diff --git "a/sf_log.txt" "b/sf_log.txt" --- "a/sf_log.txt" +++ "b/sf_log.txt" @@ -1,36 +1,32 @@ -[2023-07-08 21:38:36,649][1084893] Saving configuration to /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/config.json... -[2023-07-08 21:38:36,668][1084893] Rollout worker 0 uses device cpu -[2023-07-08 21:38:36,668][1084893] Rollout worker 1 uses device cpu -[2023-07-08 21:38:36,668][1084893] Rollout worker 2 uses device cpu -[2023-07-08 21:38:36,668][1084893] Rollout worker 3 uses device cpu -[2023-07-08 21:38:36,668][1084893] Rollout worker 4 uses device cpu -[2023-07-08 21:38:36,669][1084893] Rollout worker 5 uses device cpu -[2023-07-08 21:38:36,669][1084893] Rollout worker 6 uses device cpu -[2023-07-08 21:38:36,669][1084893] Rollout worker 7 uses device cpu -[2023-07-08 21:38:36,669][1084893] In synchronous mode, we only accumulate one batch. Setting num_batches_to_accumulate to 1 -[2023-07-08 21:38:36,681][1084893] InferenceWorker_p0-w0: min num requests: 2 -[2023-07-08 21:38:36,701][1084893] Starting all processes... -[2023-07-08 21:38:36,701][1084893] Starting process learner_proc0 -[2023-07-08 21:38:36,717][1084893] Starting all processes... -[2023-07-08 21:38:36,719][1084893] Starting process inference_proc0-0 -[2023-07-08 21:38:36,720][1084893] Starting process rollout_proc0 -[2023-07-08 21:38:36,720][1084893] Starting process rollout_proc1 -[2023-07-08 21:38:36,720][1084893] Starting process rollout_proc2 -[2023-07-08 21:38:36,720][1084893] Starting process rollout_proc3 -[2023-07-08 21:38:36,720][1084893] Starting process rollout_proc4 -[2023-07-08 21:38:36,720][1084893] Starting process rollout_proc5 -[2023-07-08 21:38:36,720][1084893] Starting process rollout_proc6 -[2023-07-08 21:38:36,720][1084893] Starting process rollout_proc7 -[2023-07-08 21:38:38,825][1085162] Worker 0 uses CPU cores [0, 1, 2, 3] -[2023-07-08 21:38:38,933][1085195] Worker 2 uses CPU cores [8, 9, 10, 11] -[2023-07-08 21:38:39,023][1085261] Worker 4 uses CPU cores [16, 17, 18, 19] -[2023-07-08 21:38:39,233][1085148] Starting seed is not provided -[2023-07-08 21:38:39,233][1085148] Initializing actor-critic model on device cpu -[2023-07-08 21:38:39,233][1085148] RunningMeanStd input shape: (39,) -[2023-07-08 21:38:39,234][1085148] RunningMeanStd input shape: (1,) -[2023-07-08 21:38:39,269][1085263] Worker 7 uses CPU cores [28, 29, 30, 31] -[2023-07-08 21:38:39,292][1085148] Created Actor Critic model with architecture: -[2023-07-08 21:38:39,292][1085148] ActorCriticSharedWeights( +[2023-07-17 01:41:04,912][291207] Saving configuration to /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/config.json... +[2023-07-17 01:41:04,929][291207] Rollout worker 0 uses device cpu +[2023-07-17 01:41:04,929][291207] Rollout worker 1 uses device cpu +[2023-07-17 01:41:04,930][291207] Rollout worker 2 uses device cpu +[2023-07-17 01:41:04,930][291207] Rollout worker 3 uses device cpu +[2023-07-17 01:41:04,930][291207] Rollout worker 4 uses device cpu +[2023-07-17 01:41:04,930][291207] Rollout worker 5 uses device cpu +[2023-07-17 01:41:04,930][291207] Rollout worker 6 uses device cpu +[2023-07-17 01:41:04,930][291207] Rollout worker 7 uses device cpu +[2023-07-17 01:41:04,930][291207] In synchronous mode, we only accumulate one batch. Setting num_batches_to_accumulate to 1 +[2023-07-17 01:41:04,941][291207] InferenceWorker_p0-w0: min num requests: 2 +[2023-07-17 01:41:04,958][291207] Starting all processes... +[2023-07-17 01:41:04,958][291207] Starting process learner_proc0 +[2023-07-17 01:41:05,007][291207] Starting all processes... +[2023-07-17 01:41:05,048][291207] Starting process inference_proc0-0 +[2023-07-17 01:41:05,058][291207] Starting process rollout_proc0 +[2023-07-17 01:41:05,068][291207] Starting process rollout_proc1 +[2023-07-17 01:41:05,069][291207] Starting process rollout_proc2 +[2023-07-17 01:41:05,069][291207] Starting process rollout_proc3 +[2023-07-17 01:41:05,070][291207] Starting process rollout_proc4 +[2023-07-17 01:41:05,070][291207] Starting process rollout_proc5 +[2023-07-17 01:41:05,072][291207] Starting process rollout_proc6 +[2023-07-17 01:41:05,072][291207] Starting process rollout_proc7 +[2023-07-17 01:41:06,862][291444] Starting seed is not provided +[2023-07-17 01:41:06,862][291444] Initializing actor-critic model on device cpu +[2023-07-17 01:41:06,862][291444] RunningMeanStd input shape: (39,) +[2023-07-17 01:41:06,862][291444] RunningMeanStd input shape: (1,) +[2023-07-17 01:41:06,919][291444] Created Actor Critic model with architecture: +[2023-07-17 01:41:06,920][291444] ActorCriticSharedWeights( (obs_normalizer): ObservationNormalizer( (running_mean_std): RunningMeanStdDictInPlace( (running_mean_std): ModuleDict( @@ -61,1196 +57,948 @@ (distribution_linear): Linear(in_features=64, out_features=4, bias=True) ) ) -[2023-07-08 21:38:39,404][1085260] Worker 5 uses CPU cores [20, 21, 22, 23] -[2023-07-08 21:38:39,543][1085163] Worker 1 uses CPU cores [4, 5, 6, 7] -[2023-07-08 21:38:39,599][1085148] Using optimizer -[2023-07-08 21:38:39,600][1085148] No checkpoints found -[2023-07-08 21:38:39,600][1085148] Did not load from checkpoint, starting from scratch! -[2023-07-08 21:38:39,600][1085148] Initialized policy 0 weights for model version 0 -[2023-07-08 21:38:39,601][1085148] LearnerWorker_p0 finished initialization! -[2023-07-08 21:38:39,602][1085161] RunningMeanStd input shape: (39,) -[2023-07-08 21:38:39,603][1085161] RunningMeanStd input shape: (1,) -[2023-07-08 21:38:39,645][1085262] Worker 6 uses CPU cores [24, 25, 26, 27] -[2023-07-08 21:38:39,665][1085196] Worker 3 uses CPU cores [12, 13, 14, 15] -[2023-07-08 21:38:39,670][1084893] Inference worker 0-0 is ready! -[2023-07-08 21:38:39,671][1084893] All inference workers are ready! Signal rollout workers to start! -[2023-07-08 21:38:43,716][1084893] Fps is (10 sec: nan, 60 sec: nan, 300 sec: nan). Total num frames: 0. Throughput: 0: nan. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) -[2023-07-08 21:38:44,399][1085260] Decorrelating experience for 0 frames... -[2023-07-08 21:38:44,415][1085260] Decorrelating experience for 64 frames... -[2023-07-08 21:38:44,416][1085261] Decorrelating experience for 0 frames... -[2023-07-08 21:38:44,432][1085261] Decorrelating experience for 64 frames... -[2023-07-08 21:38:44,440][1085195] Decorrelating experience for 0 frames... -[2023-07-08 21:38:44,444][1085262] Decorrelating experience for 0 frames... -[2023-07-08 21:38:44,454][1085263] Decorrelating experience for 0 frames... -[2023-07-08 21:38:44,456][1085195] Decorrelating experience for 64 frames... -[2023-07-08 21:38:44,459][1085260] Decorrelating experience for 128 frames... -[2023-07-08 21:38:44,460][1085262] Decorrelating experience for 64 frames... -[2023-07-08 21:38:44,469][1085263] Decorrelating experience for 64 frames... -[2023-07-08 21:38:44,475][1085261] Decorrelating experience for 128 frames... -[2023-07-08 21:38:44,503][1085262] Decorrelating experience for 128 frames... -[2023-07-08 21:38:44,504][1085195] Decorrelating experience for 128 frames... -[2023-07-08 21:38:44,512][1085263] Decorrelating experience for 128 frames... -[2023-07-08 21:38:44,543][1085260] Decorrelating experience for 192 frames... -[2023-07-08 21:38:44,551][1085163] Decorrelating experience for 0 frames... -[2023-07-08 21:38:44,557][1085261] Decorrelating experience for 192 frames... -[2023-07-08 21:38:44,569][1085163] Decorrelating experience for 64 frames... -[2023-07-08 21:38:44,588][1085262] Decorrelating experience for 192 frames... -[2023-07-08 21:38:44,593][1085263] Decorrelating experience for 192 frames... -[2023-07-08 21:38:44,596][1085195] Decorrelating experience for 192 frames... -[2023-07-08 21:38:44,617][1085163] Decorrelating experience for 128 frames... -[2023-07-08 21:38:44,704][1085163] Decorrelating experience for 192 frames... -[2023-07-08 21:38:44,712][1085196] Decorrelating experience for 0 frames... -[2023-07-08 21:38:44,727][1085196] Decorrelating experience for 64 frames... -[2023-07-08 21:38:44,769][1085196] Decorrelating experience for 128 frames... -[2023-07-08 21:38:44,858][1085196] Decorrelating experience for 192 frames... -[2023-07-08 21:38:45,316][1085162] Decorrelating experience for 0 frames... -[2023-07-08 21:38:45,336][1085162] Decorrelating experience for 64 frames... -[2023-07-08 21:38:45,396][1085162] Decorrelating experience for 128 frames... -[2023-07-08 21:38:45,508][1085162] Decorrelating experience for 192 frames... -[2023-07-08 21:38:48,717][1084893] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 0.0. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) -[2023-07-08 21:38:48,718][1085148] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000000000_0.pth... -[2023-07-08 21:38:49,277][1085260] Decorrelating experience for 256 frames... -[2023-07-08 21:38:49,293][1085261] Decorrelating experience for 256 frames... -[2023-07-08 21:38:49,304][1085262] Decorrelating experience for 256 frames... -[2023-07-08 21:38:49,346][1085263] Decorrelating experience for 256 frames... -[2023-07-08 21:38:49,371][1085163] Decorrelating experience for 256 frames... -[2023-07-08 21:38:49,381][1085195] Decorrelating experience for 256 frames... -[2023-07-08 21:38:49,440][1085260] Decorrelating experience for 320 frames... -[2023-07-08 21:38:49,444][1085261] Decorrelating experience for 320 frames... -[2023-07-08 21:38:49,462][1085262] Decorrelating experience for 320 frames... -[2023-07-08 21:38:49,505][1085263] Decorrelating experience for 320 frames... -[2023-07-08 21:38:49,522][1085163] Decorrelating experience for 320 frames... -[2023-07-08 21:38:49,541][1085195] Decorrelating experience for 320 frames... -[2023-07-08 21:38:49,575][1085196] Decorrelating experience for 256 frames... -[2023-07-08 21:38:49,637][1085261] Decorrelating experience for 384 frames... -[2023-07-08 21:38:49,639][1085260] Decorrelating experience for 384 frames... -[2023-07-08 21:38:49,676][1085262] Decorrelating experience for 384 frames... -[2023-07-08 21:38:49,702][1085263] Decorrelating experience for 384 frames... -[2023-07-08 21:38:49,722][1085196] Decorrelating experience for 320 frames... -[2023-07-08 21:38:49,732][1085195] Decorrelating experience for 384 frames... -[2023-07-08 21:38:49,733][1085163] Decorrelating experience for 384 frames... -[2023-07-08 21:38:49,880][1085261] Decorrelating experience for 448 frames... -[2023-07-08 21:38:49,890][1085260] Decorrelating experience for 448 frames... -[2023-07-08 21:38:49,899][1085262] Decorrelating experience for 448 frames... -[2023-07-08 21:38:49,911][1085196] Decorrelating experience for 384 frames... -[2023-07-08 21:38:49,928][1085263] Decorrelating experience for 448 frames... -[2023-07-08 21:38:49,949][1085195] Decorrelating experience for 448 frames... -[2023-07-08 21:38:49,959][1085163] Decorrelating experience for 448 frames... -[2023-07-08 21:38:50,131][1085196] Decorrelating experience for 448 frames... -[2023-07-08 21:38:50,542][1085162] Decorrelating experience for 256 frames... -[2023-07-08 21:38:50,694][1085162] Decorrelating experience for 320 frames... -[2023-07-08 21:38:50,890][1085162] Decorrelating experience for 384 frames... -[2023-07-08 21:38:51,107][1085162] Decorrelating experience for 448 frames... -[2023-07-08 21:38:53,716][1084893] Fps is (10 sec: 1638.4, 60 sec: 1638.4, 300 sec: 1638.4). Total num frames: 16384. Throughput: 0: 406.4. Samples: 4064. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-07-08 21:38:53,717][1084893] Avg episode reward: [(0, '4.373')] -[2023-07-08 21:38:56,676][1084893] Heartbeat connected on Batcher_0 -[2023-07-08 21:38:56,679][1084893] Heartbeat connected on LearnerWorker_p0 -[2023-07-08 21:38:56,684][1084893] Heartbeat connected on RolloutWorker_w0 -[2023-07-08 21:38:56,686][1084893] Heartbeat connected on RolloutWorker_w1 -[2023-07-08 21:38:56,689][1084893] Heartbeat connected on RolloutWorker_w2 -[2023-07-08 21:38:56,691][1084893] Heartbeat connected on RolloutWorker_w3 -[2023-07-08 21:38:56,693][1084893] Heartbeat connected on RolloutWorker_w4 -[2023-07-08 21:38:56,697][1084893] Heartbeat connected on RolloutWorker_w5 -[2023-07-08 21:38:56,697][1084893] Heartbeat connected on RolloutWorker_w6 -[2023-07-08 21:38:56,700][1084893] Heartbeat connected on RolloutWorker_w7 -[2023-07-08 21:38:56,703][1084893] Heartbeat connected on InferenceWorker_p0-w0 -[2023-07-08 21:38:56,784][1085161] Updated weights for policy 0, policy_version 80 (0.0005) -[2023-07-08 21:38:58,716][1084893] Fps is (10 sec: 5324.9, 60 sec: 3549.9, 300 sec: 3549.9). Total num frames: 53248. Throughput: 0: 3169.6. Samples: 47544. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:38:58,717][1084893] Avg episode reward: [(0, '15.842')] -[2023-07-08 21:39:02,858][1085161] Updated weights for policy 0, policy_version 160 (0.0005) -[2023-07-08 21:39:03,717][1084893] Fps is (10 sec: 6963.2, 60 sec: 4300.8, 300 sec: 4300.8). Total num frames: 86016. Throughput: 0: 4392.2. Samples: 87844. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:39:03,717][1084893] Avg episode reward: [(0, '19.458')] -[2023-07-08 21:39:03,720][1085148] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000000168_86016.pth... -[2023-07-08 21:39:08,702][1085161] Updated weights for policy 0, policy_version 240 (0.0005) -[2023-07-08 21:39:08,717][1084893] Fps is (10 sec: 6963.1, 60 sec: 4915.2, 300 sec: 4915.2). Total num frames: 122880. Throughput: 0: 4356.9. Samples: 108924. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-07-08 21:39:08,717][1084893] Avg episode reward: [(0, '20.446')] -[2023-07-08 21:39:08,718][1085148] Saving new best policy, reward=20.446! -[2023-07-08 21:39:13,716][1084893] Fps is (10 sec: 6963.2, 60 sec: 5188.3, 300 sec: 5188.3). Total num frames: 155648. Throughput: 0: 5058.4. Samples: 151752. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:39:13,717][1084893] Avg episode reward: [(0, '24.430')] -[2023-07-08 21:39:13,717][1085148] Saving new best policy, reward=24.430! -[2023-07-08 21:39:14,391][1085161] Updated weights for policy 0, policy_version 320 (0.0006) -[2023-07-08 21:39:18,716][1084893] Fps is (10 sec: 6553.7, 60 sec: 5383.3, 300 sec: 5383.3). Total num frames: 188416. Throughput: 0: 5500.2. Samples: 192508. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-07-08 21:39:18,717][1084893] Avg episode reward: [(0, '28.154')] -[2023-07-08 21:39:18,771][1085148] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000000376_192512.pth... -[2023-07-08 21:39:18,862][1085148] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000000000_0.pth -[2023-07-08 21:39:18,863][1085148] Saving new best policy, reward=28.154! -[2023-07-08 21:39:20,562][1085161] Updated weights for policy 0, policy_version 400 (0.0006) -[2023-07-08 21:39:23,716][1084893] Fps is (10 sec: 6963.2, 60 sec: 5632.0, 300 sec: 5632.0). Total num frames: 225280. Throughput: 0: 5322.3. Samples: 212892. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-07-08 21:39:23,717][1084893] Avg episode reward: [(0, '34.800')] -[2023-07-08 21:39:23,718][1085148] Saving new best policy, reward=34.800! -[2023-07-08 21:39:26,688][1085161] Updated weights for policy 0, policy_version 480 (0.0005) -[2023-07-08 21:39:28,716][1084893] Fps is (10 sec: 6963.2, 60 sec: 5734.4, 300 sec: 5734.4). Total num frames: 258048. Throughput: 0: 5640.9. Samples: 253840. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:39:28,717][1084893] Avg episode reward: [(0, '36.905')] -[2023-07-08 21:39:28,717][1085148] Saving new best policy, reward=36.905! -[2023-07-08 21:39:32,819][1085161] Updated weights for policy 0, policy_version 560 (0.0005) -[2023-07-08 21:39:33,717][1084893] Fps is (10 sec: 6553.6, 60 sec: 5816.3, 300 sec: 5816.3). Total num frames: 290816. Throughput: 0: 6503.0. Samples: 292636. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:39:33,717][1084893] Avg episode reward: [(0, '38.213')] -[2023-07-08 21:39:33,719][1085148] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000000568_290816.pth... -[2023-07-08 21:39:33,722][1085148] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000000168_86016.pth -[2023-07-08 21:39:33,722][1085148] Saving new best policy, reward=38.213! -[2023-07-08 21:39:38,716][1084893] Fps is (10 sec: 6553.7, 60 sec: 5883.4, 300 sec: 5883.4). Total num frames: 323584. Throughput: 0: 6892.1. Samples: 314208. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:39:38,717][1084893] Avg episode reward: [(0, '38.626')] -[2023-07-08 21:39:38,717][1085148] Saving new best policy, reward=38.626! -[2023-07-08 21:39:38,820][1085161] Updated weights for policy 0, policy_version 640 (0.0005) -[2023-07-08 21:39:43,716][1084893] Fps is (10 sec: 6963.2, 60 sec: 6007.5, 300 sec: 6007.5). Total num frames: 360448. Throughput: 0: 6833.0. Samples: 355028. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:39:43,717][1084893] Avg episode reward: [(0, '38.922')] -[2023-07-08 21:39:43,718][1085148] Saving new best policy, reward=38.922! -[2023-07-08 21:39:44,787][1085161] Updated weights for policy 0, policy_version 720 (0.0005) -[2023-07-08 21:39:48,717][1084893] Fps is (10 sec: 6963.1, 60 sec: 6553.6, 300 sec: 6049.5). Total num frames: 393216. Throughput: 0: 6832.5. Samples: 395308. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:39:48,717][1084893] Avg episode reward: [(0, '39.814')] -[2023-07-08 21:39:48,720][1085148] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000000768_393216.pth... -[2023-07-08 21:39:48,723][1085148] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000000376_192512.pth -[2023-07-08 21:39:48,723][1085148] Saving new best policy, reward=39.814! -[2023-07-08 21:39:50,617][1085161] Updated weights for policy 0, policy_version 800 (0.0006) -[2023-07-08 21:39:53,716][1084893] Fps is (10 sec: 6963.3, 60 sec: 6894.9, 300 sec: 6144.0). Total num frames: 430080. Throughput: 0: 6874.3. Samples: 418264. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:39:53,717][1084893] Avg episode reward: [(0, '40.775')] -[2023-07-08 21:39:53,717][1085148] Saving new best policy, reward=40.775! -[2023-07-08 21:39:56,090][1085161] Updated weights for policy 0, policy_version 880 (0.0005) -[2023-07-08 21:39:58,717][1084893] Fps is (10 sec: 7372.8, 60 sec: 6894.9, 300 sec: 6225.9). Total num frames: 466944. Throughput: 0: 6915.6. Samples: 462956. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-07-08 21:39:58,717][1084893] Avg episode reward: [(0, '40.461')] -[2023-07-08 21:40:02,115][1085161] Updated weights for policy 0, policy_version 960 (0.0005) -[2023-07-08 21:40:03,716][1084893] Fps is (10 sec: 6963.1, 60 sec: 6894.9, 300 sec: 6246.4). Total num frames: 499712. Throughput: 0: 6917.0. Samples: 503772. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:40:03,717][1084893] Avg episode reward: [(0, '44.458')] -[2023-07-08 21:40:03,720][1085148] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000000976_499712.pth... -[2023-07-08 21:40:03,722][1085148] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000000568_290816.pth -[2023-07-08 21:40:03,722][1085148] Saving new best policy, reward=44.458! -[2023-07-08 21:40:07,903][1085161] Updated weights for policy 0, policy_version 1040 (0.0006) -[2023-07-08 21:40:08,716][1084893] Fps is (10 sec: 6963.3, 60 sec: 6895.0, 300 sec: 6312.7). Total num frames: 536576. Throughput: 0: 6920.1. Samples: 524296. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:40:08,718][1084893] Avg episode reward: [(0, '44.856')] -[2023-07-08 21:40:08,718][1085148] Saving new best policy, reward=44.856! -[2023-07-08 21:40:13,716][1084893] Fps is (10 sec: 6963.2, 60 sec: 6894.9, 300 sec: 6326.0). Total num frames: 569344. Throughput: 0: 6918.6. Samples: 565176. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-07-08 21:40:13,717][1084893] Avg episode reward: [(0, '44.120')] -[2023-07-08 21:40:14,033][1085161] Updated weights for policy 0, policy_version 1120 (0.0005) -[2023-07-08 21:40:18,717][1084893] Fps is (10 sec: 6553.5, 60 sec: 6894.9, 300 sec: 6338.0). Total num frames: 602112. Throughput: 0: 6949.7. Samples: 605372. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:40:18,717][1084893] Avg episode reward: [(0, '73.255')] -[2023-07-08 21:40:18,720][1085148] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000001176_602112.pth... -[2023-07-08 21:40:18,722][1085148] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000000768_393216.pth -[2023-07-08 21:40:18,723][1085148] Saving new best policy, reward=73.255! -[2023-07-08 21:40:20,098][1085161] Updated weights for policy 0, policy_version 1200 (0.0005) -[2023-07-08 21:40:23,716][1084893] Fps is (10 sec: 6963.2, 60 sec: 6894.9, 300 sec: 6389.8). Total num frames: 638976. Throughput: 0: 6926.1. Samples: 625884. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:40:23,717][1084893] Avg episode reward: [(0, '100.424')] -[2023-07-08 21:40:23,717][1085148] Saving new best policy, reward=100.424! -[2023-07-08 21:40:25,949][1085161] Updated weights for policy 0, policy_version 1280 (0.0005) -[2023-07-08 21:40:28,716][1084893] Fps is (10 sec: 6963.3, 60 sec: 6894.9, 300 sec: 6397.6). Total num frames: 671744. Throughput: 0: 6941.1. Samples: 667376. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-07-08 21:40:28,717][1084893] Avg episode reward: [(0, '141.695')] -[2023-07-08 21:40:28,717][1085148] Saving new best policy, reward=141.695! -[2023-07-08 21:40:31,752][1085161] Updated weights for policy 0, policy_version 1360 (0.0005) -[2023-07-08 21:40:33,716][1084893] Fps is (10 sec: 6963.2, 60 sec: 6963.2, 300 sec: 6441.9). Total num frames: 708608. Throughput: 0: 6509.8. Samples: 688248. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:40:33,717][1084893] Avg episode reward: [(0, '216.285')] -[2023-07-08 21:40:33,729][1085148] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000001392_712704.pth... -[2023-07-08 21:40:33,731][1085148] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000000976_499712.pth -[2023-07-08 21:40:33,731][1085148] Saving new best policy, reward=216.285! -[2023-07-08 21:40:36,978][1085161] Updated weights for policy 0, policy_version 1440 (0.0005) -[2023-07-08 21:40:38,716][1084893] Fps is (10 sec: 7782.3, 60 sec: 7099.7, 300 sec: 6518.0). Total num frames: 749568. Throughput: 0: 7044.2. Samples: 735252. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:40:38,717][1084893] Avg episode reward: [(0, '243.402')] -[2023-07-08 21:40:38,718][1085148] Saving new best policy, reward=243.402! -[2023-07-08 21:40:42,713][1085161] Updated weights for policy 0, policy_version 1520 (0.0005) -[2023-07-08 21:40:43,716][1084893] Fps is (10 sec: 7372.8, 60 sec: 7031.5, 300 sec: 6519.5). Total num frames: 782336. Throughput: 0: 7006.3. Samples: 778240. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:40:43,717][1084893] Avg episode reward: [(0, '298.811')] -[2023-07-08 21:40:43,717][1085148] Saving new best policy, reward=298.811! -[2023-07-08 21:40:48,576][1085161] Updated weights for policy 0, policy_version 1600 (0.0005) -[2023-07-08 21:40:48,716][1084893] Fps is (10 sec: 6963.2, 60 sec: 7099.7, 300 sec: 6553.6). Total num frames: 819200. Throughput: 0: 7027.9. Samples: 820028. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:40:48,717][1084893] Avg episode reward: [(0, '320.325')] -[2023-07-08 21:40:48,720][1085148] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000001600_819200.pth... -[2023-07-08 21:40:48,722][1085148] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000001176_602112.pth -[2023-07-08 21:40:48,723][1085148] Saving new best policy, reward=320.325! -[2023-07-08 21:40:53,716][1084893] Fps is (10 sec: 6963.2, 60 sec: 7031.5, 300 sec: 6553.6). Total num frames: 851968. Throughput: 0: 7051.6. Samples: 841616. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-07-08 21:40:53,717][1084893] Avg episode reward: [(0, '350.903')] -[2023-07-08 21:40:53,717][1085148] Saving new best policy, reward=350.903! -[2023-07-08 21:40:54,551][1085161] Updated weights for policy 0, policy_version 1680 (0.0005) -[2023-07-08 21:40:58,716][1084893] Fps is (10 sec: 6963.2, 60 sec: 7031.5, 300 sec: 6583.9). Total num frames: 888832. Throughput: 0: 7041.3. Samples: 882032. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:40:58,717][1084893] Avg episode reward: [(0, '335.287')] -[2023-07-08 21:41:00,345][1085161] Updated weights for policy 0, policy_version 1760 (0.0005) -[2023-07-08 21:41:03,717][1084893] Fps is (10 sec: 7372.7, 60 sec: 7099.7, 300 sec: 6612.1). Total num frames: 925696. Throughput: 0: 7119.7. Samples: 925760. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) -[2023-07-08 21:41:03,717][1084893] Avg episode reward: [(0, '293.292')] -[2023-07-08 21:41:03,720][1085148] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000001808_925696.pth... -[2023-07-08 21:41:03,722][1085148] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000001392_712704.pth -[2023-07-08 21:41:06,124][1085161] Updated weights for policy 0, policy_version 1840 (0.0005) -[2023-07-08 21:41:08,716][1084893] Fps is (10 sec: 6963.2, 60 sec: 7031.5, 300 sec: 6610.1). Total num frames: 958464. Throughput: 0: 7127.1. Samples: 946604. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:41:08,717][1084893] Avg episode reward: [(0, '363.838')] -[2023-07-08 21:41:08,717][1085148] Saving new best policy, reward=363.838! -[2023-07-08 21:41:11,938][1085161] Updated weights for policy 0, policy_version 1920 (0.0005) -[2023-07-08 21:41:13,716][1084893] Fps is (10 sec: 6963.3, 60 sec: 7099.7, 300 sec: 6635.5). Total num frames: 995328. Throughput: 0: 7156.2. Samples: 989404. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) -[2023-07-08 21:41:13,717][1084893] Avg episode reward: [(0, '382.785')] -[2023-07-08 21:41:13,717][1085148] Saving new best policy, reward=382.785! -[2023-07-08 21:41:17,470][1085161] Updated weights for policy 0, policy_version 2000 (0.0005) -[2023-07-08 21:41:18,717][1084893] Fps is (10 sec: 7372.7, 60 sec: 7168.0, 300 sec: 6659.3). Total num frames: 1032192. Throughput: 0: 7644.8. Samples: 1032264. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-07-08 21:41:18,717][1084893] Avg episode reward: [(0, '435.943')] -[2023-07-08 21:41:18,720][1085148] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000002016_1032192.pth... -[2023-07-08 21:41:18,723][1085148] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000001600_819200.pth -[2023-07-08 21:41:18,723][1085148] Saving new best policy, reward=435.943! -[2023-07-08 21:41:23,469][1085161] Updated weights for policy 0, policy_version 2080 (0.0005) -[2023-07-08 21:41:23,717][1084893] Fps is (10 sec: 6963.2, 60 sec: 7099.7, 300 sec: 6656.0). Total num frames: 1064960. Throughput: 0: 7057.2. Samples: 1052824. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) -[2023-07-08 21:41:23,717][1084893] Avg episode reward: [(0, '477.782')] -[2023-07-08 21:41:23,718][1085148] Saving new best policy, reward=477.782! -[2023-07-08 21:41:28,716][1084893] Fps is (10 sec: 6963.3, 60 sec: 7168.0, 300 sec: 6677.7). Total num frames: 1101824. Throughput: 0: 7025.3. Samples: 1094380. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:41:28,717][1084893] Avg episode reward: [(0, '457.753')] -[2023-07-08 21:41:29,214][1085161] Updated weights for policy 0, policy_version 2160 (0.0005) -[2023-07-08 21:41:33,716][1084893] Fps is (10 sec: 7372.8, 60 sec: 7168.0, 300 sec: 6698.2). Total num frames: 1138688. Throughput: 0: 7081.2. Samples: 1138680. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:41:33,717][1084893] Avg episode reward: [(0, '465.708')] -[2023-07-08 21:41:33,720][1085148] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000002224_1138688.pth... -[2023-07-08 21:41:33,723][1085148] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000001808_925696.pth -[2023-07-08 21:41:34,827][1085161] Updated weights for policy 0, policy_version 2240 (0.0005) -[2023-07-08 21:41:38,716][1084893] Fps is (10 sec: 6963.2, 60 sec: 7031.5, 300 sec: 6694.0). Total num frames: 1171456. Throughput: 0: 7101.0. Samples: 1161160. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:41:38,717][1084893] Avg episode reward: [(0, '466.178')] -[2023-07-08 21:41:40,500][1085161] Updated weights for policy 0, policy_version 2320 (0.0005) -[2023-07-08 21:41:43,716][1084893] Fps is (10 sec: 6963.2, 60 sec: 7099.7, 300 sec: 6712.9). Total num frames: 1208320. Throughput: 0: 7152.9. Samples: 1203912. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-07-08 21:41:43,717][1084893] Avg episode reward: [(0, '484.222')] -[2023-07-08 21:41:43,717][1085148] Saving new best policy, reward=484.222! -[2023-07-08 21:41:46,174][1085161] Updated weights for policy 0, policy_version 2400 (0.0005) -[2023-07-08 21:41:48,716][1084893] Fps is (10 sec: 7372.7, 60 sec: 7099.7, 300 sec: 6730.7). Total num frames: 1245184. Throughput: 0: 7143.5. Samples: 1247216. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-07-08 21:41:48,717][1084893] Avg episode reward: [(0, '504.157')] -[2023-07-08 21:41:48,720][1085148] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000002432_1245184.pth... -[2023-07-08 21:41:48,723][1085148] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000002016_1032192.pth -[2023-07-08 21:41:48,723][1085148] Saving new best policy, reward=504.157! -[2023-07-08 21:41:51,370][1085161] Updated weights for policy 0, policy_version 2480 (0.0005) -[2023-07-08 21:41:53,716][1084893] Fps is (10 sec: 7372.7, 60 sec: 7168.0, 300 sec: 6747.6). Total num frames: 1282048. Throughput: 0: 7243.9. Samples: 1272580. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) -[2023-07-08 21:41:53,717][1084893] Avg episode reward: [(0, '501.576')] -[2023-07-08 21:41:57,434][1085161] Updated weights for policy 0, policy_version 2560 (0.0005) -[2023-07-08 21:41:58,716][1084893] Fps is (10 sec: 7372.9, 60 sec: 7168.0, 300 sec: 6763.7). Total num frames: 1318912. Throughput: 0: 7190.1. Samples: 1312960. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:41:58,717][1084893] Avg episode reward: [(0, '504.788')] -[2023-07-08 21:41:58,717][1085148] Saving new best policy, reward=504.788! -[2023-07-08 21:42:02,965][1085161] Updated weights for policy 0, policy_version 2640 (0.0005) -[2023-07-08 21:42:03,716][1084893] Fps is (10 sec: 7372.8, 60 sec: 7168.0, 300 sec: 6778.9). Total num frames: 1355776. Throughput: 0: 7230.1. Samples: 1357620. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-07-08 21:42:03,717][1084893] Avg episode reward: [(0, '497.760')] -[2023-07-08 21:42:03,720][1085148] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000002648_1355776.pth... -[2023-07-08 21:42:03,722][1085148] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000002224_1138688.pth -[2023-07-08 21:42:08,708][1085161] Updated weights for policy 0, policy_version 2720 (0.0005) -[2023-07-08 21:42:08,716][1084893] Fps is (10 sec: 7372.8, 60 sec: 7236.3, 300 sec: 6793.4). Total num frames: 1392640. Throughput: 0: 7235.7. Samples: 1378432. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-07-08 21:42:08,717][1084893] Avg episode reward: [(0, '495.903')] -[2023-07-08 21:42:13,716][1084893] Fps is (10 sec: 7372.9, 60 sec: 7236.3, 300 sec: 6807.2). Total num frames: 1429504. Throughput: 0: 7302.9. Samples: 1423012. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) -[2023-07-08 21:42:13,717][1084893] Avg episode reward: [(0, '491.744')] -[2023-07-08 21:42:14,232][1085161] Updated weights for policy 0, policy_version 2800 (0.0005) -[2023-07-08 21:42:18,717][1084893] Fps is (10 sec: 6963.1, 60 sec: 7168.0, 300 sec: 6801.3). Total num frames: 1462272. Throughput: 0: 7209.8. Samples: 1463120. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) -[2023-07-08 21:42:18,717][1084893] Avg episode reward: [(0, '489.906')] -[2023-07-08 21:42:18,720][1085148] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000002856_1462272.pth... -[2023-07-08 21:42:18,722][1085148] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000002432_1245184.pth -[2023-07-08 21:42:20,396][1085161] Updated weights for policy 0, policy_version 2880 (0.0004) -[2023-07-08 21:42:23,716][1084893] Fps is (10 sec: 6553.6, 60 sec: 7168.0, 300 sec: 6795.6). Total num frames: 1495040. Throughput: 0: 7150.2. Samples: 1482920. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:42:23,718][1084893] Avg episode reward: [(0, '504.197')] -[2023-07-08 21:42:26,259][1085161] Updated weights for policy 0, policy_version 2960 (0.0005) -[2023-07-08 21:42:28,716][1084893] Fps is (10 sec: 6963.2, 60 sec: 7168.0, 300 sec: 6808.5). Total num frames: 1531904. Throughput: 0: 7158.4. Samples: 1526040. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-07-08 21:42:28,718][1084893] Avg episode reward: [(0, '499.096')] -[2023-07-08 21:42:32,101][1085161] Updated weights for policy 0, policy_version 3040 (0.0005) -[2023-07-08 21:42:33,716][1084893] Fps is (10 sec: 6963.2, 60 sec: 7099.7, 300 sec: 6802.9). Total num frames: 1564672. Throughput: 0: 7127.1. Samples: 1567936. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:42:33,717][1084893] Avg episode reward: [(0, '525.692')] -[2023-07-08 21:42:33,721][1085148] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000003056_1564672.pth... -[2023-07-08 21:42:33,723][1085148] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000002648_1355776.pth -[2023-07-08 21:42:33,724][1085148] Saving new best policy, reward=525.692! -[2023-07-08 21:42:37,764][1085161] Updated weights for policy 0, policy_version 3120 (0.0005) -[2023-07-08 21:42:38,716][1084893] Fps is (10 sec: 6963.2, 60 sec: 7168.0, 300 sec: 6815.0). Total num frames: 1601536. Throughput: 0: 7056.2. Samples: 1590108. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:42:38,717][1084893] Avg episode reward: [(0, '500.057')] -[2023-07-08 21:42:43,589][1085161] Updated weights for policy 0, policy_version 3200 (0.0005) -[2023-07-08 21:42:43,716][1084893] Fps is (10 sec: 7372.8, 60 sec: 7168.0, 300 sec: 6826.7). Total num frames: 1638400. Throughput: 0: 7060.5. Samples: 1630684. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:42:43,717][1084893] Avg episode reward: [(0, '509.312')] -[2023-07-08 21:42:48,716][1084893] Fps is (10 sec: 7372.8, 60 sec: 7168.0, 300 sec: 6837.8). Total num frames: 1675264. Throughput: 0: 7067.4. Samples: 1675652. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:42:48,717][1084893] Avg episode reward: [(0, '510.978')] -[2023-07-08 21:42:48,720][1085148] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000003272_1675264.pth... -[2023-07-08 21:42:48,722][1085148] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000002856_1462272.pth -[2023-07-08 21:42:49,161][1085161] Updated weights for policy 0, policy_version 3280 (0.0005) -[2023-07-08 21:42:53,717][1084893] Fps is (10 sec: 7372.7, 60 sec: 7168.0, 300 sec: 6848.5). Total num frames: 1712128. Throughput: 0: 7106.6. Samples: 1698232. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-07-08 21:42:53,717][1084893] Avg episode reward: [(0, '531.491')] -[2023-07-08 21:42:53,718][1085148] Saving new best policy, reward=531.491! -[2023-07-08 21:42:54,797][1085161] Updated weights for policy 0, policy_version 3360 (0.0005) -[2023-07-08 21:42:58,716][1084893] Fps is (10 sec: 6963.2, 60 sec: 7099.7, 300 sec: 6842.7). Total num frames: 1744896. Throughput: 0: 7062.0. Samples: 1740800. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-07-08 21:42:58,717][1084893] Avg episode reward: [(0, '511.072')] -[2023-07-08 21:43:00,724][1085161] Updated weights for policy 0, policy_version 3440 (0.0005) -[2023-07-08 21:43:03,717][1084893] Fps is (10 sec: 6963.1, 60 sec: 7099.7, 300 sec: 6852.9). Total num frames: 1781760. Throughput: 0: 7087.9. Samples: 1782076. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-07-08 21:43:03,717][1084893] Avg episode reward: [(0, '520.512')] -[2023-07-08 21:43:03,722][1085148] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000003480_1781760.pth... -[2023-07-08 21:43:03,724][1085148] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000003056_1564672.pth -[2023-07-08 21:43:06,748][1085161] Updated weights for policy 0, policy_version 3520 (0.0005) -[2023-07-08 21:43:08,716][1084893] Fps is (10 sec: 6963.2, 60 sec: 7031.5, 300 sec: 6847.3). Total num frames: 1814528. Throughput: 0: 7095.8. Samples: 1802232. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:43:08,717][1084893] Avg episode reward: [(0, '524.029')] -[2023-07-08 21:43:12,609][1085161] Updated weights for policy 0, policy_version 3600 (0.0005) -[2023-07-08 21:43:13,716][1084893] Fps is (10 sec: 6963.4, 60 sec: 7031.5, 300 sec: 6857.0). Total num frames: 1851392. Throughput: 0: 7060.6. Samples: 1843768. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:43:13,717][1084893] Avg episode reward: [(0, '517.459')] -[2023-07-08 21:43:18,230][1085161] Updated weights for policy 0, policy_version 3680 (0.0005) -[2023-07-08 21:43:18,716][1084893] Fps is (10 sec: 6963.1, 60 sec: 7031.5, 300 sec: 6851.5). Total num frames: 1884160. Throughput: 0: 7116.2. Samples: 1888164. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:43:18,717][1084893] Avg episode reward: [(0, '539.374')] -[2023-07-08 21:43:18,719][1085148] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000003680_1884160.pth... -[2023-07-08 21:43:18,722][1085148] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000003272_1675264.pth -[2023-07-08 21:43:18,722][1085148] Saving new best policy, reward=539.374! -[2023-07-08 21:43:23,716][1084893] Fps is (10 sec: 6963.1, 60 sec: 7099.7, 300 sec: 6860.8). Total num frames: 1921024. Throughput: 0: 7064.3. Samples: 1908000. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:43:23,717][1084893] Avg episode reward: [(0, '543.141')] -[2023-07-08 21:43:23,718][1085148] Saving new best policy, reward=543.141! -[2023-07-08 21:43:24,176][1085161] Updated weights for policy 0, policy_version 3760 (0.0005) -[2023-07-08 21:43:28,717][1084893] Fps is (10 sec: 7372.8, 60 sec: 7099.7, 300 sec: 6869.8). Total num frames: 1957888. Throughput: 0: 7124.9. Samples: 1951304. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:43:28,717][1084893] Avg episode reward: [(0, '536.004')] -[2023-07-08 21:43:29,784][1085161] Updated weights for policy 0, policy_version 3840 (0.0005) -[2023-07-08 21:43:33,716][1084893] Fps is (10 sec: 6963.2, 60 sec: 7099.7, 300 sec: 6864.3). Total num frames: 1990656. Throughput: 0: 6622.8. Samples: 1973680. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-07-08 21:43:33,717][1084893] Avg episode reward: [(0, '541.246')] -[2023-07-08 21:43:33,760][1085148] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000003896_1994752.pth... -[2023-07-08 21:43:33,762][1085148] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000003480_1781760.pth -[2023-07-08 21:43:35,608][1085161] Updated weights for policy 0, policy_version 3920 (0.0005) -[2023-07-08 21:43:38,716][1084893] Fps is (10 sec: 6963.3, 60 sec: 7099.7, 300 sec: 6873.0). Total num frames: 2027520. Throughput: 0: 7045.9. Samples: 2015296. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-07-08 21:43:38,717][1084893] Avg episode reward: [(0, '541.298')] -[2023-07-08 21:43:41,219][1085161] Updated weights for policy 0, policy_version 4000 (0.0005) -[2023-07-08 21:43:43,716][1084893] Fps is (10 sec: 7372.9, 60 sec: 7099.7, 300 sec: 6997.9). Total num frames: 2064384. Throughput: 0: 7098.8. Samples: 2060244. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-07-08 21:43:43,717][1084893] Avg episode reward: [(0, '530.675')] -[2023-07-08 21:43:46,888][1085161] Updated weights for policy 0, policy_version 4080 (0.0006) -[2023-07-08 21:43:48,717][1084893] Fps is (10 sec: 7372.7, 60 sec: 7099.7, 300 sec: 7067.3). Total num frames: 2101248. Throughput: 0: 7123.2. Samples: 2102620. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:43:48,717][1084893] Avg episode reward: [(0, '525.639')] -[2023-07-08 21:43:48,720][1085148] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000004104_2101248.pth... -[2023-07-08 21:43:48,722][1085148] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000003680_1884160.pth -[2023-07-08 21:43:52,315][1085161] Updated weights for policy 0, policy_version 4160 (0.0005) -[2023-07-08 21:43:53,716][1084893] Fps is (10 sec: 7372.8, 60 sec: 7099.7, 300 sec: 7067.3). Total num frames: 2138112. Throughput: 0: 7176.9. Samples: 2125192. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-07-08 21:43:53,717][1084893] Avg episode reward: [(0, '530.437')] -[2023-07-08 21:43:57,681][1085161] Updated weights for policy 0, policy_version 4240 (0.0005) -[2023-07-08 21:43:58,716][1084893] Fps is (10 sec: 7372.9, 60 sec: 7168.0, 300 sec: 7081.2). Total num frames: 2174976. Throughput: 0: 7270.8. Samples: 2170952. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:43:58,717][1084893] Avg episode reward: [(0, '507.819')] -[2023-07-08 21:44:03,326][1085161] Updated weights for policy 0, policy_version 4320 (0.0005) -[2023-07-08 21:44:03,716][1084893] Fps is (10 sec: 7372.7, 60 sec: 7168.0, 300 sec: 7081.2). Total num frames: 2211840. Throughput: 0: 7258.9. Samples: 2214816. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-07-08 21:44:03,717][1084893] Avg episode reward: [(0, '515.561')] -[2023-07-08 21:44:03,720][1085148] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000004320_2211840.pth... -[2023-07-08 21:44:03,722][1085148] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000003896_1994752.pth -[2023-07-08 21:44:08,716][1084893] Fps is (10 sec: 7372.7, 60 sec: 7236.3, 300 sec: 7095.1). Total num frames: 2248704. Throughput: 0: 7284.0. Samples: 2235780. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:44:08,717][1084893] Avg episode reward: [(0, '519.143')] -[2023-07-08 21:44:09,096][1085161] Updated weights for policy 0, policy_version 4400 (0.0005) -[2023-07-08 21:44:13,716][1084893] Fps is (10 sec: 7372.8, 60 sec: 7236.3, 300 sec: 7109.0). Total num frames: 2285568. Throughput: 0: 7256.5. Samples: 2277848. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-07-08 21:44:13,717][1084893] Avg episode reward: [(0, '524.468')] -[2023-07-08 21:44:14,856][1085161] Updated weights for policy 0, policy_version 4480 (0.0005) -[2023-07-08 21:44:18,716][1084893] Fps is (10 sec: 6963.3, 60 sec: 7236.3, 300 sec: 7095.1). Total num frames: 2318336. Throughput: 0: 7723.0. Samples: 2321216. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:44:18,717][1084893] Avg episode reward: [(0, '516.093')] -[2023-07-08 21:44:18,719][1085148] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000004528_2318336.pth... -[2023-07-08 21:44:18,722][1085148] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000004104_2101248.pth -[2023-07-08 21:44:20,570][1085161] Updated weights for policy 0, policy_version 4560 (0.0005) -[2023-07-08 21:44:23,716][1084893] Fps is (10 sec: 7372.8, 60 sec: 7304.5, 300 sec: 7122.9). Total num frames: 2359296. Throughput: 0: 7285.4. Samples: 2343140. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-07-08 21:44:23,717][1084893] Avg episode reward: [(0, '501.841')] -[2023-07-08 21:44:25,991][1085161] Updated weights for policy 0, policy_version 4640 (0.0005) -[2023-07-08 21:44:28,716][1084893] Fps is (10 sec: 7372.8, 60 sec: 7236.3, 300 sec: 7122.9). Total num frames: 2392064. Throughput: 0: 7300.2. Samples: 2388752. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-07-08 21:44:28,717][1084893] Avg episode reward: [(0, '523.253')] -[2023-07-08 21:44:31,745][1085161] Updated weights for policy 0, policy_version 4720 (0.0005) -[2023-07-08 21:44:33,717][1084893] Fps is (10 sec: 6963.1, 60 sec: 7304.5, 300 sec: 7136.8). Total num frames: 2428928. Throughput: 0: 7294.1. Samples: 2430856. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-07-08 21:44:33,717][1084893] Avg episode reward: [(0, '504.616')] -[2023-07-08 21:44:33,720][1085148] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000004744_2428928.pth... -[2023-07-08 21:44:33,723][1085148] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000004320_2211840.pth -[2023-07-08 21:44:37,258][1085161] Updated weights for policy 0, policy_version 4800 (0.0006) -[2023-07-08 21:44:38,716][1084893] Fps is (10 sec: 7372.8, 60 sec: 7304.5, 300 sec: 7136.8). Total num frames: 2465792. Throughput: 0: 7302.1. Samples: 2453788. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:44:38,717][1084893] Avg episode reward: [(0, '521.102')] -[2023-07-08 21:44:43,359][1085161] Updated weights for policy 0, policy_version 4880 (0.0006) -[2023-07-08 21:44:43,716][1084893] Fps is (10 sec: 6963.3, 60 sec: 7236.3, 300 sec: 7136.8). Total num frames: 2498560. Throughput: 0: 7189.1. Samples: 2494464. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-07-08 21:44:43,717][1084893] Avg episode reward: [(0, '522.583')] -[2023-07-08 21:44:48,717][1084893] Fps is (10 sec: 6963.1, 60 sec: 7236.3, 300 sec: 7136.8). Total num frames: 2535424. Throughput: 0: 7134.0. Samples: 2535848. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:44:48,717][1084893] Avg episode reward: [(0, '501.925')] -[2023-07-08 21:44:48,720][1085148] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000004952_2535424.pth... -[2023-07-08 21:44:48,722][1085148] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000004528_2318336.pth -[2023-07-08 21:44:49,238][1085161] Updated weights for policy 0, policy_version 4960 (0.0005) -[2023-07-08 21:44:53,716][1084893] Fps is (10 sec: 7372.8, 60 sec: 7236.3, 300 sec: 7136.8). Total num frames: 2572288. Throughput: 0: 7164.2. Samples: 2558168. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) -[2023-07-08 21:44:53,717][1084893] Avg episode reward: [(0, '487.431')] -[2023-07-08 21:44:54,797][1085161] Updated weights for policy 0, policy_version 5040 (0.0005) -[2023-07-08 21:44:58,717][1084893] Fps is (10 sec: 7372.8, 60 sec: 7236.3, 300 sec: 7150.6). Total num frames: 2609152. Throughput: 0: 7211.5. Samples: 2602368. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:44:58,717][1084893] Avg episode reward: [(0, '489.225')] -[2023-07-08 21:45:00,351][1085161] Updated weights for policy 0, policy_version 5120 (0.0005) -[2023-07-08 21:45:03,716][1084893] Fps is (10 sec: 6963.2, 60 sec: 7168.0, 300 sec: 7136.8). Total num frames: 2641920. Throughput: 0: 7215.9. Samples: 2645932. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-07-08 21:45:03,717][1084893] Avg episode reward: [(0, '513.386')] -[2023-07-08 21:45:03,720][1085148] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000005160_2641920.pth... -[2023-07-08 21:45:03,722][1085148] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000004744_2428928.pth -[2023-07-08 21:45:06,270][1085161] Updated weights for policy 0, policy_version 5200 (0.0005) -[2023-07-08 21:45:08,716][1084893] Fps is (10 sec: 6963.3, 60 sec: 7168.0, 300 sec: 7150.6). Total num frames: 2678784. Throughput: 0: 7175.8. Samples: 2666052. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-07-08 21:45:08,717][1084893] Avg episode reward: [(0, '524.013')] -[2023-07-08 21:45:11,881][1085161] Updated weights for policy 0, policy_version 5280 (0.0005) -[2023-07-08 21:45:13,717][1084893] Fps is (10 sec: 6963.2, 60 sec: 7099.7, 300 sec: 7150.6). Total num frames: 2711552. Throughput: 0: 7109.3. Samples: 2708672. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-07-08 21:45:13,717][1084893] Avg episode reward: [(0, '525.793')] -[2023-07-08 21:45:17,981][1085161] Updated weights for policy 0, policy_version 5360 (0.0006) -[2023-07-08 21:45:18,716][1084893] Fps is (10 sec: 6963.2, 60 sec: 7168.0, 300 sec: 7150.6). Total num frames: 2748416. Throughput: 0: 7078.5. Samples: 2749388. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-07-08 21:45:18,717][1084893] Avg episode reward: [(0, '526.775')] -[2023-07-08 21:45:18,720][1085148] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000005368_2748416.pth... -[2023-07-08 21:45:18,723][1085148] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000004952_2535424.pth -[2023-07-08 21:45:23,427][1085161] Updated weights for policy 0, policy_version 5440 (0.0006) -[2023-07-08 21:45:23,716][1084893] Fps is (10 sec: 7372.8, 60 sec: 7099.7, 300 sec: 7164.5). Total num frames: 2785280. Throughput: 0: 7094.8. Samples: 2773056. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-07-08 21:45:23,717][1084893] Avg episode reward: [(0, '541.890')] -[2023-07-08 21:45:28,716][1084893] Fps is (10 sec: 7372.8, 60 sec: 7168.0, 300 sec: 7164.5). Total num frames: 2822144. Throughput: 0: 7156.4. Samples: 2816500. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:45:28,717][1084893] Avg episode reward: [(0, '548.673')] -[2023-07-08 21:45:28,718][1085148] Saving new best policy, reward=548.673! -[2023-07-08 21:45:29,149][1085161] Updated weights for policy 0, policy_version 5520 (0.0005) -[2023-07-08 21:45:33,716][1084893] Fps is (10 sec: 6963.2, 60 sec: 7099.7, 300 sec: 7136.8). Total num frames: 2854912. Throughput: 0: 7181.1. Samples: 2858996. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) -[2023-07-08 21:45:33,717][1084893] Avg episode reward: [(0, '549.703')] -[2023-07-08 21:45:33,720][1085148] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000005576_2854912.pth... -[2023-07-08 21:45:33,724][1085148] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000005160_2641920.pth -[2023-07-08 21:45:33,724][1085148] Saving new best policy, reward=549.703! -[2023-07-08 21:45:34,947][1085161] Updated weights for policy 0, policy_version 5600 (0.0005) -[2023-07-08 21:45:38,716][1084893] Fps is (10 sec: 6963.2, 60 sec: 7099.7, 300 sec: 7150.6). Total num frames: 2891776. Throughput: 0: 7140.7. Samples: 2879500. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:45:38,725][1084893] Avg episode reward: [(0, '548.441')] -[2023-07-08 21:45:41,151][1085161] Updated weights for policy 0, policy_version 5680 (0.0006) -[2023-07-08 21:45:43,717][1084893] Fps is (10 sec: 6963.1, 60 sec: 7099.7, 300 sec: 7136.8). Total num frames: 2924544. Throughput: 0: 7046.7. Samples: 2919472. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-07-08 21:45:43,718][1084893] Avg episode reward: [(0, '543.604')] -[2023-07-08 21:45:47,019][1085161] Updated weights for policy 0, policy_version 5760 (0.0005) -[2023-07-08 21:45:48,717][1084893] Fps is (10 sec: 6963.2, 60 sec: 7099.7, 300 sec: 7150.6). Total num frames: 2961408. Throughput: 0: 7037.1. Samples: 2962600. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:45:48,718][1084893] Avg episode reward: [(0, '542.942')] -[2023-07-08 21:45:48,720][1085148] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000005784_2961408.pth... -[2023-07-08 21:45:48,723][1085148] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000005368_2748416.pth -[2023-07-08 21:45:52,678][1085161] Updated weights for policy 0, policy_version 5840 (0.0005) -[2023-07-08 21:45:53,716][1084893] Fps is (10 sec: 6963.3, 60 sec: 7031.5, 300 sec: 7136.8). Total num frames: 2994176. Throughput: 0: 7044.4. Samples: 2983052. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:45:53,724][1084893] Avg episode reward: [(0, '529.483')] -[2023-07-08 21:45:58,400][1085161] Updated weights for policy 0, policy_version 5920 (0.0005) -[2023-07-08 21:45:58,716][1084893] Fps is (10 sec: 6963.3, 60 sec: 7031.5, 300 sec: 7136.8). Total num frames: 3031040. Throughput: 0: 7056.0. Samples: 3026192. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:45:58,717][1084893] Avg episode reward: [(0, '527.438')] -[2023-07-08 21:46:03,716][1084893] Fps is (10 sec: 7372.8, 60 sec: 7099.7, 300 sec: 7150.6). Total num frames: 3067904. Throughput: 0: 7099.6. Samples: 3068872. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-07-08 21:46:03,717][1084893] Avg episode reward: [(0, '538.633')] -[2023-07-08 21:46:03,720][1085148] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000005992_3067904.pth... -[2023-07-08 21:46:03,723][1085148] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000005576_2854912.pth -[2023-07-08 21:46:04,188][1085161] Updated weights for policy 0, policy_version 6000 (0.0005) -[2023-07-08 21:46:08,716][1084893] Fps is (10 sec: 6963.2, 60 sec: 7031.5, 300 sec: 7136.8). Total num frames: 3100672. Throughput: 0: 7078.1. Samples: 3091572. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:46:08,717][1084893] Avg episode reward: [(0, '546.663')] -[2023-07-08 21:46:10,033][1085161] Updated weights for policy 0, policy_version 6080 (0.0005) -[2023-07-08 21:46:13,716][1084893] Fps is (10 sec: 6963.2, 60 sec: 7099.7, 300 sec: 7136.8). Total num frames: 3137536. Throughput: 0: 7033.7. Samples: 3133016. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:46:13,718][1084893] Avg episode reward: [(0, '556.106')] -[2023-07-08 21:46:13,719][1085148] Saving new best policy, reward=556.106! -[2023-07-08 21:46:15,854][1085161] Updated weights for policy 0, policy_version 6160 (0.0005) -[2023-07-08 21:46:18,716][1084893] Fps is (10 sec: 6963.2, 60 sec: 7031.5, 300 sec: 7136.8). Total num frames: 3170304. Throughput: 0: 7008.3. Samples: 3174368. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-07-08 21:46:18,847][1084893] Avg episode reward: [(0, '554.165')] -[2023-07-08 21:46:18,850][1085148] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000006200_3174400.pth... -[2023-07-08 21:46:18,853][1085148] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000005784_2961408.pth -[2023-07-08 21:46:21,574][1085161] Updated weights for policy 0, policy_version 6240 (0.0005) -[2023-07-08 21:46:23,716][1084893] Fps is (10 sec: 6963.2, 60 sec: 7031.5, 300 sec: 7136.8). Total num frames: 3207168. Throughput: 0: 7031.2. Samples: 3195904. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:46:23,717][1084893] Avg episode reward: [(0, '546.359')] -[2023-07-08 21:46:27,310][1085161] Updated weights for policy 0, policy_version 6320 (0.0005) -[2023-07-08 21:46:28,716][1084893] Fps is (10 sec: 7372.8, 60 sec: 7031.5, 300 sec: 7136.8). Total num frames: 3244032. Throughput: 0: 7108.2. Samples: 3239340. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-07-08 21:46:28,717][1084893] Avg episode reward: [(0, '555.613')] -[2023-07-08 21:46:32,845][1085161] Updated weights for policy 0, policy_version 6400 (0.0005) -[2023-07-08 21:46:33,716][1084893] Fps is (10 sec: 7372.8, 60 sec: 7099.7, 300 sec: 7150.6). Total num frames: 3280896. Throughput: 0: 7129.2. Samples: 3283412. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-07-08 21:46:33,717][1084893] Avg episode reward: [(0, '548.572')] -[2023-07-08 21:46:33,721][1085148] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000006408_3280896.pth... -[2023-07-08 21:46:33,723][1085148] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000005992_3067904.pth -[2023-07-08 21:46:38,274][1085161] Updated weights for policy 0, policy_version 6480 (0.0005) -[2023-07-08 21:46:38,716][1084893] Fps is (10 sec: 7372.8, 60 sec: 7099.7, 300 sec: 7150.6). Total num frames: 3317760. Throughput: 0: 7166.5. Samples: 3305544. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-07-08 21:46:38,717][1084893] Avg episode reward: [(0, '554.163')] -[2023-07-08 21:46:43,716][1084893] Fps is (10 sec: 7372.8, 60 sec: 7168.0, 300 sec: 7150.6). Total num frames: 3354624. Throughput: 0: 7206.5. Samples: 3350484. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:46:43,717][1084893] Avg episode reward: [(0, '562.502')] -[2023-07-08 21:46:43,717][1085148] Saving new best policy, reward=562.502! -[2023-07-08 21:46:43,924][1085161] Updated weights for policy 0, policy_version 6560 (0.0006) -[2023-07-08 21:46:48,716][1084893] Fps is (10 sec: 7372.8, 60 sec: 7168.0, 300 sec: 7150.6). Total num frames: 3391488. Throughput: 0: 7238.7. Samples: 3394612. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:46:48,717][1084893] Avg episode reward: [(0, '547.082')] -[2023-07-08 21:46:48,720][1085148] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000006624_3391488.pth... -[2023-07-08 21:46:48,723][1085148] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000006200_3174400.pth -[2023-07-08 21:46:49,441][1085161] Updated weights for policy 0, policy_version 6640 (0.0005) -[2023-07-08 21:46:53,716][1084893] Fps is (10 sec: 7372.8, 60 sec: 7236.3, 300 sec: 7150.6). Total num frames: 3428352. Throughput: 0: 7249.6. Samples: 3417804. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:46:53,721][1084893] Avg episode reward: [(0, '552.274')] -[2023-07-08 21:46:54,905][1085161] Updated weights for policy 0, policy_version 6720 (0.0005) -[2023-07-08 21:46:58,716][1084893] Fps is (10 sec: 7372.9, 60 sec: 7236.3, 300 sec: 7150.6). Total num frames: 3465216. Throughput: 0: 7290.8. Samples: 3461100. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:46:58,717][1084893] Avg episode reward: [(0, '562.904')] -[2023-07-08 21:46:58,718][1085148] Saving new best policy, reward=562.904! -[2023-07-08 21:47:00,600][1085161] Updated weights for policy 0, policy_version 6800 (0.0006) -[2023-07-08 21:47:03,716][1084893] Fps is (10 sec: 7372.7, 60 sec: 7236.3, 300 sec: 7150.6). Total num frames: 3502080. Throughput: 0: 7296.9. Samples: 3502728. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) -[2023-07-08 21:47:03,717][1084893] Avg episode reward: [(0, '573.767')] -[2023-07-08 21:47:03,721][1085148] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000006840_3502080.pth... -[2023-07-08 21:47:03,722][1085148] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000006408_3280896.pth -[2023-07-08 21:47:03,723][1085148] Saving new best policy, reward=573.767! -[2023-07-08 21:47:06,512][1085161] Updated weights for policy 0, policy_version 6880 (0.0006) -[2023-07-08 21:47:08,716][1084893] Fps is (10 sec: 6963.1, 60 sec: 7236.3, 300 sec: 7136.8). Total num frames: 3534848. Throughput: 0: 7292.1. Samples: 3524048. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) -[2023-07-08 21:47:08,717][1084893] Avg episode reward: [(0, '567.015')] -[2023-07-08 21:47:12,480][1085161] Updated weights for policy 0, policy_version 6960 (0.0006) -[2023-07-08 21:47:13,716][1084893] Fps is (10 sec: 6963.2, 60 sec: 7236.3, 300 sec: 7150.6). Total num frames: 3571712. Throughput: 0: 7246.2. Samples: 3565420. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) -[2023-07-08 21:47:13,717][1084893] Avg episode reward: [(0, '575.446')] -[2023-07-08 21:47:13,718][1085148] Saving new best policy, reward=575.446! -[2023-07-08 21:47:18,305][1085161] Updated weights for policy 0, policy_version 7040 (0.0006) -[2023-07-08 21:47:18,716][1084893] Fps is (10 sec: 6963.2, 60 sec: 7236.3, 300 sec: 7150.6). Total num frames: 3604480. Throughput: 0: 7212.2. Samples: 3607960. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) -[2023-07-08 21:47:18,717][1084893] Avg episode reward: [(0, '562.773')] -[2023-07-08 21:47:18,720][1085148] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000007040_3604480.pth... -[2023-07-08 21:47:18,723][1085148] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000006624_3391488.pth -[2023-07-08 21:47:23,716][1084893] Fps is (10 sec: 6963.3, 60 sec: 7236.3, 300 sec: 7150.6). Total num frames: 3641344. Throughput: 0: 7181.4. Samples: 3628708. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-07-08 21:47:23,717][1084893] Avg episode reward: [(0, '566.784')] -[2023-07-08 21:47:24,325][1085161] Updated weights for policy 0, policy_version 7120 (0.0005) -[2023-07-08 21:47:28,716][1084893] Fps is (10 sec: 6963.2, 60 sec: 7168.0, 300 sec: 7150.6). Total num frames: 3674112. Throughput: 0: 7098.0. Samples: 3669896. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:47:28,717][1084893] Avg episode reward: [(0, '560.104')] -[2023-07-08 21:47:30,068][1085161] Updated weights for policy 0, policy_version 7200 (0.0005) -[2023-07-08 21:47:33,716][1084893] Fps is (10 sec: 6963.1, 60 sec: 7168.0, 300 sec: 7150.6). Total num frames: 3710976. Throughput: 0: 7056.4. Samples: 3712152. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-07-08 21:47:33,717][1084893] Avg episode reward: [(0, '567.335')] -[2023-07-08 21:47:33,720][1085148] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000007248_3710976.pth... -[2023-07-08 21:47:33,723][1085148] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000006840_3502080.pth -[2023-07-08 21:47:36,024][1085161] Updated weights for policy 0, policy_version 7280 (0.0005) -[2023-07-08 21:47:38,716][1084893] Fps is (10 sec: 7372.8, 60 sec: 7168.0, 300 sec: 7150.6). Total num frames: 3747840. Throughput: 0: 7011.3. Samples: 3733312. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-07-08 21:47:38,717][1084893] Avg episode reward: [(0, '557.995')] -[2023-07-08 21:47:41,141][1085161] Updated weights for policy 0, policy_version 7360 (0.0005) -[2023-07-08 21:47:43,716][1084893] Fps is (10 sec: 7372.8, 60 sec: 7168.0, 300 sec: 7150.6). Total num frames: 3784704. Throughput: 0: 7109.5. Samples: 3781028. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-07-08 21:47:43,717][1084893] Avg episode reward: [(0, '566.790')] -[2023-07-08 21:47:46,438][1085161] Updated weights for policy 0, policy_version 7440 (0.0005) -[2023-07-08 21:47:48,716][1084893] Fps is (10 sec: 7372.8, 60 sec: 7168.0, 300 sec: 7150.6). Total num frames: 3821568. Throughput: 0: 7153.5. Samples: 3824636. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:47:48,717][1084893] Avg episode reward: [(0, '577.381')] -[2023-07-08 21:47:48,720][1085148] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000007464_3821568.pth... -[2023-07-08 21:47:48,722][1085148] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000007040_3604480.pth -[2023-07-08 21:47:48,722][1085148] Saving new best policy, reward=577.381! -[2023-07-08 21:47:52,343][1085161] Updated weights for policy 0, policy_version 7520 (0.0005) -[2023-07-08 21:47:53,716][1084893] Fps is (10 sec: 7372.8, 60 sec: 7168.0, 300 sec: 7164.5). Total num frames: 3858432. Throughput: 0: 7159.1. Samples: 3846208. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-07-08 21:47:53,717][1084893] Avg episode reward: [(0, '569.682')] -[2023-07-08 21:47:57,858][1085161] Updated weights for policy 0, policy_version 7600 (0.0005) -[2023-07-08 21:47:58,716][1084893] Fps is (10 sec: 7372.8, 60 sec: 7168.0, 300 sec: 7164.5). Total num frames: 3895296. Throughput: 0: 7236.4. Samples: 3891060. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-07-08 21:47:58,717][1084893] Avg episode reward: [(0, '567.913')] -[2023-07-08 21:48:03,438][1085161] Updated weights for policy 0, policy_version 7680 (0.0005) -[2023-07-08 21:48:03,716][1084893] Fps is (10 sec: 7372.8, 60 sec: 7168.0, 300 sec: 7178.4). Total num frames: 3932160. Throughput: 0: 7253.1. Samples: 3934348. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-07-08 21:48:03,717][1084893] Avg episode reward: [(0, '570.178')] -[2023-07-08 21:48:03,720][1085148] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000007680_3932160.pth... -[2023-07-08 21:48:03,723][1085148] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000007248_3710976.pth -[2023-07-08 21:48:08,717][1084893] Fps is (10 sec: 6963.2, 60 sec: 7168.0, 300 sec: 7164.5). Total num frames: 3964928. Throughput: 0: 7250.4. Samples: 3954976. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:48:08,717][1084893] Avg episode reward: [(0, '566.825')] -[2023-07-08 21:48:09,408][1085161] Updated weights for policy 0, policy_version 7760 (0.0005) -[2023-07-08 21:48:13,716][1084893] Fps is (10 sec: 7372.8, 60 sec: 7236.3, 300 sec: 7192.3). Total num frames: 4005888. Throughput: 0: 7294.0. Samples: 3998124. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:48:13,717][1084893] Avg episode reward: [(0, '572.139')] -[2023-07-08 21:48:14,664][1085161] Updated weights for policy 0, policy_version 7840 (0.0005) -[2023-07-08 21:48:18,716][1084893] Fps is (10 sec: 7782.5, 60 sec: 7304.5, 300 sec: 7192.3). Total num frames: 4042752. Throughput: 0: 7363.8. Samples: 4043524. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:48:18,717][1084893] Avg episode reward: [(0, '573.976')] -[2023-07-08 21:48:18,720][1085148] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000007896_4042752.pth... -[2023-07-08 21:48:18,722][1085148] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000007464_3821568.pth -[2023-07-08 21:48:20,216][1085161] Updated weights for policy 0, policy_version 7920 (0.0005) -[2023-07-08 21:48:23,716][1084893] Fps is (10 sec: 7372.8, 60 sec: 7304.5, 300 sec: 7192.3). Total num frames: 4079616. Throughput: 0: 7379.6. Samples: 4065392. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-07-08 21:48:23,717][1084893] Avg episode reward: [(0, '562.205')] -[2023-07-08 21:48:25,842][1085161] Updated weights for policy 0, policy_version 8000 (0.0005) -[2023-07-08 21:48:28,716][1084893] Fps is (10 sec: 6963.2, 60 sec: 7304.5, 300 sec: 7192.3). Total num frames: 4112384. Throughput: 0: 7304.3. Samples: 4109720. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-07-08 21:48:28,717][1084893] Avg episode reward: [(0, '579.953')] -[2023-07-08 21:48:28,717][1085148] Saving new best policy, reward=579.953! -[2023-07-08 21:48:31,383][1085161] Updated weights for policy 0, policy_version 8080 (0.0006) -[2023-07-08 21:48:33,717][1084893] Fps is (10 sec: 7372.7, 60 sec: 7372.8, 300 sec: 7206.2). Total num frames: 4153344. Throughput: 0: 7343.5. Samples: 4155096. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) -[2023-07-08 21:48:33,717][1084893] Avg episode reward: [(0, '583.972')] -[2023-07-08 21:48:33,720][1085148] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000008112_4153344.pth... -[2023-07-08 21:48:33,723][1085148] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000007680_3932160.pth -[2023-07-08 21:48:33,723][1085148] Saving new best policy, reward=583.972! -[2023-07-08 21:48:36,844][1085161] Updated weights for policy 0, policy_version 8160 (0.0005) -[2023-07-08 21:48:38,716][1084893] Fps is (10 sec: 7782.4, 60 sec: 7372.8, 300 sec: 7206.2). Total num frames: 4190208. Throughput: 0: 7357.5. Samples: 4177296. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) -[2023-07-08 21:48:38,717][1084893] Avg episode reward: [(0, '583.871')] -[2023-07-08 21:48:42,533][1085161] Updated weights for policy 0, policy_version 8240 (0.0005) -[2023-07-08 21:48:43,716][1084893] Fps is (10 sec: 6963.3, 60 sec: 7304.5, 300 sec: 7192.3). Total num frames: 4222976. Throughput: 0: 7313.6. Samples: 4220172. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:48:43,717][1084893] Avg episode reward: [(0, '582.659')] -[2023-07-08 21:48:47,941][1085161] Updated weights for policy 0, policy_version 8320 (0.0005) -[2023-07-08 21:48:48,717][1084893] Fps is (10 sec: 7372.8, 60 sec: 7372.8, 300 sec: 7206.2). Total num frames: 4263936. Throughput: 0: 7394.0. Samples: 4267080. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:48:48,717][1084893] Avg episode reward: [(0, '573.886')] -[2023-07-08 21:48:48,720][1085148] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000008328_4263936.pth... -[2023-07-08 21:48:48,723][1085148] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000007896_4042752.pth -[2023-07-08 21:48:53,390][1085161] Updated weights for policy 0, policy_version 8400 (0.0006) -[2023-07-08 21:48:53,716][1084893] Fps is (10 sec: 7782.4, 60 sec: 7372.8, 300 sec: 7206.2). Total num frames: 4300800. Throughput: 0: 7412.1. Samples: 4288520. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:48:53,717][1084893] Avg episode reward: [(0, '565.578')] -[2023-07-08 21:48:58,716][1084893] Fps is (10 sec: 7372.9, 60 sec: 7372.8, 300 sec: 7206.2). Total num frames: 4337664. Throughput: 0: 7388.3. Samples: 4330596. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:48:58,717][1084893] Avg episode reward: [(0, '558.730')] -[2023-07-08 21:48:59,229][1085161] Updated weights for policy 0, policy_version 8480 (0.0005) -[2023-07-08 21:49:03,716][1084893] Fps is (10 sec: 7372.8, 60 sec: 7372.8, 300 sec: 7206.2). Total num frames: 4374528. Throughput: 0: 7362.3. Samples: 4374828. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:49:03,717][1084893] Avg episode reward: [(0, '564.154')] -[2023-07-08 21:49:03,720][1085148] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000008544_4374528.pth... -[2023-07-08 21:49:03,722][1085148] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000008112_4153344.pth -[2023-07-08 21:49:04,772][1085161] Updated weights for policy 0, policy_version 8560 (0.0006) -[2023-07-08 21:49:08,716][1084893] Fps is (10 sec: 7372.8, 60 sec: 7441.1, 300 sec: 7206.2). Total num frames: 4411392. Throughput: 0: 7367.7. Samples: 4396936. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:49:08,717][1084893] Avg episode reward: [(0, '577.170')] -[2023-07-08 21:49:10,395][1085161] Updated weights for policy 0, policy_version 8640 (0.0005) -[2023-07-08 21:49:13,716][1084893] Fps is (10 sec: 6963.2, 60 sec: 7304.5, 300 sec: 7206.2). Total num frames: 4444160. Throughput: 0: 7358.9. Samples: 4440872. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-07-08 21:49:13,717][1084893] Avg episode reward: [(0, '576.829')] -[2023-07-08 21:49:16,036][1085161] Updated weights for policy 0, policy_version 8720 (0.0005) -[2023-07-08 21:49:18,716][1084893] Fps is (10 sec: 7372.8, 60 sec: 7372.8, 300 sec: 7206.2). Total num frames: 4485120. Throughput: 0: 7357.1. Samples: 4486164. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-07-08 21:49:18,717][1084893] Avg episode reward: [(0, '575.586')] -[2023-07-08 21:49:18,720][1085148] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000008760_4485120.pth... -[2023-07-08 21:49:18,722][1085148] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000008328_4263936.pth -[2023-07-08 21:49:21,458][1085161] Updated weights for policy 0, policy_version 8800 (0.0005) -[2023-07-08 21:49:23,716][1084893] Fps is (10 sec: 7782.4, 60 sec: 7372.8, 300 sec: 7220.1). Total num frames: 4521984. Throughput: 0: 7340.5. Samples: 4507620. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-07-08 21:49:23,717][1084893] Avg episode reward: [(0, '568.290')] -[2023-07-08 21:49:27,199][1085161] Updated weights for policy 0, policy_version 8880 (0.0005) -[2023-07-08 21:49:28,716][1084893] Fps is (10 sec: 6963.2, 60 sec: 7372.8, 300 sec: 7206.2). Total num frames: 4554752. Throughput: 0: 7342.8. Samples: 4550600. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-07-08 21:49:28,717][1084893] Avg episode reward: [(0, '553.710')] -[2023-07-08 21:49:32,757][1085161] Updated weights for policy 0, policy_version 8960 (0.0005) -[2023-07-08 21:49:33,716][1084893] Fps is (10 sec: 6963.2, 60 sec: 7304.5, 300 sec: 7206.2). Total num frames: 4591616. Throughput: 0: 7281.5. Samples: 4594748. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-07-08 21:49:33,717][1084893] Avg episode reward: [(0, '556.309')] -[2023-07-08 21:49:33,720][1085148] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000008968_4591616.pth... -[2023-07-08 21:49:33,723][1085148] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000008544_4374528.pth -[2023-07-08 21:49:38,305][1085161] Updated weights for policy 0, policy_version 9040 (0.0005) -[2023-07-08 21:49:38,716][1084893] Fps is (10 sec: 7372.8, 60 sec: 7304.5, 300 sec: 7220.1). Total num frames: 4628480. Throughput: 0: 7304.6. Samples: 4617228. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-07-08 21:49:38,717][1084893] Avg episode reward: [(0, '575.411')] -[2023-07-08 21:49:43,716][1084893] Fps is (10 sec: 7372.9, 60 sec: 7372.8, 300 sec: 7220.1). Total num frames: 4665344. Throughput: 0: 7349.4. Samples: 4661320. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) -[2023-07-08 21:49:43,717][1084893] Avg episode reward: [(0, '577.211')] -[2023-07-08 21:49:43,834][1085161] Updated weights for policy 0, policy_version 9120 (0.0005) -[2023-07-08 21:49:48,716][1084893] Fps is (10 sec: 7372.8, 60 sec: 7304.5, 300 sec: 7220.1). Total num frames: 4702208. Throughput: 0: 7336.2. Samples: 4704956. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-07-08 21:49:48,717][1084893] Avg episode reward: [(0, '579.473')] -[2023-07-08 21:49:48,720][1085148] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000009184_4702208.pth... -[2023-07-08 21:49:48,723][1085148] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000008760_4485120.pth -[2023-07-08 21:49:49,457][1085161] Updated weights for policy 0, policy_version 9200 (0.0005) -[2023-07-08 21:49:53,716][1084893] Fps is (10 sec: 7372.8, 60 sec: 7304.5, 300 sec: 7220.1). Total num frames: 4739072. Throughput: 0: 7331.6. Samples: 4726856. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-07-08 21:49:53,717][1084893] Avg episode reward: [(0, '587.220')] -[2023-07-08 21:49:53,717][1085148] Saving new best policy, reward=587.220! -[2023-07-08 21:49:54,842][1085161] Updated weights for policy 0, policy_version 9280 (0.0005) -[2023-07-08 21:49:58,716][1084893] Fps is (10 sec: 7782.4, 60 sec: 7372.8, 300 sec: 7247.8). Total num frames: 4780032. Throughput: 0: 7373.0. Samples: 4772656. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:49:58,717][1084893] Avg episode reward: [(0, '578.845')] -[2023-07-08 21:50:00,275][1085161] Updated weights for policy 0, policy_version 9360 (0.0005) -[2023-07-08 21:50:03,716][1084893] Fps is (10 sec: 7782.3, 60 sec: 7372.8, 300 sec: 7247.8). Total num frames: 4816896. Throughput: 0: 7399.1. Samples: 4819124. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-07-08 21:50:03,717][1084893] Avg episode reward: [(0, '580.097')] -[2023-07-08 21:50:03,720][1085148] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000009408_4816896.pth... -[2023-07-08 21:50:03,723][1085148] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000008968_4591616.pth -[2023-07-08 21:50:05,639][1085161] Updated weights for policy 0, policy_version 9440 (0.0005) -[2023-07-08 21:50:08,716][1084893] Fps is (10 sec: 7372.9, 60 sec: 7372.8, 300 sec: 7261.7). Total num frames: 4853760. Throughput: 0: 7417.1. Samples: 4841388. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-07-08 21:50:08,717][1084893] Avg episode reward: [(0, '581.184')] -[2023-07-08 21:50:11,421][1085161] Updated weights for policy 0, policy_version 9520 (0.0006) -[2023-07-08 21:50:13,716][1084893] Fps is (10 sec: 7372.8, 60 sec: 7441.1, 300 sec: 7261.7). Total num frames: 4890624. Throughput: 0: 7406.6. Samples: 4883896. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:50:13,717][1084893] Avg episode reward: [(0, '579.806')] -[2023-07-08 21:50:16,897][1085161] Updated weights for policy 0, policy_version 9600 (0.0006) -[2023-07-08 21:50:18,717][1084893] Fps is (10 sec: 7372.7, 60 sec: 7372.8, 300 sec: 7261.7). Total num frames: 4927488. Throughput: 0: 7432.7. Samples: 4929220. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-07-08 21:50:18,718][1084893] Avg episode reward: [(0, '580.085')] -[2023-07-08 21:50:18,720][1085148] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000009624_4927488.pth... -[2023-07-08 21:50:18,723][1085148] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000009184_4702208.pth -[2023-07-08 21:50:22,430][1085161] Updated weights for policy 0, policy_version 9680 (0.0005) -[2023-07-08 21:50:23,716][1084893] Fps is (10 sec: 7372.8, 60 sec: 7372.8, 300 sec: 7261.7). Total num frames: 4964352. Throughput: 0: 7416.0. Samples: 4950948. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-07-08 21:50:23,718][1084893] Avg episode reward: [(0, '575.759')] -[2023-07-08 21:50:28,113][1085161] Updated weights for policy 0, policy_version 9760 (0.0006) -[2023-07-08 21:50:28,716][1084893] Fps is (10 sec: 7372.8, 60 sec: 7441.1, 300 sec: 7275.6). Total num frames: 5001216. Throughput: 0: 7403.3. Samples: 4994468. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:50:28,717][1084893] Avg episode reward: [(0, '579.374')] -[2023-07-08 21:50:33,371][1085161] Updated weights for policy 0, policy_version 9840 (0.0005) -[2023-07-08 21:50:33,717][1084893] Fps is (10 sec: 7372.7, 60 sec: 7441.1, 300 sec: 7275.6). Total num frames: 5038080. Throughput: 0: 7467.1. Samples: 5040976. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:50:33,718][1084893] Avg episode reward: [(0, '579.832')] -[2023-07-08 21:50:33,721][1085148] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000009840_5038080.pth... -[2023-07-08 21:50:33,723][1085148] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000009408_4816896.pth -[2023-07-08 21:50:38,716][1084893] Fps is (10 sec: 7372.8, 60 sec: 7441.1, 300 sec: 7289.5). Total num frames: 5074944. Throughput: 0: 7434.9. Samples: 5061428. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-07-08 21:50:38,717][1084893] Avg episode reward: [(0, '580.539')] -[2023-07-08 21:50:38,990][1085161] Updated weights for policy 0, policy_version 9920 (0.0005) -[2023-07-08 21:50:43,716][1084893] Fps is (10 sec: 7372.9, 60 sec: 7441.1, 300 sec: 7289.5). Total num frames: 5111808. Throughput: 0: 7418.0. Samples: 5106464. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:50:43,718][1084893] Avg episode reward: [(0, '569.536')] -[2023-07-08 21:50:44,442][1085161] Updated weights for policy 0, policy_version 10000 (0.0005) -[2023-07-08 21:50:48,717][1084893] Fps is (10 sec: 7372.7, 60 sec: 7441.1, 300 sec: 7303.4). Total num frames: 5148672. Throughput: 0: 7408.9. Samples: 5152524. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:50:48,717][1084893] Avg episode reward: [(0, '579.698')] -[2023-07-08 21:50:48,720][1085148] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000010056_5148672.pth... -[2023-07-08 21:50:48,721][1085148] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000009624_4927488.pth -[2023-07-08 21:50:50,026][1085161] Updated weights for policy 0, policy_version 10080 (0.0005) -[2023-07-08 21:50:53,716][1084893] Fps is (10 sec: 7372.7, 60 sec: 7441.1, 300 sec: 7303.4). Total num frames: 5185536. Throughput: 0: 7381.0. Samples: 5173532. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:50:53,717][1084893] Avg episode reward: [(0, '578.066')] -[2023-07-08 21:50:55,567][1085161] Updated weights for policy 0, policy_version 10160 (0.0005) -[2023-07-08 21:50:58,716][1084893] Fps is (10 sec: 7782.4, 60 sec: 7441.1, 300 sec: 7317.3). Total num frames: 5226496. Throughput: 0: 7439.1. Samples: 5218656. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:50:58,717][1084893] Avg episode reward: [(0, '579.546')] -[2023-07-08 21:51:00,601][1085161] Updated weights for policy 0, policy_version 10240 (0.0005) -[2023-07-08 21:51:03,717][1084893] Fps is (10 sec: 7782.3, 60 sec: 7441.0, 300 sec: 7331.1). Total num frames: 5263360. Throughput: 0: 7493.7. Samples: 5266436. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:51:03,717][1084893] Avg episode reward: [(0, '577.468')] -[2023-07-08 21:51:03,721][1085148] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000010280_5263360.pth... -[2023-07-08 21:51:03,724][1085148] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000009840_5038080.pth -[2023-07-08 21:51:06,111][1085161] Updated weights for policy 0, policy_version 10320 (0.0005) -[2023-07-08 21:51:08,716][1084893] Fps is (10 sec: 7372.8, 60 sec: 7441.1, 300 sec: 7331.1). Total num frames: 5300224. Throughput: 0: 7488.5. Samples: 5287932. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:51:08,717][1084893] Avg episode reward: [(0, '577.719')] -[2023-07-08 21:51:11,435][1085161] Updated weights for policy 0, policy_version 10400 (0.0005) -[2023-07-08 21:51:13,716][1084893] Fps is (10 sec: 7782.5, 60 sec: 7509.3, 300 sec: 7358.9). Total num frames: 5341184. Throughput: 0: 7539.8. Samples: 5333760. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:51:13,717][1084893] Avg episode reward: [(0, '578.776')] -[2023-07-08 21:51:16,951][1085161] Updated weights for policy 0, policy_version 10480 (0.0005) -[2023-07-08 21:51:18,716][1084893] Fps is (10 sec: 7782.4, 60 sec: 7509.3, 300 sec: 7358.9). Total num frames: 5378048. Throughput: 0: 7498.4. Samples: 5378404. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:51:18,717][1084893] Avg episode reward: [(0, '583.069')] -[2023-07-08 21:51:18,719][1085148] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000010504_5378048.pth... -[2023-07-08 21:51:18,722][1085148] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000010056_5148672.pth -[2023-07-08 21:51:22,575][1085161] Updated weights for policy 0, policy_version 10560 (0.0005) -[2023-07-08 21:51:23,716][1084893] Fps is (10 sec: 7372.8, 60 sec: 7509.3, 300 sec: 7358.9). Total num frames: 5414912. Throughput: 0: 7531.9. Samples: 5400364. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:51:23,717][1084893] Avg episode reward: [(0, '582.722')] -[2023-07-08 21:51:28,069][1085161] Updated weights for policy 0, policy_version 10640 (0.0006) -[2023-07-08 21:51:28,716][1084893] Fps is (10 sec: 7372.8, 60 sec: 7509.3, 300 sec: 7358.9). Total num frames: 5451776. Throughput: 0: 7522.0. Samples: 5444956. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:51:28,718][1084893] Avg episode reward: [(0, '581.075')] -[2023-07-08 21:51:33,442][1085161] Updated weights for policy 0, policy_version 10720 (0.0005) -[2023-07-08 21:51:33,716][1084893] Fps is (10 sec: 7372.8, 60 sec: 7509.3, 300 sec: 7358.9). Total num frames: 5488640. Throughput: 0: 7518.0. Samples: 5490832. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-07-08 21:51:33,725][1084893] Avg episode reward: [(0, '579.593')] -[2023-07-08 21:51:33,728][1085148] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000010720_5488640.pth... -[2023-07-08 21:51:33,731][1085148] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000010280_5263360.pth -[2023-07-08 21:51:38,716][1084893] Fps is (10 sec: 7372.9, 60 sec: 7509.3, 300 sec: 7358.9). Total num frames: 5525504. Throughput: 0: 7544.8. Samples: 5513048. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-07-08 21:51:38,717][1084893] Avg episode reward: [(0, '573.143')] -[2023-07-08 21:51:39,098][1085161] Updated weights for policy 0, policy_version 10800 (0.0005) -[2023-07-08 21:51:43,716][1084893] Fps is (10 sec: 7372.9, 60 sec: 7509.3, 300 sec: 7358.9). Total num frames: 5562368. Throughput: 0: 7481.7. Samples: 5555332. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:51:43,717][1084893] Avg episode reward: [(0, '580.662')] -[2023-07-08 21:51:44,704][1085161] Updated weights for policy 0, policy_version 10880 (0.0005) -[2023-07-08 21:51:48,717][1084893] Fps is (10 sec: 6963.1, 60 sec: 7441.1, 300 sec: 7345.0). Total num frames: 5595136. Throughput: 0: 6929.8. Samples: 5578276. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:51:48,717][1084893] Avg episode reward: [(0, '583.735')] -[2023-07-08 21:51:48,724][1085148] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000010936_5599232.pth... -[2023-07-08 21:51:48,726][1085148] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000010504_5378048.pth -[2023-07-08 21:51:50,495][1085161] Updated weights for policy 0, policy_version 10960 (0.0005) -[2023-07-08 21:51:53,716][1084893] Fps is (10 sec: 6963.2, 60 sec: 7441.1, 300 sec: 7345.0). Total num frames: 5632000. Throughput: 0: 7392.3. Samples: 5620584. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:51:53,717][1084893] Avg episode reward: [(0, '580.735')] -[2023-07-08 21:51:56,250][1085161] Updated weights for policy 0, policy_version 11040 (0.0006) -[2023-07-08 21:51:58,717][1084893] Fps is (10 sec: 7372.8, 60 sec: 7372.8, 300 sec: 7345.0). Total num frames: 5668864. Throughput: 0: 7338.0. Samples: 5663972. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:51:58,717][1084893] Avg episode reward: [(0, '582.761')] -[2023-07-08 21:52:01,555][1085161] Updated weights for policy 0, policy_version 11120 (0.0005) -[2023-07-08 21:52:03,716][1084893] Fps is (10 sec: 7372.8, 60 sec: 7372.8, 300 sec: 7358.9). Total num frames: 5705728. Throughput: 0: 6838.5. Samples: 5686136. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:52:03,717][1084893] Avg episode reward: [(0, '581.909')] -[2023-07-08 21:52:03,750][1085148] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000011152_5709824.pth... -[2023-07-08 21:52:03,752][1085148] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000010720_5488640.pth -[2023-07-08 21:52:06,960][1085161] Updated weights for policy 0, policy_version 11200 (0.0005) -[2023-07-08 21:52:08,716][1084893] Fps is (10 sec: 7782.5, 60 sec: 7441.1, 300 sec: 7372.8). Total num frames: 5746688. Throughput: 0: 7398.7. Samples: 5733304. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:52:08,717][1084893] Avg episode reward: [(0, '569.156')] -[2023-07-08 21:52:12,523][1085161] Updated weights for policy 0, policy_version 11280 (0.0005) -[2023-07-08 21:52:13,716][1084893] Fps is (10 sec: 7372.8, 60 sec: 7304.5, 300 sec: 7372.8). Total num frames: 5779456. Throughput: 0: 7371.6. Samples: 5776676. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:52:13,717][1084893] Avg episode reward: [(0, '582.127')] -[2023-07-08 21:52:18,276][1085161] Updated weights for policy 0, policy_version 11360 (0.0005) -[2023-07-08 21:52:18,716][1084893] Fps is (10 sec: 6963.2, 60 sec: 7304.5, 300 sec: 7372.8). Total num frames: 5816320. Throughput: 0: 7319.1. Samples: 5820192. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:52:18,717][1084893] Avg episode reward: [(0, '575.918')] -[2023-07-08 21:52:18,720][1085148] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000011360_5816320.pth... -[2023-07-08 21:52:18,722][1085148] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000010936_5599232.pth -[2023-07-08 21:52:23,716][1084893] Fps is (10 sec: 7372.8, 60 sec: 7304.5, 300 sec: 7386.7). Total num frames: 5853184. Throughput: 0: 7296.4. Samples: 5841384. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:52:23,717][1084893] Avg episode reward: [(0, '572.572')] -[2023-07-08 21:52:23,905][1085161] Updated weights for policy 0, policy_version 11440 (0.0005) -[2023-07-08 21:52:28,716][1084893] Fps is (10 sec: 7372.8, 60 sec: 7304.5, 300 sec: 7386.7). Total num frames: 5890048. Throughput: 0: 7346.0. Samples: 5885904. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:52:28,717][1084893] Avg episode reward: [(0, '572.053')] -[2023-07-08 21:52:29,524][1085161] Updated weights for policy 0, policy_version 11520 (0.0006) -[2023-07-08 21:52:33,717][1084893] Fps is (10 sec: 7372.7, 60 sec: 7304.5, 300 sec: 7386.7). Total num frames: 5926912. Throughput: 0: 7819.5. Samples: 5930152. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-07-08 21:52:33,717][1084893] Avg episode reward: [(0, '573.513')] -[2023-07-08 21:52:33,720][1085148] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000011576_5926912.pth... -[2023-07-08 21:52:33,723][1085148] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000011152_5709824.pth -[2023-07-08 21:52:34,962][1085161] Updated weights for policy 0, policy_version 11600 (0.0005) -[2023-07-08 21:52:38,716][1084893] Fps is (10 sec: 7372.8, 60 sec: 7304.5, 300 sec: 7386.7). Total num frames: 5963776. Throughput: 0: 7355.0. Samples: 5951560. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-07-08 21:52:38,717][1084893] Avg episode reward: [(0, '581.294')] -[2023-07-08 21:52:40,466][1085161] Updated weights for policy 0, policy_version 11680 (0.0005) -[2023-07-08 21:52:43,716][1084893] Fps is (10 sec: 7782.5, 60 sec: 7372.8, 300 sec: 7400.6). Total num frames: 6004736. Throughput: 0: 7446.1. Samples: 5999044. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-07-08 21:52:43,717][1084893] Avg episode reward: [(0, '581.856')] -[2023-07-08 21:52:45,975][1085161] Updated weights for policy 0, policy_version 11760 (0.0005) -[2023-07-08 21:52:48,716][1084893] Fps is (10 sec: 7372.8, 60 sec: 7372.8, 300 sec: 7386.7). Total num frames: 6037504. Throughput: 0: 7898.0. Samples: 6041548. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-07-08 21:52:48,717][1084893] Avg episode reward: [(0, '562.014')] -[2023-07-08 21:52:48,720][1085148] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000011792_6037504.pth... -[2023-07-08 21:52:48,721][1085148] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000011360_5816320.pth -[2023-07-08 21:52:51,777][1085161] Updated weights for policy 0, policy_version 11840 (0.0006) -[2023-07-08 21:52:53,716][1084893] Fps is (10 sec: 6963.2, 60 sec: 7372.8, 300 sec: 7386.7). Total num frames: 6074368. Throughput: 0: 7305.9. Samples: 6062068. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:52:53,718][1084893] Avg episode reward: [(0, '572.026')] -[2023-07-08 21:52:57,630][1085161] Updated weights for policy 0, policy_version 11920 (0.0005) -[2023-07-08 21:52:58,716][1084893] Fps is (10 sec: 6963.2, 60 sec: 7304.5, 300 sec: 7372.8). Total num frames: 6107136. Throughput: 0: 7264.0. Samples: 6103556. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:52:58,717][1084893] Avg episode reward: [(0, '582.816')] -[2023-07-08 21:53:03,130][1085161] Updated weights for policy 0, policy_version 12000 (0.0005) -[2023-07-08 21:53:03,716][1084893] Fps is (10 sec: 7372.8, 60 sec: 7372.8, 300 sec: 7400.6). Total num frames: 6148096. Throughput: 0: 7293.2. Samples: 6148388. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) -[2023-07-08 21:53:03,717][1084893] Avg episode reward: [(0, '579.262')] -[2023-07-08 21:53:03,720][1085148] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000012008_6148096.pth... -[2023-07-08 21:53:03,723][1085148] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000011576_5926912.pth -[2023-07-08 21:53:08,542][1085161] Updated weights for policy 0, policy_version 12080 (0.0005) -[2023-07-08 21:53:08,716][1084893] Fps is (10 sec: 7782.3, 60 sec: 7304.5, 300 sec: 7386.7). Total num frames: 6184960. Throughput: 0: 7309.5. Samples: 6170312. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) -[2023-07-08 21:53:08,717][1084893] Avg episode reward: [(0, '580.128')] -[2023-07-08 21:53:13,716][1084893] Fps is (10 sec: 6963.3, 60 sec: 7304.5, 300 sec: 7372.8). Total num frames: 6217728. Throughput: 0: 7291.5. Samples: 6214020. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:53:13,717][1084893] Avg episode reward: [(0, '577.437')] -[2023-07-08 21:53:14,478][1085161] Updated weights for policy 0, policy_version 12160 (0.0005) -[2023-07-08 21:53:18,716][1084893] Fps is (10 sec: 6963.3, 60 sec: 7304.5, 300 sec: 7372.8). Total num frames: 6254592. Throughput: 0: 7241.9. Samples: 6256036. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:53:18,717][1084893] Avg episode reward: [(0, '581.465')] -[2023-07-08 21:53:18,720][1085148] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000012216_6254592.pth... -[2023-07-08 21:53:18,723][1085148] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000011792_6037504.pth -[2023-07-08 21:53:20,086][1085161] Updated weights for policy 0, policy_version 12240 (0.0005) -[2023-07-08 21:53:23,716][1084893] Fps is (10 sec: 7372.7, 60 sec: 7304.5, 300 sec: 7386.7). Total num frames: 6291456. Throughput: 0: 7279.0. Samples: 6279116. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) -[2023-07-08 21:53:23,717][1084893] Avg episode reward: [(0, '582.247')] -[2023-07-08 21:53:25,630][1085161] Updated weights for policy 0, policy_version 12320 (0.0005) -[2023-07-08 21:53:28,716][1084893] Fps is (10 sec: 7372.8, 60 sec: 7304.5, 300 sec: 7372.8). Total num frames: 6328320. Throughput: 0: 7260.6. Samples: 6325772. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) -[2023-07-08 21:53:28,717][1084893] Avg episode reward: [(0, '582.719')] -[2023-07-08 21:53:31,001][1085161] Updated weights for policy 0, policy_version 12400 (0.0006) -[2023-07-08 21:53:33,716][1084893] Fps is (10 sec: 7372.9, 60 sec: 7304.5, 300 sec: 7372.8). Total num frames: 6365184. Throughput: 0: 7246.8. Samples: 6367656. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-07-08 21:53:33,717][1084893] Avg episode reward: [(0, '580.588')] -[2023-07-08 21:53:33,719][1085148] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000012432_6365184.pth... -[2023-07-08 21:53:33,722][1085148] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000012008_6148096.pth -[2023-07-08 21:53:36,672][1085161] Updated weights for policy 0, policy_version 12480 (0.0005) -[2023-07-08 21:53:38,716][1084893] Fps is (10 sec: 7782.4, 60 sec: 7372.8, 300 sec: 7400.6). Total num frames: 6406144. Throughput: 0: 7283.6. Samples: 6389832. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) -[2023-07-08 21:53:38,717][1084893] Avg episode reward: [(0, '583.272')] -[2023-07-08 21:53:42,109][1085161] Updated weights for policy 0, policy_version 12560 (0.0005) -[2023-07-08 21:53:43,716][1084893] Fps is (10 sec: 7372.8, 60 sec: 7236.3, 300 sec: 7372.8). Total num frames: 6438912. Throughput: 0: 7361.3. Samples: 6434816. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) -[2023-07-08 21:53:43,717][1084893] Avg episode reward: [(0, '580.121')] -[2023-07-08 21:53:47,871][1085161] Updated weights for policy 0, policy_version 12640 (0.0005) -[2023-07-08 21:53:48,717][1084893] Fps is (10 sec: 6963.1, 60 sec: 7304.5, 300 sec: 7372.8). Total num frames: 6475776. Throughput: 0: 7315.7. Samples: 6477596. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-07-08 21:53:48,718][1084893] Avg episode reward: [(0, '581.551')] -[2023-07-08 21:53:48,721][1085148] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000012648_6475776.pth... -[2023-07-08 21:53:48,723][1085148] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000012216_6254592.pth -[2023-07-08 21:53:53,190][1085161] Updated weights for policy 0, policy_version 12720 (0.0005) -[2023-07-08 21:53:53,716][1084893] Fps is (10 sec: 7372.8, 60 sec: 7304.5, 300 sec: 7372.8). Total num frames: 6512640. Throughput: 0: 7375.8. Samples: 6502224. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-07-08 21:53:53,717][1084893] Avg episode reward: [(0, '580.562')] -[2023-07-08 21:53:58,716][1084893] Fps is (10 sec: 7373.0, 60 sec: 7372.8, 300 sec: 7372.8). Total num frames: 6549504. Throughput: 0: 7365.6. Samples: 6545472. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:53:58,717][1084893] Avg episode reward: [(0, '578.865')] -[2023-07-08 21:53:58,760][1085161] Updated weights for policy 0, policy_version 12800 (0.0005) -[2023-07-08 21:54:03,716][1084893] Fps is (10 sec: 7372.8, 60 sec: 7304.5, 300 sec: 7372.8). Total num frames: 6586368. Throughput: 0: 7388.6. Samples: 6588524. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:54:03,717][1084893] Avg episode reward: [(0, '580.372')] -[2023-07-08 21:54:03,720][1085148] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000012864_6586368.pth... -[2023-07-08 21:54:03,722][1085148] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000012432_6365184.pth -[2023-07-08 21:54:04,634][1085161] Updated weights for policy 0, policy_version 12880 (0.0006) -[2023-07-08 21:54:08,716][1084893] Fps is (10 sec: 7372.7, 60 sec: 7304.5, 300 sec: 7386.7). Total num frames: 6623232. Throughput: 0: 7345.6. Samples: 6609668. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:54:08,718][1084893] Avg episode reward: [(0, '580.180')] -[2023-07-08 21:54:10,416][1085161] Updated weights for policy 0, policy_version 12960 (0.0005) -[2023-07-08 21:54:13,716][1084893] Fps is (10 sec: 7372.7, 60 sec: 7372.8, 300 sec: 7372.8). Total num frames: 6660096. Throughput: 0: 7253.6. Samples: 6652184. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:54:13,872][1084893] Avg episode reward: [(0, '583.316')] -[2023-07-08 21:54:15,950][1085161] Updated weights for policy 0, policy_version 13040 (0.0005) -[2023-07-08 21:54:18,717][1084893] Fps is (10 sec: 7372.7, 60 sec: 7372.8, 300 sec: 7372.8). Total num frames: 6696960. Throughput: 0: 7319.3. Samples: 6697024. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:54:18,717][1084893] Avg episode reward: [(0, '581.221')] -[2023-07-08 21:54:18,720][1085148] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000013080_6696960.pth... -[2023-07-08 21:54:18,722][1085148] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000012648_6475776.pth -[2023-07-08 21:54:21,631][1085161] Updated weights for policy 0, policy_version 13120 (0.0005) -[2023-07-08 21:54:23,716][1084893] Fps is (10 sec: 6963.2, 60 sec: 7304.5, 300 sec: 7372.8). Total num frames: 6729728. Throughput: 0: 7289.0. Samples: 6717836. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:54:23,717][1084893] Avg episode reward: [(0, '573.723')] -[2023-07-08 21:54:26,926][1085161] Updated weights for policy 0, policy_version 13200 (0.0005) -[2023-07-08 21:54:28,716][1084893] Fps is (10 sec: 7372.9, 60 sec: 7372.8, 300 sec: 7386.7). Total num frames: 6770688. Throughput: 0: 7323.3. Samples: 6764364. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-07-08 21:54:28,717][1084893] Avg episode reward: [(0, '559.090')] -[2023-07-08 21:54:32,451][1085161] Updated weights for policy 0, policy_version 13280 (0.0006) -[2023-07-08 21:54:33,716][1084893] Fps is (10 sec: 7782.3, 60 sec: 7372.8, 300 sec: 7386.7). Total num frames: 6807552. Throughput: 0: 7381.5. Samples: 6809764. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-07-08 21:54:33,717][1084893] Avg episode reward: [(0, '578.257')] -[2023-07-08 21:54:33,721][1085148] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000013296_6807552.pth... -[2023-07-08 21:54:33,724][1085148] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000012864_6586368.pth -[2023-07-08 21:54:37,844][1085161] Updated weights for policy 0, policy_version 13360 (0.0005) -[2023-07-08 21:54:38,716][1084893] Fps is (10 sec: 7372.8, 60 sec: 7304.5, 300 sec: 7386.7). Total num frames: 6844416. Throughput: 0: 7331.5. Samples: 6832140. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:54:38,717][1084893] Avg episode reward: [(0, '579.849')] -[2023-07-08 21:54:43,376][1085161] Updated weights for policy 0, policy_version 13440 (0.0005) -[2023-07-08 21:54:43,716][1084893] Fps is (10 sec: 7372.8, 60 sec: 7372.8, 300 sec: 7386.7). Total num frames: 6881280. Throughput: 0: 7370.0. Samples: 6877124. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:54:43,717][1084893] Avg episode reward: [(0, '579.044')] -[2023-07-08 21:54:48,716][1084893] Fps is (10 sec: 7372.8, 60 sec: 7372.8, 300 sec: 7386.7). Total num frames: 6918144. Throughput: 0: 7390.7. Samples: 6921108. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:54:48,717][1084893] Avg episode reward: [(0, '574.950')] -[2023-07-08 21:54:48,720][1085148] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000013512_6918144.pth... -[2023-07-08 21:54:48,723][1085148] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000013080_6696960.pth -[2023-07-08 21:54:48,959][1085161] Updated weights for policy 0, policy_version 13520 (0.0005) -[2023-07-08 21:54:53,716][1084893] Fps is (10 sec: 6963.2, 60 sec: 7304.5, 300 sec: 7358.9). Total num frames: 6950912. Throughput: 0: 7368.9. Samples: 6941268. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:54:53,717][1084893] Avg episode reward: [(0, '571.308')] -[2023-07-08 21:54:54,900][1085161] Updated weights for policy 0, policy_version 13600 (0.0005) -[2023-07-08 21:54:58,716][1084893] Fps is (10 sec: 6963.2, 60 sec: 7304.5, 300 sec: 7358.9). Total num frames: 6987776. Throughput: 0: 7353.8. Samples: 6983104. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-07-08 21:54:58,717][1084893] Avg episode reward: [(0, '564.457')] -[2023-07-08 21:55:00,773][1085161] Updated weights for policy 0, policy_version 13680 (0.0005) -[2023-07-08 21:55:03,716][1084893] Fps is (10 sec: 7372.8, 60 sec: 7304.5, 300 sec: 7358.9). Total num frames: 7024640. Throughput: 0: 7295.4. Samples: 7025316. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-07-08 21:55:03,717][1084893] Avg episode reward: [(0, '568.526')] -[2023-07-08 21:55:03,720][1085148] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000013720_7024640.pth... -[2023-07-08 21:55:03,723][1085148] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000013296_6807552.pth -[2023-07-08 21:55:06,484][1085161] Updated weights for policy 0, policy_version 13760 (0.0005) -[2023-07-08 21:55:08,716][1084893] Fps is (10 sec: 7372.8, 60 sec: 7304.5, 300 sec: 7358.9). Total num frames: 7061504. Throughput: 0: 7312.9. Samples: 7046916. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:55:08,717][1084893] Avg episode reward: [(0, '572.251')] -[2023-07-08 21:55:11,983][1085161] Updated weights for policy 0, policy_version 13840 (0.0006) -[2023-07-08 21:55:13,716][1084893] Fps is (10 sec: 7372.8, 60 sec: 7304.5, 300 sec: 7358.9). Total num frames: 7098368. Throughput: 0: 7274.4. Samples: 7091712. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:55:13,717][1084893] Avg episode reward: [(0, '571.036')] -[2023-07-08 21:55:17,303][1085161] Updated weights for policy 0, policy_version 13920 (0.0005) -[2023-07-08 21:55:18,716][1084893] Fps is (10 sec: 7372.8, 60 sec: 7304.5, 300 sec: 7358.9). Total num frames: 7135232. Throughput: 0: 7285.2. Samples: 7137596. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-07-08 21:55:18,717][1084893] Avg episode reward: [(0, '583.900')] -[2023-07-08 21:55:18,720][1085148] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000013936_7135232.pth... -[2023-07-08 21:55:18,723][1085148] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000013512_6918144.pth -[2023-07-08 21:55:22,786][1085161] Updated weights for policy 0, policy_version 14000 (0.0005) -[2023-07-08 21:55:23,716][1084893] Fps is (10 sec: 7372.9, 60 sec: 7372.8, 300 sec: 7358.9). Total num frames: 7172096. Throughput: 0: 7281.7. Samples: 7159816. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-07-08 21:55:23,717][1084893] Avg episode reward: [(0, '579.064')] -[2023-07-08 21:55:28,585][1085161] Updated weights for policy 0, policy_version 14080 (0.0005) -[2023-07-08 21:55:28,716][1084893] Fps is (10 sec: 7372.8, 60 sec: 7304.5, 300 sec: 7358.9). Total num frames: 7208960. Throughput: 0: 7235.8. Samples: 7202736. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:55:28,717][1084893] Avg episode reward: [(0, '574.205')] -[2023-07-08 21:55:33,716][1084893] Fps is (10 sec: 7372.7, 60 sec: 7304.5, 300 sec: 7358.9). Total num frames: 7245824. Throughput: 0: 7258.5. Samples: 7247740. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:55:33,717][1084893] Avg episode reward: [(0, '577.870')] -[2023-07-08 21:55:33,720][1085148] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000014152_7245824.pth... -[2023-07-08 21:55:33,723][1085148] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000013720_7024640.pth -[2023-07-08 21:55:34,037][1085161] Updated weights for policy 0, policy_version 14160 (0.0005) -[2023-07-08 21:55:38,716][1084893] Fps is (10 sec: 7372.8, 60 sec: 7304.5, 300 sec: 7358.9). Total num frames: 7282688. Throughput: 0: 7319.8. Samples: 7270660. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:55:38,717][1084893] Avg episode reward: [(0, '579.804')] -[2023-07-08 21:55:39,389][1085161] Updated weights for policy 0, policy_version 14240 (0.0005) -[2023-07-08 21:55:43,716][1084893] Fps is (10 sec: 7372.8, 60 sec: 7304.5, 300 sec: 7358.9). Total num frames: 7319552. Throughput: 0: 7385.5. Samples: 7315452. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:55:43,717][1084893] Avg episode reward: [(0, '577.880')] -[2023-07-08 21:55:45,062][1085161] Updated weights for policy 0, policy_version 14320 (0.0005) -[2023-07-08 21:55:48,716][1084893] Fps is (10 sec: 7372.8, 60 sec: 7304.5, 300 sec: 7358.9). Total num frames: 7356416. Throughput: 0: 7427.2. Samples: 7359540. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:55:48,717][1084893] Avg episode reward: [(0, '580.649')] -[2023-07-08 21:55:48,719][1085148] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000014368_7356416.pth... -[2023-07-08 21:55:48,722][1085148] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000013936_7135232.pth -[2023-07-08 21:55:50,767][1085161] Updated weights for policy 0, policy_version 14400 (0.0006) -[2023-07-08 21:55:53,716][1084893] Fps is (10 sec: 6963.2, 60 sec: 7304.5, 300 sec: 7331.1). Total num frames: 7389184. Throughput: 0: 7402.0. Samples: 7380004. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-07-08 21:55:53,717][1084893] Avg episode reward: [(0, '583.846')] -[2023-07-08 21:55:56,896][1085161] Updated weights for policy 0, policy_version 14480 (0.0005) -[2023-07-08 21:55:58,717][1084893] Fps is (10 sec: 6963.2, 60 sec: 7304.5, 300 sec: 7331.1). Total num frames: 7426048. Throughput: 0: 7305.2. Samples: 7420444. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-07-08 21:55:58,717][1084893] Avg episode reward: [(0, '580.424')] -[2023-07-08 21:56:02,690][1085161] Updated weights for policy 0, policy_version 14560 (0.0005) -[2023-07-08 21:56:03,716][1084893] Fps is (10 sec: 6963.2, 60 sec: 7236.3, 300 sec: 7317.3). Total num frames: 7458816. Throughput: 0: 7212.6. Samples: 7462164. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:56:03,717][1084893] Avg episode reward: [(0, '578.534')] -[2023-07-08 21:56:03,719][1085148] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000014568_7458816.pth... -[2023-07-08 21:56:03,721][1085148] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000014152_7245824.pth -[2023-07-08 21:56:08,445][1085161] Updated weights for policy 0, policy_version 14640 (0.0005) -[2023-07-08 21:56:08,716][1084893] Fps is (10 sec: 6963.2, 60 sec: 7236.3, 300 sec: 7303.4). Total num frames: 7495680. Throughput: 0: 7189.2. Samples: 7483332. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:56:08,717][1084893] Avg episode reward: [(0, '582.247')] -[2023-07-08 21:56:13,716][1084893] Fps is (10 sec: 6963.2, 60 sec: 7168.0, 300 sec: 7289.5). Total num frames: 7528448. Throughput: 0: 7152.9. Samples: 7524616. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:56:13,717][1084893] Avg episode reward: [(0, '580.642')] -[2023-07-08 21:56:14,289][1085161] Updated weights for policy 0, policy_version 14720 (0.0005) -[2023-07-08 21:56:18,716][1084893] Fps is (10 sec: 7372.8, 60 sec: 7236.3, 300 sec: 7303.4). Total num frames: 7569408. Throughput: 0: 7155.2. Samples: 7569724. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:56:18,717][1084893] Avg episode reward: [(0, '578.448')] -[2023-07-08 21:56:18,720][1085148] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000014784_7569408.pth... -[2023-07-08 21:56:18,722][1085148] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000014368_7356416.pth -[2023-07-08 21:56:19,631][1085161] Updated weights for policy 0, policy_version 14800 (0.0005) -[2023-07-08 21:56:23,716][1084893] Fps is (10 sec: 7782.4, 60 sec: 7236.3, 300 sec: 7303.4). Total num frames: 7606272. Throughput: 0: 7167.0. Samples: 7593176. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-07-08 21:56:23,717][1084893] Avg episode reward: [(0, '581.081')] -[2023-07-08 21:56:25,266][1085161] Updated weights for policy 0, policy_version 14880 (0.0006) -[2023-07-08 21:56:28,716][1084893] Fps is (10 sec: 7372.8, 60 sec: 7236.3, 300 sec: 7303.4). Total num frames: 7643136. Throughput: 0: 7128.7. Samples: 7636244. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-07-08 21:56:28,717][1084893] Avg episode reward: [(0, '581.459')] -[2023-07-08 21:56:30,791][1085161] Updated weights for policy 0, policy_version 14960 (0.0005) -[2023-07-08 21:56:33,716][1084893] Fps is (10 sec: 7372.8, 60 sec: 7236.3, 300 sec: 7303.4). Total num frames: 7680000. Throughput: 0: 7175.4. Samples: 7682432. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-07-08 21:56:33,717][1084893] Avg episode reward: [(0, '570.901')] -[2023-07-08 21:56:33,720][1085148] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000015000_7680000.pth... -[2023-07-08 21:56:33,722][1085148] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000014568_7458816.pth -[2023-07-08 21:56:36,296][1085161] Updated weights for policy 0, policy_version 15040 (0.0006) -[2023-07-08 21:56:38,716][1084893] Fps is (10 sec: 7372.8, 60 sec: 7236.3, 300 sec: 7303.4). Total num frames: 7716864. Throughput: 0: 7205.6. Samples: 7704256. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-07-08 21:56:38,717][1084893] Avg episode reward: [(0, '576.620')] -[2023-07-08 21:56:42,032][1085161] Updated weights for policy 0, policy_version 15120 (0.0005) -[2023-07-08 21:56:43,716][1084893] Fps is (10 sec: 6963.2, 60 sec: 7168.0, 300 sec: 7303.4). Total num frames: 7749632. Throughput: 0: 7226.0. Samples: 7745616. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-07-08 21:56:43,717][1084893] Avg episode reward: [(0, '581.599')] -[2023-07-08 21:56:47,778][1085161] Updated weights for policy 0, policy_version 15200 (0.0005) -[2023-07-08 21:56:48,716][1084893] Fps is (10 sec: 6963.2, 60 sec: 7168.0, 300 sec: 7303.4). Total num frames: 7786496. Throughput: 0: 7271.5. Samples: 7789380. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:56:48,717][1084893] Avg episode reward: [(0, '585.378')] -[2023-07-08 21:56:48,720][1085148] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000015208_7786496.pth... -[2023-07-08 21:56:48,723][1085148] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000014784_7569408.pth -[2023-07-08 21:56:53,626][1085161] Updated weights for policy 0, policy_version 15280 (0.0005) -[2023-07-08 21:56:53,717][1084893] Fps is (10 sec: 7372.8, 60 sec: 7236.3, 300 sec: 7303.4). Total num frames: 7823360. Throughput: 0: 7278.3. Samples: 7810856. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:56:53,717][1084893] Avg episode reward: [(0, '581.757')] -[2023-07-08 21:56:58,717][1084893] Fps is (10 sec: 7372.7, 60 sec: 7236.3, 300 sec: 7303.4). Total num frames: 7860224. Throughput: 0: 7306.7. Samples: 7853420. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:56:58,717][1084893] Avg episode reward: [(0, '578.852')] -[2023-07-08 21:56:59,255][1085161] Updated weights for policy 0, policy_version 15360 (0.0005) -[2023-07-08 21:57:03,717][1084893] Fps is (10 sec: 7372.7, 60 sec: 7304.5, 300 sec: 7289.5). Total num frames: 7897088. Throughput: 0: 7286.6. Samples: 7897620. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:57:03,717][1084893] Avg episode reward: [(0, '583.144')] -[2023-07-08 21:57:03,720][1085148] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000015424_7897088.pth... -[2023-07-08 21:57:03,722][1085148] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000015000_7680000.pth -[2023-07-08 21:57:04,704][1085161] Updated weights for policy 0, policy_version 15440 (0.0004) -[2023-07-08 21:57:08,716][1084893] Fps is (10 sec: 7372.9, 60 sec: 7304.5, 300 sec: 7303.4). Total num frames: 7933952. Throughput: 0: 7287.6. Samples: 7921116. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-07-08 21:57:08,717][1084893] Avg episode reward: [(0, '578.515')] -[2023-07-08 21:57:10,168][1085161] Updated weights for policy 0, policy_version 15520 (0.0005) -[2023-07-08 21:57:13,717][1084893] Fps is (10 sec: 7372.8, 60 sec: 7372.8, 300 sec: 7303.4). Total num frames: 7970816. Throughput: 0: 7275.1. Samples: 7963624. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-07-08 21:57:13,717][1084893] Avg episode reward: [(0, '574.994')] -[2023-07-08 21:57:15,715][1085161] Updated weights for policy 0, policy_version 15600 (0.0005) -[2023-07-08 21:57:18,716][1084893] Fps is (10 sec: 7372.8, 60 sec: 7304.5, 300 sec: 7303.4). Total num frames: 8007680. Throughput: 0: 7275.7. Samples: 8009840. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:57:18,717][1084893] Avg episode reward: [(0, '574.504')] -[2023-07-08 21:57:18,720][1085148] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000015640_8007680.pth... -[2023-07-08 21:57:18,723][1085148] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000015208_7786496.pth -[2023-07-08 21:57:21,092][1085161] Updated weights for policy 0, policy_version 15680 (0.0005) -[2023-07-08 21:57:23,716][1084893] Fps is (10 sec: 7782.5, 60 sec: 7372.8, 300 sec: 7317.3). Total num frames: 8048640. Throughput: 0: 7308.7. Samples: 8033148. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:57:23,717][1084893] Avg episode reward: [(0, '582.656')] -[2023-07-08 21:57:26,539][1085161] Updated weights for policy 0, policy_version 15760 (0.0006) -[2023-07-08 21:57:28,716][1084893] Fps is (10 sec: 7782.5, 60 sec: 7372.8, 300 sec: 7317.3). Total num frames: 8085504. Throughput: 0: 7419.6. Samples: 8079496. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:57:28,717][1084893] Avg episode reward: [(0, '583.171')] -[2023-07-08 21:57:31,690][1085161] Updated weights for policy 0, policy_version 15840 (0.0005) -[2023-07-08 21:57:33,716][1084893] Fps is (10 sec: 7372.9, 60 sec: 7372.8, 300 sec: 7317.3). Total num frames: 8122368. Throughput: 0: 7475.1. Samples: 8125760. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:57:33,717][1084893] Avg episode reward: [(0, '586.885')] -[2023-07-08 21:57:33,719][1085148] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000015864_8122368.pth... -[2023-07-08 21:57:33,721][1085148] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000015424_7897088.pth -[2023-07-08 21:57:37,729][1085161] Updated weights for policy 0, policy_version 15920 (0.0004) -[2023-07-08 21:57:38,716][1084893] Fps is (10 sec: 6963.2, 60 sec: 7304.5, 300 sec: 7289.5). Total num frames: 8155136. Throughput: 0: 7420.0. Samples: 8144756. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:57:38,717][1084893] Avg episode reward: [(0, '577.046')] -[2023-07-08 21:57:43,239][1085161] Updated weights for policy 0, policy_version 16000 (0.0005) -[2023-07-08 21:57:43,716][1084893] Fps is (10 sec: 6963.1, 60 sec: 7372.8, 300 sec: 7303.4). Total num frames: 8192000. Throughput: 0: 7437.6. Samples: 8188112. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:57:43,717][1084893] Avg episode reward: [(0, '580.326')] -[2023-07-08 21:57:48,717][1084893] Fps is (10 sec: 7372.7, 60 sec: 7372.8, 300 sec: 7303.4). Total num frames: 8228864. Throughput: 0: 7423.8. Samples: 8231692. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:57:48,717][1084893] Avg episode reward: [(0, '579.179')] -[2023-07-08 21:57:48,720][1085148] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000016072_8228864.pth... -[2023-07-08 21:57:48,723][1085148] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000015640_8007680.pth -[2023-07-08 21:57:48,939][1085161] Updated weights for policy 0, policy_version 16080 (0.0005) -[2023-07-08 21:57:53,716][1084893] Fps is (10 sec: 7782.4, 60 sec: 7441.1, 300 sec: 7331.1). Total num frames: 8269824. Throughput: 0: 7406.7. Samples: 8254416. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:57:53,717][1084893] Avg episode reward: [(0, '583.784')] -[2023-07-08 21:57:54,074][1085161] Updated weights for policy 0, policy_version 16160 (0.0006) -[2023-07-08 21:57:58,716][1084893] Fps is (10 sec: 7782.5, 60 sec: 7441.1, 300 sec: 7317.3). Total num frames: 8306688. Throughput: 0: 7530.2. Samples: 8302480. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:57:58,717][1084893] Avg episode reward: [(0, '587.161')] -[2023-07-08 21:57:59,670][1085161] Updated weights for policy 0, policy_version 16240 (0.0005) -[2023-07-08 21:58:03,716][1084893] Fps is (10 sec: 6963.3, 60 sec: 7372.8, 300 sec: 7303.4). Total num frames: 8339456. Throughput: 0: 7413.1. Samples: 8343428. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:58:03,717][1084893] Avg episode reward: [(0, '582.752')] -[2023-07-08 21:58:03,719][1085148] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000016288_8339456.pth... -[2023-07-08 21:58:03,721][1085148] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000015864_8122368.pth -[2023-07-08 21:58:05,453][1085161] Updated weights for policy 0, policy_version 16320 (0.0005) -[2023-07-08 21:58:08,717][1084893] Fps is (10 sec: 6963.1, 60 sec: 7372.8, 300 sec: 7317.3). Total num frames: 8376320. Throughput: 0: 7361.1. Samples: 8364396. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:58:08,717][1084893] Avg episode reward: [(0, '582.319')] -[2023-07-08 21:58:11,201][1085161] Updated weights for policy 0, policy_version 16400 (0.0005) -[2023-07-08 21:58:13,716][1084893] Fps is (10 sec: 7372.8, 60 sec: 7372.8, 300 sec: 7317.3). Total num frames: 8413184. Throughput: 0: 7301.8. Samples: 8408076. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:58:13,717][1084893] Avg episode reward: [(0, '580.768')] -[2023-07-08 21:58:17,149][1085161] Updated weights for policy 0, policy_version 16480 (0.0005) -[2023-07-08 21:58:18,716][1084893] Fps is (10 sec: 6963.2, 60 sec: 7304.5, 300 sec: 7303.4). Total num frames: 8445952. Throughput: 0: 7199.0. Samples: 8449716. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:58:18,717][1084893] Avg episode reward: [(0, '581.631')] -[2023-07-08 21:58:18,720][1085148] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000016496_8445952.pth... -[2023-07-08 21:58:18,722][1085148] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000016072_8228864.pth -[2023-07-08 21:58:23,135][1085161] Updated weights for policy 0, policy_version 16560 (0.0005) -[2023-07-08 21:58:23,716][1084893] Fps is (10 sec: 6553.6, 60 sec: 7168.0, 300 sec: 7289.5). Total num frames: 8478720. Throughput: 0: 7230.3. Samples: 8470120. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:58:23,717][1084893] Avg episode reward: [(0, '574.222')] -[2023-07-08 21:58:28,716][1084893] Fps is (10 sec: 6963.2, 60 sec: 7168.0, 300 sec: 7289.5). Total num frames: 8515584. Throughput: 0: 7194.3. Samples: 8511856. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-07-08 21:58:28,717][1084893] Avg episode reward: [(0, '585.875')] -[2023-07-08 21:58:28,735][1085161] Updated weights for policy 0, policy_version 16640 (0.0006) -[2023-07-08 21:58:33,716][1084893] Fps is (10 sec: 7782.4, 60 sec: 7236.3, 300 sec: 7289.5). Total num frames: 8556544. Throughput: 0: 7246.1. Samples: 8557764. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-07-08 21:58:33,717][1084893] Avg episode reward: [(0, '586.012')] -[2023-07-08 21:58:33,719][1085148] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000016712_8556544.pth... -[2023-07-08 21:58:33,722][1085148] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000016288_8339456.pth -[2023-07-08 21:58:34,021][1085161] Updated weights for policy 0, policy_version 16720 (0.0005) -[2023-07-08 21:58:38,716][1084893] Fps is (10 sec: 7782.4, 60 sec: 7304.5, 300 sec: 7303.4). Total num frames: 8593408. Throughput: 0: 7268.0. Samples: 8581476. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-07-08 21:58:38,717][1084893] Avg episode reward: [(0, '586.148')] -[2023-07-08 21:58:39,267][1085161] Updated weights for policy 0, policy_version 16800 (0.0005) -[2023-07-08 21:58:43,716][1084893] Fps is (10 sec: 7782.4, 60 sec: 7372.8, 300 sec: 7317.3). Total num frames: 8634368. Throughput: 0: 7234.9. Samples: 8628048. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:58:43,717][1084893] Avg episode reward: [(0, '578.715')] -[2023-07-08 21:58:44,784][1085161] Updated weights for policy 0, policy_version 16880 (0.0005) -[2023-07-08 21:58:48,717][1084893] Fps is (10 sec: 7782.3, 60 sec: 7372.8, 300 sec: 7317.3). Total num frames: 8671232. Throughput: 0: 7347.5. Samples: 8674068. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:58:48,717][1084893] Avg episode reward: [(0, '577.741')] -[2023-07-08 21:58:48,720][1085148] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000016936_8671232.pth... -[2023-07-08 21:58:48,723][1085148] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000016496_8445952.pth -[2023-07-08 21:58:50,146][1085161] Updated weights for policy 0, policy_version 16960 (0.0005) -[2023-07-08 21:58:53,716][1084893] Fps is (10 sec: 7372.7, 60 sec: 7304.5, 300 sec: 7317.3). Total num frames: 8708096. Throughput: 0: 7361.0. Samples: 8695640. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:58:53,717][1084893] Avg episode reward: [(0, '583.470')] -[2023-07-08 21:58:55,670][1085161] Updated weights for policy 0, policy_version 17040 (0.0005) -[2023-07-08 21:58:58,716][1084893] Fps is (10 sec: 6963.3, 60 sec: 7236.3, 300 sec: 7303.4). Total num frames: 8740864. Throughput: 0: 7336.7. Samples: 8738228. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:58:58,717][1084893] Avg episode reward: [(0, '590.742')] -[2023-07-08 21:58:58,717][1085148] Saving new best policy, reward=590.742! -[2023-07-08 21:59:01,525][1085161] Updated weights for policy 0, policy_version 17120 (0.0005) -[2023-07-08 21:59:03,716][1084893] Fps is (10 sec: 6963.3, 60 sec: 7304.5, 300 sec: 7303.4). Total num frames: 8777728. Throughput: 0: 6894.2. Samples: 8759956. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:59:03,717][1084893] Avg episode reward: [(0, '580.947')] -[2023-07-08 21:59:03,720][1085148] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000017152_8781824.pth... -[2023-07-08 21:59:03,723][1085148] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000016712_8556544.pth -[2023-07-08 21:59:07,019][1085161] Updated weights for policy 0, policy_version 17200 (0.0005) -[2023-07-08 21:59:08,716][1084893] Fps is (10 sec: 7372.8, 60 sec: 7304.5, 300 sec: 7303.4). Total num frames: 8814592. Throughput: 0: 7423.3. Samples: 8804168. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:59:08,717][1084893] Avg episode reward: [(0, '580.984')] -[2023-07-08 21:59:12,611][1085161] Updated weights for policy 0, policy_version 17280 (0.0005) -[2023-07-08 21:59:13,716][1084893] Fps is (10 sec: 7782.3, 60 sec: 7372.8, 300 sec: 7317.3). Total num frames: 8855552. Throughput: 0: 7468.1. Samples: 8847920. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:59:13,717][1084893] Avg episode reward: [(0, '584.191')] -[2023-07-08 21:59:18,058][1085161] Updated weights for policy 0, policy_version 17360 (0.0005) -[2023-07-08 21:59:18,717][1084893] Fps is (10 sec: 7782.3, 60 sec: 7441.1, 300 sec: 7331.1). Total num frames: 8892416. Throughput: 0: 7451.8. Samples: 8893096. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:59:18,717][1084893] Avg episode reward: [(0, '583.977')] -[2023-07-08 21:59:18,720][1085148] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000017368_8892416.pth... -[2023-07-08 21:59:18,723][1085148] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000016936_8671232.pth -[2023-07-08 21:59:23,639][1085161] Updated weights for policy 0, policy_version 17440 (0.0005) -[2023-07-08 21:59:23,717][1084893] Fps is (10 sec: 7372.7, 60 sec: 7509.3, 300 sec: 7317.3). Total num frames: 8929280. Throughput: 0: 7431.8. Samples: 8915908. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:59:23,717][1084893] Avg episode reward: [(0, '578.457')] -[2023-07-08 21:59:28,716][1084893] Fps is (10 sec: 6963.3, 60 sec: 7441.1, 300 sec: 7303.4). Total num frames: 8962048. Throughput: 0: 7332.8. Samples: 8958024. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 21:59:28,717][1084893] Avg episode reward: [(0, '582.969')] -[2023-07-08 21:59:29,480][1085161] Updated weights for policy 0, policy_version 17520 (0.0005) -[2023-07-08 21:59:33,716][1084893] Fps is (10 sec: 6963.3, 60 sec: 7372.8, 300 sec: 7303.4). Total num frames: 8998912. Throughput: 0: 7277.5. Samples: 9001556. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-07-08 21:59:33,717][1084893] Avg episode reward: [(0, '577.332')] -[2023-07-08 21:59:33,719][1085148] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000017576_8998912.pth... -[2023-07-08 21:59:33,722][1085148] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000017152_8781824.pth -[2023-07-08 21:59:35,107][1085161] Updated weights for policy 0, policy_version 17600 (0.0005) -[2023-07-08 21:59:38,716][1084893] Fps is (10 sec: 7372.8, 60 sec: 7372.8, 300 sec: 7303.4). Total num frames: 9035776. Throughput: 0: 7285.3. Samples: 9023480. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-07-08 21:59:38,717][1084893] Avg episode reward: [(0, '579.262')] -[2023-07-08 21:59:40,733][1085161] Updated weights for policy 0, policy_version 17680 (0.0004) -[2023-07-08 21:59:43,716][1084893] Fps is (10 sec: 7372.8, 60 sec: 7304.5, 300 sec: 7303.4). Total num frames: 9072640. Throughput: 0: 7321.5. Samples: 9067696. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-07-08 21:59:43,717][1084893] Avg episode reward: [(0, '579.926')] -[2023-07-08 21:59:46,308][1085161] Updated weights for policy 0, policy_version 17760 (0.0005) -[2023-07-08 21:59:48,716][1084893] Fps is (10 sec: 7372.8, 60 sec: 7304.6, 300 sec: 7317.3). Total num frames: 9109504. Throughput: 0: 7804.1. Samples: 9111140. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-07-08 21:59:48,717][1084893] Avg episode reward: [(0, '582.432')] -[2023-07-08 21:59:48,720][1085148] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000017792_9109504.pth... -[2023-07-08 21:59:48,723][1085148] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000017368_8892416.pth -[2023-07-08 21:59:51,657][1085161] Updated weights for policy 0, policy_version 17840 (0.0005) -[2023-07-08 21:59:53,716][1084893] Fps is (10 sec: 7782.5, 60 sec: 7372.8, 300 sec: 7331.1). Total num frames: 9150464. Throughput: 0: 7336.0. Samples: 9134288. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-07-08 21:59:53,718][1084893] Avg episode reward: [(0, '581.867')] -[2023-07-08 21:59:56,571][1085161] Updated weights for policy 0, policy_version 17920 (0.0005) -[2023-07-08 21:59:58,716][1084893] Fps is (10 sec: 8192.0, 60 sec: 7509.3, 300 sec: 7345.0). Total num frames: 9191424. Throughput: 0: 7456.3. Samples: 9183452. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-07-08 21:59:58,717][1084893] Avg episode reward: [(0, '583.155')] -[2023-07-08 22:00:01,767][1085161] Updated weights for policy 0, policy_version 18000 (0.0005) -[2023-07-08 22:00:03,717][1084893] Fps is (10 sec: 7782.2, 60 sec: 7509.3, 300 sec: 7345.0). Total num frames: 9228288. Throughput: 0: 7483.7. Samples: 9229864. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-07-08 22:00:03,718][1084893] Avg episode reward: [(0, '574.984')] -[2023-07-08 22:00:03,721][1085148] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000018024_9228288.pth... -[2023-07-08 22:00:03,723][1085148] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000017576_8998912.pth -[2023-07-08 22:00:07,415][1085161] Updated weights for policy 0, policy_version 18080 (0.0005) -[2023-07-08 22:00:08,716][1084893] Fps is (10 sec: 7372.8, 60 sec: 7509.3, 300 sec: 7345.0). Total num frames: 9265152. Throughput: 0: 7467.6. Samples: 9251948. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 22:00:08,718][1084893] Avg episode reward: [(0, '575.009')] -[2023-07-08 22:00:12,873][1085161] Updated weights for policy 0, policy_version 18160 (0.0005) -[2023-07-08 22:00:13,716][1084893] Fps is (10 sec: 7372.9, 60 sec: 7441.1, 300 sec: 7345.0). Total num frames: 9302016. Throughput: 0: 7539.5. Samples: 9297300. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 22:00:13,717][1084893] Avg episode reward: [(0, '576.531')] -[2023-07-08 22:00:18,428][1085161] Updated weights for policy 0, policy_version 18240 (0.0005) -[2023-07-08 22:00:18,717][1084893] Fps is (10 sec: 7372.8, 60 sec: 7441.1, 300 sec: 7345.0). Total num frames: 9338880. Throughput: 0: 7549.2. Samples: 9341272. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 22:00:18,718][1084893] Avg episode reward: [(0, '584.503')] -[2023-07-08 22:00:18,720][1085148] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000018240_9338880.pth... -[2023-07-08 22:00:18,723][1085148] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000017792_9109504.pth -[2023-07-08 22:00:23,716][1084893] Fps is (10 sec: 7372.9, 60 sec: 7441.1, 300 sec: 7345.0). Total num frames: 9375744. Throughput: 0: 7554.2. Samples: 9363420. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 22:00:23,717][1084893] Avg episode reward: [(0, '573.948')] -[2023-07-08 22:00:24,004][1085161] Updated weights for policy 0, policy_version 18320 (0.0006) -[2023-07-08 22:00:28,716][1084893] Fps is (10 sec: 7372.9, 60 sec: 7509.3, 300 sec: 7345.0). Total num frames: 9412608. Throughput: 0: 7562.8. Samples: 9408020. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 22:00:28,717][1084893] Avg episode reward: [(0, '582.052')] -[2023-07-08 22:00:29,520][1085161] Updated weights for policy 0, policy_version 18400 (0.0005) -[2023-07-08 22:00:33,716][1084893] Fps is (10 sec: 7372.8, 60 sec: 7509.3, 300 sec: 7345.0). Total num frames: 9449472. Throughput: 0: 7545.5. Samples: 9450688. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-07-08 22:00:33,718][1084893] Avg episode reward: [(0, '579.900')] -[2023-07-08 22:00:33,720][1085148] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000018456_9449472.pth... -[2023-07-08 22:00:33,723][1085148] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000018024_9228288.pth -[2023-07-08 22:00:35,168][1085161] Updated weights for policy 0, policy_version 18480 (0.0005) -[2023-07-08 22:00:38,716][1084893] Fps is (10 sec: 7372.8, 60 sec: 7509.3, 300 sec: 7345.0). Total num frames: 9486336. Throughput: 0: 7550.2. Samples: 9474048. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-07-08 22:00:38,718][1084893] Avg episode reward: [(0, '583.472')] -[2023-07-08 22:00:40,643][1085161] Updated weights for policy 0, policy_version 18560 (0.0005) -[2023-07-08 22:00:43,716][1084893] Fps is (10 sec: 7372.8, 60 sec: 7509.3, 300 sec: 7345.0). Total num frames: 9523200. Throughput: 0: 7441.9. Samples: 9518340. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-07-08 22:00:43,717][1084893] Avg episode reward: [(0, '580.710')] -[2023-07-08 22:00:46,068][1085161] Updated weights for policy 0, policy_version 18640 (0.0005) -[2023-07-08 22:00:48,716][1084893] Fps is (10 sec: 7372.8, 60 sec: 7509.3, 300 sec: 7358.9). Total num frames: 9560064. Throughput: 0: 6930.2. Samples: 9541724. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-07-08 22:00:48,717][1084893] Avg episode reward: [(0, '578.725')] -[2023-07-08 22:00:48,728][1085148] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000018680_9564160.pth... -[2023-07-08 22:00:48,730][1085148] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000018240_9338880.pth -[2023-07-08 22:00:51,483][1085161] Updated weights for policy 0, policy_version 18720 (0.0005) -[2023-07-08 22:00:53,716][1084893] Fps is (10 sec: 7372.8, 60 sec: 7441.1, 300 sec: 7358.9). Total num frames: 9596928. Throughput: 0: 7436.7. Samples: 9586600. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-07-08 22:00:53,717][1084893] Avg episode reward: [(0, '573.496')] -[2023-07-08 22:00:57,084][1085161] Updated weights for policy 0, policy_version 18800 (0.0006) -[2023-07-08 22:00:58,716][1084893] Fps is (10 sec: 7372.8, 60 sec: 7372.8, 300 sec: 7372.8). Total num frames: 9633792. Throughput: 0: 7388.0. Samples: 9629760. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-07-08 22:00:58,717][1084893] Avg episode reward: [(0, '567.757')] -[2023-07-08 22:01:02,994][1085161] Updated weights for policy 0, policy_version 18880 (0.0005) -[2023-07-08 22:01:03,717][1084893] Fps is (10 sec: 7372.7, 60 sec: 7372.8, 300 sec: 7372.8). Total num frames: 9670656. Throughput: 0: 7338.9. Samples: 9671524. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 22:01:03,717][1084893] Avg episode reward: [(0, '581.898')] -[2023-07-08 22:01:03,720][1085148] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000018888_9670656.pth... -[2023-07-08 22:01:03,723][1085148] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000018456_9449472.pth -[2023-07-08 22:01:08,716][1084893] Fps is (10 sec: 6963.2, 60 sec: 7304.5, 300 sec: 7372.8). Total num frames: 9703424. Throughput: 0: 7338.8. Samples: 9693668. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 22:01:08,717][1084893] Avg episode reward: [(0, '582.946')] -[2023-07-08 22:01:08,723][1085161] Updated weights for policy 0, policy_version 18960 (0.0005) -[2023-07-08 22:01:13,716][1084893] Fps is (10 sec: 6963.3, 60 sec: 7304.5, 300 sec: 7358.9). Total num frames: 9740288. Throughput: 0: 7297.2. Samples: 9736396. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 22:01:13,717][1084893] Avg episode reward: [(0, '579.669')] -[2023-07-08 22:01:14,381][1085161] Updated weights for policy 0, policy_version 19040 (0.0005) -[2023-07-08 22:01:18,717][1084893] Fps is (10 sec: 7372.7, 60 sec: 7304.5, 300 sec: 7358.9). Total num frames: 9777152. Throughput: 0: 7339.1. Samples: 9780948. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 22:01:18,717][1084893] Avg episode reward: [(0, '576.403')] -[2023-07-08 22:01:18,720][1085148] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000019096_9777152.pth... -[2023-07-08 22:01:18,722][1085148] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000018680_9564160.pth -[2023-07-08 22:01:19,905][1085161] Updated weights for policy 0, policy_version 19120 (0.0005) -[2023-07-08 22:01:23,716][1084893] Fps is (10 sec: 7372.8, 60 sec: 7304.5, 300 sec: 7358.9). Total num frames: 9814016. Throughput: 0: 7292.2. Samples: 9802196. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 22:01:23,717][1084893] Avg episode reward: [(0, '571.996')] -[2023-07-08 22:01:25,400][1085161] Updated weights for policy 0, policy_version 19200 (0.0005) -[2023-07-08 22:01:28,716][1084893] Fps is (10 sec: 7782.5, 60 sec: 7372.8, 300 sec: 7372.8). Total num frames: 9854976. Throughput: 0: 7346.4. Samples: 9848928. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 22:01:28,717][1084893] Avg episode reward: [(0, '581.489')] -[2023-07-08 22:01:30,593][1085161] Updated weights for policy 0, policy_version 19280 (0.0005) -[2023-07-08 22:01:33,716][1084893] Fps is (10 sec: 7782.4, 60 sec: 7372.8, 300 sec: 7372.8). Total num frames: 9891840. Throughput: 0: 7865.2. Samples: 9895656. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 22:01:33,717][1084893] Avg episode reward: [(0, '578.347')] -[2023-07-08 22:01:33,719][1085148] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000019320_9891840.pth... -[2023-07-08 22:01:33,721][1085148] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000018888_9670656.pth -[2023-07-08 22:01:36,169][1085161] Updated weights for policy 0, policy_version 19360 (0.0006) -[2023-07-08 22:01:38,716][1084893] Fps is (10 sec: 7372.8, 60 sec: 7372.8, 300 sec: 7386.7). Total num frames: 9928704. Throughput: 0: 7328.8. Samples: 9916396. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 22:01:38,717][1084893] Avg episode reward: [(0, '579.682')] -[2023-07-08 22:01:41,803][1085161] Updated weights for policy 0, policy_version 19440 (0.0004) -[2023-07-08 22:01:43,716][1084893] Fps is (10 sec: 7372.8, 60 sec: 7372.8, 300 sec: 7386.7). Total num frames: 9965568. Throughput: 0: 7332.8. Samples: 9959736. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) -[2023-07-08 22:01:43,717][1084893] Avg episode reward: [(0, '580.048')] -[2023-07-08 22:01:47,593][1085161] Updated weights for policy 0, policy_version 19520 (0.0005) -[2023-07-08 22:01:48,716][1084893] Fps is (10 sec: 7372.8, 60 sec: 7372.8, 300 sec: 7386.7). Total num frames: 10002432. Throughput: 0: 7363.7. Samples: 10002888. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) -[2023-07-08 22:01:48,717][1084893] Avg episode reward: [(0, '582.012')] -[2023-07-08 22:01:48,720][1085148] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000019536_10002432.pth... -[2023-07-08 22:01:48,723][1085148] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000019096_9777152.pth -[2023-07-08 22:01:49,090][1085148] Early stopping after 2 epochs (8 sgd steps), loss delta 0.0000000 -[2023-07-08 22:01:49,091][1085261] Stopping RolloutWorker_w4... -[2023-07-08 22:01:49,091][1085163] Stopping RolloutWorker_w1... -[2023-07-08 22:01:49,091][1085260] Stopping RolloutWorker_w5... -[2023-07-08 22:01:49,091][1085195] Stopping RolloutWorker_w2... -[2023-07-08 22:01:49,091][1085263] Stopping RolloutWorker_w7... -[2023-07-08 22:01:49,091][1085162] Stopping RolloutWorker_w0... -[2023-07-08 22:01:49,091][1085262] Stopping RolloutWorker_w6... -[2023-07-08 22:01:49,091][1085163] Loop rollout_proc1_evt_loop terminating... -[2023-07-08 22:01:49,091][1085260] Loop rollout_proc5_evt_loop terminating... -[2023-07-08 22:01:49,091][1085196] Stopping RolloutWorker_w3... -[2023-07-08 22:01:49,091][1085261] Loop rollout_proc4_evt_loop terminating... -[2023-07-08 22:01:49,091][1085162] Loop rollout_proc0_evt_loop terminating... -[2023-07-08 22:01:49,091][1085263] Loop rollout_proc7_evt_loop terminating... -[2023-07-08 22:01:49,091][1085195] Loop rollout_proc2_evt_loop terminating... -[2023-07-08 22:01:49,091][1085262] Loop rollout_proc6_evt_loop terminating... -[2023-07-08 22:01:49,091][1084893] Component RolloutWorker_w1 stopped! -[2023-07-08 22:01:49,091][1085196] Loop rollout_proc3_evt_loop terminating... -[2023-07-08 22:01:49,091][1085148] Stopping Batcher_0... -[2023-07-08 22:01:49,092][1085148] Loop batcher_evt_loop terminating... -[2023-07-08 22:01:49,092][1084893] Component RolloutWorker_w4 stopped! -[2023-07-08 22:01:49,092][1084893] Component RolloutWorker_w5 stopped! -[2023-07-08 22:01:49,092][1085148] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000019544_10006528.pth... -[2023-07-08 22:01:49,092][1084893] Component RolloutWorker_w2 stopped! -[2023-07-08 22:01:49,092][1084893] Component RolloutWorker_w7 stopped! -[2023-07-08 22:01:49,092][1084893] Component RolloutWorker_w6 stopped! -[2023-07-08 22:01:49,093][1084893] Component RolloutWorker_w0 stopped! -[2023-07-08 22:01:49,093][1084893] Component RolloutWorker_w3 stopped! -[2023-07-08 22:01:49,093][1084893] Component Batcher_0 stopped! -[2023-07-08 22:01:49,094][1085148] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000019320_9891840.pth -[2023-07-08 22:01:49,095][1085148] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000019544_10006528.pth... -[2023-07-08 22:01:49,097][1085148] Stopping LearnerWorker_p0... -[2023-07-08 22:01:49,098][1085148] Loop learner_proc0_evt_loop terminating... -[2023-07-08 22:01:49,097][1084893] Component LearnerWorker_p0 stopped! -[2023-07-08 22:01:49,175][1085161] Weights refcount: 2 0 -[2023-07-08 22:01:49,177][1085161] Stopping InferenceWorker_p0-w0... -[2023-07-08 22:01:49,177][1085161] Loop inference_proc0-0_evt_loop terminating... -[2023-07-08 22:01:49,177][1084893] Component InferenceWorker_p0-w0 stopped! -[2023-07-08 22:01:49,178][1084893] Waiting for process learner_proc0 to stop... -[2023-07-08 22:01:49,785][1084893] Waiting for process inference_proc0-0 to join... -[2023-07-08 22:01:49,823][1084893] Waiting for process rollout_proc0 to join... -[2023-07-08 22:01:49,824][1084893] Waiting for process rollout_proc1 to join... -[2023-07-08 22:01:49,824][1084893] Waiting for process rollout_proc2 to join... -[2023-07-08 22:01:49,824][1084893] Waiting for process rollout_proc3 to join... -[2023-07-08 22:01:49,824][1084893] Waiting for process rollout_proc4 to join... -[2023-07-08 22:01:49,825][1084893] Waiting for process rollout_proc5 to join... -[2023-07-08 22:01:49,825][1084893] Waiting for process rollout_proc6 to join... -[2023-07-08 22:01:49,825][1084893] Waiting for process rollout_proc7 to join... -[2023-07-08 22:01:49,825][1084893] Batcher 0 profile tree view: -batching: 1.8910, releasing_batches: 1.5737 -[2023-07-08 22:01:49,825][1084893] InferenceWorker_p0-w0 profile tree view: +[2023-07-17 01:41:06,941][291494] Worker 6 uses CPU cores [24, 25, 26, 27] +[2023-07-17 01:41:07,108][291493] Worker 4 uses CPU cores [16, 17, 18, 19] +[2023-07-17 01:41:07,130][291489] Worker 0 uses CPU cores [0, 1, 2, 3] +[2023-07-17 01:41:07,170][291491] Worker 3 uses CPU cores [12, 13, 14, 15] +[2023-07-17 01:41:07,223][291444] Using optimizer +[2023-07-17 01:41:07,224][291444] No checkpoints found +[2023-07-17 01:41:07,224][291444] Did not load from checkpoint, starting from scratch! +[2023-07-17 01:41:07,224][291444] Initialized policy 0 weights for model version 0 +[2023-07-17 01:41:07,226][291444] LearnerWorker_p0 finished initialization! +[2023-07-17 01:41:07,227][291488] RunningMeanStd input shape: (39,) +[2023-07-17 01:41:07,227][291488] RunningMeanStd input shape: (1,) +[2023-07-17 01:41:07,287][291207] Inference worker 0-0 is ready! +[2023-07-17 01:41:07,287][291207] All inference workers are ready! Signal rollout workers to start! +[2023-07-17 01:41:07,355][291526] Worker 5 uses CPU cores [20, 21, 22, 23] +[2023-07-17 01:41:07,381][291558] Worker 7 uses CPU cores [28, 29, 30, 31] +[2023-07-17 01:41:07,459][291490] Worker 1 uses CPU cores [4, 5, 6, 7] +[2023-07-17 01:41:07,583][291492] Worker 2 uses CPU cores [8, 9, 10, 11] +[2023-07-17 01:41:07,907][291207] Fps is (10 sec: nan, 60 sec: nan, 300 sec: nan). Total num frames: 0. Throughput: 0: nan. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) +[2023-07-17 01:41:08,619][291491] Decorrelating experience for 0 frames... +[2023-07-17 01:41:08,627][291491] Decorrelating experience for 64 frames... +[2023-07-17 01:41:08,629][291493] Decorrelating experience for 0 frames... +[2023-07-17 01:41:08,629][291489] Decorrelating experience for 0 frames... +[2023-07-17 01:41:08,633][291494] Decorrelating experience for 0 frames... +[2023-07-17 01:41:08,637][291493] Decorrelating experience for 64 frames... +[2023-07-17 01:41:08,638][291489] Decorrelating experience for 64 frames... +[2023-07-17 01:41:08,641][291494] Decorrelating experience for 64 frames... +[2023-07-17 01:41:08,662][291491] Decorrelating experience for 128 frames... +[2023-07-17 01:41:08,672][291493] Decorrelating experience for 128 frames... +[2023-07-17 01:41:08,672][291489] Decorrelating experience for 128 frames... +[2023-07-17 01:41:08,676][291494] Decorrelating experience for 128 frames... +[2023-07-17 01:41:08,732][291491] Decorrelating experience for 192 frames... +[2023-07-17 01:41:08,739][291489] Decorrelating experience for 192 frames... +[2023-07-17 01:41:08,745][291493] Decorrelating experience for 192 frames... +[2023-07-17 01:41:08,745][291494] Decorrelating experience for 192 frames... +[2023-07-17 01:41:08,757][291526] Decorrelating experience for 0 frames... +[2023-07-17 01:41:08,765][291526] Decorrelating experience for 64 frames... +[2023-07-17 01:41:08,786][291558] Decorrelating experience for 0 frames... +[2023-07-17 01:41:08,794][291558] Decorrelating experience for 64 frames... +[2023-07-17 01:41:08,800][291526] Decorrelating experience for 128 frames... +[2023-07-17 01:41:08,804][291490] Decorrelating experience for 0 frames... +[2023-07-17 01:41:08,812][291490] Decorrelating experience for 64 frames... +[2023-07-17 01:41:08,828][291558] Decorrelating experience for 128 frames... +[2023-07-17 01:41:08,846][291490] Decorrelating experience for 128 frames... +[2023-07-17 01:41:08,875][291526] Decorrelating experience for 192 frames... +[2023-07-17 01:41:08,896][291558] Decorrelating experience for 192 frames... +[2023-07-17 01:41:08,913][291490] Decorrelating experience for 192 frames... +[2023-07-17 01:41:08,957][291492] Decorrelating experience for 0 frames... +[2023-07-17 01:41:08,965][291492] Decorrelating experience for 64 frames... +[2023-07-17 01:41:08,999][291492] Decorrelating experience for 128 frames... +[2023-07-17 01:41:09,078][291492] Decorrelating experience for 192 frames... +[2023-07-17 01:41:10,043][291491] Decorrelating experience for 256 frames... +[2023-07-17 01:41:10,068][291494] Decorrelating experience for 256 frames... +[2023-07-17 01:41:10,073][291493] Decorrelating experience for 256 frames... +[2023-07-17 01:41:10,074][291489] Decorrelating experience for 256 frames... +[2023-07-17 01:41:10,173][291491] Decorrelating experience for 320 frames... +[2023-07-17 01:41:10,187][291526] Decorrelating experience for 256 frames... +[2023-07-17 01:41:10,193][291494] Decorrelating experience for 320 frames... +[2023-07-17 01:41:10,198][291493] Decorrelating experience for 320 frames... +[2023-07-17 01:41:10,200][291489] Decorrelating experience for 320 frames... +[2023-07-17 01:41:10,208][291558] Decorrelating experience for 256 frames... +[2023-07-17 01:41:10,224][291490] Decorrelating experience for 256 frames... +[2023-07-17 01:41:10,312][291526] Decorrelating experience for 320 frames... +[2023-07-17 01:41:10,335][291558] Decorrelating experience for 320 frames... +[2023-07-17 01:41:10,342][291491] Decorrelating experience for 384 frames... +[2023-07-17 01:41:10,351][291494] Decorrelating experience for 384 frames... +[2023-07-17 01:41:10,357][291490] Decorrelating experience for 320 frames... +[2023-07-17 01:41:10,362][291489] Decorrelating experience for 384 frames... +[2023-07-17 01:41:10,368][291493] Decorrelating experience for 384 frames... +[2023-07-17 01:41:10,401][291492] Decorrelating experience for 256 frames... +[2023-07-17 01:41:10,470][291526] Decorrelating experience for 384 frames... +[2023-07-17 01:41:10,493][291558] Decorrelating experience for 384 frames... +[2023-07-17 01:41:10,523][291490] Decorrelating experience for 384 frames... +[2023-07-17 01:41:10,528][291492] Decorrelating experience for 320 frames... +[2023-07-17 01:41:10,532][291491] Decorrelating experience for 448 frames... +[2023-07-17 01:41:10,550][291494] Decorrelating experience for 448 frames... +[2023-07-17 01:41:10,553][291493] Decorrelating experience for 448 frames... +[2023-07-17 01:41:10,553][291489] Decorrelating experience for 448 frames... +[2023-07-17 01:41:10,654][291526] Decorrelating experience for 448 frames... +[2023-07-17 01:41:10,676][291558] Decorrelating experience for 448 frames... +[2023-07-17 01:41:10,694][291492] Decorrelating experience for 384 frames... +[2023-07-17 01:41:10,712][291490] Decorrelating experience for 448 frames... +[2023-07-17 01:41:10,880][291492] Decorrelating experience for 448 frames... +[2023-07-17 01:41:12,907][291207] Fps is (10 sec: 3276.9, 60 sec: 3276.9, 300 sec: 3276.9). Total num frames: 16384. Throughput: 0: 0.0. Samples: 0. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:41:12,908][291207] Avg episode reward: [(0, '5.430')] +[2023-07-17 01:41:15,305][291488] Updated weights for policy 0, policy_version 80 (0.0005) +[2023-07-17 01:41:17,907][291207] Fps is (10 sec: 6144.0, 60 sec: 6144.0, 300 sec: 6144.0). Total num frames: 61440. Throughput: 0: 5060.0. Samples: 50600. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) +[2023-07-17 01:41:17,908][291207] Avg episode reward: [(0, '19.705')] +[2023-07-17 01:41:17,949][291444] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000000128_65536.pth... +[2023-07-17 01:41:19,748][291488] Updated weights for policy 0, policy_version 160 (0.0005) +[2023-07-17 01:41:22,907][291207] Fps is (10 sec: 9420.8, 60 sec: 7372.9, 300 sec: 7372.9). Total num frames: 110592. Throughput: 0: 7104.1. Samples: 106560. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) +[2023-07-17 01:41:22,909][291207] Avg episode reward: [(0, '20.508')] +[2023-07-17 01:41:22,909][291444] Saving new best policy, reward=20.508! +[2023-07-17 01:41:24,100][291488] Updated weights for policy 0, policy_version 240 (0.0005) +[2023-07-17 01:41:24,936][291207] Heartbeat connected on Batcher_0 +[2023-07-17 01:41:24,938][291207] Heartbeat connected on LearnerWorker_p0 +[2023-07-17 01:41:24,943][291207] Heartbeat connected on RolloutWorker_w0 +[2023-07-17 01:41:24,945][291207] Heartbeat connected on RolloutWorker_w1 +[2023-07-17 01:41:24,947][291207] Heartbeat connected on RolloutWorker_w2 +[2023-07-17 01:41:24,949][291207] Heartbeat connected on RolloutWorker_w3 +[2023-07-17 01:41:24,951][291207] Heartbeat connected on RolloutWorker_w4 +[2023-07-17 01:41:24,953][291207] Heartbeat connected on RolloutWorker_w5 +[2023-07-17 01:41:24,955][291207] Heartbeat connected on RolloutWorker_w6 +[2023-07-17 01:41:24,957][291207] Heartbeat connected on RolloutWorker_w7 +[2023-07-17 01:41:24,971][291207] Heartbeat connected on InferenceWorker_p0-w0 +[2023-07-17 01:41:27,907][291207] Fps is (10 sec: 9420.9, 60 sec: 7782.4, 300 sec: 7782.4). Total num frames: 155648. Throughput: 0: 6702.2. Samples: 134044. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) +[2023-07-17 01:41:27,907][291207] Avg episode reward: [(0, '28.771')] +[2023-07-17 01:41:27,908][291444] Saving new best policy, reward=28.771! +[2023-07-17 01:41:28,796][291488] Updated weights for policy 0, policy_version 320 (0.0005) +[2023-07-17 01:41:32,907][291207] Fps is (10 sec: 8601.6, 60 sec: 7864.3, 300 sec: 7864.3). Total num frames: 196608. Throughput: 0: 7468.0. Samples: 186700. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) +[2023-07-17 01:41:32,907][291207] Avg episode reward: [(0, '32.895')] +[2023-07-17 01:41:32,952][291444] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000000392_200704.pth... +[2023-07-17 01:41:32,954][291444] Saving new best policy, reward=32.895! +[2023-07-17 01:41:33,422][291488] Updated weights for policy 0, policy_version 400 (0.0005) +[2023-07-17 01:41:37,907][291207] Fps is (10 sec: 8601.6, 60 sec: 8055.5, 300 sec: 8055.5). Total num frames: 241664. Throughput: 0: 8000.8. Samples: 240024. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:41:37,908][291207] Avg episode reward: [(0, '36.717')] +[2023-07-17 01:41:37,908][291444] Saving new best policy, reward=36.717! +[2023-07-17 01:41:37,972][291488] Updated weights for policy 0, policy_version 480 (0.0005) +[2023-07-17 01:41:42,551][291488] Updated weights for policy 0, policy_version 560 (0.0005) +[2023-07-17 01:41:42,907][291207] Fps is (10 sec: 9011.3, 60 sec: 8192.0, 300 sec: 8192.0). Total num frames: 286720. Throughput: 0: 7608.9. Samples: 266312. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:41:42,908][291207] Avg episode reward: [(0, '48.488')] +[2023-07-17 01:41:42,908][291444] Saving new best policy, reward=48.488! +[2023-07-17 01:41:46,679][291488] Updated weights for policy 0, policy_version 640 (0.0005) +[2023-07-17 01:41:47,907][291207] Fps is (10 sec: 9830.3, 60 sec: 8499.2, 300 sec: 8499.2). Total num frames: 339968. Throughput: 0: 8091.2. Samples: 323648. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) +[2023-07-17 01:41:47,908][291207] Avg episode reward: [(0, '79.402')] +[2023-07-17 01:41:47,911][291444] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000000664_339968.pth... +[2023-07-17 01:41:47,914][291444] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000000128_65536.pth +[2023-07-17 01:41:47,914][291444] Saving new best policy, reward=79.402! +[2023-07-17 01:41:50,609][291488] Updated weights for policy 0, policy_version 720 (0.0005) +[2023-07-17 01:41:52,907][291207] Fps is (10 sec: 10239.9, 60 sec: 8647.1, 300 sec: 8647.1). Total num frames: 389120. Throughput: 0: 8585.9. Samples: 386364. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:41:52,908][291207] Avg episode reward: [(0, '117.308')] +[2023-07-17 01:41:52,908][291444] Saving new best policy, reward=117.308! +[2023-07-17 01:41:54,488][291488] Updated weights for policy 0, policy_version 800 (0.0005) +[2023-07-17 01:41:57,907][291207] Fps is (10 sec: 10240.1, 60 sec: 8847.4, 300 sec: 8847.4). Total num frames: 442368. Throughput: 0: 9295.3. Samples: 418288. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:41:57,908][291207] Avg episode reward: [(0, '159.265')] +[2023-07-17 01:41:57,908][291444] Saving new best policy, reward=159.265! +[2023-07-17 01:41:58,437][291488] Updated weights for policy 0, policy_version 880 (0.0005) +[2023-07-17 01:42:02,456][291488] Updated weights for policy 0, policy_version 960 (0.0005) +[2023-07-17 01:42:02,907][291207] Fps is (10 sec: 10649.5, 60 sec: 9011.2, 300 sec: 9011.2). Total num frames: 495616. Throughput: 0: 9533.1. Samples: 479588. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:42:02,907][291207] Avg episode reward: [(0, '175.436')] +[2023-07-17 01:42:02,910][291444] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000000968_495616.pth... +[2023-07-17 01:42:02,914][291444] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000000392_200704.pth +[2023-07-17 01:42:02,914][291444] Saving new best policy, reward=175.436! +[2023-07-17 01:42:06,311][291488] Updated weights for policy 0, policy_version 1040 (0.0005) +[2023-07-17 01:42:07,906][291207] Fps is (10 sec: 10649.7, 60 sec: 9147.8, 300 sec: 9147.8). Total num frames: 548864. Throughput: 0: 9709.3. Samples: 543476. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:42:07,907][291207] Avg episode reward: [(0, '173.920')] +[2023-07-17 01:42:10,124][291488] Updated weights for policy 0, policy_version 1120 (0.0005) +[2023-07-17 01:42:12,907][291207] Fps is (10 sec: 10649.7, 60 sec: 9762.1, 300 sec: 9263.3). Total num frames: 602112. Throughput: 0: 9813.7. Samples: 575660. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) +[2023-07-17 01:42:12,907][291207] Avg episode reward: [(0, '181.112')] +[2023-07-17 01:42:12,908][291444] Saving new best policy, reward=181.112! +[2023-07-17 01:42:13,870][291488] Updated weights for policy 0, policy_version 1200 (0.0005) +[2023-07-17 01:42:17,674][291488] Updated weights for policy 0, policy_version 1280 (0.0005) +[2023-07-17 01:42:17,907][291207] Fps is (10 sec: 10649.5, 60 sec: 9898.7, 300 sec: 9362.3). Total num frames: 655360. Throughput: 0: 10089.6. Samples: 640732. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:42:17,907][291207] Avg episode reward: [(0, '209.841')] +[2023-07-17 01:42:17,910][291444] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000001280_655360.pth... +[2023-07-17 01:42:17,913][291444] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000000664_339968.pth +[2023-07-17 01:42:17,913][291444] Saving new best policy, reward=209.841! +[2023-07-17 01:42:21,389][291488] Updated weights for policy 0, policy_version 1360 (0.0005) +[2023-07-17 01:42:22,906][291207] Fps is (10 sec: 11059.2, 60 sec: 10035.2, 300 sec: 9502.7). Total num frames: 712704. Throughput: 0: 10360.1. Samples: 706228. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) +[2023-07-17 01:42:22,907][291207] Avg episode reward: [(0, '208.108')] +[2023-07-17 01:42:25,095][291488] Updated weights for policy 0, policy_version 1440 (0.0005) +[2023-07-17 01:42:27,906][291207] Fps is (10 sec: 11059.2, 60 sec: 10171.7, 300 sec: 9574.4). Total num frames: 765952. Throughput: 0: 10522.7. Samples: 739832. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:42:27,907][291207] Avg episode reward: [(0, '238.533')] +[2023-07-17 01:42:27,907][291444] Saving new best policy, reward=238.533! +[2023-07-17 01:42:28,804][291488] Updated weights for policy 0, policy_version 1520 (0.0005) +[2023-07-17 01:42:32,490][291488] Updated weights for policy 0, policy_version 1600 (0.0005) +[2023-07-17 01:42:32,907][291207] Fps is (10 sec: 11059.1, 60 sec: 10444.8, 300 sec: 9685.8). Total num frames: 823296. Throughput: 0: 10728.0. Samples: 806408. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:42:32,907][291207] Avg episode reward: [(0, '255.365')] +[2023-07-17 01:42:32,910][291444] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000001608_823296.pth... +[2023-07-17 01:42:32,913][291444] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000000968_495616.pth +[2023-07-17 01:42:32,913][291444] Saving new best policy, reward=255.365! +[2023-07-17 01:42:36,189][291488] Updated weights for policy 0, policy_version 1680 (0.0005) +[2023-07-17 01:42:37,906][291207] Fps is (10 sec: 11059.2, 60 sec: 10581.3, 300 sec: 9739.4). Total num frames: 876544. Throughput: 0: 10808.1. Samples: 872728. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:42:37,907][291207] Avg episode reward: [(0, '263.212')] +[2023-07-17 01:42:37,907][291444] Saving new best policy, reward=263.212! +[2023-07-17 01:42:39,920][291488] Updated weights for policy 0, policy_version 1760 (0.0005) +[2023-07-17 01:42:42,907][291207] Fps is (10 sec: 11059.2, 60 sec: 10786.1, 300 sec: 9830.4). Total num frames: 933888. Throughput: 0: 10823.6. Samples: 905348. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:42:42,907][291207] Avg episode reward: [(0, '280.666')] +[2023-07-17 01:42:42,908][291444] Saving new best policy, reward=280.666! +[2023-07-17 01:42:43,533][291488] Updated weights for policy 0, policy_version 1840 (0.0005) +[2023-07-17 01:42:47,220][291488] Updated weights for policy 0, policy_version 1920 (0.0005) +[2023-07-17 01:42:47,907][291207] Fps is (10 sec: 11059.1, 60 sec: 10786.1, 300 sec: 9871.4). Total num frames: 987136. Throughput: 0: 10959.3. Samples: 972756. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) +[2023-07-17 01:42:47,907][291207] Avg episode reward: [(0, '276.145')] +[2023-07-17 01:42:47,909][291444] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000001928_987136.pth... +[2023-07-17 01:42:47,912][291444] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000001280_655360.pth +[2023-07-17 01:42:50,889][291488] Updated weights for policy 0, policy_version 2000 (0.0005) +[2023-07-17 01:42:52,906][291207] Fps is (10 sec: 11059.2, 60 sec: 10922.7, 300 sec: 9947.4). Total num frames: 1044480. Throughput: 0: 11039.2. Samples: 1040240. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) +[2023-07-17 01:42:52,907][291207] Avg episode reward: [(0, '278.090')] +[2023-07-17 01:42:54,622][291488] Updated weights for policy 0, policy_version 2080 (0.0005) +[2023-07-17 01:42:57,907][291207] Fps is (10 sec: 11059.3, 60 sec: 10922.7, 300 sec: 9979.4). Total num frames: 1097728. Throughput: 0: 11047.2. Samples: 1072784. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) +[2023-07-17 01:42:57,907][291207] Avg episode reward: [(0, '261.858')] +[2023-07-17 01:42:58,600][291488] Updated weights for policy 0, policy_version 2160 (0.0006) +[2023-07-17 01:43:02,528][291488] Updated weights for policy 0, policy_version 2240 (0.0005) +[2023-07-17 01:43:02,907][291207] Fps is (10 sec: 10649.6, 60 sec: 10922.7, 300 sec: 10008.5). Total num frames: 1150976. Throughput: 0: 10974.7. Samples: 1134592. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:43:02,907][291207] Avg episode reward: [(0, '263.617')] +[2023-07-17 01:43:02,910][291444] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000002248_1150976.pth... +[2023-07-17 01:43:02,912][291444] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000001608_823296.pth +[2023-07-17 01:43:06,202][291488] Updated weights for policy 0, policy_version 2320 (0.0004) +[2023-07-17 01:43:07,906][291207] Fps is (10 sec: 10649.7, 60 sec: 10922.7, 300 sec: 10035.2). Total num frames: 1204224. Throughput: 0: 10978.1. Samples: 1200244. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:43:07,907][291207] Avg episode reward: [(0, '278.018')] +[2023-07-17 01:43:09,779][291488] Updated weights for policy 0, policy_version 2400 (0.0004) +[2023-07-17 01:43:12,906][291207] Fps is (10 sec: 11059.2, 60 sec: 10990.9, 300 sec: 10092.6). Total num frames: 1261568. Throughput: 0: 11004.9. Samples: 1235052. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) +[2023-07-17 01:43:12,907][291207] Avg episode reward: [(0, '290.975')] +[2023-07-17 01:43:12,908][291444] Saving new best policy, reward=290.975! +[2023-07-17 01:43:13,476][291488] Updated weights for policy 0, policy_version 2480 (0.0004) +[2023-07-17 01:43:17,309][291488] Updated weights for policy 0, policy_version 2560 (0.0005) +[2023-07-17 01:43:17,907][291207] Fps is (10 sec: 11059.1, 60 sec: 10990.9, 300 sec: 10114.0). Total num frames: 1314816. Throughput: 0: 10990.4. Samples: 1300976. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) +[2023-07-17 01:43:17,907][291207] Avg episode reward: [(0, '271.618')] +[2023-07-17 01:43:17,911][291444] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000002568_1314816.pth... +[2023-07-17 01:43:17,913][291444] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000001928_987136.pth +[2023-07-17 01:43:20,972][291488] Updated weights for policy 0, policy_version 2640 (0.0004) +[2023-07-17 01:43:22,907][291207] Fps is (10 sec: 11059.2, 60 sec: 10990.9, 300 sec: 10164.2). Total num frames: 1372160. Throughput: 0: 10982.1. Samples: 1366924. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:43:22,907][291207] Avg episode reward: [(0, '295.394')] +[2023-07-17 01:43:22,908][291444] Saving new best policy, reward=295.394! +[2023-07-17 01:43:24,644][291488] Updated weights for policy 0, policy_version 2720 (0.0004) +[2023-07-17 01:43:27,906][291207] Fps is (10 sec: 11059.3, 60 sec: 10990.9, 300 sec: 10181.5). Total num frames: 1425408. Throughput: 0: 10999.9. Samples: 1400344. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) +[2023-07-17 01:43:27,907][291207] Avg episode reward: [(0, '285.166')] +[2023-07-17 01:43:28,277][291488] Updated weights for policy 0, policy_version 2800 (0.0004) +[2023-07-17 01:43:31,980][291488] Updated weights for policy 0, policy_version 2880 (0.0004) +[2023-07-17 01:43:32,906][291207] Fps is (10 sec: 11059.2, 60 sec: 10990.9, 300 sec: 10225.9). Total num frames: 1482752. Throughput: 0: 10986.1. Samples: 1467128. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:43:32,907][291207] Avg episode reward: [(0, '275.301')] +[2023-07-17 01:43:32,909][291444] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000002896_1482752.pth... +[2023-07-17 01:43:32,912][291444] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000002248_1150976.pth +[2023-07-17 01:43:36,009][291488] Updated weights for policy 0, policy_version 2960 (0.0005) +[2023-07-17 01:43:37,907][291207] Fps is (10 sec: 11059.1, 60 sec: 10990.9, 300 sec: 10240.0). Total num frames: 1536000. Throughput: 0: 10885.7. Samples: 1530096. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:43:37,907][291207] Avg episode reward: [(0, '293.819')] +[2023-07-17 01:43:39,845][291488] Updated weights for policy 0, policy_version 3040 (0.0005) +[2023-07-17 01:43:42,907][291207] Fps is (10 sec: 10240.0, 60 sec: 10854.4, 300 sec: 10226.8). Total num frames: 1585152. Throughput: 0: 10854.1. Samples: 1561220. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) +[2023-07-17 01:43:42,907][291207] Avg episode reward: [(0, '310.294')] +[2023-07-17 01:43:42,908][291444] Saving new best policy, reward=310.294! +[2023-07-17 01:43:43,749][291488] Updated weights for policy 0, policy_version 3120 (0.0005) +[2023-07-17 01:43:47,612][291488] Updated weights for policy 0, policy_version 3200 (0.0005) +[2023-07-17 01:43:47,907][291207] Fps is (10 sec: 10240.0, 60 sec: 10854.4, 300 sec: 10240.0). Total num frames: 1638400. Throughput: 0: 10891.4. Samples: 1624704. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:43:47,907][291207] Avg episode reward: [(0, '317.700')] +[2023-07-17 01:43:47,911][291444] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000003200_1638400.pth... +[2023-07-17 01:43:47,914][291444] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000002568_1314816.pth +[2023-07-17 01:43:47,914][291444] Saving new best policy, reward=317.700! +[2023-07-17 01:43:51,601][291488] Updated weights for policy 0, policy_version 3280 (0.0005) +[2023-07-17 01:43:52,907][291207] Fps is (10 sec: 10649.6, 60 sec: 10786.1, 300 sec: 10252.4). Total num frames: 1691648. Throughput: 0: 10828.9. Samples: 1687544. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:43:52,908][291207] Avg episode reward: [(0, '289.631')] +[2023-07-17 01:43:55,354][291488] Updated weights for policy 0, policy_version 3360 (0.0005) +[2023-07-17 01:43:57,907][291207] Fps is (10 sec: 10649.6, 60 sec: 10786.1, 300 sec: 10264.1). Total num frames: 1744896. Throughput: 0: 10783.9. Samples: 1720328. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) +[2023-07-17 01:43:57,908][291207] Avg episode reward: [(0, '306.910')] +[2023-07-17 01:43:59,040][291488] Updated weights for policy 0, policy_version 3440 (0.0005) +[2023-07-17 01:44:02,907][291207] Fps is (10 sec: 10649.5, 60 sec: 10786.1, 300 sec: 10275.1). Total num frames: 1798144. Throughput: 0: 10769.1. Samples: 1785584. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) +[2023-07-17 01:44:02,907][291207] Avg episode reward: [(0, '303.288')] +[2023-07-17 01:44:02,947][291444] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000003520_1802240.pth... +[2023-07-17 01:44:02,947][291488] Updated weights for policy 0, policy_version 3520 (0.0005) +[2023-07-17 01:44:02,949][291444] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000002896_1482752.pth +[2023-07-17 01:44:06,850][291488] Updated weights for policy 0, policy_version 3600 (0.0005) +[2023-07-17 01:44:07,907][291207] Fps is (10 sec: 10649.6, 60 sec: 10786.1, 300 sec: 10285.5). Total num frames: 1851392. Throughput: 0: 10691.6. Samples: 1848048. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:44:07,908][291207] Avg episode reward: [(0, '278.763')] +[2023-07-17 01:44:10,732][291488] Updated weights for policy 0, policy_version 3680 (0.0005) +[2023-07-17 01:44:12,906][291207] Fps is (10 sec: 10649.7, 60 sec: 10717.9, 300 sec: 10295.4). Total num frames: 1904640. Throughput: 0: 10660.4. Samples: 1880064. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:44:12,907][291207] Avg episode reward: [(0, '291.867')] +[2023-07-17 01:44:14,663][291488] Updated weights for policy 0, policy_version 3760 (0.0005) +[2023-07-17 01:44:17,907][291207] Fps is (10 sec: 10649.6, 60 sec: 10717.9, 300 sec: 10304.7). Total num frames: 1957888. Throughput: 0: 10578.7. Samples: 1943168. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) +[2023-07-17 01:44:17,907][291207] Avg episode reward: [(0, '289.007')] +[2023-07-17 01:44:17,911][291444] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000003824_1957888.pth... +[2023-07-17 01:44:17,914][291444] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000003200_1638400.pth +[2023-07-17 01:44:18,488][291488] Updated weights for policy 0, policy_version 3840 (0.0005) +[2023-07-17 01:44:22,435][291488] Updated weights for policy 0, policy_version 3920 (0.0005) +[2023-07-17 01:44:22,907][291207] Fps is (10 sec: 10649.6, 60 sec: 10649.6, 300 sec: 10313.5). Total num frames: 2011136. Throughput: 0: 10582.8. Samples: 2006324. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) +[2023-07-17 01:44:22,907][291207] Avg episode reward: [(0, '291.276')] +[2023-07-17 01:44:26,302][291488] Updated weights for policy 0, policy_version 4000 (0.0005) +[2023-07-17 01:44:27,906][291207] Fps is (10 sec: 10649.7, 60 sec: 10649.6, 300 sec: 10321.9). Total num frames: 2064384. Throughput: 0: 10579.4. Samples: 2037292. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:44:27,907][291207] Avg episode reward: [(0, '306.868')] +[2023-07-17 01:44:30,123][291488] Updated weights for policy 0, policy_version 4080 (0.0005) +[2023-07-17 01:44:32,907][291207] Fps is (10 sec: 10649.6, 60 sec: 10581.3, 300 sec: 10329.9). Total num frames: 2117632. Throughput: 0: 10591.5. Samples: 2101320. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:44:32,907][291207] Avg episode reward: [(0, '315.109')] +[2023-07-17 01:44:32,910][291444] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000004136_2117632.pth... +[2023-07-17 01:44:32,913][291444] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000003520_1802240.pth +[2023-07-17 01:44:34,033][291488] Updated weights for policy 0, policy_version 4160 (0.0005) +[2023-07-17 01:44:37,907][291207] Fps is (10 sec: 10240.0, 60 sec: 10513.1, 300 sec: 10318.0). Total num frames: 2166784. Throughput: 0: 10612.2. Samples: 2165092. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:44:37,907][291207] Avg episode reward: [(0, '323.676')] +[2023-07-17 01:44:37,908][291444] Saving new best policy, reward=323.676! +[2023-07-17 01:44:37,908][291488] Updated weights for policy 0, policy_version 4240 (0.0005) +[2023-07-17 01:44:41,587][291488] Updated weights for policy 0, policy_version 4320 (0.0004) +[2023-07-17 01:44:42,907][291207] Fps is (10 sec: 10649.6, 60 sec: 10649.6, 300 sec: 10344.8). Total num frames: 2224128. Throughput: 0: 10604.8. Samples: 2197544. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) +[2023-07-17 01:44:42,908][291207] Avg episode reward: [(0, '335.721')] +[2023-07-17 01:44:42,908][291444] Saving new best policy, reward=335.721! +[2023-07-17 01:44:45,461][291488] Updated weights for policy 0, policy_version 4400 (0.0005) +[2023-07-17 01:44:47,907][291207] Fps is (10 sec: 11059.2, 60 sec: 10649.6, 300 sec: 10351.7). Total num frames: 2277376. Throughput: 0: 10586.9. Samples: 2261996. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) +[2023-07-17 01:44:47,908][291207] Avg episode reward: [(0, '366.489')] +[2023-07-17 01:44:47,911][291444] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000004448_2277376.pth... +[2023-07-17 01:44:47,914][291444] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000003824_1957888.pth +[2023-07-17 01:44:47,915][291444] Saving new best policy, reward=366.489! +[2023-07-17 01:44:49,365][291488] Updated weights for policy 0, policy_version 4480 (0.0005) +[2023-07-17 01:44:52,907][291207] Fps is (10 sec: 10649.6, 60 sec: 10649.6, 300 sec: 10358.3). Total num frames: 2330624. Throughput: 0: 10602.8. Samples: 2325172. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:44:52,908][291207] Avg episode reward: [(0, '354.842')] +[2023-07-17 01:44:53,260][291488] Updated weights for policy 0, policy_version 4560 (0.0005) +[2023-07-17 01:44:57,023][291488] Updated weights for policy 0, policy_version 4640 (0.0005) +[2023-07-17 01:44:57,907][291207] Fps is (10 sec: 10649.6, 60 sec: 10649.6, 300 sec: 10364.7). Total num frames: 2383872. Throughput: 0: 10602.0. Samples: 2357156. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) +[2023-07-17 01:44:57,907][291207] Avg episode reward: [(0, '358.599')] +[2023-07-17 01:45:00,849][291488] Updated weights for policy 0, policy_version 4720 (0.0005) +[2023-07-17 01:45:02,907][291207] Fps is (10 sec: 10649.6, 60 sec: 10649.6, 300 sec: 10370.7). Total num frames: 2437120. Throughput: 0: 10633.1. Samples: 2421656. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:45:02,907][291207] Avg episode reward: [(0, '380.034')] +[2023-07-17 01:45:02,911][291444] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000004760_2437120.pth... +[2023-07-17 01:45:02,914][291444] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000004136_2117632.pth +[2023-07-17 01:45:02,914][291444] Saving new best policy, reward=380.034! +[2023-07-17 01:45:04,648][291488] Updated weights for policy 0, policy_version 4800 (0.0005) +[2023-07-17 01:45:07,906][291207] Fps is (10 sec: 10649.6, 60 sec: 10649.6, 300 sec: 10376.5). Total num frames: 2490368. Throughput: 0: 10663.7. Samples: 2486192. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:45:07,907][291207] Avg episode reward: [(0, '380.243')] +[2023-07-17 01:45:07,907][291444] Saving new best policy, reward=380.243! +[2023-07-17 01:45:08,547][291488] Updated weights for policy 0, policy_version 4880 (0.0005) +[2023-07-17 01:45:12,304][291488] Updated weights for policy 0, policy_version 4960 (0.0005) +[2023-07-17 01:45:12,907][291207] Fps is (10 sec: 10649.6, 60 sec: 10649.6, 300 sec: 10382.1). Total num frames: 2543616. Throughput: 0: 10685.7. Samples: 2518148. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) +[2023-07-17 01:45:12,907][291207] Avg episode reward: [(0, '398.214')] +[2023-07-17 01:45:12,907][291444] Saving new best policy, reward=398.214! +[2023-07-17 01:45:16,100][291488] Updated weights for policy 0, policy_version 5040 (0.0005) +[2023-07-17 01:45:17,907][291207] Fps is (10 sec: 10649.5, 60 sec: 10649.6, 300 sec: 10387.5). Total num frames: 2596864. Throughput: 0: 10704.8. Samples: 2583036. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) +[2023-07-17 01:45:17,907][291207] Avg episode reward: [(0, '422.479')] +[2023-07-17 01:45:17,911][291444] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000005072_2596864.pth... +[2023-07-17 01:45:17,914][291444] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000004448_2277376.pth +[2023-07-17 01:45:17,915][291444] Saving new best policy, reward=422.479! +[2023-07-17 01:45:19,895][291488] Updated weights for policy 0, policy_version 5120 (0.0005) +[2023-07-17 01:45:22,906][291207] Fps is (10 sec: 10649.6, 60 sec: 10649.6, 300 sec: 10392.6). Total num frames: 2650112. Throughput: 0: 10712.3. Samples: 2647144. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) +[2023-07-17 01:45:22,907][291207] Avg episode reward: [(0, '405.280')] +[2023-07-17 01:45:23,741][291488] Updated weights for policy 0, policy_version 5200 (0.0005) +[2023-07-17 01:45:27,544][291488] Updated weights for policy 0, policy_version 5280 (0.0005) +[2023-07-17 01:45:27,907][291207] Fps is (10 sec: 10649.7, 60 sec: 10649.6, 300 sec: 10397.5). Total num frames: 2703360. Throughput: 0: 10710.2. Samples: 2679504. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) +[2023-07-17 01:45:27,907][291207] Avg episode reward: [(0, '400.902')] +[2023-07-17 01:45:31,307][291488] Updated weights for policy 0, policy_version 5360 (0.0004) +[2023-07-17 01:45:32,907][291207] Fps is (10 sec: 11059.1, 60 sec: 10717.9, 300 sec: 10417.8). Total num frames: 2760704. Throughput: 0: 10719.7. Samples: 2744384. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:45:32,907][291207] Avg episode reward: [(0, '416.614')] +[2023-07-17 01:45:32,911][291444] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000005392_2760704.pth... +[2023-07-17 01:45:32,914][291444] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000004760_2437120.pth +[2023-07-17 01:45:35,060][291488] Updated weights for policy 0, policy_version 5440 (0.0005) +[2023-07-17 01:45:37,906][291207] Fps is (10 sec: 11059.2, 60 sec: 10786.1, 300 sec: 10422.1). Total num frames: 2813952. Throughput: 0: 10772.2. Samples: 2809920. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) +[2023-07-17 01:45:37,907][291207] Avg episode reward: [(0, '439.903')] +[2023-07-17 01:45:37,907][291444] Saving new best policy, reward=439.903! +[2023-07-17 01:45:38,841][291488] Updated weights for policy 0, policy_version 5520 (0.0005) +[2023-07-17 01:45:42,472][291488] Updated weights for policy 0, policy_version 5600 (0.0005) +[2023-07-17 01:45:42,907][291207] Fps is (10 sec: 11059.3, 60 sec: 10786.1, 300 sec: 10441.1). Total num frames: 2871296. Throughput: 0: 10788.4. Samples: 2842632. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:45:42,907][291207] Avg episode reward: [(0, '429.430')] +[2023-07-17 01:45:46,106][291488] Updated weights for policy 0, policy_version 5680 (0.0005) +[2023-07-17 01:45:47,907][291207] Fps is (10 sec: 11468.7, 60 sec: 10854.4, 300 sec: 10459.4). Total num frames: 2928640. Throughput: 0: 10867.5. Samples: 2910692. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:45:47,907][291207] Avg episode reward: [(0, '413.827')] +[2023-07-17 01:45:47,910][291444] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000005720_2928640.pth... +[2023-07-17 01:45:47,913][291444] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000005072_2596864.pth +[2023-07-17 01:45:49,652][291488] Updated weights for policy 0, policy_version 5760 (0.0004) +[2023-07-17 01:45:52,906][291207] Fps is (10 sec: 11468.9, 60 sec: 10922.7, 300 sec: 10477.1). Total num frames: 2985984. Throughput: 0: 10971.4. Samples: 2979904. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) +[2023-07-17 01:45:52,909][291207] Avg episode reward: [(0, '399.475')] +[2023-07-17 01:45:53,190][291488] Updated weights for policy 0, policy_version 5840 (0.0004) +[2023-07-17 01:45:56,769][291488] Updated weights for policy 0, policy_version 5920 (0.0004) +[2023-07-17 01:45:57,907][291207] Fps is (10 sec: 11468.8, 60 sec: 10990.9, 300 sec: 10494.2). Total num frames: 3043328. Throughput: 0: 11034.9. Samples: 3014720. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) +[2023-07-17 01:45:57,907][291207] Avg episode reward: [(0, '425.538')] +[2023-07-17 01:46:00,409][291488] Updated weights for policy 0, policy_version 6000 (0.0005) +[2023-07-17 01:46:02,907][291207] Fps is (10 sec: 11059.2, 60 sec: 10990.9, 300 sec: 10496.9). Total num frames: 3096576. Throughput: 0: 11090.8. Samples: 3082120. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) +[2023-07-17 01:46:02,908][291207] Avg episode reward: [(0, '451.580')] +[2023-07-17 01:46:02,910][291444] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000006048_3096576.pth... +[2023-07-17 01:46:02,912][291444] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000005392_2760704.pth +[2023-07-17 01:46:02,912][291444] Saving new best policy, reward=451.580! +[2023-07-17 01:46:04,101][291488] Updated weights for policy 0, policy_version 6080 (0.0005) +[2023-07-17 01:46:07,896][291488] Updated weights for policy 0, policy_version 6160 (0.0005) +[2023-07-17 01:46:07,907][291207] Fps is (10 sec: 11059.2, 60 sec: 11059.2, 300 sec: 10635.7). Total num frames: 3153920. Throughput: 0: 11133.3. Samples: 3148144. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) +[2023-07-17 01:46:07,908][291207] Avg episode reward: [(0, '459.314')] +[2023-07-17 01:46:07,908][291444] Saving new best policy, reward=459.314! +[2023-07-17 01:46:11,627][291488] Updated weights for policy 0, policy_version 6240 (0.0005) +[2023-07-17 01:46:12,907][291207] Fps is (10 sec: 11059.2, 60 sec: 11059.2, 300 sec: 10663.5). Total num frames: 3207168. Throughput: 0: 11135.3. Samples: 3180592. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:46:12,908][291207] Avg episode reward: [(0, '434.359')] +[2023-07-17 01:46:15,360][291488] Updated weights for policy 0, policy_version 6320 (0.0005) +[2023-07-17 01:46:17,907][291207] Fps is (10 sec: 10649.5, 60 sec: 11059.2, 300 sec: 10677.4). Total num frames: 3260416. Throughput: 0: 11155.2. Samples: 3246368. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:46:17,908][291207] Avg episode reward: [(0, '422.903')] +[2023-07-17 01:46:17,910][291444] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000006368_3260416.pth... +[2023-07-17 01:46:17,913][291444] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000005720_2928640.pth +[2023-07-17 01:46:19,135][291488] Updated weights for policy 0, policy_version 6400 (0.0005) +[2023-07-17 01:46:22,907][291207] Fps is (10 sec: 10649.6, 60 sec: 11059.2, 300 sec: 10705.1). Total num frames: 3313664. Throughput: 0: 11133.2. Samples: 3310916. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) +[2023-07-17 01:46:22,908][291207] Avg episode reward: [(0, '435.699')] +[2023-07-17 01:46:22,970][291488] Updated weights for policy 0, policy_version 6480 (0.0004) +[2023-07-17 01:46:26,572][291488] Updated weights for policy 0, policy_version 6560 (0.0003) +[2023-07-17 01:46:27,906][291207] Fps is (10 sec: 11059.3, 60 sec: 11127.5, 300 sec: 10760.7). Total num frames: 3371008. Throughput: 0: 11156.0. Samples: 3344652. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:46:27,907][291207] Avg episode reward: [(0, '462.443')] +[2023-07-17 01:46:27,959][291444] Saving new best policy, reward=462.443! +[2023-07-17 01:46:30,132][291488] Updated weights for policy 0, policy_version 6640 (0.0004) +[2023-07-17 01:46:32,907][291207] Fps is (10 sec: 11468.8, 60 sec: 11127.5, 300 sec: 10802.3). Total num frames: 3428352. Throughput: 0: 11145.5. Samples: 3412240. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:46:32,907][291207] Avg episode reward: [(0, '450.636')] +[2023-07-17 01:46:32,910][291444] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000006696_3428352.pth... +[2023-07-17 01:46:32,913][291444] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000006048_3096576.pth +[2023-07-17 01:46:33,916][291488] Updated weights for policy 0, policy_version 6720 (0.0005) +[2023-07-17 01:46:37,743][291488] Updated weights for policy 0, policy_version 6800 (0.0005) +[2023-07-17 01:46:37,907][291207] Fps is (10 sec: 11059.2, 60 sec: 11127.5, 300 sec: 10830.1). Total num frames: 3481600. Throughput: 0: 11057.8. Samples: 3477504. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:46:37,907][291207] Avg episode reward: [(0, '435.778')] +[2023-07-17 01:46:41,574][291488] Updated weights for policy 0, policy_version 6880 (0.0005) +[2023-07-17 01:46:42,906][291207] Fps is (10 sec: 10649.7, 60 sec: 11059.2, 300 sec: 10830.1). Total num frames: 3534848. Throughput: 0: 10986.6. Samples: 3509116. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:46:42,907][291207] Avg episode reward: [(0, '454.957')] +[2023-07-17 01:46:45,319][291488] Updated weights for policy 0, policy_version 6960 (0.0005) +[2023-07-17 01:46:47,907][291207] Fps is (10 sec: 11059.1, 60 sec: 11059.2, 300 sec: 10857.9). Total num frames: 3592192. Throughput: 0: 10944.3. Samples: 3574612. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:46:47,907][291207] Avg episode reward: [(0, '438.135')] +[2023-07-17 01:46:47,910][291444] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000007016_3592192.pth... +[2023-07-17 01:46:47,913][291444] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000006368_3260416.pth +[2023-07-17 01:46:48,900][291488] Updated weights for policy 0, policy_version 7040 (0.0004) +[2023-07-17 01:46:52,473][291488] Updated weights for policy 0, policy_version 7120 (0.0004) +[2023-07-17 01:46:52,907][291207] Fps is (10 sec: 11468.8, 60 sec: 11059.2, 300 sec: 10871.8). Total num frames: 3649536. Throughput: 0: 11009.8. Samples: 3643584. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) +[2023-07-17 01:46:52,907][291207] Avg episode reward: [(0, '477.096')] +[2023-07-17 01:46:52,908][291444] Saving new best policy, reward=477.096! +[2023-07-17 01:46:56,001][291488] Updated weights for policy 0, policy_version 7200 (0.0004) +[2023-07-17 01:46:57,907][291207] Fps is (10 sec: 11468.8, 60 sec: 11059.2, 300 sec: 10885.6). Total num frames: 3706880. Throughput: 0: 11059.7. Samples: 3678280. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) +[2023-07-17 01:46:57,907][291207] Avg episode reward: [(0, '462.982')] +[2023-07-17 01:46:59,534][291488] Updated weights for policy 0, policy_version 7280 (0.0004) +[2023-07-17 01:47:02,907][291207] Fps is (10 sec: 11468.7, 60 sec: 11127.5, 300 sec: 10899.5). Total num frames: 3764224. Throughput: 0: 11145.2. Samples: 3747904. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) +[2023-07-17 01:47:02,907][291207] Avg episode reward: [(0, '441.740')] +[2023-07-17 01:47:02,911][291444] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000007352_3764224.pth... +[2023-07-17 01:47:02,914][291444] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000006696_3428352.pth +[2023-07-17 01:47:03,097][291488] Updated weights for policy 0, policy_version 7360 (0.0004) +[2023-07-17 01:47:06,760][291488] Updated weights for policy 0, policy_version 7440 (0.0005) +[2023-07-17 01:47:07,907][291207] Fps is (10 sec: 11468.8, 60 sec: 11127.5, 300 sec: 10913.4). Total num frames: 3821568. Throughput: 0: 11214.5. Samples: 3815568. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) +[2023-07-17 01:47:07,907][291207] Avg episode reward: [(0, '435.470')] +[2023-07-17 01:47:10,323][291488] Updated weights for policy 0, policy_version 7520 (0.0004) +[2023-07-17 01:47:12,907][291207] Fps is (10 sec: 11059.3, 60 sec: 11127.5, 300 sec: 10913.4). Total num frames: 3874816. Throughput: 0: 11235.5. Samples: 3850252. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:47:12,907][291207] Avg episode reward: [(0, '449.044')] +[2023-07-17 01:47:14,033][291488] Updated weights for policy 0, policy_version 7600 (0.0005) +[2023-07-17 01:47:17,907][291207] Fps is (10 sec: 10649.5, 60 sec: 11127.5, 300 sec: 10899.5). Total num frames: 3928064. Throughput: 0: 11184.8. Samples: 3915556. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:47:17,907][291207] Avg episode reward: [(0, '423.503')] +[2023-07-17 01:47:17,910][291444] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000007672_3928064.pth... +[2023-07-17 01:47:17,913][291444] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000007016_3592192.pth +[2023-07-17 01:47:17,975][291488] Updated weights for policy 0, policy_version 7680 (0.0005) +[2023-07-17 01:47:21,731][291488] Updated weights for policy 0, policy_version 7760 (0.0005) +[2023-07-17 01:47:22,906][291207] Fps is (10 sec: 11059.3, 60 sec: 11195.7, 300 sec: 10913.4). Total num frames: 3985408. Throughput: 0: 11170.2. Samples: 3980164. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:47:22,907][291207] Avg episode reward: [(0, '457.182')] +[2023-07-17 01:47:25,270][291488] Updated weights for policy 0, policy_version 7840 (0.0004) +[2023-07-17 01:47:27,906][291207] Fps is (10 sec: 11468.9, 60 sec: 11195.7, 300 sec: 10913.4). Total num frames: 4042752. Throughput: 0: 11227.9. Samples: 4014372. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:47:27,907][291207] Avg episode reward: [(0, '459.638')] +[2023-07-17 01:47:28,775][291488] Updated weights for policy 0, policy_version 7920 (0.0004) +[2023-07-17 01:47:32,290][291488] Updated weights for policy 0, policy_version 8000 (0.0004) +[2023-07-17 01:47:32,907][291207] Fps is (10 sec: 11468.7, 60 sec: 11195.7, 300 sec: 10927.3). Total num frames: 4100096. Throughput: 0: 11328.3. Samples: 4084384. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:47:32,907][291207] Avg episode reward: [(0, '471.496')] +[2023-07-17 01:47:32,911][291444] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000008008_4100096.pth... +[2023-07-17 01:47:32,913][291444] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000007352_3764224.pth +[2023-07-17 01:47:35,829][291488] Updated weights for policy 0, policy_version 8080 (0.0004) +[2023-07-17 01:47:37,907][291207] Fps is (10 sec: 11468.8, 60 sec: 11264.0, 300 sec: 10927.3). Total num frames: 4157440. Throughput: 0: 11328.0. Samples: 4153344. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:47:37,908][291207] Avg episode reward: [(0, '494.047')] +[2023-07-17 01:47:37,908][291444] Saving new best policy, reward=494.047! +[2023-07-17 01:47:39,564][291488] Updated weights for policy 0, policy_version 8160 (0.0005) +[2023-07-17 01:47:42,907][291207] Fps is (10 sec: 11059.3, 60 sec: 11264.0, 300 sec: 10927.3). Total num frames: 4210688. Throughput: 0: 11286.8. Samples: 4186184. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:47:42,908][291207] Avg episode reward: [(0, '470.926')] +[2023-07-17 01:47:43,303][291488] Updated weights for policy 0, policy_version 8240 (0.0005) +[2023-07-17 01:47:46,917][291488] Updated weights for policy 0, policy_version 8320 (0.0005) +[2023-07-17 01:47:47,907][291207] Fps is (10 sec: 11059.1, 60 sec: 11264.0, 300 sec: 10927.3). Total num frames: 4268032. Throughput: 0: 11217.9. Samples: 4252708. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:47:47,908][291207] Avg episode reward: [(0, '482.086')] +[2023-07-17 01:47:47,911][291444] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000008336_4268032.pth... +[2023-07-17 01:47:47,914][291444] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000007672_3928064.pth +[2023-07-17 01:47:50,525][291488] Updated weights for policy 0, policy_version 8400 (0.0005) +[2023-07-17 01:47:52,906][291207] Fps is (10 sec: 11468.8, 60 sec: 11264.0, 300 sec: 10941.2). Total num frames: 4325376. Throughput: 0: 11238.2. Samples: 4321288. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) +[2023-07-17 01:47:52,908][291207] Avg episode reward: [(0, '479.643')] +[2023-07-17 01:47:54,244][291488] Updated weights for policy 0, policy_version 8480 (0.0004) +[2023-07-17 01:47:57,906][291207] Fps is (10 sec: 11059.3, 60 sec: 11195.7, 300 sec: 10941.2). Total num frames: 4378624. Throughput: 0: 11192.4. Samples: 4353908. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) +[2023-07-17 01:47:57,908][291207] Avg episode reward: [(0, '482.988')] +[2023-07-17 01:47:58,143][291488] Updated weights for policy 0, policy_version 8560 (0.0005) +[2023-07-17 01:48:01,942][291488] Updated weights for policy 0, policy_version 8640 (0.0005) +[2023-07-17 01:48:02,907][291207] Fps is (10 sec: 10649.5, 60 sec: 11127.5, 300 sec: 10941.2). Total num frames: 4431872. Throughput: 0: 11142.9. Samples: 4416988. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:48:02,907][291207] Avg episode reward: [(0, '479.843')] +[2023-07-17 01:48:02,910][291444] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000008656_4431872.pth... +[2023-07-17 01:48:02,913][291444] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000008008_4100096.pth +[2023-07-17 01:48:05,710][291488] Updated weights for policy 0, policy_version 8720 (0.0005) +[2023-07-17 01:48:07,907][291207] Fps is (10 sec: 10649.5, 60 sec: 11059.2, 300 sec: 10927.3). Total num frames: 4485120. Throughput: 0: 11144.2. Samples: 4481652. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) +[2023-07-17 01:48:07,908][291207] Avg episode reward: [(0, '492.200')] +[2023-07-17 01:48:09,391][291488] Updated weights for policy 0, policy_version 8800 (0.0005) +[2023-07-17 01:48:12,903][291488] Updated weights for policy 0, policy_version 8880 (0.0004) +[2023-07-17 01:48:12,907][291207] Fps is (10 sec: 11468.9, 60 sec: 11195.7, 300 sec: 10955.1). Total num frames: 4546560. Throughput: 0: 11153.7. Samples: 4516288. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) +[2023-07-17 01:48:12,908][291207] Avg episode reward: [(0, '456.387')] +[2023-07-17 01:48:16,441][291488] Updated weights for policy 0, policy_version 8960 (0.0005) +[2023-07-17 01:48:17,907][291207] Fps is (10 sec: 11878.4, 60 sec: 11264.0, 300 sec: 10955.1). Total num frames: 4603904. Throughput: 0: 11154.9. Samples: 4586352. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) +[2023-07-17 01:48:17,907][291207] Avg episode reward: [(0, '419.771')] +[2023-07-17 01:48:17,911][291444] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000008992_4603904.pth... +[2023-07-17 01:48:17,913][291444] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000008336_4268032.pth +[2023-07-17 01:48:20,120][291488] Updated weights for policy 0, policy_version 9040 (0.0005) +[2023-07-17 01:48:22,906][291207] Fps is (10 sec: 11059.3, 60 sec: 11195.7, 300 sec: 10955.1). Total num frames: 4657152. Throughput: 0: 11097.3. Samples: 4652724. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:48:22,908][291207] Avg episode reward: [(0, '438.342')] +[2023-07-17 01:48:23,945][291488] Updated weights for policy 0, policy_version 9120 (0.0005) +[2023-07-17 01:48:27,760][291488] Updated weights for policy 0, policy_version 9200 (0.0005) +[2023-07-17 01:48:27,907][291207] Fps is (10 sec: 10649.6, 60 sec: 11127.5, 300 sec: 10941.2). Total num frames: 4710400. Throughput: 0: 11071.8. Samples: 4684416. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:48:27,941][291207] Avg episode reward: [(0, '442.055')] +[2023-07-17 01:48:31,618][291488] Updated weights for policy 0, policy_version 9280 (0.0005) +[2023-07-17 01:48:32,907][291207] Fps is (10 sec: 10649.5, 60 sec: 11059.2, 300 sec: 10941.2). Total num frames: 4763648. Throughput: 0: 11011.3. Samples: 4748216. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) +[2023-07-17 01:48:32,908][291207] Avg episode reward: [(0, '458.412')] +[2023-07-17 01:48:32,911][291444] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000009304_4763648.pth... +[2023-07-17 01:48:32,914][291444] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000008656_4431872.pth +[2023-07-17 01:48:35,431][291488] Updated weights for policy 0, policy_version 9360 (0.0005) +[2023-07-17 01:48:37,907][291207] Fps is (10 sec: 10649.6, 60 sec: 10990.9, 300 sec: 10955.1). Total num frames: 4816896. Throughput: 0: 10931.5. Samples: 4813204. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) +[2023-07-17 01:48:37,908][291207] Avg episode reward: [(0, '465.126')] +[2023-07-17 01:48:39,129][291488] Updated weights for policy 0, policy_version 9440 (0.0005) +[2023-07-17 01:48:42,907][291207] Fps is (10 sec: 10649.6, 60 sec: 10990.9, 300 sec: 10955.1). Total num frames: 4870144. Throughput: 0: 10929.1. Samples: 4845720. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) +[2023-07-17 01:48:42,908][291207] Avg episode reward: [(0, '497.527')] +[2023-07-17 01:48:42,958][291444] Saving new best policy, reward=497.527! +[2023-07-17 01:48:42,959][291488] Updated weights for policy 0, policy_version 9520 (0.0005) +[2023-07-17 01:48:46,709][291488] Updated weights for policy 0, policy_version 9600 (0.0006) +[2023-07-17 01:48:47,907][291207] Fps is (10 sec: 11059.2, 60 sec: 10990.9, 300 sec: 10968.9). Total num frames: 4927488. Throughput: 0: 10980.5. Samples: 4911112. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:48:47,908][291207] Avg episode reward: [(0, '509.455')] +[2023-07-17 01:48:47,910][291444] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000009624_4927488.pth... +[2023-07-17 01:48:47,913][291444] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000008992_4603904.pth +[2023-07-17 01:48:47,914][291444] Saving new best policy, reward=509.455! +[2023-07-17 01:48:50,449][291488] Updated weights for policy 0, policy_version 9680 (0.0005) +[2023-07-17 01:48:52,907][291207] Fps is (10 sec: 11059.2, 60 sec: 10922.7, 300 sec: 10969.0). Total num frames: 4980736. Throughput: 0: 10999.9. Samples: 4976648. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) +[2023-07-17 01:48:52,907][291207] Avg episode reward: [(0, '516.231')] +[2023-07-17 01:48:52,908][291444] Saving new best policy, reward=516.231! +[2023-07-17 01:48:54,242][291488] Updated weights for policy 0, policy_version 9760 (0.0005) +[2023-07-17 01:48:57,906][291207] Fps is (10 sec: 10649.7, 60 sec: 10922.7, 300 sec: 10969.0). Total num frames: 5033984. Throughput: 0: 10958.2. Samples: 5009408. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) +[2023-07-17 01:48:57,907][291207] Avg episode reward: [(0, '497.782')] +[2023-07-17 01:48:57,971][291488] Updated weights for policy 0, policy_version 9840 (0.0005) +[2023-07-17 01:49:01,793][291488] Updated weights for policy 0, policy_version 9920 (0.0005) +[2023-07-17 01:49:02,907][291207] Fps is (10 sec: 10649.6, 60 sec: 10922.7, 300 sec: 10968.9). Total num frames: 5087232. Throughput: 0: 10847.7. Samples: 5074500. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:49:02,907][291207] Avg episode reward: [(0, '511.862')] +[2023-07-17 01:49:02,939][291444] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000009944_5091328.pth... +[2023-07-17 01:49:02,941][291444] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000009304_4763648.pth +[2023-07-17 01:49:05,620][291488] Updated weights for policy 0, policy_version 10000 (0.0005) +[2023-07-17 01:49:07,907][291207] Fps is (10 sec: 10649.6, 60 sec: 10922.7, 300 sec: 10968.9). Total num frames: 5140480. Throughput: 0: 10785.9. Samples: 5138092. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:49:07,907][291207] Avg episode reward: [(0, '502.690')] +[2023-07-17 01:49:09,419][291488] Updated weights for policy 0, policy_version 10080 (0.0005) +[2023-07-17 01:49:12,907][291207] Fps is (10 sec: 11059.2, 60 sec: 10854.4, 300 sec: 10982.8). Total num frames: 5197824. Throughput: 0: 10818.3. Samples: 5171240. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) +[2023-07-17 01:49:12,907][291207] Avg episode reward: [(0, '508.881')] +[2023-07-17 01:49:13,141][291488] Updated weights for policy 0, policy_version 10160 (0.0005) +[2023-07-17 01:49:16,917][291488] Updated weights for policy 0, policy_version 10240 (0.0005) +[2023-07-17 01:49:17,907][291207] Fps is (10 sec: 11059.1, 60 sec: 10786.1, 300 sec: 10982.8). Total num frames: 5251072. Throughput: 0: 10860.3. Samples: 5236928. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:49:17,907][291207] Avg episode reward: [(0, '518.915')] +[2023-07-17 01:49:17,910][291444] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000010256_5251072.pth... +[2023-07-17 01:49:17,913][291444] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000009624_4927488.pth +[2023-07-17 01:49:17,914][291444] Saving new best policy, reward=518.915! +[2023-07-17 01:49:20,792][291488] Updated weights for policy 0, policy_version 10320 (0.0005) +[2023-07-17 01:49:22,907][291207] Fps is (10 sec: 10649.6, 60 sec: 10786.1, 300 sec: 10982.8). Total num frames: 5304320. Throughput: 0: 10835.1. Samples: 5300784. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:49:22,907][291207] Avg episode reward: [(0, '509.967')] +[2023-07-17 01:49:24,517][291488] Updated weights for policy 0, policy_version 10400 (0.0005) +[2023-07-17 01:49:27,907][291207] Fps is (10 sec: 10649.7, 60 sec: 10786.1, 300 sec: 10982.8). Total num frames: 5357568. Throughput: 0: 10834.0. Samples: 5333252. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:49:27,907][291207] Avg episode reward: [(0, '503.678')] +[2023-07-17 01:49:28,355][291488] Updated weights for policy 0, policy_version 10480 (0.0005) +[2023-07-17 01:49:32,116][291488] Updated weights for policy 0, policy_version 10560 (0.0005) +[2023-07-17 01:49:32,907][291207] Fps is (10 sec: 11059.2, 60 sec: 10854.4, 300 sec: 11010.6). Total num frames: 5414912. Throughput: 0: 10831.6. Samples: 5398536. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:49:32,907][291207] Avg episode reward: [(0, '499.403')] +[2023-07-17 01:49:32,910][291444] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000010576_5414912.pth... +[2023-07-17 01:49:32,912][291444] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000009944_5091328.pth +[2023-07-17 01:49:35,901][291488] Updated weights for policy 0, policy_version 10640 (0.0005) +[2023-07-17 01:49:37,907][291207] Fps is (10 sec: 11059.2, 60 sec: 10854.4, 300 sec: 10996.7). Total num frames: 5468160. Throughput: 0: 10825.1. Samples: 5463776. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:49:37,907][291207] Avg episode reward: [(0, '490.843')] +[2023-07-17 01:49:39,765][291488] Updated weights for policy 0, policy_version 10720 (0.0005) +[2023-07-17 01:49:42,906][291207] Fps is (10 sec: 10649.7, 60 sec: 10854.4, 300 sec: 10996.7). Total num frames: 5521408. Throughput: 0: 10781.1. Samples: 5494556. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:49:42,907][291207] Avg episode reward: [(0, '500.609')] +[2023-07-17 01:49:43,493][291488] Updated weights for policy 0, policy_version 10800 (0.0005) +[2023-07-17 01:49:47,312][291488] Updated weights for policy 0, policy_version 10880 (0.0005) +[2023-07-17 01:49:47,907][291207] Fps is (10 sec: 10649.6, 60 sec: 10786.1, 300 sec: 10996.7). Total num frames: 5574656. Throughput: 0: 10792.9. Samples: 5560180. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:49:47,907][291207] Avg episode reward: [(0, '491.970')] +[2023-07-17 01:49:47,910][291444] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000010888_5574656.pth... +[2023-07-17 01:49:47,913][291444] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000010256_5251072.pth +[2023-07-17 01:49:51,065][291488] Updated weights for policy 0, policy_version 10960 (0.0005) +[2023-07-17 01:49:52,907][291207] Fps is (10 sec: 10649.5, 60 sec: 10786.1, 300 sec: 10996.7). Total num frames: 5627904. Throughput: 0: 10827.9. Samples: 5625348. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:49:52,908][291207] Avg episode reward: [(0, '484.101')] +[2023-07-17 01:49:54,812][291488] Updated weights for policy 0, policy_version 11040 (0.0005) +[2023-07-17 01:49:57,906][291207] Fps is (10 sec: 11059.3, 60 sec: 10854.4, 300 sec: 11010.6). Total num frames: 5685248. Throughput: 0: 10822.8. Samples: 5658264. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:49:57,907][291207] Avg episode reward: [(0, '502.352')] +[2023-07-17 01:49:58,529][291488] Updated weights for policy 0, policy_version 11120 (0.0005) +[2023-07-17 01:50:02,305][291488] Updated weights for policy 0, policy_version 11200 (0.0005) +[2023-07-17 01:50:02,907][291207] Fps is (10 sec: 11059.2, 60 sec: 10854.4, 300 sec: 11010.6). Total num frames: 5738496. Throughput: 0: 10816.5. Samples: 5723668. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:50:02,907][291207] Avg episode reward: [(0, '470.627')] +[2023-07-17 01:50:02,911][291444] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000011208_5738496.pth... +[2023-07-17 01:50:02,914][291444] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000010576_5414912.pth +[2023-07-17 01:50:06,018][291488] Updated weights for policy 0, policy_version 11280 (0.0005) +[2023-07-17 01:50:07,906][291207] Fps is (10 sec: 11059.2, 60 sec: 10922.7, 300 sec: 11024.5). Total num frames: 5795840. Throughput: 0: 10858.1. Samples: 5789400. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) +[2023-07-17 01:50:07,907][291207] Avg episode reward: [(0, '490.145')] +[2023-07-17 01:50:09,733][291488] Updated weights for policy 0, policy_version 11360 (0.0005) +[2023-07-17 01:50:12,906][291207] Fps is (10 sec: 11059.3, 60 sec: 10854.4, 300 sec: 11024.5). Total num frames: 5849088. Throughput: 0: 10884.1. Samples: 5823036. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) +[2023-07-17 01:50:12,907][291207] Avg episode reward: [(0, '487.811')] +[2023-07-17 01:50:13,478][291488] Updated weights for policy 0, policy_version 11440 (0.0005) +[2023-07-17 01:50:17,251][291488] Updated weights for policy 0, policy_version 11520 (0.0005) +[2023-07-17 01:50:17,907][291207] Fps is (10 sec: 10649.5, 60 sec: 10854.4, 300 sec: 11024.5). Total num frames: 5902336. Throughput: 0: 10887.3. Samples: 5888464. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) +[2023-07-17 01:50:17,907][291207] Avg episode reward: [(0, '486.840')] +[2023-07-17 01:50:17,911][291444] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000011528_5902336.pth... +[2023-07-17 01:50:17,914][291444] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000010888_5574656.pth +[2023-07-17 01:50:20,814][291488] Updated weights for policy 0, policy_version 11600 (0.0005) +[2023-07-17 01:50:22,907][291207] Fps is (10 sec: 11059.2, 60 sec: 10922.7, 300 sec: 11038.4). Total num frames: 5959680. Throughput: 0: 10944.0. Samples: 5956256. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) +[2023-07-17 01:50:22,908][291207] Avg episode reward: [(0, '504.200')] +[2023-07-17 01:50:24,423][291488] Updated weights for policy 0, policy_version 11680 (0.0004) +[2023-07-17 01:50:27,907][291207] Fps is (10 sec: 11468.8, 60 sec: 10990.9, 300 sec: 11038.4). Total num frames: 6017024. Throughput: 0: 11002.6. Samples: 5989676. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:50:27,908][291207] Avg episode reward: [(0, '519.194')] +[2023-07-17 01:50:27,908][291444] Saving new best policy, reward=519.194! +[2023-07-17 01:50:28,215][291488] Updated weights for policy 0, policy_version 11760 (0.0005) +[2023-07-17 01:50:31,989][291488] Updated weights for policy 0, policy_version 11840 (0.0005) +[2023-07-17 01:50:32,907][291207] Fps is (10 sec: 11059.1, 60 sec: 10922.7, 300 sec: 11038.4). Total num frames: 6070272. Throughput: 0: 10990.2. Samples: 6054740. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:50:32,907][291207] Avg episode reward: [(0, '521.067')] +[2023-07-17 01:50:32,910][291444] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000011856_6070272.pth... +[2023-07-17 01:50:32,913][291444] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000011208_5738496.pth +[2023-07-17 01:50:32,914][291444] Saving new best policy, reward=521.067! +[2023-07-17 01:50:35,710][291488] Updated weights for policy 0, policy_version 11920 (0.0005) +[2023-07-17 01:50:37,907][291207] Fps is (10 sec: 10649.6, 60 sec: 10922.7, 300 sec: 11024.5). Total num frames: 6123520. Throughput: 0: 10992.1. Samples: 6119992. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) +[2023-07-17 01:50:37,908][291207] Avg episode reward: [(0, '503.954')] +[2023-07-17 01:50:39,492][291488] Updated weights for policy 0, policy_version 12000 (0.0005) +[2023-07-17 01:50:42,907][291207] Fps is (10 sec: 11059.2, 60 sec: 10990.9, 300 sec: 11024.5). Total num frames: 6180864. Throughput: 0: 10989.8. Samples: 6152804. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) +[2023-07-17 01:50:42,908][291207] Avg episode reward: [(0, '490.305')] +[2023-07-17 01:50:43,262][291488] Updated weights for policy 0, policy_version 12080 (0.0005) +[2023-07-17 01:50:47,052][291488] Updated weights for policy 0, policy_version 12160 (0.0005) +[2023-07-17 01:50:47,907][291207] Fps is (10 sec: 11059.1, 60 sec: 10990.9, 300 sec: 11010.6). Total num frames: 6234112. Throughput: 0: 10980.5. Samples: 6217792. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:50:47,908][291207] Avg episode reward: [(0, '495.922')] +[2023-07-17 01:50:47,911][291444] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000012176_6234112.pth... +[2023-07-17 01:50:47,914][291444] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000011528_5902336.pth +[2023-07-17 01:50:50,697][291488] Updated weights for policy 0, policy_version 12240 (0.0005) +[2023-07-17 01:50:52,907][291207] Fps is (10 sec: 10649.6, 60 sec: 10990.9, 300 sec: 10996.7). Total num frames: 6287360. Throughput: 0: 10998.2. Samples: 6284320. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:50:52,908][291207] Avg episode reward: [(0, '470.347')] +[2023-07-17 01:50:54,501][291488] Updated weights for policy 0, policy_version 12320 (0.0005) +[2023-07-17 01:50:57,907][291207] Fps is (10 sec: 11059.3, 60 sec: 10990.9, 300 sec: 11010.6). Total num frames: 6344704. Throughput: 0: 10968.0. Samples: 6316596. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) +[2023-07-17 01:50:57,907][291207] Avg episode reward: [(0, '499.222')] +[2023-07-17 01:50:58,273][291488] Updated weights for policy 0, policy_version 12400 (0.0005) +[2023-07-17 01:51:01,866][291488] Updated weights for policy 0, policy_version 12480 (0.0005) +[2023-07-17 01:51:02,906][291207] Fps is (10 sec: 11468.9, 60 sec: 11059.2, 300 sec: 11010.6). Total num frames: 6402048. Throughput: 0: 10996.0. Samples: 6383284. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) +[2023-07-17 01:51:02,907][291207] Avg episode reward: [(0, '488.567')] +[2023-07-17 01:51:02,911][291444] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000012504_6402048.pth... +[2023-07-17 01:51:02,913][291444] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000011856_6070272.pth +[2023-07-17 01:51:05,377][291488] Updated weights for policy 0, policy_version 12560 (0.0004) +[2023-07-17 01:51:07,907][291207] Fps is (10 sec: 11468.8, 60 sec: 11059.2, 300 sec: 11024.5). Total num frames: 6459392. Throughput: 0: 11034.2. Samples: 6452796. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) +[2023-07-17 01:51:07,908][291207] Avg episode reward: [(0, '491.925')] +[2023-07-17 01:51:08,980][291488] Updated weights for policy 0, policy_version 12640 (0.0005) +[2023-07-17 01:51:12,541][291488] Updated weights for policy 0, policy_version 12720 (0.0004) +[2023-07-17 01:51:12,907][291207] Fps is (10 sec: 11468.7, 60 sec: 11127.5, 300 sec: 11038.4). Total num frames: 6516736. Throughput: 0: 11059.1. Samples: 6487336. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:51:12,907][291207] Avg episode reward: [(0, '501.329')] +[2023-07-17 01:51:16,056][291488] Updated weights for policy 0, policy_version 12800 (0.0004) +[2023-07-17 01:51:17,907][291207] Fps is (10 sec: 11468.7, 60 sec: 11195.7, 300 sec: 11052.3). Total num frames: 6574080. Throughput: 0: 11158.9. Samples: 6556892. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:51:17,908][291207] Avg episode reward: [(0, '507.353')] +[2023-07-17 01:51:17,911][291444] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000012840_6574080.pth... +[2023-07-17 01:51:17,913][291444] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000012176_6234112.pth +[2023-07-17 01:51:19,538][291488] Updated weights for policy 0, policy_version 12880 (0.0004) +[2023-07-17 01:51:22,907][291207] Fps is (10 sec: 11468.8, 60 sec: 11195.7, 300 sec: 11052.3). Total num frames: 6631424. Throughput: 0: 11270.8. Samples: 6627176. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:51:22,908][291207] Avg episode reward: [(0, '513.279')] +[2023-07-17 01:51:23,069][291488] Updated weights for policy 0, policy_version 12960 (0.0004) +[2023-07-17 01:51:26,746][291488] Updated weights for policy 0, policy_version 13040 (0.0005) +[2023-07-17 01:51:27,907][291207] Fps is (10 sec: 11468.9, 60 sec: 11195.7, 300 sec: 11052.3). Total num frames: 6688768. Throughput: 0: 11297.5. Samples: 6661192. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:51:27,907][291207] Avg episode reward: [(0, '518.436')] +[2023-07-17 01:51:30,477][291488] Updated weights for policy 0, policy_version 13120 (0.0005) +[2023-07-17 01:51:32,907][291207] Fps is (10 sec: 11059.2, 60 sec: 11195.7, 300 sec: 11052.3). Total num frames: 6742016. Throughput: 0: 11302.4. Samples: 6726400. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:51:32,907][291207] Avg episode reward: [(0, '474.859')] +[2023-07-17 01:51:32,909][291444] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000013168_6742016.pth... +[2023-07-17 01:51:32,912][291444] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000012504_6402048.pth +[2023-07-17 01:51:34,105][291488] Updated weights for policy 0, policy_version 13200 (0.0005) +[2023-07-17 01:51:37,665][291488] Updated weights for policy 0, policy_version 13280 (0.0004) +[2023-07-17 01:51:37,906][291207] Fps is (10 sec: 11059.3, 60 sec: 11264.0, 300 sec: 11066.1). Total num frames: 6799360. Throughput: 0: 11355.7. Samples: 6795328. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:51:37,907][291207] Avg episode reward: [(0, '488.580')] +[2023-07-17 01:51:41,545][291488] Updated weights for policy 0, policy_version 13360 (0.0005) +[2023-07-17 01:51:42,907][291207] Fps is (10 sec: 11059.2, 60 sec: 11195.7, 300 sec: 11052.3). Total num frames: 6852608. Throughput: 0: 11363.0. Samples: 6827932. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) +[2023-07-17 01:51:42,907][291207] Avg episode reward: [(0, '497.765')] +[2023-07-17 01:51:45,360][291488] Updated weights for policy 0, policy_version 13440 (0.0005) +[2023-07-17 01:51:47,907][291207] Fps is (10 sec: 10649.5, 60 sec: 11195.7, 300 sec: 11038.4). Total num frames: 6905856. Throughput: 0: 11300.2. Samples: 6891796. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) +[2023-07-17 01:51:47,907][291207] Avg episode reward: [(0, '510.398')] +[2023-07-17 01:51:47,910][291444] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000013488_6905856.pth... +[2023-07-17 01:51:47,913][291444] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000012840_6574080.pth +[2023-07-17 01:51:49,160][291488] Updated weights for policy 0, policy_version 13520 (0.0005) +[2023-07-17 01:51:52,893][291488] Updated weights for policy 0, policy_version 13600 (0.0005) +[2023-07-17 01:51:52,907][291207] Fps is (10 sec: 11059.2, 60 sec: 11264.0, 300 sec: 11038.4). Total num frames: 6963200. Throughput: 0: 11210.2. Samples: 6957256. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) +[2023-07-17 01:51:52,907][291207] Avg episode reward: [(0, '503.877')] +[2023-07-17 01:51:56,619][291488] Updated weights for policy 0, policy_version 13680 (0.0005) +[2023-07-17 01:51:57,906][291207] Fps is (10 sec: 11059.3, 60 sec: 11195.7, 300 sec: 11024.5). Total num frames: 7016448. Throughput: 0: 11156.9. Samples: 6989396. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) +[2023-07-17 01:51:57,907][291207] Avg episode reward: [(0, '515.478')] +[2023-07-17 01:52:00,128][291488] Updated weights for policy 0, policy_version 13760 (0.0004) +[2023-07-17 01:52:02,907][291207] Fps is (10 sec: 11059.2, 60 sec: 11195.7, 300 sec: 11024.5). Total num frames: 7073792. Throughput: 0: 11153.6. Samples: 7058804. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) +[2023-07-17 01:52:02,907][291207] Avg episode reward: [(0, '494.880')] +[2023-07-17 01:52:02,910][291444] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000013816_7073792.pth... +[2023-07-17 01:52:02,912][291444] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000013168_6742016.pth +[2023-07-17 01:52:03,657][291488] Updated weights for policy 0, policy_version 13840 (0.0004) +[2023-07-17 01:52:07,174][291488] Updated weights for policy 0, policy_version 13920 (0.0004) +[2023-07-17 01:52:07,907][291207] Fps is (10 sec: 11878.4, 60 sec: 11264.0, 300 sec: 11052.3). Total num frames: 7135232. Throughput: 0: 11142.9. Samples: 7128608. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) +[2023-07-17 01:52:07,907][291207] Avg episode reward: [(0, '500.279')] +[2023-07-17 01:52:10,572][291488] Updated weights for policy 0, policy_version 14000 (0.0003) +[2023-07-17 01:52:12,907][291207] Fps is (10 sec: 11878.5, 60 sec: 11264.0, 300 sec: 11066.1). Total num frames: 7192576. Throughput: 0: 11189.7. Samples: 7164728. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) +[2023-07-17 01:52:12,907][291207] Avg episode reward: [(0, '498.258')] +[2023-07-17 01:52:14,166][291488] Updated weights for policy 0, policy_version 14080 (0.0005) +[2023-07-17 01:52:17,759][291488] Updated weights for policy 0, policy_version 14160 (0.0004) +[2023-07-17 01:52:17,907][291207] Fps is (10 sec: 11468.7, 60 sec: 11264.0, 300 sec: 11066.1). Total num frames: 7249920. Throughput: 0: 11271.1. Samples: 7233600. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) +[2023-07-17 01:52:17,907][291207] Avg episode reward: [(0, '512.410')] +[2023-07-17 01:52:17,910][291444] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000014160_7249920.pth... +[2023-07-17 01:52:17,913][291444] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000013488_6905856.pth +[2023-07-17 01:52:21,265][291488] Updated weights for policy 0, policy_version 14240 (0.0004) +[2023-07-17 01:52:22,907][291207] Fps is (10 sec: 11468.8, 60 sec: 11264.0, 300 sec: 11066.1). Total num frames: 7307264. Throughput: 0: 11286.8. Samples: 7303232. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) +[2023-07-17 01:52:22,907][291207] Avg episode reward: [(0, '518.677')] +[2023-07-17 01:52:24,798][291488] Updated weights for policy 0, policy_version 14320 (0.0004) +[2023-07-17 01:52:27,907][291207] Fps is (10 sec: 11468.9, 60 sec: 11264.0, 300 sec: 11066.1). Total num frames: 7364608. Throughput: 0: 11328.6. Samples: 7337720. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:52:27,907][291207] Avg episode reward: [(0, '536.035')] +[2023-07-17 01:52:27,908][291444] Saving new best policy, reward=536.035! +[2023-07-17 01:52:28,427][291488] Updated weights for policy 0, policy_version 14400 (0.0005) +[2023-07-17 01:52:32,220][291488] Updated weights for policy 0, policy_version 14480 (0.0005) +[2023-07-17 01:52:32,907][291207] Fps is (10 sec: 11059.1, 60 sec: 11264.0, 300 sec: 11052.3). Total num frames: 7417856. Throughput: 0: 11396.0. Samples: 7404616. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:52:32,907][291207] Avg episode reward: [(0, '503.231')] +[2023-07-17 01:52:32,910][291444] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000014488_7417856.pth... +[2023-07-17 01:52:32,913][291444] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000013816_7073792.pth +[2023-07-17 01:52:36,002][291488] Updated weights for policy 0, policy_version 14560 (0.0005) +[2023-07-17 01:52:37,907][291207] Fps is (10 sec: 11059.2, 60 sec: 11264.0, 300 sec: 11066.1). Total num frames: 7475200. Throughput: 0: 11379.6. Samples: 7469336. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:52:37,907][291207] Avg episode reward: [(0, '493.554')] +[2023-07-17 01:52:39,796][291488] Updated weights for policy 0, policy_version 14640 (0.0005) +[2023-07-17 01:52:42,907][291207] Fps is (10 sec: 11059.2, 60 sec: 11264.0, 300 sec: 11052.3). Total num frames: 7528448. Throughput: 0: 11373.9. Samples: 7501220. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:52:42,907][291207] Avg episode reward: [(0, '513.016')] +[2023-07-17 01:52:43,636][291488] Updated weights for policy 0, policy_version 14720 (0.0005) +[2023-07-17 01:52:47,416][291488] Updated weights for policy 0, policy_version 14800 (0.0005) +[2023-07-17 01:52:47,907][291207] Fps is (10 sec: 10649.5, 60 sec: 11264.0, 300 sec: 11038.4). Total num frames: 7581696. Throughput: 0: 11257.3. Samples: 7565384. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:52:47,907][291207] Avg episode reward: [(0, '494.390')] +[2023-07-17 01:52:47,910][291444] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000014808_7581696.pth... +[2023-07-17 01:52:47,913][291444] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000014160_7249920.pth +[2023-07-17 01:52:51,298][291488] Updated weights for policy 0, policy_version 14880 (0.0005) +[2023-07-17 01:52:52,907][291207] Fps is (10 sec: 10649.6, 60 sec: 11195.7, 300 sec: 11038.4). Total num frames: 7634944. Throughput: 0: 11141.5. Samples: 7629976. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:52:52,907][291207] Avg episode reward: [(0, '511.728')] +[2023-07-17 01:52:55,155][291488] Updated weights for policy 0, policy_version 14960 (0.0005) +[2023-07-17 01:52:57,907][291207] Fps is (10 sec: 10649.7, 60 sec: 11195.7, 300 sec: 11038.4). Total num frames: 7688192. Throughput: 0: 11037.6. Samples: 7661420. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:52:57,907][291207] Avg episode reward: [(0, '510.239')] +[2023-07-17 01:52:58,924][291488] Updated weights for policy 0, policy_version 15040 (0.0006) +[2023-07-17 01:53:02,802][291488] Updated weights for policy 0, policy_version 15120 (0.0006) +[2023-07-17 01:53:02,907][291207] Fps is (10 sec: 10649.6, 60 sec: 11127.5, 300 sec: 11038.4). Total num frames: 7741440. Throughput: 0: 10928.8. Samples: 7725396. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:53:02,907][291207] Avg episode reward: [(0, '508.113')] +[2023-07-17 01:53:02,910][291444] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000015120_7741440.pth... +[2023-07-17 01:53:02,913][291444] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000014488_7417856.pth +[2023-07-17 01:53:06,553][291488] Updated weights for policy 0, policy_version 15200 (0.0006) +[2023-07-17 01:53:07,906][291207] Fps is (10 sec: 10649.6, 60 sec: 10990.9, 300 sec: 11010.6). Total num frames: 7794688. Throughput: 0: 10831.6. Samples: 7790656. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:53:07,907][291207] Avg episode reward: [(0, '495.123')] +[2023-07-17 01:53:10,356][291488] Updated weights for policy 0, policy_version 15280 (0.0006) +[2023-07-17 01:53:12,907][291207] Fps is (10 sec: 10649.6, 60 sec: 10922.7, 300 sec: 10996.7). Total num frames: 7847936. Throughput: 0: 10792.0. Samples: 7823360. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:53:12,907][291207] Avg episode reward: [(0, '516.544')] +[2023-07-17 01:53:13,959][291488] Updated weights for policy 0, policy_version 15360 (0.0005) +[2023-07-17 01:53:17,580][291488] Updated weights for policy 0, policy_version 15440 (0.0005) +[2023-07-17 01:53:17,907][291207] Fps is (10 sec: 11059.1, 60 sec: 10922.7, 300 sec: 11010.6). Total num frames: 7905280. Throughput: 0: 10811.7. Samples: 7891144. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:53:17,907][291207] Avg episode reward: [(0, '489.787')] +[2023-07-17 01:53:17,910][291444] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000015440_7905280.pth... +[2023-07-17 01:53:17,913][291444] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000014808_7581696.pth +[2023-07-17 01:53:21,325][291488] Updated weights for policy 0, policy_version 15520 (0.0005) +[2023-07-17 01:53:22,907][291207] Fps is (10 sec: 11468.8, 60 sec: 10922.7, 300 sec: 11024.5). Total num frames: 7962624. Throughput: 0: 10853.3. Samples: 7957736. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:53:22,907][291207] Avg episode reward: [(0, '498.795')] +[2023-07-17 01:53:24,829][291488] Updated weights for policy 0, policy_version 15600 (0.0004) +[2023-07-17 01:53:27,906][291207] Fps is (10 sec: 11468.9, 60 sec: 10922.7, 300 sec: 11038.4). Total num frames: 8019968. Throughput: 0: 10919.4. Samples: 7992592. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:53:27,907][291207] Avg episode reward: [(0, '505.123')] +[2023-07-17 01:53:28,606][291488] Updated weights for policy 0, policy_version 15680 (0.0005) +[2023-07-17 01:53:32,443][291488] Updated weights for policy 0, policy_version 15760 (0.0006) +[2023-07-17 01:53:32,907][291207] Fps is (10 sec: 11059.1, 60 sec: 10922.7, 300 sec: 11038.4). Total num frames: 8073216. Throughput: 0: 10922.5. Samples: 8056896. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:53:32,907][291207] Avg episode reward: [(0, '512.623')] +[2023-07-17 01:53:32,910][291444] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000015768_8073216.pth... +[2023-07-17 01:53:32,913][291444] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000015120_7741440.pth +[2023-07-17 01:53:36,205][291488] Updated weights for policy 0, policy_version 15840 (0.0006) +[2023-07-17 01:53:37,907][291207] Fps is (10 sec: 10649.5, 60 sec: 10854.4, 300 sec: 11038.4). Total num frames: 8126464. Throughput: 0: 10943.5. Samples: 8122432. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:53:37,907][291207] Avg episode reward: [(0, '515.491')] +[2023-07-17 01:53:39,986][291488] Updated weights for policy 0, policy_version 15920 (0.0006) +[2023-07-17 01:53:42,907][291207] Fps is (10 sec: 10649.7, 60 sec: 10854.4, 300 sec: 11024.5). Total num frames: 8179712. Throughput: 0: 10971.5. Samples: 8155136. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:53:42,907][291207] Avg episode reward: [(0, '517.768')] +[2023-07-17 01:53:43,758][291488] Updated weights for policy 0, policy_version 16000 (0.0006) +[2023-07-17 01:53:47,489][291488] Updated weights for policy 0, policy_version 16080 (0.0006) +[2023-07-17 01:53:47,907][291207] Fps is (10 sec: 11059.2, 60 sec: 10922.7, 300 sec: 11038.4). Total num frames: 8237056. Throughput: 0: 11004.4. Samples: 8220592. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:53:47,907][291207] Avg episode reward: [(0, '525.871')] +[2023-07-17 01:53:47,910][291444] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000016088_8237056.pth... +[2023-07-17 01:53:47,913][291444] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000015440_7905280.pth +[2023-07-17 01:53:51,336][291488] Updated weights for policy 0, policy_version 16160 (0.0006) +[2023-07-17 01:53:52,907][291207] Fps is (10 sec: 11059.2, 60 sec: 10922.7, 300 sec: 11038.4). Total num frames: 8290304. Throughput: 0: 10979.6. Samples: 8284740. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) +[2023-07-17 01:53:52,907][291207] Avg episode reward: [(0, '518.944')] +[2023-07-17 01:53:55,102][291488] Updated weights for policy 0, policy_version 16240 (0.0006) +[2023-07-17 01:53:57,907][291207] Fps is (10 sec: 10649.6, 60 sec: 10922.7, 300 sec: 11038.4). Total num frames: 8343552. Throughput: 0: 10980.8. Samples: 8317496. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) +[2023-07-17 01:53:57,907][291207] Avg episode reward: [(0, '533.453')] +[2023-07-17 01:53:58,816][291488] Updated weights for policy 0, policy_version 16320 (0.0006) +[2023-07-17 01:54:02,643][291488] Updated weights for policy 0, policy_version 16400 (0.0006) +[2023-07-17 01:54:02,907][291207] Fps is (10 sec: 10649.6, 60 sec: 10922.7, 300 sec: 11038.4). Total num frames: 8396800. Throughput: 0: 10920.5. Samples: 8382568. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) +[2023-07-17 01:54:02,907][291207] Avg episode reward: [(0, '538.556')] +[2023-07-17 01:54:02,910][291444] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000016400_8396800.pth... +[2023-07-17 01:54:02,913][291444] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000015768_8073216.pth +[2023-07-17 01:54:02,913][291444] Saving new best policy, reward=538.556! +[2023-07-17 01:54:06,371][291488] Updated weights for policy 0, policy_version 16480 (0.0005) +[2023-07-17 01:54:07,906][291207] Fps is (10 sec: 11059.3, 60 sec: 10990.9, 300 sec: 11038.4). Total num frames: 8454144. Throughput: 0: 10888.8. Samples: 8447732. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:54:07,907][291207] Avg episode reward: [(0, '526.649')] +[2023-07-17 01:54:10,173][291488] Updated weights for policy 0, policy_version 16560 (0.0006) +[2023-07-17 01:54:12,906][291207] Fps is (10 sec: 11059.3, 60 sec: 10990.9, 300 sec: 11038.4). Total num frames: 8507392. Throughput: 0: 10841.6. Samples: 8480464. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:54:12,907][291207] Avg episode reward: [(0, '518.147')] +[2023-07-17 01:54:13,920][291488] Updated weights for policy 0, policy_version 16640 (0.0006) +[2023-07-17 01:54:17,693][291488] Updated weights for policy 0, policy_version 16720 (0.0006) +[2023-07-17 01:54:17,907][291207] Fps is (10 sec: 10649.5, 60 sec: 10922.7, 300 sec: 11038.4). Total num frames: 8560640. Throughput: 0: 10856.0. Samples: 8545416. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) +[2023-07-17 01:54:17,907][291207] Avg episode reward: [(0, '508.031')] +[2023-07-17 01:54:17,910][291444] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000016720_8560640.pth... +[2023-07-17 01:54:17,913][291444] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000016088_8237056.pth +[2023-07-17 01:54:21,456][291488] Updated weights for policy 0, policy_version 16800 (0.0006) +[2023-07-17 01:54:22,906][291207] Fps is (10 sec: 10649.6, 60 sec: 10854.4, 300 sec: 11038.4). Total num frames: 8613888. Throughput: 0: 10845.9. Samples: 8610496. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) +[2023-07-17 01:54:22,907][291207] Avg episode reward: [(0, '494.233')] +[2023-07-17 01:54:25,313][291488] Updated weights for policy 0, policy_version 16880 (0.0006) +[2023-07-17 01:54:27,907][291207] Fps is (10 sec: 10649.6, 60 sec: 10786.1, 300 sec: 11024.5). Total num frames: 8667136. Throughput: 0: 10833.1. Samples: 8642624. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) +[2023-07-17 01:54:27,907][291207] Avg episode reward: [(0, '504.484')] +[2023-07-17 01:54:29,052][291488] Updated weights for policy 0, policy_version 16960 (0.0005) +[2023-07-17 01:54:32,858][291488] Updated weights for policy 0, policy_version 17040 (0.0006) +[2023-07-17 01:54:32,907][291207] Fps is (10 sec: 11059.1, 60 sec: 10854.4, 300 sec: 11038.4). Total num frames: 8724480. Throughput: 0: 10833.7. Samples: 8708108. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) +[2023-07-17 01:54:32,907][291207] Avg episode reward: [(0, '530.953')] +[2023-07-17 01:54:32,910][291444] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000017040_8724480.pth... +[2023-07-17 01:54:32,913][291444] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000016400_8396800.pth +[2023-07-17 01:54:36,691][291488] Updated weights for policy 0, policy_version 17120 (0.0006) +[2023-07-17 01:54:37,906][291207] Fps is (10 sec: 11059.2, 60 sec: 10854.4, 300 sec: 11038.4). Total num frames: 8777728. Throughput: 0: 10842.5. Samples: 8772652. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) +[2023-07-17 01:54:37,907][291207] Avg episode reward: [(0, '511.605')] +[2023-07-17 01:54:40,447][291488] Updated weights for policy 0, policy_version 17200 (0.0005) +[2023-07-17 01:54:42,907][291207] Fps is (10 sec: 10649.7, 60 sec: 10854.4, 300 sec: 11038.4). Total num frames: 8830976. Throughput: 0: 10840.6. Samples: 8805324. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) +[2023-07-17 01:54:42,907][291207] Avg episode reward: [(0, '494.489')] +[2023-07-17 01:54:44,282][291488] Updated weights for policy 0, policy_version 17280 (0.0005) +[2023-07-17 01:54:47,907][291207] Fps is (10 sec: 10649.5, 60 sec: 10786.1, 300 sec: 11038.4). Total num frames: 8884224. Throughput: 0: 10801.8. Samples: 8868648. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) +[2023-07-17 01:54:47,907][291207] Avg episode reward: [(0, '513.780')] +[2023-07-17 01:54:47,910][291444] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000017352_8884224.pth... +[2023-07-17 01:54:47,913][291444] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000016720_8560640.pth +[2023-07-17 01:54:48,129][291488] Updated weights for policy 0, policy_version 17360 (0.0006) +[2023-07-17 01:54:51,967][291488] Updated weights for policy 0, policy_version 17440 (0.0006) +[2023-07-17 01:54:52,906][291207] Fps is (10 sec: 10649.6, 60 sec: 10786.1, 300 sec: 11024.5). Total num frames: 8937472. Throughput: 0: 10792.3. Samples: 8933388. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:54:52,908][291207] Avg episode reward: [(0, '520.982')] +[2023-07-17 01:54:55,749][291488] Updated weights for policy 0, policy_version 17520 (0.0006) +[2023-07-17 01:54:57,907][291207] Fps is (10 sec: 10649.7, 60 sec: 10786.1, 300 sec: 11024.5). Total num frames: 8990720. Throughput: 0: 10792.2. Samples: 8966112. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:54:57,907][291207] Avg episode reward: [(0, '502.651')] +[2023-07-17 01:54:59,473][291488] Updated weights for policy 0, policy_version 17600 (0.0006) +[2023-07-17 01:55:02,907][291207] Fps is (10 sec: 11059.2, 60 sec: 10854.4, 300 sec: 11024.5). Total num frames: 9048064. Throughput: 0: 10793.5. Samples: 9031124. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:55:02,908][291207] Avg episode reward: [(0, '517.352')] +[2023-07-17 01:55:02,911][291444] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000017672_9048064.pth... +[2023-07-17 01:55:02,913][291444] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000017040_8724480.pth +[2023-07-17 01:55:03,278][291488] Updated weights for policy 0, policy_version 17680 (0.0006) +[2023-07-17 01:55:07,098][291488] Updated weights for policy 0, policy_version 17760 (0.0006) +[2023-07-17 01:55:07,906][291207] Fps is (10 sec: 11059.2, 60 sec: 10786.1, 300 sec: 11024.5). Total num frames: 9101312. Throughput: 0: 10784.4. Samples: 9095796. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) +[2023-07-17 01:55:07,907][291207] Avg episode reward: [(0, '505.946')] +[2023-07-17 01:55:10,661][291488] Updated weights for policy 0, policy_version 17840 (0.0005) +[2023-07-17 01:55:12,906][291207] Fps is (10 sec: 11059.3, 60 sec: 10854.4, 300 sec: 11038.4). Total num frames: 9158656. Throughput: 0: 10831.7. Samples: 9130048. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) +[2023-07-17 01:55:12,907][291207] Avg episode reward: [(0, '496.540')] +[2023-07-17 01:55:14,277][291488] Updated weights for policy 0, policy_version 17920 (0.0005) +[2023-07-17 01:55:17,906][291207] Fps is (10 sec: 11059.2, 60 sec: 10854.4, 300 sec: 11024.5). Total num frames: 9211904. Throughput: 0: 10895.5. Samples: 9198404. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:55:17,907][291207] Avg episode reward: [(0, '489.366')] +[2023-07-17 01:55:17,929][291444] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000018000_9216000.pth... +[2023-07-17 01:55:17,930][291488] Updated weights for policy 0, policy_version 18000 (0.0005) +[2023-07-17 01:55:17,932][291444] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000017352_8884224.pth +[2023-07-17 01:55:21,795][291488] Updated weights for policy 0, policy_version 18080 (0.0005) +[2023-07-17 01:55:22,906][291207] Fps is (10 sec: 11059.2, 60 sec: 10922.7, 300 sec: 11024.5). Total num frames: 9269248. Throughput: 0: 10891.8. Samples: 9262784. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:55:22,907][291207] Avg episode reward: [(0, '509.587')] +[2023-07-17 01:55:25,520][291488] Updated weights for policy 0, policy_version 18160 (0.0005) +[2023-07-17 01:55:27,906][291207] Fps is (10 sec: 11059.1, 60 sec: 10922.7, 300 sec: 11024.5). Total num frames: 9322496. Throughput: 0: 10907.6. Samples: 9296164. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:55:27,907][291207] Avg episode reward: [(0, '487.126')] +[2023-07-17 01:55:29,295][291488] Updated weights for policy 0, policy_version 18240 (0.0004) +[2023-07-17 01:55:32,907][291207] Fps is (10 sec: 10649.5, 60 sec: 10854.4, 300 sec: 11024.5). Total num frames: 9375744. Throughput: 0: 10924.8. Samples: 9360264. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:55:32,907][291207] Avg episode reward: [(0, '487.468')] +[2023-07-17 01:55:32,910][291444] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000018312_9375744.pth... +[2023-07-17 01:55:32,913][291444] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000017672_9048064.pth +[2023-07-17 01:55:33,112][291488] Updated weights for policy 0, policy_version 18320 (0.0005) +[2023-07-17 01:55:36,667][291488] Updated weights for policy 0, policy_version 18400 (0.0004) +[2023-07-17 01:55:37,906][291207] Fps is (10 sec: 11059.2, 60 sec: 10922.7, 300 sec: 11024.5). Total num frames: 9433088. Throughput: 0: 11004.3. Samples: 9428580. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:55:37,907][291207] Avg episode reward: [(0, '495.404')] +[2023-07-17 01:55:40,134][291488] Updated weights for policy 0, policy_version 18480 (0.0004) +[2023-07-17 01:55:42,906][291207] Fps is (10 sec: 11469.0, 60 sec: 10991.0, 300 sec: 11038.4). Total num frames: 9490432. Throughput: 0: 11061.2. Samples: 9463864. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:55:42,907][291207] Avg episode reward: [(0, '473.243')] +[2023-07-17 01:55:43,647][291488] Updated weights for policy 0, policy_version 18560 (0.0004) +[2023-07-17 01:55:47,164][291488] Updated weights for policy 0, policy_version 18640 (0.0004) +[2023-07-17 01:55:47,907][291207] Fps is (10 sec: 11878.3, 60 sec: 11127.5, 300 sec: 11066.1). Total num frames: 9551872. Throughput: 0: 11185.3. Samples: 9534464. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:55:47,907][291207] Avg episode reward: [(0, '476.440')] +[2023-07-17 01:55:47,910][291444] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000018656_9551872.pth... +[2023-07-17 01:55:47,913][291444] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000018000_9216000.pth +[2023-07-17 01:55:50,676][291488] Updated weights for policy 0, policy_version 18720 (0.0004) +[2023-07-17 01:55:52,906][291207] Fps is (10 sec: 11878.4, 60 sec: 11195.8, 300 sec: 11066.1). Total num frames: 9609216. Throughput: 0: 11298.4. Samples: 9604224. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:55:52,907][291207] Avg episode reward: [(0, '478.231')] +[2023-07-17 01:55:54,185][291488] Updated weights for policy 0, policy_version 18800 (0.0004) +[2023-07-17 01:55:57,719][291488] Updated weights for policy 0, policy_version 18880 (0.0004) +[2023-07-17 01:55:57,906][291207] Fps is (10 sec: 11468.9, 60 sec: 11264.0, 300 sec: 11066.1). Total num frames: 9666560. Throughput: 0: 11298.1. Samples: 9638464. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:55:57,907][291207] Avg episode reward: [(0, '456.890')] +[2023-07-17 01:56:01,342][291488] Updated weights for policy 0, policy_version 18960 (0.0004) +[2023-07-17 01:56:02,907][291207] Fps is (10 sec: 11468.7, 60 sec: 11264.0, 300 sec: 11066.1). Total num frames: 9723904. Throughput: 0: 11314.0. Samples: 9707536. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:56:02,907][291207] Avg episode reward: [(0, '453.753')] +[2023-07-17 01:56:02,910][291444] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000018992_9723904.pth... +[2023-07-17 01:56:02,912][291444] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000018312_9375744.pth +[2023-07-17 01:56:05,180][291488] Updated weights for policy 0, policy_version 19040 (0.0005) +[2023-07-17 01:56:07,906][291207] Fps is (10 sec: 11059.2, 60 sec: 11264.0, 300 sec: 11052.3). Total num frames: 9777152. Throughput: 0: 11300.4. Samples: 9771300. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:56:07,907][291207] Avg episode reward: [(0, '451.582')] +[2023-07-17 01:56:08,999][291488] Updated weights for policy 0, policy_version 19120 (0.0005) +[2023-07-17 01:56:12,789][291488] Updated weights for policy 0, policy_version 19200 (0.0005) +[2023-07-17 01:56:12,906][291207] Fps is (10 sec: 10649.7, 60 sec: 11195.7, 300 sec: 11038.4). Total num frames: 9830400. Throughput: 0: 11279.2. Samples: 9803728. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) +[2023-07-17 01:56:12,907][291207] Avg episode reward: [(0, '451.038')] +[2023-07-17 01:56:16,372][291488] Updated weights for policy 0, policy_version 19280 (0.0004) +[2023-07-17 01:56:17,907][291207] Fps is (10 sec: 11059.1, 60 sec: 11264.0, 300 sec: 11038.4). Total num frames: 9887744. Throughput: 0: 11349.3. Samples: 9870980. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) +[2023-07-17 01:56:17,907][291207] Avg episode reward: [(0, '450.023')] +[2023-07-17 01:56:17,910][291444] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000019312_9887744.pth... +[2023-07-17 01:56:17,913][291444] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000018656_9551872.pth +[2023-07-17 01:56:19,986][291488] Updated weights for policy 0, policy_version 19360 (0.0004) +[2023-07-17 01:56:22,906][291207] Fps is (10 sec: 11059.2, 60 sec: 11195.7, 300 sec: 11024.5). Total num frames: 9940992. Throughput: 0: 11320.1. Samples: 9937984. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) +[2023-07-17 01:56:22,907][291207] Avg episode reward: [(0, '438.091')] +[2023-07-17 01:56:23,724][291488] Updated weights for policy 0, policy_version 19440 (0.0005) +[2023-07-17 01:56:27,505][291488] Updated weights for policy 0, policy_version 19520 (0.0005) +[2023-07-17 01:56:27,906][291207] Fps is (10 sec: 10649.7, 60 sec: 11195.8, 300 sec: 11024.5). Total num frames: 9994240. Throughput: 0: 11246.8. Samples: 9969968. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) +[2023-07-17 01:56:27,907][291207] Avg episode reward: [(0, '460.391')] +[2023-07-17 01:56:28,666][291444] Early stopping after 2 epochs (8 sgd steps), loss delta 0.0000000 +[2023-07-17 01:56:28,667][291490] Stopping RolloutWorker_w1... +[2023-07-17 01:56:28,667][291526] Stopping RolloutWorker_w5... +[2023-07-17 01:56:28,667][291492] Stopping RolloutWorker_w2... +[2023-07-17 01:56:28,667][291494] Stopping RolloutWorker_w6... +[2023-07-17 01:56:28,667][291493] Stopping RolloutWorker_w4... +[2023-07-17 01:56:28,667][291490] Loop rollout_proc1_evt_loop terminating... +[2023-07-17 01:56:28,667][291526] Loop rollout_proc5_evt_loop terminating... +[2023-07-17 01:56:28,667][291492] Loop rollout_proc2_evt_loop terminating... +[2023-07-17 01:56:28,667][291491] Stopping RolloutWorker_w3... +[2023-07-17 01:56:28,667][291558] Stopping RolloutWorker_w7... +[2023-07-17 01:56:28,667][291493] Loop rollout_proc4_evt_loop terminating... +[2023-07-17 01:56:28,667][291494] Loop rollout_proc6_evt_loop terminating... +[2023-07-17 01:56:28,667][291489] Stopping RolloutWorker_w0... +[2023-07-17 01:56:28,667][291207] Component RolloutWorker_w1 stopped! +[2023-07-17 01:56:28,667][291491] Loop rollout_proc3_evt_loop terminating... +[2023-07-17 01:56:28,667][291558] Loop rollout_proc7_evt_loop terminating... +[2023-07-17 01:56:28,667][291489] Loop rollout_proc0_evt_loop terminating... +[2023-07-17 01:56:28,668][291207] Component RolloutWorker_w5 stopped! +[2023-07-17 01:56:28,668][291207] Component RolloutWorker_w2 stopped! +[2023-07-17 01:56:28,668][291207] Component RolloutWorker_w4 stopped! +[2023-07-17 01:56:28,668][291444] Stopping Batcher_0... +[2023-07-17 01:56:28,668][291207] Component RolloutWorker_w6 stopped! +[2023-07-17 01:56:28,668][291444] Loop batcher_evt_loop terminating... +[2023-07-17 01:56:28,668][291207] Component RolloutWorker_w3 stopped! +[2023-07-17 01:56:28,668][291207] Component RolloutWorker_w7 stopped! +[2023-07-17 01:56:28,668][291207] Component RolloutWorker_w0 stopped! +[2023-07-17 01:56:28,669][291207] Component Batcher_0 stopped! +[2023-07-17 01:56:28,669][291444] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000019544_10006528.pth... +[2023-07-17 01:56:28,671][291444] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000018992_9723904.pth +[2023-07-17 01:56:28,671][291444] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/peg-unplug-side-v2/checkpoint_p0/checkpoint_000019544_10006528.pth... +[2023-07-17 01:56:28,673][291444] Stopping LearnerWorker_p0... +[2023-07-17 01:56:28,673][291444] Loop learner_proc0_evt_loop terminating... +[2023-07-17 01:56:28,673][291207] Component LearnerWorker_p0 stopped! +[2023-07-17 01:56:28,733][291488] Weights refcount: 2 0 +[2023-07-17 01:56:28,734][291488] Stopping InferenceWorker_p0-w0... +[2023-07-17 01:56:28,734][291488] Loop inference_proc0-0_evt_loop terminating... +[2023-07-17 01:56:28,734][291207] Component InferenceWorker_p0-w0 stopped! +[2023-07-17 01:56:28,735][291207] Waiting for process learner_proc0 to stop... +[2023-07-17 01:56:29,249][291207] Waiting for process inference_proc0-0 to join... +[2023-07-17 01:56:29,281][291207] Waiting for process rollout_proc0 to join... +[2023-07-17 01:56:29,281][291207] Waiting for process rollout_proc1 to join... +[2023-07-17 01:56:29,281][291207] Waiting for process rollout_proc2 to join... +[2023-07-17 01:56:29,281][291207] Waiting for process rollout_proc3 to join... +[2023-07-17 01:56:29,281][291207] Waiting for process rollout_proc4 to join... +[2023-07-17 01:56:29,282][291207] Waiting for process rollout_proc5 to join... +[2023-07-17 01:56:29,282][291207] Waiting for process rollout_proc6 to join... +[2023-07-17 01:56:29,282][291207] Waiting for process rollout_proc7 to join... +[2023-07-17 01:56:29,282][291207] Batcher 0 profile tree view: +batching: 1.8509, releasing_batches: 1.6285 +[2023-07-17 01:56:29,282][291207] InferenceWorker_p0-w0 profile tree view: wait_policy: 0.0051 - wait_policy_total: 589.9334 -update_model: 15.3641 + wait_policy_total: 326.4449 +update_model: 11.6115 weight_update: 0.0005 -one_step: 0.0012 - handle_policy_step: 695.9616 - deserialize: 28.7100, stack: 7.7430, obs_to_device_normalize: 126.6626, forward: 346.5746, send_messages: 47.3445 - prepare_outputs: 77.3832 - to_cpu: 11.9310 -[2023-07-08 22:01:49,826][1084893] Learner 0 profile tree view: -misc: 0.0100, prepare_batch: 8.4243 -train: 87.2058 - epoch_init: 0.0359, minibatch_init: 1.2409, losses_postprocess: 1.2948, kl_divergence: 0.4140, after_optimizer: 0.6726 - calculate_losses: 36.8186 - losses_init: 0.0307, forward_head: 13.9424, bptt_initial: 0.1257, bptt: 0.1203, tail: 10.7691, advantages_returns: 0.8489, losses: 9.7007 - update: 45.2644 - clip: 5.4675 -[2023-07-08 22:01:49,826][1084893] RolloutWorker_w0 profile tree view: -wait_for_trajectories: 0.4485, enqueue_policy_requests: 15.3787, env_step: 935.6453, overhead: 21.2528, complete_rollouts: 0.3798 -save_policy_outputs: 42.5096 - split_output_tensors: 14.6684 -[2023-07-08 22:01:49,826][1084893] RolloutWorker_w7 profile tree view: -wait_for_trajectories: 0.4459, enqueue_policy_requests: 15.3131, env_step: 936.9842, overhead: 21.4563, complete_rollouts: 0.3999 -save_policy_outputs: 42.9734 - split_output_tensors: 14.6232 -[2023-07-08 22:01:49,826][1084893] Loop Runner_EvtLoop terminating... -[2023-07-08 22:01:49,826][1084893] Runner profile tree view: -main_loop: 1393.1264 -[2023-07-08 22:01:49,826][1084893] Collected {0: 10006528}, FPS: 7182.8 +one_step: 0.0006 + handle_policy_step: 522.0862 + deserialize: 21.8334, stack: 5.6140, obs_to_device_normalize: 94.4725, forward: 257.8720, send_messages: 37.2494 + prepare_outputs: 59.7286 + to_cpu: 9.2446 +[2023-07-17 01:56:29,283][291207] Learner 0 profile tree view: +misc: 0.0095, prepare_batch: 10.1249 +train: 104.7380 + epoch_init: 0.0377, minibatch_init: 1.4133, losses_postprocess: 1.3919, kl_divergence: 0.4763, after_optimizer: 0.6573 + calculate_losses: 44.7953 + losses_init: 0.0334, forward_head: 17.6112, bptt_initial: 0.1469, bptt: 0.1396, tail: 12.6225, advantages_returns: 0.9572, losses: 11.7376 + update: 54.2419 + clip: 6.4569 +[2023-07-17 01:56:29,283][291207] RolloutWorker_w0 profile tree view: +wait_for_trajectories: 0.3145, enqueue_policy_requests: 12.6339, env_step: 638.4567, overhead: 19.3084, complete_rollouts: 0.3235 +save_policy_outputs: 38.4674 + split_output_tensors: 13.2253 +[2023-07-17 01:56:29,283][291207] RolloutWorker_w7 profile tree view: +wait_for_trajectories: 0.2603, enqueue_policy_requests: 12.8113, env_step: 640.3790, overhead: 19.5330, complete_rollouts: 0.3358 +save_policy_outputs: 38.6849 + split_output_tensors: 13.3599 +[2023-07-17 01:56:29,283][291207] Loop Runner_EvtLoop terminating... +[2023-07-17 01:56:29,283][291207] Runner profile tree view: +main_loop: 924.3264 +[2023-07-17 01:56:29,284][291207] Collected {0: 10006528}, FPS: 10825.8