| [2024-11-08 10:37:47,579][00587] Saving configuration to /content/train_dir/default_experiment/config.json... | |
| [2024-11-08 10:37:47,581][00587] Rollout worker 0 uses device cpu | |
| [2024-11-08 10:37:47,582][00587] Rollout worker 1 uses device cpu | |
| [2024-11-08 10:37:47,584][00587] Rollout worker 2 uses device cpu | |
| [2024-11-08 10:37:47,585][00587] Rollout worker 3 uses device cpu | |
| [2024-11-08 10:37:47,586][00587] Rollout worker 4 uses device cpu | |
| [2024-11-08 10:37:47,587][00587] Rollout worker 5 uses device cpu | |
| [2024-11-08 10:37:47,588][00587] Rollout worker 6 uses device cpu | |
| [2024-11-08 10:37:47,589][00587] Rollout worker 7 uses device cpu | |
| [2024-11-08 10:37:47,983][00587] Using GPUs [0] for process 0 (actually maps to GPUs [0]) | |
| [2024-11-08 10:37:47,984][00587] InferenceWorker_p0-w0: min num requests: 2 | |
| [2024-11-08 10:37:48,016][00587] Starting all processes... | |
| [2024-11-08 10:37:48,019][00587] Starting process learner_proc0 | |
| [2024-11-08 10:37:48,061][00587] Starting all processes... | |
| [2024-11-08 10:37:48,070][00587] Starting process inference_proc0-0 | |
| [2024-11-08 10:37:48,071][00587] Starting process rollout_proc0 | |
| [2024-11-08 10:37:48,071][00587] Starting process rollout_proc1 | |
| [2024-11-08 10:37:48,071][00587] Starting process rollout_proc2 | |
| [2024-11-08 10:37:48,071][00587] Starting process rollout_proc3 | |
| [2024-11-08 10:37:48,071][00587] Starting process rollout_proc4 | |
| [2024-11-08 10:37:48,071][00587] Starting process rollout_proc5 | |
| [2024-11-08 10:37:48,071][00587] Starting process rollout_proc6 | |
| [2024-11-08 10:37:48,071][00587] Starting process rollout_proc7 | |
| [2024-11-08 10:38:04,473][03563] Using GPUs [0] for process 0 (actually maps to GPUs [0]) | |
| [2024-11-08 10:38:04,474][03563] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0 | |
| [2024-11-08 10:38:04,534][03563] Num visible devices: 1 | |
| [2024-11-08 10:38:04,579][03563] Starting seed is not provided | |
| [2024-11-08 10:38:04,579][03563] Using GPUs [0] for process 0 (actually maps to GPUs [0]) | |
| [2024-11-08 10:38:04,580][03563] Initializing actor-critic model on device cuda:0 | |
| [2024-11-08 10:38:04,581][03563] RunningMeanStd input shape: (3, 72, 128) | |
| [2024-11-08 10:38:04,584][03563] RunningMeanStd input shape: (1,) | |
| [2024-11-08 10:38:04,634][03580] Worker 2 uses CPU cores [0] | |
| [2024-11-08 10:38:04,654][03563] ConvEncoder: input_channels=3 | |
| [2024-11-08 10:38:04,896][03576] Worker 0 uses CPU cores [0] | |
| [2024-11-08 10:38:05,219][03582] Worker 5 uses CPU cores [1] | |
| [2024-11-08 10:38:05,220][03578] Using GPUs [0] for process 0 (actually maps to GPUs [0]) | |
| [2024-11-08 10:38:05,222][03578] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0 | |
| [2024-11-08 10:38:05,254][03579] Worker 3 uses CPU cores [1] | |
| [2024-11-08 10:38:05,300][03584] Worker 7 uses CPU cores [1] | |
| [2024-11-08 10:38:05,314][03578] Num visible devices: 1 | |
| [2024-11-08 10:38:05,327][03583] Worker 6 uses CPU cores [0] | |
| [2024-11-08 10:38:05,339][03563] Conv encoder output size: 512 | |
| [2024-11-08 10:38:05,339][03563] Policy head output size: 512 | |
| [2024-11-08 10:38:05,360][03577] Worker 1 uses CPU cores [1] | |
| [2024-11-08 10:38:05,418][03563] Created Actor Critic model with architecture: | |
| [2024-11-08 10:38:05,419][03563] 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) | |
| ) | |
| ) | |
| [2024-11-08 10:38:05,429][03581] Worker 4 uses CPU cores [0] | |
| [2024-11-08 10:38:05,911][03563] Using optimizer <class 'torch.optim.adam.Adam'> | |
| [2024-11-08 10:38:07,981][00587] Heartbeat connected on Batcher_0 | |
| [2024-11-08 10:38:07,986][00587] Heartbeat connected on InferenceWorker_p0-w0 | |
| [2024-11-08 10:38:07,992][00587] Heartbeat connected on RolloutWorker_w0 | |
| [2024-11-08 10:38:07,995][00587] Heartbeat connected on RolloutWorker_w1 | |
| [2024-11-08 10:38:08,000][00587] Heartbeat connected on RolloutWorker_w2 | |
| [2024-11-08 10:38:08,003][00587] Heartbeat connected on RolloutWorker_w3 | |
| [2024-11-08 10:38:08,006][00587] Heartbeat connected on RolloutWorker_w4 | |
| [2024-11-08 10:38:08,013][00587] Heartbeat connected on RolloutWorker_w6 | |
| [2024-11-08 10:38:08,015][00587] Heartbeat connected on RolloutWorker_w5 | |
| [2024-11-08 10:38:08,017][00587] Heartbeat connected on RolloutWorker_w7 | |
| [2024-11-08 10:38:10,433][03563] No checkpoints found | |
| [2024-11-08 10:38:10,433][03563] Did not load from checkpoint, starting from scratch! | |
| [2024-11-08 10:38:10,433][03563] Initialized policy 0 weights for model version 0 | |
| [2024-11-08 10:38:10,437][03563] LearnerWorker_p0 finished initialization! | |
| [2024-11-08 10:38:10,437][00587] Heartbeat connected on LearnerWorker_p0 | |
| [2024-11-08 10:38:10,441][03563] Using GPUs [0] for process 0 (actually maps to GPUs [0]) | |
| [2024-11-08 10:38:10,639][03578] RunningMeanStd input shape: (3, 72, 128) | |
| [2024-11-08 10:38:10,641][03578] RunningMeanStd input shape: (1,) | |
| [2024-11-08 10:38:10,653][03578] ConvEncoder: input_channels=3 | |
| [2024-11-08 10:38:10,755][03578] Conv encoder output size: 512 | |
| [2024-11-08 10:38:10,755][03578] Policy head output size: 512 | |
| [2024-11-08 10:38:10,806][00587] Inference worker 0-0 is ready! | |
| [2024-11-08 10:38:10,808][00587] All inference workers are ready! Signal rollout workers to start! | |
| [2024-11-08 10:38:11,002][03582] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2024-11-08 10:38:11,003][03577] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2024-11-08 10:38:10,997][03584] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2024-11-08 10:38:11,005][03583] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2024-11-08 10:38:11,004][03576] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2024-11-08 10:38:11,006][03579] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2024-11-08 10:38:11,007][03581] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2024-11-08 10:38:11,008][03580] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2024-11-08 10:38:11,020][00587] 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) | |
| [2024-11-08 10:38:12,743][03584] Decorrelating experience for 0 frames... | |
| [2024-11-08 10:38:13,148][03577] Decorrelating experience for 0 frames... | |
| [2024-11-08 10:38:13,349][03583] Decorrelating experience for 0 frames... | |
| [2024-11-08 10:38:13,356][03580] Decorrelating experience for 0 frames... | |
| [2024-11-08 10:38:13,359][03581] Decorrelating experience for 0 frames... | |
| [2024-11-08 10:38:13,710][03577] Decorrelating experience for 32 frames... | |
| [2024-11-08 10:38:14,141][03584] Decorrelating experience for 32 frames... | |
| [2024-11-08 10:38:14,432][03583] Decorrelating experience for 32 frames... | |
| [2024-11-08 10:38:14,434][03580] Decorrelating experience for 32 frames... | |
| [2024-11-08 10:38:14,505][03576] Decorrelating experience for 0 frames... | |
| [2024-11-08 10:38:14,692][03577] Decorrelating experience for 64 frames... | |
| [2024-11-08 10:38:15,358][03579] Decorrelating experience for 0 frames... | |
| [2024-11-08 10:38:15,393][03584] Decorrelating experience for 64 frames... | |
| [2024-11-08 10:38:15,635][03577] Decorrelating experience for 96 frames... | |
| [2024-11-08 10:38:15,646][03581] Decorrelating experience for 32 frames... | |
| [2024-11-08 10:38:15,695][03583] Decorrelating experience for 64 frames... | |
| [2024-11-08 10:38:15,698][03576] Decorrelating experience for 32 frames... | |
| [2024-11-08 10:38:16,020][00587] 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) | |
| [2024-11-08 10:38:16,379][03580] Decorrelating experience for 64 frames... | |
| [2024-11-08 10:38:16,580][03581] Decorrelating experience for 64 frames... | |
| [2024-11-08 10:38:16,861][03584] Decorrelating experience for 96 frames... | |
| [2024-11-08 10:38:16,860][03579] Decorrelating experience for 32 frames... | |
| [2024-11-08 10:38:17,046][03577] Decorrelating experience for 128 frames... | |
| [2024-11-08 10:38:17,533][03580] Decorrelating experience for 96 frames... | |
| [2024-11-08 10:38:17,897][03576] Decorrelating experience for 64 frames... | |
| [2024-11-08 10:38:17,954][03581] Decorrelating experience for 96 frames... | |
| [2024-11-08 10:38:18,363][03582] Decorrelating experience for 0 frames... | |
| [2024-11-08 10:38:18,410][03579] Decorrelating experience for 64 frames... | |
| [2024-11-08 10:38:18,618][03584] Decorrelating experience for 128 frames... | |
| [2024-11-08 10:38:19,468][03583] Decorrelating experience for 96 frames... | |
| [2024-11-08 10:38:19,605][03576] Decorrelating experience for 96 frames... | |
| [2024-11-08 10:38:19,852][03581] Decorrelating experience for 128 frames... | |
| [2024-11-08 10:38:20,272][03582] Decorrelating experience for 32 frames... | |
| [2024-11-08 10:38:20,329][03580] Decorrelating experience for 128 frames... | |
| [2024-11-08 10:38:20,467][03579] Decorrelating experience for 96 frames... | |
| [2024-11-08 10:38:21,020][00587] 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) | |
| [2024-11-08 10:38:21,203][03577] Decorrelating experience for 160 frames... | |
| [2024-11-08 10:38:21,792][03583] Decorrelating experience for 128 frames... | |
| [2024-11-08 10:38:22,154][03581] Decorrelating experience for 160 frames... | |
| [2024-11-08 10:38:22,371][03584] Decorrelating experience for 160 frames... | |
| [2024-11-08 10:38:22,545][03576] Decorrelating experience for 128 frames... | |
| [2024-11-08 10:38:22,768][03580] Decorrelating experience for 160 frames... | |
| [2024-11-08 10:38:23,716][03579] Decorrelating experience for 128 frames... | |
| [2024-11-08 10:38:24,025][03582] Decorrelating experience for 64 frames... | |
| [2024-11-08 10:38:24,207][03577] Decorrelating experience for 192 frames... | |
| [2024-11-08 10:38:24,727][03583] Decorrelating experience for 160 frames... | |
| [2024-11-08 10:38:24,780][03581] Decorrelating experience for 192 frames... | |
| [2024-11-08 10:38:25,089][03576] Decorrelating experience for 160 frames... | |
| [2024-11-08 10:38:25,455][03580] Decorrelating experience for 192 frames... | |
| [2024-11-08 10:38:26,021][00587] 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) | |
| [2024-11-08 10:38:26,136][03584] Decorrelating experience for 192 frames... | |
| [2024-11-08 10:38:26,518][03582] Decorrelating experience for 96 frames... | |
| [2024-11-08 10:38:27,372][03583] Decorrelating experience for 192 frames... | |
| [2024-11-08 10:38:27,529][03581] Decorrelating experience for 224 frames... | |
| [2024-11-08 10:38:27,570][03577] Decorrelating experience for 224 frames... | |
| [2024-11-08 10:38:27,705][03576] Decorrelating experience for 192 frames... | |
| [2024-11-08 10:38:27,880][03579] Decorrelating experience for 160 frames... | |
| [2024-11-08 10:38:28,110][03580] Decorrelating experience for 224 frames... | |
| [2024-11-08 10:38:28,140][03582] Decorrelating experience for 128 frames... | |
| [2024-11-08 10:38:29,186][03584] Decorrelating experience for 224 frames... | |
| [2024-11-08 10:38:29,609][03583] Decorrelating experience for 224 frames... | |
| [2024-11-08 10:38:29,701][03579] Decorrelating experience for 192 frames... | |
| [2024-11-08 10:38:29,902][03576] Decorrelating experience for 224 frames... | |
| [2024-11-08 10:38:30,764][03577] Decorrelating experience for 256 frames... | |
| [2024-11-08 10:38:30,841][03581] Decorrelating experience for 256 frames... | |
| [2024-11-08 10:38:31,015][03582] Decorrelating experience for 160 frames... | |
| [2024-11-08 10:38:31,020][00587] 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) | |
| [2024-11-08 10:38:31,775][03579] Decorrelating experience for 224 frames... | |
| [2024-11-08 10:38:32,308][03580] Decorrelating experience for 256 frames... | |
| [2024-11-08 10:38:32,360][03583] Decorrelating experience for 256 frames... | |
| [2024-11-08 10:38:32,476][03584] Decorrelating experience for 256 frames... | |
| [2024-11-08 10:38:32,750][03576] Decorrelating experience for 256 frames... | |
| [2024-11-08 10:38:32,835][03577] Decorrelating experience for 288 frames... | |
| [2024-11-08 10:38:33,730][03581] Decorrelating experience for 288 frames... | |
| [2024-11-08 10:38:33,988][03582] Decorrelating experience for 192 frames... | |
| [2024-11-08 10:38:34,113][03580] Decorrelating experience for 288 frames... | |
| [2024-11-08 10:38:34,619][03584] Decorrelating experience for 288 frames... | |
| [2024-11-08 10:38:34,772][03580] Decorrelating experience for 320 frames... | |
| [2024-11-08 10:38:34,896][03579] Decorrelating experience for 256 frames... | |
| [2024-11-08 10:38:35,364][03577] Decorrelating experience for 320 frames... | |
| [2024-11-08 10:38:35,767][03580] Decorrelating experience for 352 frames... | |
| [2024-11-08 10:38:36,020][00587] 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) | |
| [2024-11-08 10:38:36,255][03582] Decorrelating experience for 224 frames... | |
| [2024-11-08 10:38:36,936][03583] Decorrelating experience for 288 frames... | |
| [2024-11-08 10:38:37,110][03584] Decorrelating experience for 320 frames... | |
| [2024-11-08 10:38:37,381][03579] Decorrelating experience for 288 frames... | |
| [2024-11-08 10:38:38,341][03577] Decorrelating experience for 352 frames... | |
| [2024-11-08 10:38:39,059][03576] Decorrelating experience for 288 frames... | |
| [2024-11-08 10:38:39,977][03583] Decorrelating experience for 320 frames... | |
| [2024-11-08 10:38:40,380][03584] Decorrelating experience for 352 frames... | |
| [2024-11-08 10:38:40,540][03579] Decorrelating experience for 320 frames... | |
| [2024-11-08 10:38:41,020][00587] 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) | |
| [2024-11-08 10:38:41,351][03580] Decorrelating experience for 384 frames... | |
| [2024-11-08 10:38:41,947][03577] Decorrelating experience for 384 frames... | |
| [2024-11-08 10:38:43,036][03582] Decorrelating experience for 256 frames... | |
| [2024-11-08 10:38:43,204][03583] Decorrelating experience for 352 frames... | |
| [2024-11-08 10:38:44,045][03584] Decorrelating experience for 384 frames... | |
| [2024-11-08 10:38:44,108][03579] Decorrelating experience for 352 frames... | |
| [2024-11-08 10:38:44,127][03576] Decorrelating experience for 320 frames... | |
| [2024-11-08 10:38:45,217][03580] Decorrelating experience for 416 frames... | |
| [2024-11-08 10:38:45,719][03577] Decorrelating experience for 416 frames... | |
| [2024-11-08 10:38:46,020][00587] 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) | |
| [2024-11-08 10:38:46,525][03581] Decorrelating experience for 320 frames... | |
| [2024-11-08 10:38:46,544][03582] Decorrelating experience for 288 frames... | |
| [2024-11-08 10:38:47,589][03576] Decorrelating experience for 352 frames... | |
| [2024-11-08 10:38:47,863][03579] Decorrelating experience for 384 frames... | |
| [2024-11-08 10:38:47,873][03584] Decorrelating experience for 416 frames... | |
| [2024-11-08 10:38:49,174][03583] Decorrelating experience for 384 frames... | |
| [2024-11-08 10:38:49,181][03580] Decorrelating experience for 448 frames... | |
| [2024-11-08 10:38:49,397][03577] Decorrelating experience for 448 frames... | |
| [2024-11-08 10:38:50,140][03581] Decorrelating experience for 352 frames... | |
| [2024-11-08 10:38:51,020][00587] 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) | |
| [2024-11-08 10:38:51,131][03584] Decorrelating experience for 448 frames... | |
| [2024-11-08 10:38:51,203][03576] Decorrelating experience for 384 frames... | |
| [2024-11-08 10:38:51,659][03579] Decorrelating experience for 416 frames... | |
| [2024-11-08 10:38:52,216][03577] Decorrelating experience for 480 frames... | |
| [2024-11-08 10:38:52,276][03583] Decorrelating experience for 416 frames... | |
| [2024-11-08 10:38:52,416][03580] Decorrelating experience for 480 frames... | |
| [2024-11-08 10:38:53,103][03582] Decorrelating experience for 320 frames... | |
| [2024-11-08 10:38:53,717][03581] Decorrelating experience for 384 frames... | |
| [2024-11-08 10:38:54,004][03576] Decorrelating experience for 416 frames... | |
| [2024-11-08 10:38:54,024][03584] Decorrelating experience for 480 frames... | |
| [2024-11-08 10:38:55,137][03579] Decorrelating experience for 448 frames... | |
| [2024-11-08 10:38:55,273][03583] Decorrelating experience for 448 frames... | |
| [2024-11-08 10:38:56,022][00587] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 6.0. Samples: 272. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) | |
| [2024-11-08 10:38:56,576][03581] Decorrelating experience for 416 frames... | |
| [2024-11-08 10:38:56,944][03582] Decorrelating experience for 352 frames... | |
| [2024-11-08 10:38:58,472][03579] Decorrelating experience for 480 frames... | |
| [2024-11-08 10:38:59,190][03583] Decorrelating experience for 480 frames... | |
| [2024-11-08 10:38:59,716][03576] Decorrelating experience for 448 frames... | |
| [2024-11-08 10:39:01,026][00587] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 45.1. Samples: 2032. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) | |
| [2024-11-08 10:39:01,034][00587] Avg episode reward: [(0, '1.661')] | |
| [2024-11-08 10:39:01,217][03581] Decorrelating experience for 448 frames... | |
| [2024-11-08 10:39:01,972][03563] Signal inference workers to stop experience collection... | |
| [2024-11-08 10:39:02,005][03578] InferenceWorker_p0-w0: stopping experience collection | |
| [2024-11-08 10:39:02,375][03582] Decorrelating experience for 384 frames... | |
| [2024-11-08 10:39:04,723][03563] Signal inference workers to resume experience collection... | |
| [2024-11-08 10:39:04,727][03578] InferenceWorker_p0-w0: resuming experience collection | |
| [2024-11-08 10:39:05,489][03576] Decorrelating experience for 480 frames... | |
| [2024-11-08 10:39:05,849][03582] Decorrelating experience for 416 frames... | |
| [2024-11-08 10:39:06,021][00587] Fps is (10 sec: 1229.0, 60 sec: 223.4, 300 sec: 223.4). Total num frames: 12288. Throughput: 0: 72.5. Samples: 3264. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) | |
| [2024-11-08 10:39:06,023][00587] Avg episode reward: [(0, '1.734')] | |
| [2024-11-08 10:39:09,452][03581] Decorrelating experience for 480 frames... | |
| [2024-11-08 10:39:11,021][00587] Fps is (10 sec: 2049.0, 60 sec: 341.3, 300 sec: 341.3). Total num frames: 20480. Throughput: 0: 156.4. Samples: 7040. Policy #0 lag: (min: 0.0, avg: 0.6, max: 3.0) | |
| [2024-11-08 10:39:11,024][00587] Avg episode reward: [(0, '2.328')] | |
| [2024-11-08 10:39:12,213][03582] Decorrelating experience for 448 frames... | |
| [2024-11-08 10:39:16,020][00587] Fps is (10 sec: 2048.1, 60 sec: 546.1, 300 sec: 504.1). Total num frames: 32768. Throughput: 0: 198.4. Samples: 8928. Policy #0 lag: (min: 0.0, avg: 1.3, max: 4.0) | |
| [2024-11-08 10:39:16,022][00587] Avg episode reward: [(0, '2.459')] | |
| [2024-11-08 10:39:17,330][03578] Updated weights for policy 0, policy_version 10 (0.0015) | |
| [2024-11-08 10:39:18,152][03582] Decorrelating experience for 480 frames... | |
| [2024-11-08 10:39:21,020][00587] Fps is (10 sec: 4096.6, 60 sec: 1024.0, 300 sec: 877.7). Total num frames: 61440. Throughput: 0: 337.1. Samples: 15168. Policy #0 lag: (min: 0.0, avg: 0.7, max: 4.0) | |
| [2024-11-08 10:39:21,023][00587] Avg episode reward: [(0, '3.615')] | |
| [2024-11-08 10:39:26,020][00587] Fps is (10 sec: 4505.5, 60 sec: 1297.1, 300 sec: 1037.7). Total num frames: 77824. Throughput: 0: 507.2. Samples: 22824. Policy #0 lag: (min: 0.0, avg: 1.9, max: 5.0) | |
| [2024-11-08 10:39:26,025][00587] Avg episode reward: [(0, '4.014')] | |
| [2024-11-08 10:39:26,765][03578] Updated weights for policy 0, policy_version 20 (0.0014) | |
| [2024-11-08 10:39:31,020][00587] Fps is (10 sec: 3276.8, 60 sec: 1570.1, 300 sec: 1177.6). Total num frames: 94208. Throughput: 0: 565.0. Samples: 25424. Policy #0 lag: (min: 0.0, avg: 2.1, max: 5.0) | |
| [2024-11-08 10:39:31,027][00587] Avg episode reward: [(0, '4.157')] | |
| [2024-11-08 10:39:36,028][00587] Fps is (10 sec: 3683.5, 60 sec: 1911.2, 300 sec: 1349.1). Total num frames: 114688. Throughput: 0: 683.1. Samples: 30744. Policy #0 lag: (min: 0.0, avg: 1.9, max: 5.0) | |
| [2024-11-08 10:39:36,030][00587] Avg episode reward: [(0, '4.263')] | |
| [2024-11-08 10:39:36,060][03563] Saving new best policy, reward=4.263! | |
| [2024-11-08 10:39:36,731][03578] Updated weights for policy 0, policy_version 30 (0.0018) | |
| [2024-11-08 10:39:41,020][00587] Fps is (10 sec: 4505.6, 60 sec: 2321.1, 300 sec: 1547.4). Total num frames: 139264. Throughput: 0: 812.5. Samples: 36832. Policy #0 lag: (min: 0.0, avg: 1.7, max: 5.0) | |
| [2024-11-08 10:39:41,028][00587] Avg episode reward: [(0, '4.348')] | |
| [2024-11-08 10:39:41,039][03563] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000034_139264.pth... | |
| [2024-11-08 10:39:41,198][03563] Saving new best policy, reward=4.348! | |
| [2024-11-08 10:39:46,020][00587] Fps is (10 sec: 4509.3, 60 sec: 2662.4, 300 sec: 1681.5). Total num frames: 159744. Throughput: 0: 857.4. Samples: 40608. Policy #0 lag: (min: 0.0, avg: 1.9, max: 5.0) | |
| [2024-11-08 10:39:46,022][00587] Avg episode reward: [(0, '4.620')] | |
| [2024-11-08 10:39:46,028][03563] Saving new best policy, reward=4.620! | |
| [2024-11-08 10:39:46,475][03578] Updated weights for policy 0, policy_version 40 (0.0014) | |
| [2024-11-08 10:39:51,023][00587] Fps is (10 sec: 4913.5, 60 sec: 3140.1, 300 sec: 1884.1). Total num frames: 188416. Throughput: 0: 997.4. Samples: 48152. Policy #0 lag: (min: 0.0, avg: 2.0, max: 4.0) | |
| [2024-11-08 10:39:51,028][00587] Avg episode reward: [(0, '4.699')] | |
| [2024-11-08 10:39:51,039][03563] Saving new best policy, reward=4.699! | |
| [2024-11-08 10:39:55,337][03578] Updated weights for policy 0, policy_version 50 (0.0013) | |
| [2024-11-08 10:39:56,021][00587] Fps is (10 sec: 4505.3, 60 sec: 3413.4, 300 sec: 1950.5). Total num frames: 204800. Throughput: 0: 1027.7. Samples: 53288. Policy #0 lag: (min: 0.0, avg: 1.9, max: 4.0) | |
| [2024-11-08 10:39:56,026][00587] Avg episode reward: [(0, '4.594')] | |
| [2024-11-08 10:40:01,020][00587] Fps is (10 sec: 3687.5, 60 sec: 3755.0, 300 sec: 2048.0). Total num frames: 225280. Throughput: 0: 1046.6. Samples: 56024. Policy #0 lag: (min: 0.0, avg: 1.9, max: 4.0) | |
| [2024-11-08 10:40:01,027][00587] Avg episode reward: [(0, '4.362')] | |
| [2024-11-08 10:40:06,020][00587] Fps is (10 sec: 3686.7, 60 sec: 3823.0, 300 sec: 2101.4). Total num frames: 241664. Throughput: 0: 1039.3. Samples: 61936. Policy #0 lag: (min: 0.0, avg: 1.9, max: 4.0) | |
| [2024-11-08 10:40:06,027][00587] Avg episode reward: [(0, '4.409')] | |
| [2024-11-08 10:40:06,698][03578] Updated weights for policy 0, policy_version 60 (0.0015) | |
| [2024-11-08 10:40:11,022][00587] Fps is (10 sec: 4914.4, 60 sec: 4232.5, 300 sec: 2286.9). Total num frames: 274432. Throughput: 0: 1053.8. Samples: 70248. Policy #0 lag: (min: 0.0, avg: 2.0, max: 4.0) | |
| [2024-11-08 10:40:11,029][00587] Avg episode reward: [(0, '4.354')] | |
| [2024-11-08 10:40:13,161][03578] Updated weights for policy 0, policy_version 70 (0.0013) | |
| [2024-11-08 10:40:16,022][00587] Fps is (10 sec: 4914.1, 60 sec: 4300.7, 300 sec: 2326.5). Total num frames: 290816. Throughput: 0: 1086.3. Samples: 74312. Policy #0 lag: (min: 0.0, avg: 1.9, max: 4.0) | |
| [2024-11-08 10:40:16,024][00587] Avg episode reward: [(0, '4.301')] | |
| [2024-11-08 10:40:21,020][00587] Fps is (10 sec: 3277.5, 60 sec: 4096.0, 300 sec: 2363.1). Total num frames: 307200. Throughput: 0: 1084.8. Samples: 79552. Policy #0 lag: (min: 0.0, avg: 2.1, max: 4.0) | |
| [2024-11-08 10:40:21,024][00587] Avg episode reward: [(0, '4.312')] | |
| [2024-11-08 10:40:25,853][03578] Updated weights for policy 0, policy_version 80 (0.0030) | |
| [2024-11-08 10:40:26,020][00587] Fps is (10 sec: 3687.2, 60 sec: 4164.3, 300 sec: 2427.3). Total num frames: 327680. Throughput: 0: 1070.4. Samples: 85000. Policy #0 lag: (min: 0.0, avg: 1.9, max: 4.0) | |
| [2024-11-08 10:40:26,022][00587] Avg episode reward: [(0, '4.598')] | |
| [2024-11-08 10:40:31,020][00587] Fps is (10 sec: 4505.6, 60 sec: 4300.8, 300 sec: 2516.1). Total num frames: 352256. Throughput: 0: 1050.5. Samples: 87880. Policy #0 lag: (min: 0.0, avg: 1.9, max: 4.0) | |
| [2024-11-08 10:40:31,024][00587] Avg episode reward: [(0, '4.749')] | |
| [2024-11-08 10:40:31,032][03563] Saving new best policy, reward=4.749! | |
| [2024-11-08 10:40:33,184][03578] Updated weights for policy 0, policy_version 90 (0.0014) | |
| [2024-11-08 10:40:36,020][00587] Fps is (10 sec: 5324.8, 60 sec: 4437.9, 300 sec: 2627.1). Total num frames: 380928. Throughput: 0: 1062.7. Samples: 95968. Policy #0 lag: (min: 0.0, avg: 1.8, max: 4.0) | |
| [2024-11-08 10:40:36,022][00587] Avg episode reward: [(0, '4.657')] | |
| [2024-11-08 10:40:41,021][00587] Fps is (10 sec: 5324.5, 60 sec: 4437.3, 300 sec: 2703.4). Total num frames: 405504. Throughput: 0: 1107.2. Samples: 103112. Policy #0 lag: (min: 0.0, avg: 1.8, max: 4.0) | |
| [2024-11-08 10:40:41,023][00587] Avg episode reward: [(0, '4.565')] | |
| [2024-11-08 10:40:43,267][03578] Updated weights for policy 0, policy_version 100 (0.0017) | |
| [2024-11-08 10:40:46,020][00587] Fps is (10 sec: 4096.0, 60 sec: 4369.1, 300 sec: 2721.9). Total num frames: 421888. Throughput: 0: 1106.3. Samples: 105808. Policy #0 lag: (min: 0.0, avg: 1.9, max: 4.0) | |
| [2024-11-08 10:40:46,029][00587] Avg episode reward: [(0, '4.582')] | |
| [2024-11-08 10:40:51,021][00587] Fps is (10 sec: 3276.6, 60 sec: 4164.4, 300 sec: 2739.2). Total num frames: 438272. Throughput: 0: 1088.5. Samples: 110920. Policy #0 lag: (min: 0.0, avg: 2.1, max: 4.0) | |
| [2024-11-08 10:40:51,025][00587] Avg episode reward: [(0, '4.444')] | |
| [2024-11-08 10:40:53,513][03578] Updated weights for policy 0, policy_version 110 (0.0014) | |
| [2024-11-08 10:40:56,020][00587] Fps is (10 sec: 3686.4, 60 sec: 4232.6, 300 sec: 2780.3). Total num frames: 458752. Throughput: 0: 1053.2. Samples: 117640. Policy #0 lag: (min: 0.0, avg: 2.1, max: 5.0) | |
| [2024-11-08 10:40:56,027][00587] Avg episode reward: [(0, '4.401')] | |
| [2024-11-08 10:41:01,020][00587] Fps is (10 sec: 4915.8, 60 sec: 4369.1, 300 sec: 2867.2). Total num frames: 487424. Throughput: 0: 1054.5. Samples: 121760. Policy #0 lag: (min: 0.0, avg: 2.4, max: 4.0) | |
| [2024-11-08 10:41:01,025][00587] Avg episode reward: [(0, '4.509')] | |
| [2024-11-08 10:41:01,331][03578] Updated weights for policy 0, policy_version 120 (0.0013) | |
| [2024-11-08 10:41:06,020][00587] Fps is (10 sec: 4915.2, 60 sec: 4437.3, 300 sec: 2902.3). Total num frames: 507904. Throughput: 0: 1106.0. Samples: 129320. Policy #0 lag: (min: 0.0, avg: 2.3, max: 4.0) | |
| [2024-11-08 10:41:06,029][00587] Avg episode reward: [(0, '4.488')] | |
| [2024-11-08 10:41:11,020][00587] Fps is (10 sec: 4096.0, 60 sec: 4232.7, 300 sec: 2935.5). Total num frames: 528384. Throughput: 0: 1103.8. Samples: 134672. Policy #0 lag: (min: 0.0, avg: 2.2, max: 5.0) | |
| [2024-11-08 10:41:11,022][00587] Avg episode reward: [(0, '4.396')] | |
| [2024-11-08 10:41:11,186][03578] Updated weights for policy 0, policy_version 130 (0.0013) | |
| [2024-11-08 10:41:16,020][00587] Fps is (10 sec: 4096.0, 60 sec: 4301.0, 300 sec: 2966.8). Total num frames: 548864. Throughput: 0: 1099.7. Samples: 137368. Policy #0 lag: (min: 0.0, avg: 2.2, max: 4.0) | |
| [2024-11-08 10:41:16,025][00587] Avg episode reward: [(0, '4.344')] | |
| [2024-11-08 10:41:21,020][00587] Fps is (10 sec: 4096.0, 60 sec: 4369.1, 300 sec: 2996.5). Total num frames: 569344. Throughput: 0: 1055.1. Samples: 143448. Policy #0 lag: (min: 0.0, avg: 2.2, max: 4.0) | |
| [2024-11-08 10:41:21,024][00587] Avg episode reward: [(0, '4.365')] | |
| [2024-11-08 10:41:21,178][03578] Updated weights for policy 0, policy_version 140 (0.0015) | |
| [2024-11-08 10:41:26,020][00587] Fps is (10 sec: 4915.2, 60 sec: 4505.6, 300 sec: 3066.8). Total num frames: 598016. Throughput: 0: 1076.8. Samples: 151568. Policy #0 lag: (min: 0.0, avg: 2.3, max: 5.0) | |
| [2024-11-08 10:41:26,022][00587] Avg episode reward: [(0, '4.586')] | |
| [2024-11-08 10:41:29,704][03578] Updated weights for policy 0, policy_version 150 (0.0014) | |
| [2024-11-08 10:41:31,023][00587] Fps is (10 sec: 5323.3, 60 sec: 4505.4, 300 sec: 3112.9). Total num frames: 622592. Throughput: 0: 1097.7. Samples: 155208. Policy #0 lag: (min: 0.0, avg: 1.5, max: 4.0) | |
| [2024-11-08 10:41:31,025][00587] Avg episode reward: [(0, '4.752')] | |
| [2024-11-08 10:41:31,036][03563] Saving new best policy, reward=4.752! | |
| [2024-11-08 10:41:36,020][00587] Fps is (10 sec: 4096.0, 60 sec: 4300.8, 300 sec: 3117.0). Total num frames: 638976. Throughput: 0: 1099.8. Samples: 160408. Policy #0 lag: (min: 0.0, avg: 2.2, max: 4.0) | |
| [2024-11-08 10:41:36,027][00587] Avg episode reward: [(0, '4.718')] | |
| [2024-11-08 10:41:40,352][03578] Updated weights for policy 0, policy_version 160 (0.0022) | |
| [2024-11-08 10:41:41,021][00587] Fps is (10 sec: 3277.3, 60 sec: 4164.2, 300 sec: 3120.7). Total num frames: 655360. Throughput: 0: 1069.7. Samples: 165776. Policy #0 lag: (min: 0.0, avg: 1.4, max: 4.0) | |
| [2024-11-08 10:41:41,026][00587] Avg episode reward: [(0, '4.487')] | |
| [2024-11-08 10:41:41,043][03563] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000160_655360.pth... | |
| [2024-11-08 10:41:46,024][00587] Fps is (10 sec: 4094.5, 60 sec: 4300.5, 300 sec: 3162.4). Total num frames: 679936. Throughput: 0: 1057.7. Samples: 169360. Policy #0 lag: (min: 0.0, avg: 1.2, max: 4.0) | |
| [2024-11-08 10:41:46,026][00587] Avg episode reward: [(0, '4.509')] | |
| [2024-11-08 10:41:48,909][03578] Updated weights for policy 0, policy_version 170 (0.0018) | |
| [2024-11-08 10:41:51,022][00587] Fps is (10 sec: 4914.8, 60 sec: 4437.3, 300 sec: 3202.3). Total num frames: 704512. Throughput: 0: 1063.4. Samples: 177176. Policy #0 lag: (min: 0.0, avg: 1.2, max: 4.0) | |
| [2024-11-08 10:41:51,025][00587] Avg episode reward: [(0, '4.516')] | |
| [2024-11-08 10:41:56,020][00587] Fps is (10 sec: 4507.3, 60 sec: 4437.3, 300 sec: 3222.2). Total num frames: 724992. Throughput: 0: 1081.8. Samples: 183352. Policy #0 lag: (min: 0.0, avg: 1.5, max: 4.0) | |
| [2024-11-08 10:41:56,025][00587] Avg episode reward: [(0, '4.452')] | |
| [2024-11-08 10:41:58,496][03578] Updated weights for policy 0, policy_version 180 (0.0022) | |
| [2024-11-08 10:42:01,022][00587] Fps is (10 sec: 3686.4, 60 sec: 4232.4, 300 sec: 3223.3). Total num frames: 741376. Throughput: 0: 1079.8. Samples: 185960. Policy #0 lag: (min: 0.0, avg: 1.9, max: 4.0) | |
| [2024-11-08 10:42:01,026][00587] Avg episode reward: [(0, '4.460')] | |
| [2024-11-08 10:42:06,022][00587] Fps is (10 sec: 3276.1, 60 sec: 4164.1, 300 sec: 3224.5). Total num frames: 757760. Throughput: 0: 1067.0. Samples: 191464. Policy #0 lag: (min: 0.0, avg: 1.5, max: 4.0) | |
| [2024-11-08 10:42:06,024][00587] Avg episode reward: [(0, '4.420')] | |
| [2024-11-08 10:42:09,521][03578] Updated weights for policy 0, policy_version 190 (0.0015) | |
| [2024-11-08 10:42:11,020][00587] Fps is (10 sec: 4916.2, 60 sec: 4369.1, 300 sec: 3293.9). Total num frames: 790528. Throughput: 0: 1049.4. Samples: 198792. Policy #0 lag: (min: 0.0, avg: 1.5, max: 4.0) | |
| [2024-11-08 10:42:11,027][00587] Avg episode reward: [(0, '4.476')] | |
| [2024-11-08 10:42:16,020][00587] Fps is (10 sec: 5325.9, 60 sec: 4369.1, 300 sec: 3310.2). Total num frames: 811008. Throughput: 0: 1058.9. Samples: 202856. Policy #0 lag: (min: 0.0, avg: 1.7, max: 4.0) | |
| [2024-11-08 10:42:16,024][00587] Avg episode reward: [(0, '4.499')] | |
| [2024-11-08 10:42:16,428][03578] Updated weights for policy 0, policy_version 200 (0.0014) | |
| [2024-11-08 10:42:21,027][00587] Fps is (10 sec: 4093.1, 60 sec: 4368.5, 300 sec: 3325.9). Total num frames: 831488. Throughput: 0: 1091.0. Samples: 209512. Policy #0 lag: (min: 0.0, avg: 1.6, max: 4.0) | |
| [2024-11-08 10:42:21,030][00587] Avg episode reward: [(0, '4.666')] | |
| [2024-11-08 10:42:26,020][00587] Fps is (10 sec: 4096.0, 60 sec: 4232.5, 300 sec: 3341.1). Total num frames: 851968. Throughput: 0: 1085.2. Samples: 214608. Policy #0 lag: (min: 0.0, avg: 1.6, max: 4.0) | |
| [2024-11-08 10:42:26,026][00587] Avg episode reward: [(0, '4.653')] | |
| [2024-11-08 10:42:28,605][03578] Updated weights for policy 0, policy_version 210 (0.0015) | |
| [2024-11-08 10:42:31,020][00587] Fps is (10 sec: 3689.1, 60 sec: 4096.2, 300 sec: 3339.8). Total num frames: 868352. Throughput: 0: 1068.0. Samples: 217416. Policy #0 lag: (min: 0.0, avg: 1.7, max: 4.0) | |
| [2024-11-08 10:42:31,022][00587] Avg episode reward: [(0, '4.580')] | |
| [2024-11-08 10:42:36,020][00587] Fps is (10 sec: 4096.0, 60 sec: 4232.5, 300 sec: 3369.5). Total num frames: 892928. Throughput: 0: 1046.1. Samples: 224248. Policy #0 lag: (min: 0.0, avg: 1.6, max: 4.0) | |
| [2024-11-08 10:42:36,027][00587] Avg episode reward: [(0, '4.660')] | |
| [2024-11-08 10:42:36,635][03578] Updated weights for policy 0, policy_version 220 (0.0017) | |
| [2024-11-08 10:42:41,020][00587] Fps is (10 sec: 5324.8, 60 sec: 4437.4, 300 sec: 3413.3). Total num frames: 921600. Throughput: 0: 1086.2. Samples: 232232. Policy #0 lag: (min: 0.0, avg: 1.6, max: 4.0) | |
| [2024-11-08 10:42:41,022][00587] Avg episode reward: [(0, '4.620')] | |
| [2024-11-08 10:42:46,026][00587] Fps is (10 sec: 4502.9, 60 sec: 4300.6, 300 sec: 3410.8). Total num frames: 937984. Throughput: 0: 1093.8. Samples: 235184. Policy #0 lag: (min: 0.0, avg: 2.3, max: 5.0) | |
| [2024-11-08 10:42:46,028][00587] Avg episode reward: [(0, '4.730')] | |
| [2024-11-08 10:42:46,595][03578] Updated weights for policy 0, policy_version 230 (0.0017) | |
| [2024-11-08 10:42:51,020][00587] Fps is (10 sec: 3276.8, 60 sec: 4164.4, 300 sec: 3408.5). Total num frames: 954368. Throughput: 0: 1088.2. Samples: 240432. Policy #0 lag: (min: 0.0, avg: 1.6, max: 4.0) | |
| [2024-11-08 10:42:51,022][00587] Avg episode reward: [(0, '4.832')] | |
| [2024-11-08 10:42:51,034][03563] Saving new best policy, reward=4.832! | |
| [2024-11-08 10:42:56,020][00587] Fps is (10 sec: 3278.7, 60 sec: 4096.0, 300 sec: 3406.1). Total num frames: 970752. Throughput: 0: 1041.2. Samples: 245648. Policy #0 lag: (min: 0.0, avg: 1.6, max: 4.0) | |
| [2024-11-08 10:42:56,025][00587] Avg episode reward: [(0, '4.749')] | |
| [2024-11-08 10:42:57,214][03578] Updated weights for policy 0, policy_version 240 (0.0015) | |
| [2024-11-08 10:43:01,020][00587] Fps is (10 sec: 4505.6, 60 sec: 4301.0, 300 sec: 3446.3). Total num frames: 999424. Throughput: 0: 1034.8. Samples: 249424. Policy #0 lag: (min: 0.0, avg: 1.8, max: 4.0) | |
| [2024-11-08 10:43:01,023][00587] Avg episode reward: [(0, '4.642')] | |
| [2024-11-08 10:43:05,461][03578] Updated weights for policy 0, policy_version 250 (0.0018) | |
| [2024-11-08 10:43:06,020][00587] Fps is (10 sec: 5734.4, 60 sec: 4505.8, 300 sec: 3485.1). Total num frames: 1028096. Throughput: 0: 1067.7. Samples: 257552. Policy #0 lag: (min: 0.0, avg: 1.4, max: 4.0) | |
| [2024-11-08 10:43:06,022][00587] Avg episode reward: [(0, '4.835')] | |
| [2024-11-08 10:43:06,024][03563] Saving new best policy, reward=4.835! | |
| [2024-11-08 10:43:11,020][00587] Fps is (10 sec: 4915.2, 60 sec: 4300.8, 300 sec: 3554.5). Total num frames: 1048576. Throughput: 0: 1083.2. Samples: 263352. Policy #0 lag: (min: 0.0, avg: 2.3, max: 4.0) | |
| [2024-11-08 10:43:11,022][00587] Avg episode reward: [(0, '4.689')] | |
| [2024-11-08 10:43:15,686][03578] Updated weights for policy 0, policy_version 260 (0.0014) | |
| [2024-11-08 10:43:16,020][00587] Fps is (10 sec: 3686.3, 60 sec: 4232.5, 300 sec: 3610.0). Total num frames: 1064960. Throughput: 0: 1080.5. Samples: 266040. Policy #0 lag: (min: 0.0, avg: 2.4, max: 4.0) | |
| [2024-11-08 10:43:16,027][00587] Avg episode reward: [(0, '4.740')] | |
| [2024-11-08 10:43:21,020][00587] Fps is (10 sec: 3276.8, 60 sec: 4164.8, 300 sec: 3665.6). Total num frames: 1081344. Throughput: 0: 1049.2. Samples: 271464. Policy #0 lag: (min: 0.0, avg: 1.6, max: 4.0) | |
| [2024-11-08 10:43:21,022][00587] Avg episode reward: [(0, '4.909')] | |
| [2024-11-08 10:43:21,035][03563] Saving new best policy, reward=4.909! | |
| [2024-11-08 10:43:25,756][03578] Updated weights for policy 0, policy_version 270 (0.0015) | |
| [2024-11-08 10:43:26,020][00587] Fps is (10 sec: 4096.1, 60 sec: 4232.5, 300 sec: 3748.9). Total num frames: 1105920. Throughput: 0: 1030.6. Samples: 278608. Policy #0 lag: (min: 0.0, avg: 1.3, max: 4.0) | |
| [2024-11-08 10:43:26,026][00587] Avg episode reward: [(0, '4.761')] | |
| [2024-11-08 10:43:31,020][00587] Fps is (10 sec: 4915.1, 60 sec: 4369.1, 300 sec: 3832.2). Total num frames: 1130496. Throughput: 0: 1054.4. Samples: 282624. Policy #0 lag: (min: 0.0, avg: 1.3, max: 4.0) | |
| [2024-11-08 10:43:31,022][00587] Avg episode reward: [(0, '4.650')] | |
| [2024-11-08 10:43:34,036][03578] Updated weights for policy 0, policy_version 280 (0.0014) | |
| [2024-11-08 10:43:36,020][00587] Fps is (10 sec: 4096.0, 60 sec: 4232.5, 300 sec: 3887.7). Total num frames: 1146880. Throughput: 0: 1075.4. Samples: 288824. Policy #0 lag: (min: 0.0, avg: 1.5, max: 4.0) | |
| [2024-11-08 10:43:36,030][00587] Avg episode reward: [(0, '4.423')] | |
| [2024-11-08 10:43:41,020][00587] Fps is (10 sec: 3276.8, 60 sec: 4027.7, 300 sec: 3943.3). Total num frames: 1163264. Throughput: 0: 1076.8. Samples: 294104. Policy #0 lag: (min: 0.0, avg: 2.3, max: 5.0) | |
| [2024-11-08 10:43:41,023][00587] Avg episode reward: [(0, '4.527')] | |
| [2024-11-08 10:43:41,037][03563] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000284_1163264.pth... | |
| [2024-11-08 10:43:41,221][03563] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000034_139264.pth | |
| [2024-11-08 10:43:45,861][03578] Updated weights for policy 0, policy_version 290 (0.0017) | |
| [2024-11-08 10:43:46,021][00587] Fps is (10 sec: 4095.6, 60 sec: 4164.6, 300 sec: 4026.6). Total num frames: 1187840. Throughput: 0: 1051.7. Samples: 296752. Policy #0 lag: (min: 0.0, avg: 1.5, max: 4.0) | |
| [2024-11-08 10:43:46,029][00587] Avg episode reward: [(0, '4.741')] | |
| [2024-11-08 10:43:51,020][00587] Fps is (10 sec: 4915.2, 60 sec: 4300.8, 300 sec: 4109.9). Total num frames: 1212416. Throughput: 0: 1037.9. Samples: 304256. Policy #0 lag: (min: 0.0, avg: 1.5, max: 4.0) | |
| [2024-11-08 10:43:51,024][00587] Avg episode reward: [(0, '4.610')] | |
| [2024-11-08 10:43:53,091][03578] Updated weights for policy 0, policy_version 300 (0.0015) | |
| [2024-11-08 10:43:56,020][00587] Fps is (10 sec: 4915.5, 60 sec: 4437.3, 300 sec: 4193.3). Total num frames: 1236992. Throughput: 0: 1075.0. Samples: 311728. Policy #0 lag: (min: 0.0, avg: 1.4, max: 4.0) | |
| [2024-11-08 10:43:56,023][00587] Avg episode reward: [(0, '4.621')] | |
| [2024-11-08 10:44:01,020][00587] Fps is (10 sec: 4505.6, 60 sec: 4300.8, 300 sec: 4221.0). Total num frames: 1257472. Throughput: 0: 1075.6. Samples: 314440. Policy #0 lag: (min: 0.0, avg: 1.5, max: 4.0) | |
| [2024-11-08 10:44:01,026][00587] Avg episode reward: [(0, '4.629')] | |
| [2024-11-08 10:44:04,830][03578] Updated weights for policy 0, policy_version 310 (0.0016) | |
| [2024-11-08 10:44:06,020][00587] Fps is (10 sec: 4096.2, 60 sec: 4164.3, 300 sec: 4262.6). Total num frames: 1277952. Throughput: 0: 1073.8. Samples: 319784. Policy #0 lag: (min: 0.0, avg: 1.5, max: 4.0) | |
| [2024-11-08 10:44:06,026][00587] Avg episode reward: [(0, '4.684')] | |
| [2024-11-08 10:44:11,020][00587] Fps is (10 sec: 3686.4, 60 sec: 4096.0, 300 sec: 4276.5). Total num frames: 1294336. Throughput: 0: 1053.9. Samples: 326032. Policy #0 lag: (min: 0.0, avg: 1.4, max: 4.0) | |
| [2024-11-08 10:44:11,022][00587] Avg episode reward: [(0, '4.787')] | |
| [2024-11-08 10:44:13,364][03578] Updated weights for policy 0, policy_version 320 (0.0014) | |
| [2024-11-08 10:44:16,020][00587] Fps is (10 sec: 4505.6, 60 sec: 4300.8, 300 sec: 4276.5). Total num frames: 1323008. Throughput: 0: 1053.0. Samples: 330008. Policy #0 lag: (min: 0.0, avg: 1.5, max: 4.0) | |
| [2024-11-08 10:44:16,027][00587] Avg episode reward: [(0, '4.715')] | |
| [2024-11-08 10:44:21,020][00587] Fps is (10 sec: 4915.2, 60 sec: 4369.1, 300 sec: 4290.4). Total num frames: 1343488. Throughput: 0: 1090.8. Samples: 337912. Policy #0 lag: (min: 0.0, avg: 1.8, max: 4.0) | |
| [2024-11-08 10:44:21,024][00587] Avg episode reward: [(0, '4.804')] | |
| [2024-11-08 10:44:22,431][03578] Updated weights for policy 0, policy_version 330 (0.0014) | |
| [2024-11-08 10:44:26,020][00587] Fps is (10 sec: 3686.4, 60 sec: 4232.5, 300 sec: 4290.4). Total num frames: 1359872. Throughput: 0: 1090.1. Samples: 343160. Policy #0 lag: (min: 0.0, avg: 2.4, max: 4.0) | |
| [2024-11-08 10:44:26,025][00587] Avg episode reward: [(0, '4.724')] | |
| [2024-11-08 10:44:31,021][00587] Fps is (10 sec: 3276.3, 60 sec: 4095.9, 300 sec: 4276.6). Total num frames: 1376256. Throughput: 0: 1074.8. Samples: 345120. Policy #0 lag: (min: 0.0, avg: 2.2, max: 4.0) | |
| [2024-11-08 10:44:31,025][00587] Avg episode reward: [(0, '4.843')] | |
| [2024-11-08 10:44:34,447][03578] Updated weights for policy 0, policy_version 340 (0.0015) | |
| [2024-11-08 10:44:36,020][00587] Fps is (10 sec: 3686.4, 60 sec: 4164.3, 300 sec: 4262.6). Total num frames: 1396736. Throughput: 0: 1018.7. Samples: 350096. Policy #0 lag: (min: 0.0, avg: 1.7, max: 5.0) | |
| [2024-11-08 10:44:36,022][00587] Avg episode reward: [(0, '4.836')] | |
| [2024-11-08 10:44:41,020][00587] Fps is (10 sec: 4915.8, 60 sec: 4369.1, 300 sec: 4290.4). Total num frames: 1425408. Throughput: 0: 1032.9. Samples: 358208. Policy #0 lag: (min: 0.0, avg: 1.5, max: 4.0) | |
| [2024-11-08 10:44:41,022][00587] Avg episode reward: [(0, '4.902')] | |
| [2024-11-08 10:44:42,901][03578] Updated weights for policy 0, policy_version 350 (0.0013) | |
| [2024-11-08 10:44:46,020][00587] Fps is (10 sec: 4915.2, 60 sec: 4300.9, 300 sec: 4262.7). Total num frames: 1445888. Throughput: 0: 1062.6. Samples: 362256. Policy #0 lag: (min: 0.0, avg: 1.6, max: 4.0) | |
| [2024-11-08 10:44:46,023][00587] Avg episode reward: [(0, '5.003')] | |
| [2024-11-08 10:44:46,027][03563] Saving new best policy, reward=5.003! | |
| [2024-11-08 10:44:51,020][00587] Fps is (10 sec: 3686.4, 60 sec: 4164.3, 300 sec: 4262.6). Total num frames: 1462272. Throughput: 0: 1062.4. Samples: 367592. Policy #0 lag: (min: 0.0, avg: 2.5, max: 6.0) | |
| [2024-11-08 10:44:51,026][00587] Avg episode reward: [(0, '5.033')] | |
| [2024-11-08 10:44:51,035][03563] Saving new best policy, reward=5.033! | |
| [2024-11-08 10:44:52,458][03578] Updated weights for policy 0, policy_version 360 (0.0015) | |
| [2024-11-08 10:44:56,025][00587] Fps is (10 sec: 3275.0, 60 sec: 4027.4, 300 sec: 4248.7). Total num frames: 1478656. Throughput: 0: 1036.7. Samples: 372688. Policy #0 lag: (min: 0.0, avg: 1.5, max: 4.0) | |
| [2024-11-08 10:44:56,032][00587] Avg episode reward: [(0, '4.929')] | |
| [2024-11-08 10:45:01,021][00587] Fps is (10 sec: 4095.5, 60 sec: 4095.9, 300 sec: 4276.5). Total num frames: 1503232. Throughput: 0: 1011.9. Samples: 375544. Policy #0 lag: (min: 0.0, avg: 1.3, max: 4.0) | |
| [2024-11-08 10:45:01,028][00587] Avg episode reward: [(0, '5.105')] | |
| [2024-11-08 10:45:01,077][03563] Saving new best policy, reward=5.105! | |
| [2024-11-08 10:45:03,160][03578] Updated weights for policy 0, policy_version 370 (0.0015) | |
| [2024-11-08 10:45:06,020][00587] Fps is (10 sec: 5327.8, 60 sec: 4232.5, 300 sec: 4262.6). Total num frames: 1531904. Throughput: 0: 1013.0. Samples: 383496. Policy #0 lag: (min: 0.0, avg: 1.7, max: 4.0) | |
| [2024-11-08 10:45:06,022][00587] Avg episode reward: [(0, '4.982')] | |
| [2024-11-08 10:45:11,021][00587] Fps is (10 sec: 4915.1, 60 sec: 4300.7, 300 sec: 4276.5). Total num frames: 1552384. Throughput: 0: 1056.7. Samples: 390712. Policy #0 lag: (min: 0.0, avg: 2.3, max: 5.0) | |
| [2024-11-08 10:45:11,025][00587] Avg episode reward: [(0, '4.781')] | |
| [2024-11-08 10:45:11,504][03578] Updated weights for policy 0, policy_version 380 (0.0019) | |
| [2024-11-08 10:45:16,022][00587] Fps is (10 sec: 3685.7, 60 sec: 4095.9, 300 sec: 4276.5). Total num frames: 1568768. Throughput: 0: 1067.4. Samples: 393152. Policy #0 lag: (min: 0.0, avg: 2.0, max: 4.0) | |
| [2024-11-08 10:45:16,025][00587] Avg episode reward: [(0, '4.837')] | |
| [2024-11-08 10:45:21,020][00587] Fps is (10 sec: 3277.2, 60 sec: 4027.7, 300 sec: 4262.6). Total num frames: 1585152. Throughput: 0: 1069.5. Samples: 398224. Policy #0 lag: (min: 0.0, avg: 2.1, max: 5.0) | |
| [2024-11-08 10:45:21,025][00587] Avg episode reward: [(0, '4.968')] | |
| [2024-11-08 10:45:23,185][03578] Updated weights for policy 0, policy_version 390 (0.0014) | |
| [2024-11-08 10:45:26,020][00587] Fps is (10 sec: 4096.7, 60 sec: 4164.3, 300 sec: 4262.6). Total num frames: 1609728. Throughput: 0: 1024.5. Samples: 404312. Policy #0 lag: (min: 0.0, avg: 2.1, max: 4.0) | |
| [2024-11-08 10:45:26,022][00587] Avg episode reward: [(0, '5.146')] | |
| [2024-11-08 10:45:26,028][03563] Saving new best policy, reward=5.146! | |
| [2024-11-08 10:45:31,020][00587] Fps is (10 sec: 4505.7, 60 sec: 4232.6, 300 sec: 4234.8). Total num frames: 1630208. Throughput: 0: 1021.2. Samples: 408208. Policy #0 lag: (min: 0.0, avg: 1.9, max: 5.0) | |
| [2024-11-08 10:45:31,024][00587] Avg episode reward: [(0, '5.273')] | |
| [2024-11-08 10:45:31,069][03563] Saving new best policy, reward=5.273! | |
| [2024-11-08 10:45:31,572][03578] Updated weights for policy 0, policy_version 400 (0.0022) | |
| [2024-11-08 10:45:36,021][00587] Fps is (10 sec: 4505.1, 60 sec: 4300.7, 300 sec: 4234.8). Total num frames: 1654784. Throughput: 0: 1067.0. Samples: 415608. Policy #0 lag: (min: 0.0, avg: 1.8, max: 4.0) | |
| [2024-11-08 10:45:36,025][00587] Avg episode reward: [(0, '5.323')] | |
| [2024-11-08 10:45:36,106][03563] Saving new best policy, reward=5.323! | |
| [2024-11-08 10:45:41,020][00587] Fps is (10 sec: 4505.6, 60 sec: 4164.3, 300 sec: 4248.7). Total num frames: 1675264. Throughput: 0: 1068.9. Samples: 420784. Policy #0 lag: (min: 0.0, avg: 1.8, max: 4.0) | |
| [2024-11-08 10:45:41,025][00587] Avg episode reward: [(0, '5.182')] | |
| [2024-11-08 10:45:41,035][03563] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000409_1675264.pth... | |
| [2024-11-08 10:45:41,201][03563] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000160_655360.pth | |
| [2024-11-08 10:45:41,317][03578] Updated weights for policy 0, policy_version 410 (0.0013) | |
| [2024-11-08 10:45:46,023][00587] Fps is (10 sec: 3685.6, 60 sec: 4095.8, 300 sec: 4248.7). Total num frames: 1691648. Throughput: 0: 1063.1. Samples: 423384. Policy #0 lag: (min: 0.0, avg: 1.8, max: 4.0) | |
| [2024-11-08 10:45:46,029][00587] Avg episode reward: [(0, '5.483')] | |
| [2024-11-08 10:45:46,031][03563] Saving new best policy, reward=5.483! | |
| [2024-11-08 10:45:51,020][00587] Fps is (10 sec: 4096.0, 60 sec: 4232.5, 300 sec: 4262.6). Total num frames: 1716224. Throughput: 0: 1023.8. Samples: 429568. Policy #0 lag: (min: 0.0, avg: 1.3, max: 4.0) | |
| [2024-11-08 10:45:51,026][00587] Avg episode reward: [(0, '5.537')] | |
| [2024-11-08 10:45:51,045][03563] Saving new best policy, reward=5.537! | |
| [2024-11-08 10:45:51,958][03578] Updated weights for policy 0, policy_version 420 (0.0018) | |
| [2024-11-08 10:45:56,020][00587] Fps is (10 sec: 4916.8, 60 sec: 4369.5, 300 sec: 4248.7). Total num frames: 1740800. Throughput: 0: 1028.1. Samples: 436976. Policy #0 lag: (min: 0.0, avg: 1.5, max: 4.0) | |
| [2024-11-08 10:45:56,022][00587] Avg episode reward: [(0, '5.015')] | |
| [2024-11-08 10:46:00,786][03578] Updated weights for policy 0, policy_version 430 (0.0021) | |
| [2024-11-08 10:46:01,021][00587] Fps is (10 sec: 4505.1, 60 sec: 4300.8, 300 sec: 4248.7). Total num frames: 1761280. Throughput: 0: 1055.1. Samples: 440632. Policy #0 lag: (min: 0.0, avg: 2.1, max: 5.0) | |
| [2024-11-08 10:46:01,026][00587] Avg episode reward: [(0, '5.361')] | |
| [2024-11-08 10:46:06,020][00587] Fps is (10 sec: 3686.4, 60 sec: 4096.0, 300 sec: 4234.8). Total num frames: 1777664. Throughput: 0: 1055.1. Samples: 445704. Policy #0 lag: (min: 0.0, avg: 2.0, max: 4.0) | |
| [2024-11-08 10:46:06,029][00587] Avg episode reward: [(0, '5.435')] | |
| [2024-11-08 10:46:11,020][00587] Fps is (10 sec: 3686.8, 60 sec: 4096.1, 300 sec: 4234.8). Total num frames: 1798144. Throughput: 0: 1043.9. Samples: 451288. Policy #0 lag: (min: 0.0, avg: 1.9, max: 4.0) | |
| [2024-11-08 10:46:11,022][00587] Avg episode reward: [(0, '5.069')] | |
| [2024-11-08 10:46:12,058][03578] Updated weights for policy 0, policy_version 440 (0.0017) | |
| [2024-11-08 10:46:16,020][00587] Fps is (10 sec: 4505.6, 60 sec: 4232.7, 300 sec: 4248.7). Total num frames: 1822720. Throughput: 0: 1032.0. Samples: 454648. Policy #0 lag: (min: 0.0, avg: 1.9, max: 4.0) | |
| [2024-11-08 10:46:16,027][00587] Avg episode reward: [(0, '5.061')] | |
| [2024-11-08 10:46:19,737][03578] Updated weights for policy 0, policy_version 450 (0.0015) | |
| [2024-11-08 10:46:21,020][00587] Fps is (10 sec: 4915.2, 60 sec: 4369.1, 300 sec: 4234.8). Total num frames: 1847296. Throughput: 0: 1049.3. Samples: 462824. Policy #0 lag: (min: 0.0, avg: 1.7, max: 4.0) | |
| [2024-11-08 10:46:21,025][00587] Avg episode reward: [(0, '5.379')] | |
| [2024-11-08 10:46:26,020][00587] Fps is (10 sec: 4505.6, 60 sec: 4300.8, 300 sec: 4221.0). Total num frames: 1867776. Throughput: 0: 1084.1. Samples: 469568. Policy #0 lag: (min: 0.0, avg: 2.0, max: 4.0) | |
| [2024-11-08 10:46:26,028][00587] Avg episode reward: [(0, '5.451')] | |
| [2024-11-08 10:46:29,207][03578] Updated weights for policy 0, policy_version 460 (0.0014) | |
| [2024-11-08 10:46:31,020][00587] Fps is (10 sec: 3686.4, 60 sec: 4232.5, 300 sec: 4221.0). Total num frames: 1884160. Throughput: 0: 1082.2. Samples: 472080. Policy #0 lag: (min: 0.0, avg: 1.8, max: 4.0) | |
| [2024-11-08 10:46:31,025][00587] Avg episode reward: [(0, '5.224')] | |
| [2024-11-08 10:46:36,020][00587] Fps is (10 sec: 3276.8, 60 sec: 4096.1, 300 sec: 4221.0). Total num frames: 1900544. Throughput: 0: 1062.4. Samples: 477376. Policy #0 lag: (min: 0.0, avg: 1.8, max: 4.0) | |
| [2024-11-08 10:46:36,022][00587] Avg episode reward: [(0, '5.345')] | |
| [2024-11-08 10:46:40,182][03578] Updated weights for policy 0, policy_version 470 (0.0015) | |
| [2024-11-08 10:46:41,020][00587] Fps is (10 sec: 4505.6, 60 sec: 4232.5, 300 sec: 4234.9). Total num frames: 1929216. Throughput: 0: 1051.0. Samples: 484272. Policy #0 lag: (min: 0.0, avg: 1.8, max: 4.0) | |
| [2024-11-08 10:46:41,022][00587] Avg episode reward: [(0, '5.359')] | |
| [2024-11-08 10:46:46,020][00587] Fps is (10 sec: 5324.8, 60 sec: 4369.3, 300 sec: 4234.9). Total num frames: 1953792. Throughput: 0: 1059.9. Samples: 488328. Policy #0 lag: (min: 0.0, avg: 1.9, max: 4.0) | |
| [2024-11-08 10:46:46,022][00587] Avg episode reward: [(0, '5.410')] | |
| [2024-11-08 10:46:47,287][03578] Updated weights for policy 0, policy_version 480 (0.0016) | |
| [2024-11-08 10:46:51,020][00587] Fps is (10 sec: 4915.2, 60 sec: 4369.1, 300 sec: 4248.7). Total num frames: 1978368. Throughput: 0: 1108.6. Samples: 495592. Policy #0 lag: (min: 0.0, avg: 2.0, max: 4.0) | |
| [2024-11-08 10:46:51,024][00587] Avg episode reward: [(0, '5.420')] | |
| [2024-11-08 10:46:56,020][00587] Fps is (10 sec: 4095.8, 60 sec: 4232.5, 300 sec: 4248.8). Total num frames: 1994752. Throughput: 0: 1097.9. Samples: 500696. Policy #0 lag: (min: 0.0, avg: 2.1, max: 5.0) | |
| [2024-11-08 10:46:56,025][00587] Avg episode reward: [(0, '5.476')] | |
| [2024-11-08 10:47:00,005][03578] Updated weights for policy 0, policy_version 490 (0.0023) | |
| [2024-11-08 10:47:01,020][00587] Fps is (10 sec: 3276.8, 60 sec: 4164.3, 300 sec: 4248.8). Total num frames: 2011136. Throughput: 0: 1078.4. Samples: 503176. Policy #0 lag: (min: 0.0, avg: 2.0, max: 5.0) | |
| [2024-11-08 10:47:01,023][00587] Avg episode reward: [(0, '5.398')] | |
| [2024-11-08 10:47:06,020][00587] Fps is (10 sec: 3686.5, 60 sec: 4232.5, 300 sec: 4207.1). Total num frames: 2031616. Throughput: 0: 1034.3. Samples: 509368. Policy #0 lag: (min: 0.0, avg: 2.1, max: 4.0) | |
| [2024-11-08 10:47:06,022][00587] Avg episode reward: [(0, '5.823')] | |
| [2024-11-08 10:47:06,026][03563] Saving new best policy, reward=5.823! | |
| [2024-11-08 10:47:07,977][03578] Updated weights for policy 0, policy_version 500 (0.0014) | |
| [2024-11-08 10:47:11,020][00587] Fps is (10 sec: 5324.8, 60 sec: 4437.3, 300 sec: 4248.7). Total num frames: 2064384. Throughput: 0: 1057.8. Samples: 517168. Policy #0 lag: (min: 0.0, avg: 2.1, max: 5.0) | |
| [2024-11-08 10:47:11,022][00587] Avg episode reward: [(0, '5.622')] | |
| [2024-11-08 10:47:16,020][00587] Fps is (10 sec: 4915.2, 60 sec: 4300.8, 300 sec: 4235.0). Total num frames: 2080768. Throughput: 0: 1078.9. Samples: 520632. Policy #0 lag: (min: 0.0, avg: 2.1, max: 5.0) | |
| [2024-11-08 10:47:16,023][00587] Avg episode reward: [(0, '6.043')] | |
| [2024-11-08 10:47:16,027][03563] Saving new best policy, reward=6.043! | |
| [2024-11-08 10:47:18,544][03578] Updated weights for policy 0, policy_version 510 (0.0029) | |
| [2024-11-08 10:47:21,023][00587] Fps is (10 sec: 3275.7, 60 sec: 4164.0, 300 sec: 4220.9). Total num frames: 2097152. Throughput: 0: 1072.3. Samples: 525632. Policy #0 lag: (min: 0.0, avg: 2.2, max: 4.0) | |
| [2024-11-08 10:47:21,028][00587] Avg episode reward: [(0, '5.936')] | |
| [2024-11-08 10:47:26,020][00587] Fps is (10 sec: 3276.8, 60 sec: 4096.0, 300 sec: 4221.0). Total num frames: 2113536. Throughput: 0: 1039.3. Samples: 531040. Policy #0 lag: (min: 0.0, avg: 1.6, max: 4.0) | |
| [2024-11-08 10:47:26,022][00587] Avg episode reward: [(0, '6.255')] | |
| [2024-11-08 10:47:26,027][03563] Saving new best policy, reward=6.255! | |
| [2024-11-08 10:47:29,200][03578] Updated weights for policy 0, policy_version 520 (0.0016) | |
| [2024-11-08 10:47:31,020][00587] Fps is (10 sec: 3687.6, 60 sec: 4164.3, 300 sec: 4207.1). Total num frames: 2134016. Throughput: 0: 1010.8. Samples: 533816. Policy #0 lag: (min: 0.0, avg: 2.1, max: 5.0) | |
| [2024-11-08 10:47:31,022][00587] Avg episode reward: [(0, '6.227')] | |
| [2024-11-08 10:47:36,020][00587] Fps is (10 sec: 4915.2, 60 sec: 4369.1, 300 sec: 4207.1). Total num frames: 2162688. Throughput: 0: 1026.1. Samples: 541768. Policy #0 lag: (min: 0.0, avg: 1.5, max: 4.0) | |
| [2024-11-08 10:47:36,022][00587] Avg episode reward: [(0, '6.242')] | |
| [2024-11-08 10:47:37,112][03578] Updated weights for policy 0, policy_version 530 (0.0014) | |
| [2024-11-08 10:47:41,020][00587] Fps is (10 sec: 5324.8, 60 sec: 4300.8, 300 sec: 4234.9). Total num frames: 2187264. Throughput: 0: 1061.2. Samples: 548448. Policy #0 lag: (min: 0.0, avg: 2.3, max: 5.0) | |
| [2024-11-08 10:47:41,025][00587] Avg episode reward: [(0, '6.174')] | |
| [2024-11-08 10:47:41,038][03563] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000534_2187264.pth... | |
| [2024-11-08 10:47:41,227][03563] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000284_1163264.pth | |
| [2024-11-08 10:47:46,022][00587] Fps is (10 sec: 4095.2, 60 sec: 4164.1, 300 sec: 4234.8). Total num frames: 2203648. Throughput: 0: 1061.1. Samples: 550928. Policy #0 lag: (min: 0.0, avg: 2.3, max: 4.0) | |
| [2024-11-08 10:47:46,031][00587] Avg episode reward: [(0, '6.147')] | |
| [2024-11-08 10:47:48,695][03578] Updated weights for policy 0, policy_version 540 (0.0018) | |
| [2024-11-08 10:47:51,024][00587] Fps is (10 sec: 3275.4, 60 sec: 4027.5, 300 sec: 4234.8). Total num frames: 2220032. Throughput: 0: 1042.4. Samples: 556280. Policy #0 lag: (min: 0.0, avg: 1.6, max: 4.0) | |
| [2024-11-08 10:47:51,026][00587] Avg episode reward: [(0, '6.506')] | |
| [2024-11-08 10:47:51,036][03563] Saving new best policy, reward=6.506! | |
| [2024-11-08 10:47:56,020][00587] Fps is (10 sec: 4096.8, 60 sec: 4164.3, 300 sec: 4221.0). Total num frames: 2244608. Throughput: 0: 1024.2. Samples: 563256. Policy #0 lag: (min: 0.0, avg: 1.6, max: 4.0) | |
| [2024-11-08 10:47:56,022][00587] Avg episode reward: [(0, '6.179')] | |
| [2024-11-08 10:47:56,690][03578] Updated weights for policy 0, policy_version 550 (0.0018) | |
| [2024-11-08 10:48:01,020][00587] Fps is (10 sec: 4917.2, 60 sec: 4300.8, 300 sec: 4207.1). Total num frames: 2269184. Throughput: 0: 1030.6. Samples: 567008. Policy #0 lag: (min: 0.0, avg: 1.6, max: 4.0) | |
| [2024-11-08 10:48:01,022][00587] Avg episode reward: [(0, '6.017')] | |
| [2024-11-08 10:48:06,023][00587] Fps is (10 sec: 4094.9, 60 sec: 4232.3, 300 sec: 4193.2). Total num frames: 2285568. Throughput: 0: 1072.0. Samples: 573872. Policy #0 lag: (min: 0.0, avg: 1.6, max: 4.0) | |
| [2024-11-08 10:48:06,027][00587] Avg episode reward: [(0, '6.382')] | |
| [2024-11-08 10:48:06,738][03578] Updated weights for policy 0, policy_version 560 (0.0016) | |
| [2024-11-08 10:48:11,030][00587] Fps is (10 sec: 3682.7, 60 sec: 4027.1, 300 sec: 4206.9). Total num frames: 2306048. Throughput: 0: 1070.3. Samples: 579216. Policy #0 lag: (min: 0.0, avg: 1.5, max: 4.0) | |
| [2024-11-08 10:48:11,037][00587] Avg episode reward: [(0, '6.355')] | |
| [2024-11-08 10:48:16,020][00587] Fps is (10 sec: 4097.1, 60 sec: 4096.0, 300 sec: 4221.0). Total num frames: 2326528. Throughput: 0: 1068.4. Samples: 581896. Policy #0 lag: (min: 0.0, avg: 1.5, max: 4.0) | |
| [2024-11-08 10:48:16,026][00587] Avg episode reward: [(0, '6.333')] | |
| [2024-11-08 10:48:16,962][03578] Updated weights for policy 0, policy_version 570 (0.0026) | |
| [2024-11-08 10:48:21,020][00587] Fps is (10 sec: 4510.1, 60 sec: 4232.8, 300 sec: 4221.0). Total num frames: 2351104. Throughput: 0: 1045.9. Samples: 588832. Policy #0 lag: (min: 0.0, avg: 1.4, max: 4.0) | |
| [2024-11-08 10:48:21,025][00587] Avg episode reward: [(0, '6.627')] | |
| [2024-11-08 10:48:21,034][03563] Saving new best policy, reward=6.627! | |
| [2024-11-08 10:48:25,318][03578] Updated weights for policy 0, policy_version 580 (0.0014) | |
| [2024-11-08 10:48:26,020][00587] Fps is (10 sec: 5324.8, 60 sec: 4437.3, 300 sec: 4234.9). Total num frames: 2379776. Throughput: 0: 1072.7. Samples: 596720. Policy #0 lag: (min: 0.0, avg: 1.5, max: 4.0) | |
| [2024-11-08 10:48:26,026][00587] Avg episode reward: [(0, '6.873')] | |
| [2024-11-08 10:48:26,030][03563] Saving new best policy, reward=6.873! | |
| [2024-11-08 10:48:31,020][00587] Fps is (10 sec: 4915.2, 60 sec: 4437.3, 300 sec: 4248.7). Total num frames: 2400256. Throughput: 0: 1085.9. Samples: 599792. Policy #0 lag: (min: 0.0, avg: 1.5, max: 4.0) | |
| [2024-11-08 10:48:31,024][00587] Avg episode reward: [(0, '6.868')] | |
| [2024-11-08 10:48:35,374][03578] Updated weights for policy 0, policy_version 590 (0.0026) | |
| [2024-11-08 10:48:36,020][00587] Fps is (10 sec: 3686.4, 60 sec: 4232.5, 300 sec: 4248.7). Total num frames: 2416640. Throughput: 0: 1084.0. Samples: 605056. Policy #0 lag: (min: 0.0, avg: 1.4, max: 4.0) | |
| [2024-11-08 10:48:36,027][00587] Avg episode reward: [(0, '6.427')] | |
| [2024-11-08 10:48:41,020][00587] Fps is (10 sec: 3276.8, 60 sec: 4096.0, 300 sec: 4221.0). Total num frames: 2433024. Throughput: 0: 1053.0. Samples: 610640. Policy #0 lag: (min: 0.0, avg: 1.4, max: 4.0) | |
| [2024-11-08 10:48:41,024][00587] Avg episode reward: [(0, '6.477')] | |
| [2024-11-08 10:48:45,517][03578] Updated weights for policy 0, policy_version 600 (0.0022) | |
| [2024-11-08 10:48:46,020][00587] Fps is (10 sec: 4505.6, 60 sec: 4300.9, 300 sec: 4234.8). Total num frames: 2461696. Throughput: 0: 1050.7. Samples: 614288. Policy #0 lag: (min: 0.0, avg: 1.3, max: 4.0) | |
| [2024-11-08 10:48:46,022][00587] Avg episode reward: [(0, '7.096')] | |
| [2024-11-08 10:48:46,027][03563] Saving new best policy, reward=7.096! | |
| [2024-11-08 10:48:51,023][00587] Fps is (10 sec: 5323.4, 60 sec: 4437.4, 300 sec: 4234.8). Total num frames: 2486272. Throughput: 0: 1078.0. Samples: 622384. Policy #0 lag: (min: 0.0, avg: 1.7, max: 4.0) | |
| [2024-11-08 10:48:51,028][00587] Avg episode reward: [(0, '7.801')] | |
| [2024-11-08 10:48:51,037][03563] Saving new best policy, reward=7.801! | |
| [2024-11-08 10:48:53,081][03578] Updated weights for policy 0, policy_version 610 (0.0014) | |
| [2024-11-08 10:48:56,023][00587] Fps is (10 sec: 4094.9, 60 sec: 4300.6, 300 sec: 4220.9). Total num frames: 2502656. Throughput: 0: 1094.6. Samples: 628464. Policy #0 lag: (min: 0.0, avg: 1.9, max: 4.0) | |
| [2024-11-08 10:48:56,029][00587] Avg episode reward: [(0, '7.599')] | |
| [2024-11-08 10:49:01,020][00587] Fps is (10 sec: 3277.6, 60 sec: 4164.2, 300 sec: 4207.1). Total num frames: 2519040. Throughput: 0: 1093.5. Samples: 631104. Policy #0 lag: (min: 0.0, avg: 1.6, max: 4.0) | |
| [2024-11-08 10:49:01,022][00587] Avg episode reward: [(0, '7.837')] | |
| [2024-11-08 10:49:01,038][03563] Saving new best policy, reward=7.837! | |
| [2024-11-08 10:49:05,745][03578] Updated weights for policy 0, policy_version 620 (0.0014) | |
| [2024-11-08 10:49:06,025][00587] Fps is (10 sec: 3685.5, 60 sec: 4232.4, 300 sec: 4220.9). Total num frames: 2539520. Throughput: 0: 1057.5. Samples: 636424. Policy #0 lag: (min: 0.0, avg: 1.8, max: 4.0) | |
| [2024-11-08 10:49:06,029][00587] Avg episode reward: [(0, '7.361')] | |
| [2024-11-08 10:49:11,020][00587] Fps is (10 sec: 4505.7, 60 sec: 4301.5, 300 sec: 4207.1). Total num frames: 2564096. Throughput: 0: 1045.7. Samples: 643776. Policy #0 lag: (min: 0.0, avg: 1.7, max: 4.0) | |
| [2024-11-08 10:49:11,022][00587] Avg episode reward: [(0, '7.106')] | |
| [2024-11-08 10:49:12,914][03578] Updated weights for policy 0, policy_version 630 (0.0017) | |
| [2024-11-08 10:49:16,020][00587] Fps is (10 sec: 5327.6, 60 sec: 4437.3, 300 sec: 4234.8). Total num frames: 2592768. Throughput: 0: 1067.6. Samples: 647832. Policy #0 lag: (min: 0.0, avg: 1.8, max: 4.0) | |
| [2024-11-08 10:49:16,027][00587] Avg episode reward: [(0, '7.916')] | |
| [2024-11-08 10:49:16,029][03563] Saving new best policy, reward=7.916! | |
| [2024-11-08 10:49:21,022][00587] Fps is (10 sec: 4914.1, 60 sec: 4368.9, 300 sec: 4248.7). Total num frames: 2613248. Throughput: 0: 1093.5. Samples: 654264. Policy #0 lag: (min: 0.0, avg: 2.5, max: 4.0) | |
| [2024-11-08 10:49:21,026][00587] Avg episode reward: [(0, '8.404')] | |
| [2024-11-08 10:49:21,037][03563] Saving new best policy, reward=8.404! | |
| [2024-11-08 10:49:24,026][03578] Updated weights for policy 0, policy_version 640 (0.0014) | |
| [2024-11-08 10:49:26,021][00587] Fps is (10 sec: 3685.8, 60 sec: 4164.2, 300 sec: 4248.7). Total num frames: 2629632. Throughput: 0: 1086.4. Samples: 659528. Policy #0 lag: (min: 0.0, avg: 1.6, max: 4.0) | |
| [2024-11-08 10:49:26,024][00587] Avg episode reward: [(0, '7.981')] | |
| [2024-11-08 10:49:31,023][00587] Fps is (10 sec: 3277.5, 60 sec: 4096.0, 300 sec: 4234.8). Total num frames: 2646016. Throughput: 0: 1067.6. Samples: 662328. Policy #0 lag: (min: 0.0, avg: 2.2, max: 5.0) | |
| [2024-11-08 10:49:31,029][00587] Avg episode reward: [(0, '8.388')] | |
| [2024-11-08 10:49:33,454][03578] Updated weights for policy 0, policy_version 650 (0.0015) | |
| [2024-11-08 10:49:36,021][00587] Fps is (10 sec: 4096.1, 60 sec: 4232.4, 300 sec: 4220.9). Total num frames: 2670592. Throughput: 0: 1038.3. Samples: 669104. Policy #0 lag: (min: 0.0, avg: 2.0, max: 4.0) | |
| [2024-11-08 10:49:36,024][00587] Avg episode reward: [(0, '8.092')] | |
| [2024-11-08 10:49:41,016][03578] Updated weights for policy 0, policy_version 660 (0.0014) | |
| [2024-11-08 10:49:41,020][00587] Fps is (10 sec: 5734.4, 60 sec: 4505.6, 300 sec: 4262.6). Total num frames: 2703360. Throughput: 0: 1084.9. Samples: 677280. Policy #0 lag: (min: 0.0, avg: 2.4, max: 5.0) | |
| [2024-11-08 10:49:41,027][00587] Avg episode reward: [(0, '8.526')] | |
| [2024-11-08 10:49:41,040][03563] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000660_2703360.pth... | |
| [2024-11-08 10:49:41,168][03563] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000409_1675264.pth | |
| [2024-11-08 10:49:41,196][03563] Saving new best policy, reward=8.526! | |
| [2024-11-08 10:49:46,023][00587] Fps is (10 sec: 4914.3, 60 sec: 4300.6, 300 sec: 4262.6). Total num frames: 2719744. Throughput: 0: 1089.9. Samples: 680152. Policy #0 lag: (min: 0.0, avg: 2.0, max: 4.0) | |
| [2024-11-08 10:49:46,031][00587] Avg episode reward: [(0, '9.378')] | |
| [2024-11-08 10:49:46,044][03563] Saving new best policy, reward=9.378! | |
| [2024-11-08 10:49:51,022][00587] Fps is (10 sec: 3276.0, 60 sec: 4164.3, 300 sec: 4262.7). Total num frames: 2736128. Throughput: 0: 1085.4. Samples: 685264. Policy #0 lag: (min: 0.0, avg: 2.2, max: 5.0) | |
| [2024-11-08 10:49:51,027][00587] Avg episode reward: [(0, '9.780')] | |
| [2024-11-08 10:49:51,044][03563] Saving new best policy, reward=9.780! | |
| [2024-11-08 10:49:53,000][03578] Updated weights for policy 0, policy_version 670 (0.0022) | |
| [2024-11-08 10:49:56,020][00587] Fps is (10 sec: 3277.7, 60 sec: 4164.4, 300 sec: 4234.9). Total num frames: 2752512. Throughput: 0: 1041.9. Samples: 690664. Policy #0 lag: (min: 0.0, avg: 1.7, max: 4.0) | |
| [2024-11-08 10:49:56,024][00587] Avg episode reward: [(0, '10.105')] | |
| [2024-11-08 10:49:56,030][03563] Saving new best policy, reward=10.105! | |
| [2024-11-08 10:50:01,020][00587] Fps is (10 sec: 4506.6, 60 sec: 4369.1, 300 sec: 4234.8). Total num frames: 2781184. Throughput: 0: 1037.5. Samples: 694520. Policy #0 lag: (min: 0.0, avg: 1.4, max: 4.0) | |
| [2024-11-08 10:50:01,025][00587] Avg episode reward: [(0, '11.248')] | |
| [2024-11-08 10:50:01,039][03563] Saving new best policy, reward=11.248! | |
| [2024-11-08 10:50:01,835][03578] Updated weights for policy 0, policy_version 680 (0.0015) | |
| [2024-11-08 10:50:06,022][00587] Fps is (10 sec: 5323.9, 60 sec: 4437.6, 300 sec: 4248.7). Total num frames: 2805760. Throughput: 0: 1067.6. Samples: 702304. Policy #0 lag: (min: 0.0, avg: 1.3, max: 4.0) | |
| [2024-11-08 10:50:06,026][00587] Avg episode reward: [(0, '11.578')] | |
| [2024-11-08 10:50:06,030][03563] Saving new best policy, reward=11.578! | |
| [2024-11-08 10:50:10,859][03578] Updated weights for policy 0, policy_version 690 (0.0016) | |
| [2024-11-08 10:50:11,020][00587] Fps is (10 sec: 4505.5, 60 sec: 4369.0, 300 sec: 4262.6). Total num frames: 2826240. Throughput: 0: 1087.3. Samples: 708456. Policy #0 lag: (min: 0.0, avg: 2.2, max: 4.0) | |
| [2024-11-08 10:50:11,023][00587] Avg episode reward: [(0, '11.713')] | |
| [2024-11-08 10:50:11,034][03563] Saving new best policy, reward=11.713! | |
| [2024-11-08 10:50:16,020][00587] Fps is (10 sec: 4096.9, 60 sec: 4232.5, 300 sec: 4276.5). Total num frames: 2846720. Throughput: 0: 1082.8. Samples: 711056. Policy #0 lag: (min: 0.0, avg: 1.2, max: 4.0) | |
| [2024-11-08 10:50:16,031][00587] Avg episode reward: [(0, '11.195')] | |
| [2024-11-08 10:50:21,020][00587] Fps is (10 sec: 3686.5, 60 sec: 4164.4, 300 sec: 4248.7). Total num frames: 2863104. Throughput: 0: 1057.6. Samples: 716696. Policy #0 lag: (min: 0.0, avg: 1.2, max: 4.0) | |
| [2024-11-08 10:50:21,026][00587] Avg episode reward: [(0, '11.077')] | |
| [2024-11-08 10:50:21,338][03578] Updated weights for policy 0, policy_version 700 (0.0015) | |
| [2024-11-08 10:50:26,020][00587] Fps is (10 sec: 4096.0, 60 sec: 4300.9, 300 sec: 4262.6). Total num frames: 2887680. Throughput: 0: 1053.0. Samples: 724664. Policy #0 lag: (min: 0.0, avg: 1.5, max: 4.0) | |
| [2024-11-08 10:50:26,027][00587] Avg episode reward: [(0, '11.588')] | |
| [2024-11-08 10:50:28,911][03578] Updated weights for policy 0, policy_version 710 (0.0015) | |
| [2024-11-08 10:50:31,020][00587] Fps is (10 sec: 5324.7, 60 sec: 4505.6, 300 sec: 4276.5). Total num frames: 2916352. Throughput: 0: 1080.2. Samples: 728760. Policy #0 lag: (min: 0.0, avg: 1.9, max: 4.0) | |
| [2024-11-08 10:50:31,023][00587] Avg episode reward: [(0, '12.409')] | |
| [2024-11-08 10:50:31,034][03563] Saving new best policy, reward=12.409! | |
| [2024-11-08 10:50:36,020][00587] Fps is (10 sec: 4505.6, 60 sec: 4369.2, 300 sec: 4262.6). Total num frames: 2932736. Throughput: 0: 1097.7. Samples: 734656. Policy #0 lag: (min: 0.0, avg: 2.3, max: 5.0) | |
| [2024-11-08 10:50:36,024][00587] Avg episode reward: [(0, '11.644')] | |
| [2024-11-08 10:50:39,447][03578] Updated weights for policy 0, policy_version 720 (0.0017) | |
| [2024-11-08 10:50:41,024][00587] Fps is (10 sec: 3275.5, 60 sec: 4095.7, 300 sec: 4262.6). Total num frames: 2949120. Throughput: 0: 1095.9. Samples: 739984. Policy #0 lag: (min: 0.0, avg: 1.4, max: 4.0) | |
| [2024-11-08 10:50:41,027][00587] Avg episode reward: [(0, '12.018')] | |
| [2024-11-08 10:50:46,020][00587] Fps is (10 sec: 3686.4, 60 sec: 4164.5, 300 sec: 4248.7). Total num frames: 2969600. Throughput: 0: 1073.2. Samples: 742816. Policy #0 lag: (min: 0.0, avg: 2.1, max: 4.0) | |
| [2024-11-08 10:50:46,025][00587] Avg episode reward: [(0, '12.195')] | |
| [2024-11-08 10:50:49,310][03578] Updated weights for policy 0, policy_version 730 (0.0015) | |
| [2024-11-08 10:50:51,022][00587] Fps is (10 sec: 4916.2, 60 sec: 4369.1, 300 sec: 4262.6). Total num frames: 2998272. Throughput: 0: 1060.3. Samples: 750016. Policy #0 lag: (min: 0.0, avg: 1.1, max: 4.0) | |
| [2024-11-08 10:50:51,025][00587] Avg episode reward: [(0, '12.687')] | |
| [2024-11-08 10:50:51,034][03563] Saving new best policy, reward=12.687! | |
| [2024-11-08 10:50:56,026][00587] Fps is (10 sec: 5321.5, 60 sec: 4505.2, 300 sec: 4276.4). Total num frames: 3022848. Throughput: 0: 1105.5. Samples: 758208. Policy #0 lag: (min: 0.0, avg: 1.6, max: 4.0) | |
| [2024-11-08 10:50:56,029][00587] Avg episode reward: [(0, '13.700')] | |
| [2024-11-08 10:50:56,032][03563] Saving new best policy, reward=13.700! | |
| [2024-11-08 10:50:57,559][03578] Updated weights for policy 0, policy_version 740 (0.0013) | |
| [2024-11-08 10:51:01,020][00587] Fps is (10 sec: 4096.9, 60 sec: 4300.8, 300 sec: 4276.5). Total num frames: 3039232. Throughput: 0: 1106.3. Samples: 760840. Policy #0 lag: (min: 0.0, avg: 2.1, max: 5.0) | |
| [2024-11-08 10:51:01,028][00587] Avg episode reward: [(0, '13.649')] | |
| [2024-11-08 10:51:06,020][00587] Fps is (10 sec: 3278.9, 60 sec: 4164.4, 300 sec: 4262.6). Total num frames: 3055616. Throughput: 0: 1095.8. Samples: 766008. Policy #0 lag: (min: 0.0, avg: 2.2, max: 4.0) | |
| [2024-11-08 10:51:06,027][00587] Avg episode reward: [(0, '13.681')] | |
| [2024-11-08 10:51:09,323][03578] Updated weights for policy 0, policy_version 750 (0.0019) | |
| [2024-11-08 10:51:11,020][00587] Fps is (10 sec: 3686.4, 60 sec: 4164.3, 300 sec: 4248.7). Total num frames: 3076096. Throughput: 0: 1043.0. Samples: 771600. Policy #0 lag: (min: 0.0, avg: 1.9, max: 5.0) | |
| [2024-11-08 10:51:11,025][00587] Avg episode reward: [(0, '13.804')] | |
| [2024-11-08 10:51:11,033][03563] Saving new best policy, reward=13.804! | |
| [2024-11-08 10:51:16,020][00587] Fps is (10 sec: 4915.0, 60 sec: 4300.8, 300 sec: 4262.6). Total num frames: 3104768. Throughput: 0: 1039.6. Samples: 775544. Policy #0 lag: (min: 0.0, avg: 1.9, max: 5.0) | |
| [2024-11-08 10:51:16,023][00587] Avg episode reward: [(0, '13.299')] | |
| [2024-11-08 10:51:17,388][03578] Updated weights for policy 0, policy_version 760 (0.0013) | |
| [2024-11-08 10:51:21,024][00587] Fps is (10 sec: 5322.6, 60 sec: 4437.0, 300 sec: 4276.4). Total num frames: 3129344. Throughput: 0: 1085.1. Samples: 783488. Policy #0 lag: (min: 0.0, avg: 1.7, max: 4.0) | |
| [2024-11-08 10:51:21,031][00587] Avg episode reward: [(0, '13.171')] | |
| [2024-11-08 10:51:26,020][00587] Fps is (10 sec: 4505.6, 60 sec: 4369.1, 300 sec: 4290.4). Total num frames: 3149824. Throughput: 0: 1090.2. Samples: 789040. Policy #0 lag: (min: 0.0, avg: 1.7, max: 4.0) | |
| [2024-11-08 10:51:26,024][00587] Avg episode reward: [(0, '13.979')] | |
| [2024-11-08 10:51:26,027][03563] Saving new best policy, reward=13.979! | |
| [2024-11-08 10:51:26,971][03578] Updated weights for policy 0, policy_version 770 (0.0028) | |
| [2024-11-08 10:51:31,020][00587] Fps is (10 sec: 3688.0, 60 sec: 4164.3, 300 sec: 4290.4). Total num frames: 3166208. Throughput: 0: 1084.3. Samples: 791608. Policy #0 lag: (min: 0.0, avg: 1.5, max: 4.0) | |
| [2024-11-08 10:51:31,030][00587] Avg episode reward: [(0, '15.051')] | |
| [2024-11-08 10:51:31,057][03563] Saving new best policy, reward=15.051! | |
| [2024-11-08 10:51:36,020][00587] Fps is (10 sec: 3276.9, 60 sec: 4164.3, 300 sec: 4248.7). Total num frames: 3182592. Throughput: 0: 1037.9. Samples: 796720. Policy #0 lag: (min: 0.0, avg: 1.6, max: 4.0) | |
| [2024-11-08 10:51:36,022][00587] Avg episode reward: [(0, '14.815')] | |
| [2024-11-08 10:51:38,280][03578] Updated weights for policy 0, policy_version 780 (0.0017) | |
| [2024-11-08 10:51:41,020][00587] Fps is (10 sec: 4096.0, 60 sec: 4301.1, 300 sec: 4248.7). Total num frames: 3207168. Throughput: 0: 1023.8. Samples: 804272. Policy #0 lag: (min: 0.0, avg: 1.5, max: 4.0) | |
| [2024-11-08 10:51:41,025][00587] Avg episode reward: [(0, '16.071')] | |
| [2024-11-08 10:51:41,035][03563] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000783_3207168.pth... | |
| [2024-11-08 10:51:41,153][03563] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000534_2187264.pth | |
| [2024-11-08 10:51:41,194][03563] Saving new best policy, reward=16.071! | |
| [2024-11-08 10:51:45,568][03578] Updated weights for policy 0, policy_version 790 (0.0013) | |
| [2024-11-08 10:51:46,020][00587] Fps is (10 sec: 5324.8, 60 sec: 4437.3, 300 sec: 4262.6). Total num frames: 3235840. Throughput: 0: 1051.9. Samples: 808176. Policy #0 lag: (min: 0.0, avg: 1.4, max: 4.0) | |
| [2024-11-08 10:51:46,024][00587] Avg episode reward: [(0, '17.209')] | |
| [2024-11-08 10:51:46,027][03563] Saving new best policy, reward=17.209! | |
| [2024-11-08 10:51:51,022][00587] Fps is (10 sec: 4504.7, 60 sec: 4232.5, 300 sec: 4262.6). Total num frames: 3252224. Throughput: 0: 1076.6. Samples: 814456. Policy #0 lag: (min: 0.0, avg: 2.2, max: 5.0) | |
| [2024-11-08 10:51:51,025][00587] Avg episode reward: [(0, '17.073')] | |
| [2024-11-08 10:51:56,020][00587] Fps is (10 sec: 3276.8, 60 sec: 4096.4, 300 sec: 4262.6). Total num frames: 3268608. Throughput: 0: 1072.0. Samples: 819840. Policy #0 lag: (min: 0.0, avg: 1.8, max: 4.0) | |
| [2024-11-08 10:51:56,022][00587] Avg episode reward: [(0, '18.769')] | |
| [2024-11-08 10:51:56,029][03563] Saving new best policy, reward=18.769! | |
| [2024-11-08 10:51:57,429][03578] Updated weights for policy 0, policy_version 800 (0.0020) | |
| [2024-11-08 10:52:01,020][00587] Fps is (10 sec: 3277.5, 60 sec: 4096.0, 300 sec: 4248.7). Total num frames: 3284992. Throughput: 0: 1044.6. Samples: 822552. Policy #0 lag: (min: 0.0, avg: 2.1, max: 4.0) | |
| [2024-11-08 10:52:01,022][00587] Avg episode reward: [(0, '18.660')] | |
| [2024-11-08 10:52:05,974][03578] Updated weights for policy 0, policy_version 810 (0.0017) | |
| [2024-11-08 10:52:06,020][00587] Fps is (10 sec: 4915.2, 60 sec: 4369.1, 300 sec: 4248.7). Total num frames: 3317760. Throughput: 0: 1026.2. Samples: 829664. Policy #0 lag: (min: 0.0, avg: 1.5, max: 4.0) | |
| [2024-11-08 10:52:06,023][00587] Avg episode reward: [(0, '17.706')] | |
| [2024-11-08 10:52:11,020][00587] Fps is (10 sec: 5734.4, 60 sec: 4437.3, 300 sec: 4276.5). Total num frames: 3342336. Throughput: 0: 1082.1. Samples: 837736. Policy #0 lag: (min: 0.0, avg: 1.8, max: 4.0) | |
| [2024-11-08 10:52:11,022][00587] Avg episode reward: [(0, '17.888')] | |
| [2024-11-08 10:52:15,333][03578] Updated weights for policy 0, policy_version 820 (0.0016) | |
| [2024-11-08 10:52:16,020][00587] Fps is (10 sec: 4505.6, 60 sec: 4300.8, 300 sec: 4290.4). Total num frames: 3362816. Throughput: 0: 1086.0. Samples: 840480. Policy #0 lag: (min: 0.0, avg: 1.6, max: 4.0) | |
| [2024-11-08 10:52:16,022][00587] Avg episode reward: [(0, '17.414')] | |
| [2024-11-08 10:52:21,020][00587] Fps is (10 sec: 3686.4, 60 sec: 4164.6, 300 sec: 4290.4). Total num frames: 3379200. Throughput: 0: 1088.7. Samples: 845712. Policy #0 lag: (min: 0.0, avg: 1.9, max: 5.0) | |
| [2024-11-08 10:52:21,022][00587] Avg episode reward: [(0, '17.141')] | |
| [2024-11-08 10:52:26,020][00587] Fps is (10 sec: 3276.8, 60 sec: 4096.0, 300 sec: 4276.5). Total num frames: 3395584. Throughput: 0: 1052.1. Samples: 851616. Policy #0 lag: (min: 0.0, avg: 1.6, max: 4.0) | |
| [2024-11-08 10:52:26,027][00587] Avg episode reward: [(0, '18.735')] | |
| [2024-11-08 10:52:26,160][03578] Updated weights for policy 0, policy_version 830 (0.0024) | |
| [2024-11-08 10:52:31,020][00587] Fps is (10 sec: 4505.6, 60 sec: 4300.8, 300 sec: 4276.5). Total num frames: 3424256. Throughput: 0: 1055.1. Samples: 855656. Policy #0 lag: (min: 0.0, avg: 1.9, max: 4.0) | |
| [2024-11-08 10:52:31,025][00587] Avg episode reward: [(0, '18.354')] | |
| [2024-11-08 10:52:33,314][03578] Updated weights for policy 0, policy_version 840 (0.0013) | |
| [2024-11-08 10:52:36,020][00587] Fps is (10 sec: 5324.8, 60 sec: 4437.3, 300 sec: 4276.5). Total num frames: 3448832. Throughput: 0: 1091.1. Samples: 863552. Policy #0 lag: (min: 0.0, avg: 1.9, max: 4.0) | |
| [2024-11-08 10:52:36,025][00587] Avg episode reward: [(0, '18.338')] | |
| [2024-11-08 10:52:41,020][00587] Fps is (10 sec: 4096.0, 60 sec: 4300.8, 300 sec: 4276.5). Total num frames: 3465216. Throughput: 0: 1091.2. Samples: 868944. Policy #0 lag: (min: 0.0, avg: 1.8, max: 4.0) | |
| [2024-11-08 10:52:41,025][00587] Avg episode reward: [(0, '19.608')] | |
| [2024-11-08 10:52:41,033][03563] Saving new best policy, reward=19.608! | |
| [2024-11-08 10:52:44,998][03578] Updated weights for policy 0, policy_version 850 (0.0019) | |
| [2024-11-08 10:52:46,020][00587] Fps is (10 sec: 3686.4, 60 sec: 4164.3, 300 sec: 4290.4). Total num frames: 3485696. Throughput: 0: 1091.4. Samples: 871664. Policy #0 lag: (min: 0.0, avg: 1.7, max: 4.0) | |
| [2024-11-08 10:52:46,025][00587] Avg episode reward: [(0, '17.827')] | |
| [2024-11-08 10:52:51,020][00587] Fps is (10 sec: 4096.0, 60 sec: 4232.7, 300 sec: 4276.5). Total num frames: 3506176. Throughput: 0: 1059.9. Samples: 877360. Policy #0 lag: (min: 0.0, avg: 1.9, max: 4.0) | |
| [2024-11-08 10:52:51,025][00587] Avg episode reward: [(0, '17.798')] | |
| [2024-11-08 10:52:53,433][03578] Updated weights for policy 0, policy_version 860 (0.0014) | |
| [2024-11-08 10:52:56,020][00587] Fps is (10 sec: 4915.2, 60 sec: 4437.3, 300 sec: 4290.4). Total num frames: 3534848. Throughput: 0: 1063.3. Samples: 885584. Policy #0 lag: (min: 0.0, avg: 1.9, max: 5.0) | |
| [2024-11-08 10:52:56,022][00587] Avg episode reward: [(0, '19.124')] | |
| [2024-11-08 10:53:01,025][00587] Fps is (10 sec: 4912.6, 60 sec: 4505.2, 300 sec: 4304.2). Total num frames: 3555328. Throughput: 0: 1094.3. Samples: 889728. Policy #0 lag: (min: 0.0, avg: 2.0, max: 5.0) | |
| [2024-11-08 10:53:01,028][00587] Avg episode reward: [(0, '19.901')] | |
| [2024-11-08 10:53:01,042][03563] Saving new best policy, reward=19.901! | |
| [2024-11-08 10:53:02,254][03578] Updated weights for policy 0, policy_version 870 (0.0025) | |
| [2024-11-08 10:53:06,020][00587] Fps is (10 sec: 3686.4, 60 sec: 4232.5, 300 sec: 4290.5). Total num frames: 3571712. Throughput: 0: 1101.9. Samples: 895296. Policy #0 lag: (min: 0.0, avg: 1.9, max: 5.0) | |
| [2024-11-08 10:53:06,022][00587] Avg episode reward: [(0, '19.932')] | |
| [2024-11-08 10:53:06,029][03563] Saving new best policy, reward=19.932! | |
| [2024-11-08 10:53:11,024][00587] Fps is (10 sec: 3277.3, 60 sec: 4095.7, 300 sec: 4276.4). Total num frames: 3588096. Throughput: 0: 1088.1. Samples: 900584. Policy #0 lag: (min: 0.0, avg: 1.8, max: 4.0) | |
| [2024-11-08 10:53:11,032][00587] Avg episode reward: [(0, '20.374')] | |
| [2024-11-08 10:53:11,041][03563] Saving new best policy, reward=20.374! | |
| [2024-11-08 10:53:13,364][03578] Updated weights for policy 0, policy_version 880 (0.0013) | |
| [2024-11-08 10:53:16,020][00587] Fps is (10 sec: 4505.4, 60 sec: 4232.5, 300 sec: 4290.4). Total num frames: 3616768. Throughput: 0: 1055.5. Samples: 903152. Policy #0 lag: (min: 0.0, avg: 1.9, max: 5.0) | |
| [2024-11-08 10:53:16,024][00587] Avg episode reward: [(0, '21.787')] | |
| [2024-11-08 10:53:16,029][03563] Saving new best policy, reward=21.787! | |
| [2024-11-08 10:53:21,020][00587] Fps is (10 sec: 5326.9, 60 sec: 4369.1, 300 sec: 4276.5). Total num frames: 3641344. Throughput: 0: 1059.4. Samples: 911224. Policy #0 lag: (min: 0.0, avg: 1.9, max: 4.0) | |
| [2024-11-08 10:53:21,022][00587] Avg episode reward: [(0, '22.125')] | |
| [2024-11-08 10:53:21,029][03563] Saving new best policy, reward=22.125! | |
| [2024-11-08 10:53:21,834][03578] Updated weights for policy 0, policy_version 890 (0.0013) | |
| [2024-11-08 10:53:26,022][00587] Fps is (10 sec: 4914.5, 60 sec: 4505.5, 300 sec: 4290.4). Total num frames: 3665920. Throughput: 0: 1102.2. Samples: 918544. Policy #0 lag: (min: 0.0, avg: 1.8, max: 4.0) | |
| [2024-11-08 10:53:26,025][00587] Avg episode reward: [(0, '23.358')] | |
| [2024-11-08 10:53:26,027][03563] Saving new best policy, reward=23.358! | |
| [2024-11-08 10:53:31,020][00587] Fps is (10 sec: 4096.0, 60 sec: 4300.8, 300 sec: 4290.4). Total num frames: 3682304. Throughput: 0: 1102.6. Samples: 921280. Policy #0 lag: (min: 0.0, avg: 1.7, max: 4.0) | |
| [2024-11-08 10:53:31,026][00587] Avg episode reward: [(0, '23.177')] | |
| [2024-11-08 10:53:31,047][03578] Updated weights for policy 0, policy_version 900 (0.0016) | |
| [2024-11-08 10:53:36,020][00587] Fps is (10 sec: 3686.9, 60 sec: 4232.5, 300 sec: 4304.3). Total num frames: 3702784. Throughput: 0: 1094.6. Samples: 926616. Policy #0 lag: (min: 0.0, avg: 1.9, max: 5.0) | |
| [2024-11-08 10:53:36,024][00587] Avg episode reward: [(0, '22.470')] | |
| [2024-11-08 10:53:41,020][00587] Fps is (10 sec: 4096.0, 60 sec: 4300.8, 300 sec: 4276.5). Total num frames: 3723264. Throughput: 0: 1053.5. Samples: 932992. Policy #0 lag: (min: 0.0, avg: 1.9, max: 4.0) | |
| [2024-11-08 10:53:41,025][00587] Avg episode reward: [(0, '22.106')] | |
| [2024-11-08 10:53:41,121][03563] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000910_3727360.pth... | |
| [2024-11-08 10:53:41,127][03578] Updated weights for policy 0, policy_version 910 (0.0018) | |
| [2024-11-08 10:53:41,301][03563] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000660_2703360.pth | |
| [2024-11-08 10:53:46,020][00587] Fps is (10 sec: 4505.7, 60 sec: 4369.1, 300 sec: 4276.5). Total num frames: 3747840. Throughput: 0: 1050.1. Samples: 936976. Policy #0 lag: (min: 0.0, avg: 1.8, max: 4.0) | |
| [2024-11-08 10:53:46,022][00587] Avg episode reward: [(0, '20.946')] | |
| [2024-11-08 10:53:49,411][03578] Updated weights for policy 0, policy_version 920 (0.0020) | |
| [2024-11-08 10:53:51,020][00587] Fps is (10 sec: 5324.8, 60 sec: 4505.6, 300 sec: 4318.2). Total num frames: 3776512. Throughput: 0: 1099.4. Samples: 944768. Policy #0 lag: (min: 0.0, avg: 1.8, max: 5.0) | |
| [2024-11-08 10:53:51,023][00587] Avg episode reward: [(0, '20.042')] | |
| [2024-11-08 10:53:56,021][00587] Fps is (10 sec: 4505.1, 60 sec: 4300.7, 300 sec: 4318.1). Total num frames: 3792896. Throughput: 0: 1099.8. Samples: 950072. Policy #0 lag: (min: 0.0, avg: 1.9, max: 4.0) | |
| [2024-11-08 10:53:56,023][00587] Avg episode reward: [(0, '20.172')] | |
| [2024-11-08 10:53:59,477][03578] Updated weights for policy 0, policy_version 930 (0.0018) | |
| [2024-11-08 10:54:01,024][00587] Fps is (10 sec: 3275.6, 60 sec: 4232.6, 300 sec: 4304.3). Total num frames: 3809280. Throughput: 0: 1103.7. Samples: 952824. Policy #0 lag: (min: 0.0, avg: 1.8, max: 4.0) | |
| [2024-11-08 10:54:01,026][00587] Avg episode reward: [(0, '20.960')] | |
| [2024-11-08 10:54:06,020][00587] Fps is (10 sec: 3686.8, 60 sec: 4300.8, 300 sec: 4290.4). Total num frames: 3829760. Throughput: 0: 1062.8. Samples: 959048. Policy #0 lag: (min: 0.0, avg: 1.8, max: 4.0) | |
| [2024-11-08 10:54:06,025][00587] Avg episode reward: [(0, '19.995')] | |
| [2024-11-08 10:54:09,463][03578] Updated weights for policy 0, policy_version 940 (0.0021) | |
| [2024-11-08 10:54:11,020][00587] Fps is (10 sec: 4917.0, 60 sec: 4505.9, 300 sec: 4290.4). Total num frames: 3858432. Throughput: 0: 1075.4. Samples: 966936. Policy #0 lag: (min: 0.0, avg: 1.9, max: 4.0) | |
| [2024-11-08 10:54:11,027][00587] Avg episode reward: [(0, '21.200')] | |
| [2024-11-08 10:54:16,020][00587] Fps is (10 sec: 5324.8, 60 sec: 4437.4, 300 sec: 4304.3). Total num frames: 3883008. Throughput: 0: 1104.2. Samples: 970968. Policy #0 lag: (min: 0.0, avg: 1.9, max: 4.0) | |
| [2024-11-08 10:54:16,023][00587] Avg episode reward: [(0, '22.091')] | |
| [2024-11-08 10:54:17,840][03578] Updated weights for policy 0, policy_version 950 (0.0015) | |
| [2024-11-08 10:54:21,024][00587] Fps is (10 sec: 4094.3, 60 sec: 4300.5, 300 sec: 4304.2). Total num frames: 3899392. Throughput: 0: 1106.4. Samples: 976408. Policy #0 lag: (min: 0.0, avg: 2.2, max: 5.0) | |
| [2024-11-08 10:54:21,026][00587] Avg episode reward: [(0, '20.998')] | |
| [2024-11-08 10:54:26,020][00587] Fps is (10 sec: 3276.8, 60 sec: 4164.4, 300 sec: 4304.3). Total num frames: 3915776. Throughput: 0: 1089.1. Samples: 982000. Policy #0 lag: (min: 0.0, avg: 2.1, max: 4.0) | |
| [2024-11-08 10:54:26,027][00587] Avg episode reward: [(0, '20.792')] | |
| [2024-11-08 10:54:28,645][03578] Updated weights for policy 0, policy_version 960 (0.0021) | |
| [2024-11-08 10:54:31,020][00587] Fps is (10 sec: 4097.8, 60 sec: 4300.8, 300 sec: 4304.3). Total num frames: 3940352. Throughput: 0: 1069.5. Samples: 985104. Policy #0 lag: (min: 0.0, avg: 2.0, max: 4.0) | |
| [2024-11-08 10:54:31,030][00587] Avg episode reward: [(0, '20.879')] | |
| [2024-11-08 10:54:35,871][03578] Updated weights for policy 0, policy_version 970 (0.0021) | |
| [2024-11-08 10:54:36,020][00587] Fps is (10 sec: 5734.4, 60 sec: 4505.6, 300 sec: 4304.3). Total num frames: 3973120. Throughput: 0: 1079.5. Samples: 993344. Policy #0 lag: (min: 0.0, avg: 1.8, max: 4.0) | |
| [2024-11-08 10:54:36,022][00587] Avg episode reward: [(0, '20.404')] | |
| [2024-11-08 10:54:41,020][00587] Fps is (10 sec: 4915.1, 60 sec: 4437.3, 300 sec: 4304.3). Total num frames: 3989504. Throughput: 0: 1106.5. Samples: 999864. Policy #0 lag: (min: 0.0, avg: 2.1, max: 4.0) | |
| [2024-11-08 10:54:41,027][00587] Avg episode reward: [(0, '20.088')] | |
| [2024-11-08 10:54:44,302][03563] Stopping Batcher_0... | |
| [2024-11-08 10:54:44,305][03563] Loop batcher_evt_loop terminating... | |
| [2024-11-08 10:54:44,305][00587] Component Batcher_0 stopped! | |
| [2024-11-08 10:54:44,318][03563] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... | |
| [2024-11-08 10:54:44,453][03578] Weights refcount: 2 0 | |
| [2024-11-08 10:54:44,457][00587] Component InferenceWorker_p0-w0 stopped! | |
| [2024-11-08 10:54:44,459][03578] Stopping InferenceWorker_p0-w0... | |
| [2024-11-08 10:54:44,462][03578] Loop inference_proc0-0_evt_loop terminating... | |
| [2024-11-08 10:54:44,474][03563] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000783_3207168.pth | |
| [2024-11-08 10:54:44,500][03563] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... | |
| [2024-11-08 10:54:44,752][00587] Component LearnerWorker_p0 stopped! | |
| [2024-11-08 10:54:44,757][03563] Stopping LearnerWorker_p0... | |
| [2024-11-08 10:54:44,757][03563] Loop learner_proc0_evt_loop terminating... | |
| [2024-11-08 10:54:46,672][00587] Component RolloutWorker_w7 stopped! | |
| [2024-11-08 10:54:46,676][03584] Stopping RolloutWorker_w7... | |
| [2024-11-08 10:54:46,681][03584] Loop rollout_proc7_evt_loop terminating... | |
| [2024-11-08 10:54:46,872][00587] Component RolloutWorker_w3 stopped! | |
| [2024-11-08 10:54:46,876][03579] Stopping RolloutWorker_w3... | |
| [2024-11-08 10:54:46,884][03579] Loop rollout_proc3_evt_loop terminating... | |
| [2024-11-08 10:54:46,915][00587] Component RolloutWorker_w1 stopped! | |
| [2024-11-08 10:54:46,921][03577] Stopping RolloutWorker_w1... | |
| [2024-11-08 10:54:46,922][03577] Loop rollout_proc1_evt_loop terminating... | |
| [2024-11-08 10:54:46,972][03583] Stopping RolloutWorker_w6... | |
| [2024-11-08 10:54:46,972][03583] Loop rollout_proc6_evt_loop terminating... | |
| [2024-11-08 10:54:46,972][00587] Component RolloutWorker_w6 stopped! | |
| [2024-11-08 10:54:46,979][03576] Stopping RolloutWorker_w0... | |
| [2024-11-08 10:54:46,982][03576] Loop rollout_proc0_evt_loop terminating... | |
| [2024-11-08 10:54:46,981][00587] Component RolloutWorker_w0 stopped! | |
| [2024-11-08 10:54:47,035][03581] Stopping RolloutWorker_w4... | |
| [2024-11-08 10:54:47,040][03580] Stopping RolloutWorker_w2... | |
| [2024-11-08 10:54:47,041][03580] Loop rollout_proc2_evt_loop terminating... | |
| [2024-11-08 10:54:47,035][00587] Component RolloutWorker_w4 stopped! | |
| [2024-11-08 10:54:47,044][00587] Component RolloutWorker_w2 stopped! | |
| [2024-11-08 10:54:47,056][03581] Loop rollout_proc4_evt_loop terminating... | |
| [2024-11-08 10:54:47,078][03582] Stopping RolloutWorker_w5... | |
| [2024-11-08 10:54:47,078][00587] Component RolloutWorker_w5 stopped! | |
| [2024-11-08 10:54:47,083][03582] Loop rollout_proc5_evt_loop terminating... | |
| [2024-11-08 10:54:47,083][00587] Waiting for process learner_proc0 to stop... | |
| [2024-11-08 10:54:47,430][00587] Waiting for process inference_proc0-0 to join... | |
| [2024-11-08 10:54:47,433][00587] Waiting for process rollout_proc0 to join... | |
| [2024-11-08 10:54:50,160][00587] Waiting for process rollout_proc1 to join... | |
| [2024-11-08 10:54:50,171][00587] Waiting for process rollout_proc2 to join... | |
| [2024-11-08 10:54:50,180][00587] Waiting for process rollout_proc3 to join... | |
| [2024-11-08 10:54:50,183][00587] Waiting for process rollout_proc4 to join... | |
| [2024-11-08 10:54:50,198][00587] Waiting for process rollout_proc5 to join... | |
| [2024-11-08 10:54:50,202][00587] Waiting for process rollout_proc6 to join... | |
| [2024-11-08 10:54:50,205][00587] Waiting for process rollout_proc7 to join... | |
| [2024-11-08 10:54:50,209][00587] Batcher 0 profile tree view: | |
| batching: 24.2896, releasing_batches: 0.0373 | |
| [2024-11-08 10:54:50,211][00587] InferenceWorker_p0-w0 profile tree view: | |
| wait_policy: 0.0163 | |
| wait_policy_total: 737.9520 | |
| update_model: 4.4735 | |
| weight_update: 0.0025 | |
| one_step: 0.0047 | |
| handle_policy_step: 229.5986 | |
| deserialize: 9.5356, stack: 1.4607, obs_to_device_normalize: 54.0523, forward: 111.1120, send_messages: 7.9482 | |
| prepare_outputs: 34.6553 | |
| to_cpu: 20.3853 | |
| [2024-11-08 10:54:50,213][00587] Learner 0 profile tree view: | |
| misc: 0.0060, prepare_batch: 13.4176 | |
| train: 73.5821 | |
| epoch_init: 0.0059, minibatch_init: 0.0206, losses_postprocess: 0.4147, kl_divergence: 0.6265, after_optimizer: 31.1759 | |
| calculate_losses: 27.6076 | |
| losses_init: 0.0150, forward_head: 1.4582, bptt_initial: 18.0753, tail: 1.2786, advantages_returns: 0.2940, losses: 4.0784 | |
| bptt: 2.0223 | |
| bptt_forward_core: 1.8774 | |
| update: 13.0319 | |
| clip: 0.9613 | |
| [2024-11-08 10:54:50,215][00587] RolloutWorker_w0 profile tree view: | |
| wait_for_trajectories: 0.2855, enqueue_policy_requests: 96.8717, env_step: 776.9904, overhead: 15.4555, complete_rollouts: 2.9211 | |
| save_policy_outputs: 24.6069 | |
| split_output_tensors: 9.2342 | |
| [2024-11-08 10:54:50,216][00587] RolloutWorker_w7 profile tree view: | |
| wait_for_trajectories: 0.2567, enqueue_policy_requests: 97.6264, env_step: 783.0025, overhead: 16.4117, complete_rollouts: 2.8983 | |
| save_policy_outputs: 25.3882 | |
| split_output_tensors: 9.6669 | |
| [2024-11-08 10:54:50,218][00587] Loop Runner_EvtLoop terminating... | |
| [2024-11-08 10:54:50,220][00587] Runner profile tree view: | |
| main_loop: 1022.2038 | |
| [2024-11-08 10:54:50,221][00587] Collected {0: 4005888}, FPS: 3918.9 | |
| [2024-11-08 10:55:56,634][00587] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json | |
| [2024-11-08 10:55:56,637][00587] Overriding arg 'num_workers' with value 1 passed from command line | |
| [2024-11-08 10:55:56,638][00587] Adding new argument 'no_render'=True that is not in the saved config file! | |
| [2024-11-08 10:55:56,640][00587] Adding new argument 'save_video'=True that is not in the saved config file! | |
| [2024-11-08 10:55:56,641][00587] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file! | |
| [2024-11-08 10:55:56,643][00587] Adding new argument 'video_name'=None that is not in the saved config file! | |
| [2024-11-08 10:55:56,644][00587] Adding new argument 'max_num_frames'=1000000000.0 that is not in the saved config file! | |
| [2024-11-08 10:55:56,647][00587] Adding new argument 'max_num_episodes'=10 that is not in the saved config file! | |
| [2024-11-08 10:55:56,648][00587] Adding new argument 'push_to_hub'=False that is not in the saved config file! | |
| [2024-11-08 10:55:56,649][00587] Adding new argument 'hf_repository'=None that is not in the saved config file! | |
| [2024-11-08 10:55:56,650][00587] Adding new argument 'policy_index'=0 that is not in the saved config file! | |
| [2024-11-08 10:55:56,651][00587] Adding new argument 'eval_deterministic'=False that is not in the saved config file! | |
| [2024-11-08 10:55:56,652][00587] Adding new argument 'train_script'=None that is not in the saved config file! | |
| [2024-11-08 10:55:56,653][00587] Adding new argument 'enjoy_script'=None that is not in the saved config file! | |
| [2024-11-08 10:55:56,654][00587] Using frameskip 1 and render_action_repeat=4 for evaluation | |
| [2024-11-08 10:55:56,687][00587] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2024-11-08 10:55:56,692][00587] RunningMeanStd input shape: (3, 72, 128) | |
| [2024-11-08 10:55:56,694][00587] RunningMeanStd input shape: (1,) | |
| [2024-11-08 10:55:56,709][00587] ConvEncoder: input_channels=3 | |
| [2024-11-08 10:55:56,814][00587] Conv encoder output size: 512 | |
| [2024-11-08 10:55:56,817][00587] Policy head output size: 512 | |
| [2024-11-08 10:55:57,084][00587] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... | |
| [2024-11-08 10:55:57,904][00587] Num frames 100... | |
| [2024-11-08 10:55:58,022][00587] Num frames 200... | |
| [2024-11-08 10:55:58,144][00587] Num frames 300... | |
| [2024-11-08 10:55:58,270][00587] Num frames 400... | |
| [2024-11-08 10:55:58,393][00587] Num frames 500... | |
| [2024-11-08 10:55:58,519][00587] Num frames 600... | |
| [2024-11-08 10:55:58,644][00587] Num frames 700... | |
| [2024-11-08 10:55:58,771][00587] Num frames 800... | |
| [2024-11-08 10:55:58,893][00587] Num frames 900... | |
| [2024-11-08 10:55:59,012][00587] Num frames 1000... | |
| [2024-11-08 10:55:59,132][00587] Num frames 1100... | |
| [2024-11-08 10:55:59,258][00587] Num frames 1200... | |
| [2024-11-08 10:55:59,383][00587] Num frames 1300... | |
| [2024-11-08 10:55:59,454][00587] Avg episode rewards: #0: 32.120, true rewards: #0: 13.120 | |
| [2024-11-08 10:55:59,456][00587] Avg episode reward: 32.120, avg true_objective: 13.120 | |
| [2024-11-08 10:55:59,563][00587] Num frames 1400... | |
| [2024-11-08 10:55:59,681][00587] Num frames 1500... | |
| [2024-11-08 10:55:59,803][00587] Num frames 1600... | |
| [2024-11-08 10:55:59,928][00587] Num frames 1700... | |
| [2024-11-08 10:56:00,046][00587] Num frames 1800... | |
| [2024-11-08 10:56:00,140][00587] Avg episode rewards: #0: 21.160, true rewards: #0: 9.160 | |
| [2024-11-08 10:56:00,141][00587] Avg episode reward: 21.160, avg true_objective: 9.160 | |
| [2024-11-08 10:56:00,233][00587] Num frames 1900... | |
| [2024-11-08 10:56:00,351][00587] Num frames 2000... | |
| [2024-11-08 10:56:00,475][00587] Num frames 2100... | |
| [2024-11-08 10:56:00,594][00587] Num frames 2200... | |
| [2024-11-08 10:56:00,726][00587] Num frames 2300... | |
| [2024-11-08 10:56:00,850][00587] Num frames 2400... | |
| [2024-11-08 10:56:00,987][00587] Avg episode rewards: #0: 17.573, true rewards: #0: 8.240 | |
| [2024-11-08 10:56:00,989][00587] Avg episode reward: 17.573, avg true_objective: 8.240 | |
| [2024-11-08 10:56:01,027][00587] Num frames 2500... | |
| [2024-11-08 10:56:01,143][00587] Num frames 2600... | |
| [2024-11-08 10:56:01,275][00587] Num frames 2700... | |
| [2024-11-08 10:56:01,396][00587] Num frames 2800... | |
| [2024-11-08 10:56:01,525][00587] Num frames 2900... | |
| [2024-11-08 10:56:01,645][00587] Num frames 3000... | |
| [2024-11-08 10:56:01,766][00587] Num frames 3100... | |
| [2024-11-08 10:56:01,885][00587] Num frames 3200... | |
| [2024-11-08 10:56:02,009][00587] Num frames 3300... | |
| [2024-11-08 10:56:02,133][00587] Num frames 3400... | |
| [2024-11-08 10:56:02,265][00587] Num frames 3500... | |
| [2024-11-08 10:56:02,384][00587] Num frames 3600... | |
| [2024-11-08 10:56:02,508][00587] Num frames 3700... | |
| [2024-11-08 10:56:02,633][00587] Num frames 3800... | |
| [2024-11-08 10:56:02,750][00587] Num frames 3900... | |
| [2024-11-08 10:56:02,871][00587] Num frames 4000... | |
| [2024-11-08 10:56:02,991][00587] Num frames 4100... | |
| [2024-11-08 10:56:03,110][00587] Num frames 4200... | |
| [2024-11-08 10:56:03,238][00587] Num frames 4300... | |
| [2024-11-08 10:56:03,359][00587] Num frames 4400... | |
| [2024-11-08 10:56:03,479][00587] Num frames 4500... | |
| [2024-11-08 10:56:03,607][00587] Avg episode rewards: #0: 28.132, true rewards: #0: 11.383 | |
| [2024-11-08 10:56:03,609][00587] Avg episode reward: 28.132, avg true_objective: 11.383 | |
| [2024-11-08 10:56:03,665][00587] Num frames 4600... | |
| [2024-11-08 10:56:03,788][00587] Num frames 4700... | |
| [2024-11-08 10:56:03,912][00587] Num frames 4800... | |
| [2024-11-08 10:56:04,029][00587] Num frames 4900... | |
| [2024-11-08 10:56:04,146][00587] Num frames 5000... | |
| [2024-11-08 10:56:04,276][00587] Num frames 5100... | |
| [2024-11-08 10:56:04,396][00587] Num frames 5200... | |
| [2024-11-08 10:56:04,516][00587] Num frames 5300... | |
| [2024-11-08 10:56:04,638][00587] Num frames 5400... | |
| [2024-11-08 10:56:04,755][00587] Num frames 5500... | |
| [2024-11-08 10:56:04,881][00587] Num frames 5600... | |
| [2024-11-08 10:56:05,002][00587] Num frames 5700... | |
| [2024-11-08 10:56:05,123][00587] Num frames 5800... | |
| [2024-11-08 10:56:05,249][00587] Num frames 5900... | |
| [2024-11-08 10:56:05,372][00587] Num frames 6000... | |
| [2024-11-08 10:56:05,490][00587] Num frames 6100... | |
| [2024-11-08 10:56:05,617][00587] Num frames 6200... | |
| [2024-11-08 10:56:05,741][00587] Num frames 6300... | |
| [2024-11-08 10:56:05,865][00587] Num frames 6400... | |
| [2024-11-08 10:56:05,989][00587] Num frames 6500... | |
| [2024-11-08 10:56:06,110][00587] Num frames 6600... | |
| [2024-11-08 10:56:06,203][00587] Avg episode rewards: #0: 31.658, true rewards: #0: 13.258 | |
| [2024-11-08 10:56:06,205][00587] Avg episode reward: 31.658, avg true_objective: 13.258 | |
| [2024-11-08 10:56:06,288][00587] Num frames 6700... | |
| [2024-11-08 10:56:06,409][00587] Num frames 6800... | |
| [2024-11-08 10:56:06,578][00587] Num frames 6900... | |
| [2024-11-08 10:56:06,750][00587] Num frames 7000... | |
| [2024-11-08 10:56:06,925][00587] Num frames 7100... | |
| [2024-11-08 10:56:07,083][00587] Num frames 7200... | |
| [2024-11-08 10:56:07,247][00587] Num frames 7300... | |
| [2024-11-08 10:56:07,411][00587] Num frames 7400... | |
| [2024-11-08 10:56:07,570][00587] Num frames 7500... | |
| [2024-11-08 10:56:07,752][00587] Num frames 7600... | |
| [2024-11-08 10:56:07,925][00587] Num frames 7700... | |
| [2024-11-08 10:56:08,094][00587] Num frames 7800... | |
| [2024-11-08 10:56:08,265][00587] Num frames 7900... | |
| [2024-11-08 10:56:08,438][00587] Num frames 8000... | |
| [2024-11-08 10:56:08,612][00587] Num frames 8100... | |
| [2024-11-08 10:56:08,831][00587] Avg episode rewards: #0: 32.153, true rewards: #0: 13.653 | |
| [2024-11-08 10:56:08,833][00587] Avg episode reward: 32.153, avg true_objective: 13.653 | |
| [2024-11-08 10:56:08,850][00587] Num frames 8200... | |
| [2024-11-08 10:56:09,016][00587] Num frames 8300... | |
| [2024-11-08 10:56:09,136][00587] Num frames 8400... | |
| [2024-11-08 10:56:09,266][00587] Num frames 8500... | |
| [2024-11-08 10:56:09,385][00587] Num frames 8600... | |
| [2024-11-08 10:56:09,503][00587] Num frames 8700... | |
| [2024-11-08 10:56:09,626][00587] Num frames 8800... | |
| [2024-11-08 10:56:09,752][00587] Num frames 8900... | |
| [2024-11-08 10:56:09,883][00587] Num frames 9000... | |
| [2024-11-08 10:56:10,005][00587] Num frames 9100... | |
| [2024-11-08 10:56:10,128][00587] Num frames 9200... | |
| [2024-11-08 10:56:10,247][00587] Avg episode rewards: #0: 31.068, true rewards: #0: 13.211 | |
| [2024-11-08 10:56:10,248][00587] Avg episode reward: 31.068, avg true_objective: 13.211 | |
| [2024-11-08 10:56:10,312][00587] Num frames 9300... | |
| [2024-11-08 10:56:10,434][00587] Num frames 9400... | |
| [2024-11-08 10:56:10,554][00587] Num frames 9500... | |
| [2024-11-08 10:56:10,673][00587] Num frames 9600... | |
| [2024-11-08 10:56:10,810][00587] Num frames 9700... | |
| [2024-11-08 10:56:10,929][00587] Num frames 9800... | |
| [2024-11-08 10:56:11,054][00587] Num frames 9900... | |
| [2024-11-08 10:56:11,209][00587] Avg episode rewards: #0: 29.230, true rewards: #0: 12.480 | |
| [2024-11-08 10:56:11,211][00587] Avg episode reward: 29.230, avg true_objective: 12.480 | |
| [2024-11-08 10:56:11,236][00587] Num frames 10000... | |
| [2024-11-08 10:56:11,353][00587] Num frames 10100... | |
| [2024-11-08 10:56:11,474][00587] Num frames 10200... | |
| [2024-11-08 10:56:11,596][00587] Num frames 10300... | |
| [2024-11-08 10:56:11,716][00587] Num frames 10400... | |
| [2024-11-08 10:56:11,844][00587] Num frames 10500... | |
| [2024-11-08 10:56:11,967][00587] Num frames 10600... | |
| [2024-11-08 10:56:12,086][00587] Num frames 10700... | |
| [2024-11-08 10:56:12,216][00587] Num frames 10800... | |
| [2024-11-08 10:56:12,343][00587] Num frames 10900... | |
| [2024-11-08 10:56:12,460][00587] Num frames 11000... | |
| [2024-11-08 10:56:12,526][00587] Avg episode rewards: #0: 28.231, true rewards: #0: 12.231 | |
| [2024-11-08 10:56:12,527][00587] Avg episode reward: 28.231, avg true_objective: 12.231 | |
| [2024-11-08 10:56:12,635][00587] Num frames 11100... | |
| [2024-11-08 10:56:12,756][00587] Num frames 11200... | |
| [2024-11-08 10:56:12,883][00587] Num frames 11300... | |
| [2024-11-08 10:56:13,001][00587] Num frames 11400... | |
| [2024-11-08 10:56:13,117][00587] Num frames 11500... | |
| [2024-11-08 10:56:13,244][00587] Num frames 11600... | |
| [2024-11-08 10:56:13,359][00587] Num frames 11700... | |
| [2024-11-08 10:56:13,481][00587] Num frames 11800... | |
| [2024-11-08 10:56:13,599][00587] Num frames 11900... | |
| [2024-11-08 10:56:13,697][00587] Avg episode rewards: #0: 27.236, true rewards: #0: 11.936 | |
| [2024-11-08 10:56:13,699][00587] Avg episode reward: 27.236, avg true_objective: 11.936 | |
| [2024-11-08 10:57:18,294][00587] Replay video saved to /content/train_dir/default_experiment/replay.mp4! | |
| [2024-11-08 10:59:05,320][00587] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json | |
| [2024-11-08 10:59:05,322][00587] Overriding arg 'num_workers' with value 1 passed from command line | |
| [2024-11-08 10:59:05,324][00587] Adding new argument 'no_render'=True that is not in the saved config file! | |
| [2024-11-08 10:59:05,326][00587] Adding new argument 'save_video'=True that is not in the saved config file! | |
| [2024-11-08 10:59:05,327][00587] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file! | |
| [2024-11-08 10:59:05,329][00587] Adding new argument 'video_name'=None that is not in the saved config file! | |
| [2024-11-08 10:59:05,331][00587] Adding new argument 'max_num_frames'=100000 that is not in the saved config file! | |
| [2024-11-08 10:59:05,332][00587] Adding new argument 'max_num_episodes'=10 that is not in the saved config file! | |
| [2024-11-08 10:59:05,333][00587] Adding new argument 'push_to_hub'=True that is not in the saved config file! | |
| [2024-11-08 10:59:05,333][00587] Adding new argument 'hf_repository'='alidenewade/rl_course_vizdoom_health_gathering_supreme' that is not in the saved config file! | |
| [2024-11-08 10:59:05,334][00587] Adding new argument 'policy_index'=0 that is not in the saved config file! | |
| [2024-11-08 10:59:05,335][00587] Adding new argument 'eval_deterministic'=False that is not in the saved config file! | |
| [2024-11-08 10:59:05,339][00587] Adding new argument 'train_script'=None that is not in the saved config file! | |
| [2024-11-08 10:59:05,341][00587] Adding new argument 'enjoy_script'=None that is not in the saved config file! | |
| [2024-11-08 10:59:05,347][00587] Using frameskip 1 and render_action_repeat=4 for evaluation | |
| [2024-11-08 10:59:05,371][00587] RunningMeanStd input shape: (3, 72, 128) | |
| [2024-11-08 10:59:05,373][00587] RunningMeanStd input shape: (1,) | |
| [2024-11-08 10:59:05,386][00587] ConvEncoder: input_channels=3 | |
| [2024-11-08 10:59:05,422][00587] Conv encoder output size: 512 | |
| [2024-11-08 10:59:05,424][00587] Policy head output size: 512 | |
| [2024-11-08 10:59:05,442][00587] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... | |
| [2024-11-08 10:59:05,906][00587] Num frames 100... | |
| [2024-11-08 10:59:06,078][00587] Num frames 200... | |
| [2024-11-08 10:59:06,251][00587] Num frames 300... | |
| [2024-11-08 10:59:06,426][00587] Num frames 400... | |
| [2024-11-08 10:59:06,588][00587] Num frames 500... | |
| [2024-11-08 10:59:06,752][00587] Num frames 600... | |
| [2024-11-08 10:59:06,916][00587] Num frames 700... | |
| [2024-11-08 10:59:07,086][00587] Num frames 800... | |
| [2024-11-08 10:59:07,270][00587] Num frames 900... | |
| [2024-11-08 10:59:07,444][00587] Num frames 1000... | |
| [2024-11-08 10:59:07,637][00587] Num frames 1100... | |
| [2024-11-08 10:59:07,806][00587] Num frames 1200... | |
| [2024-11-08 10:59:07,984][00587] Num frames 1300... | |
| [2024-11-08 10:59:08,202][00587] Avg episode rewards: #0: 31.870, true rewards: #0: 13.870 | |
| [2024-11-08 10:59:08,204][00587] Avg episode reward: 31.870, avg true_objective: 13.870 | |
| [2024-11-08 10:59:08,230][00587] Num frames 1400... | |
| [2024-11-08 10:59:08,402][00587] Num frames 1500... | |
| [2024-11-08 10:59:08,547][00587] Num frames 1600... | |
| [2024-11-08 10:59:08,682][00587] Num frames 1700... | |
| [2024-11-08 10:59:08,805][00587] Num frames 1800... | |
| [2024-11-08 10:59:08,924][00587] Num frames 1900... | |
| [2024-11-08 10:59:09,047][00587] Num frames 2000... | |
| [2024-11-08 10:59:09,172][00587] Num frames 2100... | |
| [2024-11-08 10:59:09,344][00587] Avg episode rewards: #0: 22.935, true rewards: #0: 10.935 | |
| [2024-11-08 10:59:09,346][00587] Avg episode reward: 22.935, avg true_objective: 10.935 | |
| [2024-11-08 10:59:09,365][00587] Num frames 2200... | |
| [2024-11-08 10:59:09,480][00587] Num frames 2300... | |
| [2024-11-08 10:59:09,597][00587] Num frames 2400... | |
| [2024-11-08 10:59:09,717][00587] Num frames 2500... | |
| [2024-11-08 10:59:09,836][00587] Num frames 2600... | |
| [2024-11-08 10:59:09,952][00587] Num frames 2700... | |
| [2024-11-08 10:59:10,084][00587] Num frames 2800... | |
| [2024-11-08 10:59:10,211][00587] Num frames 2900... | |
| [2024-11-08 10:59:10,330][00587] Num frames 3000... | |
| [2024-11-08 10:59:10,450][00587] Num frames 3100... | |
| [2024-11-08 10:59:10,566][00587] Num frames 3200... | |
| [2024-11-08 10:59:10,684][00587] Num frames 3300... | |
| [2024-11-08 10:59:10,801][00587] Num frames 3400... | |
| [2024-11-08 10:59:10,924][00587] Num frames 3500... | |
| [2024-11-08 10:59:11,044][00587] Num frames 3600... | |
| [2024-11-08 10:59:11,200][00587] Num frames 3700... | |
| [2024-11-08 10:59:11,371][00587] Avg episode rewards: #0: 27.983, true rewards: #0: 12.650 | |
| [2024-11-08 10:59:11,373][00587] Avg episode reward: 27.983, avg true_objective: 12.650 | |
| [2024-11-08 10:59:11,383][00587] Num frames 3800... | |
| [2024-11-08 10:59:11,500][00587] Num frames 3900... | |
| [2024-11-08 10:59:11,621][00587] Num frames 4000... | |
| [2024-11-08 10:59:11,741][00587] Num frames 4100... | |
| [2024-11-08 10:59:11,864][00587] Num frames 4200... | |
| [2024-11-08 10:59:11,984][00587] Num frames 4300... | |
| [2024-11-08 10:59:12,108][00587] Num frames 4400... | |
| [2024-11-08 10:59:12,236][00587] Num frames 4500... | |
| [2024-11-08 10:59:12,354][00587] Num frames 4600... | |
| [2024-11-08 10:59:12,474][00587] Num frames 4700... | |
| [2024-11-08 10:59:12,634][00587] Avg episode rewards: #0: 25.718, true rewards: #0: 11.967 | |
| [2024-11-08 10:59:12,636][00587] Avg episode reward: 25.718, avg true_objective: 11.967 | |
| [2024-11-08 10:59:12,655][00587] Num frames 4800... | |
| [2024-11-08 10:59:12,775][00587] Num frames 4900... | |
| [2024-11-08 10:59:12,897][00587] Num frames 5000... | |
| [2024-11-08 10:59:13,016][00587] Num frames 5100... | |
| [2024-11-08 10:59:13,142][00587] Num frames 5200... | |
| [2024-11-08 10:59:13,278][00587] Num frames 5300... | |
| [2024-11-08 10:59:13,398][00587] Num frames 5400... | |
| [2024-11-08 10:59:13,516][00587] Num frames 5500... | |
| [2024-11-08 10:59:13,636][00587] Num frames 5600... | |
| [2024-11-08 10:59:13,756][00587] Num frames 5700... | |
| [2024-11-08 10:59:13,875][00587] Num frames 5800... | |
| [2024-11-08 10:59:14,001][00587] Num frames 5900... | |
| [2024-11-08 10:59:14,120][00587] Num frames 6000... | |
| [2024-11-08 10:59:14,259][00587] Num frames 6100... | |
| [2024-11-08 10:59:14,383][00587] Num frames 6200... | |
| [2024-11-08 10:59:14,506][00587] Num frames 6300... | |
| [2024-11-08 10:59:14,627][00587] Num frames 6400... | |
| [2024-11-08 10:59:14,754][00587] Num frames 6500... | |
| [2024-11-08 10:59:14,870][00587] Avg episode rewards: #0: 29.694, true rewards: #0: 13.094 | |
| [2024-11-08 10:59:14,871][00587] Avg episode reward: 29.694, avg true_objective: 13.094 | |
| [2024-11-08 10:59:14,934][00587] Num frames 6600... | |
| [2024-11-08 10:59:15,054][00587] Num frames 6700... | |
| [2024-11-08 10:59:15,190][00587] Num frames 6800... | |
| [2024-11-08 10:59:15,314][00587] Num frames 6900... | |
| [2024-11-08 10:59:15,375][00587] Avg episode rewards: #0: 25.840, true rewards: #0: 11.507 | |
| [2024-11-08 10:59:15,377][00587] Avg episode reward: 25.840, avg true_objective: 11.507 | |
| [2024-11-08 10:59:15,491][00587] Num frames 7000... | |
| [2024-11-08 10:59:15,611][00587] Num frames 7100... | |
| [2024-11-08 10:59:15,737][00587] Num frames 7200... | |
| [2024-11-08 10:59:15,858][00587] Num frames 7300... | |
| [2024-11-08 10:59:15,976][00587] Num frames 7400... | |
| [2024-11-08 10:59:16,099][00587] Num frames 7500... | |
| [2024-11-08 10:59:16,238][00587] Num frames 7600... | |
| [2024-11-08 10:59:16,361][00587] Num frames 7700... | |
| [2024-11-08 10:59:16,486][00587] Num frames 7800... | |
| [2024-11-08 10:59:16,603][00587] Num frames 7900... | |
| [2024-11-08 10:59:16,722][00587] Num frames 8000... | |
| [2024-11-08 10:59:16,841][00587] Num frames 8100... | |
| [2024-11-08 10:59:16,966][00587] Avg episode rewards: #0: 26.514, true rewards: #0: 11.657 | |
| [2024-11-08 10:59:16,968][00587] Avg episode reward: 26.514, avg true_objective: 11.657 | |
| [2024-11-08 10:59:17,017][00587] Num frames 8200... | |
| [2024-11-08 10:59:17,132][00587] Num frames 8300... | |
| [2024-11-08 10:59:17,277][00587] Num frames 8400... | |
| [2024-11-08 10:59:17,396][00587] Num frames 8500... | |
| [2024-11-08 10:59:17,513][00587] Num frames 8600... | |
| [2024-11-08 10:59:17,636][00587] Num frames 8700... | |
| [2024-11-08 10:59:17,706][00587] Avg episode rewards: #0: 24.761, true rewards: #0: 10.886 | |
| [2024-11-08 10:59:17,707][00587] Avg episode reward: 24.761, avg true_objective: 10.886 | |
| [2024-11-08 10:59:17,814][00587] Num frames 8800... | |
| [2024-11-08 10:59:17,942][00587] Num frames 8900... | |
| [2024-11-08 10:59:18,063][00587] Num frames 9000... | |
| [2024-11-08 10:59:18,185][00587] Num frames 9100... | |
| [2024-11-08 10:59:18,314][00587] Num frames 9200... | |
| [2024-11-08 10:59:18,453][00587] Num frames 9300... | |
| [2024-11-08 10:59:18,619][00587] Num frames 9400... | |
| [2024-11-08 10:59:18,789][00587] Num frames 9500... | |
| [2024-11-08 10:59:18,948][00587] Num frames 9600... | |
| [2024-11-08 10:59:19,109][00587] Num frames 9700... | |
| [2024-11-08 10:59:19,285][00587] Num frames 9800... | |
| [2024-11-08 10:59:19,452][00587] Num frames 9900... | |
| [2024-11-08 10:59:19,612][00587] Num frames 10000... | |
| [2024-11-08 10:59:19,782][00587] Num frames 10100... | |
| [2024-11-08 10:59:19,962][00587] Num frames 10200... | |
| [2024-11-08 10:59:20,147][00587] Num frames 10300... | |
| [2024-11-08 10:59:20,314][00587] Avg episode rewards: #0: 27.174, true rewards: #0: 11.508 | |
| [2024-11-08 10:59:20,315][00587] Avg episode reward: 27.174, avg true_objective: 11.508 | |
| [2024-11-08 10:59:20,398][00587] Num frames 10400... | |
| [2024-11-08 10:59:20,565][00587] Num frames 10500... | |
| [2024-11-08 10:59:20,733][00587] Num frames 10600... | |
| [2024-11-08 10:59:20,916][00587] Num frames 10700... | |
| [2024-11-08 10:59:21,039][00587] Num frames 10800... | |
| [2024-11-08 10:59:21,158][00587] Num frames 10900... | |
| [2024-11-08 10:59:21,288][00587] Num frames 11000... | |
| [2024-11-08 10:59:21,414][00587] Num frames 11100... | |
| [2024-11-08 10:59:21,537][00587] Num frames 11200... | |
| [2024-11-08 10:59:21,661][00587] Num frames 11300... | |
| [2024-11-08 10:59:21,787][00587] Num frames 11400... | |
| [2024-11-08 10:59:21,860][00587] Avg episode rewards: #0: 26.813, true rewards: #0: 11.413 | |
| [2024-11-08 10:59:21,861][00587] Avg episode reward: 26.813, avg true_objective: 11.413 | |
| [2024-11-08 11:00:25,215][00587] Replay video saved to /content/train_dir/default_experiment/replay.mp4! | |