03-09 10:32:39,809][119505] Decorrelating experience for 512 frames... [2023-03-09 10:32:39,832][119478] Decorrelating experience for 992 frames... [2023-03-09 10:32:39,878][119946] Decorrelating experience for 512 frames... [2023-03-09 10:32:39,974][119516] Decorrelating experience for 864 frames... [2023-03-09 10:32:39,995][119493] Decorrelating experience for 800 frames... [2023-03-09 10:32:40,001][120652] Decorrelating experience for 672 frames... [2023-03-09 10:32:40,017][119475] Decorrelating experience for 704 frames... [2023-03-09 10:32:40,030][119494] Decorrelating experience for 608 frames... [2023-03-09 10:32:40,030][120615] Decorrelating experience for 960 frames... [2023-03-09 10:32:40,035][119529] Decorrelating experience for 288 frames... [2023-03-09 10:32:40,100][119539] Decorrelating experience for 608 frames... [2023-03-09 10:32:40,202][119500] Decorrelating experience for 832 frames... [2023-03-09 10:32:40,227][119391] Decorrelating experience for 992 frames... [2023-03-09 10:32:40,235][119399] Decorrelating experience for 768 frames... [2023-03-09 10:32:40,235][120040] Decorrelating experience for 640 frames... [2023-03-09 10:32:40,235][118949] Heartbeat connected on RolloutWorker_w12 [2023-03-09 10:32:40,238][119477] Decorrelating experience for 672 frames... [2023-03-09 10:32:40,248][120199] Decorrelating experience for 832 frames... [2023-03-09 10:32:40,276][119506] Decorrelating experience for 928 frames... [2023-03-09 10:32:40,303][119501] Decorrelating experience for 832 frames... [2023-03-09 10:32:40,325][119519] Decorrelating experience for 992 frames... [2023-03-09 10:32:40,402][119614] Decorrelating experience for 480 frames... [2023-03-09 10:32:40,424][119394] Decorrelating experience for 928 frames... [2023-03-09 10:32:40,451][119388] Decorrelating experience for 832 frames... [2023-03-09 10:32:40,456][119480] Decorrelating experience for 800 frames... [2023-03-09 10:32:40,472][119494] Decorrelating experience for 640 frames... [2023-03-09 10:32:40,480][119398] Decorrelating experience for 704 frames... [2023-03-09 10:32:40,525][120652] Decorrelating experience for 704 frames... [2023-03-09 10:32:40,556][119505] Decorrelating experience for 544 frames... [2023-03-09 10:32:40,566][120135] Decorrelating experience for 640 frames... [2023-03-09 10:32:40,613][119529] Decorrelating experience for 320 frames... [2023-03-09 10:32:40,632][119538] Decorrelating experience for 800 frames... [2023-03-09 10:32:40,679][119523] Decorrelating experience for 864 frames... [2023-03-09 10:32:40,686][119521] Decorrelating experience for 928 frames... [2023-03-09 10:32:40,701][119475] Decorrelating experience for 736 frames... [2023-03-09 10:32:40,735][119395] Decorrelating experience for 896 frames... [2023-03-09 10:32:40,765][119515] Decorrelating experience for 896 frames... [2023-03-09 10:32:40,810][118949] Heartbeat connected on RolloutWorker_w17 [2023-03-09 10:32:40,817][120073] Decorrelating experience for 896 frames... [2023-03-09 10:32:40,835][119474] Decorrelating experience for 992 frames... [2023-03-09 10:32:40,853][119524] Decorrelating experience for 320 frames... [2023-03-09 10:32:40,903][118949] Heartbeat connected on RolloutWorker_w81 [2023-03-09 10:32:40,907][119491] Decorrelating experience for 864 frames... [2023-03-09 10:32:40,959][119500] Decorrelating experience for 864 frames... [2023-03-09 10:32:40,959][119494] Decorrelating experience for 672 frames... [2023-03-09 10:32:40,971][119399] Decorrelating experience for 800 frames... [2023-03-09 10:32:40,971][120004] Decorrelating experience for 544 frames... [2023-03-09 10:32:40,977][119473] Decorrelating experience for 512 frames... [2023-03-09 10:32:40,994][119388] Decorrelating experience for 864 frames... [2023-03-09 10:32:40,994][120648] Another process currently holds the lock /tmp/sf2_rolo/doom_006.lockfile, attempt: 1 [2023-03-09 10:32:41,028][120005] Decorrelating experience for 832 frames... [2023-03-09 10:32:41,035][119542] Decorrelating experience for 896 frames... [2023-03-09 10:32:41,136][119546] Decorrelating experience for 832 frames... [2023-03-09 10:32:41,168][119493] Decorrelating experience for 832 frames... [2023-03-09 10:32:41,186][119505] Decorrelating experience for 576 frames... [2023-03-09 10:32:41,190][119530] Decorrelating experience for 544 frames... [2023-03-09 10:32:41,205][119529] Decorrelating experience for 352 frames... [2023-03-09 10:32:41,210][119538] Decorrelating experience for 832 frames... [2023-03-09 10:32:41,234][118949] Heartbeat connected on RolloutWorker_w18 [2023-03-09 10:32:41,239][119495] Decorrelating experience for 768 frames... [2023-03-09 10:32:41,260][120040] Decorrelating experience for 672 frames... [2023-03-09 10:32:41,306][119502] Decorrelating experience for 480 frames... [2023-03-09 10:32:41,339][126685] Decorrelating experience for 640 frames... [2023-03-09 10:32:41,405][119473] Decorrelating experience for 544 frames... [2023-03-09 10:32:41,410][119480] Decorrelating experience for 832 frames... [2023-03-09 10:32:41,414][119501] Decorrelating experience for 864 frames... [2023-03-09 10:32:41,420][119477] Decorrelating experience for 704 frames... [2023-03-09 10:32:41,455][120904] Decorrelating experience for 608 frames... [2023-03-09 10:32:41,501][119395] Decorrelating experience for 928 frames... [2023-03-09 10:32:41,501][120199] Decorrelating experience for 864 frames... [2023-03-09 10:32:41,552][120652] Decorrelating experience for 736 frames... [2023-03-09 10:32:41,571][119615] Decorrelating experience for 832 frames... [2023-03-09 10:32:41,634][119523] Decorrelating experience for 896 frames... [2023-03-09 10:32:41,665][119491] Decorrelating experience for 896 frames... [2023-03-09 10:32:41,692][119548] Decorrelating experience for 928 frames... [2023-03-09 10:32:41,698][120073] Decorrelating experience for 928 frames... [2023-03-09 10:32:41,714][119529] Decorrelating experience for 384 frames... [2023-03-09 10:32:41,738][119500] Decorrelating experience for 896 frames... [2023-03-09 10:32:41,759][119499] Decorrelating experience for 960 frames... [2023-03-09 10:32:41,803][119494] Decorrelating experience for 704 frames... [2023-03-09 10:32:41,828][119515] Decorrelating experience for 928 frames... [2023-03-09 10:32:41,833][119473] Decorrelating experience for 576 frames... [2023-03-09 10:32:41,856][126685] Decorrelating experience for 672 frames... [2023-03-09 10:32:41,910][119544] Decorrelating experience for 832 frames... [2023-03-09 10:32:41,911][119546] Decorrelating experience for 864 frames... [2023-03-09 10:32:41,915][119493] Decorrelating experience for 864 frames... [2023-03-09 10:32:41,927][119521] Decorrelating experience for 960 frames... [2023-03-09 10:32:41,936][119479] Decorrelating experience for 448 frames... [2023-03-09 10:32:41,986][120717] Decorrelating experience for 736 frames... [2023-03-09 10:32:42,015][119495] Decorrelating experience for 800 frames... [2023-03-09 10:32:42,055][119538] Decorrelating experience for 864 frames... [2023-03-09 10:32:42,072][119477] Decorrelating experience for 736 frames... [2023-03-09 10:32:42,078][120199] Decorrelating experience for 896 frames... [2023-03-09 10:32:42,173][119480] Decorrelating experience for 864 frames... [2023-03-09 10:32:42,182][119524] Decorrelating experience for 352 frames... [2023-03-09 10:32:42,188][120877] Decorrelating experience for 832 frames... [2023-03-09 10:32:42,207][119539] Decorrelating experience for 640 frames... [2023-03-09 10:32:42,277][120040] Decorrelating experience for 704 frames... [2023-03-09 10:32:42,281][119550] Decorrelating experience for 544 frames... [2023-03-09 10:32:42,296][120550] Decorrelating experience for 864 frames... [2023-03-09 10:32:42,313][119475] Decorrelating experience for 768 frames... [2023-03-09 10:32:42,387][119499] Decorrelating experience for 992 frames... [2023-03-09 10:32:42,387][119395] Decorrelating experience for 960 frames... [2023-03-09 10:32:42,394][126685] Decorrelating experience for 704 frames... [2023-03-09 10:32:42,406][119486] Decorrelating experience for 544 frames... [2023-03-09 10:32:42,418][119615] Decorrelating experience for 864 frames... [2023-03-09 10:32:42,438][119851] Decorrelating experience for 512 frames... [2023-03-09 10:32:42,506][119497] Decorrelating experience for 256 frames... [2023-03-09 10:32:42,529][120263] Decorrelating experience for 608 frames... [2023-03-09 10:32:42,544][119521] Decorrelating experience for 992 frames... [2023-03-09 10:32:42,551][119491] Decorrelating experience for 928 frames... [2023-03-09 10:32:42,605][120717] Decorrelating experience for 768 frames... [2023-03-09 10:32:42,610][119523] Decorrelating experience for 928 frames... [2023-03-09 10:32:42,649][119383] Updated weights for policy 0, policy_version 122112 (0.0013) [2023-03-09 10:32:42,654][119510] Decorrelating experience for 672 frames... [2023-03-09 10:32:42,684][119515] Decorrelating experience for 960 frames... [2023-03-09 10:32:42,684][119399] Decorrelating experience for 832 frames... [2023-03-09 10:32:42,718][119388] Decorrelating experience for 896 frames... [2023-03-09 10:32:42,730][120004] Decorrelating experience for 576 frames... [2023-03-09 10:32:42,738][120615] Decorrelating experience for 992 frames... [2023-03-09 10:32:42,758][120199] Decorrelating experience for 928 frames... [2023-03-09 10:32:42,797][118949] Heartbeat connected on RolloutWorker_w40 [2023-03-09 10:32:42,804][119548] Decorrelating experience for 960 frames... [2023-03-09 10:32:42,864][120652] Decorrelating experience for 768 frames... [2023-03-09 10:32:42,879][119477] Decorrelating experience for 768 frames... [2023-03-09 10:32:42,890][119500] Decorrelating experience for 928 frames... [2023-03-09 10:32:42,930][119483] Decorrelating experience for 896 frames... [2023-03-09 10:32:42,949][119475] Decorrelating experience for 800 frames... [2023-03-09 10:32:42,965][119525] Decorrelating experience for 896 frames... [2023-03-09 10:32:42,975][118949] Heartbeat connected on RolloutWorker_w90 [2023-03-09 10:32:42,977][119542] Decorrelating experience for 928 frames... [2023-03-09 10:32:42,979][120073] Decorrelating experience for 960 frames... [2023-03-09 10:32:43,022][119473] Decorrelating experience for 608 frames... [2023-03-09 10:32:43,092][119480] Decorrelating experience for 896 frames... [2023-03-09 10:32:43,116][119937] Decorrelating experience for 832 frames... [2023-03-09 10:32:43,121][119544] Decorrelating experience for 864 frames... [2023-03-09 10:32:43,155][126685] Decorrelating experience for 736 frames... [2023-03-09 10:32:43,168][118949] Heartbeat connected on RolloutWorker_w117 [2023-03-09 10:32:43,187][120717] Decorrelating experience for 800 frames... [2023-03-09 10:32:43,211][119495] Decorrelating experience for 832 frames... [2023-03-09 10:32:43,214][119494] Decorrelating experience for 736 frames... [2023-03-09 10:32:43,241][119546] Decorrelating experience for 896 frames... [2023-03-09 10:32:43,287][120263] Decorrelating experience for 640 frames... [2023-03-09 10:32:43,302][119523] Decorrelating experience for 960 frames... [2023-03-09 10:32:43,346][119529] Decorrelating experience for 416 frames... [2023-03-09 10:32:43,371][119508] Decorrelating experience for 896 frames... [2023-03-09 10:32:43,411][119398] Decorrelating experience for 736 frames... [2023-03-09 10:32:43,415][119550] Decorrelating experience for 576 frames... [2023-03-09 10:32:43,437][119491] Decorrelating experience for 960 frames... [2023-03-09 10:32:43,450][120004] Decorrelating experience for 608 frames... [2023-03-09 10:32:43,507][119851] Decorrelating experience for 544 frames... [2023-03-09 10:32:43,545][119388] Decorrelating experience for 928 frames... [2023-03-09 10:32:43,555][120040] Decorrelating experience for 736 frames... [2023-03-09 10:32:43,562][119479] Decorrelating experience for 480 frames... [2023-03-09 10:32:43,634][119394] Decorrelating experience for 960 frames... [2023-03-09 10:32:43,635][119472] Decorrelating experience for 864 frames... [2023-03-09 10:32:43,676][119464] Decorrelating experience for 768 frames... [2023-03-09 10:32:43,679][119538] Decorrelating experience for 896 frames... [2023-03-09 10:32:43,745][119473] Decorrelating experience for 640 frames... [2023-03-09 10:32:43,786][120263] Decorrelating experience for 672 frames... [2023-03-09 10:32:43,803][120904] Decorrelating experience for 640 frames... [2023-03-09 10:32:43,804][126685] Decorrelating experience for 768 frames... [2023-03-09 10:32:43,804][119680] Another process currently holds the lock /tmp/sf2_rolo/doom_006.lockfile, attempt: 1 [2023-03-09 10:32:43,805][119542] Decorrelating experience for 960 frames... [2023-03-09 10:32:43,889][119655] Decorrelating experience for 768 frames... [2023-03-09 10:32:43,898][119507] Decorrelating experience for 544 frames... [2023-03-09 10:32:43,902][118949] Fps is (10 sec: 49152.0, 60 sec: 12288.0, 300 sec: 10532.6). Total num frames: 2000764928. Throughput: 0: 4439.5. Samples: 199776. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 10:32:43,903][118949] Avg episode reward: [(0, '33.422')] [2023-03-09 10:32:43,933][120073] Decorrelating experience for 992 frames... [2023-03-09 10:32:43,941][119476] Decorrelating experience for 736 frames... [2023-03-09 10:32:44,017][119495] Decorrelating experience for 864 frames... [2023-03-09 10:32:44,023][119937] Decorrelating experience for 864 frames... [2023-03-09 10:32:44,032][119479] Decorrelating experience for 512 frames... [2023-03-09 10:32:44,050][119502] Decorrelating experience for 512 frames... [2023-03-09 10:32:44,108][119494] Decorrelating experience for 768 frames... [2023-03-09 10:32:44,112][119541] Decorrelating experience for 672 frames... [2023-03-09 10:32:44,189][119498] Decorrelating experience for 736 frames... [2023-03-09 10:32:44,190][119500] Decorrelating experience for 960 frames... [2023-03-09 10:32:44,224][120004] Decorrelating experience for 640 frames... [2023-03-09 10:32:44,240][119394] Decorrelating experience for 992 frames... [2023-03-09 10:32:44,275][120263] Decorrelating experience for 704 frames... [2023-03-09 10:32:44,281][119388] Decorrelating experience for 960 frames... [2023-03-09 10:32:44,329][119539] Decorrelating experience for 672 frames... [2023-03-09 10:32:44,342][119530] Decorrelating experience for 576 frames... [2023-03-09 10:32:44,359][119550] Decorrelating experience for 608 frames... [2023-03-09 10:32:44,418][119655] Decorrelating experience for 800 frames... [2023-03-09 10:32:44,442][119507] Decorrelating experience for 576 frames... [2023-03-09 10:32:44,462][118949] Heartbeat connected on RolloutWorker_w114 [2023-03-09 10:32:44,474][120877] Decorrelating experience for 864 frames... [2023-03-09 10:32:44,479][119502] Decorrelating experience for 544 frames... [2023-03-09 10:32:44,484][119497] Decorrelating experience for 288 frames... [2023-03-09 10:32:44,536][119476] Decorrelating experience for 768 frames... [2023-03-09 10:32:44,542][119524] Decorrelating experience for 384 frames... [2023-03-09 10:32:44,557][119511] Decorrelating experience for 544 frames... [2023-03-09 10:32:44,572][119542] Decorrelating experience for 992 frames... [2023-03-09 10:32:44,606][119541] Decorrelating experience for 704 frames... [2023-03-09 10:32:44,637][119506] Decorrelating experience for 960 frames... [2023-03-09 10:32:44,655][118949] Heartbeat connected on RolloutWorker_w23 [2023-03-09 10:32:44,700][119494] Decorrelating experience for 800 frames... [2023-03-09 10:32:44,701][119483] Decorrelating experience for 928 frames... [2023-03-09 10:32:44,737][120904] Decorrelating experience for 672 frames... [2023-03-09 10:32:44,773][119937] Decorrelating experience for 896 frames... [2023-03-09 10:32:44,809][119500] Decorrelating experience for 992 frames... [2023-03-09 10:32:44,810][120896] Decorrelating experience for 928 frames... [2023-03-09 10:32:44,833][119544] Decorrelating experience for 896 frames... [2023-03-09 10:32:44,861][119475] Decorrelating experience for 832 frames... [2023-03-09 10:32:44,882][119383] Updated weights for policy 0, policy_version 122122 (0.0012) [2023-03-09 10:32:44,892][119504] Decorrelating experience for 544 frames... [2023-03-09 10:32:44,922][119524] Decorrelating experience for 416 frames... [2023-03-09 10:32:44,930][119472] Decorrelating experience for 896 frames... [2023-03-09 10:32:44,935][119530] Decorrelating experience for 608 frames... [2023-03-09 10:32:44,996][118949] Heartbeat connected on RolloutWorker_w64 [2023-03-09 10:32:45,028][119546] Decorrelating experience for 928 frames... [2023-03-09 10:32:45,074][119388] Decorrelating experience for 992 frames... [2023-03-09 10:32:45,095][119522] Decorrelating experience for 768 frames... [2023-03-09 10:32:45,106][119507] Decorrelating experience for 608 frames... [2023-03-09 10:32:45,112][119495] Decorrelating experience for 896 frames... [2023-03-09 10:32:45,149][120263] Decorrelating experience for 736 frames... [2023-03-09 10:32:45,153][119498] Decorrelating experience for 768 frames... [2023-03-09 10:32:45,166][119511] Decorrelating experience for 576 frames... [2023-03-09 10:32:45,166][120004] Decorrelating experience for 672 frames... [2023-03-09 10:32:45,177][119395] Decorrelating experience for 992 frames... [2023-03-09 10:32:45,229][118949] Heartbeat connected on RolloutWorker_w43 [2023-03-09 10:32:45,280][119547] Another process currently holds the lock /tmp/sf2_rolo/doom_006.lockfile, attempt: 3 [2023-03-09 10:32:45,310][119516] Decorrelating experience for 896 frames... [2023-03-09 10:32:45,324][119497] Decorrelating experience for 320 frames... [2023-03-09 10:32:45,325][119539] Decorrelating experience for 704 frames... [2023-03-09 10:32:45,330][119466] Another process currently holds the lock /tmp/sf2_rolo/doom_006.lockfile, attempt: 1 [2023-03-09 10:32:45,368][119655] Decorrelating experience for 832 frames... [2023-03-09 10:32:45,425][119494] Decorrelating experience for 832 frames... [2023-03-09 10:32:45,426][119530] Decorrelating experience for 640 frames... [2023-03-09 10:32:45,426][119508] Decorrelating experience for 928 frames... [2023-03-09 10:32:45,435][119550] Decorrelating experience for 640 frames... [2023-03-09 10:32:45,457][119524] Decorrelating experience for 448 frames... [2023-03-09 10:32:45,524][119398] Decorrelating experience for 768 frames... [2023-03-09 10:32:45,604][119525] Decorrelating experience for 928 frames... [2023-03-09 10:32:45,613][119504] Decorrelating experience for 576 frames... [2023-03-09 10:32:45,660][118949] Heartbeat connected on RolloutWorker_w8 [2023-03-09 10:32:45,665][120904] Decorrelating experience for 704 frames... [2023-03-09 10:32:45,700][119483] Decorrelating experience for 960 frames... [2023-03-09 10:32:45,700][119489] Decorrelating experience for 128 frames... [2023-03-09 10:32:45,701][119472] Decorrelating experience for 928 frames... [2023-03-09 10:32:45,701][119502] Decorrelating experience for 576 frames... [2023-03-09 10:32:45,749][119490] Decorrelating experience for 960 frames... [2023-03-09 10:32:45,769][118949] Heartbeat connected on RolloutWorker_w11 [2023-03-09 10:32:45,816][119546] Decorrelating experience for 960 frames... [2023-03-09 10:32:45,839][119497] Decorrelating experience for 352 frames... [2023-03-09 10:32:45,840][119511] Decorrelating experience for 608 frames... [2023-03-09 10:32:45,891][119506] Decorrelating experience for 992 frames... [2023-03-09 10:32:45,955][119530] Decorrelating experience for 672 frames... [2023-03-09 10:32:45,956][119491] Decorrelating experience for 992 frames... [2023-03-09 10:32:45,956][119479] Decorrelating experience for 544 frames... [2023-03-09 10:32:45,957][120263] Decorrelating experience for 768 frames... [2023-03-09 10:32:45,980][119549] Decorrelating experience for 896 frames... [2023-03-09 10:32:45,980][119937] Decorrelating experience for 928 frames... [2023-03-09 10:32:46,034][119550] Decorrelating experience for 672 frames... [2023-03-09 10:32:46,059][119505] Decorrelating experience for 608 frames... [2023-03-09 10:32:46,115][119240] Signal inference workers to stop experience collection... [2023-03-09 10:32:46,123][119543] Another process currently holds the lock /tmp/sf2_rolo/doom_005.lockfile, attempt: 1 [2023-03-09 10:32:46,131][119475] Decorrelating experience for 864 frames... [2023-03-09 10:32:46,136][119240] Signal inference workers to resume experience collection... [2023-03-09 10:32:46,156][119383] InferenceWorker_p0-w0: stopping experience collection [2023-03-09 10:32:46,179][119383] InferenceWorker_p0-w0: resuming experience collection [2023-03-09 10:32:46,194][119473] Decorrelating experience for 672 frames... [2023-03-09 10:32:46,207][119541] Decorrelating experience for 736 frames... [2023-03-09 10:32:46,217][120717] Decorrelating experience for 832 frames... [2023-03-09 10:32:46,224][119502] Decorrelating experience for 608 frames... [2023-03-09 10:32:46,261][119522] Decorrelating experience for 800 frames... [2023-03-09 10:32:46,271][119524] Decorrelating experience for 480 frames... [2023-03-09 10:32:46,291][119655] Decorrelating experience for 864 frames... [2023-03-09 10:32:46,316][118949] Heartbeat connected on RolloutWorker_w62 [2023-03-09 10:32:46,328][119511] Decorrelating experience for 640 frames... [2023-03-09 10:32:46,384][119498] Decorrelating experience for 800 frames... [2023-03-09 10:32:46,392][118949] Heartbeat connected on RolloutWorker_w25 [2023-03-09 10:32:46,411][119392] Decorrelating experience for 352 frames... [2023-03-09 10:32:46,479][119383] Updated weights for policy 0, policy_version 122132 (0.0010) [2023-03-09 10:32:46,493][120896] Decorrelating experience for 960 frames... [2023-03-09 10:32:46,524][119495] Decorrelating experience for 928 frames... [2023-03-09 10:32:46,548][119481] Another process currently holds the lock /tmp/sf2_rolo/doom_006.lockfile, attempt: 1 [2023-03-09 10:32:46,579][119464] Decorrelating experience for 800 frames... [2023-03-09 10:32:46,596][119507] Decorrelating experience for 640 frames... [2023-03-09 10:32:46,597][119504] Decorrelating experience for 608 frames... [2023-03-09 10:32:46,601][119505] Decorrelating experience for 640 frames... [2023-03-09 10:32:46,629][119472] Decorrelating experience for 960 frames... [2023-03-09 10:32:46,640][119550] Decorrelating experience for 704 frames... [2023-03-09 10:32:46,645][126685] Decorrelating experience for 800 frames... [2023-03-09 10:32:46,749][119485] Decorrelating experience for 832 frames... [2023-03-09 10:32:46,809][119399] Decorrelating experience for 864 frames... [2023-03-09 10:32:46,824][119515] Decorrelating experience for 992 frames... [2023-03-09 10:32:46,827][119538] Decorrelating experience for 928 frames... [2023-03-09 10:32:46,865][119483] Decorrelating experience for 992 frames... [2023-03-09 10:32:46,893][119497] Decorrelating experience for 384 frames... [2023-03-09 10:32:46,893][119525] Decorrelating experience for 960 frames... [2023-03-09 10:32:46,909][119655] Decorrelating experience for 896 frames... [2023-03-09 10:32:46,910][119546] Decorrelating experience for 992 frames... [2023-03-09 10:32:46,910][119524] Decorrelating experience for 512 frames... [2023-03-09 10:32:47,017][119807] Decorrelating experience for 960 frames... [2023-03-09 10:32:47,066][120652] Decorrelating experience for 800 frames... [2023-03-09 10:32:47,106][119937] Decorrelating experience for 960 frames... [2023-03-09 10:32:47,126][119545] Decorrelating experience for 416 frames... [2023-03-09 10:32:47,130][120717] Decorrelating experience for 864 frames... [2023-03-09 10:32:47,160][119490] Decorrelating experience for 992 frames... [2023-03-09 10:32:47,160][119511] Decorrelating experience for 672 frames... [2023-03-09 10:32:47,170][119473] Decorrelating experience for 704 frames... [2023-03-09 10:32:47,181][119541] Decorrelating experience for 768 frames... [2023-03-09 10:32:47,276][120904] Decorrelating experience for 736 frames... [2023-03-09 10:32:47,309][119464] Decorrelating experience for 832 frames... [2023-03-09 10:32:47,312][118949] Heartbeat connected on RolloutWorker_w36 [2023-03-09 10:32:47,346][118949] Heartbeat connected on RolloutWorker_w92 [2023-03-09 10:32:47,368][120005] Decorrelating experience for 864 frames... [2023-03-09 10:32:47,379][119475] Decorrelating experience for 896 frames... [2023-03-09 10:32:47,387][118949] Heartbeat connected on RolloutWorker_w89 [2023-03-09 10:32:47,396][119487] Another process currently holds the lock /tmp/sf2_rolo/doom_006.lockfile, attempt: 1 [2023-03-09 10:32:47,398][119489] Decorrelating experience for 160 frames... [2023-03-09 10:32:47,423][119392] Decorrelating experience for 384 frames... [2023-03-09 10:32:47,440][119497] Decorrelating experience for 416 frames... [2023-03-09 10:32:47,450][119517] Decorrelating experience for 608 frames... [2023-03-09 10:32:47,456][119522] Decorrelating experience for 832 frames... [2023-03-09 10:32:47,472][119524] Decorrelating experience for 544 frames... [2023-03-09 10:32:47,515][119549] Decorrelating experience for 928 frames... [2023-03-09 10:32:47,605][118949] Heartbeat connected on RolloutWorker_w19 [2023-03-09 10:32:47,629][119529] Decorrelating experience for 448 frames... [2023-03-09 10:32:47,657][119505] Decorrelating experience for 672 frames... [2023-03-09 10:32:47,669][119485] Decorrelating experience for 864 frames... [2023-03-09 10:32:47,711][119525] Decorrelating experience for 992 frames... [2023-03-09 10:32:47,712][119545] Decorrelating experience for 448 frames... [2023-03-09 10:32:47,735][119538] Decorrelating experience for 960 frames... [2023-03-09 10:32:47,737][119534] Decorrelating experience for 800 frames... [2023-03-09 10:32:47,738][119504] Decorrelating experience for 640 frames... [2023-03-09 10:32:47,743][119518] Decorrelating experience for 160 frames... [2023-03-09 10:32:47,854][119514] Another process currently holds the lock /tmp/sf2_rolo/doom_006.lockfile, attempt: 2 [2023-03-09 10:32:47,915][119473] Decorrelating experience for 736 frames... [2023-03-09 10:32:47,925][119615] Decorrelating experience for 896 frames... [2023-03-09 10:32:47,954][119507] Decorrelating experience for 672 frames... [2023-03-09 10:32:47,970][120652] Decorrelating experience for 832 frames... [2023-03-09 10:32:47,982][119508] Decorrelating experience for 960 frames... [2023-03-09 10:32:47,995][119655] Decorrelating experience for 928 frames... [2023-03-09 10:32:47,996][119472] Decorrelating experience for 992 frames... [2023-03-09 10:32:48,008][120904] Decorrelating experience for 768 frames... [2023-03-09 10:32:48,025][119533] Decorrelating experience for 992 frames... [2023-03-09 10:32:48,060][119392] Decorrelating experience for 416 frames... [2023-03-09 10:32:48,092][119383] Updated weights for policy 0, policy_version 122142 (0.0012) [2023-03-09 10:32:48,113][119488] Another process currently holds the lock /tmp/sf2_rolo/doom_006.lockfile, attempt: 1 [2023-03-09 10:32:48,163][119550] Decorrelating experience for 736 frames... [2023-03-09 10:32:48,171][119496] Another process currently holds the lock /tmp/sf2_rolo/doom_006.lockfile, attempt: 1 [2023-03-09 10:32:48,203][119489] Decorrelating experience for 192 frames... [2023-03-09 10:32:48,217][119549] Decorrelating experience for 960 frames... [2023-03-09 10:32:48,269][120005] Decorrelating experience for 896 frames... [2023-03-09 10:32:48,269][119479] Decorrelating experience for 576 frames... [2023-03-09 10:32:48,273][119517] Decorrelating experience for 640 frames... [2023-03-09 10:32:48,281][120896] Decorrelating experience for 992 frames... [2023-03-09 10:32:48,281][119475] Decorrelating experience for 928 frames... [2023-03-09 10:32:48,298][119476] Decorrelating experience for 800 frames... [2023-03-09 10:32:48,305][119497] Decorrelating experience for 448 frames... [2023-03-09 10:32:48,306][118949] Heartbeat connected on RolloutWorker_w78 [2023-03-09 10:32:48,441][119518] Decorrelating experience for 192 frames... [2023-03-09 10:32:48,441][118949] Heartbeat connected on RolloutWorker_w6 [2023-03-09 10:32:48,474][119504] Decorrelating experience for 672 frames... [2023-03-09 10:32:48,512][119529] Decorrelating experience for 480 frames... [2023-03-09 10:32:48,523][119511] Decorrelating experience for 704 frames... [2023-03-09 10:32:48,531][120040] Decorrelating experience for 768 frames... [2023-03-09 10:32:48,561][120648] Decorrelating experience for 736 frames... [2023-03-09 10:32:48,582][118949] Heartbeat connected on RolloutWorker_w55 [2023-03-09 10:32:48,591][119495] Decorrelating experience for 960 frames... [2023-03-09 10:32:48,595][119541] Decorrelating experience for 800 frames... [2023-03-09 10:32:48,624][119655] Decorrelating experience for 960 frames... [2023-03-09 10:32:48,692][119508] Decorrelating experience for 992 frames... [2023-03-09 10:32:48,767][119392] Decorrelating experience for 448 frames... [2023-03-09 10:32:48,768][120904] Decorrelating experience for 800 frames... [2023-03-09 10:32:48,784][119510] Decorrelating experience for 704 frames... [2023-03-09 10:32:48,798][119614] Decorrelating experience for 512 frames... [2023-03-09 10:32:48,798][119530] Decorrelating experience for 704 frames... [2023-03-09 10:32:48,823][119498] Decorrelating experience for 832 frames... [2023-03-09 10:32:48,827][119497] Decorrelating experience for 480 frames... [2023-03-09 10:32:48,857][119505] Decorrelating experience for 704 frames... [2023-03-09 10:32:48,858][119479] Decorrelating experience for 608 frames... [2023-03-09 10:32:48,863][118949] Heartbeat connected on RolloutWorker_w127 [2023-03-09 10:32:48,902][118949] Fps is (10 sec: 81919.1, 60 sec: 21026.1, 300 sec: 16820.9). Total num frames: 2001289216. Throughput: 0: 6053.3. Samples: 272400. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 10:32:48,903][118949] Avg episode reward: [(0, '31.233')] [2023-03-09 10:32:48,942][120005] Decorrelating experience for 928 frames... [2023-03-09 10:32:49,034][119477] Decorrelating experience for 800 frames... [2023-03-09 10:32:49,043][119494] Decorrelating experience for 864 frames... [2023-03-09 10:32:49,061][119615] Decorrelating experience for 928 frames... [2023-03-09 10:32:49,134][120040] Decorrelating experience for 800 frames... [2023-03-09 10:32:49,139][120652] Decorrelating experience for 864 frames... [2023-03-09 10:32:49,139][119807] Decorrelating experience for 992 frames... [2023-03-09 10:32:49,139][118949] Heartbeat connected on RolloutWorker_w68 [2023-03-09 10:32:49,147][119507] Decorrelating experience for 704 frames... [2023-03-09 10:32:49,151][119517] Decorrelating experience for 672 frames... [2023-03-09 10:32:49,272][119495] Decorrelating experience for 992 frames... [2023-03-09 10:32:49,300][119518] Decorrelating experience for 224 frames... [2023-03-09 10:32:49,329][119510] Decorrelating experience for 736 frames... [2023-03-09 10:32:49,336][119497] Decorrelating experience for 512 frames... [2023-03-09 10:32:49,353][119522] Decorrelating experience for 864 frames... [2023-03-09 10:32:49,395][119541] Decorrelating experience for 832 frames... [2023-03-09 10:32:49,396][119479] Decorrelating experience for 640 frames... [2023-03-09 10:32:49,396][119655] Decorrelating experience for 992 frames... [2023-03-09 10:32:49,406][119383] Updated weights for policy 0, policy_version 122152 (0.0012) [2023-03-09 10:32:49,549][119511] Decorrelating experience for 736 frames... [2023-03-09 10:32:49,556][119486] Decorrelating experience for 576 frames... [2023-03-09 10:32:49,656][119518] Decorrelating experience for 256 frames... [2023-03-09 10:32:49,657][120904] Decorrelating experience for 832 frames... [2023-03-09 10:32:49,657][119498] Decorrelating experience for 864 frames... [2023-03-09 10:32:49,663][119494] Decorrelating experience for 896 frames... [2023-03-09 10:32:49,701][118949] Heartbeat connected on RolloutWorker_w34 [2023-03-09 10:32:49,712][119469] Decorrelating experience for 416 frames... [2023-03-09 10:32:49,713][119534] Decorrelating experience for 832 frames... [2023-03-09 10:32:49,725][118949] Heartbeat connected on RolloutWorker_w116 [2023-03-09 10:32:49,799][119505] Decorrelating experience for 736 frames... [2023-03-09 10:32:49,805][119477] Decorrelating experience for 832 frames... [2023-03-09 10:32:49,835][118949] Heartbeat connected on RolloutWorker_w110 [2023-03-09 10:32:49,842][119507] Decorrelating experience for 736 frames... [2023-03-09 10:32:49,899][119530] Decorrelating experience for 736 frames... [2023-03-09 10:32:49,914][120040] Decorrelating experience for 832 frames... [2023-03-09 10:32:49,954][119497] Decorrelating experience for 544 frames... [2023-03-09 10:32:49,956][119475] Decorrelating experience for 960 frames... [2023-03-09 10:32:49,964][120717] Decorrelating experience for 896 frames... [2023-03-09 10:32:50,046][119937] Decorrelating experience for 992 frames... [2023-03-09 10:32:50,065][119518] Decorrelating experience for 288 frames... [2023-03-09 10:32:50,072][120005] Decorrelating experience for 960 frames... [2023-03-09 10:32:50,137][119476] Decorrelating experience for 832 frames... [2023-03-09 10:32:50,264][119615] Decorrelating experience for 960 frames... [2023-03-09 10:32:50,305][119464] Decorrelating experience for 864 frames... [2023-03-09 10:32:50,316][120004] Decorrelating experience for 704 frames... [2023-03-09 10:32:50,330][119541] Decorrelating experience for 864 frames... [2023-03-09 10:32:50,396][126685] Decorrelating experience for 832 frames... [2023-03-09 10:32:50,397][119522] Decorrelating experience for 896 frames... [2023-03-09 10:32:50,407][119469] Decorrelating experience for 448 frames... [2023-03-09 10:32:50,465][119383] Updated weights for policy 0, policy_version 122162 (0.0011) [2023-03-09 10:32:50,497][119510] Decorrelating experience for 768 frames... [2023-03-09 10:32:50,566][119529] Decorrelating experience for 512 frames... [2023-03-09 10:32:50,585][119497] Decorrelating experience for 576 frames... [2023-03-09 10:32:50,655][120717] Decorrelating experience for 928 frames... [2023-03-09 10:32:50,657][119507] Decorrelating experience for 768 frames... [2023-03-09 10:32:50,676][119479] Decorrelating experience for 672 frames... [2023-03-09 10:32:50,677][120040] Decorrelating experience for 864 frames... [2023-03-09 10:32:50,679][119481] Decorrelating experience for 800 frames... [2023-03-09 10:32:50,685][118949] Heartbeat connected on RolloutWorker_w93 [2023-03-09 10:32:50,747][120648] Decorrelating experience for 768 frames... [2023-03-09 10:32:50,824][119486] Decorrelating experience for 608 frames... [2023-03-09 10:32:50,912][119534] Decorrelating experience for 864 frames... [2023-03-09 10:32:51,043][119476] Decorrelating experience for 864 frames... [2023-03-09 10:32:51,062][119524] Decorrelating experience for 576 frames... [2023-03-09 10:32:51,063][120004] Decorrelating experience for 736 frames... [2023-03-09 10:32:51,063][119399] Decorrelating experience for 896 frames... [2023-03-09 10:32:51,066][126685] Decorrelating experience for 864 frames... [2023-03-09 10:32:51,067][119529] Decorrelating experience for 544 frames... [2023-03-09 10:32:51,072][119477] Decorrelating experience for 864 frames... [2023-03-09 10:32:51,298][119510] Decorrelating experience for 800 frames... [2023-03-09 10:32:51,313][120652] Decorrelating experience for 896 frames... [2023-03-09 10:32:51,314][120040] Decorrelating experience for 896 frames... [2023-03-09 10:32:51,322][120717] Decorrelating experience for 960 frames... [2023-03-09 10:32:51,372][119383] Updated weights for policy 0, policy_version 122172 (0.0012) [2023-03-09 10:32:51,397][121015] Another process currently holds the lock /tmp/sf2_rolo/doom_006.lockfile, attempt: 1 [2023-03-09 10:32:51,398][119614] Decorrelating experience for 544 frames... [2023-03-09 10:32:51,399][119522] Decorrelating experience for 928 frames... [2023-03-09 10:32:51,407][119615] Decorrelating experience for 992 frames... [2023-03-09 10:32:51,555][119529] Decorrelating experience for 576 frames... [2023-03-09 10:32:51,580][120005] Decorrelating experience for 992 frames... [2023-03-09 10:32:51,634][119547] Decorrelating experience for 128 frames... [2023-03-09 10:32:51,660][120648] Decorrelating experience for 800 frames... [2023-03-09 10:32:51,693][126685] Decorrelating experience for 896 frames... [2023-03-09 10:32:51,714][119543] Decorrelating experience for 960 frames... [2023-03-09 10:32:51,729][119486] Decorrelating experience for 640 frames... [2023-03-09 10:32:51,805][119541] Decorrelating experience for 896 frames... [2023-03-09 10:32:51,871][120263] Decorrelating experience for 800 frames... [2023-03-09 10:32:51,904][119498] Decorrelating experience for 896 frames... [2023-03-09 10:32:51,968][120652] Decorrelating experience for 928 frames... [2023-03-09 10:32:51,980][119399] Decorrelating experience for 928 frames... [2023-03-09 10:32:51,981][120040] Decorrelating experience for 928 frames... [2023-03-09 10:32:52,006][119524] Decorrelating experience for 608 frames... [2023-03-09 10:32:52,011][120717] Decorrelating experience for 992 frames... [2023-03-09 10:32:52,040][118949] Heartbeat connected on RolloutWorker_w108 [2023-03-09 10:32:52,051][118949] Heartbeat connected on RolloutWorker_w107 [2023-03-09 10:32:52,075][119518] Decorrelating experience for 320 frames... [2023-03-09 10:32:52,087][119464] Decorrelating experience for 896 frames... [2023-03-09 10:32:52,107][119473] Decorrelating experience for 768 frames... [2023-03-09 10:32:52,213][119510] Decorrelating experience for 832 frames... [2023-03-09 10:32:52,242][119477] Decorrelating experience for 896 frames... [2023-03-09 10:32:52,270][119476] Decorrelating experience for 896 frames... [2023-03-09 10:32:52,304][119383] Updated weights for policy 0, policy_version 122182 (0.0011) [2023-03-09 10:32:52,304][119462] Another process currently holds the lock /tmp/sf2_rolo/doom_005.lockfile, attempt: 1 [2023-03-09 10:32:52,343][120550] Decorrelating experience for 896 frames... [2023-03-09 10:32:52,415][119507] Decorrelating experience for 800 frames... [2023-03-09 10:32:52,464][119486] Decorrelating experience for 672 frames... [2023-03-09 10:32:52,478][119398] Decorrelating experience for 800 frames... [2023-03-09 10:32:52,479][119541] Decorrelating experience for 928 frames... [2023-03-09 10:32:52,486][119497] Decorrelating experience for 608 frames... [2023-03-09 10:32:52,491][118949] Heartbeat connected on RolloutWorker_w106 [2023-03-09 10:32:52,514][119518] Decorrelating experience for 352 frames... [2023-03-09 10:32:52,638][119399] Decorrelating experience for 960 frames... [2023-03-09 10:32:52,662][120040] Decorrelating experience for 960 frames... [2023-03-09 10:32:52,666][119550] Decorrelating experience for 768 frames... [2023-03-09 10:32:52,725][119529] Decorrelating experience for 608 frames... [2023-03-09 10:32:52,795][120648] Decorrelating experience for 832 frames... [2023-03-09 10:32:52,825][120263] Decorrelating experience for 832 frames... [2023-03-09 10:32:52,829][119481] Decorrelating experience for 832 frames... [2023-03-09 10:32:52,853][119520] Another process currently holds the lock /tmp/sf2_rolo/doom_006.lockfile, attempt: 1 [2023-03-09 10:32:52,903][119473] Decorrelating experience for 800 frames... [2023-03-09 10:32:52,957][119464] Decorrelating experience for 928 frames... [2023-03-09 10:32:52,958][119389] Another process currently holds the lock /tmp/sf2_rolo/doom_006.lockfile, attempt: 1 [2023-03-09 10:32:52,978][119475] Decorrelating experience for 992 frames... [2023-03-09 10:32:52,997][119396] Decorrelating experience for 768 frames... [2023-03-09 10:32:53,055][119511] Decorrelating experience for 768 frames... [2023-03-09 10:32:53,105][119498] Decorrelating experience for 928 frames... [2023-03-09 10:32:53,124][119509] Another process currently holds the lock /tmp/sf2_rolo/doom_006.lockfile, attempt: 1 [2023-03-09 10:32:53,160][119383] Updated weights for policy 0, policy_version 122192 (0.0011) [2023-03-09 10:32:53,182][120550] Decorrelating experience for 928 frames... [2023-03-09 10:32:53,232][119494] Decorrelating experience for 928 frames... [2023-03-09 10:32:53,279][125883] Decorrelating experience for 672 frames... [2023-03-09 10:32:53,365][119477] Decorrelating experience for 928 frames... [2023-03-09 10:32:53,390][119550] Decorrelating experience for 800 frames... [2023-03-09 10:32:53,401][119543] Decorrelating experience for 992 frames... [2023-03-09 10:32:53,424][118949] Heartbeat connected on RolloutWorker_w24 [2023-03-09 10:32:53,432][119529] Decorrelating experience for 640 frames... [2023-03-09 10:32:53,510][119502] Decorrelating experience for 640 frames... [2023-03-09 10:32:53,520][119504] Decorrelating experience for 704 frames... [2023-03-09 10:32:53,544][120263] Decorrelating experience for 864 frames... [2023-03-09 10:32:53,574][119481] Decorrelating experience for 864 frames... [2023-03-09 10:32:53,594][119505] Decorrelating experience for 768 frames... [2023-03-09 10:32:53,726][119476] Decorrelating experience for 928 frames... [2023-03-09 10:32:53,727][119396] Decorrelating experience for 800 frames... [2023-03-09 10:32:53,786][119511] Decorrelating experience for 800 frames... [2023-03-09 10:32:53,817][119531] Decorrelating experience for 672 frames... [2023-03-09 10:32:53,817][119538] Decorrelating experience for 992 frames... [2023-03-09 10:32:53,833][120550] Decorrelating experience for 960 frames... [2023-03-09 10:32:53,874][119494] Decorrelating experience for 960 frames... [2023-03-09 10:32:53,902][118949] Fps is (10 sec: 135986.5, 60 sec: 34952.5, 300 sec: 26214.4). Total num frames: 2002124800. Throughput: 0: 11237.3. Samples: 505680. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 10:32:53,903][118949] Avg episode reward: [(0, '48.867')] [2023-03-09 10:32:53,913][119486] Decorrelating experience for 704 frames... [2023-03-09 10:32:54,000][118949] Heartbeat connected on RolloutWorker_w67 [2023-03-09 10:32:54,046][125883] Decorrelating experience for 704 frames... [2023-03-09 10:32:54,051][119473] Decorrelating experience for 832 frames... [2023-03-09 10:32:54,120][119383] Updated weights for policy 0, policy_version 122202 (0.0020) [2023-03-09 10:32:54,141][119469] Decorrelating experience for 480 frames... [2023-03-09 10:32:54,142][119462] Decorrelating experience for 992 frames... [2023-03-09 10:32:54,194][119498] Decorrelating experience for 960 frames... [2023-03-09 10:32:54,238][119547] Decorrelating experience for 160 frames... [2023-03-09 10:32:54,292][119477] Decorrelating experience for 960 frames... [2023-03-09 10:32:54,372][119530] Decorrelating experience for 768 frames... [2023-03-09 10:32:54,398][119511] Decorrelating experience for 832 frames... [2023-03-09 10:32:54,441][118949] Heartbeat connected on RolloutWorker_w85 [2023-03-09 10:32:54,474][119548] Decorrelating experience for 992 frames... [2023-03-09 10:32:54,572][120550] Decorrelating experience for 992 frames... [2023-03-09 10:32:54,573][119531] Decorrelating experience for 704 frames... [2023-03-09 10:32:54,573][120648] Decorrelating experience for 864 frames... [2023-03-09 10:32:54,579][119505] Decorrelating experience for 800 frames... [2023-03-09 10:32:54,650][119547] Decorrelating experience for 192 frames... [2023-03-09 10:32:54,671][119486] Decorrelating experience for 736 frames... [2023-03-09 10:32:54,685][119540] Decorrelating experience for 832 frames... [2023-03-09 10:32:54,755][118949] Heartbeat connected on RolloutWorker_w38 [2023-03-09 10:32:54,778][119480] Decorrelating experience for 928 frames... [2023-03-09 10:32:54,817][119473] Decorrelating experience for 864 frames... [2023-03-09 10:32:54,856][119476] Decorrelating experience for 960 frames... [2023-03-09 10:32:54,881][125883] Decorrelating experience for 736 frames... [2023-03-09 10:32:54,909][119493] Decorrelating experience for 896 frames... [2023-03-09 10:32:54,932][119383] Updated weights for policy 0, policy_version 122212 (0.0013) [2023-03-09 10:32:54,942][119530] Decorrelating experience for 800 frames... [2023-03-09 10:32:55,035][119549] Decorrelating experience for 992 frames... [2023-03-09 10:32:55,079][118949] Heartbeat connected on RolloutWorker_w58 [2023-03-09 10:32:55,143][119469] Decorrelating experience for 512 frames... [2023-03-09 10:32:55,165][119497] Decorrelating experience for 640 frames... [2023-03-09 10:32:55,179][119550] Decorrelating experience for 832 frames... [2023-03-09 10:32:55,184][119505] Decorrelating experience for 832 frames... [2023-03-09 10:32:55,211][119477] Decorrelating experience for 992 frames... [2023-03-09 10:32:55,230][118949] Heartbeat connected on RolloutWorker_w94 [2023-03-09 10:32:55,312][119531] Decorrelating experience for 736 frames... [2023-03-09 10:32:55,353][119541] Decorrelating experience for 960 frames... [2023-03-09 10:32:55,434][119529] Decorrelating experience for 672 frames... [2023-03-09 10:32:55,442][119539] Decorrelating experience for 736 frames... [2023-03-09 10:32:55,478][119486] Decorrelating experience for 768 frames... [2023-03-09 10:32:55,512][118949] Heartbeat connected on RolloutWorker_w101 [2023-03-09 10:32:55,565][119530] Decorrelating experience for 832 frames... [2023-03-09 10:32:55,574][119493] Decorrelating experience for 928 frames... [2023-03-09 10:32:55,681][120877] Decorrelating experience for 896 frames... [2023-03-09 10:32:55,680][118949] Heartbeat connected on RolloutWorker_w33 [2023-03-09 10:32:55,688][125883] Decorrelating experience for 768 frames... [2023-03-09 10:32:55,767][119383] Updated weights for policy 0, policy_version 122222 (0.0010) [2023-03-09 10:32:55,770][119514] Decorrelating experience for 448 frames... [2023-03-09 10:32:55,770][119504] Decorrelating experience for 736 frames... [2023-03-09 10:32:55,802][119476] Decorrelating experience for 992 frames... [2023-03-09 10:32:55,813][119540] Decorrelating experience for 864 frames... [2023-03-09 10:32:55,825][119505] Decorrelating experience for 864 frames... [2023-03-09 10:32:55,883][119393] Another process currently holds the lock /tmp/sf2_rolo/doom_005.lockfile, attempt: 1 [2023-03-09 10:32:55,924][119536] Decorrelating experience for 960 frames... [2023-03-09 10:32:56,018][119529] Decorrelating experience for 704 frames... [2023-03-09 10:32:56,120][119469] Decorrelating experience for 544 frames... [2023-03-09 10:32:56,140][119497] Decorrelating experience for 672 frames... [2023-03-09 10:32:56,141][119531] Decorrelating experience for 768 frames... [2023-03-09 10:32:56,141][119464] Decorrelating experience for 960 frames... [2023-03-09 10:32:56,169][120653] Decorrelating experience for 384 frames... [2023-03-09 10:32:56,182][119480] Decorrelating experience for 960 frames... [2023-03-09 10:32:56,243][119541] Decorrelating experience for 992 frames... [2023-03-09 10:32:56,335][119514] Decorrelating experience for 480 frames... [2023-03-09 10:32:56,354][126685] Decorrelating experience for 928 frames... [2023-03-09 10:32:56,406][118949] Heartbeat connected on RolloutWorker_w21 [2023-03-09 10:32:56,435][119393] Decorrelating experience for 736 frames... [2023-03-09 10:32:56,462][125883] Decorrelating experience for 800 frames... [2023-03-09 10:32:56,462][120652] Decorrelating experience for 960 frames... [2023-03-09 10:32:56,472][119505] Decorrelating experience for 896 frames... [2023-03-09 10:32:56,475][119530] Decorrelating experience for 864 frames... [2023-03-09 10:32:56,500][120877] Decorrelating experience for 928 frames... [2023-03-09 10:32:56,551][119486] Decorrelating experience for 800 frames... [2023-03-09 10:32:56,564][119528] Another process currently holds the lock /tmp/sf2_rolo/doom_006.lockfile, attempt: 1 [2023-03-09 10:32:56,570][120653] Decorrelating experience for 416 frames... [2023-03-09 10:32:56,659][119523] Decorrelating experience for 992 frames... [2023-03-09 10:32:56,672][119469] Decorrelating experience for 576 frames... [2023-03-09 10:32:56,715][119481] Decorrelating experience for 896 frames... [2023-03-09 10:32:56,752][119522] Decorrelating experience for 960 frames... [2023-03-09 10:32:56,774][119504] Decorrelating experience for 768 frames... [2023-03-09 10:32:56,776][119540] Decorrelating experience for 896 frames... [2023-03-09 10:32:56,817][118949] Heartbeat connected on RolloutWorker_w88 [2023-03-09 10:32:56,841][119383] Updated weights for policy 0, policy_version 122233 (0.0011) [2023-03-09 10:32:56,917][119531] Decorrelating experience for 800 frames... [2023-03-09 10:32:56,960][119514] Decorrelating experience for 512 frames... [2023-03-09 10:32:56,965][119501] Decorrelating experience for 896 frames... [2023-03-09 10:32:57,032][119398] Decorrelating experience for 832 frames... [2023-03-09 10:32:57,033][119536] Decorrelating experience for 992 frames... [2023-03-09 10:32:57,033][119464] Decorrelating experience for 992 frames... [2023-03-09 10:32:57,044][119529] Decorrelating experience for 736 frames... [2023-03-09 10:32:57,044][120653] Decorrelating experience for 448 frames... [2023-03-09 10:32:57,230][119505] Decorrelating experience for 928 frames... [2023-03-09 10:32:57,245][119392] Decorrelating experience for 480 frames... [2023-03-09 10:32:57,247][119393] Decorrelating experience for 768 frames... [2023-03-09 10:32:57,305][120040] Decorrelating experience for 992 frames... [2023-03-09 10:32:57,309][119469] Decorrelating experience for 608 frames... [2023-03-09 10:32:57,314][119530] Decorrelating experience for 896 frames... [2023-03-09 10:32:57,313][118949] Heartbeat connected on RolloutWorker_w84 [2023-03-09 10:32:57,369][119486] Decorrelating experience for 832 frames... [2023-03-09 10:32:57,379][119479] Decorrelating experience for 704 frames... [2023-03-09 10:32:57,433][119390] Another process currently holds the lock /tmp/sf2_rolo/doom_005.lockfile, attempt: 1 [2023-03-09 10:32:57,487][119481] Decorrelating experience for 928 frames... [2023-03-09 10:32:57,527][119389] Decorrelating experience for 832 frames... [2023-03-09 10:32:57,538][119504] Decorrelating experience for 800 frames... [2023-03-09 10:32:57,578][119614] Decorrelating experience for 576 frames... [2023-03-09 10:32:57,599][118949] Heartbeat connected on RolloutWorker_w41 [2023-03-09 10:32:57,609][119540] Decorrelating experience for 928 frames... [2023-03-09 10:32:57,620][119545] Decorrelating experience for 480 frames... [2023-03-09 10:32:57,651][119529] Decorrelating experience for 768 frames... [2023-03-09 10:32:57,673][118949] Heartbeat connected on RolloutWorker_w91 [2023-03-09 10:32:57,795][119240] Signal inference workers to stop experience collection... (50 times) [2023-03-09 10:32:57,813][119383] InferenceWorker_p0-w0: stopping experience collection (50 times) [2023-03-09 10:32:57,816][119240] Signal inference workers to resume experience collection... (50 times) [2023-03-09 10:32:57,817][118949] Heartbeat connected on RolloutWorker_w111 [2023-03-09 10:32:57,821][119501] Decorrelating experience for 928 frames... [2023-03-09 10:32:57,830][119383] InferenceWorker_p0-w0: resuming experience collection (50 times) [2023-03-09 10:32:57,832][119383] Updated weights for policy 0, policy_version 122243 (0.0013) [2023-03-09 10:32:57,856][119539] Decorrelating experience for 768 frames... [2023-03-09 10:32:57,856][119851] Decorrelating experience for 576 frames... [2023-03-09 10:32:57,862][119522] Decorrelating experience for 992 frames... [2023-03-09 10:32:57,919][119469] Decorrelating experience for 640 frames... [2023-03-09 10:32:57,931][119502] Decorrelating experience for 672 frames... [2023-03-09 10:32:57,955][120652] Decorrelating experience for 992 frames... [2023-03-09 10:32:58,037][119530] Decorrelating experience for 928 frames... [2023-03-09 10:32:58,086][119398] Decorrelating experience for 864 frames... [2023-03-09 10:32:58,089][119392] Decorrelating experience for 512 frames... [2023-03-09 10:32:58,124][119524] Decorrelating experience for 640 frames... [2023-03-09 10:32:58,168][119514] Decorrelating experience for 544 frames... [2023-03-09 10:32:58,173][119547] Decorrelating experience for 224 frames... [2023-03-09 10:32:58,196][119505] Decorrelating experience for 960 frames... [2023-03-09 10:32:58,251][125883] Decorrelating experience for 832 frames... [2023-03-09 10:32:58,275][119389] Decorrelating experience for 864 frames... [2023-03-09 10:32:58,372][119529] Decorrelating experience for 800 frames... [2023-03-09 10:32:58,400][119504] Decorrelating experience for 832 frames... [2023-03-09 10:32:58,421][118949] Heartbeat connected on RolloutWorker_w72 [2023-03-09 10:32:58,437][119487] Decorrelating experience for 608 frames... [2023-03-09 10:32:58,437][119390] Decorrelating experience for 608 frames... [2023-03-09 10:32:58,462][119539] Decorrelating experience for 800 frames... [2023-03-09 10:32:58,484][119481] Decorrelating experience for 960 frames... [2023-03-09 10:32:58,505][119851] Decorrelating experience for 608 frames... [2023-03-09 10:32:58,510][119547] Decorrelating experience for 256 frames... [2023-03-09 10:32:58,574][119393] Decorrelating experience for 800 frames... [2023-03-09 10:32:58,575][119540] Decorrelating experience for 960 frames... [2023-03-09 10:32:58,612][118949] Heartbeat connected on RolloutWorker_w112 [2023-03-09 10:32:58,660][119501] Decorrelating experience for 960 frames... [2023-03-09 10:32:58,705][119488] Decorrelating experience for 608 frames... [2023-03-09 10:32:58,732][119512] Another process currently holds the lock /tmp/sf2_rolo/doom_006.lockfile, attempt: 2 [2023-03-09 10:32:58,745][119502] Decorrelating experience for 704 frames... [2023-03-09 10:32:58,745][119396] Decorrelating experience for 832 frames... [2023-03-09 10:32:58,752][119383] Updated weights for policy 0, policy_version 122253 (0.0013) [2023-03-09 10:32:58,758][119398] Decorrelating experience for 896 frames... [2023-03-09 10:32:58,875][119479] Decorrelating experience for 736 frames... [2023-03-09 10:32:58,875][119524] Decorrelating experience for 672 frames... [2023-03-09 10:32:58,882][119486] Decorrelating experience for 864 frames... [2023-03-09 10:32:58,902][118949] Fps is (10 sec: 172034.9, 60 sec: 49698.2, 300 sec: 35081.1). Total num frames: 2003009536. Throughput: 0: 17244.9. Samples: 776656. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 10:32:58,903][118949] Avg episode reward: [(0, '41.435')] [2023-03-09 10:32:58,922][119530] Decorrelating experience for 960 frames... [2023-03-09 10:32:58,952][119469] Decorrelating experience for 672 frames... [2023-03-09 10:32:59,003][125883] Decorrelating experience for 864 frames... [2023-03-09 10:32:59,095][119539] Decorrelating experience for 832 frames... [2023-03-09 10:32:59,105][119514] Decorrelating experience for 576 frames... [2023-03-09 10:32:59,116][119544] Decorrelating experience for 928 frames... [2023-03-09 10:32:59,116][119392] Decorrelating experience for 544 frames... [2023-03-09 10:32:59,123][119547] Decorrelating experience for 288 frames... [2023-03-09 10:32:59,181][119504] Decorrelating experience for 864 frames... [2023-03-09 10:32:59,223][119390] Decorrelating experience for 640 frames... [2023-03-09 10:32:59,268][119505] Decorrelating experience for 992 frames... [2023-03-09 10:32:59,346][119487] Decorrelating experience for 640 frames... [2023-03-09 10:32:59,391][119488] Decorrelating experience for 640 frames... [2023-03-09 10:32:59,484][119389] Decorrelating experience for 896 frames... [2023-03-09 10:32:59,511][119550] Decorrelating experience for 864 frames... [2023-03-09 10:32:59,512][119481] Decorrelating experience for 992 frames... [2023-03-09 10:32:59,515][119529] Decorrelating experience for 832 frames... [2023-03-09 10:32:59,527][119540] Decorrelating experience for 992 frames... [2023-03-09 10:32:59,585][119489] Decorrelating experience for 224 frames... [2023-03-09 10:32:59,616][119479] Decorrelating experience for 768 frames... [2023-03-09 10:32:59,679][119469] Decorrelating experience for 704 frames... [2023-03-09 10:32:59,709][119383] Updated weights for policy 0, policy_version 122263 (0.0010) [2023-03-09 10:32:59,713][119486] Decorrelating experience for 896 frames... [2023-03-09 10:32:59,753][118949] Heartbeat connected on RolloutWorker_w59 [2023-03-09 10:32:59,789][119547] Decorrelating experience for 320 frames... [2023-03-09 10:32:59,793][119392] Decorrelating experience for 576 frames... [2023-03-09 10:32:59,800][120904] Decorrelating experience for 864 frames... [2023-03-09 10:32:59,825][119851] Decorrelating experience for 640 frames... [2023-03-09 10:32:59,838][120004] Decorrelating experience for 768 frames... [2023-03-09 10:32:59,851][119514] Decorrelating experience for 608 frames... [2023-03-09 10:32:59,976][119539] Decorrelating experience for 864 frames... [2023-03-09 10:33:00,038][119504] Decorrelating experience for 896 frames... [2023-03-09 10:33:00,056][119493] Decorrelating experience for 960 frames... [2023-03-09 10:33:00,093][119497] Decorrelating experience for 704 frames... [2023-03-09 10:33:00,124][119501] Decorrelating experience for 992 frames... [2023-03-09 10:33:00,133][119393] Decorrelating experience for 832 frames... [2023-03-09 10:33:00,135][118949] Heartbeat connected on RolloutWorker_w39 [2023-03-09 10:33:00,146][118949] Heartbeat connected on RolloutWorker_w76 [2023-03-09 10:33:00,169][119524] Decorrelating experience for 704 frames... [2023-03-09 10:33:00,176][119390] Decorrelating experience for 672 frames... [2023-03-09 10:33:00,189][119547] Decorrelating experience for 352 frames... [2023-03-09 10:33:00,198][119946] Another process currently holds the lock /tmp/sf2_rolo/doom_006.lockfile, attempt: 1 [2023-03-09 10:33:00,365][119389] Decorrelating experience for 928 frames... [2023-03-09 10:33:00,366][119487] Decorrelating experience for 672 frames... [2023-03-09 10:33:00,385][119534] Decorrelating experience for 896 frames... [2023-03-09 10:33:00,412][119479] Decorrelating experience for 800 frames... [2023-03-09 10:33:00,423][125883] Decorrelating experience for 896 frames... [2023-03-09 10:33:00,429][119383] Updated weights for policy 0, policy_version 122273 (0.0014) [2023-03-09 10:33:00,449][119489] Decorrelating experience for 256 frames... [2023-03-09 10:33:00,466][120004] Decorrelating experience for 800 frames... [2023-03-09 10:33:00,469][119507] Decorrelating experience for 832 frames... [2023-03-09 10:33:00,573][119486] Decorrelating experience for 928 frames... [2023-03-09 10:33:00,677][119529] Decorrelating experience for 864 frames... [2023-03-09 10:33:00,687][120904] Decorrelating experience for 896 frames... [2023-03-09 10:33:00,720][119528] Decorrelating experience for 928 frames... [2023-03-09 10:33:00,738][119539] Decorrelating experience for 896 frames... [2023-03-09 10:33:00,752][118949] Heartbeat connected on RolloutWorker_w46 [2023-03-09 10:33:00,760][119851] Decorrelating experience for 672 frames... [2023-03-09 10:33:00,799][119544] Decorrelating experience for 960 frames... [2023-03-09 10:33:00,807][120648] Decorrelating experience for 896 frames... [2023-03-09 10:33:00,903][119504] Decorrelating experience for 928 frames... [2023-03-09 10:33:00,905][120135] Another process currently holds the lock /tmp/sf2_rolo/doom_006.lockfile, attempt: 1 [2023-03-09 10:33:00,977][119494] Decorrelating experience for 992 frames... [2023-03-09 10:33:01,051][119550] Decorrelating experience for 896 frames... [2023-03-09 10:33:01,064][119493] Decorrelating experience for 992 frames... [2023-03-09 10:33:01,069][119390] Decorrelating experience for 704 frames... [2023-03-09 10:33:01,090][119489] Decorrelating experience for 288 frames... [2023-03-09 10:33:01,124][119497] Decorrelating experience for 736 frames... [2023-03-09 10:33:01,140][120004] Decorrelating experience for 832 frames... [2023-03-09 10:33:01,141][119514] Decorrelating experience for 640 frames... [2023-03-09 10:33:01,237][119479] Decorrelating experience for 832 frames... [2023-03-09 10:33:01,282][119487] Decorrelating experience for 704 frames... [2023-03-09 10:33:01,324][119488] Decorrelating experience for 672 frames... [2023-03-09 10:33:01,344][119534] Decorrelating experience for 928 frames... [2023-03-09 10:33:01,355][120904] Decorrelating experience for 928 frames... [2023-03-09 10:33:01,389][119383] Updated weights for policy 0, policy_version 122283 (0.0011) [2023-03-09 10:33:01,400][125883] Decorrelating experience for 928 frames... [2023-03-09 10:33:01,473][119547] Decorrelating experience for 384 frames... [2023-03-09 10:33:01,527][118949] Heartbeat connected on RolloutWorker_w22 [2023-03-09 10:33:01,552][118949] Heartbeat connected on RolloutWorker_w31 [2023-03-09 10:33:01,570][119502] Decorrelating experience for 736 frames... [2023-03-09 10:33:01,672][119392] Decorrelating experience for 608 frames... [2023-03-09 10:33:01,682][119524] Decorrelating experience for 736 frames... [2023-03-09 10:33:01,702][119486] Decorrelating experience for 960 frames... [2023-03-09 10:33:01,702][119544] Decorrelating experience for 992 frames... [2023-03-09 10:33:01,724][119539] Decorrelating experience for 928 frames... [2023-03-09 10:33:01,749][119507] Decorrelating experience for 864 frames... [2023-03-09 10:33:01,749][119504] Decorrelating experience for 960 frames... [2023-03-09 10:33:01,853][119512] Decorrelating experience for 768 frames... [2023-03-09 10:33:01,969][119469] Decorrelating experience for 736 frames... [2023-03-09 10:33:02,011][119487] Decorrelating experience for 736 frames... [2023-03-09 10:33:02,020][119550] Decorrelating experience for 928 frames... [2023-03-09 10:33:02,046][119479] Decorrelating experience for 864 frames... [2023-03-09 10:33:02,053][119390] Decorrelating experience for 736 frames... [2023-03-09 10:33:02,085][119547] Decorrelating experience for 416 frames... [2023-03-09 10:33:02,113][119383] Updated weights for policy 0, policy_version 122293 (0.0010) [2023-03-09 10:33:02,173][119530] Decorrelating experience for 992 frames... [2023-03-09 10:33:02,221][119534] Decorrelating experience for 960 frames... [2023-03-09 10:33:02,294][125883] Decorrelating experience for 960 frames... [2023-03-09 10:33:02,323][120648] Decorrelating experience for 928 frames... [2023-03-09 10:33:02,339][118949] Heartbeat connected on RolloutWorker_w70 [2023-03-09 10:33:02,401][119502] Decorrelating experience for 768 frames... [2023-03-09 10:33:02,403][120904] Decorrelating experience for 960 frames... [2023-03-09 10:33:02,403][119489] Decorrelating experience for 320 frames... [2023-03-09 10:33:02,404][119497] Decorrelating experience for 768 frames... [2023-03-09 10:33:02,485][119510] Decorrelating experience for 864 frames... [2023-03-09 10:33:02,560][119539] Decorrelating experience for 960 frames... [2023-03-09 10:33:02,612][119512] Decorrelating experience for 800 frames... [2023-03-09 10:33:02,621][119507] Decorrelating experience for 896 frames... [2023-03-09 10:33:02,662][119390] Decorrelating experience for 768 frames... [2023-03-09 10:33:02,688][119488] Decorrelating experience for 704 frames... [2023-03-09 10:33:02,703][120004] Decorrelating experience for 864 frames... [2023-03-09 10:33:02,748][119469] Decorrelating experience for 768 frames... [2023-03-09 10:33:02,762][119524] Decorrelating experience for 768 frames... [2023-03-09 10:33:02,783][118949] Heartbeat connected on RolloutWorker_w48 [2023-03-09 10:33:02,808][119392] Decorrelating experience for 640 frames... [2023-03-09 10:33:02,875][119479] Decorrelating experience for 896 frames... [2023-03-09 10:33:02,884][119393] Decorrelating experience for 864 frames... [2023-03-09 10:33:02,911][119504] Decorrelating experience for 992 frames... [2023-03-09 10:33:02,935][119383] Updated weights for policy 0, policy_version 122303 (0.0011) [2023-03-09 10:33:02,965][119489] Decorrelating experience for 352 frames... [2023-03-09 10:33:02,998][119514] Decorrelating experience for 672 frames... [2023-03-09 10:33:03,083][119487] Decorrelating experience for 768 frames... [2023-03-09 10:33:03,098][119389] Decorrelating experience for 960 frames... [2023-03-09 10:33:03,100][119529] Decorrelating experience for 896 frames... [2023-03-09 10:33:03,148][120648] Decorrelating experience for 960 frames... [2023-03-09 10:33:03,194][125883] Decorrelating experience for 992 frames... [2023-03-09 10:33:03,195][119547] Decorrelating experience for 448 frames... [2023-03-09 10:33:03,236][120199] Another process currently holds the lock /tmp/sf2_rolo/doom_006.lockfile, attempt: 1 [2023-03-09 10:33:03,248][119550] Decorrelating experience for 960 frames... [2023-03-09 10:33:03,266][119539] Decorrelating experience for 992 frames... [2023-03-09 10:33:03,274][120904] Decorrelating experience for 992 frames... [2023-03-09 10:33:03,339][119545] Decorrelating experience for 512 frames... [2023-03-09 10:33:03,359][120004] Decorrelating experience for 896 frames... [2023-03-09 10:33:03,397][119489] Decorrelating experience for 384 frames... [2023-03-09 10:33:03,412][119486] Decorrelating experience for 992 frames... [2023-03-09 10:33:03,422][119502] Decorrelating experience for 800 frames... [2023-03-09 10:33:03,478][119488] Decorrelating experience for 736 frames... [2023-03-09 10:33:03,507][118949] Heartbeat connected on RolloutWorker_w53 [2023-03-09 10:33:03,550][119512] Decorrelating experience for 832 frames... [2023-03-09 10:33:03,551][119507] Decorrelating experience for 928 frames... [2023-03-09 10:33:03,680][119496] Decorrelating experience for 640 frames... [2023-03-09 10:33:03,701][119514] Decorrelating experience for 704 frames... [2023-03-09 10:33:03,734][119383] Updated weights for policy 0, policy_version 122313 (0.0013) [2023-03-09 10:33:03,767][118949] Heartbeat connected on RolloutWorker_w79 [2023-03-09 10:33:03,772][119479] Decorrelating experience for 928 frames... [2023-03-09 10:33:03,775][119469] Decorrelating experience for 800 frames... [2023-03-09 10:33:03,775][119392] Decorrelating experience for 672 frames... [2023-03-09 10:33:03,783][118949] Heartbeat connected on RolloutWorker_w124 [2023-03-09 10:33:03,799][119547] Decorrelating experience for 480 frames... [2023-03-09 10:33:03,839][119529] Decorrelating experience for 928 frames... [2023-03-09 10:33:03,845][119680] Another process currently holds the lock /tmp/sf2_rolo/doom_006.lockfile, attempt: 2 [2023-03-09 10:33:03,854][118949] Heartbeat connected on RolloutWorker_w0 [2023-03-09 10:33:03,860][119545] Decorrelating experience for 544 frames... [2023-03-09 10:33:03,902][118949] Fps is (10 sec: 188414.6, 60 sec: 66355.1, 300 sec: 44236.8). Total num frames: 2004008960. Throughput: 0: 20550.0. Samples: 928528. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 10:33:03,904][118949] Avg episode reward: [(0, '43.470')] [2023-03-09 10:33:04,004][119528] Decorrelating experience for 960 frames... [2023-03-09 10:33:04,038][119510] Decorrelating experience for 896 frames... [2023-03-09 10:33:04,074][120004] Decorrelating experience for 928 frames... [2023-03-09 10:33:04,074][119487] Decorrelating experience for 800 frames... [2023-03-09 10:33:04,084][118949] Heartbeat connected on RolloutWorker_w4 [2023-03-09 10:33:04,098][119534] Decorrelating experience for 992 frames... [2023-03-09 10:33:04,159][120648] Decorrelating experience for 992 frames... [2023-03-09 10:33:04,182][119389] Decorrelating experience for 992 frames... [2023-03-09 10:33:04,265][119398] Decorrelating experience for 928 frames... [2023-03-09 10:33:04,376][119240] Signal inference workers to stop experience collection... (100 times) [2023-03-09 10:33:04,377][119512] Decorrelating experience for 864 frames... [2023-03-09 10:33:04,393][119545] Decorrelating experience for 576 frames... [2023-03-09 10:33:04,393][119390] Decorrelating experience for 800 frames... [2023-03-09 10:33:04,399][119240] Signal inference workers to resume experience collection... (100 times) [2023-03-09 10:33:04,411][119383] InferenceWorker_p0-w0: stopping experience collection (100 times) [2023-03-09 10:33:04,417][119489] Decorrelating experience for 416 frames... [2023-03-09 10:33:04,433][119383] InferenceWorker_p0-w0: resuming experience collection (100 times) [2023-03-09 10:33:04,533][119496] Decorrelating experience for 672 frames... [2023-03-09 10:33:04,533][119524] Decorrelating experience for 800 frames... [2023-03-09 10:33:04,537][119383] Updated weights for policy 0, policy_version 122323 (0.0013) [2023-03-09 10:33:04,582][119469] Decorrelating experience for 832 frames... [2023-03-09 10:33:04,626][119518] Decorrelating experience for 384 frames... [2023-03-09 10:33:04,711][118949] Heartbeat connected on RolloutWorker_w82 [2023-03-09 10:33:04,712][119393] Decorrelating experience for 896 frames... [2023-03-09 10:33:04,734][119547] Decorrelating experience for 512 frames... [2023-03-09 10:33:04,761][119514] Decorrelating experience for 736 frames... [2023-03-09 10:33:04,766][120004] Decorrelating experience for 960 frames... [2023-03-09 10:33:04,791][118949] Heartbeat connected on RolloutWorker_w100 [2023-03-09 10:33:04,799][118949] Heartbeat connected on RolloutWorker_w2 [2023-03-09 10:33:04,853][119487] Decorrelating experience for 832 frames... [2023-03-09 10:33:04,870][119479] Decorrelating experience for 960 frames... [2023-03-09 10:33:04,876][119509] Decorrelating experience for 832 frames... [2023-03-09 10:33:04,906][119489] Decorrelating experience for 448 frames... [2023-03-09 10:33:04,917][119545] Decorrelating experience for 608 frames... [2023-03-09 10:33:04,984][119392] Decorrelating experience for 704 frames... [2023-03-09 10:33:04,987][119398] Decorrelating experience for 960 frames... [2023-03-09 10:33:05,025][119502] Decorrelating experience for 832 frames... [2023-03-09 10:33:05,057][119528] Decorrelating experience for 992 frames... [2023-03-09 10:33:05,128][119390] Decorrelating experience for 832 frames... [2023-03-09 10:33:05,217][121015] Decorrelating experience for 704 frames... [2023-03-09 10:33:05,217][119518] Decorrelating experience for 416 frames... [2023-03-09 10:33:05,285][119547] Decorrelating experience for 544 frames... [2023-03-09 10:33:05,332][119469] Decorrelating experience for 864 frames... [2023-03-09 10:33:05,359][119466] Another process currently holds the lock /tmp/sf2_rolo/doom_006.lockfile, attempt: 2 [2023-03-09 10:33:05,402][119512] Decorrelating experience for 896 frames... [2023-03-09 10:33:05,428][119393] Decorrelating experience for 928 frames... [2023-03-09 10:33:05,463][119489] Decorrelating experience for 480 frames... [2023-03-09 10:33:05,472][119524] Decorrelating experience for 832 frames... [2023-03-09 10:33:05,538][119509] Decorrelating experience for 864 frames... [2023-03-09 10:33:05,562][118949] Heartbeat connected on RolloutWorker_w87 [2023-03-09 10:33:05,603][119514] Decorrelating experience for 768 frames... [2023-03-09 10:33:05,606][119487] Decorrelating experience for 864 frames... [2023-03-09 10:33:05,645][119479] Decorrelating experience for 992 frames... [2023-03-09 10:33:05,675][120004] Decorrelating experience for 992 frames... [2023-03-09 10:33:05,704][119502] Decorrelating experience for 864 frames... [2023-03-09 10:33:05,714][119516] Another process currently holds the lock /tmp/sf2_rolo/doom_006.lockfile, attempt: 1 [2023-03-09 10:33:05,716][119510] Decorrelating experience for 928 frames... [2023-03-09 10:33:05,718][119550] Decorrelating experience for 992 frames... [2023-03-09 10:33:05,721][119383] Updated weights for policy 0, policy_version 122335 (0.0012) [2023-03-09 10:33:05,731][119496] Decorrelating experience for 704 frames... [2023-03-09 10:33:05,794][119488] Decorrelating experience for 768 frames... [2023-03-09 10:33:05,913][119518] Decorrelating experience for 448 frames... [2023-03-09 10:33:05,933][119545] Decorrelating experience for 640 frames... [2023-03-09 10:33:05,960][119390] Decorrelating experience for 864 frames... [2023-03-09 10:33:06,050][119512] Decorrelating experience for 928 frames... [2023-03-09 10:33:06,073][119399] Decorrelating experience for 992 frames... [2023-03-09 10:33:06,091][121015] Decorrelating experience for 736 frames... [2023-03-09 10:33:06,216][119524] Decorrelating experience for 864 frames... [2023-03-09 10:33:06,216][118949] Heartbeat connected on RolloutWorker_w27 [2023-03-09 10:33:06,236][119547] Decorrelating experience for 576 frames... [2023-03-09 10:33:06,290][118949] Heartbeat connected on RolloutWorker_w99 [2023-03-09 10:33:06,292][118949] Heartbeat connected on RolloutWorker_w98 [2023-03-09 10:33:06,310][119507] Decorrelating experience for 960 frames... [2023-03-09 10:33:06,381][119487] Decorrelating experience for 896 frames... [2023-03-09 10:33:06,383][119680] Decorrelating experience for 896 frames... [2023-03-09 10:33:06,460][119510] Decorrelating experience for 960 frames... [2023-03-09 10:33:06,505][119393] Decorrelating experience for 960 frames... [2023-03-09 10:33:06,602][119545] Decorrelating experience for 672 frames... [2023-03-09 10:33:06,636][119383] Updated weights for policy 0, policy_version 122345 (0.0035) [2023-03-09 10:33:06,674][119496] Decorrelating experience for 736 frames... [2023-03-09 10:33:06,685][118949] Heartbeat connected on RolloutWorker_w35 [2023-03-09 10:33:06,699][119390] Decorrelating experience for 896 frames... [2023-03-09 10:33:06,701][119488] Decorrelating experience for 800 frames... [2023-03-09 10:33:06,716][119512] Decorrelating experience for 960 frames... [2023-03-09 10:33:06,716][120877] Decorrelating experience for 960 frames... [2023-03-09 10:33:06,755][119518] Decorrelating experience for 480 frames... [2023-03-09 10:33:06,817][119514] Decorrelating experience for 800 frames... [2023-03-09 10:33:06,959][119946] Decorrelating experience for 544 frames... [2023-03-09 10:33:07,020][119489] Decorrelating experience for 512 frames... [2023-03-09 10:33:07,065][119502] Decorrelating experience for 896 frames... [2023-03-09 10:33:07,108][119507] Decorrelating experience for 992 frames... [2023-03-09 10:33:07,203][119485] Decorrelating experience for 896 frames... [2023-03-09 10:33:07,279][119680] Decorrelating experience for 928 frames... [2023-03-09 10:33:07,298][119510] Decorrelating experience for 992 frames... [2023-03-09 10:33:07,361][119545] Decorrelating experience for 704 frames... [2023-03-09 10:33:07,361][119524] Decorrelating experience for 896 frames... [2023-03-09 10:33:07,373][119512] Decorrelating experience for 992 frames... [2023-03-09 10:33:07,418][119393] Decorrelating experience for 992 frames... [2023-03-09 10:33:07,452][120653] Decorrelating experience for 480 frames... [2023-03-09 10:33:07,488][119514] Decorrelating experience for 832 frames... [2023-03-09 10:33:07,558][119488] Decorrelating experience for 832 frames... [2023-03-09 10:33:07,583][119383] Updated weights for policy 0, policy_version 122355 (0.0015) [2023-03-09 10:33:07,664][119392] Decorrelating experience for 736 frames... [2023-03-09 10:33:07,675][119487] Decorrelating experience for 928 frames... [2023-03-09 10:33:07,679][118949] Heartbeat connected on RolloutWorker_w56 [2023-03-09 10:33:07,714][119529] Decorrelating experience for 960 frames... [2023-03-09 10:33:07,839][119502] Decorrelating experience for 928 frames... [2023-03-09 10:33:07,853][118949] Heartbeat connected on RolloutWorker_w77 [2023-03-09 10:33:07,862][118949] Heartbeat connected on RolloutWorker_w74 [2023-03-09 10:33:07,902][119489] Decorrelating experience for 544 frames... [2023-03-09 10:33:07,968][119469] Decorrelating experience for 896 frames... [2023-03-09 10:33:07,981][118949] Heartbeat connected on RolloutWorker_w20 [2023-03-09 10:33:07,989][119485] Decorrelating experience for 928 frames... [2023-03-09 10:33:08,016][119390] Decorrelating experience for 928 frames... [2023-03-09 10:33:08,028][119511] Decorrelating experience for 864 frames... [2023-03-09 10:33:08,151][119946] Decorrelating experience for 576 frames... [2023-03-09 10:33:08,154][119545] Decorrelating experience for 736 frames... [2023-03-09 10:33:08,215][119514] Decorrelating experience for 864 frames... [2023-03-09 10:33:08,216][119680] Decorrelating experience for 960 frames... [2023-03-09 10:33:08,236][120653] Decorrelating experience for 512 frames... [2023-03-09 10:33:08,278][120877] Decorrelating experience for 992 frames... [2023-03-09 10:33:08,299][119480] Decorrelating experience for 992 frames... [2023-03-09 10:33:08,303][119392] Decorrelating experience for 768 frames... [2023-03-09 10:33:08,376][119488] Decorrelating experience for 864 frames... [2023-03-09 10:33:08,415][119518] Decorrelating experience for 512 frames... [2023-03-09 10:33:08,562][126685] Decorrelating experience for 960 frames... [2023-03-09 10:33:08,576][119502] Decorrelating experience for 960 frames... [2023-03-09 10:33:08,593][119383] Updated weights for policy 0, policy_version 122366 (0.0023) [2023-03-09 10:33:08,630][119529] Decorrelating experience for 992 frames... [2023-03-09 10:33:08,651][119946] Decorrelating experience for 608 frames... [2023-03-09 10:33:08,701][119489] Decorrelating experience for 576 frames... [2023-03-09 10:33:08,718][119524] Decorrelating experience for 928 frames... [2023-03-09 10:33:08,725][120653] Decorrelating experience for 544 frames... [2023-03-09 10:33:08,845][118949] Heartbeat connected on RolloutWorker_w109 [2023-03-09 10:33:08,849][119466] Decorrelating experience for 576 frames... [2023-03-09 10:33:08,871][118949] Heartbeat connected on RolloutWorker_w30 [2023-03-09 10:33:08,902][118949] Fps is (10 sec: 188415.4, 60 sec: 81100.9, 300 sec: 51221.7). Total num frames: 2004893696. Throughput: 0: 26781.5. Samples: 1219072. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 10:33:08,904][118949] Avg episode reward: [(0, '43.269')] [2023-03-09 10:33:08,941][119390] Decorrelating experience for 960 frames... [2023-03-09 10:33:08,955][119485] Decorrelating experience for 960 frames... [2023-03-09 10:33:08,970][119545] Decorrelating experience for 768 frames... [2023-03-09 10:33:09,007][119511] Decorrelating experience for 896 frames... [2023-03-09 10:33:09,018][119392] Decorrelating experience for 800 frames... [2023-03-09 10:33:09,145][119473] Decorrelating experience for 896 frames... [2023-03-09 10:33:09,160][119680] Decorrelating experience for 992 frames... [2023-03-09 10:33:09,205][119946] Decorrelating experience for 640 frames... [2023-03-09 10:33:09,226][119514] Decorrelating experience for 896 frames... [2023-03-09 10:33:09,295][118949] Heartbeat connected on RolloutWorker_w69 [2023-03-09 10:33:09,365][119488] Decorrelating experience for 896 frames... [2023-03-09 10:33:09,436][119497] Decorrelating experience for 800 frames... [2023-03-09 10:33:09,476][119502] Decorrelating experience for 992 frames... [2023-03-09 10:33:09,479][119466] Decorrelating experience for 608 frames... [2023-03-09 10:33:09,515][119489] Decorrelating experience for 608 frames... [2023-03-09 10:33:09,538][119487] Decorrelating experience for 960 frames... [2023-03-09 10:33:09,539][119383] Updated weights for policy 0, policy_version 122376 (0.0014) [2023-03-09 10:33:09,562][119524] Decorrelating experience for 960 frames... [2023-03-09 10:33:09,564][119517] Another process currently holds the lock /tmp/sf2_rolo/doom_006.lockfile, attempt: 1 [2023-03-09 10:33:09,732][118949] Heartbeat connected on RolloutWorker_w113 [2023-03-09 10:33:09,746][126685] Decorrelating experience for 992 frames... [2023-03-09 10:33:09,767][119392] Decorrelating experience for 832 frames... [2023-03-09 10:33:09,770][119509] Decorrelating experience for 896 frames... [2023-03-09 10:33:09,823][119485] Decorrelating experience for 992 frames... [2023-03-09 10:33:09,845][119469] Decorrelating experience for 928 frames... [2023-03-09 10:33:09,902][119511] Decorrelating experience for 928 frames... [2023-03-09 10:33:09,999][118949] Heartbeat connected on RolloutWorker_w47 [2023-03-09 10:33:10,001][119396] Decorrelating experience for 864 frames... [2023-03-09 10:33:10,038][119514] Decorrelating experience for 928 frames... [2023-03-09 10:33:10,104][119466] Decorrelating experience for 640 frames... [2023-03-09 10:33:10,106][121015] Decorrelating experience for 768 frames... [2023-03-09 10:33:10,106][119489] Decorrelating experience for 640 frames... [2023-03-09 10:33:10,118][119497] Decorrelating experience for 832 frames... [2023-03-09 10:33:10,237][119851] Decorrelating experience for 704 frames... [2023-03-09 10:33:10,277][119524] Decorrelating experience for 992 frames... [2023-03-09 10:33:10,309][118949] Heartbeat connected on RolloutWorker_w42 [2023-03-09 10:33:10,315][119390] Decorrelating experience for 992 frames... [2023-03-09 10:33:10,362][118949] Heartbeat connected on RolloutWorker_w1 [2023-03-09 10:33:10,391][119392] Decorrelating experience for 864 frames... [2023-03-09 10:33:10,391][119473] Decorrelating experience for 928 frames... [2023-03-09 10:33:10,496][119498] Decorrelating experience for 992 frames... [2023-03-09 10:33:10,543][119511] Decorrelating experience for 960 frames... [2023-03-09 10:33:10,549][119487] Decorrelating experience for 992 frames... [2023-03-09 10:33:10,565][119383] Updated weights for policy 0, policy_version 122386 (0.0015) [2023-03-09 10:33:10,674][119396] Decorrelating experience for 896 frames... [2023-03-09 10:33:10,679][119489] Decorrelating experience for 672 frames... [2023-03-09 10:33:10,735][119514] Decorrelating experience for 960 frames... [2023-03-09 10:33:10,744][119547] Decorrelating experience for 608 frames... [2023-03-09 10:33:10,771][119497] Decorrelating experience for 864 frames... [2023-03-09 10:33:10,782][118949] Heartbeat connected on RolloutWorker_w75 [2023-03-09 10:33:10,820][118949] Heartbeat connected on RolloutWorker_w5 [2023-03-09 10:33:10,843][119469] Decorrelating experience for 960 frames... [2023-03-09 10:33:10,914][121015] Decorrelating experience for 800 frames... [2023-03-09 10:33:10,991][119466] Decorrelating experience for 672 frames... [2023-03-09 10:33:11,026][118949] Heartbeat connected on RolloutWorker_w28 [2023-03-09 10:33:11,027][120135] Decorrelating experience for 672 frames... [2023-03-09 10:33:11,063][119851] Decorrelating experience for 736 frames... [2023-03-09 10:33:11,100][118949] Heartbeat connected on RolloutWorker_w7 [2023-03-09 10:33:11,110][119509] Decorrelating experience for 928 frames... [2023-03-09 10:33:11,215][119511] Decorrelating experience for 992 frames... [2023-03-09 10:33:11,292][120263] Decorrelating experience for 896 frames... [2023-03-09 10:33:11,302][119489] Decorrelating experience for 704 frames... [2023-03-09 10:33:11,348][119392] Decorrelating experience for 896 frames... [2023-03-09 10:33:11,348][119547] Decorrelating experience for 640 frames... [2023-03-09 10:33:11,412][119396] Decorrelating experience for 928 frames... [2023-03-09 10:33:11,501][119497] Decorrelating experience for 896 frames... [2023-03-09 10:33:11,539][121015] Decorrelating experience for 832 frames... [2023-03-09 10:33:11,544][119514] Decorrelating experience for 992 frames... [2023-03-09 10:33:11,547][119383] Updated weights for policy 0, policy_version 122396 (0.0012) [2023-03-09 10:33:11,560][119946] Decorrelating experience for 672 frames... [2023-03-09 10:33:11,636][119469] Decorrelating experience for 992 frames... [2023-03-09 10:33:11,663][120135] Decorrelating experience for 704 frames... [2023-03-09 10:33:11,704][118949] Heartbeat connected on RolloutWorker_w80 [2023-03-09 10:33:11,806][119851] Decorrelating experience for 768 frames... [2023-03-09 10:33:11,832][119473] Decorrelating experience for 960 frames... [2023-03-09 10:33:11,863][119466] Decorrelating experience for 704 frames... [2023-03-09 10:33:11,891][119509] Decorrelating experience for 960 frames... [2023-03-09 10:33:11,955][119489] Decorrelating experience for 736 frames... [2023-03-09 10:33:12,069][118949] Heartbeat connected on RolloutWorker_w83 [2023-03-09 10:33:12,097][119946] Decorrelating experience for 704 frames... [2023-03-09 10:33:12,109][119531] Decorrelating experience for 832 frames... [2023-03-09 10:33:12,154][121015] Decorrelating experience for 864 frames... [2023-03-09 10:33:12,162][118949] Heartbeat connected on RolloutWorker_w9 [2023-03-09 10:33:12,207][120263] Decorrelating experience for 928 frames... [2023-03-09 10:33:12,400][119396] Decorrelating experience for 960 frames... [2023-03-09 10:33:12,401][119488] Decorrelating experience for 928 frames... [2023-03-09 10:33:12,443][120135] Decorrelating experience for 736 frames... [2023-03-09 10:33:12,447][119383] Updated weights for policy 0, policy_version 122406 (0.0012) [2023-03-09 10:33:12,479][119851] Decorrelating experience for 800 frames... [2023-03-09 10:33:12,692][119392] Decorrelating experience for 928 frames... [2023-03-09 10:33:12,702][119489] Decorrelating experience for 768 frames... [2023-03-09 10:33:12,767][119466] Decorrelating experience for 736 frames... [2023-03-09 10:33:12,782][119497] Decorrelating experience for 928 frames... [2023-03-09 10:33:12,804][121015] Decorrelating experience for 896 frames... [2023-03-09 10:33:12,838][119531] Decorrelating experience for 864 frames... [2023-03-09 10:33:12,903][119520] Another process currently holds the lock /tmp/sf2_rolo/doom_006.lockfile, attempt: 2 [2023-03-09 10:33:12,949][120199] Decorrelating experience for 960 frames... [2023-03-09 10:33:12,973][120263] Decorrelating experience for 960 frames... [2023-03-09 10:33:12,983][119473] Decorrelating experience for 992 frames... [2023-03-09 10:33:13,091][120135] Decorrelating experience for 768 frames... [2023-03-09 10:33:13,163][119488] Decorrelating experience for 960 frames... [2023-03-09 10:33:13,246][119946] Decorrelating experience for 736 frames... [2023-03-09 10:33:13,247][119545] Decorrelating experience for 800 frames... [2023-03-09 10:33:13,323][119383] Updated weights for policy 0, policy_version 122416 (0.0013) [2023-03-09 10:33:13,389][119851] Decorrelating experience for 832 frames... [2023-03-09 10:33:13,458][119392] Decorrelating experience for 960 frames... [2023-03-09 10:33:13,460][121015] Decorrelating experience for 928 frames... [2023-03-09 10:33:13,538][119517] Decorrelating experience for 704 frames... [2023-03-09 10:33:13,544][118949] Heartbeat connected on RolloutWorker_w15 [2023-03-09 10:33:13,552][119396] Decorrelating experience for 992 frames... [2023-03-09 10:33:13,677][119466] Decorrelating experience for 768 frames... [2023-03-09 10:33:13,747][120135] Decorrelating experience for 800 frames... [2023-03-09 10:33:13,756][119531] Decorrelating experience for 896 frames... [2023-03-09 10:33:13,794][119614] Decorrelating experience for 608 frames... [2023-03-09 10:33:13,835][119509] Decorrelating experience for 992 frames... [2023-03-09 10:33:13,841][119946] Decorrelating experience for 768 frames... [2023-03-09 10:33:13,902][118949] Fps is (10 sec: 173673.2, 60 sec: 95300.4, 300 sec: 57180.2). Total num frames: 2005745664. Throughput: 0: 32255.0. Samples: 1486416. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 10:33:13,903][118949] Avg episode reward: [(0, '43.482')] [2023-03-09 10:33:13,906][119545] Decorrelating experience for 832 frames... [2023-03-09 10:33:13,957][119497] Decorrelating experience for 960 frames... [2023-03-09 10:33:14,082][118949] Heartbeat connected on RolloutWorker_w26 [2023-03-09 10:33:14,141][121015] Decorrelating experience for 960 frames... [2023-03-09 10:33:14,142][119488] Decorrelating experience for 992 frames... [2023-03-09 10:33:14,142][119489] Decorrelating experience for 800 frames... [2023-03-09 10:33:14,142][120263] Decorrelating experience for 992 frames... [2023-03-09 10:33:14,317][119383] Updated weights for policy 0, policy_version 122426 (0.0013) [2023-03-09 10:33:14,341][119466] Decorrelating experience for 800 frames... [2023-03-09 10:33:14,379][118949] Heartbeat connected on RolloutWorker_w65 [2023-03-09 10:33:14,443][119851] Decorrelating experience for 864 frames... [2023-03-09 10:33:14,443][120135] Decorrelating experience for 832 frames... [2023-03-09 10:33:14,443][119517] Decorrelating experience for 736 frames... [2023-03-09 10:33:14,453][119946] Decorrelating experience for 800 frames... [2023-03-09 10:33:14,453][119614] Decorrelating experience for 640 frames... [2023-03-09 10:33:14,477][119240] Signal inference workers to stop experience collection... (150 times) [2023-03-09 10:33:14,478][119240] Signal inference workers to resume experience collection... (150 times) [2023-03-09 10:33:14,525][119383] InferenceWorker_p0-w0: stopping experience collection (150 times) [2023-03-09 10:33:14,525][119383] InferenceWorker_p0-w0: resuming experience collection (150 times) [2023-03-09 10:33:14,616][119531] Decorrelating experience for 928 frames... [2023-03-09 10:33:14,659][118949] Heartbeat connected on RolloutWorker_w16 [2023-03-09 10:33:14,663][118949] Heartbeat connected on RolloutWorker_w97 [2023-03-09 10:33:14,678][119497] Decorrelating experience for 992 frames... [2023-03-09 10:33:14,685][120199] Decorrelating experience for 992 frames... [2023-03-09 10:33:14,723][119392] Decorrelating experience for 992 frames... [2023-03-09 10:33:14,907][119489] Decorrelating experience for 832 frames... [2023-03-09 10:33:14,913][121015] Decorrelating experience for 992 frames... [2023-03-09 10:33:14,964][119466] Decorrelating experience for 832 frames... [2023-03-09 10:33:14,997][119398] Decorrelating experience for 992 frames... [2023-03-09 10:33:15,107][120135] Decorrelating experience for 864 frames... [2023-03-09 10:33:15,145][119946] Decorrelating experience for 832 frames... [2023-03-09 10:33:15,194][119545] Decorrelating experience for 864 frames... [2023-03-09 10:33:15,196][118949] Heartbeat connected on RolloutWorker_w13 [2023-03-09 10:33:15,204][118949] Heartbeat connected on RolloutWorker_w123 [2023-03-09 10:33:15,229][118949] Heartbeat connected on RolloutWorker_w14 [2023-03-09 10:33:15,240][119517] Decorrelating experience for 768 frames... [2023-03-09 10:33:15,254][119496] Decorrelating experience for 768 frames... [2023-03-09 10:33:15,386][118949] Heartbeat connected on RolloutWorker_w118 [2023-03-09 10:33:15,392][119851] Decorrelating experience for 896 frames... [2023-03-09 10:33:15,440][119383] Updated weights for policy 0, policy_version 122437 (0.0016) [2023-03-09 10:33:15,511][120653] Decorrelating experience for 576 frames... [2023-03-09 10:33:15,512][119531] Decorrelating experience for 960 frames... [2023-03-09 10:33:15,597][119489] Decorrelating experience for 864 frames... [2023-03-09 10:33:15,628][119466] Decorrelating experience for 864 frames... [2023-03-09 10:33:15,643][118949] Heartbeat connected on RolloutWorker_w32 [2023-03-09 10:33:15,769][120135] Decorrelating experience for 896 frames... [2023-03-09 10:33:15,839][119520] Decorrelating experience for 480 frames... [2023-03-09 10:33:15,856][119545] Decorrelating experience for 896 frames... [2023-03-09 10:33:15,870][119517] Decorrelating experience for 800 frames... [2023-03-09 10:33:15,879][119496] Decorrelating experience for 800 frames... [2023-03-09 10:33:16,096][119851] Decorrelating experience for 928 frames... [2023-03-09 10:33:16,113][119614] Decorrelating experience for 672 frames... [2023-03-09 10:33:16,148][119946] Decorrelating experience for 864 frames... [2023-03-09 10:33:16,179][120653] Decorrelating experience for 608 frames... [2023-03-09 10:33:16,246][119531] Decorrelating experience for 992 frames... [2023-03-09 10:33:16,304][119466] Decorrelating experience for 896 frames... [2023-03-09 10:33:16,394][119516] Decorrelating experience for 928 frames... [2023-03-09 10:33:16,451][119489] Decorrelating experience for 896 frames... [2023-03-09 10:33:16,495][119383] Updated weights for policy 0, policy_version 122447 (0.0016) [2023-03-09 10:33:16,607][120135] Decorrelating experience for 928 frames... [2023-03-09 10:33:16,693][119518] Decorrelating experience for 544 frames... [2023-03-09 10:33:16,796][120653] Decorrelating experience for 640 frames... [2023-03-09 10:33:16,797][119520] Decorrelating experience for 512 frames... [2023-03-09 10:33:16,810][118949] Heartbeat connected on RolloutWorker_w57 [2023-03-09 10:33:16,871][119851] Decorrelating experience for 960 frames... [2023-03-09 10:33:16,883][119946] Decorrelating experience for 896 frames... [2023-03-09 10:33:16,925][119496] Decorrelating experience for 832 frames... [2023-03-09 10:33:16,993][119545] Decorrelating experience for 928 frames... [2023-03-09 10:33:17,099][119517] Decorrelating experience for 832 frames... [2023-03-09 10:33:17,170][119516] Decorrelating experience for 960 frames... [2023-03-09 10:33:17,191][119489] Decorrelating experience for 928 frames... [2023-03-09 10:33:17,255][119518] Decorrelating experience for 576 frames... [2023-03-09 10:33:17,284][119547] Decorrelating experience for 672 frames... [2023-03-09 10:33:17,365][119383] Updated weights for policy 0, policy_version 122457 (0.0019) [2023-03-09 10:33:17,384][120135] Decorrelating experience for 960 frames... [2023-03-09 10:33:17,434][119520] Decorrelating experience for 544 frames... [2023-03-09 10:33:17,481][119466] Decorrelating experience for 928 frames... [2023-03-09 10:33:17,586][120653] Decorrelating experience for 672 frames... [2023-03-09 10:33:17,591][119614] Decorrelating experience for 704 frames... [2023-03-09 10:33:17,624][119946] Decorrelating experience for 928 frames... [2023-03-09 10:33:17,668][119851] Decorrelating experience for 992 frames... [2023-03-09 10:33:17,768][119496] Decorrelating experience for 864 frames... [2023-03-09 10:33:17,812][119517] Decorrelating experience for 864 frames... [2023-03-09 10:33:17,955][119516] Decorrelating experience for 992 frames... [2023-03-09 10:33:17,955][119489] Decorrelating experience for 960 frames... [2023-03-09 10:33:18,045][119518] Decorrelating experience for 608 frames... [2023-03-09 10:33:18,086][119520] Decorrelating experience for 576 frames... [2023-03-09 10:33:18,129][119383] Updated weights for policy 0, policy_version 122467 (0.0024) [2023-03-09 10:33:18,160][120135] Decorrelating experience for 992 frames... [2023-03-09 10:33:18,219][118949] Heartbeat connected on RolloutWorker_w125 [2023-03-09 10:33:18,247][119466] Decorrelating experience for 960 frames... [2023-03-09 10:33:18,320][119545] Decorrelating experience for 960 frames... [2023-03-09 10:33:18,412][119946] Decorrelating experience for 960 frames... [2023-03-09 10:33:18,412][119614] Decorrelating experience for 736 frames... [2023-03-09 10:33:18,488][118949] Heartbeat connected on RolloutWorker_w86 [2023-03-09 10:33:18,513][119517] Decorrelating experience for 896 frames... [2023-03-09 10:33:18,564][119496] Decorrelating experience for 896 frames... [2023-03-09 10:33:18,601][120653] Decorrelating experience for 704 frames... [2023-03-09 10:33:18,677][118949] Heartbeat connected on RolloutWorker_w126 [2023-03-09 10:33:18,733][119520] Decorrelating experience for 608 frames... [2023-03-09 10:33:18,780][119518] Decorrelating experience for 640 frames... [2023-03-09 10:33:18,850][119547] Decorrelating experience for 704 frames... [2023-03-09 10:33:18,902][118949] Fps is (10 sec: 172026.7, 60 sec: 109499.3, 300 sec: 62727.2). Total num frames: 2006614016. Throughput: 0: 34740.5. Samples: 1614128. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-09 10:33:18,904][118949] Avg episode reward: [(0, '44.605')] [2023-03-09 10:33:18,960][119466] Decorrelating experience for 992 frames... [2023-03-09 10:33:19,049][119545] Decorrelating experience for 992 frames... [2023-03-09 10:33:19,093][119489] Decorrelating experience for 992 frames... [2023-03-09 10:33:19,127][119614] Decorrelating experience for 768 frames... [2023-03-09 10:33:19,220][119517] Decorrelating experience for 928 frames... [2023-03-09 10:33:19,271][119946] Decorrelating experience for 992 frames... [2023-03-09 10:33:19,275][119496] Decorrelating experience for 928 frames... [2023-03-09 10:33:19,311][120653] Decorrelating experience for 736 frames... [2023-03-09 10:33:19,362][119518] Decorrelating experience for 672 frames... [2023-03-09 10:33:19,395][119383] Updated weights for policy 0, policy_version 122478 (0.0013) [2023-03-09 10:33:19,478][119547] Decorrelating experience for 736 frames... [2023-03-09 10:33:19,483][118949] Heartbeat connected on RolloutWorker_w44 [2023-03-09 10:33:19,570][118949] Heartbeat connected on RolloutWorker_w49 [2023-03-09 10:33:19,599][118949] Heartbeat connected on RolloutWorker_w10 [2023-03-09 10:33:19,608][119520] Decorrelating experience for 640 frames... [2023-03-09 10:33:19,769][118949] Heartbeat connected on RolloutWorker_w96 [2023-03-09 10:33:19,780][119614] Decorrelating experience for 800 frames... [2023-03-09 10:33:19,894][119517] Decorrelating experience for 960 frames... [2023-03-09 10:33:19,915][119518] Decorrelating experience for 704 frames... [2023-03-09 10:33:19,938][119496] Decorrelating experience for 960 frames... [2023-03-09 10:33:20,158][119547] Decorrelating experience for 768 frames... [2023-03-09 10:33:20,184][119520] Decorrelating experience for 672 frames... [2023-03-09 10:33:20,251][120653] Decorrelating experience for 768 frames... [2023-03-09 10:33:20,354][119614] Decorrelating experience for 832 frames... [2023-03-09 10:33:20,480][119518] Decorrelating experience for 736 frames... [2023-03-09 10:33:20,576][119383] Updated weights for policy 0, policy_version 122489 (0.0039) [2023-03-09 10:33:20,646][119496] Decorrelating experience for 992 frames... [2023-03-09 10:33:20,771][119517] Decorrelating experience for 992 frames... [2023-03-09 10:33:20,801][119547] Decorrelating experience for 800 frames... [2023-03-09 10:33:20,925][119520] Decorrelating experience for 704 frames... [2023-03-09 10:33:21,047][120653] Decorrelating experience for 800 frames... [2023-03-09 10:33:21,117][119614] Decorrelating experience for 864 frames... [2023-03-09 10:33:21,127][119518] Decorrelating experience for 768 frames... [2023-03-09 10:33:21,174][118949] Heartbeat connected on RolloutWorker_w37 [2023-03-09 10:33:21,309][118949] Heartbeat connected on RolloutWorker_w60 [2023-03-09 10:33:21,390][119383] Updated weights for policy 0, policy_version 122499 (0.0017) [2023-03-09 10:33:21,462][119547] Decorrelating experience for 832 frames... [2023-03-09 10:33:21,675][119520] Decorrelating experience for 736 frames... [2023-03-09 10:33:21,763][119518] Decorrelating experience for 800 frames... [2023-03-09 10:33:21,784][119614] Decorrelating experience for 896 frames... [2023-03-09 10:33:21,861][120653] Decorrelating experience for 832 frames... [2023-03-09 10:33:22,150][119547] Decorrelating experience for 864 frames... [2023-03-09 10:33:22,424][119518] Decorrelating experience for 832 frames... [2023-03-09 10:33:22,426][119520] Decorrelating experience for 768 frames... [2023-03-09 10:33:22,458][119614] Decorrelating experience for 928 frames... [2023-03-09 10:33:22,467][119383] Updated weights for policy 0, policy_version 122509 (0.0025) [2023-03-09 10:33:22,671][120653] Decorrelating experience for 864 frames... [2023-03-09 10:33:22,813][119547] Decorrelating experience for 896 frames... [2023-03-09 10:33:23,125][119518] Decorrelating experience for 864 frames... [2023-03-09 10:33:23,193][119614] Decorrelating experience for 960 frames... [2023-03-09 10:33:23,220][119520] Decorrelating experience for 800 frames... [2023-03-09 10:33:23,279][119383] Updated weights for policy 0, policy_version 122519 (0.0025) [2023-03-09 10:33:23,513][120653] Decorrelating experience for 896 frames... [2023-03-09 10:33:23,517][119547] Decorrelating experience for 928 frames... [2023-03-09 10:33:23,847][119518] Decorrelating experience for 896 frames... [2023-03-09 10:33:23,902][118949] Fps is (10 sec: 173670.8, 60 sec: 123426.0, 300 sec: 67770.3). Total num frames: 2007482368. Throughput: 0: 39335.8. Samples: 1877440. Policy #0 lag: (min: 2.0, avg: 14.8, max: 30.0) [2023-03-09 10:33:23,903][118949] Avg episode reward: [(0, '47.853')] [2023-03-09 10:33:23,947][119614] Decorrelating experience for 992 frames... [2023-03-09 10:33:23,963][119240] Saving /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000122528_2007498752.pth... [2023-03-09 10:33:24,029][119240] Removing /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000121268_1986854912.pth [2023-03-09 10:33:24,033][119520] Decorrelating experience for 832 frames... [2023-03-09 10:33:24,154][119383] Updated weights for policy 0, policy_version 122529 (0.0013) [2023-03-09 10:33:24,267][119547] Decorrelating experience for 960 frames... [2023-03-09 10:33:24,470][118949] Heartbeat connected on RolloutWorker_w104 [2023-03-09 10:33:24,575][119518] Decorrelating experience for 928 frames... [2023-03-09 10:33:24,599][120653] Decorrelating experience for 928 frames... [2023-03-09 10:33:24,802][119520] Decorrelating experience for 864 frames... [2023-03-09 10:33:24,999][119383] Updated weights for policy 0, policy_version 122539 (0.0016) [2023-03-09 10:33:25,029][119547] Decorrelating experience for 992 frames... [2023-03-09 10:33:25,303][119518] Decorrelating experience for 960 frames... [2023-03-09 10:33:25,496][120653] Decorrelating experience for 960 frames... [2023-03-09 10:33:25,549][118949] Heartbeat connected on RolloutWorker_w95 [2023-03-09 10:33:25,643][119520] Decorrelating experience for 896 frames... [2023-03-09 10:33:25,882][119383] Updated weights for policy 0, policy_version 122550 (0.0013) [2023-03-09 10:33:26,066][119518] Decorrelating experience for 992 frames... [2023-03-09 10:33:26,153][119240] Signal inference workers to stop experience collection... (200 times) [2023-03-09 10:33:26,154][119240] Signal inference workers to resume experience collection... (200 times) [2023-03-09 10:33:26,205][119383] InferenceWorker_p0-w0: stopping experience collection (200 times) [2023-03-09 10:33:26,206][119383] InferenceWorker_p0-w0: resuming experience collection (200 times) [2023-03-09 10:33:26,440][120653] Decorrelating experience for 992 frames... [2023-03-09 10:33:26,541][119520] Decorrelating experience for 928 frames... [2023-03-09 10:33:26,588][118949] Heartbeat connected on RolloutWorker_w54 [2023-03-09 10:33:26,755][119383] Updated weights for policy 0, policy_version 122560 (0.0013) [2023-03-09 10:33:27,085][118949] Heartbeat connected on RolloutWorker_w115 [2023-03-09 10:33:27,367][119520] Decorrelating experience for 960 frames... [2023-03-09 10:33:27,808][119383] Updated weights for policy 0, policy_version 122570 (0.0017) [2023-03-09 10:33:28,084][119520] Decorrelating experience for 992 frames... [2023-03-09 10:33:28,575][119383] Updated weights for policy 0, policy_version 122580 (0.0012) [2023-03-09 10:33:28,627][118949] Heartbeat connected on RolloutWorker_w51 [2023-03-09 10:33:28,902][118949] Fps is (10 sec: 180224.8, 60 sec: 137898.3, 300 sec: 72944.4). Total num frames: 2008416256. Throughput: 0: 43627.2. Samples: 2163008. Policy #0 lag: (min: 2.0, avg: 14.8, max: 30.0) [2023-03-09 10:33:28,904][118949] Avg episode reward: [(0, '49.512')] [2023-03-09 10:33:29,491][119383] Updated weights for policy 0, policy_version 122591 (0.0011) [2023-03-09 10:33:30,453][119383] Updated weights for policy 0, policy_version 122601 (0.0016) [2023-03-09 10:33:31,111][119383] Updated weights for policy 0, policy_version 122611 (0.0016) [2023-03-09 10:33:31,974][119383] Updated weights for policy 0, policy_version 122621 (0.0020) [2023-03-09 10:33:32,920][119383] Updated weights for policy 0, policy_version 122631 (0.0016) [2023-03-09 10:33:33,650][119383] Updated weights for policy 0, policy_version 122641 (0.0019) [2023-03-09 10:33:33,902][118949] Fps is (10 sec: 190052.5, 60 sec: 151825.0, 300 sec: 77960.6). Total num frames: 2009382912. Throughput: 0: 45287.8. Samples: 2310352. Policy #0 lag: (min: 2.0, avg: 14.8, max: 30.0) [2023-03-09 10:33:33,903][118949] Avg episode reward: [(0, '51.459')] [2023-03-09 10:33:34,457][119383] Updated weights for policy 0, policy_version 122651 (0.0020) [2023-03-09 10:33:35,232][119383] Updated weights for policy 0, policy_version 122661 (0.0019) [2023-03-09 10:33:36,148][119383] Updated weights for policy 0, policy_version 122671 (0.0019) [2023-03-09 10:33:36,269][119240] Signal inference workers to stop experience collection... (250 times) [2023-03-09 10:33:36,287][119240] Signal inference workers to resume experience collection... (250 times) [2023-03-09 10:33:36,355][119383] InferenceWorker_p0-w0: stopping experience collection (250 times) [2023-03-09 10:33:36,355][119383] InferenceWorker_p0-w0: resuming experience collection (250 times) [2023-03-09 10:33:36,950][119383] Updated weights for policy 0, policy_version 122681 (0.0040) [2023-03-09 10:33:37,844][119383] Updated weights for policy 0, policy_version 122692 (0.0018) [2023-03-09 10:33:38,796][119383] Updated weights for policy 0, policy_version 122702 (0.0017) [2023-03-09 10:33:38,902][118949] Fps is (10 sec: 196611.8, 60 sec: 165205.2, 300 sec: 82837.6). Total num frames: 2010382336. Throughput: 0: 46655.7. Samples: 2605184. Policy #0 lag: (min: 2.0, avg: 14.8, max: 30.0) [2023-03-09 10:33:38,903][118949] Avg episode reward: [(0, '50.880')] [2023-03-09 10:33:39,552][119383] Updated weights for policy 0, policy_version 122712 (0.0019) [2023-03-09 10:33:40,297][119383] Updated weights for policy 0, policy_version 122722 (0.0014) [2023-03-09 10:33:41,313][119383] Updated weights for policy 0, policy_version 122732 (0.0022) [2023-03-09 10:33:42,069][119383] Updated weights for policy 0, policy_version 122742 (0.0016) [2023-03-09 10:33:42,874][119383] Updated weights for policy 0, policy_version 122752 (0.0021) [2023-03-09 10:33:43,815][119383] Updated weights for policy 0, policy_version 122762 (0.0016) [2023-03-09 10:33:43,902][118949] Fps is (10 sec: 196607.4, 60 sec: 176400.9, 300 sec: 87087.3). Total num frames: 2011348992. Throughput: 0: 47185.2. Samples: 2900000. Policy #0 lag: (min: 2.0, avg: 14.8, max: 30.0) [2023-03-09 10:33:43,904][118949] Avg episode reward: [(0, '54.110')] [2023-03-09 10:33:44,601][119383] Updated weights for policy 0, policy_version 122772 (0.0023) [2023-03-09 10:33:45,372][119383] Updated weights for policy 0, policy_version 122782 (0.0023) [2023-03-09 10:33:46,297][119383] Updated weights for policy 0, policy_version 122792 (0.0016) [2023-03-09 10:33:46,755][119240] Signal inference workers to stop experience collection... (300 times) [2023-03-09 10:33:46,757][119240] Signal inference workers to resume experience collection... (300 times) [2023-03-09 10:33:46,813][119383] InferenceWorker_p0-w0: stopping experience collection (300 times) [2023-03-09 10:33:46,813][119383] InferenceWorker_p0-w0: resuming experience collection (300 times) [2023-03-09 10:33:47,006][119383] Updated weights for policy 0, policy_version 122802 (0.0013) [2023-03-09 10:33:47,856][119383] Updated weights for policy 0, policy_version 122812 (0.0015) [2023-03-09 10:33:48,642][119383] Updated weights for policy 0, policy_version 122822 (0.0011) [2023-03-09 10:33:48,902][118949] Fps is (10 sec: 194970.0, 60 sec: 184047.2, 300 sec: 91143.7). Total num frames: 2012332032. Throughput: 0: 47131.9. Samples: 3049456. Policy #0 lag: (min: 2.0, avg: 14.8, max: 30.0) [2023-03-09 10:33:48,903][118949] Avg episode reward: [(0, '54.753')] [2023-03-09 10:33:49,712][119383] Updated weights for policy 0, policy_version 122834 (0.0021) [2023-03-09 10:33:50,493][119383] Updated weights for policy 0, policy_version 122844 (0.0022) [2023-03-09 10:33:51,320][119383] Updated weights for policy 0, policy_version 122854 (0.0013) [2023-03-09 10:33:52,220][119383] Updated weights for policy 0, policy_version 122864 (0.0014) [2023-03-09 10:33:52,986][119383] Updated weights for policy 0, policy_version 122874 (0.0013) [2023-03-09 10:33:53,811][119383] Updated weights for policy 0, policy_version 122884 (0.0022) [2023-03-09 10:33:53,902][118949] Fps is (10 sec: 198245.4, 60 sec: 186777.4, 300 sec: 95027.2). Total num frames: 2013331456. Throughput: 0: 47180.2. Samples: 3342192. Policy #0 lag: (min: 2.0, avg: 14.8, max: 30.0) [2023-03-09 10:33:53,904][118949] Avg episode reward: [(0, '54.253')] [2023-03-09 10:33:54,891][119383] Updated weights for policy 0, policy_version 122894 (0.0030) [2023-03-09 10:33:55,583][119383] Updated weights for policy 0, policy_version 122904 (0.0029) [2023-03-09 10:33:56,466][119383] Updated weights for policy 0, policy_version 122915 (0.0017) [2023-03-09 10:33:57,111][119240] Signal inference workers to stop experience collection... (350 times) [2023-03-09 10:33:57,122][119240] Signal inference workers to resume experience collection... (350 times) [2023-03-09 10:33:57,190][119383] InferenceWorker_p0-w0: stopping experience collection (350 times) [2023-03-09 10:33:57,191][119383] InferenceWorker_p0-w0: resuming experience collection (350 times) [2023-03-09 10:33:57,441][119383] Updated weights for policy 0, policy_version 122925 (0.0021) [2023-03-09 10:33:58,183][119383] Updated weights for policy 0, policy_version 122935 (0.0013) [2023-03-09 10:33:58,902][118949] Fps is (10 sec: 198248.2, 60 sec: 188416.0, 300 sec: 98530.1). Total num frames: 2014314496. Throughput: 0: 47790.0. Samples: 3636960. Policy #0 lag: (min: 2.0, avg: 14.8, max: 30.0) [2023-03-09 10:33:58,905][118949] Avg episode reward: [(0, '55.216')] [2023-03-09 10:33:58,940][119383] Updated weights for policy 0, policy_version 122945 (0.0012) [2023-03-09 10:33:59,917][119383] Updated weights for policy 0, policy_version 122955 (0.0013) [2023-03-09 10:34:00,722][119383] Updated weights for policy 0, policy_version 122965 (0.0025) [2023-03-09 10:34:01,500][119383] Updated weights for policy 0, policy_version 122975 (0.0015) [2023-03-09 10:34:02,410][119383] Updated weights for policy 0, policy_version 122985 (0.0013) [2023-03-09 10:34:03,100][119383] Updated weights for policy 0, policy_version 122995 (0.0028) [2023-03-09 10:34:03,902][118949] Fps is (10 sec: 196613.4, 60 sec: 188143.8, 300 sec: 101799.4). Total num frames: 2015297536. Throughput: 0: 48226.9. Samples: 3784320. Policy #0 lag: (min: 2.0, avg: 14.8, max: 30.0) [2023-03-09 10:34:03,903][118949] Avg episode reward: [(0, '55.006')] [2023-03-09 10:34:03,960][119383] Updated weights for policy 0, policy_version 123005 (0.0020) [2023-03-09 10:34:04,878][119383] Updated weights for policy 0, policy_version 123015 (0.0013) [2023-03-09 10:34:05,638][119383] Updated weights for policy 0, policy_version 123025 (0.0020) [2023-03-09 10:34:05,986][119240] Signal inference workers to stop experience collection... (400 times) [2023-03-09 10:34:06,009][119240] Signal inference workers to resume experience collection... (400 times) [2023-03-09 10:34:06,046][119383] InferenceWorker_p0-w0: stopping experience collection (400 times) [2023-03-09 10:34:06,087][119383] InferenceWorker_p0-w0: resuming experience collection (400 times) [2023-03-09 10:34:06,484][119383] Updated weights for policy 0, policy_version 123036 (0.0022) [2023-03-09 10:34:07,296][119383] Updated weights for policy 0, policy_version 123046 (0.0013) [2023-03-09 10:34:08,198][119383] Updated weights for policy 0, policy_version 123056 (0.0013) [2023-03-09 10:34:08,903][118949] Fps is (10 sec: 198233.2, 60 sec: 190052.4, 300 sec: 104963.0). Total num frames: 2016296960. Throughput: 0: 49015.5. Samples: 4083168. Policy #0 lag: (min: 2.0, avg: 14.8, max: 30.0) [2023-03-09 10:34:08,905][118949] Avg episode reward: [(0, '53.139')] [2023-03-09 10:34:08,975][119383] Updated weights for policy 0, policy_version 123066 (0.0025) [2023-03-09 10:34:09,846][119383] Updated weights for policy 0, policy_version 123077 (0.0015) [2023-03-09 10:34:10,748][119383] Updated weights for policy 0, policy_version 123087 (0.0015) [2023-03-09 10:34:11,522][119383] Updated weights for policy 0, policy_version 123097 (0.0012) [2023-03-09 10:34:12,209][119383] Updated weights for policy 0, policy_version 123107 (0.0017) [2023-03-09 10:34:13,193][119383] Updated weights for policy 0, policy_version 123117 (0.0019) [2023-03-09 10:34:13,899][119383] Updated weights for policy 0, policy_version 123127 (0.0026) [2023-03-09 10:34:13,902][118949] Fps is (10 sec: 201516.1, 60 sec: 192784.3, 300 sec: 108031.9). Total num frames: 2017312768. Throughput: 0: 49355.7. Samples: 4384016. Policy #0 lag: (min: 2.0, avg: 14.8, max: 30.0) [2023-03-09 10:34:13,904][118949] Avg episode reward: [(0, '51.404')] [2023-03-09 10:34:14,723][119383] Updated weights for policy 0, policy_version 123137 (0.0021) [2023-03-09 10:34:15,534][119240] Signal inference workers to stop experience collection... (450 times) [2023-03-09 10:34:15,553][119240] Signal inference workers to resume experience collection... (450 times) [2023-03-09 10:34:15,580][119383] InferenceWorker_p0-w0: stopping experience collection (450 times) [2023-03-09 10:34:15,616][119383] InferenceWorker_p0-w0: resuming experience collection (450 times) [2023-03-09 10:34:15,700][119383] Updated weights for policy 0, policy_version 123147 (0.0017) [2023-03-09 10:34:16,462][119383] Updated weights for policy 0, policy_version 123157 (0.0025) [2023-03-09 10:34:17,296][119383] Updated weights for policy 0, policy_version 123168 (0.0018) [2023-03-09 10:34:18,193][119383] Updated weights for policy 0, policy_version 123178 (0.0016) [2023-03-09 10:34:18,902][118949] Fps is (10 sec: 199894.2, 60 sec: 194697.0, 300 sec: 110716.1). Total num frames: 2018295808. Throughput: 0: 49401.6. Samples: 4533424. Policy #0 lag: (min: 2.0, avg: 14.8, max: 30.0) [2023-03-09 10:34:18,903][118949] Avg episode reward: [(0, '53.715')] [2023-03-09 10:34:19,092][119383] Updated weights for policy 0, policy_version 123189 (0.0013) [2023-03-09 10:34:19,892][119383] Updated weights for policy 0, policy_version 123199 (0.0014) [2023-03-09 10:34:20,839][119383] Updated weights for policy 0, policy_version 123209 (0.0025) [2023-03-09 10:34:21,520][119383] Updated weights for policy 0, policy_version 123219 (0.0021) [2023-03-09 10:34:22,358][119383] Updated weights for policy 0, policy_version 123229 (0.0027) [2023-03-09 10:34:23,314][119383] Updated weights for policy 0, policy_version 123239 (0.0016) [2023-03-09 10:34:23,902][118949] Fps is (10 sec: 196611.4, 60 sec: 196607.7, 300 sec: 113242.4). Total num frames: 2019278848. Throughput: 0: 49447.1. Samples: 4830304. Policy #0 lag: (min: 1.0, avg: 17.0, max: 33.0) [2023-03-09 10:34:23,903][118949] Avg episode reward: [(0, '54.430')] [2023-03-09 10:34:24,040][119383] Updated weights for policy 0, policy_version 123249 (0.0012) [2023-03-09 10:34:24,836][119240] Signal inference workers to stop experience collection... (500 times) [2023-03-09 10:34:24,837][119240] Signal inference workers to resume experience collection... (500 times) [2023-03-09 10:34:24,886][119383] Updated weights for policy 0, policy_version 123260 (0.0016) [2023-03-09 10:34:24,921][119383] InferenceWorker_p0-w0: stopping experience collection (500 times) [2023-03-09 10:34:24,921][119383] InferenceWorker_p0-w0: resuming experience collection (500 times) [2023-03-09 10:34:25,751][119383] Updated weights for policy 0, policy_version 123270 (0.0025) [2023-03-09 10:34:26,692][119383] Updated weights for policy 0, policy_version 123280 (0.0018) [2023-03-09 10:34:27,405][119383] Updated weights for policy 0, policy_version 123290 (0.0018) [2023-03-09 10:34:28,202][119383] Updated weights for policy 0, policy_version 123300 (0.0016) [2023-03-09 10:34:28,902][118949] Fps is (10 sec: 194968.3, 60 sec: 197154.3, 300 sec: 115530.6). Total num frames: 2020245504. Throughput: 0: 49444.6. Samples: 5125008. Policy #0 lag: (min: 1.0, avg: 17.0, max: 33.0) [2023-03-09 10:34:28,904][118949] Avg episode reward: [(0, '54.926')] [2023-03-09 10:34:29,173][119383] Updated weights for policy 0, policy_version 123310 (0.0017) [2023-03-09 10:34:29,985][119383] Updated weights for policy 0, policy_version 123320 (0.0021) [2023-03-09 10:34:30,736][119383] Updated weights for policy 0, policy_version 123330 (0.0023) [2023-03-09 10:34:31,809][119383] Updated weights for policy 0, policy_version 123341 (0.0021) [2023-03-09 10:34:32,545][119383] Updated weights for policy 0, policy_version 123351 (0.0014) [2023-03-09 10:34:33,268][119240] Signal inference workers to stop experience collection... (550 times) [2023-03-09 10:34:33,302][119240] Signal inference workers to resume experience collection... (550 times) [2023-03-09 10:34:33,344][119383] InferenceWorker_p0-w0: stopping experience collection (550 times) [2023-03-09 10:34:33,345][119383] InferenceWorker_p0-w0: resuming experience collection (550 times) [2023-03-09 10:34:33,389][119383] Updated weights for policy 0, policy_version 123361 (0.0013) [2023-03-09 10:34:33,902][118949] Fps is (10 sec: 194972.5, 60 sec: 197427.7, 300 sec: 117782.9). Total num frames: 2021228544. Throughput: 0: 49353.7. Samples: 5270368. Policy #0 lag: (min: 1.0, avg: 17.0, max: 33.0) [2023-03-09 10:34:33,903][118949] Avg episode reward: [(0, '54.601')] [2023-03-09 10:34:34,368][119383] Updated weights for policy 0, policy_version 123371 (0.0013) [2023-03-09 10:34:35,095][119383] Updated weights for policy 0, policy_version 123381 (0.0016) [2023-03-09 10:34:35,896][119383] Updated weights for policy 0, policy_version 123391 (0.0016) [2023-03-09 10:34:36,864][119383] Updated weights for policy 0, policy_version 123402 (0.0016) [2023-03-09 10:34:37,674][119383] Updated weights for policy 0, policy_version 123412 (0.0017) [2023-03-09 10:34:38,537][119383] Updated weights for policy 0, policy_version 123423 (0.0018) [2023-03-09 10:34:38,902][118949] Fps is (10 sec: 198250.2, 60 sec: 197427.3, 300 sec: 120001.8). Total num frames: 2022227968. Throughput: 0: 49399.3. Samples: 5565152. Policy #0 lag: (min: 1.0, avg: 17.0, max: 33.0) [2023-03-09 10:34:38,903][118949] Avg episode reward: [(0, '54.781')] [2023-03-09 10:34:39,566][119383] Updated weights for policy 0, policy_version 123433 (0.0024) [2023-03-09 10:34:40,204][119383] Updated weights for policy 0, policy_version 123443 (0.0023) [2023-03-09 10:34:41,074][119383] Updated weights for policy 0, policy_version 123453 (0.0016) [2023-03-09 10:34:42,046][119383] Updated weights for policy 0, policy_version 123463 (0.0030) [2023-03-09 10:34:42,423][119240] Signal inference workers to stop experience collection... (600 times) [2023-03-09 10:34:42,444][119240] Signal inference workers to resume experience collection... (600 times) [2023-03-09 10:34:42,466][119383] InferenceWorker_p0-w0: stopping experience collection (600 times) [2023-03-09 10:34:42,470][119383] InferenceWorker_p0-w0: resuming experience collection (600 times) [2023-03-09 10:34:42,821][119383] Updated weights for policy 0, policy_version 123473 (0.0033) [2023-03-09 10:34:43,664][119383] Updated weights for policy 0, policy_version 123484 (0.0015) [2023-03-09 10:34:43,902][118949] Fps is (10 sec: 196601.0, 60 sec: 197426.7, 300 sec: 121931.4). Total num frames: 2023194624. Throughput: 0: 49354.6. Samples: 5857936. Policy #0 lag: (min: 1.0, avg: 17.0, max: 33.0) [2023-03-09 10:34:43,904][118949] Avg episode reward: [(0, '54.773')] [2023-03-09 10:34:44,513][119383] Updated weights for policy 0, policy_version 123494 (0.0016) [2023-03-09 10:34:45,488][119383] Updated weights for policy 0, policy_version 123505 (0.0017) [2023-03-09 10:34:46,329][119383] Updated weights for policy 0, policy_version 123515 (0.0013) [2023-03-09 10:34:47,213][119383] Updated weights for policy 0, policy_version 123526 (0.0017) [2023-03-09 10:34:48,117][119383] Updated weights for policy 0, policy_version 123536 (0.0020) [2023-03-09 10:34:48,848][119383] Updated weights for policy 0, policy_version 123546 (0.0018) [2023-03-09 10:34:48,902][118949] Fps is (10 sec: 194968.2, 60 sec: 197427.0, 300 sec: 123846.3). Total num frames: 2024177664. Throughput: 0: 49356.3. Samples: 6005360. Policy #0 lag: (min: 1.0, avg: 17.0, max: 33.0) [2023-03-09 10:34:48,904][118949] Avg episode reward: [(0, '55.515')] [2023-03-09 10:34:49,676][119383] Updated weights for policy 0, policy_version 123556 (0.0016) [2023-03-09 10:34:50,687][119383] Updated weights for policy 0, policy_version 123566 (0.0019) [2023-03-09 10:34:51,444][119383] Updated weights for policy 0, policy_version 123576 (0.0021) [2023-03-09 10:34:51,452][119240] Signal inference workers to stop experience collection... (650 times) [2023-03-09 10:34:51,480][119240] Signal inference workers to resume experience collection... (650 times) [2023-03-09 10:34:51,530][119383] InferenceWorker_p0-w0: stopping experience collection (650 times) [2023-03-09 10:34:51,530][119383] InferenceWorker_p0-w0: resuming experience collection (650 times) [2023-03-09 10:34:52,200][119383] Updated weights for policy 0, policy_version 123586 (0.0017) [2023-03-09 10:34:53,224][119383] Updated weights for policy 0, policy_version 123596 (0.0030) [2023-03-09 10:34:53,902][118949] Fps is (10 sec: 196611.1, 60 sec: 197154.3, 300 sec: 125665.3). Total num frames: 2025160704. Throughput: 0: 49221.8. Samples: 6298128. Policy #0 lag: (min: 1.0, avg: 17.0, max: 33.0) [2023-03-09 10:34:53,903][118949] Avg episode reward: [(0, '54.725')] [2023-03-09 10:34:53,922][119383] Updated weights for policy 0, policy_version 123606 (0.0019) [2023-03-09 10:34:54,755][119383] Updated weights for policy 0, policy_version 123616 (0.0026) [2023-03-09 10:34:55,687][119383] Updated weights for policy 0, policy_version 123626 (0.0019) [2023-03-09 10:34:56,466][119383] Updated weights for policy 0, policy_version 123636 (0.0016) [2023-03-09 10:34:57,275][119383] Updated weights for policy 0, policy_version 123646 (0.0017) [2023-03-09 10:34:58,313][119383] Updated weights for policy 0, policy_version 123657 (0.0018) [2023-03-09 10:34:58,902][118949] Fps is (10 sec: 193328.0, 60 sec: 196607.0, 300 sec: 127235.7). Total num frames: 2026110976. Throughput: 0: 48997.4. Samples: 6588896. Policy #0 lag: (min: 1.0, avg: 17.0, max: 33.0) [2023-03-09 10:34:58,905][118949] Avg episode reward: [(0, '55.079')] [2023-03-09 10:34:59,100][119383] Updated weights for policy 0, policy_version 123667 (0.0018) [2023-03-09 10:34:59,918][119383] Updated weights for policy 0, policy_version 123677 (0.0016) [2023-03-09 10:35:00,815][119383] Updated weights for policy 0, policy_version 123687 (0.0016) [2023-03-09 10:35:01,353][119240] Signal inference workers to stop experience collection... (700 times) [2023-03-09 10:35:01,354][119240] Signal inference workers to resume experience collection... (700 times) [2023-03-09 10:35:01,422][119383] InferenceWorker_p0-w0: stopping experience collection (700 times) [2023-03-09 10:35:01,422][119383] InferenceWorker_p0-w0: resuming experience collection (700 times) [2023-03-09 10:35:01,557][119383] Updated weights for policy 0, policy_version 123697 (0.0020) [2023-03-09 10:35:02,337][119383] Updated weights for policy 0, policy_version 123707 (0.0025) [2023-03-09 10:35:03,157][119383] Updated weights for policy 0, policy_version 123717 (0.0040) [2023-03-09 10:35:03,902][118949] Fps is (10 sec: 191689.3, 60 sec: 196333.6, 300 sec: 128809.3). Total num frames: 2027077632. Throughput: 0: 48998.2. Samples: 6738352. Policy #0 lag: (min: 1.0, avg: 17.0, max: 33.0) [2023-03-09 10:35:03,904][118949] Avg episode reward: [(0, '54.347')] [2023-03-09 10:35:04,111][119383] Updated weights for policy 0, policy_version 123727 (0.0017) [2023-03-09 10:35:04,897][119383] Updated weights for policy 0, policy_version 123737 (0.0023) [2023-03-09 10:35:05,606][119383] Updated weights for policy 0, policy_version 123747 (0.0023) [2023-03-09 10:35:06,586][119383] Updated weights for policy 0, policy_version 123757 (0.0011) [2023-03-09 10:35:07,243][119383] Updated weights for policy 0, policy_version 123767 (0.0018) [2023-03-09 10:35:08,064][119383] Updated weights for policy 0, policy_version 123777 (0.0024) [2023-03-09 10:35:08,902][118949] Fps is (10 sec: 196614.5, 60 sec: 196337.2, 300 sec: 130462.5). Total num frames: 2028077056. Throughput: 0: 49043.4. Samples: 7037248. Policy #0 lag: (min: 1.0, avg: 17.0, max: 33.0) [2023-03-09 10:35:08,903][118949] Avg episode reward: [(0, '54.189')] [2023-03-09 10:35:09,078][119383] Updated weights for policy 0, policy_version 123787 (0.0013) [2023-03-09 10:35:09,814][119383] Updated weights for policy 0, policy_version 123797 (0.0026) [2023-03-09 10:35:10,679][119383] Updated weights for policy 0, policy_version 123807 (0.0018) [2023-03-09 10:35:11,606][119383] Updated weights for policy 0, policy_version 123818 (0.0013) [2023-03-09 10:35:11,850][119240] Signal inference workers to stop experience collection... (750 times) [2023-03-09 10:35:11,855][119240] Signal inference workers to resume experience collection... (750 times) [2023-03-09 10:35:11,928][119383] InferenceWorker_p0-w0: stopping experience collection (750 times) [2023-03-09 10:35:11,928][119383] InferenceWorker_p0-w0: resuming experience collection (750 times) [2023-03-09 10:35:12,393][119383] Updated weights for policy 0, policy_version 123828 (0.0027) [2023-03-09 10:35:13,215][119383] Updated weights for policy 0, policy_version 123838 (0.0016) [2023-03-09 10:35:13,902][118949] Fps is (10 sec: 199892.8, 60 sec: 196063.0, 300 sec: 132040.3). Total num frames: 2029076480. Throughput: 0: 49001.9. Samples: 7330080. Policy #0 lag: (min: 1.0, avg: 17.0, max: 33.0) [2023-03-09 10:35:13,903][118949] Avg episode reward: [(0, '55.561')] [2023-03-09 10:35:14,241][119383] Updated weights for policy 0, policy_version 123848 (0.0013) [2023-03-09 10:35:14,932][119383] Updated weights for policy 0, policy_version 123858 (0.0031) [2023-03-09 10:35:15,787][119383] Updated weights for policy 0, policy_version 123868 (0.0019) [2023-03-09 10:35:16,601][119383] Updated weights for policy 0, policy_version 123878 (0.0018) [2023-03-09 10:35:17,503][119383] Updated weights for policy 0, policy_version 123888 (0.0022) [2023-03-09 10:35:18,253][119383] Updated weights for policy 0, policy_version 123898 (0.0017) [2023-03-09 10:35:18,902][118949] Fps is (10 sec: 198246.6, 60 sec: 196062.6, 300 sec: 133475.1). Total num frames: 2030059520. Throughput: 0: 49047.5. Samples: 7477504. Policy #0 lag: (min: 1.0, avg: 17.0, max: 33.0) [2023-03-09 10:35:18,903][118949] Avg episode reward: [(0, '56.354')] [2023-03-09 10:35:19,079][119383] Updated weights for policy 0, policy_version 123908 (0.0016) [2023-03-09 10:35:20,106][119383] Updated weights for policy 0, policy_version 123918 (0.0021) [2023-03-09 10:35:20,842][119383] Updated weights for policy 0, policy_version 123928 (0.0018) [2023-03-09 10:35:21,642][119383] Updated weights for policy 0, policy_version 123938 (0.0016) [2023-03-09 10:35:22,248][119240] Signal inference workers to stop experience collection... (800 times) [2023-03-09 10:35:22,253][119240] Signal inference workers to resume experience collection... (800 times) [2023-03-09 10:35:22,310][119383] InferenceWorker_p0-w0: stopping experience collection (800 times) [2023-03-09 10:35:22,311][119383] InferenceWorker_p0-w0: resuming experience collection (800 times) [2023-03-09 10:35:22,628][119383] Updated weights for policy 0, policy_version 123948 (0.0023) [2023-03-09 10:35:23,315][119383] Updated weights for policy 0, policy_version 123958 (0.0017) [2023-03-09 10:35:23,902][118949] Fps is (10 sec: 196597.5, 60 sec: 196060.7, 300 sec: 134847.3). Total num frames: 2031042560. Throughput: 0: 48957.4. Samples: 7768256. Policy #0 lag: (min: 1.0, avg: 17.2, max: 33.0) [2023-03-09 10:35:23,905][118949] Avg episode reward: [(0, '55.375')] [2023-03-09 10:35:23,912][119240] Saving /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000123965_2031042560.pth... [2023-03-09 10:35:23,979][119240] Removing /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000122072_2000027648.pth [2023-03-09 10:35:24,216][119383] Updated weights for policy 0, policy_version 123969 (0.0016) [2023-03-09 10:35:25,203][119383] Updated weights for policy 0, policy_version 123979 (0.0016) [2023-03-09 10:35:25,953][119383] Updated weights for policy 0, policy_version 123989 (0.0019) [2023-03-09 10:35:26,801][119383] Updated weights for policy 0, policy_version 123999 (0.0018) [2023-03-09 10:35:27,722][119383] Updated weights for policy 0, policy_version 124009 (0.0015) [2023-03-09 10:35:28,480][119383] Updated weights for policy 0, policy_version 124019 (0.0047) [2023-03-09 10:35:28,902][118949] Fps is (10 sec: 194964.3, 60 sec: 196062.0, 300 sec: 136091.8). Total num frames: 2032009216. Throughput: 0: 48957.3. Samples: 8061008. Policy #0 lag: (min: 1.0, avg: 17.2, max: 33.0) [2023-03-09 10:35:28,904][118949] Avg episode reward: [(0, '56.110')] [2023-03-09 10:35:29,265][119383] Updated weights for policy 0, policy_version 124029 (0.0016) [2023-03-09 10:35:30,228][119383] Updated weights for policy 0, policy_version 124039 (0.0013) [2023-03-09 10:35:30,996][119383] Updated weights for policy 0, policy_version 124049 (0.0021) [2023-03-09 10:35:31,645][119240] Signal inference workers to stop experience collection... (850 times) [2023-03-09 10:35:31,669][119240] Signal inference workers to resume experience collection... (850 times) [2023-03-09 10:35:31,672][119383] InferenceWorker_p0-w0: stopping experience collection (850 times) [2023-03-09 10:35:31,672][119383] InferenceWorker_p0-w0: resuming experience collection (850 times) [2023-03-09 10:35:31,843][119383] Updated weights for policy 0, policy_version 124059 (0.0018) [2023-03-09 10:35:32,586][119383] Updated weights for policy 0, policy_version 124069 (0.0018) [2023-03-09 10:35:33,640][119383] Updated weights for policy 0, policy_version 124080 (0.0014) [2023-03-09 10:35:33,902][118949] Fps is (10 sec: 193340.6, 60 sec: 195788.7, 300 sec: 137284.4). Total num frames: 2032975872. Throughput: 0: 48912.1. Samples: 8206400. Policy #0 lag: (min: 1.0, avg: 17.2, max: 33.0) [2023-03-09 10:35:33,903][118949] Avg episode reward: [(0, '54.392')] [2023-03-09 10:35:34,371][119383] Updated weights for policy 0, policy_version 124090 (0.0013) [2023-03-09 10:35:35,172][119383] Updated weights for policy 0, policy_version 124100 (0.0013) [2023-03-09 10:35:36,120][119383] Updated weights for policy 0, policy_version 124110 (0.0020) [2023-03-09 10:35:36,970][119383] Updated weights for policy 0, policy_version 124120 (0.0016) [2023-03-09 10:35:37,721][119383] Updated weights for policy 0, policy_version 124130 (0.0024) [2023-03-09 10:35:38,696][119383] Updated weights for policy 0, policy_version 124140 (0.0019) [2023-03-09 10:35:38,902][118949] Fps is (10 sec: 194974.7, 60 sec: 195516.0, 300 sec: 138495.1). Total num frames: 2033958912. Throughput: 0: 48957.4. Samples: 8501200. Policy #0 lag: (min: 1.0, avg: 17.2, max: 33.0) [2023-03-09 10:35:38,902][118949] Avg episode reward: [(0, '53.900')] [2023-03-09 10:35:39,437][119383] Updated weights for policy 0, policy_version 124150 (0.0025) [2023-03-09 10:35:40,203][119383] Updated weights for policy 0, policy_version 124160 (0.0028) [2023-03-09 10:35:40,346][119240] Signal inference workers to stop experience collection... (900 times) [2023-03-09 10:35:40,347][119240] Signal inference workers to resume experience collection... (900 times) [2023-03-09 10:35:40,407][119383] InferenceWorker_p0-w0: stopping experience collection (900 times) [2023-03-09 10:35:40,408][119383] InferenceWorker_p0-w0: resuming experience collection (900 times) [2023-03-09 10:35:41,123][119383] Updated weights for policy 0, policy_version 124170 (0.0014) [2023-03-09 10:35:41,967][119383] Updated weights for policy 0, policy_version 124180 (0.0013) [2023-03-09 10:35:42,717][119383] Updated weights for policy 0, policy_version 124190 (0.0035) [2023-03-09 10:35:43,690][119383] Updated weights for policy 0, policy_version 124200 (0.0013) [2023-03-09 10:35:43,902][118949] Fps is (10 sec: 194970.8, 60 sec: 195517.0, 300 sec: 139591.8). Total num frames: 2034925568. Throughput: 0: 49093.3. Samples: 8798080. Policy #0 lag: (min: 1.0, avg: 17.2, max: 33.0) [2023-03-09 10:35:43,903][118949] Avg episode reward: [(0, '53.361')] [2023-03-09 10:35:44,367][119383] Updated weights for policy 0, policy_version 124210 (0.0022) [2023-03-09 10:35:45,226][119383] Updated weights for policy 0, policy_version 124220 (0.0024) [2023-03-09 10:35:46,031][119383] Updated weights for policy 0, policy_version 124230 (0.0013) [2023-03-09 10:35:46,966][119383] Updated weights for policy 0, policy_version 124240 (0.0027) [2023-03-09 10:35:47,712][119383] Updated weights for policy 0, policy_version 124250 (0.0016) [2023-03-09 10:35:48,484][119383] Updated weights for policy 0, policy_version 124260 (0.0017) [2023-03-09 10:35:48,902][118949] Fps is (10 sec: 196608.2, 60 sec: 195789.4, 300 sec: 140774.0). Total num frames: 2035924992. Throughput: 0: 49048.6. Samples: 8945520. Policy #0 lag: (min: 1.0, avg: 17.2, max: 33.0) [2023-03-09 10:35:48,903][118949] Avg episode reward: [(0, '55.122')] [2023-03-09 10:35:49,485][119383] Updated weights for policy 0, policy_version 124270 (0.0028) [2023-03-09 10:35:50,238][119240] Signal inference workers to stop experience collection... (950 times) [2023-03-09 10:35:50,244][119240] Signal inference workers to resume experience collection... (950 times) [2023-03-09 10:35:50,272][119383] Updated weights for policy 0, policy_version 124280 (0.0025) [2023-03-09 10:35:50,319][119383] InferenceWorker_p0-w0: stopping experience collection (950 times) [2023-03-09 10:35:50,321][119383] InferenceWorker_p0-w0: resuming experience collection (950 times) [2023-03-09 10:35:51,058][119383] Updated weights for policy 0, policy_version 124290 (0.0015) [2023-03-09 10:35:52,032][119383] Updated weights for policy 0, policy_version 124300 (0.0016) [2023-03-09 10:35:52,738][119383] Updated weights for policy 0, policy_version 124310 (0.0013) [2023-03-09 10:35:53,573][119383] Updated weights for policy 0, policy_version 124320 (0.0024) [2023-03-09 10:35:53,902][118949] Fps is (10 sec: 201516.4, 60 sec: 196334.6, 300 sec: 141973.6). Total num frames: 2036940800. Throughput: 0: 48956.8. Samples: 9240320. Policy #0 lag: (min: 1.0, avg: 17.2, max: 33.0) [2023-03-09 10:35:53,904][118949] Avg episode reward: [(0, '55.155')] [2023-03-09 10:35:54,456][119383] Updated weights for policy 0, policy_version 124330 (0.0013) [2023-03-09 10:35:55,311][119383] Updated weights for policy 0, policy_version 124340 (0.0016) [2023-03-09 10:35:56,062][119383] Updated weights for policy 0, policy_version 124350 (0.0024) [2023-03-09 10:35:57,032][119383] Updated weights for policy 0, policy_version 124360 (0.0013) [2023-03-09 10:35:57,762][119383] Updated weights for policy 0, policy_version 124370 (0.0013) [2023-03-09 10:35:58,597][119383] Updated weights for policy 0, policy_version 124380 (0.0026) [2023-03-09 10:35:58,902][118949] Fps is (10 sec: 196607.4, 60 sec: 196335.9, 300 sec: 142881.0). Total num frames: 2037891072. Throughput: 0: 48955.7. Samples: 9533088. Policy #0 lag: (min: 1.0, avg: 17.2, max: 33.0) [2023-03-09 10:35:58,903][118949] Avg episode reward: [(0, '56.221')] [2023-03-09 10:35:59,594][119383] Updated weights for policy 0, policy_version 124391 (0.0026) [2023-03-09 10:36:00,266][119240] Signal inference workers to stop experience collection... (1000 times) [2023-03-09 10:36:00,294][119240] Signal inference workers to resume experience collection... (1000 times) [2023-03-09 10:36:00,330][119383] InferenceWorker_p0-w0: stopping experience collection (1000 times) [2023-03-09 10:36:00,371][119383] InferenceWorker_p0-w0: resuming experience collection (1000 times) [2023-03-09 10:36:00,374][119383] Updated weights for policy 0, policy_version 124401 (0.0016) [2023-03-09 10:36:01,234][119383] Updated weights for policy 0, policy_version 124411 (0.0026) [2023-03-09 10:36:01,929][119383] Updated weights for policy 0, policy_version 124421 (0.0022) [2023-03-09 10:36:02,935][119383] Updated weights for policy 0, policy_version 124431 (0.0019) [2023-03-09 10:36:03,678][119383] Updated weights for policy 0, policy_version 124441 (0.0016) [2023-03-09 10:36:03,902][118949] Fps is (10 sec: 194972.7, 60 sec: 196881.8, 300 sec: 143936.5). Total num frames: 2038890496. Throughput: 0: 48955.9. Samples: 9680528. Policy #0 lag: (min: 1.0, avg: 17.2, max: 33.0) [2023-03-09 10:36:03,904][118949] Avg episode reward: [(0, '56.054')] [2023-03-09 10:36:04,407][119383] Updated weights for policy 0, policy_version 124451 (0.0021) [2023-03-09 10:36:05,412][119383] Updated weights for policy 0, policy_version 124461 (0.0013) [2023-03-09 10:36:06,149][119383] Updated weights for policy 0, policy_version 124471 (0.0013) [2023-03-09 10:36:06,953][119383] Updated weights for policy 0, policy_version 124481 (0.0016) [2023-03-09 10:36:07,940][119383] Updated weights for policy 0, policy_version 124491 (0.0023) [2023-03-09 10:36:08,797][119383] Updated weights for policy 0, policy_version 124502 (0.0014) [2023-03-09 10:36:08,902][118949] Fps is (10 sec: 196607.9, 60 sec: 196334.8, 300 sec: 144834.7). Total num frames: 2039857152. Throughput: 0: 49046.6. Samples: 9975328. Policy #0 lag: (min: 1.0, avg: 17.2, max: 33.0) [2023-03-09 10:36:08,903][118949] Avg episode reward: [(0, '56.082')] [2023-03-09 10:36:09,596][119383] Updated weights for policy 0, policy_version 124512 (0.0020) [2023-03-09 10:36:10,511][119383] Updated weights for policy 0, policy_version 124522 (0.0028) [2023-03-09 10:36:10,976][119240] Signal inference workers to stop experience collection... (1050 times) [2023-03-09 10:36:11,001][119240] Signal inference workers to resume experience collection... (1050 times) [2023-03-09 10:36:11,046][119383] InferenceWorker_p0-w0: stopping experience collection (1050 times) [2023-03-09 10:36:11,046][119383] InferenceWorker_p0-w0: resuming experience collection (1050 times) [2023-03-09 10:36:11,298][119383] Updated weights for policy 0, policy_version 124532 (0.0034) [2023-03-09 10:36:12,105][119383] Updated weights for policy 0, policy_version 124542 (0.0015) [2023-03-09 10:36:13,074][119383] Updated weights for policy 0, policy_version 124552 (0.0022) [2023-03-09 10:36:13,781][119383] Updated weights for policy 0, policy_version 124562 (0.0024) [2023-03-09 10:36:13,902][118949] Fps is (10 sec: 194969.4, 60 sec: 196061.3, 300 sec: 145759.1). Total num frames: 2040840192. Throughput: 0: 49092.0. Samples: 10270144. Policy #0 lag: (min: 1.0, avg: 17.2, max: 33.0) [2023-03-09 10:36:13,903][118949] Avg episode reward: [(0, '54.532')] [2023-03-09 10:36:14,681][119383] Updated weights for policy 0, policy_version 124572 (0.0020) [2023-03-09 10:36:15,486][119383] Updated weights for policy 0, policy_version 124582 (0.0022) [2023-03-09 10:36:16,337][119383] Updated weights for policy 0, policy_version 124592 (0.0018) [2023-03-09 10:36:17,147][119383] Updated weights for policy 0, policy_version 124602 (0.0015) [2023-03-09 10:36:17,890][119383] Updated weights for policy 0, policy_version 124612 (0.0017) [2023-03-09 10:36:18,833][119383] Updated weights for policy 0, policy_version 124622 (0.0013) [2023-03-09 10:36:18,902][118949] Fps is (10 sec: 194968.6, 60 sec: 195788.5, 300 sec: 146593.8). Total num frames: 2041806848. Throughput: 0: 49091.9. Samples: 10415536. Policy #0 lag: (min: 1.0, avg: 17.2, max: 33.0) [2023-03-09 10:36:18,903][118949] Avg episode reward: [(0, '56.074')] [2023-03-09 10:36:19,666][119383] Updated weights for policy 0, policy_version 124632 (0.0016) [2023-03-09 10:36:20,451][119383] Updated weights for policy 0, policy_version 124643 (0.0013) [2023-03-09 10:36:21,446][119383] Updated weights for policy 0, policy_version 124653 (0.0017) [2023-03-09 10:36:21,565][119240] Signal inference workers to stop experience collection... (1100 times) [2023-03-09 10:36:21,580][119240] Signal inference workers to resume experience collection... (1100 times) [2023-03-09 10:36:21,648][119383] InferenceWorker_p0-w0: stopping experience collection (1100 times) [2023-03-09 10:36:21,648][119383] InferenceWorker_p0-w0: resuming experience collection (1100 times) [2023-03-09 10:36:22,149][119383] Updated weights for policy 0, policy_version 124663 (0.0013) [2023-03-09 10:36:22,963][119383] Updated weights for policy 0, policy_version 124673 (0.0018) [2023-03-09 10:36:23,902][118949] Fps is (10 sec: 194973.1, 60 sec: 195790.6, 300 sec: 147456.1). Total num frames: 2042789888. Throughput: 0: 49138.1. Samples: 10712416. Policy #0 lag: (min: 1.0, avg: 17.2, max: 33.0) [2023-03-09 10:36:23,903][118949] Avg episode reward: [(0, '54.367')] [2023-03-09 10:36:23,917][119383] Updated weights for policy 0, policy_version 124683 (0.0020) [2023-03-09 10:36:24,744][119383] Updated weights for policy 0, policy_version 124693 (0.0020) [2023-03-09 10:36:25,583][119383] Updated weights for policy 0, policy_version 124703 (0.0013) [2023-03-09 10:36:26,475][119383] Updated weights for policy 0, policy_version 124713 (0.0015) [2023-03-09 10:36:27,179][119383] Updated weights for policy 0, policy_version 124723 (0.0016) [2023-03-09 10:36:28,022][119383] Updated weights for policy 0, policy_version 124733 (0.0021) [2023-03-09 10:36:28,902][118949] Fps is (10 sec: 196609.6, 60 sec: 196062.7, 300 sec: 148289.2). Total num frames: 2043772928. Throughput: 0: 49093.3. Samples: 11007280. Policy #0 lag: (min: 1.0, avg: 17.2, max: 33.0) [2023-03-09 10:36:28,903][118949] Avg episode reward: [(0, '53.627')] [2023-03-09 10:36:28,917][119383] Updated weights for policy 0, policy_version 124743 (0.0026) [2023-03-09 10:36:29,766][119383] Updated weights for policy 0, policy_version 124754 (0.0013) [2023-03-09 10:36:30,641][119383] Updated weights for policy 0, policy_version 124764 (0.0013) [2023-03-09 10:36:31,629][119383] Updated weights for policy 0, policy_version 124775 (0.0013) [2023-03-09 10:36:32,263][119240] Signal inference workers to stop experience collection... (1150 times) [2023-03-09 10:36:32,267][119240] Signal inference workers to resume experience collection... (1150 times) [2023-03-09 10:36:32,337][119383] InferenceWorker_p0-w0: stopping experience collection (1150 times) [2023-03-09 10:36:32,337][119383] InferenceWorker_p0-w0: resuming experience collection (1150 times) [2023-03-09 10:36:32,409][119383] Updated weights for policy 0, policy_version 124785 (0.0027) [2023-03-09 10:36:33,239][119383] Updated weights for policy 0, policy_version 124795 (0.0024) [2023-03-09 10:36:33,902][118949] Fps is (10 sec: 199879.7, 60 sec: 196880.4, 300 sec: 151732.4). Total num frames: 2044788736. Throughput: 0: 49092.3. Samples: 11154688. Policy #0 lag: (min: 1.0, avg: 17.2, max: 33.0) [2023-03-09 10:36:33,904][118949] Avg episode reward: [(0, '52.172')] [2023-03-09 10:36:33,990][119383] Updated weights for policy 0, policy_version 124805 (0.0025) [2023-03-09 10:36:35,003][119383] Updated weights for policy 0, policy_version 124815 (0.0023) [2023-03-09 10:36:35,758][119383] Updated weights for policy 0, policy_version 124825 (0.0027) [2023-03-09 10:36:36,522][119383] Updated weights for policy 0, policy_version 124835 (0.0016) [2023-03-09 10:36:37,549][119383] Updated weights for policy 0, policy_version 124845 (0.0016) [2023-03-09 10:36:38,279][119383] Updated weights for policy 0, policy_version 124855 (0.0026) [2023-03-09 10:36:38,902][118949] Fps is (10 sec: 196599.5, 60 sec: 196333.5, 300 sec: 154953.6). Total num frames: 2045739008. Throughput: 0: 49001.9. Samples: 11445408. Policy #0 lag: (min: 1.0, avg: 17.2, max: 33.0) [2023-03-09 10:36:38,904][118949] Avg episode reward: [(0, '54.984')] [2023-03-09 10:36:39,067][119383] Updated weights for policy 0, policy_version 124865 (0.0013) [2023-03-09 10:36:40,030][119383] Updated weights for policy 0, policy_version 124875 (0.0019) [2023-03-09 10:36:40,778][119383] Updated weights for policy 0, policy_version 124885 (0.0017) [2023-03-09 10:36:41,603][119383] Updated weights for policy 0, policy_version 124895 (0.0019) [2023-03-09 10:36:42,515][119383] Updated weights for policy 0, policy_version 124905 (0.0013) [2023-03-09 10:36:43,261][119383] Updated weights for policy 0, policy_version 124915 (0.0021) [2023-03-09 10:36:43,711][119240] Signal inference workers to stop experience collection... (1200 times) [2023-03-09 10:36:43,715][119240] Signal inference workers to resume experience collection... (1200 times) [2023-03-09 10:36:43,768][119383] InferenceWorker_p0-w0: stopping experience collection (1200 times) [2023-03-09 10:36:43,811][119383] InferenceWorker_p0-w0: resuming experience collection (1200 times) [2023-03-09 10:36:43,902][118949] Fps is (10 sec: 193328.7, 60 sec: 196606.7, 300 sec: 158286.0). Total num frames: 2046722048. Throughput: 0: 49047.8. Samples: 11740256. Policy #0 lag: (min: 1.0, avg: 17.2, max: 33.0) [2023-03-09 10:36:43,904][118949] Avg episode reward: [(0, '54.345')] [2023-03-09 10:36:44,111][119383] Updated weights for policy 0, policy_version 124925 (0.0030) [2023-03-09 10:36:45,012][119383] Updated weights for policy 0, policy_version 124935 (0.0016) [2023-03-09 10:36:45,783][119383] Updated weights for policy 0, policy_version 124945 (0.0018) [2023-03-09 10:36:46,611][119383] Updated weights for policy 0, policy_version 124955 (0.0013) [2023-03-09 10:36:47,427][119383] Updated weights for policy 0, policy_version 124965 (0.0016) [2023-03-09 10:36:48,370][119383] Updated weights for policy 0, policy_version 124975 (0.0026) [2023-03-09 10:36:48,902][118949] Fps is (10 sec: 196615.4, 60 sec: 196334.7, 300 sec: 161618.5). Total num frames: 2047705088. Throughput: 0: 49047.6. Samples: 11887664. Policy #0 lag: (min: 1.0, avg: 17.2, max: 33.0) [2023-03-09 10:36:48,903][118949] Avg episode reward: [(0, '53.640')] [2023-03-09 10:36:49,125][119383] Updated weights for policy 0, policy_version 124985 (0.0017) [2023-03-09 10:36:49,938][119383] Updated weights for policy 0, policy_version 124995 (0.0019) [2023-03-09 10:36:50,893][119383] Updated weights for policy 0, policy_version 125005 (0.0017) [2023-03-09 10:36:51,639][119383] Updated weights for policy 0, policy_version 125015 (0.0013) [2023-03-09 10:36:52,434][119383] Updated weights for policy 0, policy_version 125025 (0.0013) [2023-03-09 10:36:53,385][119383] Updated weights for policy 0, policy_version 125035 (0.0018) [2023-03-09 10:36:53,902][118949] Fps is (10 sec: 196614.5, 60 sec: 195789.7, 300 sec: 164950.8). Total num frames: 2048688128. Throughput: 0: 49003.0. Samples: 12180464. Policy #0 lag: (min: 1.0, avg: 17.2, max: 33.0) [2023-03-09 10:36:53,903][118949] Avg episode reward: [(0, '53.983')] [2023-03-09 10:36:54,136][119383] Updated weights for policy 0, policy_version 125045 (0.0016) [2023-03-09 10:36:55,024][119383] Updated weights for policy 0, policy_version 125055 (0.0018) [2023-03-09 10:36:55,913][119383] Updated weights for policy 0, policy_version 125065 (0.0016) [2023-03-09 10:36:56,227][119240] Signal inference workers to stop experience collection... (1250 times) [2023-03-09 10:36:56,228][119240] Signal inference workers to resume experience collection... (1250 times) [2023-03-09 10:36:56,292][119383] InferenceWorker_p0-w0: stopping experience collection (1250 times) [2023-03-09 10:36:56,293][119383] InferenceWorker_p0-w0: resuming experience collection (1250 times) [2023-03-09 10:36:56,652][119383] Updated weights for policy 0, policy_version 125075 (0.0017) [2023-03-09 10:36:57,485][119383] Updated weights for policy 0, policy_version 125085 (0.0026) [2023-03-09 10:36:58,430][119383] Updated weights for policy 0, policy_version 125095 (0.0013) [2023-03-09 10:36:58,902][118949] Fps is (10 sec: 193331.8, 60 sec: 195788.8, 300 sec: 168172.2). Total num frames: 2049638400. Throughput: 0: 49003.2. Samples: 12475280. Policy #0 lag: (min: 1.0, avg: 17.2, max: 33.0) [2023-03-09 10:36:58,903][118949] Avg episode reward: [(0, '55.022')] [2023-03-09 10:36:59,200][119383] Updated weights for policy 0, policy_version 125105 (0.0026) [2023-03-09 10:36:59,972][119383] Updated weights for policy 0, policy_version 125115 (0.0023) [2023-03-09 10:37:00,789][119383] Updated weights for policy 0, policy_version 125125 (0.0013) [2023-03-09 10:37:01,730][119383] Updated weights for policy 0, policy_version 125135 (0.0016) [2023-03-09 10:37:02,497][119383] Updated weights for policy 0, policy_version 125145 (0.0018) [2023-03-09 10:37:03,286][119383] Updated weights for policy 0, policy_version 125155 (0.0020) [2023-03-09 10:37:03,902][118949] Fps is (10 sec: 193330.6, 60 sec: 195516.0, 300 sec: 171504.4). Total num frames: 2050621440. Throughput: 0: 49047.8. Samples: 12622688. Policy #0 lag: (min: 1.0, avg: 17.2, max: 33.0) [2023-03-09 10:37:03,903][118949] Avg episode reward: [(0, '53.367')] [2023-03-09 10:37:04,300][119383] Updated weights for policy 0, policy_version 125165 (0.0013) [2023-03-09 10:37:04,988][119383] Updated weights for policy 0, policy_version 125175 (0.0022) [2023-03-09 10:37:05,773][119383] Updated weights for policy 0, policy_version 125185 (0.0016) [2023-03-09 10:37:06,746][119383] Updated weights for policy 0, policy_version 125195 (0.0013) [2023-03-09 10:37:07,529][119383] Updated weights for policy 0, policy_version 125205 (0.0024) [2023-03-09 10:37:07,778][119240] Signal inference workers to stop experience collection... (1300 times) [2023-03-09 10:37:07,780][119240] Signal inference workers to resume experience collection... (1300 times) [2023-03-09 10:37:07,846][119383] InferenceWorker_p0-w0: stopping experience collection (1300 times) [2023-03-09 10:37:07,847][119383] InferenceWorker_p0-w0: resuming experience collection (1300 times) [2023-03-09 10:37:08,344][119383] Updated weights for policy 0, policy_version 125215 (0.0013) [2023-03-09 10:37:08,902][118949] Fps is (10 sec: 198246.1, 60 sec: 196061.8, 300 sec: 174892.4). Total num frames: 2051620864. Throughput: 0: 48955.7. Samples: 12915424. Policy #0 lag: (min: 1.0, avg: 17.2, max: 33.0) [2023-03-09 10:37:08,903][118949] Avg episode reward: [(0, '53.619')] [2023-03-09 10:37:09,299][119383] Updated weights for policy 0, policy_version 125225 (0.0013) [2023-03-09 10:37:10,001][119383] Updated weights for policy 0, policy_version 125235 (0.0027) [2023-03-09 10:37:10,843][119383] Updated weights for policy 0, policy_version 125245 (0.0023) [2023-03-09 10:37:11,738][119383] Updated weights for policy 0, policy_version 125255 (0.0016) [2023-03-09 10:37:12,599][119383] Updated weights for policy 0, policy_version 125266 (0.0018) [2023-03-09 10:37:13,430][119383] Updated weights for policy 0, policy_version 125276 (0.0018) [2023-03-09 10:37:13,902][118949] Fps is (10 sec: 199881.0, 60 sec: 196334.6, 300 sec: 178224.5). Total num frames: 2052620288. Throughput: 0: 48954.0. Samples: 13210224. Policy #0 lag: (min: 1.0, avg: 17.2, max: 33.0) [2023-03-09 10:37:13,904][118949] Avg episode reward: [(0, '55.520')] [2023-03-09 10:37:14,312][119383] Updated weights for policy 0, policy_version 125286 (0.0024) [2023-03-09 10:37:15,189][119383] Updated weights for policy 0, policy_version 125296 (0.0034) [2023-03-09 10:37:16,113][119383] Updated weights for policy 0, policy_version 125308 (0.0016) [2023-03-09 10:37:16,945][119383] Updated weights for policy 0, policy_version 125318 (0.0020) [2023-03-09 10:37:17,896][119240] Signal inference workers to stop experience collection... (1350 times) [2023-03-09 10:37:17,913][119240] Signal inference workers to resume experience collection... (1350 times) [2023-03-09 10:37:17,940][119383] InferenceWorker_p0-w0: stopping experience collection (1350 times) [2023-03-09 10:37:17,955][119383] Updated weights for policy 0, policy_version 125329 (0.0031) [2023-03-09 10:37:17,984][119383] InferenceWorker_p0-w0: resuming experience collection (1350 times) [2023-03-09 10:37:18,689][119383] Updated weights for policy 0, policy_version 125339 (0.0016) [2023-03-09 10:37:18,902][118949] Fps is (10 sec: 196603.8, 60 sec: 196334.4, 300 sec: 181390.2). Total num frames: 2053586944. Throughput: 0: 48954.3. Samples: 13357632. Policy #0 lag: (min: 1.0, avg: 17.2, max: 33.0) [2023-03-09 10:37:18,904][118949] Avg episode reward: [(0, '54.600')] [2023-03-09 10:37:19,655][119383] Updated weights for policy 0, policy_version 125350 (0.0025) [2023-03-09 10:37:20,504][119383] Updated weights for policy 0, policy_version 125360 (0.0028) [2023-03-09 10:37:21,247][119383] Updated weights for policy 0, policy_version 125370 (0.0013) [2023-03-09 10:37:22,040][119383] Updated weights for policy 0, policy_version 125380 (0.0017) [2023-03-09 10:37:23,016][119383] Updated weights for policy 0, policy_version 125390 (0.0020) [2023-03-09 10:37:23,887][119383] Updated weights for policy 0, policy_version 125401 (0.0022) [2023-03-09 10:37:23,902][118949] Fps is (10 sec: 196608.1, 60 sec: 196607.1, 300 sec: 184556.0). Total num frames: 2054586368. Throughput: 0: 49045.5. Samples: 13652448. Policy #0 lag: (min: 1.0, avg: 17.2, max: 33.0) [2023-03-09 10:37:23,903][118949] Avg episode reward: [(0, '54.548')] [2023-03-09 10:37:23,910][119240] Saving /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000125402_2054586368.pth... [2023-03-09 10:37:23,970][119240] Removing /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000122528_2007498752.pth [2023-03-09 10:37:24,668][119383] Updated weights for policy 0, policy_version 125411 (0.0027) [2023-03-09 10:37:25,686][119383] Updated weights for policy 0, policy_version 125421 (0.0017) [2023-03-09 10:37:26,395][119383] Updated weights for policy 0, policy_version 125431 (0.0013) [2023-03-09 10:37:27,197][119383] Updated weights for policy 0, policy_version 125441 (0.0019) [2023-03-09 10:37:28,127][119383] Updated weights for policy 0, policy_version 125451 (0.0016) [2023-03-09 10:37:28,902][118949] Fps is (10 sec: 194974.3, 60 sec: 196061.8, 300 sec: 187333.1). Total num frames: 2055536640. Throughput: 0: 48999.5. Samples: 13945216. Policy #0 lag: (min: 1.0, avg: 17.1, max: 33.0) [2023-03-09 10:37:28,903][118949] Avg episode reward: [(0, '53.520')] [2023-03-09 10:37:28,952][119240] Signal inference workers to stop experience collection... (1400 times) [2023-03-09 10:37:28,967][119240] Signal inference workers to resume experience collection... (1400 times) [2023-03-09 10:37:28,996][119383] Updated weights for policy 0, policy_version 125461 (0.0037) [2023-03-09 10:37:29,031][119383] InferenceWorker_p0-w0: stopping experience collection (1400 times) [2023-03-09 10:37:29,031][119383] InferenceWorker_p0-w0: resuming experience collection (1400 times) [2023-03-09 10:37:29,853][119383] Updated weights for policy 0, policy_version 125472 (0.0013) [2023-03-09 10:37:30,792][119383] Updated weights for policy 0, policy_version 125482 (0.0016) [2023-03-09 10:37:31,587][119383] Updated weights for policy 0, policy_version 125492 (0.0018) [2023-03-09 10:37:32,387][119383] Updated weights for policy 0, policy_version 125502 (0.0013) [2023-03-09 10:37:33,372][119383] Updated weights for policy 0, policy_version 125512 (0.0025) [2023-03-09 10:37:33,902][118949] Fps is (10 sec: 191690.1, 60 sec: 195242.2, 300 sec: 189943.1). Total num frames: 2056503296. Throughput: 0: 48953.2. Samples: 14090576. Policy #0 lag: (min: 1.0, avg: 17.1, max: 33.0) [2023-03-09 10:37:33,904][118949] Avg episode reward: [(0, '54.452')] [2023-03-09 10:37:34,066][119383] Updated weights for policy 0, policy_version 125522 (0.0016) [2023-03-09 10:37:34,894][119383] Updated weights for policy 0, policy_version 125532 (0.0013) [2023-03-09 10:37:35,714][119383] Updated weights for policy 0, policy_version 125542 (0.0019) [2023-03-09 10:37:36,621][119383] Updated weights for policy 0, policy_version 125552 (0.0016) [2023-03-09 10:37:37,350][119383] Updated weights for policy 0, policy_version 125562 (0.0017) [2023-03-09 10:37:38,132][119383] Updated weights for policy 0, policy_version 125572 (0.0013) [2023-03-09 10:37:38,902][118949] Fps is (10 sec: 194970.0, 60 sec: 195790.2, 300 sec: 192276.1). Total num frames: 2057486336. Throughput: 0: 48953.7. Samples: 14383376. Policy #0 lag: (min: 1.0, avg: 17.1, max: 33.0) [2023-03-09 10:37:38,903][118949] Avg episode reward: [(0, '54.645')] [2023-03-09 10:37:39,164][119383] Updated weights for policy 0, policy_version 125582 (0.0016) [2023-03-09 10:37:39,912][119383] Updated weights for policy 0, policy_version 125592 (0.0013) [2023-03-09 10:37:40,379][119240] Signal inference workers to stop experience collection... (1450 times) [2023-03-09 10:37:40,380][119240] Signal inference workers to resume experience collection... (1450 times) [2023-03-09 10:37:40,450][119383] InferenceWorker_p0-w0: stopping experience collection (1450 times) [2023-03-09 10:37:40,451][119383] InferenceWorker_p0-w0: resuming experience collection (1450 times) [2023-03-09 10:37:40,697][119383] Updated weights for policy 0, policy_version 125602 (0.0017) [2023-03-09 10:37:41,617][119383] Updated weights for policy 0, policy_version 125612 (0.0024) [2023-03-09 10:37:42,463][119383] Updated weights for policy 0, policy_version 125622 (0.0023) [2023-03-09 10:37:43,213][119383] Updated weights for policy 0, policy_version 125632 (0.0016) [2023-03-09 10:37:43,902][118949] Fps is (10 sec: 196614.5, 60 sec: 195789.8, 300 sec: 193831.1). Total num frames: 2058469376. Throughput: 0: 48998.7. Samples: 14680224. Policy #0 lag: (min: 1.0, avg: 17.1, max: 33.0) [2023-03-09 10:37:43,903][118949] Avg episode reward: [(0, '55.147')] [2023-03-09 10:37:44,137][119383] Updated weights for policy 0, policy_version 125642 (0.0017) [2023-03-09 10:37:44,947][119383] Updated weights for policy 0, policy_version 125652 (0.0016) [2023-03-09 10:37:45,776][119383] Updated weights for policy 0, policy_version 125662 (0.0022) [2023-03-09 10:37:46,749][119383] Updated weights for policy 0, policy_version 125672 (0.0013) [2023-03-09 10:37:47,502][119383] Updated weights for policy 0, policy_version 125682 (0.0017) [2023-03-09 10:37:48,286][119383] Updated weights for policy 0, policy_version 125692 (0.0013) [2023-03-09 10:37:48,902][118949] Fps is (10 sec: 198240.4, 60 sec: 196061.1, 300 sec: 194386.4). Total num frames: 2059468800. Throughput: 0: 48953.0. Samples: 14825584. Policy #0 lag: (min: 1.0, avg: 17.1, max: 33.0) [2023-03-09 10:37:48,904][118949] Avg episode reward: [(0, '54.853')] [2023-03-09 10:37:49,094][119383] Updated weights for policy 0, policy_version 125702 (0.0016) [2023-03-09 10:37:50,023][119383] Updated weights for policy 0, policy_version 125712 (0.0013) [2023-03-09 10:37:50,747][119383] Updated weights for policy 0, policy_version 125722 (0.0025) [2023-03-09 10:37:51,243][119240] Signal inference workers to stop experience collection... (1500 times) [2023-03-09 10:37:51,269][119240] Signal inference workers to resume experience collection... (1500 times) [2023-03-09 10:37:51,297][119383] InferenceWorker_p0-w0: stopping experience collection (1500 times) [2023-03-09 10:37:51,337][119383] InferenceWorker_p0-w0: resuming experience collection (1500 times) [2023-03-09 10:37:51,591][119383] Updated weights for policy 0, policy_version 125732 (0.0016) [2023-03-09 10:37:52,525][119383] Updated weights for policy 0, policy_version 125742 (0.0027) [2023-03-09 10:37:53,338][119383] Updated weights for policy 0, policy_version 125752 (0.0036) [2023-03-09 10:37:53,902][118949] Fps is (10 sec: 196601.2, 60 sec: 195787.6, 300 sec: 194663.9). Total num frames: 2060435456. Throughput: 0: 48954.2. Samples: 15118384. Policy #0 lag: (min: 1.0, avg: 17.1, max: 33.0) [2023-03-09 10:37:53,905][118949] Avg episode reward: [(0, '55.801')] [2023-03-09 10:37:54,133][119383] Updated weights for policy 0, policy_version 125762 (0.0018) [2023-03-09 10:37:55,125][119383] Updated weights for policy 0, policy_version 125772 (0.0020) [2023-03-09 10:37:55,848][119383] Updated weights for policy 0, policy_version 125782 (0.0020) [2023-03-09 10:37:56,670][119383] Updated weights for policy 0, policy_version 125792 (0.0029) [2023-03-09 10:37:57,562][119383] Updated weights for policy 0, policy_version 125802 (0.0019) [2023-03-09 10:37:58,500][119383] Updated weights for policy 0, policy_version 125813 (0.0023) [2023-03-09 10:37:58,902][118949] Fps is (10 sec: 193336.4, 60 sec: 196061.9, 300 sec: 194553.2). Total num frames: 2061402112. Throughput: 0: 48865.0. Samples: 15409136. Policy #0 lag: (min: 1.0, avg: 17.1, max: 33.0) [2023-03-09 10:37:58,903][118949] Avg episode reward: [(0, '54.796')] [2023-03-09 10:37:59,288][119383] Updated weights for policy 0, policy_version 125823 (0.0022) [2023-03-09 10:38:00,214][119383] Updated weights for policy 0, policy_version 125833 (0.0018) [2023-03-09 10:38:00,944][119383] Updated weights for policy 0, policy_version 125843 (0.0018) [2023-03-09 10:38:01,746][119383] Updated weights for policy 0, policy_version 125853 (0.0012) [2023-03-09 10:38:01,868][119240] Signal inference workers to stop experience collection... (1550 times) [2023-03-09 10:38:01,887][119240] Signal inference workers to resume experience collection... (1550 times) [2023-03-09 10:38:01,955][119383] InferenceWorker_p0-w0: stopping experience collection (1550 times) [2023-03-09 10:38:01,956][119383] InferenceWorker_p0-w0: resuming experience collection (1550 times) [2023-03-09 10:38:02,645][119383] Updated weights for policy 0, policy_version 125863 (0.0013) [2023-03-09 10:38:03,480][119383] Updated weights for policy 0, policy_version 125873 (0.0014) [2023-03-09 10:38:03,902][118949] Fps is (10 sec: 196607.9, 60 sec: 196333.8, 300 sec: 194941.6). Total num frames: 2062401536. Throughput: 0: 48953.7. Samples: 15560560. Policy #0 lag: (min: 1.0, avg: 17.1, max: 33.0) [2023-03-09 10:38:03,904][118949] Avg episode reward: [(0, '54.010')] [2023-03-09 10:38:04,251][119383] Updated weights for policy 0, policy_version 125883 (0.0013) [2023-03-09 10:38:05,078][119383] Updated weights for policy 0, policy_version 125893 (0.0013) [2023-03-09 10:38:06,049][119383] Updated weights for policy 0, policy_version 125903 (0.0014) [2023-03-09 10:38:06,801][119383] Updated weights for policy 0, policy_version 125913 (0.0019) [2023-03-09 10:38:07,535][119383] Updated weights for policy 0, policy_version 125923 (0.0022) [2023-03-09 10:38:08,539][119383] Updated weights for policy 0, policy_version 125933 (0.0016) [2023-03-09 10:38:08,902][118949] Fps is (10 sec: 196607.4, 60 sec: 195788.8, 300 sec: 195330.7). Total num frames: 2063368192. Throughput: 0: 48861.8. Samples: 15851216. Policy #0 lag: (min: 1.0, avg: 17.1, max: 33.0) [2023-03-09 10:38:08,903][118949] Avg episode reward: [(0, '55.646')] [2023-03-09 10:38:09,409][119383] Updated weights for policy 0, policy_version 125944 (0.0013) [2023-03-09 10:38:10,203][119383] Updated weights for policy 0, policy_version 125954 (0.0031) [2023-03-09 10:38:11,124][119383] Updated weights for policy 0, policy_version 125964 (0.0016) [2023-03-09 10:38:11,899][119383] Updated weights for policy 0, policy_version 125974 (0.0013) [2023-03-09 10:38:12,543][119240] Signal inference workers to stop experience collection... (1600 times) [2023-03-09 10:38:12,544][119240] Signal inference workers to resume experience collection... (1600 times) [2023-03-09 10:38:12,607][119383] InferenceWorker_p0-w0: stopping experience collection (1600 times) [2023-03-09 10:38:12,607][119383] InferenceWorker_p0-w0: resuming experience collection (1600 times) [2023-03-09 10:38:12,691][119383] Updated weights for policy 0, policy_version 125984 (0.0019) [2023-03-09 10:38:13,685][119383] Updated weights for policy 0, policy_version 125994 (0.0016) [2023-03-09 10:38:13,902][118949] Fps is (10 sec: 193332.6, 60 sec: 195242.4, 300 sec: 195663.8). Total num frames: 2064334848. Throughput: 0: 48907.0. Samples: 16146048. Policy #0 lag: (min: 1.0, avg: 17.1, max: 33.0) [2023-03-09 10:38:13,904][118949] Avg episode reward: [(0, '54.666')] [2023-03-09 10:38:14,398][119383] Updated weights for policy 0, policy_version 126004 (0.0013) [2023-03-09 10:38:15,253][119383] Updated weights for policy 0, policy_version 126014 (0.0018) [2023-03-09 10:38:16,237][119383] Updated weights for policy 0, policy_version 126024 (0.0023) [2023-03-09 10:38:16,888][119383] Updated weights for policy 0, policy_version 126034 (0.0026) [2023-03-09 10:38:17,714][119383] Updated weights for policy 0, policy_version 126044 (0.0016) [2023-03-09 10:38:18,753][119383] Updated weights for policy 0, policy_version 126055 (0.0016) [2023-03-09 10:38:18,902][118949] Fps is (10 sec: 193332.3, 60 sec: 195243.5, 300 sec: 195997.1). Total num frames: 2065301504. Throughput: 0: 48953.7. Samples: 16293472. Policy #0 lag: (min: 1.0, avg: 17.1, max: 33.0) [2023-03-09 10:38:18,902][118949] Avg episode reward: [(0, '55.141')] [2023-03-09 10:38:19,540][119383] Updated weights for policy 0, policy_version 126065 (0.0013) [2023-03-09 10:38:20,308][119383] Updated weights for policy 0, policy_version 126075 (0.0029) [2023-03-09 10:38:21,128][119383] Updated weights for policy 0, policy_version 126085 (0.0013) [2023-03-09 10:38:21,593][119240] Signal inference workers to stop experience collection... (1650 times) [2023-03-09 10:38:21,617][119240] Signal inference workers to resume experience collection... (1650 times) [2023-03-09 10:38:21,662][119383] InferenceWorker_p0-w0: stopping experience collection (1650 times) [2023-03-09 10:38:21,662][119383] InferenceWorker_p0-w0: resuming experience collection (1650 times) [2023-03-09 10:38:22,200][119383] Updated weights for policy 0, policy_version 126096 (0.0013) [2023-03-09 10:38:23,020][119383] Updated weights for policy 0, policy_version 126107 (0.0017) [2023-03-09 10:38:23,859][119383] Updated weights for policy 0, policy_version 126117 (0.0035) [2023-03-09 10:38:23,902][118949] Fps is (10 sec: 196608.1, 60 sec: 195242.4, 300 sec: 196219.2). Total num frames: 2066300928. Throughput: 0: 48907.7. Samples: 16584240. Policy #0 lag: (min: 1.0, avg: 17.1, max: 33.0) [2023-03-09 10:38:23,904][118949] Avg episode reward: [(0, '53.429')] [2023-03-09 10:38:24,824][119383] Updated weights for policy 0, policy_version 126127 (0.0013) [2023-03-09 10:38:25,528][119383] Updated weights for policy 0, policy_version 126137 (0.0016) [2023-03-09 10:38:26,340][119383] Updated weights for policy 0, policy_version 126147 (0.0024) [2023-03-09 10:38:27,329][119383] Updated weights for policy 0, policy_version 126157 (0.0013) [2023-03-09 10:38:28,097][119383] Updated weights for policy 0, policy_version 126167 (0.0017) [2023-03-09 10:38:28,902][118949] Fps is (10 sec: 198245.8, 60 sec: 195788.7, 300 sec: 196274.9). Total num frames: 2067283968. Throughput: 0: 48772.3. Samples: 16874976. Policy #0 lag: (min: 1.0, avg: 17.3, max: 33.0) [2023-03-09 10:38:28,903][118949] Avg episode reward: [(0, '53.131')] [2023-03-09 10:38:28,907][119383] Updated weights for policy 0, policy_version 126177 (0.0013) [2023-03-09 10:38:29,874][119383] Updated weights for policy 0, policy_version 126187 (0.0023) [2023-03-09 10:38:30,679][119383] Updated weights for policy 0, policy_version 126197 (0.0017) [2023-03-09 10:38:31,419][119240] Signal inference workers to stop experience collection... (1700 times) [2023-03-09 10:38:31,444][119240] Signal inference workers to resume experience collection... (1700 times) [2023-03-09 10:38:31,450][119383] Updated weights for policy 0, policy_version 126207 (0.0018) [2023-03-09 10:38:31,488][119383] InferenceWorker_p0-w0: stopping experience collection (1700 times) [2023-03-09 10:38:31,488][119383] InferenceWorker_p0-w0: resuming experience collection (1700 times) [2023-03-09 10:38:32,417][119383] Updated weights for policy 0, policy_version 126217 (0.0023) [2023-03-09 10:38:33,174][119383] Updated weights for policy 0, policy_version 126227 (0.0013) [2023-03-09 10:38:33,902][118949] Fps is (10 sec: 194974.0, 60 sec: 195789.7, 300 sec: 196163.7). Total num frames: 2068250624. Throughput: 0: 48817.9. Samples: 17022384. Policy #0 lag: (min: 1.0, avg: 17.3, max: 33.0) [2023-03-09 10:38:33,903][118949] Avg episode reward: [(0, '52.145')] [2023-03-09 10:38:33,968][119383] Updated weights for policy 0, policy_version 126237 (0.0026) [2023-03-09 10:38:34,892][119383] Updated weights for policy 0, policy_version 126247 (0.0020) [2023-03-09 10:38:35,721][119383] Updated weights for policy 0, policy_version 126257 (0.0016) [2023-03-09 10:38:36,471][119383] Updated weights for policy 0, policy_version 126267 (0.0013) [2023-03-09 10:38:37,326][119383] Updated weights for policy 0, policy_version 126277 (0.0013) [2023-03-09 10:38:38,261][119383] Updated weights for policy 0, policy_version 126287 (0.0020) [2023-03-09 10:38:38,902][118949] Fps is (10 sec: 193331.7, 60 sec: 195515.7, 300 sec: 196163.8). Total num frames: 2069217280. Throughput: 0: 48817.9. Samples: 17315168. Policy #0 lag: (min: 1.0, avg: 17.3, max: 33.0) [2023-03-09 10:38:38,903][118949] Avg episode reward: [(0, '56.080')] [2023-03-09 10:38:39,093][119383] Updated weights for policy 0, policy_version 126298 (0.0014) [2023-03-09 10:38:39,908][119383] Updated weights for policy 0, policy_version 126308 (0.0013) [2023-03-09 10:38:40,927][119383] Updated weights for policy 0, policy_version 126318 (0.0016) [2023-03-09 10:38:40,938][119240] Signal inference workers to stop experience collection... (1750 times) [2023-03-09 10:38:40,963][119240] Signal inference workers to resume experience collection... (1750 times) [2023-03-09 10:38:41,007][119383] InferenceWorker_p0-w0: stopping experience collection (1750 times) [2023-03-09 10:38:41,007][119383] InferenceWorker_p0-w0: resuming experience collection (1750 times) [2023-03-09 10:38:41,676][119383] Updated weights for policy 0, policy_version 126328 (0.0017) [2023-03-09 10:38:42,408][119383] Updated weights for policy 0, policy_version 126338 (0.0021) [2023-03-09 10:38:43,407][119383] Updated weights for policy 0, policy_version 126348 (0.0014) [2023-03-09 10:38:43,902][118949] Fps is (10 sec: 193333.7, 60 sec: 195242.9, 300 sec: 196108.2). Total num frames: 2070183936. Throughput: 0: 48818.1. Samples: 17605952. Policy #0 lag: (min: 1.0, avg: 17.3, max: 33.0) [2023-03-09 10:38:43,903][118949] Avg episode reward: [(0, '52.285')] [2023-03-09 10:38:44,158][119383] Updated weights for policy 0, policy_version 126358 (0.0013) [2023-03-09 10:38:45,009][119383] Updated weights for policy 0, policy_version 126369 (0.0013) [2023-03-09 10:38:45,970][119383] Updated weights for policy 0, policy_version 126379 (0.0018) [2023-03-09 10:38:46,771][119383] Updated weights for policy 0, policy_version 126389 (0.0024) [2023-03-09 10:38:47,567][119383] Updated weights for policy 0, policy_version 126399 (0.0013) [2023-03-09 10:38:48,519][119383] Updated weights for policy 0, policy_version 126409 (0.0018) [2023-03-09 10:38:48,902][118949] Fps is (10 sec: 193327.3, 60 sec: 194696.8, 300 sec: 195997.1). Total num frames: 2071150592. Throughput: 0: 48774.7. Samples: 17755408. Policy #0 lag: (min: 1.0, avg: 17.3, max: 33.0) [2023-03-09 10:38:48,904][118949] Avg episode reward: [(0, '54.648')] [2023-03-09 10:38:49,230][119383] Updated weights for policy 0, policy_version 126419 (0.0016) [2023-03-09 10:38:50,056][119383] Updated weights for policy 0, policy_version 126429 (0.0013) [2023-03-09 10:38:50,300][119240] Signal inference workers to stop experience collection... (1800 times) [2023-03-09 10:38:50,317][119240] Signal inference workers to resume experience collection... (1800 times) [2023-03-09 10:38:50,347][119383] InferenceWorker_p0-w0: stopping experience collection (1800 times) [2023-03-09 10:38:50,389][119383] InferenceWorker_p0-w0: resuming experience collection (1800 times) [2023-03-09 10:38:51,032][119383] Updated weights for policy 0, policy_version 126439 (0.0017) [2023-03-09 10:38:51,812][119383] Updated weights for policy 0, policy_version 126449 (0.0021) [2023-03-09 10:38:52,568][119383] Updated weights for policy 0, policy_version 126459 (0.0028) [2023-03-09 10:38:53,357][119383] Updated weights for policy 0, policy_version 126469 (0.0017) [2023-03-09 10:38:53,902][118949] Fps is (10 sec: 196603.3, 60 sec: 195243.3, 300 sec: 196052.5). Total num frames: 2072150016. Throughput: 0: 48866.6. Samples: 18050224. Policy #0 lag: (min: 1.0, avg: 17.3, max: 33.0) [2023-03-09 10:38:53,904][118949] Avg episode reward: [(0, '54.710')] [2023-03-09 10:38:54,296][119383] Updated weights for policy 0, policy_version 126479 (0.0013) [2023-03-09 10:38:55,049][119383] Updated weights for policy 0, policy_version 126489 (0.0021) [2023-03-09 10:38:55,834][119383] Updated weights for policy 0, policy_version 126499 (0.0016) [2023-03-09 10:38:56,841][119383] Updated weights for policy 0, policy_version 126509 (0.0029) [2023-03-09 10:38:57,549][119383] Updated weights for policy 0, policy_version 126519 (0.0013) [2023-03-09 10:38:58,386][119383] Updated weights for policy 0, policy_version 126529 (0.0020) [2023-03-09 10:38:58,902][118949] Fps is (10 sec: 198249.0, 60 sec: 195515.6, 300 sec: 196052.6). Total num frames: 2073133056. Throughput: 0: 48821.7. Samples: 18343008. Policy #0 lag: (min: 1.0, avg: 17.3, max: 33.0) [2023-03-09 10:38:58,903][118949] Avg episode reward: [(0, '55.456')] [2023-03-09 10:38:59,446][119383] Updated weights for policy 0, policy_version 126540 (0.0015) [2023-03-09 10:39:00,199][119383] Updated weights for policy 0, policy_version 126550 (0.0034) [2023-03-09 10:39:01,005][119383] Updated weights for policy 0, policy_version 126560 (0.0020) [2023-03-09 10:39:01,143][119240] Signal inference workers to stop experience collection... (1850 times) [2023-03-09 10:39:01,146][119240] Signal inference workers to resume experience collection... (1850 times) [2023-03-09 10:39:01,206][119383] InferenceWorker_p0-w0: stopping experience collection (1850 times) [2023-03-09 10:39:01,209][119383] InferenceWorker_p0-w0: resuming experience collection (1850 times) [2023-03-09 10:39:01,980][119383] Updated weights for policy 0, policy_version 126570 (0.0027) [2023-03-09 10:39:02,724][119383] Updated weights for policy 0, policy_version 126580 (0.0019) [2023-03-09 10:39:03,606][119383] Updated weights for policy 0, policy_version 126591 (0.0013) [2023-03-09 10:39:03,902][118949] Fps is (10 sec: 198245.4, 60 sec: 195516.2, 300 sec: 196052.9). Total num frames: 2074132480. Throughput: 0: 48820.6. Samples: 18490416. Policy #0 lag: (min: 1.0, avg: 17.3, max: 33.0) [2023-03-09 10:39:03,904][118949] Avg episode reward: [(0, '54.577')] [2023-03-09 10:39:04,546][119383] Updated weights for policy 0, policy_version 126601 (0.0031) [2023-03-09 10:39:05,362][119383] Updated weights for policy 0, policy_version 126611 (0.0022) [2023-03-09 10:39:06,056][119383] Updated weights for policy 0, policy_version 126621 (0.0013) [2023-03-09 10:39:07,044][119383] Updated weights for policy 0, policy_version 126631 (0.0017) [2023-03-09 10:39:07,824][119383] Updated weights for policy 0, policy_version 126641 (0.0016) [2023-03-09 10:39:08,548][119383] Updated weights for policy 0, policy_version 126651 (0.0013) [2023-03-09 10:39:08,902][118949] Fps is (10 sec: 196609.2, 60 sec: 195515.9, 300 sec: 195886.2). Total num frames: 2075099136. Throughput: 0: 48957.2. Samples: 18787296. Policy #0 lag: (min: 1.0, avg: 17.3, max: 33.0) [2023-03-09 10:39:08,903][118949] Avg episode reward: [(0, '56.442')] [2023-03-09 10:39:09,361][119383] Updated weights for policy 0, policy_version 126661 (0.0030) [2023-03-09 10:39:10,440][119383] Updated weights for policy 0, policy_version 126672 (0.0016) [2023-03-09 10:39:10,783][119240] Signal inference workers to stop experience collection... (1900 times) [2023-03-09 10:39:10,787][119240] Signal inference workers to resume experience collection... (1900 times) [2023-03-09 10:39:10,845][119383] InferenceWorker_p0-w0: stopping experience collection (1900 times) [2023-03-09 10:39:10,845][119383] InferenceWorker_p0-w0: resuming experience collection (1900 times) [2023-03-09 10:39:11,130][119383] Updated weights for policy 0, policy_version 126682 (0.0026) [2023-03-09 10:39:11,948][119383] Updated weights for policy 0, policy_version 126692 (0.0017) [2023-03-09 10:39:12,924][119383] Updated weights for policy 0, policy_version 126702 (0.0013) [2023-03-09 10:39:13,729][119383] Updated weights for policy 0, policy_version 126712 (0.0013) [2023-03-09 10:39:13,902][118949] Fps is (10 sec: 196608.3, 60 sec: 196062.1, 300 sec: 195941.5). Total num frames: 2076098560. Throughput: 0: 49001.7. Samples: 19080064. Policy #0 lag: (min: 1.0, avg: 17.3, max: 33.0) [2023-03-09 10:39:13,904][118949] Avg episode reward: [(0, '52.980')] [2023-03-09 10:39:14,483][119383] Updated weights for policy 0, policy_version 126722 (0.0018) [2023-03-09 10:39:15,440][119383] Updated weights for policy 0, policy_version 126732 (0.0020) [2023-03-09 10:39:16,216][119383] Updated weights for policy 0, policy_version 126742 (0.0017) [2023-03-09 10:39:17,044][119383] Updated weights for policy 0, policy_version 126752 (0.0013) [2023-03-09 10:39:17,937][119383] Updated weights for policy 0, policy_version 126762 (0.0016) [2023-03-09 10:39:18,736][119383] Updated weights for policy 0, policy_version 126772 (0.0017) [2023-03-09 10:39:18,902][118949] Fps is (10 sec: 198238.8, 60 sec: 196333.6, 300 sec: 195941.4). Total num frames: 2077081600. Throughput: 0: 49001.7. Samples: 19227472. Policy #0 lag: (min: 1.0, avg: 17.3, max: 33.0) [2023-03-09 10:39:18,904][118949] Avg episode reward: [(0, '53.972')] [2023-03-09 10:39:19,561][119383] Updated weights for policy 0, policy_version 126782 (0.0020) [2023-03-09 10:39:20,498][119240] Signal inference workers to stop experience collection... (1950 times) [2023-03-09 10:39:20,499][119240] Signal inference workers to resume experience collection... (1950 times) [2023-03-09 10:39:20,562][119383] InferenceWorker_p0-w0: stopping experience collection (1950 times) [2023-03-09 10:39:20,568][119383] Updated weights for policy 0, policy_version 126793 (0.0025) [2023-03-09 10:39:20,604][119383] InferenceWorker_p0-w0: resuming experience collection (1950 times) [2023-03-09 10:39:21,347][119383] Updated weights for policy 0, policy_version 126803 (0.0017) [2023-03-09 10:39:22,081][119383] Updated weights for policy 0, policy_version 126813 (0.0029) [2023-03-09 10:39:23,070][119383] Updated weights for policy 0, policy_version 126823 (0.0026) [2023-03-09 10:39:23,889][119383] Updated weights for policy 0, policy_version 126833 (0.0027) [2023-03-09 10:39:23,902][118949] Fps is (10 sec: 194973.2, 60 sec: 195789.7, 300 sec: 195941.7). Total num frames: 2078048256. Throughput: 0: 49048.1. Samples: 19522336. Policy #0 lag: (min: 1.0, avg: 17.3, max: 33.0) [2023-03-09 10:39:23,903][118949] Avg episode reward: [(0, '54.722')] [2023-03-09 10:39:23,908][119240] Saving /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000126834_2078048256.pth... [2023-03-09 10:39:23,975][119240] Removing /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000123965_2031042560.pth [2023-03-09 10:39:24,596][119383] Updated weights for policy 0, policy_version 126843 (0.0033) [2023-03-09 10:39:25,419][119383] Updated weights for policy 0, policy_version 126853 (0.0016) [2023-03-09 10:39:26,410][119383] Updated weights for policy 0, policy_version 126863 (0.0013) [2023-03-09 10:39:27,120][119383] Updated weights for policy 0, policy_version 126873 (0.0041) [2023-03-09 10:39:27,881][119383] Updated weights for policy 0, policy_version 126883 (0.0014) [2023-03-09 10:39:28,877][119383] Updated weights for policy 0, policy_version 126893 (0.0023) [2023-03-09 10:39:28,902][118949] Fps is (10 sec: 193338.5, 60 sec: 195515.8, 300 sec: 195886.0). Total num frames: 2079014912. Throughput: 0: 49139.2. Samples: 19817216. Policy #0 lag: (min: 1.0, avg: 17.3, max: 33.0) [2023-03-09 10:39:28,903][118949] Avg episode reward: [(0, '54.706')] [2023-03-09 10:39:29,582][119383] Updated weights for policy 0, policy_version 126903 (0.0016) [2023-03-09 10:39:29,754][119240] Signal inference workers to stop experience collection... (2000 times) [2023-03-09 10:39:29,778][119240] Signal inference workers to resume experience collection... (2000 times) [2023-03-09 10:39:29,827][119383] InferenceWorker_p0-w0: stopping experience collection (2000 times) [2023-03-09 10:39:29,827][119383] InferenceWorker_p0-w0: resuming experience collection (2000 times) [2023-03-09 10:39:30,435][119383] Updated weights for policy 0, policy_version 126913 (0.0019) [2023-03-09 10:39:31,363][119383] Updated weights for policy 0, policy_version 126923 (0.0031) [2023-03-09 10:39:32,214][119383] Updated weights for policy 0, policy_version 126934 (0.0016) [2023-03-09 10:39:33,059][119383] Updated weights for policy 0, policy_version 126944 (0.0015) [2023-03-09 10:39:33,902][118949] Fps is (10 sec: 193325.5, 60 sec: 195514.9, 300 sec: 195774.7). Total num frames: 2079981568. Throughput: 0: 49048.3. Samples: 19962592. Policy #0 lag: (min: 2.0, avg: 18.2, max: 33.0) [2023-03-09 10:39:33,905][118949] Avg episode reward: [(0, '54.100')] [2023-03-09 10:39:34,022][119383] Updated weights for policy 0, policy_version 126954 (0.0018) [2023-03-09 10:39:34,762][119383] Updated weights for policy 0, policy_version 126964 (0.0014) [2023-03-09 10:39:35,672][119383] Updated weights for policy 0, policy_version 126975 (0.0013) [2023-03-09 10:39:36,644][119383] Updated weights for policy 0, policy_version 126985 (0.0014) [2023-03-09 10:39:37,472][119383] Updated weights for policy 0, policy_version 126996 (0.0020) [2023-03-09 10:39:38,294][119383] Updated weights for policy 0, policy_version 127006 (0.0013) [2023-03-09 10:39:38,902][118949] Fps is (10 sec: 196597.2, 60 sec: 196060.0, 300 sec: 195885.9). Total num frames: 2080980992. Throughput: 0: 49002.7. Samples: 20255360. Policy #0 lag: (min: 2.0, avg: 18.2, max: 33.0) [2023-03-09 10:39:38,905][118949] Avg episode reward: [(0, '55.017')] [2023-03-09 10:39:39,211][119383] Updated weights for policy 0, policy_version 127016 (0.0019) [2023-03-09 10:39:39,952][119383] Updated weights for policy 0, policy_version 127026 (0.0017) [2023-03-09 10:39:40,057][119240] Signal inference workers to stop experience collection... (2050 times) [2023-03-09 10:39:40,059][119240] Signal inference workers to resume experience collection... (2050 times) [2023-03-09 10:39:40,117][119383] InferenceWorker_p0-w0: stopping experience collection (2050 times) [2023-03-09 10:39:40,117][119383] InferenceWorker_p0-w0: resuming experience collection (2050 times) [2023-03-09 10:39:40,727][119383] Updated weights for policy 0, policy_version 127036 (0.0022) [2023-03-09 10:39:41,566][119383] Updated weights for policy 0, policy_version 127046 (0.0021) [2023-03-09 10:39:42,500][119383] Updated weights for policy 0, policy_version 127056 (0.0024) [2023-03-09 10:39:43,211][119383] Updated weights for policy 0, policy_version 127066 (0.0019) [2023-03-09 10:39:43,902][118949] Fps is (10 sec: 199891.7, 60 sec: 196607.9, 300 sec: 195941.6). Total num frames: 2081980416. Throughput: 0: 49048.9. Samples: 20550208. Policy #0 lag: (min: 2.0, avg: 18.2, max: 33.0) [2023-03-09 10:39:43,903][118949] Avg episode reward: [(0, '54.088')] [2023-03-09 10:39:44,157][119383] Updated weights for policy 0, policy_version 127077 (0.0022) [2023-03-09 10:39:45,148][119383] Updated weights for policy 0, policy_version 127087 (0.0013) [2023-03-09 10:39:45,877][119383] Updated weights for policy 0, policy_version 127097 (0.0016) [2023-03-09 10:39:46,612][119383] Updated weights for policy 0, policy_version 127107 (0.0018) [2023-03-09 10:39:47,601][119383] Updated weights for policy 0, policy_version 127117 (0.0024) [2023-03-09 10:39:48,349][119383] Updated weights for policy 0, policy_version 127127 (0.0013) [2023-03-09 10:39:48,902][118949] Fps is (10 sec: 196616.7, 60 sec: 196608.3, 300 sec: 195886.1). Total num frames: 2082947072. Throughput: 0: 49048.7. Samples: 20697600. Policy #0 lag: (min: 2.0, avg: 18.2, max: 33.0) [2023-03-09 10:39:48,903][118949] Avg episode reward: [(0, '56.042')] [2023-03-09 10:39:49,166][119383] Updated weights for policy 0, policy_version 127137 (0.0019) [2023-03-09 10:39:50,136][119383] Updated weights for policy 0, policy_version 127147 (0.0015) [2023-03-09 10:39:50,209][119240] Signal inference workers to stop experience collection... (2100 times) [2023-03-09 10:39:50,222][119240] Signal inference workers to resume experience collection... (2100 times) [2023-03-09 10:39:50,288][119383] InferenceWorker_p0-w0: stopping experience collection (2100 times) [2023-03-09 10:39:50,288][119383] InferenceWorker_p0-w0: resuming experience collection (2100 times) [2023-03-09 10:39:50,903][119383] Updated weights for policy 0, policy_version 127158 (0.0013) [2023-03-09 10:39:51,745][119383] Updated weights for policy 0, policy_version 127168 (0.0014) [2023-03-09 10:39:52,650][119383] Updated weights for policy 0, policy_version 127178 (0.0012) [2023-03-09 10:39:53,447][119383] Updated weights for policy 0, policy_version 127188 (0.0017) [2023-03-09 10:39:53,902][118949] Fps is (10 sec: 196608.5, 60 sec: 196608.7, 300 sec: 196052.8). Total num frames: 2083946496. Throughput: 0: 49091.9. Samples: 20996432. Policy #0 lag: (min: 2.0, avg: 18.2, max: 33.0) [2023-03-09 10:39:53,903][118949] Avg episode reward: [(0, '52.678')] [2023-03-09 10:39:54,250][119383] Updated weights for policy 0, policy_version 127198 (0.0014) [2023-03-09 10:39:55,185][119383] Updated weights for policy 0, policy_version 127208 (0.0022) [2023-03-09 10:39:55,911][119383] Updated weights for policy 0, policy_version 127218 (0.0021) [2023-03-09 10:39:56,757][119383] Updated weights for policy 0, policy_version 127228 (0.0013) [2023-03-09 10:39:57,533][119383] Updated weights for policy 0, policy_version 127238 (0.0019) [2023-03-09 10:39:58,434][119240] Signal inference workers to stop experience collection... (2150 times) [2023-03-09 10:39:58,454][119240] Signal inference workers to resume experience collection... (2150 times) [2023-03-09 10:39:58,487][119383] InferenceWorker_p0-w0: stopping experience collection (2150 times) [2023-03-09 10:39:58,493][119383] Updated weights for policy 0, policy_version 127248 (0.0018) [2023-03-09 10:39:58,533][119383] InferenceWorker_p0-w0: resuming experience collection (2150 times) [2023-03-09 10:39:58,902][118949] Fps is (10 sec: 198247.7, 60 sec: 196608.1, 300 sec: 196108.4). Total num frames: 2084929536. Throughput: 0: 49137.7. Samples: 21291248. Policy #0 lag: (min: 2.0, avg: 18.2, max: 33.0) [2023-03-09 10:39:58,903][118949] Avg episode reward: [(0, '52.746')] [2023-03-09 10:39:59,164][119383] Updated weights for policy 0, policy_version 127258 (0.0014) [2023-03-09 10:40:00,098][119383] Updated weights for policy 0, policy_version 127268 (0.0013) [2023-03-09 10:40:01,024][119383] Updated weights for policy 0, policy_version 127278 (0.0013) [2023-03-09 10:40:01,736][119383] Updated weights for policy 0, policy_version 127288 (0.0033) [2023-03-09 10:40:02,478][119383] Updated weights for policy 0, policy_version 127298 (0.0029) [2023-03-09 10:40:03,486][119383] Updated weights for policy 0, policy_version 127308 (0.0038) [2023-03-09 10:40:03,903][118949] Fps is (10 sec: 196592.8, 60 sec: 196333.3, 300 sec: 196052.1). Total num frames: 2085912576. Throughput: 0: 49137.7. Samples: 21438688. Policy #0 lag: (min: 2.0, avg: 18.2, max: 33.0) [2023-03-09 10:40:03,904][118949] Avg episode reward: [(0, '55.148')] [2023-03-09 10:40:04,290][119383] Updated weights for policy 0, policy_version 127319 (0.0013) [2023-03-09 10:40:05,078][119383] Updated weights for policy 0, policy_version 127329 (0.0024) [2023-03-09 10:40:06,048][119383] Updated weights for policy 0, policy_version 127339 (0.0029) [2023-03-09 10:40:06,813][119383] Updated weights for policy 0, policy_version 127349 (0.0016) [2023-03-09 10:40:07,517][119240] Signal inference workers to stop experience collection... (2200 times) [2023-03-09 10:40:07,533][119240] Signal inference workers to resume experience collection... (2200 times) [2023-03-09 10:40:07,596][119383] InferenceWorker_p0-w0: stopping experience collection (2200 times) [2023-03-09 10:40:07,596][119383] InferenceWorker_p0-w0: resuming experience collection (2200 times) [2023-03-09 10:40:07,643][119383] Updated weights for policy 0, policy_version 127359 (0.0016) [2023-03-09 10:40:08,600][119383] Updated weights for policy 0, policy_version 127369 (0.0027) [2023-03-09 10:40:08,902][118949] Fps is (10 sec: 194968.3, 60 sec: 196334.6, 300 sec: 195941.5). Total num frames: 2086879232. Throughput: 0: 49137.1. Samples: 21733504. Policy #0 lag: (min: 2.0, avg: 18.2, max: 33.0) [2023-03-09 10:40:08,903][118949] Avg episode reward: [(0, '55.789')] [2023-03-09 10:40:09,303][119383] Updated weights for policy 0, policy_version 127379 (0.0016) [2023-03-09 10:40:10,242][119383] Updated weights for policy 0, policy_version 127390 (0.0013) [2023-03-09 10:40:11,141][119383] Updated weights for policy 0, policy_version 127400 (0.0017) [2023-03-09 10:40:11,914][119383] Updated weights for policy 0, policy_version 127410 (0.0013) [2023-03-09 10:40:12,761][119383] Updated weights for policy 0, policy_version 127421 (0.0027) [2023-03-09 10:40:13,759][119383] Updated weights for policy 0, policy_version 127431 (0.0013) [2023-03-09 10:40:13,902][118949] Fps is (10 sec: 193343.6, 60 sec: 195789.2, 300 sec: 195885.9). Total num frames: 2087845888. Throughput: 0: 49089.3. Samples: 22026240. Policy #0 lag: (min: 2.0, avg: 18.2, max: 33.0) [2023-03-09 10:40:13,903][118949] Avg episode reward: [(0, '54.975')] [2023-03-09 10:40:14,549][119383] Updated weights for policy 0, policy_version 127441 (0.0015) [2023-03-09 10:40:15,402][119383] Updated weights for policy 0, policy_version 127452 (0.0018) [2023-03-09 10:40:16,237][119383] Updated weights for policy 0, policy_version 127462 (0.0026) [2023-03-09 10:40:17,210][119383] Updated weights for policy 0, policy_version 127472 (0.0021) [2023-03-09 10:40:17,761][119240] Signal inference workers to stop experience collection... (2250 times) [2023-03-09 10:40:17,765][119240] Signal inference workers to resume experience collection... (2250 times) [2023-03-09 10:40:17,835][119383] InferenceWorker_p0-w0: stopping experience collection (2250 times) [2023-03-09 10:40:17,837][119383] InferenceWorker_p0-w0: resuming experience collection (2250 times) [2023-03-09 10:40:17,885][119383] Updated weights for policy 0, policy_version 127482 (0.0016) [2023-03-09 10:40:18,761][119383] Updated weights for policy 0, policy_version 127492 (0.0023) [2023-03-09 10:40:18,902][118949] Fps is (10 sec: 196608.9, 60 sec: 196062.9, 300 sec: 195941.9). Total num frames: 2088845312. Throughput: 0: 49089.1. Samples: 22171584. Policy #0 lag: (min: 2.0, avg: 18.2, max: 33.0) [2023-03-09 10:40:18,903][118949] Avg episode reward: [(0, '52.441')] [2023-03-09 10:40:19,749][119383] Updated weights for policy 0, policy_version 127502 (0.0019) [2023-03-09 10:40:20,531][119383] Updated weights for policy 0, policy_version 127513 (0.0025) [2023-03-09 10:40:21,315][119383] Updated weights for policy 0, policy_version 127523 (0.0015) [2023-03-09 10:40:22,301][119383] Updated weights for policy 0, policy_version 127533 (0.0016) [2023-03-09 10:40:23,018][119383] Updated weights for policy 0, policy_version 127543 (0.0016) [2023-03-09 10:40:23,788][119383] Updated weights for policy 0, policy_version 127553 (0.0016) [2023-03-09 10:40:23,902][118949] Fps is (10 sec: 199887.3, 60 sec: 196608.2, 300 sec: 196052.8). Total num frames: 2089844736. Throughput: 0: 49133.7. Samples: 22466352. Policy #0 lag: (min: 2.0, avg: 18.2, max: 33.0) [2023-03-09 10:40:23,903][118949] Avg episode reward: [(0, '53.357')] [2023-03-09 10:40:24,724][119383] Updated weights for policy 0, policy_version 127563 (0.0025) [2023-03-09 10:40:25,566][119383] Updated weights for policy 0, policy_version 127573 (0.0020) [2023-03-09 10:40:26,319][119383] Updated weights for policy 0, policy_version 127583 (0.0019) [2023-03-09 10:40:27,309][119383] Updated weights for policy 0, policy_version 127593 (0.0014) [2023-03-09 10:40:28,008][119383] Updated weights for policy 0, policy_version 127603 (0.0013) [2023-03-09 10:40:28,796][119383] Updated weights for policy 0, policy_version 127613 (0.0013) [2023-03-09 10:40:28,902][118949] Fps is (10 sec: 198245.8, 60 sec: 196880.8, 300 sec: 196108.1). Total num frames: 2090827776. Throughput: 0: 49224.8. Samples: 22765328. Policy #0 lag: (min: 2.0, avg: 18.2, max: 33.0) [2023-03-09 10:40:28,903][118949] Avg episode reward: [(0, '56.095')] [2023-03-09 10:40:29,761][119383] Updated weights for policy 0, policy_version 127623 (0.0017) [2023-03-09 10:40:29,930][119240] Signal inference workers to stop experience collection... (2300 times) [2023-03-09 10:40:29,933][119240] Signal inference workers to resume experience collection... (2300 times) [2023-03-09 10:40:30,003][119383] InferenceWorker_p0-w0: stopping experience collection (2300 times) [2023-03-09 10:40:30,003][119383] InferenceWorker_p0-w0: resuming experience collection (2300 times) [2023-03-09 10:40:30,554][119383] Updated weights for policy 0, policy_version 127633 (0.0022) [2023-03-09 10:40:31,376][119383] Updated weights for policy 0, policy_version 127643 (0.0019) [2023-03-09 10:40:32,163][119383] Updated weights for policy 0, policy_version 127653 (0.0028) [2023-03-09 10:40:33,127][119383] Updated weights for policy 0, policy_version 127663 (0.0029) [2023-03-09 10:40:33,836][119383] Updated weights for policy 0, policy_version 127673 (0.0020) [2023-03-09 10:40:33,902][118949] Fps is (10 sec: 196606.8, 60 sec: 197155.1, 300 sec: 196108.1). Total num frames: 2091810816. Throughput: 0: 49180.5. Samples: 22910720. Policy #0 lag: (min: 0.0, avg: 16.1, max: 32.0) [2023-03-09 10:40:33,903][118949] Avg episode reward: [(0, '55.948')] [2023-03-09 10:40:34,647][119383] Updated weights for policy 0, policy_version 127683 (0.0017) [2023-03-09 10:40:35,632][119383] Updated weights for policy 0, policy_version 127693 (0.0021) [2023-03-09 10:40:36,340][119383] Updated weights for policy 0, policy_version 127703 (0.0023) [2023-03-09 10:40:37,145][119383] Updated weights for policy 0, policy_version 127713 (0.0016) [2023-03-09 10:40:38,242][119383] Updated weights for policy 0, policy_version 127724 (0.0016) [2023-03-09 10:40:38,902][118949] Fps is (10 sec: 193325.5, 60 sec: 196335.5, 300 sec: 196052.4). Total num frames: 2092761088. Throughput: 0: 49047.1. Samples: 23203568. Policy #0 lag: (min: 0.0, avg: 16.1, max: 32.0) [2023-03-09 10:40:38,904][118949] Avg episode reward: [(0, '54.854')] [2023-03-09 10:40:38,980][119383] Updated weights for policy 0, policy_version 127734 (0.0027) [2023-03-09 10:40:39,841][119383] Updated weights for policy 0, policy_version 127745 (0.0021) [2023-03-09 10:40:40,814][119383] Updated weights for policy 0, policy_version 127755 (0.0013) [2023-03-09 10:40:41,588][119240] Signal inference workers to stop experience collection... (2350 times) [2023-03-09 10:40:41,589][119240] Signal inference workers to resume experience collection... (2350 times) [2023-03-09 10:40:41,646][119383] Updated weights for policy 0, policy_version 127766 (0.0027) [2023-03-09 10:40:41,688][119383] InferenceWorker_p0-w0: stopping experience collection (2350 times) [2023-03-09 10:40:41,688][119383] InferenceWorker_p0-w0: resuming experience collection (2350 times) [2023-03-09 10:40:42,474][119383] Updated weights for policy 0, policy_version 127776 (0.0017) [2023-03-09 10:40:43,451][119383] Updated weights for policy 0, policy_version 127786 (0.0019) [2023-03-09 10:40:43,903][118949] Fps is (10 sec: 193316.9, 60 sec: 196059.3, 300 sec: 195996.5). Total num frames: 2093744128. Throughput: 0: 49001.1. Samples: 23496336. Policy #0 lag: (min: 0.0, avg: 16.1, max: 32.0) [2023-03-09 10:40:43,905][118949] Avg episode reward: [(0, '54.618')] [2023-03-09 10:40:44,177][119383] Updated weights for policy 0, policy_version 127796 (0.0016) [2023-03-09 10:40:45,009][119383] Updated weights for policy 0, policy_version 127806 (0.0028) [2023-03-09 10:40:46,045][119383] Updated weights for policy 0, policy_version 127817 (0.0016) [2023-03-09 10:40:46,751][119383] Updated weights for policy 0, policy_version 127827 (0.0025) [2023-03-09 10:40:47,530][119383] Updated weights for policy 0, policy_version 127837 (0.0016) [2023-03-09 10:40:48,502][119383] Updated weights for policy 0, policy_version 127847 (0.0021) [2023-03-09 10:40:48,902][118949] Fps is (10 sec: 196611.1, 60 sec: 196334.6, 300 sec: 195886.1). Total num frames: 2094727168. Throughput: 0: 49048.1. Samples: 23645824. Policy #0 lag: (min: 0.0, avg: 16.1, max: 32.0) [2023-03-09 10:40:48,904][118949] Avg episode reward: [(0, '54.800')] [2023-03-09 10:40:49,198][119383] Updated weights for policy 0, policy_version 127857 (0.0013) [2023-03-09 10:40:50,099][119383] Updated weights for policy 0, policy_version 127868 (0.0021) [2023-03-09 10:40:50,918][119383] Updated weights for policy 0, policy_version 127878 (0.0019) [2023-03-09 10:40:51,858][119383] Updated weights for policy 0, policy_version 127888 (0.0014) [2023-03-09 10:40:52,253][119240] Signal inference workers to stop experience collection... (2400 times) [2023-03-09 10:40:52,276][119240] Signal inference workers to resume experience collection... (2400 times) [2023-03-09 10:40:52,325][119383] InferenceWorker_p0-w0: stopping experience collection (2400 times) [2023-03-09 10:40:52,325][119383] InferenceWorker_p0-w0: resuming experience collection (2400 times) [2023-03-09 10:40:52,575][119383] Updated weights for policy 0, policy_version 127898 (0.0016) [2023-03-09 10:40:53,420][119383] Updated weights for policy 0, policy_version 127908 (0.0020) [2023-03-09 10:40:53,902][118949] Fps is (10 sec: 194978.0, 60 sec: 195787.6, 300 sec: 195941.3). Total num frames: 2095693824. Throughput: 0: 49090.9. Samples: 23942608. Policy #0 lag: (min: 0.0, avg: 16.1, max: 32.0) [2023-03-09 10:40:53,904][118949] Avg episode reward: [(0, '54.782')] [2023-03-09 10:40:54,395][119383] Updated weights for policy 0, policy_version 127918 (0.0013) [2023-03-09 10:40:55,128][119383] Updated weights for policy 0, policy_version 127928 (0.0027) [2023-03-09 10:40:55,880][119383] Updated weights for policy 0, policy_version 127938 (0.0022) [2023-03-09 10:40:56,876][119383] Updated weights for policy 0, policy_version 127948 (0.0016) [2023-03-09 10:40:57,613][119383] Updated weights for policy 0, policy_version 127958 (0.0025) [2023-03-09 10:40:58,451][119383] Updated weights for policy 0, policy_version 127968 (0.0022) [2023-03-09 10:40:58,902][118949] Fps is (10 sec: 198244.3, 60 sec: 196334.0, 300 sec: 195997.0). Total num frames: 2096709632. Throughput: 0: 49092.1. Samples: 24235392. Policy #0 lag: (min: 0.0, avg: 16.1, max: 32.0) [2023-03-09 10:40:58,904][118949] Avg episode reward: [(0, '55.418')] [2023-03-09 10:40:59,403][119383] Updated weights for policy 0, policy_version 127978 (0.0014) [2023-03-09 10:41:00,148][119383] Updated weights for policy 0, policy_version 127988 (0.0022) [2023-03-09 10:41:00,974][119383] Updated weights for policy 0, policy_version 127998 (0.0013) [2023-03-09 10:41:01,962][119383] Updated weights for policy 0, policy_version 128008 (0.0021) [2023-03-09 10:41:02,637][119383] Updated weights for policy 0, policy_version 128018 (0.0044) [2023-03-09 10:41:03,444][119383] Updated weights for policy 0, policy_version 128028 (0.0013) [2023-03-09 10:41:03,902][118949] Fps is (10 sec: 201531.3, 60 sec: 196610.6, 300 sec: 196108.2). Total num frames: 2097709056. Throughput: 0: 49138.6. Samples: 24382816. Policy #0 lag: (min: 0.0, avg: 16.1, max: 32.0) [2023-03-09 10:41:03,903][118949] Avg episode reward: [(0, '56.075')] [2023-03-09 10:41:04,285][119383] Updated weights for policy 0, policy_version 128038 (0.0028) [2023-03-09 10:41:05,094][119240] Signal inference workers to stop experience collection... (2450 times) [2023-03-09 10:41:05,096][119240] Signal inference workers to resume experience collection... (2450 times) [2023-03-09 10:41:05,165][119383] InferenceWorker_p0-w0: stopping experience collection (2450 times) [2023-03-09 10:41:05,167][119383] InferenceWorker_p0-w0: resuming experience collection (2450 times) [2023-03-09 10:41:05,253][119383] Updated weights for policy 0, policy_version 128048 (0.0016) [2023-03-09 10:41:05,928][119383] Updated weights for policy 0, policy_version 128058 (0.0018) [2023-03-09 10:41:06,866][119383] Updated weights for policy 0, policy_version 128068 (0.0023) [2023-03-09 10:41:07,835][119383] Updated weights for policy 0, policy_version 128078 (0.0014) [2023-03-09 10:41:08,491][119383] Updated weights for policy 0, policy_version 128088 (0.0027) [2023-03-09 10:41:08,902][118949] Fps is (10 sec: 196613.0, 60 sec: 196608.1, 300 sec: 196052.7). Total num frames: 2098675712. Throughput: 0: 49093.3. Samples: 24675552. Policy #0 lag: (min: 0.0, avg: 16.1, max: 32.0) [2023-03-09 10:41:08,903][118949] Avg episode reward: [(0, '55.369')] [2023-03-09 10:41:09,340][119383] Updated weights for policy 0, policy_version 128098 (0.0017) [2023-03-09 10:41:10,272][119383] Updated weights for policy 0, policy_version 128108 (0.0015) [2023-03-09 10:41:11,084][119383] Updated weights for policy 0, policy_version 128119 (0.0023) [2023-03-09 10:41:11,854][119383] Updated weights for policy 0, policy_version 128129 (0.0028) [2023-03-09 10:41:12,842][119383] Updated weights for policy 0, policy_version 128139 (0.0023) [2023-03-09 10:41:13,627][119383] Updated weights for policy 0, policy_version 128149 (0.0016) [2023-03-09 10:41:13,798][119240] Signal inference workers to stop experience collection... (2500 times) [2023-03-09 10:41:13,799][119240] Signal inference workers to resume experience collection... (2500 times) [2023-03-09 10:41:13,865][119383] InferenceWorker_p0-w0: stopping experience collection (2500 times) [2023-03-09 10:41:13,865][119383] InferenceWorker_p0-w0: resuming experience collection (2500 times) [2023-03-09 10:41:13,902][118949] Fps is (10 sec: 194967.5, 60 sec: 196881.2, 300 sec: 196108.1). Total num frames: 2099658752. Throughput: 0: 49044.6. Samples: 24972336. Policy #0 lag: (min: 0.0, avg: 16.1, max: 32.0) [2023-03-09 10:41:13,903][118949] Avg episode reward: [(0, '56.299')] [2023-03-09 10:41:14,428][119383] Updated weights for policy 0, policy_version 128159 (0.0026) [2023-03-09 10:41:15,421][119383] Updated weights for policy 0, policy_version 128169 (0.0015) [2023-03-09 10:41:16,152][119383] Updated weights for policy 0, policy_version 128179 (0.0021) [2023-03-09 10:41:16,926][119383] Updated weights for policy 0, policy_version 128189 (0.0028) [2023-03-09 10:41:17,900][119383] Updated weights for policy 0, policy_version 128199 (0.0019) [2023-03-09 10:41:18,686][119383] Updated weights for policy 0, policy_version 128210 (0.0019) [2023-03-09 10:41:18,902][118949] Fps is (10 sec: 194967.8, 60 sec: 196334.6, 300 sec: 196052.5). Total num frames: 2100625408. Throughput: 0: 48998.7. Samples: 25115664. Policy #0 lag: (min: 0.0, avg: 16.1, max: 32.0) [2023-03-09 10:41:18,904][118949] Avg episode reward: [(0, '52.866')] [2023-03-09 10:41:19,459][119383] Updated weights for policy 0, policy_version 128220 (0.0018) [2023-03-09 10:41:20,331][119383] Updated weights for policy 0, policy_version 128230 (0.0018) [2023-03-09 10:41:21,220][119383] Updated weights for policy 0, policy_version 128240 (0.0013) [2023-03-09 10:41:21,875][119383] Updated weights for policy 0, policy_version 128250 (0.0034) [2023-03-09 10:41:22,788][119383] Updated weights for policy 0, policy_version 128260 (0.0013) [2023-03-09 10:41:23,215][119240] Signal inference workers to stop experience collection... (2550 times) [2023-03-09 10:41:23,231][119240] Signal inference workers to resume experience collection... (2550 times) [2023-03-09 10:41:23,263][119383] InferenceWorker_p0-w0: stopping experience collection (2550 times) [2023-03-09 10:41:23,301][119383] InferenceWorker_p0-w0: resuming experience collection (2550 times) [2023-03-09 10:41:23,815][119383] Updated weights for policy 0, policy_version 128270 (0.0023) [2023-03-09 10:41:23,903][118949] Fps is (10 sec: 193319.0, 60 sec: 195786.5, 300 sec: 195996.6). Total num frames: 2101592064. Throughput: 0: 49179.0. Samples: 25416640. Policy #0 lag: (min: 0.0, avg: 16.1, max: 32.0) [2023-03-09 10:41:23,905][118949] Avg episode reward: [(0, '54.769')] [2023-03-09 10:41:23,961][119240] Saving /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000128273_2101624832.pth... [2023-03-09 10:41:24,035][119240] Removing /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000125402_2054586368.pth [2023-03-09 10:41:24,581][119383] Updated weights for policy 0, policy_version 128281 (0.0013) [2023-03-09 10:41:25,332][119383] Updated weights for policy 0, policy_version 128291 (0.0023) [2023-03-09 10:41:26,411][119383] Updated weights for policy 0, policy_version 128301 (0.0013) [2023-03-09 10:41:27,089][119383] Updated weights for policy 0, policy_version 128311 (0.0020) [2023-03-09 10:41:27,857][119383] Updated weights for policy 0, policy_version 128321 (0.0012) [2023-03-09 10:41:28,804][119383] Updated weights for policy 0, policy_version 128331 (0.0026) [2023-03-09 10:41:28,902][118949] Fps is (10 sec: 196607.2, 60 sec: 196061.5, 300 sec: 195941.6). Total num frames: 2102591488. Throughput: 0: 49179.3. Samples: 25709376. Policy #0 lag: (min: 0.0, avg: 16.1, max: 32.0) [2023-03-09 10:41:28,903][118949] Avg episode reward: [(0, '54.074')] [2023-03-09 10:41:29,606][119383] Updated weights for policy 0, policy_version 128342 (0.0014) [2023-03-09 10:41:30,468][119383] Updated weights for policy 0, policy_version 128352 (0.0016) [2023-03-09 10:41:31,361][119383] Updated weights for policy 0, policy_version 128362 (0.0019) [2023-03-09 10:41:31,781][119240] Signal inference workers to stop experience collection... (2600 times) [2023-03-09 10:41:31,812][119240] Signal inference workers to resume experience collection... (2600 times) [2023-03-09 10:41:31,841][119383] InferenceWorker_p0-w0: stopping experience collection (2600 times) [2023-03-09 10:41:31,880][119383] InferenceWorker_p0-w0: resuming experience collection (2600 times) [2023-03-09 10:41:32,212][119383] Updated weights for policy 0, policy_version 128372 (0.0016) [2023-03-09 10:41:32,982][119383] Updated weights for policy 0, policy_version 128382 (0.0016) [2023-03-09 10:41:33,902][118949] Fps is (10 sec: 198260.1, 60 sec: 196062.0, 300 sec: 196052.9). Total num frames: 2103574528. Throughput: 0: 49133.0. Samples: 25856800. Policy #0 lag: (min: 0.0, avg: 16.1, max: 32.0) [2023-03-09 10:41:33,903][118949] Avg episode reward: [(0, '55.302')] [2023-03-09 10:41:33,931][119383] Updated weights for policy 0, policy_version 128392 (0.0024) [2023-03-09 10:41:34,662][119383] Updated weights for policy 0, policy_version 128402 (0.0024) [2023-03-09 10:41:35,442][119383] Updated weights for policy 0, policy_version 128412 (0.0016) [2023-03-09 10:41:36,265][119383] Updated weights for policy 0, policy_version 128422 (0.0017) [2023-03-09 10:41:37,199][119383] Updated weights for policy 0, policy_version 128432 (0.0019) [2023-03-09 10:41:38,091][119383] Updated weights for policy 0, policy_version 128443 (0.0029) [2023-03-09 10:41:38,852][119383] Updated weights for policy 0, policy_version 128453 (0.0020) [2023-03-09 10:41:38,902][118949] Fps is (10 sec: 198244.6, 60 sec: 196881.3, 300 sec: 196108.2). Total num frames: 2104573952. Throughput: 0: 49135.4. Samples: 26153696. Policy #0 lag: (min: 2.0, avg: 16.4, max: 34.0) [2023-03-09 10:41:38,904][118949] Avg episode reward: [(0, '55.621')] [2023-03-09 10:41:39,758][119383] Updated weights for policy 0, policy_version 128463 (0.0024) [2023-03-09 10:41:39,805][119240] Signal inference workers to stop experience collection... (2650 times) [2023-03-09 10:41:39,808][119240] Signal inference workers to resume experience collection... (2650 times) [2023-03-09 10:41:39,836][119383] InferenceWorker_p0-w0: stopping experience collection (2650 times) [2023-03-09 10:41:39,836][119383] InferenceWorker_p0-w0: resuming experience collection (2650 times) [2023-03-09 10:41:40,567][119383] Updated weights for policy 0, policy_version 128474 (0.0017) [2023-03-09 10:41:41,393][119383] Updated weights for policy 0, policy_version 128484 (0.0030) [2023-03-09 10:41:42,377][119383] Updated weights for policy 0, policy_version 128494 (0.0020) [2023-03-09 10:41:43,128][119383] Updated weights for policy 0, policy_version 128504 (0.0013) [2023-03-09 10:41:43,902][118949] Fps is (10 sec: 199878.6, 60 sec: 197155.7, 300 sec: 196163.5). Total num frames: 2105573376. Throughput: 0: 49179.7. Samples: 26448480. Policy #0 lag: (min: 2.0, avg: 16.4, max: 34.0) [2023-03-09 10:41:43,904][118949] Avg episode reward: [(0, '54.024')] [2023-03-09 10:41:43,936][119383] Updated weights for policy 0, policy_version 128515 (0.0013) [2023-03-09 10:41:44,989][119383] Updated weights for policy 0, policy_version 128525 (0.0016) [2023-03-09 10:41:45,675][119383] Updated weights for policy 0, policy_version 128535 (0.0025) [2023-03-09 10:41:46,470][119383] Updated weights for policy 0, policy_version 128545 (0.0016) [2023-03-09 10:41:47,380][119383] Updated weights for policy 0, policy_version 128555 (0.0012) [2023-03-09 10:41:48,179][119383] Updated weights for policy 0, policy_version 128565 (0.0018) [2023-03-09 10:41:48,902][118949] Fps is (10 sec: 198248.4, 60 sec: 197154.2, 300 sec: 196163.6). Total num frames: 2106556416. Throughput: 0: 49224.3. Samples: 26597920. Policy #0 lag: (min: 2.0, avg: 16.4, max: 34.0) [2023-03-09 10:41:48,904][118949] Avg episode reward: [(0, '55.102')] [2023-03-09 10:41:48,973][119383] Updated weights for policy 0, policy_version 128575 (0.0013) [2023-03-09 10:41:49,934][119383] Updated weights for policy 0, policy_version 128585 (0.0020) [2023-03-09 10:41:50,535][119240] Signal inference workers to stop experience collection... (2700 times) [2023-03-09 10:41:50,536][119240] Signal inference workers to resume experience collection... (2700 times) [2023-03-09 10:41:50,600][119383] InferenceWorker_p0-w0: stopping experience collection (2700 times) [2023-03-09 10:41:50,601][119383] InferenceWorker_p0-w0: resuming experience collection (2700 times) [2023-03-09 10:41:50,649][119383] Updated weights for policy 0, policy_version 128595 (0.0016) [2023-03-09 10:41:51,433][119383] Updated weights for policy 0, policy_version 128605 (0.0031) [2023-03-09 10:41:52,451][119383] Updated weights for policy 0, policy_version 128615 (0.0017) [2023-03-09 10:41:53,192][119383] Updated weights for policy 0, policy_version 128625 (0.0021) [2023-03-09 10:41:53,902][118949] Fps is (10 sec: 196611.1, 60 sec: 197427.9, 300 sec: 196274.6). Total num frames: 2107539456. Throughput: 0: 49314.7. Samples: 26894720. Policy #0 lag: (min: 2.0, avg: 16.4, max: 34.0) [2023-03-09 10:41:53,904][118949] Avg episode reward: [(0, '53.148')] [2023-03-09 10:41:53,945][119383] Updated weights for policy 0, policy_version 128635 (0.0024) [2023-03-09 10:41:54,766][119383] Updated weights for policy 0, policy_version 128645 (0.0022) [2023-03-09 10:41:55,715][119383] Updated weights for policy 0, policy_version 128655 (0.0016) [2023-03-09 10:41:56,494][119383] Updated weights for policy 0, policy_version 128666 (0.0016) [2023-03-09 10:41:57,464][119383] Updated weights for policy 0, policy_version 128677 (0.0023) [2023-03-09 10:41:58,400][119383] Updated weights for policy 0, policy_version 128687 (0.0024) [2023-03-09 10:41:58,902][118949] Fps is (10 sec: 196601.3, 60 sec: 196880.4, 300 sec: 196274.5). Total num frames: 2108522496. Throughput: 0: 49269.6. Samples: 27189488. Policy #0 lag: (min: 2.0, avg: 16.4, max: 34.0) [2023-03-09 10:41:58,905][118949] Avg episode reward: [(0, '56.417')] [2023-03-09 10:41:59,131][119383] Updated weights for policy 0, policy_version 128698 (0.0022) [2023-03-09 10:41:59,994][119383] Updated weights for policy 0, policy_version 128708 (0.0016) [2023-03-09 10:42:00,988][119383] Updated weights for policy 0, policy_version 128718 (0.0013) [2023-03-09 10:42:01,832][119240] Signal inference workers to stop experience collection... (2750 times) [2023-03-09 10:42:01,855][119240] Signal inference workers to resume experience collection... (2750 times) [2023-03-09 10:42:01,856][119383] InferenceWorker_p0-w0: stopping experience collection (2750 times) [2023-03-09 10:42:01,858][119383] Updated weights for policy 0, policy_version 128729 (0.0018) [2023-03-09 10:42:01,901][119383] InferenceWorker_p0-w0: resuming experience collection (2750 times) [2023-03-09 10:42:02,600][119383] Updated weights for policy 0, policy_version 128739 (0.0015) [2023-03-09 10:42:03,621][119383] Updated weights for policy 0, policy_version 128749 (0.0020) [2023-03-09 10:42:03,902][118949] Fps is (10 sec: 194966.3, 60 sec: 196333.7, 300 sec: 196163.5). Total num frames: 2109489152. Throughput: 0: 49268.1. Samples: 27332736. Policy #0 lag: (min: 2.0, avg: 16.4, max: 34.0) [2023-03-09 10:42:03,904][118949] Avg episode reward: [(0, '55.726')] [2023-03-09 10:42:04,323][119383] Updated weights for policy 0, policy_version 128759 (0.0022) [2023-03-09 10:42:05,163][119383] Updated weights for policy 0, policy_version 128770 (0.0021) [2023-03-09 10:42:06,140][119383] Updated weights for policy 0, policy_version 128780 (0.0021) [2023-03-09 10:42:06,947][119383] Updated weights for policy 0, policy_version 128790 (0.0015) [2023-03-09 10:42:07,743][119383] Updated weights for policy 0, policy_version 128800 (0.0029) [2023-03-09 10:42:08,756][119383] Updated weights for policy 0, policy_version 128811 (0.0024) [2023-03-09 10:42:08,902][118949] Fps is (10 sec: 193341.5, 60 sec: 196335.2, 300 sec: 196052.8). Total num frames: 2110455808. Throughput: 0: 49176.3. Samples: 27629536. Policy #0 lag: (min: 2.0, avg: 16.4, max: 34.0) [2023-03-09 10:42:08,903][118949] Avg episode reward: [(0, '55.241')] [2023-03-09 10:42:09,534][119383] Updated weights for policy 0, policy_version 128821 (0.0013) [2023-03-09 10:42:10,317][119383] Updated weights for policy 0, policy_version 128831 (0.0021) [2023-03-09 10:42:11,246][119383] Updated weights for policy 0, policy_version 128841 (0.0021) [2023-03-09 10:42:12,037][119383] Updated weights for policy 0, policy_version 128851 (0.0021) [2023-03-09 10:42:12,817][119383] Updated weights for policy 0, policy_version 128861 (0.0016) [2023-03-09 10:42:13,772][119383] Updated weights for policy 0, policy_version 128871 (0.0025) [2023-03-09 10:42:13,848][119240] Signal inference workers to stop experience collection... (2800 times) [2023-03-09 10:42:13,865][119240] Signal inference workers to resume experience collection... (2800 times) [2023-03-09 10:42:13,892][119383] InferenceWorker_p0-w0: stopping experience collection (2800 times) [2023-03-09 10:42:13,902][118949] Fps is (10 sec: 194968.6, 60 sec: 196333.9, 300 sec: 196108.0). Total num frames: 2111438848. Throughput: 0: 49222.5. Samples: 27924400. Policy #0 lag: (min: 2.0, avg: 16.4, max: 34.0) [2023-03-09 10:42:13,905][118949] Avg episode reward: [(0, '54.887')] [2023-03-09 10:42:13,932][119383] InferenceWorker_p0-w0: resuming experience collection (2800 times) [2023-03-09 10:42:14,613][119383] Updated weights for policy 0, policy_version 128882 (0.0016) [2023-03-09 10:42:15,471][119383] Updated weights for policy 0, policy_version 128892 (0.0017) [2023-03-09 10:42:16,315][119383] Updated weights for policy 0, policy_version 128902 (0.0023) [2023-03-09 10:42:17,202][119383] Updated weights for policy 0, policy_version 128912 (0.0019) [2023-03-09 10:42:17,866][119383] Updated weights for policy 0, policy_version 128922 (0.0020) [2023-03-09 10:42:18,744][119383] Updated weights for policy 0, policy_version 128932 (0.0023) [2023-03-09 10:42:18,902][118949] Fps is (10 sec: 198241.3, 60 sec: 196880.8, 300 sec: 196108.2). Total num frames: 2112438272. Throughput: 0: 49175.6. Samples: 28069712. Policy #0 lag: (min: 2.0, avg: 16.4, max: 34.0) [2023-03-09 10:42:18,904][118949] Avg episode reward: [(0, '55.365')] [2023-03-09 10:42:19,725][119383] Updated weights for policy 0, policy_version 128942 (0.0013) [2023-03-09 10:42:20,460][119383] Updated weights for policy 0, policy_version 128952 (0.0016) [2023-03-09 10:42:21,183][119383] Updated weights for policy 0, policy_version 128962 (0.0028) [2023-03-09 10:42:22,173][119383] Updated weights for policy 0, policy_version 128972 (0.0020) [2023-03-09 10:42:22,907][119383] Updated weights for policy 0, policy_version 128982 (0.0026) [2023-03-09 10:42:23,756][119383] Updated weights for policy 0, policy_version 128992 (0.0031) [2023-03-09 10:42:23,902][118949] Fps is (10 sec: 199892.6, 60 sec: 197429.5, 300 sec: 196274.8). Total num frames: 2113437696. Throughput: 0: 49175.1. Samples: 28366560. Policy #0 lag: (min: 2.0, avg: 16.4, max: 34.0) [2023-03-09 10:42:23,903][118949] Avg episode reward: [(0, '54.968')] [2023-03-09 10:42:24,656][119383] Updated weights for policy 0, policy_version 129002 (0.0015) [2023-03-09 10:42:25,502][119383] Updated weights for policy 0, policy_version 129012 (0.0026) [2023-03-09 10:42:26,284][119383] Updated weights for policy 0, policy_version 129022 (0.0019) [2023-03-09 10:42:27,206][119383] Updated weights for policy 0, policy_version 129032 (0.0020) [2023-03-09 10:42:27,240][119240] Signal inference workers to stop experience collection... (2850 times) [2023-03-09 10:42:27,240][119240] Signal inference workers to resume experience collection... (2850 times) [2023-03-09 10:42:27,321][119383] InferenceWorker_p0-w0: stopping experience collection (2850 times) [2023-03-09 10:42:27,321][119383] InferenceWorker_p0-w0: resuming experience collection (2850 times) [2023-03-09 10:42:27,931][119383] Updated weights for policy 0, policy_version 129042 (0.0022) [2023-03-09 10:42:28,796][119383] Updated weights for policy 0, policy_version 129053 (0.0022) [2023-03-09 10:42:28,902][118949] Fps is (10 sec: 196610.8, 60 sec: 196881.4, 300 sec: 196275.0). Total num frames: 2114404352. Throughput: 0: 49175.7. Samples: 28661376. Policy #0 lag: (min: 2.0, avg: 16.4, max: 34.0) [2023-03-09 10:42:28,903][118949] Avg episode reward: [(0, '56.111')] [2023-03-09 10:42:29,769][119383] Updated weights for policy 0, policy_version 129063 (0.0021) [2023-03-09 10:42:30,543][119383] Updated weights for policy 0, policy_version 129073 (0.0013) [2023-03-09 10:42:31,312][119383] Updated weights for policy 0, policy_version 129083 (0.0015) [2023-03-09 10:42:32,167][119383] Updated weights for policy 0, policy_version 129093 (0.0025) [2023-03-09 10:42:33,088][119383] Updated weights for policy 0, policy_version 129103 (0.0024) [2023-03-09 10:42:33,779][119383] Updated weights for policy 0, policy_version 129113 (0.0013) [2023-03-09 10:42:33,902][118949] Fps is (10 sec: 196601.3, 60 sec: 197153.1, 300 sec: 196330.0). Total num frames: 2115403776. Throughput: 0: 49129.8. Samples: 28808768. Policy #0 lag: (min: 2.0, avg: 16.4, max: 34.0) [2023-03-09 10:42:33,905][118949] Avg episode reward: [(0, '52.082')] [2023-03-09 10:42:34,524][119383] Updated weights for policy 0, policy_version 129123 (0.0031) [2023-03-09 10:42:35,596][119383] Updated weights for policy 0, policy_version 129133 (0.0022) [2023-03-09 10:42:36,359][119383] Updated weights for policy 0, policy_version 129143 (0.0018) [2023-03-09 10:42:37,109][119383] Updated weights for policy 0, policy_version 129153 (0.0020) [2023-03-09 10:42:37,999][119383] Updated weights for policy 0, policy_version 129163 (0.0017) [2023-03-09 10:42:38,839][119383] Updated weights for policy 0, policy_version 129173 (0.0013) [2023-03-09 10:42:38,902][118949] Fps is (10 sec: 196610.1, 60 sec: 196608.9, 300 sec: 196274.8). Total num frames: 2116370432. Throughput: 0: 49177.1. Samples: 29107680. Policy #0 lag: (min: 2.0, avg: 17.7, max: 33.0) [2023-03-09 10:42:38,903][118949] Avg episode reward: [(0, '56.058')] [2023-03-09 10:42:39,054][119240] Signal inference workers to stop experience collection... (2900 times) [2023-03-09 10:42:39,070][119240] Signal inference workers to resume experience collection... (2900 times) [2023-03-09 10:42:39,128][119383] InferenceWorker_p0-w0: stopping experience collection (2900 times) [2023-03-09 10:42:39,129][119383] InferenceWorker_p0-w0: resuming experience collection (2900 times) [2023-03-09 10:42:39,668][119383] Updated weights for policy 0, policy_version 129183 (0.0021) [2023-03-09 10:42:40,582][119383] Updated weights for policy 0, policy_version 129193 (0.0021) [2023-03-09 10:42:41,326][119383] Updated weights for policy 0, policy_version 129203 (0.0024) [2023-03-09 10:42:42,137][119383] Updated weights for policy 0, policy_version 129213 (0.0031) [2023-03-09 10:42:43,052][119383] Updated weights for policy 0, policy_version 129223 (0.0016) [2023-03-09 10:42:43,856][119383] Updated weights for policy 0, policy_version 129233 (0.0019) [2023-03-09 10:42:43,902][118949] Fps is (10 sec: 196608.0, 60 sec: 196608.0, 300 sec: 196274.7). Total num frames: 2117369856. Throughput: 0: 49130.9. Samples: 29400368. Policy #0 lag: (min: 2.0, avg: 17.7, max: 33.0) [2023-03-09 10:42:43,904][118949] Avg episode reward: [(0, '53.554')] [2023-03-09 10:42:44,595][119383] Updated weights for policy 0, policy_version 129243 (0.0022) [2023-03-09 10:42:45,479][119383] Updated weights for policy 0, policy_version 129253 (0.0024) [2023-03-09 10:42:46,386][119383] Updated weights for policy 0, policy_version 129263 (0.0013) [2023-03-09 10:42:47,140][119383] Updated weights for policy 0, policy_version 129273 (0.0014) [2023-03-09 10:42:47,855][119383] Updated weights for policy 0, policy_version 129283 (0.0016) [2023-03-09 10:42:48,902][118949] Fps is (10 sec: 196608.3, 60 sec: 196335.6, 300 sec: 196275.1). Total num frames: 2118336512. Throughput: 0: 49223.9. Samples: 29547792. Policy #0 lag: (min: 2.0, avg: 17.7, max: 33.0) [2023-03-09 10:42:48,903][118949] Avg episode reward: [(0, '55.107')] [2023-03-09 10:42:48,911][119383] Updated weights for policy 0, policy_version 129293 (0.0016) [2023-03-09 10:42:49,678][119383] Updated weights for policy 0, policy_version 129303 (0.0013) [2023-03-09 10:42:50,277][119240] Signal inference workers to stop experience collection... (2950 times) [2023-03-09 10:42:50,280][119240] Signal inference workers to resume experience collection... (2950 times) [2023-03-09 10:42:50,337][119383] InferenceWorker_p0-w0: stopping experience collection (2950 times) [2023-03-09 10:42:50,337][119383] InferenceWorker_p0-w0: resuming experience collection (2950 times) [2023-03-09 10:42:50,424][119383] Updated weights for policy 0, policy_version 129313 (0.0013) [2023-03-09 10:42:51,457][119383] Updated weights for policy 0, policy_version 129324 (0.0020) [2023-03-09 10:42:52,210][119383] Updated weights for policy 0, policy_version 129334 (0.0015) [2023-03-09 10:42:53,006][119383] Updated weights for policy 0, policy_version 129344 (0.0033) [2023-03-09 10:42:53,902][118949] Fps is (10 sec: 194970.4, 60 sec: 196334.5, 300 sec: 196330.1). Total num frames: 2119319552. Throughput: 0: 49224.5. Samples: 29844656. Policy #0 lag: (min: 2.0, avg: 17.7, max: 33.0) [2023-03-09 10:42:53,905][118949] Avg episode reward: [(0, '54.336')] [2023-03-09 10:42:53,945][119383] Updated weights for policy 0, policy_version 129354 (0.0019) [2023-03-09 10:42:54,724][119383] Updated weights for policy 0, policy_version 129364 (0.0017) [2023-03-09 10:42:55,513][119383] Updated weights for policy 0, policy_version 129374 (0.0030) [2023-03-09 10:42:56,468][119383] Updated weights for policy 0, policy_version 129384 (0.0018) [2023-03-09 10:42:57,209][119383] Updated weights for policy 0, policy_version 129394 (0.0017) [2023-03-09 10:42:58,087][119383] Updated weights for policy 0, policy_version 129405 (0.0018) [2023-03-09 10:42:58,902][118949] Fps is (10 sec: 196607.2, 60 sec: 196336.6, 300 sec: 196275.0). Total num frames: 2120302592. Throughput: 0: 49179.4. Samples: 30137456. Policy #0 lag: (min: 2.0, avg: 17.7, max: 33.0) [2023-03-09 10:42:58,903][118949] Avg episode reward: [(0, '53.414')] [2023-03-09 10:42:59,044][119383] Updated weights for policy 0, policy_version 129415 (0.0025) [2023-03-09 10:42:59,835][119383] Updated weights for policy 0, policy_version 129425 (0.0014) [2023-03-09 10:43:00,589][119383] Updated weights for policy 0, policy_version 129435 (0.0016) [2023-03-09 10:43:01,460][119383] Updated weights for policy 0, policy_version 129445 (0.0020) [2023-03-09 10:43:02,384][119383] Updated weights for policy 0, policy_version 129455 (0.0021) [2023-03-09 10:43:02,425][119240] Signal inference workers to stop experience collection... (3000 times) [2023-03-09 10:43:02,428][119240] Signal inference workers to resume experience collection... (3000 times) [2023-03-09 10:43:02,498][119383] InferenceWorker_p0-w0: stopping experience collection (3000 times) [2023-03-09 10:43:02,498][119383] InferenceWorker_p0-w0: resuming experience collection (3000 times) [2023-03-09 10:43:03,078][119383] Updated weights for policy 0, policy_version 129465 (0.0038) [2023-03-09 10:43:03,833][119383] Updated weights for policy 0, policy_version 129475 (0.0017) [2023-03-09 10:43:03,902][118949] Fps is (10 sec: 199891.3, 60 sec: 197155.3, 300 sec: 196441.4). Total num frames: 2121318400. Throughput: 0: 49225.2. Samples: 30284832. Policy #0 lag: (min: 2.0, avg: 17.7, max: 33.0) [2023-03-09 10:43:03,903][118949] Avg episode reward: [(0, '52.439')] [2023-03-09 10:43:04,874][119383] Updated weights for policy 0, policy_version 129485 (0.0019) [2023-03-09 10:43:05,611][119383] Updated weights for policy 0, policy_version 129495 (0.0014) [2023-03-09 10:43:06,392][119383] Updated weights for policy 0, policy_version 129505 (0.0013) [2023-03-09 10:43:07,333][119383] Updated weights for policy 0, policy_version 129515 (0.0016) [2023-03-09 10:43:08,075][119383] Updated weights for policy 0, policy_version 129525 (0.0029) [2023-03-09 10:43:08,888][119383] Updated weights for policy 0, policy_version 129535 (0.0015) [2023-03-09 10:43:08,902][118949] Fps is (10 sec: 201518.2, 60 sec: 197699.3, 300 sec: 196552.5). Total num frames: 2122317824. Throughput: 0: 49269.4. Samples: 30583696. Policy #0 lag: (min: 2.0, avg: 17.7, max: 33.0) [2023-03-09 10:43:08,904][118949] Avg episode reward: [(0, '53.933')] [2023-03-09 10:43:09,848][119383] Updated weights for policy 0, policy_version 129545 (0.0019) [2023-03-09 10:43:10,590][119383] Updated weights for policy 0, policy_version 129555 (0.0022) [2023-03-09 10:43:11,351][119383] Updated weights for policy 0, policy_version 129565 (0.0018) [2023-03-09 10:43:12,347][119383] Updated weights for policy 0, policy_version 129575 (0.0020) [2023-03-09 10:43:13,083][119383] Updated weights for policy 0, policy_version 129585 (0.0023) [2023-03-09 10:43:13,176][119240] Signal inference workers to stop experience collection... (3050 times) [2023-03-09 10:43:13,177][119240] Signal inference workers to resume experience collection... (3050 times) [2023-03-09 10:43:13,244][119383] InferenceWorker_p0-w0: stopping experience collection (3050 times) [2023-03-09 10:43:13,246][119383] InferenceWorker_p0-w0: resuming experience collection (3050 times) [2023-03-09 10:43:13,822][119383] Updated weights for policy 0, policy_version 129595 (0.0017) [2023-03-09 10:43:13,902][118949] Fps is (10 sec: 198236.1, 60 sec: 197699.9, 300 sec: 196607.6). Total num frames: 2123300864. Throughput: 0: 49315.5. Samples: 30880592. Policy #0 lag: (min: 2.0, avg: 17.7, max: 33.0) [2023-03-09 10:43:13,904][118949] Avg episode reward: [(0, '54.257')] [2023-03-09 10:43:14,673][119383] Updated weights for policy 0, policy_version 129605 (0.0013) [2023-03-09 10:43:15,603][119383] Updated weights for policy 0, policy_version 129615 (0.0014) [2023-03-09 10:43:16,307][119383] Updated weights for policy 0, policy_version 129625 (0.0013) [2023-03-09 10:43:17,060][119383] Updated weights for policy 0, policy_version 129635 (0.0027) [2023-03-09 10:43:18,132][119383] Updated weights for policy 0, policy_version 129645 (0.0021) [2023-03-09 10:43:18,873][119383] Updated weights for policy 0, policy_version 129655 (0.0013) [2023-03-09 10:43:18,902][118949] Fps is (10 sec: 194973.5, 60 sec: 197154.7, 300 sec: 196497.1). Total num frames: 2124267520. Throughput: 0: 49316.9. Samples: 31028016. Policy #0 lag: (min: 2.0, avg: 17.7, max: 33.0) [2023-03-09 10:43:18,903][118949] Avg episode reward: [(0, '54.036')] [2023-03-09 10:43:19,656][119383] Updated weights for policy 0, policy_version 129665 (0.0014) [2023-03-09 10:43:20,585][119383] Updated weights for policy 0, policy_version 129675 (0.0020) [2023-03-09 10:43:21,320][119383] Updated weights for policy 0, policy_version 129685 (0.0028) [2023-03-09 10:43:22,147][119383] Updated weights for policy 0, policy_version 129695 (0.0012) [2023-03-09 10:43:23,076][119383] Updated weights for policy 0, policy_version 129705 (0.0018) [2023-03-09 10:43:23,902][118949] Fps is (10 sec: 196613.4, 60 sec: 197153.4, 300 sec: 196552.3). Total num frames: 2125266944. Throughput: 0: 49316.4. Samples: 31326928. Policy #0 lag: (min: 2.0, avg: 17.7, max: 33.0) [2023-03-09 10:43:23,904][118949] Avg episode reward: [(0, '54.638')] [2023-03-09 10:43:23,943][119240] Saving /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000129717_2125283328.pth... [2023-03-09 10:43:23,943][119383] Updated weights for policy 0, policy_version 129716 (0.0035) [2023-03-09 10:43:23,998][119240] Removing /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000126834_2078048256.pth [2023-03-09 10:43:24,712][119383] Updated weights for policy 0, policy_version 129726 (0.0014) [2023-03-09 10:43:24,974][119240] Signal inference workers to stop experience collection... (3100 times) [2023-03-09 10:43:24,975][119240] Signal inference workers to resume experience collection... (3100 times) [2023-03-09 10:43:25,039][119383] InferenceWorker_p0-w0: stopping experience collection (3100 times) [2023-03-09 10:43:25,040][119383] InferenceWorker_p0-w0: resuming experience collection (3100 times) [2023-03-09 10:43:25,709][119383] Updated weights for policy 0, policy_version 129737 (0.0020) [2023-03-09 10:43:26,498][119383] Updated weights for policy 0, policy_version 129747 (0.0015) [2023-03-09 10:43:27,345][119383] Updated weights for policy 0, policy_version 129758 (0.0017) [2023-03-09 10:43:28,356][119383] Updated weights for policy 0, policy_version 129768 (0.0016) [2023-03-09 10:43:28,902][118949] Fps is (10 sec: 198243.8, 60 sec: 197426.9, 300 sec: 196607.9). Total num frames: 2126249984. Throughput: 0: 49364.1. Samples: 31621744. Policy #0 lag: (min: 2.0, avg: 17.7, max: 33.0) [2023-03-09 10:43:28,903][118949] Avg episode reward: [(0, '54.011')] [2023-03-09 10:43:29,175][119383] Updated weights for policy 0, policy_version 129779 (0.0019) [2023-03-09 10:43:29,909][119383] Updated weights for policy 0, policy_version 129789 (0.0013) [2023-03-09 10:43:30,914][119383] Updated weights for policy 0, policy_version 129799 (0.0016) [2023-03-09 10:43:31,661][119383] Updated weights for policy 0, policy_version 129809 (0.0014) [2023-03-09 10:43:32,520][119383] Updated weights for policy 0, policy_version 129819 (0.0017) [2023-03-09 10:43:33,321][119383] Updated weights for policy 0, policy_version 129829 (0.0027) [2023-03-09 10:43:33,902][118949] Fps is (10 sec: 194967.9, 60 sec: 196881.2, 300 sec: 196607.8). Total num frames: 2127216640. Throughput: 0: 49363.2. Samples: 31769152. Policy #0 lag: (min: 2.0, avg: 17.7, max: 33.0) [2023-03-09 10:43:33,904][118949] Avg episode reward: [(0, '56.158')] [2023-03-09 10:43:34,193][119383] Updated weights for policy 0, policy_version 129839 (0.0020) [2023-03-09 10:43:34,921][119383] Updated weights for policy 0, policy_version 129849 (0.0032) [2023-03-09 10:43:35,838][119383] Updated weights for policy 0, policy_version 129860 (0.0019) [2023-03-09 10:43:36,393][119240] Signal inference workers to stop experience collection... (3150 times) [2023-03-09 10:43:36,395][119240] Signal inference workers to resume experience collection... (3150 times) [2023-03-09 10:43:36,441][119383] InferenceWorker_p0-w0: stopping experience collection (3150 times) [2023-03-09 10:43:36,441][119383] InferenceWorker_p0-w0: resuming experience collection (3150 times) [2023-03-09 10:43:36,810][119383] Updated weights for policy 0, policy_version 129870 (0.0018) [2023-03-09 10:43:37,532][119383] Updated weights for policy 0, policy_version 129880 (0.0022) [2023-03-09 10:43:38,317][119383] Updated weights for policy 0, policy_version 129890 (0.0018) [2023-03-09 10:43:38,902][118949] Fps is (10 sec: 194967.1, 60 sec: 197153.0, 300 sec: 196663.3). Total num frames: 2128199680. Throughput: 0: 49317.0. Samples: 32063920. Policy #0 lag: (min: 0.0, avg: 18.2, max: 34.0) [2023-03-09 10:43:38,904][118949] Avg episode reward: [(0, '54.660')] [2023-03-09 10:43:39,263][119383] Updated weights for policy 0, policy_version 129900 (0.0021) [2023-03-09 10:43:40,038][119383] Updated weights for policy 0, policy_version 129910 (0.0026) [2023-03-09 10:43:40,795][119383] Updated weights for policy 0, policy_version 129920 (0.0022) [2023-03-09 10:43:41,763][119383] Updated weights for policy 0, policy_version 129930 (0.0019) [2023-03-09 10:43:42,560][119383] Updated weights for policy 0, policy_version 129940 (0.0013) [2023-03-09 10:43:43,328][119383] Updated weights for policy 0, policy_version 129950 (0.0013) [2023-03-09 10:43:43,902][118949] Fps is (10 sec: 198252.0, 60 sec: 197155.2, 300 sec: 196774.7). Total num frames: 2129199104. Throughput: 0: 49406.6. Samples: 32360752. Policy #0 lag: (min: 0.0, avg: 18.2, max: 34.0) [2023-03-09 10:43:43,903][118949] Avg episode reward: [(0, '55.271')] [2023-03-09 10:43:44,304][119383] Updated weights for policy 0, policy_version 129960 (0.0014) [2023-03-09 10:43:45,010][119383] Updated weights for policy 0, policy_version 129970 (0.0017) [2023-03-09 10:43:45,795][119383] Updated weights for policy 0, policy_version 129980 (0.0016) [2023-03-09 10:43:46,005][119240] Signal inference workers to stop experience collection... (3200 times) [2023-03-09 10:43:46,033][119240] Signal inference workers to resume experience collection... (3200 times) [2023-03-09 10:43:46,110][119383] InferenceWorker_p0-w0: stopping experience collection (3200 times) [2023-03-09 10:43:46,110][119383] InferenceWorker_p0-w0: resuming experience collection (3200 times) [2023-03-09 10:43:46,711][119383] Updated weights for policy 0, policy_version 129990 (0.0016) [2023-03-09 10:43:47,539][119383] Updated weights for policy 0, policy_version 130000 (0.0026) [2023-03-09 10:43:48,313][119383] Updated weights for policy 0, policy_version 130010 (0.0016) [2023-03-09 10:43:48,902][118949] Fps is (10 sec: 199891.1, 60 sec: 197700.2, 300 sec: 196774.8). Total num frames: 2130198528. Throughput: 0: 49452.1. Samples: 32510176. Policy #0 lag: (min: 0.0, avg: 18.2, max: 34.0) [2023-03-09 10:43:48,904][118949] Avg episode reward: [(0, '55.724')] [2023-03-09 10:43:49,114][119383] Updated weights for policy 0, policy_version 130020 (0.0020) [2023-03-09 10:43:50,169][119383] Updated weights for policy 0, policy_version 130031 (0.0023) [2023-03-09 10:43:50,880][119383] Updated weights for policy 0, policy_version 130041 (0.0015) [2023-03-09 10:43:51,659][119383] Updated weights for policy 0, policy_version 130051 (0.0020) [2023-03-09 10:43:52,738][119383] Updated weights for policy 0, policy_version 130061 (0.0016) [2023-03-09 10:43:53,437][119383] Updated weights for policy 0, policy_version 130071 (0.0016) [2023-03-09 10:43:53,902][118949] Fps is (10 sec: 198239.7, 60 sec: 197700.0, 300 sec: 196774.4). Total num frames: 2131181568. Throughput: 0: 49316.9. Samples: 32802960. Policy #0 lag: (min: 0.0, avg: 18.2, max: 34.0) [2023-03-09 10:43:53,904][118949] Avg episode reward: [(0, '56.804')] [2023-03-09 10:43:54,228][119383] Updated weights for policy 0, policy_version 130081 (0.0020) [2023-03-09 10:43:55,144][119383] Updated weights for policy 0, policy_version 130091 (0.0019) [2023-03-09 10:43:55,549][119240] Signal inference workers to stop experience collection... (3250 times) [2023-03-09 10:43:55,553][119240] Signal inference workers to resume experience collection... (3250 times) [2023-03-09 10:43:55,618][119383] InferenceWorker_p0-w0: stopping experience collection (3250 times) [2023-03-09 10:43:55,619][119383] InferenceWorker_p0-w0: resuming experience collection (3250 times) [2023-03-09 10:43:55,995][119383] Updated weights for policy 0, policy_version 130102 (0.0012) [2023-03-09 10:43:56,755][119383] Updated weights for policy 0, policy_version 130112 (0.0024) [2023-03-09 10:43:57,712][119383] Updated weights for policy 0, policy_version 130122 (0.0018) [2023-03-09 10:43:58,519][119383] Updated weights for policy 0, policy_version 130132 (0.0015) [2023-03-09 10:43:58,902][118949] Fps is (10 sec: 196608.8, 60 sec: 197700.4, 300 sec: 196719.3). Total num frames: 2132164608. Throughput: 0: 49314.0. Samples: 33099696. Policy #0 lag: (min: 0.0, avg: 18.2, max: 34.0) [2023-03-09 10:43:58,903][118949] Avg episode reward: [(0, '55.823')] [2023-03-09 10:43:59,287][119383] Updated weights for policy 0, policy_version 130142 (0.0017) [2023-03-09 10:44:00,248][119383] Updated weights for policy 0, policy_version 130152 (0.0024) [2023-03-09 10:44:01,043][119383] Updated weights for policy 0, policy_version 130162 (0.0029) [2023-03-09 10:44:01,776][119383] Updated weights for policy 0, policy_version 130172 (0.0022) [2023-03-09 10:44:02,699][119383] Updated weights for policy 0, policy_version 130182 (0.0017) [2023-03-09 10:44:03,555][119383] Updated weights for policy 0, policy_version 130193 (0.0018) [2023-03-09 10:44:03,902][118949] Fps is (10 sec: 196615.6, 60 sec: 197154.1, 300 sec: 196774.6). Total num frames: 2133147648. Throughput: 0: 49358.0. Samples: 33249120. Policy #0 lag: (min: 0.0, avg: 18.2, max: 34.0) [2023-03-09 10:44:03,903][118949] Avg episode reward: [(0, '54.828')] [2023-03-09 10:44:04,332][119383] Updated weights for policy 0, policy_version 130203 (0.0016) [2023-03-09 10:44:05,254][119383] Updated weights for policy 0, policy_version 130213 (0.0024) [2023-03-09 10:44:05,590][119240] Signal inference workers to stop experience collection... (3300 times) [2023-03-09 10:44:05,591][119240] Signal inference workers to resume experience collection... (3300 times) [2023-03-09 10:44:05,658][119383] InferenceWorker_p0-w0: stopping experience collection (3300 times) [2023-03-09 10:44:05,658][119383] InferenceWorker_p0-w0: resuming experience collection (3300 times) [2023-03-09 10:44:06,216][119383] Updated weights for policy 0, policy_version 130224 (0.0013) [2023-03-09 10:44:06,956][119383] Updated weights for policy 0, policy_version 130234 (0.0031) [2023-03-09 10:44:07,812][119383] Updated weights for policy 0, policy_version 130244 (0.0028) [2023-03-09 10:44:08,760][119383] Updated weights for policy 0, policy_version 130254 (0.0026) [2023-03-09 10:44:08,902][118949] Fps is (10 sec: 194968.6, 60 sec: 196608.8, 300 sec: 196663.7). Total num frames: 2134114304. Throughput: 0: 49176.4. Samples: 33539856. Policy #0 lag: (min: 0.0, avg: 18.2, max: 34.0) [2023-03-09 10:44:08,903][118949] Avg episode reward: [(0, '55.481')] [2023-03-09 10:44:09,536][119383] Updated weights for policy 0, policy_version 130264 (0.0027) [2023-03-09 10:44:10,266][119383] Updated weights for policy 0, policy_version 130274 (0.0019) [2023-03-09 10:44:11,215][119383] Updated weights for policy 0, policy_version 130284 (0.0025) [2023-03-09 10:44:12,045][119383] Updated weights for policy 0, policy_version 130294 (0.0017) [2023-03-09 10:44:12,891][119383] Updated weights for policy 0, policy_version 130305 (0.0013) [2023-03-09 10:44:13,788][119383] Updated weights for policy 0, policy_version 130315 (0.0023) [2023-03-09 10:44:13,902][118949] Fps is (10 sec: 194969.3, 60 sec: 196609.6, 300 sec: 196663.8). Total num frames: 2135097344. Throughput: 0: 49221.6. Samples: 33836704. Policy #0 lag: (min: 0.0, avg: 18.2, max: 34.0) [2023-03-09 10:44:13,903][118949] Avg episode reward: [(0, '55.652')] [2023-03-09 10:44:14,608][119383] Updated weights for policy 0, policy_version 130325 (0.0017) [2023-03-09 10:44:15,388][119383] Updated weights for policy 0, policy_version 130335 (0.0013) [2023-03-09 10:44:16,270][119240] Signal inference workers to stop experience collection... (3350 times) [2023-03-09 10:44:16,272][119240] Signal inference workers to resume experience collection... (3350 times) [2023-03-09 10:44:16,338][119383] InferenceWorker_p0-w0: stopping experience collection (3350 times) [2023-03-09 10:44:16,339][119383] InferenceWorker_p0-w0: resuming experience collection (3350 times) [2023-03-09 10:44:16,342][119383] Updated weights for policy 0, policy_version 130345 (0.0017) [2023-03-09 10:44:17,165][119383] Updated weights for policy 0, policy_version 130355 (0.0017) [2023-03-09 10:44:17,899][119383] Updated weights for policy 0, policy_version 130365 (0.0024) [2023-03-09 10:44:18,874][119383] Updated weights for policy 0, policy_version 130375 (0.0018) [2023-03-09 10:44:18,902][118949] Fps is (10 sec: 194968.5, 60 sec: 196608.0, 300 sec: 196663.5). Total num frames: 2136064000. Throughput: 0: 49176.4. Samples: 33982080. Policy #0 lag: (min: 0.0, avg: 18.2, max: 34.0) [2023-03-09 10:44:18,903][118949] Avg episode reward: [(0, '54.027')] [2023-03-09 10:44:19,720][119383] Updated weights for policy 0, policy_version 130386 (0.0016) [2023-03-09 10:44:20,506][119383] Updated weights for policy 0, policy_version 130396 (0.0013) [2023-03-09 10:44:21,421][119383] Updated weights for policy 0, policy_version 130406 (0.0016) [2023-03-09 10:44:22,257][119383] Updated weights for policy 0, policy_version 130417 (0.0013) [2023-03-09 10:44:23,044][119383] Updated weights for policy 0, policy_version 130427 (0.0019) [2023-03-09 10:44:23,902][118949] Fps is (10 sec: 196601.6, 60 sec: 196607.7, 300 sec: 196774.4). Total num frames: 2137063424. Throughput: 0: 49223.8. Samples: 34278992. Policy #0 lag: (min: 0.0, avg: 18.2, max: 34.0) [2023-03-09 10:44:23,904][118949] Avg episode reward: [(0, '55.162')] [2023-03-09 10:44:23,931][119383] Updated weights for policy 0, policy_version 130437 (0.0013) [2023-03-09 10:44:24,832][119383] Updated weights for policy 0, policy_version 130447 (0.0021) [2023-03-09 10:44:25,164][119240] Signal inference workers to stop experience collection... (3400 times) [2023-03-09 10:44:25,182][119240] Signal inference workers to resume experience collection... (3400 times) [2023-03-09 10:44:25,261][119383] InferenceWorker_p0-w0: stopping experience collection (3400 times) [2023-03-09 10:44:25,261][119383] InferenceWorker_p0-w0: resuming experience collection (3400 times) [2023-03-09 10:44:25,643][119383] Updated weights for policy 0, policy_version 130458 (0.0025) [2023-03-09 10:44:26,467][119383] Updated weights for policy 0, policy_version 130468 (0.0013) [2023-03-09 10:44:27,415][119383] Updated weights for policy 0, policy_version 130479 (0.0016) [2023-03-09 10:44:28,321][119383] Updated weights for policy 0, policy_version 130490 (0.0021) [2023-03-09 10:44:28,902][118949] Fps is (10 sec: 199887.0, 60 sec: 196881.8, 300 sec: 196886.0). Total num frames: 2138062848. Throughput: 0: 49086.3. Samples: 34569632. Policy #0 lag: (min: 0.0, avg: 18.2, max: 34.0) [2023-03-09 10:44:28,903][118949] Avg episode reward: [(0, '53.969')] [2023-03-09 10:44:29,281][119383] Updated weights for policy 0, policy_version 130501 (0.0020) [2023-03-09 10:44:30,174][119383] Updated weights for policy 0, policy_version 130511 (0.0034) [2023-03-09 10:44:30,897][119383] Updated weights for policy 0, policy_version 130521 (0.0018) [2023-03-09 10:44:31,688][119383] Updated weights for policy 0, policy_version 130531 (0.0013) [2023-03-09 10:44:32,724][119383] Updated weights for policy 0, policy_version 130541 (0.0027) [2023-03-09 10:44:33,473][119383] Updated weights for policy 0, policy_version 130551 (0.0022) [2023-03-09 10:44:33,902][118949] Fps is (10 sec: 198251.6, 60 sec: 197155.0, 300 sec: 196830.5). Total num frames: 2139045888. Throughput: 0: 49086.5. Samples: 34719072. Policy #0 lag: (min: 0.0, avg: 18.2, max: 34.0) [2023-03-09 10:44:33,903][118949] Avg episode reward: [(0, '55.783')] [2023-03-09 10:44:34,209][119383] Updated weights for policy 0, policy_version 130561 (0.0017) [2023-03-09 10:44:35,122][119383] Updated weights for policy 0, policy_version 130571 (0.0024) [2023-03-09 10:44:35,441][119240] Signal inference workers to stop experience collection... (3450 times) [2023-03-09 10:44:35,457][119240] Signal inference workers to resume experience collection... (3450 times) [2023-03-09 10:44:35,485][119383] InferenceWorker_p0-w0: stopping experience collection (3450 times) [2023-03-09 10:44:35,531][119383] InferenceWorker_p0-w0: resuming experience collection (3450 times) [2023-03-09 10:44:35,938][119383] Updated weights for policy 0, policy_version 130581 (0.0030) [2023-03-09 10:44:36,716][119383] Updated weights for policy 0, policy_version 130591 (0.0013) [2023-03-09 10:44:37,641][119383] Updated weights for policy 0, policy_version 130601 (0.0022) [2023-03-09 10:44:38,523][119383] Updated weights for policy 0, policy_version 130612 (0.0017) [2023-03-09 10:44:38,902][118949] Fps is (10 sec: 196601.7, 60 sec: 197154.3, 300 sec: 196774.4). Total num frames: 2140028928. Throughput: 0: 49175.9. Samples: 35015872. Policy #0 lag: (min: 0.0, avg: 18.2, max: 34.0) [2023-03-09 10:44:38,904][118949] Avg episode reward: [(0, '54.027')] [2023-03-09 10:44:39,315][119383] Updated weights for policy 0, policy_version 130622 (0.0016) [2023-03-09 10:44:40,290][119383] Updated weights for policy 0, policy_version 130632 (0.0016) [2023-03-09 10:44:41,167][119383] Updated weights for policy 0, policy_version 130643 (0.0013) [2023-03-09 10:44:41,868][119383] Updated weights for policy 0, policy_version 130653 (0.0013) [2023-03-09 10:44:42,831][119383] Updated weights for policy 0, policy_version 130663 (0.0026) [2023-03-09 10:44:43,548][119383] Updated weights for policy 0, policy_version 130673 (0.0016) [2023-03-09 10:44:43,902][118949] Fps is (10 sec: 196608.8, 60 sec: 196881.1, 300 sec: 196830.2). Total num frames: 2141011968. Throughput: 0: 49176.5. Samples: 35312640. Policy #0 lag: (min: 0.0, avg: 16.0, max: 32.0) [2023-03-09 10:44:43,903][118949] Avg episode reward: [(0, '55.561')] [2023-03-09 10:44:44,362][119383] Updated weights for policy 0, policy_version 130683 (0.0022) [2023-03-09 10:44:45,211][119383] Updated weights for policy 0, policy_version 130693 (0.0013) [2023-03-09 10:44:45,627][119240] Signal inference workers to stop experience collection... (3500 times) [2023-03-09 10:44:45,629][119240] Signal inference workers to resume experience collection... (3500 times) [2023-03-09 10:44:45,697][119383] InferenceWorker_p0-w0: stopping experience collection (3500 times) [2023-03-09 10:44:45,698][119383] InferenceWorker_p0-w0: resuming experience collection (3500 times) [2023-03-09 10:44:46,112][119383] Updated weights for policy 0, policy_version 130703 (0.0026) [2023-03-09 10:44:46,848][119383] Updated weights for policy 0, policy_version 130713 (0.0016) [2023-03-09 10:44:47,646][119383] Updated weights for policy 0, policy_version 130723 (0.0021) [2023-03-09 10:44:48,675][119383] Updated weights for policy 0, policy_version 130733 (0.0016) [2023-03-09 10:44:48,902][118949] Fps is (10 sec: 196614.0, 60 sec: 196608.1, 300 sec: 196774.6). Total num frames: 2141995008. Throughput: 0: 49085.9. Samples: 35457984. Policy #0 lag: (min: 0.0, avg: 16.0, max: 32.0) [2023-03-09 10:44:48,903][118949] Avg episode reward: [(0, '52.966')] [2023-03-09 10:44:49,370][119383] Updated weights for policy 0, policy_version 130743 (0.0018) [2023-03-09 10:44:50,182][119383] Updated weights for policy 0, policy_version 130753 (0.0017) [2023-03-09 10:44:51,076][119383] Updated weights for policy 0, policy_version 130763 (0.0028) [2023-03-09 10:44:51,853][119383] Updated weights for policy 0, policy_version 130773 (0.0020) [2023-03-09 10:44:52,661][119383] Updated weights for policy 0, policy_version 130783 (0.0016) [2023-03-09 10:44:53,634][119383] Updated weights for policy 0, policy_version 130793 (0.0024) [2023-03-09 10:44:53,902][118949] Fps is (10 sec: 194970.1, 60 sec: 196336.2, 300 sec: 196719.1). Total num frames: 2142961664. Throughput: 0: 49220.6. Samples: 35754784. Policy #0 lag: (min: 0.0, avg: 16.0, max: 32.0) [2023-03-09 10:44:53,903][118949] Avg episode reward: [(0, '56.067')] [2023-03-09 10:44:54,529][119383] Updated weights for policy 0, policy_version 130804 (0.0022) [2023-03-09 10:44:55,244][119240] Signal inference workers to stop experience collection... (3550 times) [2023-03-09 10:44:55,245][119240] Signal inference workers to resume experience collection... (3550 times) [2023-03-09 10:44:55,268][119383] Updated weights for policy 0, policy_version 130814 (0.0025) [2023-03-09 10:44:55,311][119383] InferenceWorker_p0-w0: stopping experience collection (3550 times) [2023-03-09 10:44:55,311][119383] InferenceWorker_p0-w0: resuming experience collection (3550 times) [2023-03-09 10:44:56,226][119383] Updated weights for policy 0, policy_version 130824 (0.0017) [2023-03-09 10:44:57,038][119383] Updated weights for policy 0, policy_version 130834 (0.0013) [2023-03-09 10:44:57,760][119383] Updated weights for policy 0, policy_version 130844 (0.0016) [2023-03-09 10:44:58,710][119383] Updated weights for policy 0, policy_version 130854 (0.0017) [2023-03-09 10:44:58,902][118949] Fps is (10 sec: 194969.7, 60 sec: 196334.9, 300 sec: 196719.6). Total num frames: 2143944704. Throughput: 0: 49176.2. Samples: 36049632. Policy #0 lag: (min: 0.0, avg: 16.0, max: 32.0) [2023-03-09 10:44:58,903][118949] Avg episode reward: [(0, '54.206')] [2023-03-09 10:44:59,510][119383] Updated weights for policy 0, policy_version 130864 (0.0013) [2023-03-09 10:45:00,207][119383] Updated weights for policy 0, policy_version 130874 (0.0024) [2023-03-09 10:45:01,157][119383] Updated weights for policy 0, policy_version 130885 (0.0015) [2023-03-09 10:45:02,077][119383] Updated weights for policy 0, policy_version 130895 (0.0016) [2023-03-09 10:45:02,717][119383] Updated weights for policy 0, policy_version 130905 (0.0013) [2023-03-09 10:45:03,577][119383] Updated weights for policy 0, policy_version 130915 (0.0020) [2023-03-09 10:45:03,902][118949] Fps is (10 sec: 198240.7, 60 sec: 196607.0, 300 sec: 196830.0). Total num frames: 2144944128. Throughput: 0: 49265.6. Samples: 36199040. Policy #0 lag: (min: 0.0, avg: 16.0, max: 32.0) [2023-03-09 10:45:03,904][118949] Avg episode reward: [(0, '54.619')] [2023-03-09 10:45:04,257][119240] Signal inference workers to stop experience collection... (3600 times) [2023-03-09 10:45:04,283][119240] Signal inference workers to resume experience collection... (3600 times) [2023-03-09 10:45:04,330][119383] InferenceWorker_p0-w0: stopping experience collection (3600 times) [2023-03-09 10:45:04,330][119383] InferenceWorker_p0-w0: resuming experience collection (3600 times) [2023-03-09 10:45:04,614][119383] Updated weights for policy 0, policy_version 130925 (0.0024) [2023-03-09 10:45:05,321][119383] Updated weights for policy 0, policy_version 130935 (0.0016) [2023-03-09 10:45:06,033][119383] Updated weights for policy 0, policy_version 130945 (0.0014) [2023-03-09 10:45:06,990][119383] Updated weights for policy 0, policy_version 130955 (0.0013) [2023-03-09 10:45:07,805][119383] Updated weights for policy 0, policy_version 130965 (0.0034) [2023-03-09 10:45:08,701][119383] Updated weights for policy 0, policy_version 130976 (0.0014) [2023-03-09 10:45:08,903][118949] Fps is (10 sec: 201507.8, 60 sec: 197424.8, 300 sec: 196996.4). Total num frames: 2145959936. Throughput: 0: 49263.2. Samples: 36495856. Policy #0 lag: (min: 0.0, avg: 16.0, max: 32.0) [2023-03-09 10:45:08,905][118949] Avg episode reward: [(0, '55.785')] [2023-03-09 10:45:09,601][119383] Updated weights for policy 0, policy_version 130986 (0.0016) [2023-03-09 10:45:10,427][119383] Updated weights for policy 0, policy_version 130996 (0.0013) [2023-03-09 10:45:11,167][119383] Updated weights for policy 0, policy_version 131006 (0.0024) [2023-03-09 10:45:12,087][119383] Updated weights for policy 0, policy_version 131016 (0.0013) [2023-03-09 10:45:12,946][119240] Signal inference workers to stop experience collection... (3650 times) [2023-03-09 10:45:12,973][119240] Signal inference workers to resume experience collection... (3650 times) [2023-03-09 10:45:12,976][119383] InferenceWorker_p0-w0: stopping experience collection (3650 times) [2023-03-09 10:45:12,980][119383] InferenceWorker_p0-w0: resuming experience collection (3650 times) [2023-03-09 10:45:12,983][119383] Updated weights for policy 0, policy_version 131027 (0.0017) [2023-03-09 10:45:13,814][119383] Updated weights for policy 0, policy_version 131038 (0.0023) [2023-03-09 10:45:13,902][118949] Fps is (10 sec: 199882.5, 60 sec: 197425.9, 300 sec: 196941.0). Total num frames: 2146942976. Throughput: 0: 49400.8. Samples: 36792688. Policy #0 lag: (min: 0.0, avg: 16.0, max: 32.0) [2023-03-09 10:45:13,904][118949] Avg episode reward: [(0, '53.923')] [2023-03-09 10:45:14,824][119383] Updated weights for policy 0, policy_version 131049 (0.0013) [2023-03-09 10:45:15,697][119383] Updated weights for policy 0, policy_version 131060 (0.0030) [2023-03-09 10:45:16,534][119383] Updated weights for policy 0, policy_version 131070 (0.0014) [2023-03-09 10:45:17,456][119383] Updated weights for policy 0, policy_version 131080 (0.0023) [2023-03-09 10:45:18,226][119383] Updated weights for policy 0, policy_version 131090 (0.0016) [2023-03-09 10:45:18,902][118949] Fps is (10 sec: 196616.5, 60 sec: 197699.5, 300 sec: 196885.5). Total num frames: 2147926016. Throughput: 0: 49355.5. Samples: 36940080. Policy #0 lag: (min: 0.0, avg: 16.0, max: 32.0) [2023-03-09 10:45:18,904][118949] Avg episode reward: [(0, '55.293')] [2023-03-09 10:45:18,973][119383] Updated weights for policy 0, policy_version 131100 (0.0021) [2023-03-09 10:45:20,078][119383] Updated weights for policy 0, policy_version 131111 (0.0022) [2023-03-09 10:45:20,800][119383] Updated weights for policy 0, policy_version 131121 (0.0016) [2023-03-09 10:45:21,559][119383] Updated weights for policy 0, policy_version 131131 (0.0013) [2023-03-09 10:45:22,385][119383] Updated weights for policy 0, policy_version 131141 (0.0013) [2023-03-09 10:45:22,671][119240] Signal inference workers to stop experience collection... (3700 times) [2023-03-09 10:45:22,675][119240] Signal inference workers to resume experience collection... (3700 times) [2023-03-09 10:45:22,737][119383] InferenceWorker_p0-w0: stopping experience collection (3700 times) [2023-03-09 10:45:22,738][119383] InferenceWorker_p0-w0: resuming experience collection (3700 times) [2023-03-09 10:45:23,306][119383] Updated weights for policy 0, policy_version 131151 (0.0013) [2023-03-09 10:45:23,902][118949] Fps is (10 sec: 196608.5, 60 sec: 197427.1, 300 sec: 196885.5). Total num frames: 2148909056. Throughput: 0: 49356.4. Samples: 37236912. Policy #0 lag: (min: 0.0, avg: 16.0, max: 32.0) [2023-03-09 10:45:23,904][118949] Avg episode reward: [(0, '55.957')] [2023-03-09 10:45:23,974][119240] Saving /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000131161_2148941824.pth... [2023-03-09 10:45:23,983][119383] Updated weights for policy 0, policy_version 131161 (0.0015) [2023-03-09 10:45:24,039][119240] Removing /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000128273_2101624832.pth [2023-03-09 10:45:24,887][119383] Updated weights for policy 0, policy_version 131171 (0.0019) [2023-03-09 10:45:25,838][119383] Updated weights for policy 0, policy_version 131181 (0.0014) [2023-03-09 10:45:26,521][119383] Updated weights for policy 0, policy_version 131191 (0.0013) [2023-03-09 10:45:27,328][119383] Updated weights for policy 0, policy_version 131202 (0.0020) [2023-03-09 10:45:28,319][119383] Updated weights for policy 0, policy_version 131212 (0.0015) [2023-03-09 10:45:28,902][118949] Fps is (10 sec: 196614.5, 60 sec: 197154.1, 300 sec: 196885.7). Total num frames: 2149892096. Throughput: 0: 49356.5. Samples: 37533680. Policy #0 lag: (min: 0.0, avg: 16.0, max: 32.0) [2023-03-09 10:45:28,903][118949] Avg episode reward: [(0, '54.378')] [2023-03-09 10:45:29,075][119383] Updated weights for policy 0, policy_version 131222 (0.0022) [2023-03-09 10:45:29,999][119383] Updated weights for policy 0, policy_version 131233 (0.0027) [2023-03-09 10:45:30,768][119240] Signal inference workers to stop experience collection... (3750 times) [2023-03-09 10:45:30,793][119240] Signal inference workers to resume experience collection... (3750 times) [2023-03-09 10:45:30,843][119383] InferenceWorker_p0-w0: stopping experience collection (3750 times) [2023-03-09 10:45:30,843][119383] InferenceWorker_p0-w0: resuming experience collection (3750 times) [2023-03-09 10:45:30,845][119383] Updated weights for policy 0, policy_version 131243 (0.0013) [2023-03-09 10:45:31,724][119383] Updated weights for policy 0, policy_version 131253 (0.0022) [2023-03-09 10:45:32,503][119383] Updated weights for policy 0, policy_version 131263 (0.0023) [2023-03-09 10:45:33,447][119383] Updated weights for policy 0, policy_version 131274 (0.0013) [2023-03-09 10:45:33,902][118949] Fps is (10 sec: 196610.4, 60 sec: 197153.5, 300 sec: 196996.8). Total num frames: 2150875136. Throughput: 0: 49400.6. Samples: 37681024. Policy #0 lag: (min: 0.0, avg: 16.0, max: 32.0) [2023-03-09 10:45:33,904][118949] Avg episode reward: [(0, '54.100')] [2023-03-09 10:45:34,252][119383] Updated weights for policy 0, policy_version 131284 (0.0013) [2023-03-09 10:45:35,064][119383] Updated weights for policy 0, policy_version 131294 (0.0019) [2023-03-09 10:45:35,958][119383] Updated weights for policy 0, policy_version 131304 (0.0016) [2023-03-09 10:45:36,745][119383] Updated weights for policy 0, policy_version 131314 (0.0013) [2023-03-09 10:45:37,510][119383] Updated weights for policy 0, policy_version 131324 (0.0024) [2023-03-09 10:45:38,486][119383] Updated weights for policy 0, policy_version 131334 (0.0029) [2023-03-09 10:45:38,902][118949] Fps is (10 sec: 196601.9, 60 sec: 197154.1, 300 sec: 196997.1). Total num frames: 2151858176. Throughput: 0: 49400.6. Samples: 37977824. Policy #0 lag: (min: 0.0, avg: 16.0, max: 32.0) [2023-03-09 10:45:38,904][118949] Avg episode reward: [(0, '55.854')] [2023-03-09 10:45:39,305][119383] Updated weights for policy 0, policy_version 131344 (0.0038) [2023-03-09 10:45:39,693][119240] Signal inference workers to stop experience collection... (3800 times) [2023-03-09 10:45:39,694][119240] Signal inference workers to resume experience collection... (3800 times) [2023-03-09 10:45:39,759][119383] InferenceWorker_p0-w0: stopping experience collection (3800 times) [2023-03-09 10:45:39,759][119383] InferenceWorker_p0-w0: resuming experience collection (3800 times) [2023-03-09 10:45:40,013][119383] Updated weights for policy 0, policy_version 131354 (0.0022) [2023-03-09 10:45:40,866][119383] Updated weights for policy 0, policy_version 131364 (0.0026) [2023-03-09 10:45:41,862][119383] Updated weights for policy 0, policy_version 131374 (0.0028) [2023-03-09 10:45:42,531][119383] Updated weights for policy 0, policy_version 131384 (0.0013) [2023-03-09 10:45:43,313][119383] Updated weights for policy 0, policy_version 131394 (0.0013) [2023-03-09 10:45:43,902][118949] Fps is (10 sec: 194968.7, 60 sec: 196880.2, 300 sec: 196941.2). Total num frames: 2152824832. Throughput: 0: 49400.2. Samples: 38272656. Policy #0 lag: (min: 1.0, avg: 17.3, max: 33.0) [2023-03-09 10:45:43,904][118949] Avg episode reward: [(0, '54.680')] [2023-03-09 10:45:44,270][119383] Updated weights for policy 0, policy_version 131404 (0.0013) [2023-03-09 10:45:45,059][119383] Updated weights for policy 0, policy_version 131414 (0.0019) [2023-03-09 10:45:45,830][119383] Updated weights for policy 0, policy_version 131424 (0.0020) [2023-03-09 10:45:46,768][119383] Updated weights for policy 0, policy_version 131434 (0.0029) [2023-03-09 10:45:47,657][119383] Updated weights for policy 0, policy_version 131444 (0.0013) [2023-03-09 10:45:48,421][119383] Updated weights for policy 0, policy_version 131454 (0.0026) [2023-03-09 10:45:48,902][118949] Fps is (10 sec: 198252.6, 60 sec: 197427.2, 300 sec: 197108.1). Total num frames: 2153840640. Throughput: 0: 49355.4. Samples: 38420016. Policy #0 lag: (min: 1.0, avg: 17.3, max: 33.0) [2023-03-09 10:45:48,903][118949] Avg episode reward: [(0, '54.513')] [2023-03-09 10:45:49,351][119383] Updated weights for policy 0, policy_version 131464 (0.0025) [2023-03-09 10:45:49,920][119240] Signal inference workers to stop experience collection... (3850 times) [2023-03-09 10:45:49,937][119240] Signal inference workers to resume experience collection... (3850 times) [2023-03-09 10:45:49,968][119383] InferenceWorker_p0-w0: stopping experience collection (3850 times) [2023-03-09 10:45:50,006][119383] InferenceWorker_p0-w0: resuming experience collection (3850 times) [2023-03-09 10:45:50,207][119383] Updated weights for policy 0, policy_version 131474 (0.0028) [2023-03-09 10:45:50,896][119383] Updated weights for policy 0, policy_version 131484 (0.0016) [2023-03-09 10:45:51,838][119383] Updated weights for policy 0, policy_version 131494 (0.0021) [2023-03-09 10:45:52,641][119383] Updated weights for policy 0, policy_version 131504 (0.0021) [2023-03-09 10:45:53,346][119383] Updated weights for policy 0, policy_version 131514 (0.0018) [2023-03-09 10:45:53,903][118949] Fps is (10 sec: 199875.1, 60 sec: 197697.7, 300 sec: 196996.5). Total num frames: 2154823680. Throughput: 0: 49264.7. Samples: 38712768. Policy #0 lag: (min: 1.0, avg: 17.3, max: 33.0) [2023-03-09 10:45:53,904][118949] Avg episode reward: [(0, '54.599')] [2023-03-09 10:45:54,241][119383] Updated weights for policy 0, policy_version 131524 (0.0016) [2023-03-09 10:45:55,187][119383] Updated weights for policy 0, policy_version 131534 (0.0024) [2023-03-09 10:45:55,995][119383] Updated weights for policy 0, policy_version 131545 (0.0022) [2023-03-09 10:45:56,817][119383] Updated weights for policy 0, policy_version 131555 (0.0018) [2023-03-09 10:45:57,849][119383] Updated weights for policy 0, policy_version 131566 (0.0013) [2023-03-09 10:45:58,616][119383] Updated weights for policy 0, policy_version 131576 (0.0022) [2023-03-09 10:45:58,902][118949] Fps is (10 sec: 196604.5, 60 sec: 197699.7, 300 sec: 196941.1). Total num frames: 2155806720. Throughput: 0: 49219.1. Samples: 39007536. Policy #0 lag: (min: 1.0, avg: 17.3, max: 33.0) [2023-03-09 10:45:58,904][118949] Avg episode reward: [(0, '55.109')] [2023-03-09 10:45:59,358][119383] Updated weights for policy 0, policy_version 131586 (0.0020) [2023-03-09 10:46:00,148][119240] Signal inference workers to stop experience collection... (3900 times) [2023-03-09 10:46:00,153][119240] Signal inference workers to resume experience collection... (3900 times) [2023-03-09 10:46:00,200][119383] InferenceWorker_p0-w0: stopping experience collection (3900 times) [2023-03-09 10:46:00,203][119383] InferenceWorker_p0-w0: resuming experience collection (3900 times) [2023-03-09 10:46:00,363][119383] Updated weights for policy 0, policy_version 131596 (0.0021) [2023-03-09 10:46:01,148][119383] Updated weights for policy 0, policy_version 131606 (0.0023) [2023-03-09 10:46:01,881][119383] Updated weights for policy 0, policy_version 131616 (0.0018) [2023-03-09 10:46:02,821][119383] Updated weights for policy 0, policy_version 131626 (0.0021) [2023-03-09 10:46:03,701][119383] Updated weights for policy 0, policy_version 131636 (0.0019) [2023-03-09 10:46:03,902][118949] Fps is (10 sec: 194983.2, 60 sec: 197154.8, 300 sec: 196941.2). Total num frames: 2156773376. Throughput: 0: 49175.0. Samples: 39152944. Policy #0 lag: (min: 1.0, avg: 17.3, max: 33.0) [2023-03-09 10:46:03,903][118949] Avg episode reward: [(0, '54.194')] [2023-03-09 10:46:04,449][119383] Updated weights for policy 0, policy_version 131646 (0.0030) [2023-03-09 10:46:05,358][119383] Updated weights for policy 0, policy_version 131656 (0.0018) [2023-03-09 10:46:06,202][119383] Updated weights for policy 0, policy_version 131666 (0.0034) [2023-03-09 10:46:06,874][119383] Updated weights for policy 0, policy_version 131676 (0.0024) [2023-03-09 10:46:07,813][119383] Updated weights for policy 0, policy_version 131686 (0.0013) [2023-03-09 10:46:08,624][119383] Updated weights for policy 0, policy_version 131696 (0.0013) [2023-03-09 10:46:08,902][118949] Fps is (10 sec: 194969.9, 60 sec: 196610.0, 300 sec: 196941.2). Total num frames: 2157756416. Throughput: 0: 49219.8. Samples: 39451792. Policy #0 lag: (min: 1.0, avg: 17.3, max: 33.0) [2023-03-09 10:46:08,904][118949] Avg episode reward: [(0, '53.636')] [2023-03-09 10:46:09,347][119383] Updated weights for policy 0, policy_version 131706 (0.0013) [2023-03-09 10:46:10,237][119383] Updated weights for policy 0, policy_version 131716 (0.0016) [2023-03-09 10:46:11,136][119383] Updated weights for policy 0, policy_version 131726 (0.0021) [2023-03-09 10:46:11,173][119240] Signal inference workers to stop experience collection... (3950 times) [2023-03-09 10:46:11,191][119240] Signal inference workers to resume experience collection... (3950 times) [2023-03-09 10:46:11,217][119383] InferenceWorker_p0-w0: stopping experience collection (3950 times) [2023-03-09 10:46:11,259][119383] InferenceWorker_p0-w0: resuming experience collection (3950 times) [2023-03-09 10:46:11,921][119383] Updated weights for policy 0, policy_version 131736 (0.0027) [2023-03-09 10:46:12,666][119383] Updated weights for policy 0, policy_version 131746 (0.0017) [2023-03-09 10:46:13,789][119383] Updated weights for policy 0, policy_version 131757 (0.0025) [2023-03-09 10:46:13,902][118949] Fps is (10 sec: 196609.8, 60 sec: 196609.3, 300 sec: 196996.9). Total num frames: 2158739456. Throughput: 0: 49175.5. Samples: 39746576. Policy #0 lag: (min: 1.0, avg: 17.3, max: 33.0) [2023-03-09 10:46:13,903][118949] Avg episode reward: [(0, '54.753')] [2023-03-09 10:46:14,485][119383] Updated weights for policy 0, policy_version 131767 (0.0020) [2023-03-09 10:46:15,253][119383] Updated weights for policy 0, policy_version 131777 (0.0022) [2023-03-09 10:46:16,142][119383] Updated weights for policy 0, policy_version 131787 (0.0019) [2023-03-09 10:46:17,004][119383] Updated weights for policy 0, policy_version 131797 (0.0013) [2023-03-09 10:46:17,741][119383] Updated weights for policy 0, policy_version 131807 (0.0015) [2023-03-09 10:46:18,695][119383] Updated weights for policy 0, policy_version 131817 (0.0021) [2023-03-09 10:46:18,902][118949] Fps is (10 sec: 196605.9, 60 sec: 196608.2, 300 sec: 197052.6). Total num frames: 2159722496. Throughput: 0: 49176.9. Samples: 39893984. Policy #0 lag: (min: 1.0, avg: 17.3, max: 33.0) [2023-03-09 10:46:18,905][118949] Avg episode reward: [(0, '56.662')] [2023-03-09 10:46:19,521][119383] Updated weights for policy 0, policy_version 131827 (0.0021) [2023-03-09 10:46:20,239][119383] Updated weights for policy 0, policy_version 131837 (0.0013) [2023-03-09 10:46:21,242][119383] Updated weights for policy 0, policy_version 131847 (0.0016) [2023-03-09 10:46:21,932][119383] Updated weights for policy 0, policy_version 131857 (0.0023) [2023-03-09 10:46:22,135][119240] Signal inference workers to stop experience collection... (4000 times) [2023-03-09 10:46:22,148][119240] Signal inference workers to resume experience collection... (4000 times) [2023-03-09 10:46:22,213][119383] InferenceWorker_p0-w0: stopping experience collection (4000 times) [2023-03-09 10:46:22,213][119383] InferenceWorker_p0-w0: resuming experience collection (4000 times) [2023-03-09 10:46:22,741][119383] Updated weights for policy 0, policy_version 131867 (0.0018) [2023-03-09 10:46:23,613][119383] Updated weights for policy 0, policy_version 131877 (0.0030) [2023-03-09 10:46:23,902][118949] Fps is (10 sec: 196599.4, 60 sec: 196607.8, 300 sec: 196996.6). Total num frames: 2160705536. Throughput: 0: 49177.8. Samples: 40190832. Policy #0 lag: (min: 1.0, avg: 17.3, max: 33.0) [2023-03-09 10:46:23,904][118949] Avg episode reward: [(0, '55.188')] [2023-03-09 10:46:24,505][119383] Updated weights for policy 0, policy_version 131887 (0.0018) [2023-03-09 10:46:25,241][119383] Updated weights for policy 0, policy_version 131897 (0.0019) [2023-03-09 10:46:26,105][119383] Updated weights for policy 0, policy_version 131907 (0.0024) [2023-03-09 10:46:27,051][119383] Updated weights for policy 0, policy_version 131917 (0.0017) [2023-03-09 10:46:27,796][119383] Updated weights for policy 0, policy_version 131927 (0.0016) [2023-03-09 10:46:28,573][119383] Updated weights for policy 0, policy_version 131937 (0.0013) [2023-03-09 10:46:28,902][118949] Fps is (10 sec: 198247.7, 60 sec: 196880.4, 300 sec: 197052.2). Total num frames: 2161704960. Throughput: 0: 49178.4. Samples: 40485680. Policy #0 lag: (min: 1.0, avg: 17.3, max: 33.0) [2023-03-09 10:46:28,903][118949] Avg episode reward: [(0, '55.143')] [2023-03-09 10:46:29,606][119383] Updated weights for policy 0, policy_version 131948 (0.0014) [2023-03-09 10:46:30,397][119383] Updated weights for policy 0, policy_version 131958 (0.0024) [2023-03-09 10:46:31,228][119383] Updated weights for policy 0, policy_version 131969 (0.0013) [2023-03-09 10:46:32,126][119383] Updated weights for policy 0, policy_version 131979 (0.0013) [2023-03-09 10:46:32,739][119240] Signal inference workers to stop experience collection... (4050 times) [2023-03-09 10:46:32,788][119240] Signal inference workers to resume experience collection... (4050 times) [2023-03-09 10:46:32,841][119383] InferenceWorker_p0-w0: stopping experience collection (4050 times) [2023-03-09 10:46:32,842][119383] InferenceWorker_p0-w0: resuming experience collection (4050 times) [2023-03-09 10:46:32,974][119383] Updated weights for policy 0, policy_version 131989 (0.0012) [2023-03-09 10:46:33,732][119383] Updated weights for policy 0, policy_version 131999 (0.0016) [2023-03-09 10:46:33,902][118949] Fps is (10 sec: 201526.8, 60 sec: 197427.2, 300 sec: 197107.9). Total num frames: 2162720768. Throughput: 0: 49223.2. Samples: 40635072. Policy #0 lag: (min: 1.0, avg: 17.3, max: 33.0) [2023-03-09 10:46:33,904][118949] Avg episode reward: [(0, '55.998')] [2023-03-09 10:46:34,599][119383] Updated weights for policy 0, policy_version 132009 (0.0016) [2023-03-09 10:46:35,456][119383] Updated weights for policy 0, policy_version 132019 (0.0013) [2023-03-09 10:46:36,311][119383] Updated weights for policy 0, policy_version 132030 (0.0014) [2023-03-09 10:46:37,197][119383] Updated weights for policy 0, policy_version 132040 (0.0018) [2023-03-09 10:46:38,080][119383] Updated weights for policy 0, policy_version 132050 (0.0015) [2023-03-09 10:46:38,902][118949] Fps is (10 sec: 198249.4, 60 sec: 197155.0, 300 sec: 196997.0). Total num frames: 2163687424. Throughput: 0: 49270.2. Samples: 40929888. Policy #0 lag: (min: 1.0, avg: 17.3, max: 33.0) [2023-03-09 10:46:38,903][118949] Avg episode reward: [(0, '55.660')] [2023-03-09 10:46:38,924][119383] Updated weights for policy 0, policy_version 132061 (0.0016) [2023-03-09 10:46:39,846][119383] Updated weights for policy 0, policy_version 132071 (0.0031) [2023-03-09 10:46:40,566][119383] Updated weights for policy 0, policy_version 132081 (0.0016) [2023-03-09 10:46:41,352][119383] Updated weights for policy 0, policy_version 132091 (0.0013) [2023-03-09 10:46:42,186][119383] Updated weights for policy 0, policy_version 132101 (0.0019) [2023-03-09 10:46:42,442][119240] Signal inference workers to stop experience collection... (4100 times) [2023-03-09 10:46:42,443][119240] Signal inference workers to resume experience collection... (4100 times) [2023-03-09 10:46:42,508][119383] InferenceWorker_p0-w0: stopping experience collection (4100 times) [2023-03-09 10:46:42,509][119383] InferenceWorker_p0-w0: resuming experience collection (4100 times) [2023-03-09 10:46:43,094][119383] Updated weights for policy 0, policy_version 132111 (0.0018) [2023-03-09 10:46:43,902][118949] Fps is (10 sec: 194974.7, 60 sec: 197428.2, 300 sec: 196996.9). Total num frames: 2164670464. Throughput: 0: 49315.4. Samples: 41226720. Policy #0 lag: (min: 1.0, avg: 17.3, max: 33.0) [2023-03-09 10:46:43,903][118949] Avg episode reward: [(0, '55.783')] [2023-03-09 10:46:43,916][119383] Updated weights for policy 0, policy_version 132122 (0.0016) [2023-03-09 10:46:44,785][119383] Updated weights for policy 0, policy_version 132132 (0.0016) [2023-03-09 10:46:45,755][119383] Updated weights for policy 0, policy_version 132142 (0.0023) [2023-03-09 10:46:46,453][119383] Updated weights for policy 0, policy_version 132152 (0.0028) [2023-03-09 10:46:47,226][119383] Updated weights for policy 0, policy_version 132162 (0.0020) [2023-03-09 10:46:48,220][119383] Updated weights for policy 0, policy_version 132172 (0.0013) [2023-03-09 10:46:48,902][118949] Fps is (10 sec: 196608.6, 60 sec: 196881.0, 300 sec: 196996.9). Total num frames: 2165653504. Throughput: 0: 49312.4. Samples: 41372000. Policy #0 lag: (min: 0.0, avg: 15.8, max: 32.0) [2023-03-09 10:46:48,903][118949] Avg episode reward: [(0, '54.189')] [2023-03-09 10:46:48,964][119383] Updated weights for policy 0, policy_version 132182 (0.0018) [2023-03-09 10:46:49,771][119383] Updated weights for policy 0, policy_version 132192 (0.0025) [2023-03-09 10:46:50,671][119383] Updated weights for policy 0, policy_version 132202 (0.0016) [2023-03-09 10:46:51,595][119383] Updated weights for policy 0, policy_version 132213 (0.0026) [2023-03-09 10:46:52,377][119383] Updated weights for policy 0, policy_version 132223 (0.0013) [2023-03-09 10:46:53,304][119383] Updated weights for policy 0, policy_version 132233 (0.0025) [2023-03-09 10:46:53,902][118949] Fps is (10 sec: 194962.4, 60 sec: 196609.4, 300 sec: 196941.3). Total num frames: 2166620160. Throughput: 0: 49222.5. Samples: 41666816. Policy #0 lag: (min: 0.0, avg: 15.8, max: 32.0) [2023-03-09 10:46:53,905][118949] Avg episode reward: [(0, '55.854')] [2023-03-09 10:46:54,063][119240] Signal inference workers to stop experience collection... (4150 times) [2023-03-09 10:46:54,065][119240] Signal inference workers to resume experience collection... (4150 times) [2023-03-09 10:46:54,144][119383] InferenceWorker_p0-w0: stopping experience collection (4150 times) [2023-03-09 10:46:54,144][119383] InferenceWorker_p0-w0: resuming experience collection (4150 times) [2023-03-09 10:46:54,147][119383] Updated weights for policy 0, policy_version 132243 (0.0020) [2023-03-09 10:46:54,944][119383] Updated weights for policy 0, policy_version 132253 (0.0020) [2023-03-09 10:46:55,835][119383] Updated weights for policy 0, policy_version 132263 (0.0015) [2023-03-09 10:46:56,616][119383] Updated weights for policy 0, policy_version 132273 (0.0014) [2023-03-09 10:46:57,395][119383] Updated weights for policy 0, policy_version 132283 (0.0022) [2023-03-09 10:46:58,321][119383] Updated weights for policy 0, policy_version 132293 (0.0024) [2023-03-09 10:46:58,902][118949] Fps is (10 sec: 194963.3, 60 sec: 196607.4, 300 sec: 196996.8). Total num frames: 2167603200. Throughput: 0: 49220.6. Samples: 41961520. Policy #0 lag: (min: 0.0, avg: 15.8, max: 32.0) [2023-03-09 10:46:58,904][118949] Avg episode reward: [(0, '53.932')] [2023-03-09 10:46:59,185][119383] Updated weights for policy 0, policy_version 132303 (0.0016) [2023-03-09 10:46:59,951][119383] Updated weights for policy 0, policy_version 132314 (0.0013) [2023-03-09 10:47:00,820][119383] Updated weights for policy 0, policy_version 132324 (0.0018) [2023-03-09 10:47:01,777][119383] Updated weights for policy 0, policy_version 132334 (0.0024) [2023-03-09 10:47:02,519][119383] Updated weights for policy 0, policy_version 132345 (0.0013) [2023-03-09 10:47:03,390][119383] Updated weights for policy 0, policy_version 132355 (0.0013) [2023-03-09 10:47:03,902][118949] Fps is (10 sec: 196613.9, 60 sec: 196881.2, 300 sec: 197052.3). Total num frames: 2168586240. Throughput: 0: 49175.3. Samples: 42106864. Policy #0 lag: (min: 0.0, avg: 15.8, max: 32.0) [2023-03-09 10:47:03,903][118949] Avg episode reward: [(0, '54.396')] [2023-03-09 10:47:04,442][119383] Updated weights for policy 0, policy_version 132366 (0.0030) [2023-03-09 10:47:05,151][119383] Updated weights for policy 0, policy_version 132376 (0.0023) [2023-03-09 10:47:05,901][119383] Updated weights for policy 0, policy_version 132386 (0.0023) [2023-03-09 10:47:06,578][119240] Signal inference workers to stop experience collection... (4200 times) [2023-03-09 10:47:06,579][119240] Signal inference workers to resume experience collection... (4200 times) [2023-03-09 10:47:06,644][119383] InferenceWorker_p0-w0: stopping experience collection (4200 times) [2023-03-09 10:47:06,645][119383] InferenceWorker_p0-w0: resuming experience collection (4200 times) [2023-03-09 10:47:06,892][119383] Updated weights for policy 0, policy_version 132396 (0.0021) [2023-03-09 10:47:07,677][119383] Updated weights for policy 0, policy_version 132406 (0.0023) [2023-03-09 10:47:08,469][119383] Updated weights for policy 0, policy_version 132416 (0.0015) [2023-03-09 10:47:08,902][118949] Fps is (10 sec: 196614.8, 60 sec: 196881.6, 300 sec: 197052.6). Total num frames: 2169569280. Throughput: 0: 49130.8. Samples: 42401696. Policy #0 lag: (min: 0.0, avg: 15.8, max: 32.0) [2023-03-09 10:47:08,903][118949] Avg episode reward: [(0, '54.141')] [2023-03-09 10:47:09,381][119383] Updated weights for policy 0, policy_version 132426 (0.0016) [2023-03-09 10:47:10,258][119383] Updated weights for policy 0, policy_version 132436 (0.0019) [2023-03-09 10:47:11,052][119383] Updated weights for policy 0, policy_version 132446 (0.0019) [2023-03-09 10:47:11,978][119383] Updated weights for policy 0, policy_version 132456 (0.0013) [2023-03-09 10:47:12,758][119383] Updated weights for policy 0, policy_version 132466 (0.0016) [2023-03-09 10:47:13,618][119383] Updated weights for policy 0, policy_version 132477 (0.0017) [2023-03-09 10:47:13,902][118949] Fps is (10 sec: 198246.1, 60 sec: 197153.9, 300 sec: 197052.4). Total num frames: 2170568704. Throughput: 0: 49129.7. Samples: 42696512. Policy #0 lag: (min: 0.0, avg: 15.8, max: 32.0) [2023-03-09 10:47:13,903][118949] Avg episode reward: [(0, '54.223')] [2023-03-09 10:47:14,532][119383] Updated weights for policy 0, policy_version 132487 (0.0028) [2023-03-09 10:47:15,308][119383] Updated weights for policy 0, policy_version 132497 (0.0023) [2023-03-09 10:47:16,122][119383] Updated weights for policy 0, policy_version 132507 (0.0016) [2023-03-09 10:47:16,972][119383] Updated weights for policy 0, policy_version 132517 (0.0017) [2023-03-09 10:47:17,892][119383] Updated weights for policy 0, policy_version 132527 (0.0025) [2023-03-09 10:47:18,171][119240] Signal inference workers to stop experience collection... (4250 times) [2023-03-09 10:47:18,191][119240] Signal inference workers to resume experience collection... (4250 times) [2023-03-09 10:47:18,218][119383] InferenceWorker_p0-w0: stopping experience collection (4250 times) [2023-03-09 10:47:18,257][119383] InferenceWorker_p0-w0: resuming experience collection (4250 times) [2023-03-09 10:47:18,557][119383] Updated weights for policy 0, policy_version 132537 (0.0019) [2023-03-09 10:47:18,902][118949] Fps is (10 sec: 196606.9, 60 sec: 196881.8, 300 sec: 196941.2). Total num frames: 2171535360. Throughput: 0: 49084.3. Samples: 42843856. Policy #0 lag: (min: 0.0, avg: 15.8, max: 32.0) [2023-03-09 10:47:18,903][118949] Avg episode reward: [(0, '53.921')] [2023-03-09 10:47:19,441][119383] Updated weights for policy 0, policy_version 132547 (0.0015) [2023-03-09 10:47:20,414][119383] Updated weights for policy 0, policy_version 132557 (0.0018) [2023-03-09 10:47:21,226][119383] Updated weights for policy 0, policy_version 132568 (0.0016) [2023-03-09 10:47:21,952][119383] Updated weights for policy 0, policy_version 132578 (0.0013) [2023-03-09 10:47:23,066][119383] Updated weights for policy 0, policy_version 132589 (0.0013) [2023-03-09 10:47:23,742][119383] Updated weights for policy 0, policy_version 132599 (0.0013) [2023-03-09 10:47:23,903][118949] Fps is (10 sec: 194957.3, 60 sec: 196880.2, 300 sec: 196996.4). Total num frames: 2172518400. Throughput: 0: 49126.4. Samples: 43140608. Policy #0 lag: (min: 0.0, avg: 15.8, max: 32.0) [2023-03-09 10:47:23,905][118949] Avg episode reward: [(0, '55.074')] [2023-03-09 10:47:23,946][119240] Saving /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000132602_2172551168.pth... [2023-03-09 10:47:24,014][119240] Removing /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000129717_2125283328.pth [2023-03-09 10:47:24,533][119383] Updated weights for policy 0, policy_version 132609 (0.0013) [2023-03-09 10:47:25,501][119383] Updated weights for policy 0, policy_version 132619 (0.0016) [2023-03-09 10:47:26,366][119383] Updated weights for policy 0, policy_version 132630 (0.0016) [2023-03-09 10:47:27,144][119383] Updated weights for policy 0, policy_version 132640 (0.0013) [2023-03-09 10:47:28,064][119383] Updated weights for policy 0, policy_version 132650 (0.0017) [2023-03-09 10:47:28,902][118949] Fps is (10 sec: 194967.6, 60 sec: 196335.1, 300 sec: 196885.8). Total num frames: 2173485056. Throughput: 0: 49035.9. Samples: 43433344. Policy #0 lag: (min: 0.0, avg: 15.8, max: 32.0) [2023-03-09 10:47:28,903][118949] Avg episode reward: [(0, '55.794')] [2023-03-09 10:47:28,929][119383] Updated weights for policy 0, policy_version 132660 (0.0024) [2023-03-09 10:47:29,706][119383] Updated weights for policy 0, policy_version 132670 (0.0021) [2023-03-09 10:47:30,634][119383] Updated weights for policy 0, policy_version 132680 (0.0017) [2023-03-09 10:47:30,684][119240] Signal inference workers to stop experience collection... (4300 times) [2023-03-09 10:47:30,685][119240] Signal inference workers to resume experience collection... (4300 times) [2023-03-09 10:47:30,758][119383] InferenceWorker_p0-w0: stopping experience collection (4300 times) [2023-03-09 10:47:30,758][119383] InferenceWorker_p0-w0: resuming experience collection (4300 times) [2023-03-09 10:47:31,408][119383] Updated weights for policy 0, policy_version 132690 (0.0023) [2023-03-09 10:47:32,176][119383] Updated weights for policy 0, policy_version 132700 (0.0021) [2023-03-09 10:47:33,052][119383] Updated weights for policy 0, policy_version 132710 (0.0015) [2023-03-09 10:47:33,892][119383] Updated weights for policy 0, policy_version 132720 (0.0017) [2023-03-09 10:47:33,902][118949] Fps is (10 sec: 198257.3, 60 sec: 196335.2, 300 sec: 197052.2). Total num frames: 2174500864. Throughput: 0: 49127.7. Samples: 43582752. Policy #0 lag: (min: 0.0, avg: 15.8, max: 32.0) [2023-03-09 10:47:33,903][118949] Avg episode reward: [(0, '54.575')] [2023-03-09 10:47:34,566][119383] Updated weights for policy 0, policy_version 132730 (0.0013) [2023-03-09 10:47:35,465][119383] Updated weights for policy 0, policy_version 132740 (0.0019) [2023-03-09 10:47:36,387][119383] Updated weights for policy 0, policy_version 132750 (0.0017) [2023-03-09 10:47:37,141][119383] Updated weights for policy 0, policy_version 132760 (0.0026) [2023-03-09 10:47:37,942][119383] Updated weights for policy 0, policy_version 132770 (0.0014) [2023-03-09 10:47:38,866][119383] Updated weights for policy 0, policy_version 132780 (0.0018) [2023-03-09 10:47:38,902][118949] Fps is (10 sec: 198244.6, 60 sec: 196334.3, 300 sec: 196941.3). Total num frames: 2175467520. Throughput: 0: 49218.3. Samples: 43881632. Policy #0 lag: (min: 0.0, avg: 15.8, max: 32.0) [2023-03-09 10:47:38,904][118949] Avg episode reward: [(0, '55.526')] [2023-03-09 10:47:39,652][119383] Updated weights for policy 0, policy_version 132790 (0.0023) [2023-03-09 10:47:40,354][119383] Updated weights for policy 0, policy_version 132800 (0.0022) [2023-03-09 10:47:41,321][119383] Updated weights for policy 0, policy_version 132810 (0.0013) [2023-03-09 10:47:42,118][119240] Signal inference workers to stop experience collection... (4350 times) [2023-03-09 10:47:42,120][119240] Signal inference workers to resume experience collection... (4350 times) [2023-03-09 10:47:42,131][119383] InferenceWorker_p0-w0: stopping experience collection (4350 times) [2023-03-09 10:47:42,166][119383] Updated weights for policy 0, policy_version 132821 (0.0012) [2023-03-09 10:47:42,307][119383] InferenceWorker_p0-w0: resuming experience collection (4350 times) [2023-03-09 10:47:43,257][119383] Updated weights for policy 0, policy_version 132832 (0.0018) [2023-03-09 10:47:43,902][118949] Fps is (10 sec: 191695.7, 60 sec: 195788.7, 300 sec: 196885.7). Total num frames: 2176417792. Throughput: 0: 49037.5. Samples: 44168192. Policy #0 lag: (min: 0.0, avg: 15.8, max: 32.0) [2023-03-09 10:47:43,903][118949] Avg episode reward: [(0, '56.605')] [2023-03-09 10:47:44,162][119383] Updated weights for policy 0, policy_version 132842 (0.0013) [2023-03-09 10:47:45,050][119383] Updated weights for policy 0, policy_version 132852 (0.0027) [2023-03-09 10:47:45,804][119383] Updated weights for policy 0, policy_version 132862 (0.0031) [2023-03-09 10:47:46,763][119383] Updated weights for policy 0, policy_version 132872 (0.0019) [2023-03-09 10:47:47,590][119383] Updated weights for policy 0, policy_version 132882 (0.0013) [2023-03-09 10:47:48,389][119383] Updated weights for policy 0, policy_version 132893 (0.0017) [2023-03-09 10:47:48,902][118949] Fps is (10 sec: 194974.6, 60 sec: 196061.9, 300 sec: 196941.5). Total num frames: 2177417216. Throughput: 0: 49036.9. Samples: 44313520. Policy #0 lag: (min: 1.0, avg: 16.7, max: 33.0) [2023-03-09 10:47:48,903][118949] Avg episode reward: [(0, '56.054')] [2023-03-09 10:47:49,267][119383] Updated weights for policy 0, policy_version 132903 (0.0025) [2023-03-09 10:47:50,088][119383] Updated weights for policy 0, policy_version 132913 (0.0017) [2023-03-09 10:47:50,872][119383] Updated weights for policy 0, policy_version 132923 (0.0017) [2023-03-09 10:47:51,749][119383] Updated weights for policy 0, policy_version 132933 (0.0024) [2023-03-09 10:47:52,576][119383] Updated weights for policy 0, policy_version 132943 (0.0016) [2023-03-09 10:47:53,331][119383] Updated weights for policy 0, policy_version 132953 (0.0016) [2023-03-09 10:47:53,904][118949] Fps is (10 sec: 199851.4, 60 sec: 196603.7, 300 sec: 196995.7). Total num frames: 2178416640. Throughput: 0: 49077.6. Samples: 44610272. Policy #0 lag: (min: 1.0, avg: 16.7, max: 33.0) [2023-03-09 10:47:53,905][118949] Avg episode reward: [(0, '53.648')] [2023-03-09 10:47:54,220][119383] Updated weights for policy 0, policy_version 132963 (0.0013) [2023-03-09 10:47:54,720][119240] Signal inference workers to stop experience collection... (4400 times) [2023-03-09 10:47:54,725][119240] Signal inference workers to resume experience collection... (4400 times) [2023-03-09 10:47:54,792][119383] InferenceWorker_p0-w0: stopping experience collection (4400 times) [2023-03-09 10:47:54,792][119383] InferenceWorker_p0-w0: resuming experience collection (4400 times) [2023-03-09 10:47:55,193][119383] Updated weights for policy 0, policy_version 132974 (0.0013) [2023-03-09 10:47:55,971][119383] Updated weights for policy 0, policy_version 132984 (0.0013) [2023-03-09 10:47:56,774][119383] Updated weights for policy 0, policy_version 132994 (0.0016) [2023-03-09 10:47:57,664][119383] Updated weights for policy 0, policy_version 133004 (0.0017) [2023-03-09 10:47:58,515][119383] Updated weights for policy 0, policy_version 133014 (0.0016) [2023-03-09 10:47:58,902][118949] Fps is (10 sec: 196604.1, 60 sec: 196335.4, 300 sec: 196830.0). Total num frames: 2179383296. Throughput: 0: 49077.2. Samples: 44904992. Policy #0 lag: (min: 1.0, avg: 16.7, max: 33.0) [2023-03-09 10:47:58,903][118949] Avg episode reward: [(0, '56.976')] [2023-03-09 10:47:59,313][119383] Updated weights for policy 0, policy_version 133025 (0.0013) [2023-03-09 10:48:00,211][119383] Updated weights for policy 0, policy_version 133035 (0.0020) [2023-03-09 10:48:01,067][119383] Updated weights for policy 0, policy_version 133045 (0.0024) [2023-03-09 10:48:01,802][119383] Updated weights for policy 0, policy_version 133055 (0.0019) [2023-03-09 10:48:02,739][119383] Updated weights for policy 0, policy_version 133065 (0.0016) [2023-03-09 10:48:03,595][119383] Updated weights for policy 0, policy_version 133076 (0.0013) [2023-03-09 10:48:03,902][118949] Fps is (10 sec: 196640.9, 60 sec: 196608.2, 300 sec: 196830.3). Total num frames: 2180382720. Throughput: 0: 49032.6. Samples: 45050320. Policy #0 lag: (min: 1.0, avg: 16.7, max: 33.0) [2023-03-09 10:48:03,903][118949] Avg episode reward: [(0, '55.175')] [2023-03-09 10:48:04,409][119383] Updated weights for policy 0, policy_version 133086 (0.0014) [2023-03-09 10:48:05,346][119240] Signal inference workers to stop experience collection... (4450 times) [2023-03-09 10:48:05,362][119240] Signal inference workers to resume experience collection... (4450 times) [2023-03-09 10:48:05,383][119383] Updated weights for policy 0, policy_version 133097 (0.0017) [2023-03-09 10:48:05,419][119383] InferenceWorker_p0-w0: stopping experience collection (4450 times) [2023-03-09 10:48:05,420][119383] InferenceWorker_p0-w0: resuming experience collection (4450 times) [2023-03-09 10:48:06,248][119383] Updated weights for policy 0, policy_version 133107 (0.0014) [2023-03-09 10:48:07,015][119383] Updated weights for policy 0, policy_version 133117 (0.0014) [2023-03-09 10:48:07,928][119383] Updated weights for policy 0, policy_version 133127 (0.0013) [2023-03-09 10:48:08,716][119383] Updated weights for policy 0, policy_version 133137 (0.0018) [2023-03-09 10:48:08,902][118949] Fps is (10 sec: 194973.4, 60 sec: 196061.9, 300 sec: 196719.4). Total num frames: 2181332992. Throughput: 0: 49080.3. Samples: 45349184. Policy #0 lag: (min: 1.0, avg: 16.7, max: 33.0) [2023-03-09 10:48:08,903][118949] Avg episode reward: [(0, '56.016')] [2023-03-09 10:48:09,488][119383] Updated weights for policy 0, policy_version 133147 (0.0017) [2023-03-09 10:48:10,364][119383] Updated weights for policy 0, policy_version 133157 (0.0017) [2023-03-09 10:48:11,177][119383] Updated weights for policy 0, policy_version 133167 (0.0029) [2023-03-09 10:48:12,033][119383] Updated weights for policy 0, policy_version 133178 (0.0021) [2023-03-09 10:48:12,890][119383] Updated weights for policy 0, policy_version 133188 (0.0016) [2023-03-09 10:48:13,808][119383] Updated weights for policy 0, policy_version 133198 (0.0016) [2023-03-09 10:48:13,902][118949] Fps is (10 sec: 194964.2, 60 sec: 196061.2, 300 sec: 196830.0). Total num frames: 2182332416. Throughput: 0: 49125.2. Samples: 45643984. Policy #0 lag: (min: 1.0, avg: 16.7, max: 33.0) [2023-03-09 10:48:13,904][118949] Avg episode reward: [(0, '54.217')] [2023-03-09 10:48:14,563][119383] Updated weights for policy 0, policy_version 133208 (0.0020) [2023-03-09 10:48:15,400][119383] Updated weights for policy 0, policy_version 133218 (0.0026) [2023-03-09 10:48:16,378][119383] Updated weights for policy 0, policy_version 133228 (0.0023) [2023-03-09 10:48:16,839][119240] Signal inference workers to stop experience collection... (4500 times) [2023-03-09 10:48:16,842][119240] Signal inference workers to resume experience collection... (4500 times) [2023-03-09 10:48:16,910][119383] InferenceWorker_p0-w0: stopping experience collection (4500 times) [2023-03-09 10:48:16,910][119383] InferenceWorker_p0-w0: resuming experience collection (4500 times) [2023-03-09 10:48:17,086][119383] Updated weights for policy 0, policy_version 133238 (0.0014) [2023-03-09 10:48:17,967][119383] Updated weights for policy 0, policy_version 133249 (0.0019) [2023-03-09 10:48:18,889][119383] Updated weights for policy 0, policy_version 133259 (0.0020) [2023-03-09 10:48:18,902][118949] Fps is (10 sec: 198243.4, 60 sec: 196334.6, 300 sec: 196774.7). Total num frames: 2183315456. Throughput: 0: 49082.0. Samples: 45791440. Policy #0 lag: (min: 1.0, avg: 16.7, max: 33.0) [2023-03-09 10:48:18,904][118949] Avg episode reward: [(0, '55.071')] [2023-03-09 10:48:19,692][119383] Updated weights for policy 0, policy_version 133269 (0.0020) [2023-03-09 10:48:20,450][119383] Updated weights for policy 0, policy_version 133279 (0.0023) [2023-03-09 10:48:21,380][119383] Updated weights for policy 0, policy_version 133289 (0.0021) [2023-03-09 10:48:22,214][119383] Updated weights for policy 0, policy_version 133299 (0.0018) [2023-03-09 10:48:22,957][119383] Updated weights for policy 0, policy_version 133309 (0.0028) [2023-03-09 10:48:23,889][119383] Updated weights for policy 0, policy_version 133319 (0.0024) [2023-03-09 10:48:23,902][118949] Fps is (10 sec: 196606.7, 60 sec: 196336.1, 300 sec: 196774.5). Total num frames: 2184298496. Throughput: 0: 49034.9. Samples: 46088208. Policy #0 lag: (min: 1.0, avg: 16.7, max: 33.0) [2023-03-09 10:48:23,904][118949] Avg episode reward: [(0, '55.212')] [2023-03-09 10:48:24,666][119383] Updated weights for policy 0, policy_version 133329 (0.0016) [2023-03-09 10:48:25,430][119383] Updated weights for policy 0, policy_version 133339 (0.0025) [2023-03-09 10:48:26,288][119383] Updated weights for policy 0, policy_version 133349 (0.0015) [2023-03-09 10:48:27,130][119383] Updated weights for policy 0, policy_version 133359 (0.0027) [2023-03-09 10:48:27,877][119383] Updated weights for policy 0, policy_version 133369 (0.0013) [2023-03-09 10:48:28,902][118949] Fps is (10 sec: 198242.8, 60 sec: 196880.5, 300 sec: 196885.7). Total num frames: 2185297920. Throughput: 0: 49214.9. Samples: 46382880. Policy #0 lag: (min: 1.0, avg: 16.7, max: 33.0) [2023-03-09 10:48:28,905][118949] Avg episode reward: [(0, '54.752')] [2023-03-09 10:48:28,933][119383] Updated weights for policy 0, policy_version 133380 (0.0013) [2023-03-09 10:48:29,137][119240] Signal inference workers to stop experience collection... (4550 times) [2023-03-09 10:48:29,152][119240] Signal inference workers to resume experience collection... (4550 times) [2023-03-09 10:48:29,209][119383] InferenceWorker_p0-w0: stopping experience collection (4550 times) [2023-03-09 10:48:29,209][119383] InferenceWorker_p0-w0: resuming experience collection (4550 times) [2023-03-09 10:48:29,739][119383] Updated weights for policy 0, policy_version 133390 (0.0016) [2023-03-09 10:48:30,514][119383] Updated weights for policy 0, policy_version 133400 (0.0020) [2023-03-09 10:48:31,345][119383] Updated weights for policy 0, policy_version 133410 (0.0016) [2023-03-09 10:48:32,252][119383] Updated weights for policy 0, policy_version 133420 (0.0013) [2023-03-09 10:48:33,094][119383] Updated weights for policy 0, policy_version 133430 (0.0020) [2023-03-09 10:48:33,760][119383] Updated weights for policy 0, policy_version 133440 (0.0016) [2023-03-09 10:48:33,902][118949] Fps is (10 sec: 199889.9, 60 sec: 196608.2, 300 sec: 196941.4). Total num frames: 2186297344. Throughput: 0: 49307.2. Samples: 46532352. Policy #0 lag: (min: 1.0, avg: 16.7, max: 33.0) [2023-03-09 10:48:33,903][118949] Avg episode reward: [(0, '56.495')] [2023-03-09 10:48:34,767][119383] Updated weights for policy 0, policy_version 133450 (0.0019) [2023-03-09 10:48:35,594][119383] Updated weights for policy 0, policy_version 133460 (0.0013) [2023-03-09 10:48:36,372][119383] Updated weights for policy 0, policy_version 133470 (0.0016) [2023-03-09 10:48:37,307][119383] Updated weights for policy 0, policy_version 133480 (0.0013) [2023-03-09 10:48:38,087][119383] Updated weights for policy 0, policy_version 133490 (0.0021) [2023-03-09 10:48:38,849][119383] Updated weights for policy 0, policy_version 133500 (0.0013) [2023-03-09 10:48:38,902][118949] Fps is (10 sec: 196607.9, 60 sec: 196607.7, 300 sec: 196830.0). Total num frames: 2187264000. Throughput: 0: 49219.6. Samples: 46825088. Policy #0 lag: (min: 1.0, avg: 16.7, max: 33.0) [2023-03-09 10:48:38,904][118949] Avg episode reward: [(0, '53.753')] [2023-03-09 10:48:39,779][119383] Updated weights for policy 0, policy_version 133510 (0.0013) [2023-03-09 10:48:40,558][119383] Updated weights for policy 0, policy_version 133520 (0.0013) [2023-03-09 10:48:41,339][119383] Updated weights for policy 0, policy_version 133530 (0.0015) [2023-03-09 10:48:41,651][119240] Signal inference workers to stop experience collection... (4600 times) [2023-03-09 10:48:41,671][119240] Signal inference workers to resume experience collection... (4600 times) [2023-03-09 10:48:41,716][119383] InferenceWorker_p0-w0: stopping experience collection (4600 times) [2023-03-09 10:48:41,721][119383] InferenceWorker_p0-w0: resuming experience collection (4600 times) [2023-03-09 10:48:42,248][119383] Updated weights for policy 0, policy_version 133540 (0.0020) [2023-03-09 10:48:43,060][119383] Updated weights for policy 0, policy_version 133550 (0.0013) [2023-03-09 10:48:43,798][119383] Updated weights for policy 0, policy_version 133560 (0.0015) [2023-03-09 10:48:43,902][118949] Fps is (10 sec: 196609.7, 60 sec: 197427.2, 300 sec: 196830.2). Total num frames: 2188263424. Throughput: 0: 49219.0. Samples: 47119840. Policy #0 lag: (min: 1.0, avg: 16.7, max: 33.0) [2023-03-09 10:48:43,903][118949] Avg episode reward: [(0, '56.020')] [2023-03-09 10:48:44,755][119383] Updated weights for policy 0, policy_version 133571 (0.0025) [2023-03-09 10:48:45,665][119383] Updated weights for policy 0, policy_version 133581 (0.0016) [2023-03-09 10:48:46,439][119383] Updated weights for policy 0, policy_version 133591 (0.0017) [2023-03-09 10:48:47,214][119383] Updated weights for policy 0, policy_version 133601 (0.0024) [2023-03-09 10:48:48,112][119383] Updated weights for policy 0, policy_version 133611 (0.0015) [2023-03-09 10:48:48,902][118949] Fps is (10 sec: 196615.0, 60 sec: 196881.1, 300 sec: 196774.9). Total num frames: 2189230080. Throughput: 0: 49309.6. Samples: 47269248. Policy #0 lag: (min: 1.0, avg: 16.7, max: 33.0) [2023-03-09 10:48:48,903][118949] Avg episode reward: [(0, '54.787')] [2023-03-09 10:48:48,995][119383] Updated weights for policy 0, policy_version 133621 (0.0016) [2023-03-09 10:48:49,703][119383] Updated weights for policy 0, policy_version 133631 (0.0013) [2023-03-09 10:48:50,679][119383] Updated weights for policy 0, policy_version 133641 (0.0017) [2023-03-09 10:48:51,513][119383] Updated weights for policy 0, policy_version 133651 (0.0013) [2023-03-09 10:48:52,344][119383] Updated weights for policy 0, policy_version 133662 (0.0019) [2023-03-09 10:48:53,213][119240] Signal inference workers to stop experience collection... (4650 times) [2023-03-09 10:48:53,236][119240] Signal inference workers to resume experience collection... (4650 times) [2023-03-09 10:48:53,271][119383] InferenceWorker_p0-w0: stopping experience collection (4650 times) [2023-03-09 10:48:53,274][119383] Updated weights for policy 0, policy_version 133672 (0.0020) [2023-03-09 10:48:53,315][119383] InferenceWorker_p0-w0: resuming experience collection (4650 times) [2023-03-09 10:48:53,902][118949] Fps is (10 sec: 196600.8, 60 sec: 196885.3, 300 sec: 196829.9). Total num frames: 2190229504. Throughput: 0: 49264.6. Samples: 47566112. Policy #0 lag: (min: 2.0, avg: 18.4, max: 34.0) [2023-03-09 10:48:53,904][118949] Avg episode reward: [(0, '55.831')] [2023-03-09 10:48:54,131][119383] Updated weights for policy 0, policy_version 133683 (0.0017) [2023-03-09 10:48:54,916][119383] Updated weights for policy 0, policy_version 133693 (0.0018) [2023-03-09 10:48:55,896][119383] Updated weights for policy 0, policy_version 133703 (0.0018) [2023-03-09 10:48:56,598][119383] Updated weights for policy 0, policy_version 133713 (0.0021) [2023-03-09 10:48:57,401][119383] Updated weights for policy 0, policy_version 133723 (0.0017) [2023-03-09 10:48:58,270][119383] Updated weights for policy 0, policy_version 133733 (0.0017) [2023-03-09 10:48:58,902][118949] Fps is (10 sec: 196602.5, 60 sec: 196880.8, 300 sec: 196774.4). Total num frames: 2191196160. Throughput: 0: 49219.6. Samples: 47858864. Policy #0 lag: (min: 2.0, avg: 18.4, max: 34.0) [2023-03-09 10:48:58,904][118949] Avg episode reward: [(0, '54.905')] [2023-03-09 10:48:59,116][119383] Updated weights for policy 0, policy_version 133743 (0.0021) [2023-03-09 10:48:59,933][119383] Updated weights for policy 0, policy_version 133753 (0.0015) [2023-03-09 10:49:00,748][119383] Updated weights for policy 0, policy_version 133763 (0.0017) [2023-03-09 10:49:01,672][119383] Updated weights for policy 0, policy_version 133773 (0.0019) [2023-03-09 10:49:02,471][119383] Updated weights for policy 0, policy_version 133783 (0.0016) [2023-03-09 10:49:03,218][119383] Updated weights for policy 0, policy_version 133793 (0.0017) [2023-03-09 10:49:03,902][118949] Fps is (10 sec: 193332.8, 60 sec: 196334.0, 300 sec: 196774.4). Total num frames: 2192162816. Throughput: 0: 49215.8. Samples: 48006160. Policy #0 lag: (min: 2.0, avg: 18.4, max: 34.0) [2023-03-09 10:49:03,905][118949] Avg episode reward: [(0, '56.637')] [2023-03-09 10:49:03,911][119240] Signal inference workers to stop experience collection... (4700 times) [2023-03-09 10:49:03,934][119240] Signal inference workers to resume experience collection... (4700 times) [2023-03-09 10:49:03,980][119383] InferenceWorker_p0-w0: stopping experience collection (4700 times) [2023-03-09 10:49:04,005][119383] InferenceWorker_p0-w0: resuming experience collection (4700 times) [2023-03-09 10:49:04,327][119383] Updated weights for policy 0, policy_version 133803 (0.0018) [2023-03-09 10:49:05,209][119383] Updated weights for policy 0, policy_version 133813 (0.0019) [2023-03-09 10:49:06,038][119383] Updated weights for policy 0, policy_version 133824 (0.0020) [2023-03-09 10:49:06,994][119383] Updated weights for policy 0, policy_version 133834 (0.0013) [2023-03-09 10:49:07,858][119383] Updated weights for policy 0, policy_version 133844 (0.0018) [2023-03-09 10:49:08,552][119383] Updated weights for policy 0, policy_version 133854 (0.0022) [2023-03-09 10:49:08,902][118949] Fps is (10 sec: 191698.0, 60 sec: 196335.0, 300 sec: 196663.6). Total num frames: 2193113088. Throughput: 0: 48856.6. Samples: 48286736. Policy #0 lag: (min: 2.0, avg: 18.4, max: 34.0) [2023-03-09 10:49:08,903][118949] Avg episode reward: [(0, '57.564')] [2023-03-09 10:49:09,507][119383] Updated weights for policy 0, policy_version 133864 (0.0019) [2023-03-09 10:49:10,363][119383] Updated weights for policy 0, policy_version 133874 (0.0013) [2023-03-09 10:49:11,047][119383] Updated weights for policy 0, policy_version 133884 (0.0013) [2023-03-09 10:49:11,977][119383] Updated weights for policy 0, policy_version 133894 (0.0019) [2023-03-09 10:49:12,824][119383] Updated weights for policy 0, policy_version 133904 (0.0019) [2023-03-09 10:49:13,575][119383] Updated weights for policy 0, policy_version 133914 (0.0019) [2023-03-09 10:49:13,902][118949] Fps is (10 sec: 194975.8, 60 sec: 196335.9, 300 sec: 196774.7). Total num frames: 2194112512. Throughput: 0: 48946.9. Samples: 48585472. Policy #0 lag: (min: 2.0, avg: 18.4, max: 34.0) [2023-03-09 10:49:13,903][118949] Avg episode reward: [(0, '54.842')] [2023-03-09 10:49:14,509][119383] Updated weights for policy 0, policy_version 133924 (0.0022) [2023-03-09 10:49:14,824][119240] Signal inference workers to stop experience collection... (4750 times) [2023-03-09 10:49:14,843][119240] Signal inference workers to resume experience collection... (4750 times) [2023-03-09 10:49:14,880][119383] InferenceWorker_p0-w0: stopping experience collection (4750 times) [2023-03-09 10:49:14,883][119383] InferenceWorker_p0-w0: resuming experience collection (4750 times) [2023-03-09 10:49:15,341][119383] Updated weights for policy 0, policy_version 133934 (0.0021) [2023-03-09 10:49:16,065][119383] Updated weights for policy 0, policy_version 133944 (0.0016) [2023-03-09 10:49:16,944][119383] Updated weights for policy 0, policy_version 133954 (0.0014) [2023-03-09 10:49:17,818][119383] Updated weights for policy 0, policy_version 133964 (0.0016) [2023-03-09 10:49:18,678][119383] Updated weights for policy 0, policy_version 133974 (0.0032) [2023-03-09 10:49:18,902][118949] Fps is (10 sec: 196596.5, 60 sec: 196060.5, 300 sec: 196663.4). Total num frames: 2195079168. Throughput: 0: 48855.0. Samples: 48730848. Policy #0 lag: (min: 2.0, avg: 18.4, max: 34.0) [2023-03-09 10:49:18,904][118949] Avg episode reward: [(0, '56.745')] [2023-03-09 10:49:19,405][119383] Updated weights for policy 0, policy_version 133984 (0.0020) [2023-03-09 10:49:20,413][119383] Updated weights for policy 0, policy_version 133994 (0.0028) [2023-03-09 10:49:21,230][119383] Updated weights for policy 0, policy_version 134004 (0.0016) [2023-03-09 10:49:22,034][119383] Updated weights for policy 0, policy_version 134015 (0.0013) [2023-03-09 10:49:23,090][119383] Updated weights for policy 0, policy_version 134026 (0.0014) [2023-03-09 10:49:23,902][118949] Fps is (10 sec: 193330.9, 60 sec: 195790.0, 300 sec: 196552.4). Total num frames: 2196045824. Throughput: 0: 48810.0. Samples: 49021520. Policy #0 lag: (min: 2.0, avg: 18.4, max: 34.0) [2023-03-09 10:49:23,903][118949] Avg episode reward: [(0, '56.174')] [2023-03-09 10:49:23,906][119383] Updated weights for policy 0, policy_version 134036 (0.0025) [2023-03-09 10:49:23,914][119240] Saving /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000134036_2196045824.pth... [2023-03-09 10:49:23,977][119240] Removing /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000131161_2148941824.pth [2023-03-09 10:49:24,738][119383] Updated weights for policy 0, policy_version 134047 (0.0017) [2023-03-09 10:49:25,717][119383] Updated weights for policy 0, policy_version 134057 (0.0016) [2023-03-09 10:49:26,269][119240] Signal inference workers to stop experience collection... (4800 times) [2023-03-09 10:49:26,270][119240] Signal inference workers to resume experience collection... (4800 times) [2023-03-09 10:49:26,336][119383] InferenceWorker_p0-w0: stopping experience collection (4800 times) [2023-03-09 10:49:26,337][119383] InferenceWorker_p0-w0: resuming experience collection (4800 times) [2023-03-09 10:49:26,547][119383] Updated weights for policy 0, policy_version 134067 (0.0023) [2023-03-09 10:49:27,309][119383] Updated weights for policy 0, policy_version 134077 (0.0016) [2023-03-09 10:49:28,259][119383] Updated weights for policy 0, policy_version 134087 (0.0016) [2023-03-09 10:49:28,902][118949] Fps is (10 sec: 193341.2, 60 sec: 195243.5, 300 sec: 196496.9). Total num frames: 2197012480. Throughput: 0: 48719.2. Samples: 49312208. Policy #0 lag: (min: 2.0, avg: 18.4, max: 34.0) [2023-03-09 10:49:28,903][118949] Avg episode reward: [(0, '51.409')] [2023-03-09 10:49:29,042][119383] Updated weights for policy 0, policy_version 134097 (0.0016) [2023-03-09 10:49:29,846][119383] Updated weights for policy 0, policy_version 134107 (0.0023) [2023-03-09 10:49:30,713][119383] Updated weights for policy 0, policy_version 134117 (0.0017) [2023-03-09 10:49:31,562][119383] Updated weights for policy 0, policy_version 134127 (0.0021) [2023-03-09 10:49:32,329][119383] Updated weights for policy 0, policy_version 134137 (0.0013) [2023-03-09 10:49:33,163][119383] Updated weights for policy 0, policy_version 134147 (0.0015) [2023-03-09 10:49:33,902][118949] Fps is (10 sec: 194969.7, 60 sec: 194969.9, 300 sec: 196497.1). Total num frames: 2197995520. Throughput: 0: 48674.8. Samples: 49459616. Policy #0 lag: (min: 2.0, avg: 18.4, max: 34.0) [2023-03-09 10:49:33,903][118949] Avg episode reward: [(0, '55.915')] [2023-03-09 10:49:34,048][119383] Updated weights for policy 0, policy_version 134157 (0.0024) [2023-03-09 10:49:34,872][119383] Updated weights for policy 0, policy_version 134167 (0.0020) [2023-03-09 10:49:35,655][119383] Updated weights for policy 0, policy_version 134177 (0.0020) [2023-03-09 10:49:36,558][119383] Updated weights for policy 0, policy_version 134187 (0.0013) [2023-03-09 10:49:37,411][119383] Updated weights for policy 0, policy_version 134197 (0.0016) [2023-03-09 10:49:38,096][119240] Signal inference workers to stop experience collection... (4850 times) [2023-03-09 10:49:38,098][119240] Signal inference workers to resume experience collection... (4850 times) [2023-03-09 10:49:38,159][119383] InferenceWorker_p0-w0: stopping experience collection (4850 times) [2023-03-09 10:49:38,159][119383] InferenceWorker_p0-w0: resuming experience collection (4850 times) [2023-03-09 10:49:38,201][119383] Updated weights for policy 0, policy_version 134207 (0.0018) [2023-03-09 10:49:38,902][118949] Fps is (10 sec: 194965.7, 60 sec: 194969.8, 300 sec: 196441.2). Total num frames: 2198962176. Throughput: 0: 48629.5. Samples: 49754432. Policy #0 lag: (min: 2.0, avg: 18.4, max: 34.0) [2023-03-09 10:49:38,904][118949] Avg episode reward: [(0, '57.590')] [2023-03-09 10:49:39,139][119383] Updated weights for policy 0, policy_version 134217 (0.0022) [2023-03-09 10:49:39,971][119383] Updated weights for policy 0, policy_version 134227 (0.0018) [2023-03-09 10:49:40,680][119383] Updated weights for policy 0, policy_version 134237 (0.0016) [2023-03-09 10:49:41,680][119383] Updated weights for policy 0, policy_version 134247 (0.0024) [2023-03-09 10:49:42,379][119383] Updated weights for policy 0, policy_version 134257 (0.0030) [2023-03-09 10:49:43,132][119383] Updated weights for policy 0, policy_version 134267 (0.0016) [2023-03-09 10:49:43,902][118949] Fps is (10 sec: 194969.8, 60 sec: 194696.6, 300 sec: 196441.4). Total num frames: 2199945216. Throughput: 0: 48673.0. Samples: 50049136. Policy #0 lag: (min: 2.0, avg: 18.4, max: 34.0) [2023-03-09 10:49:43,903][118949] Avg episode reward: [(0, '54.915')] [2023-03-09 10:49:44,080][119383] Updated weights for policy 0, policy_version 134277 (0.0023) [2023-03-09 10:49:44,916][119383] Updated weights for policy 0, policy_version 134287 (0.0032) [2023-03-09 10:49:45,684][119383] Updated weights for policy 0, policy_version 134297 (0.0020) [2023-03-09 10:49:46,539][119383] Updated weights for policy 0, policy_version 134307 (0.0020) [2023-03-09 10:49:47,429][119383] Updated weights for policy 0, policy_version 134317 (0.0021) [2023-03-09 10:49:48,219][119383] Updated weights for policy 0, policy_version 134327 (0.0017) [2023-03-09 10:49:48,274][119240] Signal inference workers to stop experience collection... (4900 times) [2023-03-09 10:49:48,275][119240] Signal inference workers to resume experience collection... (4900 times) [2023-03-09 10:49:48,337][119383] InferenceWorker_p0-w0: stopping experience collection (4900 times) [2023-03-09 10:49:48,337][119383] InferenceWorker_p0-w0: resuming experience collection (4900 times) [2023-03-09 10:49:48,902][118949] Fps is (10 sec: 199890.3, 60 sec: 195515.7, 300 sec: 196608.0). Total num frames: 2200961024. Throughput: 0: 48720.4. Samples: 50198560. Policy #0 lag: (min: 2.0, avg: 18.4, max: 34.0) [2023-03-09 10:49:48,903][118949] Avg episode reward: [(0, '56.389')] [2023-03-09 10:49:48,977][119383] Updated weights for policy 0, policy_version 134337 (0.0016) [2023-03-09 10:49:49,871][119383] Updated weights for policy 0, policy_version 134347 (0.0030) [2023-03-09 10:49:50,838][119383] Updated weights for policy 0, policy_version 134358 (0.0020) [2023-03-09 10:49:51,509][119383] Updated weights for policy 0, policy_version 134368 (0.0022) [2023-03-09 10:49:52,508][119383] Updated weights for policy 0, policy_version 134378 (0.0014) [2023-03-09 10:49:53,287][119383] Updated weights for policy 0, policy_version 134388 (0.0016) [2023-03-09 10:49:53,902][118949] Fps is (10 sec: 198245.3, 60 sec: 194970.7, 300 sec: 196552.4). Total num frames: 2201927680. Throughput: 0: 48991.2. Samples: 50491344. Policy #0 lag: (min: 1.0, avg: 16.8, max: 34.0) [2023-03-09 10:49:53,903][118949] Avg episode reward: [(0, '55.592')] [2023-03-09 10:49:54,083][119383] Updated weights for policy 0, policy_version 134398 (0.0017) [2023-03-09 10:49:55,040][119383] Updated weights for policy 0, policy_version 134408 (0.0022) [2023-03-09 10:49:55,866][119383] Updated weights for policy 0, policy_version 134418 (0.0020) [2023-03-09 10:49:56,608][119383] Updated weights for policy 0, policy_version 134428 (0.0021) [2023-03-09 10:49:57,514][119383] Updated weights for policy 0, policy_version 134438 (0.0019) [2023-03-09 10:49:58,324][119383] Updated weights for policy 0, policy_version 134449 (0.0019) [2023-03-09 10:49:58,902][118949] Fps is (10 sec: 194962.2, 60 sec: 195242.3, 300 sec: 196496.9). Total num frames: 2202910720. Throughput: 0: 48948.2. Samples: 50788160. Policy #0 lag: (min: 1.0, avg: 16.8, max: 34.0) [2023-03-09 10:49:58,904][118949] Avg episode reward: [(0, '55.107')] [2023-03-09 10:49:58,919][119240] Signal inference workers to stop experience collection... (4950 times) [2023-03-09 10:49:58,920][119240] Signal inference workers to resume experience collection... (4950 times) [2023-03-09 10:49:58,986][119383] InferenceWorker_p0-w0: stopping experience collection (4950 times) [2023-03-09 10:49:58,986][119383] InferenceWorker_p0-w0: resuming experience collection (4950 times) [2023-03-09 10:49:59,150][119383] Updated weights for policy 0, policy_version 134459 (0.0020) [2023-03-09 10:50:00,189][119383] Updated weights for policy 0, policy_version 134470 (0.0023) [2023-03-09 10:50:00,957][119383] Updated weights for policy 0, policy_version 134480 (0.0026) [2023-03-09 10:50:01,697][119383] Updated weights for policy 0, policy_version 134490 (0.0022) [2023-03-09 10:50:02,657][119383] Updated weights for policy 0, policy_version 134500 (0.0016) [2023-03-09 10:50:03,475][119383] Updated weights for policy 0, policy_version 134510 (0.0017) [2023-03-09 10:50:03,902][118949] Fps is (10 sec: 196605.3, 60 sec: 195516.1, 300 sec: 196386.2). Total num frames: 2203893760. Throughput: 0: 48994.6. Samples: 50935584. Policy #0 lag: (min: 1.0, avg: 16.8, max: 34.0) [2023-03-09 10:50:03,903][118949] Avg episode reward: [(0, '56.742')] [2023-03-09 10:50:04,325][119383] Updated weights for policy 0, policy_version 134521 (0.0013) [2023-03-09 10:50:05,273][119383] Updated weights for policy 0, policy_version 134531 (0.0021) [2023-03-09 10:50:06,092][119383] Updated weights for policy 0, policy_version 134541 (0.0018) [2023-03-09 10:50:06,945][119383] Updated weights for policy 0, policy_version 134552 (0.0025) [2023-03-09 10:50:07,785][119383] Updated weights for policy 0, policy_version 134562 (0.0032) [2023-03-09 10:50:08,662][119383] Updated weights for policy 0, policy_version 134572 (0.0018) [2023-03-09 10:50:08,759][119240] Signal inference workers to stop experience collection... (5000 times) [2023-03-09 10:50:08,761][119240] Signal inference workers to resume experience collection... (5000 times) [2023-03-09 10:50:08,830][119383] InferenceWorker_p0-w0: stopping experience collection (5000 times) [2023-03-09 10:50:08,830][119383] InferenceWorker_p0-w0: resuming experience collection (5000 times) [2023-03-09 10:50:08,902][118949] Fps is (10 sec: 196613.6, 60 sec: 196061.6, 300 sec: 196386.1). Total num frames: 2204876800. Throughput: 0: 49086.1. Samples: 51230400. Policy #0 lag: (min: 1.0, avg: 16.8, max: 34.0) [2023-03-09 10:50:08,903][118949] Avg episode reward: [(0, '55.835')] [2023-03-09 10:50:09,528][119383] Updated weights for policy 0, policy_version 134583 (0.0020) [2023-03-09 10:50:10,324][119383] Updated weights for policy 0, policy_version 134593 (0.0016) [2023-03-09 10:50:11,272][119383] Updated weights for policy 0, policy_version 134603 (0.0019) [2023-03-09 10:50:12,088][119383] Updated weights for policy 0, policy_version 134613 (0.0021) [2023-03-09 10:50:12,865][119383] Updated weights for policy 0, policy_version 134623 (0.0013) [2023-03-09 10:50:13,827][119383] Updated weights for policy 0, policy_version 134633 (0.0018) [2023-03-09 10:50:13,902][118949] Fps is (10 sec: 194973.2, 60 sec: 195515.7, 300 sec: 196330.5). Total num frames: 2205843456. Throughput: 0: 49131.4. Samples: 51523120. Policy #0 lag: (min: 1.0, avg: 16.8, max: 34.0) [2023-03-09 10:50:13,903][118949] Avg episode reward: [(0, '56.733')] [2023-03-09 10:50:14,609][119383] Updated weights for policy 0, policy_version 134643 (0.0020) [2023-03-09 10:50:15,335][119383] Updated weights for policy 0, policy_version 134653 (0.0033) [2023-03-09 10:50:16,386][119383] Updated weights for policy 0, policy_version 134663 (0.0020) [2023-03-09 10:50:17,058][119383] Updated weights for policy 0, policy_version 134673 (0.0019) [2023-03-09 10:50:17,857][119383] Updated weights for policy 0, policy_version 134683 (0.0027) [2023-03-09 10:50:17,948][119240] Signal inference workers to stop experience collection... (5050 times) [2023-03-09 10:50:17,949][119240] Signal inference workers to resume experience collection... (5050 times) [2023-03-09 10:50:18,021][119383] InferenceWorker_p0-w0: stopping experience collection (5050 times) [2023-03-09 10:50:18,022][119383] InferenceWorker_p0-w0: resuming experience collection (5050 times) [2023-03-09 10:50:18,750][119383] Updated weights for policy 0, policy_version 134693 (0.0026) [2023-03-09 10:50:18,902][118949] Fps is (10 sec: 193328.1, 60 sec: 195516.8, 300 sec: 196274.9). Total num frames: 2206810112. Throughput: 0: 49130.4. Samples: 51670496. Policy #0 lag: (min: 1.0, avg: 16.8, max: 34.0) [2023-03-09 10:50:18,904][118949] Avg episode reward: [(0, '54.465')] [2023-03-09 10:50:19,557][119383] Updated weights for policy 0, policy_version 134703 (0.0016) [2023-03-09 10:50:20,364][119383] Updated weights for policy 0, policy_version 134713 (0.0026) [2023-03-09 10:50:21,309][119383] Updated weights for policy 0, policy_version 134723 (0.0030) [2023-03-09 10:50:22,189][119383] Updated weights for policy 0, policy_version 134734 (0.0013) [2023-03-09 10:50:22,958][119383] Updated weights for policy 0, policy_version 134744 (0.0024) [2023-03-09 10:50:23,902][118949] Fps is (10 sec: 196604.1, 60 sec: 196061.2, 300 sec: 196330.2). Total num frames: 2207809536. Throughput: 0: 49086.3. Samples: 51963312. Policy #0 lag: (min: 1.0, avg: 16.8, max: 34.0) [2023-03-09 10:50:23,903][118949] Avg episode reward: [(0, '53.484')] [2023-03-09 10:50:23,963][119383] Updated weights for policy 0, policy_version 134755 (0.0013) [2023-03-09 10:50:24,771][119383] Updated weights for policy 0, policy_version 134765 (0.0013) [2023-03-09 10:50:25,616][119383] Updated weights for policy 0, policy_version 134776 (0.0016) [2023-03-09 10:50:26,410][119383] Updated weights for policy 0, policy_version 134786 (0.0019) [2023-03-09 10:50:27,055][119240] Signal inference workers to stop experience collection... (5100 times) [2023-03-09 10:50:27,076][119240] Signal inference workers to resume experience collection... (5100 times) [2023-03-09 10:50:27,096][119383] InferenceWorker_p0-w0: stopping experience collection (5100 times) [2023-03-09 10:50:27,099][119383] InferenceWorker_p0-w0: resuming experience collection (5100 times) [2023-03-09 10:50:27,370][119383] Updated weights for policy 0, policy_version 134797 (0.0028) [2023-03-09 10:50:28,187][119383] Updated weights for policy 0, policy_version 134807 (0.0013) [2023-03-09 10:50:28,902][118949] Fps is (10 sec: 201528.1, 60 sec: 196881.3, 300 sec: 196441.6). Total num frames: 2208825344. Throughput: 0: 49179.0. Samples: 52262192. Policy #0 lag: (min: 1.0, avg: 16.8, max: 34.0) [2023-03-09 10:50:28,903][118949] Avg episode reward: [(0, '56.820')] [2023-03-09 10:50:28,955][119383] Updated weights for policy 0, policy_version 134817 (0.0023) [2023-03-09 10:50:29,920][119383] Updated weights for policy 0, policy_version 134827 (0.0031) [2023-03-09 10:50:30,728][119383] Updated weights for policy 0, policy_version 134837 (0.0017) [2023-03-09 10:50:31,506][119383] Updated weights for policy 0, policy_version 134847 (0.0013) [2023-03-09 10:50:32,486][119383] Updated weights for policy 0, policy_version 134858 (0.0020) [2023-03-09 10:50:33,348][119383] Updated weights for policy 0, policy_version 134868 (0.0030) [2023-03-09 10:50:33,902][118949] Fps is (10 sec: 198245.0, 60 sec: 196607.1, 300 sec: 196385.9). Total num frames: 2209792000. Throughput: 0: 49087.3. Samples: 52407504. Policy #0 lag: (min: 1.0, avg: 16.8, max: 34.0) [2023-03-09 10:50:33,904][118949] Avg episode reward: [(0, '54.139')] [2023-03-09 10:50:34,060][119383] Updated weights for policy 0, policy_version 134878 (0.0017) [2023-03-09 10:50:35,106][119383] Updated weights for policy 0, policy_version 134888 (0.0016) [2023-03-09 10:50:35,883][119383] Updated weights for policy 0, policy_version 134898 (0.0023) [2023-03-09 10:50:36,658][119383] Updated weights for policy 0, policy_version 134908 (0.0018) [2023-03-09 10:50:37,617][119240] Signal inference workers to stop experience collection... (5150 times) [2023-03-09 10:50:37,631][119240] Signal inference workers to resume experience collection... (5150 times) [2023-03-09 10:50:37,662][119383] InferenceWorker_p0-w0: stopping experience collection (5150 times) [2023-03-09 10:50:37,665][119383] Updated weights for policy 0, policy_version 134918 (0.0012) [2023-03-09 10:50:37,705][119383] InferenceWorker_p0-w0: resuming experience collection (5150 times) [2023-03-09 10:50:38,330][119383] Updated weights for policy 0, policy_version 134928 (0.0020) [2023-03-09 10:50:38,902][118949] Fps is (10 sec: 193331.6, 60 sec: 196608.9, 300 sec: 196386.1). Total num frames: 2210758656. Throughput: 0: 49130.4. Samples: 52702208. Policy #0 lag: (min: 1.0, avg: 16.8, max: 34.0) [2023-03-09 10:50:38,903][118949] Avg episode reward: [(0, '54.349')] [2023-03-09 10:50:39,207][119383] Updated weights for policy 0, policy_version 134938 (0.0025) [2023-03-09 10:50:40,072][119383] Updated weights for policy 0, policy_version 134948 (0.0016) [2023-03-09 10:50:40,983][119383] Updated weights for policy 0, policy_version 134958 (0.0032) [2023-03-09 10:50:41,766][119383] Updated weights for policy 0, policy_version 134968 (0.0018) [2023-03-09 10:50:42,541][119383] Updated weights for policy 0, policy_version 134978 (0.0026) [2023-03-09 10:50:43,436][119383] Updated weights for policy 0, policy_version 134988 (0.0013) [2023-03-09 10:50:43,902][118949] Fps is (10 sec: 193330.9, 60 sec: 196334.0, 300 sec: 196219.0). Total num frames: 2211725312. Throughput: 0: 48994.9. Samples: 52992928. Policy #0 lag: (min: 1.0, avg: 16.8, max: 34.0) [2023-03-09 10:50:43,904][118949] Avg episode reward: [(0, '55.447')] [2023-03-09 10:50:44,265][119383] Updated weights for policy 0, policy_version 134998 (0.0016) [2023-03-09 10:50:45,007][119383] Updated weights for policy 0, policy_version 135008 (0.0029) [2023-03-09 10:50:45,985][119383] Updated weights for policy 0, policy_version 135018 (0.0019) [2023-03-09 10:50:46,804][119383] Updated weights for policy 0, policy_version 135028 (0.0016) [2023-03-09 10:50:47,547][119383] Updated weights for policy 0, policy_version 135038 (0.0017) [2023-03-09 10:50:48,449][119240] Signal inference workers to stop experience collection... (5200 times) [2023-03-09 10:50:48,473][119240] Signal inference workers to resume experience collection... (5200 times) [2023-03-09 10:50:48,508][119383] InferenceWorker_p0-w0: stopping experience collection (5200 times) [2023-03-09 10:50:48,555][119383] InferenceWorker_p0-w0: resuming experience collection (5200 times) [2023-03-09 10:50:48,558][119383] Updated weights for policy 0, policy_version 135048 (0.0019) [2023-03-09 10:50:48,902][118949] Fps is (10 sec: 194968.9, 60 sec: 195788.7, 300 sec: 196219.7). Total num frames: 2212708352. Throughput: 0: 48949.2. Samples: 53138288. Policy #0 lag: (min: 1.0, avg: 16.8, max: 34.0) [2023-03-09 10:50:48,903][118949] Avg episode reward: [(0, '54.114')] [2023-03-09 10:50:49,335][119383] Updated weights for policy 0, policy_version 135058 (0.0029) [2023-03-09 10:50:50,089][119383] Updated weights for policy 0, policy_version 135068 (0.0034) [2023-03-09 10:50:51,063][119383] Updated weights for policy 0, policy_version 135078 (0.0020) [2023-03-09 10:50:51,756][119383] Updated weights for policy 0, policy_version 135088 (0.0033) [2023-03-09 10:50:52,624][119383] Updated weights for policy 0, policy_version 135099 (0.0018) [2023-03-09 10:50:53,521][119383] Updated weights for policy 0, policy_version 135109 (0.0024) [2023-03-09 10:50:53,902][118949] Fps is (10 sec: 196613.6, 60 sec: 196062.0, 300 sec: 196219.3). Total num frames: 2213691392. Throughput: 0: 48946.9. Samples: 53433008. Policy #0 lag: (min: 1.0, avg: 16.8, max: 34.0) [2023-03-09 10:50:53,903][118949] Avg episode reward: [(0, '54.083')] [2023-03-09 10:50:54,305][119383] Updated weights for policy 0, policy_version 135119 (0.0016) [2023-03-09 10:50:55,132][119383] Updated weights for policy 0, policy_version 135129 (0.0020) [2023-03-09 10:50:56,004][119383] Updated weights for policy 0, policy_version 135139 (0.0025) [2023-03-09 10:50:56,975][119383] Updated weights for policy 0, policy_version 135150 (0.0016) [2023-03-09 10:50:57,766][119383] Updated weights for policy 0, policy_version 135160 (0.0018) [2023-03-09 10:50:58,512][119383] Updated weights for policy 0, policy_version 135170 (0.0013) [2023-03-09 10:50:58,902][118949] Fps is (10 sec: 196608.3, 60 sec: 196063.1, 300 sec: 196274.8). Total num frames: 2214674432. Throughput: 0: 49037.9. Samples: 53729824. Policy #0 lag: (min: 1.0, avg: 16.7, max: 33.0) [2023-03-09 10:50:58,903][118949] Avg episode reward: [(0, '54.551')] [2023-03-09 10:50:59,169][119240] Signal inference workers to stop experience collection... (5250 times) [2023-03-09 10:50:59,170][119240] Signal inference workers to resume experience collection... (5250 times) [2023-03-09 10:50:59,232][119383] InferenceWorker_p0-w0: stopping experience collection (5250 times) [2023-03-09 10:50:59,233][119383] InferenceWorker_p0-w0: resuming experience collection (5250 times) [2023-03-09 10:50:59,521][119383] Updated weights for policy 0, policy_version 135180 (0.0017) [2023-03-09 10:51:00,292][119383] Updated weights for policy 0, policy_version 135190 (0.0013) [2023-03-09 10:51:01,095][119383] Updated weights for policy 0, policy_version 135201 (0.0013) [2023-03-09 10:51:01,987][119383] Updated weights for policy 0, policy_version 135211 (0.0016) [2023-03-09 10:51:02,920][119383] Updated weights for policy 0, policy_version 135222 (0.0013) [2023-03-09 10:51:03,597][119383] Updated weights for policy 0, policy_version 135232 (0.0018) [2023-03-09 10:51:03,902][118949] Fps is (10 sec: 198245.9, 60 sec: 196335.5, 300 sec: 196330.4). Total num frames: 2215673856. Throughput: 0: 49081.1. Samples: 53879136. Policy #0 lag: (min: 1.0, avg: 16.7, max: 33.0) [2023-03-09 10:51:03,903][118949] Avg episode reward: [(0, '56.143')] [2023-03-09 10:51:04,552][119383] Updated weights for policy 0, policy_version 135242 (0.0025) [2023-03-09 10:51:05,358][119383] Updated weights for policy 0, policy_version 135252 (0.0013) [2023-03-09 10:51:06,148][119383] Updated weights for policy 0, policy_version 135262 (0.0025) [2023-03-09 10:51:07,160][119383] Updated weights for policy 0, policy_version 135272 (0.0014) [2023-03-09 10:51:07,925][119383] Updated weights for policy 0, policy_version 135282 (0.0019) [2023-03-09 10:51:08,655][119383] Updated weights for policy 0, policy_version 135292 (0.0022) [2023-03-09 10:51:08,903][118949] Fps is (10 sec: 199870.2, 60 sec: 196605.9, 300 sec: 196385.4). Total num frames: 2216673280. Throughput: 0: 49125.1. Samples: 54173968. Policy #0 lag: (min: 1.0, avg: 16.7, max: 33.0) [2023-03-09 10:51:08,904][118949] Avg episode reward: [(0, '56.427')] [2023-03-09 10:51:09,630][119383] Updated weights for policy 0, policy_version 135302 (0.0016) [2023-03-09 10:51:10,370][119383] Updated weights for policy 0, policy_version 135312 (0.0015) [2023-03-09 10:51:10,902][119240] Signal inference workers to stop experience collection... (5300 times) [2023-03-09 10:51:10,903][119240] Signal inference workers to resume experience collection... (5300 times) [2023-03-09 10:51:10,975][119383] InferenceWorker_p0-w0: stopping experience collection (5300 times) [2023-03-09 10:51:10,976][119383] InferenceWorker_p0-w0: resuming experience collection (5300 times) [2023-03-09 10:51:11,149][119383] Updated weights for policy 0, policy_version 135322 (0.0019) [2023-03-09 10:51:12,116][119383] Updated weights for policy 0, policy_version 135332 (0.0032) [2023-03-09 10:51:12,942][119383] Updated weights for policy 0, policy_version 135342 (0.0016) [2023-03-09 10:51:13,798][119383] Updated weights for policy 0, policy_version 135353 (0.0016) [2023-03-09 10:51:13,902][118949] Fps is (10 sec: 196607.8, 60 sec: 196607.9, 300 sec: 196330.5). Total num frames: 2217639936. Throughput: 0: 48990.2. Samples: 54466752. Policy #0 lag: (min: 1.0, avg: 16.7, max: 33.0) [2023-03-09 10:51:13,903][118949] Avg episode reward: [(0, '54.269')] [2023-03-09 10:51:14,654][119383] Updated weights for policy 0, policy_version 135363 (0.0013) [2023-03-09 10:51:15,637][119383] Updated weights for policy 0, policy_version 135374 (0.0018) [2023-03-09 10:51:16,411][119383] Updated weights for policy 0, policy_version 135384 (0.0018) [2023-03-09 10:51:17,214][119383] Updated weights for policy 0, policy_version 135394 (0.0015) [2023-03-09 10:51:18,152][119383] Updated weights for policy 0, policy_version 135404 (0.0013) [2023-03-09 10:51:18,902][118949] Fps is (10 sec: 193339.5, 60 sec: 196607.8, 300 sec: 196274.9). Total num frames: 2218606592. Throughput: 0: 49035.7. Samples: 54614112. Policy #0 lag: (min: 1.0, avg: 16.7, max: 33.0) [2023-03-09 10:51:18,904][118949] Avg episode reward: [(0, '55.829')] [2023-03-09 10:51:18,971][119383] Updated weights for policy 0, policy_version 135414 (0.0014) [2023-03-09 10:51:19,626][119383] Updated weights for policy 0, policy_version 135424 (0.0017) [2023-03-09 10:51:20,676][119383] Updated weights for policy 0, policy_version 135434 (0.0019) [2023-03-09 10:51:21,408][119383] Updated weights for policy 0, policy_version 135444 (0.0013) [2023-03-09 10:51:21,591][119240] Signal inference workers to stop experience collection... (5350 times) [2023-03-09 10:51:21,592][119240] Signal inference workers to resume experience collection... (5350 times) [2023-03-09 10:51:21,653][119383] InferenceWorker_p0-w0: stopping experience collection (5350 times) [2023-03-09 10:51:21,656][119383] InferenceWorker_p0-w0: resuming experience collection (5350 times) [2023-03-09 10:51:22,155][119383] Updated weights for policy 0, policy_version 135454 (0.0017) [2023-03-09 10:51:23,127][119383] Updated weights for policy 0, policy_version 135464 (0.0016) [2023-03-09 10:51:23,902][118949] Fps is (10 sec: 194962.3, 60 sec: 196334.3, 300 sec: 196219.1). Total num frames: 2219589632. Throughput: 0: 49082.2. Samples: 54910928. Policy #0 lag: (min: 1.0, avg: 16.7, max: 33.0) [2023-03-09 10:51:23,904][118949] Avg episode reward: [(0, '54.226')] [2023-03-09 10:51:23,996][119240] Saving /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000135475_2219622400.pth... [2023-03-09 10:51:24,016][119383] Updated weights for policy 0, policy_version 135475 (0.0017) [2023-03-09 10:51:24,052][119240] Removing /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000132602_2172551168.pth [2023-03-09 10:51:24,803][119383] Updated weights for policy 0, policy_version 135485 (0.0022) [2023-03-09 10:51:25,764][119383] Updated weights for policy 0, policy_version 135495 (0.0013) [2023-03-09 10:51:26,521][119383] Updated weights for policy 0, policy_version 135505 (0.0040) [2023-03-09 10:51:27,412][119383] Updated weights for policy 0, policy_version 135516 (0.0021) [2023-03-09 10:51:28,409][119383] Updated weights for policy 0, policy_version 135526 (0.0021) [2023-03-09 10:51:28,902][118949] Fps is (10 sec: 194973.8, 60 sec: 195515.5, 300 sec: 196052.7). Total num frames: 2220556288. Throughput: 0: 49128.4. Samples: 55203696. Policy #0 lag: (min: 1.0, avg: 16.7, max: 33.0) [2023-03-09 10:51:28,903][118949] Avg episode reward: [(0, '54.476')] [2023-03-09 10:51:29,239][119383] Updated weights for policy 0, policy_version 135537 (0.0026) [2023-03-09 10:51:30,067][119383] Updated weights for policy 0, policy_version 135547 (0.0024) [2023-03-09 10:51:30,948][119383] Updated weights for policy 0, policy_version 135557 (0.0013) [2023-03-09 10:51:31,088][119240] Signal inference workers to stop experience collection... (5400 times) [2023-03-09 10:51:31,089][119240] Signal inference workers to resume experience collection... (5400 times) [2023-03-09 10:51:31,159][119383] InferenceWorker_p0-w0: stopping experience collection (5400 times) [2023-03-09 10:51:31,159][119383] InferenceWorker_p0-w0: resuming experience collection (5400 times) [2023-03-09 10:51:31,739][119383] Updated weights for policy 0, policy_version 135567 (0.0017) [2023-03-09 10:51:32,591][119383] Updated weights for policy 0, policy_version 135578 (0.0017) [2023-03-09 10:51:33,525][119383] Updated weights for policy 0, policy_version 135588 (0.0014) [2023-03-09 10:51:33,902][118949] Fps is (10 sec: 194970.2, 60 sec: 195788.5, 300 sec: 196107.9). Total num frames: 2221539328. Throughput: 0: 49127.4. Samples: 55349040. Policy #0 lag: (min: 1.0, avg: 16.7, max: 33.0) [2023-03-09 10:51:33,905][118949] Avg episode reward: [(0, '56.310')] [2023-03-09 10:51:34,358][119383] Updated weights for policy 0, policy_version 135598 (0.0013) [2023-03-09 10:51:35,128][119383] Updated weights for policy 0, policy_version 135608 (0.0016) [2023-03-09 10:51:35,965][119383] Updated weights for policy 0, policy_version 135618 (0.0013) [2023-03-09 10:51:36,910][119383] Updated weights for policy 0, policy_version 135628 (0.0039) [2023-03-09 10:51:37,715][119383] Updated weights for policy 0, policy_version 135638 (0.0030) [2023-03-09 10:51:38,399][119383] Updated weights for policy 0, policy_version 135648 (0.0044) [2023-03-09 10:51:38,902][118949] Fps is (10 sec: 194968.6, 60 sec: 195788.3, 300 sec: 196052.5). Total num frames: 2222505984. Throughput: 0: 49084.7. Samples: 55641824. Policy #0 lag: (min: 1.0, avg: 16.7, max: 33.0) [2023-03-09 10:51:38,904][118949] Avg episode reward: [(0, '55.223')] [2023-03-09 10:51:39,436][119383] Updated weights for policy 0, policy_version 135658 (0.0016) [2023-03-09 10:51:40,051][119240] Signal inference workers to stop experience collection... (5450 times) [2023-03-09 10:51:40,071][119240] Signal inference workers to resume experience collection... (5450 times) [2023-03-09 10:51:40,096][119383] InferenceWorker_p0-w0: stopping experience collection (5450 times) [2023-03-09 10:51:40,139][119383] InferenceWorker_p0-w0: resuming experience collection (5450 times) [2023-03-09 10:51:40,225][119383] Updated weights for policy 0, policy_version 135668 (0.0026) [2023-03-09 10:51:40,944][119383] Updated weights for policy 0, policy_version 135678 (0.0021) [2023-03-09 10:51:41,943][119383] Updated weights for policy 0, policy_version 135688 (0.0016) [2023-03-09 10:51:42,772][119383] Updated weights for policy 0, policy_version 135698 (0.0024) [2023-03-09 10:51:43,493][119383] Updated weights for policy 0, policy_version 135708 (0.0017) [2023-03-09 10:51:43,902][118949] Fps is (10 sec: 198243.0, 60 sec: 196607.1, 300 sec: 196163.3). Total num frames: 2223521792. Throughput: 0: 48996.0. Samples: 55934672. Policy #0 lag: (min: 1.0, avg: 16.7, max: 33.0) [2023-03-09 10:51:43,905][118949] Avg episode reward: [(0, '56.361')] [2023-03-09 10:51:44,538][119383] Updated weights for policy 0, policy_version 135719 (0.0013) [2023-03-09 10:51:45,480][119383] Updated weights for policy 0, policy_version 135730 (0.0014) [2023-03-09 10:51:46,184][119383] Updated weights for policy 0, policy_version 135740 (0.0018) [2023-03-09 10:51:47,203][119383] Updated weights for policy 0, policy_version 135750 (0.0021) [2023-03-09 10:51:47,910][119383] Updated weights for policy 0, policy_version 135760 (0.0013) [2023-03-09 10:51:48,730][119383] Updated weights for policy 0, policy_version 135770 (0.0013) [2023-03-09 10:51:48,902][118949] Fps is (10 sec: 198242.8, 60 sec: 196333.9, 300 sec: 196163.7). Total num frames: 2224488448. Throughput: 0: 48952.9. Samples: 56082032. Policy #0 lag: (min: 1.0, avg: 16.7, max: 33.0) [2023-03-09 10:51:48,904][118949] Avg episode reward: [(0, '55.591')] [2023-03-09 10:51:49,682][119383] Updated weights for policy 0, policy_version 135780 (0.0017) [2023-03-09 10:51:49,985][119240] Signal inference workers to stop experience collection... (5500 times) [2023-03-09 10:51:49,986][119240] Signal inference workers to resume experience collection... (5500 times) [2023-03-09 10:51:50,055][119383] InferenceWorker_p0-w0: stopping experience collection (5500 times) [2023-03-09 10:51:50,055][119383] InferenceWorker_p0-w0: resuming experience collection (5500 times) [2023-03-09 10:51:50,484][119383] Updated weights for policy 0, policy_version 135790 (0.0036) [2023-03-09 10:51:51,334][119383] Updated weights for policy 0, policy_version 135800 (0.0017) [2023-03-09 10:51:52,069][119383] Updated weights for policy 0, policy_version 135810 (0.0022) [2023-03-09 10:51:53,034][119383] Updated weights for policy 0, policy_version 135820 (0.0029) [2023-03-09 10:51:53,872][119383] Updated weights for policy 0, policy_version 135830 (0.0016) [2023-03-09 10:51:53,902][118949] Fps is (10 sec: 191703.0, 60 sec: 195788.8, 300 sec: 196052.8). Total num frames: 2225438720. Throughput: 0: 48908.2. Samples: 56374800. Policy #0 lag: (min: 1.0, avg: 16.7, max: 33.0) [2023-03-09 10:51:53,903][118949] Avg episode reward: [(0, '52.993')] [2023-03-09 10:51:54,502][119383] Updated weights for policy 0, policy_version 135840 (0.0013) [2023-03-09 10:51:55,534][119383] Updated weights for policy 0, policy_version 135850 (0.0013) [2023-03-09 10:51:56,323][119383] Updated weights for policy 0, policy_version 135860 (0.0029) [2023-03-09 10:51:57,036][119383] Updated weights for policy 0, policy_version 135870 (0.0018) [2023-03-09 10:51:58,062][119383] Updated weights for policy 0, policy_version 135880 (0.0014) [2023-03-09 10:51:58,460][119240] Signal inference workers to stop experience collection... (5550 times) [2023-03-09 10:51:58,486][119240] Signal inference workers to resume experience collection... (5550 times) [2023-03-09 10:51:58,531][119383] InferenceWorker_p0-w0: stopping experience collection (5550 times) [2023-03-09 10:51:58,531][119383] InferenceWorker_p0-w0: resuming experience collection (5550 times) [2023-03-09 10:51:58,902][118949] Fps is (10 sec: 193330.7, 60 sec: 195787.7, 300 sec: 196052.4). Total num frames: 2226421760. Throughput: 0: 48905.3. Samples: 56667504. Policy #0 lag: (min: 2.0, avg: 18.0, max: 34.0) [2023-03-09 10:51:58,904][118949] Avg episode reward: [(0, '54.760')] [2023-03-09 10:51:58,908][119383] Updated weights for policy 0, policy_version 135890 (0.0043) [2023-03-09 10:51:59,623][119383] Updated weights for policy 0, policy_version 135900 (0.0021) [2023-03-09 10:52:00,602][119383] Updated weights for policy 0, policy_version 135910 (0.0017) [2023-03-09 10:52:01,408][119383] Updated weights for policy 0, policy_version 135921 (0.0022) [2023-03-09 10:52:02,222][119383] Updated weights for policy 0, policy_version 135931 (0.0015) [2023-03-09 10:52:03,091][119383] Updated weights for policy 0, policy_version 135941 (0.0013) [2023-03-09 10:52:03,902][118949] Fps is (10 sec: 198246.2, 60 sec: 195788.8, 300 sec: 196108.1). Total num frames: 2227421184. Throughput: 0: 48907.7. Samples: 56814944. Policy #0 lag: (min: 2.0, avg: 18.0, max: 34.0) [2023-03-09 10:52:03,903][118949] Avg episode reward: [(0, '53.546')] [2023-03-09 10:52:03,906][119383] Updated weights for policy 0, policy_version 135951 (0.0029) [2023-03-09 10:52:04,777][119383] Updated weights for policy 0, policy_version 135962 (0.0015) [2023-03-09 10:52:05,712][119383] Updated weights for policy 0, policy_version 135972 (0.0022) [2023-03-09 10:52:06,518][119383] Updated weights for policy 0, policy_version 135982 (0.0013) [2023-03-09 10:52:07,327][119383] Updated weights for policy 0, policy_version 135992 (0.0017) [2023-03-09 10:52:08,079][119383] Updated weights for policy 0, policy_version 136002 (0.0013) [2023-03-09 10:52:08,902][118949] Fps is (10 sec: 198244.4, 60 sec: 195516.7, 300 sec: 196052.4). Total num frames: 2228404224. Throughput: 0: 48909.5. Samples: 57111856. Policy #0 lag: (min: 2.0, avg: 18.0, max: 34.0) [2023-03-09 10:52:08,904][118949] Avg episode reward: [(0, '54.698')] [2023-03-09 10:52:09,022][119240] Signal inference workers to stop experience collection... (5600 times) [2023-03-09 10:52:09,027][119240] Signal inference workers to resume experience collection... (5600 times) [2023-03-09 10:52:09,050][119383] Updated weights for policy 0, policy_version 136012 (0.0021) [2023-03-09 10:52:09,092][119383] InferenceWorker_p0-w0: stopping experience collection (5600 times) [2023-03-09 10:52:09,092][119383] InferenceWorker_p0-w0: resuming experience collection (5600 times) [2023-03-09 10:52:09,855][119383] Updated weights for policy 0, policy_version 136022 (0.0017) [2023-03-09 10:52:10,473][119383] Updated weights for policy 0, policy_version 136032 (0.0020) [2023-03-09 10:52:11,433][119383] Updated weights for policy 0, policy_version 136042 (0.0032) [2023-03-09 10:52:12,369][119383] Updated weights for policy 0, policy_version 136053 (0.0013) [2023-03-09 10:52:13,048][119383] Updated weights for policy 0, policy_version 136063 (0.0023) [2023-03-09 10:52:13,902][118949] Fps is (10 sec: 196600.7, 60 sec: 195787.6, 300 sec: 196107.9). Total num frames: 2229387264. Throughput: 0: 48999.8. Samples: 57408704. Policy #0 lag: (min: 2.0, avg: 18.0, max: 34.0) [2023-03-09 10:52:13,904][118949] Avg episode reward: [(0, '52.384')] [2023-03-09 10:52:14,016][119383] Updated weights for policy 0, policy_version 136073 (0.0017) [2023-03-09 10:52:14,871][119383] Updated weights for policy 0, policy_version 136083 (0.0032) [2023-03-09 10:52:15,567][119383] Updated weights for policy 0, policy_version 136093 (0.0017) [2023-03-09 10:52:16,599][119383] Updated weights for policy 0, policy_version 136103 (0.0016) [2023-03-09 10:52:17,313][119383] Updated weights for policy 0, policy_version 136113 (0.0021) [2023-03-09 10:52:18,199][119383] Updated weights for policy 0, policy_version 136124 (0.0025) [2023-03-09 10:52:18,902][118949] Fps is (10 sec: 196613.3, 60 sec: 196062.3, 300 sec: 196108.5). Total num frames: 2230370304. Throughput: 0: 49045.6. Samples: 57556080. Policy #0 lag: (min: 2.0, avg: 18.0, max: 34.0) [2023-03-09 10:52:18,904][118949] Avg episode reward: [(0, '56.940')] [2023-03-09 10:52:19,134][119383] Updated weights for policy 0, policy_version 136134 (0.0016) [2023-03-09 10:52:19,288][119240] Signal inference workers to stop experience collection... (5650 times) [2023-03-09 10:52:19,290][119240] Signal inference workers to resume experience collection... (5650 times) [2023-03-09 10:52:19,351][119383] InferenceWorker_p0-w0: stopping experience collection (5650 times) [2023-03-09 10:52:19,351][119383] InferenceWorker_p0-w0: resuming experience collection (5650 times) [2023-03-09 10:52:19,995][119383] Updated weights for policy 0, policy_version 136145 (0.0017) [2023-03-09 10:52:20,822][119383] Updated weights for policy 0, policy_version 136155 (0.0019) [2023-03-09 10:52:21,738][119383] Updated weights for policy 0, policy_version 136165 (0.0022) [2023-03-09 10:52:22,516][119383] Updated weights for policy 0, policy_version 136175 (0.0021) [2023-03-09 10:52:23,364][119383] Updated weights for policy 0, policy_version 136186 (0.0022) [2023-03-09 10:52:23,902][118949] Fps is (10 sec: 199887.1, 60 sec: 196608.4, 300 sec: 196274.7). Total num frames: 2231386112. Throughput: 0: 49090.7. Samples: 57850912. Policy #0 lag: (min: 2.0, avg: 18.0, max: 34.0) [2023-03-09 10:52:23,904][118949] Avg episode reward: [(0, '56.288')] [2023-03-09 10:52:24,290][119383] Updated weights for policy 0, policy_version 136196 (0.0013) [2023-03-09 10:52:25,135][119383] Updated weights for policy 0, policy_version 136206 (0.0013) [2023-03-09 10:52:25,900][119383] Updated weights for policy 0, policy_version 136216 (0.0013) [2023-03-09 10:52:26,690][119383] Updated weights for policy 0, policy_version 136226 (0.0019) [2023-03-09 10:52:27,704][119383] Updated weights for policy 0, policy_version 136236 (0.0016) [2023-03-09 10:52:28,440][119383] Updated weights for policy 0, policy_version 136246 (0.0018) [2023-03-09 10:52:28,902][118949] Fps is (10 sec: 199881.9, 60 sec: 196880.3, 300 sec: 196163.6). Total num frames: 2232369152. Throughput: 0: 49134.8. Samples: 58145728. Policy #0 lag: (min: 2.0, avg: 18.0, max: 34.0) [2023-03-09 10:52:28,904][118949] Avg episode reward: [(0, '55.443')] [2023-03-09 10:52:29,218][119383] Updated weights for policy 0, policy_version 136257 (0.0020) [2023-03-09 10:52:30,188][119383] Updated weights for policy 0, policy_version 136267 (0.0021) [2023-03-09 10:52:31,035][119383] Updated weights for policy 0, policy_version 136277 (0.0016) [2023-03-09 10:52:31,778][119383] Updated weights for policy 0, policy_version 136287 (0.0022) [2023-03-09 10:52:32,682][119383] Updated weights for policy 0, policy_version 136297 (0.0019) [2023-03-09 10:52:32,983][119240] Signal inference workers to stop experience collection... (5700 times) [2023-03-09 10:52:32,984][119240] Signal inference workers to resume experience collection... (5700 times) [2023-03-09 10:52:33,057][119383] InferenceWorker_p0-w0: stopping experience collection (5700 times) [2023-03-09 10:52:33,057][119383] InferenceWorker_p0-w0: resuming experience collection (5700 times) [2023-03-09 10:52:33,508][119383] Updated weights for policy 0, policy_version 136307 (0.0017) [2023-03-09 10:52:33,902][118949] Fps is (10 sec: 194974.1, 60 sec: 196609.1, 300 sec: 196163.8). Total num frames: 2233335808. Throughput: 0: 49135.6. Samples: 58293120. Policy #0 lag: (min: 2.0, avg: 18.0, max: 34.0) [2023-03-09 10:52:33,903][118949] Avg episode reward: [(0, '53.951')] [2023-03-09 10:52:34,213][119383] Updated weights for policy 0, policy_version 136317 (0.0016) [2023-03-09 10:52:35,288][119383] Updated weights for policy 0, policy_version 136328 (0.0015) [2023-03-09 10:52:36,111][119383] Updated weights for policy 0, policy_version 136338 (0.0022) [2023-03-09 10:52:36,877][119383] Updated weights for policy 0, policy_version 136349 (0.0029) [2023-03-09 10:52:37,880][119383] Updated weights for policy 0, policy_version 136359 (0.0019) [2023-03-09 10:52:38,649][119383] Updated weights for policy 0, policy_version 136369 (0.0023) [2023-03-09 10:52:38,902][118949] Fps is (10 sec: 194968.7, 60 sec: 196880.3, 300 sec: 196274.5). Total num frames: 2234318848. Throughput: 0: 49225.9. Samples: 58589984. Policy #0 lag: (min: 2.0, avg: 18.0, max: 34.0) [2023-03-09 10:52:38,904][118949] Avg episode reward: [(0, '54.563')] [2023-03-09 10:52:39,427][119383] Updated weights for policy 0, policy_version 136379 (0.0035) [2023-03-09 10:52:40,279][119383] Updated weights for policy 0, policy_version 136389 (0.0017) [2023-03-09 10:52:41,172][119383] Updated weights for policy 0, policy_version 136399 (0.0016) [2023-03-09 10:52:41,906][119383] Updated weights for policy 0, policy_version 136409 (0.0022) [2023-03-09 10:52:42,786][119383] Updated weights for policy 0, policy_version 136419 (0.0016) [2023-03-09 10:52:43,644][119383] Updated weights for policy 0, policy_version 136429 (0.0013) [2023-03-09 10:52:43,902][118949] Fps is (10 sec: 198239.7, 60 sec: 196608.5, 300 sec: 196274.5). Total num frames: 2235318272. Throughput: 0: 49319.1. Samples: 58886864. Policy #0 lag: (min: 2.0, avg: 18.0, max: 34.0) [2023-03-09 10:52:43,905][118949] Avg episode reward: [(0, '54.813')] [2023-03-09 10:52:44,383][119240] Signal inference workers to stop experience collection... (5750 times) [2023-03-09 10:52:44,384][119240] Signal inference workers to resume experience collection... (5750 times) [2023-03-09 10:52:44,451][119383] InferenceWorker_p0-w0: stopping experience collection (5750 times) [2023-03-09 10:52:44,451][119383] InferenceWorker_p0-w0: resuming experience collection (5750 times) [2023-03-09 10:52:44,457][119383] Updated weights for policy 0, policy_version 136439 (0.0016) [2023-03-09 10:52:45,158][119383] Updated weights for policy 0, policy_version 136449 (0.0029) [2023-03-09 10:52:46,139][119383] Updated weights for policy 0, policy_version 136459 (0.0013) [2023-03-09 10:52:46,889][119383] Updated weights for policy 0, policy_version 136469 (0.0015) [2023-03-09 10:52:47,673][119383] Updated weights for policy 0, policy_version 136480 (0.0018) [2023-03-09 10:52:48,728][119383] Updated weights for policy 0, policy_version 136490 (0.0020) [2023-03-09 10:52:48,902][118949] Fps is (10 sec: 196615.1, 60 sec: 196609.0, 300 sec: 196164.8). Total num frames: 2236284928. Throughput: 0: 49362.9. Samples: 59036272. Policy #0 lag: (min: 2.0, avg: 18.0, max: 34.0) [2023-03-09 10:52:48,903][118949] Avg episode reward: [(0, '53.555')] [2023-03-09 10:52:49,503][119383] Updated weights for policy 0, policy_version 136500 (0.0019) [2023-03-09 10:52:50,213][119383] Updated weights for policy 0, policy_version 136510 (0.0027) [2023-03-09 10:52:51,214][119383] Updated weights for policy 0, policy_version 136521 (0.0031) [2023-03-09 10:52:52,065][119383] Updated weights for policy 0, policy_version 136531 (0.0013) [2023-03-09 10:52:52,767][119383] Updated weights for policy 0, policy_version 136541 (0.0016) [2023-03-09 10:52:53,765][119383] Updated weights for policy 0, policy_version 136551 (0.0024) [2023-03-09 10:52:53,902][118949] Fps is (10 sec: 196608.5, 60 sec: 197426.1, 300 sec: 196274.7). Total num frames: 2237284352. Throughput: 0: 49316.7. Samples: 59331104. Policy #0 lag: (min: 2.0, avg: 18.0, max: 34.0) [2023-03-09 10:52:53,904][118949] Avg episode reward: [(0, '56.356')] [2023-03-09 10:52:54,502][119383] Updated weights for policy 0, policy_version 136561 (0.0019) [2023-03-09 10:52:55,394][119383] Updated weights for policy 0, policy_version 136572 (0.0016) [2023-03-09 10:52:55,609][119240] Signal inference workers to stop experience collection... (5800 times) [2023-03-09 10:52:55,613][119240] Signal inference workers to resume experience collection... (5800 times) [2023-03-09 10:52:55,678][119383] InferenceWorker_p0-w0: stopping experience collection (5800 times) [2023-03-09 10:52:55,678][119383] InferenceWorker_p0-w0: resuming experience collection (5800 times) [2023-03-09 10:52:56,394][119383] Updated weights for policy 0, policy_version 136582 (0.0025) [2023-03-09 10:52:57,086][119383] Updated weights for policy 0, policy_version 136592 (0.0021) [2023-03-09 10:52:57,894][119383] Updated weights for policy 0, policy_version 136602 (0.0022) [2023-03-09 10:52:58,844][119383] Updated weights for policy 0, policy_version 136612 (0.0019) [2023-03-09 10:52:58,902][118949] Fps is (10 sec: 198242.6, 60 sec: 197427.7, 300 sec: 196219.1). Total num frames: 2238267392. Throughput: 0: 49318.3. Samples: 59628016. Policy #0 lag: (min: 2.0, avg: 18.0, max: 34.0) [2023-03-09 10:52:58,903][118949] Avg episode reward: [(0, '54.920')] [2023-03-09 10:52:59,649][119383] Updated weights for policy 0, policy_version 136622 (0.0015) [2023-03-09 10:53:00,455][119383] Updated weights for policy 0, policy_version 136632 (0.0016) [2023-03-09 10:53:01,197][119383] Updated weights for policy 0, policy_version 136642 (0.0020) [2023-03-09 10:53:02,159][119383] Updated weights for policy 0, policy_version 136652 (0.0026) [2023-03-09 10:53:02,899][119383] Updated weights for policy 0, policy_version 136662 (0.0017) [2023-03-09 10:53:03,724][119383] Updated weights for policy 0, policy_version 136673 (0.0022) [2023-03-09 10:53:03,902][118949] Fps is (10 sec: 198253.2, 60 sec: 197427.2, 300 sec: 196385.8). Total num frames: 2239266816. Throughput: 0: 49319.3. Samples: 59775440. Policy #0 lag: (min: 0.0, avg: 16.2, max: 33.0) [2023-03-09 10:53:03,903][118949] Avg episode reward: [(0, '56.653')] [2023-03-09 10:53:04,708][119383] Updated weights for policy 0, policy_version 136683 (0.0013) [2023-03-09 10:53:05,486][119383] Updated weights for policy 0, policy_version 136693 (0.0029) [2023-03-09 10:53:05,998][119240] Signal inference workers to stop experience collection... (5850 times) [2023-03-09 10:53:05,999][119240] Signal inference workers to resume experience collection... (5850 times) [2023-03-09 10:53:06,064][119383] InferenceWorker_p0-w0: stopping experience collection (5850 times) [2023-03-09 10:53:06,065][119383] InferenceWorker_p0-w0: resuming experience collection (5850 times) [2023-03-09 10:53:06,236][119383] Updated weights for policy 0, policy_version 136703 (0.0013) [2023-03-09 10:53:07,151][119383] Updated weights for policy 0, policy_version 136713 (0.0025) [2023-03-09 10:53:07,965][119383] Updated weights for policy 0, policy_version 136723 (0.0027) [2023-03-09 10:53:08,760][119383] Updated weights for policy 0, policy_version 136733 (0.0024) [2023-03-09 10:53:08,902][118949] Fps is (10 sec: 199887.4, 60 sec: 197701.5, 300 sec: 196386.0). Total num frames: 2240266240. Throughput: 0: 49364.5. Samples: 60072304. Policy #0 lag: (min: 0.0, avg: 16.2, max: 33.0) [2023-03-09 10:53:08,903][118949] Avg episode reward: [(0, '55.555')] [2023-03-09 10:53:09,748][119383] Updated weights for policy 0, policy_version 136743 (0.0021) [2023-03-09 10:53:10,522][119383] Updated weights for policy 0, policy_version 136753 (0.0024) [2023-03-09 10:53:11,229][119383] Updated weights for policy 0, policy_version 136763 (0.0025) [2023-03-09 10:53:12,251][119383] Updated weights for policy 0, policy_version 136774 (0.0026) [2023-03-09 10:53:13,005][119383] Updated weights for policy 0, policy_version 136784 (0.0021) [2023-03-09 10:53:13,844][119383] Updated weights for policy 0, policy_version 136794 (0.0016) [2023-03-09 10:53:13,902][118949] Fps is (10 sec: 198241.3, 60 sec: 197700.7, 300 sec: 196385.8). Total num frames: 2241249280. Throughput: 0: 49363.6. Samples: 60367088. Policy #0 lag: (min: 0.0, avg: 16.2, max: 33.0) [2023-03-09 10:53:13,904][118949] Avg episode reward: [(0, '56.933')] [2023-03-09 10:53:14,743][119383] Updated weights for policy 0, policy_version 136804 (0.0013) [2023-03-09 10:53:15,601][119383] Updated weights for policy 0, policy_version 136814 (0.0029) [2023-03-09 10:53:16,366][119383] Updated weights for policy 0, policy_version 136824 (0.0018) [2023-03-09 10:53:17,172][119383] Updated weights for policy 0, policy_version 136834 (0.0025) [2023-03-09 10:53:17,698][119240] Signal inference workers to stop experience collection... (5900 times) [2023-03-09 10:53:17,721][119240] Signal inference workers to resume experience collection... (5900 times) [2023-03-09 10:53:17,767][119383] InferenceWorker_p0-w0: stopping experience collection (5900 times) [2023-03-09 10:53:17,767][119383] InferenceWorker_p0-w0: resuming experience collection (5900 times) [2023-03-09 10:53:18,131][119383] Updated weights for policy 0, policy_version 136845 (0.0014) [2023-03-09 10:53:18,902][118949] Fps is (10 sec: 194962.6, 60 sec: 197426.4, 300 sec: 196330.3). Total num frames: 2242215936. Throughput: 0: 49363.5. Samples: 60514496. Policy #0 lag: (min: 0.0, avg: 16.2, max: 33.0) [2023-03-09 10:53:18,904][118949] Avg episode reward: [(0, '56.370')] [2023-03-09 10:53:18,984][119383] Updated weights for policy 0, policy_version 136855 (0.0020) [2023-03-09 10:53:19,660][119383] Updated weights for policy 0, policy_version 136865 (0.0030) [2023-03-09 10:53:20,746][119383] Updated weights for policy 0, policy_version 136876 (0.0028) [2023-03-09 10:53:21,526][119383] Updated weights for policy 0, policy_version 136886 (0.0018) [2023-03-09 10:53:22,345][119383] Updated weights for policy 0, policy_version 136897 (0.0016) [2023-03-09 10:53:23,316][119383] Updated weights for policy 0, policy_version 136907 (0.0026) [2023-03-09 10:53:23,902][118949] Fps is (10 sec: 194971.7, 60 sec: 196881.5, 300 sec: 196274.9). Total num frames: 2243198976. Throughput: 0: 49362.4. Samples: 60811280. Policy #0 lag: (min: 0.0, avg: 16.2, max: 33.0) [2023-03-09 10:53:23,903][118949] Avg episode reward: [(0, '55.861')] [2023-03-09 10:53:23,946][119240] Saving /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000136915_2243215360.pth... [2023-03-09 10:53:24,014][119240] Removing /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000134036_2196045824.pth [2023-03-09 10:53:24,155][119383] Updated weights for policy 0, policy_version 136917 (0.0016) [2023-03-09 10:53:24,854][119383] Updated weights for policy 0, policy_version 136927 (0.0017) [2023-03-09 10:53:25,802][119383] Updated weights for policy 0, policy_version 136937 (0.0016) [2023-03-09 10:53:26,606][119383] Updated weights for policy 0, policy_version 136947 (0.0013) [2023-03-09 10:53:27,352][119383] Updated weights for policy 0, policy_version 136957 (0.0021) [2023-03-09 10:53:28,294][119383] Updated weights for policy 0, policy_version 136967 (0.0023) [2023-03-09 10:53:28,322][119240] Signal inference workers to stop experience collection... (5950 times) [2023-03-09 10:53:28,323][119240] Signal inference workers to resume experience collection... (5950 times) [2023-03-09 10:53:28,380][119383] InferenceWorker_p0-w0: stopping experience collection (5950 times) [2023-03-09 10:53:28,380][119383] InferenceWorker_p0-w0: resuming experience collection (5950 times) [2023-03-09 10:53:28,902][118949] Fps is (10 sec: 196616.6, 60 sec: 196882.2, 300 sec: 196219.3). Total num frames: 2244182016. Throughput: 0: 49362.6. Samples: 61108160. Policy #0 lag: (min: 0.0, avg: 16.2, max: 33.0) [2023-03-09 10:53:28,903][118949] Avg episode reward: [(0, '53.950')] [2023-03-09 10:53:29,159][119383] Updated weights for policy 0, policy_version 136977 (0.0026) [2023-03-09 10:53:29,840][119383] Updated weights for policy 0, policy_version 136987 (0.0022) [2023-03-09 10:53:30,797][119383] Updated weights for policy 0, policy_version 136997 (0.0013) [2023-03-09 10:53:31,619][119383] Updated weights for policy 0, policy_version 137007 (0.0020) [2023-03-09 10:53:32,419][119383] Updated weights for policy 0, policy_version 137018 (0.0020) [2023-03-09 10:53:33,349][119383] Updated weights for policy 0, policy_version 137028 (0.0013) [2023-03-09 10:53:33,902][118949] Fps is (10 sec: 196607.1, 60 sec: 197153.6, 300 sec: 196274.9). Total num frames: 2245165056. Throughput: 0: 49317.5. Samples: 61255568. Policy #0 lag: (min: 0.0, avg: 16.2, max: 33.0) [2023-03-09 10:53:33,903][118949] Avg episode reward: [(0, '53.693')] [2023-03-09 10:53:34,152][119383] Updated weights for policy 0, policy_version 137038 (0.0024) [2023-03-09 10:53:34,975][119383] Updated weights for policy 0, policy_version 137048 (0.0021) [2023-03-09 10:53:35,781][119383] Updated weights for policy 0, policy_version 137058 (0.0013) [2023-03-09 10:53:36,676][119383] Updated weights for policy 0, policy_version 137068 (0.0014) [2023-03-09 10:53:37,549][119383] Updated weights for policy 0, policy_version 137078 (0.0012) [2023-03-09 10:53:38,171][119383] Updated weights for policy 0, policy_version 137088 (0.0013) [2023-03-09 10:53:38,902][118949] Fps is (10 sec: 196607.9, 60 sec: 197155.4, 300 sec: 196219.2). Total num frames: 2246148096. Throughput: 0: 49362.5. Samples: 61552400. Policy #0 lag: (min: 0.0, avg: 16.2, max: 33.0) [2023-03-09 10:53:38,903][118949] Avg episode reward: [(0, '54.183')] [2023-03-09 10:53:39,160][119383] Updated weights for policy 0, policy_version 137098 (0.0016) [2023-03-09 10:53:39,969][119383] Updated weights for policy 0, policy_version 137108 (0.0019) [2023-03-09 10:53:40,224][119240] Signal inference workers to stop experience collection... (6000 times) [2023-03-09 10:53:40,225][119240] Signal inference workers to resume experience collection... (6000 times) [2023-03-09 10:53:40,295][119383] InferenceWorker_p0-w0: stopping experience collection (6000 times) [2023-03-09 10:53:40,296][119383] InferenceWorker_p0-w0: resuming experience collection (6000 times) [2023-03-09 10:53:40,668][119383] Updated weights for policy 0, policy_version 137118 (0.0032) [2023-03-09 10:53:41,634][119383] Updated weights for policy 0, policy_version 137128 (0.0018) [2023-03-09 10:53:42,513][119383] Updated weights for policy 0, policy_version 137139 (0.0017) [2023-03-09 10:53:43,280][119383] Updated weights for policy 0, policy_version 137150 (0.0011) [2023-03-09 10:53:43,902][118949] Fps is (10 sec: 198248.4, 60 sec: 197155.0, 300 sec: 196330.2). Total num frames: 2247147520. Throughput: 0: 49407.0. Samples: 61851328. Policy #0 lag: (min: 0.0, avg: 16.2, max: 33.0) [2023-03-09 10:53:43,903][118949] Avg episode reward: [(0, '54.654')] [2023-03-09 10:53:44,308][119383] Updated weights for policy 0, policy_version 137161 (0.0025) [2023-03-09 10:53:45,122][119383] Updated weights for policy 0, policy_version 137171 (0.0016) [2023-03-09 10:53:45,858][119383] Updated weights for policy 0, policy_version 137181 (0.0027) [2023-03-09 10:53:46,862][119383] Updated weights for policy 0, policy_version 137191 (0.0014) [2023-03-09 10:53:47,713][119383] Updated weights for policy 0, policy_version 137201 (0.0024) [2023-03-09 10:53:48,381][119383] Updated weights for policy 0, policy_version 137211 (0.0020) [2023-03-09 10:53:48,902][118949] Fps is (10 sec: 201523.3, 60 sec: 197973.4, 300 sec: 196386.1). Total num frames: 2248163328. Throughput: 0: 49406.3. Samples: 61998720. Policy #0 lag: (min: 0.0, avg: 16.2, max: 33.0) [2023-03-09 10:53:48,903][118949] Avg episode reward: [(0, '54.229')] [2023-03-09 10:53:49,315][119383] Updated weights for policy 0, policy_version 137221 (0.0020) [2023-03-09 10:53:50,132][119383] Updated weights for policy 0, policy_version 137231 (0.0021) [2023-03-09 10:53:50,954][119383] Updated weights for policy 0, policy_version 137241 (0.0023) [2023-03-09 10:53:51,828][119383] Updated weights for policy 0, policy_version 137251 (0.0022) [2023-03-09 10:53:52,636][119383] Updated weights for policy 0, policy_version 137261 (0.0026) [2023-03-09 10:53:53,039][119240] Signal inference workers to stop experience collection... (6050 times) [2023-03-09 10:53:53,041][119240] Signal inference workers to resume experience collection... (6050 times) [2023-03-09 10:53:53,087][119383] InferenceWorker_p0-w0: stopping experience collection (6050 times) [2023-03-09 10:53:53,088][119383] InferenceWorker_p0-w0: resuming experience collection (6050 times) [2023-03-09 10:53:53,460][119383] Updated weights for policy 0, policy_version 137271 (0.0013) [2023-03-09 10:53:53,902][118949] Fps is (10 sec: 199877.2, 60 sec: 197699.8, 300 sec: 196441.2). Total num frames: 2249146368. Throughput: 0: 49361.0. Samples: 62293568. Policy #0 lag: (min: 0.0, avg: 16.2, max: 33.0) [2023-03-09 10:53:53,904][118949] Avg episode reward: [(0, '55.604')] [2023-03-09 10:53:54,306][119383] Updated weights for policy 0, policy_version 137282 (0.0016) [2023-03-09 10:53:55,244][119383] Updated weights for policy 0, policy_version 137292 (0.0013) [2023-03-09 10:53:56,053][119383] Updated weights for policy 0, policy_version 137302 (0.0028) [2023-03-09 10:53:56,708][119383] Updated weights for policy 0, policy_version 137312 (0.0024) [2023-03-09 10:53:57,786][119383] Updated weights for policy 0, policy_version 137323 (0.0017) [2023-03-09 10:53:58,640][119383] Updated weights for policy 0, policy_version 137333 (0.0026) [2023-03-09 10:53:58,902][118949] Fps is (10 sec: 198243.0, 60 sec: 197973.5, 300 sec: 196552.6). Total num frames: 2250145792. Throughput: 0: 49406.3. Samples: 62590368. Policy #0 lag: (min: 0.0, avg: 16.2, max: 33.0) [2023-03-09 10:53:58,904][118949] Avg episode reward: [(0, '56.723')] [2023-03-09 10:53:59,264][119383] Updated weights for policy 0, policy_version 137343 (0.0022) [2023-03-09 10:54:00,263][119383] Updated weights for policy 0, policy_version 137353 (0.0016) [2023-03-09 10:54:01,045][119383] Updated weights for policy 0, policy_version 137363 (0.0013) [2023-03-09 10:54:01,787][119383] Updated weights for policy 0, policy_version 137373 (0.0041) [2023-03-09 10:54:02,774][119383] Updated weights for policy 0, policy_version 137383 (0.0015) [2023-03-09 10:54:03,594][119383] Updated weights for policy 0, policy_version 137393 (0.0019) [2023-03-09 10:54:03,902][118949] Fps is (10 sec: 196609.9, 60 sec: 197426.0, 300 sec: 196607.7). Total num frames: 2251112448. Throughput: 0: 49452.1. Samples: 62739840. Policy #0 lag: (min: 1.0, avg: 18.4, max: 32.0) [2023-03-09 10:54:03,905][118949] Avg episode reward: [(0, '53.814')] [2023-03-09 10:54:04,278][119383] Updated weights for policy 0, policy_version 137403 (0.0023) [2023-03-09 10:54:05,272][119383] Updated weights for policy 0, policy_version 137413 (0.0018) [2023-03-09 10:54:06,012][119383] Updated weights for policy 0, policy_version 137423 (0.0013) [2023-03-09 10:54:06,683][119240] Signal inference workers to stop experience collection... (6100 times) [2023-03-09 10:54:06,686][119240] Signal inference workers to resume experience collection... (6100 times) [2023-03-09 10:54:06,751][119383] InferenceWorker_p0-w0: stopping experience collection (6100 times) [2023-03-09 10:54:06,751][119383] InferenceWorker_p0-w0: resuming experience collection (6100 times) [2023-03-09 10:54:06,871][119383] Updated weights for policy 0, policy_version 137434 (0.0019) [2023-03-09 10:54:07,810][119383] Updated weights for policy 0, policy_version 137444 (0.0023) [2023-03-09 10:54:08,597][119383] Updated weights for policy 0, policy_version 137454 (0.0021) [2023-03-09 10:54:08,902][118949] Fps is (10 sec: 193333.1, 60 sec: 196881.1, 300 sec: 196496.9). Total num frames: 2252079104. Throughput: 0: 49407.0. Samples: 63034592. Policy #0 lag: (min: 1.0, avg: 18.4, max: 32.0) [2023-03-09 10:54:08,903][118949] Avg episode reward: [(0, '55.505')] [2023-03-09 10:54:09,442][119383] Updated weights for policy 0, policy_version 137464 (0.0014) [2023-03-09 10:54:10,223][119383] Updated weights for policy 0, policy_version 137474 (0.0023) [2023-03-09 10:54:11,152][119383] Updated weights for policy 0, policy_version 137484 (0.0017) [2023-03-09 10:54:11,971][119383] Updated weights for policy 0, policy_version 137494 (0.0023) [2023-03-09 10:54:12,739][119383] Updated weights for policy 0, policy_version 137505 (0.0035) [2023-03-09 10:54:13,782][119383] Updated weights for policy 0, policy_version 137515 (0.0013) [2023-03-09 10:54:13,902][118949] Fps is (10 sec: 196613.6, 60 sec: 197154.7, 300 sec: 196608.3). Total num frames: 2253078528. Throughput: 0: 49406.8. Samples: 63331472. Policy #0 lag: (min: 1.0, avg: 18.4, max: 32.0) [2023-03-09 10:54:13,904][118949] Avg episode reward: [(0, '55.617')] [2023-03-09 10:54:14,571][119383] Updated weights for policy 0, policy_version 137525 (0.0032) [2023-03-09 10:54:15,269][119383] Updated weights for policy 0, policy_version 137535 (0.0026) [2023-03-09 10:54:16,198][119383] Updated weights for policy 0, policy_version 137545 (0.0017) [2023-03-09 10:54:16,999][119383] Updated weights for policy 0, policy_version 137555 (0.0018) [2023-03-09 10:54:17,736][119383] Updated weights for policy 0, policy_version 137565 (0.0016) [2023-03-09 10:54:18,719][119383] Updated weights for policy 0, policy_version 137575 (0.0024) [2023-03-09 10:54:18,902][118949] Fps is (10 sec: 198248.0, 60 sec: 197428.6, 300 sec: 196663.6). Total num frames: 2254061568. Throughput: 0: 49361.3. Samples: 63476816. Policy #0 lag: (min: 1.0, avg: 18.4, max: 32.0) [2023-03-09 10:54:18,903][118949] Avg episode reward: [(0, '55.605')] [2023-03-09 10:54:19,166][119240] Signal inference workers to stop experience collection... (6150 times) [2023-03-09 10:54:19,168][119240] Signal inference workers to resume experience collection... (6150 times) [2023-03-09 10:54:19,248][119383] InferenceWorker_p0-w0: stopping experience collection (6150 times) [2023-03-09 10:54:19,249][119383] InferenceWorker_p0-w0: resuming experience collection (6150 times) [2023-03-09 10:54:19,538][119383] Updated weights for policy 0, policy_version 137585 (0.0016) [2023-03-09 10:54:20,363][119383] Updated weights for policy 0, policy_version 137596 (0.0016) [2023-03-09 10:54:21,335][119383] Updated weights for policy 0, policy_version 137606 (0.0022) [2023-03-09 10:54:22,180][119383] Updated weights for policy 0, policy_version 137617 (0.0017) [2023-03-09 10:54:22,974][119383] Updated weights for policy 0, policy_version 137627 (0.0017) [2023-03-09 10:54:23,850][119383] Updated weights for policy 0, policy_version 137637 (0.0019) [2023-03-09 10:54:23,902][118949] Fps is (10 sec: 196608.0, 60 sec: 197427.4, 300 sec: 196719.0). Total num frames: 2255044608. Throughput: 0: 49363.1. Samples: 63773744. Policy #0 lag: (min: 1.0, avg: 18.4, max: 32.0) [2023-03-09 10:54:23,903][118949] Avg episode reward: [(0, '55.997')] [2023-03-09 10:54:24,622][119383] Updated weights for policy 0, policy_version 137647 (0.0017) [2023-03-09 10:54:25,470][119383] Updated weights for policy 0, policy_version 137657 (0.0028) [2023-03-09 10:54:26,318][119383] Updated weights for policy 0, policy_version 137667 (0.0021) [2023-03-09 10:54:27,220][119383] Updated weights for policy 0, policy_version 137678 (0.0013) [2023-03-09 10:54:28,077][119383] Updated weights for policy 0, policy_version 137688 (0.0016) [2023-03-09 10:54:28,902][118949] Fps is (10 sec: 198238.6, 60 sec: 197699.0, 300 sec: 196774.4). Total num frames: 2256044032. Throughput: 0: 49272.6. Samples: 64068608. Policy #0 lag: (min: 1.0, avg: 18.4, max: 32.0) [2023-03-09 10:54:28,904][118949] Avg episode reward: [(0, '54.012')] [2023-03-09 10:54:29,015][119383] Updated weights for policy 0, policy_version 137699 (0.0013) [2023-03-09 10:54:29,863][119383] Updated weights for policy 0, policy_version 137709 (0.0029) [2023-03-09 10:54:30,665][119383] Updated weights for policy 0, policy_version 137719 (0.0020) [2023-03-09 10:54:30,715][119240] Signal inference workers to stop experience collection... (6200 times) [2023-03-09 10:54:30,716][119240] Signal inference workers to resume experience collection... (6200 times) [2023-03-09 10:54:30,787][119383] InferenceWorker_p0-w0: stopping experience collection (6200 times) [2023-03-09 10:54:30,787][119383] InferenceWorker_p0-w0: resuming experience collection (6200 times) [2023-03-09 10:54:31,330][119383] Updated weights for policy 0, policy_version 137729 (0.0028) [2023-03-09 10:54:32,375][119383] Updated weights for policy 0, policy_version 137739 (0.0018) [2023-03-09 10:54:33,112][119383] Updated weights for policy 0, policy_version 137749 (0.0028) [2023-03-09 10:54:33,890][119383] Updated weights for policy 0, policy_version 137760 (0.0024) [2023-03-09 10:54:33,902][118949] Fps is (10 sec: 201517.9, 60 sec: 198245.9, 300 sec: 196941.2). Total num frames: 2257059840. Throughput: 0: 49319.0. Samples: 64218096. Policy #0 lag: (min: 1.0, avg: 18.4, max: 32.0) [2023-03-09 10:54:33,936][118949] Avg episode reward: [(0, '56.128')] [2023-03-09 10:54:34,903][119383] Updated weights for policy 0, policy_version 137770 (0.0016) [2023-03-09 10:54:35,700][119383] Updated weights for policy 0, policy_version 137780 (0.0017) [2023-03-09 10:54:36,460][119383] Updated weights for policy 0, policy_version 137790 (0.0026) [2023-03-09 10:54:37,379][119383] Updated weights for policy 0, policy_version 137800 (0.0016) [2023-03-09 10:54:38,204][119383] Updated weights for policy 0, policy_version 137810 (0.0024) [2023-03-09 10:54:38,902][118949] Fps is (10 sec: 198243.2, 60 sec: 197971.5, 300 sec: 196885.3). Total num frames: 2258026496. Throughput: 0: 49364.2. Samples: 64514960. Policy #0 lag: (min: 1.0, avg: 18.4, max: 32.0) [2023-03-09 10:54:38,905][118949] Avg episode reward: [(0, '56.973')] [2023-03-09 10:54:39,027][119383] Updated weights for policy 0, policy_version 137821 (0.0039) [2023-03-09 10:54:40,044][119383] Updated weights for policy 0, policy_version 137831 (0.0019) [2023-03-09 10:54:40,884][119383] Updated weights for policy 0, policy_version 137841 (0.0022) [2023-03-09 10:54:41,603][119240] Signal inference workers to stop experience collection... (6250 times) [2023-03-09 10:54:41,606][119240] Signal inference workers to resume experience collection... (6250 times) [2023-03-09 10:54:41,639][119383] Updated weights for policy 0, policy_version 137851 (0.0019) [2023-03-09 10:54:41,676][119383] InferenceWorker_p0-w0: stopping experience collection (6250 times) [2023-03-09 10:54:41,677][119383] InferenceWorker_p0-w0: resuming experience collection (6250 times) [2023-03-09 10:54:42,574][119383] Updated weights for policy 0, policy_version 137861 (0.0017) [2023-03-09 10:54:43,368][119383] Updated weights for policy 0, policy_version 137871 (0.0014) [2023-03-09 10:54:43,902][118949] Fps is (10 sec: 191692.4, 60 sec: 197153.2, 300 sec: 196663.3). Total num frames: 2258976768. Throughput: 0: 49228.5. Samples: 64805664. Policy #0 lag: (min: 1.0, avg: 18.4, max: 32.0) [2023-03-09 10:54:43,904][118949] Avg episode reward: [(0, '55.801')] [2023-03-09 10:54:44,221][119383] Updated weights for policy 0, policy_version 137881 (0.0020) [2023-03-09 10:54:45,076][119383] Updated weights for policy 0, policy_version 137891 (0.0017) [2023-03-09 10:54:45,934][119383] Updated weights for policy 0, policy_version 137901 (0.0016) [2023-03-09 10:54:46,754][119383] Updated weights for policy 0, policy_version 137911 (0.0016) [2023-03-09 10:54:47,416][119383] Updated weights for policy 0, policy_version 137921 (0.0028) [2023-03-09 10:54:48,422][119383] Updated weights for policy 0, policy_version 137931 (0.0022) [2023-03-09 10:54:48,902][118949] Fps is (10 sec: 191699.8, 60 sec: 196334.3, 300 sec: 196663.5). Total num frames: 2259943424. Throughput: 0: 49135.9. Samples: 64950944. Policy #0 lag: (min: 1.0, avg: 18.4, max: 32.0) [2023-03-09 10:54:48,904][118949] Avg episode reward: [(0, '55.754')] [2023-03-09 10:54:49,271][119383] Updated weights for policy 0, policy_version 137941 (0.0013) [2023-03-09 10:54:49,995][119383] Updated weights for policy 0, policy_version 137951 (0.0019) [2023-03-09 10:54:50,896][119383] Updated weights for policy 0, policy_version 137961 (0.0017) [2023-03-09 10:54:51,760][119383] Updated weights for policy 0, policy_version 137971 (0.0017) [2023-03-09 10:54:52,017][119240] Signal inference workers to stop experience collection... (6300 times) [2023-03-09 10:54:52,018][119240] Signal inference workers to resume experience collection... (6300 times) [2023-03-09 10:54:52,086][119383] InferenceWorker_p0-w0: stopping experience collection (6300 times) [2023-03-09 10:54:52,086][119383] InferenceWorker_p0-w0: resuming experience collection (6300 times) [2023-03-09 10:54:52,478][119383] Updated weights for policy 0, policy_version 137981 (0.0016) [2023-03-09 10:54:53,479][119383] Updated weights for policy 0, policy_version 137991 (0.0013) [2023-03-09 10:54:53,902][118949] Fps is (10 sec: 194974.8, 60 sec: 196336.1, 300 sec: 196663.7). Total num frames: 2260926464. Throughput: 0: 49091.5. Samples: 65243712. Policy #0 lag: (min: 1.0, avg: 18.4, max: 32.0) [2023-03-09 10:54:53,903][118949] Avg episode reward: [(0, '55.374')] [2023-03-09 10:54:54,253][119383] Updated weights for policy 0, policy_version 138001 (0.0014) [2023-03-09 10:54:55,067][119383] Updated weights for policy 0, policy_version 138011 (0.0017) [2023-03-09 10:54:55,971][119383] Updated weights for policy 0, policy_version 138021 (0.0018) [2023-03-09 10:54:56,794][119383] Updated weights for policy 0, policy_version 138031 (0.0013) [2023-03-09 10:54:57,580][119383] Updated weights for policy 0, policy_version 138041 (0.0020) [2023-03-09 10:54:58,476][119383] Updated weights for policy 0, policy_version 138051 (0.0016) [2023-03-09 10:54:58,902][118949] Fps is (10 sec: 196607.5, 60 sec: 196061.7, 300 sec: 196663.5). Total num frames: 2261909504. Throughput: 0: 49001.1. Samples: 65536528. Policy #0 lag: (min: 1.0, avg: 18.4, max: 32.0) [2023-03-09 10:54:58,904][118949] Avg episode reward: [(0, '54.363')] [2023-03-09 10:54:59,368][119383] Updated weights for policy 0, policy_version 138061 (0.0020) [2023-03-09 10:55:00,157][119383] Updated weights for policy 0, policy_version 138071 (0.0022) [2023-03-09 10:55:00,813][119383] Updated weights for policy 0, policy_version 138081 (0.0023) [2023-03-09 10:55:01,874][119383] Updated weights for policy 0, policy_version 138091 (0.0019) [2023-03-09 10:55:02,682][119383] Updated weights for policy 0, policy_version 138101 (0.0025) [2023-03-09 10:55:03,394][119383] Updated weights for policy 0, policy_version 138111 (0.0020) [2023-03-09 10:55:03,902][118949] Fps is (10 sec: 194971.8, 60 sec: 196063.1, 300 sec: 196608.0). Total num frames: 2262876160. Throughput: 0: 49047.1. Samples: 65683936. Policy #0 lag: (min: 1.0, avg: 18.4, max: 32.0) [2023-03-09 10:55:03,903][118949] Avg episode reward: [(0, '52.162')] [2023-03-09 10:55:04,166][119240] Signal inference workers to stop experience collection... (6350 times) [2023-03-09 10:55:04,169][119240] Signal inference workers to resume experience collection... (6350 times) [2023-03-09 10:55:04,234][119383] InferenceWorker_p0-w0: stopping experience collection (6350 times) [2023-03-09 10:55:04,235][119383] InferenceWorker_p0-w0: resuming experience collection (6350 times) [2023-03-09 10:55:04,373][119383] Updated weights for policy 0, policy_version 138121 (0.0017) [2023-03-09 10:55:05,193][119383] Updated weights for policy 0, policy_version 138131 (0.0016) [2023-03-09 10:55:06,032][119383] Updated weights for policy 0, policy_version 138142 (0.0016) [2023-03-09 10:55:06,951][119383] Updated weights for policy 0, policy_version 138152 (0.0016) [2023-03-09 10:55:07,812][119383] Updated weights for policy 0, policy_version 138162 (0.0013) [2023-03-09 10:55:08,671][119383] Updated weights for policy 0, policy_version 138173 (0.0013) [2023-03-09 10:55:08,902][118949] Fps is (10 sec: 198245.4, 60 sec: 196880.5, 300 sec: 196774.5). Total num frames: 2263891968. Throughput: 0: 48954.5. Samples: 65976704. Policy #0 lag: (min: 1.0, avg: 16.5, max: 33.0) [2023-03-09 10:55:08,903][118949] Avg episode reward: [(0, '56.171')] [2023-03-09 10:55:09,626][119383] Updated weights for policy 0, policy_version 138183 (0.0027) [2023-03-09 10:55:10,432][119383] Updated weights for policy 0, policy_version 138193 (0.0013) [2023-03-09 10:55:11,175][119383] Updated weights for policy 0, policy_version 138203 (0.0017) [2023-03-09 10:55:12,113][119383] Updated weights for policy 0, policy_version 138213 (0.0018) [2023-03-09 10:55:12,883][119383] Updated weights for policy 0, policy_version 138223 (0.0025) [2023-03-09 10:55:13,687][119383] Updated weights for policy 0, policy_version 138233 (0.0019) [2023-03-09 10:55:13,902][118949] Fps is (10 sec: 196608.4, 60 sec: 196062.2, 300 sec: 196719.2). Total num frames: 2264842240. Throughput: 0: 48907.8. Samples: 66269440. Policy #0 lag: (min: 1.0, avg: 16.5, max: 33.0) [2023-03-09 10:55:13,903][118949] Avg episode reward: [(0, '52.763')] [2023-03-09 10:55:14,611][119383] Updated weights for policy 0, policy_version 138243 (0.0013) [2023-03-09 10:55:15,431][119240] Signal inference workers to stop experience collection... (6400 times) [2023-03-09 10:55:15,456][119240] Signal inference workers to resume experience collection... (6400 times) [2023-03-09 10:55:15,465][119383] Updated weights for policy 0, policy_version 138253 (0.0017) [2023-03-09 10:55:15,506][119383] InferenceWorker_p0-w0: stopping experience collection (6400 times) [2023-03-09 10:55:15,506][119383] InferenceWorker_p0-w0: resuming experience collection (6400 times) [2023-03-09 10:55:16,251][119383] Updated weights for policy 0, policy_version 138263 (0.0019) [2023-03-09 10:55:16,960][119383] Updated weights for policy 0, policy_version 138273 (0.0016) [2023-03-09 10:55:18,018][119383] Updated weights for policy 0, policy_version 138283 (0.0015) [2023-03-09 10:55:18,823][119383] Updated weights for policy 0, policy_version 138293 (0.0017) [2023-03-09 10:55:18,902][118949] Fps is (10 sec: 191696.8, 60 sec: 195788.6, 300 sec: 196608.1). Total num frames: 2265808896. Throughput: 0: 48817.1. Samples: 66414848. Policy #0 lag: (min: 1.0, avg: 16.5, max: 33.0) [2023-03-09 10:55:18,903][118949] Avg episode reward: [(0, '53.732')] [2023-03-09 10:55:19,539][119383] Updated weights for policy 0, policy_version 138303 (0.0013) [2023-03-09 10:55:20,458][119383] Updated weights for policy 0, policy_version 138313 (0.0013) [2023-03-09 10:55:21,334][119383] Updated weights for policy 0, policy_version 138323 (0.0021) [2023-03-09 10:55:22,112][119383] Updated weights for policy 0, policy_version 138333 (0.0031) [2023-03-09 10:55:23,012][119383] Updated weights for policy 0, policy_version 138343 (0.0017) [2023-03-09 10:55:23,902][118949] Fps is (10 sec: 193328.7, 60 sec: 195515.7, 300 sec: 196441.3). Total num frames: 2266775552. Throughput: 0: 48725.8. Samples: 66707600. Policy #0 lag: (min: 1.0, avg: 16.5, max: 33.0) [2023-03-09 10:55:23,903][118949] Avg episode reward: [(0, '56.759')] [2023-03-09 10:55:23,912][119383] Updated weights for policy 0, policy_version 138353 (0.0016) [2023-03-09 10:55:23,952][119240] Saving /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000138354_2266791936.pth... [2023-03-09 10:55:24,021][119240] Removing /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000135475_2219622400.pth [2023-03-09 10:55:24,618][119240] Signal inference workers to stop experience collection... (6450 times) [2023-03-09 10:55:24,620][119240] Signal inference workers to resume experience collection... (6450 times) [2023-03-09 10:55:24,649][119383] Updated weights for policy 0, policy_version 138363 (0.0013) [2023-03-09 10:55:24,689][119383] InferenceWorker_p0-w0: stopping experience collection (6450 times) [2023-03-09 10:55:24,689][119383] InferenceWorker_p0-w0: resuming experience collection (6450 times) [2023-03-09 10:55:25,505][119383] Updated weights for policy 0, policy_version 138373 (0.0020) [2023-03-09 10:55:26,351][119383] Updated weights for policy 0, policy_version 138383 (0.0018) [2023-03-09 10:55:27,138][119383] Updated weights for policy 0, policy_version 138393 (0.0013) [2023-03-09 10:55:28,062][119383] Updated weights for policy 0, policy_version 138403 (0.0014) [2023-03-09 10:55:28,894][119383] Updated weights for policy 0, policy_version 138413 (0.0013) [2023-03-09 10:55:28,902][118949] Fps is (10 sec: 194964.4, 60 sec: 195242.9, 300 sec: 196496.9). Total num frames: 2267758592. Throughput: 0: 48771.7. Samples: 67000384. Policy #0 lag: (min: 1.0, avg: 16.5, max: 33.0) [2023-03-09 10:55:28,904][118949] Avg episode reward: [(0, '54.048')] [2023-03-09 10:55:29,711][119383] Updated weights for policy 0, policy_version 138423 (0.0032) [2023-03-09 10:55:30,374][119383] Updated weights for policy 0, policy_version 138433 (0.0016) [2023-03-09 10:55:31,464][119383] Updated weights for policy 0, policy_version 138443 (0.0019) [2023-03-09 10:55:32,298][119383] Updated weights for policy 0, policy_version 138453 (0.0020) [2023-03-09 10:55:32,964][119383] Updated weights for policy 0, policy_version 138463 (0.0021) [2023-03-09 10:55:33,694][119240] Signal inference workers to stop experience collection... (6500 times) [2023-03-09 10:55:33,697][119240] Signal inference workers to resume experience collection... (6500 times) [2023-03-09 10:55:33,768][119383] InferenceWorker_p0-w0: stopping experience collection (6500 times) [2023-03-09 10:55:33,768][119383] InferenceWorker_p0-w0: resuming experience collection (6500 times) [2023-03-09 10:55:33,897][119383] Updated weights for policy 0, policy_version 138473 (0.0016) [2023-03-09 10:55:33,903][118949] Fps is (10 sec: 196597.3, 60 sec: 194695.6, 300 sec: 196552.0). Total num frames: 2268741632. Throughput: 0: 48772.8. Samples: 67145744. Policy #0 lag: (min: 1.0, avg: 16.5, max: 33.0) [2023-03-09 10:55:33,943][118949] Avg episode reward: [(0, '53.971')] [2023-03-09 10:55:34,715][119383] Updated weights for policy 0, policy_version 138483 (0.0013) [2023-03-09 10:55:35,497][119383] Updated weights for policy 0, policy_version 138493 (0.0013) [2023-03-09 10:55:36,472][119383] Updated weights for policy 0, policy_version 138503 (0.0016) [2023-03-09 10:55:37,302][119383] Updated weights for policy 0, policy_version 138513 (0.0017) [2023-03-09 10:55:38,065][119383] Updated weights for policy 0, policy_version 138523 (0.0017) [2023-03-09 10:55:38,902][118949] Fps is (10 sec: 194970.2, 60 sec: 194697.4, 300 sec: 196552.5). Total num frames: 2269708288. Throughput: 0: 48817.3. Samples: 67440496. Policy #0 lag: (min: 1.0, avg: 16.5, max: 33.0) [2023-03-09 10:55:38,904][118949] Avg episode reward: [(0, '56.918')] [2023-03-09 10:55:38,969][119383] Updated weights for policy 0, policy_version 138533 (0.0021) [2023-03-09 10:55:39,835][119383] Updated weights for policy 0, policy_version 138544 (0.0019) [2023-03-09 10:55:40,666][119383] Updated weights for policy 0, policy_version 138554 (0.0014) [2023-03-09 10:55:41,554][119383] Updated weights for policy 0, policy_version 138564 (0.0013) [2023-03-09 10:55:42,393][119383] Updated weights for policy 0, policy_version 138574 (0.0015) [2023-03-09 10:55:43,048][119240] Signal inference workers to stop experience collection... (6550 times) [2023-03-09 10:55:43,049][119240] Signal inference workers to resume experience collection... (6550 times) [2023-03-09 10:55:43,127][119383] InferenceWorker_p0-w0: stopping experience collection (6550 times) [2023-03-09 10:55:43,127][119383] InferenceWorker_p0-w0: resuming experience collection (6550 times) [2023-03-09 10:55:43,219][119383] Updated weights for policy 0, policy_version 138584 (0.0037) [2023-03-09 10:55:43,902][118949] Fps is (10 sec: 196620.2, 60 sec: 195516.9, 300 sec: 196608.0). Total num frames: 2270707712. Throughput: 0: 48771.0. Samples: 67731216. Policy #0 lag: (min: 1.0, avg: 16.5, max: 33.0) [2023-03-09 10:55:43,903][118949] Avg episode reward: [(0, '54.585')] [2023-03-09 10:55:43,997][119383] Updated weights for policy 0, policy_version 138594 (0.0027) [2023-03-09 10:55:44,960][119383] Updated weights for policy 0, policy_version 138604 (0.0016) [2023-03-09 10:55:45,852][119383] Updated weights for policy 0, policy_version 138615 (0.0016) [2023-03-09 10:55:46,487][119383] Updated weights for policy 0, policy_version 138625 (0.0033) [2023-03-09 10:55:47,593][119383] Updated weights for policy 0, policy_version 138635 (0.0013) [2023-03-09 10:55:48,416][119383] Updated weights for policy 0, policy_version 138645 (0.0018) [2023-03-09 10:55:48,902][118949] Fps is (10 sec: 196610.3, 60 sec: 195515.8, 300 sec: 196552.4). Total num frames: 2271674368. Throughput: 0: 48770.7. Samples: 67878624. Policy #0 lag: (min: 1.0, avg: 16.5, max: 33.0) [2023-03-09 10:55:48,903][118949] Avg episode reward: [(0, '56.164')] [2023-03-09 10:55:49,091][119383] Updated weights for policy 0, policy_version 138655 (0.0020) [2023-03-09 10:55:50,172][119383] Updated weights for policy 0, policy_version 138666 (0.0016) [2023-03-09 10:55:50,929][119383] Updated weights for policy 0, policy_version 138676 (0.0031) [2023-03-09 10:55:51,687][119383] Updated weights for policy 0, policy_version 138686 (0.0031) [2023-03-09 10:55:52,529][119240] Signal inference workers to stop experience collection... (6600 times) [2023-03-09 10:55:52,555][119240] Signal inference workers to resume experience collection... (6600 times) [2023-03-09 10:55:52,607][119383] InferenceWorker_p0-w0: stopping experience collection (6600 times) [2023-03-09 10:55:52,607][119383] InferenceWorker_p0-w0: resuming experience collection (6600 times) [2023-03-09 10:55:52,609][119383] Updated weights for policy 0, policy_version 138696 (0.0017) [2023-03-09 10:55:53,575][119383] Updated weights for policy 0, policy_version 138707 (0.0013) [2023-03-09 10:55:53,902][118949] Fps is (10 sec: 193331.9, 60 sec: 195243.0, 300 sec: 196496.9). Total num frames: 2272641024. Throughput: 0: 48770.4. Samples: 68171360. Policy #0 lag: (min: 1.0, avg: 16.5, max: 33.0) [2023-03-09 10:55:53,903][118949] Avg episode reward: [(0, '52.874')] [2023-03-09 10:55:54,333][119383] Updated weights for policy 0, policy_version 138717 (0.0032) [2023-03-09 10:55:55,223][119383] Updated weights for policy 0, policy_version 138727 (0.0016) [2023-03-09 10:55:56,113][119383] Updated weights for policy 0, policy_version 138737 (0.0014) [2023-03-09 10:55:56,859][119383] Updated weights for policy 0, policy_version 138747 (0.0029) [2023-03-09 10:55:57,735][119383] Updated weights for policy 0, policy_version 138757 (0.0013) [2023-03-09 10:55:58,547][119383] Updated weights for policy 0, policy_version 138767 (0.0017) [2023-03-09 10:55:58,902][118949] Fps is (10 sec: 194970.7, 60 sec: 195243.0, 300 sec: 196441.3). Total num frames: 2273624064. Throughput: 0: 48817.7. Samples: 68466240. Policy #0 lag: (min: 1.0, avg: 16.5, max: 33.0) [2023-03-09 10:55:58,904][118949] Avg episode reward: [(0, '54.882')] [2023-03-09 10:55:59,359][119383] Updated weights for policy 0, policy_version 138777 (0.0016) [2023-03-09 10:56:00,257][119383] Updated weights for policy 0, policy_version 138787 (0.0013) [2023-03-09 10:56:01,240][119383] Updated weights for policy 0, policy_version 138799 (0.0020) [2023-03-09 10:56:02,030][119383] Updated weights for policy 0, policy_version 138809 (0.0026) [2023-03-09 10:56:02,976][119383] Updated weights for policy 0, policy_version 138819 (0.0016) [2023-03-09 10:56:03,691][119240] Signal inference workers to stop experience collection... (6650 times) [2023-03-09 10:56:03,715][119240] Signal inference workers to resume experience collection... (6650 times) [2023-03-09 10:56:03,764][119383] InferenceWorker_p0-w0: stopping experience collection (6650 times) [2023-03-09 10:56:03,765][119383] InferenceWorker_p0-w0: resuming experience collection (6650 times) [2023-03-09 10:56:03,817][119383] Updated weights for policy 0, policy_version 138829 (0.0022) [2023-03-09 10:56:03,902][118949] Fps is (10 sec: 196601.1, 60 sec: 195514.6, 300 sec: 196386.1). Total num frames: 2274607104. Throughput: 0: 48815.7. Samples: 68611568. Policy #0 lag: (min: 1.0, avg: 16.5, max: 33.0) [2023-03-09 10:56:03,904][118949] Avg episode reward: [(0, '54.056')] [2023-03-09 10:56:04,595][119383] Updated weights for policy 0, policy_version 138839 (0.0042) [2023-03-09 10:56:05,245][119383] Updated weights for policy 0, policy_version 138849 (0.0036) [2023-03-09 10:56:06,326][119383] Updated weights for policy 0, policy_version 138859 (0.0026) [2023-03-09 10:56:07,134][119383] Updated weights for policy 0, policy_version 138869 (0.0013) [2023-03-09 10:56:07,795][119383] Updated weights for policy 0, policy_version 138879 (0.0019) [2023-03-09 10:56:08,729][119383] Updated weights for policy 0, policy_version 138889 (0.0020) [2023-03-09 10:56:08,902][118949] Fps is (10 sec: 194971.7, 60 sec: 194697.4, 300 sec: 196385.9). Total num frames: 2275573760. Throughput: 0: 48907.2. Samples: 68908416. Policy #0 lag: (min: 2.0, avg: 17.4, max: 34.0) [2023-03-09 10:56:08,903][118949] Avg episode reward: [(0, '55.223')] [2023-03-09 10:56:09,582][119383] Updated weights for policy 0, policy_version 138899 (0.0027) [2023-03-09 10:56:10,323][119383] Updated weights for policy 0, policy_version 138909 (0.0018) [2023-03-09 10:56:11,259][119383] Updated weights for policy 0, policy_version 138919 (0.0030) [2023-03-09 10:56:12,043][119383] Updated weights for policy 0, policy_version 138929 (0.0013) [2023-03-09 10:56:12,883][119383] Updated weights for policy 0, policy_version 138940 (0.0013) [2023-03-09 10:56:12,927][119240] Signal inference workers to stop experience collection... (6700 times) [2023-03-09 10:56:12,944][119240] Signal inference workers to resume experience collection... (6700 times) [2023-03-09 10:56:13,003][119383] InferenceWorker_p0-w0: stopping experience collection (6700 times) [2023-03-09 10:56:13,004][119383] InferenceWorker_p0-w0: resuming experience collection (6700 times) [2023-03-09 10:56:13,855][119383] Updated weights for policy 0, policy_version 138950 (0.0021) [2023-03-09 10:56:13,903][118949] Fps is (10 sec: 196601.8, 60 sec: 195513.5, 300 sec: 196496.7). Total num frames: 2276573184. Throughput: 0: 48995.2. Samples: 69205184. Policy #0 lag: (min: 2.0, avg: 17.4, max: 34.0) [2023-03-09 10:56:13,904][118949] Avg episode reward: [(0, '55.999')] [2023-03-09 10:56:14,563][119383] Updated weights for policy 0, policy_version 138960 (0.0014) [2023-03-09 10:56:15,394][119383] Updated weights for policy 0, policy_version 138970 (0.0036) [2023-03-09 10:56:16,359][119383] Updated weights for policy 0, policy_version 138980 (0.0024) [2023-03-09 10:56:17,134][119383] Updated weights for policy 0, policy_version 138990 (0.0020) [2023-03-09 10:56:17,917][119383] Updated weights for policy 0, policy_version 139000 (0.0023) [2023-03-09 10:56:18,717][119383] Updated weights for policy 0, policy_version 139010 (0.0021) [2023-03-09 10:56:18,902][118949] Fps is (10 sec: 198241.8, 60 sec: 195788.2, 300 sec: 196497.0). Total num frames: 2277556224. Throughput: 0: 48996.7. Samples: 69350576. Policy #0 lag: (min: 2.0, avg: 17.4, max: 34.0) [2023-03-09 10:56:18,904][118949] Avg episode reward: [(0, '54.405')] [2023-03-09 10:56:19,613][119383] Updated weights for policy 0, policy_version 139020 (0.0033) [2023-03-09 10:56:20,441][119383] Updated weights for policy 0, policy_version 139030 (0.0015) [2023-03-09 10:56:21,089][119383] Updated weights for policy 0, policy_version 139040 (0.0018) [2023-03-09 10:56:22,263][119383] Updated weights for policy 0, policy_version 139051 (0.0022) [2023-03-09 10:56:23,032][119383] Updated weights for policy 0, policy_version 139061 (0.0024) [2023-03-09 10:56:23,645][119240] Signal inference workers to stop experience collection... (6750 times) [2023-03-09 10:56:23,647][119240] Signal inference workers to resume experience collection... (6750 times) [2023-03-09 10:56:23,718][119383] InferenceWorker_p0-w0: stopping experience collection (6750 times) [2023-03-09 10:56:23,718][119383] InferenceWorker_p0-w0: resuming experience collection (6750 times) [2023-03-09 10:56:23,765][119383] Updated weights for policy 0, policy_version 139072 (0.0017) [2023-03-09 10:56:23,902][118949] Fps is (10 sec: 199896.7, 60 sec: 196608.1, 300 sec: 196663.5). Total num frames: 2278572032. Throughput: 0: 49088.6. Samples: 69649472. Policy #0 lag: (min: 2.0, avg: 17.4, max: 34.0) [2023-03-09 10:56:23,903][118949] Avg episode reward: [(0, '55.477')] [2023-03-09 10:56:24,812][119383] Updated weights for policy 0, policy_version 139082 (0.0016) [2023-03-09 10:56:25,787][119383] Updated weights for policy 0, policy_version 139093 (0.0016) [2023-03-09 10:56:26,452][119383] Updated weights for policy 0, policy_version 139103 (0.0022) [2023-03-09 10:56:27,414][119383] Updated weights for policy 0, policy_version 139113 (0.0013) [2023-03-09 10:56:28,297][119383] Updated weights for policy 0, policy_version 139123 (0.0016) [2023-03-09 10:56:28,902][118949] Fps is (10 sec: 196609.3, 60 sec: 196062.4, 300 sec: 196552.6). Total num frames: 2279522304. Throughput: 0: 49043.4. Samples: 69938176. Policy #0 lag: (min: 2.0, avg: 17.4, max: 34.0) [2023-03-09 10:56:28,903][118949] Avg episode reward: [(0, '56.048')] [2023-03-09 10:56:29,051][119383] Updated weights for policy 0, policy_version 139133 (0.0013) [2023-03-09 10:56:29,954][119383] Updated weights for policy 0, policy_version 139143 (0.0021) [2023-03-09 10:56:30,759][119383] Updated weights for policy 0, policy_version 139153 (0.0015) [2023-03-09 10:56:31,608][119383] Updated weights for policy 0, policy_version 139164 (0.0018) [2023-03-09 10:56:32,516][119383] Updated weights for policy 0, policy_version 139174 (0.0020) [2023-03-09 10:56:33,242][119383] Updated weights for policy 0, policy_version 139184 (0.0013) [2023-03-09 10:56:33,530][119240] Signal inference workers to stop experience collection... (6800 times) [2023-03-09 10:56:33,531][119240] Signal inference workers to resume experience collection... (6800 times) [2023-03-09 10:56:33,594][119383] InferenceWorker_p0-w0: stopping experience collection (6800 times) [2023-03-09 10:56:33,597][119383] InferenceWorker_p0-w0: resuming experience collection (6800 times) [2023-03-09 10:56:33,902][118949] Fps is (10 sec: 194967.8, 60 sec: 196336.6, 300 sec: 196663.5). Total num frames: 2280521728. Throughput: 0: 49040.7. Samples: 70085456. Policy #0 lag: (min: 2.0, avg: 17.4, max: 34.0) [2023-03-09 10:56:33,903][118949] Avg episode reward: [(0, '56.426')] [2023-03-09 10:56:34,053][119383] Updated weights for policy 0, policy_version 139194 (0.0013) [2023-03-09 10:56:34,968][119383] Updated weights for policy 0, policy_version 139204 (0.0016) [2023-03-09 10:56:35,742][119383] Updated weights for policy 0, policy_version 139214 (0.0013) [2023-03-09 10:56:36,586][119383] Updated weights for policy 0, policy_version 139225 (0.0019) [2023-03-09 10:56:37,518][119383] Updated weights for policy 0, policy_version 139235 (0.0018) [2023-03-09 10:56:38,350][119383] Updated weights for policy 0, policy_version 139245 (0.0013) [2023-03-09 10:56:38,902][118949] Fps is (10 sec: 198246.1, 60 sec: 196608.3, 300 sec: 196552.7). Total num frames: 2281504768. Throughput: 0: 49220.4. Samples: 70386288. Policy #0 lag: (min: 2.0, avg: 17.4, max: 34.0) [2023-03-09 10:56:38,903][118949] Avg episode reward: [(0, '55.081')] [2023-03-09 10:56:39,125][119383] Updated weights for policy 0, policy_version 139255 (0.0022) [2023-03-09 10:56:39,796][119383] Updated weights for policy 0, policy_version 139265 (0.0023) [2023-03-09 10:56:40,815][119383] Updated weights for policy 0, policy_version 139275 (0.0012) [2023-03-09 10:56:41,630][119383] Updated weights for policy 0, policy_version 139285 (0.0016) [2023-03-09 10:56:41,721][119240] Signal inference workers to stop experience collection... (6850 times) [2023-03-09 10:56:41,722][119240] Signal inference workers to resume experience collection... (6850 times) [2023-03-09 10:56:41,771][119383] InferenceWorker_p0-w0: stopping experience collection (6850 times) [2023-03-09 10:56:41,771][119383] InferenceWorker_p0-w0: resuming experience collection (6850 times) [2023-03-09 10:56:42,322][119383] Updated weights for policy 0, policy_version 139295 (0.0015) [2023-03-09 10:56:43,219][119383] Updated weights for policy 0, policy_version 139305 (0.0023) [2023-03-09 10:56:43,902][118949] Fps is (10 sec: 196610.8, 60 sec: 196335.0, 300 sec: 196608.2). Total num frames: 2282487808. Throughput: 0: 49263.4. Samples: 70683088. Policy #0 lag: (min: 2.0, avg: 17.4, max: 34.0) [2023-03-09 10:56:43,903][118949] Avg episode reward: [(0, '54.656')] [2023-03-09 10:56:44,087][119383] Updated weights for policy 0, policy_version 139315 (0.0025) [2023-03-09 10:56:44,859][119383] Updated weights for policy 0, policy_version 139325 (0.0013) [2023-03-09 10:56:45,786][119383] Updated weights for policy 0, policy_version 139335 (0.0013) [2023-03-09 10:56:46,611][119383] Updated weights for policy 0, policy_version 139345 (0.0017) [2023-03-09 10:56:47,363][119383] Updated weights for policy 0, policy_version 139355 (0.0019) [2023-03-09 10:56:48,231][119383] Updated weights for policy 0, policy_version 139365 (0.0016) [2023-03-09 10:56:48,902][118949] Fps is (10 sec: 198249.6, 60 sec: 196881.5, 300 sec: 196774.6). Total num frames: 2283487232. Throughput: 0: 49400.2. Samples: 70834560. Policy #0 lag: (min: 2.0, avg: 17.4, max: 34.0) [2023-03-09 10:56:48,903][118949] Avg episode reward: [(0, '56.001')] [2023-03-09 10:56:49,040][119383] Updated weights for policy 0, policy_version 139375 (0.0023) [2023-03-09 10:56:49,813][119383] Updated weights for policy 0, policy_version 139385 (0.0016) [2023-03-09 10:56:50,043][119240] Signal inference workers to stop experience collection... (6900 times) [2023-03-09 10:56:50,068][119240] Signal inference workers to resume experience collection... (6900 times) [2023-03-09 10:56:50,115][119383] InferenceWorker_p0-w0: stopping experience collection (6900 times) [2023-03-09 10:56:50,115][119383] InferenceWorker_p0-w0: resuming experience collection (6900 times) [2023-03-09 10:56:50,725][119383] Updated weights for policy 0, policy_version 139395 (0.0017) [2023-03-09 10:56:51,564][119383] Updated weights for policy 0, policy_version 139405 (0.0013) [2023-03-09 10:56:52,354][119383] Updated weights for policy 0, policy_version 139415 (0.0019) [2023-03-09 10:56:53,206][119383] Updated weights for policy 0, policy_version 139426 (0.0015) [2023-03-09 10:56:53,902][118949] Fps is (10 sec: 198240.8, 60 sec: 197153.1, 300 sec: 196774.6). Total num frames: 2284470272. Throughput: 0: 49307.4. Samples: 71127264. Policy #0 lag: (min: 2.0, avg: 17.4, max: 34.0) [2023-03-09 10:56:53,904][118949] Avg episode reward: [(0, '52.187')] [2023-03-09 10:56:54,198][119383] Updated weights for policy 0, policy_version 139436 (0.0016) [2023-03-09 10:56:54,973][119383] Updated weights for policy 0, policy_version 139446 (0.0013) [2023-03-09 10:56:55,670][119383] Updated weights for policy 0, policy_version 139456 (0.0027) [2023-03-09 10:56:56,686][119383] Updated weights for policy 0, policy_version 139466 (0.0043) [2023-03-09 10:56:57,451][119383] Updated weights for policy 0, policy_version 139476 (0.0016) [2023-03-09 10:56:58,184][119383] Updated weights for policy 0, policy_version 139486 (0.0013) [2023-03-09 10:56:58,902][118949] Fps is (10 sec: 196608.3, 60 sec: 197154.5, 300 sec: 196719.1). Total num frames: 2285453312. Throughput: 0: 49355.4. Samples: 71426144. Policy #0 lag: (min: 2.0, avg: 17.4, max: 34.0) [2023-03-09 10:56:58,903][118949] Avg episode reward: [(0, '53.821')] [2023-03-09 10:56:59,128][119383] Updated weights for policy 0, policy_version 139496 (0.0043) [2023-03-09 10:56:59,409][119240] Signal inference workers to stop experience collection... (6950 times) [2023-03-09 10:56:59,412][119240] Signal inference workers to resume experience collection... (6950 times) [2023-03-09 10:56:59,479][119383] InferenceWorker_p0-w0: stopping experience collection (6950 times) [2023-03-09 10:56:59,479][119383] InferenceWorker_p0-w0: resuming experience collection (6950 times) [2023-03-09 10:57:00,053][119383] Updated weights for policy 0, policy_version 139507 (0.0013) [2023-03-09 10:57:00,803][119383] Updated weights for policy 0, policy_version 139517 (0.0013) [2023-03-09 10:57:01,704][119383] Updated weights for policy 0, policy_version 139527 (0.0016) [2023-03-09 10:57:02,518][119383] Updated weights for policy 0, policy_version 139537 (0.0016) [2023-03-09 10:57:03,332][119383] Updated weights for policy 0, policy_version 139547 (0.0016) [2023-03-09 10:57:03,902][118949] Fps is (10 sec: 198247.6, 60 sec: 197427.6, 300 sec: 196774.7). Total num frames: 2286452736. Throughput: 0: 49354.6. Samples: 71571536. Policy #0 lag: (min: 2.0, avg: 17.4, max: 34.0) [2023-03-09 10:57:03,904][118949] Avg episode reward: [(0, '53.738')] [2023-03-09 10:57:04,191][119383] Updated weights for policy 0, policy_version 139557 (0.0014) [2023-03-09 10:57:04,984][119383] Updated weights for policy 0, policy_version 139567 (0.0013) [2023-03-09 10:57:05,764][119383] Updated weights for policy 0, policy_version 139577 (0.0023) [2023-03-09 10:57:06,675][119383] Updated weights for policy 0, policy_version 139587 (0.0020) [2023-03-09 10:57:07,534][119383] Updated weights for policy 0, policy_version 139597 (0.0021) [2023-03-09 10:57:08,310][119240] Signal inference workers to stop experience collection... (7000 times) [2023-03-09 10:57:08,311][119240] Signal inference workers to resume experience collection... (7000 times) [2023-03-09 10:57:08,380][119383] InferenceWorker_p0-w0: stopping experience collection (7000 times) [2023-03-09 10:57:08,380][119383] InferenceWorker_p0-w0: resuming experience collection (7000 times) [2023-03-09 10:57:08,385][119383] Updated weights for policy 0, policy_version 139608 (0.0017) [2023-03-09 10:57:08,902][118949] Fps is (10 sec: 201520.9, 60 sec: 198246.0, 300 sec: 196885.9). Total num frames: 2287468544. Throughput: 0: 49353.6. Samples: 71870384. Policy #0 lag: (min: 2.0, avg: 17.4, max: 34.0) [2023-03-09 10:57:08,903][118949] Avg episode reward: [(0, '56.177')] [2023-03-09 10:57:09,118][119383] Updated weights for policy 0, policy_version 139618 (0.0020) [2023-03-09 10:57:10,199][119383] Updated weights for policy 0, policy_version 139629 (0.0030) [2023-03-09 10:57:10,978][119383] Updated weights for policy 0, policy_version 139639 (0.0013) [2023-03-09 10:57:11,616][119383] Updated weights for policy 0, policy_version 139649 (0.0022) [2023-03-09 10:57:12,698][119383] Updated weights for policy 0, policy_version 139659 (0.0016) [2023-03-09 10:57:13,512][119383] Updated weights for policy 0, policy_version 139670 (0.0013) [2023-03-09 10:57:13,902][118949] Fps is (10 sec: 198250.2, 60 sec: 197702.3, 300 sec: 196830.2). Total num frames: 2288435200. Throughput: 0: 49488.5. Samples: 72165152. Policy #0 lag: (min: 1.0, avg: 16.1, max: 33.0) [2023-03-09 10:57:13,903][118949] Avg episode reward: [(0, '54.952')] [2023-03-09 10:57:14,211][119383] Updated weights for policy 0, policy_version 139680 (0.0016) [2023-03-09 10:57:15,237][119383] Updated weights for policy 0, policy_version 139690 (0.0013) [2023-03-09 10:57:16,057][119383] Updated weights for policy 0, policy_version 139700 (0.0026) [2023-03-09 10:57:16,787][119383] Updated weights for policy 0, policy_version 139710 (0.0018) [2023-03-09 10:57:17,687][119383] Updated weights for policy 0, policy_version 139720 (0.0016) [2023-03-09 10:57:18,612][119383] Updated weights for policy 0, policy_version 139730 (0.0024) [2023-03-09 10:57:18,902][118949] Fps is (10 sec: 193327.5, 60 sec: 197426.9, 300 sec: 196663.5). Total num frames: 2289401856. Throughput: 0: 49490.3. Samples: 72312528. Policy #0 lag: (min: 1.0, avg: 16.1, max: 33.0) [2023-03-09 10:57:18,905][118949] Avg episode reward: [(0, '54.821')] [2023-03-09 10:57:19,318][119383] Updated weights for policy 0, policy_version 139740 (0.0032) [2023-03-09 10:57:20,244][119383] Updated weights for policy 0, policy_version 139750 (0.0025) [2023-03-09 10:57:20,263][119240] Signal inference workers to stop experience collection... (7050 times) [2023-03-09 10:57:20,285][119240] Signal inference workers to resume experience collection... (7050 times) [2023-03-09 10:57:20,331][119383] InferenceWorker_p0-w0: stopping experience collection (7050 times) [2023-03-09 10:57:20,331][119383] InferenceWorker_p0-w0: resuming experience collection (7050 times) [2023-03-09 10:57:21,084][119383] Updated weights for policy 0, policy_version 139760 (0.0019) [2023-03-09 10:57:21,877][119383] Updated weights for policy 0, policy_version 139770 (0.0022) [2023-03-09 10:57:22,766][119383] Updated weights for policy 0, policy_version 139780 (0.0013) [2023-03-09 10:57:23,619][119383] Updated weights for policy 0, policy_version 139790 (0.0014) [2023-03-09 10:57:23,902][118949] Fps is (10 sec: 191687.8, 60 sec: 196334.1, 300 sec: 196552.5). Total num frames: 2290352128. Throughput: 0: 49310.8. Samples: 72605280. Policy #0 lag: (min: 1.0, avg: 16.1, max: 33.0) [2023-03-09 10:57:23,905][118949] Avg episode reward: [(0, '53.948')] [2023-03-09 10:57:23,974][119240] Saving /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000139794_2290384896.pth... [2023-03-09 10:57:24,041][119240] Removing /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000136915_2243215360.pth [2023-03-09 10:57:24,466][119383] Updated weights for policy 0, policy_version 139801 (0.0013) [2023-03-09 10:57:25,358][119383] Updated weights for policy 0, policy_version 139811 (0.0024) [2023-03-09 10:57:26,233][119383] Updated weights for policy 0, policy_version 139821 (0.0016) [2023-03-09 10:57:27,062][119383] Updated weights for policy 0, policy_version 139831 (0.0018) [2023-03-09 10:57:27,744][119383] Updated weights for policy 0, policy_version 139841 (0.0013) [2023-03-09 10:57:28,809][119383] Updated weights for policy 0, policy_version 139851 (0.0020) [2023-03-09 10:57:28,902][118949] Fps is (10 sec: 193331.7, 60 sec: 196880.7, 300 sec: 196607.8). Total num frames: 2291335168. Throughput: 0: 49220.3. Samples: 72898016. Policy #0 lag: (min: 1.0, avg: 16.1, max: 33.0) [2023-03-09 10:57:28,904][118949] Avg episode reward: [(0, '55.248')] [2023-03-09 10:57:29,301][119240] Signal inference workers to stop experience collection... (7100 times) [2023-03-09 10:57:29,326][119240] Signal inference workers to resume experience collection... (7100 times) [2023-03-09 10:57:29,366][119383] InferenceWorker_p0-w0: stopping experience collection (7100 times) [2023-03-09 10:57:29,369][119383] InferenceWorker_p0-w0: resuming experience collection (7100 times) [2023-03-09 10:57:29,641][119383] Updated weights for policy 0, policy_version 139862 (0.0016) [2023-03-09 10:57:30,304][119383] Updated weights for policy 0, policy_version 139872 (0.0022) [2023-03-09 10:57:31,281][119383] Updated weights for policy 0, policy_version 139882 (0.0013) [2023-03-09 10:57:32,121][119383] Updated weights for policy 0, policy_version 139892 (0.0017) [2023-03-09 10:57:32,869][119383] Updated weights for policy 0, policy_version 139902 (0.0025) [2023-03-09 10:57:33,750][119383] Updated weights for policy 0, policy_version 139912 (0.0018) [2023-03-09 10:57:33,902][118949] Fps is (10 sec: 198252.9, 60 sec: 196881.6, 300 sec: 196663.8). Total num frames: 2292334592. Throughput: 0: 49130.0. Samples: 73045408. Policy #0 lag: (min: 1.0, avg: 16.1, max: 33.0) [2023-03-09 10:57:33,903][118949] Avg episode reward: [(0, '55.759')] [2023-03-09 10:57:34,647][119383] Updated weights for policy 0, policy_version 139922 (0.0013) [2023-03-09 10:57:35,427][119383] Updated weights for policy 0, policy_version 139932 (0.0016) [2023-03-09 10:57:36,312][119383] Updated weights for policy 0, policy_version 139942 (0.0013) [2023-03-09 10:57:37,096][119383] Updated weights for policy 0, policy_version 139952 (0.0021) [2023-03-09 10:57:37,870][119383] Updated weights for policy 0, policy_version 139962 (0.0017) [2023-03-09 10:57:38,784][119383] Updated weights for policy 0, policy_version 139972 (0.0023) [2023-03-09 10:57:38,902][118949] Fps is (10 sec: 198251.7, 60 sec: 196881.6, 300 sec: 196608.2). Total num frames: 2293317632. Throughput: 0: 49222.0. Samples: 73342240. Policy #0 lag: (min: 1.0, avg: 16.1, max: 33.0) [2023-03-09 10:57:38,903][118949] Avg episode reward: [(0, '55.247')] [2023-03-09 10:57:39,422][119240] Signal inference workers to stop experience collection... (7150 times) [2023-03-09 10:57:39,423][119240] Signal inference workers to resume experience collection... (7150 times) [2023-03-09 10:57:39,513][119383] InferenceWorker_p0-w0: stopping experience collection (7150 times) [2023-03-09 10:57:39,514][119383] InferenceWorker_p0-w0: resuming experience collection (7150 times) [2023-03-09 10:57:39,692][119383] Updated weights for policy 0, policy_version 139983 (0.0020) [2023-03-09 10:57:40,475][119383] Updated weights for policy 0, policy_version 139993 (0.0013) [2023-03-09 10:57:41,424][119383] Updated weights for policy 0, policy_version 140003 (0.0014) [2023-03-09 10:57:42,300][119383] Updated weights for policy 0, policy_version 140013 (0.0013) [2023-03-09 10:57:43,106][119383] Updated weights for policy 0, policy_version 140023 (0.0025) [2023-03-09 10:57:43,797][119383] Updated weights for policy 0, policy_version 140033 (0.0019) [2023-03-09 10:57:43,902][118949] Fps is (10 sec: 196604.9, 60 sec: 196880.7, 300 sec: 196663.4). Total num frames: 2294300672. Throughput: 0: 49041.3. Samples: 73633008. Policy #0 lag: (min: 1.0, avg: 16.1, max: 33.0) [2023-03-09 10:57:43,903][118949] Avg episode reward: [(0, '55.151')] [2023-03-09 10:57:44,917][119383] Updated weights for policy 0, policy_version 140044 (0.0024) [2023-03-09 10:57:45,674][119383] Updated weights for policy 0, policy_version 140054 (0.0018) [2023-03-09 10:57:46,399][119383] Updated weights for policy 0, policy_version 140064 (0.0019) [2023-03-09 10:57:47,391][119383] Updated weights for policy 0, policy_version 140074 (0.0023) [2023-03-09 10:57:48,199][119383] Updated weights for policy 0, policy_version 140084 (0.0026) [2023-03-09 10:57:48,902][118949] Fps is (10 sec: 194968.3, 60 sec: 196334.7, 300 sec: 196552.6). Total num frames: 2295267328. Throughput: 0: 49041.6. Samples: 73778400. Policy #0 lag: (min: 1.0, avg: 16.1, max: 33.0) [2023-03-09 10:57:48,903][118949] Avg episode reward: [(0, '54.129')] [2023-03-09 10:57:48,994][119383] Updated weights for policy 0, policy_version 140094 (0.0014) [2023-03-09 10:57:49,780][119240] Signal inference workers to stop experience collection... (7200 times) [2023-03-09 10:57:49,782][119240] Signal inference workers to resume experience collection... (7200 times) [2023-03-09 10:57:49,847][119383] InferenceWorker_p0-w0: stopping experience collection (7200 times) [2023-03-09 10:57:49,847][119383] InferenceWorker_p0-w0: resuming experience collection (7200 times) [2023-03-09 10:57:49,930][119383] Updated weights for policy 0, policy_version 140104 (0.0025) [2023-03-09 10:57:50,845][119383] Updated weights for policy 0, policy_version 140114 (0.0016) [2023-03-09 10:57:51,714][119383] Updated weights for policy 0, policy_version 140126 (0.0018) [2023-03-09 10:57:52,684][119383] Updated weights for policy 0, policy_version 140136 (0.0015) [2023-03-09 10:57:53,613][119383] Updated weights for policy 0, policy_version 140146 (0.0016) [2023-03-09 10:57:53,902][118949] Fps is (10 sec: 191689.9, 60 sec: 195788.8, 300 sec: 196441.3). Total num frames: 2296217600. Throughput: 0: 48772.4. Samples: 74065152. Policy #0 lag: (min: 1.0, avg: 16.1, max: 33.0) [2023-03-09 10:57:53,904][118949] Avg episode reward: [(0, '55.828')] [2023-03-09 10:57:54,379][119383] Updated weights for policy 0, policy_version 140156 (0.0013) [2023-03-09 10:57:55,270][119383] Updated weights for policy 0, policy_version 140166 (0.0016) [2023-03-09 10:57:56,016][119383] Updated weights for policy 0, policy_version 140176 (0.0013) [2023-03-09 10:57:56,865][119383] Updated weights for policy 0, policy_version 140186 (0.0028) [2023-03-09 10:57:57,740][119383] Updated weights for policy 0, policy_version 140196 (0.0022) [2023-03-09 10:57:58,490][119240] Signal inference workers to stop experience collection... (7250 times) [2023-03-09 10:57:58,508][119240] Signal inference workers to resume experience collection... (7250 times) [2023-03-09 10:57:58,535][119383] InferenceWorker_p0-w0: stopping experience collection (7250 times) [2023-03-09 10:57:58,536][119383] InferenceWorker_p0-w0: resuming experience collection (7250 times) [2023-03-09 10:57:58,577][119383] Updated weights for policy 0, policy_version 140206 (0.0020) [2023-03-09 10:57:58,902][118949] Fps is (10 sec: 191693.9, 60 sec: 195515.7, 300 sec: 196330.3). Total num frames: 2297184256. Throughput: 0: 48772.0. Samples: 74359888. Policy #0 lag: (min: 1.0, avg: 16.1, max: 33.0) [2023-03-09 10:57:58,904][118949] Avg episode reward: [(0, '54.835')] [2023-03-09 10:57:59,433][119383] Updated weights for policy 0, policy_version 140216 (0.0037) [2023-03-09 10:58:00,165][119383] Updated weights for policy 0, policy_version 140226 (0.0027) [2023-03-09 10:58:01,144][119383] Updated weights for policy 0, policy_version 140236 (0.0022) [2023-03-09 10:58:01,877][119383] Updated weights for policy 0, policy_version 140246 (0.0016) [2023-03-09 10:58:02,660][119383] Updated weights for policy 0, policy_version 140256 (0.0020) [2023-03-09 10:58:03,603][119383] Updated weights for policy 0, policy_version 140266 (0.0016) [2023-03-09 10:58:03,902][118949] Fps is (10 sec: 194969.5, 60 sec: 195242.5, 300 sec: 196274.6). Total num frames: 2298167296. Throughput: 0: 48727.1. Samples: 74505248. Policy #0 lag: (min: 1.0, avg: 16.1, max: 33.0) [2023-03-09 10:58:03,904][118949] Avg episode reward: [(0, '56.316')] [2023-03-09 10:58:04,424][119383] Updated weights for policy 0, policy_version 140276 (0.0030) [2023-03-09 10:58:05,187][119383] Updated weights for policy 0, policy_version 140286 (0.0016) [2023-03-09 10:58:06,089][119383] Updated weights for policy 0, policy_version 140296 (0.0027) [2023-03-09 10:58:06,953][119383] Updated weights for policy 0, policy_version 140306 (0.0017) [2023-03-09 10:58:07,806][119383] Updated weights for policy 0, policy_version 140317 (0.0023) [2023-03-09 10:58:07,888][119240] Signal inference workers to stop experience collection... (7300 times) [2023-03-09 10:58:07,891][119240] Signal inference workers to resume experience collection... (7300 times) [2023-03-09 10:58:07,931][119383] InferenceWorker_p0-w0: stopping experience collection (7300 times) [2023-03-09 10:58:07,974][119383] InferenceWorker_p0-w0: resuming experience collection (7300 times) [2023-03-09 10:58:08,700][119383] Updated weights for policy 0, policy_version 140327 (0.0022) [2023-03-09 10:58:08,902][118949] Fps is (10 sec: 196604.7, 60 sec: 194696.3, 300 sec: 196274.8). Total num frames: 2299150336. Throughput: 0: 48774.5. Samples: 74800128. Policy #0 lag: (min: 1.0, avg: 16.1, max: 33.0) [2023-03-09 10:58:08,903][118949] Avg episode reward: [(0, '57.592')] [2023-03-09 10:58:09,602][119383] Updated weights for policy 0, policy_version 140337 (0.0025) [2023-03-09 10:58:10,341][119383] Updated weights for policy 0, policy_version 140347 (0.0017) [2023-03-09 10:58:11,165][119383] Updated weights for policy 0, policy_version 140357 (0.0015) [2023-03-09 10:58:11,948][119383] Updated weights for policy 0, policy_version 140367 (0.0016) [2023-03-09 10:58:12,784][119383] Updated weights for policy 0, policy_version 140377 (0.0013) [2023-03-09 10:58:13,629][119383] Updated weights for policy 0, policy_version 140387 (0.0013) [2023-03-09 10:58:13,902][118949] Fps is (10 sec: 196611.3, 60 sec: 194969.3, 300 sec: 196330.5). Total num frames: 2300133376. Throughput: 0: 48910.4. Samples: 75098976. Policy #0 lag: (min: 1.0, avg: 17.5, max: 33.0) [2023-03-09 10:58:13,903][118949] Avg episode reward: [(0, '55.481')] [2023-03-09 10:58:14,517][119383] Updated weights for policy 0, policy_version 140397 (0.0014) [2023-03-09 10:58:15,741][119383] Updated weights for policy 0, policy_version 140409 (0.0020) [2023-03-09 10:58:16,595][119383] Updated weights for policy 0, policy_version 140419 (0.0013) [2023-03-09 10:58:17,513][119383] Updated weights for policy 0, policy_version 140429 (0.0023) [2023-03-09 10:58:18,275][119383] Updated weights for policy 0, policy_version 140439 (0.0032) [2023-03-09 10:58:18,368][119240] Signal inference workers to stop experience collection... (7350 times) [2023-03-09 10:58:18,369][119240] Signal inference workers to resume experience collection... (7350 times) [2023-03-09 10:58:18,436][119383] InferenceWorker_p0-w0: stopping experience collection (7350 times) [2023-03-09 10:58:18,436][119383] InferenceWorker_p0-w0: resuming experience collection (7350 times) [2023-03-09 10:58:18,902][118949] Fps is (10 sec: 194967.4, 60 sec: 194969.6, 300 sec: 196274.7). Total num frames: 2301100032. Throughput: 0: 48568.2. Samples: 75230992. Policy #0 lag: (min: 1.0, avg: 17.5, max: 33.0) [2023-03-09 10:58:18,904][118949] Avg episode reward: [(0, '55.438')] [2023-03-09 10:58:18,975][119383] Updated weights for policy 0, policy_version 140449 (0.0019) [2023-03-09 10:58:20,031][119383] Updated weights for policy 0, policy_version 140459 (0.0016) [2023-03-09 10:58:20,816][119383] Updated weights for policy 0, policy_version 140469 (0.0016) [2023-03-09 10:58:21,562][119383] Updated weights for policy 0, policy_version 140479 (0.0015) [2023-03-09 10:58:22,416][119383] Updated weights for policy 0, policy_version 140489 (0.0013) [2023-03-09 10:58:23,333][119383] Updated weights for policy 0, policy_version 140499 (0.0015) [2023-03-09 10:58:23,902][118949] Fps is (10 sec: 193332.0, 60 sec: 195243.4, 300 sec: 196219.2). Total num frames: 2302066688. Throughput: 0: 48523.3. Samples: 75525792. Policy #0 lag: (min: 1.0, avg: 17.5, max: 33.0) [2023-03-09 10:58:23,903][118949] Avg episode reward: [(0, '54.809')] [2023-03-09 10:58:24,044][119383] Updated weights for policy 0, policy_version 140509 (0.0030) [2023-03-09 10:58:25,016][119383] Updated weights for policy 0, policy_version 140520 (0.0013) [2023-03-09 10:58:25,975][119383] Updated weights for policy 0, policy_version 140530 (0.0013) [2023-03-09 10:58:26,705][119383] Updated weights for policy 0, policy_version 140540 (0.0013) [2023-03-09 10:58:27,615][119383] Updated weights for policy 0, policy_version 140550 (0.0019) [2023-03-09 10:58:28,404][119383] Updated weights for policy 0, policy_version 140560 (0.0018) [2023-03-09 10:58:28,902][118949] Fps is (10 sec: 193330.9, 60 sec: 194969.5, 300 sec: 196163.6). Total num frames: 2303033344. Throughput: 0: 48522.8. Samples: 75816544. Policy #0 lag: (min: 1.0, avg: 17.5, max: 33.0) [2023-03-09 10:58:28,905][118949] Avg episode reward: [(0, '56.841')] [2023-03-09 10:58:29,316][119383] Updated weights for policy 0, policy_version 140571 (0.0019) [2023-03-09 10:58:29,463][119240] Signal inference workers to stop experience collection... (7400 times) [2023-03-09 10:58:29,484][119240] Signal inference workers to resume experience collection... (7400 times) [2023-03-09 10:58:29,528][119383] InferenceWorker_p0-w0: stopping experience collection (7400 times) [2023-03-09 10:58:29,531][119383] InferenceWorker_p0-w0: resuming experience collection (7400 times) [2023-03-09 10:58:30,236][119383] Updated weights for policy 0, policy_version 140581 (0.0014) [2023-03-09 10:58:31,040][119383] Updated weights for policy 0, policy_version 140591 (0.0013) [2023-03-09 10:58:31,879][119383] Updated weights for policy 0, policy_version 140601 (0.0018) [2023-03-09 10:58:32,744][119383] Updated weights for policy 0, policy_version 140611 (0.0013) [2023-03-09 10:58:33,619][119383] Updated weights for policy 0, policy_version 140621 (0.0013) [2023-03-09 10:58:33,902][118949] Fps is (10 sec: 191694.6, 60 sec: 194150.4, 300 sec: 196052.6). Total num frames: 2303983616. Throughput: 0: 48521.7. Samples: 75961872. Policy #0 lag: (min: 1.0, avg: 17.5, max: 33.0) [2023-03-09 10:58:33,903][118949] Avg episode reward: [(0, '55.038')] [2023-03-09 10:58:34,415][119383] Updated weights for policy 0, policy_version 140631 (0.0013) [2023-03-09 10:58:35,135][119383] Updated weights for policy 0, policy_version 140641 (0.0016) [2023-03-09 10:58:36,134][119383] Updated weights for policy 0, policy_version 140651 (0.0014) [2023-03-09 10:58:36,971][119383] Updated weights for policy 0, policy_version 140661 (0.0019) [2023-03-09 10:58:37,754][119383] Updated weights for policy 0, policy_version 140671 (0.0036) [2023-03-09 10:58:38,653][119383] Updated weights for policy 0, policy_version 140681 (0.0014) [2023-03-09 10:58:38,902][118949] Fps is (10 sec: 191697.4, 60 sec: 193877.1, 300 sec: 195941.6). Total num frames: 2304950272. Throughput: 0: 48565.2. Samples: 76250576. Policy #0 lag: (min: 1.0, avg: 17.5, max: 33.0) [2023-03-09 10:58:38,903][118949] Avg episode reward: [(0, '55.877')] [2023-03-09 10:58:39,542][119383] Updated weights for policy 0, policy_version 140691 (0.0013) [2023-03-09 10:58:40,237][119240] Signal inference workers to stop experience collection... (7450 times) [2023-03-09 10:58:40,261][119240] Signal inference workers to resume experience collection... (7450 times) [2023-03-09 10:58:40,287][119383] InferenceWorker_p0-w0: stopping experience collection (7450 times) [2023-03-09 10:58:40,289][119383] Updated weights for policy 0, policy_version 140701 (0.0028) [2023-03-09 10:58:40,331][119383] InferenceWorker_p0-w0: resuming experience collection (7450 times) [2023-03-09 10:58:41,209][119383] Updated weights for policy 0, policy_version 140711 (0.0015) [2023-03-09 10:58:41,991][119383] Updated weights for policy 0, policy_version 140721 (0.0016) [2023-03-09 10:58:42,894][119383] Updated weights for policy 0, policy_version 140732 (0.0021) [2023-03-09 10:58:43,816][119383] Updated weights for policy 0, policy_version 140742 (0.0013) [2023-03-09 10:58:43,902][118949] Fps is (10 sec: 194963.0, 60 sec: 193876.7, 300 sec: 195830.2). Total num frames: 2305933312. Throughput: 0: 48564.3. Samples: 76545296. Policy #0 lag: (min: 1.0, avg: 17.5, max: 33.0) [2023-03-09 10:58:43,904][118949] Avg episode reward: [(0, '54.941')] [2023-03-09 10:58:44,607][119383] Updated weights for policy 0, policy_version 140752 (0.0013) [2023-03-09 10:58:45,539][119383] Updated weights for policy 0, policy_version 140763 (0.0013) [2023-03-09 10:58:46,430][119383] Updated weights for policy 0, policy_version 140773 (0.0013) [2023-03-09 10:58:47,166][119383] Updated weights for policy 0, policy_version 140783 (0.0019) [2023-03-09 10:58:47,990][119383] Updated weights for policy 0, policy_version 140793 (0.0015) [2023-03-09 10:58:48,902][118949] Fps is (10 sec: 196609.4, 60 sec: 194150.6, 300 sec: 195830.8). Total num frames: 2306916352. Throughput: 0: 48609.0. Samples: 76692640. Policy #0 lag: (min: 1.0, avg: 17.5, max: 33.0) [2023-03-09 10:58:48,903][118949] Avg episode reward: [(0, '55.333')] [2023-03-09 10:58:48,962][119383] Updated weights for policy 0, policy_version 140804 (0.0014) [2023-03-09 10:58:49,818][119383] Updated weights for policy 0, policy_version 140814 (0.0013) [2023-03-09 10:58:50,651][119383] Updated weights for policy 0, policy_version 140824 (0.0018) [2023-03-09 10:58:50,902][119240] Signal inference workers to stop experience collection... (7500 times) [2023-03-09 10:58:50,920][119240] Signal inference workers to resume experience collection... (7500 times) [2023-03-09 10:58:50,988][119383] InferenceWorker_p0-w0: stopping experience collection (7500 times) [2023-03-09 10:58:50,988][119383] InferenceWorker_p0-w0: resuming experience collection (7500 times) [2023-03-09 10:58:51,410][119383] Updated weights for policy 0, policy_version 140834 (0.0017) [2023-03-09 10:58:52,459][119383] Updated weights for policy 0, policy_version 140845 (0.0016) [2023-03-09 10:58:53,219][119383] Updated weights for policy 0, policy_version 140855 (0.0019) [2023-03-09 10:58:53,902][118949] Fps is (10 sec: 198247.8, 60 sec: 194969.7, 300 sec: 195830.4). Total num frames: 2307915776. Throughput: 0: 48517.2. Samples: 76983408. Policy #0 lag: (min: 1.0, avg: 17.5, max: 33.0) [2023-03-09 10:58:53,904][118949] Avg episode reward: [(0, '54.259')] [2023-03-09 10:58:53,928][119383] Updated weights for policy 0, policy_version 140865 (0.0020) [2023-03-09 10:58:54,923][119383] Updated weights for policy 0, policy_version 140875 (0.0021) [2023-03-09 10:58:55,845][119383] Updated weights for policy 0, policy_version 140886 (0.0024) [2023-03-09 10:58:56,626][119383] Updated weights for policy 0, policy_version 140897 (0.0021) [2023-03-09 10:58:57,611][119383] Updated weights for policy 0, policy_version 140907 (0.0014) [2023-03-09 10:58:58,495][119383] Updated weights for policy 0, policy_version 140917 (0.0021) [2023-03-09 10:58:58,902][118949] Fps is (10 sec: 194964.4, 60 sec: 194695.7, 300 sec: 195775.0). Total num frames: 2308866048. Throughput: 0: 48426.5. Samples: 77278176. Policy #0 lag: (min: 1.0, avg: 17.5, max: 33.0) [2023-03-09 10:58:58,904][118949] Avg episode reward: [(0, '53.270')] [2023-03-09 10:58:59,203][119383] Updated weights for policy 0, policy_version 140927 (0.0026) [2023-03-09 10:59:00,131][119383] Updated weights for policy 0, policy_version 140937 (0.0013) [2023-03-09 10:59:01,049][119383] Updated weights for policy 0, policy_version 140947 (0.0024) [2023-03-09 10:59:01,355][119240] Signal inference workers to stop experience collection... (7550 times) [2023-03-09 10:59:01,358][119240] Signal inference workers to resume experience collection... (7550 times) [2023-03-09 10:59:01,421][119383] InferenceWorker_p0-w0: stopping experience collection (7550 times) [2023-03-09 10:59:01,421][119383] InferenceWorker_p0-w0: resuming experience collection (7550 times) [2023-03-09 10:59:01,758][119383] Updated weights for policy 0, policy_version 140957 (0.0017) [2023-03-09 10:59:02,691][119383] Updated weights for policy 0, policy_version 140967 (0.0021) [2023-03-09 10:59:03,518][119383] Updated weights for policy 0, policy_version 140977 (0.0013) [2023-03-09 10:59:03,902][118949] Fps is (10 sec: 193335.6, 60 sec: 194697.4, 300 sec: 195830.5). Total num frames: 2309849088. Throughput: 0: 48723.8. Samples: 77423552. Policy #0 lag: (min: 1.0, avg: 17.5, max: 33.0) [2023-03-09 10:59:03,903][118949] Avg episode reward: [(0, '53.892')] [2023-03-09 10:59:04,366][119383] Updated weights for policy 0, policy_version 140988 (0.0020) [2023-03-09 10:59:05,273][119383] Updated weights for policy 0, policy_version 140998 (0.0018) [2023-03-09 10:59:06,077][119383] Updated weights for policy 0, policy_version 141008 (0.0023) [2023-03-09 10:59:06,892][119383] Updated weights for policy 0, policy_version 141018 (0.0023) [2023-03-09 10:59:07,797][119383] Updated weights for policy 0, policy_version 141028 (0.0013) [2023-03-09 10:59:08,629][119383] Updated weights for policy 0, policy_version 141038 (0.0015) [2023-03-09 10:59:08,902][118949] Fps is (10 sec: 194975.0, 60 sec: 194424.1, 300 sec: 195719.4). Total num frames: 2310815744. Throughput: 0: 48678.2. Samples: 77716304. Policy #0 lag: (min: 1.0, avg: 17.5, max: 33.0) [2023-03-09 10:59:08,903][118949] Avg episode reward: [(0, '55.050')] [2023-03-09 10:59:09,415][119383] Updated weights for policy 0, policy_version 141048 (0.0023) [2023-03-09 10:59:10,184][119383] Updated weights for policy 0, policy_version 141058 (0.0022) [2023-03-09 10:59:10,604][119240] Signal inference workers to stop experience collection... (7600 times) [2023-03-09 10:59:10,630][119240] Signal inference workers to resume experience collection... (7600 times) [2023-03-09 10:59:10,683][119383] InferenceWorker_p0-w0: stopping experience collection (7600 times) [2023-03-09 10:59:10,684][119383] InferenceWorker_p0-w0: resuming experience collection (7600 times) [2023-03-09 10:59:11,103][119383] Updated weights for policy 0, policy_version 141068 (0.0022) [2023-03-09 10:59:11,944][119383] Updated weights for policy 0, policy_version 141078 (0.0016) [2023-03-09 10:59:12,748][119383] Updated weights for policy 0, policy_version 141089 (0.0019) [2023-03-09 10:59:13,691][119383] Updated weights for policy 0, policy_version 141099 (0.0017) [2023-03-09 10:59:13,902][118949] Fps is (10 sec: 194963.1, 60 sec: 194422.7, 300 sec: 195719.1). Total num frames: 2311798784. Throughput: 0: 48768.6. Samples: 78011136. Policy #0 lag: (min: 1.0, avg: 17.5, max: 33.0) [2023-03-09 10:59:13,904][118949] Avg episode reward: [(0, '55.304')] [2023-03-09 10:59:14,635][119383] Updated weights for policy 0, policy_version 141110 (0.0017) [2023-03-09 10:59:15,371][119383] Updated weights for policy 0, policy_version 141120 (0.0022) [2023-03-09 10:59:16,313][119383] Updated weights for policy 0, policy_version 141130 (0.0016) [2023-03-09 10:59:17,165][119383] Updated weights for policy 0, policy_version 141140 (0.0016) [2023-03-09 10:59:17,944][119383] Updated weights for policy 0, policy_version 141150 (0.0013) [2023-03-09 10:59:18,853][119383] Updated weights for policy 0, policy_version 141160 (0.0021) [2023-03-09 10:59:18,902][118949] Fps is (10 sec: 194962.7, 60 sec: 194423.3, 300 sec: 195663.7). Total num frames: 2312765440. Throughput: 0: 48723.5. Samples: 78154448. Policy #0 lag: (min: 0.0, avg: 18.3, max: 33.0) [2023-03-09 10:59:18,904][118949] Avg episode reward: [(0, '55.339')] [2023-03-09 10:59:19,879][119383] Updated weights for policy 0, policy_version 141171 (0.0021) [2023-03-09 10:59:20,581][119383] Updated weights for policy 0, policy_version 141181 (0.0018) [2023-03-09 10:59:20,672][119240] Signal inference workers to stop experience collection... (7650 times) [2023-03-09 10:59:20,694][119240] Signal inference workers to resume experience collection... (7650 times) [2023-03-09 10:59:20,717][119383] InferenceWorker_p0-w0: stopping experience collection (7650 times) [2023-03-09 10:59:20,717][119383] InferenceWorker_p0-w0: resuming experience collection (7650 times) [2023-03-09 10:59:21,493][119383] Updated weights for policy 0, policy_version 141191 (0.0022) [2023-03-09 10:59:22,333][119383] Updated weights for policy 0, policy_version 141201 (0.0017) [2023-03-09 10:59:23,115][119383] Updated weights for policy 0, policy_version 141211 (0.0012) [2023-03-09 10:59:23,902][118949] Fps is (10 sec: 194971.4, 60 sec: 194695.9, 300 sec: 195608.4). Total num frames: 2313748480. Throughput: 0: 48860.6. Samples: 78449312. Policy #0 lag: (min: 0.0, avg: 18.3, max: 33.0) [2023-03-09 10:59:23,904][118949] Avg episode reward: [(0, '56.103')] [2023-03-09 10:59:23,910][119240] Saving /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000141220_2313748480.pth... [2023-03-09 10:59:23,953][119240] Removing /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000138354_2266791936.pth [2023-03-09 10:59:24,043][119383] Updated weights for policy 0, policy_version 141221 (0.0021) [2023-03-09 10:59:24,766][119383] Updated weights for policy 0, policy_version 141231 (0.0021) [2023-03-09 10:59:25,639][119383] Updated weights for policy 0, policy_version 141241 (0.0016) [2023-03-09 10:59:26,501][119383] Updated weights for policy 0, policy_version 141251 (0.0035) [2023-03-09 10:59:27,405][119383] Updated weights for policy 0, policy_version 141261 (0.0013) [2023-03-09 10:59:28,197][119383] Updated weights for policy 0, policy_version 141271 (0.0016) [2023-03-09 10:59:28,893][119383] Updated weights for policy 0, policy_version 141281 (0.0024) [2023-03-09 10:59:28,902][118949] Fps is (10 sec: 198246.0, 60 sec: 195242.5, 300 sec: 195552.8). Total num frames: 2314747904. Throughput: 0: 48725.7. Samples: 78737952. Policy #0 lag: (min: 0.0, avg: 18.3, max: 33.0) [2023-03-09 10:59:28,904][118949] Avg episode reward: [(0, '56.034')] [2023-03-09 10:59:30,023][119383] Updated weights for policy 0, policy_version 141292 (0.0017) [2023-03-09 10:59:30,817][119383] Updated weights for policy 0, policy_version 141302 (0.0017) [2023-03-09 10:59:31,518][119383] Updated weights for policy 0, policy_version 141312 (0.0023) [2023-03-09 10:59:32,354][119240] Signal inference workers to stop experience collection... (7700 times) [2023-03-09 10:59:32,357][119240] Signal inference workers to resume experience collection... (7700 times) [2023-03-09 10:59:32,418][119383] InferenceWorker_p0-w0: stopping experience collection (7700 times) [2023-03-09 10:59:32,420][119383] InferenceWorker_p0-w0: resuming experience collection (7700 times) [2023-03-09 10:59:32,509][119383] Updated weights for policy 0, policy_version 141322 (0.0025) [2023-03-09 10:59:33,432][119383] Updated weights for policy 0, policy_version 141333 (0.0019) [2023-03-09 10:59:33,902][118949] Fps is (10 sec: 193330.6, 60 sec: 194968.6, 300 sec: 195441.8). Total num frames: 2315681792. Throughput: 0: 48682.0. Samples: 78883344. Policy #0 lag: (min: 0.0, avg: 18.3, max: 33.0) [2023-03-09 10:59:33,904][118949] Avg episode reward: [(0, '54.285')] [2023-03-09 10:59:34,173][119383] Updated weights for policy 0, policy_version 141343 (0.0014) [2023-03-09 10:59:35,124][119383] Updated weights for policy 0, policy_version 141353 (0.0020) [2023-03-09 10:59:35,997][119383] Updated weights for policy 0, policy_version 141363 (0.0017) [2023-03-09 10:59:36,876][119383] Updated weights for policy 0, policy_version 141374 (0.0020) [2023-03-09 10:59:37,773][119383] Updated weights for policy 0, policy_version 141384 (0.0019) [2023-03-09 10:59:38,799][119383] Updated weights for policy 0, policy_version 141395 (0.0028) [2023-03-09 10:59:38,902][118949] Fps is (10 sec: 190061.1, 60 sec: 194969.8, 300 sec: 195497.5). Total num frames: 2316648448. Throughput: 0: 48681.2. Samples: 79174048. Policy #0 lag: (min: 0.0, avg: 18.3, max: 33.0) [2023-03-09 10:59:38,903][118949] Avg episode reward: [(0, '53.417')] [2023-03-09 10:59:39,499][119383] Updated weights for policy 0, policy_version 141405 (0.0023) [2023-03-09 10:59:40,379][119383] Updated weights for policy 0, policy_version 141415 (0.0018) [2023-03-09 10:59:41,252][119383] Updated weights for policy 0, policy_version 141425 (0.0013) [2023-03-09 10:59:42,089][119383] Updated weights for policy 0, policy_version 141435 (0.0022) [2023-03-09 10:59:42,955][119383] Updated weights for policy 0, policy_version 141445 (0.0016) [2023-03-09 10:59:43,752][119383] Updated weights for policy 0, policy_version 141455 (0.0021) [2023-03-09 10:59:43,902][118949] Fps is (10 sec: 193336.1, 60 sec: 194697.4, 300 sec: 195497.3). Total num frames: 2317615104. Throughput: 0: 48637.0. Samples: 79466832. Policy #0 lag: (min: 0.0, avg: 18.3, max: 33.0) [2023-03-09 10:59:43,903][118949] Avg episode reward: [(0, '55.421')] [2023-03-09 10:59:44,578][119383] Updated weights for policy 0, policy_version 141465 (0.0014) [2023-03-09 10:59:44,825][119240] Signal inference workers to stop experience collection... (7750 times) [2023-03-09 10:59:44,827][119240] Signal inference workers to resume experience collection... (7750 times) [2023-03-09 10:59:44,901][119383] InferenceWorker_p0-w0: stopping experience collection (7750 times) [2023-03-09 10:59:44,901][119383] InferenceWorker_p0-w0: resuming experience collection (7750 times) [2023-03-09 10:59:45,443][119383] Updated weights for policy 0, policy_version 141475 (0.0019) [2023-03-09 10:59:46,311][119383] Updated weights for policy 0, policy_version 141485 (0.0017) [2023-03-09 10:59:47,168][119383] Updated weights for policy 0, policy_version 141495 (0.0016) [2023-03-09 10:59:47,841][119383] Updated weights for policy 0, policy_version 141505 (0.0018) [2023-03-09 10:59:48,822][119383] Updated weights for policy 0, policy_version 141515 (0.0016) [2023-03-09 10:59:48,902][118949] Fps is (10 sec: 193328.0, 60 sec: 194422.9, 300 sec: 195441.6). Total num frames: 2318581760. Throughput: 0: 48635.2. Samples: 79612144. Policy #0 lag: (min: 0.0, avg: 18.3, max: 33.0) [2023-03-09 10:59:48,904][118949] Avg episode reward: [(0, '56.215')] [2023-03-09 10:59:49,641][119383] Updated weights for policy 0, policy_version 141525 (0.0018) [2023-03-09 10:59:50,438][119383] Updated weights for policy 0, policy_version 141535 (0.0035) [2023-03-09 10:59:51,325][119383] Updated weights for policy 0, policy_version 141545 (0.0018) [2023-03-09 10:59:52,254][119383] Updated weights for policy 0, policy_version 141555 (0.0017) [2023-03-09 10:59:52,962][119383] Updated weights for policy 0, policy_version 141565 (0.0014) [2023-03-09 10:59:53,877][119383] Updated weights for policy 0, policy_version 141576 (0.0022) [2023-03-09 10:59:53,902][118949] Fps is (10 sec: 196609.3, 60 sec: 194424.4, 300 sec: 195497.4). Total num frames: 2319581184. Throughput: 0: 48635.0. Samples: 79904880. Policy #0 lag: (min: 0.0, avg: 18.3, max: 33.0) [2023-03-09 10:59:53,903][118949] Avg episode reward: [(0, '54.529')] [2023-03-09 10:59:54,786][119383] Updated weights for policy 0, policy_version 141586 (0.0023) [2023-03-09 10:59:55,574][119383] Updated weights for policy 0, policy_version 141596 (0.0020) [2023-03-09 10:59:56,496][119383] Updated weights for policy 0, policy_version 141606 (0.0018) [2023-03-09 10:59:57,256][119383] Updated weights for policy 0, policy_version 141616 (0.0016) [2023-03-09 10:59:58,035][119383] Updated weights for policy 0, policy_version 141626 (0.0016) [2023-03-09 10:59:58,428][119240] Signal inference workers to stop experience collection... (7800 times) [2023-03-09 10:59:58,429][119240] Signal inference workers to resume experience collection... (7800 times) [2023-03-09 10:59:58,513][119383] InferenceWorker_p0-w0: stopping experience collection (7800 times) [2023-03-09 10:59:58,513][119383] InferenceWorker_p0-w0: resuming experience collection (7800 times) [2023-03-09 10:59:58,902][118949] Fps is (10 sec: 196608.4, 60 sec: 194696.9, 300 sec: 195497.1). Total num frames: 2320547840. Throughput: 0: 48543.5. Samples: 80195584. Policy #0 lag: (min: 0.0, avg: 18.3, max: 33.0) [2023-03-09 10:59:58,904][118949] Avg episode reward: [(0, '55.049')] [2023-03-09 10:59:59,094][119383] Updated weights for policy 0, policy_version 141637 (0.0025) [2023-03-09 10:59:59,891][119383] Updated weights for policy 0, policy_version 141647 (0.0020) [2023-03-09 11:00:00,697][119383] Updated weights for policy 0, policy_version 141657 (0.0017) [2023-03-09 11:00:01,560][119383] Updated weights for policy 0, policy_version 141667 (0.0027) [2023-03-09 11:00:02,424][119383] Updated weights for policy 0, policy_version 141677 (0.0013) [2023-03-09 11:00:03,332][119383] Updated weights for policy 0, policy_version 141687 (0.0013) [2023-03-09 11:00:03,902][118949] Fps is (10 sec: 196606.0, 60 sec: 194969.4, 300 sec: 195441.8). Total num frames: 2321547264. Throughput: 0: 48589.4. Samples: 80340960. Policy #0 lag: (min: 0.0, avg: 18.3, max: 33.0) [2023-03-09 11:00:03,903][118949] Avg episode reward: [(0, '55.359')] [2023-03-09 11:00:03,998][119383] Updated weights for policy 0, policy_version 141697 (0.0020) [2023-03-09 11:00:04,975][119383] Updated weights for policy 0, policy_version 141707 (0.0017) [2023-03-09 11:00:05,838][119383] Updated weights for policy 0, policy_version 141717 (0.0017) [2023-03-09 11:00:06,580][119383] Updated weights for policy 0, policy_version 141728 (0.0014) [2023-03-09 11:00:07,564][119383] Updated weights for policy 0, policy_version 141738 (0.0017) [2023-03-09 11:00:08,446][119383] Updated weights for policy 0, policy_version 141748 (0.0016) [2023-03-09 11:00:08,902][118949] Fps is (10 sec: 194967.7, 60 sec: 194695.7, 300 sec: 195441.5). Total num frames: 2322497536. Throughput: 0: 48495.7. Samples: 80631616. Policy #0 lag: (min: 0.0, avg: 18.3, max: 33.0) [2023-03-09 11:00:08,904][118949] Avg episode reward: [(0, '55.965')] [2023-03-09 11:00:09,265][119383] Updated weights for policy 0, policy_version 141759 (0.0013) [2023-03-09 11:00:10,127][119383] Updated weights for policy 0, policy_version 141769 (0.0016) [2023-03-09 11:00:11,001][119383] Updated weights for policy 0, policy_version 141779 (0.0013) [2023-03-09 11:00:11,774][119383] Updated weights for policy 0, policy_version 141789 (0.0016) [2023-03-09 11:00:12,724][119383] Updated weights for policy 0, policy_version 141799 (0.0014) [2023-03-09 11:00:13,018][119240] Signal inference workers to stop experience collection... (7850 times) [2023-03-09 11:00:13,019][119240] Signal inference workers to resume experience collection... (7850 times) [2023-03-09 11:00:13,086][119383] InferenceWorker_p0-w0: stopping experience collection (7850 times) [2023-03-09 11:00:13,086][119383] InferenceWorker_p0-w0: resuming experience collection (7850 times) [2023-03-09 11:00:13,513][119383] Updated weights for policy 0, policy_version 141809 (0.0016) [2023-03-09 11:00:13,902][118949] Fps is (10 sec: 193327.9, 60 sec: 194696.9, 300 sec: 195497.1). Total num frames: 2323480576. Throughput: 0: 48679.2. Samples: 80928512. Policy #0 lag: (min: 0.0, avg: 18.3, max: 33.0) [2023-03-09 11:00:13,904][118949] Avg episode reward: [(0, '54.915')] [2023-03-09 11:00:14,282][119383] Updated weights for policy 0, policy_version 141819 (0.0024) [2023-03-09 11:00:15,312][119383] Updated weights for policy 0, policy_version 141830 (0.0013) [2023-03-09 11:00:16,104][119383] Updated weights for policy 0, policy_version 141840 (0.0018) [2023-03-09 11:00:16,878][119383] Updated weights for policy 0, policy_version 141850 (0.0023) [2023-03-09 11:00:17,818][119383] Updated weights for policy 0, policy_version 141860 (0.0039) [2023-03-09 11:00:18,631][119383] Updated weights for policy 0, policy_version 141870 (0.0024) [2023-03-09 11:00:18,902][118949] Fps is (10 sec: 193335.2, 60 sec: 194424.4, 300 sec: 195441.7). Total num frames: 2324430848. Throughput: 0: 48678.7. Samples: 81073872. Policy #0 lag: (min: 0.0, avg: 16.8, max: 33.0) [2023-03-09 11:00:18,903][118949] Avg episode reward: [(0, '54.714')] [2023-03-09 11:00:19,508][119383] Updated weights for policy 0, policy_version 141880 (0.0017) [2023-03-09 11:00:20,216][119383] Updated weights for policy 0, policy_version 141890 (0.0027) [2023-03-09 11:00:21,188][119383] Updated weights for policy 0, policy_version 141900 (0.0014) [2023-03-09 11:00:22,052][119383] Updated weights for policy 0, policy_version 141910 (0.0018) [2023-03-09 11:00:22,804][119383] Updated weights for policy 0, policy_version 141921 (0.0016) [2023-03-09 11:00:23,434][119240] Signal inference workers to stop experience collection... (7900 times) [2023-03-09 11:00:23,455][119240] Signal inference workers to resume experience collection... (7900 times) [2023-03-09 11:00:23,482][119383] InferenceWorker_p0-w0: stopping experience collection (7900 times) [2023-03-09 11:00:23,541][119383] InferenceWorker_p0-w0: resuming experience collection (7900 times) [2023-03-09 11:00:23,829][119383] Updated weights for policy 0, policy_version 141931 (0.0026) [2023-03-09 11:00:23,902][118949] Fps is (10 sec: 193335.9, 60 sec: 194424.3, 300 sec: 195441.9). Total num frames: 2325413888. Throughput: 0: 48677.0. Samples: 81364512. Policy #0 lag: (min: 0.0, avg: 16.8, max: 33.0) [2023-03-09 11:00:23,903][118949] Avg episode reward: [(0, '55.493')] [2023-03-09 11:00:24,769][119383] Updated weights for policy 0, policy_version 141942 (0.0020) [2023-03-09 11:00:25,433][119383] Updated weights for policy 0, policy_version 141952 (0.0019) [2023-03-09 11:00:26,476][119383] Updated weights for policy 0, policy_version 141963 (0.0013) [2023-03-09 11:00:27,367][119383] Updated weights for policy 0, policy_version 141973 (0.0031) [2023-03-09 11:00:28,160][119383] Updated weights for policy 0, policy_version 141983 (0.0016) [2023-03-09 11:00:28,902][118949] Fps is (10 sec: 193326.3, 60 sec: 193604.5, 300 sec: 195330.8). Total num frames: 2326364160. Throughput: 0: 48629.8. Samples: 81655184. Policy #0 lag: (min: 0.0, avg: 16.8, max: 33.0) [2023-03-09 11:00:28,904][118949] Avg episode reward: [(0, '54.093')] [2023-03-09 11:00:29,020][119383] Updated weights for policy 0, policy_version 141993 (0.0019) [2023-03-09 11:00:29,946][119383] Updated weights for policy 0, policy_version 142003 (0.0018) [2023-03-09 11:00:30,707][119383] Updated weights for policy 0, policy_version 142013 (0.0020) [2023-03-09 11:00:31,458][119240] Signal inference workers to stop experience collection... (7950 times) [2023-03-09 11:00:31,460][119240] Signal inference workers to resume experience collection... (7950 times) [2023-03-09 11:00:31,551][119383] InferenceWorker_p0-w0: stopping experience collection (7950 times) [2023-03-09 11:00:31,554][119383] InferenceWorker_p0-w0: resuming experience collection (7950 times) [2023-03-09 11:00:31,637][119383] Updated weights for policy 0, policy_version 142024 (0.0016) [2023-03-09 11:00:32,533][119383] Updated weights for policy 0, policy_version 142034 (0.0024) [2023-03-09 11:00:33,304][119383] Updated weights for policy 0, policy_version 142044 (0.0022) [2023-03-09 11:00:33,903][118949] Fps is (10 sec: 194954.9, 60 sec: 194695.0, 300 sec: 195441.3). Total num frames: 2327363584. Throughput: 0: 48629.4. Samples: 81800496. Policy #0 lag: (min: 0.0, avg: 16.8, max: 33.0) [2023-03-09 11:00:33,905][118949] Avg episode reward: [(0, '55.273')] [2023-03-09 11:00:34,190][119383] Updated weights for policy 0, policy_version 142054 (0.0016) [2023-03-09 11:00:34,961][119383] Updated weights for policy 0, policy_version 142064 (0.0017) [2023-03-09 11:00:35,893][119383] Updated weights for policy 0, policy_version 142075 (0.0014) [2023-03-09 11:00:36,788][119383] Updated weights for policy 0, policy_version 142085 (0.0036) [2023-03-09 11:00:37,607][119383] Updated weights for policy 0, policy_version 142096 (0.0016) [2023-03-09 11:00:38,387][119383] Updated weights for policy 0, policy_version 142106 (0.0016) [2023-03-09 11:00:38,902][118949] Fps is (10 sec: 201528.0, 60 sec: 195515.6, 300 sec: 195497.2). Total num frames: 2328379392. Throughput: 0: 48720.6. Samples: 82097312. Policy #0 lag: (min: 0.0, avg: 16.8, max: 33.0) [2023-03-09 11:00:38,903][118949] Avg episode reward: [(0, '55.092')] [2023-03-09 11:00:39,347][119383] Updated weights for policy 0, policy_version 142116 (0.0017) [2023-03-09 11:00:40,139][119383] Updated weights for policy 0, policy_version 142126 (0.0017) [2023-03-09 11:00:40,802][119240] Signal inference workers to stop experience collection... (8000 times) [2023-03-09 11:00:40,804][119240] Signal inference workers to resume experience collection... (8000 times) [2023-03-09 11:00:40,873][119383] InferenceWorker_p0-w0: stopping experience collection (8000 times) [2023-03-09 11:00:40,877][119383] InferenceWorker_p0-w0: resuming experience collection (8000 times) [2023-03-09 11:00:40,961][119383] Updated weights for policy 0, policy_version 142136 (0.0013) [2023-03-09 11:00:41,690][119383] Updated weights for policy 0, policy_version 142146 (0.0023) [2023-03-09 11:00:42,632][119383] Updated weights for policy 0, policy_version 142156 (0.0017) [2023-03-09 11:00:43,444][119383] Updated weights for policy 0, policy_version 142166 (0.0037) [2023-03-09 11:00:43,902][118949] Fps is (10 sec: 196618.3, 60 sec: 195242.1, 300 sec: 195441.6). Total num frames: 2329329664. Throughput: 0: 48811.3. Samples: 82392096. Policy #0 lag: (min: 0.0, avg: 16.8, max: 33.0) [2023-03-09 11:00:43,904][118949] Avg episode reward: [(0, '52.996')] [2023-03-09 11:00:44,203][119383] Updated weights for policy 0, policy_version 142176 (0.0017) [2023-03-09 11:00:45,117][119383] Updated weights for policy 0, policy_version 142186 (0.0016) [2023-03-09 11:00:46,072][119383] Updated weights for policy 0, policy_version 142196 (0.0028) [2023-03-09 11:00:46,824][119383] Updated weights for policy 0, policy_version 142206 (0.0021) [2023-03-09 11:00:47,724][119383] Updated weights for policy 0, policy_version 142216 (0.0020) [2023-03-09 11:00:48,645][119383] Updated weights for policy 0, policy_version 142226 (0.0023) [2023-03-09 11:00:48,902][118949] Fps is (10 sec: 190049.8, 60 sec: 194969.2, 300 sec: 195385.9). Total num frames: 2330279936. Throughput: 0: 48811.1. Samples: 82537472. Policy #0 lag: (min: 0.0, avg: 16.8, max: 33.0) [2023-03-09 11:00:48,904][118949] Avg episode reward: [(0, '53.504')] [2023-03-09 11:00:49,379][119383] Updated weights for policy 0, policy_version 142236 (0.0023) [2023-03-09 11:00:50,277][119240] Signal inference workers to stop experience collection... (8050 times) [2023-03-09 11:00:50,282][119383] Updated weights for policy 0, policy_version 142246 (0.0042) [2023-03-09 11:00:50,300][119240] Signal inference workers to resume experience collection... (8050 times) [2023-03-09 11:00:50,325][119383] InferenceWorker_p0-w0: stopping experience collection (8050 times) [2023-03-09 11:00:50,326][119383] InferenceWorker_p0-w0: resuming experience collection (8050 times) [2023-03-09 11:00:51,004][119383] Updated weights for policy 0, policy_version 142256 (0.0039) [2023-03-09 11:00:51,857][119383] Updated weights for policy 0, policy_version 142266 (0.0013) [2023-03-09 11:00:52,772][119383] Updated weights for policy 0, policy_version 142276 (0.0016) [2023-03-09 11:00:53,588][119383] Updated weights for policy 0, policy_version 142286 (0.0019) [2023-03-09 11:00:53,902][118949] Fps is (10 sec: 193335.5, 60 sec: 194696.4, 300 sec: 195386.2). Total num frames: 2331262976. Throughput: 0: 48856.1. Samples: 82830128. Policy #0 lag: (min: 0.0, avg: 16.8, max: 33.0) [2023-03-09 11:00:53,903][118949] Avg episode reward: [(0, '55.872')] [2023-03-09 11:00:54,418][119383] Updated weights for policy 0, policy_version 142296 (0.0014) [2023-03-09 11:00:55,154][119383] Updated weights for policy 0, policy_version 142306 (0.0013) [2023-03-09 11:00:56,129][119383] Updated weights for policy 0, policy_version 142316 (0.0015) [2023-03-09 11:00:57,046][119383] Updated weights for policy 0, policy_version 142327 (0.0015) [2023-03-09 11:00:57,712][119383] Updated weights for policy 0, policy_version 142337 (0.0017) [2023-03-09 11:00:58,719][119383] Updated weights for policy 0, policy_version 142347 (0.0018) [2023-03-09 11:00:58,902][118949] Fps is (10 sec: 196614.3, 60 sec: 194970.2, 300 sec: 195386.4). Total num frames: 2332246016. Throughput: 0: 48718.2. Samples: 83120816. Policy #0 lag: (min: 0.0, avg: 16.8, max: 33.0) [2023-03-09 11:00:58,903][118949] Avg episode reward: [(0, '53.984')] [2023-03-09 11:00:59,574][119383] Updated weights for policy 0, policy_version 142357 (0.0018) [2023-03-09 11:00:59,825][119240] Signal inference workers to stop experience collection... (8100 times) [2023-03-09 11:00:59,839][119240] Signal inference workers to resume experience collection... (8100 times) [2023-03-09 11:00:59,897][119383] InferenceWorker_p0-w0: stopping experience collection (8100 times) [2023-03-09 11:00:59,897][119383] InferenceWorker_p0-w0: resuming experience collection (8100 times) [2023-03-09 11:01:00,282][119383] Updated weights for policy 0, policy_version 142367 (0.0016) [2023-03-09 11:01:01,144][119383] Updated weights for policy 0, policy_version 142377 (0.0012) [2023-03-09 11:01:02,016][119383] Updated weights for policy 0, policy_version 142387 (0.0021) [2023-03-09 11:01:02,996][119383] Updated weights for policy 0, policy_version 142400 (0.0016) [2023-03-09 11:01:03,902][118949] Fps is (10 sec: 196599.7, 60 sec: 194695.4, 300 sec: 195441.4). Total num frames: 2333229056. Throughput: 0: 48852.6. Samples: 83272256. Policy #0 lag: (min: 0.0, avg: 16.8, max: 33.0) [2023-03-09 11:01:03,905][118949] Avg episode reward: [(0, '54.121')] [2023-03-09 11:01:03,927][119383] Updated weights for policy 0, policy_version 142410 (0.0017) [2023-03-09 11:01:04,840][119383] Updated weights for policy 0, policy_version 142420 (0.0015) [2023-03-09 11:01:05,585][119383] Updated weights for policy 0, policy_version 142430 (0.0020) [2023-03-09 11:01:06,406][119383] Updated weights for policy 0, policy_version 142440 (0.0013) [2023-03-09 11:01:07,418][119383] Updated weights for policy 0, policy_version 142450 (0.0013) [2023-03-09 11:01:08,146][119383] Updated weights for policy 0, policy_version 142460 (0.0016) [2023-03-09 11:01:08,902][118949] Fps is (10 sec: 194969.7, 60 sec: 194970.5, 300 sec: 195331.1). Total num frames: 2334195712. Throughput: 0: 48897.8. Samples: 83564912. Policy #0 lag: (min: 0.0, avg: 16.8, max: 33.0) [2023-03-09 11:01:08,903][118949] Avg episode reward: [(0, '55.232')] [2023-03-09 11:01:09,007][119383] Updated weights for policy 0, policy_version 142470 (0.0022) [2023-03-09 11:01:09,634][119240] Signal inference workers to stop experience collection... (8150 times) [2023-03-09 11:01:09,634][119240] Signal inference workers to resume experience collection... (8150 times) [2023-03-09 11:01:09,699][119383] InferenceWorker_p0-w0: stopping experience collection (8150 times) [2023-03-09 11:01:09,702][119383] InferenceWorker_p0-w0: resuming experience collection (8150 times) [2023-03-09 11:01:09,748][119383] Updated weights for policy 0, policy_version 142480 (0.0015) [2023-03-09 11:01:10,757][119383] Updated weights for policy 0, policy_version 142491 (0.0019) [2023-03-09 11:01:11,632][119383] Updated weights for policy 0, policy_version 142501 (0.0017) [2023-03-09 11:01:12,387][119383] Updated weights for policy 0, policy_version 142511 (0.0024) [2023-03-09 11:01:13,181][119383] Updated weights for policy 0, policy_version 142521 (0.0018) [2023-03-09 11:01:13,902][118949] Fps is (10 sec: 198248.6, 60 sec: 195515.5, 300 sec: 195441.6). Total num frames: 2335211520. Throughput: 0: 48942.5. Samples: 83857600. Policy #0 lag: (min: 0.0, avg: 16.8, max: 33.0) [2023-03-09 11:01:13,904][118949] Avg episode reward: [(0, '55.450')] [2023-03-09 11:01:14,205][119383] Updated weights for policy 0, policy_version 142532 (0.0017) [2023-03-09 11:01:14,984][119383] Updated weights for policy 0, policy_version 142542 (0.0018) [2023-03-09 11:01:15,824][119383] Updated weights for policy 0, policy_version 142552 (0.0021) [2023-03-09 11:01:16,563][119383] Updated weights for policy 0, policy_version 142562 (0.0013) [2023-03-09 11:01:17,486][119383] Updated weights for policy 0, policy_version 142572 (0.0018) [2023-03-09 11:01:18,345][119383] Updated weights for policy 0, policy_version 142582 (0.0017) [2023-03-09 11:01:18,902][118949] Fps is (10 sec: 198242.9, 60 sec: 195788.5, 300 sec: 195275.0). Total num frames: 2336178176. Throughput: 0: 48990.2. Samples: 84005024. Policy #0 lag: (min: 0.0, avg: 16.8, max: 33.0) [2023-03-09 11:01:18,903][118949] Avg episode reward: [(0, '56.301')] [2023-03-09 11:01:19,006][119240] Signal inference workers to stop experience collection... (8200 times) [2023-03-09 11:01:19,029][119240] Signal inference workers to resume experience collection... (8200 times) [2023-03-09 11:01:19,052][119383] InferenceWorker_p0-w0: stopping experience collection (8200 times) [2023-03-09 11:01:19,054][119383] InferenceWorker_p0-w0: resuming experience collection (8200 times) [2023-03-09 11:01:19,057][119383] Updated weights for policy 0, policy_version 142592 (0.0016) [2023-03-09 11:01:19,940][119383] Updated weights for policy 0, policy_version 142602 (0.0013) [2023-03-09 11:01:20,839][119383] Updated weights for policy 0, policy_version 142612 (0.0021) [2023-03-09 11:01:21,638][119383] Updated weights for policy 0, policy_version 142622 (0.0017) [2023-03-09 11:01:22,530][119383] Updated weights for policy 0, policy_version 142632 (0.0016) [2023-03-09 11:01:23,447][119383] Updated weights for policy 0, policy_version 142642 (0.0022) [2023-03-09 11:01:23,902][118949] Fps is (10 sec: 194967.9, 60 sec: 195787.5, 300 sec: 195386.0). Total num frames: 2337161216. Throughput: 0: 48944.3. Samples: 84299824. Policy #0 lag: (min: 0.0, avg: 17.0, max: 32.0) [2023-03-09 11:01:23,905][118949] Avg episode reward: [(0, '58.388')] [2023-03-09 11:01:23,945][119240] Saving /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000142650_2337177600.pth... [2023-03-09 11:01:24,005][119240] Removing /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000139794_2290384896.pth [2023-03-09 11:01:24,172][119383] Updated weights for policy 0, policy_version 142652 (0.0019) [2023-03-09 11:01:25,061][119383] Updated weights for policy 0, policy_version 142662 (0.0028) [2023-03-09 11:01:25,792][119383] Updated weights for policy 0, policy_version 142672 (0.0022) [2023-03-09 11:01:26,609][119383] Updated weights for policy 0, policy_version 142682 (0.0027) [2023-03-09 11:01:26,926][119240] Signal inference workers to stop experience collection... (8250 times) [2023-03-09 11:01:26,949][119240] Signal inference workers to resume experience collection... (8250 times) [2023-03-09 11:01:26,953][119383] InferenceWorker_p0-w0: stopping experience collection (8250 times) [2023-03-09 11:01:26,953][119383] InferenceWorker_p0-w0: resuming experience collection (8250 times) [2023-03-09 11:01:27,593][119383] Updated weights for policy 0, policy_version 142692 (0.0018) [2023-03-09 11:01:28,354][119383] Updated weights for policy 0, policy_version 142702 (0.0024) [2023-03-09 11:01:28,902][118949] Fps is (10 sec: 194965.8, 60 sec: 196061.7, 300 sec: 195274.9). Total num frames: 2338127872. Throughput: 0: 48943.5. Samples: 84594560. Policy #0 lag: (min: 0.0, avg: 17.0, max: 32.0) [2023-03-09 11:01:28,904][118949] Avg episode reward: [(0, '55.220')] [2023-03-09 11:01:29,170][119383] Updated weights for policy 0, policy_version 142712 (0.0017) [2023-03-09 11:01:29,824][119383] Updated weights for policy 0, policy_version 142722 (0.0026) [2023-03-09 11:01:30,936][119383] Updated weights for policy 0, policy_version 142733 (0.0023) [2023-03-09 11:01:31,724][119383] Updated weights for policy 0, policy_version 142743 (0.0026) [2023-03-09 11:01:32,367][119383] Updated weights for policy 0, policy_version 142753 (0.0014) [2023-03-09 11:01:33,348][119383] Updated weights for policy 0, policy_version 142763 (0.0018) [2023-03-09 11:01:33,902][118949] Fps is (10 sec: 194977.1, 60 sec: 195791.2, 300 sec: 195275.2). Total num frames: 2339110912. Throughput: 0: 49033.5. Samples: 84743968. Policy #0 lag: (min: 0.0, avg: 17.0, max: 32.0) [2023-03-09 11:01:33,904][118949] Avg episode reward: [(0, '54.988')] [2023-03-09 11:01:34,363][119383] Updated weights for policy 0, policy_version 142774 (0.0028) [2023-03-09 11:01:34,718][119240] Signal inference workers to stop experience collection... (8300 times) [2023-03-09 11:01:34,718][119240] Signal inference workers to resume experience collection... (8300 times) [2023-03-09 11:01:34,785][119383] InferenceWorker_p0-w0: stopping experience collection (8300 times) [2023-03-09 11:01:34,786][119383] InferenceWorker_p0-w0: resuming experience collection (8300 times) [2023-03-09 11:01:35,036][119383] Updated weights for policy 0, policy_version 142784 (0.0016) [2023-03-09 11:01:36,061][119383] Updated weights for policy 0, policy_version 142795 (0.0018) [2023-03-09 11:01:36,917][119383] Updated weights for policy 0, policy_version 142805 (0.0017) [2023-03-09 11:01:37,665][119383] Updated weights for policy 0, policy_version 142815 (0.0019) [2023-03-09 11:01:38,603][119383] Updated weights for policy 0, policy_version 142825 (0.0022) [2023-03-09 11:01:38,902][118949] Fps is (10 sec: 196612.8, 60 sec: 195242.5, 300 sec: 195275.0). Total num frames: 2340093952. Throughput: 0: 49035.3. Samples: 85036720. Policy #0 lag: (min: 0.0, avg: 17.0, max: 32.0) [2023-03-09 11:01:38,903][118949] Avg episode reward: [(0, '54.789')] [2023-03-09 11:01:39,435][119383] Updated weights for policy 0, policy_version 142835 (0.0023) [2023-03-09 11:01:40,217][119383] Updated weights for policy 0, policy_version 142845 (0.0013) [2023-03-09 11:01:41,076][119383] Updated weights for policy 0, policy_version 142855 (0.0014) [2023-03-09 11:01:41,995][119383] Updated weights for policy 0, policy_version 142865 (0.0023) [2023-03-09 11:01:42,389][119240] Signal inference workers to stop experience collection... (8350 times) [2023-03-09 11:01:42,412][119240] Signal inference workers to resume experience collection... (8350 times) [2023-03-09 11:01:42,448][119383] InferenceWorker_p0-w0: stopping experience collection (8350 times) [2023-03-09 11:01:42,491][119383] InferenceWorker_p0-w0: resuming experience collection (8350 times) [2023-03-09 11:01:42,729][119383] Updated weights for policy 0, policy_version 142875 (0.0016) [2023-03-09 11:01:43,638][119383] Updated weights for policy 0, policy_version 142885 (0.0020) [2023-03-09 11:01:43,902][118949] Fps is (10 sec: 199881.1, 60 sec: 196335.0, 300 sec: 195330.5). Total num frames: 2341109760. Throughput: 0: 49171.7. Samples: 85333552. Policy #0 lag: (min: 0.0, avg: 17.0, max: 32.0) [2023-03-09 11:01:43,903][118949] Avg episode reward: [(0, '52.363')] [2023-03-09 11:01:44,420][119383] Updated weights for policy 0, policy_version 142896 (0.0013) [2023-03-09 11:01:45,262][119383] Updated weights for policy 0, policy_version 142906 (0.0021) [2023-03-09 11:01:46,152][119383] Updated weights for policy 0, policy_version 142916 (0.0024) [2023-03-09 11:01:47,002][119383] Updated weights for policy 0, policy_version 142926 (0.0016) [2023-03-09 11:01:47,780][119383] Updated weights for policy 0, policy_version 142936 (0.0016) [2023-03-09 11:01:48,485][119383] Updated weights for policy 0, policy_version 142946 (0.0014) [2023-03-09 11:01:48,902][118949] Fps is (10 sec: 196609.2, 60 sec: 196335.8, 300 sec: 195219.7). Total num frames: 2342060032. Throughput: 0: 49129.0. Samples: 85483040. Policy #0 lag: (min: 0.0, avg: 17.0, max: 32.0) [2023-03-09 11:01:48,903][118949] Avg episode reward: [(0, '52.788')] [2023-03-09 11:01:49,460][119383] Updated weights for policy 0, policy_version 142956 (0.0022) [2023-03-09 11:01:50,329][119240] Signal inference workers to stop experience collection... (8400 times) [2023-03-09 11:01:50,330][119240] Signal inference workers to resume experience collection... (8400 times) [2023-03-09 11:01:50,405][119383] InferenceWorker_p0-w0: stopping experience collection (8400 times) [2023-03-09 11:01:50,406][119383] InferenceWorker_p0-w0: resuming experience collection (8400 times) [2023-03-09 11:01:50,409][119383] Updated weights for policy 0, policy_version 142967 (0.0023) [2023-03-09 11:01:51,069][119383] Updated weights for policy 0, policy_version 142977 (0.0016) [2023-03-09 11:01:52,019][119383] Updated weights for policy 0, policy_version 142987 (0.0015) [2023-03-09 11:01:52,878][119383] Updated weights for policy 0, policy_version 142997 (0.0013) [2023-03-09 11:01:53,644][119383] Updated weights for policy 0, policy_version 143007 (0.0016) [2023-03-09 11:01:53,902][118949] Fps is (10 sec: 196611.4, 60 sec: 196881.0, 300 sec: 195330.6). Total num frames: 2343075840. Throughput: 0: 49130.9. Samples: 85775808. Policy #0 lag: (min: 0.0, avg: 17.0, max: 32.0) [2023-03-09 11:01:53,903][118949] Avg episode reward: [(0, '55.682')] [2023-03-09 11:01:54,540][119383] Updated weights for policy 0, policy_version 143017 (0.0020) [2023-03-09 11:01:55,402][119383] Updated weights for policy 0, policy_version 143027 (0.0024) [2023-03-09 11:01:56,168][119383] Updated weights for policy 0, policy_version 143037 (0.0018) [2023-03-09 11:01:57,058][119383] Updated weights for policy 0, policy_version 143047 (0.0017) [2023-03-09 11:01:57,947][119383] Updated weights for policy 0, policy_version 143057 (0.0013) [2023-03-09 11:01:57,968][119240] Signal inference workers to stop experience collection... (8450 times) [2023-03-09 11:01:57,992][119240] Signal inference workers to resume experience collection... (8450 times) [2023-03-09 11:01:58,032][119383] InferenceWorker_p0-w0: stopping experience collection (8450 times) [2023-03-09 11:01:58,071][119383] InferenceWorker_p0-w0: resuming experience collection (8450 times) [2023-03-09 11:01:58,695][119383] Updated weights for policy 0, policy_version 143067 (0.0016) [2023-03-09 11:01:58,902][118949] Fps is (10 sec: 198247.6, 60 sec: 196608.0, 300 sec: 195219.7). Total num frames: 2344042496. Throughput: 0: 49220.7. Samples: 86072512. Policy #0 lag: (min: 0.0, avg: 17.0, max: 32.0) [2023-03-09 11:01:58,903][118949] Avg episode reward: [(0, '55.801')] [2023-03-09 11:01:59,625][119383] Updated weights for policy 0, policy_version 143077 (0.0013) [2023-03-09 11:02:00,463][119383] Updated weights for policy 0, policy_version 143088 (0.0030) [2023-03-09 11:02:01,367][119383] Updated weights for policy 0, policy_version 143099 (0.0019) [2023-03-09 11:02:02,339][119383] Updated weights for policy 0, policy_version 143109 (0.0017) [2023-03-09 11:02:03,084][119383] Updated weights for policy 0, policy_version 143119 (0.0018) [2023-03-09 11:02:03,902][118949] Fps is (10 sec: 193332.0, 60 sec: 196336.4, 300 sec: 195053.0). Total num frames: 2345009152. Throughput: 0: 49173.1. Samples: 86217808. Policy #0 lag: (min: 0.0, avg: 17.0, max: 32.0) [2023-03-09 11:02:03,903][118949] Avg episode reward: [(0, '53.865')] [2023-03-09 11:02:03,992][119383] Updated weights for policy 0, policy_version 143130 (0.0019) [2023-03-09 11:02:04,901][119383] Updated weights for policy 0, policy_version 143140 (0.0016) [2023-03-09 11:02:05,179][119240] Signal inference workers to stop experience collection... (8500 times) [2023-03-09 11:02:05,204][119240] Signal inference workers to resume experience collection... (8500 times) [2023-03-09 11:02:05,241][119383] InferenceWorker_p0-w0: stopping experience collection (8500 times) [2023-03-09 11:02:05,288][119383] InferenceWorker_p0-w0: resuming experience collection (8500 times) [2023-03-09 11:02:05,746][119383] Updated weights for policy 0, policy_version 143150 (0.0014) [2023-03-09 11:02:06,564][119383] Updated weights for policy 0, policy_version 143160 (0.0021) [2023-03-09 11:02:07,454][119383] Updated weights for policy 0, policy_version 143171 (0.0013) [2023-03-09 11:02:08,305][119383] Updated weights for policy 0, policy_version 143181 (0.0020) [2023-03-09 11:02:08,902][118949] Fps is (10 sec: 194969.7, 60 sec: 196608.0, 300 sec: 195108.5). Total num frames: 2345992192. Throughput: 0: 49128.7. Samples: 86510592. Policy #0 lag: (min: 0.0, avg: 17.0, max: 32.0) [2023-03-09 11:02:08,903][118949] Avg episode reward: [(0, '55.294')] [2023-03-09 11:02:09,164][119383] Updated weights for policy 0, policy_version 143191 (0.0022) [2023-03-09 11:02:09,814][119383] Updated weights for policy 0, policy_version 143201 (0.0024) [2023-03-09 11:02:10,762][119383] Updated weights for policy 0, policy_version 143211 (0.0016) [2023-03-09 11:02:11,662][119383] Updated weights for policy 0, policy_version 143221 (0.0033) [2023-03-09 11:02:12,383][119383] Updated weights for policy 0, policy_version 143231 (0.0016) [2023-03-09 11:02:13,161][119240] Signal inference workers to stop experience collection... (8550 times) [2023-03-09 11:02:13,186][119240] Signal inference workers to resume experience collection... (8550 times) [2023-03-09 11:02:13,231][119383] InferenceWorker_p0-w0: stopping experience collection (8550 times) [2023-03-09 11:02:13,231][119383] InferenceWorker_p0-w0: resuming experience collection (8550 times) [2023-03-09 11:02:13,280][119383] Updated weights for policy 0, policy_version 143241 (0.0017) [2023-03-09 11:02:13,902][118949] Fps is (10 sec: 193326.2, 60 sec: 195515.9, 300 sec: 195052.9). Total num frames: 2346942464. Throughput: 0: 48946.2. Samples: 86797136. Policy #0 lag: (min: 0.0, avg: 17.0, max: 32.0) [2023-03-09 11:02:13,904][118949] Avg episode reward: [(0, '54.784')] [2023-03-09 11:02:14,348][119383] Updated weights for policy 0, policy_version 143251 (0.0014) [2023-03-09 11:02:15,106][119383] Updated weights for policy 0, policy_version 143261 (0.0016) [2023-03-09 11:02:16,035][119383] Updated weights for policy 0, policy_version 143271 (0.0013) [2023-03-09 11:02:16,933][119383] Updated weights for policy 0, policy_version 143281 (0.0016) [2023-03-09 11:02:17,618][119383] Updated weights for policy 0, policy_version 143291 (0.0016) [2023-03-09 11:02:18,564][119383] Updated weights for policy 0, policy_version 143301 (0.0029) [2023-03-09 11:02:18,902][118949] Fps is (10 sec: 193331.0, 60 sec: 195789.4, 300 sec: 195164.2). Total num frames: 2347925504. Throughput: 0: 48854.8. Samples: 86942432. Policy #0 lag: (min: 0.0, avg: 17.0, max: 32.0) [2023-03-09 11:02:18,903][118949] Avg episode reward: [(0, '56.282')] [2023-03-09 11:02:19,378][119383] Updated weights for policy 0, policy_version 143311 (0.0025) [2023-03-09 11:02:20,153][119383] Updated weights for policy 0, policy_version 143321 (0.0013) [2023-03-09 11:02:21,003][119383] Updated weights for policy 0, policy_version 143331 (0.0013) [2023-03-09 11:02:21,821][119383] Updated weights for policy 0, policy_version 143341 (0.0013) [2023-03-09 11:02:21,999][119240] Signal inference workers to stop experience collection... (8600 times) [2023-03-09 11:02:22,000][119240] Signal inference workers to resume experience collection... (8600 times) [2023-03-09 11:02:22,064][119383] InferenceWorker_p0-w0: stopping experience collection (8600 times) [2023-03-09 11:02:22,065][119383] InferenceWorker_p0-w0: resuming experience collection (8600 times) [2023-03-09 11:02:22,710][119383] Updated weights for policy 0, policy_version 143351 (0.0026) [2023-03-09 11:02:23,361][119383] Updated weights for policy 0, policy_version 143361 (0.0021) [2023-03-09 11:02:23,902][118949] Fps is (10 sec: 194974.5, 60 sec: 195517.1, 300 sec: 195108.6). Total num frames: 2348892160. Throughput: 0: 48854.9. Samples: 87235184. Policy #0 lag: (min: 0.0, avg: 17.0, max: 32.0) [2023-03-09 11:02:23,903][118949] Avg episode reward: [(0, '55.183')] [2023-03-09 11:02:24,296][119383] Updated weights for policy 0, policy_version 143371 (0.0014) [2023-03-09 11:02:25,222][119383] Updated weights for policy 0, policy_version 143381 (0.0013) [2023-03-09 11:02:25,940][119383] Updated weights for policy 0, policy_version 143391 (0.0017) [2023-03-09 11:02:26,819][119383] Updated weights for policy 0, policy_version 143401 (0.0016) [2023-03-09 11:02:27,760][119383] Updated weights for policy 0, policy_version 143411 (0.0013) [2023-03-09 11:02:28,600][119383] Updated weights for policy 0, policy_version 143422 (0.0028) [2023-03-09 11:02:28,902][118949] Fps is (10 sec: 196597.7, 60 sec: 196061.3, 300 sec: 195108.1). Total num frames: 2349891584. Throughput: 0: 48716.1. Samples: 87525792. Policy #0 lag: (min: 0.0, avg: 17.0, max: 33.0) [2023-03-09 11:02:28,904][118949] Avg episode reward: [(0, '56.536')] [2023-03-09 11:02:29,471][119383] Updated weights for policy 0, policy_version 143432 (0.0019) [2023-03-09 11:02:30,423][119383] Updated weights for policy 0, policy_version 143442 (0.0017) [2023-03-09 11:02:30,738][119240] Signal inference workers to stop experience collection... (8650 times) [2023-03-09 11:02:30,760][119240] Signal inference workers to resume experience collection... (8650 times) [2023-03-09 11:02:30,799][119383] InferenceWorker_p0-w0: stopping experience collection (8650 times) [2023-03-09 11:02:30,844][119383] InferenceWorker_p0-w0: resuming experience collection (8650 times) [2023-03-09 11:02:31,142][119383] Updated weights for policy 0, policy_version 143452 (0.0013) [2023-03-09 11:02:32,077][119383] Updated weights for policy 0, policy_version 143462 (0.0017) [2023-03-09 11:02:32,838][119383] Updated weights for policy 0, policy_version 143472 (0.0018) [2023-03-09 11:02:33,649][119383] Updated weights for policy 0, policy_version 143482 (0.0020) [2023-03-09 11:02:33,902][118949] Fps is (10 sec: 196600.7, 60 sec: 195787.7, 300 sec: 195052.7). Total num frames: 2350858240. Throughput: 0: 48714.3. Samples: 87675200. Policy #0 lag: (min: 0.0, avg: 17.0, max: 33.0) [2023-03-09 11:02:33,904][118949] Avg episode reward: [(0, '56.301')] [2023-03-09 11:02:34,585][119383] Updated weights for policy 0, policy_version 143492 (0.0017) [2023-03-09 11:02:35,443][119383] Updated weights for policy 0, policy_version 143503 (0.0025) [2023-03-09 11:02:36,301][119383] Updated weights for policy 0, policy_version 143513 (0.0028) [2023-03-09 11:02:37,110][119383] Updated weights for policy 0, policy_version 143523 (0.0020) [2023-03-09 11:02:37,956][119383] Updated weights for policy 0, policy_version 143533 (0.0042) [2023-03-09 11:02:38,828][119383] Updated weights for policy 0, policy_version 143543 (0.0025) [2023-03-09 11:02:38,902][118949] Fps is (10 sec: 193341.5, 60 sec: 195516.2, 300 sec: 194997.5). Total num frames: 2351824896. Throughput: 0: 48713.7. Samples: 87967920. Policy #0 lag: (min: 0.0, avg: 17.0, max: 33.0) [2023-03-09 11:02:38,903][118949] Avg episode reward: [(0, '55.397')] [2023-03-09 11:02:39,380][119240] Signal inference workers to stop experience collection... (8700 times) [2023-03-09 11:02:39,408][119240] Signal inference workers to resume experience collection... (8700 times) [2023-03-09 11:02:39,443][119383] InferenceWorker_p0-w0: stopping experience collection (8700 times) [2023-03-09 11:02:39,490][119383] InferenceWorker_p0-w0: resuming experience collection (8700 times) [2023-03-09 11:02:39,618][119383] Updated weights for policy 0, policy_version 143554 (0.0013) [2023-03-09 11:02:40,644][119383] Updated weights for policy 0, policy_version 143565 (0.0017) [2023-03-09 11:02:41,542][119383] Updated weights for policy 0, policy_version 143575 (0.0021) [2023-03-09 11:02:42,181][119383] Updated weights for policy 0, policy_version 143585 (0.0044) [2023-03-09 11:02:43,177][119383] Updated weights for policy 0, policy_version 143595 (0.0036) [2023-03-09 11:02:43,902][118949] Fps is (10 sec: 191696.0, 60 sec: 194423.5, 300 sec: 194941.7). Total num frames: 2352775168. Throughput: 0: 48578.9. Samples: 88258576. Policy #0 lag: (min: 0.0, avg: 17.0, max: 33.0) [2023-03-09 11:02:43,903][118949] Avg episode reward: [(0, '58.382')] [2023-03-09 11:02:44,083][119383] Updated weights for policy 0, policy_version 143605 (0.0014) [2023-03-09 11:02:44,811][119383] Updated weights for policy 0, policy_version 143615 (0.0019) [2023-03-09 11:02:45,701][119383] Updated weights for policy 0, policy_version 143625 (0.0019) [2023-03-09 11:02:46,633][119383] Updated weights for policy 0, policy_version 143635 (0.0016) [2023-03-09 11:02:47,407][119383] Updated weights for policy 0, policy_version 143645 (0.0016) [2023-03-09 11:02:48,280][119383] Updated weights for policy 0, policy_version 143655 (0.0019) [2023-03-09 11:02:48,902][118949] Fps is (10 sec: 193324.5, 60 sec: 194968.7, 300 sec: 195052.9). Total num frames: 2353758208. Throughput: 0: 48578.9. Samples: 88403872. Policy #0 lag: (min: 0.0, avg: 17.0, max: 33.0) [2023-03-09 11:02:48,904][118949] Avg episode reward: [(0, '56.384')] [2023-03-09 11:02:48,906][119240] Signal inference workers to stop experience collection... (8750 times) [2023-03-09 11:02:48,907][119240] Signal inference workers to resume experience collection... (8750 times) [2023-03-09 11:02:48,975][119383] InferenceWorker_p0-w0: stopping experience collection (8750 times) [2023-03-09 11:02:48,975][119383] InferenceWorker_p0-w0: resuming experience collection (8750 times) [2023-03-09 11:02:49,220][119383] Updated weights for policy 0, policy_version 143665 (0.0023) [2023-03-09 11:02:50,032][119383] Updated weights for policy 0, policy_version 143676 (0.0021) [2023-03-09 11:02:50,944][119383] Updated weights for policy 0, policy_version 143686 (0.0016) [2023-03-09 11:02:51,701][119383] Updated weights for policy 0, policy_version 143696 (0.0027) [2023-03-09 11:02:52,483][119383] Updated weights for policy 0, policy_version 143706 (0.0016) [2023-03-09 11:02:53,479][119383] Updated weights for policy 0, policy_version 143716 (0.0025) [2023-03-09 11:02:53,902][118949] Fps is (10 sec: 196610.9, 60 sec: 194423.4, 300 sec: 195108.4). Total num frames: 2354741248. Throughput: 0: 48532.2. Samples: 88694544. Policy #0 lag: (min: 0.0, avg: 17.0, max: 33.0) [2023-03-09 11:02:53,903][118949] Avg episode reward: [(0, '56.766')] [2023-03-09 11:02:54,304][119383] Updated weights for policy 0, policy_version 143726 (0.0022) [2023-03-09 11:02:55,089][119383] Updated weights for policy 0, policy_version 143736 (0.0013) [2023-03-09 11:02:55,864][119383] Updated weights for policy 0, policy_version 143746 (0.0016) [2023-03-09 11:02:56,734][119383] Updated weights for policy 0, policy_version 143756 (0.0024) [2023-03-09 11:02:57,336][119240] Signal inference workers to stop experience collection... (8800 times) [2023-03-09 11:02:57,354][119240] Signal inference workers to resume experience collection... (8800 times) [2023-03-09 11:02:57,384][119383] InferenceWorker_p0-w0: stopping experience collection (8800 times) [2023-03-09 11:02:57,422][119383] InferenceWorker_p0-w0: resuming experience collection (8800 times) [2023-03-09 11:02:57,613][119383] Updated weights for policy 0, policy_version 143766 (0.0014) [2023-03-09 11:02:58,378][119383] Updated weights for policy 0, policy_version 143777 (0.0015) [2023-03-09 11:02:58,902][118949] Fps is (10 sec: 193334.7, 60 sec: 194149.9, 300 sec: 194997.5). Total num frames: 2355691520. Throughput: 0: 48713.7. Samples: 88989248. Policy #0 lag: (min: 0.0, avg: 17.0, max: 33.0) [2023-03-09 11:02:58,904][118949] Avg episode reward: [(0, '55.857')] [2023-03-09 11:02:59,349][119383] Updated weights for policy 0, policy_version 143787 (0.0013) [2023-03-09 11:03:00,227][119383] Updated weights for policy 0, policy_version 143797 (0.0013) [2023-03-09 11:03:00,987][119383] Updated weights for policy 0, policy_version 143807 (0.0032) [2023-03-09 11:03:01,919][119383] Updated weights for policy 0, policy_version 143817 (0.0013) [2023-03-09 11:03:02,775][119383] Updated weights for policy 0, policy_version 143827 (0.0016) [2023-03-09 11:03:03,628][119383] Updated weights for policy 0, policy_version 143837 (0.0032) [2023-03-09 11:03:03,902][118949] Fps is (10 sec: 194970.8, 60 sec: 194696.5, 300 sec: 195053.0). Total num frames: 2356690944. Throughput: 0: 48714.3. Samples: 89134576. Policy #0 lag: (min: 0.0, avg: 17.0, max: 33.0) [2023-03-09 11:03:03,903][118949] Avg episode reward: [(0, '55.827')] [2023-03-09 11:03:04,531][119383] Updated weights for policy 0, policy_version 143847 (0.0013) [2023-03-09 11:03:05,464][119383] Updated weights for policy 0, policy_version 143857 (0.0019) [2023-03-09 11:03:05,875][119240] Signal inference workers to stop experience collection... (8850 times) [2023-03-09 11:03:05,895][119240] Signal inference workers to resume experience collection... (8850 times) [2023-03-09 11:03:05,924][119383] InferenceWorker_p0-w0: stopping experience collection (8850 times) [2023-03-09 11:03:05,966][119383] InferenceWorker_p0-w0: resuming experience collection (8850 times) [2023-03-09 11:03:06,225][119383] Updated weights for policy 0, policy_version 143867 (0.0016) [2023-03-09 11:03:07,115][119383] Updated weights for policy 0, policy_version 143877 (0.0021) [2023-03-09 11:03:07,914][119383] Updated weights for policy 0, policy_version 143887 (0.0033) [2023-03-09 11:03:08,755][119383] Updated weights for policy 0, policy_version 143897 (0.0016) [2023-03-09 11:03:08,902][118949] Fps is (10 sec: 194971.8, 60 sec: 194150.2, 300 sec: 194941.9). Total num frames: 2357641216. Throughput: 0: 48577.4. Samples: 89421168. Policy #0 lag: (min: 0.0, avg: 17.0, max: 33.0) [2023-03-09 11:03:08,903][118949] Avg episode reward: [(0, '54.194')] [2023-03-09 11:03:09,649][119383] Updated weights for policy 0, policy_version 143907 (0.0015) [2023-03-09 11:03:10,568][119383] Updated weights for policy 0, policy_version 143918 (0.0032) [2023-03-09 11:03:11,396][119383] Updated weights for policy 0, policy_version 143928 (0.0018) [2023-03-09 11:03:12,085][119383] Updated weights for policy 0, policy_version 143938 (0.0025) [2023-03-09 11:03:12,984][119383] Updated weights for policy 0, policy_version 143948 (0.0022) [2023-03-09 11:03:13,515][119240] Signal inference workers to stop experience collection... (8900 times) [2023-03-09 11:03:13,517][119240] Signal inference workers to resume experience collection... (8900 times) [2023-03-09 11:03:13,583][119383] InferenceWorker_p0-w0: stopping experience collection (8900 times) [2023-03-09 11:03:13,584][119383] InferenceWorker_p0-w0: resuming experience collection (8900 times) [2023-03-09 11:03:13,902][118949] Fps is (10 sec: 190054.1, 60 sec: 194151.2, 300 sec: 194886.5). Total num frames: 2358591488. Throughput: 0: 48625.6. Samples: 89713920. Policy #0 lag: (min: 0.0, avg: 17.0, max: 33.0) [2023-03-09 11:03:13,903][118949] Avg episode reward: [(0, '56.682')] [2023-03-09 11:03:13,918][119383] Updated weights for policy 0, policy_version 143958 (0.0013) [2023-03-09 11:03:14,582][119383] Updated weights for policy 0, policy_version 143968 (0.0014) [2023-03-09 11:03:15,608][119383] Updated weights for policy 0, policy_version 143979 (0.0023) [2023-03-09 11:03:16,476][119383] Updated weights for policy 0, policy_version 143989 (0.0013) [2023-03-09 11:03:17,274][119383] Updated weights for policy 0, policy_version 143999 (0.0013) [2023-03-09 11:03:18,145][119383] Updated weights for policy 0, policy_version 144009 (0.0018) [2023-03-09 11:03:18,902][118949] Fps is (10 sec: 191691.6, 60 sec: 193877.0, 300 sec: 194886.3). Total num frames: 2359558144. Throughput: 0: 48489.6. Samples: 89857216. Policy #0 lag: (min: 0.0, avg: 17.0, max: 33.0) [2023-03-09 11:03:18,903][118949] Avg episode reward: [(0, '54.366')] [2023-03-09 11:03:19,074][119383] Updated weights for policy 0, policy_version 144019 (0.0018) [2023-03-09 11:03:19,832][119383] Updated weights for policy 0, policy_version 144029 (0.0013) [2023-03-09 11:03:20,630][119240] Signal inference workers to stop experience collection... (8950 times) [2023-03-09 11:03:20,633][119240] Signal inference workers to resume experience collection... (8950 times) [2023-03-09 11:03:20,708][119383] InferenceWorker_p0-w0: stopping experience collection (8950 times) [2023-03-09 11:03:20,708][119383] InferenceWorker_p0-w0: resuming experience collection (8950 times) [2023-03-09 11:03:20,710][119383] Updated weights for policy 0, policy_version 144039 (0.0020) [2023-03-09 11:03:21,607][119383] Updated weights for policy 0, policy_version 144049 (0.0034) [2023-03-09 11:03:22,308][119383] Updated weights for policy 0, policy_version 144059 (0.0016) [2023-03-09 11:03:23,304][119383] Updated weights for policy 0, policy_version 144070 (0.0019) [2023-03-09 11:03:23,902][118949] Fps is (10 sec: 196607.5, 60 sec: 194423.3, 300 sec: 194997.5). Total num frames: 2360557568. Throughput: 0: 48533.2. Samples: 90151920. Policy #0 lag: (min: 0.0, avg: 17.0, max: 33.0) [2023-03-09 11:03:23,903][118949] Avg episode reward: [(0, '55.729')] [2023-03-09 11:03:23,936][119240] Saving /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000144078_2360573952.pth... [2023-03-09 11:03:23,998][119240] Removing /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000141220_2313748480.pth [2023-03-09 11:03:24,128][119383] Updated weights for policy 0, policy_version 144080 (0.0013) [2023-03-09 11:03:24,911][119383] Updated weights for policy 0, policy_version 144090 (0.0013) [2023-03-09 11:03:25,814][119383] Updated weights for policy 0, policy_version 144100 (0.0013) [2023-03-09 11:03:26,724][119383] Updated weights for policy 0, policy_version 144111 (0.0022) [2023-03-09 11:03:27,563][119383] Updated weights for policy 0, policy_version 144121 (0.0020) [2023-03-09 11:03:27,734][119240] Signal inference workers to stop experience collection... (9000 times) [2023-03-09 11:03:27,751][119240] Signal inference workers to resume experience collection... (9000 times) [2023-03-09 11:03:27,814][119383] InferenceWorker_p0-w0: stopping experience collection (9000 times) [2023-03-09 11:03:27,814][119383] InferenceWorker_p0-w0: resuming experience collection (9000 times) [2023-03-09 11:03:28,501][119383] Updated weights for policy 0, policy_version 144131 (0.0014) [2023-03-09 11:03:28,902][118949] Fps is (10 sec: 198248.3, 60 sec: 194152.1, 300 sec: 195108.5). Total num frames: 2361540608. Throughput: 0: 48534.3. Samples: 90442608. Policy #0 lag: (min: 2.0, avg: 17.0, max: 34.0) [2023-03-09 11:03:28,903][118949] Avg episode reward: [(0, '56.912')] [2023-03-09 11:03:29,247][119383] Updated weights for policy 0, policy_version 144141 (0.0016) [2023-03-09 11:03:30,112][119383] Updated weights for policy 0, policy_version 144151 (0.0015) [2023-03-09 11:03:30,798][119383] Updated weights for policy 0, policy_version 144161 (0.0037) [2023-03-09 11:03:31,714][119383] Updated weights for policy 0, policy_version 144171 (0.0020) [2023-03-09 11:03:32,608][119383] Updated weights for policy 0, policy_version 144181 (0.0016) [2023-03-09 11:03:33,343][119383] Updated weights for policy 0, policy_version 144191 (0.0016) [2023-03-09 11:03:33,902][118949] Fps is (10 sec: 194962.8, 60 sec: 194150.3, 300 sec: 195108.2). Total num frames: 2362507264. Throughput: 0: 48580.5. Samples: 90590000. Policy #0 lag: (min: 2.0, avg: 17.0, max: 34.0) [2023-03-09 11:03:33,905][118949] Avg episode reward: [(0, '56.238')] [2023-03-09 11:03:34,323][119383] Updated weights for policy 0, policy_version 144202 (0.0014) [2023-03-09 11:03:35,203][119383] Updated weights for policy 0, policy_version 144212 (0.0016) [2023-03-09 11:03:36,038][119383] Updated weights for policy 0, policy_version 144222 (0.0019) [2023-03-09 11:03:36,680][119240] Signal inference workers to stop experience collection... (9050 times) [2023-03-09 11:03:36,694][119240] Signal inference workers to resume experience collection... (9050 times) [2023-03-09 11:03:36,758][119383] InferenceWorker_p0-w0: stopping experience collection (9050 times) [2023-03-09 11:03:36,758][119383] InferenceWorker_p0-w0: resuming experience collection (9050 times) [2023-03-09 11:03:36,920][119383] Updated weights for policy 0, policy_version 144232 (0.0019) [2023-03-09 11:03:37,820][119383] Updated weights for policy 0, policy_version 144242 (0.0017) [2023-03-09 11:03:38,657][119383] Updated weights for policy 0, policy_version 144253 (0.0013) [2023-03-09 11:03:38,902][118949] Fps is (10 sec: 194969.8, 60 sec: 194423.4, 300 sec: 195108.7). Total num frames: 2363490304. Throughput: 0: 48626.9. Samples: 90882752. Policy #0 lag: (min: 2.0, avg: 17.0, max: 34.0) [2023-03-09 11:03:38,903][118949] Avg episode reward: [(0, '55.175')] [2023-03-09 11:03:39,564][119383] Updated weights for policy 0, policy_version 144263 (0.0016) [2023-03-09 11:03:40,474][119383] Updated weights for policy 0, policy_version 144273 (0.0021) [2023-03-09 11:03:41,203][119383] Updated weights for policy 0, policy_version 144283 (0.0032) [2023-03-09 11:03:42,154][119383] Updated weights for policy 0, policy_version 144293 (0.0023) [2023-03-09 11:03:43,000][119383] Updated weights for policy 0, policy_version 144304 (0.0023) [2023-03-09 11:03:43,791][119383] Updated weights for policy 0, policy_version 144314 (0.0019) [2023-03-09 11:03:43,902][118949] Fps is (10 sec: 194977.5, 60 sec: 194697.2, 300 sec: 195052.9). Total num frames: 2364456960. Throughput: 0: 48538.5. Samples: 91173472. Policy #0 lag: (min: 2.0, avg: 17.0, max: 34.0) [2023-03-09 11:03:43,903][118949] Avg episode reward: [(0, '53.804')] [2023-03-09 11:03:44,739][119383] Updated weights for policy 0, policy_version 144324 (0.0020) [2023-03-09 11:03:45,624][119383] Updated weights for policy 0, policy_version 144334 (0.0025) [2023-03-09 11:03:45,929][119240] Signal inference workers to stop experience collection... (9100 times) [2023-03-09 11:03:45,930][119240] Signal inference workers to resume experience collection... (9100 times) [2023-03-09 11:03:46,001][119383] InferenceWorker_p0-w0: stopping experience collection (9100 times) [2023-03-09 11:03:46,001][119383] InferenceWorker_p0-w0: resuming experience collection (9100 times) [2023-03-09 11:03:46,446][119383] Updated weights for policy 0, policy_version 144345 (0.0018) [2023-03-09 11:03:47,354][119383] Updated weights for policy 0, policy_version 144355 (0.0019) [2023-03-09 11:03:48,141][119383] Updated weights for policy 0, policy_version 144365 (0.0029) [2023-03-09 11:03:48,902][118949] Fps is (10 sec: 191686.4, 60 sec: 194150.4, 300 sec: 194886.3). Total num frames: 2365407232. Throughput: 0: 48492.5. Samples: 91316752. Policy #0 lag: (min: 2.0, avg: 17.0, max: 34.0) [2023-03-09 11:03:48,905][118949] Avg episode reward: [(0, '55.687')] [2023-03-09 11:03:49,023][119383] Updated weights for policy 0, policy_version 144375 (0.0013) [2023-03-09 11:03:49,687][119383] Updated weights for policy 0, policy_version 144385 (0.0022) [2023-03-09 11:03:50,613][119383] Updated weights for policy 0, policy_version 144395 (0.0028) [2023-03-09 11:03:51,548][119383] Updated weights for policy 0, policy_version 144405 (0.0019) [2023-03-09 11:03:52,315][119383] Updated weights for policy 0, policy_version 144415 (0.0025) [2023-03-09 11:03:53,177][119383] Updated weights for policy 0, policy_version 144425 (0.0017) [2023-03-09 11:03:53,902][118949] Fps is (10 sec: 193324.9, 60 sec: 194149.6, 300 sec: 194997.3). Total num frames: 2366390272. Throughput: 0: 48629.0. Samples: 91609488. Policy #0 lag: (min: 2.0, avg: 17.0, max: 34.0) [2023-03-09 11:03:53,904][118949] Avg episode reward: [(0, '55.190')] [2023-03-09 11:03:54,059][119383] Updated weights for policy 0, policy_version 144435 (0.0016) [2023-03-09 11:03:54,321][119240] Signal inference workers to stop experience collection... (9150 times) [2023-03-09 11:03:54,324][119240] Signal inference workers to resume experience collection... (9150 times) [2023-03-09 11:03:54,392][119383] InferenceWorker_p0-w0: stopping experience collection (9150 times) [2023-03-09 11:03:54,392][119383] InferenceWorker_p0-w0: resuming experience collection (9150 times) [2023-03-09 11:03:54,862][119383] Updated weights for policy 0, policy_version 144445 (0.0016) [2023-03-09 11:03:55,759][119383] Updated weights for policy 0, policy_version 144455 (0.0015) [2023-03-09 11:03:56,618][119383] Updated weights for policy 0, policy_version 144465 (0.0027) [2023-03-09 11:03:57,520][119383] Updated weights for policy 0, policy_version 144476 (0.0020) [2023-03-09 11:03:58,402][119383] Updated weights for policy 0, policy_version 144486 (0.0014) [2023-03-09 11:03:58,902][118949] Fps is (10 sec: 196609.7, 60 sec: 194696.2, 300 sec: 194997.2). Total num frames: 2367373312. Throughput: 0: 48627.3. Samples: 91902160. Policy #0 lag: (min: 2.0, avg: 17.0, max: 34.0) [2023-03-09 11:03:58,905][118949] Avg episode reward: [(0, '55.814')] [2023-03-09 11:03:59,222][119383] Updated weights for policy 0, policy_version 144496 (0.0018) [2023-03-09 11:03:59,961][119383] Updated weights for policy 0, policy_version 144506 (0.0016) [2023-03-09 11:04:00,849][119383] Updated weights for policy 0, policy_version 144516 (0.0019) [2023-03-09 11:04:01,666][119383] Updated weights for policy 0, policy_version 144526 (0.0016) [2023-03-09 11:04:02,529][119383] Updated weights for policy 0, policy_version 144536 (0.0013) [2023-03-09 11:04:02,748][119240] Signal inference workers to stop experience collection... (9200 times) [2023-03-09 11:04:02,752][119240] Signal inference workers to resume experience collection... (9200 times) [2023-03-09 11:04:02,816][119383] InferenceWorker_p0-w0: stopping experience collection (9200 times) [2023-03-09 11:04:02,817][119383] InferenceWorker_p0-w0: resuming experience collection (9200 times) [2023-03-09 11:04:03,312][119383] Updated weights for policy 0, policy_version 144546 (0.0017) [2023-03-09 11:04:03,902][118949] Fps is (10 sec: 196611.9, 60 sec: 194423.1, 300 sec: 195052.8). Total num frames: 2368356352. Throughput: 0: 48718.5. Samples: 92049552. Policy #0 lag: (min: 2.0, avg: 17.0, max: 34.0) [2023-03-09 11:04:03,903][118949] Avg episode reward: [(0, '55.372')] [2023-03-09 11:04:04,158][119383] Updated weights for policy 0, policy_version 144556 (0.0031) [2023-03-09 11:04:05,126][119383] Updated weights for policy 0, policy_version 144566 (0.0020) [2023-03-09 11:04:05,776][119383] Updated weights for policy 0, policy_version 144576 (0.0014) [2023-03-09 11:04:06,643][119383] Updated weights for policy 0, policy_version 144586 (0.0019) [2023-03-09 11:04:07,551][119383] Updated weights for policy 0, policy_version 144596 (0.0019) [2023-03-09 11:04:08,341][119383] Updated weights for policy 0, policy_version 144606 (0.0021) [2023-03-09 11:04:08,902][118949] Fps is (10 sec: 193334.7, 60 sec: 194423.4, 300 sec: 194942.0). Total num frames: 2369306624. Throughput: 0: 48673.8. Samples: 92342240. Policy #0 lag: (min: 2.0, avg: 17.0, max: 34.0) [2023-03-09 11:04:08,903][118949] Avg episode reward: [(0, '58.243')] [2023-03-09 11:04:09,208][119383] Updated weights for policy 0, policy_version 144616 (0.0016) [2023-03-09 11:04:10,137][119383] Updated weights for policy 0, policy_version 144626 (0.0016) [2023-03-09 11:04:10,918][119383] Updated weights for policy 0, policy_version 144636 (0.0013) [2023-03-09 11:04:11,098][119240] Signal inference workers to stop experience collection... (9250 times) [2023-03-09 11:04:11,119][119240] Signal inference workers to resume experience collection... (9250 times) [2023-03-09 11:04:11,141][119383] InferenceWorker_p0-w0: stopping experience collection (9250 times) [2023-03-09 11:04:11,141][119383] InferenceWorker_p0-w0: resuming experience collection (9250 times) [2023-03-09 11:04:11,778][119383] Updated weights for policy 0, policy_version 144646 (0.0017) [2023-03-09 11:04:12,620][119383] Updated weights for policy 0, policy_version 144656 (0.0016) [2023-03-09 11:04:13,414][119383] Updated weights for policy 0, policy_version 144666 (0.0020) [2023-03-09 11:04:13,902][118949] Fps is (10 sec: 196608.1, 60 sec: 195515.4, 300 sec: 195108.6). Total num frames: 2370322432. Throughput: 0: 48719.5. Samples: 92634992. Policy #0 lag: (min: 2.0, avg: 17.0, max: 34.0) [2023-03-09 11:04:13,903][118949] Avg episode reward: [(0, '55.006')] [2023-03-09 11:04:14,271][119383] Updated weights for policy 0, policy_version 144676 (0.0018) [2023-03-09 11:04:15,104][119383] Updated weights for policy 0, policy_version 144686 (0.0012) [2023-03-09 11:04:15,979][119383] Updated weights for policy 0, policy_version 144696 (0.0016) [2023-03-09 11:04:16,688][119383] Updated weights for policy 0, policy_version 144706 (0.0020) [2023-03-09 11:04:17,671][119383] Updated weights for policy 0, policy_version 144717 (0.0013) [2023-03-09 11:04:18,644][119383] Updated weights for policy 0, policy_version 144728 (0.0021) [2023-03-09 11:04:18,902][118949] Fps is (10 sec: 196606.3, 60 sec: 195242.5, 300 sec: 194997.5). Total num frames: 2371272704. Throughput: 0: 48718.5. Samples: 92782320. Policy #0 lag: (min: 2.0, avg: 17.0, max: 34.0) [2023-03-09 11:04:18,903][118949] Avg episode reward: [(0, '55.097')] [2023-03-09 11:04:19,385][119383] Updated weights for policy 0, policy_version 144738 (0.0014) [2023-03-09 11:04:20,275][119383] Updated weights for policy 0, policy_version 144748 (0.0015) [2023-03-09 11:04:21,163][119240] Signal inference workers to stop experience collection... (9300 times) [2023-03-09 11:04:21,198][119240] Signal inference workers to resume experience collection... (9300 times) [2023-03-09 11:04:21,222][119383] InferenceWorker_p0-w0: stopping experience collection (9300 times) [2023-03-09 11:04:21,224][119383] Updated weights for policy 0, policy_version 144758 (0.0026) [2023-03-09 11:04:21,272][119383] InferenceWorker_p0-w0: resuming experience collection (9300 times) [2023-03-09 11:04:21,874][119383] Updated weights for policy 0, policy_version 144768 (0.0017) [2023-03-09 11:04:22,757][119383] Updated weights for policy 0, policy_version 144778 (0.0016) [2023-03-09 11:04:23,660][119383] Updated weights for policy 0, policy_version 144788 (0.0016) [2023-03-09 11:04:23,902][118949] Fps is (10 sec: 191687.4, 60 sec: 194695.4, 300 sec: 194886.3). Total num frames: 2372239360. Throughput: 0: 48672.3. Samples: 93073024. Policy #0 lag: (min: 2.0, avg: 17.0, max: 34.0) [2023-03-09 11:04:23,904][118949] Avg episode reward: [(0, '56.400')] [2023-03-09 11:04:24,492][119383] Updated weights for policy 0, policy_version 144799 (0.0019) [2023-03-09 11:04:25,389][119383] Updated weights for policy 0, policy_version 144809 (0.0018) [2023-03-09 11:04:26,280][119383] Updated weights for policy 0, policy_version 144819 (0.0018) [2023-03-09 11:04:27,082][119383] Updated weights for policy 0, policy_version 144829 (0.0014) [2023-03-09 11:04:28,012][119383] Updated weights for policy 0, policy_version 144839 (0.0014) [2023-03-09 11:04:28,822][119383] Updated weights for policy 0, policy_version 144849 (0.0013) [2023-03-09 11:04:28,902][118949] Fps is (10 sec: 193328.2, 60 sec: 194422.5, 300 sec: 194997.4). Total num frames: 2373206016. Throughput: 0: 48717.2. Samples: 93365760. Policy #0 lag: (min: 2.0, avg: 17.0, max: 34.0) [2023-03-09 11:04:28,904][118949] Avg episode reward: [(0, '55.985')] [2023-03-09 11:04:29,642][119383] Updated weights for policy 0, policy_version 144859 (0.0020) [2023-03-09 11:04:29,860][119240] Signal inference workers to stop experience collection... (9350 times) [2023-03-09 11:04:29,883][119240] Signal inference workers to resume experience collection... (9350 times) [2023-03-09 11:04:29,930][119383] InferenceWorker_p0-w0: stopping experience collection (9350 times) [2023-03-09 11:04:29,976][119383] InferenceWorker_p0-w0: resuming experience collection (9350 times) [2023-03-09 11:04:30,626][119383] Updated weights for policy 0, policy_version 144870 (0.0013) [2023-03-09 11:04:31,494][119383] Updated weights for policy 0, policy_version 144880 (0.0015) [2023-03-09 11:04:32,356][119383] Updated weights for policy 0, policy_version 144891 (0.0013) [2023-03-09 11:04:33,172][119383] Updated weights for policy 0, policy_version 144901 (0.0012) [2023-03-09 11:04:33,902][118949] Fps is (10 sec: 194971.5, 60 sec: 194696.8, 300 sec: 195052.7). Total num frames: 2374189056. Throughput: 0: 48762.7. Samples: 93511072. Policy #0 lag: (min: 1.0, avg: 16.5, max: 33.0) [2023-03-09 11:04:33,904][118949] Avg episode reward: [(0, '55.726')] [2023-03-09 11:04:34,068][119383] Updated weights for policy 0, policy_version 144911 (0.0023) [2023-03-09 11:04:34,897][119383] Updated weights for policy 0, policy_version 144921 (0.0024) [2023-03-09 11:04:35,829][119383] Updated weights for policy 0, policy_version 144932 (0.0017) [2023-03-09 11:04:36,610][119383] Updated weights for policy 0, policy_version 144942 (0.0017) [2023-03-09 11:04:37,533][119383] Updated weights for policy 0, policy_version 144953 (0.0023) [2023-03-09 11:04:38,406][119383] Updated weights for policy 0, policy_version 144963 (0.0013) [2023-03-09 11:04:38,902][118949] Fps is (10 sec: 198252.4, 60 sec: 194969.6, 300 sec: 195164.0). Total num frames: 2375188480. Throughput: 0: 48808.9. Samples: 93805872. Policy #0 lag: (min: 1.0, avg: 16.5, max: 33.0) [2023-03-09 11:04:38,903][118949] Avg episode reward: [(0, '55.340')] [2023-03-09 11:04:39,165][119383] Updated weights for policy 0, policy_version 144973 (0.0020) [2023-03-09 11:04:40,029][119240] Signal inference workers to stop experience collection... (9400 times) [2023-03-09 11:04:40,055][119240] Signal inference workers to resume experience collection... (9400 times) [2023-03-09 11:04:40,058][119383] InferenceWorker_p0-w0: stopping experience collection (9400 times) [2023-03-09 11:04:40,058][119383] InferenceWorker_p0-w0: resuming experience collection (9400 times) [2023-03-09 11:04:40,061][119383] Updated weights for policy 0, policy_version 144983 (0.0013) [2023-03-09 11:04:40,746][119383] Updated weights for policy 0, policy_version 144993 (0.0017) [2023-03-09 11:04:41,611][119383] Updated weights for policy 0, policy_version 145003 (0.0013) [2023-03-09 11:04:42,508][119383] Updated weights for policy 0, policy_version 145013 (0.0032) [2023-03-09 11:04:43,289][119383] Updated weights for policy 0, policy_version 145023 (0.0016) [2023-03-09 11:04:43,902][118949] Fps is (10 sec: 196607.0, 60 sec: 194968.4, 300 sec: 195163.9). Total num frames: 2376155136. Throughput: 0: 48811.6. Samples: 94098688. Policy #0 lag: (min: 1.0, avg: 16.5, max: 33.0) [2023-03-09 11:04:43,904][118949] Avg episode reward: [(0, '56.268')] [2023-03-09 11:04:44,184][119383] Updated weights for policy 0, policy_version 145033 (0.0017) [2023-03-09 11:04:45,095][119383] Updated weights for policy 0, policy_version 145043 (0.0024) [2023-03-09 11:04:45,852][119383] Updated weights for policy 0, policy_version 145053 (0.0022) [2023-03-09 11:04:46,765][119383] Updated weights for policy 0, policy_version 145063 (0.0013) [2023-03-09 11:04:47,658][119383] Updated weights for policy 0, policy_version 145073 (0.0013) [2023-03-09 11:04:48,364][119240] Signal inference workers to stop experience collection... (9450 times) [2023-03-09 11:04:48,366][119240] Signal inference workers to resume experience collection... (9450 times) [2023-03-09 11:04:48,392][119383] Updated weights for policy 0, policy_version 145083 (0.0020) [2023-03-09 11:04:48,432][119383] InferenceWorker_p0-w0: stopping experience collection (9450 times) [2023-03-09 11:04:48,433][119383] InferenceWorker_p0-w0: resuming experience collection (9450 times) [2023-03-09 11:04:48,902][118949] Fps is (10 sec: 196605.8, 60 sec: 195789.5, 300 sec: 195163.9). Total num frames: 2377154560. Throughput: 0: 48811.4. Samples: 94246064. Policy #0 lag: (min: 1.0, avg: 16.5, max: 33.0) [2023-03-09 11:04:48,903][118949] Avg episode reward: [(0, '54.281')] [2023-03-09 11:04:49,230][119383] Updated weights for policy 0, policy_version 145093 (0.0025) [2023-03-09 11:04:50,070][119383] Updated weights for policy 0, policy_version 145103 (0.0031) [2023-03-09 11:04:50,934][119383] Updated weights for policy 0, policy_version 145114 (0.0026) [2023-03-09 11:04:51,847][119383] Updated weights for policy 0, policy_version 145124 (0.0022) [2023-03-09 11:04:52,752][119383] Updated weights for policy 0, policy_version 145134 (0.0013) [2023-03-09 11:04:53,579][119383] Updated weights for policy 0, policy_version 145144 (0.0013) [2023-03-09 11:04:53,902][118949] Fps is (10 sec: 196614.9, 60 sec: 195516.8, 300 sec: 195164.1). Total num frames: 2378121216. Throughput: 0: 48814.3. Samples: 94538880. Policy #0 lag: (min: 1.0, avg: 16.5, max: 33.0) [2023-03-09 11:04:53,903][118949] Avg episode reward: [(0, '56.690')] [2023-03-09 11:04:54,310][119383] Updated weights for policy 0, policy_version 145154 (0.0025) [2023-03-09 11:04:55,209][119383] Updated weights for policy 0, policy_version 145164 (0.0016) [2023-03-09 11:04:56,116][119383] Updated weights for policy 0, policy_version 145174 (0.0027) [2023-03-09 11:04:56,691][119240] Signal inference workers to stop experience collection... (9500 times) [2023-03-09 11:04:56,712][119240] Signal inference workers to resume experience collection... (9500 times) [2023-03-09 11:04:56,779][119383] InferenceWorker_p0-w0: stopping experience collection (9500 times) [2023-03-09 11:04:56,779][119383] InferenceWorker_p0-w0: resuming experience collection (9500 times) [2023-03-09 11:04:56,825][119383] Updated weights for policy 0, policy_version 145185 (0.0019) [2023-03-09 11:04:57,768][119383] Updated weights for policy 0, policy_version 145195 (0.0014) [2023-03-09 11:04:58,644][119383] Updated weights for policy 0, policy_version 145205 (0.0018) [2023-03-09 11:04:58,902][118949] Fps is (10 sec: 191688.5, 60 sec: 194969.3, 300 sec: 194997.2). Total num frames: 2379071488. Throughput: 0: 48813.6. Samples: 94831616. Policy #0 lag: (min: 1.0, avg: 16.5, max: 33.0) [2023-03-09 11:04:58,904][118949] Avg episode reward: [(0, '54.840')] [2023-03-09 11:04:59,416][119383] Updated weights for policy 0, policy_version 145215 (0.0026) [2023-03-09 11:05:00,427][119383] Updated weights for policy 0, policy_version 145226 (0.0020) [2023-03-09 11:05:01,261][119383] Updated weights for policy 0, policy_version 145236 (0.0019) [2023-03-09 11:05:02,013][119383] Updated weights for policy 0, policy_version 145246 (0.0017) [2023-03-09 11:05:02,936][119383] Updated weights for policy 0, policy_version 145256 (0.0013) [2023-03-09 11:05:03,803][119383] Updated weights for policy 0, policy_version 145266 (0.0016) [2023-03-09 11:05:03,902][118949] Fps is (10 sec: 193324.0, 60 sec: 194968.8, 300 sec: 195108.4). Total num frames: 2380054528. Throughput: 0: 48769.5. Samples: 94976960. Policy #0 lag: (min: 1.0, avg: 16.5, max: 33.0) [2023-03-09 11:05:03,905][118949] Avg episode reward: [(0, '55.990')] [2023-03-09 11:05:04,578][119383] Updated weights for policy 0, policy_version 145276 (0.0017) [2023-03-09 11:05:05,501][119383] Updated weights for policy 0, policy_version 145287 (0.0013) [2023-03-09 11:05:06,405][119240] Signal inference workers to stop experience collection... (9550 times) [2023-03-09 11:05:06,421][119240] Signal inference workers to resume experience collection... (9550 times) [2023-03-09 11:05:06,464][119383] Updated weights for policy 0, policy_version 145297 (0.0035) [2023-03-09 11:05:06,503][119383] InferenceWorker_p0-w0: stopping experience collection (9550 times) [2023-03-09 11:05:06,503][119383] InferenceWorker_p0-w0: resuming experience collection (9550 times) [2023-03-09 11:05:07,182][119383] Updated weights for policy 0, policy_version 145307 (0.0016) [2023-03-09 11:05:08,129][119383] Updated weights for policy 0, policy_version 145317 (0.0018) [2023-03-09 11:05:08,902][118949] Fps is (10 sec: 196613.7, 60 sec: 195515.8, 300 sec: 195108.6). Total num frames: 2381037568. Throughput: 0: 48816.0. Samples: 95269728. Policy #0 lag: (min: 1.0, avg: 16.5, max: 33.0) [2023-03-09 11:05:08,903][118949] Avg episode reward: [(0, '53.900')] [2023-03-09 11:05:08,909][119383] Updated weights for policy 0, policy_version 145327 (0.0016) [2023-03-09 11:05:09,733][119383] Updated weights for policy 0, policy_version 145337 (0.0031) [2023-03-09 11:05:10,627][119383] Updated weights for policy 0, policy_version 145347 (0.0014) [2023-03-09 11:05:11,387][119383] Updated weights for policy 0, policy_version 145357 (0.0018) [2023-03-09 11:05:12,288][119383] Updated weights for policy 0, policy_version 145367 (0.0016) [2023-03-09 11:05:12,938][119383] Updated weights for policy 0, policy_version 145377 (0.0023) [2023-03-09 11:05:13,881][119383] Updated weights for policy 0, policy_version 145387 (0.0034) [2023-03-09 11:05:13,902][118949] Fps is (10 sec: 196614.9, 60 sec: 194969.9, 300 sec: 195219.5). Total num frames: 2382020608. Throughput: 0: 48814.9. Samples: 95562416. Policy #0 lag: (min: 1.0, avg: 16.5, max: 33.0) [2023-03-09 11:05:13,903][118949] Avg episode reward: [(0, '56.208')] [2023-03-09 11:05:14,778][119383] Updated weights for policy 0, policy_version 145397 (0.0018) [2023-03-09 11:05:15,526][119383] Updated weights for policy 0, policy_version 145407 (0.0019) [2023-03-09 11:05:16,142][119240] Signal inference workers to stop experience collection... (9600 times) [2023-03-09 11:05:16,143][119240] Signal inference workers to resume experience collection... (9600 times) [2023-03-09 11:05:16,247][119383] InferenceWorker_p0-w0: stopping experience collection (9600 times) [2023-03-09 11:05:16,247][119383] InferenceWorker_p0-w0: resuming experience collection (9600 times) [2023-03-09 11:05:16,546][119383] Updated weights for policy 0, policy_version 145418 (0.0026) [2023-03-09 11:05:17,370][119383] Updated weights for policy 0, policy_version 145428 (0.0016) [2023-03-09 11:05:18,129][119383] Updated weights for policy 0, policy_version 145438 (0.0016) [2023-03-09 11:05:18,902][118949] Fps is (10 sec: 193331.9, 60 sec: 194970.1, 300 sec: 195108.5). Total num frames: 2382970880. Throughput: 0: 48860.1. Samples: 95709760. Policy #0 lag: (min: 1.0, avg: 16.5, max: 33.0) [2023-03-09 11:05:18,903][118949] Avg episode reward: [(0, '55.557')] [2023-03-09 11:05:19,046][119383] Updated weights for policy 0, policy_version 145448 (0.0020) [2023-03-09 11:05:19,914][119383] Updated weights for policy 0, policy_version 145458 (0.0033) [2023-03-09 11:05:20,709][119383] Updated weights for policy 0, policy_version 145468 (0.0019) [2023-03-09 11:05:21,609][119383] Updated weights for policy 0, policy_version 145478 (0.0032) [2023-03-09 11:05:22,504][119383] Updated weights for policy 0, policy_version 145488 (0.0013) [2023-03-09 11:05:23,189][119383] Updated weights for policy 0, policy_version 145498 (0.0030) [2023-03-09 11:05:23,902][118949] Fps is (10 sec: 194965.3, 60 sec: 195516.2, 300 sec: 195275.1). Total num frames: 2383970304. Throughput: 0: 48815.4. Samples: 96002576. Policy #0 lag: (min: 1.0, avg: 16.5, max: 33.0) [2023-03-09 11:05:23,904][118949] Avg episode reward: [(0, '56.350')] [2023-03-09 11:05:23,908][119240] Saving /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000145506_2383970304.pth... [2023-03-09 11:05:23,980][119240] Removing /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000142650_2337177600.pth [2023-03-09 11:05:24,121][119383] Updated weights for policy 0, policy_version 145508 (0.0020) [2023-03-09 11:05:25,022][119383] Updated weights for policy 0, policy_version 145519 (0.0016) [2023-03-09 11:05:25,650][119240] Signal inference workers to stop experience collection... (9650 times) [2023-03-09 11:05:25,677][119240] Signal inference workers to resume experience collection... (9650 times) [2023-03-09 11:05:25,722][119383] InferenceWorker_p0-w0: stopping experience collection (9650 times) [2023-03-09 11:05:25,726][119383] InferenceWorker_p0-w0: resuming experience collection (9650 times) [2023-03-09 11:05:25,855][119383] Updated weights for policy 0, policy_version 145530 (0.0023) [2023-03-09 11:05:26,769][119383] Updated weights for policy 0, policy_version 145540 (0.0018) [2023-03-09 11:05:27,586][119383] Updated weights for policy 0, policy_version 145550 (0.0025) [2023-03-09 11:05:28,445][119383] Updated weights for policy 0, policy_version 145560 (0.0016) [2023-03-09 11:05:28,902][118949] Fps is (10 sec: 198246.3, 60 sec: 195789.7, 300 sec: 195220.0). Total num frames: 2384953344. Throughput: 0: 48816.7. Samples: 96295424. Policy #0 lag: (min: 1.0, avg: 16.5, max: 33.0) [2023-03-09 11:05:28,904][118949] Avg episode reward: [(0, '55.756')] [2023-03-09 11:05:29,234][119383] Updated weights for policy 0, policy_version 145570 (0.0017) [2023-03-09 11:05:30,049][119383] Updated weights for policy 0, policy_version 145580 (0.0013) [2023-03-09 11:05:30,931][119383] Updated weights for policy 0, policy_version 145590 (0.0026) [2023-03-09 11:05:31,655][119383] Updated weights for policy 0, policy_version 145600 (0.0025) [2023-03-09 11:05:32,613][119383] Updated weights for policy 0, policy_version 145610 (0.0016) [2023-03-09 11:05:33,442][119383] Updated weights for policy 0, policy_version 145620 (0.0021) [2023-03-09 11:05:33,902][118949] Fps is (10 sec: 194974.3, 60 sec: 195516.7, 300 sec: 195052.9). Total num frames: 2385920000. Throughput: 0: 48815.4. Samples: 96442752. Policy #0 lag: (min: 1.0, avg: 16.6, max: 32.0) [2023-03-09 11:05:33,903][118949] Avg episode reward: [(0, '53.163')] [2023-03-09 11:05:34,255][119383] Updated weights for policy 0, policy_version 145630 (0.0013) [2023-03-09 11:05:35,154][119383] Updated weights for policy 0, policy_version 145640 (0.0024) [2023-03-09 11:05:35,208][119240] Signal inference workers to stop experience collection... (9700 times) [2023-03-09 11:05:35,210][119240] Signal inference workers to resume experience collection... (9700 times) [2023-03-09 11:05:35,238][119383] InferenceWorker_p0-w0: stopping experience collection (9700 times) [2023-03-09 11:05:35,239][119383] InferenceWorker_p0-w0: resuming experience collection (9700 times) [2023-03-09 11:05:36,064][119383] Updated weights for policy 0, policy_version 145650 (0.0016) [2023-03-09 11:05:36,785][119383] Updated weights for policy 0, policy_version 145660 (0.0020) [2023-03-09 11:05:37,718][119383] Updated weights for policy 0, policy_version 145670 (0.0023) [2023-03-09 11:05:38,615][119383] Updated weights for policy 0, policy_version 145680 (0.0019) [2023-03-09 11:05:38,902][118949] Fps is (10 sec: 193332.1, 60 sec: 194969.7, 300 sec: 195108.6). Total num frames: 2386886656. Throughput: 0: 48768.8. Samples: 96733472. Policy #0 lag: (min: 1.0, avg: 16.6, max: 32.0) [2023-03-09 11:05:38,903][118949] Avg episode reward: [(0, '56.491')] [2023-03-09 11:05:39,299][119383] Updated weights for policy 0, policy_version 145690 (0.0024) [2023-03-09 11:05:40,188][119383] Updated weights for policy 0, policy_version 145700 (0.0013) [2023-03-09 11:05:41,124][119383] Updated weights for policy 0, policy_version 145711 (0.0019) [2023-03-09 11:05:41,912][119383] Updated weights for policy 0, policy_version 145721 (0.0013) [2023-03-09 11:05:42,783][119383] Updated weights for policy 0, policy_version 145731 (0.0021) [2023-03-09 11:05:43,527][119383] Updated weights for policy 0, policy_version 145741 (0.0033) [2023-03-09 11:05:43,902][118949] Fps is (10 sec: 194962.3, 60 sec: 195242.6, 300 sec: 195219.5). Total num frames: 2387869696. Throughput: 0: 48859.0. Samples: 97030272. Policy #0 lag: (min: 1.0, avg: 16.6, max: 32.0) [2023-03-09 11:05:43,905][118949] Avg episode reward: [(0, '55.854')] [2023-03-09 11:05:44,406][119383] Updated weights for policy 0, policy_version 145751 (0.0017) [2023-03-09 11:05:45,121][119383] Updated weights for policy 0, policy_version 145761 (0.0017) [2023-03-09 11:05:46,003][119383] Updated weights for policy 0, policy_version 145771 (0.0024) [2023-03-09 11:05:46,887][119383] Updated weights for policy 0, policy_version 145781 (0.0027) [2023-03-09 11:05:47,498][119240] Signal inference workers to stop experience collection... (9750 times) [2023-03-09 11:05:47,499][119240] Signal inference workers to resume experience collection... (9750 times) [2023-03-09 11:05:47,586][119383] InferenceWorker_p0-w0: stopping experience collection (9750 times) [2023-03-09 11:05:47,586][119383] InferenceWorker_p0-w0: resuming experience collection (9750 times) [2023-03-09 11:05:47,635][119383] Updated weights for policy 0, policy_version 145791 (0.0016) [2023-03-09 11:05:48,599][119383] Updated weights for policy 0, policy_version 145802 (0.0021) [2023-03-09 11:05:48,902][118949] Fps is (10 sec: 198238.7, 60 sec: 195241.9, 300 sec: 195274.9). Total num frames: 2388869120. Throughput: 0: 48905.6. Samples: 97177712. Policy #0 lag: (min: 1.0, avg: 16.6, max: 32.0) [2023-03-09 11:05:48,904][118949] Avg episode reward: [(0, '54.832')] [2023-03-09 11:05:49,458][119383] Updated weights for policy 0, policy_version 145812 (0.0013) [2023-03-09 11:05:50,241][119383] Updated weights for policy 0, policy_version 145822 (0.0013) [2023-03-09 11:05:51,169][119383] Updated weights for policy 0, policy_version 145833 (0.0022) [2023-03-09 11:05:52,091][119383] Updated weights for policy 0, policy_version 145843 (0.0013) [2023-03-09 11:05:52,928][119383] Updated weights for policy 0, policy_version 145853 (0.0017) [2023-03-09 11:05:53,804][119383] Updated weights for policy 0, policy_version 145863 (0.0020) [2023-03-09 11:05:53,902][118949] Fps is (10 sec: 198246.4, 60 sec: 195514.5, 300 sec: 195274.8). Total num frames: 2389852160. Throughput: 0: 48904.2. Samples: 97470432. Policy #0 lag: (min: 1.0, avg: 16.6, max: 32.0) [2023-03-09 11:05:53,904][118949] Avg episode reward: [(0, '56.385')] [2023-03-09 11:05:54,651][119383] Updated weights for policy 0, policy_version 145873 (0.0013) [2023-03-09 11:05:55,510][119383] Updated weights for policy 0, policy_version 145884 (0.0013) [2023-03-09 11:05:56,368][119383] Updated weights for policy 0, policy_version 145894 (0.0031) [2023-03-09 11:05:57,301][119383] Updated weights for policy 0, policy_version 145904 (0.0029) [2023-03-09 11:05:57,951][119383] Updated weights for policy 0, policy_version 145914 (0.0024) [2023-03-09 11:05:58,244][119240] Signal inference workers to stop experience collection... (9800 times) [2023-03-09 11:05:58,270][119240] Signal inference workers to resume experience collection... (9800 times) [2023-03-09 11:05:58,274][119383] InferenceWorker_p0-w0: stopping experience collection (9800 times) [2023-03-09 11:05:58,277][119383] InferenceWorker_p0-w0: resuming experience collection (9800 times) [2023-03-09 11:05:58,902][118949] Fps is (10 sec: 194970.3, 60 sec: 195788.9, 300 sec: 195219.6). Total num frames: 2390818816. Throughput: 0: 48995.6. Samples: 97767232. Policy #0 lag: (min: 1.0, avg: 16.6, max: 32.0) [2023-03-09 11:05:58,904][118949] Avg episode reward: [(0, '54.097')] [2023-03-09 11:05:58,961][119383] Updated weights for policy 0, policy_version 145925 (0.0019) [2023-03-09 11:05:59,773][119383] Updated weights for policy 0, policy_version 145935 (0.0013) [2023-03-09 11:06:00,552][119383] Updated weights for policy 0, policy_version 145945 (0.0020) [2023-03-09 11:06:01,511][119383] Updated weights for policy 0, policy_version 145956 (0.0017) [2023-03-09 11:06:02,299][119383] Updated weights for policy 0, policy_version 145966 (0.0025) [2023-03-09 11:06:03,180][119383] Updated weights for policy 0, policy_version 145977 (0.0023) [2023-03-09 11:06:03,902][118949] Fps is (10 sec: 196615.6, 60 sec: 196063.1, 300 sec: 195330.6). Total num frames: 2391818240. Throughput: 0: 48995.9. Samples: 97914576. Policy #0 lag: (min: 1.0, avg: 16.6, max: 32.0) [2023-03-09 11:06:03,903][118949] Avg episode reward: [(0, '53.214')] [2023-03-09 11:06:04,081][119383] Updated weights for policy 0, policy_version 145987 (0.0019) [2023-03-09 11:06:04,941][119383] Updated weights for policy 0, policy_version 145998 (0.0014) [2023-03-09 11:06:05,841][119383] Updated weights for policy 0, policy_version 146008 (0.0023) [2023-03-09 11:06:06,573][119383] Updated weights for policy 0, policy_version 146018 (0.0026) [2023-03-09 11:06:07,427][119383] Updated weights for policy 0, policy_version 146028 (0.0013) [2023-03-09 11:06:08,365][119383] Updated weights for policy 0, policy_version 146038 (0.0016) [2023-03-09 11:06:08,815][119240] Signal inference workers to stop experience collection... (9850 times) [2023-03-09 11:06:08,832][119240] Signal inference workers to resume experience collection... (9850 times) [2023-03-09 11:06:08,853][119383] InferenceWorker_p0-w0: stopping experience collection (9850 times) [2023-03-09 11:06:08,854][119383] InferenceWorker_p0-w0: resuming experience collection (9850 times) [2023-03-09 11:06:08,902][118949] Fps is (10 sec: 198247.8, 60 sec: 196061.2, 300 sec: 195219.6). Total num frames: 2392801280. Throughput: 0: 49085.9. Samples: 98211440. Policy #0 lag: (min: 1.0, avg: 16.6, max: 32.0) [2023-03-09 11:06:08,904][118949] Avg episode reward: [(0, '56.022')] [2023-03-09 11:06:09,020][119383] Updated weights for policy 0, policy_version 146048 (0.0016) [2023-03-09 11:06:09,936][119383] Updated weights for policy 0, policy_version 146058 (0.0013) [2023-03-09 11:06:10,794][119383] Updated weights for policy 0, policy_version 146068 (0.0013) [2023-03-09 11:06:11,565][119383] Updated weights for policy 0, policy_version 146078 (0.0020) [2023-03-09 11:06:12,416][119383] Updated weights for policy 0, policy_version 146088 (0.0039) [2023-03-09 11:06:13,301][119383] Updated weights for policy 0, policy_version 146098 (0.0013) [2023-03-09 11:06:13,902][118949] Fps is (10 sec: 198241.5, 60 sec: 196334.2, 300 sec: 195330.5). Total num frames: 2393800704. Throughput: 0: 49174.1. Samples: 98508272. Policy #0 lag: (min: 1.0, avg: 16.6, max: 32.0) [2023-03-09 11:06:13,904][118949] Avg episode reward: [(0, '56.984')] [2023-03-09 11:06:14,158][119383] Updated weights for policy 0, policy_version 146109 (0.0023) [2023-03-09 11:06:15,056][119383] Updated weights for policy 0, policy_version 146119 (0.0025) [2023-03-09 11:06:16,007][119383] Updated weights for policy 0, policy_version 146130 (0.0021) [2023-03-09 11:06:16,755][119383] Updated weights for policy 0, policy_version 146140 (0.0017) [2023-03-09 11:06:17,690][119383] Updated weights for policy 0, policy_version 146150 (0.0030) [2023-03-09 11:06:18,530][119383] Updated weights for policy 0, policy_version 146160 (0.0025) [2023-03-09 11:06:18,902][118949] Fps is (10 sec: 196607.4, 60 sec: 196607.1, 300 sec: 195275.2). Total num frames: 2394767360. Throughput: 0: 49129.3. Samples: 98653584. Policy #0 lag: (min: 1.0, avg: 16.6, max: 32.0) [2023-03-09 11:06:18,904][118949] Avg episode reward: [(0, '55.484')] [2023-03-09 11:06:19,253][119383] Updated weights for policy 0, policy_version 146170 (0.0022) [2023-03-09 11:06:19,332][119240] Signal inference workers to stop experience collection... (9900 times) [2023-03-09 11:06:19,348][119240] Signal inference workers to resume experience collection... (9900 times) [2023-03-09 11:06:19,416][119383] InferenceWorker_p0-w0: stopping experience collection (9900 times) [2023-03-09 11:06:19,416][119383] InferenceWorker_p0-w0: resuming experience collection (9900 times) [2023-03-09 11:06:20,106][119383] Updated weights for policy 0, policy_version 146180 (0.0019) [2023-03-09 11:06:20,891][119383] Updated weights for policy 0, policy_version 146190 (0.0017) [2023-03-09 11:06:21,744][119383] Updated weights for policy 0, policy_version 146200 (0.0032) [2023-03-09 11:06:22,526][119383] Updated weights for policy 0, policy_version 146210 (0.0014) [2023-03-09 11:06:23,493][119383] Updated weights for policy 0, policy_version 146221 (0.0014) [2023-03-09 11:06:23,902][118949] Fps is (10 sec: 193329.2, 60 sec: 196061.5, 300 sec: 195275.1). Total num frames: 2395734016. Throughput: 0: 49262.9. Samples: 98950320. Policy #0 lag: (min: 1.0, avg: 16.6, max: 32.0) [2023-03-09 11:06:23,904][118949] Avg episode reward: [(0, '56.276')] [2023-03-09 11:06:24,384][119383] Updated weights for policy 0, policy_version 146231 (0.0024) [2023-03-09 11:06:25,115][119383] Updated weights for policy 0, policy_version 146241 (0.0025) [2023-03-09 11:06:26,086][119383] Updated weights for policy 0, policy_version 146252 (0.0013) [2023-03-09 11:06:26,990][119383] Updated weights for policy 0, policy_version 146262 (0.0013) [2023-03-09 11:06:27,664][119383] Updated weights for policy 0, policy_version 146272 (0.0016) [2023-03-09 11:06:28,612][119383] Updated weights for policy 0, policy_version 146282 (0.0028) [2023-03-09 11:06:28,902][118949] Fps is (10 sec: 196608.0, 60 sec: 196334.1, 300 sec: 195330.4). Total num frames: 2396733440. Throughput: 0: 49174.5. Samples: 99243120. Policy #0 lag: (min: 1.0, avg: 16.6, max: 32.0) [2023-03-09 11:06:28,904][118949] Avg episode reward: [(0, '55.498')] [2023-03-09 11:06:29,491][119383] Updated weights for policy 0, policy_version 146292 (0.0014) [2023-03-09 11:06:30,156][119240] Signal inference workers to stop experience collection... (9950 times) [2023-03-09 11:06:30,172][119240] Signal inference workers to resume experience collection... (9950 times) [2023-03-09 11:06:30,200][119383] InferenceWorker_p0-w0: stopping experience collection (9950 times) [2023-03-09 11:06:30,200][119383] InferenceWorker_p0-w0: resuming experience collection (9950 times) [2023-03-09 11:06:30,246][119383] Updated weights for policy 0, policy_version 146302 (0.0014) [2023-03-09 11:06:31,105][119383] Updated weights for policy 0, policy_version 146312 (0.0013) [2023-03-09 11:06:32,020][119383] Updated weights for policy 0, policy_version 146322 (0.0032) [2023-03-09 11:06:32,803][119383] Updated weights for policy 0, policy_version 146332 (0.0030) [2023-03-09 11:06:33,656][119383] Updated weights for policy 0, policy_version 146342 (0.0024) [2023-03-09 11:06:33,902][118949] Fps is (10 sec: 198253.2, 60 sec: 196608.0, 300 sec: 195330.7). Total num frames: 2397716480. Throughput: 0: 49174.4. Samples: 99390544. Policy #0 lag: (min: 1.0, avg: 16.6, max: 32.0) [2023-03-09 11:06:33,903][118949] Avg episode reward: [(0, '56.084')] [2023-03-09 11:06:34,519][119383] Updated weights for policy 0, policy_version 146352 (0.0017) [2023-03-09 11:06:35,400][119383] Updated weights for policy 0, policy_version 146363 (0.0019) [2023-03-09 11:06:36,280][119383] Updated weights for policy 0, policy_version 146373 (0.0024) [2023-03-09 11:06:37,117][119383] Updated weights for policy 0, policy_version 146383 (0.0013) [2023-03-09 11:06:37,881][119383] Updated weights for policy 0, policy_version 146393 (0.0017) [2023-03-09 11:06:38,757][119383] Updated weights for policy 0, policy_version 146403 (0.0014) [2023-03-09 11:06:38,902][118949] Fps is (10 sec: 194974.6, 60 sec: 196607.8, 300 sec: 195164.1). Total num frames: 2398683136. Throughput: 0: 49221.0. Samples: 99685360. Policy #0 lag: (min: 1.0, avg: 17.3, max: 34.0) [2023-03-09 11:06:38,903][118949] Avg episode reward: [(0, '54.578')] [2023-03-09 11:06:39,532][119383] Updated weights for policy 0, policy_version 146413 (0.0018) [2023-03-09 11:06:40,397][119383] Updated weights for policy 0, policy_version 146423 (0.0018) [2023-03-09 11:06:40,960][119240] Signal inference workers to stop experience collection... (10000 times) [2023-03-09 11:06:40,961][119240] Signal inference workers to resume experience collection... (10000 times) [2023-03-09 11:06:41,043][119383] InferenceWorker_p0-w0: stopping experience collection (10000 times) [2023-03-09 11:06:41,043][119383] InferenceWorker_p0-w0: resuming experience collection (10000 times) [2023-03-09 11:06:41,164][119383] Updated weights for policy 0, policy_version 146433 (0.0016) [2023-03-09 11:06:41,988][119383] Updated weights for policy 0, policy_version 146443 (0.0022) [2023-03-09 11:06:42,988][119383] Updated weights for policy 0, policy_version 146454 (0.0013) [2023-03-09 11:06:43,698][119383] Updated weights for policy 0, policy_version 146464 (0.0016) [2023-03-09 11:06:43,902][118949] Fps is (10 sec: 198242.0, 60 sec: 197154.6, 300 sec: 195386.0). Total num frames: 2399698944. Throughput: 0: 49174.8. Samples: 99980096. Policy #0 lag: (min: 1.0, avg: 17.3, max: 34.0) [2023-03-09 11:06:43,904][118949] Avg episode reward: [(0, '55.527')] [2023-03-09 11:06:44,631][119383] Updated weights for policy 0, policy_version 146474 (0.0016) [2023-03-09 11:06:45,535][119383] Updated weights for policy 0, policy_version 146484 (0.0016) [2023-03-09 11:06:46,267][119383] Updated weights for policy 0, policy_version 146494 (0.0013) [2023-03-09 11:06:47,144][119383] Updated weights for policy 0, policy_version 146504 (0.0025) [2023-03-09 11:06:48,040][119383] Updated weights for policy 0, policy_version 146514 (0.0022) [2023-03-09 11:06:48,789][119383] Updated weights for policy 0, policy_version 146524 (0.0019) [2023-03-09 11:06:48,902][118949] Fps is (10 sec: 198247.0, 60 sec: 196609.2, 300 sec: 195219.6). Total num frames: 2400665600. Throughput: 0: 49176.2. Samples: 100127504. Policy #0 lag: (min: 1.0, avg: 17.3, max: 34.0) [2023-03-09 11:06:48,903][118949] Avg episode reward: [(0, '54.215')] [2023-03-09 11:06:49,629][119383] Updated weights for policy 0, policy_version 146534 (0.0013) [2023-03-09 11:06:50,569][119383] Updated weights for policy 0, policy_version 146544 (0.0016) [2023-03-09 11:06:51,285][119383] Updated weights for policy 0, policy_version 146554 (0.0021) [2023-03-09 11:06:52,169][119383] Updated weights for policy 0, policy_version 146564 (0.0013) [2023-03-09 11:06:52,945][119383] Updated weights for policy 0, policy_version 146574 (0.0016) [2023-03-09 11:06:53,836][119383] Updated weights for policy 0, policy_version 146584 (0.0022) [2023-03-09 11:06:53,902][118949] Fps is (10 sec: 194973.2, 60 sec: 196609.1, 300 sec: 195275.0). Total num frames: 2401648640. Throughput: 0: 49129.5. Samples: 100422256. Policy #0 lag: (min: 1.0, avg: 17.3, max: 34.0) [2023-03-09 11:06:53,903][118949] Avg episode reward: [(0, '56.728')] [2023-03-09 11:06:54,109][119240] Signal inference workers to stop experience collection... (10050 times) [2023-03-09 11:06:54,132][119240] Signal inference workers to resume experience collection... (10050 times) [2023-03-09 11:06:54,163][119383] InferenceWorker_p0-w0: stopping experience collection (10050 times) [2023-03-09 11:06:54,206][119383] InferenceWorker_p0-w0: resuming experience collection (10050 times) [2023-03-09 11:06:54,798][119383] Updated weights for policy 0, policy_version 146595 (0.0016) [2023-03-09 11:06:55,547][119383] Updated weights for policy 0, policy_version 146605 (0.0034) [2023-03-09 11:06:56,392][119383] Updated weights for policy 0, policy_version 146615 (0.0027) [2023-03-09 11:06:57,159][119383] Updated weights for policy 0, policy_version 146625 (0.0016) [2023-03-09 11:06:57,977][119383] Updated weights for policy 0, policy_version 146635 (0.0016) [2023-03-09 11:06:58,895][119383] Updated weights for policy 0, policy_version 146645 (0.0013) [2023-03-09 11:06:58,903][118949] Fps is (10 sec: 196594.9, 60 sec: 196879.9, 300 sec: 195330.2). Total num frames: 2402631680. Throughput: 0: 49084.0. Samples: 100717072. Policy #0 lag: (min: 1.0, avg: 17.3, max: 34.0) [2023-03-09 11:06:58,905][118949] Avg episode reward: [(0, '56.674')] [2023-03-09 11:06:59,637][119383] Updated weights for policy 0, policy_version 146655 (0.0016) [2023-03-09 11:07:00,535][119383] Updated weights for policy 0, policy_version 146665 (0.0016) [2023-03-09 11:07:01,379][119383] Updated weights for policy 0, policy_version 146675 (0.0021) [2023-03-09 11:07:02,162][119383] Updated weights for policy 0, policy_version 146685 (0.0016) [2023-03-09 11:07:03,085][119383] Updated weights for policy 0, policy_version 146695 (0.0018) [2023-03-09 11:07:03,902][118949] Fps is (10 sec: 194970.5, 60 sec: 196334.9, 300 sec: 195275.0). Total num frames: 2403598336. Throughput: 0: 49132.4. Samples: 100864528. Policy #0 lag: (min: 1.0, avg: 17.3, max: 34.0) [2023-03-09 11:07:03,903][118949] Avg episode reward: [(0, '53.745')] [2023-03-09 11:07:03,959][119383] Updated weights for policy 0, policy_version 146705 (0.0014) [2023-03-09 11:07:04,674][119383] Updated weights for policy 0, policy_version 146715 (0.0019) [2023-03-09 11:07:05,604][119383] Updated weights for policy 0, policy_version 146725 (0.0013) [2023-03-09 11:07:06,413][119383] Updated weights for policy 0, policy_version 146735 (0.0013) [2023-03-09 11:07:06,602][119240] Signal inference workers to stop experience collection... (10100 times) [2023-03-09 11:07:06,603][119240] Signal inference workers to resume experience collection... (10100 times) [2023-03-09 11:07:06,662][119383] InferenceWorker_p0-w0: stopping experience collection (10100 times) [2023-03-09 11:07:06,662][119383] InferenceWorker_p0-w0: resuming experience collection (10100 times) [2023-03-09 11:07:07,251][119383] Updated weights for policy 0, policy_version 146745 (0.0030) [2023-03-09 11:07:08,073][119383] Updated weights for policy 0, policy_version 146755 (0.0021) [2023-03-09 11:07:08,867][119383] Updated weights for policy 0, policy_version 146765 (0.0014) [2023-03-09 11:07:08,902][118949] Fps is (10 sec: 196618.9, 60 sec: 196608.5, 300 sec: 195441.8). Total num frames: 2404597760. Throughput: 0: 49044.5. Samples: 101157312. Policy #0 lag: (min: 1.0, avg: 17.3, max: 34.0) [2023-03-09 11:07:08,903][118949] Avg episode reward: [(0, '56.529')] [2023-03-09 11:07:09,777][119383] Updated weights for policy 0, policy_version 146775 (0.0029) [2023-03-09 11:07:10,518][119383] Updated weights for policy 0, policy_version 146785 (0.0017) [2023-03-09 11:07:11,360][119383] Updated weights for policy 0, policy_version 146795 (0.0023) [2023-03-09 11:07:12,255][119383] Updated weights for policy 0, policy_version 146805 (0.0013) [2023-03-09 11:07:13,036][119383] Updated weights for policy 0, policy_version 146815 (0.0030) [2023-03-09 11:07:13,902][118949] Fps is (10 sec: 196600.4, 60 sec: 196061.4, 300 sec: 195385.9). Total num frames: 2405564416. Throughput: 0: 49087.5. Samples: 101452064. Policy #0 lag: (min: 1.0, avg: 17.3, max: 34.0) [2023-03-09 11:07:13,904][118949] Avg episode reward: [(0, '56.275')] [2023-03-09 11:07:13,940][119383] Updated weights for policy 0, policy_version 146825 (0.0014) [2023-03-09 11:07:14,833][119383] Updated weights for policy 0, policy_version 146835 (0.0020) [2023-03-09 11:07:15,569][119383] Updated weights for policy 0, policy_version 146845 (0.0022) [2023-03-09 11:07:16,523][119383] Updated weights for policy 0, policy_version 146856 (0.0023) [2023-03-09 11:07:17,412][119383] Updated weights for policy 0, policy_version 146866 (0.0014) [2023-03-09 11:07:17,790][119240] Signal inference workers to stop experience collection... (10150 times) [2023-03-09 11:07:17,791][119240] Signal inference workers to resume experience collection... (10150 times) [2023-03-09 11:07:17,862][119383] InferenceWorker_p0-w0: stopping experience collection (10150 times) [2023-03-09 11:07:17,862][119383] InferenceWorker_p0-w0: resuming experience collection (10150 times) [2023-03-09 11:07:18,198][119383] Updated weights for policy 0, policy_version 146876 (0.0022) [2023-03-09 11:07:18,902][118949] Fps is (10 sec: 194963.1, 60 sec: 196334.4, 300 sec: 195441.4). Total num frames: 2406547456. Throughput: 0: 49087.2. Samples: 101599488. Policy #0 lag: (min: 1.0, avg: 17.3, max: 34.0) [2023-03-09 11:07:18,904][118949] Avg episode reward: [(0, '53.879')] [2023-03-09 11:07:19,026][119383] Updated weights for policy 0, policy_version 146886 (0.0020) [2023-03-09 11:07:19,961][119383] Updated weights for policy 0, policy_version 146896 (0.0022) [2023-03-09 11:07:20,664][119383] Updated weights for policy 0, policy_version 146906 (0.0013) [2023-03-09 11:07:21,526][119383] Updated weights for policy 0, policy_version 146916 (0.0018) [2023-03-09 11:07:22,273][119383] Updated weights for policy 0, policy_version 146926 (0.0022) [2023-03-09 11:07:23,145][119383] Updated weights for policy 0, policy_version 146936 (0.0022) [2023-03-09 11:07:23,902][118949] Fps is (10 sec: 198253.5, 60 sec: 196882.2, 300 sec: 195442.0). Total num frames: 2407546880. Throughput: 0: 49132.4. Samples: 101896320. Policy #0 lag: (min: 1.0, avg: 17.3, max: 34.0) [2023-03-09 11:07:23,903][118949] Avg episode reward: [(0, '55.482')] [2023-03-09 11:07:23,913][119240] Saving /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000146945_2407546880.pth... [2023-03-09 11:07:23,978][119240] Removing /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000144078_2360573952.pth [2023-03-09 11:07:24,078][119383] Updated weights for policy 0, policy_version 146946 (0.0014) [2023-03-09 11:07:24,843][119383] Updated weights for policy 0, policy_version 146956 (0.0020) [2023-03-09 11:07:25,726][119383] Updated weights for policy 0, policy_version 146966 (0.0014) [2023-03-09 11:07:26,442][119383] Updated weights for policy 0, policy_version 146976 (0.0017) [2023-03-09 11:07:27,251][119240] Signal inference workers to stop experience collection... (10200 times) [2023-03-09 11:07:27,275][119240] Signal inference workers to resume experience collection... (10200 times) [2023-03-09 11:07:27,322][119383] InferenceWorker_p0-w0: stopping experience collection (10200 times) [2023-03-09 11:07:27,325][119383] Updated weights for policy 0, policy_version 146986 (0.0017) [2023-03-09 11:07:27,362][119383] InferenceWorker_p0-w0: resuming experience collection (10200 times) [2023-03-09 11:07:28,265][119383] Updated weights for policy 0, policy_version 146997 (0.0018) [2023-03-09 11:07:28,902][118949] Fps is (10 sec: 196609.3, 60 sec: 196334.6, 300 sec: 195441.7). Total num frames: 2408513536. Throughput: 0: 49042.3. Samples: 102187008. Policy #0 lag: (min: 1.0, avg: 17.3, max: 34.0) [2023-03-09 11:07:28,904][118949] Avg episode reward: [(0, '53.122')] [2023-03-09 11:07:29,100][119383] Updated weights for policy 0, policy_version 147007 (0.0028) [2023-03-09 11:07:29,973][119383] Updated weights for policy 0, policy_version 147018 (0.0023) [2023-03-09 11:07:30,910][119383] Updated weights for policy 0, policy_version 147028 (0.0017) [2023-03-09 11:07:31,643][119383] Updated weights for policy 0, policy_version 147038 (0.0013) [2023-03-09 11:07:32,552][119383] Updated weights for policy 0, policy_version 147048 (0.0018) [2023-03-09 11:07:33,369][119383] Updated weights for policy 0, policy_version 147058 (0.0015) [2023-03-09 11:07:33,902][118949] Fps is (10 sec: 194963.0, 60 sec: 196333.8, 300 sec: 195497.0). Total num frames: 2409496576. Throughput: 0: 49040.3. Samples: 102334336. Policy #0 lag: (min: 1.0, avg: 17.3, max: 34.0) [2023-03-09 11:07:33,904][118949] Avg episode reward: [(0, '56.452')] [2023-03-09 11:07:34,179][119383] Updated weights for policy 0, policy_version 147068 (0.0024) [2023-03-09 11:07:34,998][119383] Updated weights for policy 0, policy_version 147078 (0.0013) [2023-03-09 11:07:36,025][119383] Updated weights for policy 0, policy_version 147089 (0.0014) [2023-03-09 11:07:36,814][119383] Updated weights for policy 0, policy_version 147099 (0.0013) [2023-03-09 11:07:37,660][119383] Updated weights for policy 0, policy_version 147109 (0.0017) [2023-03-09 11:07:37,948][119240] Signal inference workers to stop experience collection... (10250 times) [2023-03-09 11:07:37,949][119240] Signal inference workers to resume experience collection... (10250 times) [2023-03-09 11:07:37,998][119383] InferenceWorker_p0-w0: stopping experience collection (10250 times) [2023-03-09 11:07:37,998][119383] InferenceWorker_p0-w0: resuming experience collection (10250 times) [2023-03-09 11:07:38,597][119383] Updated weights for policy 0, policy_version 147119 (0.0018) [2023-03-09 11:07:38,902][118949] Fps is (10 sec: 194971.1, 60 sec: 196334.0, 300 sec: 195552.7). Total num frames: 2410463232. Throughput: 0: 49086.0. Samples: 102631136. Policy #0 lag: (min: 1.0, avg: 17.3, max: 34.0) [2023-03-09 11:07:38,904][118949] Avg episode reward: [(0, '55.152')] [2023-03-09 11:07:39,304][119383] Updated weights for policy 0, policy_version 147129 (0.0016) [2023-03-09 11:07:40,307][119383] Updated weights for policy 0, policy_version 147140 (0.0013) [2023-03-09 11:07:41,020][119383] Updated weights for policy 0, policy_version 147150 (0.0013) [2023-03-09 11:07:41,911][119383] Updated weights for policy 0, policy_version 147160 (0.0013) [2023-03-09 11:07:42,746][119383] Updated weights for policy 0, policy_version 147170 (0.0013) [2023-03-09 11:07:43,539][119383] Updated weights for policy 0, policy_version 147180 (0.0022) [2023-03-09 11:07:43,902][118949] Fps is (10 sec: 193333.2, 60 sec: 195515.6, 300 sec: 195497.3). Total num frames: 2411429888. Throughput: 0: 49041.1. Samples: 102923904. Policy #0 lag: (min: 0.0, avg: 16.8, max: 33.0) [2023-03-09 11:07:43,903][118949] Avg episode reward: [(0, '56.624')] [2023-03-09 11:07:44,446][119383] Updated weights for policy 0, policy_version 147190 (0.0018) [2023-03-09 11:07:45,199][119383] Updated weights for policy 0, policy_version 147200 (0.0020) [2023-03-09 11:07:46,120][119383] Updated weights for policy 0, policy_version 147210 (0.0025) [2023-03-09 11:07:46,997][119383] Updated weights for policy 0, policy_version 147220 (0.0019) [2023-03-09 11:07:47,789][119383] Updated weights for policy 0, policy_version 147230 (0.0016) [2023-03-09 11:07:48,651][119383] Updated weights for policy 0, policy_version 147240 (0.0028) [2023-03-09 11:07:48,902][118949] Fps is (10 sec: 196608.4, 60 sec: 196061.0, 300 sec: 195552.6). Total num frames: 2412429312. Throughput: 0: 48993.1. Samples: 103069232. Policy #0 lag: (min: 0.0, avg: 16.8, max: 33.0) [2023-03-09 11:07:48,904][118949] Avg episode reward: [(0, '56.382')] [2023-03-09 11:07:49,525][119383] Updated weights for policy 0, policy_version 147250 (0.0019) [2023-03-09 11:07:50,230][119240] Signal inference workers to stop experience collection... (10300 times) [2023-03-09 11:07:50,232][119240] Signal inference workers to resume experience collection... (10300 times) [2023-03-09 11:07:50,304][119383] InferenceWorker_p0-w0: stopping experience collection (10300 times) [2023-03-09 11:07:50,304][119383] InferenceWorker_p0-w0: resuming experience collection (10300 times) [2023-03-09 11:07:50,311][119383] Updated weights for policy 0, policy_version 147260 (0.0017) [2023-03-09 11:07:51,136][119383] Updated weights for policy 0, policy_version 147270 (0.0018) [2023-03-09 11:07:52,076][119383] Updated weights for policy 0, policy_version 147280 (0.0016) [2023-03-09 11:07:52,816][119383] Updated weights for policy 0, policy_version 147290 (0.0026) [2023-03-09 11:07:53,731][119383] Updated weights for policy 0, policy_version 147300 (0.0019) [2023-03-09 11:07:53,902][118949] Fps is (10 sec: 196606.0, 60 sec: 195787.8, 300 sec: 195608.2). Total num frames: 2413395968. Throughput: 0: 49037.9. Samples: 103364032. Policy #0 lag: (min: 0.0, avg: 16.8, max: 33.0) [2023-03-09 11:07:53,904][118949] Avg episode reward: [(0, '55.762')] [2023-03-09 11:07:54,480][119383] Updated weights for policy 0, policy_version 147310 (0.0015) [2023-03-09 11:07:55,420][119383] Updated weights for policy 0, policy_version 147321 (0.0024) [2023-03-09 11:07:56,324][119383] Updated weights for policy 0, policy_version 147331 (0.0024) [2023-03-09 11:07:57,179][119383] Updated weights for policy 0, policy_version 147342 (0.0024) [2023-03-09 11:07:58,009][119383] Updated weights for policy 0, policy_version 147352 (0.0020) [2023-03-09 11:07:58,886][119383] Updated weights for policy 0, policy_version 147362 (0.0017) [2023-03-09 11:07:58,902][118949] Fps is (10 sec: 194971.5, 60 sec: 195790.4, 300 sec: 195552.7). Total num frames: 2414379008. Throughput: 0: 48947.4. Samples: 103654688. Policy #0 lag: (min: 0.0, avg: 16.8, max: 33.0) [2023-03-09 11:07:58,903][118949] Avg episode reward: [(0, '55.509')] [2023-03-09 11:07:59,651][119383] Updated weights for policy 0, policy_version 147372 (0.0019) [2023-03-09 11:08:00,510][119383] Updated weights for policy 0, policy_version 147382 (0.0017) [2023-03-09 11:08:01,171][119240] Signal inference workers to stop experience collection... (10350 times) [2023-03-09 11:08:01,174][119240] Signal inference workers to resume experience collection... (10350 times) [2023-03-09 11:08:01,221][119383] InferenceWorker_p0-w0: stopping experience collection (10350 times) [2023-03-09 11:08:01,224][119383] Updated weights for policy 0, policy_version 147392 (0.0018) [2023-03-09 11:08:01,260][119383] InferenceWorker_p0-w0: resuming experience collection (10350 times) [2023-03-09 11:08:02,187][119383] Updated weights for policy 0, policy_version 147402 (0.0013) [2023-03-09 11:08:03,051][119383] Updated weights for policy 0, policy_version 147412 (0.0019) [2023-03-09 11:08:03,847][119383] Updated weights for policy 0, policy_version 147423 (0.0013) [2023-03-09 11:08:03,903][118949] Fps is (10 sec: 198240.7, 60 sec: 196332.8, 300 sec: 195719.0). Total num frames: 2415378432. Throughput: 0: 48946.3. Samples: 103802080. Policy #0 lag: (min: 0.0, avg: 16.8, max: 33.0) [2023-03-09 11:08:03,904][118949] Avg episode reward: [(0, '54.840')] [2023-03-09 11:08:04,851][119383] Updated weights for policy 0, policy_version 147433 (0.0024) [2023-03-09 11:08:05,711][119383] Updated weights for policy 0, policy_version 147443 (0.0016) [2023-03-09 11:08:06,476][119383] Updated weights for policy 0, policy_version 147453 (0.0015) [2023-03-09 11:08:07,372][119383] Updated weights for policy 0, policy_version 147463 (0.0016) [2023-03-09 11:08:08,225][119383] Updated weights for policy 0, policy_version 147473 (0.0024) [2023-03-09 11:08:08,902][118949] Fps is (10 sec: 194973.3, 60 sec: 195516.1, 300 sec: 195719.4). Total num frames: 2416328704. Throughput: 0: 48856.2. Samples: 104094848. Policy #0 lag: (min: 0.0, avg: 16.8, max: 33.0) [2023-03-09 11:08:08,903][118949] Avg episode reward: [(0, '59.015')] [2023-03-09 11:08:08,920][119240] Saving new best policy, reward=59.015! [2023-03-09 11:08:09,074][119383] Updated weights for policy 0, policy_version 147483 (0.0013) [2023-03-09 11:08:09,862][119383] Updated weights for policy 0, policy_version 147493 (0.0022) [2023-03-09 11:08:10,722][119383] Updated weights for policy 0, policy_version 147503 (0.0022) [2023-03-09 11:08:11,549][119383] Updated weights for policy 0, policy_version 147513 (0.0017) [2023-03-09 11:08:12,373][119383] Updated weights for policy 0, policy_version 147523 (0.0013) [2023-03-09 11:08:13,153][119383] Updated weights for policy 0, policy_version 147533 (0.0018) [2023-03-09 11:08:13,524][119240] Signal inference workers to stop experience collection... (10400 times) [2023-03-09 11:08:13,525][119240] Signal inference workers to resume experience collection... (10400 times) [2023-03-09 11:08:13,592][119383] InferenceWorker_p0-w0: stopping experience collection (10400 times) [2023-03-09 11:08:13,593][119383] InferenceWorker_p0-w0: resuming experience collection (10400 times) [2023-03-09 11:08:13,902][118949] Fps is (10 sec: 193340.3, 60 sec: 195789.5, 300 sec: 195774.9). Total num frames: 2417311744. Throughput: 0: 48902.3. Samples: 104387600. Policy #0 lag: (min: 0.0, avg: 16.8, max: 33.0) [2023-03-09 11:08:13,904][118949] Avg episode reward: [(0, '56.899')] [2023-03-09 11:08:14,029][119383] Updated weights for policy 0, policy_version 147543 (0.0019) [2023-03-09 11:08:15,006][119383] Updated weights for policy 0, policy_version 147554 (0.0013) [2023-03-09 11:08:15,757][119383] Updated weights for policy 0, policy_version 147564 (0.0013) [2023-03-09 11:08:16,690][119383] Updated weights for policy 0, policy_version 147574 (0.0015) [2023-03-09 11:08:17,409][119383] Updated weights for policy 0, policy_version 147584 (0.0023) [2023-03-09 11:08:18,360][119383] Updated weights for policy 0, policy_version 147594 (0.0013) [2023-03-09 11:08:18,903][118949] Fps is (10 sec: 194955.9, 60 sec: 195514.9, 300 sec: 195663.4). Total num frames: 2418278400. Throughput: 0: 48858.0. Samples: 104532960. Policy #0 lag: (min: 0.0, avg: 16.8, max: 33.0) [2023-03-09 11:08:18,904][118949] Avg episode reward: [(0, '53.996')] [2023-03-09 11:08:19,264][119383] Updated weights for policy 0, policy_version 147604 (0.0024) [2023-03-09 11:08:20,029][119383] Updated weights for policy 0, policy_version 147614 (0.0023) [2023-03-09 11:08:20,958][119383] Updated weights for policy 0, policy_version 147624 (0.0016) [2023-03-09 11:08:21,831][119383] Updated weights for policy 0, policy_version 147634 (0.0013) [2023-03-09 11:08:22,582][119383] Updated weights for policy 0, policy_version 147644 (0.0016) [2023-03-09 11:08:22,598][119240] Signal inference workers to stop experience collection... (10450 times) [2023-03-09 11:08:22,631][119240] Signal inference workers to resume experience collection... (10450 times) [2023-03-09 11:08:22,670][119383] InferenceWorker_p0-w0: stopping experience collection (10450 times) [2023-03-09 11:08:22,711][119383] InferenceWorker_p0-w0: resuming experience collection (10450 times) [2023-03-09 11:08:23,429][119383] Updated weights for policy 0, policy_version 147654 (0.0017) [2023-03-09 11:08:23,902][118949] Fps is (10 sec: 194967.4, 60 sec: 195241.8, 300 sec: 195663.6). Total num frames: 2419261440. Throughput: 0: 48723.6. Samples: 104823696. Policy #0 lag: (min: 0.0, avg: 16.8, max: 33.0) [2023-03-09 11:08:23,904][118949] Avg episode reward: [(0, '53.877')] [2023-03-09 11:08:24,354][119383] Updated weights for policy 0, policy_version 147664 (0.0014) [2023-03-09 11:08:25,156][119383] Updated weights for policy 0, policy_version 147674 (0.0018) [2023-03-09 11:08:25,982][119383] Updated weights for policy 0, policy_version 147684 (0.0019) [2023-03-09 11:08:26,981][119383] Updated weights for policy 0, policy_version 147695 (0.0020) [2023-03-09 11:08:27,744][119383] Updated weights for policy 0, policy_version 147705 (0.0021) [2023-03-09 11:08:28,716][119383] Updated weights for policy 0, policy_version 147715 (0.0017) [2023-03-09 11:08:28,902][118949] Fps is (10 sec: 193334.5, 60 sec: 194969.1, 300 sec: 195608.2). Total num frames: 2420211712. Throughput: 0: 48631.9. Samples: 105112352. Policy #0 lag: (min: 0.0, avg: 16.8, max: 33.0) [2023-03-09 11:08:28,904][118949] Avg episode reward: [(0, '54.152')] [2023-03-09 11:08:29,393][119383] Updated weights for policy 0, policy_version 147725 (0.0016) [2023-03-09 11:08:30,278][119383] Updated weights for policy 0, policy_version 147735 (0.0020) [2023-03-09 11:08:31,131][119383] Updated weights for policy 0, policy_version 147745 (0.0017) [2023-03-09 11:08:31,821][119240] Signal inference workers to stop experience collection... (10500 times) [2023-03-09 11:08:31,845][119240] Signal inference workers to resume experience collection... (10500 times) [2023-03-09 11:08:31,880][119383] InferenceWorker_p0-w0: stopping experience collection (10500 times) [2023-03-09 11:08:31,925][119383] InferenceWorker_p0-w0: resuming experience collection (10500 times) [2023-03-09 11:08:32,018][119383] Updated weights for policy 0, policy_version 147755 (0.0017) [2023-03-09 11:08:32,829][119383] Updated weights for policy 0, policy_version 147765 (0.0014) [2023-03-09 11:08:33,628][119383] Updated weights for policy 0, policy_version 147775 (0.0027) [2023-03-09 11:08:33,902][118949] Fps is (10 sec: 191698.1, 60 sec: 194697.7, 300 sec: 195552.7). Total num frames: 2421178368. Throughput: 0: 48632.8. Samples: 105257696. Policy #0 lag: (min: 0.0, avg: 16.8, max: 33.0) [2023-03-09 11:08:33,903][118949] Avg episode reward: [(0, '54.978')] [2023-03-09 11:08:34,547][119383] Updated weights for policy 0, policy_version 147785 (0.0016) [2023-03-09 11:08:35,486][119383] Updated weights for policy 0, policy_version 147795 (0.0018) [2023-03-09 11:08:36,190][119383] Updated weights for policy 0, policy_version 147805 (0.0026) [2023-03-09 11:08:37,088][119383] Updated weights for policy 0, policy_version 147815 (0.0016) [2023-03-09 11:08:37,984][119383] Updated weights for policy 0, policy_version 147825 (0.0013) [2023-03-09 11:08:38,785][119383] Updated weights for policy 0, policy_version 147835 (0.0014) [2023-03-09 11:08:38,902][118949] Fps is (10 sec: 193341.5, 60 sec: 194697.5, 300 sec: 195552.8). Total num frames: 2422145024. Throughput: 0: 48544.1. Samples: 105548496. Policy #0 lag: (min: 0.0, avg: 16.8, max: 33.0) [2023-03-09 11:08:38,903][118949] Avg episode reward: [(0, '56.175')] [2023-03-09 11:08:39,608][119383] Updated weights for policy 0, policy_version 147845 (0.0016) [2023-03-09 11:08:40,511][119383] Updated weights for policy 0, policy_version 147855 (0.0019) [2023-03-09 11:08:40,603][119240] Signal inference workers to stop experience collection... (10550 times) [2023-03-09 11:08:40,605][119240] Signal inference workers to resume experience collection... (10550 times) [2023-03-09 11:08:40,671][119383] InferenceWorker_p0-w0: stopping experience collection (10550 times) [2023-03-09 11:08:40,671][119383] InferenceWorker_p0-w0: resuming experience collection (10550 times) [2023-03-09 11:08:41,304][119383] Updated weights for policy 0, policy_version 147865 (0.0014) [2023-03-09 11:08:42,167][119383] Updated weights for policy 0, policy_version 147875 (0.0013) [2023-03-09 11:08:42,925][119383] Updated weights for policy 0, policy_version 147885 (0.0032) [2023-03-09 11:08:43,806][119383] Updated weights for policy 0, policy_version 147895 (0.0019) [2023-03-09 11:08:43,902][118949] Fps is (10 sec: 194963.3, 60 sec: 194969.3, 300 sec: 195663.8). Total num frames: 2423128064. Throughput: 0: 48546.3. Samples: 105839280. Policy #0 lag: (min: 1.0, avg: 16.4, max: 33.0) [2023-03-09 11:08:43,904][118949] Avg episode reward: [(0, '54.638')] [2023-03-09 11:08:44,646][119383] Updated weights for policy 0, policy_version 147905 (0.0019) [2023-03-09 11:08:45,476][119383] Updated weights for policy 0, policy_version 147915 (0.0014) [2023-03-09 11:08:46,380][119383] Updated weights for policy 0, policy_version 147925 (0.0016) [2023-03-09 11:08:47,129][119383] Updated weights for policy 0, policy_version 147935 (0.0014) [2023-03-09 11:08:48,124][119383] Updated weights for policy 0, policy_version 147946 (0.0017) [2023-03-09 11:08:48,902][118949] Fps is (10 sec: 193324.9, 60 sec: 194150.3, 300 sec: 195552.8). Total num frames: 2424078336. Throughput: 0: 48501.7. Samples: 105984640. Policy #0 lag: (min: 1.0, avg: 16.4, max: 33.0) [2023-03-09 11:08:48,904][118949] Avg episode reward: [(0, '55.604')] [2023-03-09 11:08:49,022][119383] Updated weights for policy 0, policy_version 147956 (0.0017) [2023-03-09 11:08:49,679][119240] Signal inference workers to stop experience collection... (10600 times) [2023-03-09 11:08:49,704][119240] Signal inference workers to resume experience collection... (10600 times) [2023-03-09 11:08:49,708][119383] InferenceWorker_p0-w0: stopping experience collection (10600 times) [2023-03-09 11:08:49,764][119383] InferenceWorker_p0-w0: resuming experience collection (10600 times) [2023-03-09 11:08:49,768][119383] Updated weights for policy 0, policy_version 147966 (0.0013) [2023-03-09 11:08:50,708][119383] Updated weights for policy 0, policy_version 147976 (0.0013) [2023-03-09 11:08:51,612][119383] Updated weights for policy 0, policy_version 147986 (0.0014) [2023-03-09 11:08:52,355][119383] Updated weights for policy 0, policy_version 147996 (0.0014) [2023-03-09 11:08:53,228][119383] Updated weights for policy 0, policy_version 148006 (0.0018) [2023-03-09 11:08:53,902][118949] Fps is (10 sec: 193331.9, 60 sec: 194423.6, 300 sec: 195552.7). Total num frames: 2425061376. Throughput: 0: 48455.1. Samples: 106275344. Policy #0 lag: (min: 1.0, avg: 16.4, max: 33.0) [2023-03-09 11:08:53,904][118949] Avg episode reward: [(0, '56.401')] [2023-03-09 11:08:54,096][119383] Updated weights for policy 0, policy_version 148016 (0.0050) [2023-03-09 11:08:54,934][119383] Updated weights for policy 0, policy_version 148026 (0.0013) [2023-03-09 11:08:55,765][119383] Updated weights for policy 0, policy_version 148036 (0.0018) [2023-03-09 11:08:56,534][119383] Updated weights for policy 0, policy_version 148046 (0.0017) [2023-03-09 11:08:57,357][119383] Updated weights for policy 0, policy_version 148056 (0.0013) [2023-03-09 11:08:58,276][119383] Updated weights for policy 0, policy_version 148066 (0.0015) [2023-03-09 11:08:58,902][118949] Fps is (10 sec: 196613.7, 60 sec: 194424.0, 300 sec: 195552.8). Total num frames: 2426044416. Throughput: 0: 48501.5. Samples: 106570160. Policy #0 lag: (min: 1.0, avg: 16.4, max: 33.0) [2023-03-09 11:08:58,903][118949] Avg episode reward: [(0, '54.870')] [2023-03-09 11:08:58,996][119383] Updated weights for policy 0, policy_version 148076 (0.0016) [2023-03-09 11:08:59,839][119240] Signal inference workers to stop experience collection... (10650 times) [2023-03-09 11:08:59,842][119240] Signal inference workers to resume experience collection... (10650 times) [2023-03-09 11:08:59,920][119383] InferenceWorker_p0-w0: stopping experience collection (10650 times) [2023-03-09 11:08:59,923][119383] InferenceWorker_p0-w0: resuming experience collection (10650 times) [2023-03-09 11:08:59,926][119383] Updated weights for policy 0, policy_version 148086 (0.0026) [2023-03-09 11:09:00,625][119383] Updated weights for policy 0, policy_version 148096 (0.0019) [2023-03-09 11:09:01,599][119383] Updated weights for policy 0, policy_version 148106 (0.0029) [2023-03-09 11:09:02,457][119383] Updated weights for policy 0, policy_version 148116 (0.0019) [2023-03-09 11:09:03,160][119383] Updated weights for policy 0, policy_version 148126 (0.0029) [2023-03-09 11:09:03,902][118949] Fps is (10 sec: 194970.2, 60 sec: 193878.5, 300 sec: 195608.2). Total num frames: 2427011072. Throughput: 0: 48501.8. Samples: 106715520. Policy #0 lag: (min: 1.0, avg: 16.4, max: 33.0) [2023-03-09 11:09:03,904][118949] Avg episode reward: [(0, '55.277')] [2023-03-09 11:09:04,191][119383] Updated weights for policy 0, policy_version 148137 (0.0013) [2023-03-09 11:09:05,067][119383] Updated weights for policy 0, policy_version 148147 (0.0016) [2023-03-09 11:09:05,828][119383] Updated weights for policy 0, policy_version 148157 (0.0022) [2023-03-09 11:09:06,710][119383] Updated weights for policy 0, policy_version 148167 (0.0019) [2023-03-09 11:09:07,584][119383] Updated weights for policy 0, policy_version 148177 (0.0030) [2023-03-09 11:09:08,332][119383] Updated weights for policy 0, policy_version 148187 (0.0031) [2023-03-09 11:09:08,557][119240] Signal inference workers to stop experience collection... (10700 times) [2023-03-09 11:09:08,573][119240] Signal inference workers to resume experience collection... (10700 times) [2023-03-09 11:09:08,655][119383] InferenceWorker_p0-w0: stopping experience collection (10700 times) [2023-03-09 11:09:08,655][119383] InferenceWorker_p0-w0: resuming experience collection (10700 times) [2023-03-09 11:09:08,902][118949] Fps is (10 sec: 194965.2, 60 sec: 194422.6, 300 sec: 195497.1). Total num frames: 2427994112. Throughput: 0: 48591.3. Samples: 107010304. Policy #0 lag: (min: 1.0, avg: 16.4, max: 33.0) [2023-03-09 11:09:08,904][118949] Avg episode reward: [(0, '54.556')] [2023-03-09 11:09:09,310][119383] Updated weights for policy 0, policy_version 148198 (0.0016) [2023-03-09 11:09:10,159][119383] Updated weights for policy 0, policy_version 148208 (0.0018) [2023-03-09 11:09:10,984][119383] Updated weights for policy 0, policy_version 148218 (0.0017) [2023-03-09 11:09:11,829][119383] Updated weights for policy 0, policy_version 148228 (0.0013) [2023-03-09 11:09:12,578][119383] Updated weights for policy 0, policy_version 148238 (0.0020) [2023-03-09 11:09:13,434][119383] Updated weights for policy 0, policy_version 148248 (0.0019) [2023-03-09 11:09:13,902][118949] Fps is (10 sec: 198251.5, 60 sec: 194697.1, 300 sec: 195663.9). Total num frames: 2428993536. Throughput: 0: 48682.5. Samples: 107303040. Policy #0 lag: (min: 1.0, avg: 16.4, max: 33.0) [2023-03-09 11:09:13,903][118949] Avg episode reward: [(0, '57.102')] [2023-03-09 11:09:14,328][119383] Updated weights for policy 0, policy_version 148258 (0.0015) [2023-03-09 11:09:15,066][119383] Updated weights for policy 0, policy_version 148268 (0.0013) [2023-03-09 11:09:15,963][119383] Updated weights for policy 0, policy_version 148278 (0.0024) [2023-03-09 11:09:16,862][119383] Updated weights for policy 0, policy_version 148289 (0.0016) [2023-03-09 11:09:17,720][119383] Updated weights for policy 0, policy_version 148299 (0.0021) [2023-03-09 11:09:18,564][119383] Updated weights for policy 0, policy_version 148309 (0.0016) [2023-03-09 11:09:18,902][118949] Fps is (10 sec: 196606.6, 60 sec: 194697.7, 300 sec: 195663.9). Total num frames: 2429960192. Throughput: 0: 48726.8. Samples: 107450416. Policy #0 lag: (min: 1.0, avg: 16.4, max: 33.0) [2023-03-09 11:09:18,904][118949] Avg episode reward: [(0, '54.566')] [2023-03-09 11:09:19,311][119383] Updated weights for policy 0, policy_version 148319 (0.0018) [2023-03-09 11:09:20,149][119240] Signal inference workers to stop experience collection... (10750 times) [2023-03-09 11:09:20,165][119240] Signal inference workers to resume experience collection... (10750 times) [2023-03-09 11:09:20,231][119383] InferenceWorker_p0-w0: stopping experience collection (10750 times) [2023-03-09 11:09:20,231][119383] InferenceWorker_p0-w0: resuming experience collection (10750 times) [2023-03-09 11:09:20,233][119383] Updated weights for policy 0, policy_version 148329 (0.0017) [2023-03-09 11:09:21,137][119383] Updated weights for policy 0, policy_version 148339 (0.0016) [2023-03-09 11:09:21,855][119383] Updated weights for policy 0, policy_version 148350 (0.0020) [2023-03-09 11:09:22,845][119383] Updated weights for policy 0, policy_version 148360 (0.0016) [2023-03-09 11:09:23,697][119383] Updated weights for policy 0, policy_version 148370 (0.0013) [2023-03-09 11:09:23,902][118949] Fps is (10 sec: 193328.3, 60 sec: 194423.9, 300 sec: 195663.9). Total num frames: 2430926848. Throughput: 0: 48814.4. Samples: 107745152. Policy #0 lag: (min: 1.0, avg: 16.4, max: 33.0) [2023-03-09 11:09:23,903][118949] Avg episode reward: [(0, '57.582')] [2023-03-09 11:09:23,923][119240] Saving /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000148373_2430943232.pth... [2023-03-09 11:09:23,984][119240] Removing /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000145506_2383970304.pth [2023-03-09 11:09:24,518][119383] Updated weights for policy 0, policy_version 148380 (0.0024) [2023-03-09 11:09:25,341][119383] Updated weights for policy 0, policy_version 148390 (0.0019) [2023-03-09 11:09:26,232][119383] Updated weights for policy 0, policy_version 148400 (0.0029) [2023-03-09 11:09:27,060][119383] Updated weights for policy 0, policy_version 148410 (0.0017) [2023-03-09 11:09:28,008][119383] Updated weights for policy 0, policy_version 148421 (0.0019) [2023-03-09 11:09:28,898][119383] Updated weights for policy 0, policy_version 148431 (0.0022) [2023-03-09 11:09:28,902][118949] Fps is (10 sec: 193331.8, 60 sec: 194697.3, 300 sec: 195608.3). Total num frames: 2431893504. Throughput: 0: 48767.7. Samples: 108033824. Policy #0 lag: (min: 1.0, avg: 16.4, max: 33.0) [2023-03-09 11:09:28,904][118949] Avg episode reward: [(0, '57.679')] [2023-03-09 11:09:29,709][119383] Updated weights for policy 0, policy_version 148441 (0.0013) [2023-03-09 11:09:30,644][119383] Updated weights for policy 0, policy_version 148451 (0.0021) [2023-03-09 11:09:30,684][119240] Signal inference workers to stop experience collection... (10800 times) [2023-03-09 11:09:30,704][119240] Signal inference workers to resume experience collection... (10800 times) [2023-03-09 11:09:30,768][119383] InferenceWorker_p0-w0: stopping experience collection (10800 times) [2023-03-09 11:09:30,768][119383] InferenceWorker_p0-w0: resuming experience collection (10800 times) [2023-03-09 11:09:31,382][119383] Updated weights for policy 0, policy_version 148461 (0.0020) [2023-03-09 11:09:32,279][119383] Updated weights for policy 0, policy_version 148471 (0.0035) [2023-03-09 11:09:33,110][119383] Updated weights for policy 0, policy_version 148481 (0.0016) [2023-03-09 11:09:33,902][118949] Fps is (10 sec: 191684.9, 60 sec: 194421.6, 300 sec: 195441.3). Total num frames: 2432843776. Throughput: 0: 48720.4. Samples: 108177072. Policy #0 lag: (min: 1.0, avg: 16.4, max: 33.0) [2023-03-09 11:09:33,904][118949] Avg episode reward: [(0, '56.116')] [2023-03-09 11:09:33,981][119383] Updated weights for policy 0, policy_version 148491 (0.0023) [2023-03-09 11:09:34,898][119383] Updated weights for policy 0, policy_version 148501 (0.0017) [2023-03-09 11:09:35,681][119383] Updated weights for policy 0, policy_version 148512 (0.0013) [2023-03-09 11:09:36,664][119383] Updated weights for policy 0, policy_version 148522 (0.0017) [2023-03-09 11:09:37,490][119383] Updated weights for policy 0, policy_version 148532 (0.0018) [2023-03-09 11:09:38,252][119383] Updated weights for policy 0, policy_version 148542 (0.0024) [2023-03-09 11:09:38,902][118949] Fps is (10 sec: 193335.3, 60 sec: 194696.2, 300 sec: 195497.4). Total num frames: 2433826816. Throughput: 0: 48730.9. Samples: 108468224. Policy #0 lag: (min: 1.0, avg: 16.4, max: 33.0) [2023-03-09 11:09:38,903][118949] Avg episode reward: [(0, '54.491')] [2023-03-09 11:09:39,127][119383] Updated weights for policy 0, policy_version 148552 (0.0026) [2023-03-09 11:09:39,452][119240] Signal inference workers to stop experience collection... (10850 times) [2023-03-09 11:09:39,453][119240] Signal inference workers to resume experience collection... (10850 times) [2023-03-09 11:09:39,515][119383] InferenceWorker_p0-w0: stopping experience collection (10850 times) [2023-03-09 11:09:39,516][119383] InferenceWorker_p0-w0: resuming experience collection (10850 times) [2023-03-09 11:09:40,078][119383] Updated weights for policy 0, policy_version 148562 (0.0019) [2023-03-09 11:09:40,828][119383] Updated weights for policy 0, policy_version 148572 (0.0021) [2023-03-09 11:09:41,815][119383] Updated weights for policy 0, policy_version 148583 (0.0021) [2023-03-09 11:09:42,704][119383] Updated weights for policy 0, policy_version 148593 (0.0017) [2023-03-09 11:09:43,494][119383] Updated weights for policy 0, policy_version 148603 (0.0020) [2023-03-09 11:09:43,902][118949] Fps is (10 sec: 194974.8, 60 sec: 194423.6, 300 sec: 195386.0). Total num frames: 2434793472. Throughput: 0: 48585.6. Samples: 108756528. Policy #0 lag: (min: 1.0, avg: 16.4, max: 33.0) [2023-03-09 11:09:43,904][118949] Avg episode reward: [(0, '55.816')] [2023-03-09 11:09:44,385][119383] Updated weights for policy 0, policy_version 148613 (0.0019) [2023-03-09 11:09:45,184][119383] Updated weights for policy 0, policy_version 148623 (0.0022) [2023-03-09 11:09:46,016][119383] Updated weights for policy 0, policy_version 148633 (0.0016) [2023-03-09 11:09:46,941][119383] Updated weights for policy 0, policy_version 148643 (0.0028) [2023-03-09 11:09:47,687][119383] Updated weights for policy 0, policy_version 148653 (0.0020) [2023-03-09 11:09:48,526][119383] Updated weights for policy 0, policy_version 148663 (0.0016) [2023-03-09 11:09:48,902][118949] Fps is (10 sec: 191693.6, 60 sec: 194424.4, 300 sec: 195330.6). Total num frames: 2435743744. Throughput: 0: 48583.7. Samples: 108901776. Policy #0 lag: (min: 0.0, avg: 16.4, max: 32.0) [2023-03-09 11:09:48,903][118949] Avg episode reward: [(0, '55.396')] [2023-03-09 11:09:49,616][119383] Updated weights for policy 0, policy_version 148674 (0.0013) [2023-03-09 11:09:49,721][119240] Signal inference workers to stop experience collection... (10900 times) [2023-03-09 11:09:49,722][119240] Signal inference workers to resume experience collection... (10900 times) [2023-03-09 11:09:49,784][119383] InferenceWorker_p0-w0: stopping experience collection (10900 times) [2023-03-09 11:09:49,787][119383] InferenceWorker_p0-w0: resuming experience collection (10900 times) [2023-03-09 11:09:50,296][119383] Updated weights for policy 0, policy_version 148684 (0.0021) [2023-03-09 11:09:51,232][119383] Updated weights for policy 0, policy_version 148694 (0.0013) [2023-03-09 11:09:51,945][119383] Updated weights for policy 0, policy_version 148704 (0.0018) [2023-03-09 11:09:52,875][119383] Updated weights for policy 0, policy_version 148714 (0.0013) [2023-03-09 11:09:53,822][119383] Updated weights for policy 0, policy_version 148725 (0.0020) [2023-03-09 11:09:53,902][118949] Fps is (10 sec: 193335.4, 60 sec: 194424.1, 300 sec: 195441.8). Total num frames: 2436726784. Throughput: 0: 48538.1. Samples: 109194512. Policy #0 lag: (min: 0.0, avg: 16.4, max: 32.0) [2023-03-09 11:09:53,903][118949] Avg episode reward: [(0, '54.693')] [2023-03-09 11:09:54,566][119383] Updated weights for policy 0, policy_version 148735 (0.0024) [2023-03-09 11:09:55,490][119383] Updated weights for policy 0, policy_version 148745 (0.0012) [2023-03-09 11:09:56,381][119383] Updated weights for policy 0, policy_version 148755 (0.0023) [2023-03-09 11:09:57,143][119383] Updated weights for policy 0, policy_version 148765 (0.0013) [2023-03-09 11:09:57,777][119240] Signal inference workers to stop experience collection... (10950 times) [2023-03-09 11:09:57,802][119240] Signal inference workers to resume experience collection... (10950 times) [2023-03-09 11:09:57,839][119383] InferenceWorker_p0-w0: stopping experience collection (10950 times) [2023-03-09 11:09:57,887][119383] InferenceWorker_p0-w0: resuming experience collection (10950 times) [2023-03-09 11:09:58,014][119383] Updated weights for policy 0, policy_version 148775 (0.0027) [2023-03-09 11:09:58,902][118949] Fps is (10 sec: 193331.9, 60 sec: 193877.4, 300 sec: 195330.9). Total num frames: 2437677056. Throughput: 0: 48492.5. Samples: 109485200. Policy #0 lag: (min: 0.0, avg: 16.4, max: 32.0) [2023-03-09 11:09:58,903][118949] Avg episode reward: [(0, '55.495')] [2023-03-09 11:09:58,952][119383] Updated weights for policy 0, policy_version 148785 (0.0029) [2023-03-09 11:09:59,726][119383] Updated weights for policy 0, policy_version 148795 (0.0016) [2023-03-09 11:10:00,601][119383] Updated weights for policy 0, policy_version 148805 (0.0014) [2023-03-09 11:10:01,457][119383] Updated weights for policy 0, policy_version 148815 (0.0017) [2023-03-09 11:10:02,247][119383] Updated weights for policy 0, policy_version 148825 (0.0017) [2023-03-09 11:10:03,180][119383] Updated weights for policy 0, policy_version 148836 (0.0016) [2023-03-09 11:10:03,902][118949] Fps is (10 sec: 194965.6, 60 sec: 194423.4, 300 sec: 195386.0). Total num frames: 2438676480. Throughput: 0: 48448.0. Samples: 109630576. Policy #0 lag: (min: 0.0, avg: 16.4, max: 32.0) [2023-03-09 11:10:03,904][118949] Avg episode reward: [(0, '56.533')] [2023-03-09 11:10:03,971][119383] Updated weights for policy 0, policy_version 148846 (0.0015) [2023-03-09 11:10:04,942][119383] Updated weights for policy 0, policy_version 148857 (0.0020) [2023-03-09 11:10:05,840][119383] Updated weights for policy 0, policy_version 148867 (0.0016) [2023-03-09 11:10:06,673][119383] Updated weights for policy 0, policy_version 148878 (0.0016) [2023-03-09 11:10:07,463][119383] Updated weights for policy 0, policy_version 148888 (0.0014) [2023-03-09 11:10:07,696][119240] Signal inference workers to stop experience collection... (11000 times) [2023-03-09 11:10:07,715][119240] Signal inference workers to resume experience collection... (11000 times) [2023-03-09 11:10:07,738][119383] InferenceWorker_p0-w0: stopping experience collection (11000 times) [2023-03-09 11:10:07,782][119383] InferenceWorker_p0-w0: resuming experience collection (11000 times) [2023-03-09 11:10:08,439][119383] Updated weights for policy 0, policy_version 148898 (0.0025) [2023-03-09 11:10:08,902][118949] Fps is (10 sec: 196602.7, 60 sec: 194150.4, 300 sec: 195330.5). Total num frames: 2439643136. Throughput: 0: 48357.6. Samples: 109921248. Policy #0 lag: (min: 0.0, avg: 16.4, max: 32.0) [2023-03-09 11:10:08,904][118949] Avg episode reward: [(0, '54.522')] [2023-03-09 11:10:09,195][119383] Updated weights for policy 0, policy_version 148908 (0.0019) [2023-03-09 11:10:10,086][119383] Updated weights for policy 0, policy_version 148918 (0.0013) [2023-03-09 11:10:11,026][119383] Updated weights for policy 0, policy_version 148929 (0.0013) [2023-03-09 11:10:11,834][119383] Updated weights for policy 0, policy_version 148939 (0.0019) [2023-03-09 11:10:12,717][119383] Updated weights for policy 0, policy_version 148949 (0.0014) [2023-03-09 11:10:13,500][119383] Updated weights for policy 0, policy_version 148959 (0.0019) [2023-03-09 11:10:13,902][118949] Fps is (10 sec: 191690.3, 60 sec: 193329.9, 300 sec: 195330.3). Total num frames: 2440593408. Throughput: 0: 48404.1. Samples: 110212016. Policy #0 lag: (min: 0.0, avg: 16.4, max: 32.0) [2023-03-09 11:10:13,904][118949] Avg episode reward: [(0, '53.839')] [2023-03-09 11:10:14,418][119383] Updated weights for policy 0, policy_version 148969 (0.0021) [2023-03-09 11:10:15,321][119383] Updated weights for policy 0, policy_version 148979 (0.0021) [2023-03-09 11:10:16,065][119240] Signal inference workers to stop experience collection... (11050 times) [2023-03-09 11:10:16,093][119240] Signal inference workers to resume experience collection... (11050 times) [2023-03-09 11:10:16,098][119383] InferenceWorker_p0-w0: stopping experience collection (11050 times) [2023-03-09 11:10:16,099][119383] InferenceWorker_p0-w0: resuming experience collection (11050 times) [2023-03-09 11:10:16,101][119383] Updated weights for policy 0, policy_version 148989 (0.0039) [2023-03-09 11:10:17,029][119383] Updated weights for policy 0, policy_version 149000 (0.0016) [2023-03-09 11:10:17,960][119383] Updated weights for policy 0, policy_version 149010 (0.0016) [2023-03-09 11:10:18,699][119383] Updated weights for policy 0, policy_version 149020 (0.0013) [2023-03-09 11:10:18,902][118949] Fps is (10 sec: 196612.1, 60 sec: 194151.3, 300 sec: 195386.3). Total num frames: 2441609216. Throughput: 0: 48450.7. Samples: 110357328. Policy #0 lag: (min: 0.0, avg: 16.4, max: 32.0) [2023-03-09 11:10:18,903][118949] Avg episode reward: [(0, '54.774')] [2023-03-09 11:10:19,581][119383] Updated weights for policy 0, policy_version 149030 (0.0018) [2023-03-09 11:10:20,366][119383] Updated weights for policy 0, policy_version 149040 (0.0019) [2023-03-09 11:10:21,274][119383] Updated weights for policy 0, policy_version 149050 (0.0022) [2023-03-09 11:10:22,187][119383] Updated weights for policy 0, policy_version 149060 (0.0017) [2023-03-09 11:10:22,907][119383] Updated weights for policy 0, policy_version 149070 (0.0018) [2023-03-09 11:10:23,532][119240] Signal inference workers to stop experience collection... (11100 times) [2023-03-09 11:10:23,557][119240] Signal inference workers to resume experience collection... (11100 times) [2023-03-09 11:10:23,597][119383] InferenceWorker_p0-w0: stopping experience collection (11100 times) [2023-03-09 11:10:23,600][119383] InferenceWorker_p0-w0: resuming experience collection (11100 times) [2023-03-09 11:10:23,902][118949] Fps is (10 sec: 194977.7, 60 sec: 193604.8, 300 sec: 195219.5). Total num frames: 2442543104. Throughput: 0: 48438.8. Samples: 110647968. Policy #0 lag: (min: 0.0, avg: 16.4, max: 32.0) [2023-03-09 11:10:23,903][118949] Avg episode reward: [(0, '56.545')] [2023-03-09 11:10:23,921][119383] Updated weights for policy 0, policy_version 149081 (0.0018) [2023-03-09 11:10:24,789][119383] Updated weights for policy 0, policy_version 149091 (0.0019) [2023-03-09 11:10:25,603][119383] Updated weights for policy 0, policy_version 149102 (0.0016) [2023-03-09 11:10:26,434][119383] Updated weights for policy 0, policy_version 149112 (0.0015) [2023-03-09 11:10:27,437][119383] Updated weights for policy 0, policy_version 149122 (0.0025) [2023-03-09 11:10:28,115][119383] Updated weights for policy 0, policy_version 149132 (0.0020) [2023-03-09 11:10:28,902][118949] Fps is (10 sec: 191683.5, 60 sec: 193876.5, 300 sec: 195274.7). Total num frames: 2443526144. Throughput: 0: 48537.0. Samples: 110940704. Policy #0 lag: (min: 0.0, avg: 16.4, max: 32.0) [2023-03-09 11:10:28,904][118949] Avg episode reward: [(0, '53.020')] [2023-03-09 11:10:28,968][119383] Updated weights for policy 0, policy_version 149142 (0.0018) [2023-03-09 11:10:29,706][119383] Updated weights for policy 0, policy_version 149152 (0.0016) [2023-03-09 11:10:30,327][119240] Signal inference workers to stop experience collection... (11150 times) [2023-03-09 11:10:30,331][119240] Signal inference workers to resume experience collection... (11150 times) [2023-03-09 11:10:30,393][119383] InferenceWorker_p0-w0: stopping experience collection (11150 times) [2023-03-09 11:10:30,394][119383] InferenceWorker_p0-w0: resuming experience collection (11150 times) [2023-03-09 11:10:30,647][119383] Updated weights for policy 0, policy_version 149162 (0.0022) [2023-03-09 11:10:31,548][119383] Updated weights for policy 0, policy_version 149172 (0.0014) [2023-03-09 11:10:32,300][119383] Updated weights for policy 0, policy_version 149182 (0.0014) [2023-03-09 11:10:33,164][119383] Updated weights for policy 0, policy_version 149192 (0.0014) [2023-03-09 11:10:33,902][118949] Fps is (10 sec: 193331.4, 60 sec: 193879.2, 300 sec: 195219.5). Total num frames: 2444476416. Throughput: 0: 48540.5. Samples: 111086096. Policy #0 lag: (min: 0.0, avg: 16.4, max: 32.0) [2023-03-09 11:10:33,903][118949] Avg episode reward: [(0, '56.031')] [2023-03-09 11:10:34,127][119383] Updated weights for policy 0, policy_version 149202 (0.0025) [2023-03-09 11:10:34,942][119383] Updated weights for policy 0, policy_version 149213 (0.0035) [2023-03-09 11:10:35,786][119383] Updated weights for policy 0, policy_version 149223 (0.0013) [2023-03-09 11:10:36,673][119383] Updated weights for policy 0, policy_version 149233 (0.0012) [2023-03-09 11:10:37,508][119383] Updated weights for policy 0, policy_version 149243 (0.0023) [2023-03-09 11:10:38,178][119240] Signal inference workers to stop experience collection... (11200 times) [2023-03-09 11:10:38,205][119240] Signal inference workers to resume experience collection... (11200 times) [2023-03-09 11:10:38,256][119383] InferenceWorker_p0-w0: stopping experience collection (11200 times) [2023-03-09 11:10:38,256][119383] InferenceWorker_p0-w0: resuming experience collection (11200 times) [2023-03-09 11:10:38,461][119383] Updated weights for policy 0, policy_version 149254 (0.0014) [2023-03-09 11:10:38,902][118949] Fps is (10 sec: 194977.0, 60 sec: 194150.1, 300 sec: 195275.2). Total num frames: 2445475840. Throughput: 0: 48539.7. Samples: 111378800. Policy #0 lag: (min: 0.0, avg: 16.4, max: 32.0) [2023-03-09 11:10:38,904][118949] Avg episode reward: [(0, '54.095')] [2023-03-09 11:10:39,285][119383] Updated weights for policy 0, policy_version 149264 (0.0015) [2023-03-09 11:10:40,105][119383] Updated weights for policy 0, policy_version 149274 (0.0014) [2023-03-09 11:10:41,019][119383] Updated weights for policy 0, policy_version 149284 (0.0034) [2023-03-09 11:10:41,710][119383] Updated weights for policy 0, policy_version 149294 (0.0013) [2023-03-09 11:10:42,514][119383] Updated weights for policy 0, policy_version 149304 (0.0018) [2023-03-09 11:10:43,515][119383] Updated weights for policy 0, policy_version 149314 (0.0022) [2023-03-09 11:10:43,902][118949] Fps is (10 sec: 196607.6, 60 sec: 194151.3, 300 sec: 195164.2). Total num frames: 2446442496. Throughput: 0: 48582.4. Samples: 111671408. Policy #0 lag: (min: 0.0, avg: 16.4, max: 32.0) [2023-03-09 11:10:43,903][118949] Avg episode reward: [(0, '56.757')] [2023-03-09 11:10:44,296][119383] Updated weights for policy 0, policy_version 149324 (0.0036) [2023-03-09 11:10:45,151][119383] Updated weights for policy 0, policy_version 149334 (0.0015) [2023-03-09 11:10:46,082][119383] Updated weights for policy 0, policy_version 149345 (0.0014) [2023-03-09 11:10:46,587][119240] Signal inference workers to stop experience collection... (11250 times) [2023-03-09 11:10:46,588][119240] Signal inference workers to resume experience collection... (11250 times) [2023-03-09 11:10:46,650][119383] InferenceWorker_p0-w0: stopping experience collection (11250 times) [2023-03-09 11:10:46,651][119383] InferenceWorker_p0-w0: resuming experience collection (11250 times) [2023-03-09 11:10:46,868][119383] Updated weights for policy 0, policy_version 149355 (0.0020) [2023-03-09 11:10:47,767][119383] Updated weights for policy 0, policy_version 149365 (0.0026) [2023-03-09 11:10:48,526][119383] Updated weights for policy 0, policy_version 149375 (0.0025) [2023-03-09 11:10:48,902][118949] Fps is (10 sec: 191696.0, 60 sec: 194150.5, 300 sec: 195053.2). Total num frames: 2447392768. Throughput: 0: 48582.7. Samples: 111816784. Policy #0 lag: (min: 0.0, avg: 16.4, max: 32.0) [2023-03-09 11:10:48,903][118949] Avg episode reward: [(0, '55.877')] [2023-03-09 11:10:49,455][119383] Updated weights for policy 0, policy_version 149385 (0.0016) [2023-03-09 11:10:50,348][119383] Updated weights for policy 0, policy_version 149395 (0.0016) [2023-03-09 11:10:51,127][119383] Updated weights for policy 0, policy_version 149406 (0.0028) [2023-03-09 11:10:52,034][119383] Updated weights for policy 0, policy_version 149416 (0.0018) [2023-03-09 11:10:52,909][119383] Updated weights for policy 0, policy_version 149426 (0.0015) [2023-03-09 11:10:53,650][119383] Updated weights for policy 0, policy_version 149436 (0.0015) [2023-03-09 11:10:53,902][118949] Fps is (10 sec: 196602.2, 60 sec: 194695.8, 300 sec: 195219.5). Total num frames: 2448408576. Throughput: 0: 48673.4. Samples: 112111552. Policy #0 lag: (min: 1.0, avg: 16.3, max: 33.0) [2023-03-09 11:10:53,904][118949] Avg episode reward: [(0, '54.534')] [2023-03-09 11:10:54,566][119383] Updated weights for policy 0, policy_version 149446 (0.0016) [2023-03-09 11:10:54,752][119240] Signal inference workers to stop experience collection... (11300 times) [2023-03-09 11:10:54,753][119240] Signal inference workers to resume experience collection... (11300 times) [2023-03-09 11:10:54,811][119383] InferenceWorker_p0-w0: stopping experience collection (11300 times) [2023-03-09 11:10:54,811][119383] InferenceWorker_p0-w0: resuming experience collection (11300 times) [2023-03-09 11:10:55,379][119383] Updated weights for policy 0, policy_version 149456 (0.0018) [2023-03-09 11:10:56,208][119383] Updated weights for policy 0, policy_version 149466 (0.0017) [2023-03-09 11:10:57,131][119383] Updated weights for policy 0, policy_version 149476 (0.0021) [2023-03-09 11:10:57,807][119383] Updated weights for policy 0, policy_version 149486 (0.0036) [2023-03-09 11:10:58,633][119383] Updated weights for policy 0, policy_version 149496 (0.0013) [2023-03-09 11:10:58,902][118949] Fps is (10 sec: 198243.7, 60 sec: 194969.2, 300 sec: 195108.4). Total num frames: 2449375232. Throughput: 0: 48716.4. Samples: 112404240. Policy #0 lag: (min: 1.0, avg: 16.3, max: 33.0) [2023-03-09 11:10:58,904][118949] Avg episode reward: [(0, '54.319')] [2023-03-09 11:10:59,599][119383] Updated weights for policy 0, policy_version 149506 (0.0017) [2023-03-09 11:11:00,317][119383] Updated weights for policy 0, policy_version 149516 (0.0017) [2023-03-09 11:11:01,175][119383] Updated weights for policy 0, policy_version 149526 (0.0030) [2023-03-09 11:11:01,979][119383] Updated weights for policy 0, policy_version 149536 (0.0019) [2023-03-09 11:11:02,817][119240] Signal inference workers to stop experience collection... (11350 times) [2023-03-09 11:11:02,818][119240] Signal inference workers to resume experience collection... (11350 times) [2023-03-09 11:11:02,888][119383] InferenceWorker_p0-w0: stopping experience collection (11350 times) [2023-03-09 11:11:02,888][119383] InferenceWorker_p0-w0: resuming experience collection (11350 times) [2023-03-09 11:11:02,894][119383] Updated weights for policy 0, policy_version 149546 (0.0019) [2023-03-09 11:11:03,788][119383] Updated weights for policy 0, policy_version 149556 (0.0013) [2023-03-09 11:11:03,902][118949] Fps is (10 sec: 194975.8, 60 sec: 194697.5, 300 sec: 195108.6). Total num frames: 2450358272. Throughput: 0: 48717.9. Samples: 112549632. Policy #0 lag: (min: 1.0, avg: 16.3, max: 33.0) [2023-03-09 11:11:03,903][118949] Avg episode reward: [(0, '53.887')] [2023-03-09 11:11:04,549][119383] Updated weights for policy 0, policy_version 149566 (0.0021) [2023-03-09 11:11:05,440][119383] Updated weights for policy 0, policy_version 149576 (0.0018) [2023-03-09 11:11:06,312][119383] Updated weights for policy 0, policy_version 149586 (0.0026) [2023-03-09 11:11:07,097][119383] Updated weights for policy 0, policy_version 149596 (0.0014) [2023-03-09 11:11:07,993][119383] Updated weights for policy 0, policy_version 149606 (0.0021) [2023-03-09 11:11:08,868][119383] Updated weights for policy 0, policy_version 149616 (0.0020) [2023-03-09 11:11:08,902][118949] Fps is (10 sec: 193332.8, 60 sec: 194424.2, 300 sec: 194942.0). Total num frames: 2451308544. Throughput: 0: 48765.5. Samples: 112842416. Policy #0 lag: (min: 1.0, avg: 16.3, max: 33.0) [2023-03-09 11:11:08,903][118949] Avg episode reward: [(0, '54.548')] [2023-03-09 11:11:09,706][119383] Updated weights for policy 0, policy_version 149626 (0.0032) [2023-03-09 11:11:10,602][119383] Updated weights for policy 0, policy_version 149636 (0.0013) [2023-03-09 11:11:11,310][119383] Updated weights for policy 0, policy_version 149646 (0.0042) [2023-03-09 11:11:12,151][119383] Updated weights for policy 0, policy_version 149656 (0.0016) [2023-03-09 11:11:13,112][119383] Updated weights for policy 0, policy_version 149666 (0.0014) [2023-03-09 11:11:13,188][119240] Signal inference workers to stop experience collection... (11400 times) [2023-03-09 11:11:13,203][119240] Signal inference workers to resume experience collection... (11400 times) [2023-03-09 11:11:13,273][119383] InferenceWorker_p0-w0: stopping experience collection (11400 times) [2023-03-09 11:11:13,273][119383] InferenceWorker_p0-w0: resuming experience collection (11400 times) [2023-03-09 11:11:13,819][119383] Updated weights for policy 0, policy_version 149676 (0.0013) [2023-03-09 11:11:13,902][118949] Fps is (10 sec: 194966.2, 60 sec: 195243.5, 300 sec: 195053.0). Total num frames: 2452307968. Throughput: 0: 48719.3. Samples: 113133056. Policy #0 lag: (min: 1.0, avg: 16.3, max: 33.0) [2023-03-09 11:11:13,904][118949] Avg episode reward: [(0, '55.924')] [2023-03-09 11:11:14,712][119383] Updated weights for policy 0, policy_version 149686 (0.0016) [2023-03-09 11:11:15,464][119383] Updated weights for policy 0, policy_version 149696 (0.0018) [2023-03-09 11:11:16,461][119383] Updated weights for policy 0, policy_version 149707 (0.0020) [2023-03-09 11:11:17,340][119383] Updated weights for policy 0, policy_version 149717 (0.0021) [2023-03-09 11:11:18,118][119383] Updated weights for policy 0, policy_version 149727 (0.0027) [2023-03-09 11:11:18,902][118949] Fps is (10 sec: 196607.3, 60 sec: 194423.4, 300 sec: 195053.1). Total num frames: 2453274624. Throughput: 0: 48762.9. Samples: 113280432. Policy #0 lag: (min: 1.0, avg: 16.3, max: 33.0) [2023-03-09 11:11:18,904][118949] Avg episode reward: [(0, '57.385')] [2023-03-09 11:11:19,030][119383] Updated weights for policy 0, policy_version 149737 (0.0016) [2023-03-09 11:11:19,916][119383] Updated weights for policy 0, policy_version 149747 (0.0013) [2023-03-09 11:11:20,667][119383] Updated weights for policy 0, policy_version 149757 (0.0022) [2023-03-09 11:11:21,640][119383] Updated weights for policy 0, policy_version 149767 (0.0029) [2023-03-09 11:11:22,450][119383] Updated weights for policy 0, policy_version 149777 (0.0017) [2023-03-09 11:11:22,628][119240] Signal inference workers to stop experience collection... (11450 times) [2023-03-09 11:11:22,635][119240] Signal inference workers to resume experience collection... (11450 times) [2023-03-09 11:11:22,704][119383] InferenceWorker_p0-w0: stopping experience collection (11450 times) [2023-03-09 11:11:22,706][119383] InferenceWorker_p0-w0: resuming experience collection (11450 times) [2023-03-09 11:11:23,254][119383] Updated weights for policy 0, policy_version 149787 (0.0026) [2023-03-09 11:11:23,902][118949] Fps is (10 sec: 190051.4, 60 sec: 194422.4, 300 sec: 194830.7). Total num frames: 2454208512. Throughput: 0: 48626.7. Samples: 113567008. Policy #0 lag: (min: 1.0, avg: 16.3, max: 33.0) [2023-03-09 11:11:23,904][118949] Avg episode reward: [(0, '54.870')] [2023-03-09 11:11:23,938][119240] Saving /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000149794_2454224896.pth... [2023-03-09 11:11:24,007][119240] Removing /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000146945_2407546880.pth [2023-03-09 11:11:24,246][119383] Updated weights for policy 0, policy_version 149797 (0.0019) [2023-03-09 11:11:25,100][119383] Updated weights for policy 0, policy_version 149808 (0.0017) [2023-03-09 11:11:26,094][119383] Updated weights for policy 0, policy_version 149819 (0.0014) [2023-03-09 11:11:26,947][119383] Updated weights for policy 0, policy_version 149829 (0.0014) [2023-03-09 11:11:27,854][119383] Updated weights for policy 0, policy_version 149839 (0.0018) [2023-03-09 11:11:28,650][119383] Updated weights for policy 0, policy_version 149849 (0.0017) [2023-03-09 11:11:28,902][118949] Fps is (10 sec: 190056.2, 60 sec: 194152.2, 300 sec: 194775.2). Total num frames: 2455175168. Throughput: 0: 48490.4. Samples: 113853472. Policy #0 lag: (min: 1.0, avg: 16.3, max: 33.0) [2023-03-09 11:11:28,903][118949] Avg episode reward: [(0, '54.150')] [2023-03-09 11:11:29,598][119383] Updated weights for policy 0, policy_version 149859 (0.0018) [2023-03-09 11:11:30,230][119383] Updated weights for policy 0, policy_version 149869 (0.0015) [2023-03-09 11:11:30,941][119240] Signal inference workers to stop experience collection... (11500 times) [2023-03-09 11:11:30,949][119240] Signal inference workers to resume experience collection... (11500 times) [2023-03-09 11:11:31,014][119383] InferenceWorker_p0-w0: stopping experience collection (11500 times) [2023-03-09 11:11:31,014][119383] InferenceWorker_p0-w0: resuming experience collection (11500 times) [2023-03-09 11:11:31,060][119383] Updated weights for policy 0, policy_version 149879 (0.0017) [2023-03-09 11:11:32,106][119383] Updated weights for policy 0, policy_version 149890 (0.0013) [2023-03-09 11:11:32,820][119383] Updated weights for policy 0, policy_version 149900 (0.0023) [2023-03-09 11:11:33,715][119383] Updated weights for policy 0, policy_version 149910 (0.0021) [2023-03-09 11:11:33,902][118949] Fps is (10 sec: 194972.4, 60 sec: 194695.9, 300 sec: 194830.6). Total num frames: 2456158208. Throughput: 0: 48533.5. Samples: 114000800. Policy #0 lag: (min: 1.0, avg: 16.3, max: 33.0) [2023-03-09 11:11:33,904][118949] Avg episode reward: [(0, '55.361')] [2023-03-09 11:11:34,471][119383] Updated weights for policy 0, policy_version 149920 (0.0023) [2023-03-09 11:11:35,452][119383] Updated weights for policy 0, policy_version 149930 (0.0032) [2023-03-09 11:11:36,267][119383] Updated weights for policy 0, policy_version 149940 (0.0013) [2023-03-09 11:11:37,083][119383] Updated weights for policy 0, policy_version 149950 (0.0043) [2023-03-09 11:11:38,026][119383] Updated weights for policy 0, policy_version 149961 (0.0027) [2023-03-09 11:11:38,902][118949] Fps is (10 sec: 194967.9, 60 sec: 194150.7, 300 sec: 194664.2). Total num frames: 2457124864. Throughput: 0: 48489.2. Samples: 114293552. Policy #0 lag: (min: 1.0, avg: 16.3, max: 33.0) [2023-03-09 11:11:38,903][118949] Avg episode reward: [(0, '58.541')] [2023-03-09 11:11:38,914][119383] Updated weights for policy 0, policy_version 149971 (0.0021) [2023-03-09 11:11:39,394][119240] Signal inference workers to stop experience collection... (11550 times) [2023-03-09 11:11:39,395][119240] Signal inference workers to resume experience collection... (11550 times) [2023-03-09 11:11:39,464][119383] InferenceWorker_p0-w0: stopping experience collection (11550 times) [2023-03-09 11:11:39,465][119383] InferenceWorker_p0-w0: resuming experience collection (11550 times) [2023-03-09 11:11:39,679][119383] Updated weights for policy 0, policy_version 149981 (0.0014) [2023-03-09 11:11:40,636][119383] Updated weights for policy 0, policy_version 149991 (0.0051) [2023-03-09 11:11:41,410][119383] Updated weights for policy 0, policy_version 150001 (0.0023) [2023-03-09 11:11:42,272][119383] Updated weights for policy 0, policy_version 150011 (0.0028) [2023-03-09 11:11:43,176][119383] Updated weights for policy 0, policy_version 150021 (0.0022) [2023-03-09 11:11:43,902][118949] Fps is (10 sec: 193329.1, 60 sec: 194149.5, 300 sec: 194663.9). Total num frames: 2458091520. Throughput: 0: 48443.9. Samples: 114584224. Policy #0 lag: (min: 1.0, avg: 16.3, max: 33.0) [2023-03-09 11:11:43,904][118949] Avg episode reward: [(0, '54.795')] [2023-03-09 11:11:44,015][119383] Updated weights for policy 0, policy_version 150031 (0.0029) [2023-03-09 11:11:44,796][119383] Updated weights for policy 0, policy_version 150041 (0.0014) [2023-03-09 11:11:45,751][119383] Updated weights for policy 0, policy_version 150052 (0.0027) [2023-03-09 11:11:46,507][119383] Updated weights for policy 0, policy_version 150062 (0.0040) [2023-03-09 11:11:47,082][119240] Signal inference workers to stop experience collection... (11600 times) [2023-03-09 11:11:47,101][119240] Signal inference workers to resume experience collection... (11600 times) [2023-03-09 11:11:47,130][119383] InferenceWorker_p0-w0: stopping experience collection (11600 times) [2023-03-09 11:11:47,130][119383] InferenceWorker_p0-w0: resuming experience collection (11600 times) [2023-03-09 11:11:47,335][119383] Updated weights for policy 0, policy_version 150072 (0.0017) [2023-03-09 11:11:48,251][119383] Updated weights for policy 0, policy_version 150082 (0.0017) [2023-03-09 11:11:48,902][118949] Fps is (10 sec: 196605.6, 60 sec: 194968.9, 300 sec: 194719.6). Total num frames: 2459090944. Throughput: 0: 48488.0. Samples: 114731600. Policy #0 lag: (min: 1.0, avg: 16.3, max: 33.0) [2023-03-09 11:11:48,904][118949] Avg episode reward: [(0, '56.402')] [2023-03-09 11:11:48,977][119383] Updated weights for policy 0, policy_version 150092 (0.0014) [2023-03-09 11:11:49,859][119383] Updated weights for policy 0, policy_version 150102 (0.0025) [2023-03-09 11:11:50,614][119383] Updated weights for policy 0, policy_version 150112 (0.0018) [2023-03-09 11:11:51,601][119383] Updated weights for policy 0, policy_version 150122 (0.0024) [2023-03-09 11:11:52,430][119383] Updated weights for policy 0, policy_version 150132 (0.0022) [2023-03-09 11:11:53,228][119383] Updated weights for policy 0, policy_version 150142 (0.0017) [2023-03-09 11:11:53,902][118949] Fps is (10 sec: 194973.2, 60 sec: 193878.0, 300 sec: 194609.0). Total num frames: 2460041216. Throughput: 0: 48441.5. Samples: 115022288. Policy #0 lag: (min: 0.0, avg: 16.5, max: 33.0) [2023-03-09 11:11:53,904][118949] Avg episode reward: [(0, '55.745')] [2023-03-09 11:11:54,091][119383] Updated weights for policy 0, policy_version 150152 (0.0013) [2023-03-09 11:11:54,912][119383] Updated weights for policy 0, policy_version 150162 (0.0048) [2023-03-09 11:11:54,997][119240] Signal inference workers to stop experience collection... (11650 times) [2023-03-09 11:11:55,012][119240] Signal inference workers to resume experience collection... (11650 times) [2023-03-09 11:11:55,080][119383] InferenceWorker_p0-w0: stopping experience collection (11650 times) [2023-03-09 11:11:55,083][119383] InferenceWorker_p0-w0: resuming experience collection (11650 times) [2023-03-09 11:11:55,705][119383] Updated weights for policy 0, policy_version 150172 (0.0016) [2023-03-09 11:11:56,673][119383] Updated weights for policy 0, policy_version 150182 (0.0016) [2023-03-09 11:11:57,451][119383] Updated weights for policy 0, policy_version 150192 (0.0043) [2023-03-09 11:11:58,367][119383] Updated weights for policy 0, policy_version 150203 (0.0021) [2023-03-09 11:11:58,902][118949] Fps is (10 sec: 193335.0, 60 sec: 194150.8, 300 sec: 194664.1). Total num frames: 2461024256. Throughput: 0: 48535.3. Samples: 115317136. Policy #0 lag: (min: 0.0, avg: 16.5, max: 33.0) [2023-03-09 11:11:58,903][118949] Avg episode reward: [(0, '54.453')] [2023-03-09 11:11:59,282][119383] Updated weights for policy 0, policy_version 150213 (0.0016) [2023-03-09 11:12:00,224][119383] Updated weights for policy 0, policy_version 150224 (0.0020) [2023-03-09 11:12:00,967][119383] Updated weights for policy 0, policy_version 150234 (0.0016) [2023-03-09 11:12:01,912][119383] Updated weights for policy 0, policy_version 150244 (0.0023) [2023-03-09 11:12:02,617][119383] Updated weights for policy 0, policy_version 150254 (0.0013) [2023-03-09 11:12:02,782][119240] Signal inference workers to stop experience collection... (11700 times) [2023-03-09 11:12:02,784][119240] Signal inference workers to resume experience collection... (11700 times) [2023-03-09 11:12:02,850][119383] InferenceWorker_p0-w0: stopping experience collection (11700 times) [2023-03-09 11:12:02,850][119383] InferenceWorker_p0-w0: resuming experience collection (11700 times) [2023-03-09 11:12:03,442][119383] Updated weights for policy 0, policy_version 150264 (0.0014) [2023-03-09 11:12:03,902][118949] Fps is (10 sec: 196608.9, 60 sec: 194150.2, 300 sec: 194608.6). Total num frames: 2462007296. Throughput: 0: 48535.5. Samples: 115464528. Policy #0 lag: (min: 0.0, avg: 16.5, max: 33.0) [2023-03-09 11:12:03,903][118949] Avg episode reward: [(0, '55.214')] [2023-03-09 11:12:04,413][119383] Updated weights for policy 0, policy_version 150274 (0.0019) [2023-03-09 11:12:05,152][119383] Updated weights for policy 0, policy_version 150284 (0.0016) [2023-03-09 11:12:05,938][119383] Updated weights for policy 0, policy_version 150294 (0.0016) [2023-03-09 11:12:06,703][119383] Updated weights for policy 0, policy_version 150304 (0.0026) [2023-03-09 11:12:07,636][119383] Updated weights for policy 0, policy_version 150314 (0.0013) [2023-03-09 11:12:08,538][119383] Updated weights for policy 0, policy_version 150324 (0.0016) [2023-03-09 11:12:08,903][118949] Fps is (10 sec: 194957.2, 60 sec: 194421.6, 300 sec: 194608.4). Total num frames: 2462973952. Throughput: 0: 48672.7. Samples: 115757296. Policy #0 lag: (min: 0.0, avg: 16.5, max: 33.0) [2023-03-09 11:12:08,905][118949] Avg episode reward: [(0, '57.122')] [2023-03-09 11:12:09,286][119383] Updated weights for policy 0, policy_version 150334 (0.0014) [2023-03-09 11:12:10,126][119383] Updated weights for policy 0, policy_version 150344 (0.0019) [2023-03-09 11:12:11,019][119240] Signal inference workers to stop experience collection... (11750 times) [2023-03-09 11:12:11,035][119240] Signal inference workers to resume experience collection... (11750 times) [2023-03-09 11:12:11,065][119383] InferenceWorker_p0-w0: stopping experience collection (11750 times) [2023-03-09 11:12:11,067][119383] Updated weights for policy 0, policy_version 150354 (0.0028) [2023-03-09 11:12:11,110][119383] InferenceWorker_p0-w0: resuming experience collection (11750 times) [2023-03-09 11:12:11,830][119383] Updated weights for policy 0, policy_version 150364 (0.0024) [2023-03-09 11:12:12,761][119383] Updated weights for policy 0, policy_version 150374 (0.0016) [2023-03-09 11:12:13,582][119383] Updated weights for policy 0, policy_version 150384 (0.0016) [2023-03-09 11:12:13,902][118949] Fps is (10 sec: 194970.7, 60 sec: 194150.9, 300 sec: 194608.9). Total num frames: 2463956992. Throughput: 0: 48858.3. Samples: 116052096. Policy #0 lag: (min: 0.0, avg: 16.5, max: 33.0) [2023-03-09 11:12:13,903][118949] Avg episode reward: [(0, '54.576')] [2023-03-09 11:12:14,433][119383] Updated weights for policy 0, policy_version 150395 (0.0013) [2023-03-09 11:12:15,366][119383] Updated weights for policy 0, policy_version 150405 (0.0013) [2023-03-09 11:12:16,178][119383] Updated weights for policy 0, policy_version 150415 (0.0019) [2023-03-09 11:12:16,971][119383] Updated weights for policy 0, policy_version 150425 (0.0016) [2023-03-09 11:12:18,014][119383] Updated weights for policy 0, policy_version 150436 (0.0016) [2023-03-09 11:12:18,682][119383] Updated weights for policy 0, policy_version 150446 (0.0016) [2023-03-09 11:12:18,902][118949] Fps is (10 sec: 194978.3, 60 sec: 194150.1, 300 sec: 194497.4). Total num frames: 2464923648. Throughput: 0: 48769.4. Samples: 116195424. Policy #0 lag: (min: 0.0, avg: 16.5, max: 33.0) [2023-03-09 11:12:18,903][118949] Avg episode reward: [(0, '58.380')] [2023-03-09 11:12:19,220][119240] Signal inference workers to stop experience collection... (11800 times) [2023-03-09 11:12:19,225][119240] Signal inference workers to resume experience collection... (11800 times) [2023-03-09 11:12:19,326][119383] InferenceWorker_p0-w0: stopping experience collection (11800 times) [2023-03-09 11:12:19,326][119383] InferenceWorker_p0-w0: resuming experience collection (11800 times) [2023-03-09 11:12:19,650][119383] Updated weights for policy 0, policy_version 150457 (0.0013) [2023-03-09 11:12:20,557][119383] Updated weights for policy 0, policy_version 150467 (0.0016) [2023-03-09 11:12:21,288][119383] Updated weights for policy 0, policy_version 150477 (0.0018) [2023-03-09 11:12:22,101][119383] Updated weights for policy 0, policy_version 150487 (0.0013) [2023-03-09 11:12:23,092][119383] Updated weights for policy 0, policy_version 150498 (0.0018) [2023-03-09 11:12:23,837][119383] Updated weights for policy 0, policy_version 150508 (0.0014) [2023-03-09 11:12:23,902][118949] Fps is (10 sec: 196608.1, 60 sec: 195243.7, 300 sec: 194608.8). Total num frames: 2465923072. Throughput: 0: 48814.3. Samples: 116490192. Policy #0 lag: (min: 0.0, avg: 16.5, max: 33.0) [2023-03-09 11:12:23,903][118949] Avg episode reward: [(0, '55.265')] [2023-03-09 11:12:24,817][119383] Updated weights for policy 0, policy_version 150519 (0.0014) [2023-03-09 11:12:25,632][119383] Updated weights for policy 0, policy_version 150529 (0.0018) [2023-03-09 11:12:26,537][119383] Updated weights for policy 0, policy_version 150540 (0.0017) [2023-03-09 11:12:27,398][119383] Updated weights for policy 0, policy_version 150550 (0.0013) [2023-03-09 11:12:27,888][119240] Signal inference workers to stop experience collection... (11850 times) [2023-03-09 11:12:27,911][119240] Signal inference workers to resume experience collection... (11850 times) [2023-03-09 11:12:27,958][119383] InferenceWorker_p0-w0: stopping experience collection (11850 times) [2023-03-09 11:12:27,959][119383] InferenceWorker_p0-w0: resuming experience collection (11850 times) [2023-03-09 11:12:28,315][119383] Updated weights for policy 0, policy_version 150561 (0.0012) [2023-03-09 11:12:28,902][118949] Fps is (10 sec: 198242.3, 60 sec: 195514.4, 300 sec: 194608.6). Total num frames: 2466906112. Throughput: 0: 48905.9. Samples: 116784992. Policy #0 lag: (min: 0.0, avg: 16.5, max: 33.0) [2023-03-09 11:12:28,905][118949] Avg episode reward: [(0, '54.482')] [2023-03-09 11:12:29,098][119383] Updated weights for policy 0, policy_version 150571 (0.0034) [2023-03-09 11:12:29,997][119383] Updated weights for policy 0, policy_version 150581 (0.0029) [2023-03-09 11:12:30,743][119383] Updated weights for policy 0, policy_version 150591 (0.0024) [2023-03-09 11:12:31,695][119383] Updated weights for policy 0, policy_version 150601 (0.0016) [2023-03-09 11:12:32,518][119383] Updated weights for policy 0, policy_version 150611 (0.0018) [2023-03-09 11:12:33,316][119383] Updated weights for policy 0, policy_version 150621 (0.0024) [2023-03-09 11:12:33,902][118949] Fps is (10 sec: 194963.1, 60 sec: 195242.2, 300 sec: 194608.6). Total num frames: 2467872768. Throughput: 0: 48905.4. Samples: 116932352. Policy #0 lag: (min: 0.0, avg: 16.5, max: 33.0) [2023-03-09 11:12:33,904][118949] Avg episode reward: [(0, '56.789')] [2023-03-09 11:12:34,190][119383] Updated weights for policy 0, policy_version 150631 (0.0016) [2023-03-09 11:12:35,025][119383] Updated weights for policy 0, policy_version 150641 (0.0019) [2023-03-09 11:12:35,812][119383] Updated weights for policy 0, policy_version 150651 (0.0020) [2023-03-09 11:12:36,736][119383] Updated weights for policy 0, policy_version 150661 (0.0026) [2023-03-09 11:12:37,504][119383] Updated weights for policy 0, policy_version 150671 (0.0021) [2023-03-09 11:12:37,598][119240] Signal inference workers to stop experience collection... (11900 times) [2023-03-09 11:12:37,599][119240] Signal inference workers to resume experience collection... (11900 times) [2023-03-09 11:12:37,669][119383] InferenceWorker_p0-w0: stopping experience collection (11900 times) [2023-03-09 11:12:37,669][119383] InferenceWorker_p0-w0: resuming experience collection (11900 times) [2023-03-09 11:12:38,436][119383] Updated weights for policy 0, policy_version 150682 (0.0033) [2023-03-09 11:12:38,902][118949] Fps is (10 sec: 196613.4, 60 sec: 195788.6, 300 sec: 194719.8). Total num frames: 2468872192. Throughput: 0: 49043.6. Samples: 117229248. Policy #0 lag: (min: 0.0, avg: 16.5, max: 33.0) [2023-03-09 11:12:38,903][118949] Avg episode reward: [(0, '54.736')] [2023-03-09 11:12:39,336][119383] Updated weights for policy 0, policy_version 150692 (0.0020) [2023-03-09 11:12:40,049][119383] Updated weights for policy 0, policy_version 150702 (0.0017) [2023-03-09 11:12:40,857][119383] Updated weights for policy 0, policy_version 150712 (0.0013) [2023-03-09 11:12:41,781][119383] Updated weights for policy 0, policy_version 150722 (0.0019) [2023-03-09 11:12:42,520][119383] Updated weights for policy 0, policy_version 150732 (0.0026) [2023-03-09 11:12:43,337][119383] Updated weights for policy 0, policy_version 150742 (0.0013) [2023-03-09 11:12:43,902][118949] Fps is (10 sec: 198240.6, 60 sec: 196060.8, 300 sec: 194663.9). Total num frames: 2469855232. Throughput: 0: 48995.6. Samples: 117521968. Policy #0 lag: (min: 0.0, avg: 16.5, max: 33.0) [2023-03-09 11:12:43,904][118949] Avg episode reward: [(0, '56.499')] [2023-03-09 11:12:44,131][119383] Updated weights for policy 0, policy_version 150752 (0.0020) [2023-03-09 11:12:45,021][119383] Updated weights for policy 0, policy_version 150762 (0.0018) [2023-03-09 11:12:45,899][119383] Updated weights for policy 0, policy_version 150772 (0.0011) [2023-03-09 11:12:46,363][119240] Signal inference workers to stop experience collection... (11950 times) [2023-03-09 11:12:46,368][119240] Signal inference workers to resume experience collection... (11950 times) [2023-03-09 11:12:46,441][119383] InferenceWorker_p0-w0: stopping experience collection (11950 times) [2023-03-09 11:12:46,441][119383] InferenceWorker_p0-w0: resuming experience collection (11950 times) [2023-03-09 11:12:46,663][119383] Updated weights for policy 0, policy_version 150782 (0.0032) [2023-03-09 11:12:47,592][119383] Updated weights for policy 0, policy_version 150792 (0.0023) [2023-03-09 11:12:48,408][119383] Updated weights for policy 0, policy_version 150802 (0.0020) [2023-03-09 11:12:48,902][118949] Fps is (10 sec: 196604.1, 60 sec: 195788.4, 300 sec: 194719.7). Total num frames: 2470838272. Throughput: 0: 49040.4. Samples: 117671360. Policy #0 lag: (min: 0.0, avg: 16.5, max: 33.0) [2023-03-09 11:12:48,904][118949] Avg episode reward: [(0, '55.652')] [2023-03-09 11:12:49,184][119383] Updated weights for policy 0, policy_version 150812 (0.0026) [2023-03-09 11:12:50,129][119383] Updated weights for policy 0, policy_version 150822 (0.0018) [2023-03-09 11:12:50,961][119383] Updated weights for policy 0, policy_version 150832 (0.0014) [2023-03-09 11:12:51,755][119383] Updated weights for policy 0, policy_version 150842 (0.0033) [2023-03-09 11:12:52,668][119383] Updated weights for policy 0, policy_version 150852 (0.0013) [2023-03-09 11:12:53,374][119383] Updated weights for policy 0, policy_version 150862 (0.0015) [2023-03-09 11:12:53,902][118949] Fps is (10 sec: 196613.4, 60 sec: 196334.1, 300 sec: 194719.6). Total num frames: 2471821312. Throughput: 0: 49085.1. Samples: 117966112. Policy #0 lag: (min: 0.0, avg: 16.5, max: 33.0) [2023-03-09 11:12:53,904][118949] Avg episode reward: [(0, '54.699')] [2023-03-09 11:12:54,168][119383] Updated weights for policy 0, policy_version 150872 (0.0015) [2023-03-09 11:12:55,081][119383] Updated weights for policy 0, policy_version 150882 (0.0024) [2023-03-09 11:12:55,887][119383] Updated weights for policy 0, policy_version 150893 (0.0017) [2023-03-09 11:12:56,718][119383] Updated weights for policy 0, policy_version 150903 (0.0014) [2023-03-09 11:12:57,239][119240] Signal inference workers to stop experience collection... (12000 times) [2023-03-09 11:12:57,242][119240] Signal inference workers to resume experience collection... (12000 times) [2023-03-09 11:12:57,312][119383] InferenceWorker_p0-w0: stopping experience collection (12000 times) [2023-03-09 11:12:57,312][119383] InferenceWorker_p0-w0: resuming experience collection (12000 times) [2023-03-09 11:12:57,561][119383] Updated weights for policy 0, policy_version 150913 (0.0013) [2023-03-09 11:12:58,429][119383] Updated weights for policy 0, policy_version 150923 (0.0018) [2023-03-09 11:12:58,902][118949] Fps is (10 sec: 196607.7, 60 sec: 196333.8, 300 sec: 194664.3). Total num frames: 2472804352. Throughput: 0: 49081.3. Samples: 118260768. Policy #0 lag: (min: 1.0, avg: 17.2, max: 34.0) [2023-03-09 11:12:58,904][118949] Avg episode reward: [(0, '55.144')] [2023-03-09 11:12:59,321][119383] Updated weights for policy 0, policy_version 150933 (0.0018) [2023-03-09 11:13:00,066][119383] Updated weights for policy 0, policy_version 150943 (0.0029) [2023-03-09 11:13:01,017][119383] Updated weights for policy 0, policy_version 150953 (0.0028) [2023-03-09 11:13:01,870][119383] Updated weights for policy 0, policy_version 150963 (0.0014) [2023-03-09 11:13:02,609][119383] Updated weights for policy 0, policy_version 150973 (0.0014) [2023-03-09 11:13:03,514][119383] Updated weights for policy 0, policy_version 150983 (0.0018) [2023-03-09 11:13:03,902][118949] Fps is (10 sec: 198248.0, 60 sec: 196607.3, 300 sec: 194830.6). Total num frames: 2473803776. Throughput: 0: 49172.2. Samples: 118408176. Policy #0 lag: (min: 1.0, avg: 17.2, max: 34.0) [2023-03-09 11:13:03,904][118949] Avg episode reward: [(0, '55.325')] [2023-03-09 11:13:04,301][119383] Updated weights for policy 0, policy_version 150993 (0.0013) [2023-03-09 11:13:05,233][119383] Updated weights for policy 0, policy_version 151004 (0.0025) [2023-03-09 11:13:06,086][119383] Updated weights for policy 0, policy_version 151014 (0.0013) [2023-03-09 11:13:06,941][119383] Updated weights for policy 0, policy_version 151024 (0.0028) [2023-03-09 11:13:07,245][119240] Signal inference workers to stop experience collection... (12050 times) [2023-03-09 11:13:07,265][119240] Signal inference workers to resume experience collection... (12050 times) [2023-03-09 11:13:07,328][119383] InferenceWorker_p0-w0: stopping experience collection (12050 times) [2023-03-09 11:13:07,329][119383] InferenceWorker_p0-w0: resuming experience collection (12050 times) [2023-03-09 11:13:07,697][119383] Updated weights for policy 0, policy_version 151034 (0.0017) [2023-03-09 11:13:08,653][119383] Updated weights for policy 0, policy_version 151044 (0.0013) [2023-03-09 11:13:08,902][118949] Fps is (10 sec: 196608.1, 60 sec: 196609.0, 300 sec: 194775.1). Total num frames: 2474770432. Throughput: 0: 49217.1. Samples: 118704976. Policy #0 lag: (min: 1.0, avg: 17.2, max: 34.0) [2023-03-09 11:13:08,904][118949] Avg episode reward: [(0, '53.518')] [2023-03-09 11:13:09,313][119383] Updated weights for policy 0, policy_version 151054 (0.0017) [2023-03-09 11:13:10,124][119383] Updated weights for policy 0, policy_version 151064 (0.0011) [2023-03-09 11:13:11,055][119383] Updated weights for policy 0, policy_version 151074 (0.0022) [2023-03-09 11:13:11,844][119383] Updated weights for policy 0, policy_version 151085 (0.0022) [2023-03-09 11:13:12,695][119383] Updated weights for policy 0, policy_version 151095 (0.0013) [2023-03-09 11:13:13,495][119383] Updated weights for policy 0, policy_version 151105 (0.0013) [2023-03-09 11:13:13,902][118949] Fps is (10 sec: 194968.4, 60 sec: 196606.9, 300 sec: 194831.0). Total num frames: 2475753472. Throughput: 0: 49261.2. Samples: 119001744. Policy #0 lag: (min: 1.0, avg: 17.2, max: 34.0) [2023-03-09 11:13:13,904][118949] Avg episode reward: [(0, '54.855')] [2023-03-09 11:13:14,356][119383] Updated weights for policy 0, policy_version 151115 (0.0017) [2023-03-09 11:13:15,291][119383] Updated weights for policy 0, policy_version 151126 (0.0013) [2023-03-09 11:13:16,032][119383] Updated weights for policy 0, policy_version 151136 (0.0016) [2023-03-09 11:13:16,940][119383] Updated weights for policy 0, policy_version 151146 (0.0025) [2023-03-09 11:13:17,825][119240] Signal inference workers to stop experience collection... (12100 times) [2023-03-09 11:13:17,826][119240] Signal inference workers to resume experience collection... (12100 times) [2023-03-09 11:13:17,830][119383] Updated weights for policy 0, policy_version 151156 (0.0013) [2023-03-09 11:13:17,871][119383] InferenceWorker_p0-w0: stopping experience collection (12100 times) [2023-03-09 11:13:17,872][119383] InferenceWorker_p0-w0: resuming experience collection (12100 times) [2023-03-09 11:13:18,622][119383] Updated weights for policy 0, policy_version 151166 (0.0023) [2023-03-09 11:13:18,902][118949] Fps is (10 sec: 198248.3, 60 sec: 197154.0, 300 sec: 194886.3). Total num frames: 2476752896. Throughput: 0: 49262.3. Samples: 119149152. Policy #0 lag: (min: 1.0, avg: 17.2, max: 34.0) [2023-03-09 11:13:18,904][118949] Avg episode reward: [(0, '52.895')] [2023-03-09 11:13:19,490][119383] Updated weights for policy 0, policy_version 151176 (0.0019) [2023-03-09 11:13:20,376][119383] Updated weights for policy 0, policy_version 151186 (0.0016) [2023-03-09 11:13:21,204][119383] Updated weights for policy 0, policy_version 151196 (0.0016) [2023-03-09 11:13:22,126][119383] Updated weights for policy 0, policy_version 151206 (0.0023) [2023-03-09 11:13:22,911][119383] Updated weights for policy 0, policy_version 151216 (0.0016) [2023-03-09 11:13:23,747][119383] Updated weights for policy 0, policy_version 151226 (0.0013) [2023-03-09 11:13:23,902][118949] Fps is (10 sec: 196612.7, 60 sec: 196607.7, 300 sec: 194942.1). Total num frames: 2477719552. Throughput: 0: 49123.6. Samples: 119439808. Policy #0 lag: (min: 1.0, avg: 17.2, max: 34.0) [2023-03-09 11:13:23,903][118949] Avg episode reward: [(0, '54.673')] [2023-03-09 11:13:23,953][119240] Saving /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000151229_2477735936.pth... [2023-03-09 11:13:24,024][119240] Removing /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000148373_2430943232.pth [2023-03-09 11:13:24,651][119383] Updated weights for policy 0, policy_version 151236 (0.0017) [2023-03-09 11:13:25,405][119383] Updated weights for policy 0, policy_version 151246 (0.0016) [2023-03-09 11:13:26,179][119383] Updated weights for policy 0, policy_version 151256 (0.0013) [2023-03-09 11:13:26,551][119240] Signal inference workers to stop experience collection... (12150 times) [2023-03-09 11:13:26,577][119240] Signal inference workers to resume experience collection... (12150 times) [2023-03-09 11:13:26,617][119383] InferenceWorker_p0-w0: stopping experience collection (12150 times) [2023-03-09 11:13:26,661][119383] InferenceWorker_p0-w0: resuming experience collection (12150 times) [2023-03-09 11:13:27,167][119383] Updated weights for policy 0, policy_version 151266 (0.0022) [2023-03-09 11:13:27,845][119383] Updated weights for policy 0, policy_version 151276 (0.0019) [2023-03-09 11:13:28,722][119383] Updated weights for policy 0, policy_version 151286 (0.0031) [2023-03-09 11:13:28,902][118949] Fps is (10 sec: 194969.3, 60 sec: 196608.5, 300 sec: 194997.2). Total num frames: 2478702592. Throughput: 0: 49123.6. Samples: 119732512. Policy #0 lag: (min: 1.0, avg: 17.2, max: 34.0) [2023-03-09 11:13:28,904][118949] Avg episode reward: [(0, '55.626')] [2023-03-09 11:13:29,477][119383] Updated weights for policy 0, policy_version 151296 (0.0020) [2023-03-09 11:13:30,405][119383] Updated weights for policy 0, policy_version 151306 (0.0013) [2023-03-09 11:13:31,294][119383] Updated weights for policy 0, policy_version 151316 (0.0035) [2023-03-09 11:13:32,063][119383] Updated weights for policy 0, policy_version 151326 (0.0014) [2023-03-09 11:13:32,932][119383] Updated weights for policy 0, policy_version 151336 (0.0019) [2023-03-09 11:13:33,884][119383] Updated weights for policy 0, policy_version 151346 (0.0020) [2023-03-09 11:13:33,902][118949] Fps is (10 sec: 193330.1, 60 sec: 196335.5, 300 sec: 194941.7). Total num frames: 2479652864. Throughput: 0: 49077.9. Samples: 119879856. Policy #0 lag: (min: 1.0, avg: 17.2, max: 34.0) [2023-03-09 11:13:33,903][118949] Avg episode reward: [(0, '58.151')] [2023-03-09 11:13:34,310][119240] Signal inference workers to stop experience collection... (12200 times) [2023-03-09 11:13:34,312][119240] Signal inference workers to resume experience collection... (12200 times) [2023-03-09 11:13:34,378][119383] InferenceWorker_p0-w0: stopping experience collection (12200 times) [2023-03-09 11:13:34,379][119383] InferenceWorker_p0-w0: resuming experience collection (12200 times) [2023-03-09 11:13:34,626][119383] Updated weights for policy 0, policy_version 151356 (0.0016) [2023-03-09 11:13:35,496][119383] Updated weights for policy 0, policy_version 151366 (0.0022) [2023-03-09 11:13:36,411][119383] Updated weights for policy 0, policy_version 151377 (0.0016) [2023-03-09 11:13:37,138][119383] Updated weights for policy 0, policy_version 151387 (0.0041) [2023-03-09 11:13:38,115][119383] Updated weights for policy 0, policy_version 151397 (0.0028) [2023-03-09 11:13:38,902][118949] Fps is (10 sec: 194969.8, 60 sec: 196334.6, 300 sec: 194997.4). Total num frames: 2480652288. Throughput: 0: 49078.2. Samples: 120174624. Policy #0 lag: (min: 1.0, avg: 17.2, max: 34.0) [2023-03-09 11:13:38,904][118949] Avg episode reward: [(0, '54.170')] [2023-03-09 11:13:38,940][119383] Updated weights for policy 0, policy_version 151407 (0.0023) [2023-03-09 11:13:39,721][119383] Updated weights for policy 0, policy_version 151417 (0.0028) [2023-03-09 11:13:40,665][119383] Updated weights for policy 0, policy_version 151427 (0.0014) [2023-03-09 11:13:41,485][119383] Updated weights for policy 0, policy_version 151438 (0.0017) [2023-03-09 11:13:42,362][119383] Updated weights for policy 0, policy_version 151448 (0.0024) [2023-03-09 11:13:42,802][119240] Signal inference workers to stop experience collection... (12250 times) [2023-03-09 11:13:42,806][119240] Signal inference workers to resume experience collection... (12250 times) [2023-03-09 11:13:42,868][119383] InferenceWorker_p0-w0: stopping experience collection (12250 times) [2023-03-09 11:13:42,868][119383] InferenceWorker_p0-w0: resuming experience collection (12250 times) [2023-03-09 11:13:43,475][119383] Updated weights for policy 0, policy_version 151460 (0.0022) [2023-03-09 11:13:43,902][118949] Fps is (10 sec: 196606.6, 60 sec: 196063.2, 300 sec: 195053.0). Total num frames: 2481618944. Throughput: 0: 48989.3. Samples: 120465280. Policy #0 lag: (min: 1.0, avg: 17.2, max: 34.0) [2023-03-09 11:13:43,904][118949] Avg episode reward: [(0, '56.360')] [2023-03-09 11:13:44,228][119383] Updated weights for policy 0, policy_version 151470 (0.0025) [2023-03-09 11:13:45,030][119383] Updated weights for policy 0, policy_version 151480 (0.0026) [2023-03-09 11:13:45,933][119383] Updated weights for policy 0, policy_version 151490 (0.0014) [2023-03-09 11:13:46,632][119383] Updated weights for policy 0, policy_version 151500 (0.0016) [2023-03-09 11:13:47,499][119383] Updated weights for policy 0, policy_version 151510 (0.0016) [2023-03-09 11:13:48,285][119383] Updated weights for policy 0, policy_version 151520 (0.0026) [2023-03-09 11:13:48,902][118949] Fps is (10 sec: 193323.4, 60 sec: 195787.8, 300 sec: 194997.2). Total num frames: 2482585600. Throughput: 0: 48988.4. Samples: 120612672. Policy #0 lag: (min: 1.0, avg: 17.2, max: 34.0) [2023-03-09 11:13:48,905][118949] Avg episode reward: [(0, '53.311')] [2023-03-09 11:13:49,237][119383] Updated weights for policy 0, policy_version 151530 (0.0021) [2023-03-09 11:13:50,096][119383] Updated weights for policy 0, policy_version 151540 (0.0013) [2023-03-09 11:13:50,851][119383] Updated weights for policy 0, policy_version 151550 (0.0021) [2023-03-09 11:13:50,902][119240] Signal inference workers to stop experience collection... (12300 times) [2023-03-09 11:13:50,903][119240] Signal inference workers to resume experience collection... (12300 times) [2023-03-09 11:13:50,967][119383] InferenceWorker_p0-w0: stopping experience collection (12300 times) [2023-03-09 11:13:50,967][119383] InferenceWorker_p0-w0: resuming experience collection (12300 times) [2023-03-09 11:13:51,750][119383] Updated weights for policy 0, policy_version 151560 (0.0019) [2023-03-09 11:13:52,642][119383] Updated weights for policy 0, policy_version 151570 (0.0016) [2023-03-09 11:13:53,438][119383] Updated weights for policy 0, policy_version 151580 (0.0024) [2023-03-09 11:13:53,903][118949] Fps is (10 sec: 194961.0, 60 sec: 195787.8, 300 sec: 194996.9). Total num frames: 2483568640. Throughput: 0: 48896.3. Samples: 120905328. Policy #0 lag: (min: 1.0, avg: 17.2, max: 34.0) [2023-03-09 11:13:53,905][118949] Avg episode reward: [(0, '55.932')] [2023-03-09 11:13:54,347][119383] Updated weights for policy 0, policy_version 151590 (0.0021) [2023-03-09 11:13:55,150][119383] Updated weights for policy 0, policy_version 151600 (0.0029) [2023-03-09 11:13:55,941][119383] Updated weights for policy 0, policy_version 151610 (0.0013) [2023-03-09 11:13:56,861][119383] Updated weights for policy 0, policy_version 151620 (0.0020) [2023-03-09 11:13:57,670][119383] Updated weights for policy 0, policy_version 151630 (0.0020) [2023-03-09 11:13:58,458][119383] Updated weights for policy 0, policy_version 151640 (0.0020) [2023-03-09 11:13:58,902][118949] Fps is (10 sec: 198249.9, 60 sec: 196061.5, 300 sec: 195108.3). Total num frames: 2484568064. Throughput: 0: 48763.3. Samples: 121196096. Policy #0 lag: (min: 1.0, avg: 17.2, max: 34.0) [2023-03-09 11:13:58,904][118949] Avg episode reward: [(0, '52.933')] [2023-03-09 11:13:59,523][119383] Updated weights for policy 0, policy_version 151651 (0.0026) [2023-03-09 11:14:00,188][119383] Updated weights for policy 0, policy_version 151661 (0.0022) [2023-03-09 11:14:00,463][119240] Signal inference workers to stop experience collection... (12350 times) [2023-03-09 11:14:00,465][119240] Signal inference workers to resume experience collection... (12350 times) [2023-03-09 11:14:00,545][119383] InferenceWorker_p0-w0: stopping experience collection (12350 times) [2023-03-09 11:14:00,545][119383] InferenceWorker_p0-w0: resuming experience collection (12350 times) [2023-03-09 11:14:01,153][119383] Updated weights for policy 0, policy_version 151672 (0.0013) [2023-03-09 11:14:02,095][119383] Updated weights for policy 0, policy_version 151682 (0.0027) [2023-03-09 11:14:02,852][119383] Updated weights for policy 0, policy_version 151692 (0.0016) [2023-03-09 11:14:03,626][119383] Updated weights for policy 0, policy_version 151702 (0.0016) [2023-03-09 11:14:03,902][118949] Fps is (10 sec: 194982.1, 60 sec: 195243.5, 300 sec: 194997.5). Total num frames: 2485518336. Throughput: 0: 48762.9. Samples: 121343472. Policy #0 lag: (min: 1.0, avg: 16.7, max: 34.0) [2023-03-09 11:14:03,903][118949] Avg episode reward: [(0, '56.312')] [2023-03-09 11:14:04,425][119383] Updated weights for policy 0, policy_version 151712 (0.0026) [2023-03-09 11:14:05,314][119383] Updated weights for policy 0, policy_version 151722 (0.0014) [2023-03-09 11:14:06,232][119383] Updated weights for policy 0, policy_version 151732 (0.0019) [2023-03-09 11:14:07,015][119383] Updated weights for policy 0, policy_version 151742 (0.0036) [2023-03-09 11:14:07,921][119383] Updated weights for policy 0, policy_version 151752 (0.0017) [2023-03-09 11:14:08,831][119383] Updated weights for policy 0, policy_version 151762 (0.0018) [2023-03-09 11:14:08,881][119240] Signal inference workers to stop experience collection... (12400 times) [2023-03-09 11:14:08,884][119240] Signal inference workers to resume experience collection... (12400 times) [2023-03-09 11:14:08,902][118949] Fps is (10 sec: 191701.7, 60 sec: 195243.7, 300 sec: 194886.3). Total num frames: 2486484992. Throughput: 0: 48809.7. Samples: 121636240. Policy #0 lag: (min: 1.0, avg: 16.7, max: 34.0) [2023-03-09 11:14:08,903][118949] Avg episode reward: [(0, '55.558')] [2023-03-09 11:14:08,960][119383] InferenceWorker_p0-w0: stopping experience collection (12400 times) [2023-03-09 11:14:08,963][119383] InferenceWorker_p0-w0: resuming experience collection (12400 times) [2023-03-09 11:14:09,601][119383] Updated weights for policy 0, policy_version 151772 (0.0021) [2023-03-09 11:14:10,580][119383] Updated weights for policy 0, policy_version 151783 (0.0020) [2023-03-09 11:14:11,462][119383] Updated weights for policy 0, policy_version 151793 (0.0029) [2023-03-09 11:14:12,170][119383] Updated weights for policy 0, policy_version 151803 (0.0013) [2023-03-09 11:14:13,141][119383] Updated weights for policy 0, policy_version 151813 (0.0019) [2023-03-09 11:14:13,902][118949] Fps is (10 sec: 193330.7, 60 sec: 194970.5, 300 sec: 194886.5). Total num frames: 2487451648. Throughput: 0: 48719.5. Samples: 121924880. Policy #0 lag: (min: 1.0, avg: 16.7, max: 34.0) [2023-03-09 11:14:13,903][118949] Avg episode reward: [(0, '53.750')] [2023-03-09 11:14:14,009][119383] Updated weights for policy 0, policy_version 151823 (0.0013) [2023-03-09 11:14:14,765][119383] Updated weights for policy 0, policy_version 151833 (0.0013) [2023-03-09 11:14:15,712][119383] Updated weights for policy 0, policy_version 151843 (0.0026) [2023-03-09 11:14:16,402][119383] Updated weights for policy 0, policy_version 151853 (0.0016) [2023-03-09 11:14:17,128][119240] Signal inference workers to stop experience collection... (12450 times) [2023-03-09 11:14:17,130][119240] Signal inference workers to resume experience collection... (12450 times) [2023-03-09 11:14:17,198][119383] InferenceWorker_p0-w0: stopping experience collection (12450 times) [2023-03-09 11:14:17,198][119383] InferenceWorker_p0-w0: resuming experience collection (12450 times) [2023-03-09 11:14:17,431][119383] Updated weights for policy 0, policy_version 151864 (0.0016) [2023-03-09 11:14:18,401][119383] Updated weights for policy 0, policy_version 151874 (0.0028) [2023-03-09 11:14:18,902][118949] Fps is (10 sec: 193331.2, 60 sec: 194424.2, 300 sec: 194886.4). Total num frames: 2488418304. Throughput: 0: 48674.0. Samples: 122070176. Policy #0 lag: (min: 1.0, avg: 16.7, max: 34.0) [2023-03-09 11:14:18,903][118949] Avg episode reward: [(0, '56.348')] [2023-03-09 11:14:19,047][119383] Updated weights for policy 0, policy_version 151884 (0.0026) [2023-03-09 11:14:19,942][119383] Updated weights for policy 0, policy_version 151894 (0.0024) [2023-03-09 11:14:20,698][119383] Updated weights for policy 0, policy_version 151904 (0.0023) [2023-03-09 11:14:21,580][119383] Updated weights for policy 0, policy_version 151914 (0.0016) [2023-03-09 11:14:22,500][119383] Updated weights for policy 0, policy_version 151924 (0.0022) [2023-03-09 11:14:23,252][119383] Updated weights for policy 0, policy_version 151934 (0.0016) [2023-03-09 11:14:23,902][118949] Fps is (10 sec: 191683.8, 60 sec: 194149.0, 300 sec: 194830.6). Total num frames: 2489368576. Throughput: 0: 48537.6. Samples: 122358832. Policy #0 lag: (min: 1.0, avg: 16.7, max: 34.0) [2023-03-09 11:14:23,904][118949] Avg episode reward: [(0, '54.898')] [2023-03-09 11:14:24,150][119383] Updated weights for policy 0, policy_version 151944 (0.0016) [2023-03-09 11:14:25,063][119383] Updated weights for policy 0, policy_version 151954 (0.0016) [2023-03-09 11:14:25,872][119383] Updated weights for policy 0, policy_version 151964 (0.0026) [2023-03-09 11:14:26,497][119240] Signal inference workers to stop experience collection... (12500 times) [2023-03-09 11:14:26,500][119240] Signal inference workers to resume experience collection... (12500 times) [2023-03-09 11:14:26,563][119383] InferenceWorker_p0-w0: stopping experience collection (12500 times) [2023-03-09 11:14:26,563][119383] InferenceWorker_p0-w0: resuming experience collection (12500 times) [2023-03-09 11:14:26,776][119383] Updated weights for policy 0, policy_version 151974 (0.0026) [2023-03-09 11:14:27,639][119383] Updated weights for policy 0, policy_version 151984 (0.0032) [2023-03-09 11:14:28,445][119383] Updated weights for policy 0, policy_version 151994 (0.0020) [2023-03-09 11:14:28,902][118949] Fps is (10 sec: 194964.0, 60 sec: 194423.3, 300 sec: 194997.6). Total num frames: 2490368000. Throughput: 0: 48448.3. Samples: 122645456. Policy #0 lag: (min: 1.0, avg: 16.7, max: 34.0) [2023-03-09 11:14:28,904][118949] Avg episode reward: [(0, '56.557')] [2023-03-09 11:14:29,406][119383] Updated weights for policy 0, policy_version 152004 (0.0013) [2023-03-09 11:14:30,367][119383] Updated weights for policy 0, policy_version 152015 (0.0020) [2023-03-09 11:14:31,069][119383] Updated weights for policy 0, policy_version 152025 (0.0016) [2023-03-09 11:14:32,121][119383] Updated weights for policy 0, policy_version 152036 (0.0013) [2023-03-09 11:14:32,943][119383] Updated weights for policy 0, policy_version 152046 (0.0012) [2023-03-09 11:14:33,642][119383] Updated weights for policy 0, policy_version 152056 (0.0019) [2023-03-09 11:14:33,731][119240] Signal inference workers to stop experience collection... (12550 times) [2023-03-09 11:14:33,742][119240] Signal inference workers to resume experience collection... (12550 times) [2023-03-09 11:14:33,811][119383] InferenceWorker_p0-w0: stopping experience collection (12550 times) [2023-03-09 11:14:33,811][119383] InferenceWorker_p0-w0: resuming experience collection (12550 times) [2023-03-09 11:14:33,902][118949] Fps is (10 sec: 196611.0, 60 sec: 194695.8, 300 sec: 194941.6). Total num frames: 2491334656. Throughput: 0: 48492.7. Samples: 122794832. Policy #0 lag: (min: 1.0, avg: 16.7, max: 34.0) [2023-03-09 11:14:33,904][118949] Avg episode reward: [(0, '57.505')] [2023-03-09 11:14:34,581][119383] Updated weights for policy 0, policy_version 152066 (0.0015) [2023-03-09 11:14:35,295][119383] Updated weights for policy 0, policy_version 152076 (0.0021) [2023-03-09 11:14:36,200][119383] Updated weights for policy 0, policy_version 152086 (0.0018) [2023-03-09 11:14:36,908][119383] Updated weights for policy 0, policy_version 152096 (0.0019) [2023-03-09 11:14:37,840][119383] Updated weights for policy 0, policy_version 152106 (0.0020) [2023-03-09 11:14:38,755][119383] Updated weights for policy 0, policy_version 152116 (0.0016) [2023-03-09 11:14:38,902][118949] Fps is (10 sec: 193329.4, 60 sec: 194149.9, 300 sec: 194941.8). Total num frames: 2492301312. Throughput: 0: 48448.7. Samples: 123085504. Policy #0 lag: (min: 1.0, avg: 16.7, max: 34.0) [2023-03-09 11:14:38,904][118949] Avg episode reward: [(0, '56.369')] [2023-03-09 11:14:39,461][119383] Updated weights for policy 0, policy_version 152126 (0.0016) [2023-03-09 11:14:40,457][119383] Updated weights for policy 0, policy_version 152137 (0.0015) [2023-03-09 11:14:41,399][119383] Updated weights for policy 0, policy_version 152147 (0.0016) [2023-03-09 11:14:41,573][119240] Signal inference workers to stop experience collection... (12600 times) [2023-03-09 11:14:41,575][119240] Signal inference workers to resume experience collection... (12600 times) [2023-03-09 11:14:41,643][119383] InferenceWorker_p0-w0: stopping experience collection (12600 times) [2023-03-09 11:14:41,643][119383] InferenceWorker_p0-w0: resuming experience collection (12600 times) [2023-03-09 11:14:42,110][119383] Updated weights for policy 0, policy_version 152157 (0.0017) [2023-03-09 11:14:43,086][119383] Updated weights for policy 0, policy_version 152167 (0.0037) [2023-03-09 11:14:43,888][119383] Updated weights for policy 0, policy_version 152177 (0.0013) [2023-03-09 11:14:43,902][118949] Fps is (10 sec: 193334.4, 60 sec: 194150.5, 300 sec: 194997.3). Total num frames: 2493267968. Throughput: 0: 48490.6. Samples: 123378160. Policy #0 lag: (min: 1.0, avg: 16.7, max: 34.0) [2023-03-09 11:14:43,904][118949] Avg episode reward: [(0, '56.868')] [2023-03-09 11:14:44,695][119383] Updated weights for policy 0, policy_version 152187 (0.0017) [2023-03-09 11:14:45,588][119383] Updated weights for policy 0, policy_version 152197 (0.0016) [2023-03-09 11:14:46,452][119383] Updated weights for policy 0, policy_version 152207 (0.0016) [2023-03-09 11:14:47,311][119383] Updated weights for policy 0, policy_version 152218 (0.0016) [2023-03-09 11:14:48,240][119383] Updated weights for policy 0, policy_version 152228 (0.0018) [2023-03-09 11:14:48,902][118949] Fps is (10 sec: 194976.9, 60 sec: 194425.5, 300 sec: 194997.4). Total num frames: 2494251008. Throughput: 0: 48491.1. Samples: 123525568. Policy #0 lag: (min: 1.0, avg: 16.7, max: 34.0) [2023-03-09 11:14:48,903][118949] Avg episode reward: [(0, '54.555')] [2023-03-09 11:14:49,188][119383] Updated weights for policy 0, policy_version 152239 (0.0017) [2023-03-09 11:14:49,472][119240] Signal inference workers to stop experience collection... (12650 times) [2023-03-09 11:14:49,473][119240] Signal inference workers to resume experience collection... (12650 times) [2023-03-09 11:14:49,542][119383] InferenceWorker_p0-w0: stopping experience collection (12650 times) [2023-03-09 11:14:49,542][119383] InferenceWorker_p0-w0: resuming experience collection (12650 times) [2023-03-09 11:14:49,905][119383] Updated weights for policy 0, policy_version 152249 (0.0016) [2023-03-09 11:14:50,812][119383] Updated weights for policy 0, policy_version 152259 (0.0022) [2023-03-09 11:14:51,511][119383] Updated weights for policy 0, policy_version 152269 (0.0041) [2023-03-09 11:14:52,284][119383] Updated weights for policy 0, policy_version 152279 (0.0026) [2023-03-09 11:14:53,123][119383] Updated weights for policy 0, policy_version 152289 (0.0032) [2023-03-09 11:14:53,902][118949] Fps is (10 sec: 198243.8, 60 sec: 194697.6, 300 sec: 195163.8). Total num frames: 2495250432. Throughput: 0: 48488.9. Samples: 123818256. Policy #0 lag: (min: 1.0, avg: 16.7, max: 34.0) [2023-03-09 11:14:53,905][118949] Avg episode reward: [(0, '54.907')] [2023-03-09 11:14:53,971][119383] Updated weights for policy 0, policy_version 152299 (0.0016) [2023-03-09 11:14:54,867][119383] Updated weights for policy 0, policy_version 152309 (0.0014) [2023-03-09 11:14:55,611][119383] Updated weights for policy 0, policy_version 152319 (0.0017) [2023-03-09 11:14:56,503][119383] Updated weights for policy 0, policy_version 152329 (0.0014) [2023-03-09 11:14:57,390][119383] Updated weights for policy 0, policy_version 152339 (0.0013) [2023-03-09 11:14:58,116][119383] Updated weights for policy 0, policy_version 152349 (0.0019) [2023-03-09 11:14:58,329][119240] Signal inference workers to stop experience collection... (12700 times) [2023-03-09 11:14:58,330][119240] Signal inference workers to resume experience collection... (12700 times) [2023-03-09 11:14:58,395][119383] InferenceWorker_p0-w0: stopping experience collection (12700 times) [2023-03-09 11:14:58,395][119383] InferenceWorker_p0-w0: resuming experience collection (12700 times) [2023-03-09 11:14:58,902][118949] Fps is (10 sec: 196604.5, 60 sec: 194151.3, 300 sec: 195053.0). Total num frames: 2496217088. Throughput: 0: 48669.4. Samples: 124115008. Policy #0 lag: (min: 1.0, avg: 16.7, max: 34.0) [2023-03-09 11:14:58,904][118949] Avg episode reward: [(0, '54.196')] [2023-03-09 11:14:59,058][119383] Updated weights for policy 0, policy_version 152359 (0.0020) [2023-03-09 11:14:59,950][119383] Updated weights for policy 0, policy_version 152370 (0.0016) [2023-03-09 11:15:00,729][119383] Updated weights for policy 0, policy_version 152380 (0.0015) [2023-03-09 11:15:01,651][119383] Updated weights for policy 0, policy_version 152390 (0.0017) [2023-03-09 11:15:02,510][119383] Updated weights for policy 0, policy_version 152400 (0.0026) [2023-03-09 11:15:03,290][119383] Updated weights for policy 0, policy_version 152410 (0.0018) [2023-03-09 11:15:03,903][118949] Fps is (10 sec: 194962.7, 60 sec: 194694.4, 300 sec: 195108.2). Total num frames: 2497200128. Throughput: 0: 48713.6. Samples: 124262320. Policy #0 lag: (min: 1.0, avg: 16.7, max: 34.0) [2023-03-09 11:15:03,904][118949] Avg episode reward: [(0, '56.069')] [2023-03-09 11:15:04,174][119383] Updated weights for policy 0, policy_version 152420 (0.0021) [2023-03-09 11:15:05,004][119383] Updated weights for policy 0, policy_version 152430 (0.0035) [2023-03-09 11:15:05,772][119383] Updated weights for policy 0, policy_version 152440 (0.0017) [2023-03-09 11:15:06,669][119383] Updated weights for policy 0, policy_version 152450 (0.0013) [2023-03-09 11:15:06,890][119240] Signal inference workers to stop experience collection... (12750 times) [2023-03-09 11:15:06,891][119240] Signal inference workers to resume experience collection... (12750 times) [2023-03-09 11:15:06,956][119383] InferenceWorker_p0-w0: stopping experience collection (12750 times) [2023-03-09 11:15:06,956][119383] InferenceWorker_p0-w0: resuming experience collection (12750 times) [2023-03-09 11:15:07,375][119383] Updated weights for policy 0, policy_version 152460 (0.0021) [2023-03-09 11:15:08,274][119383] Updated weights for policy 0, policy_version 152470 (0.0016) [2023-03-09 11:15:08,902][118949] Fps is (10 sec: 198238.3, 60 sec: 195240.7, 300 sec: 195275.0). Total num frames: 2498199552. Throughput: 0: 48850.8. Samples: 124557120. Policy #0 lag: (min: 2.0, avg: 16.4, max: 34.0) [2023-03-09 11:15:08,905][118949] Avg episode reward: [(0, '56.293')] [2023-03-09 11:15:09,102][119383] Updated weights for policy 0, policy_version 152480 (0.0023) [2023-03-09 11:15:09,927][119383] Updated weights for policy 0, policy_version 152490 (0.0024) [2023-03-09 11:15:10,793][119383] Updated weights for policy 0, policy_version 152500 (0.0016) [2023-03-09 11:15:11,592][119383] Updated weights for policy 0, policy_version 152511 (0.0020) [2023-03-09 11:15:12,523][119383] Updated weights for policy 0, policy_version 152521 (0.0014) [2023-03-09 11:15:13,333][119383] Updated weights for policy 0, policy_version 152531 (0.0016) [2023-03-09 11:15:13,902][118949] Fps is (10 sec: 196618.7, 60 sec: 195242.4, 300 sec: 195108.4). Total num frames: 2499166208. Throughput: 0: 49080.3. Samples: 124854064. Policy #0 lag: (min: 2.0, avg: 16.4, max: 34.0) [2023-03-09 11:15:13,903][118949] Avg episode reward: [(0, '55.345')] [2023-03-09 11:15:14,149][119383] Updated weights for policy 0, policy_version 152542 (0.0016) [2023-03-09 11:15:14,892][119240] Signal inference workers to stop experience collection... (12800 times) [2023-03-09 11:15:14,892][119240] Signal inference workers to resume experience collection... (12800 times) [2023-03-09 11:15:14,956][119383] InferenceWorker_p0-w0: stopping experience collection (12800 times) [2023-03-09 11:15:14,956][119383] InferenceWorker_p0-w0: resuming experience collection (12800 times) [2023-03-09 11:15:15,238][119383] Updated weights for policy 0, policy_version 152553 (0.0013) [2023-03-09 11:15:16,226][119383] Updated weights for policy 0, policy_version 152564 (0.0020) [2023-03-09 11:15:16,926][119383] Updated weights for policy 0, policy_version 152574 (0.0022) [2023-03-09 11:15:17,853][119383] Updated weights for policy 0, policy_version 152584 (0.0026) [2023-03-09 11:15:18,220][119240] Stopping Batcher_0... [2023-03-09 11:15:18,220][119240] Loop batcher_evt_loop terminating... [2023-03-09 11:15:18,222][119240] Saving /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000152589_2500018176.pth... [2023-03-09 11:15:18,221][118949] Component Batcher_0 stopped! [2023-03-09 11:15:18,310][119240] Removing /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000149794_2454224896.pth [2023-03-09 11:15:18,315][119240] Saving /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000152589_2500018176.pth... [2023-03-09 11:15:18,377][119383] Weights refcount: 2 0 [2023-03-09 11:15:18,378][119383] Stopping InferenceWorker_p0-w0... [2023-03-09 11:15:18,378][119383] Loop inference_proc0-0_evt_loop terminating... [2023-03-09 11:15:18,384][118949] Component InferenceWorker_p0-w0 stopped! [2023-03-09 11:15:18,581][119240] Stopping LearnerWorker_p0... [2023-03-09 11:15:18,581][119240] Loop learner_proc0_evt_loop terminating... [2023-03-09 11:15:18,609][118949] Component LearnerWorker_p0 stopped! [2023-03-09 11:15:20,262][119525] Stopping RolloutWorker_w78... [2023-03-09 11:15:20,263][119525] Loop rollout_proc78_evt_loop terminating... [2023-03-09 11:15:20,267][119396] Stopping RolloutWorker_w26... [2023-03-09 11:15:20,267][119396] Loop rollout_proc26_evt_loop terminating... [2023-03-09 11:15:20,267][118949] Component RolloutWorker_w78 stopped! [2023-03-09 11:15:20,269][118949] Component RolloutWorker_w6 stopped! [2023-03-09 11:15:20,270][118949] Component RolloutWorker_w26 stopped! [2023-03-09 11:15:20,266][119472] Stopping RolloutWorker_w6... [2023-03-09 11:15:20,271][119472] Loop rollout_proc6_evt_loop terminating... [2023-03-09 11:15:20,275][119388] Stopping RolloutWorker_w8... [2023-03-09 11:15:20,275][119495] Stopping RolloutWorker_w34... [2023-03-09 11:15:20,275][119388] Loop rollout_proc8_evt_loop terminating... [2023-03-09 11:15:20,275][119495] Loop rollout_proc34_evt_loop terminating... [2023-03-09 11:15:20,278][120135] Stopping RolloutWorker_w126... [2023-03-09 11:15:20,279][120135] Loop rollout_proc126_evt_loop terminating... [2023-03-09 11:15:20,276][118949] Component RolloutWorker_w57 stopped! [2023-03-09 11:15:20,280][118949] Component RolloutWorker_w8 stopped! [2023-03-09 11:15:20,282][118949] Component RolloutWorker_w34 stopped! [2023-03-09 11:15:20,283][118949] Component RolloutWorker_w126 stopped! [2023-03-09 11:15:20,287][119531] Stopping RolloutWorker_w57... [2023-03-09 11:15:20,287][119531] Loop rollout_proc57_evt_loop terminating... [2023-03-09 11:15:20,288][119500] Stopping RolloutWorker_w43... [2023-03-09 11:15:20,288][119537] Stopping RolloutWorker_w73... [2023-03-09 11:15:20,289][119500] Loop rollout_proc43_evt_loop terminating... [2023-03-09 11:15:20,289][119537] Loop rollout_proc73_evt_loop terminating... [2023-03-09 11:15:20,289][120904] Stopping RolloutWorker_w124... [2023-03-09 11:15:20,289][120904] Loop rollout_proc124_evt_loop terminating... [2023-03-09 11:15:20,289][119477] Stopping RolloutWorker_w33... [2023-03-09 11:15:20,290][119477] Loop rollout_proc33_evt_loop terminating... [2023-03-09 11:15:20,290][119484] Stopping RolloutWorker_w45... [2023-03-09 11:15:20,290][126685] Stopping RolloutWorker_w1... [2023-03-09 11:15:20,288][118949] Component RolloutWorker_w43 stopped! [2023-03-09 11:15:20,290][119506] Stopping RolloutWorker_w62... [2023-03-09 11:15:20,290][119484] Loop rollout_proc45_evt_loop terminating... [2023-03-09 11:15:20,290][126685] Loop rollout_proc1_evt_loop terminating... [2023-03-09 11:15:20,291][119506] Loop rollout_proc62_evt_loop terminating... [2023-03-09 11:15:20,291][120005] Stopping RolloutWorker_w108... [2023-03-09 11:15:20,291][120005] Loop rollout_proc108_evt_loop terminating... [2023-03-09 11:15:20,291][119491] Stopping RolloutWorker_w25... [2023-03-09 11:15:20,292][119491] Loop rollout_proc25_evt_loop terminating... [2023-03-09 11:15:20,292][119545] Stopping RolloutWorker_w49... [2023-03-09 11:15:20,292][119545] Loop rollout_proc49_evt_loop terminating... [2023-03-09 11:15:20,292][119398] Stopping RolloutWorker_w32... [2023-03-09 11:15:20,293][119398] Loop rollout_proc32_evt_loop terminating... [2023-03-09 11:15:20,293][119549] Stopping RolloutWorker_w101... [2023-03-09 11:15:20,293][119493] Stopping RolloutWorker_w22... [2023-03-09 11:15:20,294][119475] Stopping RolloutWorker_w24... [2023-03-09 11:15:20,292][118949] Component RolloutWorker_w73 stopped! [2023-03-09 11:15:20,295][119469] Stopping RolloutWorker_w9... [2023-03-09 11:15:20,295][119549] Loop rollout_proc101_evt_loop terminating... [2023-03-09 11:15:20,295][119475] Loop rollout_proc24_evt_loop terminating... [2023-03-09 11:15:20,295][119493] Loop rollout_proc22_evt_loop terminating... [2023-03-09 11:15:20,295][119469] Loop rollout_proc9_evt_loop terminating... [2023-03-09 11:15:20,295][119390] Stopping RolloutWorker_w5... [2023-03-09 11:15:20,296][120717] Stopping RolloutWorker_w106... [2023-03-09 11:15:20,296][119390] Loop rollout_proc5_evt_loop terminating... [2023-03-09 11:15:20,296][120717] Loop rollout_proc106_evt_loop terminating... [2023-03-09 11:15:20,292][119550] Stopping RolloutWorker_w98... [2023-03-09 11:15:20,296][119550] Loop rollout_proc98_evt_loop terminating... [2023-03-09 11:15:20,297][119529] Stopping RolloutWorker_w69... [2023-03-09 11:15:20,297][119529] Loop rollout_proc69_evt_loop terminating... [2023-03-09 11:15:20,296][118949] Component RolloutWorker_w124 stopped! [2023-03-09 11:15:20,298][118949] Component RolloutWorker_w33 stopped! [2023-03-09 11:15:20,299][118949] Component RolloutWorker_w45 stopped! [2023-03-09 11:15:20,300][118949] Component RolloutWorker_w1 stopped! [2023-03-09 11:15:20,305][118949] Component RolloutWorker_w62 stopped! [2023-03-09 11:15:20,306][118949] Component RolloutWorker_w108 stopped! [2023-03-09 11:15:20,307][118949] Component RolloutWorker_w25 stopped! [2023-03-09 11:15:20,308][118949] Component RolloutWorker_w49 stopped! [2023-03-09 11:15:20,309][118949] Component RolloutWorker_w32 stopped! [2023-03-09 11:15:20,309][119851] Stopping RolloutWorker_w125... [2023-03-09 11:15:20,310][119851] Loop rollout_proc125_evt_loop terminating... [2023-03-09 11:15:20,311][119807] Stopping RolloutWorker_w116... [2023-03-09 11:15:20,311][119807] Loop rollout_proc116_evt_loop terminating... [2023-03-09 11:15:20,311][119466] Stopping RolloutWorker_w44... [2023-03-09 11:15:20,312][119466] Loop rollout_proc44_evt_loop terminating... [2023-03-09 11:15:20,312][119519] Stopping RolloutWorker_w81... [2023-03-09 11:15:20,312][119519] Loop rollout_proc81_evt_loop terminating... [2023-03-09 11:15:20,312][119502] Stopping RolloutWorker_w47... [2023-03-09 11:15:20,312][120615] Stopping RolloutWorker_w117... [2023-03-09 11:15:20,312][120263] Stopping RolloutWorker_w97... [2023-03-09 11:15:20,313][120615] Loop rollout_proc117_evt_loop terminating... [2023-03-09 11:15:20,313][119502] Loop rollout_proc47_evt_loop terminating... [2023-03-09 11:15:20,313][120263] Loop rollout_proc97_evt_loop terminating... [2023-03-09 11:15:20,313][119518] Stopping RolloutWorker_w54... [2023-03-09 11:15:20,314][119518] Loop rollout_proc54_evt_loop terminating... [2023-03-09 11:15:20,314][119507] Stopping RolloutWorker_w56... [2023-03-09 11:15:20,314][119538] Stopping RolloutWorker_w85... [2023-03-09 11:15:20,314][121015] Stopping RolloutWorker_w118... [2023-03-09 11:15:20,314][119478] Stopping RolloutWorker_w12... [2023-03-09 11:15:20,314][119546] Stopping RolloutWorker_w92... [2023-03-09 11:15:20,314][119538] Loop rollout_proc85_evt_loop terminating... [2023-03-09 11:15:20,314][119946] Stopping RolloutWorker_w96... [2023-03-09 11:15:20,314][119507] Loop rollout_proc56_evt_loop terminating... [2023-03-09 11:15:20,314][119478] Loop rollout_proc12_evt_loop terminating... [2023-03-09 11:15:20,314][119394] Stopping RolloutWorker_w23... [2023-03-09 11:15:20,314][119392] Stopping RolloutWorker_w14... [2023-03-09 11:15:20,314][119497] Stopping RolloutWorker_w13... [2023-03-09 11:15:20,314][121015] Loop rollout_proc118_evt_loop terminating... [2023-03-09 11:15:20,314][119546] Loop rollout_proc92_evt_loop terminating... [2023-03-09 11:15:20,314][119946] Loop rollout_proc96_evt_loop terminating... [2023-03-09 11:15:20,314][119394] Loop rollout_proc23_evt_loop terminating... [2023-03-09 11:15:20,314][119395] Stopping RolloutWorker_w11... [2023-03-09 11:15:20,314][119392] Loop rollout_proc14_evt_loop terminating... [2023-03-09 11:15:20,314][119497] Loop rollout_proc13_evt_loop terminating... [2023-03-09 11:15:20,315][119395] Loop rollout_proc11_evt_loop terminating... [2023-03-09 11:15:20,316][119534] Stopping RolloutWorker_w82... [2023-03-09 11:15:20,316][120778] Stopping RolloutWorker_w121... [2023-03-09 11:15:20,316][119522] Stopping RolloutWorker_w72... [2023-03-09 11:15:20,316][120073] Stopping RolloutWorker_w114... [2023-03-09 11:15:20,316][119534] Loop rollout_proc82_evt_loop terminating... [2023-03-09 11:15:20,316][120778] Loop rollout_proc121_evt_loop terminating... [2023-03-09 11:15:20,316][119522] Loop rollout_proc72_evt_loop terminating... [2023-03-09 11:15:20,317][120073] Loop rollout_proc114_evt_loop terminating... [2023-03-09 11:15:20,317][119481] Stopping RolloutWorker_w39... [2023-03-09 11:15:20,317][119481] Loop rollout_proc39_evt_loop terminating... [2023-03-09 11:15:20,317][119937] Stopping RolloutWorker_w93... [2023-03-09 11:15:20,317][119496] Stopping RolloutWorker_w37... [2023-03-09 11:15:20,317][120648] Stopping RolloutWorker_w100... [2023-03-09 11:15:20,317][119505] Stopping RolloutWorker_w59... [2023-03-09 11:15:20,318][120002] Stopping RolloutWorker_w102... [2023-03-09 11:15:20,318][119489] Stopping RolloutWorker_w10... [2023-03-09 11:15:20,318][119399] Stopping RolloutWorker_w35... [2023-03-09 11:15:20,318][120004] Stopping RolloutWorker_w99... [2023-03-09 11:15:20,318][119615] Stopping RolloutWorker_w107... [2023-03-09 11:15:20,318][119614] Stopping RolloutWorker_w104... [2023-03-09 11:15:20,318][119486] Stopping RolloutWorker_w4... [2023-03-09 11:15:20,318][119496] Loop rollout_proc37_evt_loop terminating... [2023-03-09 11:15:20,318][119937] Loop rollout_proc93_evt_loop terminating... [2023-03-09 11:15:20,318][119505] Loop rollout_proc59_evt_loop terminating... [2023-03-09 11:15:20,318][120648] Loop rollout_proc100_evt_loop terminating... [2023-03-09 11:15:20,318][119504] Stopping RolloutWorker_w53... [2023-03-09 11:15:20,318][125883] Stopping RolloutWorker_w0... [2023-03-09 11:15:20,318][120002] Loop rollout_proc102_evt_loop terminating... [2023-03-09 11:15:20,318][119470] Stopping RolloutWorker_w3... [2023-03-09 11:15:20,318][119614] Loop rollout_proc104_evt_loop terminating... [2023-03-09 11:15:20,318][119511] Stopping RolloutWorker_w80... [2023-03-09 11:15:20,318][119389] Stopping RolloutWorker_w2... [2023-03-09 11:15:20,318][119680] Stopping RolloutWorker_w113... [2023-03-09 11:15:20,318][119615] Loop rollout_proc107_evt_loop terminating... [2023-03-09 11:15:20,318][119533] Stopping RolloutWorker_w55... [2023-03-09 11:15:20,318][120653] Stopping RolloutWorker_w115... [2023-03-09 11:15:20,318][120004] Loop rollout_proc99_evt_loop terminating... [2023-03-09 11:15:20,318][119399] Loop rollout_proc35_evt_loop terminating... [2023-03-09 11:15:20,318][119542] Stopping RolloutWorker_w64... [2023-03-09 11:15:20,318][119523] Stopping RolloutWorker_w84... [2023-03-09 11:15:20,318][119508] Stopping RolloutWorker_w68... [2023-03-09 11:15:20,318][119397] Stopping RolloutWorker_w29... [2023-03-09 11:15:20,318][119391] Stopping RolloutWorker_w17... [2023-03-09 11:15:20,318][119510] Stopping RolloutWorker_w74... [2023-03-09 11:15:20,318][119489] Loop rollout_proc10_evt_loop terminating... [2023-03-09 11:15:20,318][119486] Loop rollout_proc4_evt_loop terminating... [2023-03-09 11:15:20,318][119540] Stopping RolloutWorker_w76... [2023-03-09 11:15:20,318][119501] Stopping RolloutWorker_w46... [2023-03-09 11:15:20,318][119528] Stopping RolloutWorker_w87... [2023-03-09 11:15:20,318][119470] Loop rollout_proc3_evt_loop terminating... [2023-03-09 11:15:20,318][125883] Loop rollout_proc0_evt_loop terminating... [2023-03-09 11:15:20,318][119389] Loop rollout_proc2_evt_loop terminating... [2023-03-09 11:15:20,318][119504] Loop rollout_proc53_evt_loop terminating... [2023-03-09 11:15:20,318][119533] Loop rollout_proc55_evt_loop terminating... [2023-03-09 11:15:20,318][119680] Loop rollout_proc113_evt_loop terminating... [2023-03-09 11:15:20,318][120653] Loop rollout_proc115_evt_loop terminating... [2023-03-09 11:15:20,318][119511] Loop rollout_proc80_evt_loop terminating... [2023-03-09 11:15:20,318][119542] Loop rollout_proc64_evt_loop terminating... [2023-03-09 11:15:20,318][119523] Loop rollout_proc84_evt_loop terminating... [2023-03-09 11:15:20,319][119391] Loop rollout_proc17_evt_loop terminating... [2023-03-09 11:15:20,319][119397] Loop rollout_proc29_evt_loop terminating... [2023-03-09 11:15:20,319][119510] Loop rollout_proc74_evt_loop terminating... [2023-03-09 11:15:20,319][119508] Loop rollout_proc68_evt_loop terminating... [2023-03-09 11:15:20,319][119540] Loop rollout_proc76_evt_loop terminating... [2023-03-09 11:15:20,319][119528] Loop rollout_proc87_evt_loop terminating... [2023-03-09 11:15:20,319][119501] Loop rollout_proc46_evt_loop terminating... [2023-03-09 11:15:20,322][119547] Stopping RolloutWorker_w95... [2023-03-09 11:15:20,322][119547] Loop rollout_proc95_evt_loop terminating... [2023-03-09 11:15:20,322][119488] Stopping RolloutWorker_w16... [2023-03-09 11:15:20,323][119488] Loop rollout_proc16_evt_loop terminating... [2023-03-09 11:15:20,323][119494] Stopping RolloutWorker_w31... [2023-03-09 11:15:20,324][119494] Loop rollout_proc31_evt_loop terminating... [2023-03-09 11:15:20,325][119514] Stopping RolloutWorker_w83... [2023-03-09 11:15:20,325][119655] Stopping RolloutWorker_w110... [2023-03-09 11:15:20,325][119490] Stopping RolloutWorker_w19... [2023-03-09 11:15:20,325][119516] Stopping RolloutWorker_w86... [2023-03-09 11:15:20,325][119514] Loop rollout_proc83_evt_loop terminating... [2023-03-09 11:15:20,325][120040] Stopping RolloutWorker_w111... [2023-03-09 11:15:20,326][119490] Loop rollout_proc19_evt_loop terminating... [2023-03-09 11:15:20,325][119655] Loop rollout_proc110_evt_loop terminating... [2023-03-09 11:15:20,326][119516] Loop rollout_proc86_evt_loop terminating... [2023-03-09 11:15:20,326][120040] Loop rollout_proc111_evt_loop terminating... [2023-03-09 11:15:20,326][119515] Stopping RolloutWorker_w89... [2023-03-09 11:15:20,327][119515] Loop rollout_proc89_evt_loop terminating... [2023-03-09 11:15:20,330][118949] Component RolloutWorker_w98 stopped! [2023-03-09 11:15:20,333][118949] Component RolloutWorker_w101 stopped! [2023-03-09 11:15:20,334][118949] Component RolloutWorker_w22 stopped! [2023-03-09 11:15:20,335][119512] Stopping RolloutWorker_w77... [2023-03-09 11:15:20,336][119512] Loop rollout_proc77_evt_loop terminating... [2023-03-09 11:15:20,337][119393] Stopping RolloutWorker_w20... [2023-03-09 11:15:20,337][119476] Stopping RolloutWorker_w21... [2023-03-09 11:15:20,337][119541] Stopping RolloutWorker_w88... [2023-03-09 11:15:20,337][119536] Stopping RolloutWorker_w91... [2023-03-09 11:15:20,337][119479] Stopping RolloutWorker_w27... [2023-03-09 11:15:20,337][119393] Loop rollout_proc20_evt_loop terminating... [2023-03-09 11:15:20,337][119464] Stopping RolloutWorker_w41... [2023-03-09 11:15:20,337][120896] Stopping RolloutWorker_w127... [2023-03-09 11:15:20,338][119476] Loop rollout_proc21_evt_loop terminating... [2023-03-09 11:15:20,338][119541] Loop rollout_proc88_evt_loop terminating... [2023-03-09 11:15:20,338][119517] Stopping RolloutWorker_w60... [2023-03-09 11:15:20,337][119498] Stopping RolloutWorker_w28... [2023-03-09 11:15:20,338][119479] Loop rollout_proc27_evt_loop terminating... [2023-03-09 11:15:20,338][119464] Loop rollout_proc41_evt_loop terminating... [2023-03-09 11:15:20,338][119536] Loop rollout_proc91_evt_loop terminating... [2023-03-09 11:15:20,338][120896] Loop rollout_proc127_evt_loop terminating... [2023-03-09 11:15:20,338][119517] Loop rollout_proc60_evt_loop terminating... [2023-03-09 11:15:20,338][119498] Loop rollout_proc28_evt_loop terminating... [2023-03-09 11:15:20,339][120003] Stopping RolloutWorker_w105... [2023-03-09 11:15:20,339][120003] Loop rollout_proc105_evt_loop terminating... [2023-03-09 11:15:20,340][119532] Stopping RolloutWorker_w61... [2023-03-09 11:15:20,340][119900] Stopping RolloutWorker_w122... [2023-03-09 11:15:20,340][119548] Stopping RolloutWorker_w58... [2023-03-09 11:15:20,340][119527] Stopping RolloutWorker_w63... [2023-03-09 11:15:20,340][119513] Stopping RolloutWorker_w71... [2023-03-09 11:15:20,340][119530] Stopping RolloutWorker_w48... [2023-03-09 11:15:20,340][119520] Stopping RolloutWorker_w51... [2023-03-09 11:15:20,340][119462] Stopping RolloutWorker_w38... [2023-03-09 11:15:20,340][119483] Stopping RolloutWorker_w36... [2023-03-09 11:15:20,340][120199] Stopping RolloutWorker_w123... [2023-03-09 11:15:20,341][119532] Loop rollout_proc61_evt_loop terminating... [2023-03-09 11:15:20,340][119524] Stopping RolloutWorker_w75... [2023-03-09 11:15:20,340][120877] Stopping RolloutWorker_w109... [2023-03-09 11:15:20,341][119527] Loop rollout_proc63_evt_loop terminating... [2023-03-09 11:15:20,341][119548] Loop rollout_proc58_evt_loop terminating... [2023-03-09 11:15:20,341][119513] Loop rollout_proc71_evt_loop terminating... [2023-03-09 11:15:20,341][119900] Loop rollout_proc122_evt_loop terminating... [2023-03-09 11:15:20,341][119530] Loop rollout_proc48_evt_loop terminating... [2023-03-09 11:15:20,341][119520] Loop rollout_proc51_evt_loop terminating... [2023-03-09 11:15:20,341][119483] Loop rollout_proc36_evt_loop terminating... [2023-03-09 11:15:20,341][119462] Loop rollout_proc38_evt_loop terminating... [2023-03-09 11:15:20,341][120199] Loop rollout_proc123_evt_loop terminating... [2023-03-09 11:15:20,341][119524] Loop rollout_proc75_evt_loop terminating... [2023-03-09 11:15:20,341][120877] Loop rollout_proc109_evt_loop terminating... [2023-03-09 11:15:20,343][120629] Stopping RolloutWorker_w103... [2023-03-09 11:15:20,344][120629] Loop rollout_proc103_evt_loop terminating... [2023-03-09 11:15:20,335][118949] Component RolloutWorker_w24 stopped! [2023-03-09 11:15:20,345][118949] Component RolloutWorker_w9 stopped! [2023-03-09 11:15:20,347][119509] Stopping RolloutWorker_w65... [2023-03-09 11:15:20,348][119509] Loop rollout_proc65_evt_loop terminating... [2023-03-09 11:15:20,349][119521] Stopping RolloutWorker_w90... [2023-03-09 11:15:20,350][119543] Stopping RolloutWorker_w67... [2023-03-09 11:15:20,350][120134] Stopping RolloutWorker_w120... [2023-03-09 11:15:20,351][119808] Stopping RolloutWorker_w119... [2023-03-09 11:15:20,351][119503] Stopping RolloutWorker_w50... [2023-03-09 11:15:20,350][119535] Stopping RolloutWorker_w52... [2023-03-09 11:15:20,351][119544] Stopping RolloutWorker_w70... [2023-03-09 11:15:20,351][119474] Stopping RolloutWorker_w18... [2023-03-09 11:15:20,352][120652] Stopping RolloutWorker_w112... [2023-03-09 11:15:20,354][120652] Loop rollout_proc112_evt_loop terminating... [2023-03-09 11:15:20,354][120134] Loop rollout_proc120_evt_loop terminating... [2023-03-09 11:15:20,354][119503] Loop rollout_proc50_evt_loop terminating... [2023-03-09 11:15:20,353][118949] Component RolloutWorker_w5 stopped! [2023-03-09 11:15:20,354][119543] Loop rollout_proc67_evt_loop terminating... [2023-03-09 11:15:20,354][119808] Loop rollout_proc119_evt_loop terminating... [2023-03-09 11:15:20,354][119535] Loop rollout_proc52_evt_loop terminating... [2023-03-09 11:15:20,354][119521] Loop rollout_proc90_evt_loop terminating... [2023-03-09 11:15:20,354][119544] Loop rollout_proc70_evt_loop terminating... [2023-03-09 11:15:20,354][119526] Stopping RolloutWorker_w66... [2023-03-09 11:15:20,354][119474] Loop rollout_proc18_evt_loop terminating... [2023-03-09 11:15:20,354][119526] Loop rollout_proc66_evt_loop terminating... [2023-03-09 11:15:20,355][118949] Component RolloutWorker_w106 stopped! [2023-03-09 11:15:20,358][118949] Component RolloutWorker_w69 stopped! [2023-03-09 11:15:20,360][119485] Stopping RolloutWorker_w42... [2023-03-09 11:15:20,368][119487] Stopping RolloutWorker_w7... [2023-03-09 11:15:20,372][119487] Loop rollout_proc7_evt_loop terminating... [2023-03-09 11:15:20,365][119485] Loop rollout_proc42_evt_loop terminating... [2023-03-09 11:15:20,368][118949] Component RolloutWorker_w125 stopped! [2023-03-09 11:15:20,374][119539] Stopping RolloutWorker_w79... [2023-03-09 11:15:20,375][119539] Loop rollout_proc79_evt_loop terminating... [2023-03-09 11:15:20,374][118949] Component RolloutWorker_w116 stopped! [2023-03-09 11:15:20,377][118949] Component RolloutWorker_w44 stopped! [2023-03-09 11:15:20,379][118949] Component RolloutWorker_w81 stopped! [2023-03-09 11:15:20,381][118949] Component RolloutWorker_w117 stopped! [2023-03-09 11:15:20,382][118949] Component RolloutWorker_w47 stopped! [2023-03-09 11:15:20,384][118949] Component RolloutWorker_w97 stopped! [2023-03-09 11:15:20,385][120550] Stopping RolloutWorker_w94... [2023-03-09 11:15:20,386][120550] Loop rollout_proc94_evt_loop terminating... [2023-03-09 11:15:20,385][118949] Component RolloutWorker_w54 stopped! [2023-03-09 11:15:20,387][118949] Component RolloutWorker_w118 stopped! [2023-03-09 11:15:20,388][118949] Component RolloutWorker_w12 stopped! [2023-03-09 11:15:20,390][118949] Component RolloutWorker_w56 stopped! [2023-03-09 11:15:20,391][118949] Component RolloutWorker_w85 stopped! [2023-03-09 11:15:20,393][118949] Component RolloutWorker_w92 stopped! [2023-03-09 11:15:20,394][118949] Component RolloutWorker_w96 stopped! [2023-03-09 11:15:20,395][118949] Component RolloutWorker_w23 stopped! [2023-03-09 11:15:20,396][118949] Component RolloutWorker_w14 stopped! [2023-03-09 11:15:20,398][118949] Component RolloutWorker_w13 stopped! [2023-03-09 11:15:20,405][118949] Component RolloutWorker_w11 stopped! [2023-03-09 11:15:20,408][119473] Stopping RolloutWorker_w15... [2023-03-09 11:15:20,408][118949] Component RolloutWorker_w82 stopped! [2023-03-09 11:15:20,410][119473] Loop rollout_proc15_evt_loop terminating... [2023-03-09 11:15:20,410][118949] Component RolloutWorker_w121 stopped! [2023-03-09 11:15:20,412][118949] Component RolloutWorker_w72 stopped! [2023-03-09 11:15:20,413][118949] Component RolloutWorker_w114 stopped! [2023-03-09 11:15:20,414][118949] Component RolloutWorker_w39 stopped! [2023-03-09 11:15:20,416][118949] Component RolloutWorker_w93 stopped! [2023-03-09 11:15:20,417][119480] Stopping RolloutWorker_w30... [2023-03-09 11:15:20,417][118949] Component RolloutWorker_w59 stopped! [2023-03-09 11:15:20,418][118949] Component RolloutWorker_w37 stopped! [2023-03-09 11:15:20,419][118949] Component RolloutWorker_w100 stopped! [2023-03-09 11:15:20,420][118949] Component RolloutWorker_w4 stopped! [2023-03-09 11:15:20,421][118949] Component RolloutWorker_w99 stopped! [2023-03-09 11:15:20,422][118949] Component RolloutWorker_w35 stopped! [2023-03-09 11:15:20,424][118949] Component RolloutWorker_w102 stopped! [2023-03-09 11:15:20,424][118949] Component RolloutWorker_w10 stopped! [2023-03-09 11:15:20,426][118949] Component RolloutWorker_w107 stopped! [2023-03-09 11:15:20,427][118949] Component RolloutWorker_w104 stopped! [2023-03-09 11:15:20,428][118949] Component RolloutWorker_w53 stopped! [2023-03-09 11:15:20,428][118949] Component RolloutWorker_w0 stopped! [2023-03-09 11:15:20,429][118949] Component RolloutWorker_w3 stopped! [2023-03-09 11:15:20,430][118949] Component RolloutWorker_w113 stopped! [2023-03-09 11:15:20,431][118949] Component RolloutWorker_w80 stopped! [2023-03-09 11:15:20,431][118949] Component RolloutWorker_w2 stopped! [2023-03-09 11:15:20,432][118949] Component RolloutWorker_w68 stopped! [2023-03-09 11:15:20,433][119499] Stopping RolloutWorker_w40... [2023-03-09 11:15:20,434][119499] Loop rollout_proc40_evt_loop terminating... [2023-03-09 11:15:20,443][118949] Component RolloutWorker_w55 stopped! [2023-03-09 11:15:20,445][119480] Loop rollout_proc30_evt_loop terminating... [2023-03-09 11:15:20,445][118949] Component RolloutWorker_w64 stopped! [2023-03-09 11:15:20,446][118949] Component RolloutWorker_w74 stopped! [2023-03-09 11:15:20,447][118949] Component RolloutWorker_w29 stopped! [2023-03-09 11:15:20,448][118949] Component RolloutWorker_w84 stopped! [2023-03-09 11:15:20,449][118949] Component RolloutWorker_w17 stopped! [2023-03-09 11:15:20,450][118949] Component RolloutWorker_w115 stopped! [2023-03-09 11:15:20,451][118949] Component RolloutWorker_w87 stopped! [2023-03-09 11:15:20,452][118949] Component RolloutWorker_w76 stopped! [2023-03-09 11:15:20,452][118949] Component RolloutWorker_w46 stopped! [2023-03-09 11:15:20,453][118949] Component RolloutWorker_w95 stopped! [2023-03-09 11:15:20,454][118949] Component RolloutWorker_w16 stopped! [2023-03-09 11:15:20,455][118949] Component RolloutWorker_w31 stopped! [2023-03-09 11:15:20,456][118949] Component RolloutWorker_w83 stopped! [2023-03-09 11:15:20,457][118949] Component RolloutWorker_w110 stopped! [2023-03-09 11:15:20,458][118949] Component RolloutWorker_w19 stopped! [2023-03-09 11:15:20,459][118949] Component RolloutWorker_w86 stopped! [2023-03-09 11:15:20,460][118949] Component RolloutWorker_w111 stopped! [2023-03-09 11:15:20,461][118949] Component RolloutWorker_w89 stopped! [2023-03-09 11:15:20,462][118949] Component RolloutWorker_w77 stopped! [2023-03-09 11:15:20,463][118949] Component RolloutWorker_w20 stopped! [2023-03-09 11:15:20,464][118949] Component RolloutWorker_w21 stopped! [2023-03-09 11:15:20,465][118949] Component RolloutWorker_w41 stopped! [2023-03-09 11:15:20,466][118949] Component RolloutWorker_w91 stopped! [2023-03-09 11:15:20,467][118949] Component RolloutWorker_w88 stopped! [2023-03-09 11:15:20,468][118949] Component RolloutWorker_w27 stopped! [2023-03-09 11:15:20,469][118949] Component RolloutWorker_w127 stopped! [2023-03-09 11:15:20,469][118949] Component RolloutWorker_w28 stopped! [2023-03-09 11:15:20,470][118949] Component RolloutWorker_w60 stopped! [2023-03-09 11:15:20,471][118949] Component RolloutWorker_w105 stopped! [2023-03-09 11:15:20,472][118949] Component RolloutWorker_w61 stopped! [2023-03-09 11:15:20,473][118949] Component RolloutWorker_w58 stopped! [2023-03-09 11:15:20,474][118949] Component RolloutWorker_w122 stopped! [2023-03-09 11:15:20,475][118949] Component RolloutWorker_w63 stopped! [2023-03-09 11:15:20,476][118949] Component RolloutWorker_w71 stopped! [2023-03-09 11:15:20,476][118949] Component RolloutWorker_w38 stopped! [2023-03-09 11:15:20,477][118949] Component RolloutWorker_w51 stopped! [2023-03-09 11:15:20,478][118949] Component RolloutWorker_w36 stopped! [2023-03-09 11:15:20,478][118949] Component RolloutWorker_w48 stopped! [2023-03-09 11:15:20,479][118949] Component RolloutWorker_w123 stopped! [2023-03-09 11:15:20,479][118949] Component RolloutWorker_w75 stopped! [2023-03-09 11:15:20,480][118949] Component RolloutWorker_w109 stopped! [2023-03-09 11:15:20,481][118949] Component RolloutWorker_w103 stopped! [2023-03-09 11:15:20,481][118949] Component RolloutWorker_w65 stopped! [2023-03-09 11:15:20,482][118949] Component RolloutWorker_w90 stopped! [2023-03-09 11:15:20,483][118949] Component RolloutWorker_w67 stopped! [2023-03-09 11:15:20,483][118949] Component RolloutWorker_w120 stopped! [2023-03-09 11:15:20,484][118949] Component RolloutWorker_w52 stopped! [2023-03-09 11:15:20,485][118949] Component RolloutWorker_w119 stopped! [2023-03-09 11:15:20,486][118949] Component RolloutWorker_w50 stopped! [2023-03-09 11:15:20,486][118949] Component RolloutWorker_w70 stopped! [2023-03-09 11:15:20,487][118949] Component RolloutWorker_w18 stopped! [2023-03-09 11:15:20,488][118949] Component RolloutWorker_w112 stopped! [2023-03-09 11:15:20,489][118949] Component RolloutWorker_w66 stopped! [2023-03-09 11:15:20,489][118949] Component RolloutWorker_w42 stopped! [2023-03-09 11:15:20,490][118949] Component RolloutWorker_w7 stopped! [2023-03-09 11:15:20,491][118949] Component RolloutWorker_w79 stopped! [2023-03-09 11:15:20,492][118949] Component RolloutWorker_w94 stopped! [2023-03-09 11:15:20,492][118949] Component RolloutWorker_w15 stopped! [2023-03-09 11:15:20,493][118949] Component RolloutWorker_w30 stopped! [2023-03-09 11:15:20,494][118949] Component RolloutWorker_w40 stopped! [2023-03-09 11:15:20,495][118949] Waiting for process learner_proc0 to stop... [2023-03-09 11:15:22,174][118949] Waiting for process inference_proc0-0 to join... [2023-03-09 11:15:22,175][118949] Waiting for process rollout_proc0 to join... [2023-03-09 11:15:22,175][118949] Waiting for process rollout_proc1 to join... [2023-03-09 11:15:22,176][118949] Waiting for process rollout_proc2 to join... [2023-03-09 11:15:22,177][118949] Waiting for process rollout_proc3 to join... [2023-03-09 11:15:22,178][118949] Waiting for process rollout_proc4 to join... [2023-03-09 11:15:22,179][118949] Waiting for process rollout_proc5 to join... [2023-03-09 11:15:22,179][118949] Waiting for process rollout_proc6 to join... [2023-03-09 11:15:22,180][118949] Waiting for process rollout_proc7 to join... [2023-03-09 11:15:22,181][118949] Waiting for process rollout_proc8 to join... [2023-03-09 11:15:22,181][118949] Waiting for process rollout_proc9 to join... [2023-03-09 11:15:22,182][118949] Waiting for process rollout_proc10 to join... [2023-03-09 11:15:22,183][118949] Waiting for process rollout_proc11 to join... [2023-03-09 11:15:22,183][118949] Waiting for process rollout_proc12 to join... [2023-03-09 11:15:22,184][118949] Waiting for process rollout_proc13 to join... [2023-03-09 11:15:22,185][118949] Waiting for process rollout_proc14 to join... [2023-03-09 11:15:22,185][118949] Waiting for process rollout_proc15 to join... [2023-03-09 11:15:22,186][118949] Waiting for process rollout_proc16 to join... [2023-03-09 11:15:22,187][118949] Waiting for process rollout_proc17 to join... [2023-03-09 11:15:22,187][118949] Waiting for process rollout_proc18 to join... [2023-03-09 11:15:22,188][118949] Waiting for process rollout_proc19 to join... [2023-03-09 11:15:22,189][118949] Waiting for process rollout_proc20 to join... [2023-03-09 11:15:22,189][118949] Waiting for process rollout_proc21 to join... [2023-03-09 11:15:22,190][118949] Waiting for process rollout_proc22 to join... [2023-03-09 11:15:22,191][118949] Waiting for process rollout_proc23 to join... [2023-03-09 11:15:22,191][118949] Waiting for process rollout_proc24 to join... [2023-03-09 11:15:22,192][118949] Waiting for process rollout_proc25 to join... [2023-03-09 11:15:22,193][118949] Waiting for process rollout_proc26 to join... [2023-03-09 11:15:22,193][118949] Waiting for process rollout_proc27 to join... [2023-03-09 11:15:22,194][118949] Waiting for process rollout_proc28 to join... [2023-03-09 11:15:22,195][118949] Waiting for process rollout_proc29 to join... [2023-03-09 11:15:22,195][118949] Waiting for process rollout_proc30 to join... [2023-03-09 11:15:22,196][118949] Waiting for process rollout_proc31 to join... [2023-03-09 11:15:22,197][118949] Waiting for process rollout_proc32 to join... [2023-03-09 11:15:22,197][118949] Waiting for process rollout_proc33 to join... [2023-03-09 11:15:22,198][118949] Waiting for process rollout_proc34 to join... [2023-03-09 11:15:22,199][118949] Waiting for process rollout_proc35 to join... [2023-03-09 11:15:22,199][118949] Waiting for process rollout_proc36 to join... [2023-03-09 11:15:22,200][118949] Waiting for process rollout_proc37 to join... [2023-03-09 11:15:22,201][118949] Waiting for process rollout_proc38 to join... [2023-03-09 11:15:22,201][118949] Waiting for process rollout_proc39 to join... [2023-03-09 11:15:22,202][118949] Waiting for process rollout_proc40 to join... [2023-03-09 11:15:22,203][118949] Waiting for process rollout_proc41 to join... [2023-03-09 11:15:22,203][118949] Waiting for process rollout_proc42 to join... [2023-03-09 11:15:22,204][118949] Waiting for process rollout_proc43 to join... [2023-03-09 11:15:22,207][118949] Waiting for process rollout_proc44 to join... [2023-03-09 11:15:22,207][118949] Waiting for process rollout_proc45 to join... [2023-03-09 11:15:22,208][118949] Waiting for process rollout_proc46 to join... [2023-03-09 11:15:22,209][118949] Waiting for process rollout_proc47 to join... [2023-03-09 11:15:22,209][118949] Waiting for process rollout_proc48 to join... [2023-03-09 11:15:22,210][118949] Waiting for process rollout_proc49 to join... [2023-03-09 11:15:22,211][118949] Waiting for process rollout_proc50 to join... [2023-03-09 11:15:22,212][118949] Waiting for process rollout_proc51 to join... [2023-03-09 11:15:22,212][118949] Waiting for process rollout_proc52 to join... [2023-03-09 11:15:22,213][118949] Waiting for process rollout_proc53 to join... [2023-03-09 11:15:22,214][118949] Waiting for process rollout_proc54 to join... [2023-03-09 11:15:22,214][118949] Waiting for process rollout_proc55 to join... [2023-03-09 11:15:22,215][118949] Waiting for process rollout_proc56 to join... [2023-03-09 11:15:22,216][118949] Waiting for process rollout_proc57 to join... [2023-03-09 11:15:22,218][118949] Waiting for process rollout_proc58 to join... [2023-03-09 11:15:22,219][118949] Waiting for process rollout_proc59 to join... [2023-03-09 11:15:22,220][118949] Waiting for process rollout_proc60 to join... [2023-03-09 11:15:22,221][118949] Waiting for process rollout_proc61 to join... [2023-03-09 11:15:22,222][118949] Waiting for process rollout_proc62 to join... [2023-03-09 11:15:22,223][118949] Waiting for process rollout_proc63 to join... [2023-03-09 11:15:22,224][118949] Waiting for process rollout_proc64 to join... [2023-03-09 11:15:22,225][118949] Waiting for process rollout_proc65 to join... [2023-03-09 11:15:22,226][118949] Waiting for process rollout_proc66 to join... [2023-03-09 11:15:22,227][118949] Waiting for process rollout_proc67 to join... [2023-03-09 11:15:22,228][118949] Waiting for process rollout_proc68 to join... [2023-03-09 11:15:22,229][118949] Waiting for process rollout_proc69 to join... [2023-03-09 11:15:22,230][118949] Waiting for process rollout_proc70 to join... [2023-03-09 11:15:22,231][118949] Waiting for process rollout_proc71 to join... [2023-03-09 11:15:22,231][118949] Waiting for process rollout_proc72 to join... [2023-03-09 11:15:22,233][118949] Waiting for process rollout_proc73 to join... [2023-03-09 11:15:22,234][118949] Waiting for process rollout_proc74 to join... [2023-03-09 11:15:22,235][118949] Waiting for process rollout_proc75 to join... [2023-03-09 11:15:22,236][118949] Waiting for process rollout_proc76 to join... [2023-03-09 11:15:22,237][118949] Waiting for process rollout_proc77 to join... [2023-03-09 11:15:22,238][118949] Waiting for process rollout_proc78 to join... [2023-03-09 11:15:22,238][118949] Waiting for process rollout_proc79 to join... [2023-03-09 11:15:22,239][118949] Waiting for process rollout_proc80 to join... [2023-03-09 11:15:22,242][118949] Waiting for process rollout_proc81 to join... [2023-03-09 11:15:22,243][118949] Waiting for process rollout_proc82 to join... [2023-03-09 11:15:22,244][118949] Waiting for process rollout_proc83 to join... [2023-03-09 11:15:22,245][118949] Waiting for process rollout_proc84 to join... [2023-03-09 11:15:22,246][118949] Waiting for process rollout_proc85 to join... [2023-03-09 11:15:22,246][118949] Waiting for process rollout_proc86 to join... [2023-03-09 11:15:22,247][118949] Waiting for process rollout_proc87 to join... [2023-03-09 11:15:22,251][118949] Waiting for process rollout_proc88 to join... [2023-03-09 11:15:22,252][118949] Waiting for process rollout_proc89 to join... [2023-03-09 11:15:22,253][118949] Waiting for process rollout_proc90 to join... [2023-03-09 11:15:22,254][118949] Waiting for process rollout_proc91 to join... [2023-03-09 11:15:22,255][118949] Waiting for process rollout_proc92 to join... [2023-03-09 11:15:22,255][118949] Waiting for process rollout_proc93 to join... [2023-03-09 11:15:22,259][118949] Waiting for process rollout_proc94 to join... [2023-03-09 11:15:22,260][118949] Waiting for process rollout_proc95 to join... [2023-03-09 11:15:22,260][118949] Waiting for process rollout_proc96 to join... [2023-03-09 11:15:22,261][118949] Waiting for process rollout_proc97 to join... [2023-03-09 11:15:22,262][118949] Waiting for process rollout_proc98 to join... [2023-03-09 11:15:22,263][118949] Waiting for process rollout_proc99 to join... [2023-03-09 11:15:22,263][118949] Waiting for process rollout_proc100 to join... [2023-03-09 11:15:22,266][118949] Waiting for process rollout_proc101 to join... [2023-03-09 11:15:22,267][118949] Waiting for process rollout_proc102 to join... [2023-03-09 11:15:22,267][118949] Waiting for process rollout_proc103 to join... [2023-03-09 11:15:22,268][118949] Waiting for process rollout_proc104 to join... [2023-03-09 11:15:22,269][118949] Waiting for process rollout_proc105 to join... [2023-03-09 11:15:22,269][118949] Waiting for process rollout_proc106 to join... [2023-03-09 11:15:22,270][118949] Waiting for process rollout_proc107 to join... [2023-03-09 11:15:22,271][118949] Waiting for process rollout_proc108 to join... [2023-03-09 11:15:22,272][118949] Waiting for process rollout_proc109 to join... [2023-03-09 11:15:22,272][118949] Waiting for process rollout_proc110 to join... [2023-03-09 11:15:22,273][118949] Waiting for process rollout_proc111 to join... [2023-03-09 11:15:22,274][118949] Waiting for process rollout_proc112 to join... [2023-03-09 11:15:22,274][118949] Waiting for process rollout_proc113 to join... [2023-03-09 11:15:22,275][118949] Waiting for process rollout_proc114 to join... [2023-03-09 11:15:22,276][118949] Waiting for process rollout_proc115 to join... [2023-03-09 11:15:22,277][118949] Waiting for process rollout_proc116 to join... [2023-03-09 11:15:22,277][118949] Waiting for process rollout_proc117 to join... [2023-03-09 11:15:22,278][118949] Waiting for process rollout_proc118 to join... [2023-03-09 11:15:22,279][118949] Waiting for process rollout_proc119 to join... [2023-03-09 11:15:22,280][118949] Waiting for process rollout_proc120 to join... [2023-03-09 11:15:22,282][118949] Waiting for process rollout_proc121 to join... [2023-03-09 11:15:22,282][118949] Waiting for process rollout_proc122 to join... [2023-03-09 11:15:22,283][118949] Waiting for process rollout_proc123 to join... [2023-03-09 11:15:22,284][118949] Waiting for process rollout_proc124 to join... [2023-03-09 11:15:22,285][118949] Waiting for process rollout_proc125 to join... [2023-03-09 11:15:22,285][118949] Waiting for process rollout_proc126 to join... [2023-03-09 11:15:22,286][118949] Waiting for process rollout_proc127 to join... [2023-03-09 11:15:22,287][118949] Batcher 0 profile tree view: batching: 729.7513, releasing_batches: 51.3643 [2023-03-09 11:15:22,287][118949] InferenceWorker_p0-w0 profile tree view: wait_policy: 0.0005 wait_policy_total: 118.2855 update_model: 65.1574 weight_update: 0.0013 one_step: 0.0420 handle_policy_step: 2421.1419 deserialize: 1173.2590, stack: 3.0098, obs_to_device_normalize: 565.3815, forward: 92.0461, send_messages: 163.3239 prepare_outputs: 392.6996 to_cpu: 233.5327 [2023-03-09 11:15:22,288][118949] Learner 0 profile tree view: misc: 0.1549, prepare_batch: 313.3371 train: 1226.2851 epoch_init: 0.1881, minibatch_init: 0.2061, losses_postprocess: 10.7958, kl_divergence: 12.1178, after_optimizer: 4.2730 calculate_losses: 454.2700 losses_init: 0.1299, forward_head: 37.4529, bptt_initial: 284.7093, tail: 24.9609, advantages_returns: 6.8865, losses: 39.9944 bptt: 53.9828 bptt_forward_core: 51.8326 update: 730.7814 clip: 51.7646 [2023-03-09 11:15:22,290][118949] RolloutWorker_w0 profile tree view: wait_for_trajectories: 0.7489, enqueue_policy_requests: 41.7256, env_step: 1060.5644, overhead: 92.8729, complete_rollouts: 0.3168 save_policy_outputs: 132.3614 split_output_tensors: 62.3981 [2023-03-09 11:15:22,291][118949] RolloutWorker_w127 profile tree view: wait_for_trajectories: 0.7653, enqueue_policy_requests: 43.0020, env_step: 1029.6907, overhead: 92.8958, complete_rollouts: 0.3263 save_policy_outputs: 134.1576 split_output_tensors: 63.0343 [2023-03-09 11:15:22,292][118949] Loop Runner_EvtLoop terminating... [2023-03-09 11:15:22,294][118949] Runner profile tree view: main_loop: 2633.7270 [2023-03-09 11:15:22,295][118949] Collected {0: 2500018176}, FPS: 189841.4 [2023-03-09 11:15:22,381][118949] Loading existing experiment configuration from /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/config.json [2023-03-09 11:15:22,381][118949] Overriding arg 'num_workers' with value 1 passed from command line [2023-03-09 11:15:22,382][118949] Adding new argument 'no_render'=True that is not in the saved config file! [2023-03-09 11:15:22,382][118949] Adding new argument 'save_video'=True that is not in the saved config file! [2023-03-09 11:15:22,383][118949] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file! [2023-03-09 11:15:22,384][118949] Adding new argument 'video_name'=None that is not in the saved config file! [2023-03-09 11:15:22,384][118949] Adding new argument 'max_num_frames'=1000000000.0 that is not in the saved config file! [2023-03-09 11:15:22,385][118949] Adding new argument 'max_num_episodes'=10 that is not in the saved config file! [2023-03-09 11:15:22,385][118949] Adding new argument 'push_to_hub'=False that is not in the saved config file! [2023-03-09 11:15:22,386][118949] Adding new argument 'hf_repository'=None that is not in the saved config file! [2023-03-09 11:15:22,387][118949] Adding new argument 'policy_index'=0 that is not in the saved config file! [2023-03-09 11:15:22,387][118949] Adding new argument 'eval_deterministic'=False that is not in the saved config file! [2023-03-09 11:15:22,388][118949] Adding new argument 'train_script'=None that is not in the saved config file! [2023-03-09 11:15:22,388][118949] Adding new argument 'enjoy_script'=None that is not in the saved config file! [2023-03-09 11:15:22,389][118949] Using frameskip 1 and render_action_repeat=4 for evaluation [2023-03-09 11:15:22,397][118949] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 11:15:22,398][118949] RunningMeanStd input shape: (3, 72, 128) [2023-03-09 11:15:22,400][118949] RunningMeanStd input shape: (1,) [2023-03-09 11:15:22,411][118949] ConvEncoder: input_channels=3 [2023-03-09 11:15:22,495][118949] Conv encoder output size: 512 [2023-03-09 11:15:22,497][118949] Policy head output size: 512 [2023-03-09 11:15:24,214][118949] Loading state from checkpoint /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000152589_2500018176.pth... [2023-03-09 11:15:25,206][118949] Num frames 100... [2023-03-09 11:15:25,293][118949] Num frames 200... [2023-03-09 11:15:25,379][118949] Num frames 300... [2023-03-09 11:15:25,466][118949] Num frames 400... [2023-03-09 11:15:25,552][118949] Num frames 500... [2023-03-09 11:15:25,639][118949] Num frames 600... [2023-03-09 11:15:25,728][118949] Num frames 700... [2023-03-09 11:15:25,815][118949] Num frames 800... [2023-03-09 11:15:25,903][118949] Num frames 900... [2023-03-09 11:15:25,989][118949] Num frames 1000... [2023-03-09 11:15:26,077][118949] Num frames 1100... [2023-03-09 11:15:26,164][118949] Num frames 1200... [2023-03-09 11:15:26,252][118949] Num frames 1300... [2023-03-09 11:15:26,340][118949] Num frames 1400... [2023-03-09 11:15:26,428][118949] Num frames 1500... [2023-03-09 11:15:26,517][118949] Num frames 1600... [2023-03-09 11:15:26,604][118949] Num frames 1700... [2023-03-09 11:15:26,691][118949] Num frames 1800... [2023-03-09 11:15:26,778][118949] Num frames 1900... [2023-03-09 11:15:26,868][118949] Num frames 2000... [2023-03-09 11:15:26,959][118949] Num frames 2100... [2023-03-09 11:15:27,011][118949] Avg episode rewards: #0: 59.999, true rewards: #0: 21.000 [2023-03-09 11:15:27,012][118949] Avg episode reward: 59.999, avg true_objective: 21.000 [2023-03-09 11:15:27,121][118949] Num frames 2200... [2023-03-09 11:15:27,208][118949] Num frames 2300... [2023-03-09 11:15:27,294][118949] Num frames 2400... [2023-03-09 11:15:27,381][118949] Num frames 2500... [2023-03-09 11:15:27,467][118949] Num frames 2600... [2023-03-09 11:15:27,553][118949] Num frames 2700... [2023-03-09 11:15:27,641][118949] Num frames 2800... [2023-03-09 11:15:27,728][118949] Num frames 2900... [2023-03-09 11:15:27,814][118949] Num frames 3000... [2023-03-09 11:15:27,903][118949] Num frames 3100... [2023-03-09 11:15:27,992][118949] Num frames 3200... [2023-03-09 11:15:28,080][118949] Num frames 3300... [2023-03-09 11:15:28,167][118949] Num frames 3400... [2023-03-09 11:15:28,254][118949] Num frames 3500... [2023-03-09 11:15:28,341][118949] Num frames 3600... [2023-03-09 11:15:28,431][118949] Num frames 3700... [2023-03-09 11:15:28,521][118949] Num frames 3800... [2023-03-09 11:15:28,608][118949] Num frames 3900... [2023-03-09 11:15:28,698][118949] Num frames 4000... [2023-03-09 11:15:28,786][118949] Num frames 4100... [2023-03-09 11:15:28,877][118949] Num frames 4200... [2023-03-09 11:15:28,929][118949] Avg episode rewards: #0: 63.499, true rewards: #0: 21.000 [2023-03-09 11:15:28,930][118949] Avg episode reward: 63.499, avg true_objective: 21.000 [2023-03-09 11:15:29,034][118949] Num frames 4300... [2023-03-09 11:15:29,121][118949] Num frames 4400... [2023-03-09 11:15:29,207][118949] Num frames 4500... [2023-03-09 11:15:29,294][118949] Num frames 4600... [2023-03-09 11:15:29,381][118949] Num frames 4700... [2023-03-09 11:15:29,469][118949] Num frames 4800... [2023-03-09 11:15:29,554][118949] Num frames 4900... [2023-03-09 11:15:29,645][118949] Num frames 5000... [2023-03-09 11:15:29,734][118949] Num frames 5100... [2023-03-09 11:15:29,821][118949] Num frames 5200... [2023-03-09 11:15:29,909][118949] Num frames 5300... [2023-03-09 11:15:29,994][118949] Num frames 5400... [2023-03-09 11:15:30,081][118949] Num frames 5500... [2023-03-09 11:15:30,169][118949] Num frames 5600... [2023-03-09 11:15:30,256][118949] Num frames 5700... [2023-03-09 11:15:30,344][118949] Num frames 5800... [2023-03-09 11:15:30,433][118949] Num frames 5900... [2023-03-09 11:15:30,520][118949] Num frames 6000... [2023-03-09 11:15:30,608][118949] Num frames 6100... [2023-03-09 11:15:30,697][118949] Num frames 6200... [2023-03-09 11:15:30,786][118949] Num frames 6300... [2023-03-09 11:15:30,838][118949] Avg episode rewards: #0: 63.332, true rewards: #0: 21.000 [2023-03-09 11:15:30,839][118949] Avg episode reward: 63.332, avg true_objective: 21.000 [2023-03-09 11:15:30,944][118949] Num frames 6400... [2023-03-09 11:15:31,032][118949] Num frames 6500... [2023-03-09 11:15:31,118][118949] Num frames 6600... [2023-03-09 11:15:31,204][118949] Num frames 6700... [2023-03-09 11:15:31,291][118949] Num frames 6800... [2023-03-09 11:15:31,377][118949] Num frames 6900... [2023-03-09 11:15:31,464][118949] Num frames 7000... [2023-03-09 11:15:31,551][118949] Num frames 7100... [2023-03-09 11:15:31,638][118949] Num frames 7200... [2023-03-09 11:15:31,725][118949] Num frames 7300... [2023-03-09 11:15:31,811][118949] Num frames 7400... [2023-03-09 11:15:31,900][118949] Num frames 7500... [2023-03-09 11:15:31,990][118949] Num frames 7600... [2023-03-09 11:15:32,078][118949] Num frames 7700... [2023-03-09 11:15:32,165][118949] Num frames 7800... [2023-03-09 11:15:32,253][118949] Num frames 7900... [2023-03-09 11:15:32,341][118949] Num frames 8000... [2023-03-09 11:15:32,430][118949] Num frames 8100... [2023-03-09 11:15:32,519][118949] Num frames 8200... [2023-03-09 11:15:32,606][118949] Num frames 8300... [2023-03-09 11:15:32,696][118949] Num frames 8400... [2023-03-09 11:15:32,748][118949] Avg episode rewards: #0: 62.749, true rewards: #0: 21.000 [2023-03-09 11:15:32,749][118949] Avg episode reward: 62.749, avg true_objective: 21.000 [2023-03-09 11:15:32,854][118949] Num frames 8500... [2023-03-09 11:15:32,939][118949] Num frames 8600... [2023-03-09 11:15:33,026][118949] Num frames 8700... [2023-03-09 11:15:33,112][118949] Num frames 8800... [2023-03-09 11:15:33,200][118949] Num frames 8900... [2023-03-09 11:15:33,287][118949] Num frames 9000... [2023-03-09 11:15:33,373][118949] Num frames 9100... [2023-03-09 11:15:33,461][118949] Num frames 9200... [2023-03-09 11:15:33,549][118949] Num frames 9300... [2023-03-09 11:15:33,636][118949] Num frames 9400... [2023-03-09 11:15:33,723][118949] Num frames 9500... [2023-03-09 11:15:33,809][118949] Num frames 9600... [2023-03-09 11:15:33,897][118949] Num frames 9700... [2023-03-09 11:15:33,985][118949] Num frames 9800... [2023-03-09 11:15:34,073][118949] Num frames 9900... [2023-03-09 11:15:34,160][118949] Num frames 10000... [2023-03-09 11:15:34,247][118949] Num frames 10100... [2023-03-09 11:15:34,334][118949] Num frames 10200... [2023-03-09 11:15:34,422][118949] Num frames 10300... [2023-03-09 11:15:34,510][118949] Num frames 10400... [2023-03-09 11:15:34,601][118949] Num frames 10500... [2023-03-09 11:15:34,653][118949] Avg episode rewards: #0: 61.999, true rewards: #0: 21.000 [2023-03-09 11:15:34,653][118949] Avg episode reward: 61.999, avg true_objective: 21.000 [2023-03-09 11:15:34,758][118949] Num frames 10600... [2023-03-09 11:15:34,843][118949] Num frames 10700... [2023-03-09 11:15:34,930][118949] Num frames 10800... [2023-03-09 11:15:35,017][118949] Num frames 10900... [2023-03-09 11:15:35,103][118949] Num frames 11000... [2023-03-09 11:15:35,189][118949] Num frames 11100... [2023-03-09 11:15:35,277][118949] Num frames 11200... [2023-03-09 11:15:35,365][118949] Num frames 11300... [2023-03-09 11:15:35,453][118949] Num frames 11400... [2023-03-09 11:15:35,542][118949] Num frames 11500... [2023-03-09 11:15:35,635][118949] Num frames 11600... [2023-03-09 11:15:35,724][118949] Num frames 11700... [2023-03-09 11:15:35,813][118949] Num frames 11800... [2023-03-09 11:15:35,901][118949] Num frames 11900... [2023-03-09 11:15:35,989][118949] Num frames 12000... [2023-03-09 11:15:36,077][118949] Num frames 12100... [2023-03-09 11:15:36,166][118949] Num frames 12200... [2023-03-09 11:15:36,254][118949] Num frames 12300... [2023-03-09 11:15:36,342][118949] Num frames 12400... [2023-03-09 11:15:36,430][118949] Num frames 12500... [2023-03-09 11:15:36,522][118949] Num frames 12600... [2023-03-09 11:15:36,574][118949] Avg episode rewards: #0: 62.499, true rewards: #0: 21.000 [2023-03-09 11:15:36,574][118949] Avg episode reward: 62.499, avg true_objective: 21.000 [2023-03-09 11:15:36,679][118949] Num frames 12700... [2023-03-09 11:15:36,769][118949] Num frames 12800... [2023-03-09 11:15:36,857][118949] Num frames 12900... [2023-03-09 11:15:36,943][118949] Num frames 13000... [2023-03-09 11:15:37,032][118949] Num frames 13100... [2023-03-09 11:15:37,121][118949] Num frames 13200... [2023-03-09 11:15:37,210][118949] Num frames 13300... [2023-03-09 11:15:37,298][118949] Num frames 13400... [2023-03-09 11:15:37,385][118949] Num frames 13500... [2023-03-09 11:15:37,474][118949] Num frames 13600... [2023-03-09 11:15:37,564][118949] Num frames 13700... [2023-03-09 11:15:37,653][118949] Num frames 13800... [2023-03-09 11:15:37,743][118949] Num frames 13900... [2023-03-09 11:15:37,831][118949] Num frames 14000... [2023-03-09 11:15:37,919][118949] Num frames 14100... [2023-03-09 11:15:38,009][118949] Num frames 14200... [2023-03-09 11:15:38,099][118949] Num frames 14300... [2023-03-09 11:15:38,188][118949] Num frames 14400... [2023-03-09 11:15:38,280][118949] Num frames 14500... [2023-03-09 11:15:38,365][118949] Num frames 14600... [2023-03-09 11:15:38,445][118949] Num frames 14700... [2023-03-09 11:15:38,496][118949] Avg episode rewards: #0: 62.570, true rewards: #0: 21.000 [2023-03-09 11:15:38,497][118949] Avg episode reward: 62.570, avg true_objective: 21.000 [2023-03-09 11:15:38,584][118949] Num frames 14800... [2023-03-09 11:15:38,671][118949] Num frames 14900... [2023-03-09 11:15:38,757][118949] Num frames 15000... [2023-03-09 11:15:38,842][118949] Num frames 15100... [2023-03-09 11:15:38,929][118949] Num frames 15200... [2023-03-09 11:15:39,016][118949] Num frames 15300... [2023-03-09 11:15:39,103][118949] Num frames 15400... [2023-03-09 11:15:39,190][118949] Num frames 15500... [2023-03-09 11:15:39,278][118949] Num frames 15600... [2023-03-09 11:15:39,365][118949] Num frames 15700... [2023-03-09 11:15:39,452][118949] Num frames 15800... [2023-03-09 11:15:39,538][118949] Num frames 15900... [2023-03-09 11:15:39,626][118949] Num frames 16000... [2023-03-09 11:15:39,713][118949] Num frames 16100... [2023-03-09 11:15:39,800][118949] Num frames 16200... [2023-03-09 11:15:39,891][118949] Num frames 16300... [2023-03-09 11:15:39,980][118949] Num frames 16400... [2023-03-09 11:15:40,068][118949] Num frames 16500... [2023-03-09 11:15:40,158][118949] Num frames 16600... [2023-03-09 11:15:40,246][118949] Num frames 16700... [2023-03-09 11:15:40,336][118949] Num frames 16800... [2023-03-09 11:15:40,388][118949] Avg episode rewards: #0: 62.624, true rewards: #0: 21.000 [2023-03-09 11:15:40,389][118949] Avg episode reward: 62.624, avg true_objective: 21.000 [2023-03-09 11:15:40,496][118949] Num frames 16900... [2023-03-09 11:15:40,582][118949] Num frames 17000... [2023-03-09 11:15:40,669][118949] Num frames 17100... [2023-03-09 11:15:40,756][118949] Num frames 17200... [2023-03-09 11:15:40,843][118949] Num frames 17300... [2023-03-09 11:15:40,931][118949] Num frames 17400... [2023-03-09 11:15:41,018][118949] Num frames 17500... [2023-03-09 11:15:41,105][118949] Num frames 17600... [2023-03-09 11:15:41,193][118949] Num frames 17700... [2023-03-09 11:15:41,279][118949] Num frames 17800... [2023-03-09 11:15:41,367][118949] Num frames 17900... [2023-03-09 11:15:41,455][118949] Num frames 18000... [2023-03-09 11:15:41,543][118949] Num frames 18100... [2023-03-09 11:15:41,630][118949] Num frames 18200... [2023-03-09 11:15:41,721][118949] Num frames 18300... [2023-03-09 11:15:41,810][118949] Num frames 18400... [2023-03-09 11:15:41,898][118949] Num frames 18500... [2023-03-09 11:15:41,986][118949] Num frames 18600... [2023-03-09 11:15:42,075][118949] Num frames 18700... [2023-03-09 11:15:42,165][118949] Num frames 18800... [2023-03-09 11:15:42,257][118949] Num frames 18900... [2023-03-09 11:15:42,308][118949] Avg episode rewards: #0: 62.554, true rewards: #0: 21.000 [2023-03-09 11:15:42,309][118949] Avg episode reward: 62.554, avg true_objective: 21.000 [2023-03-09 11:15:42,417][118949] Num frames 19000... [2023-03-09 11:15:42,503][118949] Num frames 19100... [2023-03-09 11:15:42,590][118949] Num frames 19200... [2023-03-09 11:15:42,677][118949] Num frames 19300... [2023-03-09 11:15:42,763][118949] Num frames 19400... [2023-03-09 11:15:42,850][118949] Num frames 19500... [2023-03-09 11:15:42,936][118949] Num frames 19600... [2023-03-09 11:15:43,026][118949] Num frames 19700... [2023-03-09 11:15:43,114][118949] Num frames 19800... [2023-03-09 11:15:43,201][118949] Num frames 19900... [2023-03-09 11:15:43,288][118949] Num frames 20000... [2023-03-09 11:15:43,376][118949] Num frames 20100... [2023-03-09 11:15:43,465][118949] Num frames 20200... [2023-03-09 11:15:43,552][118949] Num frames 20300... [2023-03-09 11:15:43,640][118949] Num frames 20400... [2023-03-09 11:15:43,729][118949] Num frames 20500... [2023-03-09 11:15:43,819][118949] Num frames 20600... [2023-03-09 11:15:43,910][118949] Num frames 20700... [2023-03-09 11:15:44,001][118949] Num frames 20800... [2023-03-09 11:15:44,091][118949] Num frames 20900... [2023-03-09 11:15:44,182][118949] Num frames 21000... [2023-03-09 11:15:44,233][118949] Avg episode rewards: #0: 62.599, true rewards: #0: 21.000 [2023-03-09 11:15:44,234][118949] Avg episode reward: 62.599, avg true_objective: 21.000 [2023-03-09 11:16:11,212][118949] Replay video saved to /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/replay.mp4! [2023-03-09 12:26:25,078][118949] Environment doom_basic already registered, overwriting... [2023-03-09 12:26:25,081][118949] Environment doom_two_colors_easy already registered, overwriting... [2023-03-09 12:26:25,081][118949] Environment doom_two_colors_hard already registered, overwriting... [2023-03-09 12:26:25,082][118949] Environment doom_dm already registered, overwriting... [2023-03-09 12:26:25,083][118949] Environment doom_dwango5 already registered, overwriting... [2023-03-09 12:26:25,083][118949] Environment doom_my_way_home_flat_actions already registered, overwriting... [2023-03-09 12:26:25,084][118949] Environment doom_defend_the_center_flat_actions already registered, overwriting... [2023-03-09 12:26:25,086][118949] Environment doom_my_way_home already registered, overwriting... [2023-03-09 12:26:25,086][118949] Environment doom_deadly_corridor already registered, overwriting... [2023-03-09 12:26:25,087][118949] Environment doom_defend_the_center already registered, overwriting... [2023-03-09 12:26:25,088][118949] Environment doom_defend_the_line already registered, overwriting... [2023-03-09 12:26:25,089][118949] Environment doom_health_gathering already registered, overwriting... [2023-03-09 12:26:25,090][118949] Environment doom_health_gathering_supreme already registered, overwriting... [2023-03-09 12:26:25,091][118949] Environment doom_battle already registered, overwriting... [2023-03-09 12:26:25,091][118949] Environment doom_battle2 already registered, overwriting... [2023-03-09 12:26:25,092][118949] Environment doom_duel_bots already registered, overwriting... [2023-03-09 12:26:25,093][118949] Environment doom_deathmatch_bots already registered, overwriting... [2023-03-09 12:26:25,094][118949] Environment doom_duel already registered, overwriting... [2023-03-09 12:26:25,094][118949] Environment doom_deathmatch_full already registered, overwriting... [2023-03-09 12:26:25,095][118949] Environment doom_benchmark already registered, overwriting... [2023-03-09 12:26:25,096][118949] register_encoder_factory: [2023-03-09 12:28:02,866][118949] Environment doom_basic already registered, overwriting... [2023-03-09 12:28:02,869][118949] Environment doom_two_colors_easy already registered, overwriting... [2023-03-09 12:28:02,870][118949] Environment doom_two_colors_hard already registered, overwriting... [2023-03-09 12:28:02,871][118949] Environment doom_dm already registered, overwriting... [2023-03-09 12:28:02,871][118949] Environment doom_dwango5 already registered, overwriting... [2023-03-09 12:28:02,873][118949] Environment doom_my_way_home_flat_actions already registered, overwriting... [2023-03-09 12:28:02,873][118949] Environment doom_defend_the_center_flat_actions already registered, overwriting... [2023-03-09 12:28:02,874][118949] Environment doom_my_way_home already registered, overwriting... [2023-03-09 12:28:02,875][118949] Environment doom_deadly_corridor already registered, overwriting... [2023-03-09 12:28:02,875][118949] Environment doom_defend_the_center already registered, overwriting... [2023-03-09 12:28:02,876][118949] Environment doom_defend_the_line already registered, overwriting... [2023-03-09 12:28:02,878][118949] Environment doom_health_gathering already registered, overwriting... [2023-03-09 12:28:02,878][118949] Environment doom_health_gathering_supreme already registered, overwriting... [2023-03-09 12:28:02,879][118949] Environment doom_battle already registered, overwriting... [2023-03-09 12:28:02,880][118949] Environment doom_battle2 already registered, overwriting... [2023-03-09 12:28:02,880][118949] Environment doom_duel_bots already registered, overwriting... [2023-03-09 12:28:02,881][118949] Environment doom_deathmatch_bots already registered, overwriting... [2023-03-09 12:28:02,882][118949] Environment doom_duel already registered, overwriting... [2023-03-09 12:28:02,883][118949] Environment doom_deathmatch_full already registered, overwriting... [2023-03-09 12:28:02,884][118949] Environment doom_benchmark already registered, overwriting... [2023-03-09 12:28:02,884][118949] register_encoder_factory: [2023-03-09 12:28:48,526][118949] Loading existing experiment configuration from /mnt/Lata/projects/samplefactory/train_dir/default_experiment/config.json [2023-03-09 12:28:48,526][118949] Overriding arg 'num_workers' with value 1 passed from command line [2023-03-09 12:28:48,527][118949] Adding new argument 'no_render'=True that is not in the saved config file! [2023-03-09 12:28:48,527][118949] Adding new argument 'save_video'=True that is not in the saved config file! [2023-03-09 12:28:48,528][118949] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file! [2023-03-09 12:28:48,529][118949] Adding new argument 'video_name'=None that is not in the saved config file! [2023-03-09 12:28:48,529][118949] Adding new argument 'max_num_frames'=100000 that is not in the saved config file! [2023-03-09 12:28:48,530][118949] Adding new argument 'max_num_episodes'=10 that is not in the saved config file! [2023-03-09 12:28:48,530][118949] Adding new argument 'push_to_hub'=True that is not in the saved config file! [2023-03-09 12:28:48,531][118949] Adding new argument 'hf_repository'='Rolo/doom_health_w128-epw64-r32_b4096-2b' that is not in the saved config file! [2023-03-09 12:28:48,531][118949] Adding new argument 'policy_index'=0 that is not in the saved config file! [2023-03-09 12:28:48,532][118949] Adding new argument 'eval_deterministic'=False that is not in the saved config file! [2023-03-09 12:28:48,532][118949] Adding new argument 'train_script'=None that is not in the saved config file! [2023-03-09 12:28:48,533][118949] Adding new argument 'enjoy_script'=None that is not in the saved config file! [2023-03-09 12:28:48,534][118949] Using frameskip 1 and render_action_repeat=4 for evaluation [2023-03-09 12:28:48,539][118949] RunningMeanStd input shape: (3, 72, 128) [2023-03-09 12:28:48,540][118949] RunningMeanStd input shape: (1,) [2023-03-09 12:28:48,549][118949] ConvEncoder: input_channels=3 [2023-03-09 12:28:48,577][118949] Conv encoder output size: 512 [2023-03-09 12:28:48,578][118949] Policy head output size: 512 [2023-03-09 12:28:48,594][118949] No checkpoints found [2023-03-09 12:29:25,743][118949] Loading existing experiment configuration from /mnt/Lata/projects/samplefactory/train_dir/default_experiment/config.json [2023-03-09 12:29:25,744][118949] Overriding arg 'num_workers' with value 1 passed from command line [2023-03-09 12:29:25,745][118949] Adding new argument 'no_render'=True that is not in the saved config file! [2023-03-09 12:29:25,745][118949] Adding new argument 'save_video'=True that is not in the saved config file! [2023-03-09 12:29:25,746][118949] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file! [2023-03-09 12:29:25,746][118949] Adding new argument 'video_name'=None that is not in the saved config file! [2023-03-09 12:29:25,747][118949] Adding new argument 'max_num_frames'=100000 that is not in the saved config file! [2023-03-09 12:29:25,747][118949] Adding new argument 'max_num_episodes'=10 that is not in the saved config file! [2023-03-09 12:29:25,748][118949] Adding new argument 'push_to_hub'=True that is not in the saved config file! [2023-03-09 12:29:25,749][118949] Adding new argument 'hf_repository'='Rolo/doom_health_w128-epw64-r32_b4096-2b' that is not in the saved config file! [2023-03-09 12:29:25,749][118949] Adding new argument 'policy_index'=0 that is not in the saved config file! [2023-03-09 12:29:25,750][118949] Adding new argument 'eval_deterministic'=False that is not in the saved config file! [2023-03-09 12:29:25,750][118949] Adding new argument 'train_script'=None that is not in the saved config file! [2023-03-09 12:29:25,751][118949] Adding new argument 'enjoy_script'=None that is not in the saved config file! [2023-03-09 12:29:25,751][118949] Using frameskip 1 and render_action_repeat=4 for evaluation [2023-03-09 12:29:25,756][118949] RunningMeanStd input shape: (3, 72, 128) [2023-03-09 12:29:25,758][118949] RunningMeanStd input shape: (1,) [2023-03-09 12:29:25,766][118949] ConvEncoder: input_channels=3 [2023-03-09 12:29:25,794][118949] Conv encoder output size: 512 [2023-03-09 12:29:25,795][118949] Policy head output size: 512 [2023-03-09 12:29:25,810][118949] No checkpoints found [2023-03-09 12:31:21,943][269569] Saving configuration to /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/config.json... [2023-03-09 12:31:21,945][269569] Rollout worker 0 uses device cpu [2023-03-09 12:31:21,945][269569] Rollout worker 1 uses device cpu [2023-03-09 12:31:21,946][269569] Rollout worker 2 uses device cpu [2023-03-09 12:31:21,946][269569] Rollout worker 3 uses device cpu [2023-03-09 12:31:21,947][269569] Rollout worker 4 uses device cpu [2023-03-09 12:31:21,947][269569] Rollout worker 5 uses device cpu [2023-03-09 12:31:21,948][269569] Rollout worker 6 uses device cpu [2023-03-09 12:31:21,948][269569] Rollout worker 7 uses device cpu [2023-03-09 12:31:21,949][269569] Rollout worker 8 uses device cpu [2023-03-09 12:31:21,950][269569] Rollout worker 9 uses device cpu [2023-03-09 12:31:21,950][269569] Rollout worker 10 uses device cpu [2023-03-09 12:31:21,952][269569] Rollout worker 11 uses device cpu [2023-03-09 12:31:21,953][269569] Rollout worker 12 uses device cpu [2023-03-09 12:31:21,954][269569] Rollout worker 13 uses device cpu [2023-03-09 12:31:21,954][269569] Rollout worker 14 uses device cpu [2023-03-09 12:31:21,955][269569] Rollout worker 15 uses device cpu [2023-03-09 12:31:21,955][269569] Rollout worker 16 uses device cpu [2023-03-09 12:31:21,956][269569] Rollout worker 17 uses device cpu [2023-03-09 12:31:21,956][269569] Rollout worker 18 uses device cpu [2023-03-09 12:31:21,957][269569] Rollout worker 19 uses device cpu [2023-03-09 12:31:21,957][269569] Rollout worker 20 uses device cpu [2023-03-09 12:31:21,958][269569] Rollout worker 21 uses device cpu [2023-03-09 12:31:21,959][269569] Rollout worker 22 uses device cpu [2023-03-09 12:31:21,959][269569] Rollout worker 23 uses device cpu [2023-03-09 12:31:21,960][269569] Rollout worker 24 uses device cpu [2023-03-09 12:31:21,960][269569] Rollout worker 25 uses device cpu [2023-03-09 12:31:21,961][269569] Rollout worker 26 uses device cpu [2023-03-09 12:31:21,961][269569] Rollout worker 27 uses device cpu [2023-03-09 12:31:21,962][269569] Rollout worker 28 uses device cpu [2023-03-09 12:31:21,963][269569] Rollout worker 29 uses device cpu [2023-03-09 12:31:21,963][269569] Rollout worker 30 uses device cpu [2023-03-09 12:31:21,964][269569] Rollout worker 31 uses device cpu [2023-03-09 12:31:21,964][269569] Rollout worker 32 uses device cpu [2023-03-09 12:31:21,965][269569] Rollout worker 33 uses device cpu [2023-03-09 12:31:21,965][269569] Rollout worker 34 uses device cpu [2023-03-09 12:31:21,966][269569] Rollout worker 35 uses device cpu [2023-03-09 12:31:21,967][269569] Rollout worker 36 uses device cpu [2023-03-09 12:31:21,967][269569] Rollout worker 37 uses device cpu [2023-03-09 12:31:21,968][269569] Rollout worker 38 uses device cpu [2023-03-09 12:31:21,968][269569] Rollout worker 39 uses device cpu [2023-03-09 12:31:21,969][269569] Rollout worker 40 uses device cpu [2023-03-09 12:31:21,969][269569] Rollout worker 41 uses device cpu [2023-03-09 12:31:21,970][269569] Rollout worker 42 uses device cpu [2023-03-09 12:31:21,971][269569] Rollout worker 43 uses device cpu [2023-03-09 12:31:21,971][269569] Rollout worker 44 uses device cpu [2023-03-09 12:31:21,972][269569] Rollout worker 45 uses device cpu [2023-03-09 12:31:21,972][269569] Rollout worker 46 uses device cpu [2023-03-09 12:31:21,973][269569] Rollout worker 47 uses device cpu [2023-03-09 12:31:21,973][269569] Rollout worker 48 uses device cpu [2023-03-09 12:31:21,974][269569] Rollout worker 49 uses device cpu [2023-03-09 12:31:21,974][269569] Rollout worker 50 uses device cpu [2023-03-09 12:31:21,975][269569] Rollout worker 51 uses device cpu [2023-03-09 12:31:21,976][269569] Rollout worker 52 uses device cpu [2023-03-09 12:31:21,976][269569] Rollout worker 53 uses device cpu [2023-03-09 12:31:21,977][269569] Rollout worker 54 uses device cpu [2023-03-09 12:31:21,977][269569] Rollout worker 55 uses device cpu [2023-03-09 12:31:21,978][269569] Rollout worker 56 uses device cpu [2023-03-09 12:31:21,978][269569] Rollout worker 57 uses device cpu [2023-03-09 12:31:21,979][269569] Rollout worker 58 uses device cpu [2023-03-09 12:31:21,980][269569] Rollout worker 59 uses device cpu [2023-03-09 12:31:21,980][269569] Rollout worker 60 uses device cpu [2023-03-09 12:31:21,988][269569] Rollout worker 61 uses device cpu [2023-03-09 12:31:21,989][269569] Rollout worker 62 uses device cpu [2023-03-09 12:31:21,989][269569] Rollout worker 63 uses device cpu [2023-03-09 12:31:21,990][269569] Rollout worker 64 uses device cpu [2023-03-09 12:31:21,990][269569] Rollout worker 65 uses device cpu [2023-03-09 12:31:21,991][269569] Rollout worker 66 uses device cpu [2023-03-09 12:31:21,991][269569] Rollout worker 67 uses device cpu [2023-03-09 12:31:21,992][269569] Rollout worker 68 uses device cpu [2023-03-09 12:31:21,994][269569] Rollout worker 69 uses device cpu [2023-03-09 12:31:21,994][269569] Rollout worker 70 uses device cpu [2023-03-09 12:31:21,995][269569] Rollout worker 71 uses device cpu [2023-03-09 12:31:21,995][269569] Rollout worker 72 uses device cpu [2023-03-09 12:31:21,996][269569] Rollout worker 73 uses device cpu [2023-03-09 12:31:21,997][269569] Rollout worker 74 uses device cpu [2023-03-09 12:31:21,997][269569] Rollout worker 75 uses device cpu [2023-03-09 12:31:21,998][269569] Rollout worker 76 uses device cpu [2023-03-09 12:31:21,998][269569] Rollout worker 77 uses device cpu [2023-03-09 12:31:21,999][269569] Rollout worker 78 uses device cpu [2023-03-09 12:31:21,999][269569] Rollout worker 79 uses device cpu [2023-03-09 12:31:22,000][269569] Rollout worker 80 uses device cpu [2023-03-09 12:31:22,001][269569] Rollout worker 81 uses device cpu [2023-03-09 12:31:22,001][269569] Rollout worker 82 uses device cpu [2023-03-09 12:31:22,002][269569] Rollout worker 83 uses device cpu [2023-03-09 12:31:22,002][269569] Rollout worker 84 uses device cpu [2023-03-09 12:31:22,003][269569] Rollout worker 85 uses device cpu [2023-03-09 12:31:22,003][269569] Rollout worker 86 uses device cpu [2023-03-09 12:31:22,004][269569] Rollout worker 87 uses device cpu [2023-03-09 12:31:22,004][269569] Rollout worker 88 uses device cpu [2023-03-09 12:31:22,005][269569] Rollout worker 89 uses device cpu [2023-03-09 12:31:22,006][269569] Rollout worker 90 uses device cpu [2023-03-09 12:31:22,006][269569] Rollout worker 91 uses device cpu [2023-03-09 12:31:22,007][269569] Rollout worker 92 uses device cpu [2023-03-09 12:31:22,007][269569] Rollout worker 93 uses device cpu [2023-03-09 12:31:22,008][269569] Rollout worker 94 uses device cpu [2023-03-09 12:31:22,008][269569] Rollout worker 95 uses device cpu [2023-03-09 12:31:22,009][269569] Rollout worker 96 uses device cpu [2023-03-09 12:31:22,010][269569] Rollout worker 97 uses device cpu [2023-03-09 12:31:22,010][269569] Rollout worker 98 uses device cpu [2023-03-09 12:31:22,011][269569] Rollout worker 99 uses device cpu [2023-03-09 12:31:22,011][269569] Rollout worker 100 uses device cpu [2023-03-09 12:31:22,012][269569] Rollout worker 101 uses device cpu [2023-03-09 12:31:22,012][269569] Rollout worker 102 uses device cpu [2023-03-09 12:31:22,013][269569] Rollout worker 103 uses device cpu [2023-03-09 12:31:22,013][269569] Rollout worker 104 uses device cpu [2023-03-09 12:31:22,014][269569] Rollout worker 105 uses device cpu [2023-03-09 12:31:22,014][269569] Rollout worker 106 uses device cpu [2023-03-09 12:31:22,014][269569] Rollout worker 107 uses device cpu [2023-03-09 12:31:22,015][269569] Rollout worker 108 uses device cpu [2023-03-09 12:31:22,015][269569] Rollout worker 109 uses device cpu [2023-03-09 12:31:22,016][269569] Rollout worker 110 uses device cpu [2023-03-09 12:31:22,016][269569] Rollout worker 111 uses device cpu [2023-03-09 12:31:22,020][269569] Rollout worker 112 uses device cpu [2023-03-09 12:31:22,020][269569] Rollout worker 113 uses device cpu [2023-03-09 12:31:22,021][269569] Rollout worker 114 uses device cpu [2023-03-09 12:31:22,021][269569] Rollout worker 115 uses device cpu [2023-03-09 12:31:22,021][269569] Rollout worker 116 uses device cpu [2023-03-09 12:31:22,022][269569] Rollout worker 117 uses device cpu [2023-03-09 12:31:22,022][269569] Rollout worker 118 uses device cpu [2023-03-09 12:31:22,023][269569] Rollout worker 119 uses device cpu [2023-03-09 12:31:22,023][269569] Rollout worker 120 uses device cpu [2023-03-09 12:31:22,023][269569] Rollout worker 121 uses device cpu [2023-03-09 12:31:22,024][269569] Rollout worker 122 uses device cpu [2023-03-09 12:31:22,025][269569] Rollout worker 123 uses device cpu [2023-03-09 12:31:22,025][269569] Rollout worker 124 uses device cpu [2023-03-09 12:31:22,026][269569] Rollout worker 125 uses device cpu [2023-03-09 12:31:22,026][269569] Rollout worker 126 uses device cpu [2023-03-09 12:31:22,026][269569] Rollout worker 127 uses device cpu [2023-03-09 12:31:24,306][269569] Using GPUs [0] for process 0 (actually maps to GPUs [0]) [2023-03-09 12:31:24,307][269569] InferenceWorker_p0-w0: min num requests: 42 [2023-03-09 12:31:24,636][269569] Starting all processes... [2023-03-09 12:31:24,637][269569] Starting process learner_proc0 [2023-03-09 12:31:25,514][269569] Starting all processes... [2023-03-09 12:31:25,516][269850] Using GPUs [0] for process 0 (actually maps to GPUs [0]) [2023-03-09 12:31:25,521][269569] Starting process inference_proc0-0 [2023-03-09 12:31:25,562][269850] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0 [2023-03-09 12:31:25,522][269569] Starting process rollout_proc2 [2023-03-09 12:31:25,522][269569] Starting process rollout_proc5 [2023-03-09 12:31:25,523][269569] Starting process rollout_proc8 [2023-03-09 12:31:25,524][269569] Starting process rollout_proc11 [2023-03-09 12:31:25,524][269569] Starting process rollout_proc14 [2023-03-09 12:31:25,525][269569] Starting process rollout_proc17 [2023-03-09 12:31:25,572][269850] Num visible devices: 1 [2023-03-09 12:31:25,576][269850] Starting seed is not provided [2023-03-09 12:31:25,576][269850] Using GPUs [0] for process 0 (actually maps to GPUs [0]) [2023-03-09 12:31:25,576][269850] Initializing actor-critic model on device cuda:0 [2023-03-09 12:31:25,576][269850] RunningMeanStd input shape: (3, 72, 128) [2023-03-09 12:31:25,577][269850] RunningMeanStd input shape: (1,) [2023-03-09 12:31:25,526][269569] Starting process rollout_proc20 [2023-03-09 12:31:25,526][269569] Starting process rollout_proc23 [2023-03-09 12:31:25,527][269569] Starting process rollout_proc26 [2023-03-09 12:31:25,527][269569] Starting process rollout_proc29 [2023-03-09 12:31:25,587][269850] ConvEncoder: input_channels=3 [2023-03-09 12:31:25,528][269569] Starting process rollout_proc32 [2023-03-09 12:31:25,528][269569] Starting process rollout_proc35 [2023-03-09 12:31:25,529][269569] Starting process rollout_proc38 [2023-03-09 12:31:25,529][269569] Starting process rollout_proc41 [2023-03-09 12:31:25,530][269569] Starting process rollout_proc44 [2023-03-09 12:31:25,601][269569] Starting process rollout_proc3 [2023-03-09 12:31:25,608][269569] Starting process rollout_proc6 [2023-03-09 12:31:25,610][269569] Starting process rollout_proc9 [2023-03-09 12:31:25,621][269569] Starting process rollout_proc18 [2023-03-09 12:31:25,624][269569] Starting process rollout_proc21 [2023-03-09 12:31:25,624][269569] Starting process rollout_proc12 [2023-03-09 12:31:25,624][269569] Starting process rollout_proc15 [2023-03-09 12:31:25,628][269569] Starting process rollout_proc27 [2023-03-09 12:31:25,635][269569] Starting process rollout_proc24 [2023-03-09 12:31:25,636][269569] Starting process rollout_proc30 [2023-03-09 12:31:25,638][269569] Starting process rollout_proc33 [2023-03-09 12:31:25,651][269569] Starting process rollout_proc42 [2023-03-09 12:31:25,655][269569] Starting process rollout_proc36 [2023-03-09 12:31:25,655][269569] Starting process rollout_proc39 [2023-03-09 12:31:25,665][269569] Starting process rollout_proc45 [2023-03-09 12:31:25,677][269569] Starting process rollout_proc4 [2023-03-09 12:31:25,682][269569] Starting process rollout_proc7 [2023-03-09 12:31:25,686][269569] Starting process rollout_proc19 [2023-03-09 12:31:25,704][269850] Conv encoder output size: 512 [2023-03-09 12:31:25,704][269850] Policy head output size: 512 [2023-03-09 12:31:25,690][269569] Starting process rollout_proc10 [2023-03-09 12:31:25,702][269569] Starting process rollout_proc22 [2023-03-09 12:31:25,702][269569] Starting process rollout_proc13 [2023-03-09 12:31:25,722][269850] Created Actor Critic model with architecture: [2023-03-09 12:31:25,722][269850] ActorCriticSharedWeights( (obs_normalizer): ObservationNormalizer( (running_mean_std): RunningMeanStdDictInPlace( (running_mean_std): ModuleDict( (obs): RunningMeanStdInPlace() ) ) ) (returns_normalizer): RecursiveScriptModule(original_name=RunningMeanStdInPlace) (encoder): VizdoomEncoder( (basic_encoder): ConvEncoder( (enc): RecursiveScriptModule( original_name=ConvEncoderImpl (conv_head): RecursiveScriptModule( original_name=Sequential (0): RecursiveScriptModule(original_name=Conv2d) (1): RecursiveScriptModule(original_name=ELU) (2): RecursiveScriptModule(original_name=Conv2d) (3): RecursiveScriptModule(original_name=ELU) (4): RecursiveScriptModule(original_name=Conv2d) (5): RecursiveScriptModule(original_name=ELU) ) (mlp_layers): RecursiveScriptModule( original_name=Sequential (0): RecursiveScriptModule(original_name=Linear) (1): RecursiveScriptModule(original_name=ELU) ) ) ) ) (core): ModelCoreRNN( (core): GRU(512, 512) ) (decoder): MlpDecoder( (mlp): Identity() ) (critic_linear): Linear(in_features=512, out_features=1, bias=True) (action_parameterization): ActionParameterizationDefault( (distribution_linear): Linear(in_features=512, out_features=5, bias=True) ) ) [2023-03-09 12:31:25,709][269569] Starting process rollout_proc16 [2023-03-09 12:31:25,711][269569] Starting process rollout_proc28 [2023-03-09 12:31:25,718][269569] Starting process rollout_proc25 [2023-03-09 12:31:25,725][269569] Starting process rollout_proc34 [2023-03-09 12:31:25,729][269569] Starting process rollout_proc31 [2023-03-09 12:31:25,735][269569] Starting process rollout_proc43 [2023-03-09 12:31:25,737][269569] Starting process rollout_proc37 [2023-03-09 12:31:25,740][269569] Starting process rollout_proc40 [2023-03-09 12:31:25,745][269569] Starting process rollout_proc46 [2023-03-09 12:31:25,754][269569] Starting process rollout_proc47 [2023-03-09 12:31:25,754][269569] Starting process rollout_proc50 [2023-03-09 12:31:25,756][269569] Starting process rollout_proc53 [2023-03-09 12:31:25,759][269569] Starting process rollout_proc56 [2023-03-09 12:31:25,764][269569] Starting process rollout_proc59 [2023-03-09 12:31:25,764][269569] Starting process rollout_proc62 [2023-03-09 12:31:25,776][269569] Starting process rollout_proc65 [2023-03-09 12:31:25,779][269569] Starting process rollout_proc68 [2023-03-09 12:31:25,784][269569] Starting process rollout_proc71 [2023-03-09 12:31:25,786][269569] Starting process rollout_proc74 [2023-03-09 12:31:25,790][269569] Starting process rollout_proc77 [2023-03-09 12:31:25,791][269569] Starting process rollout_proc80 [2023-03-09 12:31:25,800][269569] Starting process rollout_proc83 [2023-03-09 12:31:25,806][269569] Starting process rollout_proc86 [2023-03-09 12:31:25,809][269569] Starting process rollout_proc89 [2023-03-09 12:31:25,812][269569] Starting process rollout_proc48 [2023-03-09 12:31:25,817][269569] Starting process rollout_proc51 [2023-03-09 12:31:25,827][269569] Starting process rollout_proc54 [2023-03-09 12:31:25,832][269569] Starting process rollout_proc60 [2023-03-09 12:31:25,842][269569] Starting process rollout_proc63 [2023-03-09 12:31:25,845][269569] Starting process rollout_proc57 [2023-03-09 12:31:25,852][269569] Starting process rollout_proc66 [2023-03-09 12:31:25,852][269569] Starting process rollout_proc69 [2023-03-09 12:31:25,867][269569] Starting process rollout_proc72 [2023-03-09 12:31:25,873][269569] Starting process rollout_proc75 [2023-03-09 12:31:25,873][269569] Starting process rollout_proc78 [2023-03-09 12:31:25,882][269569] Starting process rollout_proc81 [2023-03-09 12:31:25,886][269569] Starting process rollout_proc84 [2023-03-09 12:31:25,898][269569] Starting process rollout_proc90 [2023-03-09 12:31:25,907][269569] Starting process rollout_proc55 [2023-03-09 12:31:25,960][269569] Starting process rollout_proc91 [2023-03-09 12:31:25,976][269569] Starting process rollout_proc49 [2023-03-09 12:31:25,980][269569] Starting process rollout_proc61 [2023-03-09 12:31:25,984][269569] Starting process rollout_proc87 [2023-03-09 12:31:25,984][269569] Starting process rollout_proc64 [2023-03-09 12:31:25,985][269569] Starting process rollout_proc79 [2023-03-09 12:31:25,987][269569] Starting process rollout_proc85 [2023-03-09 12:31:25,990][269569] Starting process rollout_proc58 [2023-03-09 12:31:25,993][269569] Starting process rollout_proc76 [2023-03-09 12:31:25,996][269569] Starting process rollout_proc67 [2023-03-09 12:31:25,997][269569] Starting process rollout_proc82 [2023-03-09 12:31:25,997][269569] Starting process rollout_proc73 [2023-03-09 12:31:25,997][269569] Starting process rollout_proc70 [2023-03-09 12:31:26,003][269569] Starting process rollout_proc52 [2023-03-09 12:31:26,005][269569] Starting process rollout_proc92 [2023-03-09 12:31:26,019][269569] Starting process rollout_proc95 [2023-03-09 12:31:26,035][269569] Starting process rollout_proc98 [2023-03-09 12:31:26,053][269569] Starting process rollout_proc101 [2023-03-09 12:31:26,055][269569] Starting process rollout_proc104 [2023-03-09 12:31:26,068][269569] Starting process rollout_proc88 [2023-03-09 12:31:26,074][269569] Starting process rollout_proc107 [2023-03-09 12:31:26,081][269569] Starting process rollout_proc110 [2023-03-09 12:31:26,088][269569] Starting process rollout_proc113 [2023-03-09 12:31:26,090][269569] Starting process rollout_proc116 [2023-03-09 12:31:26,099][269569] Starting process rollout_proc119 [2023-03-09 12:31:26,101][269569] Starting process rollout_proc122 [2023-03-09 12:31:26,105][269569] Starting process rollout_proc125 [2023-03-09 12:31:26,136][269569] Starting process rollout_proc99 [2023-03-09 12:31:26,150][269569] Starting process rollout_proc93 [2023-03-09 12:31:26,150][269569] Starting process rollout_proc96 [2023-03-09 12:31:26,169][269569] Starting process rollout_proc105 [2023-03-09 12:31:26,169][269569] Starting process rollout_proc102 [2023-03-09 12:31:26,182][269569] Starting process rollout_proc114 [2023-03-09 12:31:26,285][269569] Starting process rollout_proc111 [2023-03-09 12:31:26,295][269569] Starting process rollout_proc108 [2023-03-09 12:31:26,297][269569] Starting process rollout_proc100 [2023-03-09 12:31:26,297][269569] Starting process rollout_proc123 [2023-03-09 12:31:26,298][269569] Starting process rollout_proc120 [2023-03-09 12:31:26,318][269569] Starting process rollout_proc97 [2023-03-09 12:31:26,318][269569] Starting process rollout_proc117 [2023-03-09 12:31:26,330][269569] Starting process rollout_proc106 [2023-03-09 12:31:26,333][269569] Starting process rollout_proc94 [2023-03-09 12:31:26,350][269569] Starting process rollout_proc112 [2023-03-09 12:31:26,350][269569] Starting process rollout_proc103 [2023-03-09 12:31:26,353][269569] Starting process rollout_proc115 [2023-03-09 12:31:26,353][269569] Starting process rollout_proc126 [2023-03-09 12:31:26,379][269569] Starting process rollout_proc109 [2023-03-09 12:31:26,489][269569] Starting process rollout_proc124 [2023-03-09 12:31:26,507][269569] Starting process rollout_proc121 [2023-03-09 12:31:26,561][269569] Starting process rollout_proc118 [2023-03-09 12:31:26,625][269569] Starting process rollout_proc127 [2023-03-09 12:31:28,114][270085] Worker 18 uses CPU cores [18] [2023-03-09 12:31:28,131][270005] Worker 11 uses CPU cores [11] [2023-03-09 12:31:28,168][269981] Worker 2 uses CPU cores [2] [2023-03-09 12:31:28,184][270107] Worker 16 uses CPU cores [16] [2023-03-09 12:31:28,184][270006] Worker 17 uses CPU cores [17] [2023-03-09 12:31:28,216][270091] Worker 27 uses CPU cores [27] [2023-03-09 12:31:28,291][269569] Starting process rollout_proc0 [2023-03-09 12:31:28,297][270011] Worker 23 uses CPU cores [23] [2023-03-09 12:31:28,325][270001] Using GPUs [0] for process 0 (actually maps to GPUs [0]) [2023-03-09 12:31:28,329][270001] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0 [2023-03-09 12:31:28,355][270001] Num visible devices: 1 [2023-03-09 12:31:28,431][270003] Worker 8 uses CPU cores [8] [2023-03-09 12:31:28,445][269569] Starting process rollout_proc1 [2023-03-09 12:31:28,453][270002] Worker 5 uses CPU cores [5] [2023-03-09 12:31:28,490][270084] Worker 6 uses CPU cores [6] [2023-03-09 12:31:28,544][270009] Worker 26 uses CPU cores [26] [2023-03-09 12:31:28,628][270016] Worker 44 uses CPU cores [44] [2023-03-09 12:31:28,680][270109] Worker 31 uses CPU cores [31] [2023-03-09 12:31:28,704][270103] Worker 10 uses CPU cores [10] [2023-03-09 12:31:28,708][270089] Worker 21 uses CPU cores [21] [2023-03-09 12:31:28,724][270008] Worker 14 uses CPU cores [14] [2023-03-09 12:31:28,806][270086] Worker 9 uses CPU cores [9] [2023-03-09 12:31:28,815][270092] Worker 24 uses CPU cores [24] [2023-03-09 12:31:28,840][270096] Worker 39 uses CPU cores [39] [2023-03-09 12:31:28,847][270013] Worker 41 uses CPU cores [41] [2023-03-09 12:31:28,853][270012] Worker 32 uses CPU cores [32] [2023-03-09 12:31:28,863][270095] Worker 42 uses CPU cores [42] [2023-03-09 12:31:28,864][270104] Worker 22 uses CPU cores [22] [2023-03-09 12:31:28,868][270098] Worker 45 uses CPU cores [45] [2023-03-09 12:31:28,872][270088] Worker 12 uses CPU cores [12] [2023-03-09 12:31:28,879][270014] Worker 38 uses CPU cores [38] [2023-03-09 12:31:28,885][270090] Worker 15 uses CPU cores [15] [2023-03-09 12:31:28,893][270007] Worker 20 uses CPU cores [20] [2023-03-09 12:31:28,904][270108] Worker 34 uses CPU cores [34] [2023-03-09 12:31:28,916][270129] Worker 89 uses CPU cores [89] [2023-03-09 12:31:28,928][270113] Worker 40 uses CPU cores [40] [2023-03-09 12:31:28,932][270110] Worker 25 uses CPU cores [25] [2023-03-09 12:31:28,946][270100] Worker 4 uses CPU cores [4] [2023-03-09 12:31:28,976][270015] Worker 35 uses CPU cores [35] [2023-03-09 12:31:28,979][270010] Worker 29 uses CPU cores [29] [2023-03-09 12:31:29,020][270105] Worker 13 uses CPU cores [13] [2023-03-09 12:31:29,026][270106] Worker 28 uses CPU cores [28] [2023-03-09 12:31:29,028][270131] Worker 90 uses CPU cores [90] [2023-03-09 12:31:29,039][270118] Worker 53 uses CPU cores [53] [2023-03-09 12:31:29,056][270111] Worker 43 uses CPU cores [43] [2023-03-09 12:31:29,060][270135] Worker 86 uses CPU cores [86] [2023-03-09 12:31:29,060][270097] Worker 36 uses CPU cores [36] [2023-03-09 12:31:29,060][270093] Worker 33 uses CPU cores [33] [2023-03-09 12:31:29,064][270119] Worker 59 uses CPU cores [59] [2023-03-09 12:31:29,068][270094] Worker 30 uses CPU cores [30] [2023-03-09 12:31:29,080][270150] Worker 87 uses CPU cores [87] [2023-03-09 12:31:29,088][270134] Worker 63 uses CPU cores [63] [2023-03-09 12:31:29,096][270142] Worker 66 uses CPU cores [66] [2023-03-09 12:31:29,099][270132] Worker 48 uses CPU cores [48] [2023-03-09 12:31:29,101][270125] Worker 77 uses CPU cores [77] [2023-03-09 12:31:29,102][270099] Worker 7 uses CPU cores [7] [2023-03-09 12:31:29,104][270120] Worker 56 uses CPU cores [56] [2023-03-09 12:31:29,120][270128] Worker 83 uses CPU cores [83] [2023-03-09 12:31:29,128][270127] Worker 80 uses CPU cores [80] [2023-03-09 12:31:29,132][270115] Worker 37 uses CPU cores [37] [2023-03-09 12:31:29,136][270116] Worker 47 uses CPU cores [47] [2023-03-09 12:31:29,144][270117] Worker 50 uses CPU cores [50] [2023-03-09 12:31:29,148][270137] Worker 84 uses CPU cores [84] [2023-03-09 12:31:29,148][270121] Worker 62 uses CPU cores [62] [2023-03-09 12:31:29,152][270080] Worker 3 uses CPU cores [3] [2023-03-09 12:31:29,168][270139] Worker 75 uses CPU cores [75] [2023-03-09 12:31:29,172][270122] Worker 65 uses CPU cores [65] [2023-03-09 12:31:29,172][270156] Worker 82 uses CPU cores [82] [2023-03-09 12:31:29,172][270130] Worker 54 uses CPU cores [54] [2023-03-09 12:31:29,175][270124] Worker 71 uses CPU cores [71] [2023-03-09 12:31:29,208][270123] Worker 68 uses CPU cores [68] [2023-03-09 12:31:29,216][270165] Worker 113 uses CPU cores [113] [2023-03-09 12:31:29,216][270145] Worker 51 uses CPU cores [51] [2023-03-09 12:31:29,232][270149] Worker 64 uses CPU cores [64] [2023-03-09 12:31:29,241][270101] Worker 19 uses CPU cores [19] [2023-03-09 12:31:29,244][270138] Worker 57 uses CPU cores [57] [2023-03-09 12:31:29,256][270126] Worker 74 uses CPU cores [74] [2023-03-09 12:31:29,259][270158] Worker 73 uses CPU cores [73] [2023-03-09 12:31:29,264][270159] Worker 52 uses CPU cores [52] [2023-03-09 12:31:29,268][270154] Worker 58 uses CPU cores [58] [2023-03-09 12:31:29,283][270541] Worker 93 uses CPU cores [93] [2023-03-09 12:31:29,308][270133] Worker 60 uses CPU cores [60] [2023-03-09 12:31:29,311][270114] Worker 46 uses CPU cores [46] [2023-03-09 12:31:29,316][270155] Worker 70 uses CPU cores [70] [2023-03-09 12:31:29,327][270152] Worker 79 uses CPU cores [79] [2023-03-09 12:31:29,352][270146] Worker 91 uses CPU cores [91] [2023-03-09 12:31:29,357][270153] Worker 76 uses CPU cores [76] [2023-03-09 12:31:29,357][270555] Worker 102 uses CPU cores [102] [2023-03-09 12:31:29,358][271126] Worker 109 uses CPU cores [109] [2023-03-09 12:31:29,360][270140] Worker 81 uses CPU cores [81] [2023-03-09 12:31:29,364][270144] Worker 55 uses CPU cores [55] [2023-03-09 12:31:29,368][270162] Worker 95 uses CPU cores [95] [2023-03-09 12:31:29,380][270147] Worker 49 uses CPU cores [49] [2023-03-09 12:31:29,380][270143] Worker 72 uses CPU cores [72] [2023-03-09 12:31:29,393][270934] Worker 94 uses CPU cores [94] [2023-03-09 12:31:29,395][270151] Worker 85 uses CPU cores [85] [2023-03-09 12:31:29,396][270404] Worker 119 uses CPU cores [119] [2023-03-09 12:31:29,403][270160] Worker 92 uses CPU cores [92] [2023-03-09 12:31:29,416][270622] Worker 100 uses CPU cores [100] [2023-03-09 12:31:29,418][271017] Worker 115 uses CPU cores [115] [2023-03-09 12:31:29,420][270141] Worker 69 uses CPU cores [69] [2023-03-09 12:31:29,423][270164] Worker 104 uses CPU cores [104] [2023-03-09 12:31:29,427][270553] Worker 105 uses CPU cores [105] [2023-03-09 12:31:29,428][270596] Worker 108 uses CPU cores [108] [2023-03-09 12:31:29,431][270472] Worker 99 uses CPU cores [99] [2023-03-09 12:31:29,438][271919] Worker 127 uses CPU cores [127] [2023-03-09 12:31:29,450][270623] Worker 123 uses CPU cores [123] [2023-03-09 12:31:29,464][270557] Worker 111 uses CPU cores [111] [2023-03-09 12:31:29,467][270368] Worker 107 uses CPU cores [107] [2023-03-09 12:31:29,468][270514] Worker 116 uses CPU cores [116] [2023-03-09 12:31:29,473][270148] Worker 61 uses CPU cores [61] [2023-03-09 12:31:29,476][271375] Worker 121 uses CPU cores [121] [2023-03-09 12:31:29,482][270136] Worker 78 uses CPU cores [78] [2023-03-09 12:31:29,545][270161] Worker 98 uses CPU cores [98] [2023-03-09 12:31:29,546][270751] Worker 97 uses CPU cores [97] [2023-03-09 12:31:29,562][271517] Worker 118 uses CPU cores [118] [2023-03-09 12:31:29,568][270157] Worker 67 uses CPU cores [67] [2023-03-09 12:31:29,571][270556] Worker 114 uses CPU cores [114] [2023-03-09 12:31:29,575][270473] Worker 122 uses CPU cores [122] [2023-03-09 12:31:29,584][270163] Worker 101 uses CPU cores [101] [2023-03-09 12:31:29,604][270554] Worker 125 uses CPU cores [125] [2023-03-09 12:31:29,607][271224] Worker 126 uses CPU cores [126] [2023-03-09 12:31:29,608][270945] Worker 106 uses CPU cores [106] [2023-03-09 12:31:29,610][270860] Worker 117 uses CPU cores [117] [2023-03-09 12:31:29,613][270233] Worker 110 uses CPU cores [110] [2023-03-09 12:31:29,616][271355] Worker 124 uses CPU cores [124] [2023-03-09 12:31:29,621][270293] Worker 88 uses CPU cores [88] [2023-03-09 12:31:29,650][270552] Worker 96 uses CPU cores [96] [2023-03-09 12:31:29,666][270699] Worker 120 uses CPU cores [120] [2023-03-09 12:31:29,720][270943] Worker 112 uses CPU cores [112] [2023-03-09 12:31:29,730][270944] Worker 103 uses CPU cores [103] [2023-03-09 12:31:29,950][269850] Using optimizer [2023-03-09 12:31:29,950][269850] Loading state from checkpoint /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000152589_2500018176.pth... [2023-03-09 12:31:29,967][269850] Loading model from checkpoint [2023-03-09 12:31:29,971][269850] Loaded experiment state at self.train_step=152589, self.env_steps=2500018176 [2023-03-09 12:31:29,971][269850] Initialized policy 0 weights for model version 152589 [2023-03-09 12:31:29,972][269850] LearnerWorker_p0 finished initialization! [2023-03-09 12:31:29,974][269850] Using GPUs [0] for process 0 (actually maps to GPUs [0]) [2023-03-09 12:31:29,983][269569] Fps is (10 sec: nan, 60 sec: nan, 300 sec: nan). Total num frames: 2500018176. Throughput: 0: nan. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) [2023-03-09 12:31:30,017][277995] Worker 1 uses CPU cores [1] [2023-03-09 12:31:30,049][270001] RunningMeanStd input shape: (3, 72, 128) [2023-03-09 12:31:30,050][270001] RunningMeanStd input shape: (1,) [2023-03-09 12:31:30,052][277349] Worker 0 uses CPU cores [0] [2023-03-09 12:31:30,061][270001] ConvEncoder: input_channels=3 [2023-03-09 12:31:30,134][270001] Conv encoder output size: 512 [2023-03-09 12:31:30,134][270001] Policy head output size: 512 [2023-03-09 12:31:30,978][269569] Inference worker 0-0 is ready! [2023-03-09 12:31:30,979][269569] All inference workers are ready! Signal rollout workers to start! [2023-03-09 12:31:31,100][270945] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:31,101][270088] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:31,104][270109] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:31,105][271224] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:31,105][270158] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:31,106][270099] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:31,107][270160] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:31,109][270751] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:31,110][270134] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:31,110][270128] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:31,111][270003] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:31,111][270104] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:31,111][270555] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:31,112][270943] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:31,112][270541] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:31,113][277995] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:31,113][270596] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:31,115][270149] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:31,115][270092] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:31,115][270015] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:31,115][270124] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:31,115][270008] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:31,115][270091] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:31,115][270114] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:31,115][270106] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:31,116][270089] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:31,116][270233] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:31,116][270107] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:31,116][270472] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:31,116][270093] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:31,116][270556] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:31,116][270009] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:31,116][270133] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:31,117][270151] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:31,117][270080] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:31,117][270129] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:31,117][270159] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:31,117][270094] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:31,117][270557] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:31,117][270100] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:31,117][271919] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:31,117][270002] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:31,118][270010] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:31,118][270140] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:31,118][270622] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:31,118][270115] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:31,119][270137] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:31,120][270163] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:31,121][270157] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:31,121][270111] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:31,121][270007] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:31,121][270514] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:31,122][271375] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:31,122][270125] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:31,122][270123] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:31,124][270368] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:31,124][270113] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:31,124][270150] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:31,124][270118] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:31,124][270136] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:31,125][270152] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:31,125][270132] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:31,125][270156] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:31,125][270117] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:31,125][270944] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:31,125][270014] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:31,126][270165] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:31,126][270164] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:31,126][270131] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:31,126][270119] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:31,126][270473] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:31,126][270623] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:31,127][270147] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:31,127][270085] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:31,127][270153] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:31,127][270105] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:31,127][270101] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:31,127][270084] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:31,127][270934] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:31,127][270293] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:31,128][270127] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:31,128][270095] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:31,128][270096] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:31,128][270098] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:31,128][270145] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:31,128][270699] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:31,128][270161] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:31,128][270143] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:31,128][270122] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:31,129][271017] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:31,129][270162] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:31,129][270860] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:31,129][271517] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:31,129][270552] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:31,129][270097] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:31,129][270146] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:31,130][270013] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:31,130][270553] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:31,130][270130] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:31,130][270554] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:31,130][270121] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:31,130][270148] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:31,130][271355] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:31,130][270144] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:31,130][270404] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:31,131][270154] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:31,131][270120] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:31,131][270016] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:31,131][270110] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:31,131][270135] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:31,133][270126] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:31,133][270116] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:31,133][269981] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:31,134][270139] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:31,135][277349] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:31,136][270138] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:31,136][270155] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:31,135][270141] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:31,136][270086] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:31,136][270108] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:31,138][270103] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:31,138][270012] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:31,139][270011] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:31,138][271126] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:31,139][270090] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:31,140][270005] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:31,143][270006] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:31,184][270142] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:31:32,150][269981] Decorrelating experience for 0 frames... [2023-03-09 12:31:32,156][277349] Decorrelating experience for 0 frames... [2023-03-09 12:31:32,159][270149] Decorrelating experience for 0 frames... [2023-03-09 12:31:32,247][270134] Decorrelating experience for 0 frames... [2023-03-09 12:31:32,250][270091] Decorrelating experience for 0 frames... [2023-03-09 12:31:32,251][270085] Decorrelating experience for 0 frames... [2023-03-09 12:31:32,252][270158] Decorrelating experience for 0 frames... [2023-03-09 12:31:32,252][270133] Decorrelating experience for 0 frames... [2023-03-09 12:31:32,253][270944] Decorrelating experience for 0 frames... [2023-03-09 12:31:32,253][270233] Decorrelating experience for 0 frames... [2023-03-09 12:31:32,321][270159] Decorrelating experience for 0 frames... [2023-03-09 12:31:32,330][270084] Decorrelating experience for 0 frames... [2023-03-09 12:31:32,346][270104] Decorrelating experience for 0 frames... [2023-03-09 12:31:32,423][270150] Decorrelating experience for 0 frames... [2023-03-09 12:31:32,427][270015] Decorrelating experience for 0 frames... [2023-03-09 12:31:32,431][271919] Decorrelating experience for 0 frames... [2023-03-09 12:31:32,435][270016] Decorrelating experience for 0 frames... [2023-03-09 12:31:32,436][270149] Decorrelating experience for 32 frames... [2023-03-09 12:31:32,446][270141] Decorrelating experience for 0 frames... [2023-03-09 12:31:32,447][270119] Decorrelating experience for 0 frames... [2023-03-09 12:31:32,501][270404] Decorrelating experience for 0 frames... [2023-03-09 12:31:32,505][270092] Decorrelating experience for 0 frames... [2023-03-09 12:31:32,517][270125] Decorrelating experience for 0 frames... [2023-03-09 12:31:32,600][270113] Decorrelating experience for 0 frames... [2023-03-09 12:31:32,603][270553] Decorrelating experience for 0 frames... [2023-03-09 12:31:32,605][270127] Decorrelating experience for 0 frames... [2023-03-09 12:31:32,615][270115] Decorrelating experience for 0 frames... [2023-03-09 12:31:32,616][270121] Decorrelating experience for 0 frames... [2023-03-09 12:31:32,620][270622] Decorrelating experience for 0 frames... [2023-03-09 12:31:32,621][270119] Decorrelating experience for 32 frames... [2023-03-09 12:31:32,676][270114] Decorrelating experience for 0 frames... [2023-03-09 12:31:32,677][270944] Decorrelating experience for 32 frames... [2023-03-09 12:31:32,702][270165] Decorrelating experience for 0 frames... [2023-03-09 12:31:32,775][270146] Decorrelating experience for 0 frames... [2023-03-09 12:31:32,776][270553] Decorrelating experience for 32 frames... [2023-03-09 12:31:32,791][270142] Decorrelating experience for 0 frames... [2023-03-09 12:31:32,792][270080] Decorrelating experience for 0 frames... [2023-03-09 12:31:32,793][270122] Decorrelating experience for 0 frames... [2023-03-09 12:31:32,799][270089] Decorrelating experience for 0 frames... [2023-03-09 12:31:32,806][270145] Decorrelating experience for 0 frames... [2023-03-09 12:31:32,848][271375] Decorrelating experience for 0 frames... [2023-03-09 12:31:32,863][270016] Decorrelating experience for 32 frames... [2023-03-09 12:31:32,876][270158] Decorrelating experience for 32 frames... [2023-03-09 12:31:32,953][270114] Decorrelating experience for 32 frames... [2023-03-09 12:31:32,954][270164] Decorrelating experience for 0 frames... [2023-03-09 12:31:32,969][270126] Decorrelating experience for 0 frames... [2023-03-09 12:31:32,971][270080] Decorrelating experience for 32 frames... [2023-03-09 12:31:32,971][270135] Decorrelating experience for 0 frames... [2023-03-09 12:31:32,976][270156] Decorrelating experience for 0 frames... [2023-03-09 12:31:32,981][270145] Decorrelating experience for 32 frames... [2023-03-09 12:31:33,020][270090] Decorrelating experience for 0 frames... [2023-03-09 12:31:33,034][270155] Decorrelating experience for 0 frames... [2023-03-09 12:31:33,066][270123] Decorrelating experience for 0 frames... [2023-03-09 12:31:33,127][270472] Decorrelating experience for 0 frames... [2023-03-09 12:31:33,141][270114] Decorrelating experience for 64 frames... [2023-03-09 12:31:33,146][270125] Decorrelating experience for 32 frames... [2023-03-09 12:31:33,153][270150] Decorrelating experience for 32 frames... [2023-03-09 12:31:33,154][270146] Decorrelating experience for 32 frames... [2023-03-09 12:31:33,157][270016] Decorrelating experience for 64 frames... [2023-03-09 12:31:33,158][270007] Decorrelating experience for 0 frames... [2023-03-09 12:31:33,193][270107] Decorrelating experience for 0 frames... [2023-03-09 12:31:33,211][271517] Decorrelating experience for 0 frames... [2023-03-09 12:31:33,243][270622] Decorrelating experience for 32 frames... [2023-03-09 12:31:33,305][270099] Decorrelating experience for 0 frames... [2023-03-09 12:31:33,319][270094] Decorrelating experience for 0 frames... [2023-03-09 12:31:33,330][270164] Decorrelating experience for 32 frames... [2023-03-09 12:31:33,332][270104] Decorrelating experience for 32 frames... [2023-03-09 12:31:33,336][270116] Decorrelating experience for 0 frames... [2023-03-09 12:31:33,337][270092] Decorrelating experience for 32 frames... [2023-03-09 12:31:33,344][270090] Decorrelating experience for 32 frames... [2023-03-09 12:31:33,366][270555] Decorrelating experience for 0 frames... [2023-03-09 12:31:33,385][270945] Decorrelating experience for 0 frames... [2023-03-09 12:31:33,415][270944] Decorrelating experience for 64 frames... [2023-03-09 12:31:33,476][270622] Decorrelating experience for 64 frames... [2023-03-09 12:31:33,491][270094] Decorrelating experience for 32 frames... [2023-03-09 12:31:33,512][270163] Decorrelating experience for 0 frames... [2023-03-09 12:31:33,514][270080] Decorrelating experience for 64 frames... [2023-03-09 12:31:33,516][270130] Decorrelating experience for 0 frames... [2023-03-09 12:31:33,520][270145] Decorrelating experience for 64 frames... [2023-03-09 12:31:33,522][270293] Decorrelating experience for 0 frames... [2023-03-09 12:31:33,542][270128] Decorrelating experience for 0 frames... [2023-03-09 12:31:33,563][270164] Decorrelating experience for 64 frames... [2023-03-09 12:31:33,602][270148] Decorrelating experience for 0 frames... [2023-03-09 12:31:33,663][270009] Decorrelating experience for 0 frames... [2023-03-09 12:31:33,665][270158] Decorrelating experience for 64 frames... [2023-03-09 12:31:33,685][270163] Decorrelating experience for 32 frames... [2023-03-09 12:31:33,700][270126] Decorrelating experience for 32 frames... [2023-03-09 12:31:33,701][270557] Decorrelating experience for 0 frames... [2023-03-09 12:31:33,708][270016] Decorrelating experience for 96 frames... [2023-03-09 12:31:33,709][270097] Decorrelating experience for 0 frames... [2023-03-09 12:31:33,716][270514] Decorrelating experience for 0 frames... [2023-03-09 12:31:33,739][277349] Decorrelating experience for 32 frames... [2023-03-09 12:31:33,771][270934] Decorrelating experience for 0 frames... [2023-03-09 12:31:33,843][270114] Decorrelating experience for 96 frames... [2023-03-09 12:31:33,843][270146] Decorrelating experience for 64 frames... [2023-03-09 12:31:33,861][270119] Decorrelating experience for 64 frames... [2023-03-09 12:31:33,874][270136] Decorrelating experience for 0 frames... [2023-03-09 12:31:33,884][270113] Decorrelating experience for 32 frames... [2023-03-09 12:31:33,884][270097] Decorrelating experience for 32 frames... [2023-03-09 12:31:33,888][269981] Decorrelating experience for 32 frames... [2023-03-09 12:31:33,903][270159] Decorrelating experience for 32 frames... [2023-03-09 12:31:33,917][270132] Decorrelating experience for 0 frames... [2023-03-09 12:31:33,975][270122] Decorrelating experience for 32 frames... [2023-03-09 12:31:34,025][270106] Decorrelating experience for 0 frames... [2023-03-09 12:31:34,026][270006] Decorrelating experience for 0 frames... [2023-03-09 12:31:34,044][270150] Decorrelating experience for 64 frames... [2023-03-09 12:31:34,064][270118] Decorrelating experience for 0 frames... [2023-03-09 12:31:34,067][270116] Decorrelating experience for 32 frames... [2023-03-09 12:31:34,068][270164] Decorrelating experience for 96 frames... [2023-03-09 12:31:34,069][270158] Decorrelating experience for 96 frames... [2023-03-09 12:31:34,075][277349] Decorrelating experience for 64 frames... [2023-03-09 12:31:34,110][270137] Decorrelating experience for 0 frames... [2023-03-09 12:31:34,165][270097] Decorrelating experience for 64 frames... [2023-03-09 12:31:34,199][270293] Decorrelating experience for 32 frames... [2023-03-09 12:31:34,208][271355] Decorrelating experience for 0 frames... [2023-03-09 12:31:34,226][270105] Decorrelating experience for 0 frames... [2023-03-09 12:31:34,249][270106] Decorrelating experience for 32 frames... [2023-03-09 12:31:34,252][270007] Decorrelating experience for 32 frames... [2023-03-09 12:31:34,254][270116] Decorrelating experience for 64 frames... [2023-03-09 12:31:34,267][270147] Decorrelating experience for 0 frames... [2023-03-09 12:31:34,268][270013] Decorrelating experience for 0 frames... [2023-03-09 12:31:34,285][270404] Decorrelating experience for 32 frames... [2023-03-09 12:31:34,336][270159] Decorrelating experience for 64 frames... [2023-03-09 12:31:34,377][270164] Decorrelating experience for 128 frames... [2023-03-09 12:31:34,382][270120] Decorrelating experience for 0 frames... [2023-03-09 12:31:34,400][270006] Decorrelating experience for 32 frames... [2023-03-09 12:31:34,424][270368] Decorrelating experience for 0 frames... [2023-03-09 12:31:34,427][270139] Decorrelating experience for 0 frames... [2023-03-09 12:31:34,429][271126] Decorrelating experience for 0 frames... [2023-03-09 12:31:34,441][270118] Decorrelating experience for 32 frames... [2023-03-09 12:31:34,458][270119] Decorrelating experience for 96 frames... [2023-03-09 12:31:34,469][270151] Decorrelating experience for 0 frames... [2023-03-09 12:31:34,526][270103] Decorrelating experience for 0 frames... [2023-03-09 12:31:34,554][270135] Decorrelating experience for 32 frames... [2023-03-09 12:31:34,571][270404] Decorrelating experience for 64 frames... [2023-03-09 12:31:34,580][270092] Decorrelating experience for 64 frames... [2023-03-09 12:31:34,603][270116] Decorrelating experience for 96 frames... [2023-03-09 12:31:34,614][270015] Decorrelating experience for 32 frames... [2023-03-09 12:31:34,619][270155] Decorrelating experience for 32 frames... [2023-03-09 12:31:34,622][270553] Decorrelating experience for 64 frames... [2023-03-09 12:31:34,632][270098] Decorrelating experience for 0 frames... [2023-03-09 12:31:34,670][270016] Decorrelating experience for 128 frames... [2023-03-09 12:31:34,699][270105] Decorrelating experience for 32 frames... [2023-03-09 12:31:34,744][270146] Decorrelating experience for 96 frames... [2023-03-09 12:31:34,760][270002] Decorrelating experience for 0 frames... [2023-03-09 12:31:34,766][270122] Decorrelating experience for 64 frames... [2023-03-09 12:31:34,785][271355] Decorrelating experience for 32 frames... [2023-03-09 12:31:34,790][270165] Decorrelating experience for 32 frames... [2023-03-09 12:31:34,805][270155] Decorrelating experience for 64 frames... [2023-03-09 12:31:34,807][270114] Decorrelating experience for 128 frames... [2023-03-09 12:31:34,820][271919] Decorrelating experience for 32 frames... [2023-03-09 12:31:34,855][270098] Decorrelating experience for 32 frames... [2023-03-09 12:31:34,880][270162] Decorrelating experience for 0 frames... [2023-03-09 12:31:34,926][270118] Decorrelating experience for 64 frames... [2023-03-09 12:31:34,936][270002] Decorrelating experience for 32 frames... [2023-03-09 12:31:34,953][270147] Decorrelating experience for 32 frames... [2023-03-09 12:31:34,968][270124] Decorrelating experience for 0 frames... [2023-03-09 12:31:34,982][269569] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 2500018176. Throughput: 0: 0.0. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) [2023-03-09 12:31:34,986][270010] Decorrelating experience for 0 frames... [2023-03-09 12:31:35,020][270095] Decorrelating experience for 0 frames... [2023-03-09 12:31:35,024][270143] Decorrelating experience for 0 frames... [2023-03-09 12:31:35,032][270161] Decorrelating experience for 0 frames... [2023-03-09 12:31:35,041][270003] Decorrelating experience for 0 frames... [2023-03-09 12:31:35,058][270120] Decorrelating experience for 32 frames... [2023-03-09 12:31:35,102][270096] Decorrelating experience for 0 frames... [2023-03-09 12:31:35,117][270156] Decorrelating experience for 32 frames... [2023-03-09 12:31:35,128][270092] Decorrelating experience for 96 frames... [2023-03-09 12:31:35,140][270125] Decorrelating experience for 64 frames... [2023-03-09 12:31:35,161][270121] Decorrelating experience for 32 frames... [2023-03-09 12:31:35,195][270126] Decorrelating experience for 64 frames... [2023-03-09 12:31:35,199][271517] Decorrelating experience for 32 frames... [2023-03-09 12:31:35,211][270010] Decorrelating experience for 32 frames... [2023-03-09 12:31:35,215][270003] Decorrelating experience for 32 frames... [2023-03-09 12:31:35,272][270100] Decorrelating experience for 0 frames... [2023-03-09 12:31:35,280][269981] Decorrelating experience for 64 frames... [2023-03-09 12:31:35,292][270120] Decorrelating experience for 64 frames... [2023-03-09 12:31:35,321][270860] Decorrelating experience for 0 frames... [2023-03-09 12:31:35,335][270125] Decorrelating experience for 96 frames... [2023-03-09 12:31:35,342][270123] Decorrelating experience for 32 frames... [2023-03-09 12:31:35,382][270111] Decorrelating experience for 0 frames... [2023-03-09 12:31:35,383][270096] Decorrelating experience for 32 frames... [2023-03-09 12:31:35,387][270158] Decorrelating experience for 128 frames... [2023-03-09 12:31:35,392][270293] Decorrelating experience for 64 frames... [2023-03-09 12:31:35,444][270751] Decorrelating experience for 0 frames... [2023-03-09 12:31:35,454][270115] Decorrelating experience for 32 frames... [2023-03-09 12:31:35,465][270097] Decorrelating experience for 96 frames... [2023-03-09 12:31:35,499][270007] Decorrelating experience for 64 frames... [2023-03-09 12:31:35,523][270553] Decorrelating experience for 96 frames... [2023-03-09 12:31:35,524][270084] Decorrelating experience for 32 frames... [2023-03-09 12:31:35,561][270161] Decorrelating experience for 32 frames... [2023-03-09 12:31:35,561][271126] Decorrelating experience for 32 frames... [2023-03-09 12:31:35,568][270554] Decorrelating experience for 0 frames... [2023-03-09 12:31:35,588][270145] Decorrelating experience for 96 frames... [2023-03-09 12:31:35,625][270002] Decorrelating experience for 64 frames... [2023-03-09 12:31:35,630][269981] Decorrelating experience for 96 frames... [2023-03-09 12:31:35,639][270115] Decorrelating experience for 64 frames... [2023-03-09 12:31:35,675][270080] Decorrelating experience for 96 frames... [2023-03-09 12:31:35,696][277995] Decorrelating experience for 0 frames... [2023-03-09 12:31:35,738][270699] Decorrelating experience for 0 frames... [2023-03-09 12:31:35,748][270091] Decorrelating experience for 32 frames... [2023-03-09 12:31:35,750][271017] Decorrelating experience for 0 frames... [2023-03-09 12:31:35,750][270124] Decorrelating experience for 32 frames... [2023-03-09 12:31:35,780][270104] Decorrelating experience for 64 frames... [2023-03-09 12:31:35,798][270121] Decorrelating experience for 64 frames... [2023-03-09 12:31:35,807][270133] Decorrelating experience for 32 frames... [2023-03-09 12:31:35,817][270472] Decorrelating experience for 32 frames... [2023-03-09 12:31:35,849][270013] Decorrelating experience for 32 frames... [2023-03-09 12:31:35,868][270751] Decorrelating experience for 32 frames... [2023-03-09 12:31:35,927][270404] Decorrelating experience for 96 frames... [2023-03-09 12:31:35,928][271017] Decorrelating experience for 32 frames... [2023-03-09 12:31:35,931][270123] Decorrelating experience for 64 frames... [2023-03-09 12:31:35,952][270009] Decorrelating experience for 32 frames... [2023-03-09 12:31:35,953][270143] Decorrelating experience for 32 frames... [2023-03-09 12:31:35,989][270115] Decorrelating experience for 96 frames... [2023-03-09 12:31:35,991][270160] Decorrelating experience for 0 frames... [2023-03-09 12:31:35,996][270120] Decorrelating experience for 96 frames... [2023-03-09 12:31:36,022][270945] Decorrelating experience for 32 frames... [2023-03-09 12:31:36,044][270473] Decorrelating experience for 0 frames... [2023-03-09 12:31:36,104][270151] Decorrelating experience for 32 frames... [2023-03-09 12:31:36,105][270472] Decorrelating experience for 64 frames... [2023-03-09 12:31:36,129][270123] Decorrelating experience for 96 frames... [2023-03-09 12:31:36,136][270131] Decorrelating experience for 0 frames... [2023-03-09 12:31:36,145][270121] Decorrelating experience for 96 frames... [2023-03-09 12:31:36,164][270093] Decorrelating experience for 0 frames... [2023-03-09 12:31:36,167][270132] Decorrelating experience for 32 frames... [2023-03-09 12:31:36,175][270122] Decorrelating experience for 96 frames... [2023-03-09 12:31:36,197][271126] Decorrelating experience for 64 frames... [2023-03-09 12:31:36,246][270097] Decorrelating experience for 128 frames... [2023-03-09 12:31:36,280][270119] Decorrelating experience for 128 frames... [2023-03-09 12:31:36,281][270118] Decorrelating experience for 96 frames... [2023-03-09 12:31:36,311][270155] Decorrelating experience for 96 frames... [2023-03-09 12:31:36,319][270596] Decorrelating experience for 0 frames... [2023-03-09 12:31:36,340][270152] Decorrelating experience for 0 frames... [2023-03-09 12:31:36,353][270107] Decorrelating experience for 32 frames... [2023-03-09 12:31:36,353][270100] Decorrelating experience for 32 frames... [2023-03-09 12:31:36,376][270944] Decorrelating experience for 96 frames... [2023-03-09 12:31:36,389][270622] Decorrelating experience for 96 frames... [2023-03-09 12:31:36,434][277349] Decorrelating experience for 96 frames... [2023-03-09 12:31:36,462][270111] Decorrelating experience for 32 frames... [2023-03-09 12:31:36,464][271017] Decorrelating experience for 64 frames... [2023-03-09 12:31:36,493][270596] Decorrelating experience for 32 frames... [2023-03-09 12:31:36,528][270109] Decorrelating experience for 0 frames... [2023-03-09 12:31:36,554][270008] Decorrelating experience for 0 frames... [2023-03-09 12:31:36,558][270121] Decorrelating experience for 128 frames... [2023-03-09 12:31:36,558][270097] Decorrelating experience for 160 frames... [2023-03-09 12:31:36,565][270084] Decorrelating experience for 64 frames... [2023-03-09 12:31:36,574][270136] Decorrelating experience for 32 frames... [2023-03-09 12:31:36,607][270751] Decorrelating experience for 64 frames... [2023-03-09 12:31:36,635][270553] Decorrelating experience for 128 frames... [2023-03-09 12:31:36,675][270088] Decorrelating experience for 0 frames... [2023-03-09 12:31:36,685][270134] Decorrelating experience for 32 frames... [2023-03-09 12:31:36,738][270144] Decorrelating experience for 0 frames... [2023-03-09 12:31:36,740][270944] Decorrelating experience for 128 frames... [2023-03-09 12:31:36,744][270123] Decorrelating experience for 128 frames... [2023-03-09 12:31:36,749][270107] Decorrelating experience for 64 frames... [2023-03-09 12:31:36,751][270554] Decorrelating experience for 32 frames... [2023-03-09 12:31:36,771][271919] Decorrelating experience for 64 frames... [2023-03-09 12:31:36,790][270142] Decorrelating experience for 32 frames... [2023-03-09 12:31:36,812][270160] Decorrelating experience for 32 frames... [2023-03-09 12:31:36,854][270132] Decorrelating experience for 64 frames... [2023-03-09 12:31:36,857][271017] Decorrelating experience for 96 frames... [2023-03-09 12:31:36,911][270015] Decorrelating experience for 64 frames... [2023-03-09 12:31:36,926][270945] Decorrelating experience for 64 frames... [2023-03-09 12:31:36,940][270134] Decorrelating experience for 64 frames... [2023-03-09 12:31:36,942][270122] Decorrelating experience for 128 frames... [2023-03-09 12:31:36,946][270141] Decorrelating experience for 32 frames... [2023-03-09 12:31:37,005][270944] Decorrelating experience for 160 frames... [2023-03-09 12:31:37,007][270146] Decorrelating experience for 128 frames... [2023-03-09 12:31:37,014][270699] Decorrelating experience for 32 frames... [2023-03-09 12:31:37,050][270132] Decorrelating experience for 96 frames... [2023-03-09 12:31:37,053][270121] Decorrelating experience for 160 frames... [2023-03-09 12:31:37,105][270934] Decorrelating experience for 32 frames... [2023-03-09 12:31:37,107][271355] Decorrelating experience for 64 frames... [2023-03-09 12:31:37,155][270136] Decorrelating experience for 64 frames... [2023-03-09 12:31:37,158][270554] Decorrelating experience for 64 frames... [2023-03-09 12:31:37,160][270126] Decorrelating experience for 96 frames... [2023-03-09 12:31:37,203][270699] Decorrelating experience for 64 frames... [2023-03-09 12:31:37,207][277995] Decorrelating experience for 32 frames... [2023-03-09 12:31:37,208][270155] Decorrelating experience for 128 frames... [2023-03-09 12:31:37,240][270134] Decorrelating experience for 96 frames... [2023-03-09 12:31:37,254][270160] Decorrelating experience for 64 frames... [2023-03-09 12:31:37,282][270141] Decorrelating experience for 64 frames... [2023-03-09 12:31:37,289][270934] Decorrelating experience for 64 frames... [2023-03-09 12:31:37,358][270114] Decorrelating experience for 160 frames... [2023-03-09 12:31:37,368][270137] Decorrelating experience for 32 frames... [2023-03-09 12:31:37,379][270944] Decorrelating experience for 192 frames... [2023-03-09 12:31:37,403][270136] Decorrelating experience for 96 frames... [2023-03-09 12:31:37,403][270152] Decorrelating experience for 32 frames... [2023-03-09 12:31:37,459][270554] Decorrelating experience for 96 frames... [2023-03-09 12:31:37,460][270013] Decorrelating experience for 64 frames... [2023-03-09 12:31:37,461][270130] Decorrelating experience for 32 frames... [2023-03-09 12:31:37,473][270096] Decorrelating experience for 64 frames... [2023-03-09 12:31:37,506][270122] Decorrelating experience for 160 frames... [2023-03-09 12:31:37,559][270293] Decorrelating experience for 96 frames... [2023-03-09 12:31:37,561][270158] Decorrelating experience for 160 frames... [2023-03-09 12:31:37,585][270152] Decorrelating experience for 64 frames... [2023-03-09 12:31:37,605][271355] Decorrelating experience for 96 frames... [2023-03-09 12:31:37,609][277995] Decorrelating experience for 64 frames... [2023-03-09 12:31:37,641][270934] Decorrelating experience for 96 frames... [2023-03-09 12:31:37,643][270121] Decorrelating experience for 192 frames... [2023-03-09 12:31:37,644][270114] Decorrelating experience for 192 frames... [2023-03-09 12:31:37,655][270013] Decorrelating experience for 96 frames... [2023-03-09 12:31:37,682][270146] Decorrelating experience for 160 frames... [2023-03-09 12:31:37,749][270130] Decorrelating experience for 64 frames... [2023-03-09 12:31:37,763][270125] Decorrelating experience for 128 frames... [2023-03-09 12:31:37,763][271126] Decorrelating experience for 96 frames... [2023-03-09 12:31:37,795][270158] Decorrelating experience for 192 frames... [2023-03-09 12:31:37,797][270944] Decorrelating experience for 224 frames... [2023-03-09 12:31:37,821][270126] Decorrelating experience for 128 frames... [2023-03-09 12:31:37,832][270107] Decorrelating experience for 96 frames... [2023-03-09 12:31:37,849][270934] Decorrelating experience for 128 frames... [2023-03-09 12:31:37,860][270165] Decorrelating experience for 64 frames... [2023-03-09 12:31:37,860][270145] Decorrelating experience for 128 frames... [2023-03-09 12:31:37,932][270155] Decorrelating experience for 160 frames... [2023-03-09 12:31:37,953][270134] Decorrelating experience for 128 frames... [2023-03-09 12:31:37,964][270138] Decorrelating experience for 0 frames... [2023-03-09 12:31:37,986][270114] Decorrelating experience for 224 frames... [2023-03-09 12:31:38,015][270556] Decorrelating experience for 0 frames... [2023-03-09 12:31:38,019][270099] Decorrelating experience for 32 frames... [2023-03-09 12:31:38,021][270123] Decorrelating experience for 160 frames... [2023-03-09 12:31:38,037][270121] Decorrelating experience for 224 frames... [2023-03-09 12:31:38,042][270107] Decorrelating experience for 128 frames... [2023-03-09 12:31:38,059][270622] Decorrelating experience for 128 frames... [2023-03-09 12:31:38,108][270111] Decorrelating experience for 64 frames... [2023-03-09 12:31:38,160][277995] Decorrelating experience for 96 frames... [2023-03-09 12:31:38,163][270135] Decorrelating experience for 64 frames... [2023-03-09 12:31:38,193][270100] Decorrelating experience for 64 frames... [2023-03-09 12:31:38,194][270126] Decorrelating experience for 160 frames... [2023-03-09 12:31:38,209][270944] Decorrelating experience for 256 frames... [2023-03-09 12:31:38,212][270165] Decorrelating experience for 96 frames... [2023-03-09 12:31:38,214][270132] Decorrelating experience for 128 frames... [2023-03-09 12:31:38,242][270114] Decorrelating experience for 256 frames... [2023-03-09 12:31:38,254][270086] Decorrelating experience for 0 frames... [2023-03-09 12:31:38,327][270158] Decorrelating experience for 224 frames... [2023-03-09 12:31:38,364][270113] Decorrelating experience for 64 frames... [2023-03-09 12:31:38,370][270016] Decorrelating experience for 160 frames... [2023-03-09 12:31:38,373][270934] Decorrelating experience for 160 frames... [2023-03-09 12:31:38,382][270007] Decorrelating experience for 96 frames... [2023-03-09 12:31:38,391][270556] Decorrelating experience for 32 frames... [2023-03-09 12:31:38,409][270111] Decorrelating experience for 96 frames... [2023-03-09 12:31:38,415][270108] Decorrelating experience for 0 frames... [2023-03-09 12:31:38,416][270553] Decorrelating experience for 160 frames... [2023-03-09 12:31:38,449][270130] Decorrelating experience for 96 frames... [2023-03-09 12:31:38,509][270699] Decorrelating experience for 96 frames... [2023-03-09 12:31:38,541][270100] Decorrelating experience for 96 frames... [2023-03-09 12:31:38,561][270160] Decorrelating experience for 96 frames... [2023-03-09 12:31:38,562][270114] Decorrelating experience for 288 frames... [2023-03-09 12:31:38,566][270002] Decorrelating experience for 96 frames... [2023-03-09 12:31:38,587][270132] Decorrelating experience for 160 frames... [2023-03-09 12:31:38,593][270121] Decorrelating experience for 256 frames... [2023-03-09 12:31:38,614][270099] Decorrelating experience for 64 frames... [2023-03-09 12:31:38,623][270293] Decorrelating experience for 128 frames... [2023-03-09 12:31:38,671][270124] Decorrelating experience for 64 frames... [2023-03-09 12:31:38,718][270093] Decorrelating experience for 32 frames... [2023-03-09 12:31:38,718][270133] Decorrelating experience for 64 frames... [2023-03-09 12:31:38,740][270108] Decorrelating experience for 32 frames... [2023-03-09 12:31:38,746][270125] Decorrelating experience for 160 frames... [2023-03-09 12:31:38,766][270163] Decorrelating experience for 64 frames... [2023-03-09 12:31:38,767][270147] Decorrelating experience for 64 frames... [2023-03-09 12:31:38,772][270113] Decorrelating experience for 96 frames... [2023-03-09 12:31:38,787][270152] Decorrelating experience for 96 frames... [2023-03-09 12:31:38,805][270016] Decorrelating experience for 192 frames... [2023-03-09 12:31:38,851][270100] Decorrelating experience for 128 frames... [2023-03-09 12:31:38,893][270007] Decorrelating experience for 128 frames... [2023-03-09 12:31:38,916][270133] Decorrelating experience for 96 frames... [2023-03-09 12:31:38,927][270108] Decorrelating experience for 64 frames... [2023-03-09 12:31:38,950][270553] Decorrelating experience for 192 frames... [2023-03-09 12:31:38,963][270130] Decorrelating experience for 128 frames... [2023-03-09 12:31:38,969][270117] Decorrelating experience for 0 frames... [2023-03-09 12:31:38,970][270097] Decorrelating experience for 192 frames... [2023-03-09 12:31:38,983][270164] Decorrelating experience for 160 frames... [2023-03-09 12:31:39,040][270141] Decorrelating experience for 96 frames... [2023-03-09 12:31:39,059][270113] Decorrelating experience for 128 frames... [2023-03-09 12:31:39,067][270162] Decorrelating experience for 32 frames... [2023-03-09 12:31:39,118][270147] Decorrelating experience for 96 frames... [2023-03-09 12:31:39,129][270006] Decorrelating experience for 64 frames... [2023-03-09 12:31:39,148][270138] Decorrelating experience for 32 frames... [2023-03-09 12:31:39,151][270293] Decorrelating experience for 160 frames... [2023-03-09 12:31:39,169][270135] Decorrelating experience for 96 frames... [2023-03-09 12:31:39,172][269981] Decorrelating experience for 128 frames... [2023-03-09 12:31:39,233][270142] Decorrelating experience for 64 frames... [2023-03-09 12:31:39,261][270934] Decorrelating experience for 192 frames... [2023-03-09 12:31:39,262][270163] Decorrelating experience for 96 frames... [2023-03-09 12:31:39,302][270114] Decorrelating experience for 320 frames... [2023-03-09 12:31:39,320][270131] Decorrelating experience for 32 frames... [2023-03-09 12:31:39,331][270160] Decorrelating experience for 128 frames... [2023-03-09 12:31:39,332][270699] Decorrelating experience for 128 frames... [2023-03-09 12:31:39,332][270115] Decorrelating experience for 128 frames... [2023-03-09 12:31:39,343][270117] Decorrelating experience for 32 frames... [2023-03-09 12:31:39,369][270159] Decorrelating experience for 96 frames... [2023-03-09 12:31:39,416][270097] Decorrelating experience for 224 frames... [2023-03-09 12:31:39,445][270553] Decorrelating experience for 224 frames... [2023-03-09 12:31:39,469][270007] Decorrelating experience for 160 frames... [2023-03-09 12:31:39,529][271919] Decorrelating experience for 96 frames... [2023-03-09 12:31:39,529][270943] Decorrelating experience for 0 frames... [2023-03-09 12:31:39,530][270105] Decorrelating experience for 64 frames... [2023-03-09 12:31:39,533][270131] Decorrelating experience for 64 frames... [2023-03-09 12:31:39,537][270142] Decorrelating experience for 96 frames... [2023-03-09 12:31:39,553][270934] Decorrelating experience for 224 frames... [2023-03-09 12:31:39,585][269981] Decorrelating experience for 160 frames... [2023-03-09 12:31:39,621][271224] Decorrelating experience for 0 frames... [2023-03-09 12:31:39,653][270009] Decorrelating experience for 64 frames... [2023-03-09 12:31:39,708][270160] Decorrelating experience for 160 frames... [2023-03-09 12:31:39,709][270162] Decorrelating experience for 64 frames... [2023-03-09 12:31:39,709][270115] Decorrelating experience for 160 frames... [2023-03-09 12:31:39,719][270080] Decorrelating experience for 128 frames... [2023-03-09 12:31:39,729][270155] Decorrelating experience for 192 frames... [2023-03-09 12:31:39,730][270100] Decorrelating experience for 160 frames... [2023-03-09 12:31:39,772][270139] Decorrelating experience for 32 frames... [2023-03-09 12:31:39,789][270157] Decorrelating experience for 0 frames... [2023-03-09 12:31:39,806][270114] Decorrelating experience for 352 frames... [2023-03-09 12:31:39,829][270135] Decorrelating experience for 128 frames... [2023-03-09 12:31:39,888][270944] Decorrelating experience for 288 frames... [2023-03-09 12:31:39,891][270138] Decorrelating experience for 64 frames... [2023-03-09 12:31:39,892][270086] Decorrelating experience for 32 frames... [2023-03-09 12:31:39,905][270007] Decorrelating experience for 192 frames... [2023-03-09 12:31:39,924][270097] Decorrelating experience for 256 frames... [2023-03-09 12:31:39,934][270556] Decorrelating experience for 64 frames... [2023-03-09 12:31:39,958][270080] Decorrelating experience for 160 frames... [2023-03-09 12:31:39,972][270148] Decorrelating experience for 32 frames... [2023-03-09 12:31:39,982][269569] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 2500018176. Throughput: 0: 0.0. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) [2023-03-09 12:31:40,007][270162] Decorrelating experience for 96 frames... [2023-03-09 12:31:40,010][270016] Decorrelating experience for 224 frames... [2023-03-09 12:31:40,078][270368] Decorrelating experience for 32 frames... [2023-03-09 12:31:40,079][270552] Decorrelating experience for 0 frames... [2023-03-09 12:31:40,080][270084] Decorrelating experience for 96 frames... [2023-03-09 12:31:40,085][270011] Decorrelating experience for 0 frames... [2023-03-09 12:31:40,126][270473] Decorrelating experience for 32 frames... [2023-03-09 12:31:40,139][270123] Decorrelating experience for 192 frames... [2023-03-09 12:31:40,141][271126] Decorrelating experience for 128 frames... [2023-03-09 12:31:40,156][270699] Decorrelating experience for 160 frames... [2023-03-09 12:31:40,186][270108] Decorrelating experience for 96 frames... [2023-03-09 12:31:40,188][271375] Decorrelating experience for 32 frames... [2023-03-09 12:31:40,255][270552] Decorrelating experience for 32 frames... [2023-03-09 12:31:40,258][270152] Decorrelating experience for 128 frames... [2023-03-09 12:31:40,263][270934] Decorrelating experience for 256 frames... [2023-03-09 12:31:40,274][270088] Decorrelating experience for 32 frames... [2023-03-09 12:31:40,310][270011] Decorrelating experience for 32 frames... [2023-03-09 12:31:40,322][270114] Decorrelating experience for 384 frames... [2023-03-09 12:31:40,322][270162] Decorrelating experience for 128 frames... [2023-03-09 12:31:40,333][270099] Decorrelating experience for 96 frames... [2023-03-09 12:31:40,366][270157] Decorrelating experience for 32 frames... [2023-03-09 12:31:40,374][270100] Decorrelating experience for 192 frames... [2023-03-09 12:31:40,431][270015] Decorrelating experience for 96 frames... [2023-03-09 12:31:40,435][270147] Decorrelating experience for 128 frames... [2023-03-09 12:31:40,440][270163] Decorrelating experience for 128 frames... [2023-03-09 12:31:40,454][270002] Decorrelating experience for 128 frames... [2023-03-09 12:31:40,486][270096] Decorrelating experience for 96 frames... [2023-03-09 12:31:40,505][270007] Decorrelating experience for 224 frames... [2023-03-09 12:31:40,515][270293] Decorrelating experience for 192 frames... [2023-03-09 12:31:40,517][270473] Decorrelating experience for 64 frames... [2023-03-09 12:31:40,542][270552] Decorrelating experience for 64 frames... [2023-03-09 12:31:40,552][270135] Decorrelating experience for 160 frames... [2023-03-09 12:31:40,609][270553] Decorrelating experience for 256 frames... [2023-03-09 12:31:40,611][270148] Decorrelating experience for 64 frames... [2023-03-09 12:31:40,621][270100] Decorrelating experience for 224 frames... [2023-03-09 12:31:40,628][270109] Decorrelating experience for 32 frames... [2023-03-09 12:31:40,666][271126] Decorrelating experience for 160 frames... [2023-03-09 12:31:40,693][270134] Decorrelating experience for 160 frames... [2023-03-09 12:31:40,698][270126] Decorrelating experience for 192 frames... [2023-03-09 12:31:40,700][270115] Decorrelating experience for 192 frames... [2023-03-09 12:31:40,725][269981] Decorrelating experience for 192 frames... [2023-03-09 12:31:40,734][270005] Decorrelating experience for 0 frames... [2023-03-09 12:31:40,783][270136] Decorrelating experience for 128 frames... [2023-03-09 12:31:40,794][270138] Decorrelating experience for 96 frames... [2023-03-09 12:31:40,806][270099] Decorrelating experience for 128 frames... [2023-03-09 12:31:40,806][270157] Decorrelating experience for 64 frames... [2023-03-09 12:31:40,844][270162] Decorrelating experience for 160 frames... [2023-03-09 12:31:40,881][270094] Decorrelating experience for 64 frames... [2023-03-09 12:31:40,884][270751] Decorrelating experience for 96 frames... [2023-03-09 12:31:40,885][270100] Decorrelating experience for 256 frames... [2023-03-09 12:31:40,915][270088] Decorrelating experience for 64 frames... [2023-03-09 12:31:40,919][270293] Decorrelating experience for 224 frames... [2023-03-09 12:31:40,965][270005] Decorrelating experience for 32 frames... [2023-03-09 12:31:40,982][270144] Decorrelating experience for 32 frames... [2023-03-09 12:31:40,984][270161] Decorrelating experience for 64 frames... [2023-03-09 12:31:40,990][270008] Decorrelating experience for 32 frames... [2023-03-09 12:31:41,018][270368] Decorrelating experience for 64 frames... [2023-03-09 12:31:41,062][270141] Decorrelating experience for 128 frames... [2023-03-09 12:31:41,072][270109] Decorrelating experience for 64 frames... [2023-03-09 12:31:41,097][270142] Decorrelating experience for 128 frames... [2023-03-09 12:31:41,098][270015] Decorrelating experience for 128 frames... [2023-03-09 12:31:41,099][270125] Decorrelating experience for 192 frames... [2023-03-09 12:31:41,139][270151] Decorrelating experience for 64 frames... [2023-03-09 12:31:41,168][270110] Decorrelating experience for 0 frames... [2023-03-09 12:31:41,170][270139] Decorrelating experience for 64 frames... [2023-03-09 12:31:41,195][270115] Decorrelating experience for 224 frames... [2023-03-09 12:31:41,218][269981] Decorrelating experience for 224 frames... [2023-03-09 12:31:41,248][270006] Decorrelating experience for 96 frames... [2023-03-09 12:31:41,260][270009] Decorrelating experience for 96 frames... [2023-03-09 12:31:41,283][270093] Decorrelating experience for 64 frames... [2023-03-09 12:31:41,284][270008] Decorrelating experience for 64 frames... [2023-03-09 12:31:41,284][270094] Decorrelating experience for 96 frames... [2023-03-09 12:31:41,312][270148] Decorrelating experience for 96 frames... [2023-03-09 12:31:41,344][270132] Decorrelating experience for 192 frames... [2023-03-09 12:31:41,350][270080] Decorrelating experience for 192 frames... [2023-03-09 12:31:41,370][270109] Decorrelating experience for 96 frames... [2023-03-09 12:31:41,401][270096] Decorrelating experience for 128 frames... [2023-03-09 12:31:41,441][270140] Decorrelating experience for 0 frames... [2023-03-09 12:31:41,459][270138] Decorrelating experience for 128 frames... [2023-03-09 12:31:41,465][270088] Decorrelating experience for 96 frames... [2023-03-09 12:31:41,488][270099] Decorrelating experience for 160 frames... [2023-03-09 12:31:41,488][270141] Decorrelating experience for 160 frames... [2023-03-09 12:31:41,489][270161] Decorrelating experience for 96 frames... [2023-03-09 12:31:41,533][270093] Decorrelating experience for 96 frames... [2023-03-09 12:31:41,536][270120] Decorrelating experience for 128 frames... [2023-03-09 12:31:41,542][270554] Decorrelating experience for 128 frames... [2023-03-09 12:31:41,586][270095] Decorrelating experience for 32 frames... [2023-03-09 12:31:41,622][270139] Decorrelating experience for 96 frames... [2023-03-09 12:31:41,640][270012] Decorrelating experience for 0 frames... [2023-03-09 12:31:41,643][270086] Decorrelating experience for 64 frames... [2023-03-09 12:31:41,668][270943] Decorrelating experience for 32 frames... [2023-03-09 12:31:41,669][270113] Decorrelating experience for 160 frames... [2023-03-09 12:31:41,680][270109] Decorrelating experience for 128 frames... [2023-03-09 12:31:41,713][270147] Decorrelating experience for 160 frames... [2023-03-09 12:31:41,724][270473] Decorrelating experience for 96 frames... [2023-03-09 12:31:41,732][271517] Decorrelating experience for 64 frames... [2023-03-09 12:31:41,765][270140] Decorrelating experience for 32 frames... [2023-03-09 12:31:41,795][270125] Decorrelating experience for 224 frames... [2023-03-09 12:31:41,820][270163] Decorrelating experience for 160 frames... [2023-03-09 12:31:41,824][270088] Decorrelating experience for 128 frames... [2023-03-09 12:31:41,850][270110] Decorrelating experience for 32 frames... [2023-03-09 12:31:41,851][271017] Decorrelating experience for 128 frames... [2023-03-09 12:31:41,900][270013] Decorrelating experience for 128 frames... [2023-03-09 12:31:41,903][270161] Decorrelating experience for 128 frames... [2023-03-09 12:31:41,906][270154] Decorrelating experience for 0 frames... [2023-03-09 12:31:41,937][270137] Decorrelating experience for 64 frames... [2023-03-09 12:31:41,945][270556] Decorrelating experience for 96 frames... [2023-03-09 12:31:41,986][270860] Decorrelating experience for 32 frames... [2023-03-09 12:31:42,002][270089] Decorrelating experience for 32 frames... [2023-03-09 12:31:42,008][270943] Decorrelating experience for 64 frames... [2023-03-09 12:31:42,026][270015] Decorrelating experience for 160 frames... [2023-03-09 12:31:42,031][270138] Decorrelating experience for 160 frames... [2023-03-09 12:31:42,076][270148] Decorrelating experience for 128 frames... [2023-03-09 12:31:42,081][271517] Decorrelating experience for 96 frames... [2023-03-09 12:31:42,087][270139] Decorrelating experience for 128 frames... [2023-03-09 12:31:42,125][270096] Decorrelating experience for 160 frames... [2023-03-09 12:31:42,138][270090] Decorrelating experience for 64 frames... [2023-03-09 12:31:42,162][270100] Decorrelating experience for 288 frames... [2023-03-09 12:31:42,191][270404] Decorrelating experience for 128 frames... [2023-03-09 12:31:42,204][270699] Decorrelating experience for 192 frames... [2023-03-09 12:31:42,207][270945] Decorrelating experience for 96 frames... [2023-03-09 12:31:42,227][270134] Decorrelating experience for 192 frames... [2023-03-09 12:31:42,279][270554] Decorrelating experience for 160 frames... [2023-03-09 12:31:42,303][270094] Decorrelating experience for 128 frames... [2023-03-09 12:31:42,327][271919] Decorrelating experience for 128 frames... [2023-03-09 12:31:42,340][270153] Decorrelating experience for 0 frames... [2023-03-09 12:31:42,360][270096] Decorrelating experience for 192 frames... [2023-03-09 12:31:42,367][270155] Decorrelating experience for 224 frames... [2023-03-09 12:31:42,380][271017] Decorrelating experience for 160 frames... [2023-03-09 12:31:42,388][270293] Decorrelating experience for 256 frames... [2023-03-09 12:31:42,389][270154] Decorrelating experience for 32 frames... [2023-03-09 12:31:42,405][270140] Decorrelating experience for 64 frames... [2023-03-09 12:31:42,499][270093] Decorrelating experience for 128 frames... [2023-03-09 12:31:42,507][270125] Decorrelating experience for 256 frames... [2023-03-09 12:31:42,511][270084] Decorrelating experience for 128 frames... [2023-03-09 12:31:42,546][270541] Decorrelating experience for 0 frames... [2023-03-09 12:31:42,548][270596] Decorrelating experience for 64 frames... [2023-03-09 12:31:42,558][271919] Decorrelating experience for 160 frames... [2023-03-09 12:31:42,560][270163] Decorrelating experience for 192 frames... [2023-03-09 12:31:42,565][270157] Decorrelating experience for 96 frames... [2023-03-09 12:31:42,567][270153] Decorrelating experience for 32 frames... [2023-03-09 12:31:42,586][270121] Decorrelating experience for 288 frames... [2023-03-09 12:31:42,684][269981] Decorrelating experience for 256 frames... [2023-03-09 12:31:42,692][270162] Decorrelating experience for 192 frames... [2023-03-09 12:31:42,700][270101] Decorrelating experience for 0 frames... [2023-03-09 12:31:42,753][270110] Decorrelating experience for 64 frames... [2023-03-09 12:31:42,755][270089] Decorrelating experience for 64 frames... [2023-03-09 12:31:42,757][270143] Decorrelating experience for 64 frames... [2023-03-09 12:31:42,757][270233] Decorrelating experience for 32 frames... [2023-03-09 12:31:42,758][270116] Decorrelating experience for 128 frames... [2023-03-09 12:31:42,759][270153] Decorrelating experience for 64 frames... [2023-03-09 12:31:42,765][270943] Decorrelating experience for 96 frames... [2023-03-09 12:31:42,866][270139] Decorrelating experience for 160 frames... [2023-03-09 12:31:42,871][270093] Decorrelating experience for 160 frames... [2023-03-09 12:31:42,901][270596] Decorrelating experience for 96 frames... [2023-03-09 12:31:42,929][270094] Decorrelating experience for 160 frames... [2023-03-09 12:31:42,932][270095] Decorrelating experience for 64 frames... [2023-03-09 12:31:42,954][270233] Decorrelating experience for 64 frames... [2023-03-09 12:31:42,955][271919] Decorrelating experience for 192 frames... [2023-03-09 12:31:42,955][270085] Decorrelating experience for 32 frames... [2023-03-09 12:31:42,957][270111] Decorrelating experience for 128 frames... [2023-03-09 12:31:42,958][270014] Decorrelating experience for 0 frames... [2023-03-09 12:31:43,046][271517] Decorrelating experience for 128 frames... [2023-03-09 12:31:43,048][270152] Decorrelating experience for 160 frames... [2023-03-09 12:31:43,112][270096] Decorrelating experience for 224 frames... [2023-03-09 12:31:43,113][270622] Decorrelating experience for 160 frames... [2023-03-09 12:31:43,113][270153] Decorrelating experience for 96 frames... [2023-03-09 12:31:43,131][270154] Decorrelating experience for 64 frames... [2023-03-09 12:31:43,135][270116] Decorrelating experience for 160 frames... [2023-03-09 12:31:43,150][270553] Decorrelating experience for 288 frames... [2023-03-09 12:31:43,151][277349] Decorrelating experience for 128 frames... [2023-03-09 12:31:43,159][270368] Decorrelating experience for 96 frames... [2023-03-09 12:31:43,223][270945] Decorrelating experience for 128 frames... [2023-03-09 12:31:43,262][270144] Decorrelating experience for 64 frames... [2023-03-09 12:31:43,288][270084] Decorrelating experience for 160 frames... [2023-03-09 12:31:43,294][270137] Decorrelating experience for 96 frames... [2023-03-09 12:31:43,308][270143] Decorrelating experience for 96 frames... [2023-03-09 12:31:43,313][270094] Decorrelating experience for 192 frames... [2023-03-09 12:31:43,328][270154] Decorrelating experience for 96 frames... [2023-03-09 12:31:43,353][270135] Decorrelating experience for 192 frames... [2023-03-09 12:31:43,355][270139] Decorrelating experience for 192 frames... [2023-03-09 12:31:43,361][270404] Decorrelating experience for 160 frames... [2023-03-09 12:31:43,397][270146] Decorrelating experience for 192 frames... [2023-03-09 12:31:43,445][270622] Decorrelating experience for 192 frames... [2023-03-09 12:31:43,465][270108] Decorrelating experience for 128 frames... [2023-03-09 12:31:43,476][270153] Decorrelating experience for 128 frames... [2023-03-09 12:31:43,483][270141] Decorrelating experience for 192 frames... [2023-03-09 12:31:43,502][270137] Decorrelating experience for 128 frames... [2023-03-09 12:31:43,519][270143] Decorrelating experience for 128 frames... [2023-03-09 12:31:43,530][270125] Decorrelating experience for 288 frames... [2023-03-09 12:31:43,554][270132] Decorrelating experience for 224 frames... [2023-03-09 12:31:43,572][271017] Decorrelating experience for 192 frames... [2023-03-09 12:31:43,578][277349] Decorrelating experience for 160 frames... [2023-03-09 12:31:43,640][270099] Decorrelating experience for 192 frames... [2023-03-09 12:31:43,647][270008] Decorrelating experience for 96 frames... [2023-03-09 12:31:43,653][271355] Decorrelating experience for 128 frames... [2023-03-09 12:31:43,660][270140] Decorrelating experience for 96 frames... [2023-03-09 12:31:43,742][270157] Decorrelating experience for 128 frames... [2023-03-09 12:31:43,748][270135] Decorrelating experience for 224 frames... [2023-03-09 12:31:43,756][270128] Decorrelating experience for 32 frames... [2023-03-09 12:31:43,775][270368] Decorrelating experience for 128 frames... [2023-03-09 12:31:43,776][270080] Decorrelating experience for 224 frames... [2023-03-09 12:31:43,821][270556] Decorrelating experience for 128 frames... [2023-03-09 12:31:43,822][270104] Decorrelating experience for 96 frames... [2023-03-09 12:31:43,824][270116] Decorrelating experience for 192 frames... [2023-03-09 12:31:43,842][270154] Decorrelating experience for 128 frames... [2023-03-09 12:31:43,846][270945] Decorrelating experience for 160 frames... [2023-03-09 12:31:43,923][270121] Decorrelating experience for 320 frames... [2023-03-09 12:31:43,929][270943] Decorrelating experience for 128 frames... [2023-03-09 12:31:43,957][270086] Decorrelating experience for 96 frames... [2023-03-09 12:31:43,969][270293] Decorrelating experience for 288 frames... [2023-03-09 12:31:43,975][270084] Decorrelating experience for 192 frames... [2023-03-09 12:31:44,006][270142] Decorrelating experience for 160 frames... [2023-03-09 12:31:44,019][270115] Decorrelating experience for 256 frames... [2023-03-09 12:31:44,024][271126] Decorrelating experience for 192 frames... [2023-03-09 12:31:44,080][270111] Decorrelating experience for 160 frames... [2023-03-09 12:31:44,080][270368] Decorrelating experience for 160 frames... [2023-03-09 12:31:44,101][270010] Decorrelating experience for 64 frames... [2023-03-09 12:31:44,121][277349] Decorrelating experience for 192 frames... [2023-03-09 12:31:44,141][270099] Decorrelating experience for 224 frames... [2023-03-09 12:31:44,171][270160] Decorrelating experience for 192 frames... [2023-03-09 12:31:44,191][270161] Decorrelating experience for 160 frames... [2023-03-09 12:31:44,197][270128] Decorrelating experience for 64 frames... [2023-03-09 12:31:44,201][270118] Decorrelating experience for 128 frames... [2023-03-09 12:31:44,221][270404] Decorrelating experience for 192 frames... [2023-03-09 12:31:44,261][270134] Decorrelating experience for 224 frames... [2023-03-09 12:31:44,261][270514] Decorrelating experience for 32 frames... [2023-03-09 12:31:44,296][270553] Decorrelating experience for 320 frames... [2023-03-09 12:31:44,302][269569] Heartbeat connected on Batcher_0 [2023-03-09 12:31:44,304][269569] Heartbeat connected on LearnerWorker_p0 [2023-03-09 12:31:44,318][270127] Decorrelating experience for 32 frames... [2023-03-09 12:31:44,339][269569] Heartbeat connected on InferenceWorker_p0-w0 [2023-03-09 12:31:44,354][270293] Decorrelating experience for 320 frames... [2023-03-09 12:31:44,368][270154] Decorrelating experience for 160 frames... [2023-03-09 12:31:44,371][270144] Decorrelating experience for 96 frames... [2023-03-09 12:31:44,387][270135] Decorrelating experience for 256 frames... [2023-03-09 12:31:44,387][270137] Decorrelating experience for 160 frames... [2023-03-09 12:31:44,443][270108] Decorrelating experience for 160 frames... [2023-03-09 12:31:44,491][270152] Decorrelating experience for 192 frames... [2023-03-09 12:31:44,497][270013] Decorrelating experience for 160 frames... [2023-03-09 12:31:44,497][270368] Decorrelating experience for 192 frames... [2023-03-09 12:31:44,530][271355] Decorrelating experience for 160 frames... [2023-03-09 12:31:44,560][270944] Decorrelating experience for 320 frames... [2023-03-09 12:31:44,570][269981] Decorrelating experience for 288 frames... [2023-03-09 12:31:44,571][277349] Decorrelating experience for 224 frames... [2023-03-09 12:31:44,598][270123] Decorrelating experience for 224 frames... [2023-03-09 12:31:44,603][270154] Decorrelating experience for 192 frames... [2023-03-09 12:31:44,622][270134] Decorrelating experience for 256 frames... [2023-03-09 12:31:44,678][270015] Decorrelating experience for 192 frames... [2023-03-09 12:31:44,712][270135] Decorrelating experience for 288 frames... [2023-03-09 12:31:44,732][270100] Decorrelating experience for 320 frames... [2023-03-09 12:31:44,734][270012] Decorrelating experience for 32 frames... [2023-03-09 12:31:44,739][270096] Decorrelating experience for 256 frames... [2023-03-09 12:31:44,753][270943] Decorrelating experience for 160 frames... [2023-03-09 12:31:44,778][270137] Decorrelating experience for 192 frames... [2023-03-09 12:31:44,779][270086] Decorrelating experience for 128 frames... [2023-03-09 12:31:44,791][270152] Decorrelating experience for 224 frames... [2023-03-09 12:31:44,826][270514] Decorrelating experience for 64 frames... [2023-03-09 12:31:44,852][270085] Decorrelating experience for 64 frames... [2023-03-09 12:31:44,892][270134] Decorrelating experience for 288 frames... [2023-03-09 12:31:44,911][270091] Decorrelating experience for 64 frames... [2023-03-09 12:31:44,918][270094] Decorrelating experience for 224 frames... [2023-03-09 12:31:44,931][270108] Decorrelating experience for 192 frames... [2023-03-09 12:31:44,947][270159] Decorrelating experience for 128 frames... [2023-03-09 12:31:44,956][270080] Decorrelating experience for 256 frames... [2023-03-09 12:31:44,972][270012] Decorrelating experience for 64 frames... [2023-03-09 12:31:44,982][269569] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 2500018176. Throughput: 0: 0.0. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) [2023-03-09 12:31:44,999][270123] Decorrelating experience for 256 frames... [2023-03-09 12:31:45,003][270099] Decorrelating experience for 256 frames... [2023-03-09 12:31:45,028][270126] Decorrelating experience for 224 frames... [2023-03-09 12:31:45,070][270160] Decorrelating experience for 224 frames... [2023-03-09 12:31:45,102][270368] Decorrelating experience for 224 frames... [2023-03-09 12:31:45,104][270128] Decorrelating experience for 96 frames... [2023-03-09 12:31:45,114][270153] Decorrelating experience for 160 frames... [2023-03-09 12:31:45,132][270120] Decorrelating experience for 160 frames... [2023-03-09 12:31:45,155][270085] Decorrelating experience for 96 frames... [2023-03-09 12:31:45,156][270113] Decorrelating experience for 192 frames... [2023-03-09 12:31:45,180][270108] Decorrelating experience for 224 frames... [2023-03-09 12:31:45,186][270005] Decorrelating experience for 64 frames... [2023-03-09 12:31:45,208][271375] Decorrelating experience for 64 frames... [2023-03-09 12:31:45,250][270556] Decorrelating experience for 160 frames... [2023-03-09 12:31:45,281][270134] Decorrelating experience for 320 frames... [2023-03-09 12:31:45,286][270144] Decorrelating experience for 128 frames... [2023-03-09 12:31:45,289][270150] Decorrelating experience for 96 frames... [2023-03-09 12:31:45,309][270091] Decorrelating experience for 96 frames... [2023-03-09 12:31:45,331][270148] Decorrelating experience for 160 frames... [2023-03-09 12:31:45,344][270009] Decorrelating experience for 128 frames... [2023-03-09 12:31:45,362][270096] Decorrelating experience for 288 frames... [2023-03-09 12:31:45,364][270127] Decorrelating experience for 64 frames... [2023-03-09 12:31:45,389][270141] Decorrelating experience for 224 frames... [2023-03-09 12:31:45,430][270099] Decorrelating experience for 288 frames... [2023-03-09 12:31:45,459][271375] Decorrelating experience for 96 frames... [2023-03-09 12:31:45,464][270106] Decorrelating experience for 64 frames... [2023-03-09 12:31:45,474][270159] Decorrelating experience for 160 frames... [2023-03-09 12:31:45,485][277349] Decorrelating experience for 256 frames... [2023-03-09 12:31:45,524][270088] Decorrelating experience for 160 frames... [2023-03-09 12:31:45,526][270123] Decorrelating experience for 288 frames... [2023-03-09 12:31:45,548][270945] Decorrelating experience for 192 frames... [2023-03-09 12:31:45,549][270135] Decorrelating experience for 320 frames... [2023-03-09 12:31:45,561][270151] Decorrelating experience for 96 frames... [2023-03-09 12:31:45,630][270368] Decorrelating experience for 256 frames... [2023-03-09 12:31:45,639][270126] Decorrelating experience for 256 frames... [2023-03-09 12:31:45,659][270154] Decorrelating experience for 224 frames... [2023-03-09 12:31:45,669][270148] Decorrelating experience for 192 frames... [2023-03-09 12:31:45,671][269981] Decorrelating experience for 320 frames... [2023-03-09 12:31:45,704][270146] Decorrelating experience for 224 frames... [2023-03-09 12:31:45,727][270012] Decorrelating experience for 96 frames... [2023-03-09 12:31:45,733][270160] Decorrelating experience for 256 frames... [2023-03-09 12:31:45,761][270080] Decorrelating experience for 288 frames... [2023-03-09 12:31:45,768][270096] Decorrelating experience for 320 frames... [2023-03-09 12:31:45,823][271375] Decorrelating experience for 128 frames... [2023-03-09 12:31:45,826][270121] Decorrelating experience for 352 frames... [2023-03-09 12:31:45,858][277349] Decorrelating experience for 288 frames... [2023-03-09 12:31:45,879][270094] Decorrelating experience for 256 frames... [2023-03-09 12:31:45,905][270293] Decorrelating experience for 352 frames... [2023-03-09 12:31:45,916][270157] Decorrelating experience for 160 frames... [2023-03-09 12:31:45,922][270944] Decorrelating experience for 352 frames... [2023-03-09 12:31:45,942][270013] Decorrelating experience for 192 frames... [2023-03-09 12:31:45,945][270945] Decorrelating experience for 224 frames... [2023-03-09 12:31:45,948][270101] Decorrelating experience for 32 frames... [2023-03-09 12:31:46,007][270153] Decorrelating experience for 192 frames... [2023-03-09 12:31:46,008][270160] Decorrelating experience for 288 frames... [2023-03-09 12:31:46,042][270135] Decorrelating experience for 352 frames... [2023-03-09 12:31:46,059][270090] Decorrelating experience for 96 frames... [2023-03-09 12:31:46,135][270556] Decorrelating experience for 192 frames... [2023-03-09 12:31:46,137][270404] Decorrelating experience for 224 frames... [2023-03-09 12:31:46,138][270141] Decorrelating experience for 256 frames... [2023-03-09 12:31:46,161][270095] Decorrelating experience for 96 frames... [2023-03-09 12:31:46,182][270080] Decorrelating experience for 320 frames... [2023-03-09 12:31:46,209][271017] Decorrelating experience for 224 frames... [2023-03-09 12:31:46,210][270145] Decorrelating experience for 160 frames... [2023-03-09 12:31:46,232][270140] Decorrelating experience for 128 frames... [2023-03-09 12:31:46,233][270096] Decorrelating experience for 352 frames... [2023-03-09 12:31:46,258][270293] Decorrelating experience for 384 frames... [2023-03-09 12:31:46,335][270113] Decorrelating experience for 224 frames... [2023-03-09 12:31:46,337][270142] Decorrelating experience for 192 frames... [2023-03-09 12:31:46,342][270160] Decorrelating experience for 320 frames... [2023-03-09 12:31:46,374][270095] Decorrelating experience for 128 frames... [2023-03-09 12:31:46,391][270101] Decorrelating experience for 64 frames... [2023-03-09 12:31:46,394][270013] Decorrelating experience for 224 frames... [2023-03-09 12:31:46,436][270159] Decorrelating experience for 192 frames... [2023-03-09 12:31:46,439][270146] Decorrelating experience for 256 frames... [2023-03-09 12:31:46,440][270116] Decorrelating experience for 224 frames... [2023-03-09 12:31:46,478][270145] Decorrelating experience for 192 frames... [2023-03-09 12:31:46,533][271224] Decorrelating experience for 32 frames... [2023-03-09 12:31:46,534][270088] Decorrelating experience for 192 frames... [2023-03-09 12:31:46,552][270090] Decorrelating experience for 128 frames... [2023-03-09 12:31:46,578][270080] Decorrelating experience for 352 frames... [2023-03-09 12:31:46,591][270554] Decorrelating experience for 192 frames... [2023-03-09 12:31:46,638][270012] Decorrelating experience for 128 frames... [2023-03-09 12:31:46,638][270117] Decorrelating experience for 64 frames... [2023-03-09 12:31:46,645][270115] Decorrelating experience for 288 frames... [2023-03-09 12:31:46,680][270159] Decorrelating experience for 224 frames... [2023-03-09 12:31:46,710][271017] Decorrelating experience for 256 frames... [2023-03-09 12:31:46,720][271224] Decorrelating experience for 64 frames... [2023-03-09 12:31:46,733][270104] Decorrelating experience for 128 frames... [2023-03-09 12:31:46,758][270141] Decorrelating experience for 288 frames... [2023-03-09 12:31:46,770][270148] Decorrelating experience for 224 frames... [2023-03-09 12:31:46,839][270088] Decorrelating experience for 224 frames... [2023-03-09 12:31:46,840][270163] Decorrelating experience for 224 frames... [2023-03-09 12:31:46,842][270122] Decorrelating experience for 192 frames... [2023-03-09 12:31:46,842][270099] Decorrelating experience for 320 frames... [2023-03-09 12:31:46,875][270090] Decorrelating experience for 160 frames... [2023-03-09 12:31:46,895][270404] Decorrelating experience for 256 frames... [2023-03-09 12:31:46,934][270553] Decorrelating experience for 352 frames... [2023-03-09 12:31:46,934][270164] Decorrelating experience for 192 frames... [2023-03-09 12:31:46,958][270140] Decorrelating experience for 160 frames... [2023-03-09 12:31:47,031][271017] Decorrelating experience for 288 frames... [2023-03-09 12:31:47,040][270162] Decorrelating experience for 224 frames... [2023-03-09 12:31:47,040][270934] Decorrelating experience for 288 frames... [2023-03-09 12:31:47,041][270100] Decorrelating experience for 352 frames... [2023-03-09 12:31:47,069][271224] Decorrelating experience for 96 frames... [2023-03-09 12:31:47,087][270122] Decorrelating experience for 224 frames... [2023-03-09 12:31:47,140][269981] Decorrelating experience for 352 frames... [2023-03-09 12:31:47,140][270080] Decorrelating experience for 384 frames... [2023-03-09 12:31:47,142][270099] Decorrelating experience for 352 frames... [2023-03-09 12:31:47,158][270006] Decorrelating experience for 128 frames... [2023-03-09 12:31:47,210][270153] Decorrelating experience for 224 frames... [2023-03-09 12:31:47,238][270152] Decorrelating experience for 256 frames... [2023-03-09 12:31:47,239][270622] Decorrelating experience for 224 frames... [2023-03-09 12:31:47,273][270115] Decorrelating experience for 320 frames... [2023-03-09 12:31:47,287][270553] Decorrelating experience for 384 frames... [2023-03-09 12:31:47,313][270163] Decorrelating experience for 256 frames... [2023-03-09 12:31:47,322][270934] Decorrelating experience for 320 frames... [2023-03-09 12:31:47,333][271224] Decorrelating experience for 128 frames... [2023-03-09 12:31:47,336][270106] Decorrelating experience for 96 frames... [2023-03-09 12:31:47,437][270514] Decorrelating experience for 96 frames... [2023-03-09 12:31:47,443][270552] Decorrelating experience for 96 frames... [2023-03-09 12:31:47,461][271017] Decorrelating experience for 320 frames... [2023-03-09 12:31:47,482][270012] Decorrelating experience for 160 frames... [2023-03-09 12:31:47,490][270557] Decorrelating experience for 32 frames... [2023-03-09 12:31:47,493][271919] Decorrelating experience for 224 frames... [2023-03-09 12:31:47,533][270148] Decorrelating experience for 256 frames... [2023-03-09 12:31:47,535][270006] Decorrelating experience for 160 frames... [2023-03-09 12:31:47,539][270124] Decorrelating experience for 96 frames... [2023-03-09 12:31:47,613][270146] Decorrelating experience for 288 frames... [2023-03-09 12:31:47,639][270131] Decorrelating experience for 96 frames... [2023-03-09 12:31:47,645][269981] Decorrelating experience for 384 frames... [2023-03-09 12:31:47,666][270404] Decorrelating experience for 288 frames... [2023-03-09 12:31:47,680][270557] Decorrelating experience for 64 frames... [2023-03-09 12:31:47,683][270293] Decorrelating experience for 416 frames... [2023-03-09 12:31:47,689][270123] Decorrelating experience for 320 frames... [2023-03-09 12:31:47,725][270012] Decorrelating experience for 192 frames... [2023-03-09 12:31:47,726][270115] Decorrelating experience for 352 frames... [2023-03-09 12:31:47,735][270164] Decorrelating experience for 224 frames... [2023-03-09 12:31:47,788][270151] Decorrelating experience for 128 frames... [2023-03-09 12:31:47,815][270140] Decorrelating experience for 192 frames... [2023-03-09 12:31:47,846][270159] Decorrelating experience for 256 frames... [2023-03-09 12:31:47,851][270106] Decorrelating experience for 128 frames... [2023-03-09 12:31:47,861][270104] Decorrelating experience for 160 frames... [2023-03-09 12:31:47,878][270557] Decorrelating experience for 96 frames... [2023-03-09 12:31:47,892][270126] Decorrelating experience for 288 frames... [2023-03-09 12:31:47,904][270003] Decorrelating experience for 64 frames... [2023-03-09 12:31:47,906][270162] Decorrelating experience for 256 frames... [2023-03-09 12:31:47,941][270138] Decorrelating experience for 192 frames... [2023-03-09 12:31:47,969][270934] Decorrelating experience for 352 frames... [2023-03-09 12:31:47,991][270134] Decorrelating experience for 352 frames... [2023-03-09 12:31:48,037][270006] Decorrelating experience for 192 frames... [2023-03-09 12:31:48,042][270145] Decorrelating experience for 224 frames... [2023-03-09 12:31:48,053][270148] Decorrelating experience for 288 frames... [2023-03-09 12:31:48,073][270012] Decorrelating experience for 224 frames... [2023-03-09 12:31:48,081][270163] Decorrelating experience for 288 frames... [2023-03-09 12:31:48,098][270105] Decorrelating experience for 96 frames... [2023-03-09 12:31:48,098][270128] Decorrelating experience for 128 frames... [2023-03-09 12:31:48,154][270123] Decorrelating experience for 352 frames... [2023-03-09 12:31:48,169][270090] Decorrelating experience for 192 frames... [2023-03-09 12:31:48,207][270094] Decorrelating experience for 288 frames... [2023-03-09 12:31:48,214][270159] Decorrelating experience for 288 frames... [2023-03-09 12:31:48,227][270162] Decorrelating experience for 288 frames... [2023-03-09 12:31:48,265][270151] Decorrelating experience for 160 frames... [2023-03-09 12:31:48,277][270126] Decorrelating experience for 320 frames... [2023-03-09 12:31:48,293][270133] Decorrelating experience for 128 frames... [2023-03-09 12:31:48,332][270100] Decorrelating experience for 384 frames... [2023-03-09 12:31:48,339][270138] Decorrelating experience for 224 frames... [2023-03-09 12:31:48,345][270085] Decorrelating experience for 128 frames... [2023-03-09 12:31:48,396][270557] Decorrelating experience for 128 frames... [2023-03-09 12:31:48,398][270086] Decorrelating experience for 160 frames... [2023-03-09 12:31:48,406][270131] Decorrelating experience for 128 frames... [2023-03-09 12:31:48,455][270124] Decorrelating experience for 128 frames... [2023-03-09 12:31:48,483][270163] Decorrelating experience for 320 frames... [2023-03-09 12:31:48,494][270142] Decorrelating experience for 224 frames... [2023-03-09 12:31:48,498][270159] Decorrelating experience for 320 frames... [2023-03-09 12:31:48,515][270013] Decorrelating experience for 256 frames... [2023-03-09 12:31:48,521][270090] Decorrelating experience for 224 frames... [2023-03-09 12:31:48,523][270554] Decorrelating experience for 224 frames... [2023-03-09 12:31:48,573][270153] Decorrelating experience for 256 frames... [2023-03-09 12:31:48,596][277995] Decorrelating experience for 128 frames... [2023-03-09 12:31:48,635][270012] Decorrelating experience for 256 frames... [2023-03-09 12:31:48,653][270115] Decorrelating experience for 384 frames... [2023-03-09 12:31:48,660][270162] Decorrelating experience for 320 frames... [2023-03-09 12:31:48,684][270086] Decorrelating experience for 192 frames... [2023-03-09 12:31:48,698][270009] Decorrelating experience for 160 frames... [2023-03-09 12:31:48,703][270015] Decorrelating experience for 224 frames... [2023-03-09 12:31:48,705][270164] Decorrelating experience for 256 frames... [2023-03-09 12:31:48,748][270125] Decorrelating experience for 320 frames... [2023-03-09 12:31:48,781][270090] Decorrelating experience for 256 frames... [2023-03-09 12:31:48,799][270008] Decorrelating experience for 128 frames... [2023-03-09 12:31:48,811][270135] Decorrelating experience for 384 frames... [2023-03-09 12:31:48,842][270013] Decorrelating experience for 288 frames... [2023-03-09 12:31:48,859][270123] Decorrelating experience for 384 frames... [2023-03-09 12:31:48,876][270128] Decorrelating experience for 160 frames... [2023-03-09 12:31:48,893][270148] Decorrelating experience for 320 frames... [2023-03-09 12:31:48,932][270131] Decorrelating experience for 160 frames... [2023-03-09 12:31:48,947][270554] Decorrelating experience for 256 frames... [2023-03-09 12:31:48,964][270109] Decorrelating experience for 160 frames... [2023-03-09 12:31:48,998][270149] Decorrelating experience for 64 frames... [2023-03-09 12:31:49,030][270140] Decorrelating experience for 224 frames... [2023-03-09 12:31:49,043][270162] Decorrelating experience for 352 frames... [2023-03-09 12:31:49,053][270091] Decorrelating experience for 128 frames... [2023-03-09 12:31:49,069][270157] Decorrelating experience for 192 frames... [2023-03-09 12:31:49,085][270159] Decorrelating experience for 352 frames... [2023-03-09 12:31:49,127][270013] Decorrelating experience for 320 frames... [2023-03-09 12:31:49,130][270126] Decorrelating experience for 352 frames... [2023-03-09 12:31:49,149][270139] Decorrelating experience for 224 frames... [2023-03-09 12:31:49,178][270123] Decorrelating experience for 416 frames... [2023-03-09 12:31:49,179][270514] Decorrelating experience for 128 frames... [2023-03-09 12:31:49,220][270152] Decorrelating experience for 288 frames... [2023-03-09 12:31:49,236][270106] Decorrelating experience for 160 frames... [2023-03-09 12:31:49,238][270009] Decorrelating experience for 192 frames... [2023-03-09 12:31:49,246][270153] Decorrelating experience for 288 frames... [2023-03-09 12:31:49,266][271919] Decorrelating experience for 256 frames... [2023-03-09 12:31:49,321][270105] Decorrelating experience for 128 frames... [2023-03-09 12:31:49,331][270552] Decorrelating experience for 128 frames... [2023-03-09 12:31:49,334][270109] Decorrelating experience for 192 frames... [2023-03-09 12:31:49,362][270122] Decorrelating experience for 256 frames... [2023-03-09 12:31:49,363][270145] Decorrelating experience for 256 frames... [2023-03-09 12:31:49,402][270155] Decorrelating experience for 256 frames... [2023-03-09 12:31:49,418][270157] Decorrelating experience for 224 frames... [2023-03-09 12:31:49,427][270514] Decorrelating experience for 160 frames... [2023-03-09 12:31:49,436][270086] Decorrelating experience for 224 frames... [2023-03-09 12:31:49,448][270149] Decorrelating experience for 96 frames... [2023-03-09 12:31:49,500][270137] Decorrelating experience for 224 frames... [2023-03-09 12:31:49,512][270139] Decorrelating experience for 256 frames... [2023-03-09 12:31:49,542][270140] Decorrelating experience for 256 frames... [2023-03-09 12:31:49,553][271517] Decorrelating experience for 160 frames... [2023-03-09 12:31:49,557][270012] Decorrelating experience for 288 frames... [2023-03-09 12:31:49,593][271919] Decorrelating experience for 288 frames... [2023-03-09 12:31:49,599][270125] Decorrelating experience for 352 frames... [2023-03-09 12:31:49,603][270160] Decorrelating experience for 352 frames... [2023-03-09 12:31:49,649][270122] Decorrelating experience for 288 frames... [2023-03-09 12:31:49,691][270552] Decorrelating experience for 160 frames... [2023-03-09 12:31:49,710][270152] Decorrelating experience for 320 frames... [2023-03-09 12:31:49,712][270104] Decorrelating experience for 192 frames... [2023-03-09 12:31:49,723][270163] Decorrelating experience for 352 frames... [2023-03-09 12:31:49,728][270557] Decorrelating experience for 160 frames... [2023-03-09 12:31:49,754][270089] Decorrelating experience for 96 frames... [2023-03-09 12:31:49,774][269981] Decorrelating experience for 416 frames... [2023-03-09 12:31:49,784][270164] Decorrelating experience for 288 frames... [2023-03-09 12:31:49,829][277995] Decorrelating experience for 160 frames... [2023-03-09 12:31:49,839][270126] Decorrelating experience for 384 frames... [2023-03-09 12:31:49,900][270094] Decorrelating experience for 320 frames... [2023-03-09 12:31:49,909][270111] Decorrelating experience for 192 frames... [2023-03-09 12:31:49,910][270143] Decorrelating experience for 160 frames... [2023-03-09 12:31:49,915][270117] Decorrelating experience for 96 frames... [2023-03-09 12:31:49,934][271517] Decorrelating experience for 192 frames... [2023-03-09 12:31:49,982][269569] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 2500018176. Throughput: 0: 0.0. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) [2023-03-09 12:31:50,009][270127] Decorrelating experience for 96 frames... [2023-03-09 12:31:50,022][271224] Decorrelating experience for 160 frames... [2023-03-09 12:31:50,027][270130] Decorrelating experience for 160 frames... [2023-03-09 12:31:50,036][270596] Decorrelating experience for 128 frames... [2023-03-09 12:31:50,037][270016] Decorrelating experience for 256 frames... [2023-03-09 12:31:50,082][270163] Decorrelating experience for 384 frames... [2023-03-09 12:31:50,089][270009] Decorrelating experience for 224 frames... [2023-03-09 12:31:50,093][270124] Decorrelating experience for 160 frames... [2023-03-09 12:31:50,118][270164] Decorrelating experience for 320 frames... [2023-03-09 12:31:50,122][270943] Decorrelating experience for 192 frames... [2023-03-09 12:31:50,196][270159] Decorrelating experience for 384 frames... [2023-03-09 12:31:50,211][270233] Decorrelating experience for 96 frames... [2023-03-09 12:31:50,217][270107] Decorrelating experience for 160 frames... [2023-03-09 12:31:50,220][270118] Decorrelating experience for 160 frames... [2023-03-09 12:31:50,221][270128] Decorrelating experience for 192 frames... [2023-03-09 12:31:50,257][270090] Decorrelating experience for 288 frames... [2023-03-09 12:31:50,273][270015] Decorrelating experience for 256 frames... [2023-03-09 12:31:50,279][270120] Decorrelating experience for 192 frames... [2023-03-09 12:31:50,296][270143] Decorrelating experience for 192 frames... [2023-03-09 12:31:50,378][270080] Decorrelating experience for 416 frames... [2023-03-09 12:31:50,419][271517] Decorrelating experience for 224 frames... [2023-03-09 12:31:50,420][271224] Decorrelating experience for 192 frames... [2023-03-09 12:31:50,421][270144] Decorrelating experience for 160 frames... [2023-03-09 12:31:50,421][270010] Decorrelating experience for 96 frames... [2023-03-09 12:31:50,446][270094] Decorrelating experience for 352 frames... [2023-03-09 12:31:50,458][269981] Decorrelating experience for 448 frames... [2023-03-09 12:31:50,490][270145] Decorrelating experience for 288 frames... [2023-03-09 12:31:50,492][270472] Decorrelating experience for 96 frames... [2023-03-09 12:31:50,556][270368] Decorrelating experience for 288 frames... [2023-03-09 12:31:50,606][270107] Decorrelating experience for 192 frames... [2023-03-09 12:31:50,611][270126] Decorrelating experience for 416 frames... [2023-03-09 12:31:50,614][270623] Decorrelating experience for 0 frames... [2023-03-09 12:31:50,644][270085] Decorrelating experience for 160 frames... [2023-03-09 12:31:50,644][270008] Decorrelating experience for 160 frames... [2023-03-09 12:31:50,644][270010] Decorrelating experience for 128 frames... [2023-03-09 12:31:50,666][270104] Decorrelating experience for 224 frames... [2023-03-09 12:31:50,671][270943] Decorrelating experience for 224 frames... [2023-03-09 12:31:50,686][270140] Decorrelating experience for 288 frames... [2023-03-09 12:31:50,731][270552] Decorrelating experience for 192 frames... [2023-03-09 12:31:50,792][270139] Decorrelating experience for 288 frames... [2023-03-09 12:31:50,807][270472] Decorrelating experience for 128 frames... [2023-03-09 12:31:50,814][270146] Decorrelating experience for 320 frames... [2023-03-09 12:31:50,853][269981] Decorrelating experience for 480 frames... [2023-03-09 12:31:50,855][270009] Decorrelating experience for 256 frames... [2023-03-09 12:31:50,867][270125] Decorrelating experience for 384 frames... [2023-03-09 12:31:50,868][270158] Decorrelating experience for 256 frames... [2023-03-09 12:31:50,905][271017] Decorrelating experience for 352 frames... [2023-03-09 12:31:50,906][270145] Decorrelating experience for 320 frames... [2023-03-09 12:31:50,909][270097] Decorrelating experience for 288 frames... [2023-03-09 12:31:50,970][277995] Decorrelating experience for 192 frames... [2023-03-09 12:31:50,984][270293] Decorrelating experience for 448 frames... [2023-03-09 12:31:51,012][270111] Decorrelating experience for 224 frames... [2023-03-09 12:31:51,033][270085] Decorrelating experience for 192 frames... [2023-03-09 12:31:51,074][270090] Decorrelating experience for 320 frames... [2023-03-09 12:31:51,076][270010] Decorrelating experience for 160 frames... [2023-03-09 12:31:51,077][270005] Decorrelating experience for 96 frames... [2023-03-09 12:31:51,082][270101] Decorrelating experience for 96 frames... [2023-03-09 12:31:51,094][270153] Decorrelating experience for 320 frames... [2023-03-09 12:31:51,111][270144] Decorrelating experience for 192 frames... [2023-03-09 12:31:51,170][270473] Decorrelating experience for 128 frames... [2023-03-09 12:31:51,190][270097] Decorrelating experience for 320 frames... [2023-03-09 12:31:51,217][270137] Decorrelating experience for 256 frames... [2023-03-09 12:31:51,233][270152] Decorrelating experience for 352 frames... [2023-03-09 12:31:51,258][270148] Decorrelating experience for 352 frames... [2023-03-09 12:31:51,259][269981] Decorrelating experience for 512 frames... [2023-03-09 12:31:51,269][270118] Decorrelating experience for 192 frames... [2023-03-09 12:31:51,274][270111] Decorrelating experience for 256 frames... [2023-03-09 12:31:51,304][271224] Decorrelating experience for 224 frames... [2023-03-09 12:31:51,362][270010] Decorrelating experience for 192 frames... [2023-03-09 12:31:51,368][270134] Decorrelating experience for 384 frames... [2023-03-09 12:31:51,394][270126] Decorrelating experience for 448 frames... [2023-03-09 12:31:51,412][270098] Decorrelating experience for 64 frames... [2023-03-09 12:31:51,433][270121] Decorrelating experience for 384 frames... [2023-03-09 12:31:51,438][270157] Decorrelating experience for 256 frames... [2023-03-09 12:31:51,447][270109] Decorrelating experience for 224 frames... [2023-03-09 12:31:51,453][270094] Decorrelating experience for 384 frames... [2023-03-09 12:31:51,466][270153] Decorrelating experience for 352 frames... [2023-03-09 12:31:51,483][270097] Decorrelating experience for 352 frames... [2023-03-09 12:31:51,546][270596] Decorrelating experience for 160 frames... [2023-03-09 12:31:51,591][270142] Decorrelating experience for 256 frames... [2023-03-09 12:31:51,613][270145] Decorrelating experience for 352 frames... [2023-03-09 12:31:51,621][270108] Decorrelating experience for 256 frames... [2023-03-09 12:31:51,622][270118] Decorrelating experience for 224 frames... [2023-03-09 12:31:51,627][270159] Decorrelating experience for 416 frames... [2023-03-09 12:31:51,630][270015] Decorrelating experience for 288 frames... [2023-03-09 12:31:51,655][271224] Decorrelating experience for 256 frames... [2023-03-09 12:31:51,676][270144] Decorrelating experience for 224 frames... [2023-03-09 12:31:51,677][270140] Decorrelating experience for 320 frames... [2023-03-09 12:31:51,724][270130] Decorrelating experience for 192 frames... [2023-03-09 12:31:51,799][270091] Decorrelating experience for 160 frames... [2023-03-09 12:31:51,810][270163] Decorrelating experience for 416 frames... [2023-03-09 12:31:51,829][271375] Decorrelating experience for 160 frames... [2023-03-09 12:31:51,832][271017] Decorrelating experience for 384 frames... [2023-03-09 12:31:51,835][269981] Decorrelating experience for 544 frames... [2023-03-09 12:31:51,841][270134] Decorrelating experience for 416 frames... [2023-03-09 12:31:51,873][270080] Decorrelating experience for 448 frames... [2023-03-09 12:31:51,874][270153] Decorrelating experience for 384 frames... [2023-03-09 12:31:51,928][270557] Decorrelating experience for 192 frames... [2023-03-09 12:31:51,929][270157] Decorrelating experience for 288 frames... [2023-03-09 12:31:51,942][270129] Another process currently holds the lock /tmp/sf2_rolo/doom_004.lockfile, attempt: 1 [2023-03-09 12:31:51,978][270162] Decorrelating experience for 384 frames... [2023-03-09 12:31:52,010][270159] Decorrelating experience for 448 frames... [2023-03-09 12:31:52,016][270010] Decorrelating experience for 224 frames... [2023-03-09 12:31:52,021][271126] Decorrelating experience for 224 frames... [2023-03-09 12:31:52,025][270140] Decorrelating experience for 352 frames... [2023-03-09 12:31:52,056][270143] Decorrelating experience for 224 frames... [2023-03-09 12:31:52,061][270142] Decorrelating experience for 288 frames... [2023-03-09 12:31:52,083][270122] Decorrelating experience for 320 frames... [2023-03-09 12:31:52,133][270128] Decorrelating experience for 224 frames... [2023-03-09 12:31:52,136][270104] Decorrelating experience for 256 frames... [2023-03-09 12:31:52,162][270086] Decorrelating experience for 256 frames... [2023-03-09 12:31:52,188][270008] Decorrelating experience for 192 frames... [2023-03-09 12:31:52,205][270943] Decorrelating experience for 256 frames... [2023-03-09 12:31:52,206][270121] Decorrelating experience for 416 frames... [2023-03-09 12:31:52,239][270233] Decorrelating experience for 128 frames... [2023-03-09 12:31:52,244][270127] Decorrelating experience for 128 frames... [2023-03-09 12:31:52,246][270109] Decorrelating experience for 256 frames... [2023-03-09 12:31:52,273][270157] Decorrelating experience for 320 frames... [2023-03-09 12:31:52,338][270118] Decorrelating experience for 256 frames... [2023-03-09 12:31:52,342][270120] Decorrelating experience for 224 frames... [2023-03-09 12:31:52,368][270137] Decorrelating experience for 288 frames... [2023-03-09 12:31:52,381][270088] Decorrelating experience for 256 frames... [2023-03-09 12:31:52,386][271126] Decorrelating experience for 256 frames... [2023-03-09 12:31:52,430][270103] Decorrelating experience for 32 frames... [2023-03-09 12:31:52,431][270148] Decorrelating experience for 384 frames... [2023-03-09 12:31:52,432][270090] Decorrelating experience for 352 frames... [2023-03-09 12:31:52,465][270153] Decorrelating experience for 416 frames... [2023-03-09 12:31:52,468][270233] Decorrelating experience for 160 frames... [2023-03-09 12:31:52,523][271355] Decorrelating experience for 192 frames... [2023-03-09 12:31:52,544][270113] Decorrelating experience for 256 frames... [2023-03-09 12:31:52,569][270127] Decorrelating experience for 160 frames... [2023-03-09 12:31:52,583][270122] Decorrelating experience for 352 frames... [2023-03-09 12:31:52,622][270015] Decorrelating experience for 320 frames... [2023-03-09 12:31:52,623][270109] Decorrelating experience for 288 frames... [2023-03-09 12:31:52,632][270107] Decorrelating experience for 224 frames... [2023-03-09 12:31:52,648][270098] Decorrelating experience for 96 frames... [2023-03-09 12:31:52,658][270120] Decorrelating experience for 256 frames... [2023-03-09 12:31:52,659][270137] Decorrelating experience for 320 frames... [2023-03-09 12:31:52,701][270111] Decorrelating experience for 288 frames... [2023-03-09 12:31:52,728][270134] Decorrelating experience for 448 frames... [2023-03-09 12:31:52,788][270553] Decorrelating experience for 416 frames... [2023-03-09 12:31:52,801][271126] Decorrelating experience for 288 frames... [2023-03-09 12:31:52,802][270016] Decorrelating experience for 288 frames... [2023-03-09 12:31:52,830][270556] Decorrelating experience for 224 frames... [2023-03-09 12:31:52,833][271375] Decorrelating experience for 192 frames... [2023-03-09 12:31:52,837][270010] Decorrelating experience for 256 frames... [2023-03-09 12:31:52,840][270089] Decorrelating experience for 128 frames... [2023-03-09 12:31:52,852][270148] Decorrelating experience for 416 frames... [2023-03-09 12:31:52,878][270943] Decorrelating experience for 288 frames... [2023-03-09 12:31:52,914][270473] Decorrelating experience for 160 frames... [2023-03-09 12:31:52,966][270015] Decorrelating experience for 352 frames... [2023-03-09 12:31:52,984][270127] Decorrelating experience for 192 frames... [2023-03-09 12:31:52,986][270160] Decorrelating experience for 384 frames... [2023-03-09 12:31:53,007][270623] Decorrelating experience for 32 frames... [2023-03-09 12:31:53,027][270944] Decorrelating experience for 384 frames... [2023-03-09 12:31:53,033][270162] Decorrelating experience for 416 frames... [2023-03-09 12:31:53,038][270149] Decorrelating experience for 128 frames... [2023-03-09 12:31:53,051][270098] Decorrelating experience for 128 frames... [2023-03-09 12:31:53,058][271017] Decorrelating experience for 416 frames... [2023-03-09 12:31:53,090][270122] Decorrelating experience for 384 frames... [2023-03-09 12:31:53,142][270131] Decorrelating experience for 192 frames... [2023-03-09 12:31:53,175][270157] Decorrelating experience for 352 frames... [2023-03-09 12:31:53,193][270556] Decorrelating experience for 256 frames... [2023-03-09 12:31:53,195][270141] Decorrelating experience for 320 frames... [2023-03-09 12:31:53,229][271355] Decorrelating experience for 224 frames... [2023-03-09 12:31:53,235][270120] Decorrelating experience for 288 frames... [2023-03-09 12:31:53,242][270016] Decorrelating experience for 320 frames... [2023-03-09 12:31:53,244][270293] Decorrelating experience for 480 frames... [2023-03-09 12:31:53,248][270623] Decorrelating experience for 64 frames... [2023-03-09 12:31:53,271][270134] Decorrelating experience for 480 frames... [2023-03-09 12:31:53,343][270944] Decorrelating experience for 416 frames... [2023-03-09 12:31:53,374][270015] Decorrelating experience for 384 frames... [2023-03-09 12:31:53,378][270541] Decorrelating experience for 32 frames... [2023-03-09 12:31:53,388][270131] Decorrelating experience for 224 frames... [2023-03-09 12:31:53,400][270555] Another process currently holds the lock /tmp/sf2_rolo/doom_004.lockfile, attempt: 1 [2023-03-09 12:31:53,406][270160] Decorrelating experience for 416 frames... [2023-03-09 12:31:53,422][270553] Decorrelating experience for 448 frames... [2023-03-09 12:31:53,432][270098] Decorrelating experience for 160 frames... [2023-03-09 12:31:53,444][270008] Decorrelating experience for 224 frames... [2023-03-09 12:31:53,445][270105] Decorrelating experience for 160 frames... [2023-03-09 12:31:53,459][270233] Decorrelating experience for 192 frames... [2023-03-09 12:31:53,534][270157] Decorrelating experience for 384 frames... [2023-03-09 12:31:53,559][270122] Decorrelating experience for 416 frames... [2023-03-09 12:31:53,591][271017] Decorrelating experience for 448 frames... [2023-03-09 12:31:53,598][270141] Decorrelating experience for 352 frames... [2023-03-09 12:31:53,598][270125] Decorrelating experience for 416 frames... [2023-03-09 12:31:53,612][270109] Decorrelating experience for 320 frames... [2023-03-09 12:31:53,618][270541] Decorrelating experience for 64 frames... [2023-03-09 12:31:53,623][270142] Decorrelating experience for 320 frames... [2023-03-09 12:31:53,642][270514] Decorrelating experience for 192 frames... [2023-03-09 12:31:53,648][270552] Decorrelating experience for 224 frames... [2023-03-09 12:31:53,720][270153] Decorrelating experience for 448 frames... [2023-03-09 12:31:53,741][270404] Decorrelating experience for 320 frames... [2023-03-09 12:31:53,781][270143] Decorrelating experience for 256 frames... [2023-03-09 12:31:53,792][270160] Decorrelating experience for 448 frames... [2023-03-09 12:31:53,795][270015] Decorrelating experience for 416 frames... [2023-03-09 12:31:53,798][270126] Decorrelating experience for 480 frames... [2023-03-09 12:31:53,803][270108] Decorrelating experience for 288 frames... [2023-03-09 12:31:53,810][270092] Decorrelating experience for 128 frames... [2023-03-09 12:31:53,826][270134] Decorrelating experience for 512 frames... [2023-03-09 12:31:53,835][270130] Decorrelating experience for 224 frames... [2023-03-09 12:31:53,920][270098] Decorrelating experience for 192 frames... [2023-03-09 12:31:53,944][270293] Decorrelating experience for 512 frames... [2023-03-09 12:31:53,965][270141] Decorrelating experience for 384 frames... [2023-03-09 12:31:53,985][270150] Decorrelating experience for 128 frames... [2023-03-09 12:31:53,993][270127] Decorrelating experience for 224 frames... [2023-03-09 12:31:54,000][270122] Decorrelating experience for 448 frames... [2023-03-09 12:31:54,002][270086] Decorrelating experience for 288 frames... [2023-03-09 12:31:54,019][270552] Decorrelating experience for 256 frames... [2023-03-09 12:31:54,021][270142] Decorrelating experience for 352 frames... [2023-03-09 12:31:54,025][270085] Decorrelating experience for 224 frames... [2023-03-09 12:31:54,100][270116] Decorrelating experience for 256 frames... [2023-03-09 12:31:54,120][270089] Decorrelating experience for 160 frames... [2023-03-09 12:31:54,147][270003] Decorrelating experience for 96 frames... [2023-03-09 12:31:54,163][270135] Decorrelating experience for 416 frames... [2023-03-09 12:31:54,191][270114] Decorrelating experience for 416 frames... [2023-03-09 12:31:54,192][270108] Decorrelating experience for 320 frames... [2023-03-09 12:31:54,200][270130] Decorrelating experience for 256 frames... [2023-03-09 12:31:54,201][270090] Decorrelating experience for 384 frames... [2023-03-09 12:31:54,205][270139] Decorrelating experience for 320 frames... [2023-03-09 12:31:54,218][270159] Decorrelating experience for 480 frames... [2023-03-09 12:31:54,284][270165] Decorrelating experience for 128 frames... [2023-03-09 12:31:54,328][270015] Decorrelating experience for 448 frames... [2023-03-09 12:31:54,341][270106] Decorrelating experience for 192 frames... [2023-03-09 12:31:54,343][271355] Decorrelating experience for 256 frames... [2023-03-09 12:31:54,367][270553] Decorrelating experience for 480 frames... [2023-03-09 12:31:54,393][270085] Decorrelating experience for 256 frames... [2023-03-09 12:31:54,396][271375] Decorrelating experience for 224 frames... [2023-03-09 12:31:54,400][270122] Decorrelating experience for 480 frames... [2023-03-09 12:31:54,402][270134] Decorrelating experience for 544 frames... [2023-03-09 12:31:54,454][270160] Decorrelating experience for 480 frames... [2023-03-09 12:31:54,462][270117] Decorrelating experience for 128 frames... [2023-03-09 12:31:54,505][270092] Decorrelating experience for 160 frames... [2023-03-09 12:31:54,524][270090] Decorrelating experience for 416 frames... [2023-03-09 12:31:54,526][270098] Decorrelating experience for 224 frames... [2023-03-09 12:31:54,546][270095] Decorrelating experience for 160 frames... [2023-03-09 12:31:54,579][270142] Decorrelating experience for 384 frames... [2023-03-09 12:31:54,602][270135] Decorrelating experience for 448 frames... [2023-03-09 12:31:54,606][270084] Decorrelating experience for 224 frames... [2023-03-09 12:31:54,607][270111] Decorrelating experience for 320 frames... [2023-03-09 12:31:54,639][270086] Decorrelating experience for 320 frames... [2023-03-09 12:31:54,654][270139] Decorrelating experience for 352 frames... [2023-03-09 12:31:54,685][270103] Decorrelating experience for 64 frames... [2023-03-09 12:31:54,703][270163] Decorrelating experience for 448 frames... [2023-03-09 12:31:54,711][270473] Decorrelating experience for 192 frames... [2023-03-09 12:31:54,744][270101] Decorrelating experience for 128 frames... [2023-03-09 12:31:54,762][270293] Decorrelating experience for 544 frames... [2023-03-09 12:31:54,783][270134] Decorrelating experience for 576 frames... [2023-03-09 12:31:54,787][270095] Decorrelating experience for 192 frames... [2023-03-09 12:31:54,802][270009] Decorrelating experience for 288 frames... [2023-03-09 12:31:54,825][270010] Decorrelating experience for 288 frames... [2023-03-09 12:31:54,886][270751] Decorrelating experience for 128 frames... [2023-03-09 12:31:54,896][270141] Decorrelating experience for 416 frames... [2023-03-09 12:31:54,923][270149] Decorrelating experience for 160 frames... [2023-03-09 12:31:54,932][270158] Decorrelating experience for 288 frames... [2023-03-09 12:31:54,956][270093] Decorrelating experience for 192 frames... [2023-03-09 12:31:54,970][271355] Decorrelating experience for 288 frames... [2023-03-09 12:31:54,982][269569] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 2500018176. Throughput: 0: 0.0. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) [2023-03-09 12:31:55,012][270596] Decorrelating experience for 192 frames... [2023-03-09 12:31:55,015][270090] Decorrelating experience for 448 frames... [2023-03-09 12:31:55,021][270092] Decorrelating experience for 192 frames... [2023-03-09 12:31:55,033][270086] Decorrelating experience for 352 frames... [2023-03-09 12:31:55,065][270139] Decorrelating experience for 384 frames... [2023-03-09 12:31:55,089][270009] Decorrelating experience for 320 frames... [2023-03-09 12:31:55,108][270091] Decorrelating experience for 192 frames... [2023-03-09 12:31:55,112][270126] Decorrelating experience for 512 frames... [2023-03-09 12:31:55,142][270699] Decorrelating experience for 224 frames... [2023-03-09 12:31:55,148][271224] Decorrelating experience for 288 frames... [2023-03-09 12:31:55,174][270156] Another process currently holds the lock /tmp/sf2_rolo/doom_004.lockfile, attempt: 1 [2023-03-09 12:31:55,197][270404] Decorrelating experience for 352 frames... [2023-03-09 12:31:55,207][270135] Decorrelating experience for 480 frames... [2023-03-09 12:31:55,211][269981] Decorrelating experience for 576 frames... [2023-03-09 12:31:55,217][270150] Decorrelating experience for 160 frames... [2023-03-09 12:31:55,248][270100] Decorrelating experience for 416 frames... [2023-03-09 12:31:55,271][270128] Decorrelating experience for 256 frames... [2023-03-09 12:31:55,325][270162] Decorrelating experience for 448 frames... [2023-03-09 12:31:55,338][270095] Decorrelating experience for 224 frames... [2023-03-09 12:31:55,367][270161] Decorrelating experience for 192 frames... [2023-03-09 12:31:55,367][270108] Decorrelating experience for 352 frames... [2023-03-09 12:31:55,376][270134] Decorrelating experience for 608 frames... [2023-03-09 12:31:55,443][270098] Decorrelating experience for 256 frames... [2023-03-09 12:31:55,462][270122] Decorrelating experience for 512 frames... [2023-03-09 12:31:55,486][270142] Decorrelating experience for 416 frames... [2023-03-09 12:31:55,487][270158] Decorrelating experience for 320 frames... [2023-03-09 12:31:55,487][270086] Decorrelating experience for 384 frames... [2023-03-09 12:31:55,510][271355] Decorrelating experience for 320 frames... [2023-03-09 12:31:55,519][270124] Decorrelating experience for 192 frames... [2023-03-09 12:31:55,551][270148] Decorrelating experience for 448 frames... [2023-03-09 12:31:55,552][270164] Decorrelating experience for 352 frames... [2023-03-09 12:31:55,568][270293] Decorrelating experience for 576 frames... [2023-03-09 12:31:55,656][270699] Decorrelating experience for 256 frames... [2023-03-09 12:31:55,673][270008] Decorrelating experience for 256 frames... [2023-03-09 12:31:55,679][270103] Decorrelating experience for 96 frames... [2023-03-09 12:31:55,696][270011] Decorrelating experience for 64 frames... [2023-03-09 12:31:55,711][270016] Decorrelating experience for 352 frames... [2023-03-09 12:31:55,736][270116] Decorrelating experience for 288 frames... [2023-03-09 12:31:55,739][270162] Decorrelating experience for 480 frames... [2023-03-09 12:31:55,742][270109] Decorrelating experience for 352 frames... [2023-03-09 12:31:55,767][270098] Decorrelating experience for 288 frames... [2023-03-09 12:31:55,780][270126] Decorrelating experience for 544 frames... [2023-03-09 12:31:55,864][270111] Decorrelating experience for 352 frames... [2023-03-09 12:31:55,868][270010] Decorrelating experience for 320 frames... [2023-03-09 12:31:55,881][270104] Decorrelating experience for 288 frames... [2023-03-09 12:31:55,909][270514] Decorrelating experience for 224 frames... [2023-03-09 12:31:55,922][270086] Decorrelating experience for 416 frames... [2023-03-09 12:31:55,925][270165] Decorrelating experience for 160 frames... [2023-03-09 12:31:55,927][270124] Decorrelating experience for 224 frames... [2023-03-09 12:31:55,941][270596] Decorrelating experience for 224 frames... [2023-03-09 12:31:55,947][270008] Decorrelating experience for 288 frames... [2023-03-09 12:31:55,962][270013] Decorrelating experience for 352 frames... [2023-03-09 12:31:56,060][271355] Decorrelating experience for 352 frames... [2023-03-09 12:31:56,068][270115] Decorrelating experience for 416 frames... [2023-03-09 12:31:56,093][270009] Decorrelating experience for 352 frames... [2023-03-09 12:31:56,099][277995] Decorrelating experience for 224 frames... [2023-03-09 12:31:56,107][270098] Decorrelating experience for 320 frames... [2023-03-09 12:31:56,112][270016] Decorrelating experience for 384 frames... [2023-03-09 12:31:56,133][270084] Decorrelating experience for 256 frames... [2023-03-09 12:31:56,134][270103] Decorrelating experience for 128 frames... [2023-03-09 12:31:56,141][270135] Decorrelating experience for 512 frames... [2023-03-09 12:31:56,148][270138] Decorrelating experience for 256 frames... [2023-03-09 12:31:56,239][270944] Decorrelating experience for 448 frames... [2023-03-09 12:31:56,274][270157] Decorrelating experience for 416 frames... [2023-03-09 12:31:56,277][270089] Decorrelating experience for 192 frames... [2023-03-09 12:31:56,281][270007] Decorrelating experience for 256 frames... [2023-03-09 12:31:56,299][270124] Decorrelating experience for 256 frames... [2023-03-09 12:31:56,302][270128] Decorrelating experience for 288 frames... [2023-03-09 12:31:56,317][270121] Decorrelating experience for 448 frames... [2023-03-09 12:31:56,319][270293] Decorrelating experience for 608 frames... [2023-03-09 12:31:56,342][270141] Decorrelating experience for 448 frames... [2023-03-09 12:31:56,355][270155] Decorrelating experience for 288 frames... [2023-03-09 12:31:56,373][270119] Another process currently holds the lock /tmp/sf2_rolo/doom_009.lockfile, attempt: 1 [2023-03-09 12:31:56,416][270088] Decorrelating experience for 288 frames... [2023-03-09 12:31:56,458][270156] Decorrelating experience for 64 frames... [2023-03-09 12:31:56,460][270127] Decorrelating experience for 256 frames... [2023-03-09 12:31:56,480][269981] Decorrelating experience for 608 frames... [2023-03-09 12:31:56,493][270100] Decorrelating experience for 448 frames... [2023-03-09 12:31:56,504][270158] Decorrelating experience for 352 frames... [2023-03-09 12:31:56,507][270117] Decorrelating experience for 160 frames... [2023-03-09 12:31:56,508][270115] Decorrelating experience for 448 frames... [2023-03-09 12:31:56,520][270138] Decorrelating experience for 288 frames... [2023-03-09 12:31:56,533][270097] Decorrelating experience for 384 frames... [2023-03-09 12:31:56,592][270113] Decorrelating experience for 288 frames... [2023-03-09 12:31:56,645][270120] Decorrelating experience for 320 frames... [2023-03-09 12:31:56,659][270150] Decorrelating experience for 192 frames... [2023-03-09 12:31:56,688][270016] Decorrelating experience for 416 frames... [2023-03-09 12:31:56,709][270751] Decorrelating experience for 160 frames... [2023-03-09 12:31:56,711][270107] Decorrelating experience for 256 frames... [2023-03-09 12:31:56,712][270009] Decorrelating experience for 384 frames... [2023-03-09 12:31:56,727][270130] Decorrelating experience for 288 frames... [2023-03-09 12:31:56,728][271126] Decorrelating experience for 320 frames... [2023-03-09 12:31:56,767][270163] Decorrelating experience for 480 frames... [2023-03-09 12:31:56,839][271517] Decorrelating experience for 256 frames... [2023-03-09 12:31:56,840][270134] Decorrelating experience for 640 frames... [2023-03-09 12:31:56,848][270142] Decorrelating experience for 448 frames... [2023-03-09 12:31:56,895][271224] Decorrelating experience for 320 frames... [2023-03-09 12:31:56,899][270117] Decorrelating experience for 192 frames... [2023-03-09 12:31:56,915][270699] Decorrelating experience for 288 frames... [2023-03-09 12:31:56,918][270157] Decorrelating experience for 448 frames... [2023-03-09 12:31:56,919][270161] Decorrelating experience for 224 frames... [2023-03-09 12:31:56,936][270127] Decorrelating experience for 288 frames... [2023-03-09 12:31:56,964][270096] Decorrelating experience for 384 frames... [2023-03-09 12:31:57,027][270164] Decorrelating experience for 384 frames... [2023-03-09 12:31:57,027][270934] Decorrelating experience for 384 frames... [2023-03-09 12:31:57,029][270111] Decorrelating experience for 384 frames... [2023-03-09 12:31:57,079][270623] Decorrelating experience for 96 frames... [2023-03-09 12:31:57,085][270085] Decorrelating experience for 288 frames... [2023-03-09 12:31:57,102][270139] Decorrelating experience for 416 frames... [2023-03-09 12:31:57,117][270158] Decorrelating experience for 384 frames... [2023-03-09 12:31:57,128][270473] Decorrelating experience for 224 frames... [2023-03-09 12:31:57,133][270115] Decorrelating experience for 480 frames... [2023-03-09 12:31:57,150][270117] Decorrelating experience for 224 frames... [2023-03-09 12:31:57,208][270145] Decorrelating experience for 384 frames... [2023-03-09 12:31:57,222][270090] Decorrelating experience for 480 frames... [2023-03-09 12:31:57,270][270094] Decorrelating experience for 416 frames... [2023-03-09 12:31:57,271][270404] Decorrelating experience for 384 frames... [2023-03-09 12:31:57,272][270514] Decorrelating experience for 256 frames... [2023-03-09 12:31:57,322][270016] Decorrelating experience for 448 frames... [2023-03-09 12:31:57,336][270143] Decorrelating experience for 288 frames... [2023-03-09 12:31:57,337][270161] Decorrelating experience for 256 frames... [2023-03-09 12:31:57,344][270126] Decorrelating experience for 576 frames... [2023-03-09 12:31:57,388][270103] Decorrelating experience for 160 frames... [2023-03-09 12:31:57,411][270088] Decorrelating experience for 320 frames... [2023-03-09 12:31:57,453][270155] Decorrelating experience for 320 frames... [2023-03-09 12:31:57,459][270148] Decorrelating experience for 480 frames... [2023-03-09 12:31:57,462][270152] Decorrelating experience for 384 frames... [2023-03-09 12:31:57,465][270138] Decorrelating experience for 320 frames... [2023-03-09 12:31:57,519][270120] Decorrelating experience for 352 frames... [2023-03-09 12:31:57,526][270091] Decorrelating experience for 224 frames... [2023-03-09 12:31:57,545][270015] Decorrelating experience for 480 frames... [2023-03-09 12:31:57,547][270128] Decorrelating experience for 320 frames... [2023-03-09 12:31:57,573][270127] Decorrelating experience for 320 frames... [2023-03-09 12:31:57,594][270100] Decorrelating experience for 480 frames... [2023-03-09 12:31:57,642][270124] Decorrelating experience for 288 frames... [2023-03-09 12:31:57,645][270158] Decorrelating experience for 416 frames... [2023-03-09 12:31:57,648][270008] Decorrelating experience for 320 frames... [2023-03-09 12:31:57,663][270095] Decorrelating experience for 256 frames... [2023-03-09 12:31:57,701][270934] Decorrelating experience for 416 frames... [2023-03-09 12:31:57,707][270159] Decorrelating experience for 512 frames... [2023-03-09 12:31:57,742][270122] Decorrelating experience for 544 frames... [2023-03-09 12:31:57,753][270751] Decorrelating experience for 192 frames... [2023-03-09 12:31:57,775][270085] Decorrelating experience for 320 frames... [2023-03-09 12:31:57,782][270126] Decorrelating experience for 608 frames... [2023-03-09 12:31:57,833][270006] Decorrelating experience for 224 frames... [2023-03-09 12:31:57,837][270013] Decorrelating experience for 384 frames... [2023-03-09 12:31:57,848][270128] Decorrelating experience for 352 frames... [2023-03-09 12:31:57,874][270472] Decorrelating experience for 160 frames... [2023-03-09 12:31:57,892][270133] Decorrelating experience for 160 frames... [2023-03-09 12:31:57,895][270596] Decorrelating experience for 256 frames... [2023-03-09 12:31:57,932][270113] Decorrelating experience for 320 frames... [2023-03-09 12:31:57,975][270084] Decorrelating experience for 288 frames... [2023-03-09 12:31:57,981][270120] Decorrelating experience for 384 frames... [2023-03-09 12:31:58,020][270134] Decorrelating experience for 672 frames... [2023-03-09 12:31:58,020][270117] Decorrelating experience for 256 frames... [2023-03-09 12:31:58,034][270103] Decorrelating experience for 192 frames... [2023-03-09 12:31:58,038][270009] Decorrelating experience for 416 frames... [2023-03-09 12:31:58,077][270109] Decorrelating experience for 384 frames... [2023-03-09 12:31:58,094][270552] Decorrelating experience for 288 frames... [2023-03-09 12:31:58,127][270159] Decorrelating experience for 544 frames... [2023-03-09 12:31:58,128][270155] Decorrelating experience for 352 frames... [2023-03-09 12:31:58,156][270751] Decorrelating experience for 224 frames... [2023-03-09 12:31:58,159][270472] Decorrelating experience for 192 frames... [2023-03-09 12:31:58,201][270142] Decorrelating experience for 480 frames... [2023-03-09 12:31:58,223][270150] Decorrelating experience for 224 frames... [2023-03-09 12:31:58,229][270080] Decorrelating experience for 480 frames... [2023-03-09 12:31:58,258][270094] Decorrelating experience for 448 frames... [2023-03-09 12:31:58,264][270012] Decorrelating experience for 320 frames... [2023-03-09 12:31:58,277][270132] Decorrelating experience for 256 frames... [2023-03-09 12:31:58,312][270128] Decorrelating experience for 384 frames... [2023-03-09 12:31:58,314][270147] Decorrelating experience for 192 frames... [2023-03-09 12:31:58,344][270117] Decorrelating experience for 288 frames... [2023-03-09 12:31:58,349][271224] Decorrelating experience for 352 frames... [2023-03-09 12:31:58,386][270233] Decorrelating experience for 224 frames... [2023-03-09 12:31:58,433][271517] Decorrelating experience for 288 frames... [2023-03-09 12:31:58,435][270088] Decorrelating experience for 352 frames... [2023-03-09 12:31:58,452][270006] Decorrelating experience for 256 frames... [2023-03-09 12:31:58,497][271355] Decorrelating experience for 384 frames... [2023-03-09 12:31:58,497][270115] Decorrelating experience for 512 frames... [2023-03-09 12:31:58,531][270122] Decorrelating experience for 576 frames... [2023-03-09 12:31:58,534][270113] Decorrelating experience for 352 frames... [2023-03-09 12:31:58,537][270157] Decorrelating experience for 480 frames... [2023-03-09 12:31:58,561][270163] Decorrelating experience for 512 frames... [2023-03-09 12:31:58,566][270011] Decorrelating experience for 96 frames... [2023-03-09 12:31:58,629][270085] Decorrelating experience for 352 frames... [2023-03-09 12:31:58,633][270010] Decorrelating experience for 352 frames... [2023-03-09 12:31:58,653][270147] Decorrelating experience for 224 frames... [2023-03-09 12:31:58,734][270158] Decorrelating experience for 448 frames... [2023-03-09 12:31:58,741][270099] Decorrelating experience for 384 frames... [2023-03-09 12:31:58,743][270934] Decorrelating experience for 448 frames... [2023-03-09 12:31:58,753][270165] Decorrelating experience for 192 frames... [2023-03-09 12:31:58,753][270473] Decorrelating experience for 256 frames... [2023-03-09 12:31:58,754][270944] Decorrelating experience for 480 frames... [2023-03-09 12:31:58,792][270086] Decorrelating experience for 448 frames... [2023-03-09 12:31:58,814][270142] Decorrelating experience for 512 frames... [2023-03-09 12:31:58,819][270148] Decorrelating experience for 512 frames... [2023-03-09 12:31:58,832][270144] Decorrelating experience for 256 frames... [2023-03-09 12:31:58,913][270012] Decorrelating experience for 352 frames... [2023-03-09 12:31:58,945][270143] Decorrelating experience for 320 frames... [2023-03-09 12:31:58,946][270293] Decorrelating experience for 640 frames... [2023-03-09 12:31:58,946][271919] Decorrelating experience for 320 frames... [2023-03-09 12:31:58,948][270150] Decorrelating experience for 256 frames... [2023-03-09 12:31:58,997][270101] Decorrelating experience for 160 frames... [2023-03-09 12:31:59,004][270094] Decorrelating experience for 480 frames... [2023-03-09 12:31:59,013][270164] Decorrelating experience for 416 frames... [2023-03-09 12:31:59,016][271355] Decorrelating experience for 416 frames... [2023-03-09 12:31:59,040][271224] Decorrelating experience for 384 frames... [2023-03-09 12:31:59,092][270010] Decorrelating experience for 384 frames... [2023-03-09 12:31:59,125][270751] Decorrelating experience for 256 frames... [2023-03-09 12:31:59,151][270163] Decorrelating experience for 544 frames... [2023-03-09 12:31:59,169][270154] Decorrelating experience for 256 frames... [2023-03-09 12:31:59,178][270006] Decorrelating experience for 288 frames... [2023-03-09 12:31:59,211][270096] Decorrelating experience for 416 frames... [2023-03-09 12:31:59,212][270157] Decorrelating experience for 512 frames... [2023-03-09 12:31:59,214][270121] Decorrelating experience for 480 frames... [2023-03-09 12:31:59,217][270086] Decorrelating experience for 480 frames... [2023-03-09 12:31:59,272][270130] Decorrelating experience for 320 frames... [2023-03-09 12:31:59,296][270473] Decorrelating experience for 288 frames... [2023-03-09 12:31:59,308][270120] Decorrelating experience for 416 frames... [2023-03-09 12:31:59,353][270233] Decorrelating experience for 256 frames... [2023-03-09 12:31:59,364][270165] Decorrelating experience for 224 frames... [2023-03-09 12:31:59,400][270160] Decorrelating experience for 512 frames... [2023-03-09 12:31:59,401][270155] Decorrelating experience for 384 frames... [2023-03-09 12:31:59,410][271919] Decorrelating experience for 352 frames... [2023-03-09 12:31:59,412][270132] Decorrelating experience for 288 frames... [2023-03-09 12:31:59,430][270158] Decorrelating experience for 480 frames... [2023-03-09 12:31:59,456][270139] Decorrelating experience for 448 frames... [2023-03-09 12:31:59,511][270127] Decorrelating experience for 352 frames... [2023-03-09 12:31:59,511][270142] Decorrelating experience for 544 frames... [2023-03-09 12:31:59,558][270148] Decorrelating experience for 544 frames... [2023-03-09 12:31:59,564][270128] Decorrelating experience for 416 frames... [2023-03-09 12:31:59,616][270552] Decorrelating experience for 320 frames... [2023-03-09 12:31:59,617][270117] Decorrelating experience for 320 frames... [2023-03-09 12:31:59,618][270557] Decorrelating experience for 224 frames... [2023-03-09 12:31:59,654][270009] Decorrelating experience for 448 frames... [2023-03-09 12:31:59,664][270096] Decorrelating experience for 448 frames... [2023-03-09 12:31:59,679][270944] Decorrelating experience for 512 frames... [2023-03-09 12:31:59,707][271126] Decorrelating experience for 352 frames... [2023-03-09 12:31:59,748][270132] Decorrelating experience for 320 frames... [2023-03-09 12:31:59,756][270095] Decorrelating experience for 288 frames... [2023-03-09 12:31:59,776][270101] Decorrelating experience for 192 frames... [2023-03-09 12:31:59,813][270154] Decorrelating experience for 288 frames... [2023-03-09 12:31:59,817][270125] Decorrelating experience for 448 frames... [2023-03-09 12:31:59,818][270149] Decorrelating experience for 192 frames... [2023-03-09 12:31:59,835][270157] Decorrelating experience for 544 frames... [2023-03-09 12:31:59,863][270139] Decorrelating experience for 480 frames... [2023-03-09 12:31:59,889][270163] Decorrelating experience for 576 frames... [2023-03-09 12:31:59,893][270120] Decorrelating experience for 448 frames... [2023-03-09 12:31:59,931][270557] Decorrelating experience for 256 frames... [2023-03-09 12:31:59,943][270142] Decorrelating experience for 576 frames... [2023-03-09 12:31:59,971][270130] Decorrelating experience for 352 frames... [2023-03-09 12:31:59,982][269569] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 2500018176. Throughput: 0: 0.0. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) [2023-03-09 12:31:59,998][270009] Decorrelating experience for 480 frames... [2023-03-09 12:32:00,010][270126] Decorrelating experience for 640 frames... [2023-03-09 12:32:00,016][270153] Decorrelating experience for 480 frames... [2023-03-09 12:32:00,044][270132] Decorrelating experience for 352 frames... [2023-03-09 12:32:00,069][270472] Decorrelating experience for 224 frames... [2023-03-09 12:32:00,084][270005] Decorrelating experience for 128 frames... [2023-03-09 12:32:00,085][270148] Decorrelating experience for 576 frames... [2023-03-09 12:32:00,116][270144] Decorrelating experience for 288 frames... [2023-03-09 12:32:00,124][270127] Decorrelating experience for 384 frames... [2023-03-09 12:32:00,186][270155] Decorrelating experience for 416 frames... [2023-03-09 12:32:00,186][270012] Decorrelating experience for 384 frames... [2023-03-09 12:32:00,202][270154] Decorrelating experience for 320 frames... [2023-03-09 12:32:00,254][270086] Decorrelating experience for 512 frames... [2023-03-09 12:32:00,256][270128] Decorrelating experience for 448 frames... [2023-03-09 12:32:00,262][270145] Decorrelating experience for 416 frames... [2023-03-09 12:32:00,274][271126] Decorrelating experience for 384 frames... [2023-03-09 12:32:00,312][270147] Decorrelating experience for 256 frames... [2023-03-09 12:32:00,317][270105] Decorrelating experience for 192 frames... [2023-03-09 12:32:00,343][270158] Decorrelating experience for 512 frames... [2023-03-09 12:32:00,383][270163] Decorrelating experience for 608 frames... [2023-03-09 12:32:00,391][270130] Decorrelating experience for 384 frames... [2023-03-09 12:32:00,413][270860] Decorrelating experience for 64 frames... [2023-03-09 12:32:00,447][270160] Decorrelating experience for 544 frames... [2023-03-09 12:32:00,463][270751] Decorrelating experience for 288 frames... [2023-03-09 12:32:00,468][270139] Decorrelating experience for 512 frames... [2023-03-09 12:32:00,491][270118] Decorrelating experience for 288 frames... [2023-03-09 12:32:00,499][270154] Decorrelating experience for 352 frames... [2023-03-09 12:32:00,503][270002] Another process currently holds the lock /tmp/sf2_rolo/doom_004.lockfile, attempt: 1 [2023-03-09 12:32:00,517][270157] Decorrelating experience for 576 frames... [2023-03-09 12:32:00,531][270137] Decorrelating experience for 352 frames... [2023-03-09 12:32:00,563][270541] Decorrelating experience for 96 frames... [2023-03-09 12:32:00,609][270132] Decorrelating experience for 384 frames... [2023-03-09 12:32:00,632][270101] Decorrelating experience for 224 frames... [2023-03-09 12:32:00,668][270009] Decorrelating experience for 512 frames... [2023-03-09 12:32:00,671][270005] Decorrelating experience for 160 frames... [2023-03-09 12:32:00,680][270088] Decorrelating experience for 384 frames... [2023-03-09 12:32:00,680][270105] Decorrelating experience for 224 frames... [2023-03-09 12:32:00,683][270148] Decorrelating experience for 608 frames... [2023-03-09 12:32:00,700][270145] Decorrelating experience for 448 frames... [2023-03-09 12:32:00,714][270116] Decorrelating experience for 320 frames... [2023-03-09 12:32:00,763][270107] Decorrelating experience for 288 frames... [2023-03-09 12:32:00,790][270142] Decorrelating experience for 608 frames... [2023-03-09 12:32:00,813][271355] Decorrelating experience for 448 frames... [2023-03-09 12:32:00,855][271126] Decorrelating experience for 416 frames... [2023-03-09 12:32:00,859][270136] Another process currently holds the lock /tmp/sf2_rolo/doom_004.lockfile, attempt: 1 [2023-03-09 12:32:00,875][270115] Decorrelating experience for 544 frames... [2023-03-09 12:32:00,875][270108] Decorrelating experience for 384 frames... [2023-03-09 12:32:00,878][270008] Decorrelating experience for 352 frames... [2023-03-09 12:32:00,881][270155] Decorrelating experience for 448 frames... [2023-03-09 12:32:00,888][270150] Decorrelating experience for 288 frames... [2023-03-09 12:32:00,894][270101] Decorrelating experience for 256 frames... [2023-03-09 12:32:00,965][277995] Decorrelating experience for 256 frames... [2023-03-09 12:32:00,976][270151] Decorrelating experience for 192 frames... [2023-03-09 12:32:00,998][270120] Decorrelating experience for 480 frames... [2023-03-09 12:32:01,061][270007] Decorrelating experience for 288 frames... [2023-03-09 12:32:01,071][270139] Decorrelating experience for 544 frames... [2023-03-09 12:32:01,073][270154] Decorrelating experience for 384 frames... [2023-03-09 12:32:01,073][270157] Decorrelating experience for 608 frames... [2023-03-09 12:32:01,083][270117] Decorrelating experience for 352 frames... [2023-03-09 12:32:01,084][270158] Decorrelating experience for 544 frames... [2023-03-09 12:32:01,107][270751] Decorrelating experience for 320 frames... [2023-03-09 12:32:01,165][270116] Decorrelating experience for 352 frames... [2023-03-09 12:32:01,168][270143] Decorrelating experience for 352 frames... [2023-03-09 12:32:01,253][270089] Decorrelating experience for 224 frames... [2023-03-09 12:32:01,255][270699] Decorrelating experience for 320 frames... [2023-03-09 12:32:01,273][270164] Decorrelating experience for 448 frames... [2023-03-09 12:32:01,276][270125] Decorrelating experience for 480 frames... [2023-03-09 12:32:01,289][270099] Decorrelating experience for 416 frames... [2023-03-09 12:32:01,298][270137] Decorrelating experience for 384 frames... [2023-03-09 12:32:01,309][270115] Decorrelating experience for 576 frames... [2023-03-09 12:32:01,322][270093] Decorrelating experience for 224 frames... [2023-03-09 12:32:01,346][270136] Decorrelating experience for 160 frames... [2023-03-09 12:32:01,368][270109] Decorrelating experience for 416 frames... [2023-03-09 12:32:01,440][270161] Decorrelating experience for 288 frames... [2023-03-09 12:32:01,441][270160] Decorrelating experience for 576 frames... [2023-03-09 12:32:01,473][270101] Decorrelating experience for 288 frames... [2023-03-09 12:32:01,482][270944] Decorrelating experience for 544 frames... [2023-03-09 12:32:01,493][270095] Decorrelating experience for 320 frames... [2023-03-09 12:32:01,496][270151] Decorrelating experience for 224 frames... [2023-03-09 12:32:01,503][270142] Decorrelating experience for 640 frames... [2023-03-09 12:32:01,530][270751] Decorrelating experience for 352 frames... [2023-03-09 12:32:01,567][270699] Decorrelating experience for 352 frames... [2023-03-09 12:32:01,596][270945] Decorrelating experience for 256 frames... [2023-03-09 12:32:01,625][270140] Decorrelating experience for 384 frames... [2023-03-09 12:32:01,628][270552] Decorrelating experience for 352 frames... [2023-03-09 12:32:01,670][270137] Decorrelating experience for 416 frames... [2023-03-09 12:32:01,683][270116] Decorrelating experience for 384 frames... [2023-03-09 12:32:01,691][270125] Decorrelating experience for 512 frames... [2023-03-09 12:32:01,716][270089] Decorrelating experience for 256 frames... [2023-03-09 12:32:01,720][270086] Decorrelating experience for 544 frames... [2023-03-09 12:32:01,721][270108] Decorrelating experience for 416 frames... [2023-03-09 12:32:01,747][270132] Decorrelating experience for 416 frames... [2023-03-09 12:32:01,781][270553] Decorrelating experience for 512 frames... [2023-03-09 12:32:01,815][270101] Decorrelating experience for 320 frames... [2023-03-09 12:32:01,817][271355] Decorrelating experience for 480 frames... [2023-03-09 12:32:01,880][270404] Decorrelating experience for 416 frames... [2023-03-09 12:32:01,906][270145] Decorrelating experience for 480 frames... [2023-03-09 12:32:01,910][270115] Decorrelating experience for 608 frames... [2023-03-09 12:32:01,911][271126] Decorrelating experience for 448 frames... [2023-03-09 12:32:01,928][270557] Decorrelating experience for 288 frames... [2023-03-09 12:32:01,931][270105] Decorrelating experience for 256 frames... [2023-03-09 12:32:01,936][270006] Decorrelating experience for 320 frames... [2023-03-09 12:32:01,971][270080] Decorrelating experience for 512 frames... [2023-03-09 12:32:01,997][270473] Decorrelating experience for 320 frames... [2023-03-09 12:32:02,005][270117] Decorrelating experience for 384 frames... [2023-03-09 12:32:02,063][270139] Decorrelating experience for 576 frames... [2023-03-09 12:32:02,092][270751] Decorrelating experience for 384 frames... [2023-03-09 12:32:02,098][270089] Decorrelating experience for 288 frames... [2023-03-09 12:32:02,114][270944] Decorrelating experience for 576 frames... [2023-03-09 12:32:02,128][270130] Decorrelating experience for 416 frames... [2023-03-09 12:32:02,136][270149] Decorrelating experience for 224 frames... [2023-03-09 12:32:02,186][270100] Decorrelating experience for 512 frames... [2023-03-09 12:32:02,186][270162] Decorrelating experience for 512 frames... [2023-03-09 12:32:02,191][270119] Decorrelating experience for 160 frames... [2023-03-09 12:32:02,220][270109] Decorrelating experience for 448 frames... [2023-03-09 12:32:02,252][270233] Decorrelating experience for 288 frames... [2023-03-09 12:32:02,297][270126] Decorrelating experience for 672 frames... [2023-03-09 12:32:02,306][270086] Decorrelating experience for 576 frames... [2023-03-09 12:32:02,309][270140] Decorrelating experience for 416 frames... [2023-03-09 12:32:02,318][270115] Decorrelating experience for 640 frames... [2023-03-09 12:32:02,342][270153] Decorrelating experience for 512 frames... [2023-03-09 12:32:02,376][270145] Decorrelating experience for 512 frames... [2023-03-09 12:32:02,380][270131] Decorrelating experience for 256 frames... [2023-03-09 12:32:02,381][270122] Decorrelating experience for 608 frames... [2023-03-09 12:32:02,435][270132] Decorrelating experience for 448 frames... [2023-03-09 12:32:02,444][270096] Decorrelating experience for 480 frames... [2023-03-09 12:32:02,495][270136] Decorrelating experience for 192 frames... [2023-03-09 12:32:02,500][270472] Decorrelating experience for 256 frames... [2023-03-09 12:32:02,518][270130] Decorrelating experience for 448 frames... [2023-03-09 12:32:02,548][270148] Decorrelating experience for 640 frames... [2023-03-09 12:32:02,569][271126] Decorrelating experience for 480 frames... [2023-03-09 12:32:02,572][270137] Decorrelating experience for 448 frames... [2023-03-09 12:32:02,578][270163] Decorrelating experience for 640 frames... [2023-03-09 12:32:02,620][270116] Decorrelating experience for 416 frames... [2023-03-09 12:32:02,626][270133] Decorrelating experience for 192 frames... [2023-03-09 12:32:02,638][270088] Decorrelating experience for 416 frames... [2023-03-09 12:32:02,690][270089] Decorrelating experience for 320 frames... [2023-03-09 12:32:02,700][270086] Decorrelating experience for 608 frames... [2023-03-09 12:32:02,743][270162] Decorrelating experience for 544 frames... [2023-03-09 12:32:02,759][270139] Decorrelating experience for 608 frames... [2023-03-09 12:32:02,780][270135] Decorrelating experience for 544 frames... [2023-03-09 12:32:02,813][270109] Decorrelating experience for 480 frames... [2023-03-09 12:32:02,815][270008] Decorrelating experience for 384 frames... [2023-03-09 12:32:02,815][270110] Another process currently holds the lock /tmp/sf2_rolo/doom_009.lockfile, attempt: 1 [2023-03-09 12:32:02,816][270108] Decorrelating experience for 448 frames... [2023-03-09 12:32:02,818][270093] Decorrelating experience for 256 frames... [2023-03-09 12:32:02,840][270153] Decorrelating experience for 544 frames... [2023-03-09 12:32:02,869][270130] Decorrelating experience for 480 frames... [2023-03-09 12:32:02,941][270293] Decorrelating experience for 672 frames... [2023-03-09 12:32:02,953][270473] Decorrelating experience for 352 frames... [2023-03-09 12:32:02,980][270085] Decorrelating experience for 384 frames... [2023-03-09 12:32:02,986][270014] Another process currently holds the lock /tmp/sf2_rolo/doom_004.lockfile, attempt: 1 [2023-03-09 12:32:02,993][270089] Decorrelating experience for 352 frames... [2023-03-09 12:32:03,000][270552] Decorrelating experience for 384 frames... [2023-03-09 12:32:03,019][270120] Decorrelating experience for 512 frames... [2023-03-09 12:32:03,023][270622] Decorrelating experience for 256 frames... [2023-03-09 12:32:03,036][270115] Decorrelating experience for 672 frames... [2023-03-09 12:32:03,038][271126] Decorrelating experience for 512 frames... [2023-03-09 12:32:03,087][270136] Decorrelating experience for 224 frames... [2023-03-09 12:32:03,133][270404] Decorrelating experience for 448 frames... [2023-03-09 12:32:03,161][270149] Decorrelating experience for 256 frames... [2023-03-09 12:32:03,210][270118] Decorrelating experience for 320 frames... [2023-03-09 12:32:03,211][270088] Decorrelating experience for 448 frames... [2023-03-09 12:32:03,215][270086] Decorrelating experience for 640 frames... [2023-03-09 12:32:03,217][270116] Decorrelating experience for 448 frames... [2023-03-09 12:32:03,229][270097] Decorrelating experience for 416 frames... [2023-03-09 12:32:03,234][270104] Decorrelating experience for 320 frames... [2023-03-09 12:32:03,243][270122] Decorrelating experience for 640 frames... [2023-03-09 12:32:03,278][270472] Decorrelating experience for 288 frames... [2023-03-09 12:32:03,319][270105] Decorrelating experience for 288 frames... [2023-03-09 12:32:03,351][270085] Decorrelating experience for 416 frames... [2023-03-09 12:32:03,414][270129] Decorrelating experience for 0 frames... [2023-03-09 12:32:03,415][270161] Decorrelating experience for 320 frames... [2023-03-09 12:32:03,416][270233] Decorrelating experience for 320 frames... [2023-03-09 12:32:03,417][270136] Decorrelating experience for 256 frames... [2023-03-09 12:32:03,446][270133] Decorrelating experience for 224 frames... [2023-03-09 12:32:03,461][270131] Decorrelating experience for 288 frames... [2023-03-09 12:32:03,482][270162] Decorrelating experience for 576 frames... [2023-03-09 12:32:03,499][270095] Decorrelating experience for 352 frames... [2023-03-09 12:32:03,508][270109] Decorrelating experience for 512 frames... [2023-03-09 12:32:03,561][270096] Decorrelating experience for 512 frames... [2023-03-09 12:32:03,608][270129] Decorrelating experience for 32 frames... [2023-03-09 12:32:03,609][270013] Decorrelating experience for 416 frames... [2023-03-09 12:32:03,609][270152] Decorrelating experience for 416 frames... [2023-03-09 12:32:03,615][270097] Decorrelating experience for 448 frames... [2023-03-09 12:32:03,630][270404] Decorrelating experience for 480 frames... [2023-03-09 12:32:03,642][270120] Decorrelating experience for 544 frames... [2023-03-09 12:32:03,669][270116] Decorrelating experience for 480 frames... [2023-03-09 12:32:03,719][270134] Decorrelating experience for 704 frames... [2023-03-09 12:32:03,764][270108] Decorrelating experience for 480 frames... [2023-03-09 12:32:03,803][270143] Decorrelating experience for 384 frames... [2023-03-09 12:32:03,804][270146] Decorrelating experience for 352 frames... [2023-03-09 12:32:03,807][270514] Decorrelating experience for 288 frames... [2023-03-09 12:32:03,818][270100] Decorrelating experience for 544 frames... [2023-03-09 12:32:03,830][270293] Decorrelating experience for 704 frames... [2023-03-09 12:32:03,833][270161] Decorrelating experience for 352 frames... [2023-03-09 12:32:03,852][270093] Decorrelating experience for 288 frames... [2023-03-09 12:32:03,888][270622] Decorrelating experience for 288 frames... [2023-03-09 12:32:03,904][270110] Decorrelating experience for 96 frames... [2023-03-09 12:32:03,962][270095] Decorrelating experience for 384 frames... [2023-03-09 12:32:03,992][270126] Decorrelating experience for 704 frames... [2023-03-09 12:32:03,994][270015] Decorrelating experience for 512 frames... [2023-03-09 12:32:04,003][270007] Decorrelating experience for 320 frames... [2023-03-09 12:32:04,028][270139] Decorrelating experience for 640 frames... [2023-03-09 12:32:04,029][270127] Decorrelating experience for 416 frames... [2023-03-09 12:32:04,042][270085] Decorrelating experience for 448 frames... [2023-03-09 12:32:04,048][270130] Decorrelating experience for 512 frames... [2023-03-09 12:32:04,085][270934] Decorrelating experience for 480 frames... [2023-03-09 12:32:04,111][270153] Decorrelating experience for 576 frames... [2023-03-09 12:32:04,189][270147] Decorrelating experience for 288 frames... [2023-03-09 12:32:04,190][270109] Decorrelating experience for 544 frames... [2023-03-09 12:32:04,193][270093] Decorrelating experience for 320 frames... [2023-03-09 12:32:04,193][270699] Decorrelating experience for 384 frames... [2023-03-09 12:32:04,221][270233] Decorrelating experience for 352 frames... [2023-03-09 12:32:04,234][270143] Decorrelating experience for 416 frames... [2023-03-09 12:32:04,242][270011] Decorrelating experience for 128 frames... [2023-03-09 12:32:04,273][270293] Decorrelating experience for 736 frames... [2023-03-09 12:32:04,295][270751] Decorrelating experience for 416 frames... [2023-03-09 12:32:04,310][270145] Decorrelating experience for 544 frames... [2023-03-09 12:32:04,379][270135] Decorrelating experience for 576 frames... [2023-03-09 12:32:04,390][270014] Decorrelating experience for 32 frames... [2023-03-09 12:32:04,391][270110] Decorrelating experience for 128 frames... [2023-03-09 12:32:04,393][270116] Decorrelating experience for 512 frames... [2023-03-09 12:32:04,421][270130] Decorrelating experience for 544 frames... [2023-03-09 12:32:04,423][270146] Decorrelating experience for 384 frames... [2023-03-09 12:32:04,439][270085] Decorrelating experience for 480 frames... [2023-03-09 12:32:04,456][270098] Decorrelating experience for 352 frames... [2023-03-09 12:32:04,574][270162] Decorrelating experience for 608 frames... [2023-03-09 12:32:04,576][270552] Decorrelating experience for 416 frames... [2023-03-09 12:32:04,578][270126] Decorrelating experience for 736 frames... [2023-03-09 12:32:04,628][270143] Decorrelating experience for 448 frames... [2023-03-09 12:32:04,633][270147] Decorrelating experience for 320 frames... [2023-03-09 12:32:04,633][270125] Decorrelating experience for 544 frames... [2023-03-09 12:32:04,642][270103] Decorrelating experience for 224 frames... [2023-03-09 12:32:04,651][270163] Decorrelating experience for 672 frames... [2023-03-09 12:32:04,651][270115] Decorrelating experience for 704 frames... [2023-03-09 12:32:04,711][270109] Decorrelating experience for 576 frames... [2023-03-09 12:32:04,770][270098] Decorrelating experience for 384 frames... [2023-03-09 12:32:04,776][271355] Decorrelating experience for 512 frames... [2023-03-09 12:32:04,776][270148] Decorrelating experience for 672 frames... [2023-03-09 12:32:04,819][270116] Decorrelating experience for 544 frames... [2023-03-09 12:32:04,826][270149] Decorrelating experience for 288 frames... [2023-03-09 12:32:04,876][270007] Decorrelating experience for 352 frames... [2023-03-09 12:32:04,878][270008] Decorrelating experience for 416 frames... [2023-03-09 12:32:04,893][270085] Decorrelating experience for 512 frames... [2023-03-09 12:32:04,904][270135] Decorrelating experience for 608 frames... [2023-03-09 12:32:04,905][270104] Decorrelating experience for 352 frames... [2023-03-09 12:32:04,982][269569] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 2500018176. Throughput: 0: 0.0. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) [2023-03-09 12:32:04,992][270161] Decorrelating experience for 384 frames... [2023-03-09 12:32:04,993][270107] Decorrelating experience for 320 frames... [2023-03-09 12:32:04,994][270144] Decorrelating experience for 320 frames... [2023-03-09 12:32:05,016][270552] Decorrelating experience for 448 frames... [2023-03-09 12:32:05,027][270110] Decorrelating experience for 160 frames... [2023-03-09 12:32:05,070][270125] Decorrelating experience for 576 frames... [2023-03-09 12:32:05,081][270157] Decorrelating experience for 640 frames... [2023-03-09 12:32:05,110][270751] Decorrelating experience for 448 frames... [2023-03-09 12:32:05,111][270091] Decorrelating experience for 256 frames... [2023-03-09 12:32:05,112][270130] Decorrelating experience for 576 frames... [2023-03-09 12:32:05,183][270699] Decorrelating experience for 416 frames... [2023-03-09 12:32:05,184][270124] Decorrelating experience for 320 frames... [2023-03-09 12:32:05,189][270014] Decorrelating experience for 64 frames... [2023-03-09 12:32:05,213][270109] Decorrelating experience for 608 frames... [2023-03-09 12:32:05,251][270103] Decorrelating experience for 256 frames... [2023-03-09 12:32:05,264][270146] Decorrelating experience for 416 frames... [2023-03-09 12:32:05,267][270149] Decorrelating experience for 320 frames... [2023-03-09 12:32:05,292][270107] Decorrelating experience for 352 frames... [2023-03-09 12:32:05,329][270556] Decorrelating experience for 288 frames... [2023-03-09 12:32:05,357][270015] Decorrelating experience for 544 frames... [2023-03-09 12:32:05,378][270135] Decorrelating experience for 640 frames... [2023-03-09 12:32:05,380][270136] Decorrelating experience for 288 frames... [2023-03-09 12:32:05,395][270233] Decorrelating experience for 384 frames... [2023-03-09 12:32:05,398][270144] Decorrelating experience for 352 frames... [2023-03-09 12:32:05,460][271355] Decorrelating experience for 544 frames... [2023-03-09 12:32:05,467][270085] Decorrelating experience for 544 frames... [2023-03-09 12:32:05,479][270943] Decorrelating experience for 320 frames... [2023-03-09 12:32:05,504][270472] Decorrelating experience for 320 frames... [2023-03-09 12:32:05,549][270091] Decorrelating experience for 288 frames... [2023-03-09 12:32:05,573][270148] Decorrelating experience for 704 frames... [2023-03-09 12:32:05,574][270751] Decorrelating experience for 480 frames... [2023-03-09 12:32:05,576][270699] Decorrelating experience for 448 frames... [2023-03-09 12:32:05,607][270107] Decorrelating experience for 384 frames... [2023-03-09 12:32:05,611][270117] Decorrelating experience for 416 frames... [2023-03-09 12:32:05,655][270157] Decorrelating experience for 672 frames... [2023-03-09 12:32:05,675][270109] Decorrelating experience for 640 frames... [2023-03-09 12:32:05,682][270137] Decorrelating experience for 480 frames... [2023-03-09 12:32:05,689][270293] Decorrelating experience for 768 frames... [2023-03-09 12:32:05,765][270115] Decorrelating experience for 736 frames... [2023-03-09 12:32:05,785][270088] Decorrelating experience for 480 frames... [2023-03-09 12:32:05,790][270011] Decorrelating experience for 160 frames... [2023-03-09 12:32:05,800][270135] Decorrelating experience for 672 frames... [2023-03-09 12:32:05,804][270556] Decorrelating experience for 320 frames... [2023-03-09 12:32:05,821][270008] Decorrelating experience for 448 frames... [2023-03-09 12:32:05,837][270094] Decorrelating experience for 512 frames... [2023-03-09 12:32:05,874][270161] Decorrelating experience for 416 frames... [2023-03-09 12:32:05,886][270164] Decorrelating experience for 480 frames... [2023-03-09 12:32:05,889][270012] Decorrelating experience for 416 frames... [2023-03-09 12:32:05,951][270098] Decorrelating experience for 416 frames... [2023-03-09 12:32:05,986][270944] Decorrelating experience for 608 frames... [2023-03-09 12:32:05,990][270134] Decorrelating experience for 736 frames... [2023-03-09 12:32:06,003][277349] Another process currently holds the lock /tmp/sf2_rolo/doom_004.lockfile, attempt: 1 [2023-03-09 12:32:06,007][270472] Decorrelating experience for 352 frames... [2023-03-09 12:32:06,029][270016] Decorrelating experience for 480 frames... [2023-03-09 12:32:06,047][270085] Decorrelating experience for 576 frames... [2023-03-09 12:32:06,067][270153] Decorrelating experience for 608 frames... [2023-03-09 12:32:06,079][270699] Decorrelating experience for 480 frames... [2023-03-09 12:32:06,085][270125] Decorrelating experience for 608 frames... [2023-03-09 12:32:06,135][270139] Decorrelating experience for 672 frames... [2023-03-09 12:32:06,154][270156] Decorrelating experience for 96 frames... [2023-03-09 12:32:06,179][270233] Decorrelating experience for 416 frames... [2023-03-09 12:32:06,183][270149] Decorrelating experience for 352 frames... [2023-03-09 12:32:06,215][270094] Decorrelating experience for 544 frames... [2023-03-09 12:32:06,234][270135] Decorrelating experience for 704 frames... [2023-03-09 12:32:06,234][270011] Decorrelating experience for 192 frames... [2023-03-09 12:32:06,251][270145] Decorrelating experience for 576 frames... [2023-03-09 12:32:06,260][270556] Decorrelating experience for 352 frames... [2023-03-09 12:32:06,274][270552] Decorrelating experience for 480 frames... [2023-03-09 12:32:06,366][271224] Decorrelating experience for 416 frames... [2023-03-09 12:32:06,379][270015] Decorrelating experience for 576 frames... [2023-03-09 12:32:06,391][270088] Decorrelating experience for 512 frames... [2023-03-09 12:32:06,392][277349] Decorrelating experience for 320 frames... [2023-03-09 12:32:06,424][270148] Decorrelating experience for 736 frames... [2023-03-09 12:32:06,439][270160] Decorrelating experience for 608 frames... [2023-03-09 12:32:06,476][270110] Decorrelating experience for 192 frames... [2023-03-09 12:32:06,490][270116] Decorrelating experience for 576 frames... [2023-03-09 12:32:06,496][270125] Decorrelating experience for 640 frames... [2023-03-09 12:32:06,511][270557] Decorrelating experience for 320 frames... [2023-03-09 12:32:06,586][270555] Decorrelating experience for 32 frames... [2023-03-09 12:32:06,610][270103] Decorrelating experience for 288 frames... [2023-03-09 12:32:06,625][270121] Decorrelating experience for 512 frames... [2023-03-09 12:32:06,625][270161] Decorrelating experience for 448 frames... [2023-03-09 12:32:06,625][270012] Decorrelating experience for 448 frames... [2023-03-09 12:32:06,627][270233] Decorrelating experience for 448 frames... [2023-03-09 12:32:06,681][270162] Decorrelating experience for 640 frames... [2023-03-09 12:32:06,719][270472] Decorrelating experience for 384 frames... [2023-03-09 12:32:06,769][270126] Decorrelating experience for 768 frames... [2023-03-09 12:32:06,772][270596] Decorrelating experience for 288 frames... [2023-03-09 12:32:06,802][271355] Decorrelating experience for 576 frames... [2023-03-09 12:32:06,820][270130] Decorrelating experience for 608 frames... [2023-03-09 12:32:06,824][270088] Decorrelating experience for 544 frames... [2023-03-09 12:32:06,825][270008] Decorrelating experience for 480 frames... [2023-03-09 12:32:06,890][270552] Decorrelating experience for 512 frames... [2023-03-09 12:32:06,897][270145] Decorrelating experience for 608 frames... [2023-03-09 12:32:06,919][270555] Decorrelating experience for 64 frames... [2023-03-09 12:32:06,990][270368] Decorrelating experience for 320 frames... [2023-03-09 12:32:06,995][270095] Decorrelating experience for 416 frames... [2023-03-09 12:32:07,003][270014] Decorrelating experience for 96 frames... [2023-03-09 12:32:07,021][270144] Decorrelating experience for 384 frames... [2023-03-09 12:32:07,023][270557] Decorrelating experience for 352 frames... [2023-03-09 12:32:07,037][270135] Decorrelating experience for 736 frames... [2023-03-09 12:32:07,078][270139] Decorrelating experience for 704 frames... [2023-03-09 12:32:07,081][270110] Decorrelating experience for 224 frames... [2023-03-09 12:32:07,105][270012] Decorrelating experience for 480 frames... [2023-03-09 12:32:07,109][270163] Decorrelating experience for 704 frames... [2023-03-09 12:32:07,186][270148] Decorrelating experience for 768 frames... [2023-03-09 12:32:07,199][270127] Decorrelating experience for 448 frames... [2023-03-09 12:32:07,199][270158] Decorrelating experience for 576 frames... [2023-03-09 12:32:07,211][270088] Decorrelating experience for 576 frames... [2023-03-09 12:32:07,239][270008] Decorrelating experience for 512 frames... [2023-03-09 12:32:07,242][270150] Decorrelating experience for 320 frames... [2023-03-09 12:32:07,264][270164] Decorrelating experience for 512 frames... [2023-03-09 12:32:07,271][270125] Decorrelating experience for 672 frames... [2023-03-09 12:32:07,293][270108] Decorrelating experience for 512 frames... [2023-03-09 12:32:07,305][270145] Decorrelating experience for 640 frames... [2023-03-09 12:32:07,401][270090] Decorrelating experience for 512 frames... [2023-03-09 12:32:07,446][270014] Decorrelating experience for 128 frames... [2023-03-09 12:32:07,453][270006] Decorrelating experience for 352 frames... [2023-03-09 12:32:07,471][270089] Decorrelating experience for 384 frames... [2023-03-09 12:32:07,471][270555] Decorrelating experience for 96 frames... [2023-03-09 12:32:07,473][270699] Decorrelating experience for 512 frames... [2023-03-09 12:32:07,473][271224] Decorrelating experience for 448 frames... [2023-03-09 12:32:07,476][270554] Decorrelating experience for 288 frames... [2023-03-09 12:32:07,483][270233] Decorrelating experience for 480 frames... [2023-03-09 12:32:07,495][270135] Decorrelating experience for 768 frames... [2023-03-09 12:32:07,581][270293] Decorrelating experience for 800 frames... [2023-03-09 12:32:07,640][270012] Decorrelating experience for 512 frames... [2023-03-09 12:32:07,662][270944] Decorrelating experience for 640 frames... [2023-03-09 12:32:07,666][270127] Decorrelating experience for 480 frames... [2023-03-09 12:32:07,675][270139] Decorrelating experience for 736 frames... [2023-03-09 12:32:07,690][270934] Decorrelating experience for 512 frames... [2023-03-09 12:32:07,692][270164] Decorrelating experience for 544 frames... [2023-03-09 12:32:07,713][270557] Decorrelating experience for 384 frames... [2023-03-09 12:32:07,732][270116] Decorrelating experience for 608 frames... [2023-03-09 12:32:07,831][270159] Decorrelating experience for 576 frames... [2023-03-09 12:32:07,843][270094] Decorrelating experience for 576 frames... [2023-03-09 12:32:07,851][270751] Decorrelating experience for 512 frames... [2023-03-09 12:32:07,852][271126] Decorrelating experience for 544 frames... [2023-03-09 12:32:07,862][270125] Decorrelating experience for 704 frames... [2023-03-09 12:32:07,875][271224] Decorrelating experience for 480 frames... [2023-03-09 12:32:07,900][270086] Decorrelating experience for 672 frames... [2023-03-09 12:32:07,912][270114] Decorrelating experience for 448 frames... [2023-03-09 12:32:07,934][270090] Decorrelating experience for 544 frames... [2023-03-09 12:32:08,028][277349] Decorrelating experience for 352 frames... [2023-03-09 12:32:08,047][270146] Decorrelating experience for 448 frames... [2023-03-09 12:32:08,050][270126] Decorrelating experience for 800 frames... [2023-03-09 12:32:08,057][270099] Decorrelating experience for 448 frames... [2023-03-09 12:32:08,063][270135] Decorrelating experience for 800 frames... [2023-03-09 12:32:08,098][270142] Decorrelating experience for 672 frames... [2023-03-09 12:32:08,127][270233] Decorrelating experience for 512 frames... [2023-03-09 12:32:08,135][270139] Decorrelating experience for 768 frames... [2023-03-09 12:32:08,160][270098] Decorrelating experience for 448 frames... [2023-03-09 12:32:08,233][270159] Decorrelating experience for 608 frames... [2023-03-09 12:32:08,237][270556] Decorrelating experience for 384 frames... [2023-03-09 12:32:08,249][270097] Decorrelating experience for 480 frames... [2023-03-09 12:32:08,265][271355] Decorrelating experience for 608 frames... [2023-03-09 12:32:08,302][270122] Decorrelating experience for 672 frames... [2023-03-09 12:32:08,307][270944] Decorrelating experience for 672 frames... [2023-03-09 12:32:08,314][270096] Decorrelating experience for 544 frames... [2023-03-09 12:32:08,381][270934] Decorrelating experience for 544 frames... [2023-03-09 12:32:08,397][270114] Decorrelating experience for 480 frames... [2023-03-09 12:32:08,405][271126] Decorrelating experience for 576 frames... [2023-03-09 12:32:08,441][270086] Decorrelating experience for 704 frames... [2023-03-09 12:32:08,446][270115] Decorrelating experience for 768 frames... [2023-03-09 12:32:08,452][270146] Decorrelating experience for 480 frames... [2023-03-09 12:32:08,501][270094] Decorrelating experience for 608 frames... [2023-03-09 12:32:08,507][270151] Decorrelating experience for 256 frames... [2023-03-09 12:32:08,511][270119] Decorrelating experience for 192 frames... [2023-03-09 12:32:08,512][270080] Decorrelating experience for 544 frames... [2023-03-09 12:32:08,565][270012] Decorrelating experience for 544 frames... [2023-03-09 12:32:08,599][270126] Decorrelating experience for 832 frames... [2023-03-09 12:32:08,607][270014] Decorrelating experience for 160 frames... [2023-03-09 12:32:08,643][270164] Decorrelating experience for 576 frames... [2023-03-09 12:32:08,643][270142] Decorrelating experience for 704 frames... [2023-03-09 12:32:08,656][270150] Decorrelating experience for 352 frames... [2023-03-09 12:32:08,693][271224] Decorrelating experience for 512 frames... [2023-03-09 12:32:08,718][270155] Decorrelating experience for 480 frames... [2023-03-09 12:32:08,719][270002] Decorrelating experience for 160 frames... [2023-03-09 12:32:08,719][270003] Decorrelating experience for 128 frames... [2023-03-09 12:32:08,755][270152] Decorrelating experience for 448 frames... [2023-03-09 12:32:08,801][277349] Decorrelating experience for 384 frames... [2023-03-09 12:32:08,829][271355] Decorrelating experience for 640 frames... [2023-03-09 12:32:08,842][270122] Decorrelating experience for 704 frames... [2023-03-09 12:32:08,878][270159] Decorrelating experience for 640 frames... [2023-03-09 12:32:08,912][270011] Decorrelating experience for 224 frames... [2023-03-09 12:32:08,913][270014] Decorrelating experience for 192 frames... [2023-03-09 12:32:08,913][270101] Decorrelating experience for 352 frames... [2023-03-09 12:32:08,949][270003] Decorrelating experience for 160 frames... [2023-03-09 12:32:08,974][270135] Decorrelating experience for 832 frames... [2023-03-09 12:32:08,977][270104] Decorrelating experience for 384 frames... [2023-03-09 12:32:08,989][270086] Decorrelating experience for 736 frames... [2023-03-09 12:32:09,039][270136] Decorrelating experience for 320 frames... [2023-03-09 12:32:09,062][270091] Decorrelating experience for 320 frames... [2023-03-09 12:32:09,062][270162] Decorrelating experience for 672 frames... [2023-03-09 12:32:09,098][270164] Decorrelating experience for 608 frames... [2023-03-09 12:32:09,103][270944] Decorrelating experience for 704 frames... [2023-03-09 12:32:09,105][270934] Decorrelating experience for 576 frames... [2023-03-09 12:32:09,131][270145] Decorrelating experience for 672 frames... [2023-03-09 12:32:09,164][270106] Decorrelating experience for 224 frames... [2023-03-09 12:32:09,168][270125] Decorrelating experience for 736 frames... [2023-03-09 12:32:09,177][270011] Decorrelating experience for 256 frames... [2023-03-09 12:32:09,255][270699] Decorrelating experience for 544 frames... [2023-03-09 12:32:09,269][270144] Decorrelating experience for 416 frames... [2023-03-09 12:32:09,291][270088] Decorrelating experience for 608 frames... [2023-03-09 12:32:09,315][270152] Decorrelating experience for 480 frames... [2023-03-09 12:32:09,319][270133] Decorrelating experience for 256 frames... [2023-03-09 12:32:09,319][270121] Decorrelating experience for 544 frames... [2023-03-09 12:32:09,341][270123] Another process currently holds the lock /tmp/sf2_rolo/doom_004.lockfile, attempt: 1 [2023-03-09 12:32:09,346][270136] Decorrelating experience for 352 frames... [2023-03-09 12:32:09,356][270126] Decorrelating experience for 864 frames... [2023-03-09 12:32:09,366][270157] Decorrelating experience for 704 frames... [2023-03-09 12:32:09,375][270119] Decorrelating experience for 224 frames... [2023-03-09 12:32:09,463][270129] Decorrelating experience for 64 frames... [2023-03-09 12:32:09,466][270143] Decorrelating experience for 480 frames... [2023-03-09 12:32:09,472][270293] Decorrelating experience for 832 frames... [2023-03-09 12:32:09,529][270015] Decorrelating experience for 608 frames... [2023-03-09 12:32:09,532][270127] Decorrelating experience for 512 frames... [2023-03-09 12:32:09,541][277349] Decorrelating experience for 416 frames... [2023-03-09 12:32:09,577][270142] Decorrelating experience for 736 frames... [2023-03-09 12:32:09,606][270108] Decorrelating experience for 544 frames... [2023-03-09 12:32:09,681][270106] Decorrelating experience for 256 frames... [2023-03-09 12:32:09,682][270128] Decorrelating experience for 480 frames... [2023-03-09 12:32:09,721][270136] Decorrelating experience for 384 frames... [2023-03-09 12:32:09,727][270094] Decorrelating experience for 640 frames... [2023-03-09 12:32:09,727][270162] Decorrelating experience for 704 frames... [2023-03-09 12:32:09,746][270161] Decorrelating experience for 480 frames... [2023-03-09 12:32:09,766][270129] Decorrelating experience for 96 frames... [2023-03-09 12:32:09,808][270088] Decorrelating experience for 640 frames... [2023-03-09 12:32:09,879][271517] Decorrelating experience for 320 frames... [2023-03-09 12:32:09,880][270623] Decorrelating experience for 128 frames... [2023-03-09 12:32:09,903][270944] Decorrelating experience for 736 frames... [2023-03-09 12:32:09,917][270145] Decorrelating experience for 704 frames... [2023-03-09 12:32:09,925][270164] Decorrelating experience for 640 frames... [2023-03-09 12:32:09,937][271224] Decorrelating experience for 544 frames... [2023-03-09 12:32:09,962][270293] Decorrelating experience for 864 frames... [2023-03-09 12:32:09,982][269569] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 2500018176. Throughput: 0: 0.0. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) [2023-03-09 12:32:09,984][270129] Decorrelating experience for 128 frames... [2023-03-09 12:32:10,054][270084] Decorrelating experience for 320 frames... [2023-03-09 12:32:10,062][270126] Decorrelating experience for 896 frames... [2023-03-09 12:32:10,077][270151] Decorrelating experience for 288 frames... [2023-03-09 12:32:10,085][270015] Decorrelating experience for 640 frames... [2023-03-09 12:32:10,130][271919] Decorrelating experience for 384 frames... [2023-03-09 12:32:10,154][270122] Decorrelating experience for 736 frames... [2023-03-09 12:32:10,182][270934] Decorrelating experience for 608 frames... [2023-03-09 12:32:10,185][270121] Decorrelating experience for 576 frames... [2023-03-09 12:32:10,209][271517] Decorrelating experience for 352 frames... [2023-03-09 12:32:10,250][270136] Decorrelating experience for 416 frames... [2023-03-09 12:32:10,280][270011] Decorrelating experience for 288 frames... [2023-03-09 12:32:10,309][277995] Decorrelating experience for 288 frames... [2023-03-09 12:32:10,347][271017] Decorrelating experience for 480 frames... [2023-03-09 12:32:10,352][270007] Decorrelating experience for 384 frames... [2023-03-09 12:32:10,355][270130] Decorrelating experience for 640 frames... [2023-03-09 12:32:10,383][270104] Decorrelating experience for 416 frames... [2023-03-09 12:32:10,386][270012] Decorrelating experience for 576 frames... [2023-03-09 12:32:10,446][270143] Decorrelating experience for 512 frames... [2023-03-09 12:32:10,447][270142] Decorrelating experience for 768 frames... [2023-03-09 12:32:10,476][270002] Decorrelating experience for 192 frames... [2023-03-09 12:32:10,506][270015] Decorrelating experience for 672 frames... [2023-03-09 12:32:10,514][270127] Decorrelating experience for 544 frames... [2023-03-09 12:32:10,547][270093] Decorrelating experience for 352 frames... [2023-03-09 12:32:10,548][270165] Decorrelating experience for 256 frames... [2023-03-09 12:32:10,550][270155] Decorrelating experience for 512 frames... [2023-03-09 12:32:10,585][270110] Decorrelating experience for 256 frames... [2023-03-09 12:32:10,587][270103] Decorrelating experience for 320 frames... [2023-03-09 12:32:10,632][270014] Decorrelating experience for 224 frames... [2023-03-09 12:32:10,644][270934] Decorrelating experience for 640 frames... [2023-03-09 12:32:10,670][270623] VizDoom game.init() threw an exception SignalException('Signal SIGINT received. ViZDoom instance has been closed.'). Terminate process... [2023-03-09 12:32:10,676][270473] VizDoom game.init() threw an exception SignalException('Signal SIGINT received. ViZDoom instance has been closed.'). Terminate process... [2023-03-09 12:32:10,679][270144] VizDoom game.init() threw an exception SignalException('Signal SIGINT received. ViZDoom instance has been closed.'). Terminate process... [2023-03-09 12:32:10,680][270160] VizDoom game.init() threw an exception SignalException('Signal SIGINT received. ViZDoom instance has been closed.'). Terminate process... [2023-03-09 12:32:10,682][270139] VizDoom game.init() threw an exception SignalException('Signal SIGINT received. ViZDoom instance has been closed.'). Terminate process... [2023-03-09 12:32:10,683][270145] VizDoom game.init() threw an exception ViZDoomErrorException('Unexpected ViZDoom instance crash.'). Terminate process... [2023-03-09 12:32:10,683][270080] VizDoom game.init() threw an exception SignalException('Signal SIGINT received. ViZDoom instance has been closed.'). Terminate process... [2023-03-09 12:32:10,684][270126] VizDoom game.init() threw an exception ViZDoomErrorException('Unexpected ViZDoom instance crash.'). Terminate process... [2023-03-09 12:32:10,685][270109] VizDoom game.init() threw an exception SignalException('Signal SIGINT received. ViZDoom instance has been closed.'). Terminate process... [2023-03-09 12:32:10,686][269569] Keyboard interrupt detected in the event loop EvtLoop [Runner_EvtLoop, process=main process 269569], exiting... [2023-03-09 12:32:10,687][269850] Stopping Batcher_0... [2023-03-09 12:32:10,687][269850] Loop batcher_evt_loop terminating... [2023-03-09 12:32:10,688][269850] Saving /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000152589_2500018176.pth... [2023-03-09 12:32:10,688][269569] Runner profile tree view: main_loop: 46.0524 [2023-03-09 12:32:10,689][269569] Collected {0: 2500018176}, FPS: 0.0 [2023-03-09 12:32:10,683][270145] EvtLoop [rollout_proc51_evt_loop, process=rollout_proc51] unhandled exception in slot='init' connected to emitter=Emitter(object_id='Sampler', signal_name='_inference_workers_initialized'), args=() Traceback (most recent call last): File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 228, in _game_init self.game.init() vizdoom.vizdoom.ViZDoomErrorException: Unexpected ViZDoom instance crash. During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/signal_slot/signal_slot.py", line 355, in _process_signal slot_callable(*args) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/rollout_worker.py", line 150, in init env_runner.init(self.timing) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 418, in init self._reset() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 430, in _reset observations, info = e.reset(seed=seed) # new way of doing seeding since Gym 0.26.0 File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 323, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 125, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 110, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/scenario_wrappers/gathering_reward_shaping.py", line 30, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 379, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/envs/env_wrappers.py", line 84, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 323, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/multiplayer_stats.py", line 51, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 323, in reset self._ensure_initialized() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 274, in _ensure_initialized self.initialize() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 269, in initialize self._game_init() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 244, in _game_init raise EnvCriticalError() sample_factory.envs.env_utils.EnvCriticalError [2023-03-09 12:32:10,674][270093] EvtLoop [rollout_proc33_evt_loop, process=rollout_proc33] unhandled exception in slot='init' connected to emitter=Emitter(object_id='Sampler', signal_name='_inference_workers_initialized'), args=() Traceback (most recent call last): File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/signal_slot/signal_slot.py", line 355, in _process_signal slot_callable(*args) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/rollout_worker.py", line 150, in init env_runner.init(self.timing) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 418, in init self._reset() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 439, in _reset observations, rew, terminated, truncated, info = e.step(actions) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 319, in step return self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 129, in step obs, rew, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 115, in step obs, rew, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/scenario_wrappers/gathering_reward_shaping.py", line 33, in step observation, reward, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 384, in step observation, reward, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/envs/env_wrappers.py", line 88, in step obs, reward, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 319, in step return self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/multiplayer_stats.py", line 54, in step obs, reward, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 452, in step reward = self.game.make_action(actions_flattened, self.skip_frames) vizdoom.vizdoom.ViZDoomUnexpectedExitException: Controlled ViZDoom instance exited unexpectedly. [2023-03-09 12:32:10,685][270142] EvtLoop [rollout_proc66_evt_loop, process=rollout_proc66] unhandled exception in slot='init' connected to emitter=Emitter(object_id='Sampler', signal_name='_inference_workers_initialized'), args=() Traceback (most recent call last): File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/signal_slot/signal_slot.py", line 355, in _process_signal slot_callable(*args) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/rollout_worker.py", line 150, in init env_runner.init(self.timing) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 418, in init self._reset() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 439, in _reset observations, rew, terminated, truncated, info = e.step(actions) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 319, in step return self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 129, in step obs, rew, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 115, in step obs, rew, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/scenario_wrappers/gathering_reward_shaping.py", line 33, in step observation, reward, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 384, in step observation, reward, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/envs/env_wrappers.py", line 88, in step obs, reward, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 319, in step return self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/multiplayer_stats.py", line 54, in step obs, reward, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 452, in step reward = self.game.make_action(actions_flattened, self.skip_frames) vizdoom.vizdoom.SignalException: Signal SIGINT received. ViZDoom instance has been closed. [2023-03-09 12:32:10,715][270145] Unhandled exception in evt loop rollout_proc51_evt_loop [2023-03-09 12:32:10,677][270473] EvtLoop [rollout_proc122_evt_loop, process=rollout_proc122] unhandled exception in slot='init' connected to emitter=Emitter(object_id='Sampler', signal_name='_inference_workers_initialized'), args=() Traceback (most recent call last): File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 228, in _game_init self.game.init() vizdoom.vizdoom.SignalException: Signal SIGINT received. ViZDoom instance has been closed. During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/signal_slot/signal_slot.py", line 355, in _process_signal slot_callable(*args) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/rollout_worker.py", line 150, in init env_runner.init(self.timing) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 418, in init self._reset() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 430, in _reset observations, info = e.reset(seed=seed) # new way of doing seeding since Gym 0.26.0 File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 323, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 125, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 110, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/scenario_wrappers/gathering_reward_shaping.py", line 30, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 379, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/envs/env_wrappers.py", line 84, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 323, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/multiplayer_stats.py", line 51, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 323, in reset self._ensure_initialized() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 274, in _ensure_initialized self.initialize() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 269, in initialize self._game_init() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 244, in _game_init raise EnvCriticalError() sample_factory.envs.env_utils.EnvCriticalError [2023-03-09 12:32:10,709][270014] EvtLoop [rollout_proc38_evt_loop, process=rollout_proc38] unhandled exception in slot='init' connected to emitter=Emitter(object_id='Sampler', signal_name='_inference_workers_initialized'), args=() Traceback (most recent call last): File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/signal_slot/signal_slot.py", line 355, in _process_signal slot_callable(*args) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/rollout_worker.py", line 150, in init env_runner.init(self.timing) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 418, in init self._reset() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 439, in _reset observations, rew, terminated, truncated, info = e.step(actions) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 319, in step return self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 129, in step obs, rew, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 115, in step obs, rew, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/scenario_wrappers/gathering_reward_shaping.py", line 33, in step observation, reward, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 384, in step observation, reward, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/envs/env_wrappers.py", line 88, in step obs, reward, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 319, in step return self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/multiplayer_stats.py", line 54, in step obs, reward, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 452, in step reward = self.game.make_action(actions_flattened, self.skip_frames) vizdoom.vizdoom.SignalException: Signal SIGINT received. ViZDoom instance has been closed. [2023-03-09 12:32:10,680][270144] EvtLoop [rollout_proc55_evt_loop, process=rollout_proc55] unhandled exception in slot='init' connected to emitter=Emitter(object_id='Sampler', signal_name='_inference_workers_initialized'), args=() Traceback (most recent call last): File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 228, in _game_init self.game.init() vizdoom.vizdoom.SignalException: Signal SIGINT received. ViZDoom instance has been closed. During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/signal_slot/signal_slot.py", line 355, in _process_signal slot_callable(*args) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/rollout_worker.py", line 150, in init env_runner.init(self.timing) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 418, in init self._reset() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 430, in _reset observations, info = e.reset(seed=seed) # new way of doing seeding since Gym 0.26.0 File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 323, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 125, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 110, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/scenario_wrappers/gathering_reward_shaping.py", line 30, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 379, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/envs/env_wrappers.py", line 84, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 323, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/multiplayer_stats.py", line 51, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 323, in reset self._ensure_initialized() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 274, in _ensure_initialized self.initialize() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 269, in initialize self._game_init() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 244, in _game_init raise EnvCriticalError() sample_factory.envs.env_utils.EnvCriticalError [2023-03-09 12:32:10,715][270093] Unhandled exception Controlled ViZDoom instance exited unexpectedly. in evt loop rollout_proc33_evt_loop [2023-03-09 12:32:10,715][270142] Unhandled exception Signal SIGINT received. ViZDoom instance has been closed. in evt loop rollout_proc66_evt_loop [2023-03-09 12:32:10,670][270623] EvtLoop [rollout_proc123_evt_loop, process=rollout_proc123] unhandled exception in slot='init' connected to emitter=Emitter(object_id='Sampler', signal_name='_inference_workers_initialized'), args=() Traceback (most recent call last): File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 228, in _game_init self.game.init() vizdoom.vizdoom.SignalException: Signal SIGINT received. ViZDoom instance has been closed. During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/signal_slot/signal_slot.py", line 355, in _process_signal slot_callable(*args) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/rollout_worker.py", line 150, in init env_runner.init(self.timing) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 418, in init self._reset() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 430, in _reset observations, info = e.reset(seed=seed) # new way of doing seeding since Gym 0.26.0 File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 323, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 125, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 110, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/scenario_wrappers/gathering_reward_shaping.py", line 30, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 379, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/envs/env_wrappers.py", line 84, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 323, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/multiplayer_stats.py", line 51, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 323, in reset self._ensure_initialized() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 274, in _ensure_initialized self.initialize() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 269, in initialize self._game_init() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 244, in _game_init raise EnvCriticalError() sample_factory.envs.env_utils.EnvCriticalError [2023-03-09 12:32:10,715][270473] Unhandled exception in evt loop rollout_proc122_evt_loop [2023-03-09 12:32:10,715][270014] Unhandled exception Signal SIGINT received. ViZDoom instance has been closed. in evt loop rollout_proc38_evt_loop [2023-03-09 12:32:10,715][270144] Unhandled exception in evt loop rollout_proc55_evt_loop [2023-03-09 12:32:10,680][270127] EvtLoop [rollout_proc80_evt_loop, process=rollout_proc80] unhandled exception in slot='init' connected to emitter=Emitter(object_id='Sampler', signal_name='_inference_workers_initialized'), args=() Traceback (most recent call last): File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/signal_slot/signal_slot.py", line 355, in _process_signal slot_callable(*args) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/rollout_worker.py", line 150, in init env_runner.init(self.timing) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 418, in init self._reset() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 439, in _reset observations, rew, terminated, truncated, info = e.step(actions) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 319, in step return self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 129, in step obs, rew, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 115, in step obs, rew, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/scenario_wrappers/gathering_reward_shaping.py", line 33, in step observation, reward, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 384, in step observation, reward, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/envs/env_wrappers.py", line 88, in step obs, reward, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 319, in step return self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/multiplayer_stats.py", line 54, in step obs, reward, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 452, in step reward = self.game.make_action(actions_flattened, self.skip_frames) vizdoom.vizdoom.SignalException: Signal SIGINT received. ViZDoom instance has been closed. [2023-03-09 12:32:10,685][270934] EvtLoop [rollout_proc94_evt_loop, process=rollout_proc94] unhandled exception in slot='init' connected to emitter=Emitter(object_id='Sampler', signal_name='_inference_workers_initialized'), args=() Traceback (most recent call last): File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/signal_slot/signal_slot.py", line 355, in _process_signal slot_callable(*args) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/rollout_worker.py", line 150, in init env_runner.init(self.timing) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 418, in init self._reset() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 439, in _reset observations, rew, terminated, truncated, info = e.step(actions) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 319, in step return self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 129, in step obs, rew, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 115, in step obs, rew, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/scenario_wrappers/gathering_reward_shaping.py", line 33, in step observation, reward, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 384, in step observation, reward, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/envs/env_wrappers.py", line 88, in step obs, reward, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 319, in step return self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/multiplayer_stats.py", line 54, in step obs, reward, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 452, in step reward = self.game.make_action(actions_flattened, self.skip_frames) vizdoom.vizdoom.SignalException: Signal SIGINT received. ViZDoom instance has been closed. [2023-03-09 12:32:10,685][270109] EvtLoop [rollout_proc31_evt_loop, process=rollout_proc31] unhandled exception in slot='init' connected to emitter=Emitter(object_id='Sampler', signal_name='_inference_workers_initialized'), args=() Traceback (most recent call last): File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 228, in _game_init self.game.init() vizdoom.vizdoom.SignalException: Signal SIGINT received. ViZDoom instance has been closed. During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/signal_slot/signal_slot.py", line 355, in _process_signal slot_callable(*args) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/rollout_worker.py", line 150, in init env_runner.init(self.timing) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 418, in init self._reset() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 430, in _reset observations, info = e.reset(seed=seed) # new way of doing seeding since Gym 0.26.0 File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 323, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 125, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 110, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/scenario_wrappers/gathering_reward_shaping.py", line 30, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 379, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/envs/env_wrappers.py", line 84, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 323, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/multiplayer_stats.py", line 51, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 323, in reset self._ensure_initialized() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 274, in _ensure_initialized self.initialize() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 269, in initialize self._game_init() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 244, in _game_init raise EnvCriticalError() sample_factory.envs.env_utils.EnvCriticalError [2023-03-09 12:32:10,669][270110] EvtLoop [rollout_proc25_evt_loop, process=rollout_proc25] unhandled exception in slot='init' connected to emitter=Emitter(object_id='Sampler', signal_name='_inference_workers_initialized'), args=() Traceback (most recent call last): File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/signal_slot/signal_slot.py", line 355, in _process_signal slot_callable(*args) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/rollout_worker.py", line 150, in init env_runner.init(self.timing) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 418, in init self._reset() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 439, in _reset observations, rew, terminated, truncated, info = e.step(actions) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 319, in step return self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 129, in step obs, rew, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 115, in step obs, rew, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/scenario_wrappers/gathering_reward_shaping.py", line 33, in step observation, reward, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 384, in step observation, reward, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/envs/env_wrappers.py", line 88, in step obs, reward, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 319, in step return self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/multiplayer_stats.py", line 54, in step obs, reward, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 452, in step reward = self.game.make_action(actions_flattened, self.skip_frames) vizdoom.vizdoom.SignalException: Signal SIGINT received. ViZDoom instance has been closed. [2023-03-09 12:32:10,682][270139] EvtLoop [rollout_proc75_evt_loop, process=rollout_proc75] unhandled exception in slot='init' connected to emitter=Emitter(object_id='Sampler', signal_name='_inference_workers_initialized'), args=() Traceback (most recent call last): File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 228, in _game_init self.game.init() vizdoom.vizdoom.SignalException: Signal SIGINT received. ViZDoom instance has been closed. During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/signal_slot/signal_slot.py", line 355, in _process_signal slot_callable(*args) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/rollout_worker.py", line 150, in init env_runner.init(self.timing) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 418, in init self._reset() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 430, in _reset observations, info = e.reset(seed=seed) # new way of doing seeding since Gym 0.26.0 File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 323, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 125, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 110, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/scenario_wrappers/gathering_reward_shaping.py", line 30, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 379, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/envs/env_wrappers.py", line 84, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 323, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/multiplayer_stats.py", line 51, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 323, in reset self._ensure_initialized() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 274, in _ensure_initialized self.initialize() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 269, in initialize self._game_init() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 244, in _game_init raise EnvCriticalError() sample_factory.envs.env_utils.EnvCriticalError [2023-03-09 12:32:10,716][270623] Unhandled exception in evt loop rollout_proc123_evt_loop [2023-03-09 12:32:10,679][270155] EvtLoop [rollout_proc70_evt_loop, process=rollout_proc70] unhandled exception in slot='init' connected to emitter=Emitter(object_id='Sampler', signal_name='_inference_workers_initialized'), args=() Traceback (most recent call last): File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/signal_slot/signal_slot.py", line 355, in _process_signal slot_callable(*args) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/rollout_worker.py", line 150, in init env_runner.init(self.timing) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 418, in init self._reset() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 439, in _reset observations, rew, terminated, truncated, info = e.step(actions) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 319, in step return self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 129, in step obs, rew, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 115, in step obs, rew, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/scenario_wrappers/gathering_reward_shaping.py", line 33, in step observation, reward, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 384, in step observation, reward, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/envs/env_wrappers.py", line 88, in step obs, reward, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 319, in step return self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/multiplayer_stats.py", line 54, in step obs, reward, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 452, in step reward = self.game.make_action(actions_flattened, self.skip_frames) vizdoom.vizdoom.SignalException: Signal SIGINT received. ViZDoom instance has been closed. [2023-03-09 12:32:10,716][270109] Unhandled exception in evt loop rollout_proc31_evt_loop [2023-03-09 12:32:10,716][270139] Unhandled exception in evt loop rollout_proc75_evt_loop [2023-03-09 12:32:10,683][270080] EvtLoop [rollout_proc3_evt_loop, process=rollout_proc3] unhandled exception in slot='init' connected to emitter=Emitter(object_id='Sampler', signal_name='_inference_workers_initialized'), args=() Traceback (most recent call last): File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 228, in _game_init self.game.init() vizdoom.vizdoom.SignalException: Signal SIGINT received. ViZDoom instance has been closed. During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/signal_slot/signal_slot.py", line 355, in _process_signal slot_callable(*args) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/rollout_worker.py", line 150, in init env_runner.init(self.timing) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 418, in init self._reset() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 430, in _reset observations, info = e.reset(seed=seed) # new way of doing seeding since Gym 0.26.0 File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 323, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 125, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 110, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/scenario_wrappers/gathering_reward_shaping.py", line 30, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 379, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/envs/env_wrappers.py", line 84, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 323, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/multiplayer_stats.py", line 51, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 323, in reset self._ensure_initialized() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 274, in _ensure_initialized self.initialize() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 269, in initialize self._game_init() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 244, in _game_init raise EnvCriticalError() sample_factory.envs.env_utils.EnvCriticalError [2023-03-09 12:32:10,680][270160] EvtLoop [rollout_proc92_evt_loop, process=rollout_proc92] unhandled exception in slot='init' connected to emitter=Emitter(object_id='Sampler', signal_name='_inference_workers_initialized'), args=() Traceback (most recent call last): File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 228, in _game_init self.game.init() vizdoom.vizdoom.SignalException: Signal SIGINT received. ViZDoom instance has been closed. During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/signal_slot/signal_slot.py", line 355, in _process_signal slot_callable(*args) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/rollout_worker.py", line 150, in init env_runner.init(self.timing) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 418, in init self._reset() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 430, in _reset observations, info = e.reset(seed=seed) # new way of doing seeding since Gym 0.26.0 File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 323, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 125, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 110, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/scenario_wrappers/gathering_reward_shaping.py", line 30, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 379, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/envs/env_wrappers.py", line 84, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 323, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/multiplayer_stats.py", line 51, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 323, in reset self._ensure_initialized() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 274, in _ensure_initialized self.initialize() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 269, in initialize self._game_init() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 244, in _game_init raise EnvCriticalError() sample_factory.envs.env_utils.EnvCriticalError [2023-03-09 12:32:10,721][270160] Unhandled exception in evt loop rollout_proc92_evt_loop [2023-03-09 12:32:10,716][270934] Unhandled exception Signal SIGINT received. ViZDoom instance has been closed. in evt loop rollout_proc94_evt_loop [2023-03-09 12:32:10,674][270103] EvtLoop [rollout_proc10_evt_loop, process=rollout_proc10] unhandled exception in slot='init' connected to emitter=Emitter(object_id='Sampler', signal_name='_inference_workers_initialized'), args=() Traceback (most recent call last): File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/signal_slot/signal_slot.py", line 355, in _process_signal slot_callable(*args) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/rollout_worker.py", line 150, in init env_runner.init(self.timing) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 418, in init self._reset() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 439, in _reset observations, rew, terminated, truncated, info = e.step(actions) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 319, in step return self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 129, in step obs, rew, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 115, in step obs, rew, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/scenario_wrappers/gathering_reward_shaping.py", line 33, in step observation, reward, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 384, in step observation, reward, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/envs/env_wrappers.py", line 88, in step obs, reward, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 319, in step return self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/multiplayer_stats.py", line 54, in step obs, reward, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 452, in step reward = self.game.make_action(actions_flattened, self.skip_frames) vizdoom.vizdoom.SignalException: Signal SIGINT received. ViZDoom instance has been closed. [2023-03-09 12:32:10,728][270103] Unhandled exception Signal SIGINT received. ViZDoom instance has been closed. in evt loop rollout_proc10_evt_loop [2023-03-09 12:32:10,716][270127] Unhandled exception Signal SIGINT received. ViZDoom instance has been closed. in evt loop rollout_proc80_evt_loop [2023-03-09 12:32:10,719][270080] Unhandled exception in evt loop rollout_proc3_evt_loop [2023-03-09 12:32:10,685][270126] EvtLoop [rollout_proc74_evt_loop, process=rollout_proc74] unhandled exception in slot='init' connected to emitter=Emitter(object_id='Sampler', signal_name='_inference_workers_initialized'), args=() Traceback (most recent call last): File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 228, in _game_init self.game.init() vizdoom.vizdoom.ViZDoomErrorException: Unexpected ViZDoom instance crash. During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/signal_slot/signal_slot.py", line 355, in _process_signal slot_callable(*args) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/rollout_worker.py", line 150, in init env_runner.init(self.timing) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 418, in init self._reset() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 430, in _reset observations, info = e.reset(seed=seed) # new way of doing seeding since Gym 0.26.0 File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 323, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 125, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 110, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/scenario_wrappers/gathering_reward_shaping.py", line 30, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 379, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/envs/env_wrappers.py", line 84, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 323, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/multiplayer_stats.py", line 51, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 323, in reset self._ensure_initialized() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 274, in _ensure_initialized self.initialize() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 269, in initialize self._game_init() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 244, in _game_init raise EnvCriticalError() sample_factory.envs.env_utils.EnvCriticalError [2023-03-09 12:32:10,729][270126] Unhandled exception in evt loop rollout_proc74_evt_loop [2023-03-09 12:32:10,716][270155] Unhandled exception Signal SIGINT received. ViZDoom instance has been closed. in evt loop rollout_proc70_evt_loop [2023-03-09 12:32:10,716][270110] Unhandled exception Signal SIGINT received. ViZDoom instance has been closed. in evt loop rollout_proc25_evt_loop [2023-03-09 12:32:10,735][270001] Weights refcount: 2 0 [2023-03-09 12:32:10,736][270001] Stopping InferenceWorker_p0-w0... [2023-03-09 12:32:10,736][270001] Loop inference_proc0-0_evt_loop terminating... [2023-03-09 12:32:10,728][270015] EvtLoop [rollout_proc35_evt_loop, process=rollout_proc35] unhandled exception in slot='init' connected to emitter=Emitter(object_id='Sampler', signal_name='_inference_workers_initialized'), args=() Traceback (most recent call last): File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/signal_slot/signal_slot.py", line 355, in _process_signal slot_callable(*args) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/rollout_worker.py", line 150, in init env_runner.init(self.timing) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 418, in init self._reset() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 439, in _reset observations, rew, terminated, truncated, info = e.step(actions) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 319, in step return self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 129, in step obs, rew, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 115, in step obs, rew, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/scenario_wrappers/gathering_reward_shaping.py", line 33, in step observation, reward, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 384, in step observation, reward, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/envs/env_wrappers.py", line 88, in step obs, reward, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 319, in step return self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/multiplayer_stats.py", line 54, in step obs, reward, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 452, in step reward = self.game.make_action(actions_flattened, self.skip_frames) vizdoom.vizdoom.SignalException: Signal SIGINT received. ViZDoom instance has been closed. [2023-03-09 12:32:10,736][270015] Unhandled exception Signal SIGINT received. ViZDoom instance has been closed. in evt loop rollout_proc35_evt_loop [2023-03-09 12:32:10,756][269850] Stopping LearnerWorker_p0... [2023-03-09 12:32:10,756][269850] Loop learner_proc0_evt_loop terminating... [2023-03-09 12:32:10,781][269569] Loading existing experiment configuration from /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/config.json [2023-03-09 12:32:10,783][269569] Overriding arg 'num_workers' with value 1 passed from command line [2023-03-09 12:32:10,788][269569] Adding new argument 'no_render'=True that is not in the saved config file! [2023-03-09 12:32:10,789][269569] Adding new argument 'save_video'=True that is not in the saved config file! [2023-03-09 12:32:10,790][269569] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file! [2023-03-09 12:32:10,790][269569] Adding new argument 'video_name'=None that is not in the saved config file! [2023-03-09 12:32:10,791][269569] Adding new argument 'max_num_frames'=1000000000.0 that is not in the saved config file! [2023-03-09 12:32:10,792][269569] Adding new argument 'max_num_episodes'=10 that is not in the saved config file! [2023-03-09 12:32:10,793][269569] Adding new argument 'push_to_hub'=False that is not in the saved config file! [2023-03-09 12:32:10,794][269569] Adding new argument 'hf_repository'=None that is not in the saved config file! [2023-03-09 12:32:10,794][269569] Adding new argument 'policy_index'=0 that is not in the saved config file! [2023-03-09 12:32:10,795][269569] Adding new argument 'eval_deterministic'=False that is not in the saved config file! [2023-03-09 12:32:10,795][269569] Adding new argument 'train_script'=None that is not in the saved config file! [2023-03-09 12:32:10,796][269569] Adding new argument 'enjoy_script'=None that is not in the saved config file! [2023-03-09 12:32:10,796][269569] Using frameskip 1 and render_action_repeat=4 for evaluation [2023-03-09 12:32:10,804][269569] Doom resolution: 160x120, resize resolution: (128, 72) [2023-03-09 12:32:10,805][269569] RunningMeanStd input shape: (3, 72, 128) [2023-03-09 12:32:10,806][269569] RunningMeanStd input shape: (1,) [2023-03-09 12:32:10,817][269569] ConvEncoder: input_channels=3 [2023-03-09 12:32:10,883][270152] Decorrelating experience for 512 frames... [2023-03-09 12:32:10,910][269569] Conv encoder output size: 512 [2023-03-09 12:32:10,911][269569] Policy head output size: 512 [2023-03-09 12:32:10,920][270699] Decorrelating experience for 576 frames... [2023-03-09 12:32:10,933][270104] Decorrelating experience for 448 frames... [2023-03-09 12:32:10,939][270094] Decorrelating experience for 672 frames... [2023-03-09 12:32:10,944][271517] Decorrelating experience for 384 frames... [2023-03-09 12:32:10,945][270105] Decorrelating experience for 320 frames... [2023-03-09 12:32:10,948][270157] Decorrelating experience for 736 frames... [2023-03-09 12:32:10,948][270106] Decorrelating experience for 288 frames... [2023-03-09 12:32:10,949][270134] Decorrelating experience for 768 frames... [2023-03-09 12:32:11,121][270086] Decorrelating experience for 768 frames... [2023-03-09 12:32:11,149][270011] Decorrelating experience for 320 frames... [2023-03-09 12:32:11,166][270010] Decorrelating experience for 416 frames... [2023-03-09 12:32:11,182][270007] Decorrelating experience for 416 frames... [2023-03-09 12:32:11,187][270115] Decorrelating experience for 800 frames... [2023-03-09 12:32:11,192][270146] Decorrelating experience for 512 frames... [2023-03-09 12:32:11,193][270012] Decorrelating experience for 608 frames... [2023-03-09 12:32:11,193][270121] Decorrelating experience for 608 frames... [2023-03-09 12:32:11,194][270136] Decorrelating experience for 448 frames... [2023-03-09 12:32:11,367][270098] Decorrelating experience for 480 frames... [2023-03-09 12:32:11,384][270095] Decorrelating experience for 448 frames... [2023-03-09 12:32:11,393][270129] Decorrelating experience for 160 frames... [2023-03-09 12:32:11,402][270151] Decorrelating experience for 320 frames... [2023-03-09 12:32:11,417][270120] Decorrelating experience for 576 frames... [2023-03-09 12:32:11,422][270108] Decorrelating experience for 576 frames... [2023-03-09 12:32:11,426][270152] Decorrelating experience for 544 frames... [2023-03-09 12:32:11,455][270293] Decorrelating experience for 896 frames... [2023-03-09 12:32:11,566][277995] Decorrelating experience for 320 frames... [2023-03-09 12:32:11,599][270118] Decorrelating experience for 352 frames... [2023-03-09 12:32:11,619][270135] Decorrelating experience for 864 frames... [2023-03-09 12:32:11,623][270156] Decorrelating experience for 128 frames... [2023-03-09 12:32:11,647][270136] Decorrelating experience for 480 frames... [2023-03-09 12:32:11,647][270129] Decorrelating experience for 192 frames... [2023-03-09 12:32:11,674][270088] Decorrelating experience for 672 frames... [2023-03-09 12:32:11,674][270164] Decorrelating experience for 672 frames... [2023-03-09 12:32:11,719][270086] Decorrelating experience for 800 frames... [2023-03-09 12:32:11,792][270134] Decorrelating experience for 800 frames... [2023-03-09 12:32:11,813][271375] Decorrelating experience for 256 frames... [2023-03-09 12:32:11,819][270541] Decorrelating experience for 128 frames... [2023-03-09 12:32:11,828][270124] Decorrelating experience for 352 frames... [2023-03-09 12:32:11,877][270156] Decorrelating experience for 160 frames... [2023-03-09 12:32:11,898][270151] Decorrelating experience for 352 frames... [2023-03-09 12:32:11,901][270108] Decorrelating experience for 608 frames... [2023-03-09 12:32:11,936][270120] Decorrelating experience for 608 frames... [2023-03-09 12:32:11,970][270118] Decorrelating experience for 384 frames... [2023-03-09 12:32:12,020][270146] Decorrelating experience for 544 frames... [2023-03-09 12:32:12,022][270152] Decorrelating experience for 576 frames... [2023-03-09 12:32:12,050][270154] Decorrelating experience for 416 frames... [2023-03-09 12:32:12,050][270123] Decorrelating experience for 448 frames... [2023-03-09 12:32:12,096][270115] Decorrelating experience for 832 frames... [2023-03-09 12:32:12,146][270010] Decorrelating experience for 448 frames... [2023-03-09 12:32:12,158][270007] Decorrelating experience for 448 frames... [2023-03-09 12:32:12,198][270158] Decorrelating experience for 608 frames... [2023-03-09 12:32:12,243][270099] Decorrelating experience for 480 frames... [2023-03-09 12:32:12,244][270106] Decorrelating experience for 320 frames... [2023-03-09 12:32:12,278][270012] Decorrelating experience for 640 frames... [2023-03-09 12:32:12,309][270136] Decorrelating experience for 512 frames... [2023-03-09 12:32:12,338][270137] Decorrelating experience for 512 frames... [2023-03-09 12:32:12,372][270554] Decorrelating experience for 320 frames... [2023-03-09 12:32:12,397][270120] Decorrelating experience for 640 frames... [2023-03-09 12:32:12,449][270944] Decorrelating experience for 768 frames... [2023-03-09 12:32:12,454][271224] Decorrelating experience for 576 frames... [2023-03-09 12:32:12,457][270084] Decorrelating experience for 352 frames... [2023-03-09 12:32:12,474][270152] Decorrelating experience for 608 frames... [2023-03-09 12:32:12,508][270860] Decorrelating experience for 96 frames... [2023-03-09 12:32:12,553][270009] Decorrelating experience for 544 frames... [2023-03-09 12:32:12,589][270541] Decorrelating experience for 160 frames... [2023-03-09 12:32:12,595][270135] Decorrelating experience for 896 frames... [2023-03-09 12:32:12,596][270010] Decorrelating experience for 480 frames... [2023-03-09 12:32:12,638][270146] Decorrelating experience for 576 frames... [2023-03-09 12:32:12,661][270003] Decorrelating experience for 192 frames... [2023-03-09 12:32:12,672][270233] Decorrelating experience for 544 frames... [2023-03-09 12:32:12,698][270089] Decorrelating experience for 416 frames... [2023-03-09 12:32:12,753][270137] Decorrelating experience for 544 frames... [2023-03-09 12:32:12,766][270016] Decorrelating experience for 512 frames... [2023-03-09 12:32:12,773][270011] Decorrelating experience for 352 frames... [2023-03-09 12:32:12,780][270158] Decorrelating experience for 640 frames... [2023-03-09 12:32:12,820][270124] Decorrelating experience for 384 frames... [2023-03-09 12:32:12,847][270138] Decorrelating experience for 352 frames... [2023-03-09 12:32:12,856][271224] Decorrelating experience for 608 frames... [2023-03-09 12:32:12,891][271355] Decorrelating experience for 672 frames... [2023-03-09 12:32:12,924][270596] Decorrelating experience for 320 frames... [2023-03-09 12:32:12,947][270149] Decorrelating experience for 384 frames... [2023-03-09 12:32:12,962][270106] Decorrelating experience for 352 frames... [2023-03-09 12:32:12,963][270129] Decorrelating experience for 224 frames... [2023-03-09 12:32:12,987][269569] Loading state from checkpoint /mnt/Lata/projects/samplefactory/train_dir/doom_health_w128-epw64-r32_b4096-2b/checkpoint_p0/checkpoint_000152589_2500018176.pth... [2023-03-09 12:32:13,000][270120] Decorrelating experience for 672 frames... [2023-03-09 12:32:13,037][270098] Decorrelating experience for 512 frames... [2023-03-09 12:32:13,039][270117] Decorrelating experience for 448 frames... [2023-03-09 12:32:13,040][270009] Decorrelating experience for 576 frames... [2023-03-09 12:32:13,125][270099] Decorrelating experience for 512 frames... [2023-03-09 12:32:13,130][270123] Decorrelating experience for 480 frames... [2023-03-09 12:32:13,143][270472] Decorrelating experience for 416 frames... [2023-03-09 12:32:13,164][270556] Decorrelating experience for 416 frames... [2023-03-09 12:32:13,164][270138] Decorrelating experience for 384 frames... [2023-03-09 12:32:13,211][270121] Decorrelating experience for 640 frames... [2023-03-09 12:32:13,223][270135] Decorrelating experience for 928 frames... [2023-03-09 12:32:13,238][270016] Decorrelating experience for 544 frames... [2023-03-09 12:32:13,246][270113] Decorrelating experience for 384 frames... [2023-03-09 12:32:13,315][270162] Decorrelating experience for 736 frames... [2023-03-09 12:32:13,319][270945] Decorrelating experience for 288 frames... [2023-03-09 12:32:13,351][270150] Decorrelating experience for 384 frames... [2023-03-09 12:32:13,390][270152] Decorrelating experience for 640 frames... [2023-03-09 12:32:13,408][270164] Decorrelating experience for 704 frames... [2023-03-09 12:32:13,411][270118] Decorrelating experience for 416 frames... [2023-03-09 12:32:13,429][271017] Decorrelating experience for 512 frames... [2023-03-09 12:32:13,477][270009] Decorrelating experience for 608 frames... [2023-03-09 12:32:13,500][270007] Decorrelating experience for 480 frames... [2023-03-09 12:32:13,555][270114] Decorrelating experience for 512 frames... [2023-03-09 12:32:13,563][270131] Decorrelating experience for 320 frames... [2023-03-09 12:32:13,591][270146] Decorrelating experience for 608 frames... [2023-03-09 12:32:13,608][270554] Decorrelating experience for 352 frames... [2023-03-09 12:32:13,612][270596] Decorrelating experience for 352 frames... [2023-03-09 12:32:13,612][270157] Decorrelating experience for 768 frames... [2023-03-09 12:32:13,684][270125] Decorrelating experience for 768 frames... [2023-03-09 12:32:13,748][270135] Decorrelating experience for 960 frames... [2023-03-09 12:32:13,763][270162] Decorrelating experience for 768 frames... [2023-03-09 12:32:13,790][270556] Decorrelating experience for 448 frames... [2023-03-09 12:32:13,794][270123] Decorrelating experience for 512 frames... [2023-03-09 12:32:13,797][271224] Decorrelating experience for 640 frames... [2023-03-09 12:32:13,805][270016] Decorrelating experience for 576 frames... [2023-03-09 12:32:13,850][270152] Decorrelating experience for 672 frames... [2023-03-09 12:32:13,922][270554] Decorrelating experience for 384 frames... [2023-03-09 12:32:13,931][270147] Decorrelating experience for 352 frames... [2023-03-09 12:32:13,931][270090] Decorrelating experience for 576 frames... [2023-03-09 12:32:13,970][270009] Decorrelating experience for 640 frames... [2023-03-09 12:32:13,983][270113] Decorrelating experience for 416 frames... [2023-03-09 12:32:13,992][277995] Decorrelating experience for 352 frames... [2023-03-09 12:32:13,998][271017] Decorrelating experience for 544 frames... [2023-03-09 12:32:14,060][270121] Decorrelating experience for 672 frames... [2023-03-09 12:32:14,122][270124] Decorrelating experience for 416 frames... [2023-03-09 12:32:14,123][270098] Decorrelating experience for 544 frames... [2023-03-09 12:32:14,140][270120] Decorrelating experience for 704 frames... [2023-03-09 12:32:14,151][270146] Decorrelating experience for 640 frames... [2023-03-09 12:32:14,184][270157] Decorrelating experience for 800 frames... [2023-03-09 12:32:14,196][270148] Decorrelating experience for 800 frames... [2023-03-09 12:32:14,205][270002] Decorrelating experience for 224 frames... [2023-03-09 12:32:14,245][270011] Decorrelating experience for 384 frames... [2023-03-09 12:32:14,308][270943] Decorrelating experience for 352 frames... [2023-03-09 12:32:14,317][270116] Decorrelating experience for 640 frames... [2023-03-09 12:32:14,319][270113] Decorrelating experience for 448 frames... [2023-03-09 12:32:14,341][270122] Decorrelating experience for 768 frames... [2023-03-09 12:32:14,386][270162] Decorrelating experience for 800 frames... [2023-03-09 12:32:14,400][271017] Decorrelating experience for 576 frames... [2023-03-09 12:32:14,401][270009] Decorrelating experience for 672 frames... [2023-03-09 12:32:14,427][270149] Decorrelating experience for 416 frames... [2023-03-09 12:32:14,442][270123] Decorrelating experience for 544 frames... [2023-03-09 12:32:14,453][270100] Decorrelating experience for 576 frames... [2023-03-09 12:32:14,494][270105] Decorrelating experience for 352 frames... [2023-03-09 12:32:14,503][270137] Decorrelating experience for 576 frames... [2023-03-09 12:32:14,504][269569] Num frames 100... [2023-03-09 12:32:14,520][270090] Decorrelating experience for 608 frames... [2023-03-09 12:32:14,541][270556] Decorrelating experience for 480 frames... [2023-03-09 12:32:14,572][270011] Decorrelating experience for 416 frames... [2023-03-09 12:32:14,591][269569] Num frames 200... [2023-03-09 12:32:14,624][270006] Decorrelating experience for 384 frames... [2023-03-09 12:32:14,625][270124] Decorrelating experience for 448 frames... [2023-03-09 12:32:14,636][270161] Decorrelating experience for 512 frames... [2023-03-09 12:32:14,674][269569] Num frames 300... [2023-03-09 12:32:14,680][270094] Decorrelating experience for 704 frames... [2023-03-09 12:32:14,690][270128] Decorrelating experience for 512 frames... [2023-03-09 12:32:14,690][277995] Decorrelating experience for 384 frames... [2023-03-09 12:32:14,728][270148] Decorrelating experience for 832 frames... [2023-03-09 12:32:14,751][270147] Decorrelating experience for 384 frames... [2023-03-09 12:32:14,758][270016] Decorrelating experience for 608 frames... [2023-03-09 12:32:14,763][269569] Num frames 400... [2023-03-09 12:32:14,816][270118] Decorrelating experience for 448 frames... [2023-03-09 12:32:14,822][270113] Decorrelating experience for 480 frames... [2023-03-09 12:32:14,829][270699] Decorrelating experience for 608 frames... [2023-03-09 12:32:14,853][269569] Num frames 500... [2023-03-09 12:32:14,866][270012] Decorrelating experience for 672 frames... [2023-03-09 12:32:14,877][270943] Decorrelating experience for 384 frames... [2023-03-09 12:32:14,886][270005] Decorrelating experience for 192 frames... [2023-03-09 12:32:14,926][270162] Decorrelating experience for 832 frames... [2023-03-09 12:32:14,944][269569] Num frames 600... [2023-03-09 12:32:14,955][270089] Decorrelating experience for 448 frames... [2023-03-09 12:32:14,959][270115] Decorrelating experience for 864 frames... [2023-03-09 12:32:14,983][270124] Decorrelating experience for 480 frames... [2023-03-09 12:32:15,000][270152] Decorrelating experience for 704 frames... [2023-03-09 12:32:15,010][270105] Decorrelating experience for 384 frames... [2023-03-09 12:32:15,043][269569] Num frames 700... [2023-03-09 12:32:15,049][270944] Decorrelating experience for 800 frames... [2023-03-09 12:32:15,070][270117] Decorrelating experience for 480 frames... [2023-03-09 12:32:15,073][270514] Decorrelating experience for 320 frames... [2023-03-09 12:32:15,131][270123] Decorrelating experience for 576 frames... [2023-03-09 12:32:15,136][269569] Num frames 800... [2023-03-09 12:32:15,137][270092] Another process currently holds the lock /tmp/sf2_rolo/doom_009.lockfile, attempt: 1 [2023-03-09 12:32:15,153][271375] Decorrelating experience for 288 frames... [2023-03-09 12:32:15,166][270161] Decorrelating experience for 544 frames... [2023-03-09 12:32:15,187][270009] Decorrelating experience for 704 frames... [2023-03-09 12:32:15,189][270129] Decorrelating experience for 256 frames... [2023-03-09 12:32:15,230][270596] Decorrelating experience for 384 frames... [2023-03-09 12:32:15,253][269569] Num frames 900... [2023-03-09 12:32:15,314][270150] Decorrelating experience for 416 frames... [2023-03-09 12:32:15,337][270163] Decorrelating experience for 736 frames... [2023-03-09 12:32:15,346][270116] Decorrelating experience for 672 frames... [2023-03-09 12:32:15,352][269569] Num frames 1000... [2023-03-09 12:32:15,363][270097] Decorrelating experience for 512 frames... [2023-03-09 12:32:15,376][277995] Decorrelating experience for 416 frames... [2023-03-09 12:32:15,376][270157] Decorrelating experience for 832 frames... [2023-03-09 12:32:15,394][270699] Decorrelating experience for 640 frames... [2023-03-09 12:32:15,413][269981] Decorrelating experience for 640 frames... [2023-03-09 12:32:15,446][271375] Decorrelating experience for 320 frames... [2023-03-09 12:32:15,454][269569] Num frames 1100... [2023-03-09 12:32:15,468][270129] Decorrelating experience for 288 frames... [2023-03-09 12:32:15,511][270100] Decorrelating experience for 608 frames... [2023-03-09 12:32:15,521][270293] Decorrelating experience for 928 frames... [2023-03-09 12:32:15,551][269569] Num frames 1200... [2023-03-09 12:32:15,557][270161] Decorrelating experience for 576 frames... [2023-03-09 12:32:15,557][271017] Decorrelating experience for 608 frames... [2023-03-09 12:32:15,566][270137] Decorrelating experience for 608 frames... [2023-03-09 12:32:15,635][270099] Decorrelating experience for 544 frames... [2023-03-09 12:32:15,652][270117] Decorrelating experience for 512 frames... [2023-03-09 12:32:15,654][269569] Num frames 1300... [2023-03-09 12:32:15,665][270124] Decorrelating experience for 512 frames... [2023-03-09 12:32:15,690][270009] Decorrelating experience for 736 frames... [2023-03-09 12:32:15,696][270472] Decorrelating experience for 448 frames... [2023-03-09 12:32:15,745][270097] Decorrelating experience for 544 frames... [2023-03-09 12:32:15,745][270557] Decorrelating experience for 416 frames... [2023-03-09 12:32:15,752][270012] Decorrelating experience for 704 frames... [2023-03-09 12:32:15,757][269569] Num frames 1400... [2023-03-09 12:32:15,759][270150] Decorrelating experience for 448 frames... [2023-03-09 12:32:15,820][271126] Decorrelating experience for 608 frames... [2023-03-09 12:32:15,831][270556] Decorrelating experience for 512 frames... [2023-03-09 12:32:15,851][270152] Decorrelating experience for 736 frames... [2023-03-09 12:32:15,858][269569] Num frames 1500... [2023-03-09 12:32:15,881][270123] Decorrelating experience for 608 frames... [2023-03-09 12:32:15,885][270514] Decorrelating experience for 352 frames... [2023-03-09 12:32:15,899][270115] Decorrelating experience for 896 frames... [2023-03-09 12:32:15,956][269569] Num frames 1600... [2023-03-09 12:32:15,974][270125] Decorrelating experience for 800 frames... [2023-03-09 12:32:15,975][270943] Decorrelating experience for 416 frames... [2023-03-09 12:32:15,976][269981] Decorrelating experience for 672 frames... [2023-03-09 12:32:15,976][270128] Decorrelating experience for 544 frames... [2023-03-09 12:32:16,026][271017] Decorrelating experience for 640 frames... [2023-03-09 12:32:16,045][270162] Decorrelating experience for 864 frames... [2023-03-09 12:32:16,055][269569] Num frames 1700... [2023-03-09 12:32:16,104][270555] Decorrelating experience for 128 frames... [2023-03-09 12:32:16,111][270596] Decorrelating experience for 416 frames... [2023-03-09 12:32:16,112][270084] Decorrelating experience for 384 frames... [2023-03-09 12:32:16,113][270116] Decorrelating experience for 704 frames... [2023-03-09 12:32:16,149][269569] Num frames 1800... [2023-03-09 12:32:16,171][270161] Decorrelating experience for 608 frames... [2023-03-09 12:32:16,172][270150] Decorrelating experience for 480 frames... [2023-03-09 12:32:16,201][270130] Decorrelating experience for 672 frames... [2023-03-09 12:32:16,202][270097] Decorrelating experience for 576 frames... [2023-03-09 12:32:16,231][271126] Decorrelating experience for 640 frames... [2023-03-09 12:32:16,233][269569] Num frames 1900... [2023-03-09 12:32:16,305][270157] Decorrelating experience for 864 frames... [2023-03-09 12:32:16,305][270129] Decorrelating experience for 320 frames... [2023-03-09 12:32:16,316][270293] Decorrelating experience for 960 frames... [2023-03-09 12:32:16,323][270163] Decorrelating experience for 768 frames... [2023-03-09 12:32:16,331][269569] Num frames 2000... [2023-03-09 12:32:16,369][270152] Decorrelating experience for 768 frames... [2023-03-09 12:32:16,372][270557] Decorrelating experience for 448 frames... [2023-03-09 12:32:16,404][270124] Decorrelating experience for 544 frames... [2023-03-09 12:32:16,405][270555] Decorrelating experience for 160 frames... [2023-03-09 12:32:16,405][270554] Decorrelating experience for 416 frames... [2023-03-09 12:32:16,438][269569] Num frames 2100... [2023-03-09 12:32:16,446][270101] Decorrelating experience for 384 frames... [2023-03-09 12:32:16,490][269569] Avg episode rewards: #0: 64.999, true rewards: #0: 21.000 [2023-03-09 12:32:16,491][269569] Avg episode reward: 64.999, avg true_objective: 21.000 [2023-03-09 12:32:16,514][270514] Decorrelating experience for 384 frames... [2023-03-09 12:32:16,517][270123] Decorrelating experience for 640 frames... [2023-03-09 12:32:16,524][270141] Another process currently holds the lock /tmp/sf2_rolo/doom_001.lockfile, attempt: 1 [2023-03-09 12:32:16,565][270125] Decorrelating experience for 832 frames... [2023-03-09 12:32:16,569][270115] Decorrelating experience for 928 frames... [2023-03-09 12:32:16,594][270150] Decorrelating experience for 512 frames... [2023-03-09 12:32:16,601][269569] Num frames 2200... [2023-03-09 12:32:16,615][270084] Decorrelating experience for 416 frames... [2023-03-09 12:32:16,616][270107] Decorrelating experience for 416 frames... [2023-03-09 12:32:16,617][270094] Decorrelating experience for 736 frames... [2023-03-09 12:32:16,617][270091] Decorrelating experience for 352 frames... [2023-03-09 12:32:16,647][270751] Decorrelating experience for 544 frames... [2023-03-09 12:32:16,697][269569] Num frames 2300... [2023-03-09 12:32:16,707][270009] Decorrelating experience for 768 frames... [2023-03-09 12:32:16,714][270005] Decorrelating experience for 224 frames... [2023-03-09 12:32:16,758][270097] Decorrelating experience for 608 frames... [2023-03-09 12:32:16,763][270116] Decorrelating experience for 736 frames... [2023-03-09 12:32:16,786][269569] Num frames 2400... [2023-03-09 12:32:16,803][270113] Decorrelating experience for 512 frames... [2023-03-09 12:32:16,819][270118] Decorrelating experience for 480 frames... [2023-03-09 12:32:16,834][270404] Decorrelating experience for 512 frames... [2023-03-09 12:32:16,857][271919] Decorrelating experience for 416 frames... [2023-03-09 12:32:16,862][270293] Decorrelating experience for 992 frames... [2023-03-09 12:32:16,881][269569] Num frames 2500... [2023-03-09 12:32:16,899][270106] Decorrelating experience for 384 frames... [2023-03-09 12:32:16,915][270134] Decorrelating experience for 832 frames... [2023-03-09 12:32:16,973][269569] Num frames 2600... [2023-03-09 12:32:16,982][270100] Decorrelating experience for 640 frames... [2023-03-09 12:32:17,004][270514] Decorrelating experience for 416 frames... [2023-03-09 12:32:17,006][270156] Decorrelating experience for 192 frames... [2023-03-09 12:32:17,022][270943] Decorrelating experience for 448 frames... [2023-03-09 12:32:17,027][270123] Decorrelating experience for 672 frames... [2023-03-09 12:32:17,036][270163] Decorrelating experience for 800 frames... [2023-03-09 12:32:17,041][270152] Decorrelating experience for 800 frames... [2023-03-09 12:32:17,080][269569] Num frames 2700... [2023-03-09 12:32:17,092][270161] Decorrelating experience for 640 frames... [2023-03-09 12:32:17,135][270148] Decorrelating experience for 864 frames... [2023-03-09 12:32:17,163][269569] Num frames 2800... [2023-03-09 12:32:17,170][270111] Another process currently holds the lock /tmp/sf2_rolo/doom_009.lockfile, attempt: 1 [2023-03-09 12:32:17,179][270009] Decorrelating experience for 800 frames... [2023-03-09 12:32:17,207][270124] Decorrelating experience for 576 frames... [2023-03-09 12:32:17,214][270088] Decorrelating experience for 704 frames... [2023-03-09 12:32:17,219][270157] Decorrelating experience for 896 frames... [2023-03-09 12:32:17,222][270012] Decorrelating experience for 736 frames... [2023-03-09 12:32:17,229][270106] Decorrelating experience for 416 frames... [2023-03-09 12:32:17,246][270293] Stopping RolloutWorker_w88... [2023-03-09 12:32:17,246][270293] Loop rollout_proc88_evt_loop terminating... [2023-03-09 12:32:17,247][269569] Num frames 2900... [2023-03-09 12:32:17,276][270125] Decorrelating experience for 864 frames... [2023-03-09 12:32:17,280][270554] Decorrelating experience for 448 frames... [2023-03-09 12:32:17,304][270699] Decorrelating experience for 672 frames... [2023-03-09 12:32:17,327][270094] Decorrelating experience for 768 frames... [2023-03-09 12:32:17,332][269569] Num frames 3000... [2023-03-09 12:32:17,410][270514] Decorrelating experience for 448 frames... [2023-03-09 12:32:17,421][271224] Decorrelating experience for 672 frames... [2023-03-09 12:32:17,422][269569] Num frames 3100... [2023-03-09 12:32:17,429][270164] Decorrelating experience for 736 frames... [2023-03-09 12:32:17,430][270143] Decorrelating experience for 544 frames... [2023-03-09 12:32:17,435][270116] Decorrelating experience for 768 frames... [2023-03-09 12:32:17,435][270118] Decorrelating experience for 512 frames... [2023-03-09 12:32:17,473][270117] Decorrelating experience for 544 frames... [2023-03-09 12:32:17,507][271355] Decorrelating experience for 704 frames... [2023-03-09 12:32:17,515][269569] Num frames 3200... [2023-03-09 12:32:17,533][270596] Decorrelating experience for 448 frames... [2023-03-09 12:32:17,595][270016] Decorrelating experience for 640 frames... [2023-03-09 12:32:17,608][269569] Num frames 3300... [2023-03-09 12:32:17,611][270090] Decorrelating experience for 640 frames... [2023-03-09 12:32:17,636][270156] Decorrelating experience for 224 frames... [2023-03-09 12:32:17,636][270141] Decorrelating experience for 480 frames... [2023-03-09 12:32:17,638][270100] Decorrelating experience for 672 frames... [2023-03-09 12:32:17,643][270106] Decorrelating experience for 448 frames... [2023-03-09 12:32:17,644][270943] Decorrelating experience for 480 frames... [2023-03-09 12:32:17,672][270128] Decorrelating experience for 576 frames... [2023-03-09 12:32:17,700][269569] Num frames 3400... [2023-03-09 12:32:17,706][270122] Decorrelating experience for 800 frames... [2023-03-09 12:32:17,726][270134] Decorrelating experience for 864 frames... [2023-03-09 12:32:17,786][269569] Num frames 3500... [2023-03-09 12:32:17,792][270751] Decorrelating experience for 576 frames... [2023-03-09 12:32:17,817][270135] Decorrelating experience for 992 frames... [2023-03-09 12:32:17,830][270148] Decorrelating experience for 896 frames... [2023-03-09 12:32:17,831][270096] Decorrelating experience for 576 frames... [2023-03-09 12:32:17,858][270113] Decorrelating experience for 544 frames... [2023-03-09 12:32:17,873][270117] Decorrelating experience for 576 frames... [2023-03-09 12:32:17,881][270161] Decorrelating experience for 672 frames... [2023-03-09 12:32:17,881][269569] Num frames 3600... [2023-03-09 12:32:17,889][270012] Decorrelating experience for 768 frames... [2023-03-09 12:32:17,909][270152] Decorrelating experience for 832 frames... [2023-03-09 12:32:17,968][270002] Decorrelating experience for 256 frames... [2023-03-09 12:32:17,975][269569] Num frames 3700... [2023-03-09 12:32:18,020][270092] Decorrelating experience for 224 frames... [2023-03-09 12:32:18,025][271126] Decorrelating experience for 672 frames... [2023-03-09 12:32:18,025][270114] Decorrelating experience for 544 frames... [2023-03-09 12:32:18,051][271017] Decorrelating experience for 672 frames... [2023-03-09 12:32:18,056][270099] Decorrelating experience for 576 frames... [2023-03-09 12:32:18,074][269569] Num frames 3800... [2023-03-09 12:32:18,082][270163] Decorrelating experience for 832 frames... [2023-03-09 12:32:18,099][270125] Decorrelating experience for 896 frames... [2023-03-09 12:32:18,141][270164] Decorrelating experience for 768 frames... [2023-03-09 12:32:18,158][270094] Decorrelating experience for 800 frames... [2023-03-09 12:32:18,176][269569] Num frames 3900... [2023-03-09 12:32:18,224][270135] Stopping RolloutWorker_w86... [2023-03-09 12:32:18,224][270135] Loop rollout_proc86_evt_loop terminating... [2023-03-09 12:32:18,224][270119] Decorrelating experience for 256 frames... [2023-03-09 12:32:18,225][270085] Decorrelating experience for 608 frames... [2023-03-09 12:32:18,229][270472] Decorrelating experience for 480 frames... [2023-03-09 12:32:18,239][270096] Decorrelating experience for 608 frames... [2023-03-09 12:32:18,248][270091] Decorrelating experience for 384 frames... [2023-03-09 12:32:18,256][270130] Decorrelating experience for 704 frames... [2023-03-09 12:32:18,272][269569] Num frames 4000... [2023-03-09 12:32:18,283][270116] Decorrelating experience for 800 frames... [2023-03-09 12:32:18,297][270092] Decorrelating experience for 256 frames... [2023-03-09 12:32:18,346][270122] Decorrelating experience for 832 frames... [2023-03-09 12:32:18,358][270161] Decorrelating experience for 704 frames... [2023-03-09 12:32:18,376][269569] Num frames 4100... [2023-03-09 12:32:18,443][270134] Decorrelating experience for 896 frames... [2023-03-09 12:32:18,475][277349] Decorrelating experience for 448 frames... [2023-03-09 12:32:18,475][270099] Decorrelating experience for 608 frames... [2023-03-09 12:32:18,478][270131] Decorrelating experience for 352 frames... [2023-03-09 12:32:18,479][269569] Num frames 4200... [2023-03-09 12:32:18,488][270108] Decorrelating experience for 640 frames... [2023-03-09 12:32:18,494][270557] Decorrelating experience for 480 frames... [2023-03-09 12:32:18,500][270002] Decorrelating experience for 288 frames... [2023-03-09 12:32:18,530][269569] Avg episode rewards: #0: 62.999, true rewards: #0: 21.000 [2023-03-09 12:32:18,531][269569] Avg episode reward: 62.999, avg true_objective: 21.000 [2023-03-09 12:32:18,532][270107] Decorrelating experience for 448 frames... [2023-03-09 12:32:18,544][270009] Decorrelating experience for 832 frames... [2023-03-09 12:32:18,545][270118] Decorrelating experience for 544 frames... [2023-03-09 12:32:18,630][270117] Decorrelating experience for 608 frames... [2023-03-09 12:32:18,667][269569] Num frames 4300... [2023-03-09 12:32:18,684][270541] Decorrelating experience for 192 frames... [2023-03-09 12:32:18,685][270086] Decorrelating experience for 832 frames... [2023-03-09 12:32:18,694][270012] Decorrelating experience for 800 frames... [2023-03-09 12:32:18,694][270164] Decorrelating experience for 800 frames... [2023-03-09 12:32:18,694][270125] Decorrelating experience for 928 frames... [2023-03-09 12:32:18,711][270156] Decorrelating experience for 256 frames... [2023-03-09 12:32:18,717][271517] Decorrelating experience for 416 frames... [2023-03-09 12:32:18,739][270163] Decorrelating experience for 864 frames... [2023-03-09 12:32:18,755][270472] Decorrelating experience for 512 frames... [2023-03-09 12:32:18,768][269569] Num frames 4400... [2023-03-09 12:32:18,836][270092] Decorrelating experience for 288 frames... [2023-03-09 12:32:18,861][269569] Num frames 4500... [2023-03-09 12:32:18,891][270368] Decorrelating experience for 352 frames... [2023-03-09 12:32:18,891][270162] Decorrelating experience for 896 frames... [2023-03-09 12:32:18,907][270404] Decorrelating experience for 544 frames... [2023-03-09 12:32:18,908][270120] Decorrelating experience for 736 frames... [2023-03-09 12:32:18,918][270002] Decorrelating experience for 320 frames... [2023-03-09 12:32:18,918][270122] Decorrelating experience for 864 frames... [2023-03-09 12:32:18,922][270943] Decorrelating experience for 512 frames... [2023-03-09 12:32:18,924][270003] Decorrelating experience for 224 frames... [2023-03-09 12:32:18,961][269569] Num frames 4600... [2023-03-09 12:32:18,968][271355] Decorrelating experience for 736 frames... [2023-03-09 12:32:19,046][270099] Decorrelating experience for 640 frames... [2023-03-09 12:32:19,058][269569] Num frames 4700... [2023-03-09 12:32:19,077][270153] Decorrelating experience for 640 frames... [2023-03-09 12:32:19,100][271017] Decorrelating experience for 704 frames... [2023-03-09 12:32:19,104][270541] Decorrelating experience for 224 frames... [2023-03-09 12:32:19,109][270751] Decorrelating experience for 608 frames... [2023-03-09 12:32:19,118][270096] Decorrelating experience for 640 frames... [2023-03-09 12:32:19,145][270113] Decorrelating experience for 576 frames... [2023-03-09 12:32:19,156][270132] Decorrelating experience for 480 frames... [2023-03-09 12:32:19,158][269569] Num frames 4800... [2023-03-09 12:32:19,172][270114] Decorrelating experience for 576 frames... [2023-03-09 12:32:19,191][277995] Decorrelating experience for 448 frames... [2023-03-09 12:32:19,254][269569] Num frames 4900... [2023-03-09 12:32:19,258][270005] Decorrelating experience for 256 frames... [2023-03-09 12:32:19,267][270146] Decorrelating experience for 672 frames... [2023-03-09 12:32:19,296][270009] Decorrelating experience for 864 frames... [2023-03-09 12:32:19,297][270472] Decorrelating experience for 544 frames... [2023-03-09 12:32:19,303][270553] Decorrelating experience for 544 frames... [2023-03-09 12:32:19,326][271126] Decorrelating experience for 704 frames... [2023-03-09 12:32:19,351][269569] Num frames 5000... [2023-03-09 12:32:19,352][270085] Decorrelating experience for 640 frames... [2023-03-09 12:32:19,383][269981] Decorrelating experience for 704 frames... [2023-03-09 12:32:19,405][270088] Decorrelating experience for 736 frames... [2023-03-09 12:32:19,433][270164] Decorrelating experience for 832 frames... [2023-03-09 12:32:19,450][269569] Num frames 5100... [2023-03-09 12:32:19,469][270137] Decorrelating experience for 640 frames... [2023-03-09 12:32:19,482][270125] Decorrelating experience for 960 frames... [2023-03-09 12:32:19,492][270150] Decorrelating experience for 544 frames... [2023-03-09 12:32:19,518][270116] Decorrelating experience for 832 frames... [2023-03-09 12:32:19,541][270012] Decorrelating experience for 832 frames... [2023-03-09 12:32:19,543][270086] Decorrelating experience for 864 frames... [2023-03-09 12:32:19,557][269569] Num frames 5200... [2023-03-09 12:32:19,561][270557] Decorrelating experience for 512 frames... [2023-03-09 12:32:19,569][270090] Decorrelating experience for 672 frames... [2023-03-09 12:32:19,597][270118] Decorrelating experience for 576 frames... [2023-03-09 12:32:19,634][270128] Decorrelating experience for 608 frames... [2023-03-09 12:32:19,655][269569] Num frames 5300... [2023-03-09 12:32:19,683][270002] Decorrelating experience for 352 frames... [2023-03-09 12:32:19,687][270596] Decorrelating experience for 480 frames... [2023-03-09 12:32:19,698][270556] Decorrelating experience for 544 frames... [2023-03-09 12:32:19,725][270133] Decorrelating experience for 288 frames... [2023-03-09 12:32:19,751][269569] Num frames 5400... [2023-03-09 12:32:19,754][270146] Decorrelating experience for 704 frames... [2023-03-09 12:32:19,754][270096] Decorrelating experience for 672 frames... [2023-03-09 12:32:19,822][270117] Decorrelating experience for 640 frames... [2023-03-09 12:32:19,840][270107] Decorrelating experience for 480 frames... [2023-03-09 12:32:19,848][269569] Num frames 5500... [2023-03-09 12:32:19,849][270152] Decorrelating experience for 864 frames... [2023-03-09 12:32:19,858][270091] Decorrelating experience for 416 frames... [2023-03-09 12:32:19,873][270119] Decorrelating experience for 288 frames... [2023-03-09 12:32:19,878][270555] Decorrelating experience for 192 frames... [2023-03-09 12:32:19,885][270092] Decorrelating experience for 320 frames... [2023-03-09 12:32:19,914][270108] Decorrelating experience for 672 frames... [2023-03-09 12:32:19,941][271919] Decorrelating experience for 448 frames... [2023-03-09 12:32:19,951][269569] Num frames 5600... [2023-03-09 12:32:20,012][270163] Decorrelating experience for 896 frames... [2023-03-09 12:32:20,039][270125] Decorrelating experience for 992 frames... [2023-03-09 12:32:20,048][269569] Num frames 5700... [2023-03-09 12:32:20,056][270404] Decorrelating experience for 576 frames... [2023-03-09 12:32:20,063][270003] Decorrelating experience for 256 frames... [2023-03-09 12:32:20,071][270009] Decorrelating experience for 896 frames... [2023-03-09 12:32:20,074][270121] Decorrelating experience for 704 frames... [2023-03-09 12:32:20,088][269981] Decorrelating experience for 736 frames... [2023-03-09 12:32:20,104][270122] Decorrelating experience for 896 frames... [2023-03-09 12:32:20,129][270945] Decorrelating experience for 320 frames... [2023-03-09 12:32:20,148][269569] Num frames 5800... [2023-03-09 12:32:20,169][277995] Decorrelating experience for 480 frames... [2023-03-09 12:32:20,202][270005] Decorrelating experience for 288 frames... [2023-03-09 12:32:20,248][269569] Num frames 5900... [2023-03-09 12:32:20,253][270096] Decorrelating experience for 704 frames... [2023-03-09 12:32:20,270][270556] Decorrelating experience for 576 frames... [2023-03-09 12:32:20,270][271017] Decorrelating experience for 736 frames... [2023-03-09 12:32:20,271][270137] Decorrelating experience for 672 frames... [2023-03-09 12:32:20,273][270165] Decorrelating experience for 288 frames... [2023-03-09 12:32:20,295][270012] Decorrelating experience for 864 frames... [2023-03-09 12:32:20,321][270368] Decorrelating experience for 384 frames... [2023-03-09 12:32:20,355][269569] Num frames 6000... [2023-03-09 12:32:20,397][270129] Decorrelating experience for 352 frames... [2023-03-09 12:32:20,404][270086] Decorrelating experience for 896 frames... [2023-03-09 12:32:20,405][270131] Decorrelating experience for 384 frames... [2023-03-09 12:32:20,435][270125] Stopping RolloutWorker_w77... [2023-03-09 12:32:20,435][270125] Loop rollout_proc77_evt_loop terminating... [2023-03-09 12:32:20,442][270555] Decorrelating experience for 224 frames... [2023-03-09 12:32:20,454][269569] Num frames 6100... [2023-03-09 12:32:20,462][270596] Decorrelating experience for 512 frames... [2023-03-09 12:32:20,470][270141] Decorrelating experience for 512 frames... [2023-03-09 12:32:20,493][270152] Decorrelating experience for 896 frames... [2023-03-09 12:32:20,512][270404] Decorrelating experience for 608 frames... [2023-03-09 12:32:20,546][270003] Decorrelating experience for 288 frames... [2023-03-09 12:32:20,552][270158] Decorrelating experience for 672 frames... [2023-03-09 12:32:20,558][269569] Num frames 6200... [2023-03-09 12:32:20,597][270161] Decorrelating experience for 736 frames... [2023-03-09 12:32:20,633][270089] Decorrelating experience for 480 frames... [2023-03-09 12:32:20,637][270944] Decorrelating experience for 832 frames... [2023-03-09 12:32:20,655][270107] Decorrelating experience for 512 frames... [2023-03-09 12:32:20,668][270146] Decorrelating experience for 736 frames... [2023-03-09 12:32:20,669][270143] Decorrelating experience for 576 frames... [2023-03-09 12:32:20,671][269569] Num frames 6300... [2023-03-09 12:32:20,693][270163] Decorrelating experience for 928 frames... [2023-03-09 12:32:20,715][270555] Decorrelating experience for 256 frames... [2023-03-09 12:32:20,723][269569] Avg episode rewards: #0: 62.999, true rewards: #0: 21.000 [2023-03-09 12:32:20,724][269569] Avg episode reward: 62.999, avg true_objective: 21.000 [2023-03-09 12:32:20,743][277349] Decorrelating experience for 480 frames... [2023-03-09 12:32:20,752][271919] Decorrelating experience for 480 frames... [2023-03-09 12:32:20,786][270095] Decorrelating experience for 480 frames... [2023-03-09 12:32:20,820][269569] Num frames 6400... [2023-03-09 12:32:20,827][270943] Decorrelating experience for 544 frames... [2023-03-09 12:32:20,845][270117] Decorrelating experience for 672 frames... [2023-03-09 12:32:20,845][271355] Decorrelating experience for 768 frames... [2023-03-09 12:32:20,909][270118] Decorrelating experience for 608 frames... [2023-03-09 12:32:20,916][269569] Num frames 6500... [2023-03-09 12:32:20,939][270131] Decorrelating experience for 416 frames... [2023-03-09 12:32:20,949][270751] Decorrelating experience for 640 frames... [2023-03-09 12:32:20,949][270108] Decorrelating experience for 704 frames... [2023-03-09 12:32:20,952][270096] Decorrelating experience for 736 frames... [2023-03-09 12:32:20,975][270130] Decorrelating experience for 736 frames... [2023-03-09 12:32:20,998][270003] Decorrelating experience for 320 frames... [2023-03-09 12:32:21,021][270699] Decorrelating experience for 704 frames... [2023-03-09 12:32:21,035][270085] Decorrelating experience for 672 frames... [2023-03-09 12:32:21,045][269569] Num frames 6600... [2023-03-09 12:32:21,121][270084] Decorrelating experience for 448 frames... [2023-03-09 12:32:21,131][269569] Num frames 6700... [2023-03-09 12:32:21,146][270157] Decorrelating experience for 928 frames... [2023-03-09 12:32:21,146][270404] Decorrelating experience for 640 frames... [2023-03-09 12:32:21,157][270086] Decorrelating experience for 928 frames... [2023-03-09 12:32:21,157][270091] Decorrelating experience for 448 frames... [2023-03-09 12:32:21,158][271224] Decorrelating experience for 704 frames... [2023-03-09 12:32:21,171][270152] Decorrelating experience for 928 frames... [2023-03-09 12:32:21,209][270122] Decorrelating experience for 928 frames... [2023-03-09 12:32:21,213][269569] Num frames 6800... [2023-03-09 12:32:21,218][270129] Decorrelating experience for 384 frames... [2023-03-09 12:32:21,228][270002] Decorrelating experience for 384 frames... [2023-03-09 12:32:21,296][269569] Num frames 6900... [2023-03-09 12:32:21,307][270368] Decorrelating experience for 416 frames... [2023-03-09 12:32:21,336][271919] Decorrelating experience for 512 frames... [2023-03-09 12:32:21,353][270164] Decorrelating experience for 864 frames... [2023-03-09 12:32:21,354][270596] Decorrelating experience for 544 frames... [2023-03-09 12:32:21,379][271355] Decorrelating experience for 800 frames... [2023-03-09 12:32:21,390][269569] Num frames 7000... [2023-03-09 12:32:21,391][270120] Decorrelating experience for 768 frames... [2023-03-09 12:32:21,404][270115] Decorrelating experience for 960 frames... [2023-03-09 12:32:21,417][269981] Decorrelating experience for 768 frames... [2023-03-09 12:32:21,423][270106] Decorrelating experience for 480 frames... [2023-03-09 12:32:21,432][270141] Decorrelating experience for 544 frames... [2023-03-09 12:32:21,495][269569] Num frames 7100... [2023-03-09 12:32:21,531][270161] Decorrelating experience for 768 frames... [2023-03-09 12:32:21,545][270557] Decorrelating experience for 544 frames... [2023-03-09 12:32:21,552][270541] Decorrelating experience for 256 frames... [2023-03-09 12:32:21,572][277995] Decorrelating experience for 512 frames... [2023-03-09 12:32:21,583][270105] Decorrelating experience for 416 frames... [2023-03-09 12:32:21,590][270107] Decorrelating experience for 544 frames... [2023-03-09 12:32:21,594][269569] Num frames 7200... [2023-03-09 12:32:21,595][271017] Decorrelating experience for 768 frames... [2023-03-09 12:32:21,610][270096] Decorrelating experience for 768 frames... [2023-03-09 12:32:21,625][271224] Decorrelating experience for 736 frames... [2023-03-09 12:32:21,628][270148] Decorrelating experience for 928 frames... [2023-03-09 12:32:21,689][269569] Num frames 7300... [2023-03-09 12:32:21,731][271919] Decorrelating experience for 544 frames... [2023-03-09 12:32:21,739][270233] Decorrelating experience for 576 frames... [2023-03-09 12:32:21,786][269569] Num frames 7400... [2023-03-09 12:32:21,788][270860] Decorrelating experience for 128 frames... [2023-03-09 12:32:21,798][270132] Decorrelating experience for 512 frames... [2023-03-09 12:32:21,812][270143] Decorrelating experience for 608 frames... [2023-03-09 12:32:21,823][270158] Decorrelating experience for 704 frames... [2023-03-09 12:32:21,836][270091] Decorrelating experience for 480 frames... [2023-03-09 12:32:21,837][270113] Decorrelating experience for 608 frames... [2023-03-09 12:32:21,842][270141] Decorrelating experience for 576 frames... [2023-03-09 12:32:21,844][270003] Decorrelating experience for 352 frames... [2023-03-09 12:32:21,888][269569] Num frames 7500... [2023-03-09 12:32:21,932][270133] Decorrelating experience for 320 frames... [2023-03-09 12:32:21,946][269981] Decorrelating experience for 800 frames... [2023-03-09 12:32:21,986][270111] Decorrelating experience for 416 frames... [2023-03-09 12:32:21,986][269569] Num frames 7600... [2023-03-09 12:32:21,999][270150] Decorrelating experience for 576 frames... [2023-03-09 12:32:22,008][270159] Decorrelating experience for 672 frames... [2023-03-09 12:32:22,019][270108] Decorrelating experience for 736 frames... [2023-03-09 12:32:22,028][270404] Decorrelating experience for 672 frames... [2023-03-09 12:32:22,036][270140] Decorrelating experience for 448 frames... [2023-03-09 12:32:22,077][269569] Num frames 7700... [2023-03-09 12:32:22,089][270943] Decorrelating experience for 576 frames... [2023-03-09 12:32:22,122][270146] Decorrelating experience for 768 frames... [2023-03-09 12:32:22,123][270100] Decorrelating experience for 704 frames... [2023-03-09 12:32:22,175][269569] Num frames 7800... [2023-03-09 12:32:22,188][270147] Decorrelating experience for 416 frames... [2023-03-09 12:32:22,201][270086] Decorrelating experience for 960 frames... [2023-03-09 12:32:22,209][270089] Decorrelating experience for 512 frames... [2023-03-09 12:32:22,235][270105] Decorrelating experience for 448 frames... [2023-03-09 12:32:22,249][270556] Decorrelating experience for 608 frames... [2023-03-09 12:32:22,250][270149] Decorrelating experience for 448 frames... [2023-03-09 12:32:22,258][270009] Decorrelating experience for 928 frames... [2023-03-09 12:32:22,274][269569] Num frames 7900... [2023-03-09 12:32:22,279][270118] Decorrelating experience for 640 frames... [2023-03-09 12:32:22,310][270101] Decorrelating experience for 416 frames... [2023-03-09 12:32:22,377][270131] Decorrelating experience for 448 frames... [2023-03-09 12:32:22,378][270111] Decorrelating experience for 448 frames... [2023-03-09 12:32:22,395][269569] Num frames 8000... [2023-03-09 12:32:22,398][270143] Decorrelating experience for 640 frames... [2023-03-09 12:32:22,406][270084] Decorrelating experience for 480 frames... [2023-03-09 12:32:22,436][271919] Decorrelating experience for 576 frames... [2023-03-09 12:32:22,447][270088] Decorrelating experience for 768 frames... [2023-03-09 12:32:22,448][270141] Decorrelating experience for 608 frames... [2023-03-09 12:32:22,491][270012] Decorrelating experience for 896 frames... [2023-03-09 12:32:22,495][269569] Num frames 8100... [2023-03-09 12:32:22,505][270151] Decorrelating experience for 384 frames... [2023-03-09 12:32:22,505][270557] Decorrelating experience for 576 frames... [2023-03-09 12:32:22,572][270152] Decorrelating experience for 960 frames... [2023-03-09 12:32:22,573][270092] Decorrelating experience for 352 frames... [2023-03-09 12:32:22,593][269569] Num frames 8200... [2023-03-09 12:32:22,611][270146] Decorrelating experience for 800 frames... [2023-03-09 12:32:22,614][270095] Decorrelating experience for 512 frames... [2023-03-09 12:32:22,636][270147] Decorrelating experience for 448 frames... [2023-03-09 12:32:22,637][270132] Decorrelating experience for 544 frames... [2023-03-09 12:32:22,651][270117] Decorrelating experience for 704 frames... [2023-03-09 12:32:22,694][269569] Num frames 8300... [2023-03-09 12:32:22,704][270011] Decorrelating experience for 448 frames... [2023-03-09 12:32:22,705][270136] Decorrelating experience for 544 frames... [2023-03-09 12:32:22,709][270158] Decorrelating experience for 736 frames... [2023-03-09 12:32:22,761][270013] Decorrelating experience for 448 frames... [2023-03-09 12:32:22,761][270368] Decorrelating experience for 448 frames... [2023-03-09 12:32:22,795][269569] Num frames 8400... [2023-03-09 12:32:22,824][270161] Decorrelating experience for 800 frames... [2023-03-09 12:32:22,843][270002] Decorrelating experience for 416 frames... [2023-03-09 12:32:22,846][269569] Avg episode rewards: #0: 63.999, true rewards: #0: 21.000 [2023-03-09 12:32:22,847][269569] Avg episode reward: 63.999, avg true_objective: 21.000 [2023-03-09 12:32:22,851][270751] Decorrelating experience for 672 frames... [2023-03-09 12:32:22,918][271375] Decorrelating experience for 352 frames... [2023-03-09 12:32:22,919][270098] Decorrelating experience for 576 frames... [2023-03-09 12:32:22,921][270140] Decorrelating experience for 480 frames... [2023-03-09 12:32:22,922][270131] Decorrelating experience for 480 frames... [2023-03-09 12:32:22,946][269569] Num frames 8500... [2023-03-09 12:32:22,955][270099] Decorrelating experience for 672 frames... [2023-03-09 12:32:23,006][270009] Decorrelating experience for 960 frames... [2023-03-09 12:32:23,030][270012] Decorrelating experience for 928 frames... [2023-03-09 12:32:23,032][270132] Decorrelating experience for 576 frames... [2023-03-09 12:32:23,042][269569] Num frames 8600... [2023-03-09 12:32:23,049][270233] Decorrelating experience for 608 frames... [2023-03-09 12:32:23,129][270117] Decorrelating experience for 736 frames... [2023-03-09 12:32:23,130][270554] Decorrelating experience for 480 frames... [2023-03-09 12:32:23,134][270122] Decorrelating experience for 960 frames... [2023-03-09 12:32:23,135][270011] Decorrelating experience for 480 frames... [2023-03-09 12:32:23,138][270596] Decorrelating experience for 576 frames... [2023-03-09 12:32:23,138][269569] Num frames 8700... [2023-03-09 12:32:23,142][270157] Decorrelating experience for 960 frames... [2023-03-09 12:32:23,192][270105] Decorrelating experience for 480 frames... [2023-03-09 12:32:23,218][270368] Decorrelating experience for 480 frames... [2023-03-09 12:32:23,225][270404] Decorrelating experience for 704 frames... [2023-03-09 12:32:23,236][269569] Num frames 8800... [2023-03-09 12:32:23,255][270106] Decorrelating experience for 512 frames... [2023-03-09 12:32:23,332][270098] Decorrelating experience for 608 frames... [2023-03-09 12:32:23,334][269569] Num frames 8900... [2023-03-09 12:32:23,348][270002] Decorrelating experience for 448 frames... [2023-03-09 12:32:23,351][270165] Decorrelating experience for 320 frames... [2023-03-09 12:32:23,408][270016] Decorrelating experience for 672 frames... [2023-03-09 12:32:23,420][270161] Decorrelating experience for 832 frames... [2023-03-09 12:32:23,424][270152] Decorrelating experience for 992 frames... [2023-03-09 12:32:23,425][270090] Decorrelating experience for 704 frames... [2023-03-09 12:32:23,432][269569] Num frames 9000... [2023-03-09 12:32:23,448][270148] Decorrelating experience for 960 frames... [2023-03-09 12:32:23,449][270751] Decorrelating experience for 704 frames... [2023-03-09 12:32:23,510][270131] Decorrelating experience for 512 frames... [2023-03-09 12:32:23,528][269569] Num frames 9100... [2023-03-09 12:32:23,534][270132] Decorrelating experience for 608 frames... [2023-03-09 12:32:23,605][270150] Decorrelating experience for 608 frames... [2023-03-09 12:32:23,615][270129] Decorrelating experience for 416 frames... [2023-03-09 12:32:23,619][269569] Num frames 9200... [2023-03-09 12:32:23,621][270113] Decorrelating experience for 640 frames... [2023-03-09 12:32:23,633][277995] Decorrelating experience for 544 frames... [2023-03-09 12:32:23,637][270140] Decorrelating experience for 512 frames... [2023-03-09 12:32:23,648][270092] Decorrelating experience for 384 frames... [2023-03-09 12:32:23,680][270011] Decorrelating experience for 512 frames... [2023-03-09 12:32:23,713][270105] Decorrelating experience for 512 frames... [2023-03-09 12:32:23,720][269569] Num frames 9300... [2023-03-09 12:32:23,721][270557] Decorrelating experience for 608 frames... [2023-03-09 12:32:23,810][270097] Decorrelating experience for 640 frames... [2023-03-09 12:32:23,817][269569] Num frames 9400... [2023-03-09 12:32:23,819][271126] Decorrelating experience for 736 frames... [2023-03-09 12:32:23,820][270165] Decorrelating experience for 352 frames... [2023-03-09 12:32:23,826][270010] Decorrelating experience for 512 frames... [2023-03-09 12:32:23,853][270095] Decorrelating experience for 544 frames... [2023-03-09 12:32:23,866][270118] Decorrelating experience for 672 frames... [2023-03-09 12:32:23,897][270131] Decorrelating experience for 544 frames... [2023-03-09 12:32:23,904][270012] Decorrelating experience for 960 frames... [2023-03-09 12:32:23,907][270154] Decorrelating experience for 448 frames... [2023-03-09 12:32:23,918][269569] Num frames 9500... [2023-03-09 12:32:23,938][270100] Decorrelating experience for 736 frames... [2023-03-09 12:32:23,956][270152] Stopping RolloutWorker_w79... [2023-03-09 12:32:23,956][270152] Loop rollout_proc79_evt_loop terminating... [2023-03-09 12:32:24,006][270008] Decorrelating experience for 544 frames... [2023-03-09 12:32:24,016][269569] Num frames 9600... [2023-03-09 12:32:24,020][270129] Decorrelating experience for 448 frames... [2023-03-09 12:32:24,023][270140] Decorrelating experience for 544 frames... [2023-03-09 12:32:24,044][270622] Another process currently holds the lock /tmp/sf2_rolo/doom_004.lockfile, attempt: 1 [2023-03-09 12:32:24,052][270751] Decorrelating experience for 736 frames... [2023-03-09 12:32:24,081][270161] Decorrelating experience for 864 frames... [2023-03-09 12:32:24,084][270552] Decorrelating experience for 544 frames... [2023-03-09 12:32:24,090][270157] Decorrelating experience for 992 frames... [2023-03-09 12:32:24,091][277349] Decorrelating experience for 512 frames... [2023-03-09 12:32:24,110][269569] Num frames 9700... [2023-03-09 12:32:24,139][270165] Decorrelating experience for 384 frames... [2023-03-09 12:32:24,194][271375] Decorrelating experience for 384 frames... [2023-03-09 12:32:24,197][269569] Num frames 9800... [2023-03-09 12:32:24,211][270002] Decorrelating experience for 480 frames... [2023-03-09 12:32:24,219][270084] Decorrelating experience for 512 frames... [2023-03-09 12:32:24,226][270622] VizDoom game.init() threw an exception SignalException('Signal SIGINT received. ViZDoom instance has been closed.'). Terminate process... [2023-03-09 12:32:24,227][270622] EvtLoop [rollout_proc100_evt_loop, process=rollout_proc100] unhandled exception in slot='init' connected to emitter=Emitter(object_id='Sampler', signal_name='_inference_workers_initialized'), args=() Traceback (most recent call last): File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 228, in _game_init self.game.init() vizdoom.vizdoom.SignalException: Signal SIGINT received. ViZDoom instance has been closed. During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/signal_slot/signal_slot.py", line 355, in _process_signal slot_callable(*args) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/rollout_worker.py", line 150, in init env_runner.init(self.timing) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 418, in init self._reset() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 430, in _reset observations, info = e.reset(seed=seed) # new way of doing seeding since Gym 0.26.0 File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 323, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 125, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 110, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/scenario_wrappers/gathering_reward_shaping.py", line 30, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 379, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/envs/env_wrappers.py", line 84, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 323, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/multiplayer_stats.py", line 51, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 323, in reset self._ensure_initialized() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 274, in _ensure_initialized self.initialize() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 269, in initialize self._game_init() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 244, in _game_init raise EnvCriticalError() sample_factory.envs.env_utils.EnvCriticalError [2023-03-09 12:32:24,228][271517] VizDoom game.init() threw an exception SignalException('Signal SIGINT received. ViZDoom instance has been closed.'). Terminate process... [2023-03-09 12:32:24,229][270622] Unhandled exception in evt loop rollout_proc100_evt_loop [2023-03-09 12:32:24,229][269981] VizDoom game.init() threw an exception ViZDoomErrorException('Unexpected ViZDoom instance crash.'). Terminate process... [2023-03-09 12:32:24,229][270233] VizDoom game.init() threw an exception SignalException('Signal SIGINT received. ViZDoom instance has been closed.'). Terminate process... [2023-03-09 12:32:24,229][271517] EvtLoop [rollout_proc118_evt_loop, process=rollout_proc118] unhandled exception in slot='init' connected to emitter=Emitter(object_id='Sampler', signal_name='_inference_workers_initialized'), args=() Traceback (most recent call last): File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 228, in _game_init self.game.init() vizdoom.vizdoom.SignalException: Signal SIGINT received. ViZDoom instance has been closed. During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/signal_slot/signal_slot.py", line 355, in _process_signal slot_callable(*args) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/rollout_worker.py", line 150, in init env_runner.init(self.timing) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 418, in init self._reset() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 430, in _reset observations, info = e.reset(seed=seed) # new way of doing seeding since Gym 0.26.0 File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 323, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 125, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 110, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/scenario_wrappers/gathering_reward_shaping.py", line 30, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 379, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/envs/env_wrappers.py", line 84, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 323, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/multiplayer_stats.py", line 51, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 323, in reset self._ensure_initialized() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 274, in _ensure_initialized self.initialize() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 269, in initialize self._game_init() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 244, in _game_init raise EnvCriticalError() sample_factory.envs.env_utils.EnvCriticalError [2023-03-09 12:32:24,230][271517] Unhandled exception in evt loop rollout_proc118_evt_loop [2023-03-09 12:32:24,230][269981] EvtLoop [rollout_proc2_evt_loop, process=rollout_proc2] unhandled exception in slot='init' connected to emitter=Emitter(object_id='Sampler', signal_name='_inference_workers_initialized'), args=() Traceback (most recent call last): File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 228, in _game_init self.game.init() vizdoom.vizdoom.ViZDoomErrorException: Unexpected ViZDoom instance crash. During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/signal_slot/signal_slot.py", line 355, in _process_signal slot_callable(*args) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/rollout_worker.py", line 150, in init env_runner.init(self.timing) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 418, in init self._reset() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 430, in _reset observations, info = e.reset(seed=seed) # new way of doing seeding since Gym 0.26.0 File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 323, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 125, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 110, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/scenario_wrappers/gathering_reward_shaping.py", line 30, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 379, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/envs/env_wrappers.py", line 84, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 323, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/multiplayer_stats.py", line 51, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 323, in reset self._ensure_initialized() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 274, in _ensure_initialized self.initialize() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 269, in initialize self._game_init() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 244, in _game_init raise EnvCriticalError() sample_factory.envs.env_utils.EnvCriticalError [2023-03-09 12:32:24,230][270092] VizDoom game.init() threw an exception SignalException('Signal SIGINT received. ViZDoom instance has been closed.'). Terminate process... [2023-03-09 12:32:24,231][269981] Unhandled exception in evt loop rollout_proc2_evt_loop [2023-03-09 12:32:24,230][270233] EvtLoop [rollout_proc110_evt_loop, process=rollout_proc110] unhandled exception in slot='init' connected to emitter=Emitter(object_id='Sampler', signal_name='_inference_workers_initialized'), args=() Traceback (most recent call last): File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 228, in _game_init self.game.init() vizdoom.vizdoom.SignalException: Signal SIGINT received. ViZDoom instance has been closed. During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/signal_slot/signal_slot.py", line 355, in _process_signal slot_callable(*args) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/rollout_worker.py", line 150, in init env_runner.init(self.timing) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 418, in init self._reset() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 430, in _reset observations, info = e.reset(seed=seed) # new way of doing seeding since Gym 0.26.0 File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 323, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 125, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 110, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/scenario_wrappers/gathering_reward_shaping.py", line 30, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 379, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/envs/env_wrappers.py", line 84, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 323, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/multiplayer_stats.py", line 51, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 323, in reset self._ensure_initialized() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 274, in _ensure_initialized self.initialize() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 269, in initialize self._game_init() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 244, in _game_init raise EnvCriticalError() sample_factory.envs.env_utils.EnvCriticalError [2023-03-09 12:32:24,231][270233] Unhandled exception in evt loop rollout_proc110_evt_loop [2023-03-09 12:32:24,231][270097] VizDoom game.init() threw an exception SignalException('Signal SIGINT received. ViZDoom instance has been closed.'). Terminate process... [2023-03-09 12:32:24,232][270132] VizDoom game.init() threw an exception SignalException('Signal SIGINT received. ViZDoom instance has been closed.'). Terminate process... [2023-03-09 12:32:24,231][270092] EvtLoop [rollout_proc24_evt_loop, process=rollout_proc24] unhandled exception in slot='init' connected to emitter=Emitter(object_id='Sampler', signal_name='_inference_workers_initialized'), args=() Traceback (most recent call last): File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 228, in _game_init self.game.init() vizdoom.vizdoom.SignalException: Signal SIGINT received. ViZDoom instance has been closed. During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/signal_slot/signal_slot.py", line 355, in _process_signal slot_callable(*args) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/rollout_worker.py", line 150, in init env_runner.init(self.timing) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 418, in init self._reset() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 430, in _reset observations, info = e.reset(seed=seed) # new way of doing seeding since Gym 0.26.0 File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 323, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 125, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 110, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/scenario_wrappers/gathering_reward_shaping.py", line 30, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 379, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/envs/env_wrappers.py", line 84, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 323, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/multiplayer_stats.py", line 51, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 323, in reset self._ensure_initialized() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 274, in _ensure_initialized self.initialize() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 269, in initialize self._game_init() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 244, in _game_init raise EnvCriticalError() sample_factory.envs.env_utils.EnvCriticalError [2023-03-09 12:32:24,232][270092] Unhandled exception in evt loop rollout_proc24_evt_loop [2023-03-09 12:32:24,231][270552] EvtLoop [rollout_proc96_evt_loop, process=rollout_proc96] unhandled exception in slot='init' connected to emitter=Emitter(object_id='Sampler', signal_name='_inference_workers_initialized'), args=() Traceback (most recent call last): File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/signal_slot/signal_slot.py", line 355, in _process_signal slot_callable(*args) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/rollout_worker.py", line 150, in init env_runner.init(self.timing) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 418, in init self._reset() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 439, in _reset observations, rew, terminated, truncated, info = e.step(actions) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 319, in step return self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 129, in step obs, rew, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 115, in step obs, rew, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/scenario_wrappers/gathering_reward_shaping.py", line 33, in step observation, reward, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 384, in step observation, reward, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/envs/env_wrappers.py", line 88, in step obs, reward, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 319, in step return self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/multiplayer_stats.py", line 54, in step obs, reward, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 452, in step reward = self.game.make_action(actions_flattened, self.skip_frames) vizdoom.vizdoom.SignalException: Signal SIGINT received. ViZDoom instance has been closed. [2023-03-09 12:32:24,233][270552] Unhandled exception Signal SIGINT received. ViZDoom instance has been closed. in evt loop rollout_proc96_evt_loop [2023-03-09 12:32:24,232][270132] EvtLoop [rollout_proc48_evt_loop, process=rollout_proc48] unhandled exception in slot='init' connected to emitter=Emitter(object_id='Sampler', signal_name='_inference_workers_initialized'), args=() Traceback (most recent call last): File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 228, in _game_init self.game.init() vizdoom.vizdoom.SignalException: Signal SIGINT received. ViZDoom instance has been closed. During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/signal_slot/signal_slot.py", line 355, in _process_signal slot_callable(*args) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/rollout_worker.py", line 150, in init env_runner.init(self.timing) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 418, in init self._reset() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 430, in _reset observations, info = e.reset(seed=seed) # new way of doing seeding since Gym 0.26.0 File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 323, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 125, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 110, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/scenario_wrappers/gathering_reward_shaping.py", line 30, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 379, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/envs/env_wrappers.py", line 84, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 323, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/multiplayer_stats.py", line 51, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 323, in reset self._ensure_initialized() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 274, in _ensure_initialized self.initialize() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 269, in initialize self._game_init() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 244, in _game_init raise EnvCriticalError() sample_factory.envs.env_utils.EnvCriticalError [2023-03-09 12:32:24,232][270097] EvtLoop [rollout_proc36_evt_loop, process=rollout_proc36] unhandled exception in slot='init' connected to emitter=Emitter(object_id='Sampler', signal_name='_inference_workers_initialized'), args=() Traceback (most recent call last): File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 228, in _game_init self.game.init() vizdoom.vizdoom.SignalException: Signal SIGINT received. ViZDoom instance has been closed. During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/signal_slot/signal_slot.py", line 355, in _process_signal slot_callable(*args) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/rollout_worker.py", line 150, in init env_runner.init(self.timing) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 418, in init self._reset() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 430, in _reset observations, info = e.reset(seed=seed) # new way of doing seeding since Gym 0.26.0 File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 323, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 125, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 110, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/scenario_wrappers/gathering_reward_shaping.py", line 30, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 379, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/envs/env_wrappers.py", line 84, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 323, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/multiplayer_stats.py", line 51, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 323, in reset self._ensure_initialized() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 274, in _ensure_initialized self.initialize() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 269, in initialize self._game_init() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 244, in _game_init raise EnvCriticalError() sample_factory.envs.env_utils.EnvCriticalError [2023-03-09 12:32:24,234][270132] Unhandled exception in evt loop rollout_proc48_evt_loop [2023-03-09 12:32:24,234][270011] VizDoom game.init() threw an exception SignalException('Signal SIGINT received. ViZDoom instance has been closed.'). Terminate process... [2023-03-09 12:32:24,234][270097] Unhandled exception in evt loop rollout_proc36_evt_loop [2023-03-09 12:32:24,235][270115] VizDoom game.init() threw an exception SignalException('Signal SIGINT received. ViZDoom instance has been closed.'). Terminate process... [2023-03-09 12:32:24,237][270115] EvtLoop [rollout_proc37_evt_loop, process=rollout_proc37] unhandled exception in slot='init' connected to emitter=Emitter(object_id='Sampler', signal_name='_inference_workers_initialized'), args=() Traceback (most recent call last): File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 228, in _game_init self.game.init() vizdoom.vizdoom.SignalException: Signal SIGINT received. ViZDoom instance has been closed. During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/signal_slot/signal_slot.py", line 355, in _process_signal slot_callable(*args) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/rollout_worker.py", line 150, in init env_runner.init(self.timing) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 418, in init self._reset() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 430, in _reset observations, info = e.reset(seed=seed) # new way of doing seeding since Gym 0.26.0 File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 323, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 125, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 110, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/scenario_wrappers/gathering_reward_shaping.py", line 30, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 379, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/envs/env_wrappers.py", line 84, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 323, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/multiplayer_stats.py", line 51, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 323, in reset self._ensure_initialized() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 274, in _ensure_initialized self.initialize() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 269, in initialize self._game_init() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 244, in _game_init raise EnvCriticalError() sample_factory.envs.env_utils.EnvCriticalError [2023-03-09 12:32:24,238][270115] Unhandled exception in evt loop rollout_proc37_evt_loop [2023-03-09 12:32:24,240][270012] EvtLoop [rollout_proc32_evt_loop, process=rollout_proc32] unhandled exception in slot='init' connected to emitter=Emitter(object_id='Sampler', signal_name='_inference_workers_initialized'), args=() Traceback (most recent call last): File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/signal_slot/signal_slot.py", line 355, in _process_signal slot_callable(*args) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/rollout_worker.py", line 150, in init env_runner.init(self.timing) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 418, in init self._reset() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 439, in _reset observations, rew, terminated, truncated, info = e.step(actions) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 319, in step return self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 129, in step obs, rew, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 115, in step obs, rew, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/scenario_wrappers/gathering_reward_shaping.py", line 33, in step observation, reward, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 384, in step observation, reward, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/envs/env_wrappers.py", line 88, in step obs, reward, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 319, in step return self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/multiplayer_stats.py", line 54, in step obs, reward, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 452, in step reward = self.game.make_action(actions_flattened, self.skip_frames) vizdoom.vizdoom.SignalException: Signal SIGINT received. ViZDoom instance has been closed. [2023-03-09 12:32:24,250][270012] Unhandled exception Signal SIGINT received. ViZDoom instance has been closed. in evt loop rollout_proc32_evt_loop [2023-03-09 12:32:24,234][270011] EvtLoop [rollout_proc23_evt_loop, process=rollout_proc23] unhandled exception in slot='init' connected to emitter=Emitter(object_id='Sampler', signal_name='_inference_workers_initialized'), args=() Traceback (most recent call last): File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 228, in _game_init self.game.init() vizdoom.vizdoom.SignalException: Signal SIGINT received. ViZDoom instance has been closed. During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/signal_slot/signal_slot.py", line 355, in _process_signal slot_callable(*args) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/rollout_worker.py", line 150, in init env_runner.init(self.timing) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 418, in init self._reset() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 430, in _reset observations, info = e.reset(seed=seed) # new way of doing seeding since Gym 0.26.0 File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 323, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 125, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 110, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/scenario_wrappers/gathering_reward_shaping.py", line 30, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 379, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/envs/env_wrappers.py", line 84, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 323, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/multiplayer_stats.py", line 51, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 323, in reset self._ensure_initialized() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 274, in _ensure_initialized self.initialize() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 269, in initialize self._game_init() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 244, in _game_init raise EnvCriticalError() sample_factory.envs.env_utils.EnvCriticalError [2023-03-09 12:32:24,253][270011] Unhandled exception in evt loop rollout_proc23_evt_loop [2023-03-09 12:32:24,274][270100] EvtLoop [rollout_proc4_evt_loop, process=rollout_proc4] unhandled exception in slot='init' connected to emitter=Emitter(object_id='Sampler', signal_name='_inference_workers_initialized'), args=() Traceback (most recent call last): File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/signal_slot/signal_slot.py", line 355, in _process_signal slot_callable(*args) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/rollout_worker.py", line 150, in init env_runner.init(self.timing) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 418, in init self._reset() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 439, in _reset observations, rew, terminated, truncated, info = e.step(actions) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 319, in step return self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 129, in step obs, rew, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 115, in step obs, rew, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/scenario_wrappers/gathering_reward_shaping.py", line 33, in step observation, reward, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 384, in step observation, reward, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/envs/env_wrappers.py", line 88, in step obs, reward, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 319, in step return self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/multiplayer_stats.py", line 54, in step obs, reward, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 452, in step reward = self.game.make_action(actions_flattened, self.skip_frames) vizdoom.vizdoom.SignalException: Signal SIGINT received. ViZDoom instance has been closed. [2023-03-09 12:32:24,275][270100] Unhandled exception Signal SIGINT received. ViZDoom instance has been closed. in evt loop rollout_proc4_evt_loop [2023-03-09 12:32:24,274][270165] EvtLoop [rollout_proc113_evt_loop, process=rollout_proc113] unhandled exception in slot='init' connected to emitter=Emitter(object_id='Sampler', signal_name='_inference_workers_initialized'), args=() Traceback (most recent call last): File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/signal_slot/signal_slot.py", line 355, in _process_signal slot_callable(*args) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/rollout_worker.py", line 150, in init env_runner.init(self.timing) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 418, in init self._reset() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 439, in _reset observations, rew, terminated, truncated, info = e.step(actions) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 319, in step return self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 129, in step obs, rew, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 115, in step obs, rew, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/scenario_wrappers/gathering_reward_shaping.py", line 33, in step observation, reward, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 384, in step observation, reward, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/envs/env_wrappers.py", line 88, in step obs, reward, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 319, in step return self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/multiplayer_stats.py", line 54, in step obs, reward, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 452, in step reward = self.game.make_action(actions_flattened, self.skip_frames) vizdoom.vizdoom.SignalException: Signal SIGINT received. ViZDoom instance has been closed. [2023-03-09 12:32:24,275][270165] Unhandled exception Signal SIGINT received. ViZDoom instance has been closed. in evt loop rollout_proc113_evt_loop [2023-03-09 12:32:24,276][270140] EvtLoop [rollout_proc81_evt_loop, process=rollout_proc81] unhandled exception in slot='init' connected to emitter=Emitter(object_id='Sampler', signal_name='_inference_workers_initialized'), args=() Traceback (most recent call last): File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/signal_slot/signal_slot.py", line 355, in _process_signal slot_callable(*args) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/rollout_worker.py", line 150, in init env_runner.init(self.timing) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 418, in init self._reset() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 439, in _reset observations, rew, terminated, truncated, info = e.step(actions) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 319, in step return self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 129, in step obs, rew, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 115, in step obs, rew, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/scenario_wrappers/gathering_reward_shaping.py", line 33, in step observation, reward, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 384, in step observation, reward, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/envs/env_wrappers.py", line 88, in step obs, reward, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 319, in step return self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/multiplayer_stats.py", line 54, in step obs, reward, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 452, in step reward = self.game.make_action(actions_flattened, self.skip_frames) vizdoom.vizdoom.SignalException: Signal SIGINT received. ViZDoom instance has been closed. [2023-03-09 12:32:24,275][270084] EvtLoop [rollout_proc6_evt_loop, process=rollout_proc6] unhandled exception in slot='init' connected to emitter=Emitter(object_id='Sampler', signal_name='_inference_workers_initialized'), args=() Traceback (most recent call last): File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/signal_slot/signal_slot.py", line 355, in _process_signal slot_callable(*args) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/rollout_worker.py", line 150, in init env_runner.init(self.timing) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 418, in init self._reset() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 439, in _reset observations, rew, terminated, truncated, info = e.step(actions) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 319, in step return self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 129, in step obs, rew, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 115, in step obs, rew, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/scenario_wrappers/gathering_reward_shaping.py", line 33, in step observation, reward, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 384, in step observation, reward, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/envs/env_wrappers.py", line 88, in step obs, reward, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 319, in step return self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/multiplayer_stats.py", line 54, in step obs, reward, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 452, in step reward = self.game.make_action(actions_flattened, self.skip_frames) vizdoom.vizdoom.SignalException: Signal SIGINT received. ViZDoom instance has been closed. [2023-03-09 12:32:24,277][270140] Unhandled exception Signal SIGINT received. ViZDoom instance has been closed. in evt loop rollout_proc81_evt_loop [2023-03-09 12:32:24,277][270084] Unhandled exception Signal SIGINT received. ViZDoom instance has been closed. in evt loop rollout_proc6_evt_loop [2023-03-09 12:32:24,287][270002] EvtLoop [rollout_proc5_evt_loop, process=rollout_proc5] unhandled exception in slot='init' connected to emitter=Emitter(object_id='Sampler', signal_name='_inference_workers_initialized'), args=() Traceback (most recent call last): File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/signal_slot/signal_slot.py", line 355, in _process_signal slot_callable(*args) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/rollout_worker.py", line 150, in init env_runner.init(self.timing) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 418, in init self._reset() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 439, in _reset observations, rew, terminated, truncated, info = e.step(actions) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 319, in step return self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 129, in step obs, rew, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 115, in step obs, rew, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/scenario_wrappers/gathering_reward_shaping.py", line 33, in step observation, reward, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 384, in step observation, reward, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/envs/env_wrappers.py", line 88, in step obs, reward, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 319, in step return self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/multiplayer_stats.py", line 54, in step obs, reward, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 452, in step reward = self.game.make_action(actions_flattened, self.skip_frames) vizdoom.vizdoom.SignalException: Signal SIGINT received. ViZDoom instance has been closed. [2023-03-09 12:32:24,287][270157] EvtLoop [rollout_proc67_evt_loop, process=rollout_proc67] unhandled exception in slot='init' connected to emitter=Emitter(object_id='Sampler', signal_name='_inference_workers_initialized'), args=() Traceback (most recent call last): File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/signal_slot/signal_slot.py", line 355, in _process_signal slot_callable(*args) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/rollout_worker.py", line 150, in init env_runner.init(self.timing) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 418, in init self._reset() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 439, in _reset observations, rew, terminated, truncated, info = e.step(actions) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 319, in step return self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 129, in step obs, rew, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 115, in step obs, rew, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/scenario_wrappers/gathering_reward_shaping.py", line 33, in step observation, reward, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 384, in step observation, reward, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/envs/env_wrappers.py", line 88, in step obs, reward, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 319, in step return self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/multiplayer_stats.py", line 54, in step obs, reward, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 452, in step reward = self.game.make_action(actions_flattened, self.skip_frames) vizdoom.vizdoom.SignalException: Signal SIGINT received. ViZDoom instance has been closed. [2023-03-09 12:32:24,288][270002] Unhandled exception Signal SIGINT received. ViZDoom instance has been closed. in evt loop rollout_proc5_evt_loop [2023-03-09 12:32:24,288][270157] Unhandled exception Signal SIGINT received. ViZDoom instance has been closed. in evt loop rollout_proc67_evt_loop [2023-03-09 12:32:24,303][270751] EvtLoop [rollout_proc97_evt_loop, process=rollout_proc97] unhandled exception in slot='init' connected to emitter=Emitter(object_id='Sampler', signal_name='_inference_workers_initialized'), args=() Traceback (most recent call last): File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/signal_slot/signal_slot.py", line 355, in _process_signal slot_callable(*args) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/rollout_worker.py", line 150, in init env_runner.init(self.timing) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 418, in init self._reset() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 439, in _reset observations, rew, terminated, truncated, info = e.step(actions) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 319, in step return self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 129, in step obs, rew, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 115, in step obs, rew, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/scenario_wrappers/gathering_reward_shaping.py", line 33, in step observation, reward, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 384, in step observation, reward, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/envs/env_wrappers.py", line 88, in step obs, reward, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 319, in step return self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/multiplayer_stats.py", line 54, in step obs, reward, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 452, in step reward = self.game.make_action(actions_flattened, self.skip_frames) vizdoom.vizdoom.SignalException: Signal SIGINT received. ViZDoom instance has been closed. [2023-03-09 12:32:24,305][270751] Unhandled exception Signal SIGINT received. ViZDoom instance has been closed. in evt loop rollout_proc97_evt_loop [2023-03-09 12:32:24,363][277349] EvtLoop [rollout_proc0_evt_loop, process=rollout_proc0] unhandled exception in slot='init' connected to emitter=Emitter(object_id='Sampler', signal_name='_inference_workers_initialized'), args=() Traceback (most recent call last): File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/signal_slot/signal_slot.py", line 355, in _process_signal slot_callable(*args) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/rollout_worker.py", line 150, in init env_runner.init(self.timing) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 418, in init self._reset() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 439, in _reset observations, rew, terminated, truncated, info = e.step(actions) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 319, in step return self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 129, in step obs, rew, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 115, in step obs, rew, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/scenario_wrappers/gathering_reward_shaping.py", line 33, in step observation, reward, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 384, in step observation, reward, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/envs/env_wrappers.py", line 88, in step obs, reward, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 319, in step return self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/multiplayer_stats.py", line 54, in step obs, reward, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 452, in step reward = self.game.make_action(actions_flattened, self.skip_frames) vizdoom.vizdoom.SignalException: Signal SIGINT received. ViZDoom instance has been closed. [2023-03-09 12:32:24,364][277349] Unhandled exception Signal SIGINT received. ViZDoom instance has been closed. in evt loop rollout_proc0_evt_loop [2023-03-09 12:32:24,375][271375] EvtLoop [rollout_proc121_evt_loop, process=rollout_proc121] unhandled exception in slot='init' connected to emitter=Emitter(object_id='Sampler', signal_name='_inference_workers_initialized'), args=() Traceback (most recent call last): File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/signal_slot/signal_slot.py", line 355, in _process_signal slot_callable(*args) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/rollout_worker.py", line 150, in init env_runner.init(self.timing) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 418, in init self._reset() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 439, in _reset observations, rew, terminated, truncated, info = e.step(actions) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 319, in step return self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 129, in step obs, rew, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 115, in step obs, rew, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/scenario_wrappers/gathering_reward_shaping.py", line 33, in step observation, reward, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 384, in step observation, reward, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/envs/env_wrappers.py", line 88, in step obs, reward, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 319, in step return self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/multiplayer_stats.py", line 54, in step obs, reward, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 452, in step reward = self.game.make_action(actions_flattened, self.skip_frames) vizdoom.vizdoom.SignalException: Signal SIGINT received. ViZDoom instance has been closed. [2023-03-09 12:32:24,377][271375] Unhandled exception Signal SIGINT received. ViZDoom instance has been closed. in evt loop rollout_proc121_evt_loop [2023-03-09 12:32:24,376][270161] EvtLoop [rollout_proc98_evt_loop, process=rollout_proc98] unhandled exception in slot='init' connected to emitter=Emitter(object_id='Sampler', signal_name='_inference_workers_initialized'), args=() Traceback (most recent call last): File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/signal_slot/signal_slot.py", line 355, in _process_signal slot_callable(*args) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/rollout_worker.py", line 150, in init env_runner.init(self.timing) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 418, in init self._reset() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 439, in _reset observations, rew, terminated, truncated, info = e.step(actions) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 319, in step return self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 129, in step obs, rew, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 115, in step obs, rew, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/scenario_wrappers/gathering_reward_shaping.py", line 33, in step observation, reward, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 384, in step observation, reward, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/envs/env_wrappers.py", line 88, in step obs, reward, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 319, in step return self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/multiplayer_stats.py", line 54, in step obs, reward, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 452, in step reward = self.game.make_action(actions_flattened, self.skip_frames) vizdoom.vizdoom.SignalException: Signal SIGINT received. ViZDoom instance has been closed. [2023-03-09 12:32:24,377][270161] Unhandled exception Signal SIGINT received. ViZDoom instance has been closed. in evt loop rollout_proc98_evt_loop [2023-03-09 12:32:24,441][270945] Decorrelating experience for 352 frames... [2023-03-09 12:32:24,485][270514] Decorrelating experience for 480 frames... [2023-03-09 12:32:24,485][270944] Decorrelating experience for 864 frames... [2023-03-09 12:32:24,487][270146] Decorrelating experience for 832 frames... [2023-03-09 12:32:24,487][277995] Decorrelating experience for 576 frames... [2023-03-09 12:32:24,488][270555] Decorrelating experience for 288 frames... [2023-03-09 12:32:24,488][270008] Decorrelating experience for 576 frames... [2023-03-09 12:32:24,488][270090] Decorrelating experience for 736 frames... [2023-03-09 12:32:24,497][270113] Decorrelating experience for 672 frames... [2023-03-09 12:32:24,698][270129] Decorrelating experience for 480 frames... [2023-03-09 12:32:24,703][270013] Decorrelating experience for 480 frames... [2023-03-09 12:32:24,708][270472] Decorrelating experience for 576 frames... [2023-03-09 12:32:24,721][270156] Decorrelating experience for 288 frames... [2023-03-09 12:32:24,723][270158] Decorrelating experience for 768 frames... [2023-03-09 12:32:24,739][270154] Decorrelating experience for 480 frames... [2023-03-09 12:32:24,742][270596] Decorrelating experience for 608 frames... [2023-03-09 12:32:24,768][270945] Decorrelating experience for 384 frames... [2023-03-09 12:32:24,772][270118] Decorrelating experience for 704 frames... [2023-03-09 12:32:24,808][270555] Decorrelating experience for 320 frames... [2023-03-09 12:32:24,928][270143] Decorrelating experience for 672 frames... [2023-03-09 12:32:24,929][270106] Decorrelating experience for 544 frames... [2023-03-09 12:32:24,931][271224] Decorrelating experience for 768 frames... [2023-03-09 12:32:24,931][270133] Decorrelating experience for 352 frames... [2023-03-09 12:32:24,947][270088] Decorrelating experience for 800 frames... [2023-03-09 12:32:24,983][270086] Decorrelating experience for 992 frames... [2023-03-09 12:32:25,022][270156] Decorrelating experience for 320 frames... [2023-03-09 12:32:25,072][270010] VizDoom game.init() threw an exception SignalException('Signal SIGTERM received. ViZDoom instance has been closed.'). Terminate process... [2023-03-09 12:32:25,073][270010] EvtLoop [rollout_proc29_evt_loop, process=rollout_proc29] unhandled exception in slot='init' connected to emitter=Emitter(object_id='Sampler', signal_name='_inference_workers_initialized'), args=() Traceback (most recent call last): File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 228, in _game_init self.game.init() vizdoom.vizdoom.SignalException: Signal SIGTERM received. ViZDoom instance has been closed. During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/signal_slot/signal_slot.py", line 355, in _process_signal slot_callable(*args) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/rollout_worker.py", line 150, in init env_runner.init(self.timing) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 418, in init self._reset() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 430, in _reset observations, info = e.reset(seed=seed) # new way of doing seeding since Gym 0.26.0 File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 323, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 125, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 110, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/scenario_wrappers/gathering_reward_shaping.py", line 30, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 379, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/envs/env_wrappers.py", line 84, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 323, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/multiplayer_stats.py", line 51, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 323, in reset self._ensure_initialized() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 274, in _ensure_initialized self.initialize() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 269, in initialize self._game_init() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 244, in _game_init raise EnvCriticalError() sample_factory.envs.env_utils.EnvCriticalError [2023-03-09 12:32:25,075][270010] Unhandled exception in evt loop rollout_proc29_evt_loop [2023-03-09 12:32:25,078][270088] EvtLoop [rollout_proc12_evt_loop, process=rollout_proc12] unhandled exception in slot='init' connected to emitter=Emitter(object_id='Sampler', signal_name='_inference_workers_initialized'), args=() Traceback (most recent call last): File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/signal_slot/signal_slot.py", line 355, in _process_signal slot_callable(*args) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/rollout_worker.py", line 150, in init env_runner.init(self.timing) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 418, in init self._reset() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 439, in _reset observations, rew, terminated, truncated, info = e.step(actions) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 319, in step return self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 129, in step obs, rew, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 115, in step obs, rew, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/scenario_wrappers/gathering_reward_shaping.py", line 33, in step observation, reward, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 384, in step observation, reward, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/envs/env_wrappers.py", line 88, in step obs, reward, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 319, in step return self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/multiplayer_stats.py", line 54, in step obs, reward, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 452, in step reward = self.game.make_action(actions_flattened, self.skip_frames) vizdoom.vizdoom.SignalException: Signal SIGTERM received. ViZDoom instance has been closed. [2023-03-09 12:32:25,080][270088] Unhandled exception Signal SIGTERM received. ViZDoom instance has been closed. in evt loop rollout_proc12_evt_loop [2023-03-09 12:32:25,087][270101] VizDoom game.init() threw an exception SignalException('Signal SIGTERM received. ViZDoom instance has been closed.'). Terminate process... [2023-03-09 12:32:25,087][270128] VizDoom game.init() threw an exception SignalException('Signal SIGTERM received. ViZDoom instance has been closed.'). Terminate process... [2023-03-09 12:32:25,088][270129] VizDoom game.init() threw an exception SignalException('Signal SIGTERM received. ViZDoom instance has been closed.'). Terminate process... [2023-03-09 12:32:25,089][270090] VizDoom game.init() threw an exception SignalException('Signal SIGTERM received. ViZDoom instance has been closed.'). Terminate process... [2023-03-09 12:32:25,087][270101] EvtLoop [rollout_proc19_evt_loop, process=rollout_proc19] unhandled exception in slot='init' connected to emitter=Emitter(object_id='Sampler', signal_name='_inference_workers_initialized'), args=() Traceback (most recent call last): File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 228, in _game_init self.game.init() vizdoom.vizdoom.SignalException: Signal SIGTERM received. ViZDoom instance has been closed. During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/signal_slot/signal_slot.py", line 355, in _process_signal slot_callable(*args) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/rollout_worker.py", line 150, in init env_runner.init(self.timing) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 418, in init self._reset() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 430, in _reset observations, info = e.reset(seed=seed) # new way of doing seeding since Gym 0.26.0 File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 323, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 125, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 110, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/scenario_wrappers/gathering_reward_shaping.py", line 30, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 379, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/envs/env_wrappers.py", line 84, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 323, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/multiplayer_stats.py", line 51, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 323, in reset self._ensure_initialized() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 274, in _ensure_initialized self.initialize() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 269, in initialize self._game_init() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 244, in _game_init raise EnvCriticalError() sample_factory.envs.env_utils.EnvCriticalError [2023-03-09 12:32:25,090][270101] Unhandled exception in evt loop rollout_proc19_evt_loop [2023-03-09 12:32:25,088][270128] EvtLoop [rollout_proc83_evt_loop, process=rollout_proc83] unhandled exception in slot='init' connected to emitter=Emitter(object_id='Sampler', signal_name='_inference_workers_initialized'), args=() Traceback (most recent call last): File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 228, in _game_init self.game.init() vizdoom.vizdoom.SignalException: Signal SIGTERM received. ViZDoom instance has been closed. During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/signal_slot/signal_slot.py", line 355, in _process_signal slot_callable(*args) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/rollout_worker.py", line 150, in init env_runner.init(self.timing) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 418, in init self._reset() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 430, in _reset observations, info = e.reset(seed=seed) # new way of doing seeding since Gym 0.26.0 File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 323, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 125, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 110, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/scenario_wrappers/gathering_reward_shaping.py", line 30, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 379, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/envs/env_wrappers.py", line 84, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 323, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/multiplayer_stats.py", line 51, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 323, in reset self._ensure_initialized() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 274, in _ensure_initialized self.initialize() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 269, in initialize self._game_init() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 244, in _game_init raise EnvCriticalError() sample_factory.envs.env_utils.EnvCriticalError [2023-03-09 12:32:25,091][270128] Unhandled exception in evt loop rollout_proc83_evt_loop [2023-03-09 12:32:25,088][270129] EvtLoop [rollout_proc89_evt_loop, process=rollout_proc89] unhandled exception in slot='init' connected to emitter=Emitter(object_id='Sampler', signal_name='_inference_workers_initialized'), args=() Traceback (most recent call last): File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 228, in _game_init self.game.init() vizdoom.vizdoom.SignalException: Signal SIGTERM received. ViZDoom instance has been closed. During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/signal_slot/signal_slot.py", line 355, in _process_signal slot_callable(*args) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/rollout_worker.py", line 150, in init env_runner.init(self.timing) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 418, in init self._reset() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 430, in _reset observations, info = e.reset(seed=seed) # new way of doing seeding since Gym 0.26.0 File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 323, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 125, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 110, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/scenario_wrappers/gathering_reward_shaping.py", line 30, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 379, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/envs/env_wrappers.py", line 84, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 323, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/multiplayer_stats.py", line 51, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 323, in reset self._ensure_initialized() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 274, in _ensure_initialized self.initialize() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 269, in initialize self._game_init() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 244, in _game_init raise EnvCriticalError() sample_factory.envs.env_utils.EnvCriticalError [2023-03-09 12:32:25,091][270129] Unhandled exception in evt loop rollout_proc89_evt_loop [2023-03-09 12:32:25,090][270090] EvtLoop [rollout_proc15_evt_loop, process=rollout_proc15] unhandled exception in slot='init' connected to emitter=Emitter(object_id='Sampler', signal_name='_inference_workers_initialized'), args=() Traceback (most recent call last): File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 228, in _game_init self.game.init() vizdoom.vizdoom.SignalException: Signal SIGTERM received. ViZDoom instance has been closed. During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/signal_slot/signal_slot.py", line 355, in _process_signal slot_callable(*args) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/rollout_worker.py", line 150, in init env_runner.init(self.timing) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 418, in init self._reset() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 430, in _reset observations, info = e.reset(seed=seed) # new way of doing seeding since Gym 0.26.0 File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 323, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 125, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 110, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/scenario_wrappers/gathering_reward_shaping.py", line 30, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 379, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/envs/env_wrappers.py", line 84, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 323, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/multiplayer_stats.py", line 51, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 323, in reset self._ensure_initialized() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 274, in _ensure_initialized self.initialize() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 269, in initialize self._game_init() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 244, in _game_init raise EnvCriticalError() sample_factory.envs.env_utils.EnvCriticalError [2023-03-09 12:32:25,092][270090] Unhandled exception in evt loop rollout_proc15_evt_loop [2023-03-09 12:32:25,091][270106] EvtLoop [rollout_proc28_evt_loop, process=rollout_proc28] unhandled exception in slot='init' connected to emitter=Emitter(object_id='Sampler', signal_name='_inference_workers_initialized'), args=() Traceback (most recent call last): File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/signal_slot/signal_slot.py", line 355, in _process_signal slot_callable(*args) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/rollout_worker.py", line 150, in init env_runner.init(self.timing) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 418, in init self._reset() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 439, in _reset observations, rew, terminated, truncated, info = e.step(actions) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 319, in step return self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 129, in step obs, rew, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 115, in step obs, rew, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/scenario_wrappers/gathering_reward_shaping.py", line 33, in step observation, reward, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 384, in step observation, reward, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/envs/env_wrappers.py", line 88, in step obs, reward, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 319, in step return self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/multiplayer_stats.py", line 54, in step obs, reward, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 452, in step reward = self.game.make_action(actions_flattened, self.skip_frames) vizdoom.vizdoom.SignalException: Signal SIGTERM received. ViZDoom instance has been closed. [2023-03-09 12:32:25,093][270106] Unhandled exception Signal SIGTERM received. ViZDoom instance has been closed. in evt loop rollout_proc28_evt_loop [2023-03-09 12:32:25,094][270154] VizDoom game.init() threw an exception SignalException('Signal SIGTERM received. ViZDoom instance has been closed.'). Terminate process... [2023-03-09 12:32:25,095][270134] VizDoom game.init() threw an exception SignalException('Signal SIGTERM received. ViZDoom instance has been closed.'). Terminate process... [2023-03-09 12:32:25,094][270154] EvtLoop [rollout_proc58_evt_loop, process=rollout_proc58] unhandled exception in slot='init' connected to emitter=Emitter(object_id='Sampler', signal_name='_inference_workers_initialized'), args=() Traceback (most recent call last): File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 228, in _game_init self.game.init() vizdoom.vizdoom.SignalException: Signal SIGTERM received. ViZDoom instance has been closed. During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/signal_slot/signal_slot.py", line 355, in _process_signal slot_callable(*args) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/rollout_worker.py", line 150, in init env_runner.init(self.timing) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 418, in init self._reset() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 430, in _reset observations, info = e.reset(seed=seed) # new way of doing seeding since Gym 0.26.0 File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 323, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 125, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 110, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/scenario_wrappers/gathering_reward_shaping.py", line 30, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 379, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/envs/env_wrappers.py", line 84, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 323, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/multiplayer_stats.py", line 51, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 323, in reset self._ensure_initialized() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 274, in _ensure_initialized self.initialize() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 269, in initialize self._game_init() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 244, in _game_init raise EnvCriticalError() sample_factory.envs.env_utils.EnvCriticalError [2023-03-09 12:32:25,096][270154] Unhandled exception in evt loop rollout_proc58_evt_loop [2023-03-09 12:32:25,096][270134] EvtLoop [rollout_proc63_evt_loop, process=rollout_proc63] unhandled exception in slot='init' connected to emitter=Emitter(object_id='Sampler', signal_name='_inference_workers_initialized'), args=() Traceback (most recent call last): File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 228, in _game_init self.game.init() vizdoom.vizdoom.SignalException: Signal SIGTERM received. ViZDoom instance has been closed. During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/signal_slot/signal_slot.py", line 355, in _process_signal slot_callable(*args) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/rollout_worker.py", line 150, in init env_runner.init(self.timing) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 418, in init self._reset() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 430, in _reset observations, info = e.reset(seed=seed) # new way of doing seeding since Gym 0.26.0 File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 323, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 125, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 110, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/scenario_wrappers/gathering_reward_shaping.py", line 30, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 379, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/envs/env_wrappers.py", line 84, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 323, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/multiplayer_stats.py", line 51, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 323, in reset self._ensure_initialized() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 274, in _ensure_initialized self.initialize() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 269, in initialize self._game_init() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 244, in _game_init raise EnvCriticalError() sample_factory.envs.env_utils.EnvCriticalError [2023-03-09 12:32:25,098][270134] Unhandled exception in evt loop rollout_proc63_evt_loop [2023-03-09 12:32:25,098][270596] VizDoom game.init() threw an exception SignalException('Signal SIGTERM received. ViZDoom instance has been closed.'). Terminate process... [2023-03-09 12:32:25,099][270596] EvtLoop [rollout_proc108_evt_loop, process=rollout_proc108] unhandled exception in slot='init' connected to emitter=Emitter(object_id='Sampler', signal_name='_inference_workers_initialized'), args=() Traceback (most recent call last): File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 228, in _game_init self.game.init() vizdoom.vizdoom.SignalException: Signal SIGTERM received. ViZDoom instance has been closed. During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/signal_slot/signal_slot.py", line 355, in _process_signal slot_callable(*args) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/rollout_worker.py", line 150, in init env_runner.init(self.timing) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 418, in init self._reset() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 430, in _reset observations, info = e.reset(seed=seed) # new way of doing seeding since Gym 0.26.0 File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 323, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 125, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 110, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/scenario_wrappers/gathering_reward_shaping.py", line 30, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 379, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/envs/env_wrappers.py", line 84, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 323, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/multiplayer_stats.py", line 51, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 323, in reset self._ensure_initialized() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 274, in _ensure_initialized self.initialize() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 269, in initialize self._game_init() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 244, in _game_init raise EnvCriticalError() sample_factory.envs.env_utils.EnvCriticalError [2023-03-09 12:32:25,101][270596] Unhandled exception in evt loop rollout_proc108_evt_loop [2023-03-09 12:32:25,104][270143] EvtLoop [rollout_proc72_evt_loop, process=rollout_proc72] unhandled exception in slot='init' connected to emitter=Emitter(object_id='Sampler', signal_name='_inference_workers_initialized'), args=() Traceback (most recent call last): File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/signal_slot/signal_slot.py", line 355, in _process_signal slot_callable(*args) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/rollout_worker.py", line 150, in init env_runner.init(self.timing) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 418, in init self._reset() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 439, in _reset observations, rew, terminated, truncated, info = e.step(actions) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 319, in step return self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 129, in step obs, rew, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 115, in step obs, rew, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/scenario_wrappers/gathering_reward_shaping.py", line 33, in step observation, reward, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 384, in step observation, reward, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/envs/env_wrappers.py", line 88, in step obs, reward, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 319, in step return self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/multiplayer_stats.py", line 54, in step obs, reward, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 452, in step reward = self.game.make_action(actions_flattened, self.skip_frames) vizdoom.vizdoom.SignalException: Signal SIGTERM received. ViZDoom instance has been closed. [2023-03-09 12:32:25,106][270143] Unhandled exception Signal SIGTERM received. ViZDoom instance has been closed. in evt loop rollout_proc72_evt_loop [2023-03-09 12:32:25,105][270156] EvtLoop [rollout_proc82_evt_loop, process=rollout_proc82] unhandled exception in slot='init' connected to emitter=Emitter(object_id='Sampler', signal_name='_inference_workers_initialized'), args=() Traceback (most recent call last): File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/signal_slot/signal_slot.py", line 355, in _process_signal slot_callable(*args) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/rollout_worker.py", line 150, in init env_runner.init(self.timing) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 418, in init self._reset() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 439, in _reset observations, rew, terminated, truncated, info = e.step(actions) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 319, in step return self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 129, in step obs, rew, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 115, in step obs, rew, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/scenario_wrappers/gathering_reward_shaping.py", line 33, in step observation, reward, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 384, in step observation, reward, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/envs/env_wrappers.py", line 88, in step obs, reward, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 319, in step return self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/multiplayer_stats.py", line 54, in step obs, reward, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 452, in step reward = self.game.make_action(actions_flattened, self.skip_frames) vizdoom.vizdoom.SignalException: Signal SIGTERM received. ViZDoom instance has been closed. [2023-03-09 12:32:25,108][270156] Unhandled exception Signal SIGTERM received. ViZDoom instance has been closed. in evt loop rollout_proc82_evt_loop [2023-03-09 12:32:25,108][271224] EvtLoop [rollout_proc126_evt_loop, process=rollout_proc126] unhandled exception in slot='init' connected to emitter=Emitter(object_id='Sampler', signal_name='_inference_workers_initialized'), args=() Traceback (most recent call last): File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/signal_slot/signal_slot.py", line 355, in _process_signal slot_callable(*args) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/rollout_worker.py", line 150, in init env_runner.init(self.timing) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 418, in init self._reset() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 439, in _reset observations, rew, terminated, truncated, info = e.step(actions) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 319, in step return self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 129, in step obs, rew, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 115, in step obs, rew, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/scenario_wrappers/gathering_reward_shaping.py", line 33, in step observation, reward, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 384, in step observation, reward, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/envs/env_wrappers.py", line 88, in step obs, reward, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 319, in step return self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/multiplayer_stats.py", line 54, in step obs, reward, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 452, in step reward = self.game.make_action(actions_flattened, self.skip_frames) vizdoom.vizdoom.SignalException: Signal SIGTERM received. ViZDoom instance has been closed. [2023-03-09 12:32:25,111][271224] Unhandled exception Signal SIGTERM received. ViZDoom instance has been closed. in evt loop rollout_proc126_evt_loop [2023-03-09 12:32:25,143][270086] EvtLoop [rollout_proc9_evt_loop, process=rollout_proc9] unhandled exception in slot='init' connected to emitter=Emitter(object_id='Sampler', signal_name='_inference_workers_initialized'), args=() Traceback (most recent call last): File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/signal_slot/signal_slot.py", line 355, in _process_signal slot_callable(*args) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/rollout_worker.py", line 150, in init env_runner.init(self.timing) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 418, in init self._reset() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 439, in _reset observations, rew, terminated, truncated, info = e.step(actions) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 319, in step return self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 129, in step obs, rew, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 115, in step obs, rew, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/scenario_wrappers/gathering_reward_shaping.py", line 33, in step observation, reward, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 384, in step observation, reward, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/envs/env_wrappers.py", line 88, in step obs, reward, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 319, in step return self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/multiplayer_stats.py", line 54, in step obs, reward, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 452, in step reward = self.game.make_action(actions_flattened, self.skip_frames) vizdoom.vizdoom.SignalException: Signal SIGTERM received. ViZDoom instance has been closed. [2023-03-09 12:32:25,145][270086] Unhandled exception Signal SIGTERM received. ViZDoom instance has been closed. in evt loop rollout_proc9_evt_loop [2023-03-09 12:32:25,161][270158] EvtLoop [rollout_proc73_evt_loop, process=rollout_proc73] unhandled exception in slot='init' connected to emitter=Emitter(object_id='Sampler', signal_name='_inference_workers_initialized'), args=() Traceback (most recent call last): File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/signal_slot/signal_slot.py", line 355, in _process_signal slot_callable(*args) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/rollout_worker.py", line 150, in init env_runner.init(self.timing) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 418, in init self._reset() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 439, in _reset observations, rew, terminated, truncated, info = e.step(actions) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 319, in step return self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 129, in step obs, rew, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 115, in step obs, rew, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/scenario_wrappers/gathering_reward_shaping.py", line 33, in step observation, reward, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 384, in step observation, reward, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/envs/env_wrappers.py", line 88, in step obs, reward, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 319, in step return self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/multiplayer_stats.py", line 54, in step obs, reward, terminated, truncated, info = self.env.step(action) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 452, in step reward = self.game.make_action(actions_flattened, self.skip_frames) vizdoom.vizdoom.SignalException: Signal SIGTERM received. ViZDoom instance has been closed. [2023-03-09 12:32:25,163][270158] Unhandled exception Signal SIGTERM received. ViZDoom instance has been closed. in evt loop rollout_proc73_evt_loop [2023-03-09 12:32:25,178][270013] VizDoom game.init() threw an exception SignalException('Signal SIGTERM received. ViZDoom instance has been closed.'). Terminate process... [2023-03-09 12:32:25,179][270013] EvtLoop [rollout_proc41_evt_loop, process=rollout_proc41] unhandled exception in slot='init' connected to emitter=Emitter(object_id='Sampler', signal_name='_inference_workers_initialized'), args=() Traceback (most recent call last): File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 228, in _game_init self.game.init() vizdoom.vizdoom.SignalException: Signal SIGTERM received. ViZDoom instance has been closed. During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/signal_slot/signal_slot.py", line 355, in _process_signal slot_callable(*args) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/rollout_worker.py", line 150, in init env_runner.init(self.timing) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 418, in init self._reset() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 430, in _reset observations, info = e.reset(seed=seed) # new way of doing seeding since Gym 0.26.0 File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 323, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 125, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 110, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/scenario_wrappers/gathering_reward_shaping.py", line 30, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 379, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/envs/env_wrappers.py", line 84, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 323, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/multiplayer_stats.py", line 51, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 323, in reset self._ensure_initialized() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 274, in _ensure_initialized self.initialize() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 269, in initialize self._game_init() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 244, in _game_init raise EnvCriticalError() sample_factory.envs.env_utils.EnvCriticalError [2023-03-09 12:32:25,182][270013] Unhandled exception in evt loop rollout_proc41_evt_loop [2023-03-09 12:32:25,192][270118] VizDoom game.init() threw an exception SignalException('Signal SIGTERM received. ViZDoom instance has been closed.'). Terminate process... [2023-03-09 12:32:25,192][270118] EvtLoop [rollout_proc53_evt_loop, process=rollout_proc53] unhandled exception in slot='init' connected to emitter=Emitter(object_id='Sampler', signal_name='_inference_workers_initialized'), args=() Traceback (most recent call last): File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 228, in _game_init self.game.init() vizdoom.vizdoom.SignalException: Signal SIGTERM received. ViZDoom instance has been closed. During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/signal_slot/signal_slot.py", line 355, in _process_signal slot_callable(*args) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/rollout_worker.py", line 150, in init env_runner.init(self.timing) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 418, in init self._reset() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 430, in _reset observations, info = e.reset(seed=seed) # new way of doing seeding since Gym 0.26.0 File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 323, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 125, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 110, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/scenario_wrappers/gathering_reward_shaping.py", line 30, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 379, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/envs/env_wrappers.py", line 84, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 323, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/multiplayer_stats.py", line 51, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 323, in reset self._ensure_initialized() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 274, in _ensure_initialized self.initialize() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 269, in initialize self._game_init() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 244, in _game_init raise EnvCriticalError() sample_factory.envs.env_utils.EnvCriticalError [2023-03-09 12:32:25,195][270118] Unhandled exception in evt loop rollout_proc53_evt_loop [2023-03-09 12:32:25,196][270113] VizDoom game.init() threw an exception SignalException('Signal SIGTERM received. ViZDoom instance has been closed.'). Terminate process... [2023-03-09 12:32:25,197][270146] VizDoom game.init() threw an exception SignalException('Signal SIGTERM received. ViZDoom instance has been closed.'). Terminate process... [2023-03-09 12:32:25,196][270113] EvtLoop [rollout_proc40_evt_loop, process=rollout_proc40] unhandled exception in slot='init' connected to emitter=Emitter(object_id='Sampler', signal_name='_inference_workers_initialized'), args=() Traceback (most recent call last): File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 228, in _game_init self.game.init() vizdoom.vizdoom.SignalException: Signal SIGTERM received. ViZDoom instance has been closed. During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/signal_slot/signal_slot.py", line 355, in _process_signal slot_callable(*args) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/rollout_worker.py", line 150, in init env_runner.init(self.timing) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 418, in init self._reset() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 430, in _reset observations, info = e.reset(seed=seed) # new way of doing seeding since Gym 0.26.0 File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 323, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 125, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 110, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/scenario_wrappers/gathering_reward_shaping.py", line 30, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 379, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/envs/env_wrappers.py", line 84, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 323, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/multiplayer_stats.py", line 51, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 323, in reset self._ensure_initialized() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 274, in _ensure_initialized self.initialize() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 269, in initialize self._game_init() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 244, in _game_init raise EnvCriticalError() sample_factory.envs.env_utils.EnvCriticalError [2023-03-09 12:32:25,199][270113] Unhandled exception in evt loop rollout_proc40_evt_loop [2023-03-09 12:32:25,197][270146] EvtLoop [rollout_proc91_evt_loop, process=rollout_proc91] unhandled exception in slot='init' connected to emitter=Emitter(object_id='Sampler', signal_name='_inference_workers_initialized'), args=() Traceback (most recent call last): File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 228, in _game_init self.game.init() vizdoom.vizdoom.SignalException: Signal SIGTERM received. ViZDoom instance has been closed. During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/signal_slot/signal_slot.py", line 355, in _process_signal slot_callable(*args) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/rollout_worker.py", line 150, in init env_runner.init(self.timing) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 418, in init self._reset() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 430, in _reset observations, info = e.reset(seed=seed) # new way of doing seeding since Gym 0.26.0 File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 323, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 125, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 110, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/scenario_wrappers/gathering_reward_shaping.py", line 30, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 379, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/envs/env_wrappers.py", line 84, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 323, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/multiplayer_stats.py", line 51, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 323, in reset self._ensure_initialized() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 274, in _ensure_initialized self.initialize() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 269, in initialize self._game_init() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 244, in _game_init raise EnvCriticalError() sample_factory.envs.env_utils.EnvCriticalError [2023-03-09 12:32:25,200][270146] Unhandled exception in evt loop rollout_proc91_evt_loop [2023-03-09 12:32:25,206][270944] VizDoom game.init() threw an exception SignalException('Signal SIGTERM received. ViZDoom instance has been closed.'). Terminate process... [2023-03-09 12:32:25,206][270944] EvtLoop [rollout_proc103_evt_loop, process=rollout_proc103] unhandled exception in slot='init' connected to emitter=Emitter(object_id='Sampler', signal_name='_inference_workers_initialized'), args=() Traceback (most recent call last): File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 228, in _game_init self.game.init() vizdoom.vizdoom.SignalException: Signal SIGTERM received. ViZDoom instance has been closed. During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/signal_slot/signal_slot.py", line 355, in _process_signal slot_callable(*args) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/rollout_worker.py", line 150, in init env_runner.init(self.timing) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 418, in init self._reset() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 430, in _reset observations, info = e.reset(seed=seed) # new way of doing seeding since Gym 0.26.0 File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 323, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 125, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 110, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/scenario_wrappers/gathering_reward_shaping.py", line 30, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 379, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/envs/env_wrappers.py", line 84, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 323, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/multiplayer_stats.py", line 51, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 323, in reset self._ensure_initialized() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 274, in _ensure_initialized self.initialize() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 269, in initialize self._game_init() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 244, in _game_init raise EnvCriticalError() sample_factory.envs.env_utils.EnvCriticalError [2023-03-09 12:32:25,209][270944] Unhandled exception in evt loop rollout_proc103_evt_loop [2023-03-09 12:32:25,214][270514] VizDoom game.init() threw an exception SignalException('Signal SIGTERM received. ViZDoom instance has been closed.'). Terminate process... [2023-03-09 12:32:25,215][270514] EvtLoop [rollout_proc116_evt_loop, process=rollout_proc116] unhandled exception in slot='init' connected to emitter=Emitter(object_id='Sampler', signal_name='_inference_workers_initialized'), args=() Traceback (most recent call last): File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 228, in _game_init self.game.init() vizdoom.vizdoom.SignalException: Signal SIGTERM received. ViZDoom instance has been closed. During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/signal_slot/signal_slot.py", line 355, in _process_signal slot_callable(*args) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/rollout_worker.py", line 150, in init env_runner.init(self.timing) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 418, in init self._reset() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 430, in _reset observations, info = e.reset(seed=seed) # new way of doing seeding since Gym 0.26.0 File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 323, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 125, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 110, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/scenario_wrappers/gathering_reward_shaping.py", line 30, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 379, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sample_factory/envs/env_wrappers.py", line 84, in reset obs, info = self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/gym/core.py", line 323, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/multiplayer_stats.py", line 51, in reset return self.env.reset(**kwargs) File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 323, in reset self._ensure_initialized() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 274, in _ensure_initialized self.initialize() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 269, in initialize self._game_init() File "/home/rolo/.pyenv/versions/3.10.9/envs/samplefactory/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 244, in _game_init raise EnvCriticalError() sample_factory.envs.env_utils.EnvCriticalError [2023-03-09 12:32:25,217][270514] Unhandled exception in evt loop rollout_proc116_evt_loop