| [2023-02-23 04:02:18,468][11551] Saving configuration to /content/train_dir/default_experiment/config.json... | |
| [2023-02-23 04:02:18,471][11551] Rollout worker 0 uses device cpu | |
| [2023-02-23 04:02:18,475][11551] Rollout worker 1 uses device cpu | |
| [2023-02-23 04:02:18,477][11551] Rollout worker 2 uses device cpu | |
| [2023-02-23 04:02:18,478][11551] Rollout worker 3 uses device cpu | |
| [2023-02-23 04:02:18,480][11551] Rollout worker 4 uses device cpu | |
| [2023-02-23 04:02:18,481][11551] Rollout worker 5 uses device cpu | |
| [2023-02-23 04:02:18,483][11551] Rollout worker 6 uses device cpu | |
| [2023-02-23 04:02:18,485][11551] Rollout worker 7 uses device cpu | |
| [2023-02-23 04:02:18,669][11551] Using GPUs [0] for process 0 (actually maps to GPUs [0]) | |
| [2023-02-23 04:02:18,671][11551] InferenceWorker_p0-w0: min num requests: 2 | |
| [2023-02-23 04:02:18,702][11551] Starting all processes... | |
| [2023-02-23 04:02:18,704][11551] Starting process learner_proc0 | |
| [2023-02-23 04:02:18,754][11551] Starting all processes... | |
| [2023-02-23 04:02:18,769][11551] Starting process inference_proc0-0 | |
| [2023-02-23 04:02:18,769][11551] Starting process rollout_proc0 | |
| [2023-02-23 04:02:18,769][11551] Starting process rollout_proc1 | |
| [2023-02-23 04:02:18,769][11551] Starting process rollout_proc2 | |
| [2023-02-23 04:02:18,769][11551] Starting process rollout_proc3 | |
| [2023-02-23 04:02:18,769][11551] Starting process rollout_proc4 | |
| [2023-02-23 04:02:18,769][11551] Starting process rollout_proc5 | |
| [2023-02-23 04:02:18,769][11551] Starting process rollout_proc6 | |
| [2023-02-23 04:02:18,769][11551] Starting process rollout_proc7 | |
| [2023-02-23 04:02:29,849][11833] Worker 5 uses CPU cores [1] | |
| [2023-02-23 04:02:29,974][11811] Using GPUs [0] for process 0 (actually maps to GPUs [0]) | |
| [2023-02-23 04:02:29,979][11811] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0 | |
| [2023-02-23 04:02:30,231][11829] Worker 6 uses CPU cores [0] | |
| [2023-02-23 04:02:30,278][11827] Worker 1 uses CPU cores [1] | |
| [2023-02-23 04:02:30,306][11826] Worker 0 uses CPU cores [0] | |
| [2023-02-23 04:02:30,390][11831] Worker 2 uses CPU cores [0] | |
| [2023-02-23 04:02:30,554][11825] Worker 4 uses CPU cores [0] | |
| [2023-02-23 04:02:30,595][11830] Worker 7 uses CPU cores [1] | |
| [2023-02-23 04:02:30,622][11832] Using GPUs [0] for process 0 (actually maps to GPUs [0]) | |
| [2023-02-23 04:02:30,623][11832] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0 | |
| [2023-02-23 04:02:30,637][11828] Worker 3 uses CPU cores [1] | |
| [2023-02-23 04:02:30,906][11811] Num visible devices: 1 | |
| [2023-02-23 04:02:30,906][11832] Num visible devices: 1 | |
| [2023-02-23 04:02:30,918][11811] Starting seed is not provided | |
| [2023-02-23 04:02:30,918][11811] Using GPUs [0] for process 0 (actually maps to GPUs [0]) | |
| [2023-02-23 04:02:30,918][11811] Initializing actor-critic model on device cuda:0 | |
| [2023-02-23 04:02:30,919][11811] RunningMeanStd input shape: (3, 72, 128) | |
| [2023-02-23 04:02:30,921][11811] RunningMeanStd input shape: (1,) | |
| [2023-02-23 04:02:30,933][11811] ConvEncoder: input_channels=3 | |
| [2023-02-23 04:02:31,210][11811] Conv encoder output size: 512 | |
| [2023-02-23 04:02:31,210][11811] Policy head output size: 512 | |
| [2023-02-23 04:02:31,259][11811] Created Actor Critic model with architecture: | |
| [2023-02-23 04:02:31,259][11811] ActorCriticSharedWeights( | |
| (obs_normalizer): ObservationNormalizer( | |
| (running_mean_std): RunningMeanStdDictInPlace( | |
| (running_mean_std): ModuleDict( | |
| (obs): RunningMeanStdInPlace() | |
| ) | |
| ) | |
| ) | |
| (returns_normalizer): RecursiveScriptModule(original_name=RunningMeanStdInPlace) | |
| (encoder): VizdoomEncoder( | |
| (basic_encoder): ConvEncoder( | |
| (enc): RecursiveScriptModule( | |
| original_name=ConvEncoderImpl | |
| (conv_head): RecursiveScriptModule( | |
| original_name=Sequential | |
| (0): RecursiveScriptModule(original_name=Conv2d) | |
| (1): RecursiveScriptModule(original_name=ELU) | |
| (2): RecursiveScriptModule(original_name=Conv2d) | |
| (3): RecursiveScriptModule(original_name=ELU) | |
| (4): RecursiveScriptModule(original_name=Conv2d) | |
| (5): RecursiveScriptModule(original_name=ELU) | |
| ) | |
| (mlp_layers): RecursiveScriptModule( | |
| original_name=Sequential | |
| (0): RecursiveScriptModule(original_name=Linear) | |
| (1): RecursiveScriptModule(original_name=ELU) | |
| ) | |
| ) | |
| ) | |
| ) | |
| (core): ModelCoreRNN( | |
| (core): GRU(512, 512) | |
| ) | |
| (decoder): MlpDecoder( | |
| (mlp): Identity() | |
| ) | |
| (critic_linear): Linear(in_features=512, out_features=1, bias=True) | |
| (action_parameterization): ActionParameterizationDefault( | |
| (distribution_linear): Linear(in_features=512, out_features=5, bias=True) | |
| ) | |
| ) | |
| [2023-02-23 04:02:38,484][11811] Using optimizer <class 'torch.optim.adam.Adam'> | |
| [2023-02-23 04:02:38,485][11811] No checkpoints found | |
| [2023-02-23 04:02:38,485][11811] Did not load from checkpoint, starting from scratch! | |
| [2023-02-23 04:02:38,486][11811] Initialized policy 0 weights for model version 0 | |
| [2023-02-23 04:02:38,490][11811] LearnerWorker_p0 finished initialization! | |
| [2023-02-23 04:02:38,490][11811] Using GPUs [0] for process 0 (actually maps to GPUs [0]) | |
| [2023-02-23 04:02:38,665][11551] Heartbeat connected on LearnerWorker_p0 | |
| [2023-02-23 04:02:38,680][11551] Heartbeat connected on RolloutWorker_w0 | |
| [2023-02-23 04:02:38,686][11551] Heartbeat connected on RolloutWorker_w1 | |
| [2023-02-23 04:02:38,690][11551] Heartbeat connected on RolloutWorker_w2 | |
| [2023-02-23 04:02:38,693][11551] Heartbeat connected on RolloutWorker_w4 | |
| [2023-02-23 04:02:38,694][11551] Heartbeat connected on RolloutWorker_w3 | |
| [2023-02-23 04:02:38,699][11551] Heartbeat connected on RolloutWorker_w5 | |
| [2023-02-23 04:02:38,700][11551] Heartbeat connected on RolloutWorker_w6 | |
| [2023-02-23 04:02:38,703][11551] Heartbeat connected on Batcher_0 | |
| [2023-02-23 04:02:38,706][11551] Heartbeat connected on RolloutWorker_w7 | |
| [2023-02-23 04:02:38,721][11832] RunningMeanStd input shape: (3, 72, 128) | |
| [2023-02-23 04:02:38,722][11832] RunningMeanStd input shape: (1,) | |
| [2023-02-23 04:02:38,734][11832] ConvEncoder: input_channels=3 | |
| [2023-02-23 04:02:38,837][11832] Conv encoder output size: 512 | |
| [2023-02-23 04:02:38,837][11832] Policy head output size: 512 | |
| [2023-02-23 04:02:39,009][11551] Fps is (10 sec: nan, 60 sec: nan, 300 sec: nan). Total num frames: 0. Throughput: 0: nan. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) | |
| [2023-02-23 04:02:41,757][11551] Inference worker 0-0 is ready! | |
| [2023-02-23 04:02:41,759][11551] All inference workers are ready! Signal rollout workers to start! | |
| [2023-02-23 04:02:41,760][11551] Heartbeat connected on InferenceWorker_p0-w0 | |
| [2023-02-23 04:02:41,896][11826] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2023-02-23 04:02:41,901][11829] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2023-02-23 04:02:41,921][11825] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2023-02-23 04:02:41,917][11831] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2023-02-23 04:02:42,040][11833] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2023-02-23 04:02:42,027][11827] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2023-02-23 04:02:42,051][11830] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2023-02-23 04:02:42,055][11828] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2023-02-23 04:02:42,865][11833] Decorrelating experience for 0 frames... | |
| [2023-02-23 04:02:43,197][11826] Decorrelating experience for 0 frames... | |
| [2023-02-23 04:02:43,213][11829] Decorrelating experience for 0 frames... | |
| [2023-02-23 04:02:43,218][11831] Decorrelating experience for 0 frames... | |
| [2023-02-23 04:02:43,964][11833] Decorrelating experience for 32 frames... | |
| [2023-02-23 04:02:44,009][11551] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 0.0. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) | |
| [2023-02-23 04:02:44,512][11827] Decorrelating experience for 0 frames... | |
| [2023-02-23 04:02:44,529][11830] Decorrelating experience for 0 frames... | |
| [2023-02-23 04:02:44,818][11826] Decorrelating experience for 32 frames... | |
| [2023-02-23 04:02:44,826][11831] Decorrelating experience for 32 frames... | |
| [2023-02-23 04:02:44,830][11829] Decorrelating experience for 32 frames... | |
| [2023-02-23 04:02:45,396][11833] Decorrelating experience for 64 frames... | |
| [2023-02-23 04:02:45,790][11828] Decorrelating experience for 0 frames... | |
| [2023-02-23 04:02:45,834][11827] Decorrelating experience for 32 frames... | |
| [2023-02-23 04:02:45,829][11825] Decorrelating experience for 0 frames... | |
| [2023-02-23 04:02:45,956][11826] Decorrelating experience for 64 frames... | |
| [2023-02-23 04:02:46,087][11830] Decorrelating experience for 32 frames... | |
| [2023-02-23 04:02:46,334][11831] Decorrelating experience for 64 frames... | |
| [2023-02-23 04:02:46,652][11829] Decorrelating experience for 64 frames... | |
| [2023-02-23 04:02:46,824][11828] Decorrelating experience for 32 frames... | |
| [2023-02-23 04:02:47,185][11833] Decorrelating experience for 96 frames... | |
| [2023-02-23 04:02:47,293][11825] Decorrelating experience for 32 frames... | |
| [2023-02-23 04:02:47,385][11830] Decorrelating experience for 64 frames... | |
| [2023-02-23 04:02:47,744][11826] Decorrelating experience for 96 frames... | |
| [2023-02-23 04:02:47,825][11829] Decorrelating experience for 96 frames... | |
| [2023-02-23 04:02:48,327][11828] Decorrelating experience for 64 frames... | |
| [2023-02-23 04:02:48,343][11825] Decorrelating experience for 64 frames... | |
| [2023-02-23 04:02:48,548][11827] Decorrelating experience for 64 frames... | |
| [2023-02-23 04:02:48,712][11830] Decorrelating experience for 96 frames... | |
| [2023-02-23 04:02:49,009][11551] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 0.0. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) | |
| [2023-02-23 04:02:49,233][11827] Decorrelating experience for 96 frames... | |
| [2023-02-23 04:02:49,296][11825] Decorrelating experience for 96 frames... | |
| [2023-02-23 04:02:49,483][11831] Decorrelating experience for 96 frames... | |
| [2023-02-23 04:02:49,767][11828] Decorrelating experience for 96 frames... | |
| [2023-02-23 04:02:53,812][11811] Signal inference workers to stop experience collection... | |
| [2023-02-23 04:02:53,822][11832] InferenceWorker_p0-w0: stopping experience collection | |
| [2023-02-23 04:02:54,009][11551] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 148.5. Samples: 2228. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) | |
| [2023-02-23 04:02:54,017][11551] Avg episode reward: [(0, '1.831')] | |
| [2023-02-23 04:02:56,580][11811] Signal inference workers to resume experience collection... | |
| [2023-02-23 04:02:56,581][11832] InferenceWorker_p0-w0: resuming experience collection | |
| [2023-02-23 04:02:59,009][11551] Fps is (10 sec: 409.6, 60 sec: 204.8, 300 sec: 204.8). Total num frames: 4096. Throughput: 0: 116.8. Samples: 2336. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) | |
| [2023-02-23 04:02:59,016][11551] Avg episode reward: [(0, '2.469')] | |
| [2023-02-23 04:03:04,009][11551] Fps is (10 sec: 2457.6, 60 sec: 983.0, 300 sec: 983.0). Total num frames: 24576. Throughput: 0: 229.0. Samples: 5726. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) | |
| [2023-02-23 04:03:04,012][11551] Avg episode reward: [(0, '3.585')] | |
| [2023-02-23 04:03:07,414][11832] Updated weights for policy 0, policy_version 10 (0.0030) | |
| [2023-02-23 04:03:09,009][11551] Fps is (10 sec: 4096.0, 60 sec: 1501.9, 300 sec: 1501.9). Total num frames: 45056. Throughput: 0: 406.1. Samples: 12184. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-02-23 04:03:09,012][11551] Avg episode reward: [(0, '4.302')] | |
| [2023-02-23 04:03:14,009][11551] Fps is (10 sec: 4505.6, 60 sec: 1989.5, 300 sec: 1989.5). Total num frames: 69632. Throughput: 0: 447.4. Samples: 15658. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-23 04:03:14,013][11551] Avg episode reward: [(0, '4.392')] | |
| [2023-02-23 04:03:17,998][11832] Updated weights for policy 0, policy_version 20 (0.0012) | |
| [2023-02-23 04:03:19,009][11551] Fps is (10 sec: 3686.4, 60 sec: 2048.0, 300 sec: 2048.0). Total num frames: 81920. Throughput: 0: 517.5. Samples: 20700. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-02-23 04:03:19,011][11551] Avg episode reward: [(0, '4.502')] | |
| [2023-02-23 04:03:24,009][11551] Fps is (10 sec: 2867.2, 60 sec: 2184.5, 300 sec: 2184.5). Total num frames: 98304. Throughput: 0: 565.1. Samples: 25428. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-23 04:03:24,016][11551] Avg episode reward: [(0, '4.373')] | |
| [2023-02-23 04:03:28,715][11832] Updated weights for policy 0, policy_version 30 (0.0016) | |
| [2023-02-23 04:03:29,009][11551] Fps is (10 sec: 4096.0, 60 sec: 2457.6, 300 sec: 2457.6). Total num frames: 122880. Throughput: 0: 640.9. Samples: 28840. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-02-23 04:03:29,015][11551] Avg episode reward: [(0, '4.314')] | |
| [2023-02-23 04:03:29,018][11811] Saving new best policy, reward=4.314! | |
| [2023-02-23 04:03:34,012][11551] Fps is (10 sec: 4504.5, 60 sec: 2606.4, 300 sec: 2606.4). Total num frames: 143360. Throughput: 0: 786.1. Samples: 35378. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 04:03:34,017][11551] Avg episode reward: [(0, '4.339')] | |
| [2023-02-23 04:03:34,030][11811] Saving new best policy, reward=4.339! | |
| [2023-02-23 04:03:39,009][11551] Fps is (10 sec: 3276.8, 60 sec: 2594.1, 300 sec: 2594.1). Total num frames: 155648. Throughput: 0: 832.4. Samples: 39688. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 04:03:39,012][11551] Avg episode reward: [(0, '4.389')] | |
| [2023-02-23 04:03:39,014][11811] Saving new best policy, reward=4.389! | |
| [2023-02-23 04:03:41,582][11832] Updated weights for policy 0, policy_version 40 (0.0019) | |
| [2023-02-23 04:03:44,011][11551] Fps is (10 sec: 2867.5, 60 sec: 2867.1, 300 sec: 2646.6). Total num frames: 172032. Throughput: 0: 876.8. Samples: 41792. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) | |
| [2023-02-23 04:03:44,017][11551] Avg episode reward: [(0, '4.214')] | |
| [2023-02-23 04:03:49,009][11551] Fps is (10 sec: 3686.4, 60 sec: 3208.5, 300 sec: 2750.2). Total num frames: 192512. Throughput: 0: 944.7. Samples: 48238. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2023-02-23 04:03:49,011][11551] Avg episode reward: [(0, '4.526')] | |
| [2023-02-23 04:03:49,062][11811] Saving new best policy, reward=4.526! | |
| [2023-02-23 04:03:50,873][11832] Updated weights for policy 0, policy_version 50 (0.0016) | |
| [2023-02-23 04:03:54,019][11551] Fps is (10 sec: 4502.0, 60 sec: 3617.6, 300 sec: 2894.1). Total num frames: 217088. Throughput: 0: 944.8. Samples: 54708. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 04:03:54,023][11551] Avg episode reward: [(0, '4.600')] | |
| [2023-02-23 04:03:54,037][11811] Saving new best policy, reward=4.600! | |
| [2023-02-23 04:03:59,010][11551] Fps is (10 sec: 3686.2, 60 sec: 3754.6, 300 sec: 2867.2). Total num frames: 229376. Throughput: 0: 913.5. Samples: 56768. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-23 04:03:59,012][11551] Avg episode reward: [(0, '4.553')] | |
| [2023-02-23 04:04:03,515][11832] Updated weights for policy 0, policy_version 60 (0.0030) | |
| [2023-02-23 04:04:04,009][11551] Fps is (10 sec: 2869.8, 60 sec: 3686.4, 300 sec: 2891.3). Total num frames: 245760. Throughput: 0: 897.2. Samples: 61072. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 04:04:04,018][11551] Avg episode reward: [(0, '4.608')] | |
| [2023-02-23 04:04:04,027][11811] Saving new best policy, reward=4.608! | |
| [2023-02-23 04:04:09,009][11551] Fps is (10 sec: 3686.6, 60 sec: 3686.4, 300 sec: 2958.2). Total num frames: 266240. Throughput: 0: 942.0. Samples: 67820. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-23 04:04:09,015][11551] Avg episode reward: [(0, '4.596')] | |
| [2023-02-23 04:04:12,761][11832] Updated weights for policy 0, policy_version 70 (0.0012) | |
| [2023-02-23 04:04:14,009][11551] Fps is (10 sec: 4096.1, 60 sec: 3618.1, 300 sec: 3018.1). Total num frames: 286720. Throughput: 0: 941.2. Samples: 71196. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 04:04:14,013][11551] Avg episode reward: [(0, '4.421')] | |
| [2023-02-23 04:04:14,027][11811] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000070_286720.pth... | |
| [2023-02-23 04:04:19,009][11551] Fps is (10 sec: 3686.4, 60 sec: 3686.4, 300 sec: 3031.0). Total num frames: 303104. Throughput: 0: 899.6. Samples: 75856. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 04:04:19,012][11551] Avg episode reward: [(0, '4.462')] | |
| [2023-02-23 04:04:24,009][11551] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3042.7). Total num frames: 319488. Throughput: 0: 914.8. Samples: 80854. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 04:04:24,012][11551] Avg episode reward: [(0, '4.449')] | |
| [2023-02-23 04:04:25,152][11832] Updated weights for policy 0, policy_version 80 (0.0018) | |
| [2023-02-23 04:04:29,009][11551] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3127.9). Total num frames: 344064. Throughput: 0: 942.6. Samples: 84206. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 04:04:29,012][11551] Avg episode reward: [(0, '4.473')] | |
| [2023-02-23 04:04:34,012][11551] Fps is (10 sec: 4095.0, 60 sec: 3618.1, 300 sec: 3134.3). Total num frames: 360448. Throughput: 0: 946.1. Samples: 90814. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 04:04:34,021][11551] Avg episode reward: [(0, '4.490')] | |
| [2023-02-23 04:04:35,407][11832] Updated weights for policy 0, policy_version 90 (0.0027) | |
| [2023-02-23 04:04:39,013][11551] Fps is (10 sec: 3275.7, 60 sec: 3686.2, 300 sec: 3140.2). Total num frames: 376832. Throughput: 0: 898.7. Samples: 95146. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-23 04:04:39,017][11551] Avg episode reward: [(0, '4.601')] | |
| [2023-02-23 04:04:44,009][11551] Fps is (10 sec: 3687.3, 60 sec: 3754.8, 300 sec: 3178.5). Total num frames: 397312. Throughput: 0: 904.9. Samples: 97486. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-02-23 04:04:44,017][11551] Avg episode reward: [(0, '4.489')] | |
| [2023-02-23 04:04:46,608][11832] Updated weights for policy 0, policy_version 100 (0.0015) | |
| [2023-02-23 04:04:49,009][11551] Fps is (10 sec: 4097.4, 60 sec: 3754.7, 300 sec: 3213.8). Total num frames: 417792. Throughput: 0: 960.8. Samples: 104310. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 04:04:49,014][11551] Avg episode reward: [(0, '4.511')] | |
| [2023-02-23 04:04:54,009][11551] Fps is (10 sec: 4096.0, 60 sec: 3687.0, 300 sec: 3246.5). Total num frames: 438272. Throughput: 0: 948.4. Samples: 110498. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 04:04:54,017][11551] Avg episode reward: [(0, '4.669')] | |
| [2023-02-23 04:04:54,027][11811] Saving new best policy, reward=4.669! | |
| [2023-02-23 04:04:57,329][11832] Updated weights for policy 0, policy_version 110 (0.0011) | |
| [2023-02-23 04:04:59,009][11551] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3247.5). Total num frames: 454656. Throughput: 0: 921.9. Samples: 112680. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-23 04:04:59,016][11551] Avg episode reward: [(0, '4.499')] | |
| [2023-02-23 04:05:04,009][11551] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3248.6). Total num frames: 471040. Throughput: 0: 921.9. Samples: 117340. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 04:05:04,015][11551] Avg episode reward: [(0, '4.357')] | |
| [2023-02-23 04:05:08,038][11832] Updated weights for policy 0, policy_version 120 (0.0030) | |
| [2023-02-23 04:05:09,009][11551] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3304.1). Total num frames: 495616. Throughput: 0: 964.6. Samples: 124262. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-23 04:05:09,020][11551] Avg episode reward: [(0, '4.395')] | |
| [2023-02-23 04:05:14,009][11551] Fps is (10 sec: 4096.0, 60 sec: 3754.7, 300 sec: 3303.2). Total num frames: 512000. Throughput: 0: 963.2. Samples: 127552. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 04:05:14,014][11551] Avg episode reward: [(0, '4.765')] | |
| [2023-02-23 04:05:14,026][11811] Saving new best policy, reward=4.765! | |
| [2023-02-23 04:05:19,009][11551] Fps is (10 sec: 2867.2, 60 sec: 3686.4, 300 sec: 3276.8). Total num frames: 524288. Throughput: 0: 907.3. Samples: 131640. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 04:05:19,016][11551] Avg episode reward: [(0, '4.846')] | |
| [2023-02-23 04:05:19,030][11811] Saving new best policy, reward=4.846! | |
| [2023-02-23 04:05:20,605][11832] Updated weights for policy 0, policy_version 130 (0.0012) | |
| [2023-02-23 04:05:24,009][11551] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3301.6). Total num frames: 544768. Throughput: 0: 927.3. Samples: 136870. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 04:05:24,017][11551] Avg episode reward: [(0, '4.739')] | |
| [2023-02-23 04:05:29,009][11551] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3325.0). Total num frames: 565248. Throughput: 0: 951.3. Samples: 140296. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 04:05:29,012][11551] Avg episode reward: [(0, '4.574')] | |
| [2023-02-23 04:05:30,118][11832] Updated weights for policy 0, policy_version 140 (0.0026) | |
| [2023-02-23 04:05:34,011][11551] Fps is (10 sec: 4095.1, 60 sec: 3754.7, 300 sec: 3347.0). Total num frames: 585728. Throughput: 0: 939.8. Samples: 146602. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 04:05:34,019][11551] Avg episode reward: [(0, '4.419')] | |
| [2023-02-23 04:05:39,009][11551] Fps is (10 sec: 3686.4, 60 sec: 3754.9, 300 sec: 3345.1). Total num frames: 602112. Throughput: 0: 897.4. Samples: 150880. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-23 04:05:39,015][11551] Avg episode reward: [(0, '4.403')] | |
| [2023-02-23 04:05:42,358][11832] Updated weights for policy 0, policy_version 150 (0.0011) | |
| [2023-02-23 04:05:44,009][11551] Fps is (10 sec: 3277.5, 60 sec: 3686.4, 300 sec: 3343.2). Total num frames: 618496. Throughput: 0: 902.8. Samples: 153304. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-23 04:05:44,015][11551] Avg episode reward: [(0, '4.529')] | |
| [2023-02-23 04:05:49,010][11551] Fps is (10 sec: 4095.9, 60 sec: 3754.6, 300 sec: 3384.6). Total num frames: 643072. Throughput: 0: 951.3. Samples: 160148. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2023-02-23 04:05:49,012][11551] Avg episode reward: [(0, '4.517')] | |
| [2023-02-23 04:05:51,726][11832] Updated weights for policy 0, policy_version 160 (0.0021) | |
| [2023-02-23 04:05:54,011][11551] Fps is (10 sec: 4095.3, 60 sec: 3686.3, 300 sec: 3381.8). Total num frames: 659456. Throughput: 0: 924.2. Samples: 165854. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 04:05:54,019][11551] Avg episode reward: [(0, '4.337')] | |
| [2023-02-23 04:05:59,009][11551] Fps is (10 sec: 3276.9, 60 sec: 3686.4, 300 sec: 3379.2). Total num frames: 675840. Throughput: 0: 898.4. Samples: 167978. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2023-02-23 04:05:59,018][11551] Avg episode reward: [(0, '4.470')] | |
| [2023-02-23 04:06:04,009][11551] Fps is (10 sec: 3277.3, 60 sec: 3686.4, 300 sec: 3376.7). Total num frames: 692224. Throughput: 0: 914.5. Samples: 172794. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 04:06:04,018][11551] Avg episode reward: [(0, '4.370')] | |
| [2023-02-23 04:06:04,611][11832] Updated weights for policy 0, policy_version 170 (0.0021) | |
| [2023-02-23 04:06:09,010][11551] Fps is (10 sec: 3686.2, 60 sec: 3618.1, 300 sec: 3393.8). Total num frames: 712704. Throughput: 0: 946.0. Samples: 179442. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2023-02-23 04:06:09,012][11551] Avg episode reward: [(0, '4.321')] | |
| [2023-02-23 04:06:14,010][11551] Fps is (10 sec: 4095.9, 60 sec: 3686.4, 300 sec: 3410.2). Total num frames: 733184. Throughput: 0: 935.2. Samples: 182382. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2023-02-23 04:06:14,014][11551] Avg episode reward: [(0, '4.526')] | |
| [2023-02-23 04:06:14,030][11811] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000179_733184.pth... | |
| [2023-02-23 04:06:15,138][11832] Updated weights for policy 0, policy_version 180 (0.0015) | |
| [2023-02-23 04:06:19,009][11551] Fps is (10 sec: 3276.9, 60 sec: 3686.4, 300 sec: 3388.5). Total num frames: 745472. Throughput: 0: 890.5. Samples: 186674. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-23 04:06:19,014][11551] Avg episode reward: [(0, '4.785')] | |
| [2023-02-23 04:06:24,009][11551] Fps is (10 sec: 3276.9, 60 sec: 3686.4, 300 sec: 3404.2). Total num frames: 765952. Throughput: 0: 922.9. Samples: 192410. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 04:06:24,016][11551] Avg episode reward: [(0, '5.094')] | |
| [2023-02-23 04:06:24,027][11811] Saving new best policy, reward=5.094! | |
| [2023-02-23 04:06:26,016][11832] Updated weights for policy 0, policy_version 190 (0.0018) | |
| [2023-02-23 04:06:29,009][11551] Fps is (10 sec: 4505.6, 60 sec: 3754.7, 300 sec: 3437.1). Total num frames: 790528. Throughput: 0: 945.5. Samples: 195852. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 04:06:29,014][11551] Avg episode reward: [(0, '5.132')] | |
| [2023-02-23 04:06:29,017][11811] Saving new best policy, reward=5.132! | |
| [2023-02-23 04:06:34,010][11551] Fps is (10 sec: 4095.9, 60 sec: 3686.5, 300 sec: 3433.7). Total num frames: 806912. Throughput: 0: 922.9. Samples: 201680. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-23 04:06:34,015][11551] Avg episode reward: [(0, '4.982')] | |
| [2023-02-23 04:06:37,933][11832] Updated weights for policy 0, policy_version 200 (0.0026) | |
| [2023-02-23 04:06:39,009][11551] Fps is (10 sec: 2867.2, 60 sec: 3618.1, 300 sec: 3413.3). Total num frames: 819200. Throughput: 0: 891.6. Samples: 205976. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 04:06:39,011][11551] Avg episode reward: [(0, '4.767')] | |
| [2023-02-23 04:06:44,009][11551] Fps is (10 sec: 3276.9, 60 sec: 3686.4, 300 sec: 3427.3). Total num frames: 839680. Throughput: 0: 907.0. Samples: 208792. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2023-02-23 04:06:44,016][11551] Avg episode reward: [(0, '4.747')] | |
| [2023-02-23 04:06:47,821][11832] Updated weights for policy 0, policy_version 210 (0.0015) | |
| [2023-02-23 04:06:49,009][11551] Fps is (10 sec: 4505.6, 60 sec: 3686.4, 300 sec: 3457.0). Total num frames: 864256. Throughput: 0: 951.7. Samples: 215620. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 04:06:49,012][11551] Avg episode reward: [(0, '5.141')] | |
| [2023-02-23 04:06:49,017][11811] Saving new best policy, reward=5.141! | |
| [2023-02-23 04:06:54,009][11551] Fps is (10 sec: 4095.9, 60 sec: 3686.5, 300 sec: 3453.5). Total num frames: 880640. Throughput: 0: 922.1. Samples: 220936. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) | |
| [2023-02-23 04:06:54,020][11551] Avg episode reward: [(0, '5.086')] | |
| [2023-02-23 04:06:59,009][11551] Fps is (10 sec: 2867.2, 60 sec: 3618.1, 300 sec: 3434.3). Total num frames: 892928. Throughput: 0: 904.4. Samples: 223082. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 04:06:59,015][11551] Avg episode reward: [(0, '4.689')] | |
| [2023-02-23 04:07:00,463][11832] Updated weights for policy 0, policy_version 220 (0.0019) | |
| [2023-02-23 04:07:04,010][11551] Fps is (10 sec: 3686.4, 60 sec: 3754.6, 300 sec: 3462.3). Total num frames: 917504. Throughput: 0: 929.2. Samples: 228490. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2023-02-23 04:07:04,011][11551] Avg episode reward: [(0, '4.650')] | |
| [2023-02-23 04:07:09,009][11551] Fps is (10 sec: 4505.6, 60 sec: 3754.7, 300 sec: 3474.0). Total num frames: 937984. Throughput: 0: 955.6. Samples: 235414. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 04:07:09,012][11551] Avg episode reward: [(0, '5.085')] | |
| [2023-02-23 04:07:09,348][11832] Updated weights for policy 0, policy_version 230 (0.0014) | |
| [2023-02-23 04:07:14,010][11551] Fps is (10 sec: 3686.3, 60 sec: 3686.4, 300 sec: 3470.4). Total num frames: 954368. Throughput: 0: 939.3. Samples: 238122. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 04:07:14,013][11551] Avg episode reward: [(0, '5.068')] | |
| [2023-02-23 04:07:19,011][11551] Fps is (10 sec: 3276.3, 60 sec: 3754.6, 300 sec: 3467.0). Total num frames: 970752. Throughput: 0: 906.6. Samples: 242478. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 04:07:19,014][11551] Avg episode reward: [(0, '5.151')] | |
| [2023-02-23 04:07:19,018][11811] Saving new best policy, reward=5.151! | |
| [2023-02-23 04:07:21,856][11832] Updated weights for policy 0, policy_version 240 (0.0014) | |
| [2023-02-23 04:07:24,009][11551] Fps is (10 sec: 3686.6, 60 sec: 3754.7, 300 sec: 3478.0). Total num frames: 991232. Throughput: 0: 948.3. Samples: 248650. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 04:07:24,013][11551] Avg episode reward: [(0, '5.069')] | |
| [2023-02-23 04:07:29,009][11551] Fps is (10 sec: 4096.7, 60 sec: 3686.4, 300 sec: 3488.7). Total num frames: 1011712. Throughput: 0: 961.8. Samples: 252072. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-02-23 04:07:29,016][11551] Avg episode reward: [(0, '5.310')] | |
| [2023-02-23 04:07:29,075][11811] Saving new best policy, reward=5.310! | |
| [2023-02-23 04:07:31,408][11832] Updated weights for policy 0, policy_version 250 (0.0023) | |
| [2023-02-23 04:07:34,013][11551] Fps is (10 sec: 3685.2, 60 sec: 3686.2, 300 sec: 3485.0). Total num frames: 1028096. Throughput: 0: 930.9. Samples: 257514. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 04:07:34,016][11551] Avg episode reward: [(0, '5.255')] | |
| [2023-02-23 04:07:39,009][11551] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3540.6). Total num frames: 1044480. Throughput: 0: 908.8. Samples: 261830. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 04:07:39,015][11551] Avg episode reward: [(0, '5.015')] | |
| [2023-02-23 04:07:43,436][11832] Updated weights for policy 0, policy_version 260 (0.0034) | |
| [2023-02-23 04:07:44,009][11551] Fps is (10 sec: 3687.6, 60 sec: 3754.7, 300 sec: 3610.0). Total num frames: 1064960. Throughput: 0: 928.7. Samples: 264874. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 04:07:44,017][11551] Avg episode reward: [(0, '5.246')] | |
| [2023-02-23 04:07:49,009][11551] Fps is (10 sec: 4505.6, 60 sec: 3754.7, 300 sec: 3693.3). Total num frames: 1089536. Throughput: 0: 964.0. Samples: 271870. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 04:07:49,014][11551] Avg episode reward: [(0, '5.272')] | |
| [2023-02-23 04:07:53,899][11832] Updated weights for policy 0, policy_version 270 (0.0020) | |
| [2023-02-23 04:07:54,009][11551] Fps is (10 sec: 4096.0, 60 sec: 3754.7, 300 sec: 3735.0). Total num frames: 1105920. Throughput: 0: 923.9. Samples: 276990. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-23 04:07:54,015][11551] Avg episode reward: [(0, '5.053')] | |
| [2023-02-23 04:07:59,009][11551] Fps is (10 sec: 2867.2, 60 sec: 3754.7, 300 sec: 3707.2). Total num frames: 1118208. Throughput: 0: 911.5. Samples: 279138. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 04:07:59,015][11551] Avg episode reward: [(0, '5.147')] | |
| [2023-02-23 04:08:04,009][11551] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3707.2). Total num frames: 1138688. Throughput: 0: 943.5. Samples: 284936. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 04:08:04,018][11551] Avg episode reward: [(0, '5.415')] | |
| [2023-02-23 04:08:04,028][11811] Saving new best policy, reward=5.415! | |
| [2023-02-23 04:08:05,069][11832] Updated weights for policy 0, policy_version 280 (0.0028) | |
| [2023-02-23 04:08:09,009][11551] Fps is (10 sec: 4505.6, 60 sec: 3754.7, 300 sec: 3707.2). Total num frames: 1163264. Throughput: 0: 955.8. Samples: 291660. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 04:08:09,016][11551] Avg episode reward: [(0, '5.624')] | |
| [2023-02-23 04:08:09,024][11811] Saving new best policy, reward=5.624! | |
| [2023-02-23 04:08:14,009][11551] Fps is (10 sec: 3686.4, 60 sec: 3686.4, 300 sec: 3707.2). Total num frames: 1175552. Throughput: 0: 930.9. Samples: 293962. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2023-02-23 04:08:14,012][11551] Avg episode reward: [(0, '5.772')] | |
| [2023-02-23 04:08:14,058][11811] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000288_1179648.pth... | |
| [2023-02-23 04:08:14,288][11811] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000070_286720.pth | |
| [2023-02-23 04:08:14,316][11811] Saving new best policy, reward=5.772! | |
| [2023-02-23 04:08:17,118][11832] Updated weights for policy 0, policy_version 290 (0.0016) | |
| [2023-02-23 04:08:19,010][11551] Fps is (10 sec: 2867.0, 60 sec: 3686.5, 300 sec: 3707.2). Total num frames: 1191936. Throughput: 0: 903.6. Samples: 298174. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 04:08:19,014][11551] Avg episode reward: [(0, '5.790')] | |
| [2023-02-23 04:08:19,017][11811] Saving new best policy, reward=5.790! | |
| [2023-02-23 04:08:24,009][11551] Fps is (10 sec: 4096.0, 60 sec: 3754.7, 300 sec: 3707.2). Total num frames: 1216512. Throughput: 0: 947.1. Samples: 304450. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2023-02-23 04:08:24,011][11551] Avg episode reward: [(0, '5.929')] | |
| [2023-02-23 04:08:24,023][11811] Saving new best policy, reward=5.929! | |
| [2023-02-23 04:08:26,739][11832] Updated weights for policy 0, policy_version 300 (0.0017) | |
| [2023-02-23 04:08:29,009][11551] Fps is (10 sec: 4506.0, 60 sec: 3754.7, 300 sec: 3707.3). Total num frames: 1236992. Throughput: 0: 953.5. Samples: 307780. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 04:08:29,012][11551] Avg episode reward: [(0, '6.422')] | |
| [2023-02-23 04:08:29,015][11811] Saving new best policy, reward=6.422! | |
| [2023-02-23 04:08:34,010][11551] Fps is (10 sec: 3276.7, 60 sec: 3686.6, 300 sec: 3707.2). Total num frames: 1249280. Throughput: 0: 911.7. Samples: 312898. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-23 04:08:34,019][11551] Avg episode reward: [(0, '6.387')] | |
| [2023-02-23 04:08:39,009][11551] Fps is (10 sec: 2867.2, 60 sec: 3686.4, 300 sec: 3707.2). Total num frames: 1265664. Throughput: 0: 891.9. Samples: 317126. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-02-23 04:08:39,017][11551] Avg episode reward: [(0, '6.363')] | |
| [2023-02-23 04:08:39,713][11832] Updated weights for policy 0, policy_version 310 (0.0012) | |
| [2023-02-23 04:08:44,009][11551] Fps is (10 sec: 3686.6, 60 sec: 3686.4, 300 sec: 3707.2). Total num frames: 1286144. Throughput: 0: 916.5. Samples: 320382. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-23 04:08:44,012][11551] Avg episode reward: [(0, '5.953')] | |
| [2023-02-23 04:08:48,612][11832] Updated weights for policy 0, policy_version 320 (0.0022) | |
| [2023-02-23 04:08:49,009][11551] Fps is (10 sec: 4505.6, 60 sec: 3686.4, 300 sec: 3707.3). Total num frames: 1310720. Throughput: 0: 942.7. Samples: 327356. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 04:08:49,011][11551] Avg episode reward: [(0, '6.551')] | |
| [2023-02-23 04:08:49,018][11811] Saving new best policy, reward=6.551! | |
| [2023-02-23 04:08:54,009][11551] Fps is (10 sec: 4095.9, 60 sec: 3686.4, 300 sec: 3721.1). Total num frames: 1327104. Throughput: 0: 905.3. Samples: 332400. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 04:08:54,012][11551] Avg episode reward: [(0, '6.668')] | |
| [2023-02-23 04:08:54,032][11811] Saving new best policy, reward=6.668! | |
| [2023-02-23 04:08:59,009][11551] Fps is (10 sec: 2867.2, 60 sec: 3686.4, 300 sec: 3707.2). Total num frames: 1339392. Throughput: 0: 899.8. Samples: 334452. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-02-23 04:08:59,016][11551] Avg episode reward: [(0, '6.824')] | |
| [2023-02-23 04:08:59,018][11811] Saving new best policy, reward=6.824! | |
| [2023-02-23 04:09:00,935][11832] Updated weights for policy 0, policy_version 330 (0.0012) | |
| [2023-02-23 04:09:04,009][11551] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3721.1). Total num frames: 1363968. Throughput: 0: 945.0. Samples: 340698. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-23 04:09:04,011][11551] Avg episode reward: [(0, '6.584')] | |
| [2023-02-23 04:09:09,010][11551] Fps is (10 sec: 4505.3, 60 sec: 3686.4, 300 sec: 3721.1). Total num frames: 1384448. Throughput: 0: 955.5. Samples: 347446. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 04:09:09,017][11551] Avg episode reward: [(0, '6.766')] | |
| [2023-02-23 04:09:10,585][11832] Updated weights for policy 0, policy_version 340 (0.0011) | |
| [2023-02-23 04:09:14,009][11551] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3721.1). Total num frames: 1400832. Throughput: 0: 930.1. Samples: 349636. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-02-23 04:09:14,016][11551] Avg episode reward: [(0, '6.706')] | |
| [2023-02-23 04:09:19,011][11551] Fps is (10 sec: 3277.0, 60 sec: 3754.7, 300 sec: 3721.1). Total num frames: 1417216. Throughput: 0: 917.7. Samples: 354194. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-23 04:09:19,016][11551] Avg episode reward: [(0, '6.751')] | |
| [2023-02-23 04:09:22,010][11832] Updated weights for policy 0, policy_version 350 (0.0021) | |
| [2023-02-23 04:09:24,009][11551] Fps is (10 sec: 4096.0, 60 sec: 3754.7, 300 sec: 3721.1). Total num frames: 1441792. Throughput: 0: 973.6. Samples: 360936. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 04:09:24,012][11551] Avg episode reward: [(0, '6.798')] | |
| [2023-02-23 04:09:29,009][11551] Fps is (10 sec: 4505.6, 60 sec: 3754.7, 300 sec: 3735.0). Total num frames: 1462272. Throughput: 0: 978.5. Samples: 364416. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 04:09:29,013][11551] Avg episode reward: [(0, '7.056')] | |
| [2023-02-23 04:09:29,017][11811] Saving new best policy, reward=7.056! | |
| [2023-02-23 04:09:32,482][11832] Updated weights for policy 0, policy_version 360 (0.0020) | |
| [2023-02-23 04:09:34,009][11551] Fps is (10 sec: 3686.4, 60 sec: 3823.0, 300 sec: 3735.0). Total num frames: 1478656. Throughput: 0: 933.4. Samples: 369360. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-23 04:09:34,012][11551] Avg episode reward: [(0, '7.066')] | |
| [2023-02-23 04:09:34,028][11811] Saving new best policy, reward=7.066! | |
| [2023-02-23 04:09:39,009][11551] Fps is (10 sec: 3276.8, 60 sec: 3822.9, 300 sec: 3721.1). Total num frames: 1495040. Throughput: 0: 924.5. Samples: 374002. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2023-02-23 04:09:39,017][11551] Avg episode reward: [(0, '7.623')] | |
| [2023-02-23 04:09:39,020][11811] Saving new best policy, reward=7.623! | |
| [2023-02-23 04:09:43,555][11832] Updated weights for policy 0, policy_version 370 (0.0018) | |
| [2023-02-23 04:09:44,009][11551] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3721.1). Total num frames: 1515520. Throughput: 0: 954.2. Samples: 377392. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 04:09:44,012][11551] Avg episode reward: [(0, '8.601')] | |
| [2023-02-23 04:09:44,026][11811] Saving new best policy, reward=8.601! | |
| [2023-02-23 04:09:49,009][11551] Fps is (10 sec: 4096.0, 60 sec: 3754.7, 300 sec: 3721.1). Total num frames: 1536000. Throughput: 0: 971.0. Samples: 384394. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 04:09:49,014][11551] Avg episode reward: [(0, '9.014')] | |
| [2023-02-23 04:09:49,018][11811] Saving new best policy, reward=9.014! | |
| [2023-02-23 04:09:54,009][11551] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3721.1). Total num frames: 1552384. Throughput: 0: 922.3. Samples: 388950. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 04:09:54,011][11551] Avg episode reward: [(0, '9.762')] | |
| [2023-02-23 04:09:54,027][11811] Saving new best policy, reward=9.762! | |
| [2023-02-23 04:09:54,884][11832] Updated weights for policy 0, policy_version 380 (0.0011) | |
| [2023-02-23 04:09:59,009][11551] Fps is (10 sec: 3276.8, 60 sec: 3822.9, 300 sec: 3721.1). Total num frames: 1568768. Throughput: 0: 921.0. Samples: 391082. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 04:09:59,016][11551] Avg episode reward: [(0, '9.239')] | |
| [2023-02-23 04:10:04,009][11551] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3721.1). Total num frames: 1593344. Throughput: 0: 967.4. Samples: 397728. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 04:10:04,011][11551] Avg episode reward: [(0, '10.111')] | |
| [2023-02-23 04:10:04,022][11811] Saving new best policy, reward=10.111! | |
| [2023-02-23 04:10:04,776][11832] Updated weights for policy 0, policy_version 390 (0.0014) | |
| [2023-02-23 04:10:09,009][11551] Fps is (10 sec: 4505.6, 60 sec: 3823.0, 300 sec: 3735.0). Total num frames: 1613824. Throughput: 0: 957.4. Samples: 404018. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 04:10:09,018][11551] Avg episode reward: [(0, '10.131')] | |
| [2023-02-23 04:10:09,020][11811] Saving new best policy, reward=10.131! | |
| [2023-02-23 04:10:14,019][11551] Fps is (10 sec: 3275.5, 60 sec: 3754.4, 300 sec: 3734.9). Total num frames: 1626112. Throughput: 0: 927.3. Samples: 406148. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 04:10:14,025][11551] Avg episode reward: [(0, '10.314')] | |
| [2023-02-23 04:10:14,040][11811] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000397_1626112.pth... | |
| [2023-02-23 04:10:14,164][11811] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000179_733184.pth | |
| [2023-02-23 04:10:14,182][11811] Saving new best policy, reward=10.314! | |
| [2023-02-23 04:10:17,301][11832] Updated weights for policy 0, policy_version 400 (0.0023) | |
| [2023-02-23 04:10:19,009][11551] Fps is (10 sec: 2867.2, 60 sec: 3754.7, 300 sec: 3721.1). Total num frames: 1642496. Throughput: 0: 917.6. Samples: 410650. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-23 04:10:19,012][11551] Avg episode reward: [(0, '10.032')] | |
| [2023-02-23 04:10:24,009][11551] Fps is (10 sec: 4097.6, 60 sec: 3754.7, 300 sec: 3735.0). Total num frames: 1667072. Throughput: 0: 970.3. Samples: 417664. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 04:10:24,012][11551] Avg episode reward: [(0, '9.771')] | |
| [2023-02-23 04:10:26,206][11832] Updated weights for policy 0, policy_version 410 (0.0015) | |
| [2023-02-23 04:10:29,010][11551] Fps is (10 sec: 4505.3, 60 sec: 3754.6, 300 sec: 3735.0). Total num frames: 1687552. Throughput: 0: 971.9. Samples: 421126. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 04:10:29,013][11551] Avg episode reward: [(0, '9.812')] | |
| [2023-02-23 04:10:34,009][11551] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3735.0). Total num frames: 1703936. Throughput: 0: 919.1. Samples: 425752. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-02-23 04:10:34,012][11551] Avg episode reward: [(0, '10.145')] | |
| [2023-02-23 04:10:38,562][11832] Updated weights for policy 0, policy_version 420 (0.0026) | |
| [2023-02-23 04:10:39,009][11551] Fps is (10 sec: 3277.0, 60 sec: 3754.7, 300 sec: 3735.0). Total num frames: 1720320. Throughput: 0: 931.9. Samples: 430886. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 04:10:39,012][11551] Avg episode reward: [(0, '10.105')] | |
| [2023-02-23 04:10:44,009][11551] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3735.0). Total num frames: 1744896. Throughput: 0: 961.3. Samples: 434340. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 04:10:44,011][11551] Avg episode reward: [(0, '9.671')] | |
| [2023-02-23 04:10:47,423][11832] Updated weights for policy 0, policy_version 430 (0.0020) | |
| [2023-02-23 04:10:49,010][11551] Fps is (10 sec: 4505.4, 60 sec: 3822.9, 300 sec: 3748.9). Total num frames: 1765376. Throughput: 0: 964.7. Samples: 441140. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 04:10:49,017][11551] Avg episode reward: [(0, '8.907')] | |
| [2023-02-23 04:10:54,009][11551] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3735.0). Total num frames: 1777664. Throughput: 0: 921.7. Samples: 445496. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 04:10:54,013][11551] Avg episode reward: [(0, '9.446')] | |
| [2023-02-23 04:10:59,009][11551] Fps is (10 sec: 3276.9, 60 sec: 3822.9, 300 sec: 3748.9). Total num frames: 1798144. Throughput: 0: 924.7. Samples: 447756. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 04:10:59,012][11551] Avg episode reward: [(0, '9.621')] | |
| [2023-02-23 04:10:59,761][11832] Updated weights for policy 0, policy_version 440 (0.0028) | |
| [2023-02-23 04:11:04,009][11551] Fps is (10 sec: 4096.0, 60 sec: 3754.7, 300 sec: 3748.9). Total num frames: 1818624. Throughput: 0: 979.3. Samples: 454718. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-23 04:11:04,014][11551] Avg episode reward: [(0, '10.627')] | |
| [2023-02-23 04:11:04,023][11811] Saving new best policy, reward=10.627! | |
| [2023-02-23 04:11:09,009][11551] Fps is (10 sec: 4096.0, 60 sec: 3754.7, 300 sec: 3748.9). Total num frames: 1839104. Throughput: 0: 953.9. Samples: 460590. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 04:11:09,011][11551] Avg episode reward: [(0, '10.816')] | |
| [2023-02-23 04:11:09,017][11811] Saving new best policy, reward=10.816! | |
| [2023-02-23 04:11:09,992][11832] Updated weights for policy 0, policy_version 450 (0.0026) | |
| [2023-02-23 04:11:14,014][11551] Fps is (10 sec: 3684.7, 60 sec: 3822.9, 300 sec: 3762.7). Total num frames: 1855488. Throughput: 0: 926.7. Samples: 462830. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 04:11:14,020][11551] Avg episode reward: [(0, '11.028')] | |
| [2023-02-23 04:11:14,033][11811] Saving new best policy, reward=11.028! | |
| [2023-02-23 04:11:19,009][11551] Fps is (10 sec: 3276.8, 60 sec: 3822.9, 300 sec: 3748.9). Total num frames: 1871872. Throughput: 0: 932.5. Samples: 467716. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-02-23 04:11:19,018][11551] Avg episode reward: [(0, '10.832')] | |
| [2023-02-23 04:11:21,111][11832] Updated weights for policy 0, policy_version 460 (0.0027) | |
| [2023-02-23 04:11:24,009][11551] Fps is (10 sec: 4097.9, 60 sec: 3822.9, 300 sec: 3748.9). Total num frames: 1896448. Throughput: 0: 972.2. Samples: 474634. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-23 04:11:24,011][11551] Avg episode reward: [(0, '9.691')] | |
| [2023-02-23 04:11:29,009][11551] Fps is (10 sec: 4505.6, 60 sec: 3823.0, 300 sec: 3762.8). Total num frames: 1916928. Throughput: 0: 975.1. Samples: 478220. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 04:11:29,015][11551] Avg episode reward: [(0, '10.448')] | |
| [2023-02-23 04:11:31,687][11832] Updated weights for policy 0, policy_version 470 (0.0016) | |
| [2023-02-23 04:11:34,009][11551] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3762.8). Total num frames: 1929216. Throughput: 0: 921.1. Samples: 482590. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 04:11:34,016][11551] Avg episode reward: [(0, '10.818')] | |
| [2023-02-23 04:11:39,009][11551] Fps is (10 sec: 3276.8, 60 sec: 3822.9, 300 sec: 3762.8). Total num frames: 1949696. Throughput: 0: 942.5. Samples: 487910. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 04:11:39,016][11551] Avg episode reward: [(0, '11.868')] | |
| [2023-02-23 04:11:39,021][11811] Saving new best policy, reward=11.868! | |
| [2023-02-23 04:11:42,469][11832] Updated weights for policy 0, policy_version 480 (0.0012) | |
| [2023-02-23 04:11:44,009][11551] Fps is (10 sec: 4096.0, 60 sec: 3754.7, 300 sec: 3748.9). Total num frames: 1970176. Throughput: 0: 967.6. Samples: 491300. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 04:11:44,013][11551] Avg episode reward: [(0, '13.445')] | |
| [2023-02-23 04:11:44,027][11811] Saving new best policy, reward=13.445! | |
| [2023-02-23 04:11:49,009][11551] Fps is (10 sec: 4096.0, 60 sec: 3754.7, 300 sec: 3762.8). Total num frames: 1990656. Throughput: 0: 952.0. Samples: 497560. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-23 04:11:49,019][11551] Avg episode reward: [(0, '14.001')] | |
| [2023-02-23 04:11:49,021][11811] Saving new best policy, reward=14.001! | |
| [2023-02-23 04:11:54,009][11551] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3762.8). Total num frames: 2002944. Throughput: 0: 918.1. Samples: 501904. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 04:11:54,012][11551] Avg episode reward: [(0, '14.239')] | |
| [2023-02-23 04:11:54,034][11811] Saving new best policy, reward=14.239! | |
| [2023-02-23 04:11:54,455][11832] Updated weights for policy 0, policy_version 490 (0.0020) | |
| [2023-02-23 04:11:59,010][11551] Fps is (10 sec: 3276.7, 60 sec: 3754.6, 300 sec: 3748.9). Total num frames: 2023424. Throughput: 0: 925.9. Samples: 504490. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 04:11:59,012][11551] Avg episode reward: [(0, '13.411')] | |
| [2023-02-23 04:12:03,687][11832] Updated weights for policy 0, policy_version 500 (0.0018) | |
| [2023-02-23 04:12:04,009][11551] Fps is (10 sec: 4505.5, 60 sec: 3822.9, 300 sec: 3762.8). Total num frames: 2048000. Throughput: 0: 971.5. Samples: 511432. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-23 04:12:04,012][11551] Avg episode reward: [(0, '12.144')] | |
| [2023-02-23 04:12:09,013][11551] Fps is (10 sec: 4094.7, 60 sec: 3754.5, 300 sec: 3762.7). Total num frames: 2064384. Throughput: 0: 947.1. Samples: 517258. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2023-02-23 04:12:09,020][11551] Avg episode reward: [(0, '13.689')] | |
| [2023-02-23 04:12:14,009][11551] Fps is (10 sec: 3276.8, 60 sec: 3754.9, 300 sec: 3762.8). Total num frames: 2080768. Throughput: 0: 915.4. Samples: 519414. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 04:12:14,017][11551] Avg episode reward: [(0, '13.292')] | |
| [2023-02-23 04:12:14,030][11811] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000508_2080768.pth... | |
| [2023-02-23 04:12:14,204][11811] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000288_1179648.pth | |
| [2023-02-23 04:12:16,080][11832] Updated weights for policy 0, policy_version 510 (0.0013) | |
| [2023-02-23 04:12:19,009][11551] Fps is (10 sec: 3687.7, 60 sec: 3822.9, 300 sec: 3762.8). Total num frames: 2101248. Throughput: 0: 937.0. Samples: 524756. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 04:12:19,011][11551] Avg episode reward: [(0, '14.397')] | |
| [2023-02-23 04:12:19,018][11811] Saving new best policy, reward=14.397! | |
| [2023-02-23 04:12:24,009][11551] Fps is (10 sec: 4096.0, 60 sec: 3754.7, 300 sec: 3762.8). Total num frames: 2121728. Throughput: 0: 971.3. Samples: 531620. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 04:12:24,012][11551] Avg episode reward: [(0, '16.370')] | |
| [2023-02-23 04:12:24,027][11811] Saving new best policy, reward=16.370! | |
| [2023-02-23 04:12:25,148][11832] Updated weights for policy 0, policy_version 520 (0.0014) | |
| [2023-02-23 04:12:29,011][11551] Fps is (10 sec: 4095.2, 60 sec: 3754.6, 300 sec: 3776.7). Total num frames: 2142208. Throughput: 0: 960.2. Samples: 534510. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 04:12:29,015][11551] Avg episode reward: [(0, '16.712')] | |
| [2023-02-23 04:12:29,017][11811] Saving new best policy, reward=16.712! | |
| [2023-02-23 04:12:34,011][11551] Fps is (10 sec: 3276.3, 60 sec: 3754.6, 300 sec: 3762.7). Total num frames: 2154496. Throughput: 0: 918.1. Samples: 538876. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 04:12:34,014][11551] Avg episode reward: [(0, '16.264')] | |
| [2023-02-23 04:12:37,350][11832] Updated weights for policy 0, policy_version 530 (0.0011) | |
| [2023-02-23 04:12:39,009][11551] Fps is (10 sec: 3687.1, 60 sec: 3822.9, 300 sec: 3776.7). Total num frames: 2179072. Throughput: 0: 957.6. Samples: 544996. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 04:12:39,011][11551] Avg episode reward: [(0, '16.014')] | |
| [2023-02-23 04:12:44,009][11551] Fps is (10 sec: 4506.4, 60 sec: 3822.9, 300 sec: 3762.8). Total num frames: 2199552. Throughput: 0: 977.1. Samples: 548460. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 04:12:44,012][11551] Avg episode reward: [(0, '15.241')] | |
| [2023-02-23 04:12:46,779][11832] Updated weights for policy 0, policy_version 540 (0.0014) | |
| [2023-02-23 04:12:49,015][11551] Fps is (10 sec: 3684.4, 60 sec: 3754.3, 300 sec: 3762.7). Total num frames: 2215936. Throughput: 0: 952.5. Samples: 554298. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 04:12:49,020][11551] Avg episode reward: [(0, '15.252')] | |
| [2023-02-23 04:12:54,009][11551] Fps is (10 sec: 3276.8, 60 sec: 3822.9, 300 sec: 3776.7). Total num frames: 2232320. Throughput: 0: 921.9. Samples: 558740. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 04:12:54,012][11551] Avg episode reward: [(0, '15.968')] | |
| [2023-02-23 04:12:58,312][11832] Updated weights for policy 0, policy_version 550 (0.0016) | |
| [2023-02-23 04:12:59,009][11551] Fps is (10 sec: 3688.4, 60 sec: 3823.0, 300 sec: 3776.7). Total num frames: 2252800. Throughput: 0: 944.0. Samples: 561892. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 04:12:59,012][11551] Avg episode reward: [(0, '17.512')] | |
| [2023-02-23 04:12:59,014][11811] Saving new best policy, reward=17.512! | |
| [2023-02-23 04:13:04,009][11551] Fps is (10 sec: 4505.6, 60 sec: 3822.9, 300 sec: 3776.7). Total num frames: 2277376. Throughput: 0: 976.6. Samples: 568702. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 04:13:04,011][11551] Avg episode reward: [(0, '17.905')] | |
| [2023-02-23 04:13:04,024][11811] Saving new best policy, reward=17.905! | |
| [2023-02-23 04:13:09,014][11551] Fps is (10 sec: 3684.8, 60 sec: 3754.6, 300 sec: 3776.6). Total num frames: 2289664. Throughput: 0: 938.9. Samples: 573876. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 04:13:09,016][11551] Avg episode reward: [(0, '18.607')] | |
| [2023-02-23 04:13:09,099][11811] Saving new best policy, reward=18.607! | |
| [2023-02-23 04:13:09,123][11832] Updated weights for policy 0, policy_version 560 (0.0018) | |
| [2023-02-23 04:13:14,010][11551] Fps is (10 sec: 2867.0, 60 sec: 3754.6, 300 sec: 3776.7). Total num frames: 2306048. Throughput: 0: 919.7. Samples: 575896. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-02-23 04:13:14,017][11551] Avg episode reward: [(0, '18.440')] | |
| [2023-02-23 04:13:19,009][11551] Fps is (10 sec: 3688.0, 60 sec: 3754.7, 300 sec: 3762.8). Total num frames: 2326528. Throughput: 0: 950.4. Samples: 581642. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2023-02-23 04:13:19,017][11551] Avg episode reward: [(0, '17.146')] | |
| [2023-02-23 04:13:20,111][11832] Updated weights for policy 0, policy_version 570 (0.0012) | |
| [2023-02-23 04:13:24,009][11551] Fps is (10 sec: 4505.9, 60 sec: 3822.9, 300 sec: 3776.6). Total num frames: 2351104. Throughput: 0: 972.3. Samples: 588750. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 04:13:24,018][11551] Avg episode reward: [(0, '15.682')] | |
| [2023-02-23 04:13:29,016][11551] Fps is (10 sec: 4093.4, 60 sec: 3754.4, 300 sec: 3790.5). Total num frames: 2367488. Throughput: 0: 951.8. Samples: 591298. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2023-02-23 04:13:29,019][11551] Avg episode reward: [(0, '16.111')] | |
| [2023-02-23 04:13:31,448][11832] Updated weights for policy 0, policy_version 580 (0.0011) | |
| [2023-02-23 04:13:34,009][11551] Fps is (10 sec: 2867.2, 60 sec: 3754.8, 300 sec: 3776.7). Total num frames: 2379776. Throughput: 0: 915.7. Samples: 595498. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 04:13:34,018][11551] Avg episode reward: [(0, '16.064')] | |
| [2023-02-23 04:13:39,009][11551] Fps is (10 sec: 3688.8, 60 sec: 3754.7, 300 sec: 3790.5). Total num frames: 2404352. Throughput: 0: 955.2. Samples: 601724. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-02-23 04:13:39,016][11551] Avg episode reward: [(0, '16.398')] | |
| [2023-02-23 04:13:41,509][11832] Updated weights for policy 0, policy_version 590 (0.0030) | |
| [2023-02-23 04:13:44,009][11551] Fps is (10 sec: 4505.6, 60 sec: 3754.7, 300 sec: 3776.7). Total num frames: 2424832. Throughput: 0: 960.7. Samples: 605124. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2023-02-23 04:13:44,011][11551] Avg episode reward: [(0, '18.472')] | |
| [2023-02-23 04:13:49,009][11551] Fps is (10 sec: 3686.4, 60 sec: 3755.0, 300 sec: 3776.7). Total num frames: 2441216. Throughput: 0: 931.6. Samples: 610622. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-23 04:13:49,012][11551] Avg episode reward: [(0, '18.896')] | |
| [2023-02-23 04:13:49,018][11811] Saving new best policy, reward=18.896! | |
| [2023-02-23 04:13:53,795][11832] Updated weights for policy 0, policy_version 600 (0.0011) | |
| [2023-02-23 04:13:54,011][11551] Fps is (10 sec: 3276.3, 60 sec: 3754.6, 300 sec: 3790.5). Total num frames: 2457600. Throughput: 0: 912.1. Samples: 614920. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-23 04:13:54,016][11551] Avg episode reward: [(0, '18.499')] | |
| [2023-02-23 04:13:59,009][11551] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3776.7). Total num frames: 2478080. Throughput: 0: 944.6. Samples: 618404. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 04:13:59,016][11551] Avg episode reward: [(0, '18.790')] | |
| [2023-02-23 04:14:02,571][11832] Updated weights for policy 0, policy_version 610 (0.0018) | |
| [2023-02-23 04:14:04,009][11551] Fps is (10 sec: 4506.2, 60 sec: 3754.7, 300 sec: 3790.5). Total num frames: 2502656. Throughput: 0: 972.4. Samples: 625400. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 04:14:04,012][11551] Avg episode reward: [(0, '17.524')] | |
| [2023-02-23 04:14:09,009][11551] Fps is (10 sec: 4096.0, 60 sec: 3823.2, 300 sec: 3790.5). Total num frames: 2519040. Throughput: 0: 922.8. Samples: 630276. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-23 04:14:09,014][11551] Avg episode reward: [(0, '18.254')] | |
| [2023-02-23 04:14:14,009][11551] Fps is (10 sec: 2867.2, 60 sec: 3754.7, 300 sec: 3776.6). Total num frames: 2531328. Throughput: 0: 911.5. Samples: 632310. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 04:14:14,011][11551] Avg episode reward: [(0, '17.610')] | |
| [2023-02-23 04:14:14,122][11811] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000619_2535424.pth... | |
| [2023-02-23 04:14:14,243][11811] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000397_1626112.pth | |
| [2023-02-23 04:14:15,114][11832] Updated weights for policy 0, policy_version 620 (0.0032) | |
| [2023-02-23 04:14:19,009][11551] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3776.7). Total num frames: 2555904. Throughput: 0: 956.9. Samples: 638560. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-23 04:14:19,011][11551] Avg episode reward: [(0, '17.505')] | |
| [2023-02-23 04:14:24,009][11551] Fps is (10 sec: 4505.6, 60 sec: 3754.7, 300 sec: 3776.7). Total num frames: 2576384. Throughput: 0: 969.2. Samples: 645340. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 04:14:24,017][11551] Avg episode reward: [(0, '17.429')] | |
| [2023-02-23 04:14:24,043][11832] Updated weights for policy 0, policy_version 630 (0.0023) | |
| [2023-02-23 04:14:29,009][11551] Fps is (10 sec: 3686.4, 60 sec: 3755.1, 300 sec: 3776.7). Total num frames: 2592768. Throughput: 0: 943.8. Samples: 647594. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-23 04:14:29,016][11551] Avg episode reward: [(0, '18.708')] | |
| [2023-02-23 04:14:34,009][11551] Fps is (10 sec: 3276.8, 60 sec: 3822.9, 300 sec: 3776.7). Total num frames: 2609152. Throughput: 0: 918.7. Samples: 651964. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-23 04:14:34,011][11551] Avg episode reward: [(0, '18.433')] | |
| [2023-02-23 04:14:36,247][11832] Updated weights for policy 0, policy_version 640 (0.0020) | |
| [2023-02-23 04:14:39,009][11551] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3790.5). Total num frames: 2633728. Throughput: 0: 979.4. Samples: 658992. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 04:14:39,012][11551] Avg episode reward: [(0, '19.486')] | |
| [2023-02-23 04:14:39,016][11811] Saving new best policy, reward=19.486! | |
| [2023-02-23 04:14:44,009][11551] Fps is (10 sec: 4505.6, 60 sec: 3822.9, 300 sec: 3790.5). Total num frames: 2654208. Throughput: 0: 975.7. Samples: 662310. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 04:14:44,017][11551] Avg episode reward: [(0, '20.917')] | |
| [2023-02-23 04:14:44,035][11811] Saving new best policy, reward=20.917! | |
| [2023-02-23 04:14:46,451][11832] Updated weights for policy 0, policy_version 650 (0.0015) | |
| [2023-02-23 04:14:49,009][11551] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3776.7). Total num frames: 2666496. Throughput: 0: 926.4. Samples: 667088. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 04:14:49,014][11551] Avg episode reward: [(0, '19.758')] | |
| [2023-02-23 04:14:54,009][11551] Fps is (10 sec: 2867.2, 60 sec: 3754.8, 300 sec: 3776.7). Total num frames: 2682880. Throughput: 0: 930.1. Samples: 672132. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-02-23 04:14:54,016][11551] Avg episode reward: [(0, '19.455')] | |
| [2023-02-23 04:14:57,665][11832] Updated weights for policy 0, policy_version 660 (0.0023) | |
| [2023-02-23 04:14:59,009][11551] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3776.7). Total num frames: 2707456. Throughput: 0: 959.7. Samples: 675498. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2023-02-23 04:14:59,018][11551] Avg episode reward: [(0, '19.189')] | |
| [2023-02-23 04:15:04,009][11551] Fps is (10 sec: 4505.6, 60 sec: 3754.7, 300 sec: 3776.7). Total num frames: 2727936. Throughput: 0: 969.8. Samples: 682202. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 04:15:04,018][11551] Avg episode reward: [(0, '19.001')] | |
| [2023-02-23 04:15:08,589][11832] Updated weights for policy 0, policy_version 670 (0.0011) | |
| [2023-02-23 04:15:09,009][11551] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3790.6). Total num frames: 2744320. Throughput: 0: 918.4. Samples: 686670. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 04:15:09,015][11551] Avg episode reward: [(0, '18.825')] | |
| [2023-02-23 04:15:14,009][11551] Fps is (10 sec: 3276.8, 60 sec: 3822.9, 300 sec: 3790.5). Total num frames: 2760704. Throughput: 0: 915.0. Samples: 688768. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 04:15:14,018][11551] Avg episode reward: [(0, '19.226')] | |
| [2023-02-23 04:15:18,681][11832] Updated weights for policy 0, policy_version 680 (0.0029) | |
| [2023-02-23 04:15:19,009][11551] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3790.5). Total num frames: 2785280. Throughput: 0: 972.0. Samples: 695706. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 04:15:19,012][11551] Avg episode reward: [(0, '17.998')] | |
| [2023-02-23 04:15:24,009][11551] Fps is (10 sec: 4505.6, 60 sec: 3822.9, 300 sec: 3790.5). Total num frames: 2805760. Throughput: 0: 953.9. Samples: 701916. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 04:15:24,017][11551] Avg episode reward: [(0, '17.558')] | |
| [2023-02-23 04:15:29,009][11551] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3776.7). Total num frames: 2818048. Throughput: 0: 927.1. Samples: 704030. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-23 04:15:29,013][11551] Avg episode reward: [(0, '17.669')] | |
| [2023-02-23 04:15:30,777][11832] Updated weights for policy 0, policy_version 690 (0.0025) | |
| [2023-02-23 04:15:34,009][11551] Fps is (10 sec: 3276.8, 60 sec: 3822.9, 300 sec: 3790.5). Total num frames: 2838528. Throughput: 0: 933.6. Samples: 709098. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-23 04:15:34,019][11551] Avg episode reward: [(0, '17.805')] | |
| [2023-02-23 04:15:39,009][11551] Fps is (10 sec: 4096.0, 60 sec: 3754.7, 300 sec: 3776.7). Total num frames: 2859008. Throughput: 0: 977.9. Samples: 716136. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 04:15:39,016][11551] Avg episode reward: [(0, '18.769')] | |
| [2023-02-23 04:15:39,983][11832] Updated weights for policy 0, policy_version 700 (0.0011) | |
| [2023-02-23 04:15:44,011][11551] Fps is (10 sec: 4095.4, 60 sec: 3754.6, 300 sec: 3776.6). Total num frames: 2879488. Throughput: 0: 975.4. Samples: 719394. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 04:15:44,014][11551] Avg episode reward: [(0, '20.951')] | |
| [2023-02-23 04:15:44,025][11811] Saving new best policy, reward=20.951! | |
| [2023-02-23 04:15:49,011][11551] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3790.5). Total num frames: 2895872. Throughput: 0: 921.4. Samples: 723664. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-23 04:15:49,017][11551] Avg episode reward: [(0, '23.403')] | |
| [2023-02-23 04:15:49,021][11811] Saving new best policy, reward=23.403! | |
| [2023-02-23 04:15:52,629][11832] Updated weights for policy 0, policy_version 710 (0.0041) | |
| [2023-02-23 04:15:54,009][11551] Fps is (10 sec: 3277.2, 60 sec: 3822.9, 300 sec: 3776.7). Total num frames: 2912256. Throughput: 0: 942.2. Samples: 729070. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2023-02-23 04:15:54,012][11551] Avg episode reward: [(0, '23.042')] | |
| [2023-02-23 04:15:59,009][11551] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3790.5). Total num frames: 2936832. Throughput: 0: 973.9. Samples: 732592. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2023-02-23 04:15:59,014][11551] Avg episode reward: [(0, '25.147')] | |
| [2023-02-23 04:15:59,017][11811] Saving new best policy, reward=25.147! | |
| [2023-02-23 04:16:01,612][11832] Updated weights for policy 0, policy_version 720 (0.0015) | |
| [2023-02-23 04:16:04,009][11551] Fps is (10 sec: 4096.0, 60 sec: 3754.7, 300 sec: 3776.7). Total num frames: 2953216. Throughput: 0: 959.0. Samples: 738860. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2023-02-23 04:16:04,016][11551] Avg episode reward: [(0, '24.875')] | |
| [2023-02-23 04:16:09,009][11551] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3776.7). Total num frames: 2969600. Throughput: 0: 918.5. Samples: 743248. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2023-02-23 04:16:09,014][11551] Avg episode reward: [(0, '23.578')] | |
| [2023-02-23 04:16:13,628][11832] Updated weights for policy 0, policy_version 730 (0.0018) | |
| [2023-02-23 04:16:14,009][11551] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3790.5). Total num frames: 2990080. Throughput: 0: 929.6. Samples: 745860. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 04:16:14,017][11551] Avg episode reward: [(0, '22.007')] | |
| [2023-02-23 04:16:14,028][11811] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000730_2990080.pth... | |
| [2023-02-23 04:16:14,140][11811] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000508_2080768.pth | |
| [2023-02-23 04:16:19,009][11551] Fps is (10 sec: 4096.0, 60 sec: 3754.7, 300 sec: 3776.7). Total num frames: 3010560. Throughput: 0: 969.0. Samples: 752704. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2023-02-23 04:16:19,015][11551] Avg episode reward: [(0, '22.034')] | |
| [2023-02-23 04:16:23,544][11832] Updated weights for policy 0, policy_version 740 (0.0024) | |
| [2023-02-23 04:16:24,012][11551] Fps is (10 sec: 4095.0, 60 sec: 3754.5, 300 sec: 3776.6). Total num frames: 3031040. Throughput: 0: 938.0. Samples: 758348. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2023-02-23 04:16:24,014][11551] Avg episode reward: [(0, '20.968')] | |
| [2023-02-23 04:16:29,009][11551] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3776.7). Total num frames: 3043328. Throughput: 0: 914.6. Samples: 760548. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-23 04:16:29,016][11551] Avg episode reward: [(0, '20.573')] | |
| [2023-02-23 04:16:34,009][11551] Fps is (10 sec: 3277.6, 60 sec: 3754.7, 300 sec: 3776.7). Total num frames: 3063808. Throughput: 0: 940.5. Samples: 765986. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 04:16:34,012][11551] Avg episode reward: [(0, '20.201')] | |
| [2023-02-23 04:16:35,007][11832] Updated weights for policy 0, policy_version 750 (0.0011) | |
| [2023-02-23 04:16:39,009][11551] Fps is (10 sec: 4505.6, 60 sec: 3822.9, 300 sec: 3790.5). Total num frames: 3088384. Throughput: 0: 978.5. Samples: 773102. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 04:16:39,012][11551] Avg episode reward: [(0, '19.472')] | |
| [2023-02-23 04:16:44,009][11551] Fps is (10 sec: 4096.0, 60 sec: 3754.8, 300 sec: 3776.7). Total num frames: 3104768. Throughput: 0: 962.9. Samples: 775924. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 04:16:44,017][11551] Avg episode reward: [(0, '19.917')] | |
| [2023-02-23 04:16:45,747][11832] Updated weights for policy 0, policy_version 760 (0.0027) | |
| [2023-02-23 04:16:49,009][11551] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3790.5). Total num frames: 3121152. Throughput: 0: 919.2. Samples: 780224. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-23 04:16:49,012][11551] Avg episode reward: [(0, '19.322')] | |
| [2023-02-23 04:16:54,009][11551] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3790.5). Total num frames: 3141632. Throughput: 0: 955.7. Samples: 786254. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2023-02-23 04:16:54,012][11551] Avg episode reward: [(0, '19.812')] | |
| [2023-02-23 04:16:56,163][11832] Updated weights for policy 0, policy_version 770 (0.0017) | |
| [2023-02-23 04:16:59,009][11551] Fps is (10 sec: 4505.6, 60 sec: 3822.9, 300 sec: 3790.5). Total num frames: 3166208. Throughput: 0: 974.8. Samples: 789724. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-23 04:16:59,012][11551] Avg episode reward: [(0, '20.913')] | |
| [2023-02-23 04:17:04,009][11551] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3790.6). Total num frames: 3182592. Throughput: 0: 953.6. Samples: 795616. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2023-02-23 04:17:04,015][11551] Avg episode reward: [(0, '22.070')] | |
| [2023-02-23 04:17:07,797][11832] Updated weights for policy 0, policy_version 780 (0.0017) | |
| [2023-02-23 04:17:09,013][11551] Fps is (10 sec: 2866.3, 60 sec: 3754.5, 300 sec: 3776.6). Total num frames: 3194880. Throughput: 0: 924.1. Samples: 799934. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2023-02-23 04:17:09,017][11551] Avg episode reward: [(0, '21.762')] | |
| [2023-02-23 04:17:14,009][11551] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3776.6). Total num frames: 3215360. Throughput: 0: 941.1. Samples: 802898. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 04:17:14,012][11551] Avg episode reward: [(0, '22.514')] | |
| [2023-02-23 04:17:17,733][11832] Updated weights for policy 0, policy_version 790 (0.0020) | |
| [2023-02-23 04:17:19,009][11551] Fps is (10 sec: 4507.1, 60 sec: 3822.9, 300 sec: 3790.5). Total num frames: 3239936. Throughput: 0: 971.3. Samples: 809694. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 04:17:19,018][11551] Avg episode reward: [(0, '22.483')] | |
| [2023-02-23 04:17:24,014][11551] Fps is (10 sec: 4094.2, 60 sec: 3754.5, 300 sec: 3776.6). Total num frames: 3256320. Throughput: 0: 932.5. Samples: 815068. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 04:17:24,016][11551] Avg episode reward: [(0, '22.639')] | |
| [2023-02-23 04:17:29,012][11551] Fps is (10 sec: 3276.0, 60 sec: 3822.8, 300 sec: 3790.5). Total num frames: 3272704. Throughput: 0: 919.3. Samples: 817296. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) | |
| [2023-02-23 04:17:29,014][11551] Avg episode reward: [(0, '22.241')] | |
| [2023-02-23 04:17:30,038][11832] Updated weights for policy 0, policy_version 800 (0.0028) | |
| [2023-02-23 04:17:34,009][11551] Fps is (10 sec: 3688.0, 60 sec: 3822.9, 300 sec: 3776.7). Total num frames: 3293184. Throughput: 0: 951.2. Samples: 823030. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 04:17:34,018][11551] Avg episode reward: [(0, '21.629')] | |
| [2023-02-23 04:17:38,905][11832] Updated weights for policy 0, policy_version 810 (0.0021) | |
| [2023-02-23 04:17:39,009][11551] Fps is (10 sec: 4506.7, 60 sec: 3822.9, 300 sec: 3790.5). Total num frames: 3317760. Throughput: 0: 970.3. Samples: 829918. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 04:17:39,014][11551] Avg episode reward: [(0, '21.764')] | |
| [2023-02-23 04:17:44,009][11551] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3790.6). Total num frames: 3334144. Throughput: 0: 950.3. Samples: 832486. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-02-23 04:17:44,011][11551] Avg episode reward: [(0, '23.158')] | |
| [2023-02-23 04:17:49,009][11551] Fps is (10 sec: 2867.2, 60 sec: 3754.7, 300 sec: 3776.7). Total num frames: 3346432. Throughput: 0: 918.2. Samples: 836936. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 04:17:49,015][11551] Avg episode reward: [(0, '22.866')] | |
| [2023-02-23 04:17:51,183][11832] Updated weights for policy 0, policy_version 820 (0.0029) | |
| [2023-02-23 04:17:54,009][11551] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3790.5). Total num frames: 3371008. Throughput: 0: 962.6. Samples: 843248. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-02-23 04:17:54,015][11551] Avg episode reward: [(0, '23.338')] | |
| [2023-02-23 04:17:59,009][11551] Fps is (10 sec: 4505.6, 60 sec: 3754.7, 300 sec: 3776.7). Total num frames: 3391488. Throughput: 0: 974.8. Samples: 846766. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2023-02-23 04:17:59,016][11551] Avg episode reward: [(0, '22.965')] | |
| [2023-02-23 04:18:00,457][11832] Updated weights for policy 0, policy_version 830 (0.0014) | |
| [2023-02-23 04:18:04,012][11551] Fps is (10 sec: 3685.5, 60 sec: 3754.5, 300 sec: 3790.6). Total num frames: 3407872. Throughput: 0: 942.8. Samples: 852124. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 04:18:04,014][11551] Avg episode reward: [(0, '22.204')] | |
| [2023-02-23 04:18:09,009][11551] Fps is (10 sec: 3276.8, 60 sec: 3823.1, 300 sec: 3790.5). Total num frames: 3424256. Throughput: 0: 922.3. Samples: 856566. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-02-23 04:18:09,018][11551] Avg episode reward: [(0, '21.666')] | |
| [2023-02-23 04:18:12,577][11832] Updated weights for policy 0, policy_version 840 (0.0025) | |
| [2023-02-23 04:18:14,009][11551] Fps is (10 sec: 3687.3, 60 sec: 3822.9, 300 sec: 3790.5). Total num frames: 3444736. Throughput: 0: 945.6. Samples: 859846. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 04:18:14,016][11551] Avg episode reward: [(0, '21.512')] | |
| [2023-02-23 04:18:14,030][11811] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000841_3444736.pth... | |
| [2023-02-23 04:18:14,170][11811] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000619_2535424.pth | |
| [2023-02-23 04:18:19,009][11551] Fps is (10 sec: 4505.6, 60 sec: 3822.9, 300 sec: 3790.5). Total num frames: 3469312. Throughput: 0: 966.3. Samples: 866512. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 04:18:19,012][11551] Avg episode reward: [(0, '20.899')] | |
| [2023-02-23 04:18:23,068][11832] Updated weights for policy 0, policy_version 850 (0.0021) | |
| [2023-02-23 04:18:24,009][11551] Fps is (10 sec: 3686.4, 60 sec: 3754.9, 300 sec: 3776.7). Total num frames: 3481600. Throughput: 0: 923.5. Samples: 871474. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-23 04:18:24,018][11551] Avg episode reward: [(0, '21.368')] | |
| [2023-02-23 04:18:29,009][11551] Fps is (10 sec: 2867.2, 60 sec: 3754.8, 300 sec: 3790.5). Total num frames: 3497984. Throughput: 0: 914.3. Samples: 873628. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 04:18:29,015][11551] Avg episode reward: [(0, '21.733')] | |
| [2023-02-23 04:18:34,009][11551] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3776.6). Total num frames: 3518464. Throughput: 0: 949.9. Samples: 879682. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 04:18:34,016][11551] Avg episode reward: [(0, '22.965')] | |
| [2023-02-23 04:18:34,171][11832] Updated weights for policy 0, policy_version 860 (0.0025) | |
| [2023-02-23 04:18:39,009][11551] Fps is (10 sec: 4505.6, 60 sec: 3754.7, 300 sec: 3790.5). Total num frames: 3543040. Throughput: 0: 959.9. Samples: 886442. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 04:18:39,016][11551] Avg episode reward: [(0, '22.530')] | |
| [2023-02-23 04:18:44,009][11551] Fps is (10 sec: 3686.4, 60 sec: 3686.4, 300 sec: 3776.7). Total num frames: 3555328. Throughput: 0: 931.2. Samples: 888670. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 04:18:44,012][11551] Avg episode reward: [(0, '22.855')] | |
| [2023-02-23 04:18:45,544][11832] Updated weights for policy 0, policy_version 870 (0.0017) | |
| [2023-02-23 04:18:49,009][11551] Fps is (10 sec: 2867.2, 60 sec: 3754.7, 300 sec: 3776.7). Total num frames: 3571712. Throughput: 0: 911.2. Samples: 893124. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 04:18:49,012][11551] Avg episode reward: [(0, '23.074')] | |
| [2023-02-23 04:18:54,009][11551] Fps is (10 sec: 4096.0, 60 sec: 3754.7, 300 sec: 3790.5). Total num frames: 3596288. Throughput: 0: 959.4. Samples: 899738. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 04:18:54,015][11551] Avg episode reward: [(0, '23.286')] | |
| [2023-02-23 04:18:55,542][11832] Updated weights for policy 0, policy_version 880 (0.0023) | |
| [2023-02-23 04:18:59,009][11551] Fps is (10 sec: 4505.6, 60 sec: 3754.7, 300 sec: 3776.7). Total num frames: 3616768. Throughput: 0: 962.8. Samples: 903170. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 04:18:59,012][11551] Avg episode reward: [(0, '22.994')] | |
| [2023-02-23 04:19:04,009][11551] Fps is (10 sec: 3686.4, 60 sec: 3754.8, 300 sec: 3776.7). Total num frames: 3633152. Throughput: 0: 931.6. Samples: 908432. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 04:19:04,012][11551] Avg episode reward: [(0, '22.192')] | |
| [2023-02-23 04:19:07,796][11832] Updated weights for policy 0, policy_version 890 (0.0011) | |
| [2023-02-23 04:19:09,009][11551] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3790.5). Total num frames: 3649536. Throughput: 0: 921.2. Samples: 912930. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) | |
| [2023-02-23 04:19:09,015][11551] Avg episode reward: [(0, '23.731')] | |
| [2023-02-23 04:19:14,009][11551] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3790.5). Total num frames: 3674112. Throughput: 0: 951.9. Samples: 916462. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2023-02-23 04:19:14,016][11551] Avg episode reward: [(0, '23.861')] | |
| [2023-02-23 04:19:16,786][11832] Updated weights for policy 0, policy_version 900 (0.0012) | |
| [2023-02-23 04:19:19,009][11551] Fps is (10 sec: 4505.6, 60 sec: 3754.7, 300 sec: 3790.5). Total num frames: 3694592. Throughput: 0: 968.0. Samples: 923244. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2023-02-23 04:19:19,012][11551] Avg episode reward: [(0, '23.719')] | |
| [2023-02-23 04:19:24,010][11551] Fps is (10 sec: 3276.4, 60 sec: 3754.6, 300 sec: 3776.6). Total num frames: 3706880. Throughput: 0: 923.4. Samples: 927994. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2023-02-23 04:19:24,016][11551] Avg episode reward: [(0, '24.409')] | |
| [2023-02-23 04:19:29,009][11551] Fps is (10 sec: 2867.2, 60 sec: 3754.7, 300 sec: 3776.7). Total num frames: 3723264. Throughput: 0: 922.4. Samples: 930178. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 04:19:29,018][11551] Avg episode reward: [(0, '24.226')] | |
| [2023-02-23 04:19:29,176][11832] Updated weights for policy 0, policy_version 910 (0.0017) | |
| [2023-02-23 04:19:34,009][11551] Fps is (10 sec: 4096.5, 60 sec: 3822.9, 300 sec: 3776.6). Total num frames: 3747840. Throughput: 0: 967.2. Samples: 936648. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 04:19:34,016][11551] Avg episode reward: [(0, '24.918')] | |
| [2023-02-23 04:19:37,828][11832] Updated weights for policy 0, policy_version 920 (0.0023) | |
| [2023-02-23 04:19:39,009][11551] Fps is (10 sec: 4505.6, 60 sec: 3754.7, 300 sec: 3776.7). Total num frames: 3768320. Throughput: 0: 967.8. Samples: 943288. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2023-02-23 04:19:39,016][11551] Avg episode reward: [(0, '24.921')] | |
| [2023-02-23 04:19:44,010][11551] Fps is (10 sec: 3686.2, 60 sec: 3822.9, 300 sec: 3790.5). Total num frames: 3784704. Throughput: 0: 940.9. Samples: 945512. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-23 04:19:44,018][11551] Avg episode reward: [(0, '25.532')] | |
| [2023-02-23 04:19:44,030][11811] Saving new best policy, reward=25.532! | |
| [2023-02-23 04:19:49,009][11551] Fps is (10 sec: 3276.8, 60 sec: 3822.9, 300 sec: 3790.5). Total num frames: 3801088. Throughput: 0: 917.9. Samples: 949738. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-02-23 04:19:49,012][11551] Avg episode reward: [(0, '25.276')] | |
| [2023-02-23 04:19:50,345][11832] Updated weights for policy 0, policy_version 930 (0.0025) | |
| [2023-02-23 04:19:54,009][11551] Fps is (10 sec: 4096.2, 60 sec: 3822.9, 300 sec: 3790.5). Total num frames: 3825664. Throughput: 0: 972.5. Samples: 956694. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 04:19:54,015][11551] Avg episode reward: [(0, '26.401')] | |
| [2023-02-23 04:19:54,027][11811] Saving new best policy, reward=26.401! | |
| [2023-02-23 04:19:59,009][11551] Fps is (10 sec: 4505.6, 60 sec: 3822.9, 300 sec: 3790.5). Total num frames: 3846144. Throughput: 0: 968.1. Samples: 960028. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-23 04:19:59,017][11551] Avg episode reward: [(0, '25.024')] | |
| [2023-02-23 04:20:00,018][11832] Updated weights for policy 0, policy_version 940 (0.0020) | |
| [2023-02-23 04:20:04,017][11551] Fps is (10 sec: 3274.4, 60 sec: 3754.2, 300 sec: 3776.6). Total num frames: 3858432. Throughput: 0: 925.9. Samples: 964918. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-02-23 04:20:04,023][11551] Avg episode reward: [(0, '24.831')] | |
| [2023-02-23 04:20:09,009][11551] Fps is (10 sec: 2867.2, 60 sec: 3754.7, 300 sec: 3776.7). Total num frames: 3874816. Throughput: 0: 931.2. Samples: 969898. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 04:20:09,015][11551] Avg episode reward: [(0, '24.537')] | |
| [2023-02-23 04:20:11,734][11832] Updated weights for policy 0, policy_version 950 (0.0017) | |
| [2023-02-23 04:20:14,009][11551] Fps is (10 sec: 4099.0, 60 sec: 3754.7, 300 sec: 3776.7). Total num frames: 3899392. Throughput: 0: 958.1. Samples: 973292. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-23 04:20:14,011][11551] Avg episode reward: [(0, '22.202')] | |
| [2023-02-23 04:20:14,030][11811] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000952_3899392.pth... | |
| [2023-02-23 04:20:14,179][11811] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000730_2990080.pth | |
| [2023-02-23 04:20:19,009][11551] Fps is (10 sec: 4505.6, 60 sec: 3754.7, 300 sec: 3776.7). Total num frames: 3919872. Throughput: 0: 966.0. Samples: 980116. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-23 04:20:19,014][11551] Avg episode reward: [(0, '21.401')] | |
| [2023-02-23 04:20:22,317][11832] Updated weights for policy 0, policy_version 960 (0.0026) | |
| [2023-02-23 04:20:24,010][11551] Fps is (10 sec: 3686.3, 60 sec: 3823.0, 300 sec: 3790.5). Total num frames: 3936256. Throughput: 0: 912.1. Samples: 984334. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) | |
| [2023-02-23 04:20:24,012][11551] Avg episode reward: [(0, '23.181')] | |
| [2023-02-23 04:20:29,009][11551] Fps is (10 sec: 3276.8, 60 sec: 3822.9, 300 sec: 3776.7). Total num frames: 3952640. Throughput: 0: 910.5. Samples: 986486. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-02-23 04:20:29,012][11551] Avg episode reward: [(0, '22.491')] | |
| [2023-02-23 04:20:33,046][11832] Updated weights for policy 0, policy_version 970 (0.0025) | |
| [2023-02-23 04:20:34,009][11551] Fps is (10 sec: 4096.2, 60 sec: 3822.9, 300 sec: 3790.5). Total num frames: 3977216. Throughput: 0: 968.9. Samples: 993338. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-23 04:20:34,014][11551] Avg episode reward: [(0, '21.959')] | |
| [2023-02-23 04:20:39,009][11551] Fps is (10 sec: 4096.0, 60 sec: 3754.7, 300 sec: 3776.7). Total num frames: 3993600. Throughput: 0: 953.0. Samples: 999580. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-23 04:20:39,012][11551] Avg episode reward: [(0, '20.936')] | |
| [2023-02-23 04:20:42,359][11811] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... | |
| [2023-02-23 04:20:42,362][11551] Component Batcher_0 stopped! | |
| [2023-02-23 04:20:42,360][11811] Stopping Batcher_0... | |
| [2023-02-23 04:20:42,370][11811] Loop batcher_evt_loop terminating... | |
| [2023-02-23 04:20:42,440][11551] Component RolloutWorker_w7 stopped! | |
| [2023-02-23 04:20:42,448][11551] Component RolloutWorker_w4 stopped! | |
| [2023-02-23 04:20:42,449][11551] Component RolloutWorker_w3 stopped! | |
| [2023-02-23 04:20:42,456][11825] Stopping RolloutWorker_w4... | |
| [2023-02-23 04:20:42,457][11825] Loop rollout_proc4_evt_loop terminating... | |
| [2023-02-23 04:20:42,440][11830] Stopping RolloutWorker_w7... | |
| [2023-02-23 04:20:42,465][11830] Loop rollout_proc7_evt_loop terminating... | |
| [2023-02-23 04:20:42,449][11828] Stopping RolloutWorker_w3... | |
| [2023-02-23 04:20:42,470][11828] Loop rollout_proc3_evt_loop terminating... | |
| [2023-02-23 04:20:42,474][11833] Stopping RolloutWorker_w5... | |
| [2023-02-23 04:20:42,474][11833] Loop rollout_proc5_evt_loop terminating... | |
| [2023-02-23 04:20:42,475][11551] Component RolloutWorker_w5 stopped! | |
| [2023-02-23 04:20:42,484][11832] Weights refcount: 2 0 | |
| [2023-02-23 04:20:42,485][11551] Component InferenceWorker_p0-w0 stopped! | |
| [2023-02-23 04:20:42,485][11832] Stopping InferenceWorker_p0-w0... | |
| [2023-02-23 04:20:42,501][11832] Loop inference_proc0-0_evt_loop terminating... | |
| [2023-02-23 04:20:42,506][11827] Stopping RolloutWorker_w1... | |
| [2023-02-23 04:20:42,506][11827] Loop rollout_proc1_evt_loop terminating... | |
| [2023-02-23 04:20:42,506][11551] Component RolloutWorker_w1 stopped! | |
| [2023-02-23 04:20:42,525][11551] Component RolloutWorker_w6 stopped! | |
| [2023-02-23 04:20:42,530][11829] Stopping RolloutWorker_w6... | |
| [2023-02-23 04:20:42,545][11829] Loop rollout_proc6_evt_loop terminating... | |
| [2023-02-23 04:20:42,552][11551] Component RolloutWorker_w0 stopped! | |
| [2023-02-23 04:20:42,559][11826] Stopping RolloutWorker_w0... | |
| [2023-02-23 04:20:42,560][11826] Loop rollout_proc0_evt_loop terminating... | |
| [2023-02-23 04:20:42,571][11551] Component RolloutWorker_w2 stopped! | |
| [2023-02-23 04:20:42,577][11831] Stopping RolloutWorker_w2... | |
| [2023-02-23 04:20:42,577][11831] Loop rollout_proc2_evt_loop terminating... | |
| [2023-02-23 04:20:42,589][11811] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000841_3444736.pth | |
| [2023-02-23 04:20:42,608][11811] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... | |
| [2023-02-23 04:20:42,899][11551] Component LearnerWorker_p0 stopped! | |
| [2023-02-23 04:20:42,902][11551] Waiting for process learner_proc0 to stop... | |
| [2023-02-23 04:20:42,907][11811] Stopping LearnerWorker_p0... | |
| [2023-02-23 04:20:42,908][11811] Loop learner_proc0_evt_loop terminating... | |
| [2023-02-23 04:20:45,398][11551] Waiting for process inference_proc0-0 to join... | |
| [2023-02-23 04:20:45,895][11551] Waiting for process rollout_proc0 to join... | |
| [2023-02-23 04:20:46,261][11551] Waiting for process rollout_proc1 to join... | |
| [2023-02-23 04:20:46,517][11551] Waiting for process rollout_proc2 to join... | |
| [2023-02-23 04:20:46,519][11551] Waiting for process rollout_proc3 to join... | |
| [2023-02-23 04:20:46,523][11551] Waiting for process rollout_proc4 to join... | |
| [2023-02-23 04:20:46,525][11551] Waiting for process rollout_proc5 to join... | |
| [2023-02-23 04:20:46,527][11551] Waiting for process rollout_proc6 to join... | |
| [2023-02-23 04:20:46,528][11551] Waiting for process rollout_proc7 to join... | |
| [2023-02-23 04:20:46,530][11551] Batcher 0 profile tree view: | |
| batching: 25.5056, releasing_batches: 0.0251 | |
| [2023-02-23 04:20:46,536][11551] InferenceWorker_p0-w0 profile tree view: | |
| wait_policy: 0.0000 | |
| wait_policy_total: 544.6169 | |
| update_model: 7.2583 | |
| weight_update: 0.0016 | |
| one_step: 0.0193 | |
| handle_policy_step: 489.1434 | |
| deserialize: 14.3067, stack: 2.7687, obs_to_device_normalize: 110.8314, forward: 233.6035, send_messages: 24.4603 | |
| prepare_outputs: 78.9184 | |
| to_cpu: 49.5998 | |
| [2023-02-23 04:20:46,540][11551] Learner 0 profile tree view: | |
| misc: 0.0068, prepare_batch: 16.5790 | |
| train: 74.9841 | |
| epoch_init: 0.0058, minibatch_init: 0.0063, losses_postprocess: 0.5635, kl_divergence: 0.6402, after_optimizer: 33.1600 | |
| calculate_losses: 26.1750 | |
| losses_init: 0.0035, forward_head: 1.6091, bptt_initial: 17.3746, tail: 1.0218, advantages_returns: 0.3168, losses: 3.4277 | |
| bptt: 2.1602 | |
| bptt_forward_core: 2.0968 | |
| update: 13.8282 | |
| clip: 1.3711 | |
| [2023-02-23 04:20:46,541][11551] RolloutWorker_w0 profile tree view: | |
| wait_for_trajectories: 0.3692, enqueue_policy_requests: 148.0179, env_step: 808.4861, overhead: 20.3673, complete_rollouts: 6.8261 | |
| save_policy_outputs: 19.5477 | |
| split_output_tensors: 9.6226 | |
| [2023-02-23 04:20:46,543][11551] RolloutWorker_w7 profile tree view: | |
| wait_for_trajectories: 0.4134, enqueue_policy_requests: 151.3033, env_step: 806.6787, overhead: 20.6108, complete_rollouts: 6.7067 | |
| save_policy_outputs: 18.7018 | |
| split_output_tensors: 9.2783 | |
| [2023-02-23 04:20:46,545][11551] Loop Runner_EvtLoop terminating... | |
| [2023-02-23 04:20:46,547][11551] Runner profile tree view: | |
| main_loop: 1107.8446 | |
| [2023-02-23 04:20:46,548][11551] Collected {0: 4005888}, FPS: 3615.9 | |
| [2023-02-23 04:20:46,603][11551] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json | |
| [2023-02-23 04:20:46,604][11551] Overriding arg 'num_workers' with value 1 passed from command line | |
| [2023-02-23 04:20:46,607][11551] Adding new argument 'no_render'=True that is not in the saved config file! | |
| [2023-02-23 04:20:46,609][11551] Adding new argument 'save_video'=True that is not in the saved config file! | |
| [2023-02-23 04:20:46,614][11551] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file! | |
| [2023-02-23 04:20:46,616][11551] Adding new argument 'video_name'=None that is not in the saved config file! | |
| [2023-02-23 04:20:46,617][11551] Adding new argument 'max_num_frames'=1000000000.0 that is not in the saved config file! | |
| [2023-02-23 04:20:46,621][11551] Adding new argument 'max_num_episodes'=10 that is not in the saved config file! | |
| [2023-02-23 04:20:46,623][11551] Adding new argument 'push_to_hub'=False that is not in the saved config file! | |
| [2023-02-23 04:20:46,625][11551] Adding new argument 'hf_repository'=None that is not in the saved config file! | |
| [2023-02-23 04:20:46,627][11551] Adding new argument 'policy_index'=0 that is not in the saved config file! | |
| [2023-02-23 04:20:46,630][11551] Adding new argument 'eval_deterministic'=False that is not in the saved config file! | |
| [2023-02-23 04:20:46,634][11551] Adding new argument 'train_script'=None that is not in the saved config file! | |
| [2023-02-23 04:20:46,635][11551] Adding new argument 'enjoy_script'=None that is not in the saved config file! | |
| [2023-02-23 04:20:46,637][11551] Using frameskip 1 and render_action_repeat=4 for evaluation | |
| [2023-02-23 04:20:46,659][11551] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2023-02-23 04:20:46,662][11551] RunningMeanStd input shape: (3, 72, 128) | |
| [2023-02-23 04:20:46,665][11551] RunningMeanStd input shape: (1,) | |
| [2023-02-23 04:20:46,681][11551] ConvEncoder: input_channels=3 | |
| [2023-02-23 04:20:47,370][11551] Conv encoder output size: 512 | |
| [2023-02-23 04:20:47,371][11551] Policy head output size: 512 | |
| [2023-02-23 04:20:49,783][11551] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... | |
| [2023-02-23 04:20:51,041][11551] Num frames 100... | |
| [2023-02-23 04:20:51,154][11551] Num frames 200... | |
| [2023-02-23 04:20:51,268][11551] Num frames 300... | |
| [2023-02-23 04:20:51,381][11551] Num frames 400... | |
| [2023-02-23 04:20:51,494][11551] Num frames 500... | |
| [2023-02-23 04:20:51,615][11551] Num frames 600... | |
| [2023-02-23 04:20:51,730][11551] Num frames 700... | |
| [2023-02-23 04:20:51,852][11551] Num frames 800... | |
| [2023-02-23 04:20:51,980][11551] Num frames 900... | |
| [2023-02-23 04:20:52,089][11551] Num frames 1000... | |
| [2023-02-23 04:20:52,200][11551] Num frames 1100... | |
| [2023-02-23 04:20:52,315][11551] Num frames 1200... | |
| [2023-02-23 04:20:52,429][11551] Num frames 1300... | |
| [2023-02-23 04:20:52,539][11551] Num frames 1400... | |
| [2023-02-23 04:20:52,660][11551] Num frames 1500... | |
| [2023-02-23 04:20:52,774][11551] Num frames 1600... | |
| [2023-02-23 04:20:52,886][11551] Num frames 1700... | |
| [2023-02-23 04:20:52,998][11551] Num frames 1800... | |
| [2023-02-23 04:20:53,142][11551] Avg episode rewards: #0: 50.749, true rewards: #0: 18.750 | |
| [2023-02-23 04:20:53,144][11551] Avg episode reward: 50.749, avg true_objective: 18.750 | |
| [2023-02-23 04:20:53,176][11551] Num frames 1900... | |
| [2023-02-23 04:20:53,287][11551] Num frames 2000... | |
| [2023-02-23 04:20:53,401][11551] Num frames 2100... | |
| [2023-02-23 04:20:53,512][11551] Num frames 2200... | |
| [2023-02-23 04:20:53,625][11551] Num frames 2300... | |
| [2023-02-23 04:20:53,749][11551] Num frames 2400... | |
| [2023-02-23 04:20:53,859][11551] Num frames 2500... | |
| [2023-02-23 04:20:53,980][11551] Num frames 2600... | |
| [2023-02-23 04:20:54,091][11551] Num frames 2700... | |
| [2023-02-23 04:20:54,204][11551] Num frames 2800... | |
| [2023-02-23 04:20:54,299][11551] Avg episode rewards: #0: 37.175, true rewards: #0: 14.175 | |
| [2023-02-23 04:20:54,300][11551] Avg episode reward: 37.175, avg true_objective: 14.175 | |
| [2023-02-23 04:20:54,380][11551] Num frames 2900... | |
| [2023-02-23 04:20:54,496][11551] Num frames 3000... | |
| [2023-02-23 04:20:54,611][11551] Num frames 3100... | |
| [2023-02-23 04:20:54,730][11551] Num frames 3200... | |
| [2023-02-23 04:20:54,842][11551] Num frames 3300... | |
| [2023-02-23 04:20:54,954][11551] Num frames 3400... | |
| [2023-02-23 04:20:55,069][11551] Num frames 3500... | |
| [2023-02-23 04:20:55,180][11551] Num frames 3600... | |
| [2023-02-23 04:20:55,292][11551] Num frames 3700... | |
| [2023-02-23 04:20:55,405][11551] Num frames 3800... | |
| [2023-02-23 04:20:55,513][11551] Num frames 3900... | |
| [2023-02-23 04:20:55,628][11551] Num frames 4000... | |
| [2023-02-23 04:20:55,774][11551] Avg episode rewards: #0: 33.893, true rewards: #0: 13.560 | |
| [2023-02-23 04:20:55,776][11551] Avg episode reward: 33.893, avg true_objective: 13.560 | |
| [2023-02-23 04:20:55,815][11551] Num frames 4100... | |
| [2023-02-23 04:20:55,925][11551] Num frames 4200... | |
| [2023-02-23 04:20:56,036][11551] Num frames 4300... | |
| [2023-02-23 04:20:56,147][11551] Num frames 4400... | |
| [2023-02-23 04:20:56,261][11551] Num frames 4500... | |
| [2023-02-23 04:20:56,370][11551] Num frames 4600... | |
| [2023-02-23 04:20:56,482][11551] Num frames 4700... | |
| [2023-02-23 04:20:56,635][11551] Num frames 4800... | |
| [2023-02-23 04:20:56,757][11551] Avg episode rewards: #0: 29.092, true rewards: #0: 12.092 | |
| [2023-02-23 04:20:56,760][11551] Avg episode reward: 29.092, avg true_objective: 12.092 | |
| [2023-02-23 04:20:56,859][11551] Num frames 4900... | |
| [2023-02-23 04:20:57,008][11551] Num frames 5000... | |
| [2023-02-23 04:20:57,157][11551] Num frames 5100... | |
| [2023-02-23 04:20:57,307][11551] Num frames 5200... | |
| [2023-02-23 04:20:57,446][11551] Avg episode rewards: #0: 24.306, true rewards: #0: 10.506 | |
| [2023-02-23 04:20:57,448][11551] Avg episode reward: 24.306, avg true_objective: 10.506 | |
| [2023-02-23 04:20:57,523][11551] Num frames 5300... | |
| [2023-02-23 04:20:57,684][11551] Num frames 5400... | |
| [2023-02-23 04:20:57,841][11551] Num frames 5500... | |
| [2023-02-23 04:20:58,003][11551] Num frames 5600... | |
| [2023-02-23 04:20:58,162][11551] Num frames 5700... | |
| [2023-02-23 04:20:58,322][11551] Num frames 5800... | |
| [2023-02-23 04:20:58,482][11551] Num frames 5900... | |
| [2023-02-23 04:20:58,639][11551] Num frames 6000... | |
| [2023-02-23 04:20:58,800][11551] Num frames 6100... | |
| [2023-02-23 04:20:58,956][11551] Num frames 6200... | |
| [2023-02-23 04:20:59,118][11551] Num frames 6300... | |
| [2023-02-23 04:20:59,278][11551] Num frames 6400... | |
| [2023-02-23 04:20:59,444][11551] Num frames 6500... | |
| [2023-02-23 04:20:59,604][11551] Num frames 6600... | |
| [2023-02-23 04:20:59,762][11551] Num frames 6700... | |
| [2023-02-23 04:20:59,918][11551] Num frames 6800... | |
| [2023-02-23 04:21:00,042][11551] Num frames 6900... | |
| [2023-02-23 04:21:00,158][11551] Num frames 7000... | |
| [2023-02-23 04:21:00,276][11551] Num frames 7100... | |
| [2023-02-23 04:21:00,387][11551] Num frames 7200... | |
| [2023-02-23 04:21:00,504][11551] Num frames 7300... | |
| [2023-02-23 04:21:00,619][11551] Avg episode rewards: #0: 28.588, true rewards: #0: 12.255 | |
| [2023-02-23 04:21:00,622][11551] Avg episode reward: 28.588, avg true_objective: 12.255 | |
| [2023-02-23 04:21:00,676][11551] Num frames 7400... | |
| [2023-02-23 04:21:00,786][11551] Num frames 7500... | |
| [2023-02-23 04:21:00,906][11551] Num frames 7600... | |
| [2023-02-23 04:21:01,015][11551] Num frames 7700... | |
| [2023-02-23 04:21:01,128][11551] Num frames 7800... | |
| [2023-02-23 04:21:01,239][11551] Num frames 7900... | |
| [2023-02-23 04:21:01,354][11551] Num frames 8000... | |
| [2023-02-23 04:21:01,469][11551] Num frames 8100... | |
| [2023-02-23 04:21:01,578][11551] Num frames 8200... | |
| [2023-02-23 04:21:01,698][11551] Num frames 8300... | |
| [2023-02-23 04:21:01,806][11551] Num frames 8400... | |
| [2023-02-23 04:21:01,920][11551] Num frames 8500... | |
| [2023-02-23 04:21:02,033][11551] Num frames 8600... | |
| [2023-02-23 04:21:02,149][11551] Num frames 8700... | |
| [2023-02-23 04:21:02,262][11551] Num frames 8800... | |
| [2023-02-23 04:21:02,372][11551] Num frames 8900... | |
| [2023-02-23 04:21:02,534][11551] Avg episode rewards: #0: 30.844, true rewards: #0: 12.844 | |
| [2023-02-23 04:21:02,535][11551] Avg episode reward: 30.844, avg true_objective: 12.844 | |
| [2023-02-23 04:21:02,551][11551] Num frames 9000... | |
| [2023-02-23 04:21:02,661][11551] Num frames 9100... | |
| [2023-02-23 04:21:02,773][11551] Num frames 9200... | |
| [2023-02-23 04:21:02,891][11551] Num frames 9300... | |
| [2023-02-23 04:21:03,001][11551] Num frames 9400... | |
| [2023-02-23 04:21:03,123][11551] Num frames 9500... | |
| [2023-02-23 04:21:03,235][11551] Num frames 9600... | |
| [2023-02-23 04:21:03,343][11551] Num frames 9700... | |
| [2023-02-23 04:21:03,456][11551] Num frames 9800... | |
| [2023-02-23 04:21:03,566][11551] Num frames 9900... | |
| [2023-02-23 04:21:03,679][11551] Num frames 10000... | |
| [2023-02-23 04:21:03,790][11551] Num frames 10100... | |
| [2023-02-23 04:21:03,904][11551] Num frames 10200... | |
| [2023-02-23 04:21:04,015][11551] Num frames 10300... | |
| [2023-02-23 04:21:04,132][11551] Num frames 10400... | |
| [2023-02-23 04:21:04,245][11551] Num frames 10500... | |
| [2023-02-23 04:21:04,360][11551] Num frames 10600... | |
| [2023-02-23 04:21:04,481][11551] Num frames 10700... | |
| [2023-02-23 04:21:04,592][11551] Num frames 10800... | |
| [2023-02-23 04:21:04,706][11551] Num frames 10900... | |
| [2023-02-23 04:21:04,816][11551] Num frames 11000... | |
| [2023-02-23 04:21:04,955][11551] Avg episode rewards: #0: 33.586, true rewards: #0: 13.836 | |
| [2023-02-23 04:21:04,958][11551] Avg episode reward: 33.586, avg true_objective: 13.836 | |
| [2023-02-23 04:21:04,995][11551] Num frames 11100... | |
| [2023-02-23 04:21:05,118][11551] Num frames 11200... | |
| [2023-02-23 04:21:05,230][11551] Num frames 11300... | |
| [2023-02-23 04:21:05,340][11551] Num frames 11400... | |
| [2023-02-23 04:21:05,459][11551] Num frames 11500... | |
| [2023-02-23 04:21:05,568][11551] Num frames 11600... | |
| [2023-02-23 04:21:05,682][11551] Num frames 11700... | |
| [2023-02-23 04:21:05,791][11551] Num frames 11800... | |
| [2023-02-23 04:21:05,909][11551] Num frames 11900... | |
| [2023-02-23 04:21:06,020][11551] Num frames 12000... | |
| [2023-02-23 04:21:06,136][11551] Num frames 12100... | |
| [2023-02-23 04:21:06,247][11551] Num frames 12200... | |
| [2023-02-23 04:21:06,357][11551] Num frames 12300... | |
| [2023-02-23 04:21:06,475][11551] Num frames 12400... | |
| [2023-02-23 04:21:06,586][11551] Num frames 12500... | |
| [2023-02-23 04:21:06,699][11551] Num frames 12600... | |
| [2023-02-23 04:21:06,814][11551] Num frames 12700... | |
| [2023-02-23 04:21:06,934][11551] Num frames 12800... | |
| [2023-02-23 04:21:07,052][11551] Num frames 12900... | |
| [2023-02-23 04:21:07,166][11551] Num frames 13000... | |
| [2023-02-23 04:21:07,232][11551] Avg episode rewards: #0: 36.231, true rewards: #0: 14.453 | |
| [2023-02-23 04:21:07,234][11551] Avg episode reward: 36.231, avg true_objective: 14.453 | |
| [2023-02-23 04:21:07,344][11551] Num frames 13100... | |
| [2023-02-23 04:21:07,467][11551] Num frames 13200... | |
| [2023-02-23 04:21:07,581][11551] Num frames 13300... | |
| [2023-02-23 04:21:07,701][11551] Num frames 13400... | |
| [2023-02-23 04:21:07,815][11551] Num frames 13500... | |
| [2023-02-23 04:21:07,936][11551] Num frames 13600... | |
| [2023-02-23 04:21:08,051][11551] Num frames 13700... | |
| [2023-02-23 04:21:08,164][11551] Num frames 13800... | |
| [2023-02-23 04:21:08,291][11551] Num frames 13900... | |
| [2023-02-23 04:21:08,404][11551] Num frames 14000... | |
| [2023-02-23 04:21:08,567][11551] Avg episode rewards: #0: 35.096, true rewards: #0: 14.096 | |
| [2023-02-23 04:21:08,569][11551] Avg episode reward: 35.096, avg true_objective: 14.096 | |
| [2023-02-23 04:22:32,293][11551] Replay video saved to /content/train_dir/default_experiment/replay.mp4! | |
| [2023-02-23 04:22:32,759][11551] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json | |
| [2023-02-23 04:22:32,762][11551] Overriding arg 'num_workers' with value 1 passed from command line | |
| [2023-02-23 04:22:32,764][11551] Adding new argument 'no_render'=True that is not in the saved config file! | |
| [2023-02-23 04:22:32,766][11551] Adding new argument 'save_video'=True that is not in the saved config file! | |
| [2023-02-23 04:22:32,768][11551] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file! | |
| [2023-02-23 04:22:32,770][11551] Adding new argument 'video_name'=None that is not in the saved config file! | |
| [2023-02-23 04:22:32,772][11551] Adding new argument 'max_num_frames'=100000 that is not in the saved config file! | |
| [2023-02-23 04:22:32,775][11551] Adding new argument 'max_num_episodes'=10 that is not in the saved config file! | |
| [2023-02-23 04:22:32,777][11551] Adding new argument 'push_to_hub'=True that is not in the saved config file! | |
| [2023-02-23 04:22:32,779][11551] Adding new argument 'hf_repository'='rahul-t-p/rl_course_vizdoom_health_gathering_supreme' that is not in the saved config file! | |
| [2023-02-23 04:22:32,781][11551] Adding new argument 'policy_index'=0 that is not in the saved config file! | |
| [2023-02-23 04:22:32,784][11551] Adding new argument 'eval_deterministic'=False that is not in the saved config file! | |
| [2023-02-23 04:22:32,786][11551] Adding new argument 'train_script'=None that is not in the saved config file! | |
| [2023-02-23 04:22:32,788][11551] Adding new argument 'enjoy_script'=None that is not in the saved config file! | |
| [2023-02-23 04:22:32,791][11551] Using frameskip 1 and render_action_repeat=4 for evaluation | |
| [2023-02-23 04:22:32,809][11551] RunningMeanStd input shape: (3, 72, 128) | |
| [2023-02-23 04:22:32,812][11551] RunningMeanStd input shape: (1,) | |
| [2023-02-23 04:22:32,832][11551] ConvEncoder: input_channels=3 | |
| [2023-02-23 04:22:32,886][11551] Conv encoder output size: 512 | |
| [2023-02-23 04:22:32,889][11551] Policy head output size: 512 | |
| [2023-02-23 04:22:32,916][11551] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... | |
| [2023-02-23 04:22:33,574][11551] Num frames 100... | |
| [2023-02-23 04:22:33,687][11551] Num frames 200... | |
| [2023-02-23 04:22:33,801][11551] Num frames 300... | |
| [2023-02-23 04:22:33,910][11551] Num frames 400... | |
| [2023-02-23 04:22:34,019][11551] Num frames 500... | |
| [2023-02-23 04:22:34,131][11551] Num frames 600... | |
| [2023-02-23 04:22:34,287][11551] Num frames 700... | |
| [2023-02-23 04:22:34,438][11551] Num frames 800... | |
| [2023-02-23 04:22:34,593][11551] Num frames 900... | |
| [2023-02-23 04:22:34,749][11551] Num frames 1000... | |
| [2023-02-23 04:22:34,879][11551] Avg episode rewards: #0: 19.490, true rewards: #0: 10.490 | |
| [2023-02-23 04:22:34,882][11551] Avg episode reward: 19.490, avg true_objective: 10.490 | |
| [2023-02-23 04:22:34,981][11551] Num frames 1100... | |
| [2023-02-23 04:22:35,137][11551] Num frames 1200... | |
| [2023-02-23 04:22:35,293][11551] Num frames 1300... | |
| [2023-02-23 04:22:35,444][11551] Num frames 1400... | |
| [2023-02-23 04:22:35,596][11551] Num frames 1500... | |
| [2023-02-23 04:22:35,751][11551] Num frames 1600... | |
| [2023-02-23 04:22:35,900][11551] Num frames 1700... | |
| [2023-02-23 04:22:36,059][11551] Num frames 1800... | |
| [2023-02-23 04:22:36,218][11551] Num frames 1900... | |
| [2023-02-23 04:22:36,375][11551] Num frames 2000... | |
| [2023-02-23 04:22:36,532][11551] Num frames 2100... | |
| [2023-02-23 04:22:36,693][11551] Num frames 2200... | |
| [2023-02-23 04:22:36,849][11551] Num frames 2300... | |
| [2023-02-23 04:22:37,007][11551] Num frames 2400... | |
| [2023-02-23 04:22:37,183][11551] Num frames 2500... | |
| [2023-02-23 04:22:37,345][11551] Num frames 2600... | |
| [2023-02-23 04:22:37,503][11551] Num frames 2700... | |
| [2023-02-23 04:22:37,670][11551] Num frames 2800... | |
| [2023-02-23 04:22:37,808][11551] Num frames 2900... | |
| [2023-02-23 04:22:37,927][11551] Num frames 3000... | |
| [2023-02-23 04:22:38,041][11551] Num frames 3100... | |
| [2023-02-23 04:22:38,152][11551] Avg episode rewards: #0: 41.244, true rewards: #0: 15.745 | |
| [2023-02-23 04:22:38,154][11551] Avg episode reward: 41.244, avg true_objective: 15.745 | |
| [2023-02-23 04:22:38,213][11551] Num frames 3200... | |
| [2023-02-23 04:22:38,319][11551] Num frames 3300... | |
| [2023-02-23 04:22:38,434][11551] Num frames 3400... | |
| [2023-02-23 04:22:38,542][11551] Num frames 3500... | |
| [2023-02-23 04:22:38,650][11551] Num frames 3600... | |
| [2023-02-23 04:22:38,757][11551] Num frames 3700... | |
| [2023-02-23 04:22:38,864][11551] Num frames 3800... | |
| [2023-02-23 04:22:38,974][11551] Num frames 3900... | |
| [2023-02-23 04:22:39,095][11551] Num frames 4000... | |
| [2023-02-23 04:22:39,205][11551] Num frames 4100... | |
| [2023-02-23 04:22:39,314][11551] Num frames 4200... | |
| [2023-02-23 04:22:39,431][11551] Num frames 4300... | |
| [2023-02-23 04:22:39,540][11551] Num frames 4400... | |
| [2023-02-23 04:22:39,696][11551] Avg episode rewards: #0: 37.643, true rewards: #0: 14.977 | |
| [2023-02-23 04:22:39,697][11551] Avg episode reward: 37.643, avg true_objective: 14.977 | |
| [2023-02-23 04:22:39,709][11551] Num frames 4500... | |
| [2023-02-23 04:22:39,817][11551] Num frames 4600... | |
| [2023-02-23 04:22:39,928][11551] Num frames 4700... | |
| [2023-02-23 04:22:40,044][11551] Num frames 4800... | |
| [2023-02-23 04:22:40,155][11551] Num frames 4900... | |
| [2023-02-23 04:22:40,264][11551] Num frames 5000... | |
| [2023-02-23 04:22:40,395][11551] Num frames 5100... | |
| [2023-02-23 04:22:40,501][11551] Num frames 5200... | |
| [2023-02-23 04:22:40,613][11551] Num frames 5300... | |
| [2023-02-23 04:22:40,722][11551] Num frames 5400... | |
| [2023-02-23 04:22:40,830][11551] Num frames 5500... | |
| [2023-02-23 04:22:40,941][11551] Num frames 5600... | |
| [2023-02-23 04:22:41,052][11551] Num frames 5700... | |
| [2023-02-23 04:22:41,163][11551] Num frames 5800... | |
| [2023-02-23 04:22:41,283][11551] Num frames 5900... | |
| [2023-02-23 04:22:41,400][11551] Num frames 6000... | |
| [2023-02-23 04:22:41,524][11551] Avg episode rewards: #0: 36.652, true rewards: #0: 15.152 | |
| [2023-02-23 04:22:41,526][11551] Avg episode reward: 36.652, avg true_objective: 15.152 | |
| [2023-02-23 04:22:41,573][11551] Num frames 6100... | |
| [2023-02-23 04:22:41,686][11551] Num frames 6200... | |
| [2023-02-23 04:22:41,800][11551] Num frames 6300... | |
| [2023-02-23 04:22:41,912][11551] Num frames 6400... | |
| [2023-02-23 04:22:42,026][11551] Num frames 6500... | |
| [2023-02-23 04:22:42,139][11551] Num frames 6600... | |
| [2023-02-23 04:22:42,252][11551] Num frames 6700... | |
| [2023-02-23 04:22:42,363][11551] Num frames 6800... | |
| [2023-02-23 04:22:42,479][11551] Num frames 6900... | |
| [2023-02-23 04:22:42,592][11551] Num frames 7000... | |
| [2023-02-23 04:22:42,703][11551] Num frames 7100... | |
| [2023-02-23 04:22:42,817][11551] Num frames 7200... | |
| [2023-02-23 04:22:42,928][11551] Num frames 7300... | |
| [2023-02-23 04:22:43,046][11551] Num frames 7400... | |
| [2023-02-23 04:22:43,145][11551] Avg episode rewards: #0: 35.674, true rewards: #0: 14.874 | |
| [2023-02-23 04:22:43,147][11551] Avg episode reward: 35.674, avg true_objective: 14.874 | |
| [2023-02-23 04:22:43,221][11551] Num frames 7500... | |
| [2023-02-23 04:22:43,342][11551] Num frames 7600... | |
| [2023-02-23 04:22:43,457][11551] Num frames 7700... | |
| [2023-02-23 04:22:43,568][11551] Num frames 7800... | |
| [2023-02-23 04:22:43,678][11551] Num frames 7900... | |
| [2023-02-23 04:22:43,787][11551] Num frames 8000... | |
| [2023-02-23 04:22:43,898][11551] Num frames 8100... | |
| [2023-02-23 04:22:43,965][11551] Avg episode rewards: #0: 31.515, true rewards: #0: 13.515 | |
| [2023-02-23 04:22:43,967][11551] Avg episode reward: 31.515, avg true_objective: 13.515 | |
| [2023-02-23 04:22:44,071][11551] Num frames 8200... | |
| [2023-02-23 04:22:44,185][11551] Num frames 8300... | |
| [2023-02-23 04:22:44,299][11551] Num frames 8400... | |
| [2023-02-23 04:22:44,414][11551] Num frames 8500... | |
| [2023-02-23 04:22:44,535][11551] Num frames 8600... | |
| [2023-02-23 04:22:44,648][11551] Num frames 8700... | |
| [2023-02-23 04:22:44,765][11551] Num frames 8800... | |
| [2023-02-23 04:22:44,879][11551] Num frames 8900... | |
| [2023-02-23 04:22:44,994][11551] Num frames 9000... | |
| [2023-02-23 04:22:45,107][11551] Num frames 9100... | |
| [2023-02-23 04:22:45,223][11551] Num frames 9200... | |
| [2023-02-23 04:22:45,335][11551] Num frames 9300... | |
| [2023-02-23 04:22:45,448][11551] Num frames 9400... | |
| [2023-02-23 04:22:45,606][11551] Avg episode rewards: #0: 31.978, true rewards: #0: 13.550 | |
| [2023-02-23 04:22:45,608][11551] Avg episode reward: 31.978, avg true_objective: 13.550 | |
| [2023-02-23 04:22:45,630][11551] Num frames 9500... | |
| [2023-02-23 04:22:45,741][11551] Num frames 9600... | |
| [2023-02-23 04:22:45,852][11551] Num frames 9700... | |
| [2023-02-23 04:22:45,965][11551] Num frames 9800... | |
| [2023-02-23 04:22:46,080][11551] Num frames 9900... | |
| [2023-02-23 04:22:46,195][11551] Num frames 10000... | |
| [2023-02-23 04:22:46,306][11551] Num frames 10100... | |
| [2023-02-23 04:22:46,419][11551] Num frames 10200... | |
| [2023-02-23 04:22:46,537][11551] Num frames 10300... | |
| [2023-02-23 04:22:46,654][11551] Num frames 10400... | |
| [2023-02-23 04:22:46,766][11551] Num frames 10500... | |
| [2023-02-23 04:22:46,882][11551] Num frames 10600... | |
| [2023-02-23 04:22:46,998][11551] Num frames 10700... | |
| [2023-02-23 04:22:47,116][11551] Num frames 10800... | |
| [2023-02-23 04:22:47,238][11551] Num frames 10900... | |
| [2023-02-23 04:22:47,348][11551] Num frames 11000... | |
| [2023-02-23 04:22:47,461][11551] Num frames 11100... | |
| [2023-02-23 04:22:47,580][11551] Num frames 11200... | |
| [2023-02-23 04:22:47,695][11551] Num frames 11300... | |
| [2023-02-23 04:22:47,847][11551] Num frames 11400... | |
| [2023-02-23 04:22:48,005][11551] Num frames 11500... | |
| [2023-02-23 04:22:48,206][11551] Avg episode rewards: #0: 34.981, true rewards: #0: 14.481 | |
| [2023-02-23 04:22:48,208][11551] Avg episode reward: 34.981, avg true_objective: 14.481 | |
| [2023-02-23 04:22:48,235][11551] Num frames 11600... | |
| [2023-02-23 04:22:48,388][11551] Num frames 11700... | |
| [2023-02-23 04:22:48,549][11551] Num frames 11800... | |
| [2023-02-23 04:22:48,704][11551] Num frames 11900... | |
| [2023-02-23 04:22:48,863][11551] Num frames 12000... | |
| [2023-02-23 04:22:48,982][11551] Avg episode rewards: #0: 31.703, true rewards: #0: 13.370 | |
| [2023-02-23 04:22:48,986][11551] Avg episode reward: 31.703, avg true_objective: 13.370 | |
| [2023-02-23 04:22:49,120][11551] Num frames 12100... | |
| [2023-02-23 04:22:49,306][11551] Num frames 12200... | |
| [2023-02-23 04:22:49,505][11551] Num frames 12300... | |
| [2023-02-23 04:22:49,699][11551] Num frames 12400... | |
| [2023-02-23 04:22:49,890][11551] Num frames 12500... | |
| [2023-02-23 04:22:49,953][11551] Avg episode rewards: #0: 29.301, true rewards: #0: 12.501 | |
| [2023-02-23 04:22:49,956][11551] Avg episode reward: 29.301, avg true_objective: 12.501 | |
| [2023-02-23 04:24:02,747][11551] Replay video saved to /content/train_dir/default_experiment/replay.mp4! | |