box-close-v2 / sf_log.txt
qgallouedec's picture
qgallouedec HF Staff
Upload folder using huggingface_hub
98b0975
[2023-07-15 18:38:58,256][33296] Saving configuration to /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/config.json...
[2023-07-15 18:38:58,270][33296] Rollout worker 0 uses device cpu
[2023-07-15 18:38:58,271][33296] Rollout worker 1 uses device cpu
[2023-07-15 18:38:58,271][33296] Rollout worker 2 uses device cpu
[2023-07-15 18:38:58,271][33296] Rollout worker 3 uses device cpu
[2023-07-15 18:38:58,271][33296] Rollout worker 4 uses device cpu
[2023-07-15 18:38:58,271][33296] Rollout worker 5 uses device cpu
[2023-07-15 18:38:58,271][33296] Rollout worker 6 uses device cpu
[2023-07-15 18:38:58,272][33296] Rollout worker 7 uses device cpu
[2023-07-15 18:38:58,272][33296] In synchronous mode, we only accumulate one batch. Setting num_batches_to_accumulate to 1
[2023-07-15 18:38:58,283][33296] InferenceWorker_p0-w0: min num requests: 2
[2023-07-15 18:38:58,300][33296] Starting all processes...
[2023-07-15 18:38:58,300][33296] Starting process learner_proc0
[2023-07-15 18:38:58,349][33296] Starting all processes...
[2023-07-15 18:38:58,401][33296] Starting process inference_proc0-0
[2023-07-15 18:38:58,401][33296] Starting process rollout_proc0
[2023-07-15 18:38:58,401][33296] Starting process rollout_proc1
[2023-07-15 18:38:58,401][33296] Starting process rollout_proc2
[2023-07-15 18:38:58,401][33296] Starting process rollout_proc3
[2023-07-15 18:38:58,402][33296] Starting process rollout_proc4
[2023-07-15 18:38:58,402][33296] Starting process rollout_proc5
[2023-07-15 18:38:58,402][33296] Starting process rollout_proc6
[2023-07-15 18:38:58,402][33296] Starting process rollout_proc7
[2023-07-15 18:39:00,255][33537] Starting seed is not provided
[2023-07-15 18:39:00,255][33537] Initializing actor-critic model on device cpu
[2023-07-15 18:39:00,256][33537] RunningMeanStd input shape: (39,)
[2023-07-15 18:39:00,256][33537] RunningMeanStd input shape: (1,)
[2023-07-15 18:39:00,346][33537] Created Actor Critic model with architecture:
[2023-07-15 18:39:00,347][33537] ActorCriticSharedWeights(
(obs_normalizer): ObservationNormalizer(
(running_mean_std): RunningMeanStdDictInPlace(
(running_mean_std): ModuleDict(
(obs): RunningMeanStdInPlace()
)
)
)
(returns_normalizer): RecursiveScriptModule(original_name=RunningMeanStdInPlace)
(encoder): MultiInputEncoder(
(encoders): ModuleDict(
(obs): MlpEncoder(
(mlp_head): RecursiveScriptModule(
original_name=Sequential
(0): RecursiveScriptModule(original_name=Linear)
(1): RecursiveScriptModule(original_name=Tanh)
(2): RecursiveScriptModule(original_name=Linear)
(3): RecursiveScriptModule(original_name=Tanh)
)
)
)
)
(core): ModelCoreIdentity()
(decoder): MlpDecoder(
(mlp): Identity()
)
(critic_linear): Linear(in_features=64, out_features=1, bias=True)
(action_parameterization): ActionParameterizationContinuousNonAdaptiveStddev(
(distribution_linear): Linear(in_features=64, out_features=4, bias=True)
)
)
[2023-07-15 18:39:00,580][33583] Worker 0 uses CPU cores [0, 1, 2, 3]
[2023-07-15 18:39:00,628][33586] Worker 4 uses CPU cores [16, 17, 18, 19]
[2023-07-15 18:39:00,639][33619] Worker 6 uses CPU cores [24, 25, 26, 27]
[2023-07-15 18:39:00,663][33537] Using optimizer <class 'torch.optim.adam.Adam'>
[2023-07-15 18:39:00,664][33537] No checkpoints found
[2023-07-15 18:39:00,664][33537] Did not load from checkpoint, starting from scratch!
[2023-07-15 18:39:00,664][33537] Initialized policy 0 weights for model version 0
[2023-07-15 18:39:00,665][33537] LearnerWorker_p0 finished initialization!
[2023-07-15 18:39:00,697][33585] Worker 2 uses CPU cores [8, 9, 10, 11]
[2023-07-15 18:39:00,739][33682] Worker 7 uses CPU cores [28, 29, 30, 31]
[2023-07-15 18:39:00,752][33296] 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)
[2023-07-15 18:39:00,782][33584] Worker 3 uses CPU cores [12, 13, 14, 15]
[2023-07-15 18:39:00,863][33582] Worker 1 uses CPU cores [4, 5, 6, 7]
[2023-07-15 18:39:01,120][33581] RunningMeanStd input shape: (39,)
[2023-07-15 18:39:01,120][33581] RunningMeanStd input shape: (1,)
[2023-07-15 18:39:01,179][33296] Inference worker 0-0 is ready!
[2023-07-15 18:39:01,180][33296] All inference workers are ready! Signal rollout workers to start!
[2023-07-15 18:39:01,180][33587] Worker 5 uses CPU cores [20, 21, 22, 23]
[2023-07-15 18:39:04,082][33586] Decorrelating experience for 0 frames...
[2023-07-15 18:39:04,094][33586] Decorrelating experience for 64 frames...
[2023-07-15 18:39:04,096][33583] Decorrelating experience for 0 frames...
[2023-07-15 18:39:04,108][33583] Decorrelating experience for 64 frames...
[2023-07-15 18:39:04,111][33582] Decorrelating experience for 0 frames...
[2023-07-15 18:39:04,124][33582] Decorrelating experience for 64 frames...
[2023-07-15 18:39:04,124][33585] Decorrelating experience for 0 frames...
[2023-07-15 18:39:04,132][33619] Decorrelating experience for 0 frames...
[2023-07-15 18:39:04,137][33586] Decorrelating experience for 128 frames...
[2023-07-15 18:39:04,137][33585] Decorrelating experience for 64 frames...
[2023-07-15 18:39:04,142][33682] Decorrelating experience for 0 frames...
[2023-07-15 18:39:04,142][33584] Decorrelating experience for 0 frames...
[2023-07-15 18:39:04,143][33587] Decorrelating experience for 0 frames...
[2023-07-15 18:39:04,145][33619] Decorrelating experience for 64 frames...
[2023-07-15 18:39:04,149][33583] Decorrelating experience for 128 frames...
[2023-07-15 18:39:04,154][33682] Decorrelating experience for 64 frames...
[2023-07-15 18:39:04,154][33584] Decorrelating experience for 64 frames...
[2023-07-15 18:39:04,155][33587] Decorrelating experience for 64 frames...
[2023-07-15 18:39:04,166][33582] Decorrelating experience for 128 frames...
[2023-07-15 18:39:04,179][33585] Decorrelating experience for 128 frames...
[2023-07-15 18:39:04,187][33619] Decorrelating experience for 128 frames...
[2023-07-15 18:39:04,196][33584] Decorrelating experience for 128 frames...
[2023-07-15 18:39:04,196][33587] Decorrelating experience for 128 frames...
[2023-07-15 18:39:04,198][33682] Decorrelating experience for 128 frames...
[2023-07-15 18:39:04,220][33586] Decorrelating experience for 192 frames...
[2023-07-15 18:39:04,236][33583] Decorrelating experience for 192 frames...
[2023-07-15 18:39:04,249][33582] Decorrelating experience for 192 frames...
[2023-07-15 18:39:04,263][33585] Decorrelating experience for 192 frames...
[2023-07-15 18:39:04,270][33619] Decorrelating experience for 192 frames...
[2023-07-15 18:39:04,280][33587] Decorrelating experience for 192 frames...
[2023-07-15 18:39:04,280][33584] Decorrelating experience for 192 frames...
[2023-07-15 18:39:04,283][33682] Decorrelating experience for 192 frames...
[2023-07-15 18:39:05,752][33296] 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)
[2023-07-15 18:39:07,088][33586] Decorrelating experience for 256 frames...
[2023-07-15 18:39:07,105][33582] Decorrelating experience for 256 frames...
[2023-07-15 18:39:07,105][33583] Decorrelating experience for 256 frames...
[2023-07-15 18:39:07,142][33585] Decorrelating experience for 256 frames...
[2023-07-15 18:39:07,145][33587] Decorrelating experience for 256 frames...
[2023-07-15 18:39:07,159][33619] Decorrelating experience for 256 frames...
[2023-07-15 18:39:07,180][33682] Decorrelating experience for 256 frames...
[2023-07-15 18:39:07,180][33584] Decorrelating experience for 256 frames...
[2023-07-15 18:39:07,244][33586] Decorrelating experience for 320 frames...
[2023-07-15 18:39:07,258][33582] Decorrelating experience for 320 frames...
[2023-07-15 18:39:07,259][33583] Decorrelating experience for 320 frames...
[2023-07-15 18:39:07,299][33585] Decorrelating experience for 320 frames...
[2023-07-15 18:39:07,309][33587] Decorrelating experience for 320 frames...
[2023-07-15 18:39:07,314][33619] Decorrelating experience for 320 frames...
[2023-07-15 18:39:07,334][33682] Decorrelating experience for 320 frames...
[2023-07-15 18:39:07,337][33584] Decorrelating experience for 320 frames...
[2023-07-15 18:39:07,455][33586] Decorrelating experience for 384 frames...
[2023-07-15 18:39:07,456][33582] Decorrelating experience for 384 frames...
[2023-07-15 18:39:07,457][33583] Decorrelating experience for 384 frames...
[2023-07-15 18:39:07,495][33585] Decorrelating experience for 384 frames...
[2023-07-15 18:39:07,503][33587] Decorrelating experience for 384 frames...
[2023-07-15 18:39:07,510][33619] Decorrelating experience for 384 frames...
[2023-07-15 18:39:07,532][33682] Decorrelating experience for 384 frames...
[2023-07-15 18:39:07,535][33584] Decorrelating experience for 384 frames...
[2023-07-15 18:39:07,678][33586] Decorrelating experience for 448 frames...
[2023-07-15 18:39:07,678][33582] Decorrelating experience for 448 frames...
[2023-07-15 18:39:07,680][33583] Decorrelating experience for 448 frames...
[2023-07-15 18:39:07,724][33585] Decorrelating experience for 448 frames...
[2023-07-15 18:39:07,725][33587] Decorrelating experience for 448 frames...
[2023-07-15 18:39:07,734][33619] Decorrelating experience for 448 frames...
[2023-07-15 18:39:07,754][33682] Decorrelating experience for 448 frames...
[2023-07-15 18:39:07,760][33584] Decorrelating experience for 448 frames...
[2023-07-15 18:39:10,752][33296] Fps is (10 sec: 1228.8, 60 sec: 1228.8, 300 sec: 1228.8). Total num frames: 12288. Throughput: 0: 1229.6. Samples: 12296. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0)
[2023-07-15 18:39:10,753][33296] Avg episode reward: [(0, '71.204')]
[2023-07-15 18:39:10,755][33537] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000000024_12288.pth...
[2023-07-15 18:39:13,721][33581] Updated weights for policy 0, policy_version 80 (0.0006)
[2023-07-15 18:39:15,752][33296] Fps is (10 sec: 5734.4, 60 sec: 3822.9, 300 sec: 3822.9). Total num frames: 57344. Throughput: 0: 2457.6. Samples: 36864. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 18:39:15,753][33296] Avg episode reward: [(0, '85.336')]
[2023-07-15 18:39:18,278][33296] Heartbeat connected on Batcher_0
[2023-07-15 18:39:18,281][33296] Heartbeat connected on LearnerWorker_p0
[2023-07-15 18:39:18,285][33296] Heartbeat connected on RolloutWorker_w0
[2023-07-15 18:39:18,287][33296] Heartbeat connected on RolloutWorker_w1
[2023-07-15 18:39:18,289][33296] Heartbeat connected on InferenceWorker_p0-w0
[2023-07-15 18:39:18,291][33296] Heartbeat connected on RolloutWorker_w3
[2023-07-15 18:39:18,293][33296] Heartbeat connected on RolloutWorker_w4
[2023-07-15 18:39:18,295][33296] Heartbeat connected on RolloutWorker_w5
[2023-07-15 18:39:18,296][33296] Heartbeat connected on RolloutWorker_w2
[2023-07-15 18:39:18,298][33296] Heartbeat connected on RolloutWorker_w7
[2023-07-15 18:39:18,301][33296] Heartbeat connected on RolloutWorker_w6
[2023-07-15 18:39:18,957][33581] Updated weights for policy 0, policy_version 160 (0.0005)
[2023-07-15 18:39:20,752][33296] Fps is (10 sec: 8192.0, 60 sec: 4710.4, 300 sec: 4710.4). Total num frames: 94208. Throughput: 0: 4232.4. Samples: 84648. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0)
[2023-07-15 18:39:20,753][33296] Avg episode reward: [(0, '107.482')]
[2023-07-15 18:39:23,954][33581] Updated weights for policy 0, policy_version 240 (0.0005)
[2023-07-15 18:39:25,752][33296] Fps is (10 sec: 7782.3, 60 sec: 5406.7, 300 sec: 5406.7). Total num frames: 135168. Throughput: 0: 5346.4. Samples: 133660. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 18:39:25,939][33296] Avg episode reward: [(0, '122.346')]
[2023-07-15 18:39:25,942][33537] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000000264_135168.pth...
[2023-07-15 18:39:25,945][33537] Saving new best policy, reward=122.346!
[2023-07-15 18:39:29,238][33581] Updated weights for policy 0, policy_version 320 (0.0005)
[2023-07-15 18:39:30,752][33296] Fps is (10 sec: 8192.0, 60 sec: 5870.9, 300 sec: 5870.9). Total num frames: 176128. Throughput: 0: 5220.3. Samples: 156608. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 18:39:30,753][33296] Avg episode reward: [(0, '148.743')]
[2023-07-15 18:39:30,753][33537] Saving new best policy, reward=148.743!
[2023-07-15 18:39:34,383][33581] Updated weights for policy 0, policy_version 400 (0.0005)
[2023-07-15 18:39:35,752][33296] Fps is (10 sec: 7782.5, 60 sec: 6085.5, 300 sec: 6085.5). Total num frames: 212992. Throughput: 0: 5840.1. Samples: 204404. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
[2023-07-15 18:39:35,753][33296] Avg episode reward: [(0, '160.403')]
[2023-07-15 18:39:35,753][33537] Saving new best policy, reward=160.403!
[2023-07-15 18:39:40,219][33581] Updated weights for policy 0, policy_version 480 (0.0005)
[2023-07-15 18:39:40,752][33296] Fps is (10 sec: 6963.1, 60 sec: 6144.0, 300 sec: 6144.0). Total num frames: 245760. Throughput: 0: 6144.2. Samples: 245768. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 18:39:40,753][33296] Avg episode reward: [(0, '163.521')]
[2023-07-15 18:39:40,755][33537] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000000480_245760.pth...
[2023-07-15 18:39:40,757][33537] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000000024_12288.pth
[2023-07-15 18:39:40,757][33537] Saving new best policy, reward=163.521!
[2023-07-15 18:39:45,752][33296] Fps is (10 sec: 6553.7, 60 sec: 6189.5, 300 sec: 6189.5). Total num frames: 278528. Throughput: 0: 5878.7. Samples: 264540. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0)
[2023-07-15 18:39:45,752][33296] Avg episode reward: [(0, '172.910')]
[2023-07-15 18:39:45,753][33537] Saving new best policy, reward=172.910!
[2023-07-15 18:39:46,947][33581] Updated weights for policy 0, policy_version 560 (0.0004)
[2023-07-15 18:39:50,752][33296] Fps is (10 sec: 6553.6, 60 sec: 6225.9, 300 sec: 6225.9). Total num frames: 311296. Throughput: 0: 6735.8. Samples: 303112. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 18:39:50,753][33296] Avg episode reward: [(0, '180.987')]
[2023-07-15 18:39:50,753][33537] Saving new best policy, reward=180.987!
[2023-07-15 18:39:52,758][33581] Updated weights for policy 0, policy_version 640 (0.0005)
[2023-07-15 18:39:55,752][33296] Fps is (10 sec: 6553.5, 60 sec: 6255.7, 300 sec: 6255.7). Total num frames: 344064. Throughput: 0: 7364.4. Samples: 343696. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 18:39:55,753][33296] Avg episode reward: [(0, '176.935')]
[2023-07-15 18:39:55,755][33537] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000000672_344064.pth...
[2023-07-15 18:39:55,758][33537] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000000264_135168.pth
[2023-07-15 18:39:59,429][33581] Updated weights for policy 0, policy_version 720 (0.0005)
[2023-07-15 18:40:00,752][33296] Fps is (10 sec: 6144.0, 60 sec: 6212.3, 300 sec: 6212.3). Total num frames: 372736. Throughput: 0: 7208.7. Samples: 361256. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 18:40:00,752][33296] Avg episode reward: [(0, '187.742')]
[2023-07-15 18:40:00,753][33537] Saving new best policy, reward=187.742!
[2023-07-15 18:40:05,752][33296] Fps is (10 sec: 6144.1, 60 sec: 6758.4, 300 sec: 6238.5). Total num frames: 405504. Throughput: 0: 6942.8. Samples: 397076. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0)
[2023-07-15 18:40:05,752][33296] Avg episode reward: [(0, '180.655')]
[2023-07-15 18:40:06,366][33581] Updated weights for policy 0, policy_version 800 (0.0005)
[2023-07-15 18:40:10,752][33296] Fps is (10 sec: 6143.9, 60 sec: 7031.5, 300 sec: 6202.5). Total num frames: 434176. Throughput: 0: 6642.6. Samples: 432576. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 18:40:10,753][33296] Avg episode reward: [(0, '182.414')]
[2023-07-15 18:40:10,755][33537] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000000848_434176.pth...
[2023-07-15 18:40:10,758][33537] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000000480_245760.pth
[2023-07-15 18:40:12,821][33581] Updated weights for policy 0, policy_version 880 (0.0005)
[2023-07-15 18:40:15,752][33296] Fps is (10 sec: 6553.6, 60 sec: 6894.9, 300 sec: 6280.5). Total num frames: 471040. Throughput: 0: 6605.4. Samples: 453852. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 18:40:15,752][33296] Avg episode reward: [(0, '190.103')]
[2023-07-15 18:40:15,753][33537] Saving new best policy, reward=190.103!
[2023-07-15 18:40:18,781][33581] Updated weights for policy 0, policy_version 960 (0.0005)
[2023-07-15 18:40:20,752][33296] Fps is (10 sec: 6963.2, 60 sec: 6826.7, 300 sec: 6297.6). Total num frames: 503808. Throughput: 0: 6459.5. Samples: 495080. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0)
[2023-07-15 18:40:20,753][33296] Avg episode reward: [(0, '187.979')]
[2023-07-15 18:40:25,119][33581] Updated weights for policy 0, policy_version 1040 (0.0005)
[2023-07-15 18:40:25,752][33296] Fps is (10 sec: 6143.9, 60 sec: 6621.9, 300 sec: 6264.5). Total num frames: 532480. Throughput: 0: 6386.4. Samples: 533156. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0)
[2023-07-15 18:40:25,753][33296] Avg episode reward: [(0, '202.663')]
[2023-07-15 18:40:25,787][33537] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000001048_536576.pth...
[2023-07-15 18:40:25,789][33537] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000000672_344064.pth
[2023-07-15 18:40:25,789][33537] Saving new best policy, reward=202.663!
[2023-07-15 18:40:30,752][33296] Fps is (10 sec: 6553.6, 60 sec: 6553.6, 300 sec: 6326.0). Total num frames: 569344. Throughput: 0: 6416.8. Samples: 553296. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 18:40:30,753][33296] Avg episode reward: [(0, '213.508')]
[2023-07-15 18:40:30,753][33537] Saving new best policy, reward=213.508!
[2023-07-15 18:40:31,322][33581] Updated weights for policy 0, policy_version 1120 (0.0005)
[2023-07-15 18:40:35,752][33296] Fps is (10 sec: 6963.3, 60 sec: 6485.3, 300 sec: 6338.0). Total num frames: 602112. Throughput: 0: 6437.8. Samples: 592812. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0)
[2023-07-15 18:40:35,753][33296] Avg episode reward: [(0, '241.450')]
[2023-07-15 18:40:35,753][33537] Saving new best policy, reward=241.450!
[2023-07-15 18:40:37,547][33581] Updated weights for policy 0, policy_version 1200 (0.0005)
[2023-07-15 18:40:40,752][33296] Fps is (10 sec: 6553.6, 60 sec: 6485.3, 300 sec: 6348.8). Total num frames: 634880. Throughput: 0: 6435.8. Samples: 633308. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 18:40:40,753][33296] Avg episode reward: [(0, '236.514')]
[2023-07-15 18:40:40,755][33537] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000001240_634880.pth...
[2023-07-15 18:40:40,758][33537] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000000848_434176.pth
[2023-07-15 18:40:43,558][33581] Updated weights for policy 0, policy_version 1280 (0.0005)
[2023-07-15 18:40:45,752][33296] Fps is (10 sec: 6553.6, 60 sec: 6485.3, 300 sec: 6358.5). Total num frames: 667648. Throughput: 0: 6486.9. Samples: 653168. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0)
[2023-07-15 18:40:45,753][33296] Avg episode reward: [(0, '263.247')]
[2023-07-15 18:40:45,753][33537] Saving new best policy, reward=263.247!
[2023-07-15 18:40:49,440][33581] Updated weights for policy 0, policy_version 1360 (0.0005)
[2023-07-15 18:40:50,752][33296] Fps is (10 sec: 6963.2, 60 sec: 6553.6, 300 sec: 6404.7). Total num frames: 704512. Throughput: 0: 6627.1. Samples: 695296. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
[2023-07-15 18:40:50,753][33296] Avg episode reward: [(0, '234.786')]
[2023-07-15 18:40:54,795][33581] Updated weights for policy 0, policy_version 1440 (0.0005)
[2023-07-15 18:40:55,752][33296] Fps is (10 sec: 7372.8, 60 sec: 6621.9, 300 sec: 6446.7). Total num frames: 741376. Throughput: 0: 6853.0. Samples: 740960. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 18:40:55,753][33296] Avg episode reward: [(0, '264.723')]
[2023-07-15 18:40:55,756][33537] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000001448_741376.pth...
[2023-07-15 18:40:55,759][33537] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000001048_536576.pth
[2023-07-15 18:40:55,759][33537] Saving new best policy, reward=264.723!
[2023-07-15 18:41:00,497][33581] Updated weights for policy 0, policy_version 1520 (0.0005)
[2023-07-15 18:41:00,752][33296] Fps is (10 sec: 7372.9, 60 sec: 6758.4, 300 sec: 6485.3). Total num frames: 778240. Throughput: 0: 6828.4. Samples: 761128. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 18:41:00,753][33296] Avg episode reward: [(0, '265.137')]
[2023-07-15 18:41:00,753][33537] Saving new best policy, reward=265.137!
[2023-07-15 18:41:05,752][33296] Fps is (10 sec: 6963.2, 60 sec: 6758.4, 300 sec: 6488.1). Total num frames: 811008. Throughput: 0: 6891.4. Samples: 805192. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0)
[2023-07-15 18:41:05,753][33296] Avg episode reward: [(0, '256.482')]
[2023-07-15 18:41:06,376][33581] Updated weights for policy 0, policy_version 1600 (0.0005)
[2023-07-15 18:41:10,752][33296] Fps is (10 sec: 6963.1, 60 sec: 6894.9, 300 sec: 6522.1). Total num frames: 847872. Throughput: 0: 6931.1. Samples: 845056. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 18:41:10,753][33296] Avg episode reward: [(0, '255.256')]
[2023-07-15 18:41:10,755][33537] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000001656_847872.pth...
[2023-07-15 18:41:10,759][33537] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000001240_634880.pth
[2023-07-15 18:41:12,529][33581] Updated weights for policy 0, policy_version 1680 (0.0005)
[2023-07-15 18:41:15,752][33296] Fps is (10 sec: 6963.2, 60 sec: 6826.7, 300 sec: 6523.3). Total num frames: 880640. Throughput: 0: 6915.9. Samples: 864512. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 18:41:15,753][33296] Avg episode reward: [(0, '274.893')]
[2023-07-15 18:41:15,753][33537] Saving new best policy, reward=274.893!
[2023-07-15 18:41:18,234][33581] Updated weights for policy 0, policy_version 1760 (0.0005)
[2023-07-15 18:41:20,752][33296] Fps is (10 sec: 6963.2, 60 sec: 6894.9, 300 sec: 6553.6). Total num frames: 917504. Throughput: 0: 7034.8. Samples: 909376. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0)
[2023-07-15 18:41:20,753][33296] Avg episode reward: [(0, '293.321')]
[2023-07-15 18:41:20,753][33537] Saving new best policy, reward=293.321!
[2023-07-15 18:41:23,926][33581] Updated weights for policy 0, policy_version 1840 (0.0005)
[2023-07-15 18:41:25,752][33296] Fps is (10 sec: 6963.3, 60 sec: 6963.2, 300 sec: 6553.6). Total num frames: 950272. Throughput: 0: 7049.8. Samples: 950548. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0)
[2023-07-15 18:41:25,752][33296] Avg episode reward: [(0, '311.440')]
[2023-07-15 18:41:25,754][33537] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000001856_950272.pth...
[2023-07-15 18:41:25,756][33537] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000001448_741376.pth
[2023-07-15 18:41:25,756][33537] Saving new best policy, reward=311.440!
[2023-07-15 18:41:29,706][33581] Updated weights for policy 0, policy_version 1920 (0.0005)
[2023-07-15 18:41:30,752][33296] Fps is (10 sec: 7372.8, 60 sec: 7031.5, 300 sec: 6608.2). Total num frames: 991232. Throughput: 0: 7118.6. Samples: 973504. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0)
[2023-07-15 18:41:30,753][33296] Avg episode reward: [(0, '343.886')]
[2023-07-15 18:41:30,753][33537] Saving new best policy, reward=343.886!
[2023-07-15 18:41:35,200][33581] Updated weights for policy 0, policy_version 2000 (0.0005)
[2023-07-15 18:41:35,752][33296] Fps is (10 sec: 7372.8, 60 sec: 7031.5, 300 sec: 6606.5). Total num frames: 1024000. Throughput: 0: 7145.2. Samples: 1016828. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0)
[2023-07-15 18:41:35,752][33296] Avg episode reward: [(0, '392.893')]
[2023-07-15 18:41:35,753][33537] Saving new best policy, reward=392.893!
[2023-07-15 18:41:40,752][33296] Fps is (10 sec: 6963.3, 60 sec: 7099.7, 300 sec: 6630.4). Total num frames: 1060864. Throughput: 0: 7102.9. Samples: 1060588. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0)
[2023-07-15 18:41:40,752][33296] Avg episode reward: [(0, '431.697')]
[2023-07-15 18:41:40,755][33537] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000002072_1060864.pth...
[2023-07-15 18:41:40,757][33537] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000001656_847872.pth
[2023-07-15 18:41:40,758][33537] Saving new best policy, reward=431.697!
[2023-07-15 18:41:40,921][33581] Updated weights for policy 0, policy_version 2080 (0.0005)
[2023-07-15 18:41:45,752][33296] Fps is (10 sec: 7372.8, 60 sec: 7168.0, 300 sec: 6652.9). Total num frames: 1097728. Throughput: 0: 7113.9. Samples: 1081252. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 18:41:45,753][33296] Avg episode reward: [(0, '477.952')]
[2023-07-15 18:41:45,753][33537] Saving new best policy, reward=477.952!
[2023-07-15 18:41:46,778][33581] Updated weights for policy 0, policy_version 2160 (0.0005)
[2023-07-15 18:41:50,752][33296] Fps is (10 sec: 7372.7, 60 sec: 7168.0, 300 sec: 6674.1). Total num frames: 1134592. Throughput: 0: 7113.5. Samples: 1125300. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 18:41:50,753][33296] Avg episode reward: [(0, '467.172')]
[2023-07-15 18:41:51,797][33581] Updated weights for policy 0, policy_version 2240 (0.0005)
[2023-07-15 18:41:55,752][33296] Fps is (10 sec: 7782.4, 60 sec: 7236.3, 300 sec: 6717.4). Total num frames: 1175552. Throughput: 0: 7263.7. Samples: 1171920. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 18:41:55,752][33296] Avg episode reward: [(0, '482.498')]
[2023-07-15 18:41:55,755][33537] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000002296_1175552.pth...
[2023-07-15 18:41:55,757][33537] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000001856_950272.pth
[2023-07-15 18:41:55,758][33537] Saving new best policy, reward=482.498!
[2023-07-15 18:41:57,314][33581] Updated weights for policy 0, policy_version 2320 (0.0005)
[2023-07-15 18:42:00,752][33296] Fps is (10 sec: 7782.4, 60 sec: 7236.3, 300 sec: 6735.6). Total num frames: 1212416. Throughput: 0: 7359.9. Samples: 1195708. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 18:42:00,753][33296] Avg episode reward: [(0, '488.872')]
[2023-07-15 18:42:00,753][33537] Saving new best policy, reward=488.872!
[2023-07-15 18:42:02,587][33581] Updated weights for policy 0, policy_version 2400 (0.0005)
[2023-07-15 18:42:05,752][33296] Fps is (10 sec: 7372.8, 60 sec: 7304.5, 300 sec: 6752.9). Total num frames: 1249280. Throughput: 0: 7370.1. Samples: 1241032. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0)
[2023-07-15 18:42:05,753][33296] Avg episode reward: [(0, '497.700')]
[2023-07-15 18:42:05,753][33537] Saving new best policy, reward=497.700!
[2023-07-15 18:42:08,337][33581] Updated weights for policy 0, policy_version 2480 (0.0005)
[2023-07-15 18:42:10,752][33296] Fps is (10 sec: 7372.8, 60 sec: 7304.5, 300 sec: 6769.2). Total num frames: 1286144. Throughput: 0: 7410.7. Samples: 1284032. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0)
[2023-07-15 18:42:10,753][33296] Avg episode reward: [(0, '500.374')]
[2023-07-15 18:42:10,755][33537] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000002512_1286144.pth...
[2023-07-15 18:42:10,758][33537] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000002072_1060864.pth
[2023-07-15 18:42:10,758][33537] Saving new best policy, reward=500.374!
[2023-07-15 18:42:13,864][33581] Updated weights for policy 0, policy_version 2560 (0.0005)
[2023-07-15 18:42:15,752][33296] Fps is (10 sec: 7372.8, 60 sec: 7372.8, 300 sec: 6784.7). Total num frames: 1323008. Throughput: 0: 7404.1. Samples: 1306688. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 18:42:15,753][33296] Avg episode reward: [(0, '489.198')]
[2023-07-15 18:42:19,320][33581] Updated weights for policy 0, policy_version 2640 (0.0005)
[2023-07-15 18:42:20,752][33296] Fps is (10 sec: 7372.8, 60 sec: 7372.8, 300 sec: 6799.4). Total num frames: 1359872. Throughput: 0: 7439.3. Samples: 1351596. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
[2023-07-15 18:42:20,753][33296] Avg episode reward: [(0, '454.857')]
[2023-07-15 18:42:24,651][33581] Updated weights for policy 0, policy_version 2720 (0.0006)
[2023-07-15 18:42:25,752][33296] Fps is (10 sec: 7372.9, 60 sec: 7441.1, 300 sec: 6813.3). Total num frames: 1396736. Throughput: 0: 7470.0. Samples: 1396736. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0)
[2023-07-15 18:42:25,752][33296] Avg episode reward: [(0, '470.334')]
[2023-07-15 18:42:25,755][33537] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000002728_1396736.pth...
[2023-07-15 18:42:25,758][33537] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000002296_1175552.pth
[2023-07-15 18:42:30,260][33581] Updated weights for policy 0, policy_version 2800 (0.0005)
[2023-07-15 18:42:30,752][33296] Fps is (10 sec: 7372.8, 60 sec: 7372.8, 300 sec: 6826.7). Total num frames: 1433600. Throughput: 0: 7479.0. Samples: 1417808. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 18:42:30,752][33296] Avg episode reward: [(0, '461.719')]
[2023-07-15 18:42:35,750][33581] Updated weights for policy 0, policy_version 2880 (0.0005)
[2023-07-15 18:42:35,752][33296] Fps is (10 sec: 7782.4, 60 sec: 7509.3, 300 sec: 6858.4). Total num frames: 1474560. Throughput: 0: 7508.2. Samples: 1463168. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0)
[2023-07-15 18:42:35,753][33296] Avg episode reward: [(0, '497.424')]
[2023-07-15 18:42:40,752][33296] Fps is (10 sec: 7372.8, 60 sec: 7441.1, 300 sec: 6851.5). Total num frames: 1507328. Throughput: 0: 7455.1. Samples: 1507400. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0)
[2023-07-15 18:42:40,753][33296] Avg episode reward: [(0, '481.526')]
[2023-07-15 18:42:40,782][33537] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000002952_1511424.pth...
[2023-07-15 18:42:40,784][33537] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000002512_1286144.pth
[2023-07-15 18:42:41,273][33581] Updated weights for policy 0, policy_version 2960 (0.0005)
[2023-07-15 18:42:45,752][33296] Fps is (10 sec: 7372.8, 60 sec: 7509.3, 300 sec: 6881.3). Total num frames: 1548288. Throughput: 0: 7464.0. Samples: 1531588. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0)
[2023-07-15 18:42:45,753][33296] Avg episode reward: [(0, '454.348')]
[2023-07-15 18:42:46,768][33581] Updated weights for policy 0, policy_version 3040 (0.0005)
[2023-07-15 18:42:50,752][33296] Fps is (10 sec: 7372.9, 60 sec: 7441.1, 300 sec: 6874.2). Total num frames: 1581056. Throughput: 0: 7414.1. Samples: 1574664. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 18:42:50,753][33296] Avg episode reward: [(0, '448.048')]
[2023-07-15 18:42:52,620][33581] Updated weights for policy 0, policy_version 3120 (0.0005)
[2023-07-15 18:42:55,752][33296] Fps is (10 sec: 6963.1, 60 sec: 7372.8, 300 sec: 6884.8). Total num frames: 1617920. Throughput: 0: 7409.2. Samples: 1617448. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 18:42:55,753][33296] Avg episode reward: [(0, '479.371')]
[2023-07-15 18:42:55,756][33537] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000003160_1617920.pth...
[2023-07-15 18:42:55,759][33537] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000002728_1396736.pth
[2023-07-15 18:42:58,387][33581] Updated weights for policy 0, policy_version 3200 (0.0005)
[2023-07-15 18:43:00,752][33296] Fps is (10 sec: 6963.2, 60 sec: 7304.5, 300 sec: 6877.9). Total num frames: 1650688. Throughput: 0: 7360.2. Samples: 1637896. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 18:43:00,752][33296] Avg episode reward: [(0, '455.942')]
[2023-07-15 18:43:04,577][33581] Updated weights for policy 0, policy_version 3280 (0.0005)
[2023-07-15 18:43:05,752][33296] Fps is (10 sec: 6553.6, 60 sec: 7236.3, 300 sec: 6871.2). Total num frames: 1683456. Throughput: 0: 7235.2. Samples: 1677180. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0)
[2023-07-15 18:43:05,753][33296] Avg episode reward: [(0, '487.342')]
[2023-07-15 18:43:10,558][33581] Updated weights for policy 0, policy_version 3360 (0.0005)
[2023-07-15 18:43:10,752][33296] Fps is (10 sec: 6963.1, 60 sec: 7236.3, 300 sec: 6881.3). Total num frames: 1720320. Throughput: 0: 7131.4. Samples: 1717652. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0)
[2023-07-15 18:43:10,753][33296] Avg episode reward: [(0, '479.961')]
[2023-07-15 18:43:10,755][33537] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000003360_1720320.pth...
[2023-07-15 18:43:10,758][33537] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000002952_1511424.pth
[2023-07-15 18:43:15,752][33296] Fps is (10 sec: 7372.8, 60 sec: 7236.3, 300 sec: 6890.9). Total num frames: 1757184. Throughput: 0: 7179.7. Samples: 1740892. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0)
[2023-07-15 18:43:15,753][33296] Avg episode reward: [(0, '464.512')]
[2023-07-15 18:43:16,217][33581] Updated weights for policy 0, policy_version 3440 (0.0005)
[2023-07-15 18:43:20,752][33296] Fps is (10 sec: 6963.3, 60 sec: 7168.0, 300 sec: 6884.4). Total num frames: 1789952. Throughput: 0: 7105.6. Samples: 1782920. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 18:43:20,753][33296] Avg episode reward: [(0, '469.825')]
[2023-07-15 18:43:21,932][33581] Updated weights for policy 0, policy_version 3520 (0.0006)
[2023-07-15 18:43:25,752][33296] Fps is (10 sec: 6963.2, 60 sec: 7168.0, 300 sec: 6893.6). Total num frames: 1826816. Throughput: 0: 7096.7. Samples: 1826752. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0)
[2023-07-15 18:43:25,752][33296] Avg episode reward: [(0, '470.080')]
[2023-07-15 18:43:25,755][33537] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000003568_1826816.pth...
[2023-07-15 18:43:25,757][33537] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000003160_1617920.pth
[2023-07-15 18:43:27,576][33581] Updated weights for policy 0, policy_version 3600 (0.0005)
[2023-07-15 18:43:30,752][33296] Fps is (10 sec: 7372.8, 60 sec: 7168.0, 300 sec: 6902.5). Total num frames: 1863680. Throughput: 0: 7017.3. Samples: 1847368. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 18:43:30,753][33296] Avg episode reward: [(0, '472.350')]
[2023-07-15 18:43:33,530][33581] Updated weights for policy 0, policy_version 3680 (0.0005)
[2023-07-15 18:43:35,752][33296] Fps is (10 sec: 7372.8, 60 sec: 7099.7, 300 sec: 6911.1). Total num frames: 1900544. Throughput: 0: 6980.3. Samples: 1888776. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 18:43:35,752][33296] Avg episode reward: [(0, '481.108')]
[2023-07-15 18:43:39,158][33581] Updated weights for policy 0, policy_version 3760 (0.0005)
[2023-07-15 18:43:40,752][33296] Fps is (10 sec: 6963.2, 60 sec: 7099.7, 300 sec: 6904.7). Total num frames: 1933312. Throughput: 0: 7004.6. Samples: 1932656. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0)
[2023-07-15 18:43:40,759][33296] Avg episode reward: [(0, '474.767')]
[2023-07-15 18:43:40,762][33537] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000003776_1933312.pth...
[2023-07-15 18:43:40,765][33537] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000003360_1720320.pth
[2023-07-15 18:43:44,861][33581] Updated weights for policy 0, policy_version 3840 (0.0004)
[2023-07-15 18:43:45,752][33296] Fps is (10 sec: 6963.2, 60 sec: 7031.5, 300 sec: 6912.9). Total num frames: 1970176. Throughput: 0: 7014.1. Samples: 1953532. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0)
[2023-07-15 18:43:45,753][33296] Avg episode reward: [(0, '491.850')]
[2023-07-15 18:43:50,315][33581] Updated weights for policy 0, policy_version 3920 (0.0005)
[2023-07-15 18:43:50,752][33296] Fps is (10 sec: 7372.9, 60 sec: 7099.7, 300 sec: 6920.8). Total num frames: 2007040. Throughput: 0: 7147.9. Samples: 1998836. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0)
[2023-07-15 18:43:50,792][33296] Avg episode reward: [(0, '501.384')]
[2023-07-15 18:43:50,821][33537] Saving new best policy, reward=501.384!
[2023-07-15 18:43:55,752][33296] Fps is (10 sec: 7372.8, 60 sec: 7099.7, 300 sec: 6928.5). Total num frames: 2043904. Throughput: 0: 7196.9. Samples: 2041512. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0)
[2023-07-15 18:43:55,752][33296] Avg episode reward: [(0, '500.494')]
[2023-07-15 18:43:55,755][33537] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000003992_2043904.pth...
[2023-07-15 18:43:55,757][33537] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000003568_1826816.pth
[2023-07-15 18:43:56,195][33581] Updated weights for policy 0, policy_version 4000 (0.0005)
[2023-07-15 18:44:00,752][33296] Fps is (10 sec: 6963.2, 60 sec: 7099.7, 300 sec: 7039.6). Total num frames: 2076672. Throughput: 0: 7161.7. Samples: 2063168. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0)
[2023-07-15 18:44:00,753][33296] Avg episode reward: [(0, '484.576')]
[2023-07-15 18:44:02,082][33581] Updated weights for policy 0, policy_version 4080 (0.0005)
[2023-07-15 18:44:05,752][33296] Fps is (10 sec: 6963.2, 60 sec: 7168.0, 300 sec: 7122.9). Total num frames: 2113536. Throughput: 0: 7141.2. Samples: 2104272. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 18:44:05,753][33296] Avg episode reward: [(0, '487.964')]
[2023-07-15 18:44:07,791][33581] Updated weights for policy 0, policy_version 4160 (0.0005)
[2023-07-15 18:44:10,752][33296] Fps is (10 sec: 7372.7, 60 sec: 7168.0, 300 sec: 7095.1). Total num frames: 2150400. Throughput: 0: 7169.8. Samples: 2149392. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0)
[2023-07-15 18:44:10,753][33296] Avg episode reward: [(0, '478.011')]
[2023-07-15 18:44:10,756][33537] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000004200_2150400.pth...
[2023-07-15 18:44:10,758][33537] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000003776_1933312.pth
[2023-07-15 18:44:13,261][33581] Updated weights for policy 0, policy_version 4240 (0.0005)
[2023-07-15 18:44:15,752][33296] Fps is (10 sec: 7372.8, 60 sec: 7168.0, 300 sec: 7095.1). Total num frames: 2187264. Throughput: 0: 7188.3. Samples: 2170840. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0)
[2023-07-15 18:44:15,753][33296] Avg episode reward: [(0, '489.003')]
[2023-07-15 18:44:18,841][33581] Updated weights for policy 0, policy_version 4320 (0.0005)
[2023-07-15 18:44:20,752][33296] Fps is (10 sec: 7372.8, 60 sec: 7236.3, 300 sec: 7081.2). Total num frames: 2224128. Throughput: 0: 7248.7. Samples: 2214968. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 18:44:20,753][33296] Avg episode reward: [(0, '510.689')]
[2023-07-15 18:44:20,753][33537] Saving new best policy, reward=510.689!
[2023-07-15 18:44:24,662][33581] Updated weights for policy 0, policy_version 4400 (0.0004)
[2023-07-15 18:44:25,752][33296] Fps is (10 sec: 6963.2, 60 sec: 7168.0, 300 sec: 7053.4). Total num frames: 2256896. Throughput: 0: 7204.7. Samples: 2256868. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0)
[2023-07-15 18:44:25,752][33296] Avg episode reward: [(0, '506.088')]
[2023-07-15 18:44:25,755][33537] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000004408_2256896.pth...
[2023-07-15 18:44:25,757][33537] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000003992_2043904.pth
[2023-07-15 18:44:30,538][33581] Updated weights for policy 0, policy_version 4480 (0.0005)
[2023-07-15 18:44:30,752][33296] Fps is (10 sec: 6963.2, 60 sec: 7168.0, 300 sec: 7053.5). Total num frames: 2293760. Throughput: 0: 7196.5. Samples: 2277376. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 18:44:30,752][33296] Avg episode reward: [(0, '487.472')]
[2023-07-15 18:44:35,752][33296] Fps is (10 sec: 7372.8, 60 sec: 7168.0, 300 sec: 7067.3). Total num frames: 2330624. Throughput: 0: 7164.0. Samples: 2321216. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0)
[2023-07-15 18:44:35,752][33296] Avg episode reward: [(0, '519.555')]
[2023-07-15 18:44:35,753][33537] Saving new best policy, reward=519.555!
[2023-07-15 18:44:36,250][33581] Updated weights for policy 0, policy_version 4560 (0.0004)
[2023-07-15 18:44:40,752][33296] Fps is (10 sec: 6963.1, 60 sec: 7168.0, 300 sec: 7067.3). Total num frames: 2363392. Throughput: 0: 7153.1. Samples: 2363400. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 18:44:40,753][33296] Avg episode reward: [(0, '513.704')]
[2023-07-15 18:44:40,757][33537] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000004616_2363392.pth...
[2023-07-15 18:44:40,758][33537] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000004200_2150400.pth
[2023-07-15 18:44:42,004][33581] Updated weights for policy 0, policy_version 4640 (0.0005)
[2023-07-15 18:44:45,752][33296] Fps is (10 sec: 6963.2, 60 sec: 7168.0, 300 sec: 7081.2). Total num frames: 2400256. Throughput: 0: 7130.6. Samples: 2384044. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 18:44:45,752][33296] Avg episode reward: [(0, '515.348')]
[2023-07-15 18:44:47,798][33581] Updated weights for policy 0, policy_version 4720 (0.0005)
[2023-07-15 18:44:50,752][33296] Fps is (10 sec: 7372.9, 60 sec: 7168.0, 300 sec: 7095.1). Total num frames: 2437120. Throughput: 0: 7169.3. Samples: 2426888. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0)
[2023-07-15 18:44:50,752][33296] Avg episode reward: [(0, '530.252')]
[2023-07-15 18:44:50,753][33537] Saving new best policy, reward=530.252!
[2023-07-15 18:44:53,462][33581] Updated weights for policy 0, policy_version 4800 (0.0005)
[2023-07-15 18:44:55,752][33296] Fps is (10 sec: 6963.2, 60 sec: 7099.7, 300 sec: 7109.0). Total num frames: 2469888. Throughput: 0: 7127.3. Samples: 2470120. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 18:44:55,752][33296] Avg episode reward: [(0, '501.199')]
[2023-07-15 18:44:55,757][33537] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000004832_2473984.pth...
[2023-07-15 18:44:55,759][33537] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000004408_2256896.pth
[2023-07-15 18:44:59,283][33581] Updated weights for policy 0, policy_version 4880 (0.0005)
[2023-07-15 18:45:00,752][33296] Fps is (10 sec: 6963.1, 60 sec: 7168.0, 300 sec: 7122.9). Total num frames: 2506752. Throughput: 0: 7109.7. Samples: 2490776. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 18:45:00,753][33296] Avg episode reward: [(0, '498.318')]
[2023-07-15 18:45:05,052][33581] Updated weights for policy 0, policy_version 4960 (0.0004)
[2023-07-15 18:45:05,752][33296] Fps is (10 sec: 7372.8, 60 sec: 7168.0, 300 sec: 7150.6). Total num frames: 2543616. Throughput: 0: 7097.2. Samples: 2534340. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
[2023-07-15 18:45:05,753][33296] Avg episode reward: [(0, '516.913')]
[2023-07-15 18:45:10,752][33296] Fps is (10 sec: 6963.2, 60 sec: 7099.7, 300 sec: 7136.8). Total num frames: 2576384. Throughput: 0: 7099.1. Samples: 2576328. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0)
[2023-07-15 18:45:10,753][33296] Avg episode reward: [(0, '514.309')]
[2023-07-15 18:45:10,755][33537] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000005032_2576384.pth...
[2023-07-15 18:45:10,757][33537] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000004616_2363392.pth
[2023-07-15 18:45:10,864][33581] Updated weights for policy 0, policy_version 5040 (0.0005)
[2023-07-15 18:45:15,752][33296] Fps is (10 sec: 7372.8, 60 sec: 7168.0, 300 sec: 7164.5). Total num frames: 2617344. Throughput: 0: 7126.2. Samples: 2598056. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
[2023-07-15 18:45:15,753][33296] Avg episode reward: [(0, '502.980')]
[2023-07-15 18:45:16,268][33581] Updated weights for policy 0, policy_version 5120 (0.0005)
[2023-07-15 18:45:20,752][33296] Fps is (10 sec: 7782.5, 60 sec: 7168.0, 300 sec: 7192.3). Total num frames: 2654208. Throughput: 0: 7179.5. Samples: 2644292. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0)
[2023-07-15 18:45:20,752][33296] Avg episode reward: [(0, '494.483')]
[2023-07-15 18:45:21,900][33581] Updated weights for policy 0, policy_version 5200 (0.0005)
[2023-07-15 18:45:25,752][33296] Fps is (10 sec: 6963.2, 60 sec: 7168.0, 300 sec: 7178.4). Total num frames: 2686976. Throughput: 0: 7142.4. Samples: 2684808. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0)
[2023-07-15 18:45:25,753][33296] Avg episode reward: [(0, '491.242')]
[2023-07-15 18:45:25,755][33537] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000005248_2686976.pth...
[2023-07-15 18:45:25,758][33537] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000004832_2473984.pth
[2023-07-15 18:45:28,012][33581] Updated weights for policy 0, policy_version 5280 (0.0004)
[2023-07-15 18:45:30,752][33296] Fps is (10 sec: 6553.6, 60 sec: 7099.7, 300 sec: 7178.4). Total num frames: 2719744. Throughput: 0: 7128.1. Samples: 2704808. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 18:45:30,752][33296] Avg episode reward: [(0, '509.018')]
[2023-07-15 18:45:33,745][33581] Updated weights for policy 0, policy_version 5360 (0.0005)
[2023-07-15 18:45:35,752][33296] Fps is (10 sec: 6963.2, 60 sec: 7099.7, 300 sec: 7192.3). Total num frames: 2756608. Throughput: 0: 7143.5. Samples: 2748348. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 18:45:35,753][33296] Avg episode reward: [(0, '484.345')]
[2023-07-15 18:45:39,282][33581] Updated weights for policy 0, policy_version 5440 (0.0005)
[2023-07-15 18:45:40,752][33296] Fps is (10 sec: 7372.7, 60 sec: 7168.0, 300 sec: 7206.2). Total num frames: 2793472. Throughput: 0: 7175.6. Samples: 2793024. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 18:45:40,753][33296] Avg episode reward: [(0, '492.398')]
[2023-07-15 18:45:40,755][33537] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000005456_2793472.pth...
[2023-07-15 18:45:40,758][33537] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000005032_2576384.pth
[2023-07-15 18:45:44,801][33581] Updated weights for policy 0, policy_version 5520 (0.0005)
[2023-07-15 18:45:45,752][33296] Fps is (10 sec: 7372.8, 60 sec: 7168.0, 300 sec: 7206.2). Total num frames: 2830336. Throughput: 0: 7194.4. Samples: 2814524. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0)
[2023-07-15 18:45:45,753][33296] Avg episode reward: [(0, '483.045')]
[2023-07-15 18:45:50,303][33581] Updated weights for policy 0, policy_version 5600 (0.0005)
[2023-07-15 18:45:50,752][33296] Fps is (10 sec: 7372.8, 60 sec: 7168.0, 300 sec: 7206.2). Total num frames: 2867200. Throughput: 0: 7211.8. Samples: 2858872. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
[2023-07-15 18:45:50,753][33296] Avg episode reward: [(0, '499.233')]
[2023-07-15 18:45:55,752][33296] Fps is (10 sec: 7372.8, 60 sec: 7236.3, 300 sec: 7206.2). Total num frames: 2904064. Throughput: 0: 7244.5. Samples: 2902328. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0)
[2023-07-15 18:45:55,752][33296] Avg episode reward: [(0, '475.650')]
[2023-07-15 18:45:55,755][33537] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000005672_2904064.pth...
[2023-07-15 18:45:55,758][33537] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000005248_2686976.pth
[2023-07-15 18:45:56,138][33581] Updated weights for policy 0, policy_version 5680 (0.0006)
[2023-07-15 18:46:00,752][33296] Fps is (10 sec: 7372.9, 60 sec: 7236.3, 300 sec: 7220.1). Total num frames: 2940928. Throughput: 0: 7219.9. Samples: 2922952. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 18:46:00,752][33296] Avg episode reward: [(0, '492.130')]
[2023-07-15 18:46:01,813][33581] Updated weights for policy 0, policy_version 5760 (0.0004)
[2023-07-15 18:46:05,752][33296] Fps is (10 sec: 7372.8, 60 sec: 7236.3, 300 sec: 7220.1). Total num frames: 2977792. Throughput: 0: 7174.0. Samples: 2967120. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 18:46:05,752][33296] Avg episode reward: [(0, '484.509')]
[2023-07-15 18:46:07,343][33581] Updated weights for policy 0, policy_version 5840 (0.0005)
[2023-07-15 18:46:10,752][33296] Fps is (10 sec: 6963.2, 60 sec: 7236.3, 300 sec: 7220.1). Total num frames: 3010560. Throughput: 0: 7240.7. Samples: 3010640. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0)
[2023-07-15 18:46:10,752][33296] Avg episode reward: [(0, '491.864')]
[2023-07-15 18:46:10,755][33537] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000005880_3010560.pth...
[2023-07-15 18:46:10,756][33537] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000005456_2793472.pth
[2023-07-15 18:46:13,003][33581] Updated weights for policy 0, policy_version 5920 (0.0005)
[2023-07-15 18:46:15,752][33296] Fps is (10 sec: 6963.1, 60 sec: 7168.0, 300 sec: 7220.1). Total num frames: 3047424. Throughput: 0: 7284.6. Samples: 3032616. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 18:46:15,753][33296] Avg episode reward: [(0, '461.313')]
[2023-07-15 18:46:18,962][33581] Updated weights for policy 0, policy_version 6000 (0.0005)
[2023-07-15 18:46:20,752][33296] Fps is (10 sec: 7372.9, 60 sec: 7168.0, 300 sec: 7234.0). Total num frames: 3084288. Throughput: 0: 7237.5. Samples: 3074036. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 18:46:20,752][33296] Avg episode reward: [(0, '502.944')]
[2023-07-15 18:46:24,485][33581] Updated weights for policy 0, policy_version 6080 (0.0006)
[2023-07-15 18:46:25,752][33296] Fps is (10 sec: 7372.8, 60 sec: 7236.3, 300 sec: 7220.1). Total num frames: 3121152. Throughput: 0: 7213.6. Samples: 3117636. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 18:46:25,753][33296] Avg episode reward: [(0, '510.667')]
[2023-07-15 18:46:25,755][33537] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000006096_3121152.pth...
[2023-07-15 18:46:25,758][33537] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000005672_2904064.pth
[2023-07-15 18:46:30,452][33581] Updated weights for policy 0, policy_version 6160 (0.0005)
[2023-07-15 18:46:30,752][33296] Fps is (10 sec: 6963.1, 60 sec: 7236.3, 300 sec: 7220.1). Total num frames: 3153920. Throughput: 0: 7207.5. Samples: 3138864. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0)
[2023-07-15 18:46:30,753][33296] Avg episode reward: [(0, '509.097')]
[2023-07-15 18:46:35,752][33296] Fps is (10 sec: 6963.2, 60 sec: 7236.3, 300 sec: 7220.1). Total num frames: 3190784. Throughput: 0: 7193.2. Samples: 3182564. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
[2023-07-15 18:46:35,753][33296] Avg episode reward: [(0, '506.431')]
[2023-07-15 18:46:36,073][33581] Updated weights for policy 0, policy_version 6240 (0.0005)
[2023-07-15 18:46:40,752][33296] Fps is (10 sec: 6963.2, 60 sec: 7168.0, 300 sec: 7206.2). Total num frames: 3223552. Throughput: 0: 7136.8. Samples: 3223484. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 18:46:40,753][33296] Avg episode reward: [(0, '522.663')]
[2023-07-15 18:46:40,755][33537] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000006296_3223552.pth...
[2023-07-15 18:46:40,757][33537] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000005880_3010560.pth
[2023-07-15 18:46:41,880][33581] Updated weights for policy 0, policy_version 6320 (0.0005)
[2023-07-15 18:46:45,752][33296] Fps is (10 sec: 6963.2, 60 sec: 7168.0, 300 sec: 7206.2). Total num frames: 3260416. Throughput: 0: 7171.8. Samples: 3245684. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0)
[2023-07-15 18:46:45,753][33296] Avg episode reward: [(0, '497.772')]
[2023-07-15 18:46:47,571][33581] Updated weights for policy 0, policy_version 6400 (0.0005)
[2023-07-15 18:46:50,752][33296] Fps is (10 sec: 7372.8, 60 sec: 7168.0, 300 sec: 7192.3). Total num frames: 3297280. Throughput: 0: 7130.0. Samples: 3287972. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0)
[2023-07-15 18:46:50,753][33296] Avg episode reward: [(0, '502.182')]
[2023-07-15 18:46:53,169][33581] Updated weights for policy 0, policy_version 6480 (0.0005)
[2023-07-15 18:46:55,752][33296] Fps is (10 sec: 7372.8, 60 sec: 7168.0, 300 sec: 7192.3). Total num frames: 3334144. Throughput: 0: 7179.5. Samples: 3333716. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 18:46:55,753][33296] Avg episode reward: [(0, '511.057')]
[2023-07-15 18:46:55,756][33537] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000006512_3334144.pth...
[2023-07-15 18:46:55,758][33537] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000006096_3121152.pth
[2023-07-15 18:46:58,576][33581] Updated weights for policy 0, policy_version 6560 (0.0005)
[2023-07-15 18:47:00,752][33296] Fps is (10 sec: 7372.8, 60 sec: 7168.0, 300 sec: 7192.3). Total num frames: 3371008. Throughput: 0: 7187.5. Samples: 3356052. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 18:47:00,752][33296] Avg episode reward: [(0, '496.792')]
[2023-07-15 18:47:04,600][33581] Updated weights for policy 0, policy_version 6640 (0.0005)
[2023-07-15 18:47:05,752][33296] Fps is (10 sec: 6963.3, 60 sec: 7099.7, 300 sec: 7178.4). Total num frames: 3403776. Throughput: 0: 7186.0. Samples: 3397404. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 18:47:05,752][33296] Avg episode reward: [(0, '507.774')]
[2023-07-15 18:47:10,620][33581] Updated weights for policy 0, policy_version 6720 (0.0005)
[2023-07-15 18:47:10,752][33296] Fps is (10 sec: 6963.1, 60 sec: 7168.0, 300 sec: 7178.4). Total num frames: 3440640. Throughput: 0: 7121.8. Samples: 3438120. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0)
[2023-07-15 18:47:10,753][33296] Avg episode reward: [(0, '500.541')]
[2023-07-15 18:47:10,756][33537] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000006720_3440640.pth...
[2023-07-15 18:47:10,758][33537] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000006296_3223552.pth
[2023-07-15 18:47:15,752][33296] Fps is (10 sec: 7372.8, 60 sec: 7168.0, 300 sec: 7178.4). Total num frames: 3477504. Throughput: 0: 7147.4. Samples: 3460496. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 18:47:15,752][33296] Avg episode reward: [(0, '512.485')]
[2023-07-15 18:47:16,162][33581] Updated weights for policy 0, policy_version 6800 (0.0005)
[2023-07-15 18:47:20,752][33296] Fps is (10 sec: 6963.3, 60 sec: 7099.7, 300 sec: 7164.5). Total num frames: 3510272. Throughput: 0: 7112.2. Samples: 3502612. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 18:47:20,753][33296] Avg episode reward: [(0, '525.884')]
[2023-07-15 18:47:22,129][33581] Updated weights for policy 0, policy_version 6880 (0.0005)
[2023-07-15 18:47:25,752][33296] Fps is (10 sec: 6553.5, 60 sec: 7031.5, 300 sec: 7150.6). Total num frames: 3543040. Throughput: 0: 7102.8. Samples: 3543112. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 18:47:25,753][33296] Avg episode reward: [(0, '519.557')]
[2023-07-15 18:47:25,756][33537] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000006920_3543040.pth...
[2023-07-15 18:47:25,758][33537] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000006512_3334144.pth
[2023-07-15 18:47:28,257][33581] Updated weights for policy 0, policy_version 6960 (0.0005)
[2023-07-15 18:47:30,752][33296] Fps is (10 sec: 6963.2, 60 sec: 7099.7, 300 sec: 7136.8). Total num frames: 3579904. Throughput: 0: 7062.1. Samples: 3563480. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0)
[2023-07-15 18:47:30,753][33296] Avg episode reward: [(0, '520.218')]
[2023-07-15 18:47:34,002][33581] Updated weights for policy 0, policy_version 7040 (0.0005)
[2023-07-15 18:47:35,752][33296] Fps is (10 sec: 7372.9, 60 sec: 7099.7, 300 sec: 7150.6). Total num frames: 3616768. Throughput: 0: 7073.8. Samples: 3606292. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0)
[2023-07-15 18:47:35,752][33296] Avg episode reward: [(0, '502.242')]
[2023-07-15 18:47:39,660][33581] Updated weights for policy 0, policy_version 7120 (0.0004)
[2023-07-15 18:47:40,752][33296] Fps is (10 sec: 6963.2, 60 sec: 7099.7, 300 sec: 7122.9). Total num frames: 3649536. Throughput: 0: 7018.1. Samples: 3649528. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0)
[2023-07-15 18:47:40,752][33296] Avg episode reward: [(0, '523.009')]
[2023-07-15 18:47:40,755][33537] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000007128_3649536.pth...
[2023-07-15 18:47:40,756][33537] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000006720_3440640.pth
[2023-07-15 18:47:45,240][33581] Updated weights for policy 0, policy_version 7200 (0.0005)
[2023-07-15 18:47:45,752][33296] Fps is (10 sec: 6963.2, 60 sec: 7099.7, 300 sec: 7136.8). Total num frames: 3686400. Throughput: 0: 6994.2. Samples: 3670792. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0)
[2023-07-15 18:47:45,753][33296] Avg episode reward: [(0, '504.328')]
[2023-07-15 18:47:50,752][33296] Fps is (10 sec: 7372.8, 60 sec: 7099.7, 300 sec: 7136.8). Total num frames: 3723264. Throughput: 0: 7060.7. Samples: 3715136. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 18:47:50,752][33296] Avg episode reward: [(0, '499.186')]
[2023-07-15 18:47:50,921][33581] Updated weights for policy 0, policy_version 7280 (0.0005)
[2023-07-15 18:47:55,752][33296] Fps is (10 sec: 7372.7, 60 sec: 7099.7, 300 sec: 7150.6). Total num frames: 3760128. Throughput: 0: 7098.8. Samples: 3757564. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0)
[2023-07-15 18:47:55,753][33296] Avg episode reward: [(0, '525.828')]
[2023-07-15 18:47:55,756][33537] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000007344_3760128.pth...
[2023-07-15 18:47:55,759][33537] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000006920_3543040.pth
[2023-07-15 18:47:56,866][33581] Updated weights for policy 0, policy_version 7360 (0.0005)
[2023-07-15 18:48:00,752][33296] Fps is (10 sec: 6963.2, 60 sec: 7031.5, 300 sec: 7150.6). Total num frames: 3792896. Throughput: 0: 7044.6. Samples: 3777504. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 18:48:00,752][33296] Avg episode reward: [(0, '523.931')]
[2023-07-15 18:48:02,568][33581] Updated weights for policy 0, policy_version 7440 (0.0005)
[2023-07-15 18:48:05,752][33296] Fps is (10 sec: 6963.3, 60 sec: 7099.7, 300 sec: 7150.6). Total num frames: 3829760. Throughput: 0: 7087.8. Samples: 3821564. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 18:48:05,752][33296] Avg episode reward: [(0, '527.582')]
[2023-07-15 18:48:08,283][33581] Updated weights for policy 0, policy_version 7520 (0.0005)
[2023-07-15 18:48:10,752][33296] Fps is (10 sec: 6963.2, 60 sec: 7031.5, 300 sec: 7136.8). Total num frames: 3862528. Throughput: 0: 7100.1. Samples: 3862616. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 18:48:10,752][33296] Avg episode reward: [(0, '526.060')]
[2023-07-15 18:48:10,772][33537] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000007552_3866624.pth...
[2023-07-15 18:48:10,774][33537] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000007128_3649536.pth
[2023-07-15 18:48:14,265][33581] Updated weights for policy 0, policy_version 7600 (0.0005)
[2023-07-15 18:48:15,752][33296] Fps is (10 sec: 6963.2, 60 sec: 7031.5, 300 sec: 7150.6). Total num frames: 3899392. Throughput: 0: 7108.7. Samples: 3883372. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0)
[2023-07-15 18:48:15,752][33296] Avg episode reward: [(0, '518.061')]
[2023-07-15 18:48:20,168][33581] Updated weights for policy 0, policy_version 7680 (0.0004)
[2023-07-15 18:48:20,752][33296] Fps is (10 sec: 7372.8, 60 sec: 7099.7, 300 sec: 7150.6). Total num frames: 3936256. Throughput: 0: 7103.0. Samples: 3925928. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 18:48:20,752][33296] Avg episode reward: [(0, '500.120')]
[2023-07-15 18:48:25,752][33296] Fps is (10 sec: 6963.1, 60 sec: 7099.7, 300 sec: 7136.8). Total num frames: 3969024. Throughput: 0: 7038.2. Samples: 3966248. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 18:48:25,753][33296] Avg episode reward: [(0, '486.886')]
[2023-07-15 18:48:25,755][33537] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000007752_3969024.pth...
[2023-07-15 18:48:25,758][33537] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000007344_3760128.pth
[2023-07-15 18:48:26,008][33581] Updated weights for policy 0, policy_version 7760 (0.0004)
[2023-07-15 18:48:30,752][33296] Fps is (10 sec: 6963.2, 60 sec: 7099.7, 300 sec: 7136.8). Total num frames: 4005888. Throughput: 0: 7092.8. Samples: 3989968. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0)
[2023-07-15 18:48:30,753][33296] Avg episode reward: [(0, '502.813')]
[2023-07-15 18:48:31,535][33581] Updated weights for policy 0, policy_version 7840 (0.0005)
[2023-07-15 18:48:35,752][33296] Fps is (10 sec: 7372.8, 60 sec: 7099.7, 300 sec: 7150.6). Total num frames: 4042752. Throughput: 0: 7061.7. Samples: 4032912. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 18:48:35,752][33296] Avg episode reward: [(0, '499.770')]
[2023-07-15 18:48:37,216][33581] Updated weights for policy 0, policy_version 7920 (0.0005)
[2023-07-15 18:48:40,752][33296] Fps is (10 sec: 7372.8, 60 sec: 7168.0, 300 sec: 7150.6). Total num frames: 4079616. Throughput: 0: 7104.1. Samples: 4077248. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 18:48:40,753][33296] Avg episode reward: [(0, '516.224')]
[2023-07-15 18:48:40,756][33537] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000007968_4079616.pth...
[2023-07-15 18:48:40,758][33537] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000007552_3866624.pth
[2023-07-15 18:48:42,669][33581] Updated weights for policy 0, policy_version 8000 (0.0005)
[2023-07-15 18:48:45,752][33296] Fps is (10 sec: 7372.8, 60 sec: 7168.0, 300 sec: 7150.6). Total num frames: 4116480. Throughput: 0: 7168.6. Samples: 4100092. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 18:48:45,752][33296] Avg episode reward: [(0, '495.891')]
[2023-07-15 18:48:48,213][33581] Updated weights for policy 0, policy_version 8080 (0.0005)
[2023-07-15 18:48:50,752][33296] Fps is (10 sec: 7372.8, 60 sec: 7168.0, 300 sec: 7150.6). Total num frames: 4153344. Throughput: 0: 7168.1. Samples: 4144128. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0)
[2023-07-15 18:48:50,753][33296] Avg episode reward: [(0, '524.731')]
[2023-07-15 18:48:54,142][33581] Updated weights for policy 0, policy_version 8160 (0.0005)
[2023-07-15 18:48:55,752][33296] Fps is (10 sec: 7372.7, 60 sec: 7168.0, 300 sec: 7164.5). Total num frames: 4190208. Throughput: 0: 7190.4. Samples: 4186184. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 18:48:55,753][33296] Avg episode reward: [(0, '523.648')]
[2023-07-15 18:48:55,755][33537] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000008184_4190208.pth...
[2023-07-15 18:48:55,758][33537] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000007752_3969024.pth
[2023-07-15 18:48:59,680][33581] Updated weights for policy 0, policy_version 8240 (0.0006)
[2023-07-15 18:49:00,752][33296] Fps is (10 sec: 6963.2, 60 sec: 7168.0, 300 sec: 7150.6). Total num frames: 4222976. Throughput: 0: 7243.4. Samples: 4209324. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 18:49:00,752][33296] Avg episode reward: [(0, '485.697')]
[2023-07-15 18:49:05,108][33581] Updated weights for policy 0, policy_version 8320 (0.0005)
[2023-07-15 18:49:05,752][33296] Fps is (10 sec: 7372.8, 60 sec: 7236.3, 300 sec: 7164.5). Total num frames: 4263936. Throughput: 0: 7244.3. Samples: 4251924. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 18:49:05,753][33296] Avg episode reward: [(0, '507.947')]
[2023-07-15 18:49:10,528][33581] Updated weights for policy 0, policy_version 8400 (0.0005)
[2023-07-15 18:49:10,752][33296] Fps is (10 sec: 7782.4, 60 sec: 7304.5, 300 sec: 7164.5). Total num frames: 4300800. Throughput: 0: 7390.2. Samples: 4298808. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 18:49:10,752][33296] Avg episode reward: [(0, '487.791')]
[2023-07-15 18:49:10,755][33537] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000008400_4300800.pth...
[2023-07-15 18:49:10,758][33537] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000007968_4079616.pth
[2023-07-15 18:49:15,752][33296] Fps is (10 sec: 7372.8, 60 sec: 7304.5, 300 sec: 7164.5). Total num frames: 4337664. Throughput: 0: 7358.6. Samples: 4321104. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0)
[2023-07-15 18:49:15,753][33296] Avg episode reward: [(0, '487.548')]
[2023-07-15 18:49:15,973][33581] Updated weights for policy 0, policy_version 8480 (0.0005)
[2023-07-15 18:49:20,752][33296] Fps is (10 sec: 7372.8, 60 sec: 7304.5, 300 sec: 7178.4). Total num frames: 4374528. Throughput: 0: 7377.1. Samples: 4364880. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0)
[2023-07-15 18:49:20,753][33296] Avg episode reward: [(0, '510.468')]
[2023-07-15 18:49:21,673][33581] Updated weights for policy 0, policy_version 8560 (0.0006)
[2023-07-15 18:49:25,752][33296] Fps is (10 sec: 7372.8, 60 sec: 7372.8, 300 sec: 7178.4). Total num frames: 4411392. Throughput: 0: 7390.0. Samples: 4409796. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 18:49:25,752][33296] Avg episode reward: [(0, '505.664')]
[2023-07-15 18:49:25,755][33537] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000008616_4411392.pth...
[2023-07-15 18:49:25,757][33537] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000008184_4190208.pth
[2023-07-15 18:49:27,099][33581] Updated weights for policy 0, policy_version 8640 (0.0006)
[2023-07-15 18:49:30,752][33296] Fps is (10 sec: 7372.8, 60 sec: 7372.8, 300 sec: 7178.4). Total num frames: 4448256. Throughput: 0: 7373.2. Samples: 4431888. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 18:49:30,753][33296] Avg episode reward: [(0, '513.152')]
[2023-07-15 18:49:33,051][33581] Updated weights for policy 0, policy_version 8720 (0.0005)
[2023-07-15 18:49:35,752][33296] Fps is (10 sec: 6963.2, 60 sec: 7304.5, 300 sec: 7178.4). Total num frames: 4481024. Throughput: 0: 7303.6. Samples: 4472792. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 18:49:35,753][33296] Avg episode reward: [(0, '510.034')]
[2023-07-15 18:49:38,663][33581] Updated weights for policy 0, policy_version 8800 (0.0005)
[2023-07-15 18:49:40,752][33296] Fps is (10 sec: 6963.2, 60 sec: 7304.5, 300 sec: 7178.4). Total num frames: 4517888. Throughput: 0: 7339.7. Samples: 4516472. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0)
[2023-07-15 18:49:40,752][33296] Avg episode reward: [(0, '521.441')]
[2023-07-15 18:49:40,755][33537] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000008824_4517888.pth...
[2023-07-15 18:49:40,756][33537] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000008400_4300800.pth
[2023-07-15 18:49:44,556][33581] Updated weights for policy 0, policy_version 8880 (0.0005)
[2023-07-15 18:49:45,752][33296] Fps is (10 sec: 7372.8, 60 sec: 7304.5, 300 sec: 7178.4). Total num frames: 4554752. Throughput: 0: 7305.2. Samples: 4538056. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0)
[2023-07-15 18:49:45,752][33296] Avg episode reward: [(0, '515.008')]
[2023-07-15 18:49:50,267][33581] Updated weights for policy 0, policy_version 8960 (0.0005)
[2023-07-15 18:49:50,752][33296] Fps is (10 sec: 6963.2, 60 sec: 7236.3, 300 sec: 7178.4). Total num frames: 4587520. Throughput: 0: 7303.0. Samples: 4580560. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0)
[2023-07-15 18:49:50,752][33296] Avg episode reward: [(0, '504.083')]
[2023-07-15 18:49:55,620][33581] Updated weights for policy 0, policy_version 9040 (0.0005)
[2023-07-15 18:49:55,752][33296] Fps is (10 sec: 7372.8, 60 sec: 7304.5, 300 sec: 7192.3). Total num frames: 4628480. Throughput: 0: 7241.3. Samples: 4624664. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0)
[2023-07-15 18:49:55,752][33296] Avg episode reward: [(0, '505.060')]
[2023-07-15 18:49:55,755][33537] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000009040_4628480.pth...
[2023-07-15 18:49:55,757][33537] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000008616_4411392.pth
[2023-07-15 18:50:00,752][33296] Fps is (10 sec: 7372.8, 60 sec: 7304.5, 300 sec: 7178.4). Total num frames: 4661248. Throughput: 0: 7237.0. Samples: 4646768. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 18:50:00,753][33296] Avg episode reward: [(0, '517.226')]
[2023-07-15 18:50:01,596][33581] Updated weights for policy 0, policy_version 9120 (0.0005)
[2023-07-15 18:50:05,752][33296] Fps is (10 sec: 6553.6, 60 sec: 7168.0, 300 sec: 7178.4). Total num frames: 4694016. Throughput: 0: 7180.5. Samples: 4688004. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 18:50:05,753][33296] Avg episode reward: [(0, '484.361')]
[2023-07-15 18:50:07,623][33581] Updated weights for policy 0, policy_version 9200 (0.0005)
[2023-07-15 18:50:10,752][33296] Fps is (10 sec: 6963.2, 60 sec: 7168.0, 300 sec: 7164.5). Total num frames: 4730880. Throughput: 0: 7078.6. Samples: 4728332. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
[2023-07-15 18:50:10,753][33296] Avg episode reward: [(0, '536.963')]
[2023-07-15 18:50:10,756][33537] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000009240_4730880.pth...
[2023-07-15 18:50:10,758][33537] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000008824_4517888.pth
[2023-07-15 18:50:10,759][33537] Saving new best policy, reward=536.963!
[2023-07-15 18:50:13,592][33581] Updated weights for policy 0, policy_version 9280 (0.0005)
[2023-07-15 18:50:15,752][33296] Fps is (10 sec: 6963.1, 60 sec: 7099.7, 300 sec: 7150.6). Total num frames: 4763648. Throughput: 0: 7050.6. Samples: 4749164. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 18:50:15,753][33296] Avg episode reward: [(0, '516.316')]
[2023-07-15 18:50:19,609][33581] Updated weights for policy 0, policy_version 9360 (0.0004)
[2023-07-15 18:50:20,752][33296] Fps is (10 sec: 6963.2, 60 sec: 7099.7, 300 sec: 7164.5). Total num frames: 4800512. Throughput: 0: 7028.1. Samples: 4789056. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 18:50:20,753][33296] Avg episode reward: [(0, '500.893')]
[2023-07-15 18:50:25,360][33581] Updated weights for policy 0, policy_version 9440 (0.0006)
[2023-07-15 18:50:25,752][33296] Fps is (10 sec: 6963.2, 60 sec: 7031.5, 300 sec: 7164.5). Total num frames: 4833280. Throughput: 0: 7034.7. Samples: 4833032. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0)
[2023-07-15 18:50:25,753][33296] Avg episode reward: [(0, '517.635')]
[2023-07-15 18:50:25,756][33537] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000009440_4833280.pth...
[2023-07-15 18:50:25,759][33537] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000009040_4628480.pth
[2023-07-15 18:50:30,752][33296] Fps is (10 sec: 6963.2, 60 sec: 7031.5, 300 sec: 7164.5). Total num frames: 4870144. Throughput: 0: 7017.7. Samples: 4853852. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0)
[2023-07-15 18:50:30,753][33296] Avg episode reward: [(0, '544.877')]
[2023-07-15 18:50:30,753][33537] Saving new best policy, reward=544.877!
[2023-07-15 18:50:30,822][33581] Updated weights for policy 0, policy_version 9520 (0.0006)
[2023-07-15 18:50:35,752][33296] Fps is (10 sec: 7782.4, 60 sec: 7168.0, 300 sec: 7178.4). Total num frames: 4911104. Throughput: 0: 7111.9. Samples: 4900596. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 18:50:35,753][33296] Avg episode reward: [(0, '526.072')]
[2023-07-15 18:50:36,155][33581] Updated weights for policy 0, policy_version 9600 (0.0005)
[2023-07-15 18:50:40,752][33296] Fps is (10 sec: 7782.3, 60 sec: 7168.0, 300 sec: 7178.4). Total num frames: 4947968. Throughput: 0: 7095.1. Samples: 4943944. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
[2023-07-15 18:50:40,753][33296] Avg episode reward: [(0, '520.218')]
[2023-07-15 18:50:40,756][33537] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000009664_4947968.pth...
[2023-07-15 18:50:40,758][33537] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000009240_4730880.pth
[2023-07-15 18:50:41,954][33581] Updated weights for policy 0, policy_version 9680 (0.0005)
[2023-07-15 18:50:45,752][33296] Fps is (10 sec: 6963.2, 60 sec: 7099.7, 300 sec: 7164.5). Total num frames: 4980736. Throughput: 0: 7070.3. Samples: 4964932. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
[2023-07-15 18:50:45,752][33296] Avg episode reward: [(0, '517.518')]
[2023-07-15 18:50:47,535][33581] Updated weights for policy 0, policy_version 9760 (0.0004)
[2023-07-15 18:50:50,752][33296] Fps is (10 sec: 6963.3, 60 sec: 7168.0, 300 sec: 7164.5). Total num frames: 5017600. Throughput: 0: 7138.4. Samples: 5009232. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 18:50:50,753][33296] Avg episode reward: [(0, '498.717')]
[2023-07-15 18:50:53,506][33581] Updated weights for policy 0, policy_version 9840 (0.0005)
[2023-07-15 18:50:55,752][33296] Fps is (10 sec: 6963.1, 60 sec: 7031.5, 300 sec: 7150.6). Total num frames: 5050368. Throughput: 0: 7156.3. Samples: 5050368. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 18:50:55,753][33296] Avg episode reward: [(0, '521.694')]
[2023-07-15 18:50:55,755][33537] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000009864_5050368.pth...
[2023-07-15 18:50:55,757][33537] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000009440_4833280.pth
[2023-07-15 18:50:59,225][33581] Updated weights for policy 0, policy_version 9920 (0.0005)
[2023-07-15 18:51:00,752][33296] Fps is (10 sec: 6963.2, 60 sec: 7099.7, 300 sec: 7150.6). Total num frames: 5087232. Throughput: 0: 7180.3. Samples: 5072276. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 18:51:00,753][33296] Avg episode reward: [(0, '511.744')]
[2023-07-15 18:51:05,117][33581] Updated weights for policy 0, policy_version 10000 (0.0006)
[2023-07-15 18:51:05,752][33296] Fps is (10 sec: 7372.9, 60 sec: 7168.0, 300 sec: 7164.5). Total num frames: 5124096. Throughput: 0: 7216.7. Samples: 5113808. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 18:51:05,752][33296] Avg episode reward: [(0, '524.722')]
[2023-07-15 18:51:10,752][33296] Fps is (10 sec: 6963.1, 60 sec: 7099.7, 300 sec: 7150.6). Total num frames: 5156864. Throughput: 0: 7161.2. Samples: 5155288. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 18:51:10,753][33296] Avg episode reward: [(0, '538.865')]
[2023-07-15 18:51:10,756][33537] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000010072_5156864.pth...
[2023-07-15 18:51:10,759][33537] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000009664_4947968.pth
[2023-07-15 18:51:11,119][33581] Updated weights for policy 0, policy_version 10080 (0.0005)
[2023-07-15 18:51:15,752][33296] Fps is (10 sec: 6963.2, 60 sec: 7168.0, 300 sec: 7150.6). Total num frames: 5193728. Throughput: 0: 7188.9. Samples: 5177352. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0)
[2023-07-15 18:51:15,753][33296] Avg episode reward: [(0, '518.473')]
[2023-07-15 18:51:16,582][33581] Updated weights for policy 0, policy_version 10160 (0.0005)
[2023-07-15 18:51:20,752][33296] Fps is (10 sec: 7372.9, 60 sec: 7168.0, 300 sec: 7150.6). Total num frames: 5230592. Throughput: 0: 7118.4. Samples: 5220924. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 18:51:20,753][33296] Avg episode reward: [(0, '528.654')]
[2023-07-15 18:51:22,473][33581] Updated weights for policy 0, policy_version 10240 (0.0005)
[2023-07-15 18:51:25,752][33296] Fps is (10 sec: 6963.1, 60 sec: 7168.0, 300 sec: 7150.6). Total num frames: 5263360. Throughput: 0: 7090.6. Samples: 5263020. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 18:51:25,753][33296] Avg episode reward: [(0, '523.980')]
[2023-07-15 18:51:25,756][33537] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000010280_5263360.pth...
[2023-07-15 18:51:25,758][33537] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000009864_5050368.pth
[2023-07-15 18:51:28,422][33581] Updated weights for policy 0, policy_version 10320 (0.0005)
[2023-07-15 18:51:30,752][33296] Fps is (10 sec: 6553.6, 60 sec: 7099.7, 300 sec: 7136.8). Total num frames: 5296128. Throughput: 0: 7067.2. Samples: 5282956. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 18:51:30,753][33296] Avg episode reward: [(0, '540.439')]
[2023-07-15 18:51:34,023][33581] Updated weights for policy 0, policy_version 10400 (0.0005)
[2023-07-15 18:51:35,752][33296] Fps is (10 sec: 7372.9, 60 sec: 7099.7, 300 sec: 7164.5). Total num frames: 5337088. Throughput: 0: 7042.0. Samples: 5326120. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 18:51:35,753][33296] Avg episode reward: [(0, '534.957')]
[2023-07-15 18:51:39,435][33581] Updated weights for policy 0, policy_version 10480 (0.0005)
[2023-07-15 18:51:40,752][33296] Fps is (10 sec: 7782.3, 60 sec: 7099.7, 300 sec: 7164.5). Total num frames: 5373952. Throughput: 0: 7130.5. Samples: 5371240. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0)
[2023-07-15 18:51:40,773][33296] Avg episode reward: [(0, '506.393')]
[2023-07-15 18:51:40,776][33537] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000010496_5373952.pth...
[2023-07-15 18:51:40,777][33537] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000010072_5156864.pth
[2023-07-15 18:51:45,096][33581] Updated weights for policy 0, policy_version 10560 (0.0005)
[2023-07-15 18:51:45,752][33296] Fps is (10 sec: 7372.8, 60 sec: 7168.0, 300 sec: 7164.5). Total num frames: 5410816. Throughput: 0: 7153.9. Samples: 5394200. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 18:51:45,753][33296] Avg episode reward: [(0, '522.765')]
[2023-07-15 18:51:50,752][33296] Fps is (10 sec: 6963.3, 60 sec: 7099.7, 300 sec: 7150.6). Total num frames: 5443584. Throughput: 0: 7179.8. Samples: 5436900. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 18:51:50,753][33296] Avg episode reward: [(0, '494.893')]
[2023-07-15 18:51:50,780][33581] Updated weights for policy 0, policy_version 10640 (0.0005)
[2023-07-15 18:51:55,752][33296] Fps is (10 sec: 6963.1, 60 sec: 7168.0, 300 sec: 7150.6). Total num frames: 5480448. Throughput: 0: 7196.2. Samples: 5479116. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0)
[2023-07-15 18:51:55,753][33296] Avg episode reward: [(0, '519.729')]
[2023-07-15 18:51:55,756][33537] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000010704_5480448.pth...
[2023-07-15 18:51:55,759][33537] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000010280_5263360.pth
[2023-07-15 18:51:56,649][33581] Updated weights for policy 0, policy_version 10720 (0.0004)
[2023-07-15 18:52:00,752][33296] Fps is (10 sec: 6963.1, 60 sec: 7099.7, 300 sec: 7150.6). Total num frames: 5513216. Throughput: 0: 7146.0. Samples: 5498924. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0)
[2023-07-15 18:52:00,753][33296] Avg episode reward: [(0, '513.761')]
[2023-07-15 18:52:02,822][33581] Updated weights for policy 0, policy_version 10800 (0.0005)
[2023-07-15 18:52:05,752][33296] Fps is (10 sec: 6963.3, 60 sec: 7099.7, 300 sec: 7150.6). Total num frames: 5550080. Throughput: 0: 7079.8. Samples: 5539516. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0)
[2023-07-15 18:52:05,753][33296] Avg episode reward: [(0, '513.448')]
[2023-07-15 18:52:08,548][33581] Updated weights for policy 0, policy_version 10880 (0.0004)
[2023-07-15 18:52:10,752][33296] Fps is (10 sec: 6963.2, 60 sec: 7099.8, 300 sec: 7136.8). Total num frames: 5582848. Throughput: 0: 7106.3. Samples: 5582804. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0)
[2023-07-15 18:52:10,847][33296] Avg episode reward: [(0, '523.394')]
[2023-07-15 18:52:10,851][33537] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000010912_5586944.pth...
[2023-07-15 18:52:10,852][33537] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000010496_5373952.pth
[2023-07-15 18:52:14,502][33581] Updated weights for policy 0, policy_version 10960 (0.0005)
[2023-07-15 18:52:15,752][33296] Fps is (10 sec: 6963.1, 60 sec: 7099.7, 300 sec: 7150.6). Total num frames: 5619712. Throughput: 0: 7118.6. Samples: 5603292. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 18:52:15,753][33296] Avg episode reward: [(0, '538.553')]
[2023-07-15 18:52:19,794][33581] Updated weights for policy 0, policy_version 11040 (0.0005)
[2023-07-15 18:52:20,752][33296] Fps is (10 sec: 7372.8, 60 sec: 7099.7, 300 sec: 7164.5). Total num frames: 5656576. Throughput: 0: 7163.0. Samples: 5648456. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 18:52:20,753][33296] Avg episode reward: [(0, '522.082')]
[2023-07-15 18:52:25,752][33296] Fps is (10 sec: 6963.1, 60 sec: 7099.7, 300 sec: 7150.6). Total num frames: 5689344. Throughput: 0: 7070.4. Samples: 5689408. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 18:52:25,753][33296] Avg episode reward: [(0, '547.799')]
[2023-07-15 18:52:25,757][33537] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000011112_5689344.pth...
[2023-07-15 18:52:25,759][33537] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000010704_5480448.pth
[2023-07-15 18:52:25,759][33537] Saving new best policy, reward=547.799!
[2023-07-15 18:52:25,794][33581] Updated weights for policy 0, policy_version 11120 (0.0005)
[2023-07-15 18:52:30,752][33296] Fps is (10 sec: 6963.2, 60 sec: 7168.0, 300 sec: 7150.6). Total num frames: 5726208. Throughput: 0: 7014.0. Samples: 5709832. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0)
[2023-07-15 18:52:30,752][33296] Avg episode reward: [(0, '552.101')]
[2023-07-15 18:52:30,753][33537] Saving new best policy, reward=552.101!
[2023-07-15 18:52:31,872][33581] Updated weights for policy 0, policy_version 11200 (0.0004)
[2023-07-15 18:52:35,752][33296] Fps is (10 sec: 6963.3, 60 sec: 7031.5, 300 sec: 7150.6). Total num frames: 5758976. Throughput: 0: 6985.8. Samples: 5751260. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0)
[2023-07-15 18:52:35,752][33296] Avg episode reward: [(0, '516.746')]
[2023-07-15 18:52:37,740][33581] Updated weights for policy 0, policy_version 11280 (0.0005)
[2023-07-15 18:52:40,752][33296] Fps is (10 sec: 6963.1, 60 sec: 7031.5, 300 sec: 7150.6). Total num frames: 5795840. Throughput: 0: 6969.8. Samples: 5792756. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 18:52:40,753][33296] Avg episode reward: [(0, '548.593')]
[2023-07-15 18:52:40,756][33537] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000011320_5795840.pth...
[2023-07-15 18:52:40,758][33537] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000010912_5586944.pth
[2023-07-15 18:52:43,705][33581] Updated weights for policy 0, policy_version 11360 (0.0004)
[2023-07-15 18:52:45,752][33296] Fps is (10 sec: 6963.1, 60 sec: 6963.2, 300 sec: 7136.8). Total num frames: 5828608. Throughput: 0: 6984.1. Samples: 5813208. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 18:52:45,753][33296] Avg episode reward: [(0, '551.331')]
[2023-07-15 18:52:49,825][33581] Updated weights for policy 0, policy_version 11440 (0.0004)
[2023-07-15 18:52:50,752][33296] Fps is (10 sec: 6553.6, 60 sec: 6963.2, 300 sec: 7122.9). Total num frames: 5861376. Throughput: 0: 6972.0. Samples: 5853256. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0)
[2023-07-15 18:52:50,753][33296] Avg episode reward: [(0, '542.644')]
[2023-07-15 18:52:55,275][33581] Updated weights for policy 0, policy_version 11520 (0.0005)
[2023-07-15 18:52:55,752][33296] Fps is (10 sec: 6963.2, 60 sec: 6963.2, 300 sec: 7136.8). Total num frames: 5898240. Throughput: 0: 7009.4. Samples: 5898228. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0)
[2023-07-15 18:52:55,753][33296] Avg episode reward: [(0, '512.991')]
[2023-07-15 18:52:55,755][33537] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000011520_5898240.pth...
[2023-07-15 18:52:55,758][33537] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000011112_5689344.pth
[2023-07-15 18:53:00,752][33296] Fps is (10 sec: 7372.8, 60 sec: 7031.5, 300 sec: 7136.8). Total num frames: 5935104. Throughput: 0: 7046.9. Samples: 5920400. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0)
[2023-07-15 18:53:00,752][33296] Avg episode reward: [(0, '522.277')]
[2023-07-15 18:53:00,895][33581] Updated weights for policy 0, policy_version 11600 (0.0005)
[2023-07-15 18:53:05,752][33296] Fps is (10 sec: 6963.2, 60 sec: 6963.2, 300 sec: 7136.8). Total num frames: 5967872. Throughput: 0: 6959.0. Samples: 5961612. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 18:53:05,753][33296] Avg episode reward: [(0, '525.929')]
[2023-07-15 18:53:06,921][33581] Updated weights for policy 0, policy_version 11680 (0.0006)
[2023-07-15 18:53:10,752][33296] Fps is (10 sec: 6963.1, 60 sec: 7031.5, 300 sec: 7136.8). Total num frames: 6004736. Throughput: 0: 6985.0. Samples: 6003732. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 18:53:10,753][33296] Avg episode reward: [(0, '521.813')]
[2023-07-15 18:53:10,756][33537] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000011728_6004736.pth...
[2023-07-15 18:53:10,758][33537] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000011320_5795840.pth
[2023-07-15 18:53:12,678][33581] Updated weights for policy 0, policy_version 11760 (0.0005)
[2023-07-15 18:53:15,752][33296] Fps is (10 sec: 7372.8, 60 sec: 7031.5, 300 sec: 7136.8). Total num frames: 6041600. Throughput: 0: 7008.3. Samples: 6025204. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0)
[2023-07-15 18:53:15,753][33296] Avg episode reward: [(0, '514.468')]
[2023-07-15 18:53:18,129][33581] Updated weights for policy 0, policy_version 11840 (0.0005)
[2023-07-15 18:53:20,752][33296] Fps is (10 sec: 7372.9, 60 sec: 7031.5, 300 sec: 7150.6). Total num frames: 6078464. Throughput: 0: 7088.0. Samples: 6070220. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0)
[2023-07-15 18:53:20,752][33296] Avg episode reward: [(0, '548.339')]
[2023-07-15 18:53:24,155][33581] Updated weights for policy 0, policy_version 11920 (0.0004)
[2023-07-15 18:53:25,752][33296] Fps is (10 sec: 6963.2, 60 sec: 7031.5, 300 sec: 7136.8). Total num frames: 6111232. Throughput: 0: 7091.3. Samples: 6111864. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 18:53:25,753][33296] Avg episode reward: [(0, '523.112')]
[2023-07-15 18:53:25,770][33537] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000011944_6115328.pth...
[2023-07-15 18:53:25,772][33537] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000011520_5898240.pth
[2023-07-15 18:53:29,986][33581] Updated weights for policy 0, policy_version 12000 (0.0005)
[2023-07-15 18:53:30,752][33296] Fps is (10 sec: 6963.1, 60 sec: 7031.5, 300 sec: 7136.8). Total num frames: 6148096. Throughput: 0: 7086.7. Samples: 6132108. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 18:53:30,753][33296] Avg episode reward: [(0, '515.999')]
[2023-07-15 18:53:35,653][33581] Updated weights for policy 0, policy_version 12080 (0.0005)
[2023-07-15 18:53:35,752][33296] Fps is (10 sec: 7372.8, 60 sec: 7099.7, 300 sec: 7136.8). Total num frames: 6184960. Throughput: 0: 7161.8. Samples: 6175536. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0)
[2023-07-15 18:53:35,753][33296] Avg episode reward: [(0, '504.898')]
[2023-07-15 18:53:40,752][33296] Fps is (10 sec: 6963.3, 60 sec: 7031.5, 300 sec: 7122.9). Total num frames: 6217728. Throughput: 0: 7101.4. Samples: 6217792. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0)
[2023-07-15 18:53:40,752][33296] Avg episode reward: [(0, '515.294')]
[2023-07-15 18:53:40,755][33537] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000012144_6217728.pth...
[2023-07-15 18:53:40,756][33537] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000011728_6004736.pth
[2023-07-15 18:53:41,395][33581] Updated weights for policy 0, policy_version 12160 (0.0005)
[2023-07-15 18:53:45,752][33296] Fps is (10 sec: 6963.2, 60 sec: 7099.7, 300 sec: 7122.9). Total num frames: 6254592. Throughput: 0: 7097.4. Samples: 6239784. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 18:53:45,752][33296] Avg episode reward: [(0, '508.913')]
[2023-07-15 18:53:47,118][33581] Updated weights for policy 0, policy_version 12240 (0.0005)
[2023-07-15 18:53:50,752][33296] Fps is (10 sec: 7372.7, 60 sec: 7168.0, 300 sec: 7122.9). Total num frames: 6291456. Throughput: 0: 7117.6. Samples: 6281904. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 18:53:50,753][33296] Avg episode reward: [(0, '513.429')]
[2023-07-15 18:53:52,997][33581] Updated weights for policy 0, policy_version 12320 (0.0004)
[2023-07-15 18:53:55,752][33296] Fps is (10 sec: 6963.1, 60 sec: 7099.7, 300 sec: 7122.9). Total num frames: 6324224. Throughput: 0: 7097.5. Samples: 6323120. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0)
[2023-07-15 18:53:55,753][33296] Avg episode reward: [(0, '513.015')]
[2023-07-15 18:53:55,756][33537] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000012352_6324224.pth...
[2023-07-15 18:53:55,759][33537] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000011944_6115328.pth
[2023-07-15 18:53:59,139][33581] Updated weights for policy 0, policy_version 12400 (0.0005)
[2023-07-15 18:54:00,752][33296] Fps is (10 sec: 6553.6, 60 sec: 7031.5, 300 sec: 7095.1). Total num frames: 6356992. Throughput: 0: 7058.7. Samples: 6342844. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0)
[2023-07-15 18:54:00,753][33296] Avg episode reward: [(0, '496.627')]
[2023-07-15 18:54:04,739][33581] Updated weights for policy 0, policy_version 12480 (0.0005)
[2023-07-15 18:54:05,752][33296] Fps is (10 sec: 6963.2, 60 sec: 7099.7, 300 sec: 7095.1). Total num frames: 6393856. Throughput: 0: 7016.9. Samples: 6385980. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 18:54:05,753][33296] Avg episode reward: [(0, '528.824')]
[2023-07-15 18:54:10,154][33581] Updated weights for policy 0, policy_version 12560 (0.0006)
[2023-07-15 18:54:10,752][33296] Fps is (10 sec: 7782.4, 60 sec: 7168.0, 300 sec: 7109.0). Total num frames: 6434816. Throughput: 0: 7092.0. Samples: 6431004. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0)
[2023-07-15 18:54:10,753][33296] Avg episode reward: [(0, '504.686')]
[2023-07-15 18:54:10,756][33537] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000012568_6434816.pth...
[2023-07-15 18:54:10,758][33537] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000012144_6217728.pth
[2023-07-15 18:54:15,745][33581] Updated weights for policy 0, policy_version 12640 (0.0005)
[2023-07-15 18:54:15,752][33296] Fps is (10 sec: 7782.4, 60 sec: 7168.0, 300 sec: 7109.0). Total num frames: 6471680. Throughput: 0: 7151.8. Samples: 6453940. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0)
[2023-07-15 18:54:15,753][33296] Avg episode reward: [(0, '530.920')]
[2023-07-15 18:54:20,752][33296] Fps is (10 sec: 6963.3, 60 sec: 7099.7, 300 sec: 7095.1). Total num frames: 6504448. Throughput: 0: 7145.1. Samples: 6497064. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 18:54:20,753][33296] Avg episode reward: [(0, '537.559')]
[2023-07-15 18:54:21,634][33581] Updated weights for policy 0, policy_version 12720 (0.0005)
[2023-07-15 18:54:25,752][33296] Fps is (10 sec: 6963.2, 60 sec: 7168.0, 300 sec: 7095.1). Total num frames: 6541312. Throughput: 0: 7140.0. Samples: 6539092. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 18:54:25,753][33296] Avg episode reward: [(0, '526.239')]
[2023-07-15 18:54:25,756][33537] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000012776_6541312.pth...
[2023-07-15 18:54:25,758][33537] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000012352_6324224.pth
[2023-07-15 18:54:27,187][33581] Updated weights for policy 0, policy_version 12800 (0.0005)
[2023-07-15 18:54:30,752][33296] Fps is (10 sec: 7372.8, 60 sec: 7168.0, 300 sec: 7109.0). Total num frames: 6578176. Throughput: 0: 7153.2. Samples: 6561680. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 18:54:30,753][33296] Avg episode reward: [(0, '534.364')]
[2023-07-15 18:54:33,025][33581] Updated weights for policy 0, policy_version 12880 (0.0005)
[2023-07-15 18:54:35,752][33296] Fps is (10 sec: 6963.2, 60 sec: 7099.7, 300 sec: 7095.1). Total num frames: 6610944. Throughput: 0: 7130.0. Samples: 6602752. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 18:54:35,898][33296] Avg episode reward: [(0, '541.004')]
[2023-07-15 18:54:38,881][33581] Updated weights for policy 0, policy_version 12960 (0.0005)
[2023-07-15 18:54:40,752][33296] Fps is (10 sec: 6963.2, 60 sec: 7168.0, 300 sec: 7095.1). Total num frames: 6647808. Throughput: 0: 7181.0. Samples: 6646264. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0)
[2023-07-15 18:54:40,753][33296] Avg episode reward: [(0, '541.516')]
[2023-07-15 18:54:40,756][33537] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000012984_6647808.pth...
[2023-07-15 18:54:40,758][33537] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000012568_6434816.pth
[2023-07-15 18:54:44,315][33581] Updated weights for policy 0, policy_version 13040 (0.0005)
[2023-07-15 18:54:45,752][33296] Fps is (10 sec: 7372.7, 60 sec: 7168.0, 300 sec: 7109.0). Total num frames: 6684672. Throughput: 0: 7232.4. Samples: 6668300. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0)
[2023-07-15 18:54:45,753][33296] Avg episode reward: [(0, '520.398')]
[2023-07-15 18:54:50,031][33581] Updated weights for policy 0, policy_version 13120 (0.0006)
[2023-07-15 18:54:50,752][33296] Fps is (10 sec: 7372.8, 60 sec: 7168.0, 300 sec: 7095.1). Total num frames: 6721536. Throughput: 0: 7251.6. Samples: 6712300. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 18:54:50,753][33296] Avg episode reward: [(0, '534.288')]
[2023-07-15 18:54:55,095][33581] Updated weights for policy 0, policy_version 13200 (0.0005)
[2023-07-15 18:54:55,752][33296] Fps is (10 sec: 7782.4, 60 sec: 7304.5, 300 sec: 7122.9). Total num frames: 6762496. Throughput: 0: 7294.6. Samples: 6759260. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 18:54:55,753][33296] Avg episode reward: [(0, '512.313')]
[2023-07-15 18:54:55,756][33537] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000013208_6762496.pth...
[2023-07-15 18:54:55,758][33537] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000012776_6541312.pth
[2023-07-15 18:55:00,752][33296] Fps is (10 sec: 7372.8, 60 sec: 7304.5, 300 sec: 7122.9). Total num frames: 6795264. Throughput: 0: 7284.9. Samples: 6781760. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0)
[2023-07-15 18:55:00,753][33296] Avg episode reward: [(0, '524.902')]
[2023-07-15 18:55:00,758][33581] Updated weights for policy 0, policy_version 13280 (0.0006)
[2023-07-15 18:55:05,752][33296] Fps is (10 sec: 7372.9, 60 sec: 7372.8, 300 sec: 7136.8). Total num frames: 6836224. Throughput: 0: 7318.5. Samples: 6826396. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0)
[2023-07-15 18:55:05,753][33296] Avg episode reward: [(0, '513.892')]
[2023-07-15 18:55:06,225][33581] Updated weights for policy 0, policy_version 13360 (0.0005)
[2023-07-15 18:55:10,752][33296] Fps is (10 sec: 7372.8, 60 sec: 7236.3, 300 sec: 7136.8). Total num frames: 6868992. Throughput: 0: 7327.6. Samples: 6868832. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 18:55:10,752][33296] Avg episode reward: [(0, '517.924')]
[2023-07-15 18:55:10,755][33537] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000013416_6868992.pth...
[2023-07-15 18:55:10,757][33537] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000012984_6647808.pth
[2023-07-15 18:55:12,127][33581] Updated weights for policy 0, policy_version 13440 (0.0004)
[2023-07-15 18:55:15,752][33296] Fps is (10 sec: 6963.2, 60 sec: 7236.3, 300 sec: 7136.8). Total num frames: 6905856. Throughput: 0: 7282.9. Samples: 6889408. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 18:55:15,753][33296] Avg episode reward: [(0, '543.722')]
[2023-07-15 18:55:17,911][33581] Updated weights for policy 0, policy_version 13520 (0.0006)
[2023-07-15 18:55:20,752][33296] Fps is (10 sec: 7372.8, 60 sec: 7304.5, 300 sec: 7150.6). Total num frames: 6942720. Throughput: 0: 7333.5. Samples: 6932760. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
[2023-07-15 18:55:20,752][33296] Avg episode reward: [(0, '527.777')]
[2023-07-15 18:55:23,399][33581] Updated weights for policy 0, policy_version 13600 (0.0006)
[2023-07-15 18:55:25,752][33296] Fps is (10 sec: 7372.8, 60 sec: 7304.5, 300 sec: 7150.6). Total num frames: 6979584. Throughput: 0: 7353.7. Samples: 6977180. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
[2023-07-15 18:55:25,753][33296] Avg episode reward: [(0, '546.459')]
[2023-07-15 18:55:25,755][33537] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000013632_6979584.pth...
[2023-07-15 18:55:25,758][33537] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000013208_6762496.pth
[2023-07-15 18:55:28,958][33581] Updated weights for policy 0, policy_version 13680 (0.0005)
[2023-07-15 18:55:30,752][33296] Fps is (10 sec: 7372.8, 60 sec: 7304.5, 300 sec: 7136.8). Total num frames: 7016448. Throughput: 0: 7361.5. Samples: 6999568. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 18:55:30,752][33296] Avg episode reward: [(0, '528.297')]
[2023-07-15 18:55:34,469][33581] Updated weights for policy 0, policy_version 13760 (0.0005)
[2023-07-15 18:55:35,752][33296] Fps is (10 sec: 7372.8, 60 sec: 7372.8, 300 sec: 7136.8). Total num frames: 7053312. Throughput: 0: 7346.5. Samples: 7042892. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 18:55:35,753][33296] Avg episode reward: [(0, '544.227')]
[2023-07-15 18:55:40,022][33581] Updated weights for policy 0, policy_version 13840 (0.0005)
[2023-07-15 18:55:40,752][33296] Fps is (10 sec: 7372.7, 60 sec: 7372.8, 300 sec: 7150.6). Total num frames: 7090176. Throughput: 0: 7295.9. Samples: 7087576. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 18:55:40,753][33296] Avg episode reward: [(0, '521.126')]
[2023-07-15 18:55:40,756][33537] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000013848_7090176.pth...
[2023-07-15 18:55:40,758][33537] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000013416_6868992.pth
[2023-07-15 18:55:45,752][33296] Fps is (10 sec: 6963.2, 60 sec: 7304.5, 300 sec: 7136.8). Total num frames: 7122944. Throughput: 0: 7260.9. Samples: 7108500. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 18:55:45,752][33296] Avg episode reward: [(0, '524.292')]
[2023-07-15 18:55:45,947][33581] Updated weights for policy 0, policy_version 13920 (0.0004)
[2023-07-15 18:55:50,752][33296] Fps is (10 sec: 6963.2, 60 sec: 7304.5, 300 sec: 7150.6). Total num frames: 7159808. Throughput: 0: 7192.8. Samples: 7150072. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 18:55:50,753][33296] Avg episode reward: [(0, '513.534')]
[2023-07-15 18:55:51,584][33581] Updated weights for policy 0, policy_version 14000 (0.0004)
[2023-07-15 18:55:55,752][33296] Fps is (10 sec: 7372.7, 60 sec: 7236.3, 300 sec: 7150.6). Total num frames: 7196672. Throughput: 0: 7263.6. Samples: 7195696. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0)
[2023-07-15 18:55:55,753][33296] Avg episode reward: [(0, '531.973')]
[2023-07-15 18:55:55,755][33537] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000014056_7196672.pth...
[2023-07-15 18:55:55,758][33537] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000013632_6979584.pth
[2023-07-15 18:55:57,005][33581] Updated weights for policy 0, policy_version 14080 (0.0005)
[2023-07-15 18:56:00,752][33296] Fps is (10 sec: 7372.8, 60 sec: 7304.5, 300 sec: 7150.6). Total num frames: 7233536. Throughput: 0: 7300.9. Samples: 7217948. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0)
[2023-07-15 18:56:00,753][33296] Avg episode reward: [(0, '521.203')]
[2023-07-15 18:56:02,620][33581] Updated weights for policy 0, policy_version 14160 (0.0005)
[2023-07-15 18:56:05,752][33296] Fps is (10 sec: 7372.9, 60 sec: 7236.3, 300 sec: 7164.5). Total num frames: 7270400. Throughput: 0: 7291.7. Samples: 7260888. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 18:56:05,752][33296] Avg episode reward: [(0, '526.125')]
[2023-07-15 18:56:08,545][33581] Updated weights for policy 0, policy_version 14240 (0.0004)
[2023-07-15 18:56:10,752][33296] Fps is (10 sec: 6963.2, 60 sec: 7236.3, 300 sec: 7150.6). Total num frames: 7303168. Throughput: 0: 7231.6. Samples: 7302604. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 18:56:10,753][33296] Avg episode reward: [(0, '532.316')]
[2023-07-15 18:56:10,755][33537] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000014264_7303168.pth...
[2023-07-15 18:56:10,758][33537] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000013848_7090176.pth
[2023-07-15 18:56:14,477][33581] Updated weights for policy 0, policy_version 14320 (0.0005)
[2023-07-15 18:56:15,752][33296] Fps is (10 sec: 6963.2, 60 sec: 7236.3, 300 sec: 7150.6). Total num frames: 7340032. Throughput: 0: 7201.5. Samples: 7323636. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 18:56:15,753][33296] Avg episode reward: [(0, '547.868')]
[2023-07-15 18:56:20,169][33581] Updated weights for policy 0, policy_version 14400 (0.0005)
[2023-07-15 18:56:20,752][33296] Fps is (10 sec: 6963.2, 60 sec: 7168.0, 300 sec: 7150.6). Total num frames: 7372800. Throughput: 0: 7188.6. Samples: 7366380. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 18:56:20,753][33296] Avg episode reward: [(0, '519.075')]
[2023-07-15 18:56:25,752][33296] Fps is (10 sec: 6963.1, 60 sec: 7168.0, 300 sec: 7164.5). Total num frames: 7409664. Throughput: 0: 7159.1. Samples: 7409736. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0)
[2023-07-15 18:56:25,753][33296] Avg episode reward: [(0, '541.425')]
[2023-07-15 18:56:25,761][33537] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000014480_7413760.pth...
[2023-07-15 18:56:25,762][33581] Updated weights for policy 0, policy_version 14480 (0.0005)
[2023-07-15 18:56:25,763][33537] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000014056_7196672.pth
[2023-07-15 18:56:30,752][33296] Fps is (10 sec: 7372.8, 60 sec: 7168.0, 300 sec: 7150.6). Total num frames: 7446528. Throughput: 0: 7192.0. Samples: 7432140. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0)
[2023-07-15 18:56:30,753][33296] Avg episode reward: [(0, '544.691')]
[2023-07-15 18:56:31,444][33581] Updated weights for policy 0, policy_version 14560 (0.0005)
[2023-07-15 18:56:35,752][33296] Fps is (10 sec: 7372.8, 60 sec: 7168.0, 300 sec: 7150.6). Total num frames: 7483392. Throughput: 0: 7195.5. Samples: 7473872. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 18:56:35,753][33296] Avg episode reward: [(0, '524.801')]
[2023-07-15 18:56:37,491][33581] Updated weights for policy 0, policy_version 14640 (0.0005)
[2023-07-15 18:56:40,752][33296] Fps is (10 sec: 6963.1, 60 sec: 7099.7, 300 sec: 7136.8). Total num frames: 7516160. Throughput: 0: 7103.1. Samples: 7515336. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 18:56:40,753][33296] Avg episode reward: [(0, '510.783')]
[2023-07-15 18:56:40,756][33537] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000014680_7516160.pth...
[2023-07-15 18:56:40,758][33537] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000014264_7303168.pth
[2023-07-15 18:56:43,509][33581] Updated weights for policy 0, policy_version 14720 (0.0005)
[2023-07-15 18:56:45,752][33296] Fps is (10 sec: 6553.6, 60 sec: 7099.7, 300 sec: 7136.8). Total num frames: 7548928. Throughput: 0: 7050.4. Samples: 7535216. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 18:56:45,752][33296] Avg episode reward: [(0, '545.283')]
[2023-07-15 18:56:49,194][33581] Updated weights for policy 0, policy_version 14800 (0.0005)
[2023-07-15 18:56:50,752][33296] Fps is (10 sec: 6963.2, 60 sec: 7099.7, 300 sec: 7136.8). Total num frames: 7585792. Throughput: 0: 7039.5. Samples: 7577664. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 18:56:50,753][33296] Avg episode reward: [(0, '494.236')]
[2023-07-15 18:56:54,626][33581] Updated weights for policy 0, policy_version 14880 (0.0005)
[2023-07-15 18:56:55,752][33296] Fps is (10 sec: 7782.3, 60 sec: 7168.0, 300 sec: 7164.5). Total num frames: 7626752. Throughput: 0: 7115.1. Samples: 7622784. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0)
[2023-07-15 18:56:55,753][33296] Avg episode reward: [(0, '504.712')]
[2023-07-15 18:56:55,756][33537] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000014896_7626752.pth...
[2023-07-15 18:56:55,758][33537] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000014480_7413760.pth
[2023-07-15 18:57:00,150][33581] Updated weights for policy 0, policy_version 14960 (0.0005)
[2023-07-15 18:57:00,752][33296] Fps is (10 sec: 7782.3, 60 sec: 7168.0, 300 sec: 7164.5). Total num frames: 7663616. Throughput: 0: 7142.7. Samples: 7645056. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0)
[2023-07-15 18:57:00,753][33296] Avg episode reward: [(0, '530.857')]
[2023-07-15 18:57:05,752][33296] Fps is (10 sec: 6963.3, 60 sec: 7099.7, 300 sec: 7164.5). Total num frames: 7696384. Throughput: 0: 7161.2. Samples: 7688632. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0)
[2023-07-15 18:57:05,752][33296] Avg episode reward: [(0, '520.092')]
[2023-07-15 18:57:05,992][33581] Updated weights for policy 0, policy_version 15040 (0.0005)
[2023-07-15 18:57:10,752][33296] Fps is (10 sec: 6963.3, 60 sec: 7168.0, 300 sec: 7164.5). Total num frames: 7733248. Throughput: 0: 7169.4. Samples: 7732360. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0)
[2023-07-15 18:57:10,753][33296] Avg episode reward: [(0, '512.407')]
[2023-07-15 18:57:10,755][33537] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000015104_7733248.pth...
[2023-07-15 18:57:10,757][33537] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000014680_7516160.pth
[2023-07-15 18:57:11,548][33581] Updated weights for policy 0, policy_version 15120 (0.0005)
[2023-07-15 18:57:15,752][33296] Fps is (10 sec: 7372.8, 60 sec: 7168.0, 300 sec: 7164.5). Total num frames: 7770112. Throughput: 0: 7173.8. Samples: 7754960. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0)
[2023-07-15 18:57:15,753][33296] Avg episode reward: [(0, '544.145')]
[2023-07-15 18:57:16,869][33581] Updated weights for policy 0, policy_version 15200 (0.0005)
[2023-07-15 18:57:20,752][33296] Fps is (10 sec: 7372.8, 60 sec: 7236.3, 300 sec: 7178.4). Total num frames: 7806976. Throughput: 0: 7237.2. Samples: 7799544. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0)
[2023-07-15 18:57:20,752][33296] Avg episode reward: [(0, '537.687')]
[2023-07-15 18:57:22,659][33581] Updated weights for policy 0, policy_version 15280 (0.0004)
[2023-07-15 18:57:25,752][33296] Fps is (10 sec: 7372.8, 60 sec: 7236.3, 300 sec: 7178.4). Total num frames: 7843840. Throughput: 0: 7244.7. Samples: 7841348. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0)
[2023-07-15 18:57:25,753][33296] Avg episode reward: [(0, '551.648')]
[2023-07-15 18:57:25,755][33537] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000015320_7843840.pth...
[2023-07-15 18:57:25,758][33537] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000014896_7626752.pth
[2023-07-15 18:57:28,584][33581] Updated weights for policy 0, policy_version 15360 (0.0005)
[2023-07-15 18:57:30,752][33296] Fps is (10 sec: 6963.2, 60 sec: 7168.0, 300 sec: 7178.4). Total num frames: 7876608. Throughput: 0: 7261.8. Samples: 7861996. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 18:57:30,752][33296] Avg episode reward: [(0, '534.579')]
[2023-07-15 18:57:34,305][33581] Updated weights for policy 0, policy_version 15440 (0.0005)
[2023-07-15 18:57:35,752][33296] Fps is (10 sec: 6963.2, 60 sec: 7168.0, 300 sec: 7178.4). Total num frames: 7913472. Throughput: 0: 7278.8. Samples: 7905212. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 18:57:35,753][33296] Avg episode reward: [(0, '537.731')]
[2023-07-15 18:57:39,841][33581] Updated weights for policy 0, policy_version 15520 (0.0005)
[2023-07-15 18:57:40,752][33296] Fps is (10 sec: 7372.7, 60 sec: 7236.3, 300 sec: 7192.3). Total num frames: 7950336. Throughput: 0: 7260.4. Samples: 7949504. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0)
[2023-07-15 18:57:40,753][33296] Avg episode reward: [(0, '529.414')]
[2023-07-15 18:57:40,756][33537] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000015528_7950336.pth...
[2023-07-15 18:57:40,758][33537] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000015104_7733248.pth
[2023-07-15 18:57:45,578][33581] Updated weights for policy 0, policy_version 15600 (0.0005)
[2023-07-15 18:57:45,752][33296] Fps is (10 sec: 7372.8, 60 sec: 7304.5, 300 sec: 7206.2). Total num frames: 7987200. Throughput: 0: 7238.7. Samples: 7970796. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0)
[2023-07-15 18:57:45,752][33296] Avg episode reward: [(0, '543.323')]
[2023-07-15 18:57:50,752][33296] Fps is (10 sec: 6963.3, 60 sec: 7236.3, 300 sec: 7192.3). Total num frames: 8019968. Throughput: 0: 7215.7. Samples: 8013336. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0)
[2023-07-15 18:57:50,752][33296] Avg episode reward: [(0, '501.482')]
[2023-07-15 18:57:51,440][33581] Updated weights for policy 0, policy_version 15680 (0.0004)
[2023-07-15 18:57:55,752][33296] Fps is (10 sec: 6963.1, 60 sec: 7168.0, 300 sec: 7192.3). Total num frames: 8056832. Throughput: 0: 7189.6. Samples: 8055892. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 18:57:55,753][33296] Avg episode reward: [(0, '534.346')]
[2023-07-15 18:57:55,756][33537] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000015736_8056832.pth...
[2023-07-15 18:57:55,758][33537] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000015320_7843840.pth
[2023-07-15 18:57:57,339][33581] Updated weights for policy 0, policy_version 15760 (0.0005)
[2023-07-15 18:58:00,752][33296] Fps is (10 sec: 6963.1, 60 sec: 7099.7, 300 sec: 7192.3). Total num frames: 8089600. Throughput: 0: 7117.8. Samples: 8075260. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 18:58:00,753][33296] Avg episode reward: [(0, '536.652')]
[2023-07-15 18:58:03,221][33581] Updated weights for policy 0, policy_version 15840 (0.0005)
[2023-07-15 18:58:05,752][33296] Fps is (10 sec: 6963.3, 60 sec: 7168.0, 300 sec: 7192.3). Total num frames: 8126464. Throughput: 0: 7078.9. Samples: 8118096. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 18:58:05,752][33296] Avg episode reward: [(0, '524.507')]
[2023-07-15 18:58:08,791][33581] Updated weights for policy 0, policy_version 15920 (0.0005)
[2023-07-15 18:58:10,752][33296] Fps is (10 sec: 7372.8, 60 sec: 7168.0, 300 sec: 7192.3). Total num frames: 8163328. Throughput: 0: 7113.0. Samples: 8161432. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 18:58:10,753][33296] Avg episode reward: [(0, '516.778')]
[2023-07-15 18:58:10,756][33537] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000015944_8163328.pth...
[2023-07-15 18:58:10,758][33537] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000015528_7950336.pth
[2023-07-15 18:58:14,531][33581] Updated weights for policy 0, policy_version 16000 (0.0005)
[2023-07-15 18:58:15,752][33296] Fps is (10 sec: 6963.2, 60 sec: 7099.7, 300 sec: 7178.4). Total num frames: 8196096. Throughput: 0: 7150.7. Samples: 8183780. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0)
[2023-07-15 18:58:15,753][33296] Avg episode reward: [(0, '556.521')]
[2023-07-15 18:58:15,793][33537] Saving new best policy, reward=556.521!
[2023-07-15 18:58:20,469][33581] Updated weights for policy 0, policy_version 16080 (0.0005)
[2023-07-15 18:58:20,752][33296] Fps is (10 sec: 6963.2, 60 sec: 7099.7, 300 sec: 7192.3). Total num frames: 8232960. Throughput: 0: 7093.5. Samples: 8224420. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0)
[2023-07-15 18:58:20,753][33296] Avg episode reward: [(0, '519.003')]
[2023-07-15 18:58:25,752][33296] Fps is (10 sec: 6963.2, 60 sec: 7031.5, 300 sec: 7178.4). Total num frames: 8265728. Throughput: 0: 7024.3. Samples: 8265596. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0)
[2023-07-15 18:58:25,752][33296] Avg episode reward: [(0, '524.282')]
[2023-07-15 18:58:25,755][33537] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000016144_8265728.pth...
[2023-07-15 18:58:25,757][33537] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000015736_8056832.pth
[2023-07-15 18:58:26,673][33581] Updated weights for policy 0, policy_version 16160 (0.0005)
[2023-07-15 18:58:30,752][33296] Fps is (10 sec: 6553.6, 60 sec: 7031.5, 300 sec: 7164.5). Total num frames: 8298496. Throughput: 0: 6975.1. Samples: 8284676. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0)
[2023-07-15 18:58:30,753][33296] Avg episode reward: [(0, '541.929')]
[2023-07-15 18:58:32,836][33581] Updated weights for policy 0, policy_version 16240 (0.0005)
[2023-07-15 18:58:35,752][33296] Fps is (10 sec: 6553.6, 60 sec: 6963.2, 300 sec: 7164.5). Total num frames: 8331264. Throughput: 0: 6903.5. Samples: 8323992. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0)
[2023-07-15 18:58:35,753][33296] Avg episode reward: [(0, '518.750')]
[2023-07-15 18:58:38,835][33581] Updated weights for policy 0, policy_version 16320 (0.0005)
[2023-07-15 18:58:40,752][33296] Fps is (10 sec: 6963.1, 60 sec: 6963.2, 300 sec: 7164.5). Total num frames: 8368128. Throughput: 0: 6910.4. Samples: 8366860. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0)
[2023-07-15 18:58:40,753][33296] Avg episode reward: [(0, '552.404')]
[2023-07-15 18:58:40,756][33537] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000016344_8368128.pth...
[2023-07-15 18:58:40,759][33537] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000015944_8163328.pth
[2023-07-15 18:58:44,061][33581] Updated weights for policy 0, policy_version 16400 (0.0005)
[2023-07-15 18:58:45,752][33296] Fps is (10 sec: 7782.5, 60 sec: 7031.5, 300 sec: 7178.4). Total num frames: 8409088. Throughput: 0: 6970.2. Samples: 8388916. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0)
[2023-07-15 18:58:45,752][33296] Avg episode reward: [(0, '559.720')]
[2023-07-15 18:58:45,753][33537] Saving new best policy, reward=559.720!
[2023-07-15 18:58:49,434][33581] Updated weights for policy 0, policy_version 16480 (0.0005)
[2023-07-15 18:58:50,752][33296] Fps is (10 sec: 7782.5, 60 sec: 7099.7, 300 sec: 7192.3). Total num frames: 8445952. Throughput: 0: 7083.1. Samples: 8436836. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0)
[2023-07-15 18:58:50,753][33296] Avg episode reward: [(0, '515.901')]
[2023-07-15 18:58:55,611][33581] Updated weights for policy 0, policy_version 16560 (0.0005)
[2023-07-15 18:58:55,752][33296] Fps is (10 sec: 6963.1, 60 sec: 7031.5, 300 sec: 7192.3). Total num frames: 8478720. Throughput: 0: 6987.8. Samples: 8475884. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0)
[2023-07-15 18:58:55,753][33296] Avg episode reward: [(0, '512.744')]
[2023-07-15 18:58:55,755][33537] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000016560_8478720.pth...
[2023-07-15 18:58:55,758][33537] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000016144_8265728.pth
[2023-07-15 18:59:00,752][33296] Fps is (10 sec: 6553.6, 60 sec: 7031.5, 300 sec: 7178.4). Total num frames: 8511488. Throughput: 0: 6989.7. Samples: 8498316. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0)
[2023-07-15 18:59:00,753][33296] Avg episode reward: [(0, '535.410')]
[2023-07-15 18:59:01,551][33581] Updated weights for policy 0, policy_version 16640 (0.0005)
[2023-07-15 18:59:05,752][33296] Fps is (10 sec: 6963.2, 60 sec: 7031.5, 300 sec: 7164.5). Total num frames: 8548352. Throughput: 0: 6977.8. Samples: 8538420. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 18:59:05,753][33296] Avg episode reward: [(0, '532.936')]
[2023-07-15 18:59:07,372][33581] Updated weights for policy 0, policy_version 16720 (0.0005)
[2023-07-15 18:59:10,752][33296] Fps is (10 sec: 6963.2, 60 sec: 6963.2, 300 sec: 7150.6). Total num frames: 8581120. Throughput: 0: 7011.6. Samples: 8581120. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 18:59:10,753][33296] Avg episode reward: [(0, '536.781')]
[2023-07-15 18:59:10,756][33537] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000016760_8581120.pth...
[2023-07-15 18:59:10,758][33537] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000016344_8368128.pth
[2023-07-15 18:59:13,061][33581] Updated weights for policy 0, policy_version 16800 (0.0005)
[2023-07-15 18:59:15,752][33296] Fps is (10 sec: 6963.2, 60 sec: 7031.5, 300 sec: 7164.5). Total num frames: 8617984. Throughput: 0: 7066.4. Samples: 8602664. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 18:59:15,753][33296] Avg episode reward: [(0, '532.030')]
[2023-07-15 18:59:18,724][33581] Updated weights for policy 0, policy_version 16880 (0.0005)
[2023-07-15 18:59:20,752][33296] Fps is (10 sec: 7372.8, 60 sec: 7031.5, 300 sec: 7164.5). Total num frames: 8654848. Throughput: 0: 7169.2. Samples: 8646608. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 18:59:20,753][33296] Avg episode reward: [(0, '537.402')]
[2023-07-15 18:59:24,730][33581] Updated weights for policy 0, policy_version 16960 (0.0005)
[2023-07-15 18:59:25,752][33296] Fps is (10 sec: 6963.3, 60 sec: 7031.5, 300 sec: 7150.6). Total num frames: 8687616. Throughput: 0: 7127.1. Samples: 8687576. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 18:59:25,753][33296] Avg episode reward: [(0, '539.403')]
[2023-07-15 18:59:25,755][33537] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000016968_8687616.pth...
[2023-07-15 18:59:25,756][33537] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000016560_8478720.pth
[2023-07-15 18:59:30,539][33581] Updated weights for policy 0, policy_version 17040 (0.0005)
[2023-07-15 18:59:30,752][33296] Fps is (10 sec: 6963.2, 60 sec: 7099.7, 300 sec: 7164.5). Total num frames: 8724480. Throughput: 0: 7098.6. Samples: 8708352. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0)
[2023-07-15 18:59:30,753][33296] Avg episode reward: [(0, '519.034')]
[2023-07-15 18:59:35,752][33296] Fps is (10 sec: 7372.8, 60 sec: 7168.0, 300 sec: 7164.5). Total num frames: 8761344. Throughput: 0: 7048.0. Samples: 8753996. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0)
[2023-07-15 18:59:35,753][33296] Avg episode reward: [(0, '525.534')]
[2023-07-15 18:59:35,931][33581] Updated weights for policy 0, policy_version 17120 (0.0005)
[2023-07-15 18:59:40,752][33296] Fps is (10 sec: 7372.8, 60 sec: 7168.0, 300 sec: 7164.5). Total num frames: 8798208. Throughput: 0: 7159.5. Samples: 8798060. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 18:59:40,753][33296] Avg episode reward: [(0, '515.906')]
[2023-07-15 18:59:40,755][33537] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000017184_8798208.pth...
[2023-07-15 18:59:40,757][33537] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000016760_8581120.pth
[2023-07-15 18:59:41,340][33581] Updated weights for policy 0, policy_version 17200 (0.0005)
[2023-07-15 18:59:45,752][33296] Fps is (10 sec: 7372.8, 60 sec: 7099.7, 300 sec: 7164.5). Total num frames: 8835072. Throughput: 0: 7131.5. Samples: 8819236. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 18:59:45,753][33296] Avg episode reward: [(0, '545.048')]
[2023-07-15 18:59:47,114][33581] Updated weights for policy 0, policy_version 17280 (0.0005)
[2023-07-15 18:59:50,752][33296] Fps is (10 sec: 7372.8, 60 sec: 7099.7, 300 sec: 7150.6). Total num frames: 8871936. Throughput: 0: 7229.6. Samples: 8863752. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
[2023-07-15 18:59:50,753][33296] Avg episode reward: [(0, '486.051')]
[2023-07-15 18:59:52,477][33581] Updated weights for policy 0, policy_version 17360 (0.0005)
[2023-07-15 18:59:55,752][33296] Fps is (10 sec: 7372.8, 60 sec: 7168.0, 300 sec: 7164.5). Total num frames: 8908800. Throughput: 0: 7273.1. Samples: 8908408. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
[2023-07-15 18:59:55,753][33296] Avg episode reward: [(0, '498.782')]
[2023-07-15 18:59:55,755][33537] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000017400_8908800.pth...
[2023-07-15 18:59:55,758][33537] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000016968_8687616.pth
[2023-07-15 18:59:58,350][33581] Updated weights for policy 0, policy_version 17440 (0.0005)
[2023-07-15 19:00:00,752][33296] Fps is (10 sec: 7372.9, 60 sec: 7236.3, 300 sec: 7150.6). Total num frames: 8945664. Throughput: 0: 7256.1. Samples: 8929188. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
[2023-07-15 19:00:00,752][33296] Avg episode reward: [(0, '511.481')]
[2023-07-15 19:00:04,188][33581] Updated weights for policy 0, policy_version 17520 (0.0005)
[2023-07-15 19:00:05,752][33296] Fps is (10 sec: 6963.1, 60 sec: 7168.0, 300 sec: 7150.6). Total num frames: 8978432. Throughput: 0: 7193.4. Samples: 8970312. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 19:00:05,753][33296] Avg episode reward: [(0, '534.195')]
[2023-07-15 19:00:10,075][33581] Updated weights for policy 0, policy_version 17600 (0.0005)
[2023-07-15 19:00:10,752][33296] Fps is (10 sec: 6963.2, 60 sec: 7236.3, 300 sec: 7150.6). Total num frames: 9015296. Throughput: 0: 7211.2. Samples: 9012080. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 19:00:10,752][33296] Avg episode reward: [(0, '523.403')]
[2023-07-15 19:00:10,755][33537] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000017608_9015296.pth...
[2023-07-15 19:00:10,757][33537] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000017184_8798208.pth
[2023-07-15 19:00:15,752][33296] Fps is (10 sec: 6963.3, 60 sec: 7168.0, 300 sec: 7136.8). Total num frames: 9048064. Throughput: 0: 7226.0. Samples: 9033520. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0)
[2023-07-15 19:00:15,752][33296] Avg episode reward: [(0, '511.312')]
[2023-07-15 19:00:15,820][33581] Updated weights for policy 0, policy_version 17680 (0.0005)
[2023-07-15 19:00:20,752][33296] Fps is (10 sec: 6963.2, 60 sec: 7168.0, 300 sec: 7136.8). Total num frames: 9084928. Throughput: 0: 7169.2. Samples: 9076608. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0)
[2023-07-15 19:00:20,753][33296] Avg episode reward: [(0, '523.620')]
[2023-07-15 19:00:21,627][33581] Updated weights for policy 0, policy_version 17760 (0.0005)
[2023-07-15 19:00:25,752][33296] Fps is (10 sec: 7372.8, 60 sec: 7236.3, 300 sec: 7136.8). Total num frames: 9121792. Throughput: 0: 7191.0. Samples: 9121656. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0)
[2023-07-15 19:00:25,753][33296] Avg episode reward: [(0, '523.527')]
[2023-07-15 19:00:25,755][33537] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000017816_9121792.pth...
[2023-07-15 19:00:25,757][33537] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000017400_8908800.pth
[2023-07-15 19:00:27,091][33581] Updated weights for policy 0, policy_version 17840 (0.0005)
[2023-07-15 19:00:30,752][33296] Fps is (10 sec: 7372.8, 60 sec: 7236.3, 300 sec: 7136.8). Total num frames: 9158656. Throughput: 0: 7186.0. Samples: 9142608. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 19:00:30,753][33296] Avg episode reward: [(0, '499.892')]
[2023-07-15 19:00:32,555][33581] Updated weights for policy 0, policy_version 17920 (0.0005)
[2023-07-15 19:00:35,752][33296] Fps is (10 sec: 7782.4, 60 sec: 7304.5, 300 sec: 7150.6). Total num frames: 9199616. Throughput: 0: 7190.8. Samples: 9187336. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 19:00:35,753][33296] Avg episode reward: [(0, '514.801')]
[2023-07-15 19:00:37,909][33581] Updated weights for policy 0, policy_version 18000 (0.0005)
[2023-07-15 19:00:40,752][33296] Fps is (10 sec: 7782.4, 60 sec: 7304.5, 300 sec: 7164.5). Total num frames: 9236480. Throughput: 0: 7272.0. Samples: 9235648. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 19:00:40,753][33296] Avg episode reward: [(0, '514.100')]
[2023-07-15 19:00:40,756][33537] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000018040_9236480.pth...
[2023-07-15 19:00:40,758][33537] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000017608_9015296.pth
[2023-07-15 19:00:43,202][33581] Updated weights for policy 0, policy_version 18080 (0.0005)
[2023-07-15 19:00:45,752][33296] Fps is (10 sec: 7372.8, 60 sec: 7304.5, 300 sec: 7164.5). Total num frames: 9273344. Throughput: 0: 7285.2. Samples: 9257024. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0)
[2023-07-15 19:00:45,753][33296] Avg episode reward: [(0, '523.979')]
[2023-07-15 19:00:48,972][33581] Updated weights for policy 0, policy_version 18160 (0.0005)
[2023-07-15 19:00:50,752][33296] Fps is (10 sec: 6963.2, 60 sec: 7236.3, 300 sec: 7150.6). Total num frames: 9306112. Throughput: 0: 7325.7. Samples: 9299968. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0)
[2023-07-15 19:00:50,753][33296] Avg episode reward: [(0, '522.783')]
[2023-07-15 19:00:54,746][33581] Updated weights for policy 0, policy_version 18240 (0.0005)
[2023-07-15 19:00:55,752][33296] Fps is (10 sec: 6963.2, 60 sec: 7236.3, 300 sec: 7150.6). Total num frames: 9342976. Throughput: 0: 7353.4. Samples: 9342984. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 19:00:55,883][33296] Avg episode reward: [(0, '528.683')]
[2023-07-15 19:00:55,887][33537] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000018256_9347072.pth...
[2023-07-15 19:00:55,889][33537] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000017816_9121792.pth
[2023-07-15 19:01:00,601][33581] Updated weights for policy 0, policy_version 18320 (0.0006)
[2023-07-15 19:01:00,752][33296] Fps is (10 sec: 7372.8, 60 sec: 7236.3, 300 sec: 7150.6). Total num frames: 9379840. Throughput: 0: 7340.6. Samples: 9363848. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 19:01:00,753][33296] Avg episode reward: [(0, '504.455')]
[2023-07-15 19:01:05,752][33296] Fps is (10 sec: 7372.9, 60 sec: 7304.6, 300 sec: 7164.5). Total num frames: 9416704. Throughput: 0: 7304.8. Samples: 9405324. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 19:01:05,753][33296] Avg episode reward: [(0, '516.201')]
[2023-07-15 19:01:06,125][33581] Updated weights for policy 0, policy_version 18400 (0.0005)
[2023-07-15 19:01:10,752][33296] Fps is (10 sec: 7372.7, 60 sec: 7304.5, 300 sec: 7164.5). Total num frames: 9453568. Throughput: 0: 7307.7. Samples: 9450504. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0)
[2023-07-15 19:01:10,753][33296] Avg episode reward: [(0, '523.014')]
[2023-07-15 19:01:10,757][33537] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000018464_9453568.pth...
[2023-07-15 19:01:10,760][33537] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000018040_9236480.pth
[2023-07-15 19:01:11,808][33581] Updated weights for policy 0, policy_version 18480 (0.0005)
[2023-07-15 19:01:15,752][33296] Fps is (10 sec: 6963.1, 60 sec: 7304.5, 300 sec: 7164.5). Total num frames: 9486336. Throughput: 0: 7294.8. Samples: 9470872. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0)
[2023-07-15 19:01:15,753][33296] Avg episode reward: [(0, '500.914')]
[2023-07-15 19:01:17,775][33581] Updated weights for policy 0, policy_version 18560 (0.0005)
[2023-07-15 19:01:20,752][33296] Fps is (10 sec: 6963.3, 60 sec: 7304.5, 300 sec: 7164.5). Total num frames: 9523200. Throughput: 0: 7238.7. Samples: 9513076. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0)
[2023-07-15 19:01:20,753][33296] Avg episode reward: [(0, '520.581')]
[2023-07-15 19:01:23,621][33581] Updated weights for policy 0, policy_version 18640 (0.0005)
[2023-07-15 19:01:25,752][33296] Fps is (10 sec: 7372.7, 60 sec: 7304.5, 300 sec: 7164.5). Total num frames: 9560064. Throughput: 0: 7124.9. Samples: 9556268. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0)
[2023-07-15 19:01:25,753][33296] Avg episode reward: [(0, '514.069')]
[2023-07-15 19:01:25,758][33537] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000018672_9560064.pth...
[2023-07-15 19:01:25,761][33537] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000018256_9347072.pth
[2023-07-15 19:01:29,119][33581] Updated weights for policy 0, policy_version 18720 (0.0005)
[2023-07-15 19:01:30,752][33296] Fps is (10 sec: 6963.2, 60 sec: 7236.3, 300 sec: 7150.6). Total num frames: 9592832. Throughput: 0: 7152.0. Samples: 9578864. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0)
[2023-07-15 19:01:30,753][33296] Avg episode reward: [(0, '533.395')]
[2023-07-15 19:01:34,749][33581] Updated weights for policy 0, policy_version 18800 (0.0005)
[2023-07-15 19:01:35,752][33296] Fps is (10 sec: 6963.3, 60 sec: 7168.0, 300 sec: 7164.5). Total num frames: 9629696. Throughput: 0: 7148.0. Samples: 9621628. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0)
[2023-07-15 19:01:35,753][33296] Avg episode reward: [(0, '500.662')]
[2023-07-15 19:01:40,752][33296] Fps is (10 sec: 6963.1, 60 sec: 7099.7, 300 sec: 7164.5). Total num frames: 9662464. Throughput: 0: 7103.2. Samples: 9662628. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0)
[2023-07-15 19:01:40,753][33296] Avg episode reward: [(0, '517.435')]
[2023-07-15 19:01:40,808][33537] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000018880_9666560.pth...
[2023-07-15 19:01:40,809][33581] Updated weights for policy 0, policy_version 18880 (0.0004)
[2023-07-15 19:01:40,811][33537] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000018464_9453568.pth
[2023-07-15 19:01:45,752][33296] Fps is (10 sec: 6963.3, 60 sec: 7099.7, 300 sec: 7164.5). Total num frames: 9699328. Throughput: 0: 7097.2. Samples: 9683220. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0)
[2023-07-15 19:01:45,753][33296] Avg episode reward: [(0, '516.846')]
[2023-07-15 19:01:46,440][33581] Updated weights for policy 0, policy_version 18960 (0.0005)
[2023-07-15 19:01:50,752][33296] Fps is (10 sec: 7372.9, 60 sec: 7168.0, 300 sec: 7150.6). Total num frames: 9736192. Throughput: 0: 7154.9. Samples: 9727296. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
[2023-07-15 19:01:50,752][33296] Avg episode reward: [(0, '499.505')]
[2023-07-15 19:01:52,299][33581] Updated weights for policy 0, policy_version 19040 (0.0005)
[2023-07-15 19:01:55,752][33296] Fps is (10 sec: 7372.7, 60 sec: 7168.0, 300 sec: 7150.6). Total num frames: 9773056. Throughput: 0: 7090.3. Samples: 9769568. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
[2023-07-15 19:01:55,753][33296] Avg episode reward: [(0, '501.416')]
[2023-07-15 19:01:55,755][33537] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000019088_9773056.pth...
[2023-07-15 19:01:55,757][33537] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000018672_9560064.pth
[2023-07-15 19:01:58,026][33581] Updated weights for policy 0, policy_version 19120 (0.0005)
[2023-07-15 19:02:00,752][33296] Fps is (10 sec: 6963.2, 60 sec: 7099.7, 300 sec: 7150.6). Total num frames: 9805824. Throughput: 0: 7107.7. Samples: 9790720. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 19:02:00,753][33296] Avg episode reward: [(0, '517.657')]
[2023-07-15 19:02:03,562][33581] Updated weights for policy 0, policy_version 19200 (0.0005)
[2023-07-15 19:02:05,752][33296] Fps is (10 sec: 6963.2, 60 sec: 7099.7, 300 sec: 7150.6). Total num frames: 9842688. Throughput: 0: 7146.9. Samples: 9834688. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 19:02:05,753][33296] Avg episode reward: [(0, '509.493')]
[2023-07-15 19:02:09,139][33581] Updated weights for policy 0, policy_version 19280 (0.0005)
[2023-07-15 19:02:10,752][33296] Fps is (10 sec: 7372.8, 60 sec: 7099.7, 300 sec: 7150.6). Total num frames: 9879552. Throughput: 0: 7179.7. Samples: 9879352. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 19:02:10,753][33296] Avg episode reward: [(0, '496.289')]
[2023-07-15 19:02:10,755][33537] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000019296_9879552.pth...
[2023-07-15 19:02:10,758][33537] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000018880_9666560.pth
[2023-07-15 19:02:15,095][33581] Updated weights for policy 0, policy_version 19360 (0.0005)
[2023-07-15 19:02:15,752][33296] Fps is (10 sec: 7372.8, 60 sec: 7168.0, 300 sec: 7150.6). Total num frames: 9916416. Throughput: 0: 7137.0. Samples: 9900028. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 19:02:15,753][33296] Avg episode reward: [(0, '516.537')]
[2023-07-15 19:02:20,752][33296] Fps is (10 sec: 6963.3, 60 sec: 7099.7, 300 sec: 7136.8). Total num frames: 9949184. Throughput: 0: 7098.6. Samples: 9941064. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 19:02:20,752][33296] Avg episode reward: [(0, '510.314')]
[2023-07-15 19:02:20,912][33581] Updated weights for policy 0, policy_version 19440 (0.0005)
[2023-07-15 19:02:25,752][33296] Fps is (10 sec: 6963.2, 60 sec: 7099.7, 300 sec: 7150.6). Total num frames: 9986048. Throughput: 0: 7175.9. Samples: 9985544. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0)
[2023-07-15 19:02:25,753][33296] Avg episode reward: [(0, '495.510')]
[2023-07-15 19:02:25,756][33537] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000019504_9986048.pth...
[2023-07-15 19:02:25,758][33537] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000019088_9773056.pth
[2023-07-15 19:02:26,634][33581] Updated weights for policy 0, policy_version 19520 (0.0005)
[2023-07-15 19:02:28,428][33537] Early stopping after 2 epochs (8 sgd steps), loss delta 0.0000000
[2023-07-15 19:02:28,429][33587] Stopping RolloutWorker_w5...
[2023-07-15 19:02:28,429][33585] Stopping RolloutWorker_w2...
[2023-07-15 19:02:28,429][33586] Stopping RolloutWorker_w4...
[2023-07-15 19:02:28,429][33583] Stopping RolloutWorker_w0...
[2023-07-15 19:02:28,429][33584] Stopping RolloutWorker_w3...
[2023-07-15 19:02:28,429][33582] Stopping RolloutWorker_w1...
[2023-07-15 19:02:28,429][33619] Stopping RolloutWorker_w6...
[2023-07-15 19:02:28,429][33587] Loop rollout_proc5_evt_loop terminating...
[2023-07-15 19:02:28,429][33585] Loop rollout_proc2_evt_loop terminating...
[2023-07-15 19:02:28,429][33537] Stopping Batcher_0...
[2023-07-15 19:02:28,429][33586] Loop rollout_proc4_evt_loop terminating...
[2023-07-15 19:02:28,429][33583] Loop rollout_proc0_evt_loop terminating...
[2023-07-15 19:02:28,429][33584] Loop rollout_proc3_evt_loop terminating...
[2023-07-15 19:02:28,429][33682] Stopping RolloutWorker_w7...
[2023-07-15 19:02:28,429][33296] Component RolloutWorker_w5 stopped!
[2023-07-15 19:02:28,429][33582] Loop rollout_proc1_evt_loop terminating...
[2023-07-15 19:02:28,429][33619] Loop rollout_proc6_evt_loop terminating...
[2023-07-15 19:02:28,429][33537] Loop batcher_evt_loop terminating...
[2023-07-15 19:02:28,430][33682] Loop rollout_proc7_evt_loop terminating...
[2023-07-15 19:02:28,430][33296] Component RolloutWorker_w2 stopped!
[2023-07-15 19:02:28,430][33537] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000019544_10006528.pth...
[2023-07-15 19:02:28,430][33296] Component RolloutWorker_w4 stopped!
[2023-07-15 19:02:28,430][33296] Component RolloutWorker_w3 stopped!
[2023-07-15 19:02:28,430][33296] Component RolloutWorker_w0 stopped!
[2023-07-15 19:02:28,431][33296] Component RolloutWorker_w1 stopped!
[2023-07-15 19:02:28,431][33296] Component RolloutWorker_w6 stopped!
[2023-07-15 19:02:28,431][33296] Component Batcher_0 stopped!
[2023-07-15 19:02:28,431][33537] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000019296_9879552.pth
[2023-07-15 19:02:28,431][33296] Component RolloutWorker_w7 stopped!
[2023-07-15 19:02:28,432][33537] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/box-close-v2/checkpoint_p0/checkpoint_000019544_10006528.pth...
[2023-07-15 19:02:28,433][33537] Stopping LearnerWorker_p0...
[2023-07-15 19:02:28,434][33537] Loop learner_proc0_evt_loop terminating...
[2023-07-15 19:02:28,434][33296] Component LearnerWorker_p0 stopped!
[2023-07-15 19:02:28,484][33581] Weights refcount: 2 0
[2023-07-15 19:02:28,485][33581] Stopping InferenceWorker_p0-w0...
[2023-07-15 19:02:28,485][33581] Loop inference_proc0-0_evt_loop terminating...
[2023-07-15 19:02:28,486][33296] Component InferenceWorker_p0-w0 stopped!
[2023-07-15 19:02:28,486][33296] Waiting for process learner_proc0 to stop...
[2023-07-15 19:02:29,123][33296] Waiting for process inference_proc0-0 to join...
[2023-07-15 19:02:29,130][33296] Waiting for process rollout_proc0 to join...
[2023-07-15 19:02:29,130][33296] Waiting for process rollout_proc1 to join...
[2023-07-15 19:02:29,130][33296] Waiting for process rollout_proc2 to join...
[2023-07-15 19:02:29,131][33296] Waiting for process rollout_proc3 to join...
[2023-07-15 19:02:29,131][33296] Waiting for process rollout_proc4 to join...
[2023-07-15 19:02:29,131][33296] Waiting for process rollout_proc5 to join...
[2023-07-15 19:02:29,131][33296] Waiting for process rollout_proc6 to join...
[2023-07-15 19:02:29,131][33296] Waiting for process rollout_proc7 to join...
[2023-07-15 19:02:29,131][33296] Batcher 0 profile tree view:
batching: 1.8535, releasing_batches: 1.5090
[2023-07-15 19:02:29,132][33296] InferenceWorker_p0-w0 profile tree view:
wait_policy: 0.0051
wait_policy_total: 608.5213
update_model: 15.8583
weight_update: 0.0005
one_step: 0.0006
handle_policy_step: 694.9594
deserialize: 28.2983, stack: 7.4643, obs_to_device_normalize: 126.7109, forward: 346.9954, send_messages: 47.1111
prepare_outputs: 77.5403
to_cpu: 12.0365
[2023-07-15 19:02:29,132][33296] Learner 0 profile tree view:
misc: 0.0094, prepare_batch: 8.2258
train: 85.0180
epoch_init: 0.0356, minibatch_init: 1.2234, losses_postprocess: 1.2742, kl_divergence: 0.4004, after_optimizer: 0.6673
calculate_losses: 35.8321
losses_init: 0.0307, forward_head: 13.5513, bptt_initial: 0.1277, bptt: 0.1220, tail: 10.5113, advantages_returns: 0.8090, losses: 9.4074
update: 44.1418
clip: 5.3461
[2023-07-15 19:02:29,132][33296] RolloutWorker_w0 profile tree view:
wait_for_trajectories: 0.4707, enqueue_policy_requests: 16.4362, env_step: 960.6958, overhead: 22.5872, complete_rollouts: 0.3934
save_policy_outputs: 44.6283
split_output_tensors: 15.1432
[2023-07-15 19:02:29,132][33296] RolloutWorker_w7 profile tree view:
wait_for_trajectories: 0.4282, enqueue_policy_requests: 16.1294, env_step: 930.7935, overhead: 21.9429, complete_rollouts: 0.3898
save_policy_outputs: 42.5839
split_output_tensors: 14.4256
[2023-07-15 19:02:29,132][33296] Loop Runner_EvtLoop terminating...
[2023-07-15 19:02:29,132][33296] Runner profile tree view:
main_loop: 1410.8337
[2023-07-15 19:02:29,133][33296] Collected {0: 10006528}, FPS: 7092.6