diff --git "a/sf_log.txt" "b/sf_log.txt" --- "a/sf_log.txt" +++ "b/sf_log.txt" @@ -1,50 +1,60 @@ -[2024-09-21 00:11:24,342][01870] Saving configuration to /content/train_dir/default_experiment/config.json... -[2024-09-21 00:11:24,346][01870] Rollout worker 0 uses device cpu -[2024-09-21 00:11:24,347][01870] Rollout worker 1 uses device cpu -[2024-09-21 00:11:24,349][01870] Rollout worker 2 uses device cpu -[2024-09-21 00:11:24,353][01870] Rollout worker 3 uses device cpu -[2024-09-21 00:11:24,354][01870] Rollout worker 4 uses device cpu -[2024-09-21 00:11:24,356][01870] Rollout worker 5 uses device cpu -[2024-09-21 00:11:24,358][01870] Rollout worker 6 uses device cpu -[2024-09-21 00:11:24,359][01870] Rollout worker 7 uses device cpu -[2024-09-21 00:11:24,526][01870] Using GPUs [0] for process 0 (actually maps to GPUs [0]) -[2024-09-21 00:11:24,527][01870] InferenceWorker_p0-w0: min num requests: 2 -[2024-09-21 00:11:24,562][01870] Starting all processes... -[2024-09-21 00:11:24,563][01870] Starting process learner_proc0 -[2024-09-21 00:11:25,322][01870] Starting all processes... -[2024-09-21 00:11:25,330][01870] Starting process inference_proc0-0 -[2024-09-21 00:11:25,331][01870] Starting process rollout_proc0 -[2024-09-21 00:11:25,334][01870] Starting process rollout_proc1 -[2024-09-21 00:11:25,334][01870] Starting process rollout_proc2 -[2024-09-21 00:11:25,334][01870] Starting process rollout_proc3 -[2024-09-21 00:11:25,334][01870] Starting process rollout_proc4 -[2024-09-21 00:11:25,334][01870] Starting process rollout_proc5 -[2024-09-21 00:11:25,334][01870] Starting process rollout_proc6 -[2024-09-21 00:11:25,334][01870] Starting process rollout_proc7 -[2024-09-21 00:11:42,137][04656] Using GPUs [0] for process 0 (actually maps to GPUs [0]) -[2024-09-21 00:11:42,139][04656] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0 -[2024-09-21 00:11:42,233][04656] Num visible devices: 1 -[2024-09-21 00:11:42,417][04657] Worker 0 uses CPU cores [0] -[2024-09-21 00:11:42,593][04658] Worker 2 uses CPU cores [0] -[2024-09-21 00:11:42,609][04659] Worker 4 uses CPU cores [0] -[2024-09-21 00:11:42,610][04662] Worker 5 uses CPU cores [1] -[2024-09-21 00:11:42,694][04664] Worker 7 uses CPU cores [1] -[2024-09-21 00:11:42,699][04643] Using GPUs [0] for process 0 (actually maps to GPUs [0]) -[2024-09-21 00:11:42,700][04643] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0 -[2024-09-21 00:11:42,706][04663] Worker 6 uses CPU cores [0] -[2024-09-21 00:11:42,718][04661] Worker 3 uses CPU cores [1] -[2024-09-21 00:11:42,730][04643] Num visible devices: 1 -[2024-09-21 00:11:42,745][04643] Starting seed is not provided -[2024-09-21 00:11:42,746][04643] Using GPUs [0] for process 0 (actually maps to GPUs [0]) -[2024-09-21 00:11:42,746][04643] Initializing actor-critic model on device cuda:0 -[2024-09-21 00:11:42,747][04643] RunningMeanStd input shape: (3, 72, 128) -[2024-09-21 00:11:42,751][04643] RunningMeanStd input shape: (1,) -[2024-09-21 00:11:42,764][04660] Worker 1 uses CPU cores [1] -[2024-09-21 00:11:42,771][04643] ConvEncoder: input_channels=3 -[2024-09-21 00:11:43,053][04643] Conv encoder output size: 512 -[2024-09-21 00:11:43,053][04643] Policy head output size: 512 -[2024-09-21 00:11:43,115][04643] Created Actor Critic model with architecture: -[2024-09-21 00:11:43,116][04643] ActorCriticSharedWeights( +[2024-09-21 02:04:11,191][00440] Saving configuration to /content/train_dir/default_experiment/config.json... +[2024-09-21 02:04:11,195][00440] Rollout worker 0 uses device cpu +[2024-09-21 02:04:11,199][00440] Rollout worker 1 uses device cpu +[2024-09-21 02:04:11,200][00440] Rollout worker 2 uses device cpu +[2024-09-21 02:04:11,202][00440] Rollout worker 3 uses device cpu +[2024-09-21 02:04:11,204][00440] Rollout worker 4 uses device cpu +[2024-09-21 02:04:11,205][00440] Rollout worker 5 uses device cpu +[2024-09-21 02:04:11,210][00440] Rollout worker 6 uses device cpu +[2024-09-21 02:04:11,211][00440] Rollout worker 7 uses device cpu +[2024-09-21 02:04:11,375][00440] Using GPUs [0] for process 0 (actually maps to GPUs [0]) +[2024-09-21 02:04:11,377][00440] InferenceWorker_p0-w0: min num requests: 2 +[2024-09-21 02:04:11,412][00440] Starting all processes... +[2024-09-21 02:04:11,413][00440] Starting process learner_proc0 +[2024-09-21 02:04:12,258][00440] Starting all processes... +[2024-09-21 02:04:12,290][00440] Starting process inference_proc0-0 +[2024-09-21 02:04:12,292][00440] Starting process rollout_proc0 +[2024-09-21 02:04:12,292][00440] Starting process rollout_proc1 +[2024-09-21 02:04:12,292][00440] Starting process rollout_proc2 +[2024-09-21 02:04:12,292][00440] Starting process rollout_proc3 +[2024-09-21 02:04:12,292][00440] Starting process rollout_proc4 +[2024-09-21 02:04:12,292][00440] Starting process rollout_proc5 +[2024-09-21 02:04:12,292][00440] Starting process rollout_proc6 +[2024-09-21 02:04:12,292][00440] Starting process rollout_proc7 +[2024-09-21 02:04:31,631][02550] Worker 5 uses CPU cores [1] +[2024-09-21 02:04:31,795][00440] Heartbeat connected on RolloutWorker_w5 +[2024-09-21 02:04:32,139][02531] Using GPUs [0] for process 0 (actually maps to GPUs [0]) +[2024-09-21 02:04:32,140][02531] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0 +[2024-09-21 02:04:32,215][02531] Num visible devices: 1 +[2024-09-21 02:04:32,255][00440] Heartbeat connected on Batcher_0 +[2024-09-21 02:04:32,256][02531] Starting seed is not provided +[2024-09-21 02:04:32,259][02531] Using GPUs [0] for process 0 (actually maps to GPUs [0]) +[2024-09-21 02:04:32,259][02531] Initializing actor-critic model on device cuda:0 +[2024-09-21 02:04:32,261][02531] RunningMeanStd input shape: (3, 72, 128) +[2024-09-21 02:04:32,266][02531] RunningMeanStd input shape: (1,) +[2024-09-21 02:04:32,398][02549] Worker 4 uses CPU cores [0] +[2024-09-21 02:04:32,417][02531] ConvEncoder: input_channels=3 +[2024-09-21 02:04:32,488][02547] Worker 2 uses CPU cores [0] +[2024-09-21 02:04:32,505][00440] Heartbeat connected on RolloutWorker_w4 +[2024-09-21 02:04:32,588][00440] Heartbeat connected on RolloutWorker_w2 +[2024-09-21 02:04:32,677][02552] Worker 7 uses CPU cores [1] +[2024-09-21 02:04:32,757][02544] Using GPUs [0] for process 0 (actually maps to GPUs [0]) +[2024-09-21 02:04:32,760][02544] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0 +[2024-09-21 02:04:32,764][00440] Heartbeat connected on RolloutWorker_w7 +[2024-09-21 02:04:32,798][02545] Worker 0 uses CPU cores [0] +[2024-09-21 02:04:32,862][02548] Worker 3 uses CPU cores [1] +[2024-09-21 02:04:32,875][02551] Worker 6 uses CPU cores [0] +[2024-09-21 02:04:32,893][02544] Num visible devices: 1 +[2024-09-21 02:04:32,904][00440] Heartbeat connected on RolloutWorker_w3 +[2024-09-21 02:04:32,909][00440] Heartbeat connected on RolloutWorker_w0 +[2024-09-21 02:04:32,922][00440] Heartbeat connected on InferenceWorker_p0-w0 +[2024-09-21 02:04:32,965][00440] Heartbeat connected on RolloutWorker_w6 +[2024-09-21 02:04:32,972][02546] Worker 1 uses CPU cores [1] +[2024-09-21 02:04:33,013][00440] Heartbeat connected on RolloutWorker_w1 +[2024-09-21 02:04:33,044][02531] Conv encoder output size: 512 +[2024-09-21 02:04:33,045][02531] Policy head output size: 512 +[2024-09-21 02:04:33,156][02531] Created Actor Critic model with architecture: +[2024-09-21 02:04:33,157][02531] ActorCriticSharedWeights( (obs_normalizer): ObservationNormalizer( (running_mean_std): RunningMeanStdDictInPlace( (running_mean_std): ModuleDict( @@ -85,1131 +95,1051 @@ (distribution_linear): Linear(in_features=512, out_features=5, bias=True) ) ) -[2024-09-21 00:11:43,419][04643] Using optimizer -[2024-09-21 00:11:44,142][04643] No checkpoints found -[2024-09-21 00:11:44,142][04643] Did not load from checkpoint, starting from scratch! -[2024-09-21 00:11:44,143][04643] Initialized policy 0 weights for model version 0 -[2024-09-21 00:11:44,148][04643] Using GPUs [0] for process 0 (actually maps to GPUs [0]) -[2024-09-21 00:11:44,155][04643] LearnerWorker_p0 finished initialization! -[2024-09-21 00:11:44,245][04656] RunningMeanStd input shape: (3, 72, 128) -[2024-09-21 00:11:44,246][04656] RunningMeanStd input shape: (1,) -[2024-09-21 00:11:44,260][04656] ConvEncoder: input_channels=3 -[2024-09-21 00:11:44,372][04656] Conv encoder output size: 512 -[2024-09-21 00:11:44,373][04656] Policy head output size: 512 -[2024-09-21 00:11:44,427][01870] Inference worker 0-0 is ready! -[2024-09-21 00:11:44,428][01870] All inference workers are ready! Signal rollout workers to start! -[2024-09-21 00:11:44,518][01870] Heartbeat connected on Batcher_0 -[2024-09-21 00:11:44,521][01870] Heartbeat connected on LearnerWorker_p0 -[2024-09-21 00:11:44,562][01870] Heartbeat connected on InferenceWorker_p0-w0 -[2024-09-21 00:11:44,655][04658] Doom resolution: 160x120, resize resolution: (128, 72) -[2024-09-21 00:11:44,659][04663] Doom resolution: 160x120, resize resolution: (128, 72) -[2024-09-21 00:11:44,661][04664] Doom resolution: 160x120, resize resolution: (128, 72) -[2024-09-21 00:11:44,653][04659] Doom resolution: 160x120, resize resolution: (128, 72) -[2024-09-21 00:11:44,663][04661] Doom resolution: 160x120, resize resolution: (128, 72) -[2024-09-21 00:11:44,658][04657] Doom resolution: 160x120, resize resolution: (128, 72) -[2024-09-21 00:11:44,664][04660] Doom resolution: 160x120, resize resolution: (128, 72) -[2024-09-21 00:11:44,666][04662] Doom resolution: 160x120, resize resolution: (128, 72) -[2024-09-21 00:11:45,919][04657] Decorrelating experience for 0 frames... -[2024-09-21 00:11:45,921][04663] Decorrelating experience for 0 frames... -[2024-09-21 00:11:45,921][04658] Decorrelating experience for 0 frames... -[2024-09-21 00:11:45,923][04659] Decorrelating experience for 0 frames... -[2024-09-21 00:11:47,128][04662] Decorrelating experience for 0 frames... -[2024-09-21 00:11:47,133][04660] Decorrelating experience for 0 frames... -[2024-09-21 00:11:47,137][04659] Decorrelating experience for 32 frames... -[2024-09-21 00:11:47,141][04661] Decorrelating experience for 0 frames... -[2024-09-21 00:11:47,144][04663] Decorrelating experience for 32 frames... -[2024-09-21 00:11:47,148][04657] Decorrelating experience for 32 frames... -[2024-09-21 00:11:48,146][01870] 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) -[2024-09-21 00:11:48,348][04658] Decorrelating experience for 32 frames... -[2024-09-21 00:11:48,511][04662] Decorrelating experience for 32 frames... -[2024-09-21 00:11:48,554][04661] Decorrelating experience for 32 frames... -[2024-09-21 00:11:48,552][04664] Decorrelating experience for 0 frames... -[2024-09-21 00:11:48,746][04659] Decorrelating experience for 64 frames... -[2024-09-21 00:11:49,938][04664] Decorrelating experience for 32 frames... -[2024-09-21 00:11:50,420][04662] Decorrelating experience for 64 frames... -[2024-09-21 00:11:50,664][04663] Decorrelating experience for 64 frames... -[2024-09-21 00:11:50,778][04657] Decorrelating experience for 64 frames... -[2024-09-21 00:11:50,999][04658] Decorrelating experience for 64 frames... -[2024-09-21 00:11:52,032][04661] Decorrelating experience for 64 frames... -[2024-09-21 00:11:52,517][04664] Decorrelating experience for 64 frames... -[2024-09-21 00:11:52,725][04662] Decorrelating experience for 96 frames... -[2024-09-21 00:11:52,837][04660] Decorrelating experience for 32 frames... -[2024-09-21 00:11:53,145][01870] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 0.0. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) -[2024-09-21 00:11:53,275][01870] Heartbeat connected on RolloutWorker_w5 -[2024-09-21 00:11:53,772][04659] Decorrelating experience for 96 frames... -[2024-09-21 00:11:53,852][04663] Decorrelating experience for 96 frames... -[2024-09-21 00:11:54,091][04657] Decorrelating experience for 96 frames... -[2024-09-21 00:11:54,399][01870] Heartbeat connected on RolloutWorker_w4 -[2024-09-21 00:11:54,492][01870] Heartbeat connected on RolloutWorker_w6 -[2024-09-21 00:11:54,495][04658] Decorrelating experience for 96 frames... -[2024-09-21 00:11:54,674][04661] Decorrelating experience for 96 frames... -[2024-09-21 00:11:54,741][01870] Heartbeat connected on RolloutWorker_w0 -[2024-09-21 00:11:55,067][01870] Heartbeat connected on RolloutWorker_w2 -[2024-09-21 00:11:55,091][01870] Heartbeat connected on RolloutWorker_w3 -[2024-09-21 00:11:55,299][04664] Decorrelating experience for 96 frames... -[2024-09-21 00:11:55,555][01870] Heartbeat connected on RolloutWorker_w7 -[2024-09-21 00:11:55,720][04660] Decorrelating experience for 64 frames... -[2024-09-21 00:11:57,945][04660] Decorrelating experience for 96 frames... -[2024-09-21 00:11:58,143][01870] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 19.6. Samples: 196. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) -[2024-09-21 00:11:58,145][01870] Avg episode reward: [(0, '1.472')] -[2024-09-21 00:11:58,293][01870] Heartbeat connected on RolloutWorker_w1 -[2024-09-21 00:12:00,212][04643] Signal inference workers to stop experience collection... -[2024-09-21 00:12:00,237][04656] InferenceWorker_p0-w0: stopping experience collection -[2024-09-21 00:12:03,143][01870] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 181.9. Samples: 2728. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) -[2024-09-21 00:12:03,146][01870] Avg episode reward: [(0, '2.315')] -[2024-09-21 00:12:03,450][04643] Signal inference workers to resume experience collection... -[2024-09-21 00:12:03,453][04656] InferenceWorker_p0-w0: resuming experience collection -[2024-09-21 00:12:08,143][01870] Fps is (10 sec: 2048.0, 60 sec: 1024.1, 300 sec: 1024.1). Total num frames: 20480. Throughput: 0: 219.5. Samples: 4390. Policy #0 lag: (min: 0.0, avg: 0.9, max: 3.0) -[2024-09-21 00:12:08,145][01870] Avg episode reward: [(0, '3.729')] -[2024-09-21 00:12:13,143][01870] Fps is (10 sec: 3276.9, 60 sec: 1310.8, 300 sec: 1310.8). Total num frames: 32768. Throughput: 0: 329.9. Samples: 8246. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) -[2024-09-21 00:12:13,146][01870] Avg episode reward: [(0, '3.958')] -[2024-09-21 00:12:15,246][04656] Updated weights for policy 0, policy_version 10 (0.0169) -[2024-09-21 00:12:18,143][01870] Fps is (10 sec: 3276.8, 60 sec: 1775.1, 300 sec: 1775.1). Total num frames: 53248. Throughput: 0: 441.8. Samples: 13252. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) -[2024-09-21 00:12:18,146][01870] Avg episode reward: [(0, '4.351')] -[2024-09-21 00:12:23,143][01870] Fps is (10 sec: 3276.8, 60 sec: 1872.6, 300 sec: 1872.6). Total num frames: 65536. Throughput: 0: 463.7. Samples: 16228. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) -[2024-09-21 00:12:23,146][01870] Avg episode reward: [(0, '4.458')] -[2024-09-21 00:12:28,143][01870] Fps is (10 sec: 2457.6, 60 sec: 1945.7, 300 sec: 1945.7). Total num frames: 77824. Throughput: 0: 490.0. Samples: 19600. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) -[2024-09-21 00:12:28,150][01870] Avg episode reward: [(0, '4.475')] -[2024-09-21 00:12:29,727][04656] Updated weights for policy 0, policy_version 20 (0.0052) -[2024-09-21 00:12:33,146][01870] Fps is (10 sec: 2456.9, 60 sec: 2002.5, 300 sec: 2002.5). Total num frames: 90112. Throughput: 0: 505.1. Samples: 22732. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) -[2024-09-21 00:12:33,149][01870] Avg episode reward: [(0, '4.604')] -[2024-09-21 00:12:38,143][01870] Fps is (10 sec: 2867.2, 60 sec: 2130.0, 300 sec: 2130.0). Total num frames: 106496. Throughput: 0: 555.7. Samples: 25008. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) -[2024-09-21 00:12:38,151][01870] Avg episode reward: [(0, '4.520')] -[2024-09-21 00:12:38,161][04643] Saving new best policy, reward=4.520! -[2024-09-21 00:12:41,835][04656] Updated weights for policy 0, policy_version 30 (0.0030) -[2024-09-21 00:12:43,143][01870] Fps is (10 sec: 3687.5, 60 sec: 2308.7, 300 sec: 2308.7). Total num frames: 126976. Throughput: 0: 683.5. Samples: 30952. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) -[2024-09-21 00:12:43,150][01870] Avg episode reward: [(0, '4.507')] -[2024-09-21 00:12:48,143][01870] Fps is (10 sec: 3276.8, 60 sec: 2321.2, 300 sec: 2321.2). Total num frames: 139264. Throughput: 0: 732.7. Samples: 35700. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) -[2024-09-21 00:12:48,148][01870] Avg episode reward: [(0, '4.479')] -[2024-09-21 00:12:53,143][01870] Fps is (10 sec: 2867.2, 60 sec: 2594.2, 300 sec: 2394.7). Total num frames: 155648. Throughput: 0: 735.1. Samples: 37470. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) -[2024-09-21 00:12:53,147][01870] Avg episode reward: [(0, '4.363')] -[2024-09-21 00:12:55,382][04656] Updated weights for policy 0, policy_version 40 (0.0048) -[2024-09-21 00:12:58,143][01870] Fps is (10 sec: 3276.8, 60 sec: 2867.2, 300 sec: 2457.7). Total num frames: 172032. Throughput: 0: 767.6. Samples: 42786. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) -[2024-09-21 00:12:58,146][01870] Avg episode reward: [(0, '4.452')] -[2024-09-21 00:13:03,143][01870] Fps is (10 sec: 3686.4, 60 sec: 3208.5, 300 sec: 2566.9). Total num frames: 192512. Throughput: 0: 784.7. Samples: 48564. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) -[2024-09-21 00:13:03,146][01870] Avg episode reward: [(0, '4.423')] -[2024-09-21 00:13:07,816][04656] Updated weights for policy 0, policy_version 50 (0.0030) -[2024-09-21 00:13:08,147][01870] Fps is (10 sec: 3275.5, 60 sec: 3071.8, 300 sec: 2559.9). Total num frames: 204800. Throughput: 0: 757.5. Samples: 50320. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) -[2024-09-21 00:13:08,150][01870] Avg episode reward: [(0, '4.525')] -[2024-09-21 00:13:08,168][04643] Saving new best policy, reward=4.525! -[2024-09-21 00:13:13,144][01870] Fps is (10 sec: 2867.1, 60 sec: 3140.3, 300 sec: 2602.2). Total num frames: 221184. Throughput: 0: 775.8. Samples: 54510. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) -[2024-09-21 00:13:13,148][01870] Avg episode reward: [(0, '4.614')] -[2024-09-21 00:13:13,150][04643] Saving new best policy, reward=4.614! -[2024-09-21 00:13:18,143][01870] Fps is (10 sec: 3687.9, 60 sec: 3140.3, 300 sec: 2685.2). Total num frames: 241664. Throughput: 0: 836.8. Samples: 60386. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) -[2024-09-21 00:13:18,148][01870] Avg episode reward: [(0, '4.511')] -[2024-09-21 00:13:18,159][04643] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000059_241664.pth... -[2024-09-21 00:13:19,339][04656] Updated weights for policy 0, policy_version 60 (0.0030) -[2024-09-21 00:13:23,143][01870] Fps is (10 sec: 3276.9, 60 sec: 3140.3, 300 sec: 2673.2). Total num frames: 253952. Throughput: 0: 843.1. Samples: 62946. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) -[2024-09-21 00:13:23,151][01870] Avg episode reward: [(0, '4.284')] -[2024-09-21 00:13:28,143][01870] Fps is (10 sec: 2457.6, 60 sec: 3140.3, 300 sec: 2662.5). Total num frames: 266240. Throughput: 0: 789.8. Samples: 66492. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) -[2024-09-21 00:13:28,145][01870] Avg episode reward: [(0, '4.371')] -[2024-09-21 00:13:32,763][04656] Updated weights for policy 0, policy_version 70 (0.0060) -[2024-09-21 00:13:33,143][01870] Fps is (10 sec: 3276.8, 60 sec: 3277.0, 300 sec: 2730.7). Total num frames: 286720. Throughput: 0: 802.3. Samples: 71804. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) -[2024-09-21 00:13:33,146][01870] Avg episode reward: [(0, '4.439')] -[2024-09-21 00:13:38,148][01870] Fps is (10 sec: 3684.6, 60 sec: 3276.5, 300 sec: 2755.4). Total num frames: 303104. Throughput: 0: 829.2. Samples: 74788. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) -[2024-09-21 00:13:38,156][01870] Avg episode reward: [(0, '4.551')] -[2024-09-21 00:13:43,146][01870] Fps is (10 sec: 2866.5, 60 sec: 3140.1, 300 sec: 2742.5). Total num frames: 315392. Throughput: 0: 809.5. Samples: 79216. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) -[2024-09-21 00:13:43,149][01870] Avg episode reward: [(0, '4.535')] -[2024-09-21 00:13:46,178][04656] Updated weights for policy 0, policy_version 80 (0.0019) -[2024-09-21 00:13:48,143][01870] Fps is (10 sec: 3278.4, 60 sec: 3276.8, 300 sec: 2799.0). Total num frames: 335872. Throughput: 0: 780.2. Samples: 83674. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) -[2024-09-21 00:13:48,148][01870] Avg episode reward: [(0, '4.599')] -[2024-09-21 00:13:53,143][01870] Fps is (10 sec: 3687.4, 60 sec: 3276.8, 300 sec: 2818.1). Total num frames: 352256. Throughput: 0: 804.6. Samples: 86524. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) -[2024-09-21 00:13:53,150][01870] Avg episode reward: [(0, '4.314')] -[2024-09-21 00:13:57,796][04656] Updated weights for policy 0, policy_version 90 (0.0035) -[2024-09-21 00:13:58,143][01870] Fps is (10 sec: 3276.8, 60 sec: 3276.8, 300 sec: 2835.7). Total num frames: 368640. Throughput: 0: 831.7. Samples: 91938. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) -[2024-09-21 00:13:58,149][01870] Avg episode reward: [(0, '4.165')] -[2024-09-21 00:14:03,144][01870] Fps is (10 sec: 2867.1, 60 sec: 3140.2, 300 sec: 2821.7). Total num frames: 380928. Throughput: 0: 779.6. Samples: 95468. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) -[2024-09-21 00:14:03,150][01870] Avg episode reward: [(0, '4.242')] -[2024-09-21 00:14:08,143][01870] Fps is (10 sec: 2867.2, 60 sec: 3208.7, 300 sec: 2838.0). Total num frames: 397312. Throughput: 0: 780.1. Samples: 98052. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) -[2024-09-21 00:14:08,146][01870] Avg episode reward: [(0, '4.717')] -[2024-09-21 00:14:08,156][04643] Saving new best policy, reward=4.717! -[2024-09-21 00:14:10,604][04656] Updated weights for policy 0, policy_version 100 (0.0040) -[2024-09-21 00:14:13,143][01870] Fps is (10 sec: 3686.5, 60 sec: 3276.8, 300 sec: 2881.4). Total num frames: 417792. Throughput: 0: 828.4. Samples: 103772. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) -[2024-09-21 00:14:13,146][01870] Avg episode reward: [(0, '4.897')] -[2024-09-21 00:14:13,151][04643] Saving new best policy, reward=4.897! -[2024-09-21 00:14:18,143][01870] Fps is (10 sec: 3276.8, 60 sec: 3140.3, 300 sec: 2867.2). Total num frames: 430080. Throughput: 0: 802.2. Samples: 107902. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) -[2024-09-21 00:14:18,146][01870] Avg episode reward: [(0, '4.815')] -[2024-09-21 00:14:23,143][01870] Fps is (10 sec: 2457.6, 60 sec: 3140.3, 300 sec: 2854.0). Total num frames: 442368. Throughput: 0: 774.9. Samples: 109656. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) -[2024-09-21 00:14:23,146][01870] Avg episode reward: [(0, '4.669')] -[2024-09-21 00:14:24,233][04656] Updated weights for policy 0, policy_version 110 (0.0018) -[2024-09-21 00:14:28,143][01870] Fps is (10 sec: 3276.8, 60 sec: 3276.8, 300 sec: 2892.8). Total num frames: 462848. Throughput: 0: 804.0. Samples: 115394. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) -[2024-09-21 00:14:28,146][01870] Avg episode reward: [(0, '4.663')] -[2024-09-21 00:14:33,144][01870] Fps is (10 sec: 3686.0, 60 sec: 3208.5, 300 sec: 2904.5). Total num frames: 479232. Throughput: 0: 818.3. Samples: 120498. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) -[2024-09-21 00:14:33,151][01870] Avg episode reward: [(0, '4.705')] -[2024-09-21 00:14:37,689][04656] Updated weights for policy 0, policy_version 120 (0.0024) -[2024-09-21 00:14:38,143][01870] Fps is (10 sec: 2867.2, 60 sec: 3140.5, 300 sec: 2891.3). Total num frames: 491520. Throughput: 0: 793.2. Samples: 122218. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) -[2024-09-21 00:14:38,150][01870] Avg episode reward: [(0, '4.501')] -[2024-09-21 00:14:43,143][01870] Fps is (10 sec: 2867.5, 60 sec: 3208.7, 300 sec: 2902.3). Total num frames: 507904. Throughput: 0: 775.6. Samples: 126840. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) -[2024-09-21 00:14:43,151][01870] Avg episode reward: [(0, '4.680')] -[2024-09-21 00:14:48,143][01870] Fps is (10 sec: 3686.4, 60 sec: 3208.5, 300 sec: 2935.5). Total num frames: 528384. Throughput: 0: 827.3. Samples: 132694. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) -[2024-09-21 00:14:48,150][01870] Avg episode reward: [(0, '4.908')] -[2024-09-21 00:14:48,162][04643] Saving new best policy, reward=4.908! -[2024-09-21 00:14:48,547][04656] Updated weights for policy 0, policy_version 130 (0.0047) -[2024-09-21 00:14:53,143][01870] Fps is (10 sec: 3276.8, 60 sec: 3140.3, 300 sec: 2922.6). Total num frames: 540672. Throughput: 0: 816.8. Samples: 134810. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) -[2024-09-21 00:14:53,148][01870] Avg episode reward: [(0, '4.863')] -[2024-09-21 00:14:58,143][01870] Fps is (10 sec: 2867.2, 60 sec: 3140.3, 300 sec: 2931.9). Total num frames: 557056. Throughput: 0: 766.8. Samples: 138276. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) -[2024-09-21 00:14:58,152][01870] Avg episode reward: [(0, '4.601')] -[2024-09-21 00:15:03,143][01870] Fps is (10 sec: 2867.2, 60 sec: 3140.3, 300 sec: 2919.7). Total num frames: 569344. Throughput: 0: 783.9. Samples: 143176. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) -[2024-09-21 00:15:03,150][01870] Avg episode reward: [(0, '4.730')] -[2024-09-21 00:15:03,754][04656] Updated weights for policy 0, policy_version 140 (0.0041) -[2024-09-21 00:15:08,143][01870] Fps is (10 sec: 2457.6, 60 sec: 3072.0, 300 sec: 2908.2). Total num frames: 581632. Throughput: 0: 783.9. Samples: 144932. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) -[2024-09-21 00:15:08,145][01870] Avg episode reward: [(0, '4.591')] -[2024-09-21 00:15:13,143][01870] Fps is (10 sec: 2457.6, 60 sec: 2935.5, 300 sec: 2897.2). Total num frames: 593920. Throughput: 0: 728.0. Samples: 148154. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) -[2024-09-21 00:15:13,146][01870] Avg episode reward: [(0, '4.592')] -[2024-09-21 00:15:18,143][01870] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2906.2). Total num frames: 610304. Throughput: 0: 720.0. Samples: 152896. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) -[2024-09-21 00:15:18,148][01870] Avg episode reward: [(0, '4.487')] -[2024-09-21 00:15:18,158][04643] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000149_610304.pth... -[2024-09-21 00:15:18,891][04656] Updated weights for policy 0, policy_version 150 (0.0033) -[2024-09-21 00:15:23,143][01870] Fps is (10 sec: 3686.4, 60 sec: 3140.3, 300 sec: 2933.9). Total num frames: 630784. Throughput: 0: 744.5. Samples: 155722. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) -[2024-09-21 00:15:23,150][01870] Avg episode reward: [(0, '4.638')] -[2024-09-21 00:15:28,144][01870] Fps is (10 sec: 3276.7, 60 sec: 3003.7, 300 sec: 2923.1). Total num frames: 643072. Throughput: 0: 758.6. Samples: 160976. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) -[2024-09-21 00:15:28,149][01870] Avg episode reward: [(0, '4.841')] -[2024-09-21 00:15:32,324][04656] Updated weights for policy 0, policy_version 160 (0.0042) -[2024-09-21 00:15:33,143][01870] Fps is (10 sec: 2457.6, 60 sec: 2935.5, 300 sec: 2912.7). Total num frames: 655360. Throughput: 0: 705.9. Samples: 164458. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) -[2024-09-21 00:15:33,150][01870] Avg episode reward: [(0, '4.740')] -[2024-09-21 00:15:38,143][01870] Fps is (10 sec: 3276.9, 60 sec: 3072.0, 300 sec: 2938.5). Total num frames: 675840. Throughput: 0: 722.9. Samples: 167340. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) -[2024-09-21 00:15:38,150][01870] Avg episode reward: [(0, '4.685')] -[2024-09-21 00:15:42,551][04656] Updated weights for policy 0, policy_version 170 (0.0028) -[2024-09-21 00:15:43,143][01870] Fps is (10 sec: 4096.0, 60 sec: 3140.3, 300 sec: 2963.1). Total num frames: 696320. Throughput: 0: 785.0. Samples: 173600. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) -[2024-09-21 00:15:43,145][01870] Avg episode reward: [(0, '4.822')] -[2024-09-21 00:15:48,144][01870] Fps is (10 sec: 3276.6, 60 sec: 3003.7, 300 sec: 2952.6). Total num frames: 708608. Throughput: 0: 771.3. Samples: 177884. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) -[2024-09-21 00:15:48,147][01870] Avg episode reward: [(0, '4.696')] -[2024-09-21 00:15:53,143][01870] Fps is (10 sec: 2867.2, 60 sec: 3072.0, 300 sec: 2959.2). Total num frames: 724992. Throughput: 0: 776.6. Samples: 179880. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) -[2024-09-21 00:15:53,145][01870] Avg episode reward: [(0, '4.703')] -[2024-09-21 00:15:55,308][04656] Updated weights for policy 0, policy_version 180 (0.0017) -[2024-09-21 00:15:58,143][01870] Fps is (10 sec: 3686.6, 60 sec: 3140.3, 300 sec: 2981.9). Total num frames: 745472. Throughput: 0: 841.7. Samples: 186030. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) -[2024-09-21 00:15:58,148][01870] Avg episode reward: [(0, '4.758')] -[2024-09-21 00:16:03,143][01870] Fps is (10 sec: 3686.4, 60 sec: 3208.5, 300 sec: 2987.7). Total num frames: 761856. Throughput: 0: 856.0. Samples: 191414. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) -[2024-09-21 00:16:03,148][01870] Avg episode reward: [(0, '4.963')] -[2024-09-21 00:16:03,153][04643] Saving new best policy, reward=4.963! -[2024-09-21 00:16:08,143][01870] Fps is (10 sec: 2867.2, 60 sec: 3208.5, 300 sec: 2977.5). Total num frames: 774144. Throughput: 0: 832.4. Samples: 193180. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) -[2024-09-21 00:16:08,149][01870] Avg episode reward: [(0, '5.001')] -[2024-09-21 00:16:08,159][04643] Saving new best policy, reward=5.001! -[2024-09-21 00:16:08,428][04656] Updated weights for policy 0, policy_version 190 (0.0028) -[2024-09-21 00:16:13,143][01870] Fps is (10 sec: 3276.8, 60 sec: 3345.1, 300 sec: 2998.6). Total num frames: 794624. Throughput: 0: 828.7. Samples: 198266. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) -[2024-09-21 00:16:13,146][01870] Avg episode reward: [(0, '5.371')] -[2024-09-21 00:16:13,157][04643] Saving new best policy, reward=5.371! -[2024-09-21 00:16:18,143][01870] Fps is (10 sec: 4096.0, 60 sec: 3413.3, 300 sec: 3018.9). Total num frames: 815104. Throughput: 0: 891.9. Samples: 204592. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) -[2024-09-21 00:16:18,148][01870] Avg episode reward: [(0, '5.162')] -[2024-09-21 00:16:18,169][04656] Updated weights for policy 0, policy_version 200 (0.0041) -[2024-09-21 00:16:23,143][01870] Fps is (10 sec: 3276.8, 60 sec: 3276.8, 300 sec: 3008.7). Total num frames: 827392. Throughput: 0: 877.2. Samples: 206814. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) -[2024-09-21 00:16:23,148][01870] Avg episode reward: [(0, '5.138')] -[2024-09-21 00:16:28,143][01870] Fps is (10 sec: 3276.8, 60 sec: 3413.4, 300 sec: 3028.1). Total num frames: 847872. Throughput: 0: 826.2. Samples: 210780. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) -[2024-09-21 00:16:28,146][01870] Avg episode reward: [(0, '5.032')] -[2024-09-21 00:16:31,060][04656] Updated weights for policy 0, policy_version 210 (0.0024) -[2024-09-21 00:16:33,143][01870] Fps is (10 sec: 3686.4, 60 sec: 3481.6, 300 sec: 3032.5). Total num frames: 864256. Throughput: 0: 865.5. Samples: 216830. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) -[2024-09-21 00:16:33,148][01870] Avg episode reward: [(0, '4.893')] -[2024-09-21 00:16:38,143][01870] Fps is (10 sec: 3686.4, 60 sec: 3481.6, 300 sec: 3050.8). Total num frames: 884736. Throughput: 0: 894.2. Samples: 220118. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) -[2024-09-21 00:16:38,145][01870] Avg episode reward: [(0, '5.006')] -[2024-09-21 00:16:43,145][01870] Fps is (10 sec: 3276.3, 60 sec: 3345.0, 300 sec: 3040.8). Total num frames: 897024. Throughput: 0: 844.2. Samples: 224022. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) -[2024-09-21 00:16:43,151][01870] Avg episode reward: [(0, '4.892')] -[2024-09-21 00:16:44,050][04656] Updated weights for policy 0, policy_version 220 (0.0046) -[2024-09-21 00:16:48,143][01870] Fps is (10 sec: 3276.8, 60 sec: 3481.6, 300 sec: 3110.2). Total num frames: 917504. Throughput: 0: 845.8. Samples: 229474. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) -[2024-09-21 00:16:48,146][01870] Avg episode reward: [(0, '5.085')] -[2024-09-21 00:16:53,143][01870] Fps is (10 sec: 4096.6, 60 sec: 3549.9, 300 sec: 3179.6). Total num frames: 937984. Throughput: 0: 874.4. Samples: 232530. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) -[2024-09-21 00:16:53,145][01870] Avg episode reward: [(0, '5.272')] -[2024-09-21 00:16:54,108][04656] Updated weights for policy 0, policy_version 230 (0.0018) -[2024-09-21 00:16:58,143][01870] Fps is (10 sec: 3276.8, 60 sec: 3413.3, 300 sec: 3221.3). Total num frames: 950272. Throughput: 0: 872.8. Samples: 237542. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) -[2024-09-21 00:16:58,146][01870] Avg episode reward: [(0, '5.152')] -[2024-09-21 00:17:03,145][01870] Fps is (10 sec: 2866.7, 60 sec: 3413.2, 300 sec: 3207.4). Total num frames: 966656. Throughput: 0: 827.9. Samples: 241850. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) -[2024-09-21 00:17:03,148][01870] Avg episode reward: [(0, '5.226')] -[2024-09-21 00:17:06,638][04656] Updated weights for policy 0, policy_version 240 (0.0051) -[2024-09-21 00:17:08,143][01870] Fps is (10 sec: 3686.4, 60 sec: 3549.9, 300 sec: 3235.1). Total num frames: 987136. Throughput: 0: 847.8. Samples: 244966. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) -[2024-09-21 00:17:08,152][01870] Avg episode reward: [(0, '4.902')] -[2024-09-21 00:17:13,143][01870] Fps is (10 sec: 3687.1, 60 sec: 3481.6, 300 sec: 3221.3). Total num frames: 1003520. Throughput: 0: 895.3. Samples: 251068. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) -[2024-09-21 00:17:13,150][01870] Avg episode reward: [(0, '5.019')] -[2024-09-21 00:17:18,145][01870] Fps is (10 sec: 2866.8, 60 sec: 3345.0, 300 sec: 3221.2). Total num frames: 1015808. Throughput: 0: 845.8. Samples: 254894. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) -[2024-09-21 00:17:18,147][01870] Avg episode reward: [(0, '5.135')] -[2024-09-21 00:17:18,164][04643] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000248_1015808.pth... -[2024-09-21 00:17:18,373][04643] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000059_241664.pth -[2024-09-21 00:17:19,585][04656] Updated weights for policy 0, policy_version 250 (0.0041) -[2024-09-21 00:17:23,143][01870] Fps is (10 sec: 3276.8, 60 sec: 3481.6, 300 sec: 3249.0). Total num frames: 1036288. Throughput: 0: 827.8. Samples: 257368. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) -[2024-09-21 00:17:23,152][01870] Avg episode reward: [(0, '5.418')] -[2024-09-21 00:17:23,162][04643] Saving new best policy, reward=5.418! -[2024-09-21 00:17:28,143][01870] Fps is (10 sec: 3277.3, 60 sec: 3345.1, 300 sec: 3249.1). Total num frames: 1048576. Throughput: 0: 836.5. Samples: 261662. Policy #0 lag: (min: 0.0, avg: 0.3, max: 2.0) -[2024-09-21 00:17:28,149][01870] Avg episode reward: [(0, '5.554')] -[2024-09-21 00:17:28,161][04643] Saving new best policy, reward=5.554! -[2024-09-21 00:17:32,569][04656] Updated weights for policy 0, policy_version 260 (0.0074) -[2024-09-21 00:17:33,143][01870] Fps is (10 sec: 2867.2, 60 sec: 3345.1, 300 sec: 3249.0). Total num frames: 1064960. Throughput: 0: 824.6. Samples: 266582. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) -[2024-09-21 00:17:33,146][01870] Avg episode reward: [(0, '5.374')] -[2024-09-21 00:17:38,143][01870] Fps is (10 sec: 2867.2, 60 sec: 3208.5, 300 sec: 3221.3). Total num frames: 1077248. Throughput: 0: 796.9. Samples: 268390. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) -[2024-09-21 00:17:38,150][01870] Avg episode reward: [(0, '5.468')] -[2024-09-21 00:17:43,148][01870] Fps is (10 sec: 2865.9, 60 sec: 3276.6, 300 sec: 3235.1). Total num frames: 1093632. Throughput: 0: 796.9. Samples: 273408. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) -[2024-09-21 00:17:43,158][01870] Avg episode reward: [(0, '5.527')] -[2024-09-21 00:17:47,542][04656] Updated weights for policy 0, policy_version 270 (0.0027) -[2024-09-21 00:17:48,143][01870] Fps is (10 sec: 2867.2, 60 sec: 3140.3, 300 sec: 3221.3). Total num frames: 1105920. Throughput: 0: 783.9. Samples: 277126. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) -[2024-09-21 00:17:48,148][01870] Avg episode reward: [(0, '5.773')] -[2024-09-21 00:17:48,158][04643] Saving new best policy, reward=5.773! -[2024-09-21 00:17:53,149][01870] Fps is (10 sec: 2457.4, 60 sec: 3003.5, 300 sec: 3207.3). Total num frames: 1118208. Throughput: 0: 753.6. Samples: 278882. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) -[2024-09-21 00:17:53,151][01870] Avg episode reward: [(0, '5.656')] -[2024-09-21 00:17:58,143][01870] Fps is (10 sec: 2867.2, 60 sec: 3072.0, 300 sec: 3193.5). Total num frames: 1134592. Throughput: 0: 716.7. Samples: 283320. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) -[2024-09-21 00:17:58,148][01870] Avg episode reward: [(0, '5.612')] -[2024-09-21 00:18:00,353][04656] Updated weights for policy 0, policy_version 280 (0.0026) -[2024-09-21 00:18:03,143][01870] Fps is (10 sec: 3688.4, 60 sec: 3140.4, 300 sec: 3221.3). Total num frames: 1155072. Throughput: 0: 768.9. Samples: 289494. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) -[2024-09-21 00:18:03,146][01870] Avg episode reward: [(0, '5.677')] -[2024-09-21 00:18:08,145][01870] Fps is (10 sec: 3685.9, 60 sec: 3071.9, 300 sec: 3221.3). Total num frames: 1171456. Throughput: 0: 777.9. Samples: 292374. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) -[2024-09-21 00:18:08,150][01870] Avg episode reward: [(0, '5.915')] -[2024-09-21 00:18:08,165][04643] Saving new best policy, reward=5.915! -[2024-09-21 00:18:13,143][01870] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 3193.5). Total num frames: 1183744. Throughput: 0: 763.4. Samples: 296014. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) -[2024-09-21 00:18:13,149][01870] Avg episode reward: [(0, '5.897')] -[2024-09-21 00:18:13,512][04656] Updated weights for policy 0, policy_version 290 (0.0030) -[2024-09-21 00:18:18,143][01870] Fps is (10 sec: 3277.2, 60 sec: 3140.3, 300 sec: 3221.3). Total num frames: 1204224. Throughput: 0: 781.6. Samples: 301754. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) -[2024-09-21 00:18:18,151][01870] Avg episode reward: [(0, '5.918')] -[2024-09-21 00:18:18,171][04643] Saving new best policy, reward=5.918! -[2024-09-21 00:18:23,143][01870] Fps is (10 sec: 4096.0, 60 sec: 3140.3, 300 sec: 3249.0). Total num frames: 1224704. Throughput: 0: 808.0. Samples: 304748. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) -[2024-09-21 00:18:23,147][01870] Avg episode reward: [(0, '5.908')] -[2024-09-21 00:18:23,892][04656] Updated weights for policy 0, policy_version 300 (0.0028) -[2024-09-21 00:18:28,144][01870] Fps is (10 sec: 3276.7, 60 sec: 3140.2, 300 sec: 3221.3). Total num frames: 1236992. Throughput: 0: 800.9. Samples: 309444. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) -[2024-09-21 00:18:28,151][01870] Avg episode reward: [(0, '5.948')] -[2024-09-21 00:18:28,163][04643] Saving new best policy, reward=5.948! -[2024-09-21 00:18:33,143][01870] Fps is (10 sec: 2867.2, 60 sec: 3140.3, 300 sec: 3221.3). Total num frames: 1253376. Throughput: 0: 820.7. Samples: 314056. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) -[2024-09-21 00:18:33,147][01870] Avg episode reward: [(0, '5.928')] -[2024-09-21 00:18:36,549][04656] Updated weights for policy 0, policy_version 310 (0.0036) -[2024-09-21 00:18:38,143][01870] Fps is (10 sec: 3686.5, 60 sec: 3276.8, 300 sec: 3249.1). Total num frames: 1273856. Throughput: 0: 847.7. Samples: 317022. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) -[2024-09-21 00:18:38,149][01870] Avg episode reward: [(0, '5.566')] -[2024-09-21 00:18:43,143][01870] Fps is (10 sec: 3686.4, 60 sec: 3277.1, 300 sec: 3235.1). Total num frames: 1290240. Throughput: 0: 865.7. Samples: 322278. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) -[2024-09-21 00:18:43,152][01870] Avg episode reward: [(0, '5.193')] -[2024-09-21 00:18:48,143][01870] Fps is (10 sec: 2867.2, 60 sec: 3276.8, 300 sec: 3221.3). Total num frames: 1302528. Throughput: 0: 812.7. Samples: 326066. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) -[2024-09-21 00:18:48,150][01870] Avg episode reward: [(0, '5.206')] -[2024-09-21 00:18:49,627][04656] Updated weights for policy 0, policy_version 320 (0.0026) -[2024-09-21 00:18:53,143][01870] Fps is (10 sec: 3276.8, 60 sec: 3413.6, 300 sec: 3235.1). Total num frames: 1323008. Throughput: 0: 814.2. Samples: 329012. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) -[2024-09-21 00:18:53,150][01870] Avg episode reward: [(0, '5.576')] -[2024-09-21 00:18:58,143][01870] Fps is (10 sec: 4096.0, 60 sec: 3481.6, 300 sec: 3262.9). Total num frames: 1343488. Throughput: 0: 871.3. Samples: 335224. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) -[2024-09-21 00:18:58,146][01870] Avg episode reward: [(0, '6.195')] -[2024-09-21 00:18:58,153][04643] Saving new best policy, reward=6.195! -[2024-09-21 00:19:00,956][04656] Updated weights for policy 0, policy_version 330 (0.0032) -[2024-09-21 00:19:03,144][01870] Fps is (10 sec: 3276.7, 60 sec: 3345.1, 300 sec: 3249.0). Total num frames: 1355776. Throughput: 0: 837.3. Samples: 339434. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) -[2024-09-21 00:19:03,146][01870] Avg episode reward: [(0, '6.340')] -[2024-09-21 00:19:03,148][04643] Saving new best policy, reward=6.340! -[2024-09-21 00:19:08,143][01870] Fps is (10 sec: 2867.2, 60 sec: 3345.1, 300 sec: 3235.1). Total num frames: 1372160. Throughput: 0: 810.2. Samples: 341208. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) -[2024-09-21 00:19:08,152][01870] Avg episode reward: [(0, '6.317')] -[2024-09-21 00:19:12,676][04656] Updated weights for policy 0, policy_version 340 (0.0019) -[2024-09-21 00:19:13,143][01870] Fps is (10 sec: 3686.5, 60 sec: 3481.6, 300 sec: 3262.9). Total num frames: 1392640. Throughput: 0: 844.3. Samples: 347438. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) -[2024-09-21 00:19:13,151][01870] Avg episode reward: [(0, '6.294')] -[2024-09-21 00:19:18,144][01870] Fps is (10 sec: 3686.2, 60 sec: 3413.3, 300 sec: 3276.8). Total num frames: 1409024. Throughput: 0: 862.4. Samples: 352864. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) -[2024-09-21 00:19:18,152][01870] Avg episode reward: [(0, '6.288')] -[2024-09-21 00:19:18,165][04643] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000344_1409024.pth... -[2024-09-21 00:19:18,371][04643] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000149_610304.pth -[2024-09-21 00:19:23,143][01870] Fps is (10 sec: 2867.2, 60 sec: 3276.8, 300 sec: 3249.0). Total num frames: 1421312. Throughput: 0: 836.3. Samples: 354656. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) -[2024-09-21 00:19:23,146][01870] Avg episode reward: [(0, '6.272')] -[2024-09-21 00:19:25,899][04656] Updated weights for policy 0, policy_version 350 (0.0027) -[2024-09-21 00:19:28,143][01870] Fps is (10 sec: 3276.9, 60 sec: 3413.4, 300 sec: 3262.9). Total num frames: 1441792. Throughput: 0: 831.0. Samples: 359674. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) -[2024-09-21 00:19:28,151][01870] Avg episode reward: [(0, '5.853')] -[2024-09-21 00:19:33,143][01870] Fps is (10 sec: 4096.0, 60 sec: 3481.6, 300 sec: 3290.7). Total num frames: 1462272. Throughput: 0: 885.8. Samples: 365928. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) -[2024-09-21 00:19:33,151][01870] Avg episode reward: [(0, '5.807')] -[2024-09-21 00:19:37,533][04656] Updated weights for policy 0, policy_version 360 (0.0024) -[2024-09-21 00:19:38,146][01870] Fps is (10 sec: 3276.0, 60 sec: 3344.9, 300 sec: 3276.8). Total num frames: 1474560. Throughput: 0: 867.3. Samples: 368044. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) -[2024-09-21 00:19:38,155][01870] Avg episode reward: [(0, '6.210')] -[2024-09-21 00:19:43,143][01870] Fps is (10 sec: 2867.2, 60 sec: 3345.1, 300 sec: 3262.9). Total num frames: 1490944. Throughput: 0: 816.8. Samples: 371980. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) -[2024-09-21 00:19:43,151][01870] Avg episode reward: [(0, '5.931')] -[2024-09-21 00:19:48,146][01870] Fps is (10 sec: 3686.4, 60 sec: 3481.5, 300 sec: 3290.7). Total num frames: 1511424. Throughput: 0: 860.6. Samples: 378164. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) -[2024-09-21 00:19:48,150][01870] Avg episode reward: [(0, '5.421')] -[2024-09-21 00:19:48,787][04656] Updated weights for policy 0, policy_version 370 (0.0048) -[2024-09-21 00:19:53,147][01870] Fps is (10 sec: 3685.1, 60 sec: 3413.1, 300 sec: 3290.6). Total num frames: 1527808. Throughput: 0: 888.7. Samples: 381202. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) -[2024-09-21 00:19:53,154][01870] Avg episode reward: [(0, '5.586')] -[2024-09-21 00:19:58,143][01870] Fps is (10 sec: 2867.9, 60 sec: 3276.8, 300 sec: 3290.7). Total num frames: 1540096. Throughput: 0: 839.1. Samples: 385198. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) -[2024-09-21 00:19:58,148][01870] Avg episode reward: [(0, '5.746')] -[2024-09-21 00:20:01,511][04656] Updated weights for policy 0, policy_version 380 (0.0016) -[2024-09-21 00:20:03,144][01870] Fps is (10 sec: 3277.9, 60 sec: 3413.3, 300 sec: 3318.5). Total num frames: 1560576. Throughput: 0: 838.8. Samples: 390610. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) -[2024-09-21 00:20:03,149][01870] Avg episode reward: [(0, '6.031')] -[2024-09-21 00:20:08,143][01870] Fps is (10 sec: 4096.0, 60 sec: 3481.6, 300 sec: 3346.2). Total num frames: 1581056. Throughput: 0: 864.8. Samples: 393574. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) -[2024-09-21 00:20:08,151][01870] Avg episode reward: [(0, '6.058')] -[2024-09-21 00:20:13,144][01870] Fps is (10 sec: 3276.7, 60 sec: 3345.0, 300 sec: 3332.3). Total num frames: 1593344. Throughput: 0: 865.9. Samples: 398638. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) -[2024-09-21 00:20:13,147][01870] Avg episode reward: [(0, '6.012')] -[2024-09-21 00:20:13,732][04656] Updated weights for policy 0, policy_version 390 (0.0015) -[2024-09-21 00:20:18,144][01870] Fps is (10 sec: 2867.1, 60 sec: 3345.1, 300 sec: 3318.5). Total num frames: 1609728. Throughput: 0: 822.3. Samples: 402932. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) -[2024-09-21 00:20:18,151][01870] Avg episode reward: [(0, '6.192')] -[2024-09-21 00:20:23,143][01870] Fps is (10 sec: 3276.9, 60 sec: 3413.3, 300 sec: 3332.3). Total num frames: 1626112. Throughput: 0: 832.5. Samples: 405504. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) -[2024-09-21 00:20:23,149][01870] Avg episode reward: [(0, '6.398')] -[2024-09-21 00:20:23,156][04643] Saving new best policy, reward=6.398! -[2024-09-21 00:20:28,149][01870] Fps is (10 sec: 2865.7, 60 sec: 3276.5, 300 sec: 3332.3). Total num frames: 1638400. Throughput: 0: 824.8. Samples: 409102. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) -[2024-09-21 00:20:28,149][04656] Updated weights for policy 0, policy_version 400 (0.0028) -[2024-09-21 00:20:28,152][01870] Avg episode reward: [(0, '6.418')] -[2024-09-21 00:20:28,167][04643] Saving new best policy, reward=6.418! -[2024-09-21 00:20:33,143][01870] Fps is (10 sec: 2048.0, 60 sec: 3072.0, 300 sec: 3290.7). Total num frames: 1646592. Throughput: 0: 767.9. Samples: 412716. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) -[2024-09-21 00:20:33,151][01870] Avg episode reward: [(0, '6.399')] -[2024-09-21 00:20:38,144][01870] Fps is (10 sec: 2868.7, 60 sec: 3208.7, 300 sec: 3290.7). Total num frames: 1667072. Throughput: 0: 749.7. Samples: 414936. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) -[2024-09-21 00:20:38,150][01870] Avg episode reward: [(0, '6.012')] -[2024-09-21 00:20:40,915][04656] Updated weights for policy 0, policy_version 410 (0.0024) -[2024-09-21 00:20:43,143][01870] Fps is (10 sec: 4096.0, 60 sec: 3276.8, 300 sec: 3318.5). Total num frames: 1687552. Throughput: 0: 797.2. Samples: 421074. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) -[2024-09-21 00:20:43,153][01870] Avg episode reward: [(0, '5.442')] -[2024-09-21 00:20:48,144][01870] Fps is (10 sec: 3276.8, 60 sec: 3140.4, 300 sec: 3304.6). Total num frames: 1699840. Throughput: 0: 786.7. Samples: 426010. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) -[2024-09-21 00:20:48,149][01870] Avg episode reward: [(0, '5.885')] -[2024-09-21 00:20:53,143][01870] Fps is (10 sec: 2867.2, 60 sec: 3140.5, 300 sec: 3290.7). Total num frames: 1716224. Throughput: 0: 760.7. Samples: 427804. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) -[2024-09-21 00:20:53,146][01870] Avg episode reward: [(0, '6.282')] -[2024-09-21 00:20:53,651][04656] Updated weights for policy 0, policy_version 420 (0.0043) -[2024-09-21 00:20:58,143][01870] Fps is (10 sec: 3686.5, 60 sec: 3276.8, 300 sec: 3304.6). Total num frames: 1736704. Throughput: 0: 774.5. Samples: 433490. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) -[2024-09-21 00:20:58,148][01870] Avg episode reward: [(0, '6.573')] -[2024-09-21 00:20:58,157][04643] Saving new best policy, reward=6.573! -[2024-09-21 00:21:03,143][01870] Fps is (10 sec: 4096.0, 60 sec: 3276.8, 300 sec: 3332.3). Total num frames: 1757184. Throughput: 0: 811.0. Samples: 439428. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) -[2024-09-21 00:21:03,148][01870] Avg episode reward: [(0, '6.574')] -[2024-09-21 00:21:03,159][04643] Saving new best policy, reward=6.574! -[2024-09-21 00:21:04,808][04656] Updated weights for policy 0, policy_version 430 (0.0031) -[2024-09-21 00:21:08,144][01870] Fps is (10 sec: 2867.2, 60 sec: 3072.0, 300 sec: 3290.7). Total num frames: 1765376. Throughput: 0: 791.4. Samples: 441116. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) -[2024-09-21 00:21:08,147][01870] Avg episode reward: [(0, '6.954')] -[2024-09-21 00:21:08,174][04643] Saving new best policy, reward=6.954! -[2024-09-21 00:21:13,143][01870] Fps is (10 sec: 2867.2, 60 sec: 3208.6, 300 sec: 3290.7). Total num frames: 1785856. Throughput: 0: 810.1. Samples: 445550. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) -[2024-09-21 00:21:13,146][01870] Avg episode reward: [(0, '6.886')] -[2024-09-21 00:21:16,738][04656] Updated weights for policy 0, policy_version 440 (0.0047) -[2024-09-21 00:21:18,143][01870] Fps is (10 sec: 4096.0, 60 sec: 3276.8, 300 sec: 3318.5). Total num frames: 1806336. Throughput: 0: 869.1. Samples: 451824. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) -[2024-09-21 00:21:18,150][01870] Avg episode reward: [(0, '7.363')] -[2024-09-21 00:21:18,164][04643] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000441_1806336.pth... -[2024-09-21 00:21:18,291][04643] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000248_1015808.pth -[2024-09-21 00:21:18,310][04643] Saving new best policy, reward=7.363! -[2024-09-21 00:21:23,144][01870] Fps is (10 sec: 3276.5, 60 sec: 3208.5, 300 sec: 3290.7). Total num frames: 1818624. Throughput: 0: 878.5. Samples: 454468. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) -[2024-09-21 00:21:23,150][01870] Avg episode reward: [(0, '7.589')] -[2024-09-21 00:21:23,157][04643] Saving new best policy, reward=7.589! -[2024-09-21 00:21:28,143][01870] Fps is (10 sec: 2867.2, 60 sec: 3277.1, 300 sec: 3290.7). Total num frames: 1835008. Throughput: 0: 822.9. Samples: 458106. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) -[2024-09-21 00:21:28,151][01870] Avg episode reward: [(0, '7.556')] -[2024-09-21 00:21:30,002][04656] Updated weights for policy 0, policy_version 450 (0.0046) -[2024-09-21 00:21:33,143][01870] Fps is (10 sec: 3686.7, 60 sec: 3481.6, 300 sec: 3290.7). Total num frames: 1855488. Throughput: 0: 842.8. Samples: 463934. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) -[2024-09-21 00:21:33,152][01870] Avg episode reward: [(0, '7.429')] -[2024-09-21 00:21:38,147][01870] Fps is (10 sec: 3685.1, 60 sec: 3413.1, 300 sec: 3304.5). Total num frames: 1871872. Throughput: 0: 868.2. Samples: 466876. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) -[2024-09-21 00:21:38,150][01870] Avg episode reward: [(0, '6.943')] -[2024-09-21 00:21:41,547][04656] Updated weights for policy 0, policy_version 460 (0.0028) -[2024-09-21 00:21:43,146][01870] Fps is (10 sec: 2866.6, 60 sec: 3276.7, 300 sec: 3276.8). Total num frames: 1884160. Throughput: 0: 843.7. Samples: 471460. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) -[2024-09-21 00:21:43,151][01870] Avg episode reward: [(0, '7.130')] -[2024-09-21 00:21:48,143][01870] Fps is (10 sec: 3277.9, 60 sec: 3413.3, 300 sec: 3276.8). Total num frames: 1904640. Throughput: 0: 820.5. Samples: 476350. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) -[2024-09-21 00:21:48,145][01870] Avg episode reward: [(0, '6.994')] -[2024-09-21 00:21:52,898][04656] Updated weights for policy 0, policy_version 470 (0.0028) -[2024-09-21 00:21:53,143][01870] Fps is (10 sec: 4096.9, 60 sec: 3481.6, 300 sec: 3304.6). Total num frames: 1925120. Throughput: 0: 851.4. Samples: 479430. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) -[2024-09-21 00:21:53,149][01870] Avg episode reward: [(0, '6.880')] -[2024-09-21 00:21:58,143][01870] Fps is (10 sec: 3686.4, 60 sec: 3413.3, 300 sec: 3304.6). Total num frames: 1941504. Throughput: 0: 877.3. Samples: 485028. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) -[2024-09-21 00:21:58,149][01870] Avg episode reward: [(0, '7.371')] -[2024-09-21 00:22:03,143][01870] Fps is (10 sec: 2867.2, 60 sec: 3276.8, 300 sec: 3276.8). Total num frames: 1953792. Throughput: 0: 824.3. Samples: 488916. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) -[2024-09-21 00:22:03,149][01870] Avg episode reward: [(0, '7.469')] -[2024-09-21 00:22:05,671][04656] Updated weights for policy 0, policy_version 480 (0.0019) -[2024-09-21 00:22:08,143][01870] Fps is (10 sec: 3276.8, 60 sec: 3481.6, 300 sec: 3290.7). Total num frames: 1974272. Throughput: 0: 831.7. Samples: 491896. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) -[2024-09-21 00:22:08,146][01870] Avg episode reward: [(0, '8.073')] -[2024-09-21 00:22:08,158][04643] Saving new best policy, reward=8.073! -[2024-09-21 00:22:13,143][01870] Fps is (10 sec: 4096.0, 60 sec: 3481.6, 300 sec: 3318.5). Total num frames: 1994752. Throughput: 0: 887.5. Samples: 498042. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) -[2024-09-21 00:22:13,145][01870] Avg episode reward: [(0, '8.338')] -[2024-09-21 00:22:13,150][04643] Saving new best policy, reward=8.338! -[2024-09-21 00:22:17,933][04656] Updated weights for policy 0, policy_version 490 (0.0021) -[2024-09-21 00:22:18,143][01870] Fps is (10 sec: 3276.8, 60 sec: 3345.1, 300 sec: 3290.7). Total num frames: 2007040. Throughput: 0: 850.1. Samples: 502190. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) -[2024-09-21 00:22:18,154][01870] Avg episode reward: [(0, '8.513')] -[2024-09-21 00:22:18,164][04643] Saving new best policy, reward=8.513! -[2024-09-21 00:22:23,143][01870] Fps is (10 sec: 2867.2, 60 sec: 3413.4, 300 sec: 3304.6). Total num frames: 2023424. Throughput: 0: 828.8. Samples: 504168. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) -[2024-09-21 00:22:23,151][01870] Avg episode reward: [(0, '8.333')] -[2024-09-21 00:22:28,143][01870] Fps is (10 sec: 3686.4, 60 sec: 3481.6, 300 sec: 3318.5). Total num frames: 2043904. Throughput: 0: 865.8. Samples: 510418. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) -[2024-09-21 00:22:28,149][01870] Avg episode reward: [(0, '9.239')] -[2024-09-21 00:22:28,161][04643] Saving new best policy, reward=9.239! -[2024-09-21 00:22:28,563][04656] Updated weights for policy 0, policy_version 500 (0.0028) -[2024-09-21 00:22:33,143][01870] Fps is (10 sec: 3686.4, 60 sec: 3413.3, 300 sec: 3332.3). Total num frames: 2060288. Throughput: 0: 872.3. Samples: 515604. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) -[2024-09-21 00:22:33,146][01870] Avg episode reward: [(0, '9.290')] -[2024-09-21 00:22:33,149][04643] Saving new best policy, reward=9.290! -[2024-09-21 00:22:38,143][01870] Fps is (10 sec: 2867.2, 60 sec: 3345.3, 300 sec: 3318.5). Total num frames: 2072576. Throughput: 0: 844.9. Samples: 517450. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) -[2024-09-21 00:22:38,150][01870] Avg episode reward: [(0, '9.106')] -[2024-09-21 00:22:41,649][04656] Updated weights for policy 0, policy_version 510 (0.0036) -[2024-09-21 00:22:43,143][01870] Fps is (10 sec: 3276.8, 60 sec: 3481.7, 300 sec: 3346.2). Total num frames: 2093056. Throughput: 0: 836.6. Samples: 522676. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) -[2024-09-21 00:22:43,149][01870] Avg episode reward: [(0, '9.054')] -[2024-09-21 00:22:48,144][01870] Fps is (10 sec: 4095.9, 60 sec: 3481.6, 300 sec: 3374.1). Total num frames: 2113536. Throughput: 0: 890.2. Samples: 528974. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) -[2024-09-21 00:22:48,149][01870] Avg episode reward: [(0, '8.431')] -[2024-09-21 00:22:53,143][01870] Fps is (10 sec: 3276.8, 60 sec: 3345.1, 300 sec: 3360.1). Total num frames: 2125824. Throughput: 0: 870.0. Samples: 531044. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) -[2024-09-21 00:22:53,149][01870] Avg episode reward: [(0, '8.475')] -[2024-09-21 00:22:53,504][04656] Updated weights for policy 0, policy_version 520 (0.0026) -[2024-09-21 00:22:58,143][01870] Fps is (10 sec: 2867.3, 60 sec: 3345.1, 300 sec: 3346.2). Total num frames: 2142208. Throughput: 0: 824.0. Samples: 535124. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) -[2024-09-21 00:22:58,149][01870] Avg episode reward: [(0, '9.166')] -[2024-09-21 00:23:03,143][01870] Fps is (10 sec: 2867.2, 60 sec: 3345.1, 300 sec: 3332.4). Total num frames: 2154496. Throughput: 0: 832.1. Samples: 539636. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) -[2024-09-21 00:23:03,149][01870] Avg episode reward: [(0, '9.622')] -[2024-09-21 00:23:03,266][04643] Saving new best policy, reward=9.622! -[2024-09-21 00:23:08,145][01870] Fps is (10 sec: 2457.2, 60 sec: 3208.5, 300 sec: 3332.3). Total num frames: 2166784. Throughput: 0: 828.7. Samples: 541462. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) -[2024-09-21 00:23:08,151][01870] Avg episode reward: [(0, '9.676')] -[2024-09-21 00:23:08,164][04643] Saving new best policy, reward=9.676! -[2024-09-21 00:23:08,511][04656] Updated weights for policy 0, policy_version 530 (0.0029) -[2024-09-21 00:23:13,144][01870] Fps is (10 sec: 2457.5, 60 sec: 3072.0, 300 sec: 3304.6). Total num frames: 2179072. Throughput: 0: 767.5. Samples: 544956. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) -[2024-09-21 00:23:13,151][01870] Avg episode reward: [(0, '9.843')] -[2024-09-21 00:23:13,157][04643] Saving new best policy, reward=9.843! -[2024-09-21 00:23:18,143][01870] Fps is (10 sec: 3277.2, 60 sec: 3208.5, 300 sec: 3304.6). Total num frames: 2199552. Throughput: 0: 771.3. Samples: 550312. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) -[2024-09-21 00:23:18,152][01870] Avg episode reward: [(0, '9.437')] -[2024-09-21 00:23:18,166][04643] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000537_2199552.pth... -[2024-09-21 00:23:18,334][04643] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000344_1409024.pth -[2024-09-21 00:23:20,517][04656] Updated weights for policy 0, policy_version 540 (0.0029) -[2024-09-21 00:23:23,143][01870] Fps is (10 sec: 4096.1, 60 sec: 3276.8, 300 sec: 3332.3). Total num frames: 2220032. Throughput: 0: 797.6. Samples: 553342. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) -[2024-09-21 00:23:23,152][01870] Avg episode reward: [(0, '9.719')] -[2024-09-21 00:23:28,143][01870] Fps is (10 sec: 3276.8, 60 sec: 3140.3, 300 sec: 3318.5). Total num frames: 2232320. Throughput: 0: 794.6. Samples: 558432. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) -[2024-09-21 00:23:28,149][01870] Avg episode reward: [(0, '9.831')] -[2024-09-21 00:23:33,143][01870] Fps is (10 sec: 2867.2, 60 sec: 3140.3, 300 sec: 3304.6). Total num frames: 2248704. Throughput: 0: 749.3. Samples: 562694. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) -[2024-09-21 00:23:33,151][01870] Avg episode reward: [(0, '9.612')] -[2024-09-21 00:23:33,453][04656] Updated weights for policy 0, policy_version 550 (0.0024) -[2024-09-21 00:23:38,143][01870] Fps is (10 sec: 3686.4, 60 sec: 3276.8, 300 sec: 3318.5). Total num frames: 2269184. Throughput: 0: 773.5. Samples: 565850. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) -[2024-09-21 00:23:38,147][01870] Avg episode reward: [(0, '9.340')] -[2024-09-21 00:23:43,144][01870] Fps is (10 sec: 3686.2, 60 sec: 3208.5, 300 sec: 3332.3). Total num frames: 2285568. Throughput: 0: 817.8. Samples: 571926. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) -[2024-09-21 00:23:43,148][01870] Avg episode reward: [(0, '9.541')] -[2024-09-21 00:23:44,863][04656] Updated weights for policy 0, policy_version 560 (0.0019) -[2024-09-21 00:23:48,143][01870] Fps is (10 sec: 3276.8, 60 sec: 3140.3, 300 sec: 3318.5). Total num frames: 2301952. Throughput: 0: 801.0. Samples: 575682. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) -[2024-09-21 00:23:48,146][01870] Avg episode reward: [(0, '9.591')] -[2024-09-21 00:23:53,143][01870] Fps is (10 sec: 3276.9, 60 sec: 3208.5, 300 sec: 3304.6). Total num frames: 2318336. Throughput: 0: 818.7. Samples: 578302. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) -[2024-09-21 00:23:53,148][01870] Avg episode reward: [(0, '9.839')] -[2024-09-21 00:23:56,077][04656] Updated weights for policy 0, policy_version 570 (0.0023) -[2024-09-21 00:23:58,143][01870] Fps is (10 sec: 4096.0, 60 sec: 3345.1, 300 sec: 3346.2). Total num frames: 2342912. Throughput: 0: 882.1. Samples: 584652. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) -[2024-09-21 00:23:58,151][01870] Avg episode reward: [(0, '9.563')] -[2024-09-21 00:24:03,143][01870] Fps is (10 sec: 3686.4, 60 sec: 3345.1, 300 sec: 3332.3). Total num frames: 2355200. Throughput: 0: 865.7. Samples: 589268. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) -[2024-09-21 00:24:03,149][01870] Avg episode reward: [(0, '9.729')] -[2024-09-21 00:24:08,143][01870] Fps is (10 sec: 2867.2, 60 sec: 3413.4, 300 sec: 3318.5). Total num frames: 2371584. Throughput: 0: 841.5. Samples: 591210. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) -[2024-09-21 00:24:08,146][01870] Avg episode reward: [(0, '9.805')] -[2024-09-21 00:24:09,013][04656] Updated weights for policy 0, policy_version 580 (0.0029) -[2024-09-21 00:24:13,143][01870] Fps is (10 sec: 3686.4, 60 sec: 3549.9, 300 sec: 3332.3). Total num frames: 2392064. Throughput: 0: 858.6. Samples: 597070. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) -[2024-09-21 00:24:13,147][01870] Avg episode reward: [(0, '10.853')] -[2024-09-21 00:24:13,151][04643] Saving new best policy, reward=10.853! -[2024-09-21 00:24:18,145][01870] Fps is (10 sec: 3685.9, 60 sec: 3481.5, 300 sec: 3346.2). Total num frames: 2408448. Throughput: 0: 889.9. Samples: 602742. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) -[2024-09-21 00:24:18,149][01870] Avg episode reward: [(0, '12.298')] -[2024-09-21 00:24:18,165][04643] Saving new best policy, reward=12.298! -[2024-09-21 00:24:20,807][04656] Updated weights for policy 0, policy_version 590 (0.0016) -[2024-09-21 00:24:23,143][01870] Fps is (10 sec: 2867.2, 60 sec: 3345.1, 300 sec: 3318.5). Total num frames: 2420736. Throughput: 0: 861.2. Samples: 604606. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) -[2024-09-21 00:24:23,151][01870] Avg episode reward: [(0, '12.293')] -[2024-09-21 00:24:28,143][01870] Fps is (10 sec: 3277.3, 60 sec: 3481.6, 300 sec: 3318.5). Total num frames: 2441216. Throughput: 0: 835.7. Samples: 609530. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) -[2024-09-21 00:24:28,147][01870] Avg episode reward: [(0, '13.022')] -[2024-09-21 00:24:28,155][04643] Saving new best policy, reward=13.022! -[2024-09-21 00:24:31,496][04656] Updated weights for policy 0, policy_version 600 (0.0018) -[2024-09-21 00:24:33,143][01870] Fps is (10 sec: 4095.9, 60 sec: 3549.9, 300 sec: 3346.2). Total num frames: 2461696. Throughput: 0: 892.5. Samples: 615844. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) -[2024-09-21 00:24:33,146][01870] Avg episode reward: [(0, '12.169')] -[2024-09-21 00:24:38,143][01870] Fps is (10 sec: 3276.8, 60 sec: 3413.3, 300 sec: 3332.3). Total num frames: 2473984. Throughput: 0: 887.1. Samples: 618222. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) -[2024-09-21 00:24:38,148][01870] Avg episode reward: [(0, '11.788')] -[2024-09-21 00:24:43,143][01870] Fps is (10 sec: 2867.2, 60 sec: 3413.4, 300 sec: 3318.5). Total num frames: 2490368. Throughput: 0: 830.2. Samples: 622010. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) -[2024-09-21 00:24:43,146][01870] Avg episode reward: [(0, '11.448')] -[2024-09-21 00:24:44,698][04656] Updated weights for policy 0, policy_version 610 (0.0023) -[2024-09-21 00:24:48,143][01870] Fps is (10 sec: 3686.4, 60 sec: 3481.6, 300 sec: 3332.4). Total num frames: 2510848. Throughput: 0: 868.5. Samples: 628350. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) -[2024-09-21 00:24:48,145][01870] Avg episode reward: [(0, '11.766')] -[2024-09-21 00:24:53,146][01870] Fps is (10 sec: 4095.0, 60 sec: 3549.7, 300 sec: 3360.1). Total num frames: 2531328. Throughput: 0: 893.9. Samples: 631438. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) -[2024-09-21 00:24:53,160][01870] Avg episode reward: [(0, '12.952')] -[2024-09-21 00:24:56,157][04656] Updated weights for policy 0, policy_version 620 (0.0033) -[2024-09-21 00:24:58,143][01870] Fps is (10 sec: 3276.8, 60 sec: 3345.1, 300 sec: 3332.3). Total num frames: 2543616. Throughput: 0: 859.0. Samples: 635726. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) -[2024-09-21 00:24:58,148][01870] Avg episode reward: [(0, '12.057')] -[2024-09-21 00:25:03,143][01870] Fps is (10 sec: 2867.9, 60 sec: 3413.3, 300 sec: 3318.5). Total num frames: 2560000. Throughput: 0: 847.9. Samples: 640894. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) -[2024-09-21 00:25:03,154][01870] Avg episode reward: [(0, '12.141')] -[2024-09-21 00:25:07,211][04656] Updated weights for policy 0, policy_version 630 (0.0020) -[2024-09-21 00:25:08,144][01870] Fps is (10 sec: 3686.3, 60 sec: 3481.6, 300 sec: 3346.2). Total num frames: 2580480. Throughput: 0: 872.7. Samples: 643876. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) -[2024-09-21 00:25:08,149][01870] Avg episode reward: [(0, '13.271')] -[2024-09-21 00:25:08,161][04643] Saving new best policy, reward=13.271! -[2024-09-21 00:25:13,143][01870] Fps is (10 sec: 3686.4, 60 sec: 3413.3, 300 sec: 3346.2). Total num frames: 2596864. Throughput: 0: 871.2. Samples: 648734. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) -[2024-09-21 00:25:13,151][01870] Avg episode reward: [(0, '13.698')] -[2024-09-21 00:25:13,153][04643] Saving new best policy, reward=13.698! -[2024-09-21 00:25:18,144][01870] Fps is (10 sec: 2867.1, 60 sec: 3345.1, 300 sec: 3332.3). Total num frames: 2609152. Throughput: 0: 823.0. Samples: 652878. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) -[2024-09-21 00:25:18,146][01870] Avg episode reward: [(0, '13.537')] -[2024-09-21 00:25:18,162][04643] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000637_2609152.pth... -[2024-09-21 00:25:18,293][04643] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000441_1806336.pth -[2024-09-21 00:25:20,350][04656] Updated weights for policy 0, policy_version 640 (0.0027) -[2024-09-21 00:25:23,143][01870] Fps is (10 sec: 3276.8, 60 sec: 3481.6, 300 sec: 3360.2). Total num frames: 2629632. Throughput: 0: 838.9. Samples: 655972. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) -[2024-09-21 00:25:23,149][01870] Avg episode reward: [(0, '15.073')] -[2024-09-21 00:25:23,151][04643] Saving new best policy, reward=15.073! -[2024-09-21 00:25:28,143][01870] Fps is (10 sec: 4096.2, 60 sec: 3481.6, 300 sec: 3401.8). Total num frames: 2650112. Throughput: 0: 891.3. Samples: 662118. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) -[2024-09-21 00:25:28,146][01870] Avg episode reward: [(0, '14.494')] -[2024-09-21 00:25:32,610][04656] Updated weights for policy 0, policy_version 650 (0.0025) -[2024-09-21 00:25:33,143][01870] Fps is (10 sec: 3276.8, 60 sec: 3345.1, 300 sec: 3374.0). Total num frames: 2662400. Throughput: 0: 834.9. Samples: 665920. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) -[2024-09-21 00:25:33,146][01870] Avg episode reward: [(0, '14.479')] -[2024-09-21 00:25:38,143][01870] Fps is (10 sec: 2867.2, 60 sec: 3413.3, 300 sec: 3360.1). Total num frames: 2678784. Throughput: 0: 818.4. Samples: 668262. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) -[2024-09-21 00:25:38,148][01870] Avg episode reward: [(0, '14.870')] -[2024-09-21 00:25:43,146][01870] Fps is (10 sec: 2866.4, 60 sec: 3344.9, 300 sec: 3360.1). Total num frames: 2691072. Throughput: 0: 828.4. Samples: 673008. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) -[2024-09-21 00:25:43,149][01870] Avg episode reward: [(0, '15.556')] -[2024-09-21 00:25:43,154][04643] Saving new best policy, reward=15.556! -[2024-09-21 00:25:47,591][04656] Updated weights for policy 0, policy_version 660 (0.0040) -[2024-09-21 00:25:48,143][01870] Fps is (10 sec: 2457.6, 60 sec: 3208.5, 300 sec: 3346.2). Total num frames: 2703360. Throughput: 0: 787.5. Samples: 676330. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) -[2024-09-21 00:25:48,148][01870] Avg episode reward: [(0, '15.610')] -[2024-09-21 00:25:48,156][04643] Saving new best policy, reward=15.610! -[2024-09-21 00:25:53,143][01870] Fps is (10 sec: 2458.3, 60 sec: 3072.1, 300 sec: 3318.5). Total num frames: 2715648. Throughput: 0: 760.8. Samples: 678112. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) -[2024-09-21 00:25:53,146][01870] Avg episode reward: [(0, '15.683')] -[2024-09-21 00:25:53,152][04643] Saving new best policy, reward=15.683! -[2024-09-21 00:25:58,143][01870] Fps is (10 sec: 3276.8, 60 sec: 3208.5, 300 sec: 3318.5). Total num frames: 2736128. Throughput: 0: 769.6. Samples: 683366. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) -[2024-09-21 00:25:58,148][01870] Avg episode reward: [(0, '15.555')] -[2024-09-21 00:25:59,518][04656] Updated weights for policy 0, policy_version 670 (0.0029) -[2024-09-21 00:26:03,151][01870] Fps is (10 sec: 4093.0, 60 sec: 3276.4, 300 sec: 3360.0). Total num frames: 2756608. Throughput: 0: 817.7. Samples: 689682. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) -[2024-09-21 00:26:03,154][01870] Avg episode reward: [(0, '16.176')] -[2024-09-21 00:26:03,160][04643] Saving new best policy, reward=16.176! -[2024-09-21 00:26:08,143][01870] Fps is (10 sec: 3276.8, 60 sec: 3140.3, 300 sec: 3332.3). Total num frames: 2768896. Throughput: 0: 793.8. Samples: 691692. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) -[2024-09-21 00:26:08,146][01870] Avg episode reward: [(0, '16.495')] -[2024-09-21 00:26:08,159][04643] Saving new best policy, reward=16.495! -[2024-09-21 00:26:12,578][04656] Updated weights for policy 0, policy_version 680 (0.0033) -[2024-09-21 00:26:13,143][01870] Fps is (10 sec: 2869.3, 60 sec: 3140.3, 300 sec: 3318.5). Total num frames: 2785280. Throughput: 0: 745.8. Samples: 695678. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) -[2024-09-21 00:26:13,147][01870] Avg episode reward: [(0, '15.764')] -[2024-09-21 00:26:18,144][01870] Fps is (10 sec: 3686.3, 60 sec: 3276.8, 300 sec: 3346.2). Total num frames: 2805760. Throughput: 0: 800.7. Samples: 701950. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) -[2024-09-21 00:26:18,146][01870] Avg episode reward: [(0, '15.912')] -[2024-09-21 00:26:23,143][01870] Fps is (10 sec: 3686.4, 60 sec: 3208.5, 300 sec: 3346.2). Total num frames: 2822144. Throughput: 0: 818.4. Samples: 705090. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) -[2024-09-21 00:26:23,150][01870] Avg episode reward: [(0, '15.351')] -[2024-09-21 00:26:23,166][04656] Updated weights for policy 0, policy_version 690 (0.0027) -[2024-09-21 00:26:28,143][01870] Fps is (10 sec: 3276.9, 60 sec: 3140.3, 300 sec: 3332.3). Total num frames: 2838528. Throughput: 0: 799.7. Samples: 708994. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) -[2024-09-21 00:26:28,147][01870] Avg episode reward: [(0, '15.771')] -[2024-09-21 00:26:33,145][01870] Fps is (10 sec: 3276.3, 60 sec: 3208.5, 300 sec: 3332.4). Total num frames: 2854912. Throughput: 0: 851.0. Samples: 714624. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) -[2024-09-21 00:26:33,147][01870] Avg episode reward: [(0, '15.552')] -[2024-09-21 00:26:35,110][04656] Updated weights for policy 0, policy_version 700 (0.0034) -[2024-09-21 00:26:38,146][01870] Fps is (10 sec: 4095.1, 60 sec: 3344.9, 300 sec: 3374.0). Total num frames: 2879488. Throughput: 0: 880.8. Samples: 717750. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) -[2024-09-21 00:26:38,150][01870] Avg episode reward: [(0, '15.990')] -[2024-09-21 00:26:43,143][01870] Fps is (10 sec: 3686.9, 60 sec: 3345.2, 300 sec: 3346.2). Total num frames: 2891776. Throughput: 0: 872.0. Samples: 722606. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) -[2024-09-21 00:26:43,153][01870] Avg episode reward: [(0, '14.619')] -[2024-09-21 00:26:48,145][01870] Fps is (10 sec: 2457.9, 60 sec: 3345.0, 300 sec: 3318.4). Total num frames: 2904064. Throughput: 0: 827.8. Samples: 726926. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) -[2024-09-21 00:26:48,151][01870] Avg episode reward: [(0, '15.293')] -[2024-09-21 00:26:48,177][04656] Updated weights for policy 0, policy_version 710 (0.0027) -[2024-09-21 00:26:53,143][01870] Fps is (10 sec: 3686.4, 60 sec: 3549.9, 300 sec: 3346.2). Total num frames: 2928640. Throughput: 0: 853.6. Samples: 730102. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) -[2024-09-21 00:26:53,146][01870] Avg episode reward: [(0, '15.915')] -[2024-09-21 00:26:58,143][01870] Fps is (10 sec: 4096.5, 60 sec: 3481.6, 300 sec: 3360.1). Total num frames: 2945024. Throughput: 0: 899.7. Samples: 736166. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) -[2024-09-21 00:26:58,148][01870] Avg episode reward: [(0, '16.285')] -[2024-09-21 00:26:59,046][04656] Updated weights for policy 0, policy_version 720 (0.0022) -[2024-09-21 00:27:03,144][01870] Fps is (10 sec: 2867.1, 60 sec: 3345.5, 300 sec: 3332.3). Total num frames: 2957312. Throughput: 0: 843.3. Samples: 739898. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) -[2024-09-21 00:27:03,150][01870] Avg episode reward: [(0, '16.785')] -[2024-09-21 00:27:03,161][04643] Saving new best policy, reward=16.785! -[2024-09-21 00:27:08,143][01870] Fps is (10 sec: 3276.8, 60 sec: 3481.6, 300 sec: 3332.3). Total num frames: 2977792. Throughput: 0: 829.1. Samples: 742400. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) -[2024-09-21 00:27:08,151][01870] Avg episode reward: [(0, '17.199')] -[2024-09-21 00:27:08,167][04643] Saving new best policy, reward=17.199! -[2024-09-21 00:27:11,059][04656] Updated weights for policy 0, policy_version 730 (0.0037) -[2024-09-21 00:27:13,143][01870] Fps is (10 sec: 4096.1, 60 sec: 3549.9, 300 sec: 3360.1). Total num frames: 2998272. Throughput: 0: 877.7. Samples: 748490. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) -[2024-09-21 00:27:13,146][01870] Avg episode reward: [(0, '18.024')] -[2024-09-21 00:27:13,154][04643] Saving new best policy, reward=18.024! -[2024-09-21 00:27:18,143][01870] Fps is (10 sec: 3276.8, 60 sec: 3413.3, 300 sec: 3346.2). Total num frames: 3010560. Throughput: 0: 856.5. Samples: 753166. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) -[2024-09-21 00:27:18,145][01870] Avg episode reward: [(0, '17.255')] -[2024-09-21 00:27:18,158][04643] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000735_3010560.pth... -[2024-09-21 00:27:18,318][04643] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000537_2199552.pth -[2024-09-21 00:27:23,143][01870] Fps is (10 sec: 2867.2, 60 sec: 3413.3, 300 sec: 3332.3). Total num frames: 3026944. Throughput: 0: 828.1. Samples: 755012. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) -[2024-09-21 00:27:23,149][01870] Avg episode reward: [(0, '17.162')] -[2024-09-21 00:27:24,146][04656] Updated weights for policy 0, policy_version 740 (0.0027) -[2024-09-21 00:27:28,143][01870] Fps is (10 sec: 3686.4, 60 sec: 3481.6, 300 sec: 3346.2). Total num frames: 3047424. Throughput: 0: 848.1. Samples: 760770. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) -[2024-09-21 00:27:28,149][01870] Avg episode reward: [(0, '16.961')] -[2024-09-21 00:27:33,143][01870] Fps is (10 sec: 3686.4, 60 sec: 3481.7, 300 sec: 3360.1). Total num frames: 3063808. Throughput: 0: 882.9. Samples: 766656. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) -[2024-09-21 00:27:33,148][01870] Avg episode reward: [(0, '17.179')] -[2024-09-21 00:27:35,496][04656] Updated weights for policy 0, policy_version 750 (0.0027) -[2024-09-21 00:27:38,143][01870] Fps is (10 sec: 2867.2, 60 sec: 3276.9, 300 sec: 3332.3). Total num frames: 3076096. Throughput: 0: 854.5. Samples: 768556. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) -[2024-09-21 00:27:38,149][01870] Avg episode reward: [(0, '17.916')] -[2024-09-21 00:27:43,143][01870] Fps is (10 sec: 3276.8, 60 sec: 3413.3, 300 sec: 3332.3). Total num frames: 3096576. Throughput: 0: 819.1. Samples: 773024. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) -[2024-09-21 00:27:43,146][01870] Avg episode reward: [(0, '18.378')] -[2024-09-21 00:27:43,149][04643] Saving new best policy, reward=18.378! -[2024-09-21 00:27:47,164][04656] Updated weights for policy 0, policy_version 760 (0.0027) -[2024-09-21 00:27:48,144][01870] Fps is (10 sec: 3686.3, 60 sec: 3481.7, 300 sec: 3346.2). Total num frames: 3112960. Throughput: 0: 870.8. Samples: 779086. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) -[2024-09-21 00:27:48,148][01870] Avg episode reward: [(0, '18.804')] -[2024-09-21 00:27:48,225][04643] Saving new best policy, reward=18.804! -[2024-09-21 00:27:53,143][01870] Fps is (10 sec: 3276.8, 60 sec: 3345.1, 300 sec: 3346.2). Total num frames: 3129344. Throughput: 0: 870.2. Samples: 781558. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) -[2024-09-21 00:27:53,148][01870] Avg episode reward: [(0, '18.556')] -[2024-09-21 00:27:58,143][01870] Fps is (10 sec: 2867.2, 60 sec: 3276.8, 300 sec: 3346.2). Total num frames: 3141632. Throughput: 0: 813.7. Samples: 785106. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) -[2024-09-21 00:27:58,146][01870] Avg episode reward: [(0, '19.523')] -[2024-09-21 00:27:58,161][04643] Saving new best policy, reward=19.523! -[2024-09-21 00:28:00,857][04656] Updated weights for policy 0, policy_version 770 (0.0052) -[2024-09-21 00:28:03,143][01870] Fps is (10 sec: 3276.8, 60 sec: 3413.4, 300 sec: 3374.0). Total num frames: 3162112. Throughput: 0: 833.9. Samples: 790690. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) -[2024-09-21 00:28:03,146][01870] Avg episode reward: [(0, '19.641')] -[2024-09-21 00:28:03,154][04643] Saving new best policy, reward=19.641! -[2024-09-21 00:28:08,152][01870] Fps is (10 sec: 3683.3, 60 sec: 3344.6, 300 sec: 3387.8). Total num frames: 3178496. Throughput: 0: 858.4. Samples: 793646. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) -[2024-09-21 00:28:08,161][01870] Avg episode reward: [(0, '18.818')] -[2024-09-21 00:28:13,147][01870] Fps is (10 sec: 2866.2, 60 sec: 3208.4, 300 sec: 3360.1). Total num frames: 3190784. Throughput: 0: 828.7. Samples: 798066. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) -[2024-09-21 00:28:13,157][01870] Avg episode reward: [(0, '17.993')] -[2024-09-21 00:28:13,505][04656] Updated weights for policy 0, policy_version 780 (0.0026) -[2024-09-21 00:28:18,143][01870] Fps is (10 sec: 2869.6, 60 sec: 3276.8, 300 sec: 3346.2). Total num frames: 3207168. Throughput: 0: 801.5. Samples: 802724. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) -[2024-09-21 00:28:18,147][01870] Avg episode reward: [(0, '17.388')] -[2024-09-21 00:28:23,143][01870] Fps is (10 sec: 2868.2, 60 sec: 3208.5, 300 sec: 3346.2). Total num frames: 3219456. Throughput: 0: 804.4. Samples: 804756. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) -[2024-09-21 00:28:23,146][01870] Avg episode reward: [(0, '16.958')] -[2024-09-21 00:28:28,144][01870] Fps is (10 sec: 2457.5, 60 sec: 3072.0, 300 sec: 3332.3). Total num frames: 3231744. Throughput: 0: 784.7. Samples: 808334. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) -[2024-09-21 00:28:28,147][01870] Avg episode reward: [(0, '16.429')] -[2024-09-21 00:28:28,327][04656] Updated weights for policy 0, policy_version 790 (0.0039) -[2024-09-21 00:28:33,143][01870] Fps is (10 sec: 2867.2, 60 sec: 3072.0, 300 sec: 3318.5). Total num frames: 3248128. Throughput: 0: 733.4. Samples: 812088. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) -[2024-09-21 00:28:33,148][01870] Avg episode reward: [(0, '16.094')] -[2024-09-21 00:28:38,143][01870] Fps is (10 sec: 3277.0, 60 sec: 3140.3, 300 sec: 3318.5). Total num frames: 3264512. Throughput: 0: 740.4. Samples: 814878. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) -[2024-09-21 00:28:38,150][01870] Avg episode reward: [(0, '15.722')] -[2024-09-21 00:28:40,300][04656] Updated weights for policy 0, policy_version 800 (0.0026) -[2024-09-21 00:28:43,144][01870] Fps is (10 sec: 3686.2, 60 sec: 3140.2, 300 sec: 3332.3). Total num frames: 3284992. Throughput: 0: 794.9. Samples: 820878. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) -[2024-09-21 00:28:43,146][01870] Avg episode reward: [(0, '15.757')] -[2024-09-21 00:28:48,147][01870] Fps is (10 sec: 3275.6, 60 sec: 3071.8, 300 sec: 3318.4). Total num frames: 3297280. Throughput: 0: 768.3. Samples: 825268. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) -[2024-09-21 00:28:48,153][01870] Avg episode reward: [(0, '16.044')] -[2024-09-21 00:28:53,143][01870] Fps is (10 sec: 2867.3, 60 sec: 3072.0, 300 sec: 3290.7). Total num frames: 3313664. Throughput: 0: 744.0. Samples: 827118. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) -[2024-09-21 00:28:53,147][01870] Avg episode reward: [(0, '15.716')] -[2024-09-21 00:28:53,398][04656] Updated weights for policy 0, policy_version 810 (0.0039) -[2024-09-21 00:28:58,143][01870] Fps is (10 sec: 3687.7, 60 sec: 3208.5, 300 sec: 3318.5). Total num frames: 3334144. Throughput: 0: 779.6. Samples: 833146. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) -[2024-09-21 00:28:58,146][01870] Avg episode reward: [(0, '16.244')] -[2024-09-21 00:29:03,144][01870] Fps is (10 sec: 3686.2, 60 sec: 3140.2, 300 sec: 3318.4). Total num frames: 3350528. Throughput: 0: 798.6. Samples: 838660. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) -[2024-09-21 00:29:03,151][01870] Avg episode reward: [(0, '16.312')] -[2024-09-21 00:29:05,008][04656] Updated weights for policy 0, policy_version 820 (0.0037) -[2024-09-21 00:29:08,145][01870] Fps is (10 sec: 3276.4, 60 sec: 3140.6, 300 sec: 3304.6). Total num frames: 3366912. Throughput: 0: 793.3. Samples: 840456. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) -[2024-09-21 00:29:08,152][01870] Avg episode reward: [(0, '16.809')] -[2024-09-21 00:29:13,143][01870] Fps is (10 sec: 3277.0, 60 sec: 3208.7, 300 sec: 3304.6). Total num frames: 3383296. Throughput: 0: 825.3. Samples: 845472. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) -[2024-09-21 00:29:13,146][01870] Avg episode reward: [(0, '18.130')] -[2024-09-21 00:29:16,268][04656] Updated weights for policy 0, policy_version 830 (0.0033) -[2024-09-21 00:29:18,143][01870] Fps is (10 sec: 3686.8, 60 sec: 3276.8, 300 sec: 3332.3). Total num frames: 3403776. Throughput: 0: 880.5. Samples: 851712. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) -[2024-09-21 00:29:18,146][01870] Avg episode reward: [(0, '17.139')] -[2024-09-21 00:29:18,215][04643] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000832_3407872.pth... -[2024-09-21 00:29:18,413][04643] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000637_2609152.pth -[2024-09-21 00:29:23,143][01870] Fps is (10 sec: 3276.8, 60 sec: 3276.8, 300 sec: 3304.6). Total num frames: 3416064. Throughput: 0: 866.2. Samples: 853856. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) -[2024-09-21 00:29:23,151][01870] Avg episode reward: [(0, '17.398')] -[2024-09-21 00:29:28,143][01870] Fps is (10 sec: 2867.2, 60 sec: 3345.1, 300 sec: 3290.7). Total num frames: 3432448. Throughput: 0: 820.6. Samples: 857806. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) -[2024-09-21 00:29:28,151][01870] Avg episode reward: [(0, '18.975')] -[2024-09-21 00:29:29,391][04656] Updated weights for policy 0, policy_version 840 (0.0039) -[2024-09-21 00:29:33,143][01870] Fps is (10 sec: 4096.0, 60 sec: 3481.6, 300 sec: 3332.3). Total num frames: 3457024. Throughput: 0: 860.2. Samples: 863974. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) -[2024-09-21 00:29:33,146][01870] Avg episode reward: [(0, '20.113')] -[2024-09-21 00:29:33,149][04643] Saving new best policy, reward=20.113! -[2024-09-21 00:29:38,147][01870] Fps is (10 sec: 4094.7, 60 sec: 3481.4, 300 sec: 3332.3). Total num frames: 3473408. Throughput: 0: 885.9. Samples: 866986. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) -[2024-09-21 00:29:38,150][01870] Avg episode reward: [(0, '20.820')] -[2024-09-21 00:29:38,165][04643] Saving new best policy, reward=20.820! -[2024-09-21 00:29:41,637][04656] Updated weights for policy 0, policy_version 850 (0.0020) -[2024-09-21 00:29:43,143][01870] Fps is (10 sec: 2457.6, 60 sec: 3276.8, 300 sec: 3290.7). Total num frames: 3481600. Throughput: 0: 837.6. Samples: 870840. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) -[2024-09-21 00:29:43,149][01870] Avg episode reward: [(0, '20.193')] -[2024-09-21 00:29:48,143][01870] Fps is (10 sec: 2868.1, 60 sec: 3413.5, 300 sec: 3290.7). Total num frames: 3502080. Throughput: 0: 828.8. Samples: 875954. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) -[2024-09-21 00:29:48,151][01870] Avg episode reward: [(0, '21.155')] -[2024-09-21 00:29:48,162][04643] Saving new best policy, reward=21.155! -[2024-09-21 00:29:52,684][04656] Updated weights for policy 0, policy_version 860 (0.0017) -[2024-09-21 00:29:53,143][01870] Fps is (10 sec: 4096.0, 60 sec: 3481.6, 300 sec: 3318.5). Total num frames: 3522560. Throughput: 0: 855.3. Samples: 878944. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) -[2024-09-21 00:29:53,150][01870] Avg episode reward: [(0, '20.235')] -[2024-09-21 00:29:58,143][01870] Fps is (10 sec: 3276.8, 60 sec: 3345.1, 300 sec: 3304.6). Total num frames: 3534848. Throughput: 0: 857.6. Samples: 884066. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) -[2024-09-21 00:29:58,148][01870] Avg episode reward: [(0, '20.099')] -[2024-09-21 00:30:03,143][01870] Fps is (10 sec: 2867.2, 60 sec: 3345.1, 300 sec: 3290.7). Total num frames: 3551232. Throughput: 0: 811.0. Samples: 888206. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) -[2024-09-21 00:30:03,148][01870] Avg episode reward: [(0, '20.342')] -[2024-09-21 00:30:05,685][04656] Updated weights for policy 0, policy_version 870 (0.0019) -[2024-09-21 00:30:08,143][01870] Fps is (10 sec: 3686.4, 60 sec: 3413.4, 300 sec: 3304.6). Total num frames: 3571712. Throughput: 0: 832.5. Samples: 891318. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) -[2024-09-21 00:30:08,148][01870] Avg episode reward: [(0, '20.678')] -[2024-09-21 00:30:13,145][01870] Fps is (10 sec: 3685.8, 60 sec: 3413.2, 300 sec: 3318.4). Total num frames: 3588096. Throughput: 0: 879.2. Samples: 897372. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) -[2024-09-21 00:30:13,151][01870] Avg episode reward: [(0, '19.339')] -[2024-09-21 00:30:18,143][01870] Fps is (10 sec: 2867.2, 60 sec: 3276.8, 300 sec: 3290.7). Total num frames: 3600384. Throughput: 0: 825.5. Samples: 901122. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) -[2024-09-21 00:30:18,147][01870] Avg episode reward: [(0, '19.232')] -[2024-09-21 00:30:18,529][04656] Updated weights for policy 0, policy_version 880 (0.0032) -[2024-09-21 00:30:23,144][01870] Fps is (10 sec: 3277.2, 60 sec: 3413.3, 300 sec: 3290.7). Total num frames: 3620864. Throughput: 0: 812.2. Samples: 903532. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) -[2024-09-21 00:30:23,146][01870] Avg episode reward: [(0, '17.255')] -[2024-09-21 00:30:28,143][01870] Fps is (10 sec: 4096.0, 60 sec: 3481.6, 300 sec: 3318.5). Total num frames: 3641344. Throughput: 0: 868.4. Samples: 909920. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) -[2024-09-21 00:30:28,146][01870] Avg episode reward: [(0, '18.116')] -[2024-09-21 00:30:28,434][04656] Updated weights for policy 0, policy_version 890 (0.0054) -[2024-09-21 00:30:33,143][01870] Fps is (10 sec: 3686.5, 60 sec: 3345.1, 300 sec: 3318.5). Total num frames: 3657728. Throughput: 0: 863.9. Samples: 914828. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) -[2024-09-21 00:30:33,146][01870] Avg episode reward: [(0, '17.916')] -[2024-09-21 00:30:38,143][01870] Fps is (10 sec: 2867.2, 60 sec: 3277.0, 300 sec: 3318.5). Total num frames: 3670016. Throughput: 0: 839.6. Samples: 916726. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) -[2024-09-21 00:30:38,146][01870] Avg episode reward: [(0, '18.571')] -[2024-09-21 00:30:41,145][04656] Updated weights for policy 0, policy_version 900 (0.0038) -[2024-09-21 00:30:43,143][01870] Fps is (10 sec: 3276.8, 60 sec: 3481.6, 300 sec: 3346.2). Total num frames: 3690496. Throughput: 0: 852.7. Samples: 922436. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) -[2024-09-21 00:30:43,151][01870] Avg episode reward: [(0, '19.973')] -[2024-09-21 00:30:48,143][01870] Fps is (10 sec: 4096.0, 60 sec: 3481.6, 300 sec: 3374.0). Total num frames: 3710976. Throughput: 0: 890.7. Samples: 928286. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) -[2024-09-21 00:30:48,151][01870] Avg episode reward: [(0, '21.750')] -[2024-09-21 00:30:48,163][04643] Saving new best policy, reward=21.750! -[2024-09-21 00:30:53,143][01870] Fps is (10 sec: 3276.8, 60 sec: 3345.1, 300 sec: 3346.2). Total num frames: 3723264. Throughput: 0: 861.8. Samples: 930098. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) -[2024-09-21 00:30:53,150][01870] Avg episode reward: [(0, '21.429')] -[2024-09-21 00:30:53,981][04656] Updated weights for policy 0, policy_version 910 (0.0023) -[2024-09-21 00:30:58,145][01870] Fps is (10 sec: 2866.8, 60 sec: 3413.3, 300 sec: 3332.4). Total num frames: 3739648. Throughput: 0: 828.3. Samples: 934644. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) -[2024-09-21 00:30:58,147][01870] Avg episode reward: [(0, '20.683')] -[2024-09-21 00:31:03,143][01870] Fps is (10 sec: 2867.2, 60 sec: 3345.1, 300 sec: 3332.3). Total num frames: 3751936. Throughput: 0: 837.4. Samples: 938804. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) -[2024-09-21 00:31:03,146][01870] Avg episode reward: [(0, '19.400')] -[2024-09-21 00:31:08,144][01870] Fps is (10 sec: 2457.9, 60 sec: 3208.5, 300 sec: 3318.5). Total num frames: 3764224. Throughput: 0: 825.2. Samples: 940668. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) -[2024-09-21 00:31:08,146][01870] Avg episode reward: [(0, '19.036')] -[2024-09-21 00:31:08,452][04656] Updated weights for policy 0, policy_version 920 (0.0032) -[2024-09-21 00:31:13,143][01870] Fps is (10 sec: 2867.2, 60 sec: 3208.6, 300 sec: 3304.6). Total num frames: 3780608. Throughput: 0: 768.6. Samples: 944506. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) -[2024-09-21 00:31:13,146][01870] Avg episode reward: [(0, '19.591')] -[2024-09-21 00:31:18,144][01870] Fps is (10 sec: 3686.3, 60 sec: 3345.0, 300 sec: 3318.4). Total num frames: 3801088. Throughput: 0: 785.1. Samples: 950156. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) -[2024-09-21 00:31:18,147][01870] Avg episode reward: [(0, '18.234')] -[2024-09-21 00:31:18,168][04643] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000928_3801088.pth... -[2024-09-21 00:31:18,307][04643] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000735_3010560.pth -[2024-09-21 00:31:20,207][04656] Updated weights for policy 0, policy_version 930 (0.0039) -[2024-09-21 00:31:23,143][01870] Fps is (10 sec: 4096.0, 60 sec: 3345.1, 300 sec: 3332.3). Total num frames: 3821568. Throughput: 0: 810.9. Samples: 953216. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) -[2024-09-21 00:31:23,152][01870] Avg episode reward: [(0, '18.275')] -[2024-09-21 00:31:28,150][01870] Fps is (10 sec: 2865.5, 60 sec: 3139.9, 300 sec: 3304.5). Total num frames: 3829760. Throughput: 0: 789.0. Samples: 957946. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) -[2024-09-21 00:31:28,156][01870] Avg episode reward: [(0, '19.006')] -[2024-09-21 00:31:32,842][04656] Updated weights for policy 0, policy_version 940 (0.0035) -[2024-09-21 00:31:33,143][01870] Fps is (10 sec: 2867.2, 60 sec: 3208.5, 300 sec: 3290.7). Total num frames: 3850240. Throughput: 0: 763.0. Samples: 962620. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) -[2024-09-21 00:31:33,150][01870] Avg episode reward: [(0, '19.926')] -[2024-09-21 00:31:38,143][01870] Fps is (10 sec: 4098.6, 60 sec: 3345.1, 300 sec: 3318.5). Total num frames: 3870720. Throughput: 0: 792.6. Samples: 965766. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) -[2024-09-21 00:31:38,146][01870] Avg episode reward: [(0, '18.388')] -[2024-09-21 00:31:43,145][01870] Fps is (10 sec: 3685.9, 60 sec: 3276.7, 300 sec: 3332.3). Total num frames: 3887104. Throughput: 0: 822.7. Samples: 971666. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) -[2024-09-21 00:31:43,147][01870] Avg episode reward: [(0, '19.375')] -[2024-09-21 00:31:44,101][04656] Updated weights for policy 0, policy_version 950 (0.0039) -[2024-09-21 00:31:48,145][01870] Fps is (10 sec: 2866.9, 60 sec: 3140.2, 300 sec: 3290.7). Total num frames: 3899392. Throughput: 0: 813.9. Samples: 975432. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) -[2024-09-21 00:31:48,149][01870] Avg episode reward: [(0, '18.942')] -[2024-09-21 00:31:53,143][01870] Fps is (10 sec: 3277.2, 60 sec: 3276.8, 300 sec: 3304.6). Total num frames: 3919872. Throughput: 0: 835.2. Samples: 978250. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) -[2024-09-21 00:31:53,146][01870] Avg episode reward: [(0, '19.747')] -[2024-09-21 00:31:55,501][04656] Updated weights for policy 0, policy_version 960 (0.0027) -[2024-09-21 00:31:58,143][01870] Fps is (10 sec: 4096.5, 60 sec: 3345.1, 300 sec: 3332.3). Total num frames: 3940352. Throughput: 0: 893.9. Samples: 984732. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) -[2024-09-21 00:31:58,146][01870] Avg episode reward: [(0, '20.028')] -[2024-09-21 00:32:03,143][01870] Fps is (10 sec: 3686.4, 60 sec: 3413.3, 300 sec: 3318.5). Total num frames: 3956736. Throughput: 0: 873.5. Samples: 989462. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) -[2024-09-21 00:32:03,147][01870] Avg episode reward: [(0, '21.355')] -[2024-09-21 00:32:07,816][04656] Updated weights for policy 0, policy_version 970 (0.0039) -[2024-09-21 00:32:08,143][01870] Fps is (10 sec: 3276.8, 60 sec: 3481.6, 300 sec: 3304.6). Total num frames: 3973120. Throughput: 0: 849.8. Samples: 991456. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) -[2024-09-21 00:32:08,147][01870] Avg episode reward: [(0, '21.571')] -[2024-09-21 00:32:13,143][01870] Fps is (10 sec: 3686.4, 60 sec: 3549.9, 300 sec: 3332.3). Total num frames: 3993600. Throughput: 0: 882.5. Samples: 997654. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) -[2024-09-21 00:32:13,146][01870] Avg episode reward: [(0, '21.708')] -[2024-09-21 00:32:15,830][01870] Component Batcher_0 stopped! -[2024-09-21 00:32:15,830][04643] Stopping Batcher_0... -[2024-09-21 00:32:15,837][04643] Loop batcher_evt_loop terminating... -[2024-09-21 00:32:15,840][04643] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... -[2024-09-21 00:32:15,882][04656] Weights refcount: 2 0 -[2024-09-21 00:32:15,886][04656] Stopping InferenceWorker_p0-w0... -[2024-09-21 00:32:15,887][04656] Loop inference_proc0-0_evt_loop terminating... -[2024-09-21 00:32:15,886][01870] Component InferenceWorker_p0-w0 stopped! -[2024-09-21 00:32:15,989][04643] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000832_3407872.pth -[2024-09-21 00:32:16,009][04643] Saving new best policy, reward=21.819! -[2024-09-21 00:32:16,196][04643] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... -[2024-09-21 00:32:16,501][01870] Component RolloutWorker_w4 stopped! -[2024-09-21 00:32:16,503][04659] Stopping RolloutWorker_w4... -[2024-09-21 00:32:16,504][04659] Loop rollout_proc4_evt_loop terminating... -[2024-09-21 00:32:16,516][04643] Stopping LearnerWorker_p0... -[2024-09-21 00:32:16,518][04643] Loop learner_proc0_evt_loop terminating... -[2024-09-21 00:32:16,518][01870] Component LearnerWorker_p0 stopped! -[2024-09-21 00:32:16,530][01870] Component RolloutWorker_w2 stopped! -[2024-09-21 00:32:16,532][04658] Stopping RolloutWorker_w2... -[2024-09-21 00:32:16,532][04658] Loop rollout_proc2_evt_loop terminating... -[2024-09-21 00:32:16,569][01870] Component RolloutWorker_w0 stopped! -[2024-09-21 00:32:16,571][04657] Stopping RolloutWorker_w0... -[2024-09-21 00:32:16,572][04657] Loop rollout_proc0_evt_loop terminating... -[2024-09-21 00:32:16,609][04660] Stopping RolloutWorker_w1... -[2024-09-21 00:32:16,609][04660] Loop rollout_proc1_evt_loop terminating... -[2024-09-21 00:32:16,608][01870] Component RolloutWorker_w6 stopped! -[2024-09-21 00:32:16,614][04663] Stopping RolloutWorker_w6... -[2024-09-21 00:32:16,614][04663] Loop rollout_proc6_evt_loop terminating... -[2024-09-21 00:32:16,614][01870] Component RolloutWorker_w1 stopped! -[2024-09-21 00:32:16,618][01870] Component RolloutWorker_w7 stopped! -[2024-09-21 00:32:16,616][04664] Stopping RolloutWorker_w7... -[2024-09-21 00:32:16,622][04662] Stopping RolloutWorker_w5... -[2024-09-21 00:32:16,622][01870] Component RolloutWorker_w5 stopped! -[2024-09-21 00:32:16,627][04662] Loop rollout_proc5_evt_loop terminating... -[2024-09-21 00:32:16,633][04664] Loop rollout_proc7_evt_loop terminating... -[2024-09-21 00:32:16,711][04661] Stopping RolloutWorker_w3... -[2024-09-21 00:32:16,710][01870] Component RolloutWorker_w3 stopped! -[2024-09-21 00:32:16,715][01870] Waiting for process learner_proc0 to stop... -[2024-09-21 00:32:16,711][04661] Loop rollout_proc3_evt_loop terminating... -[2024-09-21 00:32:18,468][01870] Waiting for process inference_proc0-0 to join... -[2024-09-21 00:32:18,634][01870] Waiting for process rollout_proc0 to join... -[2024-09-21 00:32:21,448][01870] Waiting for process rollout_proc1 to join... -[2024-09-21 00:32:21,453][01870] Waiting for process rollout_proc2 to join... -[2024-09-21 00:32:21,458][01870] Waiting for process rollout_proc3 to join... -[2024-09-21 00:32:21,461][01870] Waiting for process rollout_proc4 to join... -[2024-09-21 00:32:21,467][01870] Waiting for process rollout_proc5 to join... -[2024-09-21 00:32:21,470][01870] Waiting for process rollout_proc6 to join... -[2024-09-21 00:32:21,472][01870] Waiting for process rollout_proc7 to join... -[2024-09-21 00:32:21,478][01870] Batcher 0 profile tree view: -batching: 28.6873, releasing_batches: 0.0347 -[2024-09-21 00:32:21,480][01870] InferenceWorker_p0-w0 profile tree view: +[2024-09-21 02:04:33,821][02531] Using optimizer +[2024-09-21 02:04:34,565][02531] No checkpoints found +[2024-09-21 02:04:34,565][02531] Did not load from checkpoint, starting from scratch! +[2024-09-21 02:04:34,565][02531] Initialized policy 0 weights for model version 0 +[2024-09-21 02:04:34,570][02531] LearnerWorker_p0 finished initialization! +[2024-09-21 02:04:34,572][02531] Using GPUs [0] for process 0 (actually maps to GPUs [0]) +[2024-09-21 02:04:34,572][00440] Heartbeat connected on LearnerWorker_p0 +[2024-09-21 02:04:34,809][02544] RunningMeanStd input shape: (3, 72, 128) +[2024-09-21 02:04:34,810][02544] RunningMeanStd input shape: (1,) +[2024-09-21 02:04:34,823][02544] ConvEncoder: input_channels=3 +[2024-09-21 02:04:34,935][02544] Conv encoder output size: 512 +[2024-09-21 02:04:34,935][02544] Policy head output size: 512 +[2024-09-21 02:04:34,995][00440] Inference worker 0-0 is ready! +[2024-09-21 02:04:34,996][00440] All inference workers are ready! Signal rollout workers to start! +[2024-09-21 02:04:35,248][02546] Doom resolution: 160x120, resize resolution: (128, 72) +[2024-09-21 02:04:35,249][02547] Doom resolution: 160x120, resize resolution: (128, 72) +[2024-09-21 02:04:35,252][02552] Doom resolution: 160x120, resize resolution: (128, 72) +[2024-09-21 02:04:35,250][02548] Doom resolution: 160x120, resize resolution: (128, 72) +[2024-09-21 02:04:35,253][02550] Doom resolution: 160x120, resize resolution: (128, 72) +[2024-09-21 02:04:35,252][02551] Doom resolution: 160x120, resize resolution: (128, 72) +[2024-09-21 02:04:35,255][02549] Doom resolution: 160x120, resize resolution: (128, 72) +[2024-09-21 02:04:35,254][02545] Doom resolution: 160x120, resize resolution: (128, 72) +[2024-09-21 02:04:35,974][00440] 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) +[2024-09-21 02:04:36,359][02549] Decorrelating experience for 0 frames... +[2024-09-21 02:04:36,358][02551] Decorrelating experience for 0 frames... +[2024-09-21 02:04:36,990][02552] Decorrelating experience for 0 frames... +[2024-09-21 02:04:36,996][02548] Decorrelating experience for 0 frames... +[2024-09-21 02:04:36,995][02546] Decorrelating experience for 0 frames... +[2024-09-21 02:04:36,995][02550] Decorrelating experience for 0 frames... +[2024-09-21 02:04:37,183][02545] Decorrelating experience for 0 frames... +[2024-09-21 02:04:37,203][02549] Decorrelating experience for 32 frames... +[2024-09-21 02:04:37,665][02551] Decorrelating experience for 32 frames... +[2024-09-21 02:04:38,171][02551] Decorrelating experience for 64 frames... +[2024-09-21 02:04:38,354][02552] Decorrelating experience for 32 frames... +[2024-09-21 02:04:38,356][02548] Decorrelating experience for 32 frames... +[2024-09-21 02:04:38,358][02546] Decorrelating experience for 32 frames... +[2024-09-21 02:04:38,708][02550] Decorrelating experience for 32 frames... +[2024-09-21 02:04:38,900][02545] Decorrelating experience for 32 frames... +[2024-09-21 02:04:39,910][02547] Decorrelating experience for 0 frames... +[2024-09-21 02:04:40,070][02551] Decorrelating experience for 96 frames... +[2024-09-21 02:04:40,958][02552] Decorrelating experience for 64 frames... +[2024-09-21 02:04:40,957][02546] Decorrelating experience for 64 frames... +[2024-09-21 02:04:40,976][00440] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 0.0. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) +[2024-09-21 02:04:41,607][02550] Decorrelating experience for 64 frames... +[2024-09-21 02:04:41,840][02549] Decorrelating experience for 64 frames... +[2024-09-21 02:04:42,624][02548] Decorrelating experience for 64 frames... +[2024-09-21 02:04:43,231][02547] Decorrelating experience for 32 frames... +[2024-09-21 02:04:43,229][02545] Decorrelating experience for 64 frames... +[2024-09-21 02:04:43,794][02546] Decorrelating experience for 96 frames... +[2024-09-21 02:04:43,797][02552] Decorrelating experience for 96 frames... +[2024-09-21 02:04:45,546][02550] Decorrelating experience for 96 frames... +[2024-09-21 02:04:45,926][02548] Decorrelating experience for 96 frames... +[2024-09-21 02:04:45,974][00440] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 8.6. Samples: 86. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) +[2024-09-21 02:04:45,977][00440] Avg episode reward: [(0, '2.048')] +[2024-09-21 02:04:46,276][02549] Decorrelating experience for 96 frames... +[2024-09-21 02:04:46,394][02545] Decorrelating experience for 96 frames... +[2024-09-21 02:04:47,293][02547] Decorrelating experience for 64 frames... +[2024-09-21 02:04:49,026][02531] Signal inference workers to stop experience collection... +[2024-09-21 02:04:49,033][02544] InferenceWorker_p0-w0: stopping experience collection +[2024-09-21 02:04:49,527][02547] Decorrelating experience for 96 frames... +[2024-09-21 02:04:50,974][00440] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 175.1. Samples: 2626. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) +[2024-09-21 02:04:50,976][00440] Avg episode reward: [(0, '2.853')] +[2024-09-21 02:04:52,881][02531] Signal inference workers to resume experience collection... +[2024-09-21 02:04:52,882][02544] InferenceWorker_p0-w0: resuming experience collection +[2024-09-21 02:04:55,974][00440] Fps is (10 sec: 1638.4, 60 sec: 819.2, 300 sec: 819.2). Total num frames: 16384. Throughput: 0: 134.1. Samples: 2682. Policy #0 lag: (min: 0.0, avg: 1.4, max: 2.0) +[2024-09-21 02:04:55,977][00440] Avg episode reward: [(0, '3.380')] +[2024-09-21 02:05:00,974][00440] Fps is (10 sec: 2867.2, 60 sec: 1146.9, 300 sec: 1146.9). Total num frames: 28672. Throughput: 0: 263.9. Samples: 6598. Policy #0 lag: (min: 0.0, avg: 0.3, max: 2.0) +[2024-09-21 02:05:00,980][00440] Avg episode reward: [(0, '3.931')] +[2024-09-21 02:05:04,282][02544] Updated weights for policy 0, policy_version 10 (0.0020) +[2024-09-21 02:05:05,974][00440] Fps is (10 sec: 2867.2, 60 sec: 1501.9, 300 sec: 1501.9). Total num frames: 45056. Throughput: 0: 385.7. Samples: 11572. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2024-09-21 02:05:05,977][00440] Avg episode reward: [(0, '4.257')] +[2024-09-21 02:05:10,974][00440] Fps is (10 sec: 4096.0, 60 sec: 1989.5, 300 sec: 1989.5). Total num frames: 69632. Throughput: 0: 425.0. Samples: 14874. Policy #0 lag: (min: 0.0, avg: 0.3, max: 2.0) +[2024-09-21 02:05:10,977][00440] Avg episode reward: [(0, '4.494')] +[2024-09-21 02:05:13,540][02544] Updated weights for policy 0, policy_version 20 (0.0018) +[2024-09-21 02:05:15,974][00440] Fps is (10 sec: 4096.0, 60 sec: 2150.4, 300 sec: 2150.4). Total num frames: 86016. Throughput: 0: 530.1. Samples: 21206. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2024-09-21 02:05:15,981][00440] Avg episode reward: [(0, '4.487')] +[2024-09-21 02:05:20,974][00440] Fps is (10 sec: 3276.8, 60 sec: 2275.6, 300 sec: 2275.6). Total num frames: 102400. Throughput: 0: 563.5. Samples: 25358. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2024-09-21 02:05:20,976][00440] Avg episode reward: [(0, '4.389')] +[2024-09-21 02:05:20,985][02531] Saving new best policy, reward=4.389! +[2024-09-21 02:05:25,607][02544] Updated weights for policy 0, policy_version 30 (0.0036) +[2024-09-21 02:05:25,974][00440] Fps is (10 sec: 3686.3, 60 sec: 2457.6, 300 sec: 2457.6). Total num frames: 122880. Throughput: 0: 632.8. Samples: 28474. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2024-09-21 02:05:25,983][00440] Avg episode reward: [(0, '4.418')] +[2024-09-21 02:05:25,997][02531] Saving new best policy, reward=4.418! +[2024-09-21 02:05:30,974][00440] Fps is (10 sec: 4095.9, 60 sec: 2606.5, 300 sec: 2606.5). Total num frames: 143360. Throughput: 0: 778.1. Samples: 35102. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2024-09-21 02:05:30,979][00440] Avg episode reward: [(0, '4.624')] +[2024-09-21 02:05:30,983][02531] Saving new best policy, reward=4.624! +[2024-09-21 02:05:35,974][00440] Fps is (10 sec: 3276.9, 60 sec: 2594.1, 300 sec: 2594.1). Total num frames: 155648. Throughput: 0: 824.7. Samples: 39736. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2024-09-21 02:05:35,980][00440] Avg episode reward: [(0, '4.551')] +[2024-09-21 02:05:37,572][02544] Updated weights for policy 0, policy_version 40 (0.0043) +[2024-09-21 02:05:40,974][00440] Fps is (10 sec: 3276.9, 60 sec: 2935.6, 300 sec: 2709.7). Total num frames: 176128. Throughput: 0: 874.0. Samples: 42012. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2024-09-21 02:05:40,978][00440] Avg episode reward: [(0, '4.422')] +[2024-09-21 02:05:45,974][00440] Fps is (10 sec: 4505.6, 60 sec: 3345.1, 300 sec: 2867.2). Total num frames: 200704. Throughput: 0: 937.3. Samples: 48778. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2024-09-21 02:05:45,980][00440] Avg episode reward: [(0, '4.602')] +[2024-09-21 02:05:46,627][02544] Updated weights for policy 0, policy_version 50 (0.0027) +[2024-09-21 02:05:50,981][00440] Fps is (10 sec: 4093.0, 60 sec: 3617.7, 300 sec: 2894.2). Total num frames: 217088. Throughput: 0: 957.2. Samples: 54652. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2024-09-21 02:05:50,987][00440] Avg episode reward: [(0, '4.527')] +[2024-09-21 02:05:55,974][00440] Fps is (10 sec: 2867.2, 60 sec: 3549.9, 300 sec: 2867.2). Total num frames: 229376. Throughput: 0: 929.4. Samples: 56696. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2024-09-21 02:05:55,981][00440] Avg episode reward: [(0, '4.347')] +[2024-09-21 02:06:00,975][00440] Fps is (10 sec: 2459.1, 60 sec: 3549.8, 300 sec: 2843.1). Total num frames: 241664. Throughput: 0: 871.6. Samples: 60430. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2024-09-21 02:06:00,980][00440] Avg episode reward: [(0, '4.245')] +[2024-09-21 02:06:01,036][02544] Updated weights for policy 0, policy_version 60 (0.0034) +[2024-09-21 02:06:05,974][00440] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 2912.7). Total num frames: 262144. Throughput: 0: 902.8. Samples: 65984. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2024-09-21 02:06:05,979][00440] Avg episode reward: [(0, '4.608')] +[2024-09-21 02:06:05,990][02531] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000064_262144.pth... +[2024-09-21 02:06:10,974][00440] Fps is (10 sec: 3686.8, 60 sec: 3481.6, 300 sec: 2931.9). Total num frames: 278528. Throughput: 0: 888.0. Samples: 68432. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2024-09-21 02:06:10,979][00440] Avg episode reward: [(0, '4.718')] +[2024-09-21 02:06:10,984][02531] Saving new best policy, reward=4.718! +[2024-09-21 02:06:13,606][02544] Updated weights for policy 0, policy_version 70 (0.0018) +[2024-09-21 02:06:15,974][00440] Fps is (10 sec: 3276.8, 60 sec: 3481.6, 300 sec: 2949.1). Total num frames: 294912. Throughput: 0: 837.6. Samples: 72794. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2024-09-21 02:06:15,978][00440] Avg episode reward: [(0, '4.774')] +[2024-09-21 02:06:15,991][02531] Saving new best policy, reward=4.774! +[2024-09-21 02:06:20,974][00440] Fps is (10 sec: 3686.4, 60 sec: 3549.9, 300 sec: 3003.7). Total num frames: 315392. Throughput: 0: 877.3. Samples: 79214. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2024-09-21 02:06:20,980][00440] Avg episode reward: [(0, '4.712')] +[2024-09-21 02:06:23,024][02544] Updated weights for policy 0, policy_version 80 (0.0026) +[2024-09-21 02:06:25,974][00440] Fps is (10 sec: 4096.1, 60 sec: 3549.9, 300 sec: 3053.4). Total num frames: 335872. Throughput: 0: 897.8. Samples: 82414. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2024-09-21 02:06:25,979][00440] Avg episode reward: [(0, '4.499')] +[2024-09-21 02:06:30,974][00440] Fps is (10 sec: 3276.8, 60 sec: 3413.3, 300 sec: 3027.5). Total num frames: 348160. Throughput: 0: 840.2. Samples: 86588. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2024-09-21 02:06:30,979][00440] Avg episode reward: [(0, '4.419')] +[2024-09-21 02:06:34,844][02544] Updated weights for policy 0, policy_version 90 (0.0036) +[2024-09-21 02:06:35,974][00440] Fps is (10 sec: 3686.4, 60 sec: 3618.1, 300 sec: 3106.1). Total num frames: 372736. Throughput: 0: 847.3. Samples: 92774. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2024-09-21 02:06:35,981][00440] Avg episode reward: [(0, '4.629')] +[2024-09-21 02:06:40,975][00440] Fps is (10 sec: 4505.4, 60 sec: 3618.1, 300 sec: 3145.7). Total num frames: 393216. Throughput: 0: 877.8. Samples: 96196. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2024-09-21 02:06:40,979][00440] Avg episode reward: [(0, '4.924')] +[2024-09-21 02:06:40,981][02531] Saving new best policy, reward=4.924! +[2024-09-21 02:06:45,974][00440] Fps is (10 sec: 3276.8, 60 sec: 3413.3, 300 sec: 3119.3). Total num frames: 405504. Throughput: 0: 910.9. Samples: 101420. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2024-09-21 02:06:45,977][00440] Avg episode reward: [(0, '4.867')] +[2024-09-21 02:06:46,307][02544] Updated weights for policy 0, policy_version 100 (0.0022) +[2024-09-21 02:06:50,975][00440] Fps is (10 sec: 3276.5, 60 sec: 3481.9, 300 sec: 3155.4). Total num frames: 425984. Throughput: 0: 903.4. Samples: 106636. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) +[2024-09-21 02:06:50,981][00440] Avg episode reward: [(0, '5.093')] +[2024-09-21 02:06:50,984][02531] Saving new best policy, reward=5.093! +[2024-09-21 02:06:55,835][02544] Updated weights for policy 0, policy_version 110 (0.0046) +[2024-09-21 02:06:55,974][00440] Fps is (10 sec: 4505.6, 60 sec: 3686.4, 300 sec: 3218.3). Total num frames: 450560. Throughput: 0: 923.8. Samples: 110004. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2024-09-21 02:06:55,977][00440] Avg episode reward: [(0, '4.928')] +[2024-09-21 02:07:00,974][00440] Fps is (10 sec: 4096.5, 60 sec: 3754.7, 300 sec: 3220.3). Total num frames: 466944. Throughput: 0: 965.1. Samples: 116222. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2024-09-21 02:07:00,979][00440] Avg episode reward: [(0, '4.989')] +[2024-09-21 02:07:05,974][00440] Fps is (10 sec: 2867.2, 60 sec: 3618.1, 300 sec: 3194.9). Total num frames: 479232. Throughput: 0: 914.3. Samples: 120358. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2024-09-21 02:07:05,978][00440] Avg episode reward: [(0, '5.089')] +[2024-09-21 02:07:07,875][02544] Updated weights for policy 0, policy_version 120 (0.0026) +[2024-09-21 02:07:10,974][00440] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3250.4). Total num frames: 503808. Throughput: 0: 915.7. Samples: 123622. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2024-09-21 02:07:10,980][00440] Avg episode reward: [(0, '5.305')] +[2024-09-21 02:07:10,983][02531] Saving new best policy, reward=5.305! +[2024-09-21 02:07:15,974][00440] Fps is (10 sec: 4505.6, 60 sec: 3822.9, 300 sec: 3276.8). Total num frames: 524288. Throughput: 0: 974.2. Samples: 130426. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2024-09-21 02:07:15,977][00440] Avg episode reward: [(0, '5.082')] +[2024-09-21 02:07:17,969][02544] Updated weights for policy 0, policy_version 130 (0.0025) +[2024-09-21 02:07:20,975][00440] Fps is (10 sec: 3276.4, 60 sec: 3686.3, 300 sec: 3252.0). Total num frames: 536576. Throughput: 0: 939.0. Samples: 135032. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2024-09-21 02:07:20,979][00440] Avg episode reward: [(0, '5.060')] +[2024-09-21 02:07:25,974][00440] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3276.8). Total num frames: 557056. Throughput: 0: 914.7. Samples: 137358. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2024-09-21 02:07:25,977][00440] Avg episode reward: [(0, '5.321')] +[2024-09-21 02:07:25,989][02531] Saving new best policy, reward=5.321! +[2024-09-21 02:07:29,183][02544] Updated weights for policy 0, policy_version 140 (0.0044) +[2024-09-21 02:07:30,974][00440] Fps is (10 sec: 4506.1, 60 sec: 3891.2, 300 sec: 3323.6). Total num frames: 581632. Throughput: 0: 944.0. Samples: 143902. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2024-09-21 02:07:30,977][00440] Avg episode reward: [(0, '5.661')] +[2024-09-21 02:07:30,981][02531] Saving new best policy, reward=5.661! +[2024-09-21 02:07:35,974][00440] Fps is (10 sec: 4096.0, 60 sec: 3754.7, 300 sec: 3322.3). Total num frames: 598016. Throughput: 0: 954.2. Samples: 149574. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2024-09-21 02:07:35,977][00440] Avg episode reward: [(0, '5.651')] +[2024-09-21 02:07:40,974][00440] Fps is (10 sec: 2867.1, 60 sec: 3618.1, 300 sec: 3298.9). Total num frames: 610304. Throughput: 0: 923.9. Samples: 151578. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2024-09-21 02:07:40,982][00440] Avg episode reward: [(0, '5.616')] +[2024-09-21 02:07:41,018][02544] Updated weights for policy 0, policy_version 150 (0.0027) +[2024-09-21 02:07:45,974][00440] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3341.5). Total num frames: 634880. Throughput: 0: 918.9. Samples: 157574. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2024-09-21 02:07:45,981][00440] Avg episode reward: [(0, '5.418')] +[2024-09-21 02:07:50,170][02544] Updated weights for policy 0, policy_version 160 (0.0020) +[2024-09-21 02:07:50,976][00440] Fps is (10 sec: 4504.7, 60 sec: 3822.9, 300 sec: 3360.8). Total num frames: 655360. Throughput: 0: 978.3. Samples: 164382. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2024-09-21 02:07:50,979][00440] Avg episode reward: [(0, '5.663')] +[2024-09-21 02:07:50,983][02531] Saving new best policy, reward=5.663! +[2024-09-21 02:07:55,974][00440] Fps is (10 sec: 3276.7, 60 sec: 3618.1, 300 sec: 3338.2). Total num frames: 667648. Throughput: 0: 948.5. Samples: 166304. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2024-09-21 02:07:55,982][00440] Avg episode reward: [(0, '5.831')] +[2024-09-21 02:07:55,992][02531] Saving new best policy, reward=5.831! +[2024-09-21 02:08:00,974][00440] Fps is (10 sec: 3277.5, 60 sec: 3686.4, 300 sec: 3356.7). Total num frames: 688128. Throughput: 0: 900.5. Samples: 170950. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2024-09-21 02:08:00,977][00440] Avg episode reward: [(0, '6.218')] +[2024-09-21 02:08:00,980][02531] Saving new best policy, reward=6.218! +[2024-09-21 02:08:02,395][02544] Updated weights for policy 0, policy_version 170 (0.0035) +[2024-09-21 02:08:05,974][00440] Fps is (10 sec: 4505.7, 60 sec: 3891.2, 300 sec: 3393.8). Total num frames: 712704. Throughput: 0: 947.0. Samples: 177646. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2024-09-21 02:08:05,980][00440] Avg episode reward: [(0, '5.621')] +[2024-09-21 02:08:05,989][02531] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000174_712704.pth... +[2024-09-21 02:08:10,975][00440] Fps is (10 sec: 3686.0, 60 sec: 3686.3, 300 sec: 3372.0). Total num frames: 724992. Throughput: 0: 964.2. Samples: 180746. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2024-09-21 02:08:10,979][00440] Avg episode reward: [(0, '5.909')] +[2024-09-21 02:08:14,010][02544] Updated weights for policy 0, policy_version 180 (0.0032) +[2024-09-21 02:08:15,974][00440] Fps is (10 sec: 2867.2, 60 sec: 3618.1, 300 sec: 3369.9). Total num frames: 741376. Throughput: 0: 909.6. Samples: 184834. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2024-09-21 02:08:15,977][00440] Avg episode reward: [(0, '6.230')] +[2024-09-21 02:08:15,989][02531] Saving new best policy, reward=6.230! +[2024-09-21 02:08:20,974][00440] Fps is (10 sec: 4096.5, 60 sec: 3823.0, 300 sec: 3404.2). Total num frames: 765952. Throughput: 0: 924.9. Samples: 191194. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2024-09-21 02:08:20,980][00440] Avg episode reward: [(0, '6.463')] +[2024-09-21 02:08:20,984][02531] Saving new best policy, reward=6.463! +[2024-09-21 02:08:23,563][02544] Updated weights for policy 0, policy_version 190 (0.0042) +[2024-09-21 02:08:25,978][00440] Fps is (10 sec: 4503.7, 60 sec: 3822.7, 300 sec: 3419.2). Total num frames: 786432. Throughput: 0: 954.5. Samples: 194536. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2024-09-21 02:08:25,981][00440] Avg episode reward: [(0, '6.796')] +[2024-09-21 02:08:25,994][02531] Saving new best policy, reward=6.796! +[2024-09-21 02:08:30,976][00440] Fps is (10 sec: 3276.2, 60 sec: 3618.0, 300 sec: 3398.8). Total num frames: 798720. Throughput: 0: 927.6. Samples: 199318. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2024-09-21 02:08:30,983][00440] Avg episode reward: [(0, '6.732')] +[2024-09-21 02:08:35,974][00440] Fps is (10 sec: 2458.6, 60 sec: 3549.9, 300 sec: 3379.2). Total num frames: 811008. Throughput: 0: 861.9. Samples: 203164. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2024-09-21 02:08:35,976][00440] Avg episode reward: [(0, '6.752')] +[2024-09-21 02:08:38,180][02544] Updated weights for policy 0, policy_version 200 (0.0049) +[2024-09-21 02:08:40,974][00440] Fps is (10 sec: 2867.7, 60 sec: 3618.1, 300 sec: 3377.1). Total num frames: 827392. Throughput: 0: 864.0. Samples: 205186. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2024-09-21 02:08:40,981][00440] Avg episode reward: [(0, '6.180')] +[2024-09-21 02:08:45,978][00440] Fps is (10 sec: 3684.9, 60 sec: 3549.6, 300 sec: 3391.4). Total num frames: 847872. Throughput: 0: 891.3. Samples: 211062. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2024-09-21 02:08:45,990][00440] Avg episode reward: [(0, '6.355')] +[2024-09-21 02:08:50,470][02544] Updated weights for policy 0, policy_version 210 (0.0025) +[2024-09-21 02:08:50,974][00440] Fps is (10 sec: 3276.8, 60 sec: 3413.5, 300 sec: 3373.2). Total num frames: 860160. Throughput: 0: 834.6. Samples: 215202. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2024-09-21 02:08:50,980][00440] Avg episode reward: [(0, '6.578')] +[2024-09-21 02:08:55,974][00440] Fps is (10 sec: 3688.0, 60 sec: 3618.1, 300 sec: 3402.8). Total num frames: 884736. Throughput: 0: 837.2. Samples: 218418. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2024-09-21 02:08:55,977][00440] Avg episode reward: [(0, '7.529')] +[2024-09-21 02:08:55,989][02531] Saving new best policy, reward=7.529! +[2024-09-21 02:08:59,771][02544] Updated weights for policy 0, policy_version 220 (0.0039) +[2024-09-21 02:09:00,974][00440] Fps is (10 sec: 4505.6, 60 sec: 3618.1, 300 sec: 3415.9). Total num frames: 905216. Throughput: 0: 895.0. Samples: 225110. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2024-09-21 02:09:00,978][00440] Avg episode reward: [(0, '8.144')] +[2024-09-21 02:09:00,983][02531] Saving new best policy, reward=8.144! +[2024-09-21 02:09:05,977][00440] Fps is (10 sec: 3275.7, 60 sec: 3413.2, 300 sec: 3398.1). Total num frames: 917504. Throughput: 0: 859.0. Samples: 229854. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2024-09-21 02:09:05,980][00440] Avg episode reward: [(0, '8.674')] +[2024-09-21 02:09:05,994][02531] Saving new best policy, reward=8.674! +[2024-09-21 02:09:10,974][00440] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3410.9). Total num frames: 937984. Throughput: 0: 833.6. Samples: 232044. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2024-09-21 02:09:10,977][00440] Avg episode reward: [(0, '9.143')] +[2024-09-21 02:09:10,982][02531] Saving new best policy, reward=9.143! +[2024-09-21 02:09:11,726][02544] Updated weights for policy 0, policy_version 230 (0.0032) +[2024-09-21 02:09:15,974][00440] Fps is (10 sec: 4097.2, 60 sec: 3618.1, 300 sec: 3423.1). Total num frames: 958464. Throughput: 0: 877.4. Samples: 238798. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2024-09-21 02:09:15,985][00440] Avg episode reward: [(0, '9.054')] +[2024-09-21 02:09:20,974][00440] Fps is (10 sec: 3686.4, 60 sec: 3481.6, 300 sec: 3420.5). Total num frames: 974848. Throughput: 0: 919.6. Samples: 244548. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2024-09-21 02:09:20,981][00440] Avg episode reward: [(0, '8.765')] +[2024-09-21 02:09:22,611][02544] Updated weights for policy 0, policy_version 240 (0.0043) +[2024-09-21 02:09:25,974][00440] Fps is (10 sec: 3276.9, 60 sec: 3413.6, 300 sec: 3418.0). Total num frames: 991232. Throughput: 0: 919.4. Samples: 246558. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2024-09-21 02:09:25,979][00440] Avg episode reward: [(0, '8.592')] +[2024-09-21 02:09:30,975][00440] Fps is (10 sec: 4095.8, 60 sec: 3618.2, 300 sec: 3443.4). Total num frames: 1015808. Throughput: 0: 918.5. Samples: 252390. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2024-09-21 02:09:30,981][00440] Avg episode reward: [(0, '8.762')] +[2024-09-21 02:09:32,556][02544] Updated weights for policy 0, policy_version 250 (0.0023) +[2024-09-21 02:09:35,974][00440] Fps is (10 sec: 4505.6, 60 sec: 3754.7, 300 sec: 3512.9). Total num frames: 1036288. Throughput: 0: 976.2. Samples: 259130. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2024-09-21 02:09:35,977][00440] Avg episode reward: [(0, '8.791')] +[2024-09-21 02:09:40,974][00440] Fps is (10 sec: 3277.0, 60 sec: 3686.4, 300 sec: 3554.5). Total num frames: 1048576. Throughput: 0: 950.2. Samples: 261178. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2024-09-21 02:09:40,977][00440] Avg episode reward: [(0, '8.562')] +[2024-09-21 02:09:44,770][02544] Updated weights for policy 0, policy_version 260 (0.0020) +[2024-09-21 02:09:45,974][00440] Fps is (10 sec: 3276.7, 60 sec: 3686.6, 300 sec: 3623.9). Total num frames: 1069056. Throughput: 0: 909.9. Samples: 266058. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2024-09-21 02:09:45,977][00440] Avg episode reward: [(0, '8.729')] +[2024-09-21 02:09:50,974][00440] Fps is (10 sec: 4505.6, 60 sec: 3891.2, 300 sec: 3651.7). Total num frames: 1093632. Throughput: 0: 957.6. Samples: 272942. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2024-09-21 02:09:50,981][00440] Avg episode reward: [(0, '8.677')] +[2024-09-21 02:09:54,684][02544] Updated weights for policy 0, policy_version 270 (0.0024) +[2024-09-21 02:09:55,977][00440] Fps is (10 sec: 3685.3, 60 sec: 3686.2, 300 sec: 3651.6). Total num frames: 1105920. Throughput: 0: 976.3. Samples: 275980. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2024-09-21 02:09:55,981][00440] Avg episode reward: [(0, '9.191')] +[2024-09-21 02:09:55,994][02531] Saving new best policy, reward=9.191! +[2024-09-21 02:10:00,974][00440] Fps is (10 sec: 2867.2, 60 sec: 3618.1, 300 sec: 3651.7). Total num frames: 1122304. Throughput: 0: 914.1. Samples: 279932. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2024-09-21 02:10:00,981][00440] Avg episode reward: [(0, '8.912')] +[2024-09-21 02:10:05,685][02544] Updated weights for policy 0, policy_version 280 (0.0036) +[2024-09-21 02:10:05,974][00440] Fps is (10 sec: 4097.3, 60 sec: 3823.1, 300 sec: 3651.7). Total num frames: 1146880. Throughput: 0: 930.7. Samples: 286430. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2024-09-21 02:10:05,976][00440] Avg episode reward: [(0, '9.567')] +[2024-09-21 02:10:05,989][02531] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000280_1146880.pth... +[2024-09-21 02:10:06,121][02531] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000064_262144.pth +[2024-09-21 02:10:06,141][02531] Saving new best policy, reward=9.567! +[2024-09-21 02:10:10,974][00440] Fps is (10 sec: 4505.6, 60 sec: 3822.9, 300 sec: 3665.6). Total num frames: 1167360. Throughput: 0: 956.9. Samples: 289618. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2024-09-21 02:10:10,980][00440] Avg episode reward: [(0, '9.525')] +[2024-09-21 02:10:15,974][00440] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3651.7). Total num frames: 1179648. Throughput: 0: 934.5. Samples: 294444. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) +[2024-09-21 02:10:15,978][00440] Avg episode reward: [(0, '9.791')] +[2024-09-21 02:10:15,992][02531] Saving new best policy, reward=9.791! +[2024-09-21 02:10:17,880][02544] Updated weights for policy 0, policy_version 290 (0.0024) +[2024-09-21 02:10:20,974][00440] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3651.7). Total num frames: 1200128. Throughput: 0: 903.5. Samples: 299788. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2024-09-21 02:10:20,976][00440] Avg episode reward: [(0, '10.944')] +[2024-09-21 02:10:20,980][02531] Saving new best policy, reward=10.944! +[2024-09-21 02:10:25,974][00440] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3651.7). Total num frames: 1220608. Throughput: 0: 932.0. Samples: 303118. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2024-09-21 02:10:25,978][00440] Avg episode reward: [(0, '12.020')] +[2024-09-21 02:10:25,994][02531] Saving new best policy, reward=12.020! +[2024-09-21 02:10:27,126][02544] Updated weights for policy 0, policy_version 300 (0.0024) +[2024-09-21 02:10:30,976][00440] Fps is (10 sec: 3685.8, 60 sec: 3686.3, 300 sec: 3665.6). Total num frames: 1236992. Throughput: 0: 955.0. Samples: 309034. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2024-09-21 02:10:30,978][00440] Avg episode reward: [(0, '12.872')] +[2024-09-21 02:10:30,981][02531] Saving new best policy, reward=12.872! +[2024-09-21 02:10:35,974][00440] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3651.7). Total num frames: 1253376. Throughput: 0: 896.1. Samples: 313266. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2024-09-21 02:10:35,977][00440] Avg episode reward: [(0, '12.615')] +[2024-09-21 02:10:39,298][02544] Updated weights for policy 0, policy_version 310 (0.0025) +[2024-09-21 02:10:40,974][00440] Fps is (10 sec: 3687.0, 60 sec: 3754.7, 300 sec: 3637.8). Total num frames: 1273856. Throughput: 0: 905.5. Samples: 316726. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2024-09-21 02:10:40,979][00440] Avg episode reward: [(0, '13.167')] +[2024-09-21 02:10:40,993][02531] Saving new best policy, reward=13.167! +[2024-09-21 02:10:45,974][00440] Fps is (10 sec: 4505.6, 60 sec: 3822.9, 300 sec: 3665.7). Total num frames: 1298432. Throughput: 0: 967.6. Samples: 323472. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2024-09-21 02:10:45,984][00440] Avg episode reward: [(0, '12.950')] +[2024-09-21 02:10:50,366][02544] Updated weights for policy 0, policy_version 320 (0.0032) +[2024-09-21 02:10:50,974][00440] Fps is (10 sec: 3686.4, 60 sec: 3618.1, 300 sec: 3665.6). Total num frames: 1310720. Throughput: 0: 920.2. Samples: 327840. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2024-09-21 02:10:50,978][00440] Avg episode reward: [(0, '13.414')] +[2024-09-21 02:10:50,985][02531] Saving new best policy, reward=13.414! +[2024-09-21 02:10:55,975][00440] Fps is (10 sec: 3276.6, 60 sec: 3754.8, 300 sec: 3693.3). Total num frames: 1331200. Throughput: 0: 906.0. Samples: 330390. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2024-09-21 02:10:55,980][00440] Avg episode reward: [(0, '14.018')] +[2024-09-21 02:10:55,992][02531] Saving new best policy, reward=14.018! +[2024-09-21 02:11:00,378][02544] Updated weights for policy 0, policy_version 330 (0.0020) +[2024-09-21 02:11:00,974][00440] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3693.3). Total num frames: 1351680. Throughput: 0: 946.4. Samples: 337030. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2024-09-21 02:11:00,979][00440] Avg episode reward: [(0, '13.773')] +[2024-09-21 02:11:05,974][00440] Fps is (10 sec: 3686.6, 60 sec: 3686.4, 300 sec: 3693.3). Total num frames: 1368064. Throughput: 0: 947.1. Samples: 342408. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2024-09-21 02:11:05,982][00440] Avg episode reward: [(0, '14.037')] +[2024-09-21 02:11:05,996][02531] Saving new best policy, reward=14.037! +[2024-09-21 02:11:10,974][00440] Fps is (10 sec: 2867.2, 60 sec: 3549.9, 300 sec: 3679.5). Total num frames: 1380352. Throughput: 0: 917.2. Samples: 344394. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2024-09-21 02:11:10,978][00440] Avg episode reward: [(0, '13.174')] +[2024-09-21 02:11:14,684][02544] Updated weights for policy 0, policy_version 340 (0.0032) +[2024-09-21 02:11:15,974][00440] Fps is (10 sec: 2457.6, 60 sec: 3549.9, 300 sec: 3651.7). Total num frames: 1392640. Throughput: 0: 874.4. Samples: 348380. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2024-09-21 02:11:15,979][00440] Avg episode reward: [(0, '13.410')] +[2024-09-21 02:11:20,974][00440] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3651.7). Total num frames: 1413120. Throughput: 0: 902.2. Samples: 353864. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2024-09-21 02:11:20,980][00440] Avg episode reward: [(0, '12.682')] +[2024-09-21 02:11:25,974][00440] Fps is (10 sec: 3686.4, 60 sec: 3481.6, 300 sec: 3665.6). Total num frames: 1429504. Throughput: 0: 869.5. Samples: 355854. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2024-09-21 02:11:25,979][00440] Avg episode reward: [(0, '11.757')] +[2024-09-21 02:11:27,041][02544] Updated weights for policy 0, policy_version 350 (0.0030) +[2024-09-21 02:11:30,976][00440] Fps is (10 sec: 3685.6, 60 sec: 3549.8, 300 sec: 3651.7). Total num frames: 1449984. Throughput: 0: 835.1. Samples: 361052. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2024-09-21 02:11:30,979][00440] Avg episode reward: [(0, '12.320')] +[2024-09-21 02:11:35,974][00440] Fps is (10 sec: 4096.0, 60 sec: 3618.1, 300 sec: 3651.7). Total num frames: 1470464. Throughput: 0: 889.2. Samples: 367852. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2024-09-21 02:11:35,976][00440] Avg episode reward: [(0, '11.941')] +[2024-09-21 02:11:36,209][02544] Updated weights for policy 0, policy_version 360 (0.0039) +[2024-09-21 02:11:40,975][00440] Fps is (10 sec: 3686.8, 60 sec: 3549.8, 300 sec: 3665.6). Total num frames: 1486848. Throughput: 0: 894.2. Samples: 370630. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2024-09-21 02:11:40,978][00440] Avg episode reward: [(0, '12.704')] +[2024-09-21 02:11:45,974][00440] Fps is (10 sec: 3276.8, 60 sec: 3413.3, 300 sec: 3651.7). Total num frames: 1503232. Throughput: 0: 839.0. Samples: 374784. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2024-09-21 02:11:45,977][00440] Avg episode reward: [(0, '13.319')] +[2024-09-21 02:11:48,103][02544] Updated weights for policy 0, policy_version 370 (0.0035) +[2024-09-21 02:11:50,974][00440] Fps is (10 sec: 4096.5, 60 sec: 3618.1, 300 sec: 3651.7). Total num frames: 1527808. Throughput: 0: 871.2. Samples: 381614. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2024-09-21 02:11:50,981][00440] Avg episode reward: [(0, '13.879')] +[2024-09-21 02:11:55,976][00440] Fps is (10 sec: 4095.5, 60 sec: 3549.8, 300 sec: 3651.7). Total num frames: 1544192. Throughput: 0: 902.8. Samples: 385020. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2024-09-21 02:11:55,981][00440] Avg episode reward: [(0, '14.205')] +[2024-09-21 02:11:55,990][02531] Saving new best policy, reward=14.205! +[2024-09-21 02:11:59,398][02544] Updated weights for policy 0, policy_version 380 (0.0016) +[2024-09-21 02:12:00,974][00440] Fps is (10 sec: 3276.8, 60 sec: 3481.6, 300 sec: 3665.6). Total num frames: 1560576. Throughput: 0: 912.7. Samples: 389450. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2024-09-21 02:12:00,977][00440] Avg episode reward: [(0, '13.677')] +[2024-09-21 02:12:05,974][00440] Fps is (10 sec: 3686.9, 60 sec: 3549.9, 300 sec: 3651.7). Total num frames: 1581056. Throughput: 0: 918.6. Samples: 395200. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2024-09-21 02:12:05,977][00440] Avg episode reward: [(0, '15.059')] +[2024-09-21 02:12:05,987][02531] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000386_1581056.pth... +[2024-09-21 02:12:06,116][02531] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000174_712704.pth +[2024-09-21 02:12:06,135][02531] Saving new best policy, reward=15.059! +[2024-09-21 02:12:09,359][02544] Updated weights for policy 0, policy_version 390 (0.0033) +[2024-09-21 02:12:10,974][00440] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3651.7). Total num frames: 1601536. Throughput: 0: 945.7. Samples: 398410. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2024-09-21 02:12:10,979][00440] Avg episode reward: [(0, '15.208')] +[2024-09-21 02:12:10,984][02531] Saving new best policy, reward=15.208! +[2024-09-21 02:12:15,974][00440] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3665.6). Total num frames: 1617920. Throughput: 0: 952.8. Samples: 403924. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2024-09-21 02:12:15,976][00440] Avg episode reward: [(0, '15.769')] +[2024-09-21 02:12:15,989][02531] Saving new best policy, reward=15.769! +[2024-09-21 02:12:20,974][00440] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3651.7). Total num frames: 1634304. Throughput: 0: 902.0. Samples: 408444. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2024-09-21 02:12:20,981][00440] Avg episode reward: [(0, '16.251')] +[2024-09-21 02:12:20,986][02531] Saving new best policy, reward=16.251! +[2024-09-21 02:12:21,630][02544] Updated weights for policy 0, policy_version 400 (0.0027) +[2024-09-21 02:12:25,974][00440] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3637.8). Total num frames: 1654784. Throughput: 0: 913.7. Samples: 411744. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) +[2024-09-21 02:12:25,979][00440] Avg episode reward: [(0, '15.806')] +[2024-09-21 02:12:30,974][00440] Fps is (10 sec: 3686.4, 60 sec: 3686.5, 300 sec: 3637.8). Total num frames: 1671168. Throughput: 0: 948.0. Samples: 417444. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2024-09-21 02:12:30,978][00440] Avg episode reward: [(0, '15.725')] +[2024-09-21 02:12:33,673][02544] Updated weights for policy 0, policy_version 410 (0.0037) +[2024-09-21 02:12:35,974][00440] Fps is (10 sec: 2867.2, 60 sec: 3549.9, 300 sec: 3637.8). Total num frames: 1683456. Throughput: 0: 886.1. Samples: 421490. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2024-09-21 02:12:35,977][00440] Avg episode reward: [(0, '15.780')] +[2024-09-21 02:12:40,974][00440] Fps is (10 sec: 3686.4, 60 sec: 3686.5, 300 sec: 3637.8). Total num frames: 1708032. Throughput: 0: 875.0. Samples: 424396. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2024-09-21 02:12:40,977][00440] Avg episode reward: [(0, '15.347')] +[2024-09-21 02:12:43,588][02544] Updated weights for policy 0, policy_version 420 (0.0028) +[2024-09-21 02:12:45,974][00440] Fps is (10 sec: 4505.6, 60 sec: 3754.7, 300 sec: 3637.8). Total num frames: 1728512. Throughput: 0: 928.3. Samples: 431224. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2024-09-21 02:12:45,983][00440] Avg episode reward: [(0, '15.450')] +[2024-09-21 02:12:50,978][00440] Fps is (10 sec: 3684.9, 60 sec: 3617.9, 300 sec: 3651.6). Total num frames: 1744896. Throughput: 0: 913.1. Samples: 436292. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2024-09-21 02:12:50,981][00440] Avg episode reward: [(0, '15.327')] +[2024-09-21 02:12:55,365][02544] Updated weights for policy 0, policy_version 430 (0.0043) +[2024-09-21 02:12:55,974][00440] Fps is (10 sec: 3276.8, 60 sec: 3618.2, 300 sec: 3637.8). Total num frames: 1761280. Throughput: 0: 887.4. Samples: 438344. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2024-09-21 02:12:55,977][00440] Avg episode reward: [(0, '13.957')] +[2024-09-21 02:13:00,974][00440] Fps is (10 sec: 3687.9, 60 sec: 3686.4, 300 sec: 3623.9). Total num frames: 1781760. Throughput: 0: 912.0. Samples: 444964. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2024-09-21 02:13:00,980][00440] Avg episode reward: [(0, '13.914')] +[2024-09-21 02:13:05,974][00440] Fps is (10 sec: 3686.4, 60 sec: 3618.1, 300 sec: 3637.8). Total num frames: 1798144. Throughput: 0: 941.9. Samples: 450828. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2024-09-21 02:13:05,979][00440] Avg episode reward: [(0, '13.874')] +[2024-09-21 02:13:06,038][02544] Updated weights for policy 0, policy_version 440 (0.0066) +[2024-09-21 02:13:10,974][00440] Fps is (10 sec: 2457.6, 60 sec: 3413.3, 300 sec: 3610.0). Total num frames: 1806336. Throughput: 0: 883.6. Samples: 451506. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2024-09-21 02:13:10,979][00440] Avg episode reward: [(0, '14.056')] +[2024-09-21 02:13:15,974][00440] Fps is (10 sec: 2867.2, 60 sec: 3481.6, 300 sec: 3596.1). Total num frames: 1826816. Throughput: 0: 850.1. Samples: 455700. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2024-09-21 02:13:15,979][00440] Avg episode reward: [(0, '15.164')] +[2024-09-21 02:13:19,264][02544] Updated weights for policy 0, policy_version 450 (0.0044) +[2024-09-21 02:13:20,978][00440] Fps is (10 sec: 4094.4, 60 sec: 3549.6, 300 sec: 3596.2). Total num frames: 1847296. Throughput: 0: 907.9. Samples: 462348. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2024-09-21 02:13:20,984][00440] Avg episode reward: [(0, '17.365')] +[2024-09-21 02:13:20,987][02531] Saving new best policy, reward=17.365! +[2024-09-21 02:13:25,974][00440] Fps is (10 sec: 3276.8, 60 sec: 3413.3, 300 sec: 3596.2). Total num frames: 1859584. Throughput: 0: 889.9. Samples: 464440. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2024-09-21 02:13:25,981][00440] Avg episode reward: [(0, '18.049')] +[2024-09-21 02:13:26,016][02531] Saving new best policy, reward=18.049! +[2024-09-21 02:13:30,974][00440] Fps is (10 sec: 3278.1, 60 sec: 3481.6, 300 sec: 3623.9). Total num frames: 1880064. Throughput: 0: 843.5. Samples: 469182. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2024-09-21 02:13:30,979][00440] Avg episode reward: [(0, '18.554')] +[2024-09-21 02:13:30,983][02531] Saving new best policy, reward=18.554! +[2024-09-21 02:13:31,300][02544] Updated weights for policy 0, policy_version 460 (0.0020) +[2024-09-21 02:13:35,974][00440] Fps is (10 sec: 4505.6, 60 sec: 3686.4, 300 sec: 3651.7). Total num frames: 1904640. Throughput: 0: 879.6. Samples: 475872. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2024-09-21 02:13:35,977][00440] Avg episode reward: [(0, '18.010')] +[2024-09-21 02:13:40,974][00440] Fps is (10 sec: 4095.9, 60 sec: 3549.9, 300 sec: 3637.9). Total num frames: 1921024. Throughput: 0: 905.6. Samples: 479098. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2024-09-21 02:13:40,977][00440] Avg episode reward: [(0, '16.637')] +[2024-09-21 02:13:42,904][02544] Updated weights for policy 0, policy_version 470 (0.0026) +[2024-09-21 02:13:45,974][00440] Fps is (10 sec: 2867.2, 60 sec: 3413.3, 300 sec: 3637.8). Total num frames: 1933312. Throughput: 0: 836.0. Samples: 482582. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2024-09-21 02:13:45,977][00440] Avg episode reward: [(0, '16.572')] +[2024-09-21 02:13:50,974][00440] Fps is (10 sec: 2457.6, 60 sec: 3345.3, 300 sec: 3596.1). Total num frames: 1945600. Throughput: 0: 805.2. Samples: 487062. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2024-09-21 02:13:50,979][00440] Avg episode reward: [(0, '17.587')] +[2024-09-21 02:13:55,974][00440] Fps is (10 sec: 2867.2, 60 sec: 3345.1, 300 sec: 3582.3). Total num frames: 1961984. Throughput: 0: 829.3. Samples: 488826. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2024-09-21 02:13:55,979][00440] Avg episode reward: [(0, '18.221')] +[2024-09-21 02:13:56,689][02544] Updated weights for policy 0, policy_version 480 (0.0039) +[2024-09-21 02:14:00,974][00440] Fps is (10 sec: 2867.2, 60 sec: 3208.5, 300 sec: 3582.3). Total num frames: 1974272. Throughput: 0: 844.2. Samples: 493690. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2024-09-21 02:14:00,977][00440] Avg episode reward: [(0, '18.335')] +[2024-09-21 02:14:05,975][00440] Fps is (10 sec: 3276.7, 60 sec: 3276.8, 300 sec: 3582.3). Total num frames: 1994752. Throughput: 0: 817.4. Samples: 499130. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2024-09-21 02:14:05,977][00440] Avg episode reward: [(0, '20.019')] +[2024-09-21 02:14:05,987][02531] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000487_1994752.pth... +[2024-09-21 02:14:06,159][02531] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000280_1146880.pth +[2024-09-21 02:14:06,178][02531] Saving new best policy, reward=20.019! +[2024-09-21 02:14:08,533][02544] Updated weights for policy 0, policy_version 490 (0.0034) +[2024-09-21 02:14:10,974][00440] Fps is (10 sec: 4096.0, 60 sec: 3481.6, 300 sec: 3582.3). Total num frames: 2015232. Throughput: 0: 834.7. Samples: 502002. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2024-09-21 02:14:10,981][00440] Avg episode reward: [(0, '20.192')] +[2024-09-21 02:14:10,985][02531] Saving new best policy, reward=20.192! +[2024-09-21 02:14:15,974][00440] Fps is (10 sec: 3686.5, 60 sec: 3413.3, 300 sec: 3582.3). Total num frames: 2031616. Throughput: 0: 857.2. Samples: 507754. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2024-09-21 02:14:15,979][00440] Avg episode reward: [(0, '19.122')] +[2024-09-21 02:14:20,393][02544] Updated weights for policy 0, policy_version 500 (0.0031) +[2024-09-21 02:14:20,974][00440] Fps is (10 sec: 3276.8, 60 sec: 3345.3, 300 sec: 3582.3). Total num frames: 2048000. Throughput: 0: 805.2. Samples: 512104. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2024-09-21 02:14:20,977][00440] Avg episode reward: [(0, '19.059')] +[2024-09-21 02:14:25,974][00440] Fps is (10 sec: 4096.0, 60 sec: 3549.9, 300 sec: 3582.3). Total num frames: 2072576. Throughput: 0: 810.6. Samples: 515576. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2024-09-21 02:14:25,977][00440] Avg episode reward: [(0, '17.862')] +[2024-09-21 02:14:29,412][02544] Updated weights for policy 0, policy_version 510 (0.0046) +[2024-09-21 02:14:30,978][00440] Fps is (10 sec: 4503.7, 60 sec: 3549.6, 300 sec: 3582.2). Total num frames: 2093056. Throughput: 0: 887.4. Samples: 522518. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2024-09-21 02:14:30,981][00440] Avg episode reward: [(0, '17.258')] +[2024-09-21 02:14:35,974][00440] Fps is (10 sec: 3276.8, 60 sec: 3345.1, 300 sec: 3582.3). Total num frames: 2105344. Throughput: 0: 882.4. Samples: 526772. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2024-09-21 02:14:35,977][00440] Avg episode reward: [(0, '17.281')] +[2024-09-21 02:14:40,974][00440] Fps is (10 sec: 3278.1, 60 sec: 3413.3, 300 sec: 3582.3). Total num frames: 2125824. Throughput: 0: 900.8. Samples: 529362. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2024-09-21 02:14:40,977][00440] Avg episode reward: [(0, '17.801')] +[2024-09-21 02:14:41,320][02544] Updated weights for policy 0, policy_version 520 (0.0034) +[2024-09-21 02:14:45,974][00440] Fps is (10 sec: 4505.6, 60 sec: 3618.1, 300 sec: 3582.3). Total num frames: 2150400. Throughput: 0: 944.4. Samples: 536190. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2024-09-21 02:14:45,977][00440] Avg episode reward: [(0, '17.578')] +[2024-09-21 02:14:50,974][00440] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3596.2). Total num frames: 2166784. Throughput: 0: 943.6. Samples: 541592. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2024-09-21 02:14:50,978][00440] Avg episode reward: [(0, '18.040')] +[2024-09-21 02:14:53,109][02544] Updated weights for policy 0, policy_version 530 (0.0037) +[2024-09-21 02:14:55,974][00440] Fps is (10 sec: 2867.2, 60 sec: 3618.1, 300 sec: 3582.3). Total num frames: 2179072. Throughput: 0: 916.4. Samples: 543238. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2024-09-21 02:14:55,980][00440] Avg episode reward: [(0, '19.187')] +[2024-09-21 02:15:00,974][00440] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3582.3). Total num frames: 2203648. Throughput: 0: 933.6. Samples: 549764. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2024-09-21 02:15:00,977][00440] Avg episode reward: [(0, '20.224')] +[2024-09-21 02:15:00,979][02531] Saving new best policy, reward=20.224! +[2024-09-21 02:15:02,572][02544] Updated weights for policy 0, policy_version 540 (0.0022) +[2024-09-21 02:15:05,975][00440] Fps is (10 sec: 4095.5, 60 sec: 3754.6, 300 sec: 3568.4). Total num frames: 2220032. Throughput: 0: 972.7. Samples: 555878. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2024-09-21 02:15:05,981][00440] Avg episode reward: [(0, '18.933')] +[2024-09-21 02:15:10,974][00440] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3582.3). Total num frames: 2236416. Throughput: 0: 940.4. Samples: 557894. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2024-09-21 02:15:10,977][00440] Avg episode reward: [(0, '19.335')] +[2024-09-21 02:15:14,857][02544] Updated weights for policy 0, policy_version 550 (0.0037) +[2024-09-21 02:15:15,974][00440] Fps is (10 sec: 3686.8, 60 sec: 3754.7, 300 sec: 3582.3). Total num frames: 2256896. Throughput: 0: 893.7. Samples: 562730. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2024-09-21 02:15:15,980][00440] Avg episode reward: [(0, '18.185')] +[2024-09-21 02:15:20,974][00440] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3582.3). Total num frames: 2277376. Throughput: 0: 954.0. Samples: 569700. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2024-09-21 02:15:20,976][00440] Avg episode reward: [(0, '18.085')] +[2024-09-21 02:15:25,829][02544] Updated weights for policy 0, policy_version 560 (0.0029) +[2024-09-21 02:15:25,974][00440] Fps is (10 sec: 3686.5, 60 sec: 3686.4, 300 sec: 3582.3). Total num frames: 2293760. Throughput: 0: 952.9. Samples: 572244. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2024-09-21 02:15:25,979][00440] Avg episode reward: [(0, '18.382')] +[2024-09-21 02:15:30,974][00440] Fps is (10 sec: 3276.8, 60 sec: 3618.4, 300 sec: 3582.3). Total num frames: 2310144. Throughput: 0: 895.0. Samples: 576464. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2024-09-21 02:15:30,984][00440] Avg episode reward: [(0, '18.025')] +[2024-09-21 02:15:35,974][00440] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3582.3). Total num frames: 2330624. Throughput: 0: 915.3. Samples: 582780. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2024-09-21 02:15:35,981][00440] Avg episode reward: [(0, '17.899')] +[2024-09-21 02:15:36,396][02544] Updated weights for policy 0, policy_version 570 (0.0028) +[2024-09-21 02:15:40,974][00440] Fps is (10 sec: 4096.0, 60 sec: 3754.7, 300 sec: 3568.4). Total num frames: 2351104. Throughput: 0: 954.9. Samples: 586208. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2024-09-21 02:15:40,980][00440] Avg episode reward: [(0, '18.003')] +[2024-09-21 02:15:45,977][00440] Fps is (10 sec: 3276.0, 60 sec: 3549.7, 300 sec: 3568.4). Total num frames: 2363392. Throughput: 0: 906.4. Samples: 590554. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2024-09-21 02:15:45,981][00440] Avg episode reward: [(0, '16.968')] +[2024-09-21 02:15:48,283][02544] Updated weights for policy 0, policy_version 580 (0.0043) +[2024-09-21 02:15:50,974][00440] Fps is (10 sec: 3686.4, 60 sec: 3686.4, 300 sec: 3582.3). Total num frames: 2387968. Throughput: 0: 903.2. Samples: 596520. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2024-09-21 02:15:50,983][00440] Avg episode reward: [(0, '18.242')] +[2024-09-21 02:15:55,974][00440] Fps is (10 sec: 4506.7, 60 sec: 3822.9, 300 sec: 3582.3). Total num frames: 2408448. Throughput: 0: 934.3. Samples: 599938. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2024-09-21 02:15:55,981][00440] Avg episode reward: [(0, '19.562')] +[2024-09-21 02:15:57,540][02544] Updated weights for policy 0, policy_version 590 (0.0040) +[2024-09-21 02:16:00,976][00440] Fps is (10 sec: 3685.6, 60 sec: 3686.3, 300 sec: 3582.2). Total num frames: 2424832. Throughput: 0: 949.3. Samples: 605450. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2024-09-21 02:16:00,978][00440] Avg episode reward: [(0, '19.638')] +[2024-09-21 02:16:05,974][00440] Fps is (10 sec: 2867.2, 60 sec: 3618.2, 300 sec: 3582.3). Total num frames: 2437120. Throughput: 0: 893.9. Samples: 609924. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2024-09-21 02:16:05,976][00440] Avg episode reward: [(0, '19.951')] +[2024-09-21 02:16:05,990][02531] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000595_2437120.pth... +[2024-09-21 02:16:06,262][02531] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000386_1581056.pth +[2024-09-21 02:16:10,079][02544] Updated weights for policy 0, policy_version 600 (0.0043) +[2024-09-21 02:16:10,974][00440] Fps is (10 sec: 3277.5, 60 sec: 3686.4, 300 sec: 3610.0). Total num frames: 2457600. Throughput: 0: 895.7. Samples: 612552. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2024-09-21 02:16:10,979][00440] Avg episode reward: [(0, '19.702')] +[2024-09-21 02:16:15,974][00440] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3610.0). Total num frames: 2478080. Throughput: 0: 948.1. Samples: 619128. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2024-09-21 02:16:15,977][00440] Avg episode reward: [(0, '18.803')] +[2024-09-21 02:16:20,974][00440] Fps is (10 sec: 3276.7, 60 sec: 3549.9, 300 sec: 3596.1). Total num frames: 2490368. Throughput: 0: 896.9. Samples: 623140. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2024-09-21 02:16:20,977][00440] Avg episode reward: [(0, '19.021')] +[2024-09-21 02:16:22,263][02544] Updated weights for policy 0, policy_version 610 (0.0025) +[2024-09-21 02:16:25,974][00440] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3596.2). Total num frames: 2510848. Throughput: 0: 886.8. Samples: 626112. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2024-09-21 02:16:25,977][00440] Avg episode reward: [(0, '18.157')] +[2024-09-21 02:16:30,978][00440] Fps is (10 sec: 3275.7, 60 sec: 3549.7, 300 sec: 3568.3). Total num frames: 2523136. Throughput: 0: 883.7. Samples: 630322. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2024-09-21 02:16:30,985][00440] Avg episode reward: [(0, '18.844')] +[2024-09-21 02:16:35,974][00440] Fps is (10 sec: 2457.6, 60 sec: 3413.3, 300 sec: 3554.5). Total num frames: 2535424. Throughput: 0: 838.0. Samples: 634232. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2024-09-21 02:16:35,977][00440] Avg episode reward: [(0, '19.577')] +[2024-09-21 02:16:36,931][02544] Updated weights for policy 0, policy_version 620 (0.0028) +[2024-09-21 02:16:40,974][00440] Fps is (10 sec: 2868.2, 60 sec: 3345.1, 300 sec: 3554.5). Total num frames: 2551808. Throughput: 0: 806.9. Samples: 636248. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2024-09-21 02:16:40,982][00440] Avg episode reward: [(0, '20.567')] +[2024-09-21 02:16:40,984][02531] Saving new best policy, reward=20.567! +[2024-09-21 02:16:45,974][00440] Fps is (10 sec: 4096.0, 60 sec: 3550.0, 300 sec: 3554.5). Total num frames: 2576384. Throughput: 0: 823.9. Samples: 642526. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2024-09-21 02:16:45,976][00440] Avg episode reward: [(0, '20.837')] +[2024-09-21 02:16:45,998][02531] Saving new best policy, reward=20.837! +[2024-09-21 02:16:46,874][02544] Updated weights for policy 0, policy_version 630 (0.0037) +[2024-09-21 02:16:50,975][00440] Fps is (10 sec: 4095.8, 60 sec: 3413.3, 300 sec: 3554.5). Total num frames: 2592768. Throughput: 0: 864.8. Samples: 648840. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2024-09-21 02:16:50,978][00440] Avg episode reward: [(0, '21.057')] +[2024-09-21 02:16:50,980][02531] Saving new best policy, reward=21.057! +[2024-09-21 02:16:55,976][00440] Fps is (10 sec: 3276.1, 60 sec: 3344.9, 300 sec: 3554.5). Total num frames: 2609152. Throughput: 0: 848.9. Samples: 650754. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2024-09-21 02:16:55,983][00440] Avg episode reward: [(0, '21.820')] +[2024-09-21 02:16:55,997][02531] Saving new best policy, reward=21.820! +[2024-09-21 02:16:58,960][02544] Updated weights for policy 0, policy_version 640 (0.0026) +[2024-09-21 02:17:00,974][00440] Fps is (10 sec: 3686.6, 60 sec: 3413.4, 300 sec: 3554.5). Total num frames: 2629632. Throughput: 0: 817.9. Samples: 655932. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2024-09-21 02:17:00,976][00440] Avg episode reward: [(0, '20.344')] +[2024-09-21 02:17:05,974][00440] Fps is (10 sec: 4096.9, 60 sec: 3549.9, 300 sec: 3554.5). Total num frames: 2650112. Throughput: 0: 877.6. Samples: 662630. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2024-09-21 02:17:05,980][00440] Avg episode reward: [(0, '19.757')] +[2024-09-21 02:17:09,075][02544] Updated weights for policy 0, policy_version 650 (0.0020) +[2024-09-21 02:17:10,975][00440] Fps is (10 sec: 3686.0, 60 sec: 3481.5, 300 sec: 3554.5). Total num frames: 2666496. Throughput: 0: 874.2. Samples: 665454. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2024-09-21 02:17:10,982][00440] Avg episode reward: [(0, '19.620')] +[2024-09-21 02:17:15,974][00440] Fps is (10 sec: 3276.8, 60 sec: 3413.3, 300 sec: 3554.5). Total num frames: 2682880. Throughput: 0: 874.6. Samples: 669676. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2024-09-21 02:17:15,977][00440] Avg episode reward: [(0, '18.914')] +[2024-09-21 02:17:19,837][02544] Updated weights for policy 0, policy_version 660 (0.0036) +[2024-09-21 02:17:20,974][00440] Fps is (10 sec: 4096.4, 60 sec: 3618.1, 300 sec: 3568.4). Total num frames: 2707456. Throughput: 0: 940.8. Samples: 676566. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2024-09-21 02:17:20,980][00440] Avg episode reward: [(0, '19.162')] +[2024-09-21 02:17:25,974][00440] Fps is (10 sec: 4096.0, 60 sec: 3549.9, 300 sec: 3568.4). Total num frames: 2723840. Throughput: 0: 972.8. Samples: 680024. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2024-09-21 02:17:25,977][00440] Avg episode reward: [(0, '20.514')] +[2024-09-21 02:17:30,976][00440] Fps is (10 sec: 3276.1, 60 sec: 3618.2, 300 sec: 3582.2). Total num frames: 2740224. Throughput: 0: 932.7. Samples: 684500. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2024-09-21 02:17:30,981][00440] Avg episode reward: [(0, '20.925')] +[2024-09-21 02:17:31,717][02544] Updated weights for policy 0, policy_version 670 (0.0038) +[2024-09-21 02:17:35,974][00440] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3568.4). Total num frames: 2760704. Throughput: 0: 920.9. Samples: 690278. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2024-09-21 02:17:35,976][00440] Avg episode reward: [(0, '22.270')] +[2024-09-21 02:17:35,987][02531] Saving new best policy, reward=22.270! +[2024-09-21 02:17:40,974][00440] Fps is (10 sec: 4096.8, 60 sec: 3822.9, 300 sec: 3568.4). Total num frames: 2781184. Throughput: 0: 953.3. Samples: 693650. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2024-09-21 02:17:40,980][00440] Avg episode reward: [(0, '22.585')] +[2024-09-21 02:17:40,984][02531] Saving new best policy, reward=22.585! +[2024-09-21 02:17:40,995][02544] Updated weights for policy 0, policy_version 680 (0.0032) +[2024-09-21 02:17:45,974][00440] Fps is (10 sec: 3686.4, 60 sec: 3686.4, 300 sec: 3568.4). Total num frames: 2797568. Throughput: 0: 958.4. Samples: 699060. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2024-09-21 02:17:45,981][00440] Avg episode reward: [(0, '22.546')] +[2024-09-21 02:17:50,974][00440] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3568.4). Total num frames: 2813952. Throughput: 0: 916.8. Samples: 703888. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2024-09-21 02:17:50,981][00440] Avg episode reward: [(0, '21.300')] +[2024-09-21 02:17:53,227][02544] Updated weights for policy 0, policy_version 690 (0.0016) +[2024-09-21 02:17:55,974][00440] Fps is (10 sec: 4096.0, 60 sec: 3823.1, 300 sec: 3582.3). Total num frames: 2838528. Throughput: 0: 923.1. Samples: 706992. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2024-09-21 02:17:55,981][00440] Avg episode reward: [(0, '20.248')] +[2024-09-21 02:18:00,974][00440] Fps is (10 sec: 4096.0, 60 sec: 3754.7, 300 sec: 3582.3). Total num frames: 2854912. Throughput: 0: 976.5. Samples: 713620. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2024-09-21 02:18:00,982][00440] Avg episode reward: [(0, '19.854')] +[2024-09-21 02:18:04,537][02544] Updated weights for policy 0, policy_version 700 (0.0020) +[2024-09-21 02:18:05,974][00440] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3610.0). Total num frames: 2871296. Throughput: 0: 913.6. Samples: 717678. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2024-09-21 02:18:05,977][00440] Avg episode reward: [(0, '19.811')] +[2024-09-21 02:18:05,992][02531] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000701_2871296.pth... +[2024-09-21 02:18:06,165][02531] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000487_1994752.pth +[2024-09-21 02:18:10,974][00440] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3610.0). Total num frames: 2891776. Throughput: 0: 900.1. Samples: 720530. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2024-09-21 02:18:10,980][00440] Avg episode reward: [(0, '19.445')] +[2024-09-21 02:18:14,157][02544] Updated weights for policy 0, policy_version 710 (0.0036) +[2024-09-21 02:18:15,974][00440] Fps is (10 sec: 4096.1, 60 sec: 3822.9, 300 sec: 3610.1). Total num frames: 2912256. Throughput: 0: 951.6. Samples: 727322. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2024-09-21 02:18:15,977][00440] Avg episode reward: [(0, '21.258')] +[2024-09-21 02:18:20,974][00440] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3610.0). Total num frames: 2924544. Throughput: 0: 921.7. Samples: 731754. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2024-09-21 02:18:20,980][00440] Avg episode reward: [(0, '22.160')] +[2024-09-21 02:18:25,974][00440] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3610.0). Total num frames: 2945024. Throughput: 0: 893.3. Samples: 733850. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) +[2024-09-21 02:18:25,979][00440] Avg episode reward: [(0, '21.556')] +[2024-09-21 02:18:26,477][02544] Updated weights for policy 0, policy_version 720 (0.0034) +[2024-09-21 02:18:30,974][00440] Fps is (10 sec: 4505.6, 60 sec: 3823.1, 300 sec: 3610.0). Total num frames: 2969600. Throughput: 0: 925.1. Samples: 740688. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2024-09-21 02:18:30,982][00440] Avg episode reward: [(0, '23.018')] +[2024-09-21 02:18:30,985][02531] Saving new best policy, reward=23.018! +[2024-09-21 02:18:35,974][00440] Fps is (10 sec: 4096.0, 60 sec: 3754.7, 300 sec: 3610.0). Total num frames: 2985984. Throughput: 0: 947.8. Samples: 746538. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2024-09-21 02:18:35,979][00440] Avg episode reward: [(0, '22.082')] +[2024-09-21 02:18:37,160][02544] Updated weights for policy 0, policy_version 730 (0.0017) +[2024-09-21 02:18:40,974][00440] Fps is (10 sec: 2867.2, 60 sec: 3618.1, 300 sec: 3610.0). Total num frames: 2998272. Throughput: 0: 922.7. Samples: 748514. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2024-09-21 02:18:40,977][00440] Avg episode reward: [(0, '20.822')] +[2024-09-21 02:18:45,974][00440] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3651.7). Total num frames: 3022848. Throughput: 0: 905.9. Samples: 754386. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2024-09-21 02:18:45,979][00440] Avg episode reward: [(0, '19.101')] +[2024-09-21 02:18:47,259][02544] Updated weights for policy 0, policy_version 740 (0.0018) +[2024-09-21 02:18:50,974][00440] Fps is (10 sec: 4505.6, 60 sec: 3822.9, 300 sec: 3665.6). Total num frames: 3043328. Throughput: 0: 969.2. Samples: 761290. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2024-09-21 02:18:50,977][00440] Avg episode reward: [(0, '17.466')] +[2024-09-21 02:18:55,974][00440] Fps is (10 sec: 3686.4, 60 sec: 3686.4, 300 sec: 3679.5). Total num frames: 3059712. Throughput: 0: 954.2. Samples: 763468. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) +[2024-09-21 02:18:55,982][00440] Avg episode reward: [(0, '16.425')] +[2024-09-21 02:18:59,056][02544] Updated weights for policy 0, policy_version 750 (0.0036) +[2024-09-21 02:19:00,974][00440] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3679.5). Total num frames: 3080192. Throughput: 0: 911.7. Samples: 768350. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2024-09-21 02:19:00,976][00440] Avg episode reward: [(0, '17.295')] +[2024-09-21 02:19:05,974][00440] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3665.6). Total num frames: 3096576. Throughput: 0: 936.8. Samples: 773912. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2024-09-21 02:19:05,976][00440] Avg episode reward: [(0, '16.525')] +[2024-09-21 02:19:10,974][00440] Fps is (10 sec: 2457.6, 60 sec: 3549.9, 300 sec: 3637.8). Total num frames: 3104768. Throughput: 0: 933.0. Samples: 775836. Policy #0 lag: (min: 0.0, avg: 0.3, max: 2.0) +[2024-09-21 02:19:10,979][00440] Avg episode reward: [(0, '17.562')] +[2024-09-21 02:19:12,727][02544] Updated weights for policy 0, policy_version 760 (0.0027) +[2024-09-21 02:19:15,974][00440] Fps is (10 sec: 2457.6, 60 sec: 3481.6, 300 sec: 3637.8). Total num frames: 3121152. Throughput: 0: 863.3. Samples: 779536. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2024-09-21 02:19:15,983][00440] Avg episode reward: [(0, '17.955')] +[2024-09-21 02:19:20,974][00440] Fps is (10 sec: 3686.4, 60 sec: 3618.1, 300 sec: 3623.9). Total num frames: 3141632. Throughput: 0: 869.2. Samples: 785652. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2024-09-21 02:19:20,979][00440] Avg episode reward: [(0, '17.858')] +[2024-09-21 02:19:23,127][02544] Updated weights for policy 0, policy_version 770 (0.0047) +[2024-09-21 02:19:25,974][00440] Fps is (10 sec: 4505.6, 60 sec: 3686.4, 300 sec: 3637.9). Total num frames: 3166208. Throughput: 0: 901.2. Samples: 789068. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2024-09-21 02:19:25,981][00440] Avg episode reward: [(0, '18.570')] +[2024-09-21 02:19:30,974][00440] Fps is (10 sec: 3686.4, 60 sec: 3481.6, 300 sec: 3637.8). Total num frames: 3178496. Throughput: 0: 888.3. Samples: 794358. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2024-09-21 02:19:30,978][00440] Avg episode reward: [(0, '19.533')] +[2024-09-21 02:19:35,183][02544] Updated weights for policy 0, policy_version 780 (0.0026) +[2024-09-21 02:19:35,974][00440] Fps is (10 sec: 2867.2, 60 sec: 3481.6, 300 sec: 3623.9). Total num frames: 3194880. Throughput: 0: 842.9. Samples: 799220. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2024-09-21 02:19:35,982][00440] Avg episode reward: [(0, '19.831')] +[2024-09-21 02:19:40,974][00440] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3623.9). Total num frames: 3219456. Throughput: 0: 868.8. Samples: 802566. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2024-09-21 02:19:40,977][00440] Avg episode reward: [(0, '19.032')] +[2024-09-21 02:19:44,756][02544] Updated weights for policy 0, policy_version 790 (0.0026) +[2024-09-21 02:19:45,974][00440] Fps is (10 sec: 4096.0, 60 sec: 3549.9, 300 sec: 3623.9). Total num frames: 3235840. Throughput: 0: 904.0. Samples: 809028. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2024-09-21 02:19:45,977][00440] Avg episode reward: [(0, '19.474')] +[2024-09-21 02:19:50,974][00440] Fps is (10 sec: 3276.8, 60 sec: 3481.6, 300 sec: 3637.8). Total num frames: 3252224. Throughput: 0: 871.5. Samples: 813130. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2024-09-21 02:19:50,982][00440] Avg episode reward: [(0, '19.429')] +[2024-09-21 02:19:55,974][00440] Fps is (10 sec: 3686.4, 60 sec: 3549.9, 300 sec: 3623.9). Total num frames: 3272704. Throughput: 0: 901.6. Samples: 816406. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2024-09-21 02:19:55,976][00440] Avg episode reward: [(0, '19.050')] +[2024-09-21 02:19:55,993][02544] Updated weights for policy 0, policy_version 800 (0.0031) +[2024-09-21 02:20:00,974][00440] Fps is (10 sec: 4505.6, 60 sec: 3618.1, 300 sec: 3651.7). Total num frames: 3297280. Throughput: 0: 969.9. Samples: 823180. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2024-09-21 02:20:00,978][00440] Avg episode reward: [(0, '18.935')] +[2024-09-21 02:20:05,974][00440] Fps is (10 sec: 3686.4, 60 sec: 3549.9, 300 sec: 3637.8). Total num frames: 3309568. Throughput: 0: 939.6. Samples: 827936. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2024-09-21 02:20:05,980][00440] Avg episode reward: [(0, '20.433')] +[2024-09-21 02:20:05,995][02531] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000808_3309568.pth... +[2024-09-21 02:20:06,166][02531] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000595_2437120.pth +[2024-09-21 02:20:07,944][02544] Updated weights for policy 0, policy_version 810 (0.0040) +[2024-09-21 02:20:10,974][00440] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3637.8). Total num frames: 3330048. Throughput: 0: 907.8. Samples: 829918. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2024-09-21 02:20:10,979][00440] Avg episode reward: [(0, '21.105')] +[2024-09-21 02:20:15,974][00440] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3637.8). Total num frames: 3350528. Throughput: 0: 941.1. Samples: 836706. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2024-09-21 02:20:15,981][00440] Avg episode reward: [(0, '21.310')] +[2024-09-21 02:20:17,096][02544] Updated weights for policy 0, policy_version 820 (0.0038) +[2024-09-21 02:20:20,974][00440] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3637.8). Total num frames: 3366912. Throughput: 0: 965.4. Samples: 842664. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2024-09-21 02:20:20,981][00440] Avg episode reward: [(0, '21.935')] +[2024-09-21 02:20:25,974][00440] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3637.8). Total num frames: 3383296. Throughput: 0: 935.5. Samples: 844662. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2024-09-21 02:20:25,977][00440] Avg episode reward: [(0, '21.306')] +[2024-09-21 02:20:28,938][02544] Updated weights for policy 0, policy_version 830 (0.0041) +[2024-09-21 02:20:30,974][00440] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3651.7). Total num frames: 3407872. Throughput: 0: 922.6. Samples: 850544. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2024-09-21 02:20:30,977][00440] Avg episode reward: [(0, '19.835')] +[2024-09-21 02:20:35,974][00440] Fps is (10 sec: 4505.5, 60 sec: 3891.2, 300 sec: 3651.7). Total num frames: 3428352. Throughput: 0: 983.3. Samples: 857378. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2024-09-21 02:20:35,979][00440] Avg episode reward: [(0, '21.090')] +[2024-09-21 02:20:39,797][02544] Updated weights for policy 0, policy_version 840 (0.0034) +[2024-09-21 02:20:40,974][00440] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3651.7). Total num frames: 3440640. Throughput: 0: 958.1. Samples: 859522. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2024-09-21 02:20:40,980][00440] Avg episode reward: [(0, '20.332')] +[2024-09-21 02:20:45,974][00440] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3637.8). Total num frames: 3461120. Throughput: 0: 910.7. Samples: 864160. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2024-09-21 02:20:45,983][00440] Avg episode reward: [(0, '19.606')] +[2024-09-21 02:20:50,019][02544] Updated weights for policy 0, policy_version 850 (0.0028) +[2024-09-21 02:20:50,974][00440] Fps is (10 sec: 4505.6, 60 sec: 3891.2, 300 sec: 3651.7). Total num frames: 3485696. Throughput: 0: 957.5. Samples: 871024. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2024-09-21 02:20:50,981][00440] Avg episode reward: [(0, '20.129')] +[2024-09-21 02:20:55,975][00440] Fps is (10 sec: 4095.7, 60 sec: 3822.9, 300 sec: 3651.7). Total num frames: 3502080. Throughput: 0: 987.4. Samples: 874352. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2024-09-21 02:20:55,981][00440] Avg episode reward: [(0, '20.388')] +[2024-09-21 02:21:00,974][00440] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 3518464. Throughput: 0: 928.5. Samples: 878490. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2024-09-21 02:21:00,979][00440] Avg episode reward: [(0, '19.639')] +[2024-09-21 02:21:01,831][02544] Updated weights for policy 0, policy_version 860 (0.0028) +[2024-09-21 02:21:05,974][00440] Fps is (10 sec: 3686.8, 60 sec: 3822.9, 300 sec: 3665.6). Total num frames: 3538944. Throughput: 0: 939.7. Samples: 884950. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2024-09-21 02:21:05,984][00440] Avg episode reward: [(0, '20.972')] +[2024-09-21 02:21:10,979][00440] Fps is (10 sec: 4093.9, 60 sec: 3822.6, 300 sec: 3665.5). Total num frames: 3559424. Throughput: 0: 967.4. Samples: 888198. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2024-09-21 02:21:10,982][00440] Avg episode reward: [(0, '21.905')] +[2024-09-21 02:21:11,424][02544] Updated weights for policy 0, policy_version 870 (0.0016) +[2024-09-21 02:21:15,978][00440] Fps is (10 sec: 3684.9, 60 sec: 3754.4, 300 sec: 3679.4). Total num frames: 3575808. Throughput: 0: 947.2. Samples: 893172. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2024-09-21 02:21:15,981][00440] Avg episode reward: [(0, '21.219')] +[2024-09-21 02:21:20,974][00440] Fps is (10 sec: 3688.3, 60 sec: 3822.9, 300 sec: 3679.5). Total num frames: 3596288. Throughput: 0: 916.1. Samples: 898604. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2024-09-21 02:21:20,977][00440] Avg episode reward: [(0, '21.033')] +[2024-09-21 02:21:22,750][02544] Updated weights for policy 0, policy_version 880 (0.0035) +[2024-09-21 02:21:25,974][00440] Fps is (10 sec: 4097.7, 60 sec: 3891.2, 300 sec: 3707.3). Total num frames: 3616768. Throughput: 0: 944.2. Samples: 902012. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2024-09-21 02:21:25,976][00440] Avg episode reward: [(0, '19.827')] +[2024-09-21 02:21:30,974][00440] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3721.1). Total num frames: 3633152. Throughput: 0: 972.3. Samples: 907914. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2024-09-21 02:21:30,983][00440] Avg episode reward: [(0, '19.585')] +[2024-09-21 02:21:34,863][02544] Updated weights for policy 0, policy_version 890 (0.0041) +[2024-09-21 02:21:35,974][00440] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3721.1). Total num frames: 3649536. Throughput: 0: 915.5. Samples: 912220. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2024-09-21 02:21:35,983][00440] Avg episode reward: [(0, '19.504')] +[2024-09-21 02:21:40,974][00440] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3707.2). Total num frames: 3670016. Throughput: 0: 912.7. Samples: 915424. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2024-09-21 02:21:40,977][00440] Avg episode reward: [(0, '20.620')] +[2024-09-21 02:21:45,582][02544] Updated weights for policy 0, policy_version 900 (0.0022) +[2024-09-21 02:21:45,974][00440] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3707.2). Total num frames: 3686400. Throughput: 0: 947.4. Samples: 921122. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2024-09-21 02:21:45,977][00440] Avg episode reward: [(0, '20.221')] +[2024-09-21 02:21:50,977][00440] Fps is (10 sec: 2457.0, 60 sec: 3481.5, 300 sec: 3679.5). Total num frames: 3694592. Throughput: 0: 877.5. Samples: 924440. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2024-09-21 02:21:50,979][00440] Avg episode reward: [(0, '21.294')] +[2024-09-21 02:21:55,974][00440] Fps is (10 sec: 2867.2, 60 sec: 3549.9, 300 sec: 3679.5). Total num frames: 3715072. Throughput: 0: 847.2. Samples: 926318. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2024-09-21 02:21:55,977][00440] Avg episode reward: [(0, '22.010')] +[2024-09-21 02:21:58,696][02544] Updated weights for policy 0, policy_version 910 (0.0046) +[2024-09-21 02:22:00,974][00440] Fps is (10 sec: 4097.0, 60 sec: 3618.1, 300 sec: 3679.5). Total num frames: 3735552. Throughput: 0: 878.0. Samples: 932680. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2024-09-21 02:22:00,979][00440] Avg episode reward: [(0, '22.411')] +[2024-09-21 02:22:05,974][00440] Fps is (10 sec: 4096.0, 60 sec: 3618.1, 300 sec: 3693.4). Total num frames: 3756032. Throughput: 0: 903.4. Samples: 939258. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2024-09-21 02:22:05,981][00440] Avg episode reward: [(0, '22.022')] +[2024-09-21 02:22:05,994][02531] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000917_3756032.pth... +[2024-09-21 02:22:06,152][02531] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000701_2871296.pth +[2024-09-21 02:22:10,485][02544] Updated weights for policy 0, policy_version 920 (0.0041) +[2024-09-21 02:22:10,974][00440] Fps is (10 sec: 3276.7, 60 sec: 3481.9, 300 sec: 3679.5). Total num frames: 3768320. Throughput: 0: 869.2. Samples: 941126. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2024-09-21 02:22:10,977][00440] Avg episode reward: [(0, '21.894')] +[2024-09-21 02:22:15,974][00440] Fps is (10 sec: 3276.8, 60 sec: 3550.1, 300 sec: 3665.6). Total num frames: 3788800. Throughput: 0: 853.9. Samples: 946340. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2024-09-21 02:22:15,980][00440] Avg episode reward: [(0, '23.650')] +[2024-09-21 02:22:15,991][02531] Saving new best policy, reward=23.650! +[2024-09-21 02:22:19,706][02544] Updated weights for policy 0, policy_version 930 (0.0032) +[2024-09-21 02:22:20,974][00440] Fps is (10 sec: 4505.6, 60 sec: 3618.1, 300 sec: 3693.3). Total num frames: 3813376. Throughput: 0: 909.2. Samples: 953132. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2024-09-21 02:22:20,981][00440] Avg episode reward: [(0, '23.272')] +[2024-09-21 02:22:25,974][00440] Fps is (10 sec: 3686.4, 60 sec: 3481.6, 300 sec: 3679.5). Total num frames: 3825664. Throughput: 0: 899.3. Samples: 955892. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2024-09-21 02:22:25,976][00440] Avg episode reward: [(0, '23.869')] +[2024-09-21 02:22:26,061][02531] Saving new best policy, reward=23.869! +[2024-09-21 02:22:30,974][00440] Fps is (10 sec: 3276.9, 60 sec: 3549.9, 300 sec: 3679.5). Total num frames: 3846144. Throughput: 0: 861.2. Samples: 959876. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2024-09-21 02:22:30,982][00440] Avg episode reward: [(0, '23.152')] +[2024-09-21 02:22:31,796][02544] Updated weights for policy 0, policy_version 940 (0.0017) +[2024-09-21 02:22:35,974][00440] Fps is (10 sec: 4096.0, 60 sec: 3618.1, 300 sec: 3679.5). Total num frames: 3866624. Throughput: 0: 939.6. Samples: 966722. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2024-09-21 02:22:35,978][00440] Avg episode reward: [(0, '24.540')] +[2024-09-21 02:22:35,989][02531] Saving new best policy, reward=24.540! +[2024-09-21 02:22:40,975][00440] Fps is (10 sec: 3686.0, 60 sec: 3549.8, 300 sec: 3679.4). Total num frames: 3883008. Throughput: 0: 968.6. Samples: 969908. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2024-09-21 02:22:40,978][00440] Avg episode reward: [(0, '23.024')] +[2024-09-21 02:22:42,612][02544] Updated weights for policy 0, policy_version 950 (0.0052) +[2024-09-21 02:22:45,974][00440] Fps is (10 sec: 2867.2, 60 sec: 3481.6, 300 sec: 3665.6). Total num frames: 3895296. Throughput: 0: 926.5. Samples: 974372. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2024-09-21 02:22:45,982][00440] Avg episode reward: [(0, '23.233')] +[2024-09-21 02:22:50,974][00440] Fps is (10 sec: 3277.1, 60 sec: 3686.5, 300 sec: 3651.7). Total num frames: 3915776. Throughput: 0: 888.4. Samples: 979238. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2024-09-21 02:22:50,977][00440] Avg episode reward: [(0, '22.769')] +[2024-09-21 02:22:54,066][02544] Updated weights for policy 0, policy_version 960 (0.0033) +[2024-09-21 02:22:55,974][00440] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 3936256. Throughput: 0: 923.1. Samples: 982666. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2024-09-21 02:22:55,982][00440] Avg episode reward: [(0, '22.652')] +[2024-09-21 02:23:00,974][00440] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3651.7). Total num frames: 3948544. Throughput: 0: 908.4. Samples: 987220. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2024-09-21 02:23:00,978][00440] Avg episode reward: [(0, '23.433')] +[2024-09-21 02:23:05,974][00440] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3651.7). Total num frames: 3969024. Throughput: 0: 864.3. Samples: 992024. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2024-09-21 02:23:05,979][00440] Avg episode reward: [(0, '22.897')] +[2024-09-21 02:23:06,576][02544] Updated weights for policy 0, policy_version 970 (0.0026) +[2024-09-21 02:23:10,974][00440] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3651.7). Total num frames: 3989504. Throughput: 0: 877.6. Samples: 995386. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2024-09-21 02:23:10,977][00440] Avg episode reward: [(0, '23.127')] +[2024-09-21 02:23:13,997][02531] Stopping Batcher_0... +[2024-09-21 02:23:13,998][02531] Loop batcher_evt_loop terminating... +[2024-09-21 02:23:13,998][00440] Component Batcher_0 stopped! +[2024-09-21 02:23:14,009][02531] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... +[2024-09-21 02:23:14,074][02544] Weights refcount: 2 0 +[2024-09-21 02:23:14,079][00440] Component InferenceWorker_p0-w0 stopped! +[2024-09-21 02:23:14,086][02544] Stopping InferenceWorker_p0-w0... +[2024-09-21 02:23:14,087][02544] Loop inference_proc0-0_evt_loop terminating... +[2024-09-21 02:23:14,215][02531] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000808_3309568.pth +[2024-09-21 02:23:14,245][02531] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... +[2024-09-21 02:23:14,485][02531] Stopping LearnerWorker_p0... +[2024-09-21 02:23:14,486][02531] Loop learner_proc0_evt_loop terminating... +[2024-09-21 02:23:14,486][00440] Component LearnerWorker_p0 stopped! +[2024-09-21 02:23:14,720][00440] Component RolloutWorker_w5 stopped! +[2024-09-21 02:23:14,720][02550] Stopping RolloutWorker_w5... +[2024-09-21 02:23:14,739][02550] Loop rollout_proc5_evt_loop terminating... +[2024-09-21 02:23:14,757][02552] Stopping RolloutWorker_w7... +[2024-09-21 02:23:14,757][02552] Loop rollout_proc7_evt_loop terminating... +[2024-09-21 02:23:14,756][00440] Component RolloutWorker_w7 stopped! +[2024-09-21 02:23:14,776][00440] Component RolloutWorker_w3 stopped! +[2024-09-21 02:23:14,778][02548] Stopping RolloutWorker_w3... +[2024-09-21 02:23:14,789][02548] Loop rollout_proc3_evt_loop terminating... +[2024-09-21 02:23:14,806][00440] Component RolloutWorker_w1 stopped! +[2024-09-21 02:23:14,808][00440] Component RolloutWorker_w4 stopped! +[2024-09-21 02:23:14,808][02549] Stopping RolloutWorker_w4... +[2024-09-21 02:23:14,812][02549] Loop rollout_proc4_evt_loop terminating... +[2024-09-21 02:23:14,811][02546] Stopping RolloutWorker_w1... +[2024-09-21 02:23:14,813][02546] Loop rollout_proc1_evt_loop terminating... +[2024-09-21 02:23:14,848][02551] Stopping RolloutWorker_w6... +[2024-09-21 02:23:14,848][00440] Component RolloutWorker_w6 stopped! +[2024-09-21 02:23:14,860][02551] Loop rollout_proc6_evt_loop terminating... +[2024-09-21 02:23:14,902][00440] Component RolloutWorker_w0 stopped! +[2024-09-21 02:23:14,903][02545] Stopping RolloutWorker_w0... +[2024-09-21 02:23:14,918][02545] Loop rollout_proc0_evt_loop terminating... +[2024-09-21 02:23:14,997][00440] Component RolloutWorker_w2 stopped! +[2024-09-21 02:23:15,003][02547] Stopping RolloutWorker_w2... +[2024-09-21 02:23:15,002][00440] Waiting for process learner_proc0 to stop... +[2024-09-21 02:23:15,014][02547] Loop rollout_proc2_evt_loop terminating... +[2024-09-21 02:23:16,621][00440] Waiting for process inference_proc0-0 to join... +[2024-09-21 02:23:16,864][00440] Waiting for process rollout_proc0 to join... +[2024-09-21 02:23:19,584][00440] Waiting for process rollout_proc1 to join... +[2024-09-21 02:23:19,587][00440] Waiting for process rollout_proc2 to join... +[2024-09-21 02:23:19,592][00440] Waiting for process rollout_proc3 to join... +[2024-09-21 02:23:19,596][00440] Waiting for process rollout_proc4 to join... +[2024-09-21 02:23:19,599][00440] Waiting for process rollout_proc5 to join... +[2024-09-21 02:23:19,602][00440] Waiting for process rollout_proc6 to join... +[2024-09-21 02:23:19,606][00440] Waiting for process rollout_proc7 to join... +[2024-09-21 02:23:19,610][00440] Batcher 0 profile tree view: +batching: 29.0248, releasing_batches: 0.0327 +[2024-09-21 02:23:19,612][00440] InferenceWorker_p0-w0 profile tree view: wait_policy: 0.0000 - wait_policy_total: 480.6529 -update_model: 10.5270 - weight_update: 0.0032 -one_step: 0.0067 - handle_policy_step: 686.3036 - deserialize: 16.8077, stack: 3.8914, obs_to_device_normalize: 135.4189, forward: 369.1527, send_messages: 33.1738 - prepare_outputs: 94.1801 - to_cpu: 52.8703 -[2024-09-21 00:32:21,483][01870] Learner 0 profile tree view: -misc: 0.0066, prepare_batch: 13.7032 -train: 76.3728 - epoch_init: 0.0064, minibatch_init: 0.0098, losses_postprocess: 0.5684, kl_divergence: 0.7089, after_optimizer: 34.1747 - calculate_losses: 27.5279 - losses_init: 0.0040, forward_head: 1.3482, bptt_initial: 18.1621, tail: 1.1910, advantages_returns: 0.3237, losses: 3.8295 - bptt: 2.3276 - bptt_forward_core: 2.2020 - update: 12.6233 - clip: 1.0185 -[2024-09-21 00:32:21,484][01870] RolloutWorker_w0 profile tree view: -wait_for_trajectories: 0.4464, enqueue_policy_requests: 132.1851, env_step: 938.8673, overhead: 18.1370, complete_rollouts: 8.1048 -save_policy_outputs: 25.9149 - split_output_tensors: 10.5231 -[2024-09-21 00:32:21,486][01870] RolloutWorker_w7 profile tree view: -wait_for_trajectories: 0.4908, enqueue_policy_requests: 133.9559, env_step: 936.0776, overhead: 18.1099, complete_rollouts: 9.0465 -save_policy_outputs: 26.2263 - split_output_tensors: 10.0755 -[2024-09-21 00:32:21,492][01870] Loop Runner_EvtLoop terminating... -[2024-09-21 00:32:21,493][01870] Runner profile tree view: -main_loop: 1256.9313 -[2024-09-21 00:32:21,494][01870] Collected {0: 4005888}, FPS: 3187.0 -[2024-09-21 00:32:57,611][01870] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json -[2024-09-21 00:32:57,613][01870] Overriding arg 'num_workers' with value 1 passed from command line -[2024-09-21 00:32:57,615][01870] Adding new argument 'no_render'=True that is not in the saved config file! -[2024-09-21 00:32:57,617][01870] Adding new argument 'save_video'=True that is not in the saved config file! -[2024-09-21 00:32:57,619][01870] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file! -[2024-09-21 00:32:57,621][01870] Adding new argument 'video_name'=None that is not in the saved config file! -[2024-09-21 00:32:57,623][01870] Adding new argument 'max_num_frames'=1000000000.0 that is not in the saved config file! -[2024-09-21 00:32:57,624][01870] Adding new argument 'max_num_episodes'=10 that is not in the saved config file! -[2024-09-21 00:32:57,628][01870] Adding new argument 'push_to_hub'=False that is not in the saved config file! -[2024-09-21 00:32:57,629][01870] Adding new argument 'hf_repository'=None that is not in the saved config file! -[2024-09-21 00:32:57,631][01870] Adding new argument 'policy_index'=0 that is not in the saved config file! -[2024-09-21 00:32:57,632][01870] Adding new argument 'eval_deterministic'=False that is not in the saved config file! -[2024-09-21 00:32:57,633][01870] Adding new argument 'train_script'=None that is not in the saved config file! -[2024-09-21 00:32:57,634][01870] Adding new argument 'enjoy_script'=None that is not in the saved config file! -[2024-09-21 00:32:57,635][01870] Using frameskip 1 and render_action_repeat=4 for evaluation -[2024-09-21 00:32:57,671][01870] Doom resolution: 160x120, resize resolution: (128, 72) -[2024-09-21 00:32:57,675][01870] RunningMeanStd input shape: (3, 72, 128) -[2024-09-21 00:32:57,679][01870] RunningMeanStd input shape: (1,) -[2024-09-21 00:32:57,696][01870] ConvEncoder: input_channels=3 -[2024-09-21 00:32:57,807][01870] Conv encoder output size: 512 -[2024-09-21 00:32:57,809][01870] Policy head output size: 512 -[2024-09-21 00:32:58,007][01870] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... -[2024-09-21 00:32:58,874][01870] Num frames 100... -[2024-09-21 00:32:59,007][01870] Num frames 200... -[2024-09-21 00:32:59,132][01870] Num frames 300... -[2024-09-21 00:32:59,265][01870] Num frames 400... -[2024-09-21 00:32:59,394][01870] Num frames 500... -[2024-09-21 00:32:59,533][01870] Num frames 600... -[2024-09-21 00:32:59,664][01870] Num frames 700... -[2024-09-21 00:32:59,804][01870] Avg episode rewards: #0: 16.680, true rewards: #0: 7.680 -[2024-09-21 00:32:59,808][01870] Avg episode reward: 16.680, avg true_objective: 7.680 -[2024-09-21 00:32:59,851][01870] Num frames 800... -[2024-09-21 00:32:59,996][01870] Num frames 900... -[2024-09-21 00:33:00,131][01870] Num frames 1000... -[2024-09-21 00:33:00,259][01870] Num frames 1100... -[2024-09-21 00:33:00,385][01870] Num frames 1200... -[2024-09-21 00:33:00,522][01870] Num frames 1300... -[2024-09-21 00:33:00,645][01870] Num frames 1400... -[2024-09-21 00:33:00,777][01870] Num frames 1500... -[2024-09-21 00:33:00,904][01870] Num frames 1600... -[2024-09-21 00:33:01,048][01870] Num frames 1700... -[2024-09-21 00:33:01,181][01870] Num frames 1800... -[2024-09-21 00:33:01,314][01870] Num frames 1900... -[2024-09-21 00:33:01,450][01870] Num frames 2000... -[2024-09-21 00:33:01,586][01870] Num frames 2100... -[2024-09-21 00:33:01,712][01870] Num frames 2200... -[2024-09-21 00:33:01,842][01870] Avg episode rewards: #0: 26.290, true rewards: #0: 11.290 -[2024-09-21 00:33:01,844][01870] Avg episode reward: 26.290, avg true_objective: 11.290 -[2024-09-21 00:33:01,903][01870] Num frames 2300... -[2024-09-21 00:33:02,044][01870] Num frames 2400... -[2024-09-21 00:33:02,172][01870] Num frames 2500... -[2024-09-21 00:33:02,306][01870] Num frames 2600... -[2024-09-21 00:33:02,431][01870] Num frames 2700... -[2024-09-21 00:33:02,568][01870] Num frames 2800... -[2024-09-21 00:33:02,701][01870] Num frames 2900... -[2024-09-21 00:33:02,831][01870] Num frames 3000... -[2024-09-21 00:33:02,968][01870] Num frames 3100... -[2024-09-21 00:33:03,095][01870] Num frames 3200... -[2024-09-21 00:33:03,224][01870] Num frames 3300... -[2024-09-21 00:33:03,356][01870] Num frames 3400... -[2024-09-21 00:33:03,483][01870] Num frames 3500... -[2024-09-21 00:33:03,623][01870] Num frames 3600... -[2024-09-21 00:33:03,748][01870] Num frames 3700... -[2024-09-21 00:33:03,876][01870] Num frames 3800... -[2024-09-21 00:33:04,015][01870] Num frames 3900... -[2024-09-21 00:33:04,147][01870] Num frames 4000... -[2024-09-21 00:33:04,276][01870] Num frames 4100... -[2024-09-21 00:33:04,410][01870] Num frames 4200... -[2024-09-21 00:33:04,535][01870] Num frames 4300... -[2024-09-21 00:33:04,674][01870] Avg episode rewards: #0: 35.860, true rewards: #0: 14.527 -[2024-09-21 00:33:04,676][01870] Avg episode reward: 35.860, avg true_objective: 14.527 -[2024-09-21 00:33:04,731][01870] Num frames 4400... -[2024-09-21 00:33:04,857][01870] Num frames 4500... -[2024-09-21 00:33:04,995][01870] Num frames 4600... -[2024-09-21 00:33:05,176][01870] Num frames 4700... -[2024-09-21 00:33:05,354][01870] Num frames 4800... -[2024-09-21 00:33:05,541][01870] Num frames 4900... -[2024-09-21 00:33:05,725][01870] Num frames 5000... -[2024-09-21 00:33:05,837][01870] Avg episode rewards: #0: 30.325, true rewards: #0: 12.575 -[2024-09-21 00:33:05,839][01870] Avg episode reward: 30.325, avg true_objective: 12.575 -[2024-09-21 00:33:05,970][01870] Num frames 5100... -[2024-09-21 00:33:06,140][01870] Num frames 5200... -[2024-09-21 00:33:06,318][01870] Num frames 5300... -[2024-09-21 00:33:06,503][01870] Num frames 5400... -[2024-09-21 00:33:06,689][01870] Num frames 5500... -[2024-09-21 00:33:06,877][01870] Num frames 5600... -[2024-09-21 00:33:07,064][01870] Num frames 5700... -[2024-09-21 00:33:07,303][01870] Avg episode rewards: #0: 26.796, true rewards: #0: 11.596 -[2024-09-21 00:33:07,305][01870] Avg episode reward: 26.796, avg true_objective: 11.596 -[2024-09-21 00:33:07,311][01870] Num frames 5800... -[2024-09-21 00:33:07,502][01870] Num frames 5900... -[2024-09-21 00:33:07,633][01870] Num frames 6000... -[2024-09-21 00:33:07,771][01870] Num frames 6100... -[2024-09-21 00:33:07,901][01870] Num frames 6200... -[2024-09-21 00:33:08,040][01870] Num frames 6300... -[2024-09-21 00:33:08,170][01870] Num frames 6400... -[2024-09-21 00:33:08,303][01870] Num frames 6500... -[2024-09-21 00:33:08,431][01870] Num frames 6600... -[2024-09-21 00:33:08,560][01870] Num frames 6700... -[2024-09-21 00:33:08,738][01870] Avg episode rewards: #0: 26.323, true rewards: #0: 11.323 -[2024-09-21 00:33:08,740][01870] Avg episode reward: 26.323, avg true_objective: 11.323 -[2024-09-21 00:33:08,753][01870] Num frames 6800... -[2024-09-21 00:33:08,883][01870] Num frames 6900... -[2024-09-21 00:33:09,020][01870] Num frames 7000... -[2024-09-21 00:33:09,149][01870] Num frames 7100... -[2024-09-21 00:33:09,280][01870] Num frames 7200... -[2024-09-21 00:33:09,409][01870] Num frames 7300... -[2024-09-21 00:33:09,537][01870] Num frames 7400... -[2024-09-21 00:33:09,671][01870] Num frames 7500... -[2024-09-21 00:33:09,810][01870] Num frames 7600... -[2024-09-21 00:33:09,948][01870] Num frames 7700... -[2024-09-21 00:33:10,081][01870] Num frames 7800... -[2024-09-21 00:33:10,212][01870] Num frames 7900... -[2024-09-21 00:33:10,340][01870] Num frames 8000... -[2024-09-21 00:33:10,466][01870] Num frames 8100... -[2024-09-21 00:33:10,590][01870] Num frames 8200... -[2024-09-21 00:33:10,715][01870] Num frames 8300... -[2024-09-21 00:33:10,852][01870] Num frames 8400... -[2024-09-21 00:33:10,990][01870] Num frames 8500... -[2024-09-21 00:33:11,110][01870] Avg episode rewards: #0: 28.924, true rewards: #0: 12.210 -[2024-09-21 00:33:11,114][01870] Avg episode reward: 28.924, avg true_objective: 12.210 -[2024-09-21 00:33:11,185][01870] Num frames 8600... -[2024-09-21 00:33:11,314][01870] Num frames 8700... -[2024-09-21 00:33:11,440][01870] Num frames 8800... -[2024-09-21 00:33:11,568][01870] Num frames 8900... -[2024-09-21 00:33:11,693][01870] Num frames 9000... -[2024-09-21 00:33:11,828][01870] Num frames 9100... -[2024-09-21 00:33:11,964][01870] Num frames 9200... -[2024-09-21 00:33:12,088][01870] Num frames 9300... -[2024-09-21 00:33:12,211][01870] Num frames 9400... -[2024-09-21 00:33:12,361][01870] Avg episode rewards: #0: 27.344, true rewards: #0: 11.844 -[2024-09-21 00:33:12,363][01870] Avg episode reward: 27.344, avg true_objective: 11.844 -[2024-09-21 00:33:12,399][01870] Num frames 9500... -[2024-09-21 00:33:12,527][01870] Num frames 9600... -[2024-09-21 00:33:12,652][01870] Num frames 9700... -[2024-09-21 00:33:12,774][01870] Num frames 9800... -[2024-09-21 00:33:12,911][01870] Num frames 9900... -[2024-09-21 00:33:13,058][01870] Num frames 10000... -[2024-09-21 00:33:13,218][01870] Num frames 10100... -[2024-09-21 00:33:13,352][01870] Num frames 10200... -[2024-09-21 00:33:13,476][01870] Avg episode rewards: #0: 25.949, true rewards: #0: 11.393 -[2024-09-21 00:33:13,477][01870] Avg episode reward: 25.949, avg true_objective: 11.393 -[2024-09-21 00:33:13,648][01870] Num frames 10300... -[2024-09-21 00:33:13,777][01870] Num frames 10400... -[2024-09-21 00:33:13,911][01870] Num frames 10500... -[2024-09-21 00:33:14,050][01870] Num frames 10600... -[2024-09-21 00:33:14,173][01870] Num frames 10700... -[2024-09-21 00:33:14,413][01870] Num frames 10800... -[2024-09-21 00:33:14,542][01870] Num frames 10900... -[2024-09-21 00:33:14,670][01870] Num frames 11000... -[2024-09-21 00:33:14,800][01870] Num frames 11100... -[2024-09-21 00:33:14,941][01870] Num frames 11200... -[2024-09-21 00:33:15,075][01870] Num frames 11300... -[2024-09-21 00:33:15,204][01870] Num frames 11400... -[2024-09-21 00:33:15,332][01870] Num frames 11500... -[2024-09-21 00:33:15,456][01870] Avg episode rewards: #0: 26.149, true rewards: #0: 11.549 -[2024-09-21 00:33:15,458][01870] Avg episode reward: 26.149, avg true_objective: 11.549 -[2024-09-21 00:34:37,032][01870] Replay video saved to /content/train_dir/default_experiment/replay.mp4! -[2024-09-21 01:12:00,491][01870] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json -[2024-09-21 01:12:00,493][01870] Overriding arg 'num_workers' with value 1 passed from command line -[2024-09-21 01:12:00,495][01870] Adding new argument 'no_render'=True that is not in the saved config file! -[2024-09-21 01:12:00,498][01870] Adding new argument 'save_video'=True that is not in the saved config file! -[2024-09-21 01:12:00,499][01870] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file! -[2024-09-21 01:12:00,501][01870] Adding new argument 'video_name'=None that is not in the saved config file! -[2024-09-21 01:12:00,503][01870] Adding new argument 'max_num_frames'=100000 that is not in the saved config file! -[2024-09-21 01:12:00,504][01870] Adding new argument 'max_num_episodes'=10 that is not in the saved config file! -[2024-09-21 01:12:00,507][01870] Adding new argument 'push_to_hub'=True that is not in the saved config file! -[2024-09-21 01:12:00,508][01870] Adding new argument 'hf_repository'='yin771/rl_course_vizdoom_health_gathering_supreme' that is not in the saved config file! -[2024-09-21 01:12:00,509][01870] Adding new argument 'policy_index'=0 that is not in the saved config file! -[2024-09-21 01:12:00,510][01870] Adding new argument 'eval_deterministic'=False that is not in the saved config file! -[2024-09-21 01:12:00,511][01870] Adding new argument 'train_script'=None that is not in the saved config file! -[2024-09-21 01:12:00,512][01870] Adding new argument 'enjoy_script'=None that is not in the saved config file! -[2024-09-21 01:12:00,513][01870] Using frameskip 1 and render_action_repeat=4 for evaluation -[2024-09-21 01:12:00,543][01870] RunningMeanStd input shape: (3, 72, 128) -[2024-09-21 01:12:00,546][01870] RunningMeanStd input shape: (1,) -[2024-09-21 01:12:00,560][01870] ConvEncoder: input_channels=3 -[2024-09-21 01:12:00,602][01870] Conv encoder output size: 512 -[2024-09-21 01:12:00,604][01870] Policy head output size: 512 -[2024-09-21 01:12:00,624][01870] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... -[2024-09-21 01:12:01,096][01870] Num frames 100... -[2024-09-21 01:12:01,221][01870] Num frames 200... -[2024-09-21 01:12:01,348][01870] Num frames 300... -[2024-09-21 01:12:01,484][01870] Num frames 400... -[2024-09-21 01:12:01,620][01870] Num frames 500... -[2024-09-21 01:12:01,745][01870] Num frames 600... -[2024-09-21 01:12:01,895][01870] Num frames 700... -[2024-09-21 01:12:02,034][01870] Num frames 800... -[2024-09-21 01:12:02,160][01870] Num frames 900... -[2024-09-21 01:12:02,288][01870] Num frames 1000... -[2024-09-21 01:12:02,375][01870] Avg episode rewards: #0: 24.240, true rewards: #0: 10.240 -[2024-09-21 01:12:02,378][01870] Avg episode reward: 24.240, avg true_objective: 10.240 -[2024-09-21 01:12:02,480][01870] Num frames 1100... -[2024-09-21 01:12:02,609][01870] Num frames 1200... -[2024-09-21 01:12:02,743][01870] Num frames 1300... -[2024-09-21 01:12:02,869][01870] Num frames 1400... -[2024-09-21 01:12:03,023][01870] Num frames 1500... -[2024-09-21 01:12:03,151][01870] Num frames 1600... -[2024-09-21 01:12:03,288][01870] Num frames 1700... -[2024-09-21 01:12:03,423][01870] Num frames 1800... -[2024-09-21 01:12:03,550][01870] Num frames 1900... -[2024-09-21 01:12:03,681][01870] Num frames 2000... -[2024-09-21 01:12:03,810][01870] Num frames 2100... -[2024-09-21 01:12:03,959][01870] Num frames 2200... -[2024-09-21 01:12:04,087][01870] Num frames 2300... -[2024-09-21 01:12:04,216][01870] Num frames 2400... -[2024-09-21 01:12:04,367][01870] Avg episode rewards: #0: 27.380, true rewards: #0: 12.380 -[2024-09-21 01:12:04,369][01870] Avg episode reward: 27.380, avg true_objective: 12.380 -[2024-09-21 01:12:04,403][01870] Num frames 2500... -[2024-09-21 01:12:04,528][01870] Num frames 2600... -[2024-09-21 01:12:04,653][01870] Num frames 2700... -[2024-09-21 01:12:04,777][01870] Num frames 2800... -[2024-09-21 01:12:04,912][01870] Num frames 2900... -[2024-09-21 01:12:05,092][01870] Avg episode rewards: #0: 20.960, true rewards: #0: 9.960 -[2024-09-21 01:12:05,094][01870] Avg episode reward: 20.960, avg true_objective: 9.960 -[2024-09-21 01:12:05,115][01870] Num frames 3000... -[2024-09-21 01:12:05,240][01870] Num frames 3100... -[2024-09-21 01:12:05,373][01870] Num frames 3200... -[2024-09-21 01:12:05,503][01870] Num frames 3300... -[2024-09-21 01:12:05,632][01870] Num frames 3400... -[2024-09-21 01:12:05,756][01870] Num frames 3500... -[2024-09-21 01:12:05,883][01870] Num frames 3600... -[2024-09-21 01:12:06,027][01870] Num frames 3700... -[2024-09-21 01:12:06,153][01870] Num frames 3800... -[2024-09-21 01:12:06,286][01870] Num frames 3900... -[2024-09-21 01:12:06,413][01870] Num frames 4000... -[2024-09-21 01:12:06,542][01870] Num frames 4100... -[2024-09-21 01:12:06,671][01870] Num frames 4200... -[2024-09-21 01:12:06,809][01870] Avg episode rewards: #0: 23.915, true rewards: #0: 10.665 -[2024-09-21 01:12:06,811][01870] Avg episode reward: 23.915, avg true_objective: 10.665 -[2024-09-21 01:12:06,857][01870] Num frames 4300... -[2024-09-21 01:12:06,995][01870] Num frames 4400... -[2024-09-21 01:12:07,127][01870] Num frames 4500... -[2024-09-21 01:12:07,250][01870] Num frames 4600... -[2024-09-21 01:12:07,374][01870] Num frames 4700... -[2024-09-21 01:12:07,500][01870] Num frames 4800... -[2024-09-21 01:12:07,640][01870] Num frames 4900... -[2024-09-21 01:12:07,765][01870] Num frames 5000... -[2024-09-21 01:12:07,895][01870] Num frames 5100... -[2024-09-21 01:12:07,998][01870] Avg episode rewards: #0: 22.060, true rewards: #0: 10.260 -[2024-09-21 01:12:08,004][01870] Avg episode reward: 22.060, avg true_objective: 10.260 -[2024-09-21 01:12:08,148][01870] Num frames 5200... -[2024-09-21 01:12:08,333][01870] Num frames 5300... -[2024-09-21 01:12:08,505][01870] Num frames 5400... -[2024-09-21 01:12:08,681][01870] Num frames 5500... -[2024-09-21 01:12:08,851][01870] Num frames 5600... -[2024-09-21 01:12:09,030][01870] Num frames 5700... -[2024-09-21 01:12:09,219][01870] Num frames 5800... -[2024-09-21 01:12:09,394][01870] Num frames 5900... -[2024-09-21 01:12:09,575][01870] Num frames 6000... -[2024-09-21 01:12:09,756][01870] Num frames 6100... -[2024-09-21 01:12:09,950][01870] Num frames 6200... -[2024-09-21 01:12:10,133][01870] Num frames 6300... -[2024-09-21 01:12:10,334][01870] Num frames 6400... -[2024-09-21 01:12:10,524][01870] Num frames 6500... -[2024-09-21 01:12:10,696][01870] Num frames 6600... -[2024-09-21 01:12:10,826][01870] Num frames 6700... -[2024-09-21 01:12:10,962][01870] Num frames 6800... -[2024-09-21 01:12:11,093][01870] Num frames 6900... -[2024-09-21 01:12:11,235][01870] Num frames 7000... -[2024-09-21 01:12:11,364][01870] Num frames 7100... -[2024-09-21 01:12:11,486][01870] Avg episode rewards: #0: 27.243, true rewards: #0: 11.910 -[2024-09-21 01:12:11,487][01870] Avg episode reward: 27.243, avg true_objective: 11.910 -[2024-09-21 01:12:11,559][01870] Num frames 7200... -[2024-09-21 01:12:11,693][01870] Num frames 7300... -[2024-09-21 01:12:11,829][01870] Num frames 7400... -[2024-09-21 01:12:11,965][01870] Num frames 7500... -[2024-09-21 01:12:12,096][01870] Num frames 7600... -[2024-09-21 01:12:12,226][01870] Num frames 7700... -[2024-09-21 01:12:12,359][01870] Num frames 7800... -[2024-09-21 01:12:12,485][01870] Num frames 7900... -[2024-09-21 01:12:12,610][01870] Num frames 8000... -[2024-09-21 01:12:12,746][01870] Num frames 8100... -[2024-09-21 01:12:12,876][01870] Num frames 8200... -[2024-09-21 01:12:13,017][01870] Num frames 8300... -[2024-09-21 01:12:13,148][01870] Num frames 8400... -[2024-09-21 01:12:13,290][01870] Num frames 8500... -[2024-09-21 01:12:13,420][01870] Num frames 8600... -[2024-09-21 01:12:13,501][01870] Avg episode rewards: #0: 27.454, true rewards: #0: 12.311 -[2024-09-21 01:12:13,504][01870] Avg episode reward: 27.454, avg true_objective: 12.311 -[2024-09-21 01:12:13,609][01870] Num frames 8700... -[2024-09-21 01:12:13,742][01870] Num frames 8800... -[2024-09-21 01:12:13,879][01870] Num frames 8900... -[2024-09-21 01:12:14,016][01870] Num frames 9000... -[2024-09-21 01:12:14,154][01870] Num frames 9100... -[2024-09-21 01:12:14,305][01870] Num frames 9200... -[2024-09-21 01:12:14,436][01870] Num frames 9300... -[2024-09-21 01:12:14,566][01870] Num frames 9400... -[2024-09-21 01:12:14,696][01870] Num frames 9500... -[2024-09-21 01:12:14,822][01870] Num frames 9600... -[2024-09-21 01:12:14,955][01870] Num frames 9700... -[2024-09-21 01:12:15,090][01870] Num frames 9800... -[2024-09-21 01:12:15,216][01870] Num frames 9900... -[2024-09-21 01:12:15,353][01870] Num frames 10000... -[2024-09-21 01:12:15,547][01870] Avg episode rewards: #0: 28.866, true rewards: #0: 12.616 -[2024-09-21 01:12:15,548][01870] Avg episode reward: 28.866, avg true_objective: 12.616 -[2024-09-21 01:12:15,561][01870] Num frames 10100... -[2024-09-21 01:12:15,688][01870] Num frames 10200... -[2024-09-21 01:12:15,814][01870] Num frames 10300... -[2024-09-21 01:12:15,948][01870] Num frames 10400... -[2024-09-21 01:12:16,080][01870] Num frames 10500... -[2024-09-21 01:12:16,206][01870] Num frames 10600... -[2024-09-21 01:12:16,368][01870] Avg episode rewards: #0: 26.646, true rewards: #0: 11.868 -[2024-09-21 01:12:16,371][01870] Avg episode reward: 26.646, avg true_objective: 11.868 -[2024-09-21 01:12:16,398][01870] Num frames 10700... -[2024-09-21 01:12:16,524][01870] Num frames 10800... -[2024-09-21 01:12:16,654][01870] Num frames 10900... -[2024-09-21 01:12:16,781][01870] Num frames 11000... -[2024-09-21 01:12:16,912][01870] Num frames 11100... -[2024-09-21 01:12:17,048][01870] Num frames 11200... -[2024-09-21 01:12:17,173][01870] Num frames 11300... -[2024-09-21 01:12:17,302][01870] Num frames 11400... -[2024-09-21 01:12:17,438][01870] Num frames 11500... -[2024-09-21 01:12:17,566][01870] Num frames 11600... -[2024-09-21 01:12:17,692][01870] Num frames 11700... -[2024-09-21 01:12:17,818][01870] Num frames 11800... -[2024-09-21 01:12:17,951][01870] Num frames 11900... -[2024-09-21 01:12:18,075][01870] Avg episode rewards: #0: 27.250, true rewards: #0: 11.950 -[2024-09-21 01:12:18,077][01870] Avg episode reward: 27.250, avg true_objective: 11.950 -[2024-09-21 01:13:42,457][01870] Replay video saved to /content/train_dir/default_experiment/replay.mp4! + wait_policy_total: 407.0186 +update_model: 9.8448 + weight_update: 0.0034 +one_step: 0.0055 + handle_policy_step: 653.5996 + deserialize: 15.8371, stack: 3.5892, obs_to_device_normalize: 131.7549, forward: 348.8599, send_messages: 31.2155 + prepare_outputs: 90.5582 + to_cpu: 51.8778 +[2024-09-21 02:23:19,614][00440] Learner 0 profile tree view: +misc: 0.0062, prepare_batch: 14.4260 +train: 74.0754 + epoch_init: 0.0056, minibatch_init: 0.0182, losses_postprocess: 0.6605, kl_divergence: 0.7201, after_optimizer: 33.7126 + calculate_losses: 26.0268 + losses_init: 0.0035, forward_head: 1.2164, bptt_initial: 17.2207, tail: 1.2457, advantages_returns: 0.2597, losses: 3.6522 + bptt: 2.0391 + bptt_forward_core: 1.9026 + update: 12.2437 + clip: 0.9446 +[2024-09-21 02:23:19,615][00440] RolloutWorker_w0 profile tree view: +wait_for_trajectories: 0.3249, enqueue_policy_requests: 102.2515, env_step: 863.2234, overhead: 14.5644, complete_rollouts: 7.4808 +save_policy_outputs: 23.3946 + split_output_tensors: 9.3306 +[2024-09-21 02:23:19,617][00440] RolloutWorker_w7 profile tree view: +wait_for_trajectories: 0.3913, enqueue_policy_requests: 106.0330, env_step: 862.3417, overhead: 15.2255, complete_rollouts: 7.1341 +save_policy_outputs: 21.6515 + split_output_tensors: 9.2174 +[2024-09-21 02:23:19,618][00440] Loop Runner_EvtLoop terminating... +[2024-09-21 02:23:19,620][00440] Runner profile tree view: +main_loop: 1148.2084 +[2024-09-21 02:23:19,621][00440] Collected {0: 4005888}, FPS: 3488.8 +[2024-09-21 02:23:26,216][00440] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json +[2024-09-21 02:23:26,217][00440] Overriding arg 'num_workers' with value 1 passed from command line +[2024-09-21 02:23:26,222][00440] Adding new argument 'no_render'=True that is not in the saved config file! +[2024-09-21 02:23:26,224][00440] Adding new argument 'save_video'=True that is not in the saved config file! +[2024-09-21 02:23:26,225][00440] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file! +[2024-09-21 02:23:26,229][00440] Adding new argument 'video_name'=None that is not in the saved config file! +[2024-09-21 02:23:26,230][00440] Adding new argument 'max_num_frames'=1000000000.0 that is not in the saved config file! +[2024-09-21 02:23:26,232][00440] Adding new argument 'max_num_episodes'=10 that is not in the saved config file! +[2024-09-21 02:23:26,234][00440] Adding new argument 'push_to_hub'=False that is not in the saved config file! +[2024-09-21 02:23:26,236][00440] Adding new argument 'hf_repository'=None that is not in the saved config file! +[2024-09-21 02:23:26,238][00440] Adding new argument 'policy_index'=0 that is not in the saved config file! +[2024-09-21 02:23:26,240][00440] Adding new argument 'eval_deterministic'=False that is not in the saved config file! +[2024-09-21 02:23:26,242][00440] Adding new argument 'train_script'=None that is not in the saved config file! +[2024-09-21 02:23:26,246][00440] Adding new argument 'enjoy_script'=None that is not in the saved config file! +[2024-09-21 02:23:26,249][00440] Using frameskip 1 and render_action_repeat=4 for evaluation +[2024-09-21 02:23:26,278][00440] Doom resolution: 160x120, resize resolution: (128, 72) +[2024-09-21 02:23:26,282][00440] RunningMeanStd input shape: (3, 72, 128) +[2024-09-21 02:23:26,284][00440] RunningMeanStd input shape: (1,) +[2024-09-21 02:23:26,301][00440] ConvEncoder: input_channels=3 +[2024-09-21 02:23:26,405][00440] Conv encoder output size: 512 +[2024-09-21 02:23:26,407][00440] Policy head output size: 512 +[2024-09-21 02:23:26,696][00440] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... +[2024-09-21 02:23:27,561][00440] Num frames 100... +[2024-09-21 02:23:27,688][00440] Num frames 200... +[2024-09-21 02:23:27,819][00440] Num frames 300... +[2024-09-21 02:23:27,951][00440] Num frames 400... +[2024-09-21 02:23:28,078][00440] Num frames 500... +[2024-09-21 02:23:28,205][00440] Num frames 600... +[2024-09-21 02:23:28,329][00440] Num frames 700... +[2024-09-21 02:23:28,509][00440] Num frames 800... +[2024-09-21 02:23:28,686][00440] Num frames 900... +[2024-09-21 02:23:28,869][00440] Num frames 1000... +[2024-09-21 02:23:29,042][00440] Num frames 1100... +[2024-09-21 02:23:29,223][00440] Num frames 1200... +[2024-09-21 02:23:29,394][00440] Num frames 1300... +[2024-09-21 02:23:29,576][00440] Num frames 1400... +[2024-09-21 02:23:29,761][00440] Num frames 1500... +[2024-09-21 02:23:29,840][00440] Avg episode rewards: #0: 33.090, true rewards: #0: 15.090 +[2024-09-21 02:23:29,842][00440] Avg episode reward: 33.090, avg true_objective: 15.090 +[2024-09-21 02:23:30,011][00440] Num frames 1600... +[2024-09-21 02:23:30,188][00440] Num frames 1700... +[2024-09-21 02:23:30,377][00440] Num frames 1800... +[2024-09-21 02:23:30,556][00440] Num frames 1900... +[2024-09-21 02:23:30,736][00440] Num frames 2000... +[2024-09-21 02:23:30,922][00440] Num frames 2100... +[2024-09-21 02:23:31,070][00440] Num frames 2200... +[2024-09-21 02:23:31,200][00440] Num frames 2300... +[2024-09-21 02:23:31,329][00440] Num frames 2400... +[2024-09-21 02:23:31,454][00440] Num frames 2500... +[2024-09-21 02:23:31,583][00440] Num frames 2600... +[2024-09-21 02:23:31,715][00440] Num frames 2700... +[2024-09-21 02:23:31,849][00440] Num frames 2800... +[2024-09-21 02:23:31,978][00440] Num frames 2900... +[2024-09-21 02:23:32,117][00440] Num frames 3000... +[2024-09-21 02:23:32,247][00440] Num frames 3100... +[2024-09-21 02:23:32,375][00440] Num frames 3200... +[2024-09-21 02:23:32,499][00440] Num frames 3300... +[2024-09-21 02:23:32,625][00440] Avg episode rewards: #0: 38.270, true rewards: #0: 16.770 +[2024-09-21 02:23:32,626][00440] Avg episode reward: 38.270, avg true_objective: 16.770 +[2024-09-21 02:23:32,684][00440] Num frames 3400... +[2024-09-21 02:23:32,820][00440] Num frames 3500... +[2024-09-21 02:23:32,943][00440] Num frames 3600... +[2024-09-21 02:23:33,077][00440] Num frames 3700... +[2024-09-21 02:23:33,202][00440] Num frames 3800... +[2024-09-21 02:23:33,330][00440] Num frames 3900... +[2024-09-21 02:23:33,460][00440] Num frames 4000... +[2024-09-21 02:23:33,589][00440] Num frames 4100... +[2024-09-21 02:23:33,719][00440] Num frames 4200... +[2024-09-21 02:23:33,845][00440] Num frames 4300... +[2024-09-21 02:23:33,977][00440] Num frames 4400... +[2024-09-21 02:23:34,039][00440] Avg episode rewards: #0: 35.343, true rewards: #0: 14.677 +[2024-09-21 02:23:34,041][00440] Avg episode reward: 35.343, avg true_objective: 14.677 +[2024-09-21 02:23:34,176][00440] Num frames 4500... +[2024-09-21 02:23:34,301][00440] Num frames 4600... +[2024-09-21 02:23:34,427][00440] Num frames 4700... +[2024-09-21 02:23:34,556][00440] Num frames 4800... +[2024-09-21 02:23:34,714][00440] Avg episode rewards: #0: 28.458, true rewards: #0: 12.207 +[2024-09-21 02:23:34,716][00440] Avg episode reward: 28.458, avg true_objective: 12.207 +[2024-09-21 02:23:34,745][00440] Num frames 4900... +[2024-09-21 02:23:34,873][00440] Num frames 5000... +[2024-09-21 02:23:34,999][00440] Num frames 5100... +[2024-09-21 02:23:35,136][00440] Num frames 5200... +[2024-09-21 02:23:35,267][00440] Num frames 5300... +[2024-09-21 02:23:35,394][00440] Num frames 5400... +[2024-09-21 02:23:35,520][00440] Num frames 5500... +[2024-09-21 02:23:35,654][00440] Num frames 5600... +[2024-09-21 02:23:35,793][00440] Num frames 5700... +[2024-09-21 02:23:35,924][00440] Num frames 5800... +[2024-09-21 02:23:36,052][00440] Num frames 5900... +[2024-09-21 02:23:36,190][00440] Num frames 6000... +[2024-09-21 02:23:36,318][00440] Avg episode rewards: #0: 28.710, true rewards: #0: 12.110 +[2024-09-21 02:23:36,320][00440] Avg episode reward: 28.710, avg true_objective: 12.110 +[2024-09-21 02:23:36,379][00440] Num frames 6100... +[2024-09-21 02:23:36,504][00440] Num frames 6200... +[2024-09-21 02:23:36,632][00440] Num frames 6300... +[2024-09-21 02:23:36,768][00440] Num frames 6400... +[2024-09-21 02:23:36,893][00440] Num frames 6500... +[2024-09-21 02:23:37,020][00440] Num frames 6600... +[2024-09-21 02:23:37,162][00440] Num frames 6700... +[2024-09-21 02:23:37,290][00440] Num frames 6800... +[2024-09-21 02:23:37,415][00440] Num frames 6900... +[2024-09-21 02:23:37,548][00440] Num frames 7000... +[2024-09-21 02:23:37,710][00440] Num frames 7100... +[2024-09-21 02:23:37,843][00440] Num frames 7200... +[2024-09-21 02:23:37,973][00440] Num frames 7300... +[2024-09-21 02:23:38,101][00440] Num frames 7400... +[2024-09-21 02:23:38,240][00440] Num frames 7500... +[2024-09-21 02:23:38,371][00440] Num frames 7600... +[2024-09-21 02:23:38,506][00440] Num frames 7700... +[2024-09-21 02:23:38,633][00440] Num frames 7800... +[2024-09-21 02:23:38,815][00440] Avg episode rewards: #0: 32.817, true rewards: #0: 13.150 +[2024-09-21 02:23:38,818][00440] Avg episode reward: 32.817, avg true_objective: 13.150 +[2024-09-21 02:23:38,832][00440] Num frames 7900... +[2024-09-21 02:23:38,957][00440] Num frames 8000... +[2024-09-21 02:23:39,085][00440] Num frames 8100... +[2024-09-21 02:23:39,223][00440] Num frames 8200... +[2024-09-21 02:23:39,357][00440] Num frames 8300... +[2024-09-21 02:23:39,491][00440] Num frames 8400... +[2024-09-21 02:23:39,595][00440] Avg episode rewards: #0: 29.334, true rewards: #0: 12.049 +[2024-09-21 02:23:39,597][00440] Avg episode reward: 29.334, avg true_objective: 12.049 +[2024-09-21 02:23:39,679][00440] Num frames 8500... +[2024-09-21 02:23:39,832][00440] Num frames 8600... +[2024-09-21 02:23:39,958][00440] Num frames 8700... +[2024-09-21 02:23:40,086][00440] Num frames 8800... +[2024-09-21 02:23:40,223][00440] Num frames 8900... +[2024-09-21 02:23:40,352][00440] Num frames 9000... +[2024-09-21 02:23:40,478][00440] Num frames 9100... +[2024-09-21 02:23:40,607][00440] Num frames 9200... +[2024-09-21 02:23:40,739][00440] Num frames 9300... +[2024-09-21 02:23:40,833][00440] Avg episode rewards: #0: 28.411, true rewards: #0: 11.661 +[2024-09-21 02:23:40,835][00440] Avg episode reward: 28.411, avg true_objective: 11.661 +[2024-09-21 02:23:40,931][00440] Num frames 9400... +[2024-09-21 02:23:41,090][00440] Num frames 9500... +[2024-09-21 02:23:41,278][00440] Num frames 9600... +[2024-09-21 02:23:41,454][00440] Num frames 9700... +[2024-09-21 02:23:41,634][00440] Num frames 9800... +[2024-09-21 02:23:41,826][00440] Num frames 9900... +[2024-09-21 02:23:41,993][00440] Num frames 10000... +[2024-09-21 02:23:42,163][00440] Num frames 10100... +[2024-09-21 02:23:42,353][00440] Num frames 10200... +[2024-09-21 02:23:42,526][00440] Num frames 10300... +[2024-09-21 02:23:42,704][00440] Num frames 10400... +[2024-09-21 02:23:42,801][00440] Avg episode rewards: #0: 28.019, true rewards: #0: 11.574 +[2024-09-21 02:23:42,804][00440] Avg episode reward: 28.019, avg true_objective: 11.574 +[2024-09-21 02:23:42,951][00440] Num frames 10500... +[2024-09-21 02:23:43,137][00440] Num frames 10600... +[2024-09-21 02:23:43,322][00440] Num frames 10700... +[2024-09-21 02:23:43,511][00440] Num frames 10800... +[2024-09-21 02:23:43,637][00440] Num frames 10900... +[2024-09-21 02:23:43,767][00440] Num frames 11000... +[2024-09-21 02:23:43,901][00440] Num frames 11100... +[2024-09-21 02:23:44,027][00440] Num frames 11200... +[2024-09-21 02:23:44,154][00440] Num frames 11300... +[2024-09-21 02:23:44,284][00440] Num frames 11400... +[2024-09-21 02:23:44,392][00440] Avg episode rewards: #0: 27.241, true rewards: #0: 11.441 +[2024-09-21 02:23:44,394][00440] Avg episode reward: 27.241, avg true_objective: 11.441 +[2024-09-21 02:24:53,513][00440] Replay video saved to /content/train_dir/default_experiment/replay.mp4! +[2024-09-21 02:26:56,392][00440] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json +[2024-09-21 02:26:56,394][00440] Overriding arg 'num_workers' with value 1 passed from command line +[2024-09-21 02:26:56,396][00440] Adding new argument 'no_render'=True that is not in the saved config file! +[2024-09-21 02:26:56,398][00440] Adding new argument 'save_video'=True that is not in the saved config file! +[2024-09-21 02:26:56,401][00440] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file! +[2024-09-21 02:26:56,406][00440] Adding new argument 'video_name'=None that is not in the saved config file! +[2024-09-21 02:26:56,409][00440] Adding new argument 'max_num_frames'=100000 that is not in the saved config file! +[2024-09-21 02:26:56,411][00440] Adding new argument 'max_num_episodes'=10 that is not in the saved config file! +[2024-09-21 02:26:56,412][00440] Adding new argument 'push_to_hub'=True that is not in the saved config file! +[2024-09-21 02:26:56,413][00440] Adding new argument 'hf_repository'='yin771/rl_course_vizdoom_health_gathering_supreme' that is not in the saved config file! +[2024-09-21 02:26:56,414][00440] Adding new argument 'policy_index'=0 that is not in the saved config file! +[2024-09-21 02:26:56,415][00440] Adding new argument 'eval_deterministic'=False that is not in the saved config file! +[2024-09-21 02:26:56,418][00440] Adding new argument 'train_script'=None that is not in the saved config file! +[2024-09-21 02:26:56,419][00440] Adding new argument 'enjoy_script'=None that is not in the saved config file! +[2024-09-21 02:26:56,420][00440] Using frameskip 1 and render_action_repeat=4 for evaluation +[2024-09-21 02:26:56,474][00440] RunningMeanStd input shape: (3, 72, 128) +[2024-09-21 02:26:56,477][00440] RunningMeanStd input shape: (1,) +[2024-09-21 02:26:56,496][00440] ConvEncoder: input_channels=3 +[2024-09-21 02:26:56,554][00440] Conv encoder output size: 512 +[2024-09-21 02:26:56,556][00440] Policy head output size: 512 +[2024-09-21 02:26:56,586][00440] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... +[2024-09-21 02:26:57,268][00440] Num frames 100... +[2024-09-21 02:26:57,434][00440] Num frames 200... +[2024-09-21 02:26:57,622][00440] Num frames 300... +[2024-09-21 02:26:57,796][00440] Num frames 400... +[2024-09-21 02:26:57,979][00440] Num frames 500... +[2024-09-21 02:26:58,117][00440] Avg episode rewards: #0: 9.440, true rewards: #0: 5.440 +[2024-09-21 02:26:58,120][00440] Avg episode reward: 9.440, avg true_objective: 5.440 +[2024-09-21 02:26:58,222][00440] Num frames 600... +[2024-09-21 02:26:58,398][00440] Num frames 700... +[2024-09-21 02:26:58,591][00440] Num frames 800... +[2024-09-21 02:26:58,735][00440] Num frames 900... +[2024-09-21 02:26:58,864][00440] Num frames 1000... +[2024-09-21 02:26:58,989][00440] Num frames 1100... +[2024-09-21 02:26:59,119][00440] Num frames 1200... +[2024-09-21 02:26:59,236][00440] Avg episode rewards: #0: 11.240, true rewards: #0: 6.240 +[2024-09-21 02:26:59,239][00440] Avg episode reward: 11.240, avg true_objective: 6.240 +[2024-09-21 02:26:59,321][00440] Num frames 1300... +[2024-09-21 02:26:59,493][00440] Num frames 1400... +[2024-09-21 02:26:59,677][00440] Num frames 1500... +[2024-09-21 02:26:59,854][00440] Num frames 1600... +[2024-09-21 02:27:00,025][00440] Num frames 1700... +[2024-09-21 02:27:00,201][00440] Num frames 1800... +[2024-09-21 02:27:00,369][00440] Num frames 1900... +[2024-09-21 02:27:00,535][00440] Num frames 2000... +[2024-09-21 02:27:00,725][00440] Num frames 2100... +[2024-09-21 02:27:00,911][00440] Num frames 2200... +[2024-09-21 02:27:01,103][00440] Num frames 2300... +[2024-09-21 02:27:01,293][00440] Num frames 2400... +[2024-09-21 02:27:01,475][00440] Num frames 2500... +[2024-09-21 02:27:01,659][00440] Num frames 2600... +[2024-09-21 02:27:01,863][00440] Num frames 2700... +[2024-09-21 02:27:02,025][00440] Num frames 2800... +[2024-09-21 02:27:02,154][00440] Num frames 2900... +[2024-09-21 02:27:02,280][00440] Num frames 3000... +[2024-09-21 02:27:02,406][00440] Num frames 3100... +[2024-09-21 02:27:02,532][00440] Num frames 3200... +[2024-09-21 02:27:02,668][00440] Avg episode rewards: #0: 25.546, true rewards: #0: 10.880 +[2024-09-21 02:27:02,670][00440] Avg episode reward: 25.546, avg true_objective: 10.880 +[2024-09-21 02:27:02,722][00440] Num frames 3300... +[2024-09-21 02:27:02,858][00440] Num frames 3400... +[2024-09-21 02:27:02,982][00440] Num frames 3500... +[2024-09-21 02:27:03,108][00440] Num frames 3600... +[2024-09-21 02:27:03,238][00440] Num frames 3700... +[2024-09-21 02:27:03,361][00440] Num frames 3800... +[2024-09-21 02:27:03,466][00440] Avg episode rewards: #0: 21.600, true rewards: #0: 9.600 +[2024-09-21 02:27:03,469][00440] Avg episode reward: 21.600, avg true_objective: 9.600 +[2024-09-21 02:27:03,546][00440] Num frames 3900... +[2024-09-21 02:27:03,667][00440] Num frames 4000... +[2024-09-21 02:27:03,809][00440] Num frames 4100... +[2024-09-21 02:27:03,939][00440] Num frames 4200... +[2024-09-21 02:27:04,064][00440] Num frames 4300... +[2024-09-21 02:27:04,187][00440] Num frames 4400... +[2024-09-21 02:27:04,317][00440] Num frames 4500... +[2024-09-21 02:27:04,411][00440] Avg episode rewards: #0: 19.658, true rewards: #0: 9.058 +[2024-09-21 02:27:04,412][00440] Avg episode reward: 19.658, avg true_objective: 9.058 +[2024-09-21 02:27:04,500][00440] Num frames 4600... +[2024-09-21 02:27:04,623][00440] Num frames 4700... +[2024-09-21 02:27:04,759][00440] Num frames 4800... +[2024-09-21 02:27:04,897][00440] Num frames 4900... +[2024-09-21 02:27:05,033][00440] Num frames 5000... +[2024-09-21 02:27:05,163][00440] Num frames 5100... +[2024-09-21 02:27:05,290][00440] Num frames 5200... +[2024-09-21 02:27:05,416][00440] Num frames 5300... +[2024-09-21 02:27:05,538][00440] Num frames 5400... +[2024-09-21 02:27:05,664][00440] Num frames 5500... +[2024-09-21 02:27:05,804][00440] Num frames 5600... +[2024-09-21 02:27:05,940][00440] Num frames 5700... +[2024-09-21 02:27:06,020][00440] Avg episode rewards: #0: 20.532, true rewards: #0: 9.532 +[2024-09-21 02:27:06,022][00440] Avg episode reward: 20.532, avg true_objective: 9.532 +[2024-09-21 02:27:06,127][00440] Num frames 5800... +[2024-09-21 02:27:06,252][00440] Num frames 5900... +[2024-09-21 02:27:06,374][00440] Num frames 6000... +[2024-09-21 02:27:06,499][00440] Num frames 6100... +[2024-09-21 02:27:06,623][00440] Num frames 6200... +[2024-09-21 02:27:06,759][00440] Num frames 6300... +[2024-09-21 02:27:06,895][00440] Num frames 6400... +[2024-09-21 02:27:07,023][00440] Num frames 6500... +[2024-09-21 02:27:07,155][00440] Num frames 6600... +[2024-09-21 02:27:07,288][00440] Num frames 6700... +[2024-09-21 02:27:07,413][00440] Num frames 6800... +[2024-09-21 02:27:07,540][00440] Num frames 6900... +[2024-09-21 02:27:07,664][00440] Num frames 7000... +[2024-09-21 02:27:07,800][00440] Num frames 7100... +[2024-09-21 02:27:07,940][00440] Num frames 7200... +[2024-09-21 02:27:08,066][00440] Num frames 7300... +[2024-09-21 02:27:08,195][00440] Num frames 7400... +[2024-09-21 02:27:08,329][00440] Num frames 7500... +[2024-09-21 02:27:08,504][00440] Num frames 7600... +[2024-09-21 02:27:08,647][00440] Num frames 7700... +[2024-09-21 02:27:08,841][00440] Avg episode rewards: #0: 26.381, true rewards: #0: 11.096 +[2024-09-21 02:27:08,844][00440] Avg episode reward: 26.381, avg true_objective: 11.096 +[2024-09-21 02:27:08,911][00440] Num frames 7800... +[2024-09-21 02:27:09,088][00440] Num frames 7900... +[2024-09-21 02:27:09,262][00440] Num frames 8000... +[2024-09-21 02:27:09,432][00440] Num frames 8100... +[2024-09-21 02:27:09,605][00440] Num frames 8200... +[2024-09-21 02:27:09,785][00440] Num frames 8300... +[2024-09-21 02:27:09,967][00440] Num frames 8400... +[2024-09-21 02:27:10,178][00440] Avg episode rewards: #0: 25.214, true rewards: #0: 10.589 +[2024-09-21 02:27:10,180][00440] Avg episode reward: 25.214, avg true_objective: 10.589 +[2024-09-21 02:27:10,238][00440] Num frames 8500... +[2024-09-21 02:27:10,414][00440] Num frames 8600... +[2024-09-21 02:27:10,594][00440] Num frames 8700... +[2024-09-21 02:27:10,781][00440] Num frames 8800... +[2024-09-21 02:27:10,966][00440] Num frames 8900... +[2024-09-21 02:27:11,165][00440] Num frames 9000... +[2024-09-21 02:27:11,323][00440] Num frames 9100... +[2024-09-21 02:27:11,453][00440] Num frames 9200... +[2024-09-21 02:27:11,577][00440] Num frames 9300... +[2024-09-21 02:27:11,701][00440] Num frames 9400... +[2024-09-21 02:27:11,784][00440] Avg episode rewards: #0: 24.794, true rewards: #0: 10.461 +[2024-09-21 02:27:11,786][00440] Avg episode reward: 24.794, avg true_objective: 10.461 +[2024-09-21 02:27:11,906][00440] Num frames 9500... +[2024-09-21 02:27:12,035][00440] Num frames 9600... +[2024-09-21 02:27:12,172][00440] Num frames 9700... +[2024-09-21 02:27:12,302][00440] Num frames 9800... +[2024-09-21 02:27:12,429][00440] Num frames 9900... +[2024-09-21 02:27:12,556][00440] Num frames 10000... +[2024-09-21 02:27:12,716][00440] Avg episode rewards: #0: 23.687, true rewards: #0: 10.087 +[2024-09-21 02:27:12,718][00440] Avg episode reward: 23.687, avg true_objective: 10.087 +[2024-09-21 02:28:11,891][00440] Replay video saved to /content/train_dir/default_experiment/replay.mp4!