diff --git "a/sf_log.txt" "b/sf_log.txt" new file mode 100644--- /dev/null +++ "b/sf_log.txt" @@ -0,0 +1,1130 @@ +[2023-02-25 16:58:22,542][09465] Saving configuration to /content/train_dir/default_experiment/config.json... +[2023-02-25 16:58:22,545][09465] Rollout worker 0 uses device cpu +[2023-02-25 16:58:22,547][09465] Rollout worker 1 uses device cpu +[2023-02-25 16:58:22,548][09465] Rollout worker 2 uses device cpu +[2023-02-25 16:58:22,549][09465] Rollout worker 3 uses device cpu +[2023-02-25 16:58:22,551][09465] Rollout worker 4 uses device cpu +[2023-02-25 16:58:22,552][09465] Rollout worker 5 uses device cpu +[2023-02-25 16:58:22,553][09465] Rollout worker 6 uses device cpu +[2023-02-25 16:58:22,555][09465] Rollout worker 7 uses device cpu +[2023-02-25 16:58:22,748][09465] Using GPUs [0] for process 0 (actually maps to GPUs [0]) +[2023-02-25 16:58:22,750][09465] InferenceWorker_p0-w0: min num requests: 2 +[2023-02-25 16:58:22,782][09465] Starting all processes... +[2023-02-25 16:58:22,783][09465] Starting process learner_proc0 +[2023-02-25 16:58:22,840][09465] Starting all processes... +[2023-02-25 16:58:22,858][09465] Starting process inference_proc0-0 +[2023-02-25 16:58:22,858][09465] Starting process rollout_proc0 +[2023-02-25 16:58:22,862][09465] Starting process rollout_proc1 +[2023-02-25 16:58:22,889][09465] Starting process rollout_proc2 +[2023-02-25 16:58:22,891][09465] Starting process rollout_proc3 +[2023-02-25 16:58:22,891][09465] Starting process rollout_proc4 +[2023-02-25 16:58:22,891][09465] Starting process rollout_proc5 +[2023-02-25 16:58:22,891][09465] Starting process rollout_proc6 +[2023-02-25 16:58:22,891][09465] Starting process rollout_proc7 +[2023-02-25 16:58:34,547][15489] Worker 1 uses CPU cores [1] +[2023-02-25 16:58:34,618][15469] Using GPUs [0] for process 0 (actually maps to GPUs [0]) +[2023-02-25 16:58:34,618][15469] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0 +[2023-02-25 16:58:34,859][15488] Using GPUs [0] for process 0 (actually maps to GPUs [0]) +[2023-02-25 16:58:34,860][15488] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0 +[2023-02-25 16:58:34,864][15487] Worker 0 uses CPU cores [0] +[2023-02-25 16:58:34,879][15491] Worker 3 uses CPU cores [1] +[2023-02-25 16:58:34,968][15494] Worker 6 uses CPU cores [0] +[2023-02-25 16:58:34,973][15493] Worker 5 uses CPU cores [1] +[2023-02-25 16:58:34,996][15495] Worker 7 uses CPU cores [1] +[2023-02-25 16:58:35,016][15490] Worker 2 uses CPU cores [0] +[2023-02-25 16:58:35,018][15492] Worker 4 uses CPU cores [0] +[2023-02-25 16:58:35,465][15469] Num visible devices: 1 +[2023-02-25 16:58:35,466][15488] Num visible devices: 1 +[2023-02-25 16:58:35,477][15469] Starting seed is not provided +[2023-02-25 16:58:35,477][15469] Using GPUs [0] for process 0 (actually maps to GPUs [0]) +[2023-02-25 16:58:35,478][15469] Initializing actor-critic model on device cuda:0 +[2023-02-25 16:58:35,478][15469] RunningMeanStd input shape: (3, 72, 128) +[2023-02-25 16:58:35,480][15469] RunningMeanStd input shape: (1,) +[2023-02-25 16:58:35,492][15469] ConvEncoder: input_channels=3 +[2023-02-25 16:58:35,767][15469] Conv encoder output size: 512 +[2023-02-25 16:58:35,768][15469] Policy head output size: 512 +[2023-02-25 16:58:35,816][15469] Created Actor Critic model with architecture: +[2023-02-25 16:58:35,817][15469] 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) + ) +) +[2023-02-25 16:58:42,740][09465] Heartbeat connected on Batcher_0 +[2023-02-25 16:58:42,748][09465] Heartbeat connected on InferenceWorker_p0-w0 +[2023-02-25 16:58:42,758][09465] Heartbeat connected on RolloutWorker_w0 +[2023-02-25 16:58:42,762][09465] Heartbeat connected on RolloutWorker_w1 +[2023-02-25 16:58:42,765][09465] Heartbeat connected on RolloutWorker_w2 +[2023-02-25 16:58:42,769][09465] Heartbeat connected on RolloutWorker_w3 +[2023-02-25 16:58:42,772][09465] Heartbeat connected on RolloutWorker_w4 +[2023-02-25 16:58:42,780][09465] Heartbeat connected on RolloutWorker_w5 +[2023-02-25 16:58:42,781][09465] Heartbeat connected on RolloutWorker_w6 +[2023-02-25 16:58:42,783][09465] Heartbeat connected on RolloutWorker_w7 +[2023-02-25 16:58:42,902][15469] Using optimizer +[2023-02-25 16:58:42,903][15469] No checkpoints found +[2023-02-25 16:58:42,903][15469] Did not load from checkpoint, starting from scratch! +[2023-02-25 16:58:42,903][15469] Initialized policy 0 weights for model version 0 +[2023-02-25 16:58:42,907][15469] LearnerWorker_p0 finished initialization! +[2023-02-25 16:58:42,910][15469] Using GPUs [0] for process 0 (actually maps to GPUs [0]) +[2023-02-25 16:58:42,910][09465] Heartbeat connected on LearnerWorker_p0 +[2023-02-25 16:58:43,179][15488] RunningMeanStd input shape: (3, 72, 128) +[2023-02-25 16:58:43,181][15488] RunningMeanStd input shape: (1,) +[2023-02-25 16:58:43,200][15488] ConvEncoder: input_channels=3 +[2023-02-25 16:58:43,359][15488] Conv encoder output size: 512 +[2023-02-25 16:58:43,360][15488] Policy head output size: 512 +[2023-02-25 16:58:43,467][09465] 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) +[2023-02-25 16:58:46,580][09465] Inference worker 0-0 is ready! +[2023-02-25 16:58:46,583][09465] All inference workers are ready! Signal rollout workers to start! +[2023-02-25 16:58:46,728][15495] Doom resolution: 160x120, resize resolution: (128, 72) +[2023-02-25 16:58:46,746][15489] Doom resolution: 160x120, resize resolution: (128, 72) +[2023-02-25 16:58:46,751][15491] Doom resolution: 160x120, resize resolution: (128, 72) +[2023-02-25 16:58:46,790][15493] Doom resolution: 160x120, resize resolution: (128, 72) +[2023-02-25 16:58:46,820][15492] Doom resolution: 160x120, resize resolution: (128, 72) +[2023-02-25 16:58:46,823][15490] Doom resolution: 160x120, resize resolution: (128, 72) +[2023-02-25 16:58:46,827][15487] Doom resolution: 160x120, resize resolution: (128, 72) +[2023-02-25 16:58:46,859][15494] Doom resolution: 160x120, resize resolution: (128, 72) +[2023-02-25 16:58:48,184][15495] Decorrelating experience for 0 frames... +[2023-02-25 16:58:48,186][15493] Decorrelating experience for 0 frames... +[2023-02-25 16:58:48,187][15491] Decorrelating experience for 0 frames... +[2023-02-25 16:58:48,314][15487] Decorrelating experience for 0 frames... +[2023-02-25 16:58:48,319][15490] Decorrelating experience for 0 frames... +[2023-02-25 16:58:48,322][15492] Decorrelating experience for 0 frames... +[2023-02-25 16:58:48,467][09465] 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) +[2023-02-25 16:58:49,041][15492] Decorrelating experience for 32 frames... +[2023-02-25 16:58:49,061][15494] Decorrelating experience for 0 frames... +[2023-02-25 16:58:49,217][15493] Decorrelating experience for 32 frames... +[2023-02-25 16:58:49,220][15489] Decorrelating experience for 0 frames... +[2023-02-25 16:58:49,453][15491] Decorrelating experience for 32 frames... +[2023-02-25 16:58:50,058][15492] Decorrelating experience for 64 frames... +[2023-02-25 16:58:50,111][15489] Decorrelating experience for 32 frames... +[2023-02-25 16:58:50,239][15493] Decorrelating experience for 64 frames... +[2023-02-25 16:58:50,486][15490] Decorrelating experience for 32 frames... +[2023-02-25 16:58:50,492][15487] Decorrelating experience for 32 frames... +[2023-02-25 16:58:50,787][15494] Decorrelating experience for 32 frames... +[2023-02-25 16:58:51,592][15489] Decorrelating experience for 64 frames... +[2023-02-25 16:58:51,612][15491] Decorrelating experience for 64 frames... +[2023-02-25 16:58:51,639][15492] Decorrelating experience for 96 frames... +[2023-02-25 16:58:51,764][15493] Decorrelating experience for 96 frames... +[2023-02-25 16:58:51,843][15487] Decorrelating experience for 64 frames... +[2023-02-25 16:58:51,983][15495] Decorrelating experience for 32 frames... +[2023-02-25 16:58:52,099][15494] Decorrelating experience for 64 frames... +[2023-02-25 16:58:52,985][15489] Decorrelating experience for 96 frames... +[2023-02-25 16:58:53,130][15487] Decorrelating experience for 96 frames... +[2023-02-25 16:58:53,212][15491] Decorrelating experience for 96 frames... +[2023-02-25 16:58:53,365][15495] Decorrelating experience for 64 frames... +[2023-02-25 16:58:53,451][15494] Decorrelating experience for 96 frames... +[2023-02-25 16:58:53,468][09465] 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) +[2023-02-25 16:58:53,847][15495] Decorrelating experience for 96 frames... +[2023-02-25 16:58:54,057][15490] Decorrelating experience for 64 frames... +[2023-02-25 16:58:54,385][15490] Decorrelating experience for 96 frames... +[2023-02-25 16:58:58,467][09465] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 2.9. Samples: 44. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) +[2023-02-25 16:58:58,472][09465] Avg episode reward: [(0, '1.685')] +[2023-02-25 16:58:58,903][15469] Signal inference workers to stop experience collection... +[2023-02-25 16:58:58,934][15488] InferenceWorker_p0-w0: stopping experience collection +[2023-02-25 16:59:01,813][15469] Signal inference workers to resume experience collection... +[2023-02-25 16:59:01,814][15488] InferenceWorker_p0-w0: resuming experience collection +[2023-02-25 16:59:03,469][09465] Fps is (10 sec: 409.5, 60 sec: 204.8, 300 sec: 204.8). Total num frames: 4096. Throughput: 0: 115.3. Samples: 2306. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) +[2023-02-25 16:59:03,476][09465] Avg episode reward: [(0, '2.362')] +[2023-02-25 16:59:08,467][09465] Fps is (10 sec: 2867.2, 60 sec: 1146.9, 300 sec: 1146.9). Total num frames: 28672. Throughput: 0: 258.5. Samples: 6462. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) +[2023-02-25 16:59:08,475][09465] Avg episode reward: [(0, '3.760')] +[2023-02-25 16:59:11,424][15488] Updated weights for policy 0, policy_version 10 (0.0014) +[2023-02-25 16:59:13,467][09465] Fps is (10 sec: 4506.3, 60 sec: 1638.4, 300 sec: 1638.4). Total num frames: 49152. Throughput: 0: 328.0. Samples: 9840. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-02-25 16:59:13,470][09465] Avg episode reward: [(0, '4.381')] +[2023-02-25 16:59:18,468][09465] Fps is (10 sec: 3686.4, 60 sec: 1872.5, 300 sec: 1872.5). Total num frames: 65536. Throughput: 0: 463.9. Samples: 16238. Policy #0 lag: (min: 0.0, avg: 0.3, max: 2.0) +[2023-02-25 16:59:18,472][09465] Avg episode reward: [(0, '4.376')] +[2023-02-25 16:59:23,056][15488] Updated weights for policy 0, policy_version 20 (0.0014) +[2023-02-25 16:59:23,467][09465] Fps is (10 sec: 3276.8, 60 sec: 2048.0, 300 sec: 2048.0). Total num frames: 81920. Throughput: 0: 517.0. Samples: 20678. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-25 16:59:23,470][09465] Avg episode reward: [(0, '4.431')] +[2023-02-25 16:59:28,467][09465] Fps is (10 sec: 3686.4, 60 sec: 2275.6, 300 sec: 2275.6). Total num frames: 102400. Throughput: 0: 510.0. Samples: 22950. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-02-25 16:59:28,469][09465] Avg episode reward: [(0, '4.296')] +[2023-02-25 16:59:28,482][15469] Saving new best policy, reward=4.296! +[2023-02-25 16:59:32,757][15488] Updated weights for policy 0, policy_version 30 (0.0023) +[2023-02-25 16:59:33,474][09465] Fps is (10 sec: 4093.1, 60 sec: 2457.3, 300 sec: 2457.3). Total num frames: 122880. Throughput: 0: 663.4. Samples: 29858. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2023-02-25 16:59:33,478][09465] Avg episode reward: [(0, '4.362')] +[2023-02-25 16:59:33,482][15469] Saving new best policy, reward=4.362! +[2023-02-25 16:59:38,467][09465] Fps is (10 sec: 4096.0, 60 sec: 2606.5, 300 sec: 2606.5). Total num frames: 143360. Throughput: 0: 794.6. Samples: 35758. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-25 16:59:38,481][09465] Avg episode reward: [(0, '4.358')] +[2023-02-25 16:59:43,468][09465] Fps is (10 sec: 3279.1, 60 sec: 2594.1, 300 sec: 2594.1). Total num frames: 155648. Throughput: 0: 843.1. Samples: 37982. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-25 16:59:43,470][09465] Avg episode reward: [(0, '4.207')] +[2023-02-25 16:59:45,543][15488] Updated weights for policy 0, policy_version 40 (0.0025) +[2023-02-25 16:59:48,467][09465] Fps is (10 sec: 3276.8, 60 sec: 2935.5, 300 sec: 2709.7). Total num frames: 176128. Throughput: 0: 898.8. Samples: 42750. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-02-25 16:59:48,469][09465] Avg episode reward: [(0, '4.241')] +[2023-02-25 16:59:53,468][09465] Fps is (10 sec: 3686.4, 60 sec: 3208.5, 300 sec: 2750.2). Total num frames: 192512. Throughput: 0: 941.8. Samples: 48842. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-02-25 16:59:53,470][09465] Avg episode reward: [(0, '4.382')] +[2023-02-25 16:59:53,476][15469] Saving new best policy, reward=4.382! +[2023-02-25 16:59:56,466][15488] Updated weights for policy 0, policy_version 50 (0.0014) +[2023-02-25 16:59:58,469][09465] Fps is (10 sec: 3276.3, 60 sec: 3481.5, 300 sec: 2785.2). Total num frames: 208896. Throughput: 0: 915.1. Samples: 51020. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-02-25 16:59:58,472][09465] Avg episode reward: [(0, '4.373')] +[2023-02-25 17:00:03,467][09465] Fps is (10 sec: 2867.2, 60 sec: 3618.2, 300 sec: 2764.8). Total num frames: 221184. Throughput: 0: 870.7. Samples: 55418. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2023-02-25 17:00:03,470][09465] Avg episode reward: [(0, '4.384')] +[2023-02-25 17:00:03,480][15469] Saving new best policy, reward=4.384! +[2023-02-25 17:00:08,467][09465] Fps is (10 sec: 3277.3, 60 sec: 3549.9, 300 sec: 2843.1). Total num frames: 241664. Throughput: 0: 883.4. Samples: 60432. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-25 17:00:08,471][09465] Avg episode reward: [(0, '4.520')] +[2023-02-25 17:00:08,484][15469] Saving new best policy, reward=4.520! +[2023-02-25 17:00:08,939][15488] Updated weights for policy 0, policy_version 60 (0.0033) +[2023-02-25 17:00:13,467][09465] Fps is (10 sec: 4096.0, 60 sec: 3549.9, 300 sec: 2912.7). Total num frames: 262144. Throughput: 0: 907.0. Samples: 63764. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2023-02-25 17:00:13,473][09465] Avg episode reward: [(0, '4.478')] +[2023-02-25 17:00:18,468][09465] Fps is (10 sec: 4095.8, 60 sec: 3618.1, 300 sec: 2975.0). Total num frames: 282624. Throughput: 0: 897.0. Samples: 70218. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-02-25 17:00:18,474][09465] Avg episode reward: [(0, '4.411')] +[2023-02-25 17:00:18,489][15469] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000069_282624.pth... +[2023-02-25 17:00:19,513][15488] Updated weights for policy 0, policy_version 70 (0.0019) +[2023-02-25 17:00:23,467][09465] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 2949.1). Total num frames: 294912. Throughput: 0: 860.4. Samples: 74474. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-25 17:00:23,473][09465] Avg episode reward: [(0, '4.402')] +[2023-02-25 17:00:28,468][09465] Fps is (10 sec: 3276.9, 60 sec: 3549.9, 300 sec: 3003.7). Total num frames: 315392. Throughput: 0: 860.9. Samples: 76724. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-02-25 17:00:28,474][09465] Avg episode reward: [(0, '4.349')] +[2023-02-25 17:00:30,524][15488] Updated weights for policy 0, policy_version 80 (0.0018) +[2023-02-25 17:00:33,468][09465] Fps is (10 sec: 4505.5, 60 sec: 3618.5, 300 sec: 3090.6). Total num frames: 339968. Throughput: 0: 909.6. Samples: 83682. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2023-02-25 17:00:33,470][09465] Avg episode reward: [(0, '4.407')] +[2023-02-25 17:00:38,467][09465] Fps is (10 sec: 4096.0, 60 sec: 3549.9, 300 sec: 3098.7). Total num frames: 356352. Throughput: 0: 908.5. Samples: 89726. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-02-25 17:00:38,473][09465] Avg episode reward: [(0, '4.313')] +[2023-02-25 17:00:41,808][15488] Updated weights for policy 0, policy_version 90 (0.0018) +[2023-02-25 17:00:43,467][09465] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3106.1). Total num frames: 372736. Throughput: 0: 908.4. Samples: 91896. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-02-25 17:00:43,472][09465] Avg episode reward: [(0, '4.322')] +[2023-02-25 17:00:48,467][09465] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3113.0). Total num frames: 389120. Throughput: 0: 918.3. Samples: 96742. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2023-02-25 17:00:48,474][09465] Avg episode reward: [(0, '4.391')] +[2023-02-25 17:00:52,086][15488] Updated weights for policy 0, policy_version 100 (0.0021) +[2023-02-25 17:00:53,467][09465] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3182.3). Total num frames: 413696. Throughput: 0: 957.3. Samples: 103510. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-02-25 17:00:53,470][09465] Avg episode reward: [(0, '4.341')] +[2023-02-25 17:00:58,467][09465] Fps is (10 sec: 4096.0, 60 sec: 3686.5, 300 sec: 3185.8). Total num frames: 430080. Throughput: 0: 957.2. Samples: 106840. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-02-25 17:00:58,482][09465] Avg episode reward: [(0, '4.413')] +[2023-02-25 17:01:03,467][09465] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3189.0). Total num frames: 446464. Throughput: 0: 910.5. Samples: 111188. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-25 17:01:03,474][09465] Avg episode reward: [(0, '4.468')] +[2023-02-25 17:01:04,354][15488] Updated weights for policy 0, policy_version 110 (0.0020) +[2023-02-25 17:01:08,468][09465] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3220.3). Total num frames: 466944. Throughput: 0: 930.1. Samples: 116328. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-25 17:01:08,470][09465] Avg episode reward: [(0, '4.405')] +[2023-02-25 17:01:13,467][09465] Fps is (10 sec: 4096.0, 60 sec: 3754.7, 300 sec: 3249.5). Total num frames: 487424. Throughput: 0: 957.0. Samples: 119788. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-02-25 17:01:13,472][09465] Avg episode reward: [(0, '4.431')] +[2023-02-25 17:01:13,884][15488] Updated weights for policy 0, policy_version 120 (0.0018) +[2023-02-25 17:01:18,467][09465] Fps is (10 sec: 3686.4, 60 sec: 3686.4, 300 sec: 3250.4). Total num frames: 503808. Throughput: 0: 947.5. Samples: 126320. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) +[2023-02-25 17:01:18,477][09465] Avg episode reward: [(0, '4.511')] +[2023-02-25 17:01:23,467][09465] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3251.2). Total num frames: 520192. Throughput: 0: 910.4. Samples: 130692. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2023-02-25 17:01:23,470][09465] Avg episode reward: [(0, '4.546')] +[2023-02-25 17:01:23,476][15469] Saving new best policy, reward=4.546! +[2023-02-25 17:01:26,464][15488] Updated weights for policy 0, policy_version 130 (0.0020) +[2023-02-25 17:01:28,491][09465] Fps is (10 sec: 3677.9, 60 sec: 3753.2, 300 sec: 3276.3). Total num frames: 540672. Throughput: 0: 908.9. Samples: 132816. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-02-25 17:01:28,499][09465] Avg episode reward: [(0, '4.520')] +[2023-02-25 17:01:33,467][09465] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3300.9). Total num frames: 561152. Throughput: 0: 954.6. Samples: 139698. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-25 17:01:33,475][09465] Avg episode reward: [(0, '4.543')] +[2023-02-25 17:01:35,495][15488] Updated weights for policy 0, policy_version 140 (0.0032) +[2023-02-25 17:01:38,467][09465] Fps is (10 sec: 4105.5, 60 sec: 3754.7, 300 sec: 3323.6). Total num frames: 581632. Throughput: 0: 939.9. Samples: 145804. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2023-02-25 17:01:38,474][09465] Avg episode reward: [(0, '4.687')] +[2023-02-25 17:01:38,487][15469] Saving new best policy, reward=4.687! +[2023-02-25 17:01:43,467][09465] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3322.3). Total num frames: 598016. Throughput: 0: 913.8. Samples: 147960. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-02-25 17:01:43,474][09465] Avg episode reward: [(0, '4.514')] +[2023-02-25 17:01:48,016][15488] Updated weights for policy 0, policy_version 150 (0.0015) +[2023-02-25 17:01:48,467][09465] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3321.1). Total num frames: 614400. Throughput: 0: 918.6. Samples: 152524. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-25 17:01:48,470][09465] Avg episode reward: [(0, '4.204')] +[2023-02-25 17:01:53,467][09465] Fps is (10 sec: 3686.4, 60 sec: 3686.4, 300 sec: 3341.5). Total num frames: 634880. Throughput: 0: 957.5. Samples: 159416. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-02-25 17:01:53,475][09465] Avg episode reward: [(0, '4.462')] +[2023-02-25 17:01:57,795][15488] Updated weights for policy 0, policy_version 160 (0.0017) +[2023-02-25 17:01:58,468][09465] Fps is (10 sec: 4095.9, 60 sec: 3754.6, 300 sec: 3360.8). Total num frames: 655360. Throughput: 0: 956.7. Samples: 162838. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-25 17:01:58,470][09465] Avg episode reward: [(0, '4.690')] +[2023-02-25 17:01:58,485][15469] Saving new best policy, reward=4.690! +[2023-02-25 17:02:03,467][09465] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3338.2). Total num frames: 667648. Throughput: 0: 893.6. Samples: 166534. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-25 17:02:03,470][09465] Avg episode reward: [(0, '4.736')] +[2023-02-25 17:02:03,474][15469] Saving new best policy, reward=4.736! +[2023-02-25 17:02:08,469][09465] Fps is (10 sec: 2457.3, 60 sec: 3549.8, 300 sec: 3316.7). Total num frames: 679936. Throughput: 0: 873.8. Samples: 170014. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2023-02-25 17:02:08,472][09465] Avg episode reward: [(0, '4.589')] +[2023-02-25 17:02:13,297][15488] Updated weights for policy 0, policy_version 170 (0.0043) +[2023-02-25 17:02:13,467][09465] Fps is (10 sec: 2867.2, 60 sec: 3481.6, 300 sec: 3315.8). Total num frames: 696320. Throughput: 0: 870.3. Samples: 171960. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-25 17:02:13,474][09465] Avg episode reward: [(0, '4.563')] +[2023-02-25 17:02:18,467][09465] Fps is (10 sec: 3687.0, 60 sec: 3549.9, 300 sec: 3334.0). Total num frames: 716800. Throughput: 0: 863.1. Samples: 178538. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-02-25 17:02:18,469][09465] Avg episode reward: [(0, '4.455')] +[2023-02-25 17:02:18,486][15469] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000175_716800.pth... +[2023-02-25 17:02:22,582][15488] Updated weights for policy 0, policy_version 180 (0.0022) +[2023-02-25 17:02:23,467][09465] Fps is (10 sec: 4096.0, 60 sec: 3618.1, 300 sec: 3351.3). Total num frames: 737280. Throughput: 0: 869.0. Samples: 184908. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-02-25 17:02:23,473][09465] Avg episode reward: [(0, '4.441')] +[2023-02-25 17:02:28,467][09465] Fps is (10 sec: 3686.4, 60 sec: 3551.2, 300 sec: 3349.6). Total num frames: 753664. Throughput: 0: 869.5. Samples: 187088. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-25 17:02:28,473][09465] Avg episode reward: [(0, '4.441')] +[2023-02-25 17:02:33,467][09465] Fps is (10 sec: 3276.8, 60 sec: 3481.6, 300 sec: 3348.0). Total num frames: 770048. Throughput: 0: 866.8. Samples: 191528. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) +[2023-02-25 17:02:33,472][09465] Avg episode reward: [(0, '4.606')] +[2023-02-25 17:02:34,754][15488] Updated weights for policy 0, policy_version 190 (0.0023) +[2023-02-25 17:02:38,467][09465] Fps is (10 sec: 4096.0, 60 sec: 3549.9, 300 sec: 3381.4). Total num frames: 794624. Throughput: 0: 864.3. Samples: 198308. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) +[2023-02-25 17:02:38,472][09465] Avg episode reward: [(0, '4.747')] +[2023-02-25 17:02:38,486][15469] Saving new best policy, reward=4.747! +[2023-02-25 17:02:43,467][09465] Fps is (10 sec: 4096.0, 60 sec: 3549.9, 300 sec: 3379.2). Total num frames: 811008. Throughput: 0: 863.5. Samples: 201694. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-02-25 17:02:43,469][09465] Avg episode reward: [(0, '4.766')] +[2023-02-25 17:02:43,476][15469] Saving new best policy, reward=4.766! +[2023-02-25 17:02:45,064][15488] Updated weights for policy 0, policy_version 200 (0.0029) +[2023-02-25 17:02:48,467][09465] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3377.1). Total num frames: 827392. Throughput: 0: 885.6. Samples: 206384. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2023-02-25 17:02:48,473][09465] Avg episode reward: [(0, '4.678')] +[2023-02-25 17:02:53,467][09465] Fps is (10 sec: 3276.8, 60 sec: 3481.6, 300 sec: 3375.1). Total num frames: 843776. Throughput: 0: 914.7. Samples: 211172. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-25 17:02:53,470][09465] Avg episode reward: [(0, '4.643')] +[2023-02-25 17:02:56,478][15488] Updated weights for policy 0, policy_version 210 (0.0025) +[2023-02-25 17:02:58,467][09465] Fps is (10 sec: 4096.0, 60 sec: 3549.9, 300 sec: 3405.3). Total num frames: 868352. Throughput: 0: 947.9. Samples: 214616. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2023-02-25 17:02:58,472][09465] Avg episode reward: [(0, '4.467')] +[2023-02-25 17:03:03,470][09465] Fps is (10 sec: 4504.4, 60 sec: 3686.2, 300 sec: 3418.6). Total num frames: 888832. Throughput: 0: 956.1. Samples: 221566. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-25 17:03:03,473][09465] Avg episode reward: [(0, '4.749')] +[2023-02-25 17:03:07,389][15488] Updated weights for policy 0, policy_version 220 (0.0032) +[2023-02-25 17:03:08,472][09465] Fps is (10 sec: 3275.3, 60 sec: 3686.2, 300 sec: 3400.4). Total num frames: 901120. Throughput: 0: 913.5. Samples: 226020. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-02-25 17:03:08,475][09465] Avg episode reward: [(0, '4.785')] +[2023-02-25 17:03:08,492][15469] Saving new best policy, reward=4.785! +[2023-02-25 17:03:13,467][09465] Fps is (10 sec: 2867.9, 60 sec: 3686.4, 300 sec: 3398.2). Total num frames: 917504. Throughput: 0: 913.3. Samples: 228186. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-25 17:03:13,470][09465] Avg episode reward: [(0, '4.545')] +[2023-02-25 17:03:17,961][15488] Updated weights for policy 0, policy_version 230 (0.0022) +[2023-02-25 17:03:18,467][09465] Fps is (10 sec: 4097.9, 60 sec: 3754.7, 300 sec: 3425.7). Total num frames: 942080. Throughput: 0: 955.3. Samples: 234516. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-02-25 17:03:18,470][09465] Avg episode reward: [(0, '4.439')] +[2023-02-25 17:03:23,467][09465] Fps is (10 sec: 4505.6, 60 sec: 3754.7, 300 sec: 3437.7). Total num frames: 962560. Throughput: 0: 953.9. Samples: 241232. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-02-25 17:03:23,470][09465] Avg episode reward: [(0, '4.627')] +[2023-02-25 17:03:28,467][09465] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3434.9). Total num frames: 978944. Throughput: 0: 926.0. Samples: 243366. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-25 17:03:28,472][09465] Avg episode reward: [(0, '4.775')] +[2023-02-25 17:03:29,597][15488] Updated weights for policy 0, policy_version 240 (0.0011) +[2023-02-25 17:03:33,467][09465] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3432.2). Total num frames: 995328. Throughput: 0: 918.9. Samples: 247736. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-25 17:03:33,471][09465] Avg episode reward: [(0, '4.699')] +[2023-02-25 17:03:38,467][09465] Fps is (10 sec: 3686.4, 60 sec: 3686.4, 300 sec: 3443.4). Total num frames: 1015808. Throughput: 0: 958.6. Samples: 254310. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-25 17:03:38,477][09465] Avg episode reward: [(0, '4.731')] +[2023-02-25 17:03:39,546][15488] Updated weights for policy 0, policy_version 250 (0.0012) +[2023-02-25 17:03:43,467][09465] Fps is (10 sec: 4096.0, 60 sec: 3754.7, 300 sec: 3512.8). Total num frames: 1036288. Throughput: 0: 956.8. Samples: 257672. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-25 17:03:43,474][09465] Avg episode reward: [(0, '4.796')] +[2023-02-25 17:03:43,552][15469] Saving new best policy, reward=4.796! +[2023-02-25 17:03:48,467][09465] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3568.4). Total num frames: 1052672. Throughput: 0: 915.6. Samples: 262764. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-25 17:03:48,470][09465] Avg episode reward: [(0, '4.815')] +[2023-02-25 17:03:48,490][15469] Saving new best policy, reward=4.815! +[2023-02-25 17:03:52,326][15488] Updated weights for policy 0, policy_version 260 (0.0031) +[2023-02-25 17:03:53,467][09465] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3623.9). Total num frames: 1069056. Throughput: 0: 914.1. Samples: 267148. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-25 17:03:53,469][09465] Avg episode reward: [(0, '4.858')] +[2023-02-25 17:03:53,480][15469] Saving new best policy, reward=4.858! +[2023-02-25 17:03:58,467][09465] Fps is (10 sec: 3686.4, 60 sec: 3686.4, 300 sec: 3679.5). Total num frames: 1089536. Throughput: 0: 938.5. Samples: 270418. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-02-25 17:03:58,470][09465] Avg episode reward: [(0, '5.118')] +[2023-02-25 17:03:58,484][15469] Saving new best policy, reward=5.118! +[2023-02-25 17:04:01,436][15488] Updated weights for policy 0, policy_version 270 (0.0020) +[2023-02-25 17:04:03,467][09465] Fps is (10 sec: 4096.0, 60 sec: 3686.6, 300 sec: 3665.6). Total num frames: 1110016. Throughput: 0: 948.0. Samples: 277178. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-02-25 17:04:03,470][09465] Avg episode reward: [(0, '5.170')] +[2023-02-25 17:04:03,524][15469] Saving new best policy, reward=5.170! +[2023-02-25 17:04:08,470][09465] Fps is (10 sec: 3685.4, 60 sec: 3754.8, 300 sec: 3651.7). Total num frames: 1126400. Throughput: 0: 904.8. Samples: 281950. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2023-02-25 17:04:08,473][09465] Avg episode reward: [(0, '5.106')] +[2023-02-25 17:04:13,467][09465] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3651.7). Total num frames: 1142784. Throughput: 0: 905.4. Samples: 284108. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-25 17:04:13,474][09465] Avg episode reward: [(0, '4.946')] +[2023-02-25 17:04:14,214][15488] Updated weights for policy 0, policy_version 280 (0.0027) +[2023-02-25 17:04:18,468][09465] Fps is (10 sec: 3687.3, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 1163264. Throughput: 0: 940.9. Samples: 290078. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-25 17:04:18,475][09465] Avg episode reward: [(0, '5.003')] +[2023-02-25 17:04:18,486][15469] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000284_1163264.pth... +[2023-02-25 17:04:18,606][15469] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000069_282624.pth +[2023-02-25 17:04:23,163][15488] Updated weights for policy 0, policy_version 290 (0.0018) +[2023-02-25 17:04:23,467][09465] Fps is (10 sec: 4505.6, 60 sec: 3754.7, 300 sec: 3679.5). Total num frames: 1187840. Throughput: 0: 944.9. Samples: 296832. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-25 17:04:23,472][09465] Avg episode reward: [(0, '4.661')] +[2023-02-25 17:04:28,468][09465] Fps is (10 sec: 3686.3, 60 sec: 3686.4, 300 sec: 3651.8). Total num frames: 1200128. Throughput: 0: 923.0. Samples: 299206. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-25 17:04:28,477][09465] Avg episode reward: [(0, '4.540')] +[2023-02-25 17:04:33,468][09465] Fps is (10 sec: 2867.1, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 1216512. Throughput: 0: 906.8. Samples: 303572. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-02-25 17:04:33,475][09465] Avg episode reward: [(0, '4.780')] +[2023-02-25 17:04:35,905][15488] Updated weights for policy 0, policy_version 300 (0.0033) +[2023-02-25 17:04:38,468][09465] Fps is (10 sec: 3686.5, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 1236992. Throughput: 0: 947.2. Samples: 309772. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-02-25 17:04:38,470][09465] Avg episode reward: [(0, '4.928')] +[2023-02-25 17:04:43,473][09465] Fps is (10 sec: 4503.0, 60 sec: 3754.3, 300 sec: 3679.4). Total num frames: 1261568. Throughput: 0: 950.1. Samples: 313178. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-02-25 17:04:43,477][09465] Avg episode reward: [(0, '5.008')] +[2023-02-25 17:04:45,785][15488] Updated weights for policy 0, policy_version 310 (0.0019) +[2023-02-25 17:04:48,471][09465] Fps is (10 sec: 3685.1, 60 sec: 3686.2, 300 sec: 3665.5). Total num frames: 1273856. Throughput: 0: 921.2. Samples: 318636. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2023-02-25 17:04:48,477][09465] Avg episode reward: [(0, '5.022')] +[2023-02-25 17:04:53,468][09465] Fps is (10 sec: 2868.8, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 1290240. Throughput: 0: 914.8. Samples: 323112. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-25 17:04:53,474][09465] Avg episode reward: [(0, '4.968')] +[2023-02-25 17:04:57,568][15488] Updated weights for policy 0, policy_version 320 (0.0026) +[2023-02-25 17:04:58,467][09465] Fps is (10 sec: 4097.5, 60 sec: 3754.7, 300 sec: 3707.2). Total num frames: 1314816. Throughput: 0: 933.6. Samples: 326120. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-02-25 17:04:58,470][09465] Avg episode reward: [(0, '4.706')] +[2023-02-25 17:05:03,467][09465] Fps is (10 sec: 4505.8, 60 sec: 3754.7, 300 sec: 3707.2). Total num frames: 1335296. Throughput: 0: 953.1. Samples: 332968. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-02-25 17:05:03,469][09465] Avg episode reward: [(0, '5.011')] +[2023-02-25 17:05:08,211][15488] Updated weights for policy 0, policy_version 330 (0.0027) +[2023-02-25 17:05:08,467][09465] Fps is (10 sec: 3686.4, 60 sec: 3754.8, 300 sec: 3693.3). Total num frames: 1351680. Throughput: 0: 917.4. Samples: 338114. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-02-25 17:05:08,473][09465] Avg episode reward: [(0, '5.247')] +[2023-02-25 17:05:08,485][15469] Saving new best policy, reward=5.247! +[2023-02-25 17:05:13,467][09465] Fps is (10 sec: 2867.2, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 1363968. Throughput: 0: 911.3. Samples: 340214. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-02-25 17:05:13,471][09465] Avg episode reward: [(0, '5.147')] +[2023-02-25 17:05:18,468][09465] Fps is (10 sec: 3686.3, 60 sec: 3754.7, 300 sec: 3707.2). Total num frames: 1388544. Throughput: 0: 935.6. Samples: 345672. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2023-02-25 17:05:18,474][09465] Avg episode reward: [(0, '5.321')] +[2023-02-25 17:05:18,483][15469] Saving new best policy, reward=5.321! +[2023-02-25 17:05:19,277][15488] Updated weights for policy 0, policy_version 340 (0.0021) +[2023-02-25 17:05:23,469][09465] Fps is (10 sec: 4504.7, 60 sec: 3686.3, 300 sec: 3707.2). Total num frames: 1409024. Throughput: 0: 951.3. Samples: 352582. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2023-02-25 17:05:23,482][09465] Avg episode reward: [(0, '5.279')] +[2023-02-25 17:05:28,467][09465] Fps is (10 sec: 3686.5, 60 sec: 3754.7, 300 sec: 3679.5). Total num frames: 1425408. Throughput: 0: 935.5. Samples: 355272. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-25 17:05:28,473][09465] Avg episode reward: [(0, '5.116')] +[2023-02-25 17:05:30,656][15488] Updated weights for policy 0, policy_version 350 (0.0030) +[2023-02-25 17:05:33,469][09465] Fps is (10 sec: 2867.4, 60 sec: 3686.3, 300 sec: 3665.6). Total num frames: 1437696. Throughput: 0: 911.3. Samples: 359644. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-25 17:05:33,476][09465] Avg episode reward: [(0, '4.959')] +[2023-02-25 17:05:38,467][09465] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3693.3). Total num frames: 1462272. Throughput: 0: 942.1. Samples: 365504. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-25 17:05:38,475][09465] Avg episode reward: [(0, '5.159')] +[2023-02-25 17:05:40,830][15488] Updated weights for policy 0, policy_version 360 (0.0019) +[2023-02-25 17:05:43,467][09465] Fps is (10 sec: 4506.2, 60 sec: 3686.8, 300 sec: 3707.2). Total num frames: 1482752. Throughput: 0: 952.4. Samples: 368976. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-25 17:05:43,475][09465] Avg episode reward: [(0, '5.250')] +[2023-02-25 17:05:48,467][09465] Fps is (10 sec: 3686.4, 60 sec: 3754.9, 300 sec: 3679.5). Total num frames: 1499136. Throughput: 0: 927.6. Samples: 374710. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-25 17:05:48,475][09465] Avg episode reward: [(0, '5.598')] +[2023-02-25 17:05:48,488][15469] Saving new best policy, reward=5.598! +[2023-02-25 17:05:53,073][15488] Updated weights for policy 0, policy_version 370 (0.0025) +[2023-02-25 17:05:53,467][09465] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3679.5). Total num frames: 1515520. Throughput: 0: 911.1. Samples: 379112. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-25 17:05:53,474][09465] Avg episode reward: [(0, '5.390')] +[2023-02-25 17:05:58,472][09465] Fps is (10 sec: 3684.6, 60 sec: 3686.1, 300 sec: 3693.3). Total num frames: 1536000. Throughput: 0: 925.5. Samples: 381866. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-25 17:05:58,476][09465] Avg episode reward: [(0, '5.857')] +[2023-02-25 17:05:58,490][15469] Saving new best policy, reward=5.857! +[2023-02-25 17:06:02,435][15488] Updated weights for policy 0, policy_version 380 (0.0020) +[2023-02-25 17:06:03,467][09465] Fps is (10 sec: 4505.6, 60 sec: 3754.7, 300 sec: 3707.2). Total num frames: 1560576. Throughput: 0: 959.8. Samples: 388862. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2023-02-25 17:06:03,470][09465] Avg episode reward: [(0, '6.012')] +[2023-02-25 17:06:03,477][15469] Saving new best policy, reward=6.012! +[2023-02-25 17:06:08,473][09465] Fps is (10 sec: 4095.9, 60 sec: 3754.3, 300 sec: 3693.3). Total num frames: 1576960. Throughput: 0: 925.8. Samples: 394244. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-25 17:06:08,480][09465] Avg episode reward: [(0, '5.846')] +[2023-02-25 17:06:13,467][09465] Fps is (10 sec: 2867.2, 60 sec: 3754.7, 300 sec: 3679.5). Total num frames: 1589248. Throughput: 0: 914.9. Samples: 396444. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-25 17:06:13,472][09465] Avg episode reward: [(0, '5.935')] +[2023-02-25 17:06:14,973][15488] Updated weights for policy 0, policy_version 390 (0.0045) +[2023-02-25 17:06:18,468][09465] Fps is (10 sec: 3278.5, 60 sec: 3686.4, 300 sec: 3693.3). Total num frames: 1609728. Throughput: 0: 934.2. Samples: 401682. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2023-02-25 17:06:18,470][09465] Avg episode reward: [(0, '6.130')] +[2023-02-25 17:06:18,480][15469] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000393_1609728.pth... +[2023-02-25 17:06:18,606][15469] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000175_716800.pth +[2023-02-25 17:06:18,618][15469] Saving new best policy, reward=6.130! +[2023-02-25 17:06:23,467][09465] Fps is (10 sec: 4505.6, 60 sec: 3754.8, 300 sec: 3707.5). Total num frames: 1634304. Throughput: 0: 950.8. Samples: 408288. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-02-25 17:06:23,469][09465] Avg episode reward: [(0, '6.004')] +[2023-02-25 17:06:24,276][15488] Updated weights for policy 0, policy_version 400 (0.0017) +[2023-02-25 17:06:28,472][09465] Fps is (10 sec: 3684.7, 60 sec: 3686.1, 300 sec: 3679.4). Total num frames: 1646592. Throughput: 0: 939.6. Samples: 411262. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-02-25 17:06:28,474][09465] Avg episode reward: [(0, '6.162')] +[2023-02-25 17:06:28,504][15469] Saving new best policy, reward=6.162! +[2023-02-25 17:06:33,467][09465] Fps is (10 sec: 2867.2, 60 sec: 3754.7, 300 sec: 3665.6). Total num frames: 1662976. Throughput: 0: 906.3. Samples: 415492. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2023-02-25 17:06:33,473][09465] Avg episode reward: [(0, '5.987')] +[2023-02-25 17:06:37,177][15488] Updated weights for policy 0, policy_version 410 (0.0022) +[2023-02-25 17:06:38,467][09465] Fps is (10 sec: 3688.1, 60 sec: 3686.4, 300 sec: 3679.5). Total num frames: 1683456. Throughput: 0: 930.9. Samples: 421004. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-02-25 17:06:38,470][09465] Avg episode reward: [(0, '5.859')] +[2023-02-25 17:06:43,468][09465] Fps is (10 sec: 4505.5, 60 sec: 3754.7, 300 sec: 3707.2). Total num frames: 1708032. Throughput: 0: 947.7. Samples: 424510. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2023-02-25 17:06:43,471][09465] Avg episode reward: [(0, '6.327')] +[2023-02-25 17:06:43,472][15469] Saving new best policy, reward=6.327! +[2023-02-25 17:06:46,987][15488] Updated weights for policy 0, policy_version 420 (0.0014) +[2023-02-25 17:06:48,469][09465] Fps is (10 sec: 4095.4, 60 sec: 3754.6, 300 sec: 3693.3). Total num frames: 1724416. Throughput: 0: 926.5. Samples: 430554. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2023-02-25 17:06:48,472][09465] Avg episode reward: [(0, '6.736')] +[2023-02-25 17:06:48,487][15469] Saving new best policy, reward=6.736! +[2023-02-25 17:06:53,467][09465] Fps is (10 sec: 2867.3, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 1736704. Throughput: 0: 901.4. Samples: 434802. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2023-02-25 17:06:53,476][09465] Avg episode reward: [(0, '7.251')] +[2023-02-25 17:06:53,485][15469] Saving new best policy, reward=7.251! +[2023-02-25 17:06:58,467][09465] Fps is (10 sec: 3277.3, 60 sec: 3686.7, 300 sec: 3693.3). Total num frames: 1757184. Throughput: 0: 904.8. Samples: 437162. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2023-02-25 17:06:58,469][09465] Avg episode reward: [(0, '7.252')] +[2023-02-25 17:06:58,479][15469] Saving new best policy, reward=7.252! +[2023-02-25 17:06:58,907][15488] Updated weights for policy 0, policy_version 430 (0.0015) +[2023-02-25 17:07:03,468][09465] Fps is (10 sec: 4505.5, 60 sec: 3686.4, 300 sec: 3735.0). Total num frames: 1781760. Throughput: 0: 940.8. Samples: 444020. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-02-25 17:07:03,470][09465] Avg episode reward: [(0, '7.221')] +[2023-02-25 17:07:08,468][09465] Fps is (10 sec: 4095.9, 60 sec: 3686.7, 300 sec: 3735.0). Total num frames: 1798144. Throughput: 0: 926.6. Samples: 449984. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-25 17:07:08,472][09465] Avg episode reward: [(0, '7.089')] +[2023-02-25 17:07:09,042][15488] Updated weights for policy 0, policy_version 440 (0.0014) +[2023-02-25 17:07:13,467][09465] Fps is (10 sec: 3276.9, 60 sec: 3754.7, 300 sec: 3721.1). Total num frames: 1814528. Throughput: 0: 909.8. Samples: 452198. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-25 17:07:13,473][09465] Avg episode reward: [(0, '7.168')] +[2023-02-25 17:07:18,467][09465] Fps is (10 sec: 3276.9, 60 sec: 3686.4, 300 sec: 3707.2). Total num frames: 1830912. Throughput: 0: 924.3. Samples: 457086. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-02-25 17:07:18,471][09465] Avg episode reward: [(0, '7.585')] +[2023-02-25 17:07:18,579][15469] Saving new best policy, reward=7.585! +[2023-02-25 17:07:20,414][15488] Updated weights for policy 0, policy_version 450 (0.0029) +[2023-02-25 17:07:23,467][09465] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3735.0). Total num frames: 1855488. Throughput: 0: 953.6. Samples: 463918. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-25 17:07:23,470][09465] Avg episode reward: [(0, '7.435')] +[2023-02-25 17:07:28,471][09465] Fps is (10 sec: 4094.5, 60 sec: 3754.7, 300 sec: 3735.0). Total num frames: 1871872. Throughput: 0: 951.0. Samples: 467306. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-25 17:07:28,473][09465] Avg episode reward: [(0, '7.962')] +[2023-02-25 17:07:28,485][15469] Saving new best policy, reward=7.962! +[2023-02-25 17:07:31,667][15488] Updated weights for policy 0, policy_version 460 (0.0019) +[2023-02-25 17:07:33,467][09465] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3707.2). Total num frames: 1888256. Throughput: 0: 910.5. Samples: 471524. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-25 17:07:33,473][09465] Avg episode reward: [(0, '8.425')] +[2023-02-25 17:07:33,478][15469] Saving new best policy, reward=8.425! +[2023-02-25 17:07:38,467][09465] Fps is (10 sec: 3278.0, 60 sec: 3686.4, 300 sec: 3707.2). Total num frames: 1904640. Throughput: 0: 933.0. Samples: 476786. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-25 17:07:38,472][09465] Avg episode reward: [(0, '8.785')] +[2023-02-25 17:07:38,505][15469] Saving new best policy, reward=8.785! +[2023-02-25 17:07:42,123][15488] Updated weights for policy 0, policy_version 470 (0.0022) +[2023-02-25 17:07:43,467][09465] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3735.0). Total num frames: 1929216. Throughput: 0: 955.7. Samples: 480170. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-25 17:07:43,478][09465] Avg episode reward: [(0, '9.398')] +[2023-02-25 17:07:43,483][15469] Saving new best policy, reward=9.398! +[2023-02-25 17:07:48,467][09465] Fps is (10 sec: 4096.0, 60 sec: 3686.5, 300 sec: 3735.0). Total num frames: 1945600. Throughput: 0: 945.1. Samples: 486550. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-25 17:07:48,476][09465] Avg episode reward: [(0, '9.396')] +[2023-02-25 17:07:53,468][09465] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3707.2). Total num frames: 1961984. Throughput: 0: 908.4. Samples: 490860. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-02-25 17:07:53,475][09465] Avg episode reward: [(0, '9.276')] +[2023-02-25 17:07:54,511][15488] Updated weights for policy 0, policy_version 480 (0.0024) +[2023-02-25 17:07:58,467][09465] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3707.3). Total num frames: 1982464. Throughput: 0: 908.1. Samples: 493062. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-02-25 17:07:58,475][09465] Avg episode reward: [(0, '9.415')] +[2023-02-25 17:07:58,485][15469] Saving new best policy, reward=9.415! +[2023-02-25 17:08:03,467][09465] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3735.1). Total num frames: 2002944. Throughput: 0: 949.3. Samples: 499806. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2023-02-25 17:08:03,470][09465] Avg episode reward: [(0, '9.087')] +[2023-02-25 17:08:03,688][15488] Updated weights for policy 0, policy_version 490 (0.0028) +[2023-02-25 17:08:08,470][09465] Fps is (10 sec: 4094.8, 60 sec: 3754.5, 300 sec: 3748.8). Total num frames: 2023424. Throughput: 0: 934.0. Samples: 505950. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-25 17:08:08,477][09465] Avg episode reward: [(0, '9.710')] +[2023-02-25 17:08:08,488][15469] Saving new best policy, reward=9.710! +[2023-02-25 17:08:13,467][09465] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3707.2). Total num frames: 2035712. Throughput: 0: 906.9. Samples: 508114. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-25 17:08:13,477][09465] Avg episode reward: [(0, '9.267')] +[2023-02-25 17:08:16,397][15488] Updated weights for policy 0, policy_version 500 (0.0011) +[2023-02-25 17:08:18,468][09465] Fps is (10 sec: 3277.7, 60 sec: 3754.7, 300 sec: 3707.2). Total num frames: 2056192. Throughput: 0: 916.4. Samples: 512764. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-25 17:08:18,470][09465] Avg episode reward: [(0, '9.584')] +[2023-02-25 17:08:18,483][15469] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000502_2056192.pth... +[2023-02-25 17:08:18,598][15469] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000284_1163264.pth +[2023-02-25 17:08:23,467][09465] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3721.1). Total num frames: 2076672. Throughput: 0: 940.9. Samples: 519128. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-25 17:08:23,470][09465] Avg episode reward: [(0, '9.950')] +[2023-02-25 17:08:23,477][15469] Saving new best policy, reward=9.950! +[2023-02-25 17:08:28,035][15488] Updated weights for policy 0, policy_version 510 (0.0012) +[2023-02-25 17:08:28,472][09465] Fps is (10 sec: 3275.3, 60 sec: 3618.1, 300 sec: 3707.2). Total num frames: 2088960. Throughput: 0: 912.9. Samples: 521254. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-25 17:08:28,475][09465] Avg episode reward: [(0, '10.072')] +[2023-02-25 17:08:28,491][15469] Saving new best policy, reward=10.072! +[2023-02-25 17:08:33,469][09465] Fps is (10 sec: 2457.2, 60 sec: 3549.8, 300 sec: 3679.4). Total num frames: 2101248. Throughput: 0: 849.5. Samples: 524780. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-25 17:08:33,473][09465] Avg episode reward: [(0, '11.722')] +[2023-02-25 17:08:33,481][15469] Saving new best policy, reward=11.722! +[2023-02-25 17:08:38,468][09465] Fps is (10 sec: 2458.7, 60 sec: 3481.6, 300 sec: 3651.7). Total num frames: 2113536. Throughput: 0: 844.2. Samples: 528848. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-25 17:08:38,470][09465] Avg episode reward: [(0, '11.806')] +[2023-02-25 17:08:38,488][15469] Saving new best policy, reward=11.806! +[2023-02-25 17:08:41,864][15488] Updated weights for policy 0, policy_version 520 (0.0044) +[2023-02-25 17:08:43,467][09465] Fps is (10 sec: 3277.4, 60 sec: 3413.3, 300 sec: 3665.6). Total num frames: 2134016. Throughput: 0: 856.1. Samples: 531588. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-02-25 17:08:43,472][09465] Avg episode reward: [(0, '12.059')] +[2023-02-25 17:08:43,477][15469] Saving new best policy, reward=12.059! +[2023-02-25 17:08:48,467][09465] Fps is (10 sec: 4505.7, 60 sec: 3549.9, 300 sec: 3693.3). Total num frames: 2158592. Throughput: 0: 859.0. Samples: 538462. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-02-25 17:08:48,469][09465] Avg episode reward: [(0, '11.752')] +[2023-02-25 17:08:51,703][15488] Updated weights for policy 0, policy_version 530 (0.0012) +[2023-02-25 17:08:53,467][09465] Fps is (10 sec: 4096.0, 60 sec: 3549.9, 300 sec: 3679.5). Total num frames: 2174976. Throughput: 0: 844.8. Samples: 543964. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2023-02-25 17:08:53,470][09465] Avg episode reward: [(0, '11.165')] +[2023-02-25 17:08:58,467][09465] Fps is (10 sec: 2867.2, 60 sec: 3413.3, 300 sec: 3651.7). Total num frames: 2187264. Throughput: 0: 845.8. Samples: 546176. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-25 17:08:58,471][09465] Avg episode reward: [(0, '11.503')] +[2023-02-25 17:09:03,441][15488] Updated weights for policy 0, policy_version 540 (0.0012) +[2023-02-25 17:09:03,467][09465] Fps is (10 sec: 3686.4, 60 sec: 3481.6, 300 sec: 3679.5). Total num frames: 2211840. Throughput: 0: 860.0. Samples: 551464. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2023-02-25 17:09:03,471][09465] Avg episode reward: [(0, '12.495')] +[2023-02-25 17:09:03,473][15469] Saving new best policy, reward=12.495! +[2023-02-25 17:09:08,468][09465] Fps is (10 sec: 4505.5, 60 sec: 3481.8, 300 sec: 3693.3). Total num frames: 2232320. Throughput: 0: 872.5. Samples: 558392. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-25 17:09:08,470][09465] Avg episode reward: [(0, '12.536')] +[2023-02-25 17:09:08,484][15469] Saving new best policy, reward=12.536! +[2023-02-25 17:09:13,468][09465] Fps is (10 sec: 3686.1, 60 sec: 3549.8, 300 sec: 3679.5). Total num frames: 2248704. Throughput: 0: 892.5. Samples: 561414. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-25 17:09:13,473][09465] Avg episode reward: [(0, '13.304')] +[2023-02-25 17:09:13,478][15469] Saving new best policy, reward=13.304! +[2023-02-25 17:09:13,925][15488] Updated weights for policy 0, policy_version 550 (0.0021) +[2023-02-25 17:09:18,468][09465] Fps is (10 sec: 3276.8, 60 sec: 3481.6, 300 sec: 3651.7). Total num frames: 2265088. Throughput: 0: 910.2. Samples: 565736. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-25 17:09:18,475][09465] Avg episode reward: [(0, '13.103')] +[2023-02-25 17:09:23,467][09465] Fps is (10 sec: 3686.7, 60 sec: 3481.6, 300 sec: 3679.5). Total num frames: 2285568. Throughput: 0: 942.5. Samples: 571262. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-02-25 17:09:23,475][09465] Avg episode reward: [(0, '13.039')] +[2023-02-25 17:09:24,972][15488] Updated weights for policy 0, policy_version 560 (0.0037) +[2023-02-25 17:09:28,468][09465] Fps is (10 sec: 4505.5, 60 sec: 3686.7, 300 sec: 3707.2). Total num frames: 2310144. Throughput: 0: 960.5. Samples: 574812. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2023-02-25 17:09:28,470][09465] Avg episode reward: [(0, '13.135')] +[2023-02-25 17:09:33,467][09465] Fps is (10 sec: 4096.0, 60 sec: 3754.8, 300 sec: 3693.3). Total num frames: 2326528. Throughput: 0: 946.4. Samples: 581050. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-25 17:09:33,472][09465] Avg episode reward: [(0, '13.266')] +[2023-02-25 17:09:36,097][15488] Updated weights for policy 0, policy_version 570 (0.0013) +[2023-02-25 17:09:38,467][09465] Fps is (10 sec: 2867.3, 60 sec: 3754.7, 300 sec: 3651.8). Total num frames: 2338816. Throughput: 0: 920.8. Samples: 585398. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2023-02-25 17:09:38,473][09465] Avg episode reward: [(0, '13.612')] +[2023-02-25 17:09:38,489][15469] Saving new best policy, reward=13.612! +[2023-02-25 17:09:43,467][09465] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3679.5). Total num frames: 2359296. Throughput: 0: 926.8. Samples: 587880. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-02-25 17:09:43,470][09465] Avg episode reward: [(0, '13.825')] +[2023-02-25 17:09:43,474][15469] Saving new best policy, reward=13.825! +[2023-02-25 17:09:46,250][15488] Updated weights for policy 0, policy_version 580 (0.0019) +[2023-02-25 17:09:48,467][09465] Fps is (10 sec: 4505.6, 60 sec: 3754.7, 300 sec: 3707.2). Total num frames: 2383872. Throughput: 0: 965.0. Samples: 594888. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-25 17:09:48,469][09465] Avg episode reward: [(0, '13.959')] +[2023-02-25 17:09:48,482][15469] Saving new best policy, reward=13.959! +[2023-02-25 17:09:53,467][09465] Fps is (10 sec: 4096.0, 60 sec: 3754.7, 300 sec: 3679.5). Total num frames: 2400256. Throughput: 0: 939.1. Samples: 600652. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-02-25 17:09:53,473][09465] Avg episode reward: [(0, '14.629')] +[2023-02-25 17:09:53,479][15469] Saving new best policy, reward=14.629! +[2023-02-25 17:09:58,412][15488] Updated weights for policy 0, policy_version 590 (0.0011) +[2023-02-25 17:09:58,467][09465] Fps is (10 sec: 3276.8, 60 sec: 3822.9, 300 sec: 3665.6). Total num frames: 2416640. Throughput: 0: 920.6. Samples: 602840. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-25 17:09:58,474][09465] Avg episode reward: [(0, '15.537')] +[2023-02-25 17:09:58,487][15469] Saving new best policy, reward=15.537! +[2023-02-25 17:10:03,468][09465] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3679.5). Total num frames: 2437120. Throughput: 0: 936.9. Samples: 607896. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-02-25 17:10:03,470][09465] Avg episode reward: [(0, '16.453')] +[2023-02-25 17:10:03,473][15469] Saving new best policy, reward=16.453! +[2023-02-25 17:10:07,743][15488] Updated weights for policy 0, policy_version 600 (0.0017) +[2023-02-25 17:10:08,468][09465] Fps is (10 sec: 4096.0, 60 sec: 3754.7, 300 sec: 3707.2). Total num frames: 2457600. Throughput: 0: 971.6. Samples: 614984. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2023-02-25 17:10:08,469][09465] Avg episode reward: [(0, '16.839')] +[2023-02-25 17:10:08,490][15469] Saving new best policy, reward=16.839! +[2023-02-25 17:10:13,469][09465] Fps is (10 sec: 4095.4, 60 sec: 3822.9, 300 sec: 3693.3). Total num frames: 2478080. Throughput: 0: 962.8. Samples: 618138. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-02-25 17:10:13,477][09465] Avg episode reward: [(0, '18.144')] +[2023-02-25 17:10:13,479][15469] Saving new best policy, reward=18.144! +[2023-02-25 17:10:18,468][09465] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3665.6). Total num frames: 2490368. Throughput: 0: 921.2. Samples: 622504. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-02-25 17:10:18,475][09465] Avg episode reward: [(0, '17.902')] +[2023-02-25 17:10:18,488][15469] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000608_2490368.pth... +[2023-02-25 17:10:18,634][15469] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000393_1609728.pth +[2023-02-25 17:10:20,065][15488] Updated weights for policy 0, policy_version 610 (0.0029) +[2023-02-25 17:10:23,467][09465] Fps is (10 sec: 3277.3, 60 sec: 3754.7, 300 sec: 3679.5). Total num frames: 2510848. Throughput: 0: 950.2. Samples: 628156. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-25 17:10:23,474][09465] Avg episode reward: [(0, '17.738')] +[2023-02-25 17:10:28,467][09465] Fps is (10 sec: 4505.7, 60 sec: 3754.7, 300 sec: 3721.1). Total num frames: 2535424. Throughput: 0: 971.4. Samples: 631592. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-25 17:10:28,470][09465] Avg episode reward: [(0, '17.817')] +[2023-02-25 17:10:28,731][15488] Updated weights for policy 0, policy_version 620 (0.0012) +[2023-02-25 17:10:33,470][09465] Fps is (10 sec: 4095.1, 60 sec: 3754.5, 300 sec: 3693.3). Total num frames: 2551808. Throughput: 0: 956.2. Samples: 637918. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2023-02-25 17:10:33,475][09465] Avg episode reward: [(0, '17.120')] +[2023-02-25 17:10:38,468][09465] Fps is (10 sec: 3276.7, 60 sec: 3822.9, 300 sec: 3679.5). Total num frames: 2568192. Throughput: 0: 925.0. Samples: 642276. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2023-02-25 17:10:38,470][09465] Avg episode reward: [(0, '18.184')] +[2023-02-25 17:10:38,486][15469] Saving new best policy, reward=18.184! +[2023-02-25 17:10:41,210][15488] Updated weights for policy 0, policy_version 630 (0.0032) +[2023-02-25 17:10:43,467][09465] Fps is (10 sec: 3687.2, 60 sec: 3822.9, 300 sec: 3693.3). Total num frames: 2588672. Throughput: 0: 934.1. Samples: 644876. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2023-02-25 17:10:43,470][09465] Avg episode reward: [(0, '17.322')] +[2023-02-25 17:10:48,467][09465] Fps is (10 sec: 4505.8, 60 sec: 3822.9, 300 sec: 3721.1). Total num frames: 2613248. Throughput: 0: 978.9. Samples: 651948. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-25 17:10:48,478][09465] Avg episode reward: [(0, '18.109')] +[2023-02-25 17:10:50,229][15488] Updated weights for policy 0, policy_version 640 (0.0013) +[2023-02-25 17:10:53,471][09465] Fps is (10 sec: 4094.7, 60 sec: 3822.7, 300 sec: 3707.2). Total num frames: 2629632. Throughput: 0: 950.5. Samples: 657760. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-02-25 17:10:53,479][09465] Avg episode reward: [(0, '19.500')] +[2023-02-25 17:10:53,482][15469] Saving new best policy, reward=19.500! +[2023-02-25 17:10:58,468][09465] Fps is (10 sec: 2867.1, 60 sec: 3754.7, 300 sec: 3665.6). Total num frames: 2641920. Throughput: 0: 928.5. Samples: 659918. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-02-25 17:10:58,473][09465] Avg episode reward: [(0, '20.781')] +[2023-02-25 17:10:58,494][15469] Saving new best policy, reward=20.781! +[2023-02-25 17:11:02,433][15488] Updated weights for policy 0, policy_version 650 (0.0021) +[2023-02-25 17:11:03,467][09465] Fps is (10 sec: 3687.6, 60 sec: 3822.9, 300 sec: 3693.4). Total num frames: 2666496. Throughput: 0: 947.8. Samples: 665154. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-25 17:11:03,475][09465] Avg episode reward: [(0, '20.914')] +[2023-02-25 17:11:03,480][15469] Saving new best policy, reward=20.914! +[2023-02-25 17:11:08,467][09465] Fps is (10 sec: 4505.7, 60 sec: 3822.9, 300 sec: 3721.1). Total num frames: 2686976. Throughput: 0: 978.1. Samples: 672172. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2023-02-25 17:11:08,469][09465] Avg episode reward: [(0, '20.973')] +[2023-02-25 17:11:08,541][15469] Saving new best policy, reward=20.973! +[2023-02-25 17:11:12,071][15488] Updated weights for policy 0, policy_version 660 (0.0016) +[2023-02-25 17:11:13,467][09465] Fps is (10 sec: 4096.0, 60 sec: 3823.0, 300 sec: 3721.1). Total num frames: 2707456. Throughput: 0: 970.4. Samples: 675260. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-25 17:11:13,472][09465] Avg episode reward: [(0, '18.575')] +[2023-02-25 17:11:18,472][09465] Fps is (10 sec: 3275.4, 60 sec: 3822.7, 300 sec: 3679.4). Total num frames: 2719744. Throughput: 0: 929.4. Samples: 679744. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-25 17:11:18,475][09465] Avg episode reward: [(0, '17.739')] +[2023-02-25 17:11:23,457][15488] Updated weights for policy 0, policy_version 670 (0.0014) +[2023-02-25 17:11:23,467][09465] Fps is (10 sec: 3686.4, 60 sec: 3891.2, 300 sec: 3721.2). Total num frames: 2744320. Throughput: 0: 959.9. Samples: 685470. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-25 17:11:23,469][09465] Avg episode reward: [(0, '17.645')] +[2023-02-25 17:11:28,468][09465] Fps is (10 sec: 4507.5, 60 sec: 3822.9, 300 sec: 3735.0). Total num frames: 2764800. Throughput: 0: 978.7. Samples: 688916. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-25 17:11:28,470][09465] Avg episode reward: [(0, '17.886')] +[2023-02-25 17:11:33,471][09465] Fps is (10 sec: 3685.1, 60 sec: 3822.8, 300 sec: 3721.1). Total num frames: 2781184. Throughput: 0: 957.7. Samples: 695050. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-25 17:11:33,474][09465] Avg episode reward: [(0, '17.186')] +[2023-02-25 17:11:34,065][15488] Updated weights for policy 0, policy_version 680 (0.0012) +[2023-02-25 17:11:38,468][09465] Fps is (10 sec: 3276.6, 60 sec: 3822.9, 300 sec: 3693.3). Total num frames: 2797568. Throughput: 0: 926.3. Samples: 699440. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-25 17:11:38,471][09465] Avg episode reward: [(0, '18.185')] +[2023-02-25 17:11:43,467][09465] Fps is (10 sec: 3687.8, 60 sec: 3822.9, 300 sec: 3707.2). Total num frames: 2818048. Throughput: 0: 938.5. Samples: 702150. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-25 17:11:43,474][09465] Avg episode reward: [(0, '18.889')] +[2023-02-25 17:11:44,847][15488] Updated weights for policy 0, policy_version 690 (0.0016) +[2023-02-25 17:11:48,467][09465] Fps is (10 sec: 4505.9, 60 sec: 3822.9, 300 sec: 3748.9). Total num frames: 2842624. Throughput: 0: 979.6. Samples: 709234. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-02-25 17:11:48,469][09465] Avg episode reward: [(0, '17.040')] +[2023-02-25 17:11:53,467][09465] Fps is (10 sec: 4096.0, 60 sec: 3823.1, 300 sec: 3735.0). Total num frames: 2859008. Throughput: 0: 953.9. Samples: 715096. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-02-25 17:11:53,470][09465] Avg episode reward: [(0, '16.800')] +[2023-02-25 17:11:55,824][15488] Updated weights for policy 0, policy_version 700 (0.0045) +[2023-02-25 17:11:58,468][09465] Fps is (10 sec: 2867.1, 60 sec: 3822.9, 300 sec: 3693.3). Total num frames: 2871296. Throughput: 0: 934.0. Samples: 717292. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-02-25 17:11:58,473][09465] Avg episode reward: [(0, '16.995')] +[2023-02-25 17:12:03,467][09465] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3721.1). Total num frames: 2895872. Throughput: 0: 951.6. Samples: 722560. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2023-02-25 17:12:03,470][09465] Avg episode reward: [(0, '17.150')] +[2023-02-25 17:12:05,975][15488] Updated weights for policy 0, policy_version 710 (0.0012) +[2023-02-25 17:12:08,468][09465] Fps is (10 sec: 4915.3, 60 sec: 3891.2, 300 sec: 3748.9). Total num frames: 2920448. Throughput: 0: 980.6. Samples: 729598. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-02-25 17:12:08,470][09465] Avg episode reward: [(0, '17.308')] +[2023-02-25 17:12:13,467][09465] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3748.9). Total num frames: 2936832. Throughput: 0: 974.4. Samples: 732764. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2023-02-25 17:12:13,470][09465] Avg episode reward: [(0, '17.838')] +[2023-02-25 17:12:17,288][15488] Updated weights for policy 0, policy_version 720 (0.0027) +[2023-02-25 17:12:18,470][09465] Fps is (10 sec: 2866.5, 60 sec: 3823.1, 300 sec: 3707.2). Total num frames: 2949120. Throughput: 0: 936.9. Samples: 737210. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2023-02-25 17:12:18,479][09465] Avg episode reward: [(0, '19.016')] +[2023-02-25 17:12:18,487][15469] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000720_2949120.pth... +[2023-02-25 17:12:18,654][15469] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000502_2056192.pth +[2023-02-25 17:12:23,467][09465] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3735.0). Total num frames: 2973696. Throughput: 0: 967.6. Samples: 742980. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-25 17:12:23,472][09465] Avg episode reward: [(0, '18.660')] +[2023-02-25 17:12:26,889][15488] Updated weights for policy 0, policy_version 730 (0.0018) +[2023-02-25 17:12:28,468][09465] Fps is (10 sec: 4506.7, 60 sec: 3822.9, 300 sec: 3748.9). Total num frames: 2994176. Throughput: 0: 986.8. Samples: 746558. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-02-25 17:12:28,470][09465] Avg episode reward: [(0, '18.404')] +[2023-02-25 17:12:33,470][09465] Fps is (10 sec: 3685.4, 60 sec: 3823.0, 300 sec: 3748.8). Total num frames: 3010560. Throughput: 0: 969.5. Samples: 752864. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-02-25 17:12:33,475][09465] Avg episode reward: [(0, '19.132')] +[2023-02-25 17:12:38,468][09465] Fps is (10 sec: 3276.6, 60 sec: 3822.9, 300 sec: 3721.1). Total num frames: 3026944. Throughput: 0: 938.0. Samples: 757306. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-02-25 17:12:38,476][09465] Avg episode reward: [(0, '19.065')] +[2023-02-25 17:12:38,996][15488] Updated weights for policy 0, policy_version 740 (0.0037) +[2023-02-25 17:12:43,467][09465] Fps is (10 sec: 3687.3, 60 sec: 3822.9, 300 sec: 3735.0). Total num frames: 3047424. Throughput: 0: 947.6. Samples: 759934. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2023-02-25 17:12:43,469][09465] Avg episode reward: [(0, '18.770')] +[2023-02-25 17:12:47,983][15488] Updated weights for policy 0, policy_version 750 (0.0012) +[2023-02-25 17:12:48,467][09465] Fps is (10 sec: 4505.8, 60 sec: 3822.9, 300 sec: 3762.8). Total num frames: 3072000. Throughput: 0: 986.1. Samples: 766936. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2023-02-25 17:12:48,479][09465] Avg episode reward: [(0, '20.505')] +[2023-02-25 17:12:53,467][09465] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3748.9). Total num frames: 3088384. Throughput: 0: 957.7. Samples: 772694. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-02-25 17:12:53,470][09465] Avg episode reward: [(0, '20.894')] +[2023-02-25 17:12:58,468][09465] Fps is (10 sec: 3276.7, 60 sec: 3891.2, 300 sec: 3735.0). Total num frames: 3104768. Throughput: 0: 932.2. Samples: 774712. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2023-02-25 17:12:58,476][09465] Avg episode reward: [(0, '21.343')] +[2023-02-25 17:12:58,492][15469] Saving new best policy, reward=21.343! +[2023-02-25 17:13:00,504][15488] Updated weights for policy 0, policy_version 760 (0.0012) +[2023-02-25 17:13:03,467][09465] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3735.0). Total num frames: 3125248. Throughput: 0: 950.1. Samples: 779964. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2023-02-25 17:13:03,475][09465] Avg episode reward: [(0, '22.085')] +[2023-02-25 17:13:03,480][15469] Saving new best policy, reward=22.085! +[2023-02-25 17:13:08,467][09465] Fps is (10 sec: 4096.1, 60 sec: 3754.7, 300 sec: 3762.8). Total num frames: 3145728. Throughput: 0: 976.6. Samples: 786928. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2023-02-25 17:13:08,475][09465] Avg episode reward: [(0, '22.110')] +[2023-02-25 17:13:08,486][15469] Saving new best policy, reward=22.110! +[2023-02-25 17:13:09,573][15488] Updated weights for policy 0, policy_version 770 (0.0021) +[2023-02-25 17:13:13,467][09465] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3748.9). Total num frames: 3162112. Throughput: 0: 964.4. Samples: 789958. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2023-02-25 17:13:13,471][09465] Avg episode reward: [(0, '21.364')] +[2023-02-25 17:13:18,467][09465] Fps is (10 sec: 3276.8, 60 sec: 3823.1, 300 sec: 3735.0). Total num frames: 3178496. Throughput: 0: 922.2. Samples: 794362. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2023-02-25 17:13:18,469][09465] Avg episode reward: [(0, '21.104')] +[2023-02-25 17:13:21,828][15488] Updated weights for policy 0, policy_version 780 (0.0031) +[2023-02-25 17:13:23,467][09465] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3762.8). Total num frames: 3198976. Throughput: 0: 951.5. Samples: 800124. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-02-25 17:13:23,477][09465] Avg episode reward: [(0, '22.103')] +[2023-02-25 17:13:28,468][09465] Fps is (10 sec: 4505.5, 60 sec: 3822.9, 300 sec: 3804.4). Total num frames: 3223552. Throughput: 0: 969.8. Samples: 803576. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-25 17:13:28,475][09465] Avg episode reward: [(0, '21.596')] +[2023-02-25 17:13:31,197][15488] Updated weights for policy 0, policy_version 790 (0.0017) +[2023-02-25 17:13:33,467][09465] Fps is (10 sec: 4096.0, 60 sec: 3823.1, 300 sec: 3818.3). Total num frames: 3239936. Throughput: 0: 952.0. Samples: 809774. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-25 17:13:33,470][09465] Avg episode reward: [(0, '22.114')] +[2023-02-25 17:13:33,481][15469] Saving new best policy, reward=22.114! +[2023-02-25 17:13:38,468][09465] Fps is (10 sec: 3276.9, 60 sec: 3823.0, 300 sec: 3804.4). Total num frames: 3256320. Throughput: 0: 920.3. Samples: 814108. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-02-25 17:13:38,470][09465] Avg episode reward: [(0, '22.863')] +[2023-02-25 17:13:38,487][15469] Saving new best policy, reward=22.863! +[2023-02-25 17:13:43,310][15488] Updated weights for policy 0, policy_version 800 (0.0026) +[2023-02-25 17:13:43,468][09465] Fps is (10 sec: 3686.3, 60 sec: 3822.9, 300 sec: 3790.5). Total num frames: 3276800. Throughput: 0: 930.3. Samples: 816574. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-25 17:13:43,470][09465] Avg episode reward: [(0, '21.353')] +[2023-02-25 17:13:48,468][09465] Fps is (10 sec: 4095.9, 60 sec: 3754.6, 300 sec: 3804.4). Total num frames: 3297280. Throughput: 0: 969.8. Samples: 823606. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) +[2023-02-25 17:13:48,471][09465] Avg episode reward: [(0, '19.426')] +[2023-02-25 17:13:53,187][15488] Updated weights for policy 0, policy_version 810 (0.0027) +[2023-02-25 17:13:53,467][09465] Fps is (10 sec: 4096.1, 60 sec: 3822.9, 300 sec: 3832.2). Total num frames: 3317760. Throughput: 0: 946.1. Samples: 829502. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-02-25 17:13:53,475][09465] Avg episode reward: [(0, '18.391')] +[2023-02-25 17:13:58,467][09465] Fps is (10 sec: 3276.9, 60 sec: 3754.7, 300 sec: 3790.5). Total num frames: 3330048. Throughput: 0: 926.8. Samples: 831666. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-25 17:13:58,473][09465] Avg episode reward: [(0, '17.930')] +[2023-02-25 17:14:03,467][09465] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3790.5). Total num frames: 3350528. Throughput: 0: 940.0. Samples: 836660. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-02-25 17:14:03,476][09465] Avg episode reward: [(0, '16.992')] +[2023-02-25 17:14:04,696][15488] Updated weights for policy 0, policy_version 820 (0.0012) +[2023-02-25 17:14:08,467][09465] Fps is (10 sec: 4505.6, 60 sec: 3822.9, 300 sec: 3818.3). Total num frames: 3375104. Throughput: 0: 965.6. Samples: 843578. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-25 17:14:08,475][09465] Avg episode reward: [(0, '18.370')] +[2023-02-25 17:14:13,467][09465] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3818.3). Total num frames: 3391488. Throughput: 0: 960.9. Samples: 846816. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-25 17:14:13,473][09465] Avg episode reward: [(0, '19.511')] +[2023-02-25 17:14:15,768][15488] Updated weights for policy 0, policy_version 830 (0.0012) +[2023-02-25 17:14:18,468][09465] Fps is (10 sec: 2867.1, 60 sec: 3754.6, 300 sec: 3790.5). Total num frames: 3403776. Throughput: 0: 920.5. Samples: 851198. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2023-02-25 17:14:18,474][09465] Avg episode reward: [(0, '19.352')] +[2023-02-25 17:14:18,491][15469] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000831_3403776.pth... +[2023-02-25 17:14:18,638][15469] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000608_2490368.pth +[2023-02-25 17:14:23,467][09465] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3790.5). Total num frames: 3428352. Throughput: 0: 944.9. Samples: 856628. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-02-25 17:14:23,470][09465] Avg episode reward: [(0, '21.008')] +[2023-02-25 17:14:26,003][15488] Updated weights for policy 0, policy_version 840 (0.0019) +[2023-02-25 17:14:28,467][09465] Fps is (10 sec: 4505.8, 60 sec: 3754.7, 300 sec: 3804.4). Total num frames: 3448832. Throughput: 0: 968.5. Samples: 860156. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-25 17:14:28,471][09465] Avg episode reward: [(0, '21.470')] +[2023-02-25 17:14:33,469][09465] Fps is (10 sec: 4095.4, 60 sec: 3822.8, 300 sec: 3832.2). Total num frames: 3469312. Throughput: 0: 954.1. Samples: 866542. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-25 17:14:33,472][09465] Avg episode reward: [(0, '22.169')] +[2023-02-25 17:14:38,309][15488] Updated weights for policy 0, policy_version 850 (0.0021) +[2023-02-25 17:14:38,467][09465] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3804.4). Total num frames: 3481600. Throughput: 0: 911.2. Samples: 870506. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-25 17:14:38,475][09465] Avg episode reward: [(0, '22.163')] +[2023-02-25 17:14:43,467][09465] Fps is (10 sec: 2458.0, 60 sec: 3618.1, 300 sec: 3762.8). Total num frames: 3493888. Throughput: 0: 902.2. Samples: 872266. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-25 17:14:43,474][09465] Avg episode reward: [(0, '21.649')] +[2023-02-25 17:14:48,467][09465] Fps is (10 sec: 2867.2, 60 sec: 3549.9, 300 sec: 3762.8). Total num frames: 3510272. Throughput: 0: 881.8. Samples: 876342. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2023-02-25 17:14:48,474][09465] Avg episode reward: [(0, '23.016')] +[2023-02-25 17:14:48,487][15469] Saving new best policy, reward=23.016! +[2023-02-25 17:14:50,890][15488] Updated weights for policy 0, policy_version 860 (0.0027) +[2023-02-25 17:14:53,467][09465] Fps is (10 sec: 3686.4, 60 sec: 3549.9, 300 sec: 3776.7). Total num frames: 3530752. Throughput: 0: 878.7. Samples: 883120. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-25 17:14:53,470][09465] Avg episode reward: [(0, '24.598')] +[2023-02-25 17:14:53,477][15469] Saving new best policy, reward=24.598! +[2023-02-25 17:14:58,469][09465] Fps is (10 sec: 3685.8, 60 sec: 3618.0, 300 sec: 3762.7). Total num frames: 3547136. Throughput: 0: 860.2. Samples: 885526. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-02-25 17:14:58,472][09465] Avg episode reward: [(0, '24.473')] +[2023-02-25 17:15:03,467][09465] Fps is (10 sec: 2867.2, 60 sec: 3481.6, 300 sec: 3735.0). Total num frames: 3559424. Throughput: 0: 861.5. Samples: 889966. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-02-25 17:15:03,470][09465] Avg episode reward: [(0, '24.125')] +[2023-02-25 17:15:03,571][15488] Updated weights for policy 0, policy_version 870 (0.0027) +[2023-02-25 17:15:08,467][09465] Fps is (10 sec: 3687.0, 60 sec: 3481.6, 300 sec: 3748.9). Total num frames: 3584000. Throughput: 0: 883.6. Samples: 896388. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-02-25 17:15:08,472][09465] Avg episode reward: [(0, '23.174')] +[2023-02-25 17:15:12,125][15488] Updated weights for policy 0, policy_version 880 (0.0014) +[2023-02-25 17:15:13,472][09465] Fps is (10 sec: 4913.2, 60 sec: 3617.9, 300 sec: 3790.5). Total num frames: 3608576. Throughput: 0: 884.6. Samples: 899968. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2023-02-25 17:15:13,474][09465] Avg episode reward: [(0, '23.086')] +[2023-02-25 17:15:18,467][09465] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3776.7). Total num frames: 3624960. Throughput: 0: 868.9. Samples: 905640. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-25 17:15:18,471][09465] Avg episode reward: [(0, '22.426')] +[2023-02-25 17:15:23,467][09465] Fps is (10 sec: 2868.4, 60 sec: 3481.6, 300 sec: 3735.0). Total num frames: 3637248. Throughput: 0: 879.1. Samples: 910066. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-02-25 17:15:23,475][09465] Avg episode reward: [(0, '21.633')] +[2023-02-25 17:15:24,609][15488] Updated weights for policy 0, policy_version 890 (0.0012) +[2023-02-25 17:15:28,467][09465] Fps is (10 sec: 3686.4, 60 sec: 3549.9, 300 sec: 3762.8). Total num frames: 3661824. Throughput: 0: 909.0. Samples: 913170. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-02-25 17:15:28,474][09465] Avg episode reward: [(0, '22.108')] +[2023-02-25 17:15:33,097][15488] Updated weights for policy 0, policy_version 900 (0.0032) +[2023-02-25 17:15:33,467][09465] Fps is (10 sec: 4915.2, 60 sec: 3618.2, 300 sec: 3790.5). Total num frames: 3686400. Throughput: 0: 977.5. Samples: 920330. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-25 17:15:33,475][09465] Avg episode reward: [(0, '23.413')] +[2023-02-25 17:15:38,467][09465] Fps is (10 sec: 3686.4, 60 sec: 3618.1, 300 sec: 3762.8). Total num frames: 3698688. Throughput: 0: 939.8. Samples: 925412. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-02-25 17:15:38,470][09465] Avg episode reward: [(0, '23.967')] +[2023-02-25 17:15:43,467][09465] Fps is (10 sec: 2867.2, 60 sec: 3686.4, 300 sec: 3735.0). Total num frames: 3715072. Throughput: 0: 934.2. Samples: 927564. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2023-02-25 17:15:43,470][09465] Avg episode reward: [(0, '24.214')] +[2023-02-25 17:15:45,672][15488] Updated weights for policy 0, policy_version 910 (0.0034) +[2023-02-25 17:15:48,467][09465] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3762.8). Total num frames: 3739648. Throughput: 0: 966.2. Samples: 933444. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-02-25 17:15:48,476][09465] Avg episode reward: [(0, '23.992')] +[2023-02-25 17:15:53,468][09465] Fps is (10 sec: 4505.3, 60 sec: 3822.9, 300 sec: 3790.5). Total num frames: 3760128. Throughput: 0: 979.4. Samples: 940462. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-02-25 17:15:53,472][09465] Avg episode reward: [(0, '23.335')] +[2023-02-25 17:15:55,018][15488] Updated weights for policy 0, policy_version 920 (0.0019) +[2023-02-25 17:15:58,472][09465] Fps is (10 sec: 3684.7, 60 sec: 3822.7, 300 sec: 3762.7). Total num frames: 3776512. Throughput: 0: 957.5. Samples: 943058. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-25 17:15:58,475][09465] Avg episode reward: [(0, '22.098')] +[2023-02-25 17:16:03,467][09465] Fps is (10 sec: 3277.0, 60 sec: 3891.2, 300 sec: 3748.9). Total num frames: 3792896. Throughput: 0: 928.9. Samples: 947442. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-25 17:16:03,471][09465] Avg episode reward: [(0, '20.586')] +[2023-02-25 17:16:06,929][15488] Updated weights for policy 0, policy_version 930 (0.0030) +[2023-02-25 17:16:08,467][09465] Fps is (10 sec: 3688.1, 60 sec: 3822.9, 300 sec: 3748.9). Total num frames: 3813376. Throughput: 0: 971.7. Samples: 953794. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-02-25 17:16:08,469][09465] Avg episode reward: [(0, '20.191')] +[2023-02-25 17:16:13,467][09465] Fps is (10 sec: 4505.6, 60 sec: 3823.2, 300 sec: 3790.6). Total num frames: 3837952. Throughput: 0: 980.7. Samples: 957300. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-02-25 17:16:13,474][09465] Avg episode reward: [(0, '19.938')] +[2023-02-25 17:16:16,886][15488] Updated weights for policy 0, policy_version 940 (0.0015) +[2023-02-25 17:16:18,468][09465] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3762.8). Total num frames: 3854336. Throughput: 0: 948.0. Samples: 962990. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2023-02-25 17:16:18,476][09465] Avg episode reward: [(0, '20.364')] +[2023-02-25 17:16:18,490][15469] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000941_3854336.pth... +[2023-02-25 17:16:18,629][15469] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000720_2949120.pth +[2023-02-25 17:16:23,470][09465] Fps is (10 sec: 2866.5, 60 sec: 3822.8, 300 sec: 3735.0). Total num frames: 3866624. Throughput: 0: 933.1. Samples: 967404. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-02-25 17:16:23,472][09465] Avg episode reward: [(0, '20.596')] +[2023-02-25 17:16:27,868][15488] Updated weights for policy 0, policy_version 950 (0.0031) +[2023-02-25 17:16:28,467][09465] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3762.8). Total num frames: 3891200. Throughput: 0: 956.1. Samples: 970590. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-02-25 17:16:28,475][09465] Avg episode reward: [(0, '22.484')] +[2023-02-25 17:16:33,471][09465] Fps is (10 sec: 4505.2, 60 sec: 3754.4, 300 sec: 3776.6). Total num frames: 3911680. Throughput: 0: 976.7. Samples: 977400. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-25 17:16:33,479][09465] Avg episode reward: [(0, '22.568')] +[2023-02-25 17:16:38,467][09465] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3762.8). Total num frames: 3928064. Throughput: 0: 931.7. Samples: 982388. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-02-25 17:16:38,473][09465] Avg episode reward: [(0, '22.805')] +[2023-02-25 17:16:39,468][15488] Updated weights for policy 0, policy_version 960 (0.0042) +[2023-02-25 17:16:43,467][09465] Fps is (10 sec: 2868.2, 60 sec: 3754.7, 300 sec: 3721.1). Total num frames: 3940352. Throughput: 0: 921.7. Samples: 984532. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-02-25 17:16:43,473][09465] Avg episode reward: [(0, '22.607')] +[2023-02-25 17:16:48,467][09465] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3748.9). Total num frames: 3964928. Throughput: 0: 944.4. Samples: 989942. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-02-25 17:16:48,470][09465] Avg episode reward: [(0, '22.773')] +[2023-02-25 17:16:50,114][15488] Updated weights for policy 0, policy_version 970 (0.0029) +[2023-02-25 17:16:53,467][09465] Fps is (10 sec: 4505.6, 60 sec: 3754.7, 300 sec: 3776.7). Total num frames: 3985408. Throughput: 0: 951.2. Samples: 996598. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-02-25 17:16:53,472][09465] Avg episode reward: [(0, '21.686')] +[2023-02-25 17:16:58,468][09465] Fps is (10 sec: 3686.4, 60 sec: 3755.0, 300 sec: 3748.9). Total num frames: 4001792. Throughput: 0: 930.3. Samples: 999164. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-25 17:16:58,473][09465] Avg episode reward: [(0, '21.724')] +[2023-02-25 17:16:59,601][15469] Stopping Batcher_0... +[2023-02-25 17:16:59,603][15469] Loop batcher_evt_loop terminating... +[2023-02-25 17:16:59,603][09465] Component Batcher_0 stopped! +[2023-02-25 17:16:59,610][15469] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... +[2023-02-25 17:16:59,690][09465] Component RolloutWorker_w3 stopped! +[2023-02-25 17:16:59,697][15491] Stopping RolloutWorker_w3... +[2023-02-25 17:16:59,697][15491] Loop rollout_proc3_evt_loop terminating... +[2023-02-25 17:16:59,716][09465] Component RolloutWorker_w5 stopped! +[2023-02-25 17:16:59,713][15493] Stopping RolloutWorker_w5... +[2023-02-25 17:16:59,726][15488] Weights refcount: 2 0 +[2023-02-25 17:16:59,728][15493] Loop rollout_proc5_evt_loop terminating... +[2023-02-25 17:16:59,747][15489] Stopping RolloutWorker_w1... +[2023-02-25 17:16:59,747][09465] Component InferenceWorker_p0-w0 stopped! +[2023-02-25 17:16:59,748][15495] Stopping RolloutWorker_w7... +[2023-02-25 17:16:59,749][15488] Stopping InferenceWorker_p0-w0... +[2023-02-25 17:16:59,751][15488] Loop inference_proc0-0_evt_loop terminating... +[2023-02-25 17:16:59,760][09465] Component RolloutWorker_w1 stopped! +[2023-02-25 17:16:59,764][15495] Loop rollout_proc7_evt_loop terminating... +[2023-02-25 17:16:59,762][15489] Loop rollout_proc1_evt_loop terminating... +[2023-02-25 17:16:59,763][09465] Component RolloutWorker_w7 stopped! +[2023-02-25 17:16:59,788][09465] Component RolloutWorker_w0 stopped! +[2023-02-25 17:16:59,799][15487] Stopping RolloutWorker_w0... +[2023-02-25 17:16:59,799][15487] Loop rollout_proc0_evt_loop terminating... +[2023-02-25 17:16:59,821][15469] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000831_3403776.pth +[2023-02-25 17:16:59,836][15469] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... +[2023-02-25 17:16:59,837][09465] Component RolloutWorker_w2 stopped! +[2023-02-25 17:16:59,843][15490] Stopping RolloutWorker_w2... +[2023-02-25 17:16:59,844][15490] Loop rollout_proc2_evt_loop terminating... +[2023-02-25 17:16:59,857][15492] Stopping RolloutWorker_w4... +[2023-02-25 17:16:59,858][15492] Loop rollout_proc4_evt_loop terminating... +[2023-02-25 17:16:59,856][09465] Component RolloutWorker_w4 stopped! +[2023-02-25 17:16:59,871][09465] Component RolloutWorker_w6 stopped! +[2023-02-25 17:16:59,874][15494] Stopping RolloutWorker_w6... +[2023-02-25 17:16:59,874][15494] Loop rollout_proc6_evt_loop terminating... +[2023-02-25 17:17:00,166][09465] Component LearnerWorker_p0 stopped! +[2023-02-25 17:17:00,169][09465] Waiting for process learner_proc0 to stop... +[2023-02-25 17:17:00,171][15469] Stopping LearnerWorker_p0... +[2023-02-25 17:17:00,172][15469] Loop learner_proc0_evt_loop terminating... +[2023-02-25 17:17:02,401][09465] Waiting for process inference_proc0-0 to join... +[2023-02-25 17:17:03,180][09465] Waiting for process rollout_proc0 to join... +[2023-02-25 17:17:03,842][09465] Waiting for process rollout_proc1 to join... +[2023-02-25 17:17:03,845][09465] Waiting for process rollout_proc2 to join... +[2023-02-25 17:17:03,846][09465] Waiting for process rollout_proc3 to join... +[2023-02-25 17:17:03,848][09465] Waiting for process rollout_proc4 to join... +[2023-02-25 17:17:03,857][09465] Waiting for process rollout_proc5 to join... +[2023-02-25 17:17:03,858][09465] Waiting for process rollout_proc6 to join... +[2023-02-25 17:17:03,859][09465] Waiting for process rollout_proc7 to join... +[2023-02-25 17:17:03,860][09465] Batcher 0 profile tree view: +batching: 26.4756, releasing_batches: 0.0250 +[2023-02-25 17:17:03,866][09465] InferenceWorker_p0-w0 profile tree view: +wait_policy: 0.0101 + wait_policy_total: 534.2617 +update_model: 7.4674 + weight_update: 0.0032 +one_step: 0.0088 + handle_policy_step: 508.4441 + deserialize: 14.7466, stack: 2.8181, obs_to_device_normalize: 114.0070, forward: 241.3566, send_messages: 26.3637 + prepare_outputs: 83.3078 + to_cpu: 52.3688 +[2023-02-25 17:17:03,868][09465] Learner 0 profile tree view: +misc: 0.0066, prepare_batch: 17.4787 +train: 76.3863 + epoch_init: 0.0056, minibatch_init: 0.0098, losses_postprocess: 0.4878, kl_divergence: 0.6374, after_optimizer: 33.0138 + calculate_losses: 27.2178 + losses_init: 0.0035, forward_head: 1.6556, bptt_initial: 17.9599, tail: 1.0816, advantages_returns: 0.3520, losses: 3.6775 + bptt: 2.1856 + bptt_forward_core: 2.1087 + update: 14.4016 + clip: 1.4061 +[2023-02-25 17:17:03,869][09465] RolloutWorker_w0 profile tree view: +wait_for_trajectories: 0.3915, enqueue_policy_requests: 142.4984, env_step: 825.7155, overhead: 20.7273, complete_rollouts: 6.7821 +save_policy_outputs: 20.0824 + split_output_tensors: 9.7964 +[2023-02-25 17:17:03,871][09465] RolloutWorker_w7 profile tree view: +wait_for_trajectories: 0.3463, enqueue_policy_requests: 146.0947, env_step: 822.4486, overhead: 19.9156, complete_rollouts: 7.4870 +save_policy_outputs: 18.9318 + split_output_tensors: 9.1657 +[2023-02-25 17:17:03,877][09465] Loop Runner_EvtLoop terminating... +[2023-02-25 17:17:03,878][09465] Runner profile tree view: +main_loop: 1121.0972 +[2023-02-25 17:17:03,880][09465] Collected {0: 4005888}, FPS: 3573.2 +[2023-02-25 17:17:31,555][09465] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json +[2023-02-25 17:17:31,559][09465] Overriding arg 'num_workers' with value 1 passed from command line +[2023-02-25 17:17:31,561][09465] Adding new argument 'no_render'=True that is not in the saved config file! +[2023-02-25 17:17:31,564][09465] Adding new argument 'save_video'=True that is not in the saved config file! +[2023-02-25 17:17:31,566][09465] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file! +[2023-02-25 17:17:31,568][09465] Adding new argument 'video_name'=None that is not in the saved config file! +[2023-02-25 17:17:31,570][09465] Adding new argument 'max_num_frames'=1000000000.0 that is not in the saved config file! +[2023-02-25 17:17:31,571][09465] Adding new argument 'max_num_episodes'=10 that is not in the saved config file! +[2023-02-25 17:17:31,572][09465] Adding new argument 'push_to_hub'=False that is not in the saved config file! +[2023-02-25 17:17:31,574][09465] Adding new argument 'hf_repository'=None that is not in the saved config file! +[2023-02-25 17:17:31,575][09465] Adding new argument 'policy_index'=0 that is not in the saved config file! +[2023-02-25 17:17:31,576][09465] Adding new argument 'eval_deterministic'=False that is not in the saved config file! +[2023-02-25 17:17:31,578][09465] Adding new argument 'train_script'=None that is not in the saved config file! +[2023-02-25 17:17:31,579][09465] Adding new argument 'enjoy_script'=None that is not in the saved config file! +[2023-02-25 17:17:31,581][09465] Using frameskip 1 and render_action_repeat=4 for evaluation +[2023-02-25 17:17:31,611][09465] Doom resolution: 160x120, resize resolution: (128, 72) +[2023-02-25 17:17:31,615][09465] RunningMeanStd input shape: (3, 72, 128) +[2023-02-25 17:17:31,619][09465] RunningMeanStd input shape: (1,) +[2023-02-25 17:17:31,640][09465] ConvEncoder: input_channels=3 +[2023-02-25 17:17:32,314][09465] Conv encoder output size: 512 +[2023-02-25 17:17:32,316][09465] Policy head output size: 512 +[2023-02-25 17:17:34,787][09465] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... +[2023-02-25 17:17:36,130][09465] Num frames 100... +[2023-02-25 17:17:36,246][09465] Num frames 200... +[2023-02-25 17:17:36,371][09465] Num frames 300... +[2023-02-25 17:17:36,492][09465] Avg episode rewards: #0: 4.520, true rewards: #0: 3.520 +[2023-02-25 17:17:36,494][09465] Avg episode reward: 4.520, avg true_objective: 3.520 +[2023-02-25 17:17:36,552][09465] Num frames 400... +[2023-02-25 17:17:36,670][09465] Num frames 500... +[2023-02-25 17:17:36,795][09465] Num frames 600... +[2023-02-25 17:17:36,907][09465] Num frames 700... +[2023-02-25 17:17:37,027][09465] Num frames 800... +[2023-02-25 17:17:37,144][09465] Num frames 900... +[2023-02-25 17:17:37,254][09465] Num frames 1000... +[2023-02-25 17:17:37,366][09465] Num frames 1100... +[2023-02-25 17:17:37,492][09465] Num frames 1200... +[2023-02-25 17:17:37,621][09465] Avg episode rewards: #0: 10.825, true rewards: #0: 6.325 +[2023-02-25 17:17:37,622][09465] Avg episode reward: 10.825, avg true_objective: 6.325 +[2023-02-25 17:17:37,669][09465] Num frames 1300... +[2023-02-25 17:17:37,796][09465] Num frames 1400... +[2023-02-25 17:17:37,915][09465] Avg episode rewards: #0: 7.830, true rewards: #0: 4.830 +[2023-02-25 17:17:37,916][09465] Avg episode reward: 7.830, avg true_objective: 4.830 +[2023-02-25 17:17:37,978][09465] Num frames 1500... +[2023-02-25 17:17:38,098][09465] Num frames 1600... +[2023-02-25 17:17:38,234][09465] Num frames 1700... +[2023-02-25 17:17:38,348][09465] Num frames 1800... +[2023-02-25 17:17:38,466][09465] Num frames 1900... +[2023-02-25 17:17:38,590][09465] Num frames 2000... +[2023-02-25 17:17:38,713][09465] Num frames 2100... +[2023-02-25 17:17:38,902][09465] Num frames 2200... +[2023-02-25 17:17:39,075][09465] Num frames 2300... +[2023-02-25 17:17:39,237][09465] Num frames 2400... +[2023-02-25 17:17:39,403][09465] Num frames 2500... +[2023-02-25 17:17:39,565][09465] Num frames 2600... +[2023-02-25 17:17:39,785][09465] Avg episode rewards: #0: 13.243, true rewards: #0: 6.742 +[2023-02-25 17:17:39,788][09465] Avg episode reward: 13.243, avg true_objective: 6.742 +[2023-02-25 17:17:39,796][09465] Num frames 2700... +[2023-02-25 17:17:39,971][09465] Num frames 2800... +[2023-02-25 17:17:40,130][09465] Num frames 2900... +[2023-02-25 17:17:40,288][09465] Num frames 3000... +[2023-02-25 17:17:40,452][09465] Num frames 3100... +[2023-02-25 17:17:40,615][09465] Num frames 3200... +[2023-02-25 17:17:40,694][09465] Avg episode rewards: #0: 12.218, true rewards: #0: 6.418 +[2023-02-25 17:17:40,697][09465] Avg episode reward: 12.218, avg true_objective: 6.418 +[2023-02-25 17:17:40,853][09465] Num frames 3300... +[2023-02-25 17:17:41,030][09465] Num frames 3400... +[2023-02-25 17:17:41,192][09465] Num frames 3500... +[2023-02-25 17:17:41,355][09465] Num frames 3600... +[2023-02-25 17:17:41,527][09465] Num frames 3700... +[2023-02-25 17:17:41,697][09465] Num frames 3800... +[2023-02-25 17:17:41,867][09465] Num frames 3900... +[2023-02-25 17:17:42,037][09465] Num frames 4000... +[2023-02-25 17:17:42,209][09465] Num frames 4100... +[2023-02-25 17:17:42,375][09465] Num frames 4200... +[2023-02-25 17:17:42,518][09465] Num frames 4300... +[2023-02-25 17:17:42,638][09465] Num frames 4400... +[2023-02-25 17:17:42,755][09465] Num frames 4500... +[2023-02-25 17:17:42,888][09465] Num frames 4600... +[2023-02-25 17:17:43,024][09465] Num frames 4700... +[2023-02-25 17:17:43,140][09465] Num frames 4800... +[2023-02-25 17:17:43,253][09465] Num frames 4900... +[2023-02-25 17:17:43,319][09465] Avg episode rewards: #0: 17.013, true rewards: #0: 8.180 +[2023-02-25 17:17:43,320][09465] Avg episode reward: 17.013, avg true_objective: 8.180 +[2023-02-25 17:17:43,432][09465] Num frames 5000... +[2023-02-25 17:17:43,548][09465] Num frames 5100... +[2023-02-25 17:17:43,682][09465] Num frames 5200... +[2023-02-25 17:17:43,809][09465] Num frames 5300... +[2023-02-25 17:17:43,940][09465] Num frames 5400... +[2023-02-25 17:17:44,065][09465] Num frames 5500... +[2023-02-25 17:17:44,194][09465] Num frames 5600... +[2023-02-25 17:17:44,316][09465] Num frames 5700... +[2023-02-25 17:17:44,471][09465] Avg episode rewards: #0: 16.970, true rewards: #0: 8.256 +[2023-02-25 17:17:44,473][09465] Avg episode reward: 16.970, avg true_objective: 8.256 +[2023-02-25 17:17:44,501][09465] Num frames 5800... +[2023-02-25 17:17:44,631][09465] Num frames 5900... +[2023-02-25 17:17:44,750][09465] Num frames 6000... +[2023-02-25 17:17:44,872][09465] Num frames 6100... +[2023-02-25 17:17:44,996][09465] Num frames 6200... +[2023-02-25 17:17:45,134][09465] Num frames 6300... +[2023-02-25 17:17:45,248][09465] Num frames 6400... +[2023-02-25 17:17:45,371][09465] Num frames 6500... +[2023-02-25 17:17:45,514][09465] Avg episode rewards: #0: 16.974, true rewards: #0: 8.224 +[2023-02-25 17:17:45,516][09465] Avg episode reward: 16.974, avg true_objective: 8.224 +[2023-02-25 17:17:45,544][09465] Num frames 6600... +[2023-02-25 17:17:45,659][09465] Num frames 6700... +[2023-02-25 17:17:45,782][09465] Num frames 6800... +[2023-02-25 17:17:45,897][09465] Num frames 6900... +[2023-02-25 17:17:46,026][09465] Num frames 7000... +[2023-02-25 17:17:46,147][09465] Num frames 7100... +[2023-02-25 17:17:46,261][09465] Num frames 7200... +[2023-02-25 17:17:46,377][09465] Num frames 7300... +[2023-02-25 17:17:46,490][09465] Num frames 7400... +[2023-02-25 17:17:46,610][09465] Num frames 7500... +[2023-02-25 17:17:46,733][09465] Num frames 7600... +[2023-02-25 17:17:46,858][09465] Num frames 7700... +[2023-02-25 17:17:46,975][09465] Num frames 7800... +[2023-02-25 17:17:47,079][09465] Avg episode rewards: #0: 18.147, true rewards: #0: 8.702 +[2023-02-25 17:17:47,081][09465] Avg episode reward: 18.147, avg true_objective: 8.702 +[2023-02-25 17:17:47,172][09465] Num frames 7900... +[2023-02-25 17:17:47,288][09465] Num frames 8000... +[2023-02-25 17:17:47,401][09465] Num frames 8100... +[2023-02-25 17:17:47,515][09465] Num frames 8200... +[2023-02-25 17:17:47,633][09465] Num frames 8300... +[2023-02-25 17:17:47,747][09465] Num frames 8400... +[2023-02-25 17:17:47,868][09465] Num frames 8500... +[2023-02-25 17:17:48,005][09465] Avg episode rewards: #0: 17.668, true rewards: #0: 8.568 +[2023-02-25 17:17:48,008][09465] Avg episode reward: 17.668, avg true_objective: 8.568 +[2023-02-25 17:18:40,246][09465] Replay video saved to /content/train_dir/default_experiment/replay.mp4! +[2023-02-25 17:19:49,771][09465] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json +[2023-02-25 17:19:49,773][09465] Overriding arg 'num_workers' with value 1 passed from command line +[2023-02-25 17:19:49,774][09465] Adding new argument 'no_render'=True that is not in the saved config file! +[2023-02-25 17:19:49,776][09465] Adding new argument 'save_video'=True that is not in the saved config file! +[2023-02-25 17:19:49,783][09465] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file! +[2023-02-25 17:19:49,785][09465] Adding new argument 'video_name'=None that is not in the saved config file! +[2023-02-25 17:19:49,788][09465] Adding new argument 'max_num_frames'=100000 that is not in the saved config file! +[2023-02-25 17:19:49,789][09465] Adding new argument 'max_num_episodes'=10 that is not in the saved config file! +[2023-02-25 17:19:49,790][09465] Adding new argument 'push_to_hub'=True that is not in the saved config file! +[2023-02-25 17:19:49,791][09465] Adding new argument 'hf_repository'='morganjeffries/rl_course_vizdoom_health_gathering_supreme' that is not in the saved config file! +[2023-02-25 17:19:49,793][09465] Adding new argument 'policy_index'=0 that is not in the saved config file! +[2023-02-25 17:19:49,794][09465] Adding new argument 'eval_deterministic'=False that is not in the saved config file! +[2023-02-25 17:19:49,795][09465] Adding new argument 'train_script'=None that is not in the saved config file! +[2023-02-25 17:19:49,796][09465] Adding new argument 'enjoy_script'=None that is not in the saved config file! +[2023-02-25 17:19:49,797][09465] Using frameskip 1 and render_action_repeat=4 for evaluation +[2023-02-25 17:19:49,825][09465] RunningMeanStd input shape: (3, 72, 128) +[2023-02-25 17:19:49,828][09465] RunningMeanStd input shape: (1,) +[2023-02-25 17:19:49,843][09465] ConvEncoder: input_channels=3 +[2023-02-25 17:19:49,881][09465] Conv encoder output size: 512 +[2023-02-25 17:19:49,882][09465] Policy head output size: 512 +[2023-02-25 17:19:49,903][09465] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... +[2023-02-25 17:19:50,381][09465] Num frames 100... +[2023-02-25 17:19:50,503][09465] Num frames 200... +[2023-02-25 17:19:50,628][09465] Num frames 300... +[2023-02-25 17:19:50,751][09465] Num frames 400... +[2023-02-25 17:19:50,902][09465] Num frames 500... +[2023-02-25 17:19:51,080][09465] Num frames 600... +[2023-02-25 17:19:51,252][09465] Num frames 700... +[2023-02-25 17:19:51,428][09465] Num frames 800... +[2023-02-25 17:19:51,589][09465] Num frames 900... +[2023-02-25 17:19:51,755][09465] Num frames 1000... +[2023-02-25 17:19:51,940][09465] Num frames 1100... +[2023-02-25 17:19:52,107][09465] Num frames 1200... +[2023-02-25 17:19:52,193][09465] Avg episode rewards: #0: 28.160, true rewards: #0: 12.160 +[2023-02-25 17:19:52,198][09465] Avg episode reward: 28.160, avg true_objective: 12.160 +[2023-02-25 17:19:52,338][09465] Num frames 1300... +[2023-02-25 17:19:52,517][09465] Num frames 1400... +[2023-02-25 17:19:52,682][09465] Num frames 1500... +[2023-02-25 17:19:52,849][09465] Num frames 1600... +[2023-02-25 17:19:53,017][09465] Num frames 1700... +[2023-02-25 17:19:53,176][09465] Num frames 1800... +[2023-02-25 17:19:53,335][09465] Num frames 1900... +[2023-02-25 17:19:53,496][09465] Num frames 2000... +[2023-02-25 17:19:53,660][09465] Num frames 2100... +[2023-02-25 17:19:53,822][09465] Num frames 2200... +[2023-02-25 17:19:53,984][09465] Num frames 2300... +[2023-02-25 17:19:54,302][09465] Num frames 2400... +[2023-02-25 17:19:54,706][09465] Avg episode rewards: #0: 26.980, true rewards: #0: 12.480 +[2023-02-25 17:19:54,712][09465] Avg episode reward: 26.980, avg true_objective: 12.480 +[2023-02-25 17:19:54,734][09465] Num frames 2500... +[2023-02-25 17:19:55,007][09465] Num frames 2600... +[2023-02-25 17:19:55,242][09465] Num frames 2700... +[2023-02-25 17:19:55,488][09465] Num frames 2800... +[2023-02-25 17:19:55,642][09465] Num frames 2900... +[2023-02-25 17:19:55,761][09465] Num frames 3000... +[2023-02-25 17:19:55,878][09465] Num frames 3100... +[2023-02-25 17:19:55,994][09465] Num frames 3200... +[2023-02-25 17:19:56,116][09465] Num frames 3300... +[2023-02-25 17:19:56,241][09465] Num frames 3400... +[2023-02-25 17:19:56,394][09465] Avg episode rewards: #0: 24.294, true rewards: #0: 11.627 +[2023-02-25 17:19:56,396][09465] Avg episode reward: 24.294, avg true_objective: 11.627 +[2023-02-25 17:19:56,417][09465] Num frames 3500... +[2023-02-25 17:19:56,535][09465] Num frames 3600... +[2023-02-25 17:19:56,660][09465] Num frames 3700... +[2023-02-25 17:19:56,775][09465] Num frames 3800... +[2023-02-25 17:19:56,894][09465] Num frames 3900... +[2023-02-25 17:19:56,956][09465] Avg episode rewards: #0: 19.760, true rewards: #0: 9.760 +[2023-02-25 17:19:56,961][09465] Avg episode reward: 19.760, avg true_objective: 9.760 +[2023-02-25 17:19:57,080][09465] Num frames 4000... +[2023-02-25 17:19:57,204][09465] Num frames 4100... +[2023-02-25 17:19:57,327][09465] Num frames 4200... +[2023-02-25 17:19:57,447][09465] Num frames 4300... +[2023-02-25 17:19:57,569][09465] Num frames 4400... +[2023-02-25 17:19:57,695][09465] Num frames 4500... +[2023-02-25 17:19:57,815][09465] Avg episode rewards: #0: 18.514, true rewards: #0: 9.114 +[2023-02-25 17:19:57,817][09465] Avg episode reward: 18.514, avg true_objective: 9.114 +[2023-02-25 17:19:57,871][09465] Num frames 4600... +[2023-02-25 17:19:58,002][09465] Num frames 4700... +[2023-02-25 17:19:58,124][09465] Num frames 4800... +[2023-02-25 17:19:58,241][09465] Num frames 4900... +[2023-02-25 17:19:58,360][09465] Num frames 5000... +[2023-02-25 17:19:58,487][09465] Num frames 5100... +[2023-02-25 17:19:58,584][09465] Avg episode rewards: #0: 17.055, true rewards: #0: 8.555 +[2023-02-25 17:19:58,585][09465] Avg episode reward: 17.055, avg true_objective: 8.555 +[2023-02-25 17:19:58,686][09465] Num frames 5200... +[2023-02-25 17:19:58,802][09465] Num frames 5300... +[2023-02-25 17:19:58,916][09465] Num frames 5400... +[2023-02-25 17:19:59,034][09465] Num frames 5500... +[2023-02-25 17:19:59,154][09465] Num frames 5600... +[2023-02-25 17:19:59,279][09465] Num frames 5700... +[2023-02-25 17:19:59,395][09465] Num frames 5800... +[2023-02-25 17:19:59,512][09465] Num frames 5900... +[2023-02-25 17:19:59,628][09465] Num frames 6000... +[2023-02-25 17:19:59,758][09465] Num frames 6100... +[2023-02-25 17:19:59,876][09465] Num frames 6200... +[2023-02-25 17:19:59,991][09465] Num frames 6300... +[2023-02-25 17:20:00,115][09465] Num frames 6400... +[2023-02-25 17:20:00,242][09465] Num frames 6500... +[2023-02-25 17:20:00,361][09465] Num frames 6600... +[2023-02-25 17:20:00,484][09465] Num frames 6700... +[2023-02-25 17:20:00,601][09465] Num frames 6800... +[2023-02-25 17:20:00,726][09465] Num frames 6900... +[2023-02-25 17:20:00,901][09465] Avg episode rewards: #0: 21.423, true rewards: #0: 9.994 +[2023-02-25 17:20:00,903][09465] Avg episode reward: 21.423, avg true_objective: 9.994 +[2023-02-25 17:20:00,911][09465] Num frames 7000... +[2023-02-25 17:20:01,022][09465] Num frames 7100... +[2023-02-25 17:20:01,139][09465] Num frames 7200... +[2023-02-25 17:20:01,260][09465] Num frames 7300... +[2023-02-25 17:20:01,380][09465] Num frames 7400... +[2023-02-25 17:20:01,500][09465] Num frames 7500... +[2023-02-25 17:20:01,615][09465] Num frames 7600... +[2023-02-25 17:20:01,748][09465] Num frames 7700... +[2023-02-25 17:20:01,877][09465] Num frames 7800... +[2023-02-25 17:20:02,007][09465] Num frames 7900... +[2023-02-25 17:20:02,147][09465] Num frames 8000... +[2023-02-25 17:20:02,264][09465] Num frames 8100... +[2023-02-25 17:20:02,389][09465] Num frames 8200... +[2023-02-25 17:20:02,513][09465] Num frames 8300... +[2023-02-25 17:20:02,635][09465] Num frames 8400... +[2023-02-25 17:20:02,756][09465] Num frames 8500... +[2023-02-25 17:20:02,880][09465] Num frames 8600... +[2023-02-25 17:20:02,994][09465] Num frames 8700... +[2023-02-25 17:20:03,111][09465] Num frames 8800... +[2023-02-25 17:20:03,237][09465] Num frames 8900... +[2023-02-25 17:20:03,355][09465] Num frames 9000... +[2023-02-25 17:20:03,468][09465] Avg episode rewards: #0: 25.680, true rewards: #0: 11.305 +[2023-02-25 17:20:03,469][09465] Avg episode reward: 25.680, avg true_objective: 11.305 +[2023-02-25 17:20:03,536][09465] Num frames 9100... +[2023-02-25 17:20:03,655][09465] Num frames 9200... +[2023-02-25 17:20:03,776][09465] Num frames 9300... +[2023-02-25 17:20:03,894][09465] Num frames 9400... +[2023-02-25 17:20:04,016][09465] Num frames 9500... +[2023-02-25 17:20:04,136][09465] Num frames 9600... +[2023-02-25 17:20:04,220][09465] Avg episode rewards: #0: 23.911, true rewards: #0: 10.689 +[2023-02-25 17:20:04,223][09465] Avg episode reward: 23.911, avg true_objective: 10.689 +[2023-02-25 17:20:04,316][09465] Num frames 9700... +[2023-02-25 17:20:04,436][09465] Num frames 9800... +[2023-02-25 17:20:04,561][09465] Num frames 9900... +[2023-02-25 17:20:04,679][09465] Num frames 10000... +[2023-02-25 17:20:04,805][09465] Num frames 10100... +[2023-02-25 17:20:04,964][09465] Num frames 10200... +[2023-02-25 17:20:05,133][09465] Num frames 10300... +[2023-02-25 17:20:05,307][09465] Num frames 10400... +[2023-02-25 17:20:05,471][09465] Num frames 10500... +[2023-02-25 17:20:05,637][09465] Num frames 10600... +[2023-02-25 17:20:05,813][09465] Num frames 10700... +[2023-02-25 17:20:05,981][09465] Num frames 10800... +[2023-02-25 17:20:06,149][09465] Num frames 10900... +[2023-02-25 17:20:06,309][09465] Num frames 11000... +[2023-02-25 17:20:06,531][09465] Avg episode rewards: #0: 25.399, true rewards: #0: 11.099 +[2023-02-25 17:20:06,537][09465] Avg episode reward: 25.399, avg true_objective: 11.099 +[2023-02-25 17:20:06,542][09465] Num frames 11100... +[2023-02-25 17:21:16,250][09465] Replay video saved to /content/train_dir/default_experiment/replay.mp4!