[2024-11-13 13:31:05,379][00418] Saving configuration to /content/train_dir/default_experiment/config.json... [2024-11-13 13:31:05,384][00418] Rollout worker 0 uses device cpu [2024-11-13 13:31:05,387][00418] Rollout worker 1 uses device cpu [2024-11-13 13:31:05,390][00418] Rollout worker 2 uses device cpu [2024-11-13 13:31:05,392][00418] Rollout worker 3 uses device cpu [2024-11-13 13:31:05,394][00418] Rollout worker 4 uses device cpu [2024-11-13 13:31:05,396][00418] Rollout worker 5 uses device cpu [2024-11-13 13:31:05,398][00418] Rollout worker 6 uses device cpu [2024-11-13 13:31:05,401][00418] Rollout worker 7 uses device cpu [2024-11-13 13:31:05,646][00418] Using GPUs [0] for process 0 (actually maps to GPUs [0]) [2024-11-13 13:31:05,652][00418] InferenceWorker_p0-w0: min num requests: 2 [2024-11-13 13:31:05,740][00418] Starting all processes... [2024-11-13 13:31:05,745][00418] Starting process learner_proc0 [2024-11-13 13:31:05,851][00418] Starting all processes... [2024-11-13 13:31:05,863][00418] Starting process inference_proc0-0 [2024-11-13 13:31:05,863][00418] Starting process rollout_proc0 [2024-11-13 13:31:05,863][00418] Starting process rollout_proc1 [2024-11-13 13:31:05,863][00418] Starting process rollout_proc2 [2024-11-13 13:31:05,863][00418] Starting process rollout_proc3 [2024-11-13 13:31:05,863][00418] Starting process rollout_proc4 [2024-11-13 13:31:05,863][00418] Starting process rollout_proc5 [2024-11-13 13:31:05,864][00418] Starting process rollout_proc6 [2024-11-13 13:31:05,864][00418] Starting process rollout_proc7 [2024-11-13 13:31:23,973][02455] Worker 4 uses CPU cores [0] [2024-11-13 13:31:24,063][02436] Using GPUs [0] for process 0 (actually maps to GPUs [0]) [2024-11-13 13:31:24,067][02436] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0 [2024-11-13 13:31:24,169][02436] Num visible devices: 1 [2024-11-13 13:31:24,226][02436] Starting seed is not provided [2024-11-13 13:31:24,227][02436] Using GPUs [0] for process 0 (actually maps to GPUs [0]) [2024-11-13 13:31:24,228][02436] Initializing actor-critic model on device cuda:0 [2024-11-13 13:31:24,228][02436] RunningMeanStd input shape: (3, 72, 128) [2024-11-13 13:31:24,231][02436] RunningMeanStd input shape: (1,) [2024-11-13 13:31:24,382][02436] ConvEncoder: input_channels=3 [2024-11-13 13:31:24,675][02451] Worker 2 uses CPU cores [0] [2024-11-13 13:31:24,690][02457] Worker 6 uses CPU cores [0] [2024-11-13 13:31:24,759][02450] Worker 5 uses CPU cores [1] [2024-11-13 13:31:24,958][02456] Using GPUs [0] for process 0 (actually maps to GPUs [0]) [2024-11-13 13:31:24,959][02456] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0 [2024-11-13 13:31:25,003][02453] Worker 0 uses CPU cores [0] [2024-11-13 13:31:25,023][02452] Worker 3 uses CPU cores [1] [2024-11-13 13:31:25,049][02456] Num visible devices: 1 [2024-11-13 13:31:25,163][02454] Worker 7 uses CPU cores [1] [2024-11-13 13:31:25,222][02449] Worker 1 uses CPU cores [1] [2024-11-13 13:31:25,282][02436] Conv encoder output size: 512 [2024-11-13 13:31:25,283][02436] Policy head output size: 512 [2024-11-13 13:31:25,343][02436] Created Actor Critic model with architecture: [2024-11-13 13:31:25,344][02436] ActorCriticSharedWeights( (obs_normalizer): ObservationNormalizer( (running_mean_std): RunningMeanStdDictInPlace( (running_mean_std): ModuleDict( (obs): RunningMeanStdInPlace() ) ) ) (returns_normalizer): RecursiveScriptModule(original_name=RunningMeanStdInPlace) (encoder): VizdoomEncoder( (basic_encoder): ConvEncoder( (enc): RecursiveScriptModule( original_name=ConvEncoderImpl (conv_head): RecursiveScriptModule( original_name=Sequential (0): RecursiveScriptModule(original_name=Conv2d) (1): RecursiveScriptModule(original_name=ELU) (2): RecursiveScriptModule(original_name=Conv2d) (3): RecursiveScriptModule(original_name=ELU) (4): RecursiveScriptModule(original_name=Conv2d) (5): RecursiveScriptModule(original_name=ELU) ) (mlp_layers): RecursiveScriptModule( original_name=Sequential (0): RecursiveScriptModule(original_name=Linear) (1): RecursiveScriptModule(original_name=ELU) ) ) ) ) (core): ModelCoreRNN( (core): GRU(512, 512) ) (decoder): MlpDecoder( (mlp): Identity() ) (critic_linear): Linear(in_features=512, out_features=1, bias=True) (action_parameterization): ActionParameterizationDefault( (distribution_linear): Linear(in_features=512, out_features=5, bias=True) ) ) [2024-11-13 13:31:25,635][00418] Heartbeat connected on Batcher_0 [2024-11-13 13:31:25,646][00418] Heartbeat connected on InferenceWorker_p0-w0 [2024-11-13 13:31:25,664][00418] Heartbeat connected on RolloutWorker_w0 [2024-11-13 13:31:25,670][00418] Heartbeat connected on RolloutWorker_w1 [2024-11-13 13:31:25,674][02436] Using optimizer [2024-11-13 13:31:25,697][00418] Heartbeat connected on RolloutWorker_w2 [2024-11-13 13:31:25,708][00418] Heartbeat connected on RolloutWorker_w3 [2024-11-13 13:31:25,723][00418] Heartbeat connected on RolloutWorker_w5 [2024-11-13 13:31:25,725][00418] Heartbeat connected on RolloutWorker_w4 [2024-11-13 13:31:25,736][00418] Heartbeat connected on RolloutWorker_w6 [2024-11-13 13:31:25,739][00418] Heartbeat connected on RolloutWorker_w7 [2024-11-13 13:31:29,171][02436] No checkpoints found [2024-11-13 13:31:29,171][02436] Did not load from checkpoint, starting from scratch! [2024-11-13 13:31:29,172][02436] Initialized policy 0 weights for model version 0 [2024-11-13 13:31:29,175][02436] Using GPUs [0] for process 0 (actually maps to GPUs [0]) [2024-11-13 13:31:29,183][02436] LearnerWorker_p0 finished initialization! [2024-11-13 13:31:29,184][00418] Heartbeat connected on LearnerWorker_p0 [2024-11-13 13:31:29,275][02456] RunningMeanStd input shape: (3, 72, 128) [2024-11-13 13:31:29,276][02456] RunningMeanStd input shape: (1,) [2024-11-13 13:31:29,288][02456] ConvEncoder: input_channels=3 [2024-11-13 13:31:29,389][02456] Conv encoder output size: 512 [2024-11-13 13:31:29,389][02456] Policy head output size: 512 [2024-11-13 13:31:29,442][00418] Inference worker 0-0 is ready! [2024-11-13 13:31:29,443][00418] All inference workers are ready! Signal rollout workers to start! [2024-11-13 13:31:29,645][02451] Doom resolution: 160x120, resize resolution: (128, 72) [2024-11-13 13:31:29,649][02457] Doom resolution: 160x120, resize resolution: (128, 72) [2024-11-13 13:31:29,651][02455] Doom resolution: 160x120, resize resolution: (128, 72) [2024-11-13 13:31:29,648][02453] Doom resolution: 160x120, resize resolution: (128, 72) [2024-11-13 13:31:29,648][02452] Doom resolution: 160x120, resize resolution: (128, 72) [2024-11-13 13:31:29,650][02449] Doom resolution: 160x120, resize resolution: (128, 72) [2024-11-13 13:31:29,660][02450] Doom resolution: 160x120, resize resolution: (128, 72) [2024-11-13 13:31:29,655][02454] Doom resolution: 160x120, resize resolution: (128, 72) [2024-11-13 13:31:30,606][02455] Decorrelating experience for 0 frames... [2024-11-13 13:31:31,053][02454] Decorrelating experience for 0 frames... [2024-11-13 13:31:31,057][02452] Decorrelating experience for 0 frames... [2024-11-13 13:31:31,061][02450] Decorrelating experience for 0 frames... [2024-11-13 13:31:31,412][02449] Decorrelating experience for 0 frames... [2024-11-13 13:31:31,435][02455] Decorrelating experience for 32 frames... [2024-11-13 13:31:31,937][02454] Decorrelating experience for 32 frames... [2024-11-13 13:31:31,940][02450] Decorrelating experience for 32 frames... [2024-11-13 13:31:32,291][02449] Decorrelating experience for 32 frames... [2024-11-13 13:31:32,615][00418] Fps is (10 sec: nan, 60 sec: nan, 300 sec: nan). Total num frames: 0. Throughput: 0: nan. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) [2024-11-13 13:31:32,912][02452] Decorrelating experience for 32 frames... [2024-11-13 13:31:33,299][02455] Decorrelating experience for 64 frames... [2024-11-13 13:31:33,323][02450] Decorrelating experience for 64 frames... [2024-11-13 13:31:33,321][02454] Decorrelating experience for 64 frames... [2024-11-13 13:31:33,711][02455] Decorrelating experience for 96 frames... [2024-11-13 13:31:33,874][02449] Decorrelating experience for 64 frames... [2024-11-13 13:31:34,460][02452] Decorrelating experience for 64 frames... [2024-11-13 13:31:34,550][02450] Decorrelating experience for 96 frames... [2024-11-13 13:31:34,554][02454] Decorrelating experience for 96 frames... [2024-11-13 13:31:35,000][02452] Decorrelating experience for 96 frames... [2024-11-13 13:31:35,393][02449] Decorrelating experience for 96 frames... [2024-11-13 13:31:37,615][00418] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 4.8. Samples: 24. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) [2024-11-13 13:31:37,621][00418] Avg episode reward: [(0, '1.581')] [2024-11-13 13:31:39,989][02436] Signal inference workers to stop experience collection... [2024-11-13 13:31:40,016][02456] InferenceWorker_p0-w0: stopping experience collection [2024-11-13 13:31:42,615][00418] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 230.6. Samples: 2306. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) [2024-11-13 13:31:42,617][00418] Avg episode reward: [(0, '2.831')] [2024-11-13 13:31:42,888][02436] Signal inference workers to resume experience collection... [2024-11-13 13:31:42,889][02456] InferenceWorker_p0-w0: resuming experience collection [2024-11-13 13:31:47,615][00418] Fps is (10 sec: 2457.6, 60 sec: 1638.4, 300 sec: 1638.4). Total num frames: 24576. Throughput: 0: 443.6. Samples: 6654. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2024-11-13 13:31:47,618][00418] Avg episode reward: [(0, '3.824')] [2024-11-13 13:31:51,731][02456] Updated weights for policy 0, policy_version 10 (0.0147) [2024-11-13 13:31:52,615][00418] Fps is (10 sec: 4096.0, 60 sec: 2048.0, 300 sec: 2048.0). Total num frames: 40960. Throughput: 0: 485.0. Samples: 9700. Policy #0 lag: (min: 0.0, avg: 0.2, max: 2.0) [2024-11-13 13:31:52,618][00418] Avg episode reward: [(0, '4.256')] [2024-11-13 13:31:57,615][00418] Fps is (10 sec: 3276.8, 60 sec: 2293.8, 300 sec: 2293.8). Total num frames: 57344. Throughput: 0: 553.8. Samples: 13846. Policy #0 lag: (min: 0.0, avg: 0.2, max: 2.0) [2024-11-13 13:31:57,617][00418] Avg episode reward: [(0, '4.439')] [2024-11-13 13:32:02,615][00418] Fps is (10 sec: 3276.8, 60 sec: 2457.6, 300 sec: 2457.6). Total num frames: 73728. Throughput: 0: 657.0. Samples: 19710. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2024-11-13 13:32:02,618][00418] Avg episode reward: [(0, '4.532')] [2024-11-13 13:32:03,475][02456] Updated weights for policy 0, policy_version 20 (0.0016) [2024-11-13 13:32:07,616][00418] Fps is (10 sec: 3685.9, 60 sec: 2691.6, 300 sec: 2691.6). Total num frames: 94208. Throughput: 0: 651.7. Samples: 22812. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-11-13 13:32:07,621][00418] Avg episode reward: [(0, '4.552')] [2024-11-13 13:32:12,615][00418] Fps is (10 sec: 3686.4, 60 sec: 2764.8, 300 sec: 2764.8). Total num frames: 110592. Throughput: 0: 679.0. Samples: 27158. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2024-11-13 13:32:12,620][00418] Avg episode reward: [(0, '4.492')] [2024-11-13 13:32:12,624][02436] Saving new best policy, reward=4.492! [2024-11-13 13:32:15,339][02456] Updated weights for policy 0, policy_version 30 (0.0019) [2024-11-13 13:32:17,615][00418] Fps is (10 sec: 3686.9, 60 sec: 2912.7, 300 sec: 2912.7). Total num frames: 131072. Throughput: 0: 740.8. Samples: 33334. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-11-13 13:32:17,618][00418] Avg episode reward: [(0, '4.441')] [2024-11-13 13:32:22,615][00418] Fps is (10 sec: 4096.0, 60 sec: 3031.0, 300 sec: 3031.0). Total num frames: 151552. Throughput: 0: 808.6. Samples: 36410. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2024-11-13 13:32:22,617][00418] Avg episode reward: [(0, '4.381')] [2024-11-13 13:32:27,087][02456] Updated weights for policy 0, policy_version 40 (0.0029) [2024-11-13 13:32:27,615][00418] Fps is (10 sec: 3276.8, 60 sec: 2978.9, 300 sec: 2978.9). Total num frames: 163840. Throughput: 0: 853.8. Samples: 40726. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2024-11-13 13:32:27,618][00418] Avg episode reward: [(0, '4.433')] [2024-11-13 13:32:32,617][00418] Fps is (10 sec: 3276.1, 60 sec: 3071.9, 300 sec: 3071.9). Total num frames: 184320. Throughput: 0: 891.4. Samples: 46768. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2024-11-13 13:32:32,620][00418] Avg episode reward: [(0, '4.336')] [2024-11-13 13:32:37,615][00418] Fps is (10 sec: 3686.4, 60 sec: 3345.1, 300 sec: 3087.8). Total num frames: 200704. Throughput: 0: 893.1. Samples: 49890. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2024-11-13 13:32:37,620][00418] Avg episode reward: [(0, '4.317')] [2024-11-13 13:32:37,635][02456] Updated weights for policy 0, policy_version 50 (0.0013) [2024-11-13 13:32:42,615][00418] Fps is (10 sec: 3277.5, 60 sec: 3618.1, 300 sec: 3101.3). Total num frames: 217088. Throughput: 0: 895.5. Samples: 54142. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2024-11-13 13:32:42,617][00418] Avg episode reward: [(0, '4.350')] [2024-11-13 13:32:47,615][00418] Fps is (10 sec: 3686.4, 60 sec: 3549.9, 300 sec: 3167.6). Total num frames: 237568. Throughput: 0: 903.7. Samples: 60376. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2024-11-13 13:32:47,618][00418] Avg episode reward: [(0, '4.375')] [2024-11-13 13:32:48,950][02456] Updated weights for policy 0, policy_version 60 (0.0025) [2024-11-13 13:32:52,621][00418] Fps is (10 sec: 4093.5, 60 sec: 3617.8, 300 sec: 3225.4). Total num frames: 258048. Throughput: 0: 903.9. Samples: 63492. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2024-11-13 13:32:52,627][00418] Avg episode reward: [(0, '4.354')] [2024-11-13 13:32:57,615][00418] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3180.4). Total num frames: 270336. Throughput: 0: 892.8. Samples: 67334. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2024-11-13 13:32:57,618][00418] Avg episode reward: [(0, '4.332')] [2024-11-13 13:32:57,627][02436] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000066_270336.pth... [2024-11-13 13:33:01,098][02456] Updated weights for policy 0, policy_version 70 (0.0030) [2024-11-13 13:33:02,615][00418] Fps is (10 sec: 3278.8, 60 sec: 3618.1, 300 sec: 3231.3). Total num frames: 290816. Throughput: 0: 887.3. Samples: 73264. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2024-11-13 13:33:02,617][00418] Avg episode reward: [(0, '4.545')] [2024-11-13 13:33:02,625][02436] Saving new best policy, reward=4.545! [2024-11-13 13:33:07,617][00418] Fps is (10 sec: 4095.1, 60 sec: 3618.1, 300 sec: 3276.7). Total num frames: 311296. Throughput: 0: 887.6. Samples: 76352. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2024-11-13 13:33:07,621][00418] Avg episode reward: [(0, '4.500')] [2024-11-13 13:33:12,615][00418] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3235.8). Total num frames: 323584. Throughput: 0: 889.6. Samples: 80756. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2024-11-13 13:33:12,618][00418] Avg episode reward: [(0, '4.422')] [2024-11-13 13:33:13,038][02456] Updated weights for policy 0, policy_version 80 (0.0015) [2024-11-13 13:33:17,616][00418] Fps is (10 sec: 3277.2, 60 sec: 3549.8, 300 sec: 3276.8). Total num frames: 344064. Throughput: 0: 893.3. Samples: 86964. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-11-13 13:33:17,618][00418] Avg episode reward: [(0, '4.465')] [2024-11-13 13:33:22,615][00418] Fps is (10 sec: 4096.0, 60 sec: 3549.9, 300 sec: 3314.0). Total num frames: 364544. Throughput: 0: 893.8. Samples: 90110. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-11-13 13:33:22,618][00418] Avg episode reward: [(0, '4.517')] [2024-11-13 13:33:23,644][02456] Updated weights for policy 0, policy_version 90 (0.0013) [2024-11-13 13:33:27,615][00418] Fps is (10 sec: 3277.1, 60 sec: 3549.9, 300 sec: 3276.8). Total num frames: 376832. Throughput: 0: 891.7. Samples: 94270. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2024-11-13 13:33:27,618][00418] Avg episode reward: [(0, '4.470')] [2024-11-13 13:33:32,615][00418] Fps is (10 sec: 3276.8, 60 sec: 3550.0, 300 sec: 3310.9). Total num frames: 397312. Throughput: 0: 887.9. Samples: 100330. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2024-11-13 13:33:32,619][00418] Avg episode reward: [(0, '4.319')] [2024-11-13 13:33:34,970][02456] Updated weights for policy 0, policy_version 100 (0.0013) [2024-11-13 13:33:37,615][00418] Fps is (10 sec: 4096.0, 60 sec: 3618.1, 300 sec: 3342.3). Total num frames: 417792. Throughput: 0: 885.0. Samples: 103310. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2024-11-13 13:33:37,617][00418] Avg episode reward: [(0, '4.399')] [2024-11-13 13:33:42,615][00418] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3308.3). Total num frames: 430080. Throughput: 0: 890.8. Samples: 107418. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-11-13 13:33:42,620][00418] Avg episode reward: [(0, '4.544')] [2024-11-13 13:33:46,967][02456] Updated weights for policy 0, policy_version 110 (0.0015) [2024-11-13 13:33:47,617][00418] Fps is (10 sec: 3276.1, 60 sec: 3549.7, 300 sec: 3337.4). Total num frames: 450560. Throughput: 0: 894.1. Samples: 113500. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2024-11-13 13:33:47,622][00418] Avg episode reward: [(0, '4.462')] [2024-11-13 13:33:52,617][00418] Fps is (10 sec: 4095.1, 60 sec: 3550.1, 300 sec: 3364.5). Total num frames: 471040. Throughput: 0: 893.5. Samples: 116560. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2024-11-13 13:33:52,621][00418] Avg episode reward: [(0, '4.340')] [2024-11-13 13:33:57,618][00418] Fps is (10 sec: 3276.6, 60 sec: 3549.7, 300 sec: 3333.2). Total num frames: 483328. Throughput: 0: 888.8. Samples: 120754. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2024-11-13 13:33:57,620][00418] Avg episode reward: [(0, '4.310')] [2024-11-13 13:33:59,310][02456] Updated weights for policy 0, policy_version 120 (0.0017) [2024-11-13 13:34:02,615][00418] Fps is (10 sec: 3277.5, 60 sec: 3549.9, 300 sec: 3358.7). Total num frames: 503808. Throughput: 0: 873.5. Samples: 126270. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-11-13 13:34:02,617][00418] Avg episode reward: [(0, '4.435')] [2024-11-13 13:34:07,615][00418] Fps is (10 sec: 3687.4, 60 sec: 3481.7, 300 sec: 3356.1). Total num frames: 520192. Throughput: 0: 871.1. Samples: 129308. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2024-11-13 13:34:07,621][00418] Avg episode reward: [(0, '4.603')] [2024-11-13 13:34:07,681][02436] Saving new best policy, reward=4.603! [2024-11-13 13:34:11,123][02456] Updated weights for policy 0, policy_version 130 (0.0015) [2024-11-13 13:34:12,620][00418] Fps is (10 sec: 3275.2, 60 sec: 3549.6, 300 sec: 3353.5). Total num frames: 536576. Throughput: 0: 874.8. Samples: 133642. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2024-11-13 13:34:12,627][00418] Avg episode reward: [(0, '4.649')] [2024-11-13 13:34:12,630][02436] Saving new best policy, reward=4.649! [2024-11-13 13:34:17,618][00418] Fps is (10 sec: 3275.8, 60 sec: 3481.5, 300 sec: 3351.2). Total num frames: 552960. Throughput: 0: 867.7. Samples: 139378. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2024-11-13 13:34:17,621][00418] Avg episode reward: [(0, '4.608')] [2024-11-13 13:34:21,654][02456] Updated weights for policy 0, policy_version 140 (0.0022) [2024-11-13 13:34:22,615][00418] Fps is (10 sec: 3688.1, 60 sec: 3481.6, 300 sec: 3373.2). Total num frames: 573440. Throughput: 0: 870.5. Samples: 142482. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2024-11-13 13:34:22,623][00418] Avg episode reward: [(0, '4.735')] [2024-11-13 13:34:22,625][02436] Saving new best policy, reward=4.735! [2024-11-13 13:34:27,615][00418] Fps is (10 sec: 3687.6, 60 sec: 3549.9, 300 sec: 3370.4). Total num frames: 589824. Throughput: 0: 880.4. Samples: 147038. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2024-11-13 13:34:27,618][00418] Avg episode reward: [(0, '4.637')] [2024-11-13 13:34:32,615][00418] Fps is (10 sec: 3276.8, 60 sec: 3481.6, 300 sec: 3367.8). Total num frames: 606208. Throughput: 0: 869.0. Samples: 152604. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2024-11-13 13:34:32,617][00418] Avg episode reward: [(0, '4.512')] [2024-11-13 13:34:33,739][02456] Updated weights for policy 0, policy_version 150 (0.0017) [2024-11-13 13:34:37,618][00418] Fps is (10 sec: 3685.5, 60 sec: 3481.5, 300 sec: 3387.5). Total num frames: 626688. Throughput: 0: 869.0. Samples: 155666. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2024-11-13 13:34:37,619][00418] Avg episode reward: [(0, '4.300')] [2024-11-13 13:34:42,615][00418] Fps is (10 sec: 3686.4, 60 sec: 3549.9, 300 sec: 3384.6). Total num frames: 643072. Throughput: 0: 882.1. Samples: 160446. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-11-13 13:34:42,617][00418] Avg episode reward: [(0, '4.478')] [2024-11-13 13:34:45,695][02456] Updated weights for policy 0, policy_version 160 (0.0015) [2024-11-13 13:34:47,615][00418] Fps is (10 sec: 3277.6, 60 sec: 3481.7, 300 sec: 3381.8). Total num frames: 659456. Throughput: 0: 882.4. Samples: 165976. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2024-11-13 13:34:47,620][00418] Avg episode reward: [(0, '4.452')] [2024-11-13 13:34:52,615][00418] Fps is (10 sec: 3686.4, 60 sec: 3481.7, 300 sec: 3399.7). Total num frames: 679936. Throughput: 0: 881.6. Samples: 168980. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2024-11-13 13:34:52,617][00418] Avg episode reward: [(0, '4.430')] [2024-11-13 13:34:57,340][02456] Updated weights for policy 0, policy_version 170 (0.0019) [2024-11-13 13:34:57,615][00418] Fps is (10 sec: 3686.4, 60 sec: 3550.0, 300 sec: 3396.7). Total num frames: 696320. Throughput: 0: 893.4. Samples: 173840. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2024-11-13 13:34:57,620][00418] Avg episode reward: [(0, '4.573')] [2024-11-13 13:34:57,630][02436] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000170_696320.pth... [2024-11-13 13:35:02,615][00418] Fps is (10 sec: 3276.8, 60 sec: 3481.6, 300 sec: 3393.8). Total num frames: 712704. Throughput: 0: 883.9. Samples: 179152. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2024-11-13 13:35:02,623][00418] Avg episode reward: [(0, '4.369')] [2024-11-13 13:35:07,615][00418] Fps is (10 sec: 3686.4, 60 sec: 3549.9, 300 sec: 3410.2). Total num frames: 733184. Throughput: 0: 883.8. Samples: 182254. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2024-11-13 13:35:07,617][00418] Avg episode reward: [(0, '4.369')] [2024-11-13 13:35:07,831][02456] Updated weights for policy 0, policy_version 180 (0.0017) [2024-11-13 13:35:12,615][00418] Fps is (10 sec: 3686.4, 60 sec: 3550.1, 300 sec: 3407.1). Total num frames: 749568. Throughput: 0: 889.7. Samples: 187076. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2024-11-13 13:35:12,619][00418] Avg episode reward: [(0, '4.445')] [2024-11-13 13:35:17,615][00418] Fps is (10 sec: 3276.8, 60 sec: 3550.1, 300 sec: 3404.2). Total num frames: 765952. Throughput: 0: 885.7. Samples: 192460. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2024-11-13 13:35:17,617][00418] Avg episode reward: [(0, '4.581')] [2024-11-13 13:35:19,895][02456] Updated weights for policy 0, policy_version 190 (0.0020) [2024-11-13 13:35:22,617][00418] Fps is (10 sec: 3685.7, 60 sec: 3549.7, 300 sec: 3419.2). Total num frames: 786432. Throughput: 0: 885.0. Samples: 195492. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2024-11-13 13:35:22,624][00418] Avg episode reward: [(0, '4.743')] [2024-11-13 13:35:22,628][02436] Saving new best policy, reward=4.743! [2024-11-13 13:35:27,615][00418] Fps is (10 sec: 3686.4, 60 sec: 3549.9, 300 sec: 3416.2). Total num frames: 802816. Throughput: 0: 890.6. Samples: 200522. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2024-11-13 13:35:27,617][00418] Avg episode reward: [(0, '4.718')] [2024-11-13 13:35:31,993][02456] Updated weights for policy 0, policy_version 200 (0.0023) [2024-11-13 13:35:32,615][00418] Fps is (10 sec: 3277.5, 60 sec: 3549.9, 300 sec: 3413.3). Total num frames: 819200. Throughput: 0: 882.3. Samples: 205678. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2024-11-13 13:35:32,621][00418] Avg episode reward: [(0, '4.541')] [2024-11-13 13:35:37,615][00418] Fps is (10 sec: 3686.4, 60 sec: 3550.0, 300 sec: 3427.3). Total num frames: 839680. Throughput: 0: 882.2. Samples: 208678. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2024-11-13 13:35:37,618][00418] Avg episode reward: [(0, '4.504')] [2024-11-13 13:35:42,622][00418] Fps is (10 sec: 3683.8, 60 sec: 3549.4, 300 sec: 3424.2). Total num frames: 856064. Throughput: 0: 889.3. Samples: 213866. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2024-11-13 13:35:42,624][00418] Avg episode reward: [(0, '4.533')] [2024-11-13 13:35:43,676][02456] Updated weights for policy 0, policy_version 210 (0.0015) [2024-11-13 13:35:47,616][00418] Fps is (10 sec: 3276.3, 60 sec: 3549.8, 300 sec: 3421.3). Total num frames: 872448. Throughput: 0: 886.4. Samples: 219040. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-11-13 13:35:47,619][00418] Avg episode reward: [(0, '4.450')] [2024-11-13 13:35:52,615][00418] Fps is (10 sec: 3689.0, 60 sec: 3549.9, 300 sec: 3434.3). Total num frames: 892928. Throughput: 0: 886.5. Samples: 222148. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2024-11-13 13:35:52,619][00418] Avg episode reward: [(0, '4.471')] [2024-11-13 13:35:53,915][02456] Updated weights for policy 0, policy_version 220 (0.0014) [2024-11-13 13:35:57,618][00418] Fps is (10 sec: 3685.7, 60 sec: 3549.7, 300 sec: 3431.3). Total num frames: 909312. Throughput: 0: 897.7. Samples: 227476. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-11-13 13:35:57,626][00418] Avg episode reward: [(0, '4.513')] [2024-11-13 13:36:02,615][00418] Fps is (10 sec: 3276.7, 60 sec: 3549.8, 300 sec: 3428.5). Total num frames: 925696. Throughput: 0: 890.2. Samples: 232520. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-11-13 13:36:02,622][00418] Avg episode reward: [(0, '4.392')] [2024-11-13 13:36:05,714][02456] Updated weights for policy 0, policy_version 230 (0.0017) [2024-11-13 13:36:07,617][00418] Fps is (10 sec: 3686.8, 60 sec: 3549.7, 300 sec: 3440.6). Total num frames: 946176. Throughput: 0: 892.8. Samples: 235666. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2024-11-13 13:36:07,619][00418] Avg episode reward: [(0, '4.473')] [2024-11-13 13:36:12,623][00418] Fps is (10 sec: 4092.8, 60 sec: 3617.7, 300 sec: 3452.2). Total num frames: 966656. Throughput: 0: 902.0. Samples: 241118. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2024-11-13 13:36:12,626][00418] Avg episode reward: [(0, '4.654')] [2024-11-13 13:36:17,542][02456] Updated weights for policy 0, policy_version 240 (0.0015) [2024-11-13 13:36:17,615][00418] Fps is (10 sec: 3687.2, 60 sec: 3618.1, 300 sec: 3449.3). Total num frames: 983040. Throughput: 0: 897.7. Samples: 246076. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2024-11-13 13:36:17,617][00418] Avg episode reward: [(0, '4.832')] [2024-11-13 13:36:17,629][02436] Saving new best policy, reward=4.832! [2024-11-13 13:36:22,615][00418] Fps is (10 sec: 3689.4, 60 sec: 3618.3, 300 sec: 3460.4). Total num frames: 1003520. Throughput: 0: 897.7. Samples: 249074. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2024-11-13 13:36:22,622][00418] Avg episode reward: [(0, '4.566')] [2024-11-13 13:36:27,616][00418] Fps is (10 sec: 3685.9, 60 sec: 3618.0, 300 sec: 3457.3). Total num frames: 1019904. Throughput: 0: 908.8. Samples: 254758. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2024-11-13 13:36:27,620][00418] Avg episode reward: [(0, '4.543')] [2024-11-13 13:36:28,929][02456] Updated weights for policy 0, policy_version 250 (0.0013) [2024-11-13 13:36:32,615][00418] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3512.8). Total num frames: 1036288. Throughput: 0: 897.5. Samples: 259426. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2024-11-13 13:36:32,617][00418] Avg episode reward: [(0, '4.379')] [2024-11-13 13:36:37,615][00418] Fps is (10 sec: 3686.9, 60 sec: 3618.1, 300 sec: 3582.3). Total num frames: 1056768. Throughput: 0: 897.3. Samples: 262528. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2024-11-13 13:36:37,619][00418] Avg episode reward: [(0, '4.467')] [2024-11-13 13:36:39,443][02456] Updated weights for policy 0, policy_version 260 (0.0012) [2024-11-13 13:36:42,615][00418] Fps is (10 sec: 3686.3, 60 sec: 3618.5, 300 sec: 3554.5). Total num frames: 1073152. Throughput: 0: 904.8. Samples: 268190. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2024-11-13 13:36:42,617][00418] Avg episode reward: [(0, '4.408')] [2024-11-13 13:36:47,615][00418] Fps is (10 sec: 3276.8, 60 sec: 3618.2, 300 sec: 3554.5). Total num frames: 1089536. Throughput: 0: 896.5. Samples: 272860. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-11-13 13:36:47,617][00418] Avg episode reward: [(0, '4.336')] [2024-11-13 13:36:51,235][02456] Updated weights for policy 0, policy_version 270 (0.0014) [2024-11-13 13:36:52,615][00418] Fps is (10 sec: 3686.5, 60 sec: 3618.1, 300 sec: 3568.4). Total num frames: 1110016. Throughput: 0: 895.5. Samples: 275960. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2024-11-13 13:36:52,618][00418] Avg episode reward: [(0, '4.421')] [2024-11-13 13:36:57,617][00418] Fps is (10 sec: 3685.6, 60 sec: 3618.2, 300 sec: 3568.4). Total num frames: 1126400. Throughput: 0: 904.9. Samples: 281832. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2024-11-13 13:36:57,624][00418] Avg episode reward: [(0, '4.476')] [2024-11-13 13:36:57,636][02436] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000275_1126400.pth... [2024-11-13 13:36:57,742][02436] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000066_270336.pth [2024-11-13 13:37:02,615][00418] Fps is (10 sec: 3276.8, 60 sec: 3618.2, 300 sec: 3554.5). Total num frames: 1142784. Throughput: 0: 892.8. Samples: 286250. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2024-11-13 13:37:02,621][00418] Avg episode reward: [(0, '4.429')] [2024-11-13 13:37:03,303][02456] Updated weights for policy 0, policy_version 280 (0.0013) [2024-11-13 13:37:07,617][00418] Fps is (10 sec: 3686.4, 60 sec: 3618.1, 300 sec: 3568.4). Total num frames: 1163264. Throughput: 0: 892.4. Samples: 289236. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2024-11-13 13:37:07,622][00418] Avg episode reward: [(0, '4.496')] [2024-11-13 13:37:12,615][00418] Fps is (10 sec: 3686.4, 60 sec: 3550.3, 300 sec: 3554.5). Total num frames: 1179648. Throughput: 0: 896.6. Samples: 295106. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2024-11-13 13:37:12,617][00418] Avg episode reward: [(0, '4.543')] [2024-11-13 13:37:15,051][02456] Updated weights for policy 0, policy_version 290 (0.0013) [2024-11-13 13:37:17,615][00418] Fps is (10 sec: 3277.5, 60 sec: 3549.9, 300 sec: 3540.6). Total num frames: 1196032. Throughput: 0: 888.0. Samples: 299386. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2024-11-13 13:37:17,622][00418] Avg episode reward: [(0, '4.694')] [2024-11-13 13:37:22,615][00418] Fps is (10 sec: 3686.4, 60 sec: 3549.9, 300 sec: 3568.4). Total num frames: 1216512. Throughput: 0: 886.1. Samples: 302404. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2024-11-13 13:37:22,618][00418] Avg episode reward: [(0, '4.681')] [2024-11-13 13:37:25,515][02456] Updated weights for policy 0, policy_version 300 (0.0013) [2024-11-13 13:37:27,615][00418] Fps is (10 sec: 3686.4, 60 sec: 3549.9, 300 sec: 3554.5). Total num frames: 1232896. Throughput: 0: 893.6. Samples: 308404. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2024-11-13 13:37:27,619][00418] Avg episode reward: [(0, '4.582')] [2024-11-13 13:37:32,615][00418] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3554.5). Total num frames: 1249280. Throughput: 0: 884.8. Samples: 312678. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2024-11-13 13:37:32,622][00418] Avg episode reward: [(0, '4.626')] [2024-11-13 13:37:37,331][02456] Updated weights for policy 0, policy_version 310 (0.0017) [2024-11-13 13:37:37,615][00418] Fps is (10 sec: 3686.3, 60 sec: 3549.9, 300 sec: 3568.4). Total num frames: 1269760. Throughput: 0: 884.7. Samples: 315772. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-11-13 13:37:37,617][00418] Avg episode reward: [(0, '4.737')] [2024-11-13 13:37:42,615][00418] Fps is (10 sec: 3686.4, 60 sec: 3549.9, 300 sec: 3554.5). Total num frames: 1286144. Throughput: 0: 889.9. Samples: 321876. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2024-11-13 13:37:42,620][00418] Avg episode reward: [(0, '4.670')] [2024-11-13 13:37:47,615][00418] Fps is (10 sec: 3276.9, 60 sec: 3549.9, 300 sec: 3540.7). Total num frames: 1302528. Throughput: 0: 885.7. Samples: 326106. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2024-11-13 13:37:47,619][00418] Avg episode reward: [(0, '4.759')] [2024-11-13 13:37:49,301][02456] Updated weights for policy 0, policy_version 320 (0.0022) [2024-11-13 13:37:52,615][00418] Fps is (10 sec: 3686.4, 60 sec: 3549.9, 300 sec: 3568.4). Total num frames: 1323008. Throughput: 0: 887.3. Samples: 329162. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2024-11-13 13:37:52,622][00418] Avg episode reward: [(0, '4.710')] [2024-11-13 13:37:57,615][00418] Fps is (10 sec: 3686.4, 60 sec: 3550.0, 300 sec: 3554.5). Total num frames: 1339392. Throughput: 0: 892.6. Samples: 335272. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-11-13 13:37:57,623][00418] Avg episode reward: [(0, '4.751')] [2024-11-13 13:38:01,111][02456] Updated weights for policy 0, policy_version 330 (0.0019) [2024-11-13 13:38:02,615][00418] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3540.6). Total num frames: 1355776. Throughput: 0: 890.4. Samples: 339456. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2024-11-13 13:38:02,617][00418] Avg episode reward: [(0, '4.678')] [2024-11-13 13:38:07,615][00418] Fps is (10 sec: 3686.5, 60 sec: 3550.0, 300 sec: 3568.4). Total num frames: 1376256. Throughput: 0: 893.2. Samples: 342596. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2024-11-13 13:38:07,617][00418] Avg episode reward: [(0, '4.512')] [2024-11-13 13:38:11,052][02456] Updated weights for policy 0, policy_version 340 (0.0014) [2024-11-13 13:38:12,621][00418] Fps is (10 sec: 4093.5, 60 sec: 3617.8, 300 sec: 3568.3). Total num frames: 1396736. Throughput: 0: 899.7. Samples: 348898. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2024-11-13 13:38:12,627][00418] Avg episode reward: [(0, '4.711')] [2024-11-13 13:38:17,615][00418] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3540.6). Total num frames: 1409024. Throughput: 0: 900.4. Samples: 353198. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-11-13 13:38:17,622][00418] Avg episode reward: [(0, '4.799')] [2024-11-13 13:38:22,615][00418] Fps is (10 sec: 3278.8, 60 sec: 3549.9, 300 sec: 3568.4). Total num frames: 1429504. Throughput: 0: 901.0. Samples: 356316. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2024-11-13 13:38:22,620][00418] Avg episode reward: [(0, '4.971')] [2024-11-13 13:38:22,623][02436] Saving new best policy, reward=4.971! [2024-11-13 13:38:22,856][02456] Updated weights for policy 0, policy_version 350 (0.0016) [2024-11-13 13:38:27,615][00418] Fps is (10 sec: 4096.0, 60 sec: 3618.1, 300 sec: 3568.4). Total num frames: 1449984. Throughput: 0: 899.2. Samples: 362338. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2024-11-13 13:38:27,621][00418] Avg episode reward: [(0, '4.792')] [2024-11-13 13:38:32,615][00418] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3540.6). Total num frames: 1462272. Throughput: 0: 898.9. Samples: 366558. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2024-11-13 13:38:32,621][00418] Avg episode reward: [(0, '4.785')] [2024-11-13 13:38:34,801][02456] Updated weights for policy 0, policy_version 360 (0.0014) [2024-11-13 13:38:37,615][00418] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3568.4). Total num frames: 1482752. Throughput: 0: 899.3. Samples: 369632. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2024-11-13 13:38:37,617][00418] Avg episode reward: [(0, '5.086')] [2024-11-13 13:38:37,684][02436] Saving new best policy, reward=5.086! [2024-11-13 13:38:42,616][00418] Fps is (10 sec: 4095.5, 60 sec: 3618.1, 300 sec: 3568.4). Total num frames: 1503232. Throughput: 0: 901.4. Samples: 375834. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2024-11-13 13:38:42,619][00418] Avg episode reward: [(0, '5.258')] [2024-11-13 13:38:42,627][02436] Saving new best policy, reward=5.258! [2024-11-13 13:38:46,218][02456] Updated weights for policy 0, policy_version 370 (0.0021) [2024-11-13 13:38:47,615][00418] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3540.6). Total num frames: 1515520. Throughput: 0: 902.2. Samples: 380056. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-11-13 13:38:47,617][00418] Avg episode reward: [(0, '5.359')] [2024-11-13 13:38:47,630][02436] Saving new best policy, reward=5.359! [2024-11-13 13:38:52,619][00418] Fps is (10 sec: 3275.8, 60 sec: 3549.6, 300 sec: 3568.4). Total num frames: 1536000. Throughput: 0: 901.6. Samples: 383172. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2024-11-13 13:38:52,625][00418] Avg episode reward: [(0, '5.238')] [2024-11-13 13:38:56,528][02456] Updated weights for policy 0, policy_version 380 (0.0019) [2024-11-13 13:38:57,615][00418] Fps is (10 sec: 4096.0, 60 sec: 3618.1, 300 sec: 3568.4). Total num frames: 1556480. Throughput: 0: 898.3. Samples: 389318. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2024-11-13 13:38:57,617][00418] Avg episode reward: [(0, '5.494')] [2024-11-13 13:38:57,630][02436] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000380_1556480.pth... [2024-11-13 13:38:57,746][02436] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000170_696320.pth [2024-11-13 13:38:57,759][02436] Saving new best policy, reward=5.494! [2024-11-13 13:39:02,615][00418] Fps is (10 sec: 3687.9, 60 sec: 3618.1, 300 sec: 3568.4). Total num frames: 1572864. Throughput: 0: 896.0. Samples: 393516. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-11-13 13:39:02,619][00418] Avg episode reward: [(0, '5.498')] [2024-11-13 13:39:02,624][02436] Saving new best policy, reward=5.498! [2024-11-13 13:39:07,615][00418] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3568.4). Total num frames: 1589248. Throughput: 0: 892.0. Samples: 396454. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2024-11-13 13:39:07,621][00418] Avg episode reward: [(0, '5.451')] [2024-11-13 13:39:08,467][02456] Updated weights for policy 0, policy_version 390 (0.0017) [2024-11-13 13:39:12,617][00418] Fps is (10 sec: 4095.2, 60 sec: 3618.4, 300 sec: 3596.2). Total num frames: 1613824. Throughput: 0: 897.2. Samples: 402714. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2024-11-13 13:39:12,619][00418] Avg episode reward: [(0, '5.498')] [2024-11-13 13:39:17,615][00418] Fps is (10 sec: 3686.4, 60 sec: 3618.1, 300 sec: 3568.4). Total num frames: 1626112. Throughput: 0: 905.4. Samples: 407302. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2024-11-13 13:39:17,619][00418] Avg episode reward: [(0, '5.474')] [2024-11-13 13:39:20,278][02456] Updated weights for policy 0, policy_version 400 (0.0021) [2024-11-13 13:39:22,615][00418] Fps is (10 sec: 3277.5, 60 sec: 3618.1, 300 sec: 3582.3). Total num frames: 1646592. Throughput: 0: 899.2. Samples: 410094. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2024-11-13 13:39:22,621][00418] Avg episode reward: [(0, '5.657')] [2024-11-13 13:39:22,623][02436] Saving new best policy, reward=5.657! [2024-11-13 13:39:27,615][00418] Fps is (10 sec: 4096.0, 60 sec: 3618.1, 300 sec: 3596.1). Total num frames: 1667072. Throughput: 0: 899.4. Samples: 416308. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2024-11-13 13:39:27,617][00418] Avg episode reward: [(0, '5.895')] [2024-11-13 13:39:27,635][02436] Saving new best policy, reward=5.895! [2024-11-13 13:39:31,312][02456] Updated weights for policy 0, policy_version 410 (0.0016) [2024-11-13 13:39:32,615][00418] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3568.4). Total num frames: 1679360. Throughput: 0: 906.3. Samples: 420838. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-11-13 13:39:32,622][00418] Avg episode reward: [(0, '5.908')] [2024-11-13 13:39:32,624][02436] Saving new best policy, reward=5.908! [2024-11-13 13:39:37,615][00418] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3582.3). Total num frames: 1699840. Throughput: 0: 896.2. Samples: 423496. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2024-11-13 13:39:37,618][00418] Avg episode reward: [(0, '6.026')] [2024-11-13 13:39:37,629][02436] Saving new best policy, reward=6.026! [2024-11-13 13:39:42,143][02456] Updated weights for policy 0, policy_version 420 (0.0017) [2024-11-13 13:39:42,615][00418] Fps is (10 sec: 4096.0, 60 sec: 3618.2, 300 sec: 3596.1). Total num frames: 1720320. Throughput: 0: 896.3. Samples: 429652. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2024-11-13 13:39:42,617][00418] Avg episode reward: [(0, '5.793')] [2024-11-13 13:39:47,615][00418] Fps is (10 sec: 3686.4, 60 sec: 3686.4, 300 sec: 3582.3). Total num frames: 1736704. Throughput: 0: 910.0. Samples: 434466. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-11-13 13:39:47,618][00418] Avg episode reward: [(0, '5.963')] [2024-11-13 13:39:52,615][00418] Fps is (10 sec: 3276.8, 60 sec: 3618.4, 300 sec: 3582.3). Total num frames: 1753088. Throughput: 0: 902.6. Samples: 437070. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2024-11-13 13:39:52,617][00418] Avg episode reward: [(0, '6.377')] [2024-11-13 13:39:52,619][02436] Saving new best policy, reward=6.377! [2024-11-13 13:39:54,023][02456] Updated weights for policy 0, policy_version 430 (0.0020) [2024-11-13 13:39:57,615][00418] Fps is (10 sec: 3686.4, 60 sec: 3618.1, 300 sec: 3596.2). Total num frames: 1773568. Throughput: 0: 898.7. Samples: 443152. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2024-11-13 13:39:57,617][00418] Avg episode reward: [(0, '6.812')] [2024-11-13 13:39:57,628][02436] Saving new best policy, reward=6.812! [2024-11-13 13:40:02,619][00418] Fps is (10 sec: 3685.1, 60 sec: 3617.9, 300 sec: 3582.2). Total num frames: 1789952. Throughput: 0: 900.1. Samples: 447808. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2024-11-13 13:40:02,624][00418] Avg episode reward: [(0, '7.080')] [2024-11-13 13:40:02,627][02436] Saving new best policy, reward=7.080! [2024-11-13 13:40:06,038][02456] Updated weights for policy 0, policy_version 440 (0.0014) [2024-11-13 13:40:07,615][00418] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3582.3). Total num frames: 1806336. Throughput: 0: 892.8. Samples: 450268. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2024-11-13 13:40:07,620][00418] Avg episode reward: [(0, '6.545')] [2024-11-13 13:40:12,615][00418] Fps is (10 sec: 3687.7, 60 sec: 3550.0, 300 sec: 3596.1). Total num frames: 1826816. Throughput: 0: 892.0. Samples: 456450. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2024-11-13 13:40:12,621][00418] Avg episode reward: [(0, '6.134')] [2024-11-13 13:40:17,176][02456] Updated weights for policy 0, policy_version 450 (0.0014) [2024-11-13 13:40:17,615][00418] Fps is (10 sec: 3686.4, 60 sec: 3618.1, 300 sec: 3582.3). Total num frames: 1843200. Throughput: 0: 900.2. Samples: 461348. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2024-11-13 13:40:17,621][00418] Avg episode reward: [(0, '6.114')] [2024-11-13 13:40:22,615][00418] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3582.3). Total num frames: 1859584. Throughput: 0: 896.9. Samples: 463858. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2024-11-13 13:40:22,621][00418] Avg episode reward: [(0, '6.545')] [2024-11-13 13:40:27,615][00418] Fps is (10 sec: 3686.4, 60 sec: 3549.9, 300 sec: 3596.1). Total num frames: 1880064. Throughput: 0: 898.0. Samples: 470064. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2024-11-13 13:40:27,621][00418] Avg episode reward: [(0, '6.780')] [2024-11-13 13:40:27,684][02456] Updated weights for policy 0, policy_version 460 (0.0014) [2024-11-13 13:40:32,615][00418] Fps is (10 sec: 3686.4, 60 sec: 3618.1, 300 sec: 3582.3). Total num frames: 1896448. Throughput: 0: 901.5. Samples: 475034. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-11-13 13:40:32,623][00418] Avg episode reward: [(0, '7.012')] [2024-11-13 13:40:37,615][00418] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3582.4). Total num frames: 1912832. Throughput: 0: 895.9. Samples: 477384. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2024-11-13 13:40:37,618][00418] Avg episode reward: [(0, '7.169')] [2024-11-13 13:40:37,695][02436] Saving new best policy, reward=7.169! [2024-11-13 13:40:39,722][02456] Updated weights for policy 0, policy_version 470 (0.0014) [2024-11-13 13:40:42,615][00418] Fps is (10 sec: 4096.0, 60 sec: 3618.1, 300 sec: 3610.0). Total num frames: 1937408. Throughput: 0: 894.4. Samples: 483400. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-11-13 13:40:42,624][00418] Avg episode reward: [(0, '7.637')] [2024-11-13 13:40:42,627][02436] Saving new best policy, reward=7.637! [2024-11-13 13:40:47,615][00418] Fps is (10 sec: 3686.3, 60 sec: 3549.9, 300 sec: 3582.3). Total num frames: 1949696. Throughput: 0: 903.7. Samples: 488472. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2024-11-13 13:40:47,618][00418] Avg episode reward: [(0, '7.298')] [2024-11-13 13:40:51,525][02456] Updated weights for policy 0, policy_version 480 (0.0019) [2024-11-13 13:40:52,615][00418] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3596.2). Total num frames: 1970176. Throughput: 0: 898.2. Samples: 490686. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-11-13 13:40:52,622][00418] Avg episode reward: [(0, '7.485')] [2024-11-13 13:40:57,615][00418] Fps is (10 sec: 4096.1, 60 sec: 3618.1, 300 sec: 3610.0). Total num frames: 1990656. Throughput: 0: 900.0. Samples: 496948. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2024-11-13 13:40:57,617][00418] Avg episode reward: [(0, '8.280')] [2024-11-13 13:40:57,628][02436] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000486_1990656.pth... [2024-11-13 13:40:57,731][02436] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000275_1126400.pth [2024-11-13 13:40:57,744][02436] Saving new best policy, reward=8.280! [2024-11-13 13:41:02,615][00418] Fps is (10 sec: 3276.8, 60 sec: 3550.1, 300 sec: 3582.3). Total num frames: 2002944. Throughput: 0: 900.2. Samples: 501858. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2024-11-13 13:41:02,622][00418] Avg episode reward: [(0, '8.374')] [2024-11-13 13:41:02,625][02436] Saving new best policy, reward=8.374! [2024-11-13 13:41:02,935][02456] Updated weights for policy 0, policy_version 490 (0.0017) [2024-11-13 13:41:07,615][00418] Fps is (10 sec: 2867.2, 60 sec: 3549.9, 300 sec: 3568.5). Total num frames: 2019328. Throughput: 0: 890.3. Samples: 503922. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2024-11-13 13:41:07,618][00418] Avg episode reward: [(0, '9.082')] [2024-11-13 13:41:07,682][02436] Saving new best policy, reward=9.082! [2024-11-13 13:41:12,615][00418] Fps is (10 sec: 3686.4, 60 sec: 3549.9, 300 sec: 3582.3). Total num frames: 2039808. Throughput: 0: 888.3. Samples: 510036. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2024-11-13 13:41:12,618][00418] Avg episode reward: [(0, '8.828')] [2024-11-13 13:41:13,634][02456] Updated weights for policy 0, policy_version 500 (0.0013) [2024-11-13 13:41:17,615][00418] Fps is (10 sec: 3686.4, 60 sec: 3549.9, 300 sec: 3568.4). Total num frames: 2056192. Throughput: 0: 895.8. Samples: 515344. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-11-13 13:41:17,621][00418] Avg episode reward: [(0, '9.503')] [2024-11-13 13:41:17,638][02436] Saving new best policy, reward=9.503! [2024-11-13 13:41:22,615][00418] Fps is (10 sec: 3686.4, 60 sec: 3618.1, 300 sec: 3582.3). Total num frames: 2076672. Throughput: 0: 888.3. Samples: 517356. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2024-11-13 13:41:22,621][00418] Avg episode reward: [(0, '10.326')] [2024-11-13 13:41:22,628][02436] Saving new best policy, reward=10.326! [2024-11-13 13:41:25,519][02456] Updated weights for policy 0, policy_version 510 (0.0018) [2024-11-13 13:41:27,615][00418] Fps is (10 sec: 4096.0, 60 sec: 3618.1, 300 sec: 3596.1). Total num frames: 2097152. Throughput: 0: 891.0. Samples: 523496. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-11-13 13:41:27,617][00418] Avg episode reward: [(0, '10.742')] [2024-11-13 13:41:27,635][02436] Saving new best policy, reward=10.742! [2024-11-13 13:41:32,617][00418] Fps is (10 sec: 3685.6, 60 sec: 3618.0, 300 sec: 3582.2). Total num frames: 2113536. Throughput: 0: 897.3. Samples: 528854. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2024-11-13 13:41:32,620][00418] Avg episode reward: [(0, '11.098')] [2024-11-13 13:41:32,624][02436] Saving new best policy, reward=11.098! [2024-11-13 13:41:37,503][02456] Updated weights for policy 0, policy_version 520 (0.0021) [2024-11-13 13:41:37,615][00418] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3582.3). Total num frames: 2129920. Throughput: 0: 891.4. Samples: 530798. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2024-11-13 13:41:37,618][00418] Avg episode reward: [(0, '10.934')] [2024-11-13 13:41:42,615][00418] Fps is (10 sec: 3687.2, 60 sec: 3549.9, 300 sec: 3596.1). Total num frames: 2150400. Throughput: 0: 886.8. Samples: 536856. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2024-11-13 13:41:42,624][00418] Avg episode reward: [(0, '11.453')] [2024-11-13 13:41:42,628][02436] Saving new best policy, reward=11.453! [2024-11-13 13:41:47,615][00418] Fps is (10 sec: 3686.4, 60 sec: 3618.2, 300 sec: 3582.3). Total num frames: 2166784. Throughput: 0: 903.2. Samples: 542504. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2024-11-13 13:41:47,625][00418] Avg episode reward: [(0, '11.976')] [2024-11-13 13:41:47,640][02436] Saving new best policy, reward=11.976! [2024-11-13 13:41:48,371][02456] Updated weights for policy 0, policy_version 530 (0.0015) [2024-11-13 13:41:52,615][00418] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3582.3). Total num frames: 2183168. Throughput: 0: 900.4. Samples: 544442. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2024-11-13 13:41:52,620][00418] Avg episode reward: [(0, '12.270')] [2024-11-13 13:41:52,623][02436] Saving new best policy, reward=12.270! [2024-11-13 13:41:57,615][00418] Fps is (10 sec: 3686.3, 60 sec: 3549.9, 300 sec: 3596.1). Total num frames: 2203648. Throughput: 0: 894.4. Samples: 550284. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2024-11-13 13:41:57,618][00418] Avg episode reward: [(0, '13.246')] [2024-11-13 13:41:57,627][02436] Saving new best policy, reward=13.246! [2024-11-13 13:41:59,582][02456] Updated weights for policy 0, policy_version 540 (0.0013) [2024-11-13 13:42:02,615][00418] Fps is (10 sec: 3686.4, 60 sec: 3618.1, 300 sec: 3582.3). Total num frames: 2220032. Throughput: 0: 903.6. Samples: 556004. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2024-11-13 13:42:02,619][00418] Avg episode reward: [(0, '13.816')] [2024-11-13 13:42:02,621][02436] Saving new best policy, reward=13.816! [2024-11-13 13:42:07,615][00418] Fps is (10 sec: 3276.9, 60 sec: 3618.1, 300 sec: 3582.3). Total num frames: 2236416. Throughput: 0: 901.7. Samples: 557934. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2024-11-13 13:42:07,617][00418] Avg episode reward: [(0, '14.216')] [2024-11-13 13:42:07,631][02436] Saving new best policy, reward=14.216! [2024-11-13 13:42:11,634][02456] Updated weights for policy 0, policy_version 550 (0.0017) [2024-11-13 13:42:12,615][00418] Fps is (10 sec: 3686.4, 60 sec: 3618.1, 300 sec: 3596.1). Total num frames: 2256896. Throughput: 0: 889.0. Samples: 563500. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2024-11-13 13:42:12,619][00418] Avg episode reward: [(0, '13.964')] [2024-11-13 13:42:17,615][00418] Fps is (10 sec: 3686.4, 60 sec: 3618.1, 300 sec: 3582.3). Total num frames: 2273280. Throughput: 0: 903.7. Samples: 569520. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2024-11-13 13:42:17,621][00418] Avg episode reward: [(0, '13.520')] [2024-11-13 13:42:22,615][00418] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3582.3). Total num frames: 2289664. Throughput: 0: 904.6. Samples: 571504. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2024-11-13 13:42:22,623][00418] Avg episode reward: [(0, '13.412')] [2024-11-13 13:42:23,302][02456] Updated weights for policy 0, policy_version 560 (0.0018) [2024-11-13 13:42:27,615][00418] Fps is (10 sec: 3686.4, 60 sec: 3549.9, 300 sec: 3596.1). Total num frames: 2310144. Throughput: 0: 892.8. Samples: 577032. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2024-11-13 13:42:27,618][00418] Avg episode reward: [(0, '13.198')] [2024-11-13 13:42:32,615][00418] Fps is (10 sec: 4096.0, 60 sec: 3618.3, 300 sec: 3596.2). Total num frames: 2330624. Throughput: 0: 903.9. Samples: 583178. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-11-13 13:42:32,617][00418] Avg episode reward: [(0, '13.640')] [2024-11-13 13:42:33,836][02456] Updated weights for policy 0, policy_version 570 (0.0019) [2024-11-13 13:42:37,615][00418] Fps is (10 sec: 3276.7, 60 sec: 3549.9, 300 sec: 3582.3). Total num frames: 2342912. Throughput: 0: 902.3. Samples: 585044. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-11-13 13:42:37,619][00418] Avg episode reward: [(0, '14.919')] [2024-11-13 13:42:37,629][02436] Saving new best policy, reward=14.919! [2024-11-13 13:42:42,615][00418] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3596.2). Total num frames: 2363392. Throughput: 0: 892.0. Samples: 590424. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2024-11-13 13:42:42,617][00418] Avg episode reward: [(0, '15.089')] [2024-11-13 13:42:42,619][02436] Saving new best policy, reward=15.089! [2024-11-13 13:42:45,271][02456] Updated weights for policy 0, policy_version 580 (0.0013) [2024-11-13 13:42:47,615][00418] Fps is (10 sec: 4096.0, 60 sec: 3618.1, 300 sec: 3596.1). Total num frames: 2383872. Throughput: 0: 900.8. Samples: 596540. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2024-11-13 13:42:47,617][00418] Avg episode reward: [(0, '13.193')] [2024-11-13 13:42:52,615][00418] Fps is (10 sec: 3276.7, 60 sec: 3549.8, 300 sec: 3582.3). Total num frames: 2396160. Throughput: 0: 904.2. Samples: 598622. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2024-11-13 13:42:52,620][00418] Avg episode reward: [(0, '12.754')] [2024-11-13 13:42:57,052][02456] Updated weights for policy 0, policy_version 590 (0.0016) [2024-11-13 13:42:57,615][00418] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3596.1). Total num frames: 2416640. Throughput: 0: 898.7. Samples: 603940. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2024-11-13 13:42:57,618][00418] Avg episode reward: [(0, '12.680')] [2024-11-13 13:42:57,629][02436] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000590_2416640.pth... [2024-11-13 13:42:57,752][02436] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000380_1556480.pth [2024-11-13 13:43:02,615][00418] Fps is (10 sec: 4096.1, 60 sec: 3618.1, 300 sec: 3596.1). Total num frames: 2437120. Throughput: 0: 901.2. Samples: 610072. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-11-13 13:43:02,620][00418] Avg episode reward: [(0, '12.838')] [2024-11-13 13:43:07,617][00418] Fps is (10 sec: 3276.1, 60 sec: 3549.7, 300 sec: 3568.4). Total num frames: 2449408. Throughput: 0: 907.5. Samples: 612344. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2024-11-13 13:43:07,624][00418] Avg episode reward: [(0, '13.578')] [2024-11-13 13:43:08,881][02456] Updated weights for policy 0, policy_version 600 (0.0020) [2024-11-13 13:43:12,615][00418] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3596.1). Total num frames: 2469888. Throughput: 0: 895.9. Samples: 617346. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2024-11-13 13:43:12,617][00418] Avg episode reward: [(0, '13.481')] [2024-11-13 13:43:17,615][00418] Fps is (10 sec: 4096.9, 60 sec: 3618.1, 300 sec: 3596.1). Total num frames: 2490368. Throughput: 0: 899.3. Samples: 623648. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2024-11-13 13:43:17,618][00418] Avg episode reward: [(0, '13.297')] [2024-11-13 13:43:18,963][02456] Updated weights for policy 0, policy_version 610 (0.0020) [2024-11-13 13:43:22,615][00418] Fps is (10 sec: 3686.4, 60 sec: 3618.1, 300 sec: 3582.3). Total num frames: 2506752. Throughput: 0: 911.2. Samples: 626050. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2024-11-13 13:43:22,622][00418] Avg episode reward: [(0, '13.074')] [2024-11-13 13:43:27,615][00418] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3596.1). Total num frames: 2523136. Throughput: 0: 899.6. Samples: 630908. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2024-11-13 13:43:27,618][00418] Avg episode reward: [(0, '12.532')] [2024-11-13 13:43:30,553][02456] Updated weights for policy 0, policy_version 620 (0.0017) [2024-11-13 13:43:32,615][00418] Fps is (10 sec: 3686.4, 60 sec: 3549.9, 300 sec: 3596.1). Total num frames: 2543616. Throughput: 0: 902.0. Samples: 637130. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2024-11-13 13:43:32,620][00418] Avg episode reward: [(0, '14.184')] [2024-11-13 13:43:37,615][00418] Fps is (10 sec: 3686.4, 60 sec: 3618.1, 300 sec: 3582.3). Total num frames: 2560000. Throughput: 0: 909.1. Samples: 639530. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2024-11-13 13:43:37,617][00418] Avg episode reward: [(0, '14.902')] [2024-11-13 13:43:42,380][02456] Updated weights for policy 0, policy_version 630 (0.0021) [2024-11-13 13:43:42,616][00418] Fps is (10 sec: 3686.2, 60 sec: 3618.1, 300 sec: 3610.0). Total num frames: 2580480. Throughput: 0: 899.5. Samples: 644420. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2024-11-13 13:43:42,618][00418] Avg episode reward: [(0, '15.844')] [2024-11-13 13:43:42,627][02436] Saving new best policy, reward=15.844! [2024-11-13 13:43:47,615][00418] Fps is (10 sec: 4096.0, 60 sec: 3618.1, 300 sec: 3610.1). Total num frames: 2600960. Throughput: 0: 900.0. Samples: 650570. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2024-11-13 13:43:47,617][00418] Avg episode reward: [(0, '18.439')] [2024-11-13 13:43:47,631][02436] Saving new best policy, reward=18.439! [2024-11-13 13:43:52,616][00418] Fps is (10 sec: 3276.6, 60 sec: 3618.1, 300 sec: 3582.3). Total num frames: 2613248. Throughput: 0: 905.8. Samples: 653106. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2024-11-13 13:43:52,622][00418] Avg episode reward: [(0, '19.567')] [2024-11-13 13:43:52,631][02436] Saving new best policy, reward=19.567! [2024-11-13 13:43:54,280][02456] Updated weights for policy 0, policy_version 640 (0.0020) [2024-11-13 13:43:57,615][00418] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3596.1). Total num frames: 2633728. Throughput: 0: 899.1. Samples: 657806. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-11-13 13:43:57,623][00418] Avg episode reward: [(0, '20.349')] [2024-11-13 13:43:57,632][02436] Saving new best policy, reward=20.349! [2024-11-13 13:44:02,615][00418] Fps is (10 sec: 4096.5, 60 sec: 3618.1, 300 sec: 3610.0). Total num frames: 2654208. Throughput: 0: 894.8. Samples: 663912. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2024-11-13 13:44:02,619][00418] Avg episode reward: [(0, '20.682')] [2024-11-13 13:44:02,625][02436] Saving new best policy, reward=20.682! [2024-11-13 13:44:04,691][02456] Updated weights for policy 0, policy_version 650 (0.0013) [2024-11-13 13:44:07,615][00418] Fps is (10 sec: 3276.8, 60 sec: 3618.3, 300 sec: 3568.4). Total num frames: 2666496. Throughput: 0: 897.6. Samples: 666440. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2024-11-13 13:44:07,622][00418] Avg episode reward: [(0, '19.610')] [2024-11-13 13:44:12,615][00418] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3596.1). Total num frames: 2686976. Throughput: 0: 894.0. Samples: 671140. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2024-11-13 13:44:12,617][00418] Avg episode reward: [(0, '19.503')] [2024-11-13 13:44:16,288][02456] Updated weights for policy 0, policy_version 660 (0.0014) [2024-11-13 13:44:17,615][00418] Fps is (10 sec: 4096.0, 60 sec: 3618.1, 300 sec: 3596.1). Total num frames: 2707456. Throughput: 0: 895.2. Samples: 677416. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2024-11-13 13:44:17,622][00418] Avg episode reward: [(0, '18.477')] [2024-11-13 13:44:22,617][00418] Fps is (10 sec: 3685.6, 60 sec: 3618.0, 300 sec: 3582.2). Total num frames: 2723840. Throughput: 0: 902.8. Samples: 680156. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2024-11-13 13:44:22,620][00418] Avg episode reward: [(0, '18.174')] [2024-11-13 13:44:27,615][00418] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3596.1). Total num frames: 2740224. Throughput: 0: 896.3. Samples: 684754. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2024-11-13 13:44:27,617][00418] Avg episode reward: [(0, '17.770')] [2024-11-13 13:44:28,136][02456] Updated weights for policy 0, policy_version 670 (0.0013) [2024-11-13 13:44:32,615][00418] Fps is (10 sec: 3687.2, 60 sec: 3618.1, 300 sec: 3596.1). Total num frames: 2760704. Throughput: 0: 896.0. Samples: 690890. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2024-11-13 13:44:32,619][00418] Avg episode reward: [(0, '19.979')] [2024-11-13 13:44:37,615][00418] Fps is (10 sec: 3686.4, 60 sec: 3618.1, 300 sec: 3582.3). Total num frames: 2777088. Throughput: 0: 900.4. Samples: 693622. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2024-11-13 13:44:37,617][00418] Avg episode reward: [(0, '21.260')] [2024-11-13 13:44:37,636][02436] Saving new best policy, reward=21.260! [2024-11-13 13:44:40,050][02456] Updated weights for policy 0, policy_version 680 (0.0022) [2024-11-13 13:44:42,615][00418] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3582.3). Total num frames: 2793472. Throughput: 0: 895.7. Samples: 698114. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-11-13 13:44:42,617][00418] Avg episode reward: [(0, '21.828')] [2024-11-13 13:44:42,624][02436] Saving new best policy, reward=21.828! [2024-11-13 13:44:47,615][00418] Fps is (10 sec: 3686.4, 60 sec: 3549.9, 300 sec: 3596.1). Total num frames: 2813952. Throughput: 0: 895.8. Samples: 704224. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-11-13 13:44:47,617][00418] Avg episode reward: [(0, '21.598')] [2024-11-13 13:44:50,105][02456] Updated weights for policy 0, policy_version 690 (0.0019) [2024-11-13 13:44:52,616][00418] Fps is (10 sec: 3686.0, 60 sec: 3618.1, 300 sec: 3582.2). Total num frames: 2830336. Throughput: 0: 904.3. Samples: 707136. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2024-11-13 13:44:52,624][00418] Avg episode reward: [(0, '22.320')] [2024-11-13 13:44:52,629][02436] Saving new best policy, reward=22.320! [2024-11-13 13:44:57,615][00418] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3582.3). Total num frames: 2846720. Throughput: 0: 897.2. Samples: 711514. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2024-11-13 13:44:57,617][00418] Avg episode reward: [(0, '24.544')] [2024-11-13 13:44:57,626][02436] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000695_2846720.pth... [2024-11-13 13:44:57,751][02436] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000486_1990656.pth [2024-11-13 13:44:57,772][02436] Saving new best policy, reward=24.544! [2024-11-13 13:45:02,125][02456] Updated weights for policy 0, policy_version 700 (0.0018) [2024-11-13 13:45:02,615][00418] Fps is (10 sec: 3686.8, 60 sec: 3549.9, 300 sec: 3596.1). Total num frames: 2867200. Throughput: 0: 890.2. Samples: 717474. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2024-11-13 13:45:02,624][00418] Avg episode reward: [(0, '23.320')] [2024-11-13 13:45:07,615][00418] Fps is (10 sec: 3686.4, 60 sec: 3618.1, 300 sec: 3582.3). Total num frames: 2883584. Throughput: 0: 896.3. Samples: 720488. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2024-11-13 13:45:07,617][00418] Avg episode reward: [(0, '22.992')] [2024-11-13 13:45:12,615][00418] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3582.3). Total num frames: 2899968. Throughput: 0: 886.6. Samples: 724650. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2024-11-13 13:45:12,617][00418] Avg episode reward: [(0, '23.255')] [2024-11-13 13:45:14,164][02456] Updated weights for policy 0, policy_version 710 (0.0022) [2024-11-13 13:45:17,615][00418] Fps is (10 sec: 3686.4, 60 sec: 3549.9, 300 sec: 3596.1). Total num frames: 2920448. Throughput: 0: 889.5. Samples: 730918. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2024-11-13 13:45:17,617][00418] Avg episode reward: [(0, '22.152')] [2024-11-13 13:45:22,615][00418] Fps is (10 sec: 4096.0, 60 sec: 3618.3, 300 sec: 3596.1). Total num frames: 2940928. Throughput: 0: 897.9. Samples: 734026. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2024-11-13 13:45:22,617][00418] Avg episode reward: [(0, '19.372')] [2024-11-13 13:45:25,310][02456] Updated weights for policy 0, policy_version 720 (0.0014) [2024-11-13 13:45:27,615][00418] Fps is (10 sec: 3276.7, 60 sec: 3549.8, 300 sec: 3582.3). Total num frames: 2953216. Throughput: 0: 894.2. Samples: 738352. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-11-13 13:45:27,628][00418] Avg episode reward: [(0, '19.601')] [2024-11-13 13:45:32,615][00418] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3596.1). Total num frames: 2973696. Throughput: 0: 895.3. Samples: 744512. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2024-11-13 13:45:32,618][00418] Avg episode reward: [(0, '19.612')] [2024-11-13 13:45:35,716][02456] Updated weights for policy 0, policy_version 730 (0.0013) [2024-11-13 13:45:37,620][00418] Fps is (10 sec: 4094.0, 60 sec: 3617.8, 300 sec: 3582.2). Total num frames: 2994176. Throughput: 0: 898.0. Samples: 747548. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2024-11-13 13:45:37,622][00418] Avg episode reward: [(0, '19.075')] [2024-11-13 13:45:42,615][00418] Fps is (10 sec: 3686.4, 60 sec: 3618.1, 300 sec: 3596.2). Total num frames: 3010560. Throughput: 0: 898.6. Samples: 751950. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2024-11-13 13:45:42,617][00418] Avg episode reward: [(0, '20.216')] [2024-11-13 13:45:47,503][02456] Updated weights for policy 0, policy_version 740 (0.0023) [2024-11-13 13:45:47,615][00418] Fps is (10 sec: 3688.3, 60 sec: 3618.1, 300 sec: 3596.1). Total num frames: 3031040. Throughput: 0: 901.1. Samples: 758022. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2024-11-13 13:45:47,617][00418] Avg episode reward: [(0, '20.833')] [2024-11-13 13:45:52,619][00418] Fps is (10 sec: 3684.9, 60 sec: 3618.0, 300 sec: 3582.2). Total num frames: 3047424. Throughput: 0: 903.0. Samples: 761126. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-11-13 13:45:52,626][00418] Avg episode reward: [(0, '20.903')] [2024-11-13 13:45:57,615][00418] Fps is (10 sec: 3276.7, 60 sec: 3618.1, 300 sec: 3596.1). Total num frames: 3063808. Throughput: 0: 911.9. Samples: 765686. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2024-11-13 13:45:57,619][00418] Avg episode reward: [(0, '20.206')] [2024-11-13 13:45:59,410][02456] Updated weights for policy 0, policy_version 750 (0.0013) [2024-11-13 13:46:02,615][00418] Fps is (10 sec: 3687.9, 60 sec: 3618.1, 300 sec: 3610.0). Total num frames: 3084288. Throughput: 0: 902.5. Samples: 771530. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2024-11-13 13:46:02,617][00418] Avg episode reward: [(0, '20.668')] [2024-11-13 13:46:07,616][00418] Fps is (10 sec: 4095.7, 60 sec: 3686.3, 300 sec: 3610.0). Total num frames: 3104768. Throughput: 0: 900.1. Samples: 774530. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-11-13 13:46:07,621][00418] Avg episode reward: [(0, '20.133')] [2024-11-13 13:46:10,245][02456] Updated weights for policy 0, policy_version 760 (0.0014) [2024-11-13 13:46:12,616][00418] Fps is (10 sec: 3276.6, 60 sec: 3618.1, 300 sec: 3596.1). Total num frames: 3117056. Throughput: 0: 910.7. Samples: 779334. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2024-11-13 13:46:12,623][00418] Avg episode reward: [(0, '19.877')] [2024-11-13 13:46:17,615][00418] Fps is (10 sec: 3277.2, 60 sec: 3618.1, 300 sec: 3596.2). Total num frames: 3137536. Throughput: 0: 900.8. Samples: 785046. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2024-11-13 13:46:17,618][00418] Avg episode reward: [(0, '20.601')] [2024-11-13 13:46:20,932][02456] Updated weights for policy 0, policy_version 770 (0.0014) [2024-11-13 13:46:22,615][00418] Fps is (10 sec: 4096.2, 60 sec: 3618.1, 300 sec: 3596.1). Total num frames: 3158016. Throughput: 0: 903.9. Samples: 788220. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2024-11-13 13:46:22,618][00418] Avg episode reward: [(0, '20.979')] [2024-11-13 13:46:27,615][00418] Fps is (10 sec: 3276.8, 60 sec: 3618.2, 300 sec: 3582.3). Total num frames: 3170304. Throughput: 0: 914.0. Samples: 793080. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2024-11-13 13:46:27,620][00418] Avg episode reward: [(0, '20.892')] [2024-11-13 13:46:32,615][00418] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3596.1). Total num frames: 3190784. Throughput: 0: 903.0. Samples: 798656. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2024-11-13 13:46:32,624][00418] Avg episode reward: [(0, '20.952')] [2024-11-13 13:46:32,859][02456] Updated weights for policy 0, policy_version 780 (0.0020) [2024-11-13 13:46:37,615][00418] Fps is (10 sec: 4095.9, 60 sec: 3618.4, 300 sec: 3596.1). Total num frames: 3211264. Throughput: 0: 901.0. Samples: 801666. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2024-11-13 13:46:37,618][00418] Avg episode reward: [(0, '21.337')] [2024-11-13 13:46:42,615][00418] Fps is (10 sec: 3686.4, 60 sec: 3618.1, 300 sec: 3596.1). Total num frames: 3227648. Throughput: 0: 910.0. Samples: 806634. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-11-13 13:46:42,620][00418] Avg episode reward: [(0, '21.297')] [2024-11-13 13:46:44,706][02456] Updated weights for policy 0, policy_version 790 (0.0013) [2024-11-13 13:46:47,615][00418] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3596.1). Total num frames: 3244032. Throughput: 0: 903.3. Samples: 812180. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2024-11-13 13:46:47,618][00418] Avg episode reward: [(0, '21.577')] [2024-11-13 13:46:52,615][00418] Fps is (10 sec: 4096.0, 60 sec: 3686.7, 300 sec: 3610.0). Total num frames: 3268608. Throughput: 0: 905.3. Samples: 815266. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2024-11-13 13:46:52,622][00418] Avg episode reward: [(0, '22.014')] [2024-11-13 13:46:55,407][02456] Updated weights for policy 0, policy_version 800 (0.0013) [2024-11-13 13:46:57,617][00418] Fps is (10 sec: 3685.6, 60 sec: 3618.0, 300 sec: 3596.1). Total num frames: 3280896. Throughput: 0: 911.5. Samples: 820354. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2024-11-13 13:46:57,621][00418] Avg episode reward: [(0, '22.540')] [2024-11-13 13:46:57,630][02436] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000801_3280896.pth... [2024-11-13 13:46:57,763][02436] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000590_2416640.pth [2024-11-13 13:47:02,615][00418] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3610.0). Total num frames: 3301376. Throughput: 0: 905.7. Samples: 825802. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2024-11-13 13:47:02,623][00418] Avg episode reward: [(0, '22.820')] [2024-11-13 13:47:06,540][02456] Updated weights for policy 0, policy_version 810 (0.0016) [2024-11-13 13:47:07,615][00418] Fps is (10 sec: 4096.9, 60 sec: 3618.2, 300 sec: 3610.0). Total num frames: 3321856. Throughput: 0: 903.2. Samples: 828866. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2024-11-13 13:47:07,618][00418] Avg episode reward: [(0, '23.352')] [2024-11-13 13:47:12,615][00418] Fps is (10 sec: 3276.7, 60 sec: 3618.2, 300 sec: 3596.1). Total num frames: 3334144. Throughput: 0: 908.4. Samples: 833956. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2024-11-13 13:47:12,618][00418] Avg episode reward: [(0, '23.291')] [2024-11-13 13:47:17,615][00418] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3610.0). Total num frames: 3354624. Throughput: 0: 903.0. Samples: 839290. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-11-13 13:47:17,622][00418] Avg episode reward: [(0, '23.181')] [2024-11-13 13:47:18,055][02456] Updated weights for policy 0, policy_version 820 (0.0025) [2024-11-13 13:47:22,615][00418] Fps is (10 sec: 4096.1, 60 sec: 3618.1, 300 sec: 3610.0). Total num frames: 3375104. Throughput: 0: 905.6. Samples: 842416. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2024-11-13 13:47:22,617][00418] Avg episode reward: [(0, '23.335')] [2024-11-13 13:47:27,615][00418] Fps is (10 sec: 3686.4, 60 sec: 3686.4, 300 sec: 3596.1). Total num frames: 3391488. Throughput: 0: 911.4. Samples: 847648. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2024-11-13 13:47:27,621][00418] Avg episode reward: [(0, '22.861')] [2024-11-13 13:47:30,036][02456] Updated weights for policy 0, policy_version 830 (0.0026) [2024-11-13 13:47:32,615][00418] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3610.0). Total num frames: 3407872. Throughput: 0: 904.2. Samples: 852870. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-11-13 13:47:32,621][00418] Avg episode reward: [(0, '23.566')] [2024-11-13 13:47:37,615][00418] Fps is (10 sec: 3686.4, 60 sec: 3618.1, 300 sec: 3610.0). Total num frames: 3428352. Throughput: 0: 903.8. Samples: 855938. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2024-11-13 13:47:37,619][00418] Avg episode reward: [(0, '23.935')] [2024-11-13 13:47:40,614][02456] Updated weights for policy 0, policy_version 840 (0.0024) [2024-11-13 13:47:42,615][00418] Fps is (10 sec: 3686.4, 60 sec: 3618.1, 300 sec: 3596.1). Total num frames: 3444736. Throughput: 0: 905.2. Samples: 861086. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2024-11-13 13:47:42,618][00418] Avg episode reward: [(0, '24.420')] [2024-11-13 13:47:47,618][00418] Fps is (10 sec: 3275.7, 60 sec: 3617.9, 300 sec: 3610.0). Total num frames: 3461120. Throughput: 0: 897.3. Samples: 866184. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2024-11-13 13:47:47,620][00418] Avg episode reward: [(0, '24.461')] [2024-11-13 13:47:52,015][02456] Updated weights for policy 0, policy_version 850 (0.0014) [2024-11-13 13:47:52,617][00418] Fps is (10 sec: 3685.6, 60 sec: 3549.7, 300 sec: 3610.0). Total num frames: 3481600. Throughput: 0: 896.8. Samples: 869222. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2024-11-13 13:47:52,621][00418] Avg episode reward: [(0, '24.757')] [2024-11-13 13:47:52,624][02436] Saving new best policy, reward=24.757! [2024-11-13 13:47:57,615][00418] Fps is (10 sec: 3687.6, 60 sec: 3618.3, 300 sec: 3596.1). Total num frames: 3497984. Throughput: 0: 902.2. Samples: 874556. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-11-13 13:47:57,625][00418] Avg episode reward: [(0, '23.536')] [2024-11-13 13:48:02,615][00418] Fps is (10 sec: 3277.5, 60 sec: 3549.9, 300 sec: 3610.1). Total num frames: 3514368. Throughput: 0: 894.0. Samples: 879518. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2024-11-13 13:48:02,621][00418] Avg episode reward: [(0, '22.118')] [2024-11-13 13:48:03,980][02456] Updated weights for policy 0, policy_version 860 (0.0025) [2024-11-13 13:48:07,618][00418] Fps is (10 sec: 3685.4, 60 sec: 3549.7, 300 sec: 3610.0). Total num frames: 3534848. Throughput: 0: 892.9. Samples: 882600. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2024-11-13 13:48:07,622][00418] Avg episode reward: [(0, '22.676')] [2024-11-13 13:48:12,615][00418] Fps is (10 sec: 3686.4, 60 sec: 3618.1, 300 sec: 3596.1). Total num frames: 3551232. Throughput: 0: 896.2. Samples: 887976. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2024-11-13 13:48:12,622][00418] Avg episode reward: [(0, '23.318')] [2024-11-13 13:48:16,128][02456] Updated weights for policy 0, policy_version 870 (0.0014) [2024-11-13 13:48:17,615][00418] Fps is (10 sec: 3277.7, 60 sec: 3549.9, 300 sec: 3596.1). Total num frames: 3567616. Throughput: 0: 883.0. Samples: 892606. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2024-11-13 13:48:17,618][00418] Avg episode reward: [(0, '23.198')] [2024-11-13 13:48:22,615][00418] Fps is (10 sec: 3686.4, 60 sec: 3549.9, 300 sec: 3610.0). Total num frames: 3588096. Throughput: 0: 884.3. Samples: 895732. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2024-11-13 13:48:22,623][00418] Avg episode reward: [(0, '22.695')] [2024-11-13 13:48:26,567][02456] Updated weights for policy 0, policy_version 880 (0.0014) [2024-11-13 13:48:27,616][00418] Fps is (10 sec: 3686.0, 60 sec: 3549.8, 300 sec: 3596.1). Total num frames: 3604480. Throughput: 0: 895.3. Samples: 901376. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2024-11-13 13:48:27,623][00418] Avg episode reward: [(0, '23.225')] [2024-11-13 13:48:32,615][00418] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3596.1). Total num frames: 3620864. Throughput: 0: 887.4. Samples: 906114. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2024-11-13 13:48:32,622][00418] Avg episode reward: [(0, '23.467')] [2024-11-13 13:48:37,615][00418] Fps is (10 sec: 3686.8, 60 sec: 3549.9, 300 sec: 3596.2). Total num frames: 3641344. Throughput: 0: 889.6. Samples: 909250. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2024-11-13 13:48:37,620][00418] Avg episode reward: [(0, '24.051')] [2024-11-13 13:48:37,886][02456] Updated weights for policy 0, policy_version 890 (0.0014) [2024-11-13 13:48:42,616][00418] Fps is (10 sec: 3686.0, 60 sec: 3549.8, 300 sec: 3582.2). Total num frames: 3657728. Throughput: 0: 898.0. Samples: 914966. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2024-11-13 13:48:42,620][00418] Avg episode reward: [(0, '24.555')] [2024-11-13 13:48:47,615][00418] Fps is (10 sec: 3276.8, 60 sec: 3550.1, 300 sec: 3596.2). Total num frames: 3674112. Throughput: 0: 892.8. Samples: 919692. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2024-11-13 13:48:47,617][00418] Avg episode reward: [(0, '23.876')] [2024-11-13 13:48:49,652][02456] Updated weights for policy 0, policy_version 900 (0.0016) [2024-11-13 13:48:52,615][00418] Fps is (10 sec: 3686.9, 60 sec: 3550.0, 300 sec: 3596.1). Total num frames: 3694592. Throughput: 0: 892.1. Samples: 922744. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2024-11-13 13:48:52,620][00418] Avg episode reward: [(0, '25.644')] [2024-11-13 13:48:52,676][02436] Saving new best policy, reward=25.644! [2024-11-13 13:48:57,615][00418] Fps is (10 sec: 4096.0, 60 sec: 3618.1, 300 sec: 3596.1). Total num frames: 3715072. Throughput: 0: 904.3. Samples: 928668. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2024-11-13 13:48:57,625][00418] Avg episode reward: [(0, '24.631')] [2024-11-13 13:48:57,634][02436] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000907_3715072.pth... [2024-11-13 13:48:57,750][02436] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000695_2846720.pth [2024-11-13 13:49:01,606][02456] Updated weights for policy 0, policy_version 910 (0.0018) [2024-11-13 13:49:02,618][00418] Fps is (10 sec: 3275.8, 60 sec: 3549.7, 300 sec: 3596.1). Total num frames: 3727360. Throughput: 0: 900.2. Samples: 933120. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2024-11-13 13:49:02,620][00418] Avg episode reward: [(0, '23.276')] [2024-11-13 13:49:07,615][00418] Fps is (10 sec: 3276.8, 60 sec: 3550.0, 300 sec: 3596.1). Total num frames: 3747840. Throughput: 0: 900.1. Samples: 936236. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2024-11-13 13:49:07,620][00418] Avg episode reward: [(0, '22.505')] [2024-11-13 13:49:11,928][02456] Updated weights for policy 0, policy_version 920 (0.0018) [2024-11-13 13:49:12,621][00418] Fps is (10 sec: 4094.7, 60 sec: 3617.8, 300 sec: 3596.1). Total num frames: 3768320. Throughput: 0: 905.0. Samples: 942106. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2024-11-13 13:49:12,626][00418] Avg episode reward: [(0, '22.686')] [2024-11-13 13:49:17,615][00418] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3582.3). Total num frames: 3780608. Throughput: 0: 894.4. Samples: 946360. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2024-11-13 13:49:17,625][00418] Avg episode reward: [(0, '24.006')] [2024-11-13 13:49:22,615][00418] Fps is (10 sec: 3688.7, 60 sec: 3618.2, 300 sec: 3610.0). Total num frames: 3805184. Throughput: 0: 894.4. Samples: 949500. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2024-11-13 13:49:22,621][00418] Avg episode reward: [(0, '23.053')] [2024-11-13 13:49:23,552][02456] Updated weights for policy 0, policy_version 930 (0.0015) [2024-11-13 13:49:27,619][00418] Fps is (10 sec: 4094.3, 60 sec: 3618.0, 300 sec: 3596.1). Total num frames: 3821568. Throughput: 0: 904.8. Samples: 955684. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2024-11-13 13:49:27,625][00418] Avg episode reward: [(0, '22.854')] [2024-11-13 13:49:32,615][00418] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3596.1). Total num frames: 3837952. Throughput: 0: 895.8. Samples: 960002. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2024-11-13 13:49:32,618][00418] Avg episode reward: [(0, '22.387')] [2024-11-13 13:49:35,306][02456] Updated weights for policy 0, policy_version 940 (0.0019) [2024-11-13 13:49:37,615][00418] Fps is (10 sec: 3687.9, 60 sec: 3618.1, 300 sec: 3610.0). Total num frames: 3858432. Throughput: 0: 896.5. Samples: 963086. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2024-11-13 13:49:37,618][00418] Avg episode reward: [(0, '24.519')] [2024-11-13 13:49:42,615][00418] Fps is (10 sec: 4096.0, 60 sec: 3686.5, 300 sec: 3610.0). Total num frames: 3878912. Throughput: 0: 902.0. Samples: 969258. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2024-11-13 13:49:42,617][00418] Avg episode reward: [(0, '22.135')] [2024-11-13 13:49:46,953][02456] Updated weights for policy 0, policy_version 950 (0.0014) [2024-11-13 13:49:47,615][00418] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3596.2). Total num frames: 3891200. Throughput: 0: 896.8. Samples: 973474. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2024-11-13 13:49:47,617][00418] Avg episode reward: [(0, '22.036')] [2024-11-13 13:49:52,615][00418] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3610.0). Total num frames: 3911680. Throughput: 0: 897.7. Samples: 976634. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2024-11-13 13:49:52,623][00418] Avg episode reward: [(0, '21.232')] [2024-11-13 13:49:56,967][02456] Updated weights for policy 0, policy_version 960 (0.0017) [2024-11-13 13:49:57,617][00418] Fps is (10 sec: 4095.1, 60 sec: 3618.0, 300 sec: 3610.0). Total num frames: 3932160. Throughput: 0: 905.6. Samples: 982854. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2024-11-13 13:49:57,619][00418] Avg episode reward: [(0, '22.850')] [2024-11-13 13:50:02,615][00418] Fps is (10 sec: 3276.8, 60 sec: 3618.3, 300 sec: 3596.1). Total num frames: 3944448. Throughput: 0: 906.8. Samples: 987164. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2024-11-13 13:50:02,621][00418] Avg episode reward: [(0, '22.716')] [2024-11-13 13:50:07,615][00418] Fps is (10 sec: 3277.5, 60 sec: 3618.1, 300 sec: 3610.0). Total num frames: 3964928. Throughput: 0: 906.8. Samples: 990306. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2024-11-13 13:50:07,618][00418] Avg episode reward: [(0, '21.464')] [2024-11-13 13:50:08,741][02456] Updated weights for policy 0, policy_version 970 (0.0020) [2024-11-13 13:50:12,615][00418] Fps is (10 sec: 4096.0, 60 sec: 3618.5, 300 sec: 3610.0). Total num frames: 3985408. Throughput: 0: 906.0. Samples: 996452. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2024-11-13 13:50:12,620][00418] Avg episode reward: [(0, '23.837')] [2024-11-13 13:50:17,615][00418] Fps is (10 sec: 3686.4, 60 sec: 3686.4, 300 sec: 3596.1). Total num frames: 4001792. Throughput: 0: 904.3. Samples: 1000694. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2024-11-13 13:50:17,625][00418] Avg episode reward: [(0, '23.444')] [2024-11-13 13:50:18,528][02436] Stopping Batcher_0... [2024-11-13 13:50:18,535][02436] Loop batcher_evt_loop terminating... [2024-11-13 13:50:18,533][02436] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... [2024-11-13 13:50:18,529][00418] Component Batcher_0 stopped! [2024-11-13 13:50:18,540][00418] Component RolloutWorker_w0 process died already! Don't wait for it. [2024-11-13 13:50:18,545][00418] Component RolloutWorker_w2 process died already! Don't wait for it. [2024-11-13 13:50:18,548][00418] Component RolloutWorker_w6 process died already! Don't wait for it. [2024-11-13 13:50:18,584][02456] Weights refcount: 2 0 [2024-11-13 13:50:18,587][00418] Component InferenceWorker_p0-w0 stopped! [2024-11-13 13:50:18,590][02456] Stopping InferenceWorker_p0-w0... [2024-11-13 13:50:18,593][02456] Loop inference_proc0-0_evt_loop terminating... [2024-11-13 13:50:18,672][02436] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000801_3280896.pth [2024-11-13 13:50:18,683][02436] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... [2024-11-13 13:50:18,864][02436] Stopping LearnerWorker_p0... [2024-11-13 13:50:18,868][02436] Loop learner_proc0_evt_loop terminating... [2024-11-13 13:50:18,864][00418] Component LearnerWorker_p0 stopped! [2024-11-13 13:50:18,895][02455] Stopping RolloutWorker_w4... [2024-11-13 13:50:18,895][00418] Component RolloutWorker_w4 stopped! [2024-11-13 13:50:18,897][02455] Loop rollout_proc4_evt_loop terminating... [2024-11-13 13:50:19,006][00418] Component RolloutWorker_w7 stopped! [2024-11-13 13:50:19,012][02454] Stopping RolloutWorker_w7... [2024-11-13 13:50:19,029][00418] Component RolloutWorker_w5 stopped! [2024-11-13 13:50:19,035][02450] Stopping RolloutWorker_w5... [2024-11-13 13:50:19,036][02450] Loop rollout_proc5_evt_loop terminating... [2024-11-13 13:50:19,018][02454] Loop rollout_proc7_evt_loop terminating... [2024-11-13 13:50:19,045][00418] Component RolloutWorker_w3 stopped! [2024-11-13 13:50:19,045][02452] Stopping RolloutWorker_w3... [2024-11-13 13:50:19,051][02452] Loop rollout_proc3_evt_loop terminating... [2024-11-13 13:50:19,111][02449] Stopping RolloutWorker_w1... [2024-11-13 13:50:19,111][00418] Component RolloutWorker_w1 stopped! [2024-11-13 13:50:19,113][00418] Waiting for process learner_proc0 to stop... [2024-11-13 13:50:19,112][02449] Loop rollout_proc1_evt_loop terminating... [2024-11-13 13:50:20,089][00418] Waiting for process inference_proc0-0 to join... [2024-11-13 13:50:20,096][00418] Waiting for process rollout_proc0 to join... [2024-11-13 13:50:20,100][00418] Waiting for process rollout_proc1 to join... [2024-11-13 13:50:21,711][00418] Waiting for process rollout_proc2 to join... [2024-11-13 13:50:21,713][00418] Waiting for process rollout_proc3 to join... [2024-11-13 13:50:21,716][00418] Waiting for process rollout_proc4 to join... [2024-11-13 13:50:21,721][00418] Waiting for process rollout_proc5 to join... [2024-11-13 13:50:21,724][00418] Waiting for process rollout_proc6 to join... [2024-11-13 13:50:21,727][00418] Waiting for process rollout_proc7 to join... [2024-11-13 13:50:21,731][00418] Batcher 0 profile tree view: batching: 24.2029, releasing_batches: 0.0275 [2024-11-13 13:50:21,732][00418] InferenceWorker_p0-w0 profile tree view: wait_policy: 0.0021 wait_policy_total: 438.7715 update_model: 9.9846 weight_update: 0.0017 one_step: 0.0028 handle_policy_step: 632.6868 deserialize: 15.7244, stack: 4.0640, obs_to_device_normalize: 142.9990, forward: 323.6985, send_messages: 22.5785 prepare_outputs: 90.4376 to_cpu: 55.2914 [2024-11-13 13:50:21,734][00418] Learner 0 profile tree view: misc: 0.0056, prepare_batch: 13.4476 train: 69.9180 epoch_init: 0.0060, minibatch_init: 0.0068, losses_postprocess: 0.6873, kl_divergence: 0.6159, after_optimizer: 32.6940 calculate_losses: 24.1000 losses_init: 0.0035, forward_head: 1.1722, bptt_initial: 16.5712, tail: 0.9689, advantages_returns: 0.2601, losses: 3.2993 bptt: 1.5732 bptt_forward_core: 1.5122 update: 11.2419 clip: 0.8896 [2024-11-13 13:50:21,735][00418] RolloutWorker_w7 profile tree view: wait_for_trajectories: 0.4712, enqueue_policy_requests: 104.8874, env_step: 910.8620, overhead: 16.6098, complete_rollouts: 7.5122 save_policy_outputs: 25.8709 split_output_tensors: 10.3801 [2024-11-13 13:50:21,737][00418] Loop Runner_EvtLoop terminating... [2024-11-13 13:50:21,739][00418] Runner profile tree view: main_loop: 1155.9991 [2024-11-13 13:50:21,740][00418] Collected {0: 4005888}, FPS: 3465.3 [2024-11-13 13:50:22,156][00418] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json [2024-11-13 13:50:22,158][00418] Overriding arg 'num_workers' with value 1 passed from command line [2024-11-13 13:50:22,161][00418] Adding new argument 'no_render'=True that is not in the saved config file! [2024-11-13 13:50:22,162][00418] Adding new argument 'save_video'=True that is not in the saved config file! [2024-11-13 13:50:22,164][00418] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file! [2024-11-13 13:50:22,166][00418] Adding new argument 'video_name'=None that is not in the saved config file! [2024-11-13 13:50:22,168][00418] Adding new argument 'max_num_frames'=1000000000.0 that is not in the saved config file! [2024-11-13 13:50:22,170][00418] Adding new argument 'max_num_episodes'=10 that is not in the saved config file! [2024-11-13 13:50:22,171][00418] Adding new argument 'push_to_hub'=False that is not in the saved config file! [2024-11-13 13:50:22,174][00418] Adding new argument 'hf_repository'=None that is not in the saved config file! [2024-11-13 13:50:22,175][00418] Adding new argument 'policy_index'=0 that is not in the saved config file! [2024-11-13 13:50:22,176][00418] Adding new argument 'eval_deterministic'=False that is not in the saved config file! [2024-11-13 13:50:22,178][00418] Adding new argument 'train_script'=None that is not in the saved config file! [2024-11-13 13:50:22,180][00418] Adding new argument 'enjoy_script'=None that is not in the saved config file! [2024-11-13 13:50:22,182][00418] Using frameskip 1 and render_action_repeat=4 for evaluation [2024-11-13 13:50:22,211][00418] Doom resolution: 160x120, resize resolution: (128, 72) [2024-11-13 13:50:22,216][00418] RunningMeanStd input shape: (3, 72, 128) [2024-11-13 13:50:22,218][00418] RunningMeanStd input shape: (1,) [2024-11-13 13:50:22,234][00418] ConvEncoder: input_channels=3 [2024-11-13 13:50:22,333][00418] Conv encoder output size: 512 [2024-11-13 13:50:22,335][00418] Policy head output size: 512 [2024-11-13 13:50:22,515][00418] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... [2024-11-13 13:50:23,328][00418] Num frames 100... [2024-11-13 13:50:23,451][00418] Num frames 200... [2024-11-13 13:50:23,571][00418] Num frames 300... [2024-11-13 13:50:23,702][00418] Num frames 400... [2024-11-13 13:50:23,825][00418] Num frames 500... [2024-11-13 13:50:23,945][00418] Num frames 600... [2024-11-13 13:50:24,068][00418] Num frames 700... [2024-11-13 13:50:24,190][00418] Num frames 800... [2024-11-13 13:50:24,311][00418] Num frames 900... [2024-11-13 13:50:24,400][00418] Avg episode rewards: #0: 23.280, true rewards: #0: 9.280 [2024-11-13 13:50:24,401][00418] Avg episode reward: 23.280, avg true_objective: 9.280 [2024-11-13 13:50:24,488][00418] Num frames 1000... [2024-11-13 13:50:24,611][00418] Num frames 1100... [2024-11-13 13:50:24,738][00418] Num frames 1200... [2024-11-13 13:50:24,865][00418] Num frames 1300... [2024-11-13 13:50:24,983][00418] Num frames 1400... [2024-11-13 13:50:25,106][00418] Num frames 1500... [2024-11-13 13:50:25,230][00418] Num frames 1600... [2024-11-13 13:50:25,323][00418] Avg episode rewards: #0: 18.160, true rewards: #0: 8.160 [2024-11-13 13:50:25,325][00418] Avg episode reward: 18.160, avg true_objective: 8.160 [2024-11-13 13:50:25,408][00418] Num frames 1700... [2024-11-13 13:50:25,530][00418] Num frames 1800... [2024-11-13 13:50:25,648][00418] Num frames 1900... [2024-11-13 13:50:25,777][00418] Num frames 2000... [2024-11-13 13:50:25,909][00418] Num frames 2100... [2024-11-13 13:50:26,030][00418] Num frames 2200... [2024-11-13 13:50:26,154][00418] Num frames 2300... [2024-11-13 13:50:26,275][00418] Num frames 2400... [2024-11-13 13:50:26,401][00418] Num frames 2500... [2024-11-13 13:50:26,524][00418] Num frames 2600... [2024-11-13 13:50:26,645][00418] Num frames 2700... [2024-11-13 13:50:26,776][00418] Num frames 2800... [2024-11-13 13:50:26,902][00418] Num frames 2900... [2024-11-13 13:50:27,026][00418] Num frames 3000... [2024-11-13 13:50:27,146][00418] Num frames 3100... [2024-11-13 13:50:27,267][00418] Num frames 3200... [2024-11-13 13:50:27,405][00418] Num frames 3300... [2024-11-13 13:50:27,576][00418] Num frames 3400... [2024-11-13 13:50:27,785][00418] Avg episode rewards: #0: 28.633, true rewards: #0: 11.633 [2024-11-13 13:50:27,787][00418] Avg episode reward: 28.633, avg true_objective: 11.633 [2024-11-13 13:50:27,810][00418] Num frames 3500... [2024-11-13 13:50:27,986][00418] Num frames 3600... [2024-11-13 13:50:28,168][00418] Num frames 3700... [2024-11-13 13:50:28,330][00418] Num frames 3800... [2024-11-13 13:50:28,500][00418] Num frames 3900... [2024-11-13 13:50:28,677][00418] Num frames 4000... [2024-11-13 13:50:28,877][00418] Num frames 4100... [2024-11-13 13:50:29,080][00418] Num frames 4200... [2024-11-13 13:50:29,264][00418] Num frames 4300... [2024-11-13 13:50:29,440][00418] Num frames 4400... [2024-11-13 13:50:29,532][00418] Avg episode rewards: #0: 26.545, true rewards: #0: 11.045 [2024-11-13 13:50:29,534][00418] Avg episode reward: 26.545, avg true_objective: 11.045 [2024-11-13 13:50:29,678][00418] Num frames 4500... [2024-11-13 13:50:29,860][00418] Num frames 4600... [2024-11-13 13:50:29,986][00418] Num frames 4700... [2024-11-13 13:50:30,114][00418] Num frames 4800... [2024-11-13 13:50:30,241][00418] Num frames 4900... [2024-11-13 13:50:30,372][00418] Num frames 5000... [2024-11-13 13:50:30,495][00418] Num frames 5100... [2024-11-13 13:50:30,623][00418] Num frames 5200... [2024-11-13 13:50:30,708][00418] Avg episode rewards: #0: 24.846, true rewards: #0: 10.446 [2024-11-13 13:50:30,710][00418] Avg episode reward: 24.846, avg true_objective: 10.446 [2024-11-13 13:50:30,810][00418] Num frames 5300... [2024-11-13 13:50:30,943][00418] Num frames 5400... [2024-11-13 13:50:31,065][00418] Num frames 5500... [2024-11-13 13:50:31,186][00418] Num frames 5600... [2024-11-13 13:50:31,309][00418] Num frames 5700... [2024-11-13 13:50:31,433][00418] Num frames 5800... [2024-11-13 13:50:31,562][00418] Num frames 5900... [2024-11-13 13:50:31,688][00418] Num frames 6000... [2024-11-13 13:50:31,816][00418] Num frames 6100... [2024-11-13 13:50:31,954][00418] Num frames 6200... [2024-11-13 13:50:32,077][00418] Num frames 6300... [2024-11-13 13:50:32,198][00418] Num frames 6400... [2024-11-13 13:50:32,316][00418] Num frames 6500... [2024-11-13 13:50:32,460][00418] Avg episode rewards: #0: 25.623, true rewards: #0: 10.957 [2024-11-13 13:50:32,461][00418] Avg episode reward: 25.623, avg true_objective: 10.957 [2024-11-13 13:50:32,499][00418] Num frames 6600... [2024-11-13 13:50:32,616][00418] Num frames 6700... [2024-11-13 13:50:32,735][00418] Num frames 6800... [2024-11-13 13:50:32,861][00418] Num frames 6900... [2024-11-13 13:50:32,986][00418] Num frames 7000... [2024-11-13 13:50:33,108][00418] Num frames 7100... [2024-11-13 13:50:33,205][00418] Avg episode rewards: #0: 23.190, true rewards: #0: 10.190 [2024-11-13 13:50:33,206][00418] Avg episode reward: 23.190, avg true_objective: 10.190 [2024-11-13 13:50:33,287][00418] Num frames 7200... [2024-11-13 13:50:33,406][00418] Num frames 7300... [2024-11-13 13:50:33,529][00418] Num frames 7400... [2024-11-13 13:50:33,657][00418] Num frames 7500... [2024-11-13 13:50:33,779][00418] Num frames 7600... [2024-11-13 13:50:33,906][00418] Num frames 7700... [2024-11-13 13:50:34,032][00418] Num frames 7800... [2024-11-13 13:50:34,154][00418] Num frames 7900... [2024-11-13 13:50:34,280][00418] Num frames 8000... [2024-11-13 13:50:34,406][00418] Avg episode rewards: #0: 22.574, true rewards: #0: 10.074 [2024-11-13 13:50:34,408][00418] Avg episode reward: 22.574, avg true_objective: 10.074 [2024-11-13 13:50:34,458][00418] Num frames 8100... [2024-11-13 13:50:34,584][00418] Num frames 8200... [2024-11-13 13:50:34,705][00418] Num frames 8300... [2024-11-13 13:50:34,835][00418] Num frames 8400... [2024-11-13 13:50:34,955][00418] Num frames 8500... [2024-11-13 13:50:35,084][00418] Num frames 8600... [2024-11-13 13:50:35,208][00418] Num frames 8700... [2024-11-13 13:50:35,273][00418] Avg episode rewards: #0: 21.895, true rewards: #0: 9.672 [2024-11-13 13:50:35,274][00418] Avg episode reward: 21.895, avg true_objective: 9.672 [2024-11-13 13:50:35,389][00418] Num frames 8800... [2024-11-13 13:50:35,521][00418] Num frames 8900... [2024-11-13 13:50:35,648][00418] Num frames 9000... [2024-11-13 13:50:35,774][00418] Num frames 9100... [2024-11-13 13:50:35,908][00418] Num frames 9200... [2024-11-13 13:50:36,046][00418] Num frames 9300... [2024-11-13 13:50:36,168][00418] Num frames 9400... [2024-11-13 13:50:36,288][00418] Num frames 9500... [2024-11-13 13:50:36,412][00418] Num frames 9600... [2024-11-13 13:50:36,534][00418] Num frames 9700... [2024-11-13 13:50:36,665][00418] Num frames 9800... [2024-11-13 13:50:36,790][00418] Num frames 9900... [2024-11-13 13:50:36,916][00418] Num frames 10000... [2024-11-13 13:50:37,046][00418] Num frames 10100... [2024-11-13 13:50:37,166][00418] Num frames 10200... [2024-11-13 13:50:37,235][00418] Avg episode rewards: #0: 23.609, true rewards: #0: 10.209 [2024-11-13 13:50:37,236][00418] Avg episode reward: 23.609, avg true_objective: 10.209 [2024-11-13 13:51:39,661][00418] Replay video saved to /content/train_dir/default_experiment/replay.mp4! [2024-11-13 13:51:40,258][00418] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json [2024-11-13 13:51:40,260][00418] Overriding arg 'num_workers' with value 1 passed from command line [2024-11-13 13:51:40,262][00418] Adding new argument 'no_render'=True that is not in the saved config file! [2024-11-13 13:51:40,263][00418] Adding new argument 'save_video'=True that is not in the saved config file! [2024-11-13 13:51:40,265][00418] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file! [2024-11-13 13:51:40,266][00418] Adding new argument 'video_name'=None that is not in the saved config file! [2024-11-13 13:51:40,268][00418] Adding new argument 'max_num_frames'=100000 that is not in the saved config file! [2024-11-13 13:51:40,269][00418] Adding new argument 'max_num_episodes'=10 that is not in the saved config file! [2024-11-13 13:51:40,270][00418] Adding new argument 'push_to_hub'=True that is not in the saved config file! [2024-11-13 13:51:40,271][00418] Adding new argument 'hf_repository'='SD403/rl_course_vizdoom_health_gathering_supreme' that is not in the saved config file! [2024-11-13 13:51:40,272][00418] Adding new argument 'policy_index'=0 that is not in the saved config file! [2024-11-13 13:51:40,273][00418] Adding new argument 'eval_deterministic'=False that is not in the saved config file! [2024-11-13 13:51:40,274][00418] Adding new argument 'train_script'=None that is not in the saved config file! [2024-11-13 13:51:40,275][00418] Adding new argument 'enjoy_script'=None that is not in the saved config file! [2024-11-13 13:51:40,276][00418] Using frameskip 1 and render_action_repeat=4 for evaluation [2024-11-13 13:51:40,314][00418] RunningMeanStd input shape: (3, 72, 128) [2024-11-13 13:51:40,316][00418] RunningMeanStd input shape: (1,) [2024-11-13 13:51:40,335][00418] ConvEncoder: input_channels=3 [2024-11-13 13:51:40,394][00418] Conv encoder output size: 512 [2024-11-13 13:51:40,396][00418] Policy head output size: 512 [2024-11-13 13:51:40,426][00418] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... [2024-11-13 13:51:41,067][00418] Num frames 100... [2024-11-13 13:51:41,226][00418] Num frames 200... [2024-11-13 13:51:41,386][00418] Num frames 300... [2024-11-13 13:51:41,539][00418] Num frames 400... [2024-11-13 13:51:41,714][00418] Num frames 500... [2024-11-13 13:51:41,869][00418] Num frames 600... [2024-11-13 13:51:42,026][00418] Num frames 700... [2024-11-13 13:51:42,178][00418] Num frames 800... [2024-11-13 13:51:42,343][00418] Num frames 900... [2024-11-13 13:51:42,408][00418] Avg episode rewards: #0: 22.040, true rewards: #0: 9.040 [2024-11-13 13:51:42,409][00418] Avg episode reward: 22.040, avg true_objective: 9.040 [2024-11-13 13:51:42,561][00418] Num frames 1000... [2024-11-13 13:51:42,733][00418] Num frames 1100... [2024-11-13 13:51:42,908][00418] Num frames 1200... [2024-11-13 13:51:43,070][00418] Num frames 1300... [2024-11-13 13:51:43,239][00418] Num frames 1400... [2024-11-13 13:51:43,419][00418] Num frames 1500... [2024-11-13 13:51:43,582][00418] Num frames 1600... [2024-11-13 13:51:43,764][00418] Num frames 1700... [2024-11-13 13:51:43,940][00418] Num frames 1800... [2024-11-13 13:51:44,103][00418] Avg episode rewards: #0: 23.215, true rewards: #0: 9.215 [2024-11-13 13:51:44,105][00418] Avg episode reward: 23.215, avg true_objective: 9.215 [2024-11-13 13:51:44,239][00418] Num frames 1900... [2024-11-13 13:51:44,429][00418] Num frames 2000... [2024-11-13 13:51:44,599][00418] Num frames 2100... [2024-11-13 13:51:44,783][00418] Num frames 2200... [2024-11-13 13:51:44,958][00418] Num frames 2300... [2024-11-13 13:51:45,155][00418] Num frames 2400... [2024-11-13 13:51:45,338][00418] Num frames 2500... [2024-11-13 13:51:45,517][00418] Num frames 2600... [2024-11-13 13:51:45,725][00418] Num frames 2700... [2024-11-13 13:51:45,945][00418] Num frames 2800... [2024-11-13 13:51:46,162][00418] Num frames 2900... [2024-11-13 13:51:46,302][00418] Avg episode rewards: #0: 23.807, true rewards: #0: 9.807 [2024-11-13 13:51:46,303][00418] Avg episode reward: 23.807, avg true_objective: 9.807 [2024-11-13 13:51:46,426][00418] Num frames 3000... [2024-11-13 13:51:46,605][00418] Num frames 3100... [2024-11-13 13:51:46,799][00418] Num frames 3200... [2024-11-13 13:51:46,997][00418] Num frames 3300... [2024-11-13 13:51:47,159][00418] Num frames 3400... [2024-11-13 13:51:47,317][00418] Num frames 3500... [2024-11-13 13:51:47,480][00418] Num frames 3600... [2024-11-13 13:51:47,651][00418] Num frames 3700... [2024-11-13 13:51:47,837][00418] Num frames 3800... [2024-11-13 13:51:48,016][00418] Num frames 3900... [2024-11-13 13:51:48,193][00418] Num frames 4000... [2024-11-13 13:51:48,379][00418] Num frames 4100... [2024-11-13 13:51:48,588][00418] Avg episode rewards: #0: 25.225, true rewards: #0: 10.475 [2024-11-13 13:51:48,591][00418] Avg episode reward: 25.225, avg true_objective: 10.475 [2024-11-13 13:51:48,614][00418] Num frames 4200... [2024-11-13 13:51:48,761][00418] Num frames 4300... [2024-11-13 13:51:48,890][00418] Num frames 4400... [2024-11-13 13:51:49,016][00418] Num frames 4500... [2024-11-13 13:51:49,135][00418] Num frames 4600... [2024-11-13 13:51:49,255][00418] Num frames 4700... [2024-11-13 13:51:49,372][00418] Num frames 4800... [2024-11-13 13:51:49,492][00418] Num frames 4900... [2024-11-13 13:51:49,607][00418] Num frames 5000... [2024-11-13 13:51:49,726][00418] Num frames 5100... [2024-11-13 13:51:49,852][00418] Num frames 5200... [2024-11-13 13:51:49,911][00418] Avg episode rewards: #0: 24.602, true rewards: #0: 10.402 [2024-11-13 13:51:49,912][00418] Avg episode reward: 24.602, avg true_objective: 10.402 [2024-11-13 13:51:50,041][00418] Num frames 5300... [2024-11-13 13:51:50,160][00418] Num frames 5400... [2024-11-13 13:51:50,278][00418] Num frames 5500... [2024-11-13 13:51:50,397][00418] Num frames 5600... [2024-11-13 13:51:50,463][00418] Avg episode rewards: #0: 21.513, true rewards: #0: 9.347 [2024-11-13 13:51:50,464][00418] Avg episode reward: 21.513, avg true_objective: 9.347 [2024-11-13 13:51:50,576][00418] Num frames 5700... [2024-11-13 13:51:50,698][00418] Num frames 5800... [2024-11-13 13:51:50,824][00418] Num frames 5900... [2024-11-13 13:51:50,945][00418] Num frames 6000... [2024-11-13 13:51:51,072][00418] Num frames 6100... [2024-11-13 13:51:51,196][00418] Num frames 6200... [2024-11-13 13:51:51,316][00418] Num frames 6300... [2024-11-13 13:51:51,419][00418] Avg episode rewards: #0: 20.913, true rewards: #0: 9.056 [2024-11-13 13:51:51,421][00418] Avg episode reward: 20.913, avg true_objective: 9.056 [2024-11-13 13:51:51,496][00418] Num frames 6400... [2024-11-13 13:51:51,617][00418] Num frames 6500... [2024-11-13 13:51:51,736][00418] Num frames 6600... [2024-11-13 13:51:51,865][00418] Num frames 6700... [2024-11-13 13:51:51,991][00418] Num frames 6800... [2024-11-13 13:51:52,119][00418] Num frames 6900... [2024-11-13 13:51:52,240][00418] Num frames 7000... [2024-11-13 13:51:52,360][00418] Num frames 7100... [2024-11-13 13:51:52,481][00418] Num frames 7200... [2024-11-13 13:51:52,602][00418] Num frames 7300... [2024-11-13 13:51:52,722][00418] Num frames 7400... [2024-11-13 13:51:52,854][00418] Num frames 7500... [2024-11-13 13:51:52,974][00418] Num frames 7600... [2024-11-13 13:51:53,103][00418] Num frames 7700... [2024-11-13 13:51:53,229][00418] Num frames 7800... [2024-11-13 13:51:53,382][00418] Num frames 7900... [2024-11-13 13:51:53,543][00418] Num frames 8000... [2024-11-13 13:51:53,746][00418] Avg episode rewards: #0: 23.374, true rewards: #0: 10.124 [2024-11-13 13:51:53,748][00418] Avg episode reward: 23.374, avg true_objective: 10.124 [2024-11-13 13:51:53,752][00418] Num frames 8100... [2024-11-13 13:51:53,879][00418] Num frames 8200... [2024-11-13 13:51:54,000][00418] Num frames 8300... [2024-11-13 13:51:54,144][00418] Num frames 8400... [2024-11-13 13:51:54,264][00418] Num frames 8500... [2024-11-13 13:51:54,389][00418] Num frames 8600... [2024-11-13 13:51:54,496][00418] Avg episode rewards: #0: 21.825, true rewards: #0: 9.602 [2024-11-13 13:51:54,497][00418] Avg episode reward: 21.825, avg true_objective: 9.602 [2024-11-13 13:51:54,575][00418] Num frames 8700... [2024-11-13 13:51:54,695][00418] Num frames 8800... [2024-11-13 13:51:54,843][00418] Num frames 8900... [2024-11-13 13:51:54,968][00418] Num frames 9000... [2024-11-13 13:51:55,092][00418] Num frames 9100... [2024-11-13 13:51:55,224][00418] Num frames 9200... [2024-11-13 13:51:55,344][00418] Num frames 9300... [2024-11-13 13:51:55,464][00418] Num frames 9400... [2024-11-13 13:51:55,585][00418] Num frames 9500... [2024-11-13 13:51:55,707][00418] Num frames 9600... [2024-11-13 13:51:55,842][00418] Num frames 9700... [2024-11-13 13:51:55,964][00418] Num frames 9800... [2024-11-13 13:51:56,086][00418] Num frames 9900... [2024-11-13 13:51:56,228][00418] Num frames 10000... [2024-11-13 13:51:56,380][00418] Avg episode rewards: #0: 23.182, true rewards: #0: 10.082 [2024-11-13 13:51:56,382][00418] Avg episode reward: 23.182, avg true_objective: 10.082 [2024-11-13 13:52:59,057][00418] Replay video saved to /content/train_dir/default_experiment/replay.mp4! [2024-11-13 13:53:14,919][00418] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json [2024-11-13 13:53:14,921][00418] Overriding arg 'num_workers' with value 1 passed from command line [2024-11-13 13:53:14,922][00418] Adding new argument 'no_render'=True that is not in the saved config file! [2024-11-13 13:53:14,924][00418] Adding new argument 'save_video'=True that is not in the saved config file! [2024-11-13 13:53:14,926][00418] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file! [2024-11-13 13:53:14,928][00418] Adding new argument 'video_name'=None that is not in the saved config file! [2024-11-13 13:53:14,929][00418] Adding new argument 'max_num_frames'=100000 that is not in the saved config file! [2024-11-13 13:53:14,930][00418] Adding new argument 'max_num_episodes'=10 that is not in the saved config file! [2024-11-13 13:53:14,933][00418] Adding new argument 'push_to_hub'=True that is not in the saved config file! [2024-11-13 13:53:14,934][00418] Adding new argument 'hf_repository'='SD403/rl_course_vizdoom_health_gathering_supreme' that is not in the saved config file! [2024-11-13 13:53:14,936][00418] Adding new argument 'policy_index'=0 that is not in the saved config file! [2024-11-13 13:53:14,937][00418] Adding new argument 'eval_deterministic'=False that is not in the saved config file! [2024-11-13 13:53:14,939][00418] Adding new argument 'train_script'=None that is not in the saved config file! [2024-11-13 13:53:14,940][00418] Adding new argument 'enjoy_script'=None that is not in the saved config file! [2024-11-13 13:53:14,941][00418] Using frameskip 1 and render_action_repeat=4 for evaluation [2024-11-13 13:53:14,973][00418] RunningMeanStd input shape: (3, 72, 128) [2024-11-13 13:53:14,975][00418] RunningMeanStd input shape: (1,) [2024-11-13 13:53:14,990][00418] ConvEncoder: input_channels=3 [2024-11-13 13:53:15,028][00418] Conv encoder output size: 512 [2024-11-13 13:53:15,029][00418] Policy head output size: 512 [2024-11-13 13:53:15,048][00418] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... [2024-11-13 13:53:15,460][00418] Num frames 100... [2024-11-13 13:53:15,603][00418] Num frames 200... [2024-11-13 13:53:15,777][00418] Num frames 300... [2024-11-13 13:53:15,981][00418] Num frames 400... [2024-11-13 13:53:16,154][00418] Num frames 500... [2024-11-13 13:53:16,318][00418] Num frames 600... [2024-11-13 13:53:16,489][00418] Num frames 700... [2024-11-13 13:53:16,651][00418] Num frames 800... [2024-11-13 13:53:16,820][00418] Num frames 900... [2024-11-13 13:53:17,001][00418] Num frames 1000... [2024-11-13 13:53:17,180][00418] Num frames 1100... [2024-11-13 13:53:17,360][00418] Num frames 1200... [2024-11-13 13:53:17,548][00418] Num frames 1300... [2024-11-13 13:53:17,731][00418] Num frames 1400... [2024-11-13 13:53:17,909][00418] Num frames 1500... [2024-11-13 13:53:18,101][00418] Num frames 1600... [2024-11-13 13:53:18,230][00418] Num frames 1700... [2024-11-13 13:53:18,354][00418] Num frames 1800... [2024-11-13 13:53:18,478][00418] Num frames 1900... [2024-11-13 13:53:18,607][00418] Num frames 2000... [2024-11-13 13:53:18,733][00418] Num frames 2100... [2024-11-13 13:53:18,786][00418] Avg episode rewards: #0: 59.999, true rewards: #0: 21.000 [2024-11-13 13:53:18,788][00418] Avg episode reward: 59.999, avg true_objective: 21.000 [2024-11-13 13:53:18,916][00418] Num frames 2200... [2024-11-13 13:53:19,035][00418] Num frames 2300... [2024-11-13 13:53:19,163][00418] Num frames 2400... [2024-11-13 13:53:19,288][00418] Num frames 2500... [2024-11-13 13:53:19,411][00418] Num frames 2600... [2024-11-13 13:53:19,531][00418] Num frames 2700... [2024-11-13 13:53:19,653][00418] Num frames 2800... [2024-11-13 13:53:19,752][00418] Avg episode rewards: #0: 36.679, true rewards: #0: 14.180 [2024-11-13 13:53:19,754][00418] Avg episode reward: 36.679, avg true_objective: 14.180 [2024-11-13 13:53:19,840][00418] Num frames 2900... [2024-11-13 13:53:19,961][00418] Num frames 3000... [2024-11-13 13:53:20,095][00418] Num frames 3100... [2024-11-13 13:53:20,214][00418] Num frames 3200... [2024-11-13 13:53:20,337][00418] Num frames 3300... [2024-11-13 13:53:20,460][00418] Num frames 3400... [2024-11-13 13:53:20,581][00418] Num frames 3500... [2024-11-13 13:53:20,711][00418] Num frames 3600... [2024-11-13 13:53:20,842][00418] Num frames 3700... [2024-11-13 13:53:20,968][00418] Num frames 3800... [2024-11-13 13:53:21,090][00418] Num frames 3900... [2024-11-13 13:53:21,226][00418] Num frames 4000... [2024-11-13 13:53:21,346][00418] Num frames 4100... [2024-11-13 13:53:21,471][00418] Num frames 4200... [2024-11-13 13:53:21,596][00418] Num frames 4300... [2024-11-13 13:53:21,721][00418] Num frames 4400... [2024-11-13 13:53:21,859][00418] Num frames 4500... [2024-11-13 13:53:21,999][00418] Num frames 4600... [2024-11-13 13:53:22,128][00418] Num frames 4700... [2024-11-13 13:53:22,259][00418] Num frames 4800... [2024-11-13 13:53:22,386][00418] Avg episode rewards: #0: 44.193, true rewards: #0: 16.193 [2024-11-13 13:53:22,387][00418] Avg episode reward: 44.193, avg true_objective: 16.193 [2024-11-13 13:53:22,444][00418] Num frames 4900... [2024-11-13 13:53:22,562][00418] Num frames 5000... [2024-11-13 13:53:22,684][00418] Num frames 5100... [2024-11-13 13:53:22,743][00418] Avg episode rewards: #0: 34.002, true rewards: #0: 12.753 [2024-11-13 13:53:22,745][00418] Avg episode reward: 34.002, avg true_objective: 12.753 [2024-11-13 13:53:22,872][00418] Num frames 5200... [2024-11-13 13:53:22,997][00418] Num frames 5300... [2024-11-13 13:53:23,123][00418] Num frames 5400... [2024-11-13 13:53:23,253][00418] Num frames 5500... [2024-11-13 13:53:23,376][00418] Num frames 5600... [2024-11-13 13:53:23,498][00418] Num frames 5700... [2024-11-13 13:53:23,624][00418] Num frames 5800... [2024-11-13 13:53:23,747][00418] Num frames 5900... [2024-11-13 13:53:23,876][00418] Num frames 6000... [2024-11-13 13:53:23,996][00418] Num frames 6100... [2024-11-13 13:53:24,117][00418] Num frames 6200... [2024-11-13 13:53:24,248][00418] Num frames 6300... [2024-11-13 13:53:24,371][00418] Num frames 6400... [2024-11-13 13:53:24,494][00418] Num frames 6500... [2024-11-13 13:53:24,619][00418] Num frames 6600... [2024-11-13 13:53:24,721][00418] Avg episode rewards: #0: 34.673, true rewards: #0: 13.274 [2024-11-13 13:53:24,722][00418] Avg episode reward: 34.673, avg true_objective: 13.274 [2024-11-13 13:53:24,805][00418] Num frames 6700... [2024-11-13 13:53:24,927][00418] Num frames 6800... [2024-11-13 13:53:25,057][00418] Num frames 6900... [2024-11-13 13:53:25,178][00418] Num frames 7000... [2024-11-13 13:53:25,310][00418] Num frames 7100... [2024-11-13 13:53:25,434][00418] Num frames 7200... [2024-11-13 13:53:25,552][00418] Num frames 7300... [2024-11-13 13:53:25,672][00418] Num frames 7400... [2024-11-13 13:53:25,802][00418] Num frames 7500... [2024-11-13 13:53:25,923][00418] Num frames 7600... [2024-11-13 13:53:26,043][00418] Num frames 7700... [2024-11-13 13:53:26,166][00418] Num frames 7800... [2024-11-13 13:53:26,294][00418] Num frames 7900... [2024-11-13 13:53:26,422][00418] Num frames 8000... [2024-11-13 13:53:26,545][00418] Num frames 8100... [2024-11-13 13:53:26,673][00418] Num frames 8200... [2024-11-13 13:53:26,797][00418] Num frames 8300... [2024-11-13 13:53:26,920][00418] Num frames 8400... [2024-11-13 13:53:27,044][00418] Num frames 8500... [2024-11-13 13:53:27,168][00418] Num frames 8600... [2024-11-13 13:53:27,296][00418] Num frames 8700... [2024-11-13 13:53:27,397][00418] Avg episode rewards: #0: 39.561, true rewards: #0: 14.562 [2024-11-13 13:53:27,398][00418] Avg episode reward: 39.561, avg true_objective: 14.562 [2024-11-13 13:53:27,483][00418] Num frames 8800... [2024-11-13 13:53:27,603][00418] Num frames 8900... [2024-11-13 13:53:27,724][00418] Num frames 9000... [2024-11-13 13:53:27,861][00418] Num frames 9100... [2024-11-13 13:53:27,981][00418] Num frames 9200... [2024-11-13 13:53:28,114][00418] Num frames 9300... [2024-11-13 13:53:28,294][00418] Num frames 9400... [2024-11-13 13:53:28,466][00418] Num frames 9500... [2024-11-13 13:53:28,628][00418] Num frames 9600... [2024-11-13 13:53:28,803][00418] Num frames 9700... [2024-11-13 13:53:28,966][00418] Num frames 9800... [2024-11-13 13:53:29,131][00418] Num frames 9900... [2024-11-13 13:53:29,291][00418] Num frames 10000... [2024-11-13 13:53:29,468][00418] Num frames 10100... [2024-11-13 13:53:29,603][00418] Avg episode rewards: #0: 38.778, true rewards: #0: 14.493 [2024-11-13 13:53:29,605][00418] Avg episode reward: 38.778, avg true_objective: 14.493 [2024-11-13 13:53:29,704][00418] Num frames 10200... [2024-11-13 13:53:29,890][00418] Num frames 10300... [2024-11-13 13:53:30,065][00418] Num frames 10400... [2024-11-13 13:53:30,240][00418] Num frames 10500... [2024-11-13 13:53:30,411][00418] Avg episode rewards: #0: 34.701, true rewards: #0: 13.201 [2024-11-13 13:53:30,413][00418] Avg episode reward: 34.701, avg true_objective: 13.201 [2024-11-13 13:53:30,486][00418] Num frames 10600... [2024-11-13 13:53:30,635][00418] Num frames 10700... [2024-11-13 13:53:30,763][00418] Num frames 10800... [2024-11-13 13:53:30,891][00418] Num frames 10900... [2024-11-13 13:53:31,012][00418] Num frames 11000... [2024-11-13 13:53:31,131][00418] Num frames 11100... [2024-11-13 13:53:31,254][00418] Num frames 11200... [2024-11-13 13:53:31,369][00418] Num frames 11300... [2024-11-13 13:53:31,500][00418] Num frames 11400... [2024-11-13 13:53:31,620][00418] Num frames 11500... [2024-11-13 13:53:31,742][00418] Num frames 11600... [2024-11-13 13:53:31,871][00418] Num frames 11700... [2024-11-13 13:53:31,992][00418] Num frames 11800... [2024-11-13 13:53:32,118][00418] Num frames 11900... [2024-11-13 13:53:32,241][00418] Num frames 12000... [2024-11-13 13:53:32,326][00418] Avg episode rewards: #0: 34.915, true rewards: #0: 13.360 [2024-11-13 13:53:32,327][00418] Avg episode reward: 34.915, avg true_objective: 13.360 [2024-11-13 13:53:32,438][00418] Num frames 12100... [2024-11-13 13:53:32,562][00418] Num frames 12200... [2024-11-13 13:53:32,689][00418] Num frames 12300... [2024-11-13 13:53:32,818][00418] Num frames 12400... [2024-11-13 13:53:32,939][00418] Num frames 12500... [2024-11-13 13:53:33,060][00418] Num frames 12600... [2024-11-13 13:53:33,184][00418] Num frames 12700... [2024-11-13 13:53:33,303][00418] Num frames 12800... [2024-11-13 13:53:33,431][00418] Num frames 12900... [2024-11-13 13:53:33,563][00418] Num frames 13000... [2024-11-13 13:53:33,685][00418] Num frames 13100... [2024-11-13 13:53:33,814][00418] Num frames 13200... [2024-11-13 13:53:33,937][00418] Num frames 13300... [2024-11-13 13:53:34,060][00418] Num frames 13400... [2024-11-13 13:53:34,184][00418] Num frames 13500... [2024-11-13 13:53:34,304][00418] Num frames 13600... [2024-11-13 13:53:34,429][00418] Num frames 13700... [2024-11-13 13:53:34,557][00418] Num frames 13800... [2024-11-13 13:53:34,680][00418] Num frames 13900... [2024-11-13 13:53:34,810][00418] Num frames 14000... [2024-11-13 13:53:34,933][00418] Num frames 14100... [2024-11-13 13:53:35,018][00418] Avg episode rewards: #0: 37.223, true rewards: #0: 14.124 [2024-11-13 13:53:35,019][00418] Avg episode reward: 37.223, avg true_objective: 14.124 [2024-11-13 13:54:58,949][00418] Replay video saved to /content/train_dir/default_experiment/replay.mp4!