diff --git "a/sf_log.txt" "b/sf_log.txt" --- "a/sf_log.txt" +++ "b/sf_log.txt" @@ -1,33 +1,33 @@ -[2023-07-08 20:40:18,725][1071413] Saving configuration to /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/config.json... -[2023-07-08 20:40:18,747][1071413] Rollout worker 0 uses device cpu -[2023-07-08 20:40:18,748][1071413] Rollout worker 1 uses device cpu -[2023-07-08 20:40:18,748][1071413] Rollout worker 2 uses device cpu -[2023-07-08 20:40:18,748][1071413] Rollout worker 3 uses device cpu -[2023-07-08 20:40:18,748][1071413] Rollout worker 4 uses device cpu -[2023-07-08 20:40:18,748][1071413] Rollout worker 5 uses device cpu -[2023-07-08 20:40:18,748][1071413] Rollout worker 6 uses device cpu -[2023-07-08 20:40:18,749][1071413] Rollout worker 7 uses device cpu -[2023-07-08 20:40:18,749][1071413] In synchronous mode, we only accumulate one batch. Setting num_batches_to_accumulate to 1 -[2023-07-08 20:40:18,761][1071413] InferenceWorker_p0-w0: min num requests: 2 -[2023-07-08 20:40:18,781][1071413] Starting all processes... -[2023-07-08 20:40:18,782][1071413] Starting process learner_proc0 -[2023-07-08 20:40:18,830][1071413] Starting all processes... -[2023-07-08 20:40:18,873][1071413] Starting process inference_proc0-0 -[2023-07-08 20:40:18,873][1071413] Starting process rollout_proc0 -[2023-07-08 20:40:18,873][1071413] Starting process rollout_proc1 -[2023-07-08 20:40:18,873][1071413] Starting process rollout_proc2 -[2023-07-08 20:40:18,873][1071413] Starting process rollout_proc3 -[2023-07-08 20:40:18,873][1071413] Starting process rollout_proc4 -[2023-07-08 20:40:18,873][1071413] Starting process rollout_proc5 -[2023-07-08 20:40:18,873][1071413] Starting process rollout_proc6 -[2023-07-08 20:40:18,873][1071413] Starting process rollout_proc7 -[2023-07-08 20:40:21,010][1071702] Worker 3 uses CPU cores [12, 13, 14, 15] -[2023-07-08 20:40:21,014][1071654] Starting seed is not provided -[2023-07-08 20:40:21,015][1071654] Initializing actor-critic model on device cpu -[2023-07-08 20:40:21,015][1071654] RunningMeanStd input shape: (39,) -[2023-07-08 20:40:21,015][1071654] RunningMeanStd input shape: (1,) -[2023-07-08 20:40:21,079][1071654] Created Actor Critic model with architecture: -[2023-07-08 20:40:21,079][1071654] ActorCriticSharedWeights( +[2023-07-17 00:58:48,065][282552] Saving configuration to /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/config.json... +[2023-07-17 00:58:48,081][282552] Rollout worker 0 uses device cpu +[2023-07-17 00:58:48,082][282552] Rollout worker 1 uses device cpu +[2023-07-17 00:58:48,082][282552] Rollout worker 2 uses device cpu +[2023-07-17 00:58:48,082][282552] Rollout worker 3 uses device cpu +[2023-07-17 00:58:48,082][282552] Rollout worker 4 uses device cpu +[2023-07-17 00:58:48,082][282552] Rollout worker 5 uses device cpu +[2023-07-17 00:58:48,082][282552] Rollout worker 6 uses device cpu +[2023-07-17 00:58:48,083][282552] Rollout worker 7 uses device cpu +[2023-07-17 00:58:48,083][282552] In synchronous mode, we only accumulate one batch. Setting num_batches_to_accumulate to 1 +[2023-07-17 00:58:48,093][282552] InferenceWorker_p0-w0: min num requests: 2 +[2023-07-17 00:58:48,111][282552] Starting all processes... +[2023-07-17 00:58:48,111][282552] Starting process learner_proc0 +[2023-07-17 00:58:48,160][282552] Starting all processes... +[2023-07-17 00:58:48,203][282552] Starting process inference_proc0-0 +[2023-07-17 00:58:48,213][282552] Starting process rollout_proc0 +[2023-07-17 00:58:48,213][282552] Starting process rollout_proc1 +[2023-07-17 00:58:48,214][282552] Starting process rollout_proc2 +[2023-07-17 00:58:48,214][282552] Starting process rollout_proc3 +[2023-07-17 00:58:48,214][282552] Starting process rollout_proc4 +[2023-07-17 00:58:48,214][282552] Starting process rollout_proc5 +[2023-07-17 00:58:48,214][282552] Starting process rollout_proc6 +[2023-07-17 00:58:48,214][282552] Starting process rollout_proc7 +[2023-07-17 00:58:49,981][282793] Starting seed is not provided +[2023-07-17 00:58:49,981][282793] Initializing actor-critic model on device cpu +[2023-07-17 00:58:49,981][282793] RunningMeanStd input shape: (39,) +[2023-07-17 00:58:49,981][282793] RunningMeanStd input shape: (1,) +[2023-07-17 00:58:49,997][282838] Worker 1 uses CPU cores [4, 5, 6, 7] +[2023-07-17 00:58:50,041][282793] Created Actor Critic model with architecture: +[2023-07-17 00:58:50,041][282793] ActorCriticSharedWeights( (obs_normalizer): ObservationNormalizer( (running_mean_std): RunningMeanStdDictInPlace( (running_mean_std): ModuleDict( @@ -58,1027 +58,872 @@ (distribution_linear): Linear(in_features=64, out_features=4, bias=True) ) ) -[2023-07-08 20:40:21,161][1071798] Worker 6 uses CPU cores [24, 25, 26, 27] -[2023-07-08 20:40:21,233][1071699] Worker 1 uses CPU cores [4, 5, 6, 7] -[2023-07-08 20:40:21,329][1071701] Worker 2 uses CPU cores [8, 9, 10, 11] -[2023-07-08 20:40:21,379][1071654] Using optimizer -[2023-07-08 20:40:21,380][1071654] No checkpoints found -[2023-07-08 20:40:21,380][1071654] Did not load from checkpoint, starting from scratch! -[2023-07-08 20:40:21,380][1071654] Initialized policy 0 weights for model version 0 -[2023-07-08 20:40:21,381][1071654] LearnerWorker_p0 finished initialization! -[2023-07-08 20:40:21,382][1071698] RunningMeanStd input shape: (39,) -[2023-07-08 20:40:21,383][1071698] RunningMeanStd input shape: (1,) -[2023-07-08 20:40:21,441][1071413] Inference worker 0-0 is ready! -[2023-07-08 20:40:21,442][1071413] All inference workers are ready! Signal rollout workers to start! -[2023-07-08 20:40:21,469][1071700] Worker 0 uses CPU cores [0, 1, 2, 3] -[2023-07-08 20:40:21,530][1071830] Worker 7 uses CPU cores [28, 29, 30, 31] -[2023-07-08 20:40:21,635][1071766] Worker 5 uses CPU cores [20, 21, 22, 23] -[2023-07-08 20:40:21,681][1071734] Worker 4 uses CPU cores [16, 17, 18, 19] -[2023-07-08 20:40:25,475][1071702] Decorrelating experience for 0 frames... -[2023-07-08 20:40:25,488][1071702] Decorrelating experience for 64 frames... -[2023-07-08 20:40:25,522][1071702] Decorrelating experience for 128 frames... -[2023-07-08 20:40:25,585][1071701] Decorrelating experience for 0 frames... -[2023-07-08 20:40:25,592][1071702] Decorrelating experience for 192 frames... -[2023-07-08 20:40:25,598][1071701] Decorrelating experience for 64 frames... -[2023-07-08 20:40:25,620][1071798] Decorrelating experience for 0 frames... -[2023-07-08 20:40:25,633][1071701] Decorrelating experience for 128 frames... -[2023-07-08 20:40:25,634][1071798] Decorrelating experience for 64 frames... -[2023-07-08 20:40:25,669][1071798] Decorrelating experience for 128 frames... -[2023-07-08 20:40:25,679][1071830] Decorrelating experience for 0 frames... -[2023-07-08 20:40:25,692][1071830] Decorrelating experience for 64 frames... -[2023-07-08 20:40:25,697][1071700] Decorrelating experience for 0 frames... -[2023-07-08 20:40:25,703][1071701] Decorrelating experience for 192 frames... -[2023-07-08 20:40:25,711][1071700] Decorrelating experience for 64 frames... -[2023-07-08 20:40:25,728][1071830] Decorrelating experience for 128 frames... -[2023-07-08 20:40:25,740][1071798] Decorrelating experience for 192 frames... -[2023-07-08 20:40:25,746][1071700] Decorrelating experience for 128 frames... -[2023-07-08 20:40:25,787][1071766] Decorrelating experience for 0 frames... -[2023-07-08 20:40:25,798][1071830] Decorrelating experience for 192 frames... -[2023-07-08 20:40:25,801][1071766] Decorrelating experience for 64 frames... -[2023-07-08 20:40:25,816][1071700] Decorrelating experience for 192 frames... -[2023-07-08 20:40:25,829][1071734] Decorrelating experience for 0 frames... -[2023-07-08 20:40:25,836][1071766] Decorrelating experience for 128 frames... -[2023-07-08 20:40:25,843][1071734] Decorrelating experience for 64 frames... -[2023-07-08 20:40:25,878][1071734] Decorrelating experience for 128 frames... -[2023-07-08 20:40:25,908][1071766] Decorrelating experience for 192 frames... -[2023-07-08 20:40:25,923][1071413] Fps is (10 sec: nan, 60 sec: nan, 300 sec: nan). Total num frames: 0. Throughput: 0: nan. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) -[2023-07-08 20:40:25,949][1071734] Decorrelating experience for 192 frames... -[2023-07-08 20:40:26,686][1071699] Decorrelating experience for 0 frames... -[2023-07-08 20:40:26,699][1071699] Decorrelating experience for 64 frames... -[2023-07-08 20:40:26,736][1071699] Decorrelating experience for 128 frames... -[2023-07-08 20:40:26,814][1071699] Decorrelating experience for 192 frames... -[2023-07-08 20:40:29,622][1071702] Decorrelating experience for 256 frames... -[2023-07-08 20:40:29,730][1071701] Decorrelating experience for 256 frames... -[2023-07-08 20:40:29,745][1071702] Decorrelating experience for 320 frames... -[2023-07-08 20:40:29,809][1071798] Decorrelating experience for 256 frames... -[2023-07-08 20:40:29,811][1071830] Decorrelating experience for 256 frames... -[2023-07-08 20:40:29,857][1071701] Decorrelating experience for 320 frames... -[2023-07-08 20:40:29,874][1071700] Decorrelating experience for 256 frames... -[2023-07-08 20:40:29,903][1071702] Decorrelating experience for 384 frames... -[2023-07-08 20:40:29,933][1071798] Decorrelating experience for 320 frames... -[2023-07-08 20:40:29,935][1071830] Decorrelating experience for 320 frames... -[2023-07-08 20:40:29,963][1071766] Decorrelating experience for 256 frames... -[2023-07-08 20:40:29,985][1071734] Decorrelating experience for 256 frames... -[2023-07-08 20:40:29,998][1071700] Decorrelating experience for 320 frames... -[2023-07-08 20:40:30,019][1071701] Decorrelating experience for 384 frames... -[2023-07-08 20:40:30,081][1071702] Decorrelating experience for 448 frames... -[2023-07-08 20:40:30,090][1071766] Decorrelating experience for 320 frames... -[2023-07-08 20:40:30,092][1071798] Decorrelating experience for 384 frames... -[2023-07-08 20:40:30,094][1071830] Decorrelating experience for 384 frames... -[2023-07-08 20:40:30,110][1071734] Decorrelating experience for 320 frames... -[2023-07-08 20:40:30,158][1071700] Decorrelating experience for 384 frames... -[2023-07-08 20:40:30,196][1071701] Decorrelating experience for 448 frames... -[2023-07-08 20:40:30,255][1071766] Decorrelating experience for 384 frames... -[2023-07-08 20:40:30,272][1071734] Decorrelating experience for 384 frames... -[2023-07-08 20:40:30,274][1071830] Decorrelating experience for 448 frames... -[2023-07-08 20:40:30,275][1071798] Decorrelating experience for 448 frames... -[2023-07-08 20:40:30,341][1071700] Decorrelating experience for 448 frames... -[2023-07-08 20:40:30,437][1071766] Decorrelating experience for 448 frames... -[2023-07-08 20:40:30,451][1071734] Decorrelating experience for 448 frames... -[2023-07-08 20:40:30,922][1071413] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 51.2. Samples: 256. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) -[2023-07-08 20:40:30,923][1071413] Avg episode reward: [(0, '1.879')] -[2023-07-08 20:40:30,925][1071654] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000000000_0.pth... -[2023-07-08 20:40:31,666][1071699] Decorrelating experience for 256 frames... -[2023-07-08 20:40:31,789][1071699] Decorrelating experience for 320 frames... -[2023-07-08 20:40:31,943][1071699] Decorrelating experience for 384 frames... -[2023-07-08 20:40:32,118][1071699] Decorrelating experience for 448 frames... -[2023-07-08 20:40:35,922][1071413] Fps is (10 sec: 2867.2, 60 sec: 2867.2, 300 sec: 2867.2). Total num frames: 28672. Throughput: 0: 826.4. Samples: 8264. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-07-08 20:40:35,923][1071413] Avg episode reward: [(0, '34.584')] -[2023-07-08 20:40:36,920][1071698] Updated weights for policy 0, policy_version 80 (0.0005) -[2023-07-08 20:40:38,756][1071413] Heartbeat connected on Batcher_0 -[2023-07-08 20:40:38,759][1071413] Heartbeat connected on LearnerWorker_p0 -[2023-07-08 20:40:38,765][1071413] Heartbeat connected on RolloutWorker_w0 -[2023-07-08 20:40:38,766][1071413] Heartbeat connected on InferenceWorker_p0-w0 -[2023-07-08 20:40:38,769][1071413] Heartbeat connected on RolloutWorker_w2 -[2023-07-08 20:40:38,772][1071413] Heartbeat connected on RolloutWorker_w1 -[2023-07-08 20:40:38,773][1071413] Heartbeat connected on RolloutWorker_w3 -[2023-07-08 20:40:38,774][1071413] Heartbeat connected on RolloutWorker_w4 -[2023-07-08 20:40:38,776][1071413] Heartbeat connected on RolloutWorker_w5 -[2023-07-08 20:40:38,778][1071413] Heartbeat connected on RolloutWorker_w6 -[2023-07-08 20:40:38,780][1071413] Heartbeat connected on RolloutWorker_w7 -[2023-07-08 20:40:40,923][1071413] Fps is (10 sec: 7372.8, 60 sec: 4915.2, 300 sec: 4915.2). Total num frames: 73728. Throughput: 0: 4239.7. Samples: 63596. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 20:40:40,923][1071413] Avg episode reward: [(0, '149.962')] -[2023-07-08 20:40:41,432][1071698] Updated weights for policy 0, policy_version 160 (0.0005) -[2023-07-08 20:40:45,522][1071698] Updated weights for policy 0, policy_version 240 (0.0005) -[2023-07-08 20:40:45,923][1071413] Fps is (10 sec: 9830.3, 60 sec: 6348.8, 300 sec: 6348.8). Total num frames: 126976. Throughput: 0: 6142.6. Samples: 122852. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-07-08 20:40:45,923][1071413] Avg episode reward: [(0, '313.210')] -[2023-07-08 20:40:45,926][1071654] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000000248_126976.pth... -[2023-07-08 20:40:45,928][1071654] Saving new best policy, reward=313.210! -[2023-07-08 20:40:49,886][1071698] Updated weights for policy 0, policy_version 320 (0.0005) -[2023-07-08 20:40:50,922][1071413] Fps is (10 sec: 9830.5, 60 sec: 6881.3, 300 sec: 6881.3). Total num frames: 172032. Throughput: 0: 6049.3. Samples: 151232. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-07-08 20:40:50,923][1071413] Avg episode reward: [(0, '326.978')] -[2023-07-08 20:40:50,924][1071654] Saving new best policy, reward=326.978! -[2023-07-08 20:40:54,136][1071698] Updated weights for policy 0, policy_version 400 (0.0005) -[2023-07-08 20:40:55,922][1071413] Fps is (10 sec: 9420.9, 60 sec: 7372.8, 300 sec: 7372.8). Total num frames: 221184. Throughput: 0: 6962.9. Samples: 208888. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-07-08 20:40:55,923][1071413] Avg episode reward: [(0, '330.591')] -[2023-07-08 20:40:55,923][1071654] Saving new best policy, reward=330.591! -[2023-07-08 20:40:58,208][1071698] Updated weights for policy 0, policy_version 480 (0.0005) -[2023-07-08 20:41:00,922][1071413] Fps is (10 sec: 9830.4, 60 sec: 7723.9, 300 sec: 7723.9). Total num frames: 270336. Throughput: 0: 7646.9. Samples: 267640. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 20:41:00,923][1071413] Avg episode reward: [(0, '334.018')] -[2023-07-08 20:41:00,925][1071654] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000000528_270336.pth... -[2023-07-08 20:41:00,927][1071654] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000000000_0.pth -[2023-07-08 20:41:00,927][1071654] Saving new best policy, reward=334.018! -[2023-07-08 20:41:02,656][1071698] Updated weights for policy 0, policy_version 560 (0.0005) -[2023-07-08 20:41:05,922][1071413] Fps is (10 sec: 9420.8, 60 sec: 7884.8, 300 sec: 7884.8). Total num frames: 315392. Throughput: 0: 7373.1. Samples: 294924. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 20:41:05,923][1071413] Avg episode reward: [(0, '333.732')] -[2023-07-08 20:41:06,798][1071698] Updated weights for policy 0, policy_version 640 (0.0005) -[2023-07-08 20:41:10,722][1071698] Updated weights for policy 0, policy_version 720 (0.0005) -[2023-07-08 20:41:10,922][1071413] Fps is (10 sec: 9830.4, 60 sec: 8192.0, 300 sec: 8192.0). Total num frames: 368640. Throughput: 0: 7906.5. Samples: 355792. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-07-08 20:41:10,923][1071413] Avg episode reward: [(0, '343.019')] -[2023-07-08 20:41:10,924][1071654] Saving new best policy, reward=343.019! -[2023-07-08 20:41:14,810][1071698] Updated weights for policy 0, policy_version 800 (0.0005) -[2023-07-08 20:41:15,923][1071413] Fps is (10 sec: 10239.9, 60 sec: 8355.8, 300 sec: 8355.8). Total num frames: 417792. Throughput: 0: 9266.0. Samples: 417228. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 20:41:15,923][1071413] Avg episode reward: [(0, '348.950')] -[2023-07-08 20:41:15,927][1071654] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000000816_417792.pth... -[2023-07-08 20:41:15,928][1071654] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000000248_126976.pth -[2023-07-08 20:41:15,929][1071654] Saving new best policy, reward=348.950! -[2023-07-08 20:41:19,067][1071698] Updated weights for policy 0, policy_version 880 (0.0005) -[2023-07-08 20:41:20,923][1071413] Fps is (10 sec: 9830.4, 60 sec: 8489.9, 300 sec: 8489.9). Total num frames: 466944. Throughput: 0: 9730.2. Samples: 446124. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 20:41:20,923][1071413] Avg episode reward: [(0, '346.200')] -[2023-07-08 20:41:23,312][1071698] Updated weights for policy 0, policy_version 960 (0.0005) -[2023-07-08 20:41:25,922][1071413] Fps is (10 sec: 9830.6, 60 sec: 8601.6, 300 sec: 8601.6). Total num frames: 516096. Throughput: 0: 9759.7. Samples: 502780. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 20:41:25,923][1071413] Avg episode reward: [(0, '348.566')] -[2023-07-08 20:41:27,616][1071698] Updated weights for policy 0, policy_version 1040 (0.0005) -[2023-07-08 20:41:30,922][1071413] Fps is (10 sec: 9830.5, 60 sec: 9420.8, 300 sec: 8696.1). Total num frames: 565248. Throughput: 0: 9730.6. Samples: 560728. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 20:41:30,923][1071413] Avg episode reward: [(0, '375.508')] -[2023-07-08 20:41:30,926][1071654] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000001104_565248.pth... -[2023-07-08 20:41:30,928][1071654] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000000528_270336.pth -[2023-07-08 20:41:30,929][1071654] Saving new best policy, reward=375.508! -[2023-07-08 20:41:31,657][1071698] Updated weights for policy 0, policy_version 1120 (0.0005) -[2023-07-08 20:41:35,923][1071413] Fps is (10 sec: 9420.7, 60 sec: 9693.8, 300 sec: 8718.6). Total num frames: 610304. Throughput: 0: 9746.7. Samples: 589832. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 20:41:35,923][1071413] Avg episode reward: [(0, '354.903')] -[2023-07-08 20:41:35,996][1071698] Updated weights for policy 0, policy_version 1200 (0.0005) -[2023-07-08 20:41:40,280][1071698] Updated weights for policy 0, policy_version 1280 (0.0005) -[2023-07-08 20:41:40,923][1071413] Fps is (10 sec: 9420.7, 60 sec: 9762.1, 300 sec: 8792.7). Total num frames: 659456. Throughput: 0: 9742.1. Samples: 647284. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) -[2023-07-08 20:41:40,940][1071413] Avg episode reward: [(0, '408.196')] -[2023-07-08 20:41:40,941][1071654] Saving new best policy, reward=408.196! -[2023-07-08 20:41:44,712][1071698] Updated weights for policy 0, policy_version 1360 (0.0005) -[2023-07-08 20:41:45,923][1071413] Fps is (10 sec: 9830.4, 60 sec: 9693.9, 300 sec: 8857.6). Total num frames: 708608. Throughput: 0: 9708.4. Samples: 704520. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 20:41:45,924][1071413] Avg episode reward: [(0, '392.415')] -[2023-07-08 20:41:45,927][1071654] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000001384_708608.pth... -[2023-07-08 20:41:45,929][1071654] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000000816_417792.pth -[2023-07-08 20:41:48,583][1071698] Updated weights for policy 0, policy_version 1440 (0.0004) -[2023-07-08 20:41:50,922][1071413] Fps is (10 sec: 9830.4, 60 sec: 9762.1, 300 sec: 8914.8). Total num frames: 757760. Throughput: 0: 9828.4. Samples: 737204. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 20:41:50,923][1071413] Avg episode reward: [(0, '441.713')] -[2023-07-08 20:41:50,929][1071654] Saving new best policy, reward=441.713! -[2023-07-08 20:41:52,804][1071698] Updated weights for policy 0, policy_version 1520 (0.0005) -[2023-07-08 20:41:55,922][1071413] Fps is (10 sec: 9830.5, 60 sec: 9762.1, 300 sec: 8965.7). Total num frames: 806912. Throughput: 0: 9748.5. Samples: 794472. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 20:41:55,923][1071413] Avg episode reward: [(0, '450.162')] -[2023-07-08 20:41:55,923][1071654] Saving new best policy, reward=450.162! -[2023-07-08 20:41:56,774][1071698] Updated weights for policy 0, policy_version 1600 (0.0005) -[2023-07-08 20:42:00,923][1071413] Fps is (10 sec: 9830.4, 60 sec: 9762.1, 300 sec: 9011.2). Total num frames: 856064. Throughput: 0: 9668.6. Samples: 852316. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 20:42:00,923][1071413] Avg episode reward: [(0, '479.638')] -[2023-07-08 20:42:00,925][1071654] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000001672_856064.pth... -[2023-07-08 20:42:00,928][1071654] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000001104_565248.pth -[2023-07-08 20:42:00,928][1071654] Saving new best policy, reward=479.638! -[2023-07-08 20:42:01,300][1071698] Updated weights for policy 0, policy_version 1680 (0.0005) -[2023-07-08 20:42:05,585][1071698] Updated weights for policy 0, policy_version 1760 (0.0005) -[2023-07-08 20:42:05,922][1071413] Fps is (10 sec: 9420.9, 60 sec: 9762.1, 300 sec: 9011.2). Total num frames: 901120. Throughput: 0: 9674.9. Samples: 881492. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 20:42:05,923][1071413] Avg episode reward: [(0, '443.416')] -[2023-07-08 20:42:10,053][1071698] Updated weights for policy 0, policy_version 1840 (0.0005) -[2023-07-08 20:42:10,922][1071413] Fps is (10 sec: 9011.2, 60 sec: 9625.6, 300 sec: 9011.2). Total num frames: 946176. Throughput: 0: 9665.1. Samples: 937708. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 20:42:10,923][1071413] Avg episode reward: [(0, '455.213')] -[2023-07-08 20:42:14,552][1071698] Updated weights for policy 0, policy_version 1920 (0.0005) -[2023-07-08 20:42:15,922][1071413] Fps is (10 sec: 9420.7, 60 sec: 9625.6, 300 sec: 9048.4). Total num frames: 995328. Throughput: 0: 9590.8. Samples: 992312. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) -[2023-07-08 20:42:15,923][1071413] Avg episode reward: [(0, '540.957')] -[2023-07-08 20:42:15,925][1071654] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000001944_995328.pth... -[2023-07-08 20:42:15,928][1071654] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000001384_708608.pth -[2023-07-08 20:42:15,928][1071654] Saving new best policy, reward=540.957! -[2023-07-08 20:42:18,846][1071698] Updated weights for policy 0, policy_version 2000 (0.0005) -[2023-07-08 20:42:20,922][1071413] Fps is (10 sec: 9420.8, 60 sec: 9557.3, 300 sec: 9046.8). Total num frames: 1040384. Throughput: 0: 9558.8. Samples: 1019976. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-07-08 20:42:20,923][1071413] Avg episode reward: [(0, '575.284')] -[2023-07-08 20:42:20,923][1071654] Saving new best policy, reward=574.775! -[2023-07-08 20:42:23,452][1071698] Updated weights for policy 0, policy_version 2080 (0.0005) -[2023-07-08 20:42:25,923][1071413] Fps is (10 sec: 9011.1, 60 sec: 9489.0, 300 sec: 9045.3). Total num frames: 1085440. Throughput: 0: 9477.3. Samples: 1073764. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 20:42:25,923][1071413] Avg episode reward: [(0, '575.681')] -[2023-07-08 20:42:25,924][1071654] Saving new best policy, reward=575.681! -[2023-07-08 20:42:28,003][1071698] Updated weights for policy 0, policy_version 2160 (0.0005) -[2023-07-08 20:42:30,923][1071413] Fps is (10 sec: 9420.7, 60 sec: 9489.1, 300 sec: 9076.7). Total num frames: 1134592. Throughput: 0: 9557.2. Samples: 1134592. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-07-08 20:42:30,923][1071413] Avg episode reward: [(0, '563.036')] -[2023-07-08 20:42:30,951][1071654] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000002224_1138688.pth... -[2023-07-08 20:42:30,953][1071654] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000001672_856064.pth -[2023-07-08 20:42:31,925][1071698] Updated weights for policy 0, policy_version 2240 (0.0005) -[2023-07-08 20:42:35,922][1071413] Fps is (10 sec: 9830.5, 60 sec: 9557.3, 300 sec: 9105.7). Total num frames: 1183744. Throughput: 0: 9428.1. Samples: 1161468. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 20:42:35,924][1071413] Avg episode reward: [(0, '610.237')] -[2023-07-08 20:42:35,924][1071654] Saving new best policy, reward=610.237! -[2023-07-08 20:42:36,327][1071698] Updated weights for policy 0, policy_version 2320 (0.0005) -[2023-07-08 20:42:40,709][1071698] Updated weights for policy 0, policy_version 2400 (0.0005) -[2023-07-08 20:42:40,922][1071413] Fps is (10 sec: 9420.9, 60 sec: 9489.1, 300 sec: 9102.2). Total num frames: 1228800. Throughput: 0: 9378.7. Samples: 1216512. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-07-08 20:42:40,924][1071413] Avg episode reward: [(0, '613.817')] -[2023-07-08 20:42:40,924][1071654] Saving new best policy, reward=613.817! -[2023-07-08 20:42:45,221][1071698] Updated weights for policy 0, policy_version 2480 (0.0005) -[2023-07-08 20:42:45,923][1071413] Fps is (10 sec: 9011.1, 60 sec: 9420.8, 300 sec: 9099.0). Total num frames: 1273856. Throughput: 0: 9334.9. Samples: 1272388. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) -[2023-07-08 20:42:45,925][1071413] Avg episode reward: [(0, '641.176')] -[2023-07-08 20:42:45,928][1071654] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000002488_1273856.pth... -[2023-07-08 20:42:45,931][1071654] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000001944_995328.pth -[2023-07-08 20:42:45,931][1071654] Saving new best policy, reward=641.176! -[2023-07-08 20:42:49,469][1071698] Updated weights for policy 0, policy_version 2560 (0.0005) -[2023-07-08 20:42:50,923][1071413] Fps is (10 sec: 9420.7, 60 sec: 9420.8, 300 sec: 9124.2). Total num frames: 1323008. Throughput: 0: 9351.1. Samples: 1302292. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) -[2023-07-08 20:42:50,924][1071413] Avg episode reward: [(0, '625.696')] -[2023-07-08 20:42:53,758][1071698] Updated weights for policy 0, policy_version 2640 (0.0005) -[2023-07-08 20:42:55,922][1071413] Fps is (10 sec: 9420.9, 60 sec: 9352.5, 300 sec: 9120.4). Total num frames: 1368064. Throughput: 0: 9371.3. Samples: 1359416. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 20:42:55,924][1071413] Avg episode reward: [(0, '600.964')] -[2023-07-08 20:42:58,223][1071698] Updated weights for policy 0, policy_version 2720 (0.0005) -[2023-07-08 20:43:00,923][1071413] Fps is (10 sec: 9420.8, 60 sec: 9352.5, 300 sec: 9143.3). Total num frames: 1417216. Throughput: 0: 9358.4. Samples: 1413440. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 20:43:00,924][1071413] Avg episode reward: [(0, '609.179')] -[2023-07-08 20:43:00,927][1071654] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000002768_1417216.pth... -[2023-07-08 20:43:00,930][1071654] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000002224_1138688.pth -[2023-07-08 20:43:02,600][1071698] Updated weights for policy 0, policy_version 2800 (0.0005) -[2023-07-08 20:43:05,922][1071413] Fps is (10 sec: 9830.4, 60 sec: 9420.8, 300 sec: 9164.8). Total num frames: 1466368. Throughput: 0: 9385.9. Samples: 1442340. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) -[2023-07-08 20:43:05,923][1071413] Avg episode reward: [(0, '662.263')] -[2023-07-08 20:43:05,923][1071654] Saving new best policy, reward=662.263! -[2023-07-08 20:43:06,792][1071698] Updated weights for policy 0, policy_version 2880 (0.0005) -[2023-07-08 20:43:10,922][1071413] Fps is (10 sec: 9420.8, 60 sec: 9420.8, 300 sec: 9160.1). Total num frames: 1511424. Throughput: 0: 9452.9. Samples: 1499144. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-07-08 20:43:10,923][1071413] Avg episode reward: [(0, '593.214')] -[2023-07-08 20:43:11,251][1071698] Updated weights for policy 0, policy_version 2960 (0.0005) -[2023-07-08 20:43:15,886][1071698] Updated weights for policy 0, policy_version 3040 (0.0005) -[2023-07-08 20:43:15,923][1071413] Fps is (10 sec: 9011.1, 60 sec: 9352.5, 300 sec: 9155.8). Total num frames: 1556480. Throughput: 0: 9297.6. Samples: 1552984. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-07-08 20:43:15,923][1071413] Avg episode reward: [(0, '634.424')] -[2023-07-08 20:43:15,927][1071654] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000003040_1556480.pth... -[2023-07-08 20:43:15,929][1071654] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000002488_1273856.pth -[2023-07-08 20:43:20,366][1071698] Updated weights for policy 0, policy_version 3120 (0.0005) -[2023-07-08 20:43:20,922][1071413] Fps is (10 sec: 9011.3, 60 sec: 9352.5, 300 sec: 9151.6). Total num frames: 1601536. Throughput: 0: 9320.8. Samples: 1580904. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-07-08 20:43:20,923][1071413] Avg episode reward: [(0, '668.658')] -[2023-07-08 20:43:20,923][1071654] Saving new best policy, reward=668.658! -[2023-07-08 20:43:24,564][1071698] Updated weights for policy 0, policy_version 3200 (0.0005) -[2023-07-08 20:43:25,922][1071413] Fps is (10 sec: 9011.3, 60 sec: 9352.5, 300 sec: 9147.7). Total num frames: 1646592. Throughput: 0: 9371.4. Samples: 1638224. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 20:43:25,923][1071413] Avg episode reward: [(0, '665.958')] -[2023-07-08 20:43:28,558][1071698] Updated weights for policy 0, policy_version 3280 (0.0005) -[2023-07-08 20:43:30,922][1071413] Fps is (10 sec: 9830.3, 60 sec: 9420.8, 300 sec: 9188.3). Total num frames: 1699840. Throughput: 0: 9458.6. Samples: 1698024. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) -[2023-07-08 20:43:30,923][1071413] Avg episode reward: [(0, '656.926')] -[2023-07-08 20:43:30,926][1071654] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000003320_1699840.pth... -[2023-07-08 20:43:30,929][1071654] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000002768_1417216.pth -[2023-07-08 20:43:33,073][1071698] Updated weights for policy 0, policy_version 3360 (0.0005) -[2023-07-08 20:43:35,922][1071413] Fps is (10 sec: 9830.5, 60 sec: 9352.5, 300 sec: 9183.7). Total num frames: 1744896. Throughput: 0: 9379.9. Samples: 1724388. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-07-08 20:43:35,923][1071413] Avg episode reward: [(0, '634.260')] -[2023-07-08 20:43:37,359][1071698] Updated weights for policy 0, policy_version 3440 (0.0005) -[2023-07-08 20:43:40,922][1071413] Fps is (10 sec: 9420.8, 60 sec: 9420.8, 300 sec: 9200.2). Total num frames: 1794048. Throughput: 0: 9384.7. Samples: 1781728. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-07-08 20:43:40,924][1071413] Avg episode reward: [(0, '648.512')] -[2023-07-08 20:43:41,786][1071698] Updated weights for policy 0, policy_version 3520 (0.0006) -[2023-07-08 20:43:45,923][1071413] Fps is (10 sec: 9420.6, 60 sec: 9420.8, 300 sec: 9195.5). Total num frames: 1839104. Throughput: 0: 9370.6. Samples: 1835120. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) -[2023-07-08 20:43:45,923][1071413] Avg episode reward: [(0, '657.097')] -[2023-07-08 20:43:45,927][1071654] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000003592_1839104.pth... -[2023-07-08 20:43:45,931][1071654] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000003040_1556480.pth -[2023-07-08 20:43:46,330][1071698] Updated weights for policy 0, policy_version 3600 (0.0005) -[2023-07-08 20:43:50,922][1071413] Fps is (10 sec: 8601.6, 60 sec: 9284.3, 300 sec: 9171.0). Total num frames: 1880064. Throughput: 0: 9340.8. Samples: 1862676. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-07-08 20:43:50,923][1071413] Avg episode reward: [(0, '657.078')] -[2023-07-08 20:43:50,961][1071698] Updated weights for policy 0, policy_version 3680 (0.0005) -[2023-07-08 20:43:55,254][1071698] Updated weights for policy 0, policy_version 3760 (0.0005) -[2023-07-08 20:43:55,922][1071413] Fps is (10 sec: 9011.3, 60 sec: 9352.5, 300 sec: 9186.7). Total num frames: 1929216. Throughput: 0: 9290.1. Samples: 1917196. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-07-08 20:43:55,923][1071413] Avg episode reward: [(0, '673.806')] -[2023-07-08 20:43:55,923][1071654] Saving new best policy, reward=673.806! -[2023-07-08 20:43:59,388][1071698] Updated weights for policy 0, policy_version 3840 (0.0005) -[2023-07-08 20:44:00,923][1071413] Fps is (10 sec: 9830.3, 60 sec: 9352.5, 300 sec: 9201.7). Total num frames: 1978368. Throughput: 0: 9406.8. Samples: 1976288. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-07-08 20:44:00,923][1071413] Avg episode reward: [(0, '670.694')] -[2023-07-08 20:44:00,926][1071654] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000003864_1978368.pth... -[2023-07-08 20:44:00,928][1071654] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000003320_1699840.pth -[2023-07-08 20:44:04,006][1071698] Updated weights for policy 0, policy_version 3920 (0.0005) -[2023-07-08 20:44:05,923][1071413] Fps is (10 sec: 9420.7, 60 sec: 9284.3, 300 sec: 9197.4). Total num frames: 2023424. Throughput: 0: 9376.2. Samples: 2002836. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 20:44:05,923][1071413] Avg episode reward: [(0, '681.210')] -[2023-07-08 20:44:05,923][1071654] Saving new best policy, reward=681.210! -[2023-07-08 20:44:08,521][1071698] Updated weights for policy 0, policy_version 4000 (0.0005) -[2023-07-08 20:44:10,922][1071413] Fps is (10 sec: 9011.3, 60 sec: 9284.3, 300 sec: 9193.2). Total num frames: 2068480. Throughput: 0: 9296.9. Samples: 2056584. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 20:44:10,923][1071413] Avg episode reward: [(0, '662.900')] -[2023-07-08 20:44:13,026][1071698] Updated weights for policy 0, policy_version 4080 (0.0005) -[2023-07-08 20:44:15,923][1071413] Fps is (10 sec: 9011.2, 60 sec: 9284.3, 300 sec: 9189.3). Total num frames: 2113536. Throughput: 0: 9204.1. Samples: 2112208. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 20:44:15,923][1071413] Avg episode reward: [(0, '668.282')] -[2023-07-08 20:44:15,926][1071654] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000004128_2113536.pth... -[2023-07-08 20:44:15,929][1071654] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000003592_1839104.pth -[2023-07-08 20:44:17,413][1071698] Updated weights for policy 0, policy_version 4160 (0.0005) -[2023-07-08 20:44:20,922][1071413] Fps is (10 sec: 9011.2, 60 sec: 9284.3, 300 sec: 9185.5). Total num frames: 2158592. Throughput: 0: 9233.3. Samples: 2139888. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 20:44:20,923][1071413] Avg episode reward: [(0, '664.099')] -[2023-07-08 20:44:21,997][1071698] Updated weights for policy 0, policy_version 4240 (0.0005) -[2023-07-08 20:44:25,923][1071413] Fps is (10 sec: 9420.8, 60 sec: 9352.5, 300 sec: 9198.9). Total num frames: 2207744. Throughput: 0: 9121.0. Samples: 2192176. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) -[2023-07-08 20:44:25,923][1071413] Avg episode reward: [(0, '662.333')] -[2023-07-08 20:44:26,355][1071698] Updated weights for policy 0, policy_version 4320 (0.0005) -[2023-07-08 20:44:30,456][1071698] Updated weights for policy 0, policy_version 4400 (0.0005) -[2023-07-08 20:44:30,923][1071413] Fps is (10 sec: 9830.3, 60 sec: 9284.2, 300 sec: 9211.8). Total num frames: 2256896. Throughput: 0: 9283.2. Samples: 2252864. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 20:44:30,923][1071413] Avg episode reward: [(0, '672.079')] -[2023-07-08 20:44:30,927][1071654] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000004408_2256896.pth... -[2023-07-08 20:44:30,930][1071654] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000003864_1978368.pth -[2023-07-08 20:44:34,921][1071698] Updated weights for policy 0, policy_version 4480 (0.0005) -[2023-07-08 20:44:35,923][1071413] Fps is (10 sec: 9420.8, 60 sec: 9284.2, 300 sec: 9207.8). Total num frames: 2301952. Throughput: 0: 9306.6. Samples: 2281472. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 20:44:35,923][1071413] Avg episode reward: [(0, '669.350')] -[2023-07-08 20:44:39,635][1071698] Updated weights for policy 0, policy_version 4560 (0.0006) -[2023-07-08 20:44:40,923][1071413] Fps is (10 sec: 8601.7, 60 sec: 9147.7, 300 sec: 9187.9). Total num frames: 2342912. Throughput: 0: 9275.5. Samples: 2334596. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-07-08 20:44:40,923][1071413] Avg episode reward: [(0, '654.814')] -[2023-07-08 20:44:44,147][1071698] Updated weights for policy 0, policy_version 4640 (0.0005) -[2023-07-08 20:44:45,923][1071413] Fps is (10 sec: 9011.2, 60 sec: 9216.0, 300 sec: 9200.2). Total num frames: 2392064. Throughput: 0: 9182.1. Samples: 2389480. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 20:44:45,923][1071413] Avg episode reward: [(0, '646.384')] -[2023-07-08 20:44:45,926][1071654] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000004672_2392064.pth... -[2023-07-08 20:44:45,929][1071654] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000004128_2113536.pth -[2023-07-08 20:44:48,658][1071698] Updated weights for policy 0, policy_version 4720 (0.0005) -[2023-07-08 20:44:50,922][1071413] Fps is (10 sec: 9011.2, 60 sec: 9216.0, 300 sec: 9181.2). Total num frames: 2433024. Throughput: 0: 9164.2. Samples: 2415224. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 20:44:50,923][1071413] Avg episode reward: [(0, '665.207')] -[2023-07-08 20:44:53,105][1071698] Updated weights for policy 0, policy_version 4800 (0.0005) -[2023-07-08 20:44:55,922][1071413] Fps is (10 sec: 9420.9, 60 sec: 9284.3, 300 sec: 9208.4). Total num frames: 2486272. Throughput: 0: 9206.9. Samples: 2470896. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-07-08 20:44:55,923][1071413] Avg episode reward: [(0, '667.408')] -[2023-07-08 20:44:57,247][1071698] Updated weights for policy 0, policy_version 4880 (0.0005) -[2023-07-08 20:45:00,922][1071413] Fps is (10 sec: 9830.4, 60 sec: 9216.0, 300 sec: 9204.8). Total num frames: 2531328. Throughput: 0: 9309.7. Samples: 2531144. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 20:45:00,923][1071413] Avg episode reward: [(0, '661.768')] -[2023-07-08 20:45:00,926][1071654] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000004944_2531328.pth... -[2023-07-08 20:45:00,930][1071654] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000004408_2256896.pth -[2023-07-08 20:45:01,438][1071698] Updated weights for policy 0, policy_version 4960 (0.0005) -[2023-07-08 20:45:05,776][1071698] Updated weights for policy 0, policy_version 5040 (0.0005) -[2023-07-08 20:45:05,922][1071413] Fps is (10 sec: 9420.8, 60 sec: 9284.3, 300 sec: 9216.0). Total num frames: 2580480. Throughput: 0: 9317.2. Samples: 2559160. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 20:45:05,923][1071413] Avg episode reward: [(0, '616.053')] -[2023-07-08 20:45:10,326][1071698] Updated weights for policy 0, policy_version 5120 (0.0005) -[2023-07-08 20:45:10,922][1071413] Fps is (10 sec: 9420.8, 60 sec: 9284.3, 300 sec: 9212.4). Total num frames: 2625536. Throughput: 0: 9383.4. Samples: 2614428. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 20:45:10,923][1071413] Avg episode reward: [(0, '657.420')] -[2023-07-08 20:45:14,878][1071698] Updated weights for policy 0, policy_version 5200 (0.0006) -[2023-07-08 20:45:15,923][1071413] Fps is (10 sec: 9011.0, 60 sec: 9284.3, 300 sec: 9208.9). Total num frames: 2670592. Throughput: 0: 9247.6. Samples: 2669008. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-07-08 20:45:15,923][1071413] Avg episode reward: [(0, '665.818')] -[2023-07-08 20:45:15,927][1071654] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000005216_2670592.pth... -[2023-07-08 20:45:15,929][1071654] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000004672_2392064.pth -[2023-07-08 20:45:18,811][1071698] Updated weights for policy 0, policy_version 5280 (0.0005) -[2023-07-08 20:45:20,922][1071413] Fps is (10 sec: 9420.8, 60 sec: 9352.5, 300 sec: 9219.5). Total num frames: 2719744. Throughput: 0: 9291.3. Samples: 2699580. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) -[2023-07-08 20:45:20,923][1071413] Avg episode reward: [(0, '669.957')] -[2023-07-08 20:45:23,429][1071698] Updated weights for policy 0, policy_version 5360 (0.0005) -[2023-07-08 20:45:25,922][1071413] Fps is (10 sec: 9420.9, 60 sec: 9284.3, 300 sec: 9372.2). Total num frames: 2764800. Throughput: 0: 9330.3. Samples: 2754460. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-07-08 20:45:25,923][1071413] Avg episode reward: [(0, '684.714')] -[2023-07-08 20:45:25,924][1071654] Saving new best policy, reward=684.714! -[2023-07-08 20:45:28,071][1071698] Updated weights for policy 0, policy_version 5440 (0.0005) -[2023-07-08 20:45:30,923][1071413] Fps is (10 sec: 9011.1, 60 sec: 9216.0, 300 sec: 9427.7). Total num frames: 2809856. Throughput: 0: 9303.6. Samples: 2808140. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 20:45:30,923][1071413] Avg episode reward: [(0, '680.403')] -[2023-07-08 20:45:30,926][1071654] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000005488_2809856.pth... -[2023-07-08 20:45:30,929][1071654] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000004944_2531328.pth -[2023-07-08 20:45:32,551][1071698] Updated weights for policy 0, policy_version 5520 (0.0005) -[2023-07-08 20:45:35,923][1071413] Fps is (10 sec: 9011.1, 60 sec: 9216.0, 300 sec: 9427.7). Total num frames: 2854912. Throughput: 0: 9315.5. Samples: 2834420. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-07-08 20:45:35,923][1071413] Avg episode reward: [(0, '658.324')] -[2023-07-08 20:45:37,205][1071698] Updated weights for policy 0, policy_version 5600 (0.0005) -[2023-07-08 20:45:40,922][1071413] Fps is (10 sec: 9011.3, 60 sec: 9284.3, 300 sec: 9400.0). Total num frames: 2899968. Throughput: 0: 9263.3. Samples: 2887744. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-07-08 20:45:40,923][1071413] Avg episode reward: [(0, '678.135')] -[2023-07-08 20:45:41,717][1071698] Updated weights for policy 0, policy_version 5680 (0.0005) -[2023-07-08 20:45:45,922][1071413] Fps is (10 sec: 8601.6, 60 sec: 9147.7, 300 sec: 9386.1). Total num frames: 2940928. Throughput: 0: 9107.7. Samples: 2940992. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-07-08 20:45:45,923][1071413] Avg episode reward: [(0, '668.148')] -[2023-07-08 20:45:45,942][1071654] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000005752_2945024.pth... -[2023-07-08 20:45:45,944][1071654] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000005216_2670592.pth -[2023-07-08 20:45:46,395][1071698] Updated weights for policy 0, policy_version 5760 (0.0005) -[2023-07-08 20:45:50,922][1071413] Fps is (10 sec: 8601.7, 60 sec: 9216.0, 300 sec: 9372.2). Total num frames: 2985984. Throughput: 0: 9080.0. Samples: 2967760. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-07-08 20:45:50,923][1071413] Avg episode reward: [(0, '669.955')] -[2023-07-08 20:45:50,963][1071698] Updated weights for policy 0, policy_version 5840 (0.0006) -[2023-07-08 20:45:55,693][1071698] Updated weights for policy 0, policy_version 5920 (0.0005) -[2023-07-08 20:45:55,923][1071413] Fps is (10 sec: 9011.2, 60 sec: 9079.4, 300 sec: 9358.3). Total num frames: 3031040. Throughput: 0: 9014.8. Samples: 3020092. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-07-08 20:45:55,923][1071413] Avg episode reward: [(0, '672.983')] -[2023-07-08 20:45:59,533][1071698] Updated weights for policy 0, policy_version 6000 (0.0005) -[2023-07-08 20:46:00,922][1071413] Fps is (10 sec: 9830.4, 60 sec: 9216.0, 300 sec: 9386.1). Total num frames: 3084288. Throughput: 0: 9163.8. Samples: 3081376. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) -[2023-07-08 20:46:00,923][1071413] Avg episode reward: [(0, '678.059')] -[2023-07-08 20:46:00,925][1071654] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000006024_3084288.pth... -[2023-07-08 20:46:00,927][1071654] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000005488_2809856.pth -[2023-07-08 20:46:04,202][1071698] Updated weights for policy 0, policy_version 6080 (0.0005) -[2023-07-08 20:46:05,922][1071413] Fps is (10 sec: 9420.8, 60 sec: 9079.5, 300 sec: 9344.4). Total num frames: 3125248. Throughput: 0: 9063.7. Samples: 3107448. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) -[2023-07-08 20:46:05,923][1071413] Avg episode reward: [(0, '673.982')] -[2023-07-08 20:46:08,686][1071698] Updated weights for policy 0, policy_version 6160 (0.0005) -[2023-07-08 20:46:10,922][1071413] Fps is (10 sec: 9011.2, 60 sec: 9147.7, 300 sec: 9344.4). Total num frames: 3174400. Throughput: 0: 9059.2. Samples: 3162124. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 20:46:10,923][1071413] Avg episode reward: [(0, '666.952')] -[2023-07-08 20:46:12,905][1071698] Updated weights for policy 0, policy_version 6240 (0.0005) -[2023-07-08 20:46:15,923][1071413] Fps is (10 sec: 9420.8, 60 sec: 9147.7, 300 sec: 9330.5). Total num frames: 3219456. Throughput: 0: 9068.4. Samples: 3216216. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 20:46:15,923][1071413] Avg episode reward: [(0, '680.070')] -[2023-07-08 20:46:15,926][1071654] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000006288_3219456.pth... -[2023-07-08 20:46:15,929][1071654] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000005752_2945024.pth -[2023-07-08 20:46:17,684][1071698] Updated weights for policy 0, policy_version 6320 (0.0005) -[2023-07-08 20:46:20,922][1071413] Fps is (10 sec: 9011.2, 60 sec: 9079.5, 300 sec: 9316.7). Total num frames: 3264512. Throughput: 0: 9097.3. Samples: 3243796. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 20:46:20,923][1071413] Avg episode reward: [(0, '675.712')] -[2023-07-08 20:46:21,873][1071698] Updated weights for policy 0, policy_version 6400 (0.0005) -[2023-07-08 20:46:25,922][1071413] Fps is (10 sec: 9011.2, 60 sec: 9079.5, 300 sec: 9302.8). Total num frames: 3309568. Throughput: 0: 9191.4. Samples: 3301356. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-07-08 20:46:25,923][1071413] Avg episode reward: [(0, '668.596')] -[2023-07-08 20:46:26,422][1071698] Updated weights for policy 0, policy_version 6480 (0.0005) -[2023-07-08 20:46:30,923][1071413] Fps is (10 sec: 9011.1, 60 sec: 9079.5, 300 sec: 9302.8). Total num frames: 3354624. Throughput: 0: 9153.9. Samples: 3352920. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 20:46:30,923][1071413] Avg episode reward: [(0, '674.457')] -[2023-07-08 20:46:30,925][1071654] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000006552_3354624.pth... -[2023-07-08 20:46:30,928][1071654] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000006024_3084288.pth -[2023-07-08 20:46:31,184][1071698] Updated weights for policy 0, policy_version 6560 (0.0005) -[2023-07-08 20:46:35,665][1071698] Updated weights for policy 0, policy_version 6640 (0.0005) -[2023-07-08 20:46:35,923][1071413] Fps is (10 sec: 9011.1, 60 sec: 9079.5, 300 sec: 9288.9). Total num frames: 3399680. Throughput: 0: 9172.8. Samples: 3380536. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 20:46:35,923][1071413] Avg episode reward: [(0, '664.575')] -[2023-07-08 20:46:40,279][1071698] Updated weights for policy 0, policy_version 6720 (0.0005) -[2023-07-08 20:46:40,922][1071413] Fps is (10 sec: 9011.2, 60 sec: 9079.5, 300 sec: 9275.0). Total num frames: 3444736. Throughput: 0: 9184.7. Samples: 3433404. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) -[2023-07-08 20:46:40,923][1071413] Avg episode reward: [(0, '681.929')] -[2023-07-08 20:46:44,640][1071698] Updated weights for policy 0, policy_version 6800 (0.0004) -[2023-07-08 20:46:45,923][1071413] Fps is (10 sec: 9011.3, 60 sec: 9147.7, 300 sec: 9261.1). Total num frames: 3489792. Throughput: 0: 9076.1. Samples: 3489800. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) -[2023-07-08 20:46:45,923][1071413] Avg episode reward: [(0, '673.358')] -[2023-07-08 20:46:45,926][1071654] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000006824_3493888.pth... -[2023-07-08 20:46:45,929][1071654] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000006288_3219456.pth -[2023-07-08 20:46:49,198][1071698] Updated weights for policy 0, policy_version 6880 (0.0005) -[2023-07-08 20:46:50,922][1071413] Fps is (10 sec: 9011.2, 60 sec: 9147.7, 300 sec: 9247.2). Total num frames: 3534848. Throughput: 0: 9084.8. Samples: 3516264. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 20:46:50,923][1071413] Avg episode reward: [(0, '661.087')] -[2023-07-08 20:46:53,658][1071698] Updated weights for policy 0, policy_version 6960 (0.0006) -[2023-07-08 20:46:55,923][1071413] Fps is (10 sec: 9420.8, 60 sec: 9216.0, 300 sec: 9247.2). Total num frames: 3584000. Throughput: 0: 9100.7. Samples: 3571656. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 20:46:55,923][1071413] Avg episode reward: [(0, '666.723')] -[2023-07-08 20:46:58,069][1071698] Updated weights for policy 0, policy_version 7040 (0.0005) -[2023-07-08 20:47:00,923][1071413] Fps is (10 sec: 9420.7, 60 sec: 9079.4, 300 sec: 9247.2). Total num frames: 3629056. Throughput: 0: 9140.2. Samples: 3627524. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 20:47:00,923][1071413] Avg episode reward: [(0, '671.942')] -[2023-07-08 20:47:00,927][1071654] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000007088_3629056.pth... -[2023-07-08 20:47:00,930][1071654] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000006552_3354624.pth -[2023-07-08 20:47:02,498][1071698] Updated weights for policy 0, policy_version 7120 (0.0005) -[2023-07-08 20:47:05,922][1071413] Fps is (10 sec: 9011.3, 60 sec: 9147.8, 300 sec: 9247.2). Total num frames: 3674112. Throughput: 0: 9128.1. Samples: 3654560. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 20:47:05,923][1071413] Avg episode reward: [(0, '660.886')] -[2023-07-08 20:47:07,056][1071698] Updated weights for policy 0, policy_version 7200 (0.0005) -[2023-07-08 20:47:10,922][1071413] Fps is (10 sec: 9011.3, 60 sec: 9079.5, 300 sec: 9233.4). Total num frames: 3719168. Throughput: 0: 9085.5. Samples: 3710204. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-07-08 20:47:10,923][1071413] Avg episode reward: [(0, '684.433')] -[2023-07-08 20:47:11,509][1071698] Updated weights for policy 0, policy_version 7280 (0.0005) -[2023-07-08 20:47:15,922][1071413] Fps is (10 sec: 9011.1, 60 sec: 9079.5, 300 sec: 9233.4). Total num frames: 3764224. Throughput: 0: 9139.5. Samples: 3764196. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 20:47:15,923][1071413] Avg episode reward: [(0, '659.426')] -[2023-07-08 20:47:15,925][1071654] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000007352_3764224.pth... -[2023-07-08 20:47:15,927][1071654] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000006824_3493888.pth -[2023-07-08 20:47:16,049][1071698] Updated weights for policy 0, policy_version 7360 (0.0005) -[2023-07-08 20:47:20,651][1071698] Updated weights for policy 0, policy_version 7440 (0.0005) -[2023-07-08 20:47:20,922][1071413] Fps is (10 sec: 9011.2, 60 sec: 9079.5, 300 sec: 9233.4). Total num frames: 3809280. Throughput: 0: 9079.9. Samples: 3789132. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-07-08 20:47:20,923][1071413] Avg episode reward: [(0, '676.194')] -[2023-07-08 20:47:25,250][1071698] Updated weights for policy 0, policy_version 7520 (0.0005) -[2023-07-08 20:47:25,923][1071413] Fps is (10 sec: 9011.1, 60 sec: 9079.5, 300 sec: 9219.5). Total num frames: 3854336. Throughput: 0: 9116.8. Samples: 3843660. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-07-08 20:47:25,923][1071413] Avg episode reward: [(0, '651.353')] -[2023-07-08 20:47:29,919][1071698] Updated weights for policy 0, policy_version 7600 (0.0005) -[2023-07-08 20:47:30,923][1071413] Fps is (10 sec: 9011.1, 60 sec: 9079.5, 300 sec: 9205.6). Total num frames: 3899392. Throughput: 0: 9016.8. Samples: 3895556. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 20:47:30,923][1071413] Avg episode reward: [(0, '644.267')] -[2023-07-08 20:47:30,926][1071654] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000007616_3899392.pth... -[2023-07-08 20:47:30,929][1071654] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000007088_3629056.pth -[2023-07-08 20:47:34,616][1071698] Updated weights for policy 0, policy_version 7680 (0.0005) -[2023-07-08 20:47:35,922][1071413] Fps is (10 sec: 8601.7, 60 sec: 9011.2, 300 sec: 9191.7). Total num frames: 3940352. Throughput: 0: 9051.8. Samples: 3923596. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-07-08 20:47:35,923][1071413] Avg episode reward: [(0, '655.441')] -[2023-07-08 20:47:39,204][1071698] Updated weights for policy 0, policy_version 7760 (0.0005) -[2023-07-08 20:47:40,922][1071413] Fps is (10 sec: 8601.7, 60 sec: 9011.2, 300 sec: 9191.7). Total num frames: 3985408. Throughput: 0: 8986.6. Samples: 3976052. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-07-08 20:47:40,923][1071413] Avg episode reward: [(0, '642.721')] -[2023-07-08 20:47:43,735][1071698] Updated weights for policy 0, policy_version 7840 (0.0005) -[2023-07-08 20:47:45,922][1071413] Fps is (10 sec: 9011.2, 60 sec: 9011.2, 300 sec: 9177.8). Total num frames: 4030464. Throughput: 0: 8953.5. Samples: 4030428. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-07-08 20:47:45,923][1071413] Avg episode reward: [(0, '632.240')] -[2023-07-08 20:47:45,925][1071654] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000007872_4030464.pth... -[2023-07-08 20:47:45,927][1071654] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000007352_3764224.pth -[2023-07-08 20:47:48,059][1071698] Updated weights for policy 0, policy_version 7920 (0.0005) -[2023-07-08 20:47:50,923][1071413] Fps is (10 sec: 9420.7, 60 sec: 9079.5, 300 sec: 9191.7). Total num frames: 4079616. Throughput: 0: 8987.8. Samples: 4059012. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 20:47:50,923][1071413] Avg episode reward: [(0, '675.411')] -[2023-07-08 20:47:52,742][1071698] Updated weights for policy 0, policy_version 8000 (0.0005) -[2023-07-08 20:47:55,923][1071413] Fps is (10 sec: 9420.6, 60 sec: 9011.2, 300 sec: 9177.8). Total num frames: 4124672. Throughput: 0: 8934.7. Samples: 4112268. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-07-08 20:47:55,923][1071413] Avg episode reward: [(0, '678.762')] -[2023-07-08 20:47:57,042][1071698] Updated weights for policy 0, policy_version 8080 (0.0005) -[2023-07-08 20:48:00,923][1071413] Fps is (10 sec: 9420.8, 60 sec: 9079.5, 300 sec: 9177.8). Total num frames: 4173824. Throughput: 0: 9063.4. Samples: 4172048. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-07-08 20:48:01,027][1071413] Avg episode reward: [(0, '666.071')] -[2023-07-08 20:48:01,036][1071654] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000008160_4177920.pth... -[2023-07-08 20:48:01,036][1071698] Updated weights for policy 0, policy_version 8160 (0.0005) -[2023-07-08 20:48:01,038][1071654] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000007616_3899392.pth -[2023-07-08 20:48:05,023][1071698] Updated weights for policy 0, policy_version 8240 (0.0005) -[2023-07-08 20:48:05,923][1071413] Fps is (10 sec: 9830.5, 60 sec: 9147.7, 300 sec: 9191.7). Total num frames: 4222976. Throughput: 0: 9235.5. Samples: 4204732. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) -[2023-07-08 20:48:05,924][1071413] Avg episode reward: [(0, '649.242')] -[2023-07-08 20:48:09,342][1071698] Updated weights for policy 0, policy_version 8320 (0.0005) -[2023-07-08 20:48:10,922][1071413] Fps is (10 sec: 9830.5, 60 sec: 9216.0, 300 sec: 9205.6). Total num frames: 4272128. Throughput: 0: 9273.1. Samples: 4260948. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 20:48:10,923][1071413] Avg episode reward: [(0, '673.363')] -[2023-07-08 20:48:13,565][1071698] Updated weights for policy 0, policy_version 8400 (0.0005) -[2023-07-08 20:48:15,923][1071413] Fps is (10 sec: 9830.4, 60 sec: 9284.3, 300 sec: 9219.5). Total num frames: 4321280. Throughput: 0: 9389.4. Samples: 4318080. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-07-08 20:48:15,923][1071413] Avg episode reward: [(0, '670.738')] -[2023-07-08 20:48:15,926][1071654] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000008440_4321280.pth... -[2023-07-08 20:48:15,929][1071654] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000007872_4030464.pth -[2023-07-08 20:48:17,833][1071698] Updated weights for policy 0, policy_version 8480 (0.0005) -[2023-07-08 20:48:20,923][1071413] Fps is (10 sec: 9830.3, 60 sec: 9352.5, 300 sec: 9233.4). Total num frames: 4370432. Throughput: 0: 9459.7. Samples: 4349284. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-07-08 20:48:20,924][1071413] Avg episode reward: [(0, '682.149')] -[2023-07-08 20:48:21,869][1071698] Updated weights for policy 0, policy_version 8560 (0.0006) -[2023-07-08 20:48:25,923][1071413] Fps is (10 sec: 9830.4, 60 sec: 9420.8, 300 sec: 9219.5). Total num frames: 4419584. Throughput: 0: 9606.6. Samples: 4408348. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 20:48:25,924][1071413] Avg episode reward: [(0, '682.438')] -[2023-07-08 20:48:26,122][1071698] Updated weights for policy 0, policy_version 8640 (0.0005) -[2023-07-08 20:48:30,569][1071698] Updated weights for policy 0, policy_version 8720 (0.0005) -[2023-07-08 20:48:30,922][1071413] Fps is (10 sec: 9420.8, 60 sec: 9420.8, 300 sec: 9219.5). Total num frames: 4464640. Throughput: 0: 9645.7. Samples: 4464484. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-07-08 20:48:30,923][1071413] Avg episode reward: [(0, '684.475')] -[2023-07-08 20:48:30,925][1071654] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000008720_4464640.pth... -[2023-07-08 20:48:30,927][1071654] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000008160_4177920.pth -[2023-07-08 20:48:35,085][1071698] Updated weights for policy 0, policy_version 8800 (0.0005) -[2023-07-08 20:48:35,922][1071413] Fps is (10 sec: 9011.3, 60 sec: 9489.1, 300 sec: 9205.6). Total num frames: 4509696. Throughput: 0: 9608.0. Samples: 4491372. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-07-08 20:48:35,923][1071413] Avg episode reward: [(0, '680.502')] -[2023-07-08 20:48:39,497][1071698] Updated weights for policy 0, policy_version 8880 (0.0005) -[2023-07-08 20:48:40,922][1071413] Fps is (10 sec: 9420.8, 60 sec: 9557.3, 300 sec: 9219.5). Total num frames: 4558848. Throughput: 0: 9651.0. Samples: 4546560. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-07-08 20:48:40,924][1071413] Avg episode reward: [(0, '681.735')] -[2023-07-08 20:48:43,685][1071698] Updated weights for policy 0, policy_version 8960 (0.0005) -[2023-07-08 20:48:45,923][1071413] Fps is (10 sec: 9830.2, 60 sec: 9625.6, 300 sec: 9247.2). Total num frames: 4608000. Throughput: 0: 9598.2. Samples: 4603968. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 20:48:45,923][1071413] Avg episode reward: [(0, '670.008')] -[2023-07-08 20:48:45,928][1071654] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000009000_4608000.pth... -[2023-07-08 20:48:45,930][1071654] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000008440_4321280.pth -[2023-07-08 20:48:48,163][1071698] Updated weights for policy 0, policy_version 9040 (0.0005) -[2023-07-08 20:48:50,922][1071413] Fps is (10 sec: 9011.2, 60 sec: 9489.1, 300 sec: 9219.5). Total num frames: 4648960. Throughput: 0: 9492.8. Samples: 4631908. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 20:48:50,923][1071413] Avg episode reward: [(0, '664.725')] -[2023-07-08 20:48:52,739][1071698] Updated weights for policy 0, policy_version 9120 (0.0005) -[2023-07-08 20:48:55,922][1071413] Fps is (10 sec: 8601.7, 60 sec: 9489.1, 300 sec: 9205.6). Total num frames: 4694016. Throughput: 0: 9415.2. Samples: 4684632. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 20:48:55,923][1071413] Avg episode reward: [(0, '686.985')] -[2023-07-08 20:48:55,924][1071654] Saving new best policy, reward=686.985! -[2023-07-08 20:48:57,450][1071698] Updated weights for policy 0, policy_version 9200 (0.0005) -[2023-07-08 20:49:00,923][1071413] Fps is (10 sec: 9011.1, 60 sec: 9420.8, 300 sec: 9205.6). Total num frames: 4739072. Throughput: 0: 9317.6. Samples: 4737372. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 20:49:00,923][1071413] Avg episode reward: [(0, '665.979')] -[2023-07-08 20:49:00,926][1071654] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000009256_4739072.pth... -[2023-07-08 20:49:00,929][1071654] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000008720_4464640.pth -[2023-07-08 20:49:02,028][1071698] Updated weights for policy 0, policy_version 9280 (0.0005) -[2023-07-08 20:49:05,923][1071413] Fps is (10 sec: 9011.2, 60 sec: 9352.5, 300 sec: 9205.6). Total num frames: 4784128. Throughput: 0: 9210.9. Samples: 4763776. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 20:49:05,923][1071413] Avg episode reward: [(0, '680.268')] -[2023-07-08 20:49:06,704][1071698] Updated weights for policy 0, policy_version 9360 (0.0005) -[2023-07-08 20:49:10,922][1071413] Fps is (10 sec: 9011.3, 60 sec: 9284.3, 300 sec: 9205.6). Total num frames: 4829184. Throughput: 0: 9126.3. Samples: 4819032. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 20:49:10,923][1071413] Avg episode reward: [(0, '682.483')] -[2023-07-08 20:49:11,036][1071698] Updated weights for policy 0, policy_version 9440 (0.0005) -[2023-07-08 20:49:15,522][1071698] Updated weights for policy 0, policy_version 9520 (0.0005) -[2023-07-08 20:49:15,923][1071413] Fps is (10 sec: 9011.2, 60 sec: 9216.0, 300 sec: 9205.6). Total num frames: 4874240. Throughput: 0: 9105.4. Samples: 4874228. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) -[2023-07-08 20:49:15,923][1071413] Avg episode reward: [(0, '689.803')] -[2023-07-08 20:49:15,925][1071654] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000009520_4874240.pth... -[2023-07-08 20:49:15,927][1071654] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000009000_4608000.pth -[2023-07-08 20:49:15,927][1071654] Saving new best policy, reward=689.803! -[2023-07-08 20:49:20,134][1071698] Updated weights for policy 0, policy_version 9600 (0.0005) -[2023-07-08 20:49:20,922][1071413] Fps is (10 sec: 9011.2, 60 sec: 9147.8, 300 sec: 9191.7). Total num frames: 4919296. Throughput: 0: 9071.7. Samples: 4899600. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) -[2023-07-08 20:49:20,923][1071413] Avg episode reward: [(0, '680.373')] -[2023-07-08 20:49:24,725][1071698] Updated weights for policy 0, policy_version 9680 (0.0006) -[2023-07-08 20:49:25,922][1071413] Fps is (10 sec: 9011.2, 60 sec: 9079.5, 300 sec: 9177.8). Total num frames: 4964352. Throughput: 0: 9086.2. Samples: 4955440. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 20:49:25,923][1071413] Avg episode reward: [(0, '680.884')] -[2023-07-08 20:49:29,178][1071698] Updated weights for policy 0, policy_version 9760 (0.0005) -[2023-07-08 20:49:30,922][1071413] Fps is (10 sec: 9420.7, 60 sec: 9147.7, 300 sec: 9191.7). Total num frames: 5013504. Throughput: 0: 9009.8. Samples: 5009408. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 20:49:30,923][1071413] Avg episode reward: [(0, '689.982')] -[2023-07-08 20:49:30,926][1071654] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000009792_5013504.pth... -[2023-07-08 20:49:30,929][1071654] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000009256_4739072.pth -[2023-07-08 20:49:30,929][1071654] Saving new best policy, reward=689.982! -[2023-07-08 20:49:33,712][1071698] Updated weights for policy 0, policy_version 9840 (0.0005) -[2023-07-08 20:49:35,922][1071413] Fps is (10 sec: 9011.2, 60 sec: 9079.5, 300 sec: 9191.7). Total num frames: 5054464. Throughput: 0: 9003.3. Samples: 5037056. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 20:49:35,923][1071413] Avg episode reward: [(0, '685.756')] -[2023-07-08 20:49:38,090][1071698] Updated weights for policy 0, policy_version 9920 (0.0005) -[2023-07-08 20:49:40,923][1071413] Fps is (10 sec: 9011.1, 60 sec: 9079.5, 300 sec: 9191.7). Total num frames: 5103616. Throughput: 0: 9037.3. Samples: 5091312. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 20:49:40,923][1071413] Avg episode reward: [(0, '693.406')] -[2023-07-08 20:49:40,924][1071654] Saving new best policy, reward=693.406! -[2023-07-08 20:49:42,692][1071698] Updated weights for policy 0, policy_version 10000 (0.0005) -[2023-07-08 20:49:45,923][1071413] Fps is (10 sec: 9011.0, 60 sec: 8942.9, 300 sec: 9191.7). Total num frames: 5144576. Throughput: 0: 9048.1. Samples: 5144536. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 20:49:45,923][1071413] Avg episode reward: [(0, '691.104')] -[2023-07-08 20:49:45,979][1071654] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000010056_5148672.pth... -[2023-07-08 20:49:45,981][1071654] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000009520_4874240.pth -[2023-07-08 20:49:47,346][1071698] Updated weights for policy 0, policy_version 10080 (0.0005) -[2023-07-08 20:49:50,923][1071413] Fps is (10 sec: 9011.1, 60 sec: 9079.4, 300 sec: 9177.8). Total num frames: 5193728. Throughput: 0: 9097.1. Samples: 5173148. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-07-08 20:49:50,923][1071413] Avg episode reward: [(0, '684.354')] -[2023-07-08 20:49:51,763][1071698] Updated weights for policy 0, policy_version 10160 (0.0005) -[2023-07-08 20:49:55,922][1071413] Fps is (10 sec: 9421.0, 60 sec: 9079.5, 300 sec: 9177.8). Total num frames: 5238784. Throughput: 0: 9066.8. Samples: 5227040. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 20:49:55,923][1071413] Avg episode reward: [(0, '696.820')] -[2023-07-08 20:49:55,923][1071654] Saving new best policy, reward=696.820! -[2023-07-08 20:49:56,199][1071698] Updated weights for policy 0, policy_version 10240 (0.0006) -[2023-07-08 20:50:00,410][1071698] Updated weights for policy 0, policy_version 10320 (0.0006) -[2023-07-08 20:50:00,923][1071413] Fps is (10 sec: 9420.8, 60 sec: 9147.7, 300 sec: 9177.8). Total num frames: 5287936. Throughput: 0: 9114.4. Samples: 5284376. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 20:50:00,923][1071413] Avg episode reward: [(0, '688.317')] -[2023-07-08 20:50:00,926][1071654] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000010328_5287936.pth... -[2023-07-08 20:50:00,928][1071654] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000009792_5013504.pth -[2023-07-08 20:50:05,006][1071698] Updated weights for policy 0, policy_version 10400 (0.0005) -[2023-07-08 20:50:05,922][1071413] Fps is (10 sec: 9011.2, 60 sec: 9079.5, 300 sec: 9163.9). Total num frames: 5328896. Throughput: 0: 9147.8. Samples: 5311252. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 20:50:05,923][1071413] Avg episode reward: [(0, '683.068')] -[2023-07-08 20:50:09,313][1071698] Updated weights for policy 0, policy_version 10480 (0.0005) -[2023-07-08 20:50:10,923][1071413] Fps is (10 sec: 9011.1, 60 sec: 9147.7, 300 sec: 9177.8). Total num frames: 5378048. Throughput: 0: 9158.6. Samples: 5367580. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 20:50:10,923][1071413] Avg episode reward: [(0, '691.823')] -[2023-07-08 20:50:13,810][1071698] Updated weights for policy 0, policy_version 10560 (0.0005) -[2023-07-08 20:50:15,922][1071413] Fps is (10 sec: 9420.8, 60 sec: 9147.7, 300 sec: 9163.9). Total num frames: 5423104. Throughput: 0: 9176.3. Samples: 5422344. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 20:50:15,923][1071413] Avg episode reward: [(0, '696.509')] -[2023-07-08 20:50:15,926][1071654] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000010592_5423104.pth... -[2023-07-08 20:50:15,929][1071654] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000010056_5148672.pth -[2023-07-08 20:50:18,522][1071698] Updated weights for policy 0, policy_version 10640 (0.0005) -[2023-07-08 20:50:20,922][1071413] Fps is (10 sec: 9011.3, 60 sec: 9147.7, 300 sec: 9163.9). Total num frames: 5468160. Throughput: 0: 9124.4. Samples: 5447656. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 20:50:20,923][1071413] Avg episode reward: [(0, '684.874')] -[2023-07-08 20:50:22,830][1071698] Updated weights for policy 0, policy_version 10720 (0.0004) -[2023-07-08 20:50:25,923][1071413] Fps is (10 sec: 9420.8, 60 sec: 9216.0, 300 sec: 9177.8). Total num frames: 5517312. Throughput: 0: 9195.0. Samples: 5505088. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-07-08 20:50:25,923][1071413] Avg episode reward: [(0, '667.730')] -[2023-07-08 20:50:26,899][1071698] Updated weights for policy 0, policy_version 10800 (0.0005) -[2023-07-08 20:50:30,584][1071698] Updated weights for policy 0, policy_version 10880 (0.0005) -[2023-07-08 20:50:30,923][1071413] Fps is (10 sec: 10239.9, 60 sec: 9284.2, 300 sec: 9205.6). Total num frames: 5570560. Throughput: 0: 9434.6. Samples: 5569092. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 20:50:30,923][1071413] Avg episode reward: [(0, '675.070')] -[2023-07-08 20:50:30,953][1071654] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000010888_5574656.pth... -[2023-07-08 20:50:30,956][1071654] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000010328_5287936.pth -[2023-07-08 20:50:34,923][1071698] Updated weights for policy 0, policy_version 10960 (0.0005) -[2023-07-08 20:50:35,923][1071413] Fps is (10 sec: 10240.0, 60 sec: 9420.8, 300 sec: 9219.5). Total num frames: 5619712. Throughput: 0: 9453.3. Samples: 5598544. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 20:50:35,923][1071413] Avg episode reward: [(0, '694.494')] -[2023-07-08 20:50:39,465][1071698] Updated weights for policy 0, policy_version 11040 (0.0005) -[2023-07-08 20:50:40,922][1071413] Fps is (10 sec: 9420.9, 60 sec: 9352.5, 300 sec: 9233.4). Total num frames: 5664768. Throughput: 0: 9455.6. Samples: 5652544. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-07-08 20:50:40,923][1071413] Avg episode reward: [(0, '689.482')] -[2023-07-08 20:50:43,752][1071698] Updated weights for policy 0, policy_version 11120 (0.0005) -[2023-07-08 20:50:45,922][1071413] Fps is (10 sec: 9011.3, 60 sec: 9420.8, 300 sec: 9233.4). Total num frames: 5709824. Throughput: 0: 9454.6. Samples: 5709832. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-07-08 20:50:45,923][1071413] Avg episode reward: [(0, '681.534')] -[2023-07-08 20:50:45,926][1071654] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000011152_5709824.pth... -[2023-07-08 20:50:45,928][1071654] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000010592_5423104.pth -[2023-07-08 20:50:48,248][1071698] Updated weights for policy 0, policy_version 11200 (0.0005) -[2023-07-08 20:50:50,922][1071413] Fps is (10 sec: 9420.8, 60 sec: 9420.8, 300 sec: 9247.2). Total num frames: 5758976. Throughput: 0: 9460.2. Samples: 5736960. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-07-08 20:50:50,923][1071413] Avg episode reward: [(0, '690.670')] -[2023-07-08 20:50:52,576][1071698] Updated weights for policy 0, policy_version 11280 (0.0005) -[2023-07-08 20:50:55,922][1071413] Fps is (10 sec: 9420.8, 60 sec: 9420.8, 300 sec: 9219.5). Total num frames: 5804032. Throughput: 0: 9462.9. Samples: 5793408. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-07-08 20:50:55,923][1071413] Avg episode reward: [(0, '690.220')] -[2023-07-08 20:50:56,995][1071698] Updated weights for policy 0, policy_version 11360 (0.0005) -[2023-07-08 20:51:00,922][1071413] Fps is (10 sec: 9420.8, 60 sec: 9420.8, 300 sec: 9247.2). Total num frames: 5853184. Throughput: 0: 9498.3. Samples: 5849768. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-07-08 20:51:00,923][1071413] Avg episode reward: [(0, '686.142')] -[2023-07-08 20:51:00,927][1071654] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000011432_5853184.pth... -[2023-07-08 20:51:00,929][1071654] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000010888_5574656.pth -[2023-07-08 20:51:01,259][1071698] Updated weights for policy 0, policy_version 11440 (0.0005) -[2023-07-08 20:51:05,632][1071698] Updated weights for policy 0, policy_version 11520 (0.0005) -[2023-07-08 20:51:05,922][1071413] Fps is (10 sec: 9420.8, 60 sec: 9489.1, 300 sec: 9233.4). Total num frames: 5898240. Throughput: 0: 9591.4. Samples: 5879268. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-07-08 20:51:05,924][1071413] Avg episode reward: [(0, '679.229')] -[2023-07-08 20:51:09,686][1071698] Updated weights for policy 0, policy_version 11600 (0.0005) -[2023-07-08 20:51:10,922][1071413] Fps is (10 sec: 9420.9, 60 sec: 9489.1, 300 sec: 9247.2). Total num frames: 5947392. Throughput: 0: 9605.4. Samples: 5937328. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) -[2023-07-08 20:51:10,924][1071413] Avg episode reward: [(0, '686.245')] -[2023-07-08 20:51:14,217][1071698] Updated weights for policy 0, policy_version 11680 (0.0005) -[2023-07-08 20:51:15,922][1071413] Fps is (10 sec: 9420.8, 60 sec: 9489.1, 300 sec: 9247.2). Total num frames: 5992448. Throughput: 0: 9400.8. Samples: 5992128. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 20:51:15,923][1071413] Avg episode reward: [(0, '683.392')] -[2023-07-08 20:51:15,926][1071654] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000011704_5992448.pth... -[2023-07-08 20:51:15,928][1071654] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000011152_5709824.pth -[2023-07-08 20:51:18,690][1071698] Updated weights for policy 0, policy_version 11760 (0.0006) -[2023-07-08 20:51:20,922][1071413] Fps is (10 sec: 9420.7, 60 sec: 9557.3, 300 sec: 9261.1). Total num frames: 6041600. Throughput: 0: 9349.9. Samples: 6019288. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 20:51:20,923][1071413] Avg episode reward: [(0, '687.407')] -[2023-07-08 20:51:23,320][1071698] Updated weights for policy 0, policy_version 11840 (0.0005) -[2023-07-08 20:51:25,922][1071413] Fps is (10 sec: 9011.3, 60 sec: 9420.8, 300 sec: 9247.2). Total num frames: 6082560. Throughput: 0: 9348.1. Samples: 6073208. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-07-08 20:51:25,923][1071413] Avg episode reward: [(0, '681.233')] -[2023-07-08 20:51:27,780][1071698] Updated weights for policy 0, policy_version 11920 (0.0005) -[2023-07-08 20:51:30,923][1071413] Fps is (10 sec: 8601.5, 60 sec: 9284.3, 300 sec: 9247.2). Total num frames: 6127616. Throughput: 0: 9280.1. Samples: 6127436. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-07-08 20:51:30,923][1071413] Avg episode reward: [(0, '690.607')] -[2023-07-08 20:51:30,926][1071654] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000011968_6127616.pth... -[2023-07-08 20:51:30,929][1071654] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000011432_5853184.pth -[2023-07-08 20:51:32,413][1071698] Updated weights for policy 0, policy_version 12000 (0.0006) -[2023-07-08 20:51:35,922][1071413] Fps is (10 sec: 9011.1, 60 sec: 9216.0, 300 sec: 9247.2). Total num frames: 6172672. Throughput: 0: 9312.1. Samples: 6156004. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-07-08 20:51:35,923][1071413] Avg episode reward: [(0, '683.171')] -[2023-07-08 20:51:36,864][1071698] Updated weights for policy 0, policy_version 12080 (0.0005) -[2023-07-08 20:51:40,923][1071413] Fps is (10 sec: 9420.8, 60 sec: 9284.2, 300 sec: 9261.1). Total num frames: 6221824. Throughput: 0: 9246.0. Samples: 6209480. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-07-08 20:51:40,923][1071413] Avg episode reward: [(0, '681.029')] -[2023-07-08 20:51:41,330][1071698] Updated weights for policy 0, policy_version 12160 (0.0005) -[2023-07-08 20:51:45,697][1071698] Updated weights for policy 0, policy_version 12240 (0.0005) -[2023-07-08 20:51:45,922][1071413] Fps is (10 sec: 9420.8, 60 sec: 9284.3, 300 sec: 9261.1). Total num frames: 6266880. Throughput: 0: 9216.5. Samples: 6264512. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-07-08 20:51:45,923][1071413] Avg episode reward: [(0, '689.793')] -[2023-07-08 20:51:45,926][1071654] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000012240_6266880.pth... -[2023-07-08 20:51:45,928][1071654] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000011704_5992448.pth -[2023-07-08 20:51:50,258][1071698] Updated weights for policy 0, policy_version 12320 (0.0005) -[2023-07-08 20:51:50,922][1071413] Fps is (10 sec: 9011.3, 60 sec: 9216.0, 300 sec: 9247.2). Total num frames: 6311936. Throughput: 0: 9165.3. Samples: 6291708. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-07-08 20:51:50,923][1071413] Avg episode reward: [(0, '690.164')] -[2023-07-08 20:51:54,755][1071698] Updated weights for policy 0, policy_version 12400 (0.0006) -[2023-07-08 20:51:55,923][1071413] Fps is (10 sec: 9011.2, 60 sec: 9216.0, 300 sec: 9247.2). Total num frames: 6356992. Throughput: 0: 9098.2. Samples: 6346748. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-07-08 20:51:55,923][1071413] Avg episode reward: [(0, '687.582')] -[2023-07-08 20:51:59,455][1071698] Updated weights for policy 0, policy_version 12480 (0.0005) -[2023-07-08 20:52:00,923][1071413] Fps is (10 sec: 9011.1, 60 sec: 9147.7, 300 sec: 9247.2). Total num frames: 6402048. Throughput: 0: 9023.1. Samples: 6398168. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 20:52:00,923][1071413] Avg episode reward: [(0, '682.791')] -[2023-07-08 20:52:00,926][1071654] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000012504_6402048.pth... -[2023-07-08 20:52:00,929][1071654] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000011968_6127616.pth -[2023-07-08 20:52:04,223][1071698] Updated weights for policy 0, policy_version 12560 (0.0005) -[2023-07-08 20:52:05,923][1071413] Fps is (10 sec: 8601.5, 60 sec: 9079.4, 300 sec: 9233.4). Total num frames: 6443008. Throughput: 0: 9021.1. Samples: 6425240. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 20:52:05,923][1071413] Avg episode reward: [(0, '692.974')] -[2023-07-08 20:52:08,878][1071698] Updated weights for policy 0, policy_version 12640 (0.0005) -[2023-07-08 20:52:10,922][1071413] Fps is (10 sec: 8601.7, 60 sec: 9011.2, 300 sec: 9233.4). Total num frames: 6488064. Throughput: 0: 8954.5. Samples: 6476160. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 20:52:10,923][1071413] Avg episode reward: [(0, '685.659')] -[2023-07-08 20:52:13,542][1071698] Updated weights for policy 0, policy_version 12720 (0.0005) -[2023-07-08 20:52:15,923][1071413] Fps is (10 sec: 9011.2, 60 sec: 9011.2, 300 sec: 9233.4). Total num frames: 6533120. Throughput: 0: 8976.6. Samples: 6531384. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 20:52:15,923][1071413] Avg episode reward: [(0, '689.551')] -[2023-07-08 20:52:15,926][1071654] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000012760_6533120.pth... -[2023-07-08 20:52:15,927][1071654] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000012240_6266880.pth -[2023-07-08 20:52:17,563][1071698] Updated weights for policy 0, policy_version 12800 (0.0005) -[2023-07-08 20:52:20,922][1071413] Fps is (10 sec: 9420.8, 60 sec: 9011.2, 300 sec: 9247.2). Total num frames: 6582272. Throughput: 0: 9039.8. Samples: 6562796. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) -[2023-07-08 20:52:20,923][1071413] Avg episode reward: [(0, '689.146')] -[2023-07-08 20:52:22,206][1071698] Updated weights for policy 0, policy_version 12880 (0.0005) -[2023-07-08 20:52:25,922][1071413] Fps is (10 sec: 9420.9, 60 sec: 9079.5, 300 sec: 9247.2). Total num frames: 6627328. Throughput: 0: 9046.3. Samples: 6616564. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) -[2023-07-08 20:52:25,923][1071413] Avg episode reward: [(0, '685.236')] -[2023-07-08 20:52:26,417][1071698] Updated weights for policy 0, policy_version 12960 (0.0005) -[2023-07-08 20:52:30,511][1071698] Updated weights for policy 0, policy_version 13040 (0.0005) -[2023-07-08 20:52:30,923][1071413] Fps is (10 sec: 9830.1, 60 sec: 9216.0, 300 sec: 9288.9). Total num frames: 6680576. Throughput: 0: 9154.8. Samples: 6676480. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 20:52:30,923][1071413] Avg episode reward: [(0, '689.416')] -[2023-07-08 20:52:30,926][1071654] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000013048_6680576.pth... -[2023-07-08 20:52:30,929][1071654] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000012504_6402048.pth -[2023-07-08 20:52:34,842][1071698] Updated weights for policy 0, policy_version 13120 (0.0005) -[2023-07-08 20:52:35,923][1071413] Fps is (10 sec: 9830.2, 60 sec: 9216.0, 300 sec: 9288.9). Total num frames: 6725632. Throughput: 0: 9164.2. Samples: 6704100. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 20:52:35,923][1071413] Avg episode reward: [(0, '681.077')] -[2023-07-08 20:52:39,248][1071698] Updated weights for policy 0, policy_version 13200 (0.0005) -[2023-07-08 20:52:40,923][1071413] Fps is (10 sec: 9011.4, 60 sec: 9147.7, 300 sec: 9288.9). Total num frames: 6770688. Throughput: 0: 9201.5. Samples: 6760816. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 20:52:40,950][1071413] Avg episode reward: [(0, '687.374')] -[2023-07-08 20:52:43,798][1071698] Updated weights for policy 0, policy_version 13280 (0.0005) -[2023-07-08 20:52:45,923][1071413] Fps is (10 sec: 9011.3, 60 sec: 9147.7, 300 sec: 9275.0). Total num frames: 6815744. Throughput: 0: 9277.3. Samples: 6815648. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 20:52:46,067][1071413] Avg episode reward: [(0, '686.428')] -[2023-07-08 20:52:46,071][1071654] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000013320_6819840.pth... -[2023-07-08 20:52:46,074][1071654] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000012760_6533120.pth -[2023-07-08 20:52:48,074][1071698] Updated weights for policy 0, policy_version 13360 (0.0005) -[2023-07-08 20:52:50,922][1071413] Fps is (10 sec: 9420.9, 60 sec: 9216.0, 300 sec: 9288.9). Total num frames: 6864896. Throughput: 0: 9315.0. Samples: 6844412. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 20:52:50,959][1071413] Avg episode reward: [(0, '685.020')] -[2023-07-08 20:52:52,513][1071698] Updated weights for policy 0, policy_version 13440 (0.0005) -[2023-07-08 20:52:55,922][1071413] Fps is (10 sec: 9420.9, 60 sec: 9216.0, 300 sec: 9275.0). Total num frames: 6909952. Throughput: 0: 9410.3. Samples: 6899624. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 20:52:56,039][1071413] Avg episode reward: [(0, '683.530')] -[2023-07-08 20:52:56,883][1071698] Updated weights for policy 0, policy_version 13520 (0.0005) -[2023-07-08 20:53:00,923][1071413] Fps is (10 sec: 9011.1, 60 sec: 9216.0, 300 sec: 9261.1). Total num frames: 6955008. Throughput: 0: 9414.1. Samples: 6955020. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-07-08 20:53:00,929][1071413] Avg episode reward: [(0, '680.999')] -[2023-07-08 20:53:00,931][1071654] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000013584_6955008.pth... -[2023-07-08 20:53:00,934][1071654] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000013048_6680576.pth -[2023-07-08 20:53:01,461][1071698] Updated weights for policy 0, policy_version 13600 (0.0005) -[2023-07-08 20:53:05,922][1071413] Fps is (10 sec: 9011.2, 60 sec: 9284.3, 300 sec: 9247.2). Total num frames: 7000064. Throughput: 0: 9309.5. Samples: 6981724. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-07-08 20:53:06,033][1071698] Updated weights for policy 0, policy_version 13680 (0.0005) -[2023-07-08 20:53:06,048][1071413] Avg episode reward: [(0, '685.125')] -[2023-07-08 20:53:10,582][1071698] Updated weights for policy 0, policy_version 13760 (0.0005) -[2023-07-08 20:53:10,922][1071413] Fps is (10 sec: 9011.3, 60 sec: 9284.3, 300 sec: 9233.4). Total num frames: 7045120. Throughput: 0: 9288.1. Samples: 7034528. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-07-08 20:53:10,923][1071413] Avg episode reward: [(0, '687.992')] -[2023-07-08 20:53:15,214][1071698] Updated weights for policy 0, policy_version 13840 (0.0005) -[2023-07-08 20:53:15,923][1071413] Fps is (10 sec: 9011.1, 60 sec: 9284.3, 300 sec: 9219.5). Total num frames: 7090176. Throughput: 0: 9162.4. Samples: 7088788. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-07-08 20:53:15,924][1071413] Avg episode reward: [(0, '685.366')] -[2023-07-08 20:53:15,926][1071654] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000013848_7090176.pth... -[2023-07-08 20:53:15,929][1071654] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000013320_6819840.pth -[2023-07-08 20:53:20,046][1071698] Updated weights for policy 0, policy_version 13920 (0.0005) -[2023-07-08 20:53:20,922][1071413] Fps is (10 sec: 8601.6, 60 sec: 9147.7, 300 sec: 9191.7). Total num frames: 7131136. Throughput: 0: 9123.0. Samples: 7114632. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 20:53:20,924][1071413] Avg episode reward: [(0, '692.206')] -[2023-07-08 20:53:24,836][1071698] Updated weights for policy 0, policy_version 14000 (0.0004) -[2023-07-08 20:53:25,922][1071413] Fps is (10 sec: 8601.7, 60 sec: 9147.7, 300 sec: 9191.7). Total num frames: 7176192. Throughput: 0: 8969.9. Samples: 7164460. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 20:53:25,923][1071413] Avg episode reward: [(0, '683.987')] -[2023-07-08 20:53:29,476][1071698] Updated weights for policy 0, policy_version 14080 (0.0005) -[2023-07-08 20:53:30,922][1071413] Fps is (10 sec: 9011.2, 60 sec: 9011.2, 300 sec: 9191.7). Total num frames: 7221248. Throughput: 0: 8934.4. Samples: 7217696. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 20:53:30,923][1071413] Avg episode reward: [(0, '679.972')] -[2023-07-08 20:53:30,926][1071654] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000014104_7221248.pth... -[2023-07-08 20:53:30,930][1071654] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000013584_6955008.pth -[2023-07-08 20:53:34,138][1071698] Updated weights for policy 0, policy_version 14160 (0.0005) -[2023-07-08 20:53:35,923][1071413] Fps is (10 sec: 9011.1, 60 sec: 9011.2, 300 sec: 9177.8). Total num frames: 7266304. Throughput: 0: 8900.8. Samples: 7244948. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 20:53:35,923][1071413] Avg episode reward: [(0, '691.317')] -[2023-07-08 20:53:38,132][1071698] Updated weights for policy 0, policy_version 14240 (0.0005) -[2023-07-08 20:53:40,922][1071413] Fps is (10 sec: 9420.8, 60 sec: 9079.5, 300 sec: 9177.8). Total num frames: 7315456. Throughput: 0: 8977.1. Samples: 7303592. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 20:53:40,923][1071413] Avg episode reward: [(0, '681.587')] -[2023-07-08 20:53:42,580][1071698] Updated weights for policy 0, policy_version 14320 (0.0005) -[2023-07-08 20:53:45,923][1071413] Fps is (10 sec: 9420.8, 60 sec: 9079.5, 300 sec: 9191.7). Total num frames: 7360512. Throughput: 0: 8978.1. Samples: 7359036. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) -[2023-07-08 20:53:45,923][1071413] Avg episode reward: [(0, '688.166')] -[2023-07-08 20:53:45,927][1071654] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000014376_7360512.pth... -[2023-07-08 20:53:45,930][1071654] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000013848_7090176.pth -[2023-07-08 20:53:46,847][1071698] Updated weights for policy 0, policy_version 14400 (0.0005) -[2023-07-08 20:53:50,922][1071413] Fps is (10 sec: 9011.3, 60 sec: 9011.2, 300 sec: 9191.7). Total num frames: 7405568. Throughput: 0: 9030.6. Samples: 7388100. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) -[2023-07-08 20:53:50,923][1071413] Avg episode reward: [(0, '684.082')] -[2023-07-08 20:53:51,340][1071698] Updated weights for policy 0, policy_version 14480 (0.0005) -[2023-07-08 20:53:55,922][1071413] Fps is (10 sec: 9011.3, 60 sec: 9011.2, 300 sec: 9191.7). Total num frames: 7450624. Throughput: 0: 9059.8. Samples: 7442220. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-07-08 20:53:55,923][1071413] Avg episode reward: [(0, '692.531')] -[2023-07-08 20:53:56,061][1071698] Updated weights for policy 0, policy_version 14560 (0.0005) -[2023-07-08 20:54:00,728][1071698] Updated weights for policy 0, policy_version 14640 (0.0005) -[2023-07-08 20:54:00,923][1071413] Fps is (10 sec: 9011.1, 60 sec: 9011.2, 300 sec: 9191.7). Total num frames: 7495680. Throughput: 0: 9019.7. Samples: 7494672. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-07-08 20:54:00,923][1071413] Avg episode reward: [(0, '695.990')] -[2023-07-08 20:54:00,926][1071654] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000014640_7495680.pth... -[2023-07-08 20:54:00,929][1071654] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000014104_7221248.pth -[2023-07-08 20:54:05,191][1071698] Updated weights for policy 0, policy_version 14720 (0.0005) -[2023-07-08 20:54:05,923][1071413] Fps is (10 sec: 9011.1, 60 sec: 9011.2, 300 sec: 9191.7). Total num frames: 7540736. Throughput: 0: 9032.4. Samples: 7521092. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 20:54:05,923][1071413] Avg episode reward: [(0, '685.544')] -[2023-07-08 20:54:09,931][1071698] Updated weights for policy 0, policy_version 14800 (0.0005) -[2023-07-08 20:54:10,923][1071413] Fps is (10 sec: 9011.1, 60 sec: 9011.2, 300 sec: 9191.7). Total num frames: 7585792. Throughput: 0: 9091.4. Samples: 7573576. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 20:54:10,923][1071413] Avg episode reward: [(0, '685.954')] -[2023-07-08 20:54:14,784][1071698] Updated weights for policy 0, policy_version 14880 (0.0005) -[2023-07-08 20:54:15,923][1071413] Fps is (10 sec: 8601.6, 60 sec: 8942.9, 300 sec: 9177.8). Total num frames: 7626752. Throughput: 0: 9049.9. Samples: 7624944. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 20:54:15,923][1071413] Avg episode reward: [(0, '675.719')] -[2023-07-08 20:54:15,927][1071654] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000014896_7626752.pth... -[2023-07-08 20:54:15,929][1071654] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000014376_7360512.pth -[2023-07-08 20:54:19,252][1071698] Updated weights for policy 0, policy_version 14960 (0.0005) -[2023-07-08 20:54:20,922][1071413] Fps is (10 sec: 9011.3, 60 sec: 9079.5, 300 sec: 9191.7). Total num frames: 7675904. Throughput: 0: 9034.9. Samples: 7651520. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 20:54:20,923][1071413] Avg episode reward: [(0, '685.018')] -[2023-07-08 20:54:23,587][1071698] Updated weights for policy 0, policy_version 15040 (0.0004) -[2023-07-08 20:54:25,923][1071413] Fps is (10 sec: 9420.8, 60 sec: 9079.5, 300 sec: 9177.8). Total num frames: 7720960. Throughput: 0: 9001.9. Samples: 7708680. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-07-08 20:54:25,924][1071413] Avg episode reward: [(0, '691.063')] -[2023-07-08 20:54:28,021][1071698] Updated weights for policy 0, policy_version 15120 (0.0006) -[2023-07-08 20:54:30,923][1071413] Fps is (10 sec: 9011.1, 60 sec: 9079.5, 300 sec: 9191.7). Total num frames: 7766016. Throughput: 0: 9045.4. Samples: 7766080. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) -[2023-07-08 20:54:30,923][1071413] Avg episode reward: [(0, '680.140')] -[2023-07-08 20:54:30,928][1071654] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000015176_7770112.pth... -[2023-07-08 20:54:30,930][1071654] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000014640_7495680.pth -[2023-07-08 20:54:32,287][1071698] Updated weights for policy 0, policy_version 15200 (0.0005) -[2023-07-08 20:54:35,923][1071413] Fps is (10 sec: 9420.8, 60 sec: 9147.7, 300 sec: 9191.7). Total num frames: 7815168. Throughput: 0: 9016.4. Samples: 7793840. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-07-08 20:54:35,923][1071413] Avg episode reward: [(0, '679.722')] -[2023-07-08 20:54:36,823][1071698] Updated weights for policy 0, policy_version 15280 (0.0006) -[2023-07-08 20:54:40,922][1071413] Fps is (10 sec: 9420.9, 60 sec: 9079.5, 300 sec: 9205.6). Total num frames: 7860224. Throughput: 0: 9049.2. Samples: 7849432. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-07-08 20:54:40,923][1071413] Avg episode reward: [(0, '679.599')] -[2023-07-08 20:54:40,954][1071698] Updated weights for policy 0, policy_version 15360 (0.0005) -[2023-07-08 20:54:45,583][1071698] Updated weights for policy 0, policy_version 15440 (0.0005) -[2023-07-08 20:54:45,923][1071413] Fps is (10 sec: 9011.2, 60 sec: 9079.5, 300 sec: 9191.7). Total num frames: 7905280. Throughput: 0: 9122.9. Samples: 7905204. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-07-08 20:54:45,923][1071413] Avg episode reward: [(0, '677.652')] -[2023-07-08 20:54:45,926][1071654] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000015440_7905280.pth... -[2023-07-08 20:54:45,927][1071654] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000014896_7626752.pth -[2023-07-08 20:54:50,050][1071698] Updated weights for policy 0, policy_version 15520 (0.0004) -[2023-07-08 20:54:50,922][1071413] Fps is (10 sec: 9011.1, 60 sec: 9079.5, 300 sec: 9191.7). Total num frames: 7950336. Throughput: 0: 9162.5. Samples: 7933404. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-07-08 20:54:50,923][1071413] Avg episode reward: [(0, '686.860')] -[2023-07-08 20:54:54,759][1071698] Updated weights for policy 0, policy_version 15600 (0.0005) -[2023-07-08 20:54:55,922][1071413] Fps is (10 sec: 9011.3, 60 sec: 9079.5, 300 sec: 9177.8). Total num frames: 7995392. Throughput: 0: 9143.8. Samples: 7985044. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-07-08 20:54:55,923][1071413] Avg episode reward: [(0, '676.479')] -[2023-07-08 20:54:59,484][1071698] Updated weights for policy 0, policy_version 15680 (0.0005) -[2023-07-08 20:55:00,923][1071413] Fps is (10 sec: 8601.5, 60 sec: 9011.2, 300 sec: 9177.8). Total num frames: 8036352. Throughput: 0: 9143.8. Samples: 8036416. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-07-08 20:55:00,923][1071413] Avg episode reward: [(0, '684.880')] -[2023-07-08 20:55:00,937][1071654] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000015704_8040448.pth... -[2023-07-08 20:55:00,939][1071654] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000015176_7770112.pth -[2023-07-08 20:55:04,273][1071698] Updated weights for policy 0, policy_version 15760 (0.0006) -[2023-07-08 20:55:05,922][1071413] Fps is (10 sec: 8601.6, 60 sec: 9011.2, 300 sec: 9163.9). Total num frames: 8081408. Throughput: 0: 9113.6. Samples: 8061632. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-07-08 20:55:05,923][1071413] Avg episode reward: [(0, '679.173')] -[2023-07-08 20:55:08,776][1071698] Updated weights for policy 0, policy_version 15840 (0.0005) -[2023-07-08 20:55:10,923][1071413] Fps is (10 sec: 9011.3, 60 sec: 9011.2, 300 sec: 9163.9). Total num frames: 8126464. Throughput: 0: 9101.1. Samples: 8118228. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 20:55:10,923][1071413] Avg episode reward: [(0, '681.824')] -[2023-07-08 20:55:13,373][1071698] Updated weights for policy 0, policy_version 15920 (0.0005) -[2023-07-08 20:55:15,923][1071413] Fps is (10 sec: 9420.7, 60 sec: 9147.7, 300 sec: 9177.8). Total num frames: 8175616. Throughput: 0: 9023.5. Samples: 8172140. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 20:55:15,923][1071413] Avg episode reward: [(0, '683.361')] -[2023-07-08 20:55:15,926][1071654] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000015968_8175616.pth... -[2023-07-08 20:55:15,930][1071654] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000015440_7905280.pth -[2023-07-08 20:55:17,580][1071698] Updated weights for policy 0, policy_version 16000 (0.0005) -[2023-07-08 20:55:20,922][1071413] Fps is (10 sec: 9420.8, 60 sec: 9079.5, 300 sec: 9163.9). Total num frames: 8220672. Throughput: 0: 9031.5. Samples: 8200256. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 20:55:20,923][1071413] Avg episode reward: [(0, '684.314')] -[2023-07-08 20:55:22,002][1071698] Updated weights for policy 0, policy_version 16080 (0.0005) -[2023-07-08 20:55:25,923][1071413] Fps is (10 sec: 9011.3, 60 sec: 9079.5, 300 sec: 9136.2). Total num frames: 8265728. Throughput: 0: 9035.7. Samples: 8256040. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) -[2023-07-08 20:55:25,923][1071413] Avg episode reward: [(0, '692.609')] -[2023-07-08 20:55:26,521][1071698] Updated weights for policy 0, policy_version 16160 (0.0004) -[2023-07-08 20:55:30,922][1071413] Fps is (10 sec: 9011.2, 60 sec: 9079.5, 300 sec: 9122.3). Total num frames: 8310784. Throughput: 0: 9012.2. Samples: 8310752. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) -[2023-07-08 20:55:30,923][1071413] Avg episode reward: [(0, '686.628')] -[2023-07-08 20:55:30,925][1071654] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000016232_8310784.pth... -[2023-07-08 20:55:30,928][1071654] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000015704_8040448.pth -[2023-07-08 20:55:30,985][1071698] Updated weights for policy 0, policy_version 16240 (0.0005) -[2023-07-08 20:55:35,684][1071698] Updated weights for policy 0, policy_version 16320 (0.0005) -[2023-07-08 20:55:35,922][1071413] Fps is (10 sec: 9011.3, 60 sec: 9011.2, 300 sec: 9122.3). Total num frames: 8355840. Throughput: 0: 8969.2. Samples: 8337016. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-07-08 20:55:35,923][1071413] Avg episode reward: [(0, '685.565')] -[2023-07-08 20:55:39,910][1071698] Updated weights for policy 0, policy_version 16400 (0.0005) -[2023-07-08 20:55:40,923][1071413] Fps is (10 sec: 9420.7, 60 sec: 9079.4, 300 sec: 9136.2). Total num frames: 8404992. Throughput: 0: 9038.2. Samples: 8391764. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-07-08 20:55:40,923][1071413] Avg episode reward: [(0, '674.973')] -[2023-07-08 20:55:44,690][1071698] Updated weights for policy 0, policy_version 16480 (0.0005) -[2023-07-08 20:55:45,922][1071413] Fps is (10 sec: 9420.8, 60 sec: 9079.5, 300 sec: 9122.3). Total num frames: 8450048. Throughput: 0: 9102.4. Samples: 8446024. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) -[2023-07-08 20:55:45,923][1071413] Avg episode reward: [(0, '687.196')] -[2023-07-08 20:55:45,926][1071654] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000016504_8450048.pth... -[2023-07-08 20:55:45,929][1071654] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000015968_8175616.pth -[2023-07-08 20:55:48,817][1071698] Updated weights for policy 0, policy_version 16560 (0.0005) -[2023-07-08 20:55:50,922][1071413] Fps is (10 sec: 9011.3, 60 sec: 9079.5, 300 sec: 9122.3). Total num frames: 8495104. Throughput: 0: 9206.8. Samples: 8475940. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) -[2023-07-08 20:55:50,923][1071413] Avg episode reward: [(0, '684.411')] -[2023-07-08 20:55:53,574][1071698] Updated weights for policy 0, policy_version 16640 (0.0005) -[2023-07-08 20:55:55,922][1071413] Fps is (10 sec: 9011.2, 60 sec: 9079.5, 300 sec: 9108.4). Total num frames: 8540160. Throughput: 0: 9098.0. Samples: 8527636. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) -[2023-07-08 20:55:55,923][1071413] Avg episode reward: [(0, '687.817')] -[2023-07-08 20:55:58,044][1071698] Updated weights for policy 0, policy_version 16720 (0.0005) -[2023-07-08 20:56:00,922][1071413] Fps is (10 sec: 9011.2, 60 sec: 9147.8, 300 sec: 9108.4). Total num frames: 8585216. Throughput: 0: 9090.1. Samples: 8581192. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 20:56:00,923][1071413] Avg episode reward: [(0, '687.767')] -[2023-07-08 20:56:00,925][1071654] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000016768_8585216.pth... -[2023-07-08 20:56:00,929][1071654] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000016232_8310784.pth -[2023-07-08 20:56:02,656][1071698] Updated weights for policy 0, policy_version 16800 (0.0005) -[2023-07-08 20:56:05,922][1071413] Fps is (10 sec: 8601.6, 60 sec: 9079.5, 300 sec: 9080.6). Total num frames: 8626176. Throughput: 0: 9096.2. Samples: 8609584. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 20:56:05,923][1071413] Avg episode reward: [(0, '683.368')] -[2023-07-08 20:56:07,374][1071698] Updated weights for policy 0, policy_version 16880 (0.0005) -[2023-07-08 20:56:10,923][1071413] Fps is (10 sec: 9011.1, 60 sec: 9147.7, 300 sec: 9094.5). Total num frames: 8675328. Throughput: 0: 9033.6. Samples: 8662552. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) -[2023-07-08 20:56:10,923][1071413] Avg episode reward: [(0, '684.144')] -[2023-07-08 20:56:11,845][1071698] Updated weights for policy 0, policy_version 16960 (0.0005) -[2023-07-08 20:56:15,923][1071413] Fps is (10 sec: 9420.6, 60 sec: 9079.4, 300 sec: 9080.6). Total num frames: 8720384. Throughput: 0: 9027.9. Samples: 8717012. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) -[2023-07-08 20:56:15,923][1071413] Avg episode reward: [(0, '683.518')] -[2023-07-08 20:56:15,927][1071654] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000017032_8720384.pth... -[2023-07-08 20:56:15,931][1071654] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000016504_8450048.pth -[2023-07-08 20:56:16,332][1071698] Updated weights for policy 0, policy_version 17040 (0.0005) -[2023-07-08 20:56:20,743][1071698] Updated weights for policy 0, policy_version 17120 (0.0005) -[2023-07-08 20:56:20,923][1071413] Fps is (10 sec: 9011.2, 60 sec: 9079.5, 300 sec: 9094.5). Total num frames: 8765440. Throughput: 0: 9053.9. Samples: 8744444. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 20:56:20,923][1071413] Avg episode reward: [(0, '678.224')] -[2023-07-08 20:56:25,428][1071698] Updated weights for policy 0, policy_version 17200 (0.0005) -[2023-07-08 20:56:25,922][1071413] Fps is (10 sec: 8601.8, 60 sec: 9011.2, 300 sec: 9080.6). Total num frames: 8806400. Throughput: 0: 9027.6. Samples: 8798004. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 20:56:25,923][1071413] Avg episode reward: [(0, '680.799')] -[2023-07-08 20:56:30,259][1071698] Updated weights for policy 0, policy_version 17280 (0.0005) -[2023-07-08 20:56:30,922][1071413] Fps is (10 sec: 8601.6, 60 sec: 9011.2, 300 sec: 9080.6). Total num frames: 8851456. Throughput: 0: 8966.4. Samples: 8849512. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 20:56:30,923][1071413] Avg episode reward: [(0, '680.420')] -[2023-07-08 20:56:30,926][1071654] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000017288_8851456.pth... -[2023-07-08 20:56:30,929][1071654] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000016768_8585216.pth -[2023-07-08 20:56:34,962][1071698] Updated weights for policy 0, policy_version 17360 (0.0005) -[2023-07-08 20:56:35,923][1071413] Fps is (10 sec: 8601.5, 60 sec: 8942.9, 300 sec: 9052.9). Total num frames: 8892416. Throughput: 0: 8865.1. Samples: 8874872. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 20:56:35,924][1071413] Avg episode reward: [(0, '692.233')] -[2023-07-08 20:56:39,717][1071698] Updated weights for policy 0, policy_version 17440 (0.0005) -[2023-07-08 20:56:40,922][1071413] Fps is (10 sec: 8601.6, 60 sec: 8874.7, 300 sec: 9052.9). Total num frames: 8937472. Throughput: 0: 8887.5. Samples: 8927572. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 20:56:40,923][1071413] Avg episode reward: [(0, '688.446')] -[2023-07-08 20:56:44,433][1071698] Updated weights for policy 0, policy_version 17520 (0.0005) -[2023-07-08 20:56:45,922][1071413] Fps is (10 sec: 9011.2, 60 sec: 8874.7, 300 sec: 9052.9). Total num frames: 8982528. Throughput: 0: 8880.7. Samples: 8980824. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 20:56:45,923][1071413] Avg episode reward: [(0, '680.623')] -[2023-07-08 20:56:45,927][1071654] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000017544_8982528.pth... -[2023-07-08 20:56:45,929][1071654] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000017032_8720384.pth -[2023-07-08 20:56:49,022][1071698] Updated weights for policy 0, policy_version 17600 (0.0005) -[2023-07-08 20:56:50,922][1071413] Fps is (10 sec: 8601.7, 60 sec: 8806.4, 300 sec: 9039.0). Total num frames: 9023488. Throughput: 0: 8828.5. Samples: 9006864. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 20:56:50,923][1071413] Avg episode reward: [(0, '682.257')] -[2023-07-08 20:56:53,643][1071698] Updated weights for policy 0, policy_version 17680 (0.0005) -[2023-07-08 20:56:55,922][1071413] Fps is (10 sec: 8601.6, 60 sec: 8806.4, 300 sec: 9039.0). Total num frames: 9068544. Throughput: 0: 8833.6. Samples: 9060064. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 20:56:55,923][1071413] Avg episode reward: [(0, '683.476')] -[2023-07-08 20:56:58,246][1071698] Updated weights for policy 0, policy_version 17760 (0.0005) -[2023-07-08 20:57:00,922][1071413] Fps is (10 sec: 9420.7, 60 sec: 8874.7, 300 sec: 9066.7). Total num frames: 9117696. Throughput: 0: 8814.7. Samples: 9113672. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-07-08 20:57:00,923][1071413] Avg episode reward: [(0, '694.676')] -[2023-07-08 20:57:00,926][1071654] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000017808_9117696.pth... -[2023-07-08 20:57:00,929][1071654] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000017288_8851456.pth -[2023-07-08 20:57:02,547][1071698] Updated weights for policy 0, policy_version 17840 (0.0005) -[2023-07-08 20:57:05,922][1071413] Fps is (10 sec: 9420.8, 60 sec: 8942.9, 300 sec: 9066.7). Total num frames: 9162752. Throughput: 0: 8847.9. Samples: 9142600. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) -[2023-07-08 20:57:05,924][1071413] Avg episode reward: [(0, '687.071')] -[2023-07-08 20:57:07,006][1071698] Updated weights for policy 0, policy_version 17920 (0.0006) -[2023-07-08 20:57:10,922][1071413] Fps is (10 sec: 9011.2, 60 sec: 8874.7, 300 sec: 9066.7). Total num frames: 9207808. Throughput: 0: 8835.3. Samples: 9195592. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 20:57:10,923][1071413] Avg episode reward: [(0, '684.090')] -[2023-07-08 20:57:11,783][1071698] Updated weights for policy 0, policy_version 18000 (0.0005) -[2023-07-08 20:57:15,923][1071413] Fps is (10 sec: 8601.5, 60 sec: 8806.4, 300 sec: 9039.0). Total num frames: 9248768. Throughput: 0: 8864.5. Samples: 9248416. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 20:57:15,923][1071413] Avg episode reward: [(0, '681.552')] -[2023-07-08 20:57:15,926][1071654] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000018064_9248768.pth... -[2023-07-08 20:57:15,928][1071654] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000017544_8982528.pth -[2023-07-08 20:57:16,435][1071698] Updated weights for policy 0, policy_version 18080 (0.0005) -[2023-07-08 20:57:20,922][1071413] Fps is (10 sec: 8601.6, 60 sec: 8806.4, 300 sec: 9039.0). Total num frames: 9293824. Throughput: 0: 8912.8. Samples: 9275948. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 20:57:20,923][1071413] Avg episode reward: [(0, '680.353')] -[2023-07-08 20:57:21,048][1071698] Updated weights for policy 0, policy_version 18160 (0.0005) -[2023-07-08 20:57:25,335][1071698] Updated weights for policy 0, policy_version 18240 (0.0005) -[2023-07-08 20:57:25,922][1071413] Fps is (10 sec: 9420.9, 60 sec: 8942.9, 300 sec: 9025.1). Total num frames: 9342976. Throughput: 0: 8989.9. Samples: 9332116. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) -[2023-07-08 20:57:25,924][1071413] Avg episode reward: [(0, '692.095')] -[2023-07-08 20:57:30,057][1071698] Updated weights for policy 0, policy_version 18320 (0.0004) -[2023-07-08 20:57:30,922][1071413] Fps is (10 sec: 9420.7, 60 sec: 8942.9, 300 sec: 9025.1). Total num frames: 9388032. Throughput: 0: 8965.3. Samples: 9384264. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) -[2023-07-08 20:57:30,923][1071413] Avg episode reward: [(0, '685.494')] -[2023-07-08 20:57:30,927][1071654] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000018336_9388032.pth... -[2023-07-08 20:57:30,929][1071654] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000017808_9117696.pth -[2023-07-08 20:57:34,375][1071698] Updated weights for policy 0, policy_version 18400 (0.0005) -[2023-07-08 20:57:35,923][1071413] Fps is (10 sec: 9011.2, 60 sec: 9011.2, 300 sec: 9025.1). Total num frames: 9433088. Throughput: 0: 9020.2. Samples: 9412776. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) -[2023-07-08 20:57:35,924][1071413] Avg episode reward: [(0, '686.504')] -[2023-07-08 20:57:39,023][1071698] Updated weights for policy 0, policy_version 18480 (0.0006) -[2023-07-08 20:57:40,922][1071413] Fps is (10 sec: 8601.6, 60 sec: 8942.9, 300 sec: 9011.2). Total num frames: 9474048. Throughput: 0: 9017.4. Samples: 9465848. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 20:57:40,923][1071413] Avg episode reward: [(0, '692.981')] -[2023-07-08 20:57:43,600][1071698] Updated weights for policy 0, policy_version 18560 (0.0006) -[2023-07-08 20:57:45,923][1071413] Fps is (10 sec: 9011.2, 60 sec: 9011.2, 300 sec: 9011.2). Total num frames: 9523200. Throughput: 0: 9026.8. Samples: 9519880. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 20:57:45,923][1071413] Avg episode reward: [(0, '690.827')] -[2023-07-08 20:57:45,926][1071654] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000018600_9523200.pth... -[2023-07-08 20:57:45,929][1071654] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000018064_9248768.pth -[2023-07-08 20:57:48,001][1071698] Updated weights for policy 0, policy_version 18640 (0.0005) -[2023-07-08 20:57:50,922][1071413] Fps is (10 sec: 9420.9, 60 sec: 9079.5, 300 sec: 9011.2). Total num frames: 9568256. Throughput: 0: 9005.6. Samples: 9547852. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 20:57:50,923][1071413] Avg episode reward: [(0, '688.940')] -[2023-07-08 20:57:52,665][1071698] Updated weights for policy 0, policy_version 18720 (0.0006) -[2023-07-08 20:57:55,922][1071413] Fps is (10 sec: 9011.3, 60 sec: 9079.5, 300 sec: 9011.2). Total num frames: 9613312. Throughput: 0: 9034.3. Samples: 9602136. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 20:57:55,923][1071413] Avg episode reward: [(0, '694.044')] -[2023-07-08 20:57:57,067][1071698] Updated weights for policy 0, policy_version 18800 (0.0005) -[2023-07-08 20:58:00,922][1071413] Fps is (10 sec: 9011.2, 60 sec: 9011.2, 300 sec: 9011.2). Total num frames: 9658368. Throughput: 0: 9108.2. Samples: 9658284. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 20:58:00,923][1071413] Avg episode reward: [(0, '692.440')] -[2023-07-08 20:58:00,926][1071654] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000018864_9658368.pth... -[2023-07-08 20:58:00,929][1071654] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000018336_9388032.pth -[2023-07-08 20:58:01,533][1071698] Updated weights for policy 0, policy_version 18880 (0.0005) -[2023-07-08 20:58:05,923][1071413] Fps is (10 sec: 8601.5, 60 sec: 8942.9, 300 sec: 8997.3). Total num frames: 9699328. Throughput: 0: 9045.8. Samples: 9683008. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 20:58:05,923][1071413] Avg episode reward: [(0, '696.834')] -[2023-07-08 20:58:05,957][1071654] Saving new best policy, reward=696.834! -[2023-07-08 20:58:06,351][1071698] Updated weights for policy 0, policy_version 18960 (0.0005) -[2023-07-08 20:58:10,922][1071413] Fps is (10 sec: 8601.6, 60 sec: 8942.9, 300 sec: 8997.3). Total num frames: 9744384. Throughput: 0: 8950.9. Samples: 9734904. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) -[2023-07-08 20:58:10,923][1071413] Avg episode reward: [(0, '688.184')] -[2023-07-08 20:58:11,041][1071698] Updated weights for policy 0, policy_version 19040 (0.0005) -[2023-07-08 20:58:15,807][1071698] Updated weights for policy 0, policy_version 19120 (0.0005) -[2023-07-08 20:58:15,923][1071413] Fps is (10 sec: 9011.2, 60 sec: 9011.2, 300 sec: 9011.2). Total num frames: 9789440. Throughput: 0: 8956.7. Samples: 9787316. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-07-08 20:58:15,923][1071413] Avg episode reward: [(0, '673.436')] -[2023-07-08 20:58:15,926][1071654] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000019120_9789440.pth... -[2023-07-08 20:58:15,929][1071654] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000018600_9523200.pth -[2023-07-08 20:58:20,301][1071698] Updated weights for policy 0, policy_version 19200 (0.0005) -[2023-07-08 20:58:20,922][1071413] Fps is (10 sec: 9011.1, 60 sec: 9011.2, 300 sec: 9011.2). Total num frames: 9834496. Throughput: 0: 8916.8. Samples: 9814032. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-07-08 20:58:20,923][1071413] Avg episode reward: [(0, '686.645')] -[2023-07-08 20:58:24,944][1071698] Updated weights for policy 0, policy_version 19280 (0.0005) -[2023-07-08 20:58:25,922][1071413] Fps is (10 sec: 9011.4, 60 sec: 8942.9, 300 sec: 9011.2). Total num frames: 9879552. Throughput: 0: 8921.8. Samples: 9867328. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) -[2023-07-08 20:58:25,933][1071413] Avg episode reward: [(0, '687.858')] -[2023-07-08 20:58:29,950][1071698] Updated weights for policy 0, policy_version 19360 (0.0005) -[2023-07-08 20:58:30,923][1071413] Fps is (10 sec: 8601.5, 60 sec: 8874.7, 300 sec: 8997.3). Total num frames: 9920512. Throughput: 0: 8813.5. Samples: 9916488. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-07-08 20:58:30,924][1071413] Avg episode reward: [(0, '682.162')] -[2023-07-08 20:58:30,926][1071654] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000019376_9920512.pth... -[2023-07-08 20:58:30,929][1071654] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000018864_9658368.pth -[2023-07-08 20:58:34,277][1071698] Updated weights for policy 0, policy_version 19440 (0.0005) -[2023-07-08 20:58:35,923][1071413] Fps is (10 sec: 8601.5, 60 sec: 8874.7, 300 sec: 8983.4). Total num frames: 9965568. Throughput: 0: 8828.9. Samples: 9945152. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) -[2023-07-08 20:58:35,924][1071413] Avg episode reward: [(0, '678.870')] -[2023-07-08 20:58:38,667][1071698] Updated weights for policy 0, policy_version 19520 (0.0005) -[2023-07-08 20:58:39,969][1071654] Early stopping after 2 epochs (8 sgd steps), loss delta 0.0000000 -[2023-07-08 20:58:39,970][1071734] Stopping RolloutWorker_w4... -[2023-07-08 20:58:39,970][1071699] Stopping RolloutWorker_w1... -[2023-07-08 20:58:39,970][1071766] Stopping RolloutWorker_w5... -[2023-07-08 20:58:39,970][1071798] Stopping RolloutWorker_w6... -[2023-07-08 20:58:39,970][1071702] Stopping RolloutWorker_w3... -[2023-07-08 20:58:39,970][1071830] Stopping RolloutWorker_w7... -[2023-07-08 20:58:39,970][1071699] Loop rollout_proc1_evt_loop terminating... -[2023-07-08 20:58:39,970][1071734] Loop rollout_proc4_evt_loop terminating... -[2023-07-08 20:58:39,970][1071701] Stopping RolloutWorker_w2... -[2023-07-08 20:58:39,970][1071798] Loop rollout_proc6_evt_loop terminating... -[2023-07-08 20:58:39,970][1071766] Loop rollout_proc5_evt_loop terminating... -[2023-07-08 20:58:39,970][1071700] Stopping RolloutWorker_w0... -[2023-07-08 20:58:39,970][1071702] Loop rollout_proc3_evt_loop terminating... -[2023-07-08 20:58:39,971][1071830] Loop rollout_proc7_evt_loop terminating... -[2023-07-08 20:58:39,970][1071413] Component RolloutWorker_w4 stopped! -[2023-07-08 20:58:39,971][1071701] Loop rollout_proc2_evt_loop terminating... -[2023-07-08 20:58:39,971][1071700] Loop rollout_proc0_evt_loop terminating... -[2023-07-08 20:58:39,971][1071413] Component RolloutWorker_w1 stopped! -[2023-07-08 20:58:39,971][1071654] Stopping Batcher_0... -[2023-07-08 20:58:39,971][1071413] Component RolloutWorker_w5 stopped! -[2023-07-08 20:58:39,971][1071654] Loop batcher_evt_loop terminating... -[2023-07-08 20:58:39,971][1071413] Component RolloutWorker_w6 stopped! -[2023-07-08 20:58:39,971][1071413] Component RolloutWorker_w3 stopped! -[2023-07-08 20:58:39,972][1071413] Component RolloutWorker_w2 stopped! -[2023-07-08 20:58:39,972][1071654] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000019544_10006528.pth... -[2023-07-08 20:58:39,972][1071413] Component RolloutWorker_w7 stopped! -[2023-07-08 20:58:39,972][1071413] Component RolloutWorker_w0 stopped! -[2023-07-08 20:58:39,972][1071413] Component Batcher_0 stopped! -[2023-07-08 20:58:39,974][1071654] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000019120_9789440.pth -[2023-07-08 20:58:39,975][1071654] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000019544_10006528.pth... -[2023-07-08 20:58:39,977][1071654] Stopping LearnerWorker_p0... -[2023-07-08 20:58:39,978][1071654] Loop learner_proc0_evt_loop terminating... -[2023-07-08 20:58:39,978][1071413] Component LearnerWorker_p0 stopped! -[2023-07-08 20:58:40,050][1071698] Weights refcount: 2 0 -[2023-07-08 20:58:40,051][1071698] Stopping InferenceWorker_p0-w0... -[2023-07-08 20:58:40,051][1071698] Loop inference_proc0-0_evt_loop terminating... -[2023-07-08 20:58:40,051][1071413] Component InferenceWorker_p0-w0 stopped! -[2023-07-08 20:58:40,052][1071413] Waiting for process learner_proc0 to stop... -[2023-07-08 20:58:40,686][1071413] Waiting for process inference_proc0-0 to join... -[2023-07-08 20:58:40,687][1071413] Waiting for process rollout_proc0 to join... -[2023-07-08 20:58:40,687][1071413] Waiting for process rollout_proc1 to join... -[2023-07-08 20:58:40,688][1071413] Waiting for process rollout_proc2 to join... -[2023-07-08 20:58:40,688][1071413] Waiting for process rollout_proc3 to join... -[2023-07-08 20:58:40,688][1071413] Waiting for process rollout_proc4 to join... -[2023-07-08 20:58:40,688][1071413] Waiting for process rollout_proc5 to join... -[2023-07-08 20:58:40,689][1071413] Waiting for process rollout_proc6 to join... -[2023-07-08 20:58:40,689][1071413] Waiting for process rollout_proc7 to join... -[2023-07-08 20:58:40,689][1071413] Batcher 0 profile tree view: -batching: 1.8109, releasing_batches: 1.5500 -[2023-07-08 20:58:40,689][1071413] InferenceWorker_p0-w0 profile tree view: +[2023-07-17 00:58:50,102][282843] Worker 5 uses CPU cores [20, 21, 22, 23] +[2023-07-17 00:58:50,185][282938] Worker 7 uses CPU cores [28, 29, 30, 31] +[2023-07-17 00:58:50,353][282793] Using optimizer +[2023-07-17 00:58:50,354][282793] No checkpoints found +[2023-07-17 00:58:50,354][282793] Did not load from checkpoint, starting from scratch! +[2023-07-17 00:58:50,354][282793] Initialized policy 0 weights for model version 0 +[2023-07-17 00:58:50,355][282793] LearnerWorker_p0 finished initialization! +[2023-07-17 00:58:50,395][282841] Worker 0 uses CPU cores [0, 1, 2, 3] +[2023-07-17 00:58:50,409][282842] Worker 4 uses CPU cores [16, 17, 18, 19] +[2023-07-17 00:58:50,429][282906] Worker 6 uses CPU cores [24, 25, 26, 27] +[2023-07-17 00:58:50,618][282837] RunningMeanStd input shape: (39,) +[2023-07-17 00:58:50,619][282837] RunningMeanStd input shape: (1,) +[2023-07-17 00:58:50,656][282840] Worker 2 uses CPU cores [8, 9, 10, 11] +[2023-07-17 00:58:50,673][282552] Inference worker 0-0 is ready! +[2023-07-17 00:58:50,674][282552] All inference workers are ready! Signal rollout workers to start! +[2023-07-17 00:58:50,790][282839] Worker 3 uses CPU cores [12, 13, 14, 15] +[2023-07-17 00:58:51,076][282552] Fps is (10 sec: nan, 60 sec: nan, 300 sec: nan). Total num frames: 0. Throughput: 0: nan. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) +[2023-07-17 00:58:52,124][282841] Decorrelating experience for 0 frames... +[2023-07-17 00:58:52,131][282841] Decorrelating experience for 64 frames... +[2023-07-17 00:58:52,137][282842] Decorrelating experience for 0 frames... +[2023-07-17 00:58:52,144][282842] Decorrelating experience for 64 frames... +[2023-07-17 00:58:52,160][282841] Decorrelating experience for 128 frames... +[2023-07-17 00:58:52,173][282842] Decorrelating experience for 128 frames... +[2023-07-17 00:58:52,180][282938] Decorrelating experience for 0 frames... +[2023-07-17 00:58:52,182][282843] Decorrelating experience for 0 frames... +[2023-07-17 00:58:52,183][282838] Decorrelating experience for 0 frames... +[2023-07-17 00:58:52,184][282906] Decorrelating experience for 0 frames... +[2023-07-17 00:58:52,185][282840] Decorrelating experience for 0 frames... +[2023-07-17 00:58:52,188][282938] Decorrelating experience for 64 frames... +[2023-07-17 00:58:52,189][282843] Decorrelating experience for 64 frames... +[2023-07-17 00:58:52,190][282838] Decorrelating experience for 64 frames... +[2023-07-17 00:58:52,191][282906] Decorrelating experience for 64 frames... +[2023-07-17 00:58:52,192][282840] Decorrelating experience for 64 frames... +[2023-07-17 00:58:52,215][282841] Decorrelating experience for 192 frames... +[2023-07-17 00:58:52,216][282938] Decorrelating experience for 128 frames... +[2023-07-17 00:58:52,218][282838] Decorrelating experience for 128 frames... +[2023-07-17 00:58:52,218][282843] Decorrelating experience for 128 frames... +[2023-07-17 00:58:52,219][282906] Decorrelating experience for 128 frames... +[2023-07-17 00:58:52,221][282840] Decorrelating experience for 128 frames... +[2023-07-17 00:58:52,229][282842] Decorrelating experience for 192 frames... +[2023-07-17 00:58:52,271][282938] Decorrelating experience for 192 frames... +[2023-07-17 00:58:52,274][282843] Decorrelating experience for 192 frames... +[2023-07-17 00:58:52,274][282906] Decorrelating experience for 192 frames... +[2023-07-17 00:58:52,275][282838] Decorrelating experience for 192 frames... +[2023-07-17 00:58:52,275][282840] Decorrelating experience for 192 frames... +[2023-07-17 00:58:52,308][282839] Decorrelating experience for 0 frames... +[2023-07-17 00:58:52,315][282839] Decorrelating experience for 64 frames... +[2023-07-17 00:58:52,344][282839] Decorrelating experience for 128 frames... +[2023-07-17 00:58:52,400][282839] Decorrelating experience for 192 frames... +[2023-07-17 00:58:53,629][282841] Decorrelating experience for 256 frames... +[2023-07-17 00:58:53,642][282842] Decorrelating experience for 256 frames... +[2023-07-17 00:58:53,709][282843] Decorrelating experience for 256 frames... +[2023-07-17 00:58:53,714][282838] Decorrelating experience for 256 frames... +[2023-07-17 00:58:53,732][282840] Decorrelating experience for 256 frames... +[2023-07-17 00:58:53,733][282841] Decorrelating experience for 320 frames... +[2023-07-17 00:58:53,735][282938] Decorrelating experience for 256 frames... +[2023-07-17 00:58:53,738][282906] Decorrelating experience for 256 frames... +[2023-07-17 00:58:53,747][282842] Decorrelating experience for 320 frames... +[2023-07-17 00:58:53,812][282843] Decorrelating experience for 320 frames... +[2023-07-17 00:58:53,818][282838] Decorrelating experience for 320 frames... +[2023-07-17 00:58:53,838][282840] Decorrelating experience for 320 frames... +[2023-07-17 00:58:53,841][282938] Decorrelating experience for 320 frames... +[2023-07-17 00:58:53,842][282906] Decorrelating experience for 320 frames... +[2023-07-17 00:58:53,849][282839] Decorrelating experience for 256 frames... +[2023-07-17 00:58:53,863][282841] Decorrelating experience for 384 frames... +[2023-07-17 00:58:53,879][282842] Decorrelating experience for 384 frames... +[2023-07-17 00:58:53,943][282843] Decorrelating experience for 384 frames... +[2023-07-17 00:58:53,949][282838] Decorrelating experience for 384 frames... +[2023-07-17 00:58:53,954][282839] Decorrelating experience for 320 frames... +[2023-07-17 00:58:53,970][282840] Decorrelating experience for 384 frames... +[2023-07-17 00:58:53,972][282938] Decorrelating experience for 384 frames... +[2023-07-17 00:58:53,975][282906] Decorrelating experience for 384 frames... +[2023-07-17 00:58:54,015][282841] Decorrelating experience for 448 frames... +[2023-07-17 00:58:54,033][282842] Decorrelating experience for 448 frames... +[2023-07-17 00:58:54,092][282839] Decorrelating experience for 384 frames... +[2023-07-17 00:58:54,097][282843] Decorrelating experience for 448 frames... +[2023-07-17 00:58:54,105][282838] Decorrelating experience for 448 frames... +[2023-07-17 00:58:54,124][282840] Decorrelating experience for 448 frames... +[2023-07-17 00:58:54,124][282938] Decorrelating experience for 448 frames... +[2023-07-17 00:58:54,127][282906] Decorrelating experience for 448 frames... +[2023-07-17 00:58:54,246][282839] Decorrelating experience for 448 frames... +[2023-07-17 00:58:56,076][282552] Fps is (10 sec: 2457.6, 60 sec: 2457.6, 300 sec: 2457.6). Total num frames: 12288. Throughput: 0: 0.0. Samples: 0. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) +[2023-07-17 00:58:56,076][282552] Avg episode reward: [(0, '18.035')] +[2023-07-17 00:58:58,205][282837] Updated weights for policy 0, policy_version 80 (0.0005) +[2023-07-17 00:59:01,076][282552] Fps is (10 sec: 7782.4, 60 sec: 7782.4, 300 sec: 7782.4). Total num frames: 77824. Throughput: 0: 6127.6. Samples: 61276. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 00:59:01,076][282552] Avg episode reward: [(0, '152.908')] +[2023-07-17 00:59:01,079][282793] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000000152_77824.pth... +[2023-07-17 00:59:01,263][282837] Updated weights for policy 0, policy_version 160 (0.0004) +[2023-07-17 00:59:04,330][282837] Updated weights for policy 0, policy_version 240 (0.0004) +[2023-07-17 00:59:06,076][282552] Fps is (10 sec: 13516.7, 60 sec: 9830.4, 300 sec: 9830.4). Total num frames: 147456. Throughput: 0: 9468.3. Samples: 142024. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 00:59:06,076][282552] Avg episode reward: [(0, '282.163')] +[2023-07-17 00:59:06,077][282793] Saving new best policy, reward=282.163! +[2023-07-17 00:59:07,261][282837] Updated weights for policy 0, policy_version 320 (0.0004) +[2023-07-17 00:59:08,089][282552] Heartbeat connected on Batcher_0 +[2023-07-17 00:59:08,091][282552] Heartbeat connected on LearnerWorker_p0 +[2023-07-17 00:59:08,095][282552] Heartbeat connected on InferenceWorker_p0-w0 +[2023-07-17 00:59:08,099][282552] Heartbeat connected on RolloutWorker_w0 +[2023-07-17 00:59:08,100][282552] Heartbeat connected on RolloutWorker_w1 +[2023-07-17 00:59:08,102][282552] Heartbeat connected on RolloutWorker_w2 +[2023-07-17 00:59:08,104][282552] Heartbeat connected on RolloutWorker_w3 +[2023-07-17 00:59:08,107][282552] Heartbeat connected on RolloutWorker_w4 +[2023-07-17 00:59:08,108][282552] Heartbeat connected on RolloutWorker_w5 +[2023-07-17 00:59:08,110][282552] Heartbeat connected on RolloutWorker_w6 +[2023-07-17 00:59:08,112][282552] Heartbeat connected on RolloutWorker_w7 +[2023-07-17 00:59:10,366][282837] Updated weights for policy 0, policy_version 400 (0.0005) +[2023-07-17 00:59:11,076][282552] Fps is (10 sec: 13516.9, 60 sec: 10649.6, 300 sec: 10649.6). Total num frames: 212992. Throughput: 0: 9142.4. Samples: 182848. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 00:59:11,076][282552] Avg episode reward: [(0, '324.557')] +[2023-07-17 00:59:11,077][282793] Saving new best policy, reward=324.557! +[2023-07-17 00:59:13,525][282837] Updated weights for policy 0, policy_version 480 (0.0005) +[2023-07-17 00:59:16,076][282552] Fps is (10 sec: 13107.2, 60 sec: 11141.1, 300 sec: 11141.1). Total num frames: 278528. Throughput: 0: 10464.3. Samples: 261608. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 00:59:16,076][282552] Avg episode reward: [(0, '328.300')] +[2023-07-17 00:59:16,079][282793] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000000544_278528.pth... +[2023-07-17 00:59:16,082][282793] Saving new best policy, reward=328.300! +[2023-07-17 00:59:16,564][282837] Updated weights for policy 0, policy_version 560 (0.0005) +[2023-07-17 00:59:19,714][282837] Updated weights for policy 0, policy_version 640 (0.0005) +[2023-07-17 00:59:21,076][282552] Fps is (10 sec: 13107.2, 60 sec: 11468.8, 300 sec: 11468.8). Total num frames: 344064. Throughput: 0: 11332.6. Samples: 339976. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) +[2023-07-17 00:59:21,077][282552] Avg episode reward: [(0, '337.254')] +[2023-07-17 00:59:21,077][282793] Saving new best policy, reward=337.254! +[2023-07-17 00:59:22,907][282837] Updated weights for policy 0, policy_version 720 (0.0005) +[2023-07-17 00:59:26,076][282552] Fps is (10 sec: 12697.7, 60 sec: 11585.9, 300 sec: 11585.9). Total num frames: 405504. Throughput: 0: 10790.3. Samples: 377660. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) +[2023-07-17 00:59:26,096][282552] Avg episode reward: [(0, '341.021')] +[2023-07-17 00:59:26,096][282793] Saving new best policy, reward=341.021! +[2023-07-17 00:59:26,186][282837] Updated weights for policy 0, policy_version 800 (0.0005) +[2023-07-17 00:59:29,395][282837] Updated weights for policy 0, policy_version 880 (0.0005) +[2023-07-17 00:59:31,076][282552] Fps is (10 sec: 12287.9, 60 sec: 11673.6, 300 sec: 11673.6). Total num frames: 466944. Throughput: 0: 11366.7. Samples: 454668. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 00:59:31,077][282552] Avg episode reward: [(0, '348.446')] +[2023-07-17 00:59:31,079][282793] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000000920_471040.pth... +[2023-07-17 00:59:31,082][282793] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000000152_77824.pth +[2023-07-17 00:59:31,082][282793] Saving new best policy, reward=348.446! +[2023-07-17 00:59:32,716][282837] Updated weights for policy 0, policy_version 960 (0.0005) +[2023-07-17 00:59:35,948][282837] Updated weights for policy 0, policy_version 1040 (0.0005) +[2023-07-17 00:59:36,076][282552] Fps is (10 sec: 12697.6, 60 sec: 11832.9, 300 sec: 11832.9). Total num frames: 532480. Throughput: 0: 11756.9. Samples: 529060. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 00:59:36,078][282552] Avg episode reward: [(0, '352.196')] +[2023-07-17 00:59:36,079][282793] Saving new best policy, reward=352.196! +[2023-07-17 00:59:39,256][282837] Updated weights for policy 0, policy_version 1120 (0.0005) +[2023-07-17 00:59:41,076][282552] Fps is (10 sec: 12697.7, 60 sec: 11878.4, 300 sec: 11878.4). Total num frames: 593920. Throughput: 0: 12586.1. Samples: 566376. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 00:59:41,077][282552] Avg episode reward: [(0, '362.194')] +[2023-07-17 00:59:41,077][282793] Saving new best policy, reward=362.194! +[2023-07-17 00:59:42,525][282837] Updated weights for policy 0, policy_version 1200 (0.0006) +[2023-07-17 00:59:45,724][282837] Updated weights for policy 0, policy_version 1280 (0.0005) +[2023-07-17 00:59:46,076][282552] Fps is (10 sec: 12697.5, 60 sec: 11990.1, 300 sec: 11990.1). Total num frames: 659456. Throughput: 0: 12913.6. Samples: 642388. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) +[2023-07-17 00:59:46,076][282552] Avg episode reward: [(0, '363.907')] +[2023-07-17 00:59:46,080][282793] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000001288_659456.pth... +[2023-07-17 00:59:46,082][282793] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000000544_278528.pth +[2023-07-17 00:59:46,082][282793] Saving new best policy, reward=363.907! +[2023-07-17 00:59:48,975][282837] Updated weights for policy 0, policy_version 1360 (0.0005) +[2023-07-17 00:59:51,076][282552] Fps is (10 sec: 12697.6, 60 sec: 12014.9, 300 sec: 12014.9). Total num frames: 720896. Throughput: 0: 12797.7. Samples: 717920. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 00:59:51,076][282552] Avg episode reward: [(0, '379.317')] +[2023-07-17 00:59:51,077][282793] Saving new best policy, reward=379.317! +[2023-07-17 00:59:52,189][282837] Updated weights for policy 0, policy_version 1440 (0.0005) +[2023-07-17 00:59:55,346][282837] Updated weights for policy 0, policy_version 1520 (0.0005) +[2023-07-17 00:59:56,076][282552] Fps is (10 sec: 12697.6, 60 sec: 12902.4, 300 sec: 12099.0). Total num frames: 786432. Throughput: 0: 12775.8. Samples: 757760. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 00:59:56,076][282552] Avg episode reward: [(0, '376.537')] +[2023-07-17 00:59:58,647][282837] Updated weights for policy 0, policy_version 1600 (0.0004) +[2023-07-17 01:00:01,076][282552] Fps is (10 sec: 12697.6, 60 sec: 12834.1, 300 sec: 12112.5). Total num frames: 847872. Throughput: 0: 12678.0. Samples: 832120. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) +[2023-07-17 01:00:01,076][282552] Avg episode reward: [(0, '386.411')] +[2023-07-17 01:00:01,079][282793] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000001656_847872.pth... +[2023-07-17 01:00:01,082][282793] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000000920_471040.pth +[2023-07-17 01:00:01,083][282793] Saving new best policy, reward=386.411! +[2023-07-17 01:00:01,949][282837] Updated weights for policy 0, policy_version 1680 (0.0005) +[2023-07-17 01:00:05,174][282837] Updated weights for policy 0, policy_version 1760 (0.0005) +[2023-07-17 01:00:06,076][282552] Fps is (10 sec: 12288.1, 60 sec: 12697.6, 300 sec: 12124.2). Total num frames: 909312. Throughput: 0: 12640.9. Samples: 908816. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:00:06,076][282552] Avg episode reward: [(0, '394.224')] +[2023-07-17 01:00:06,109][282793] Saving new best policy, reward=394.224! +[2023-07-17 01:00:08,385][282837] Updated weights for policy 0, policy_version 1840 (0.0005) +[2023-07-17 01:00:11,076][282552] Fps is (10 sec: 12697.7, 60 sec: 12697.6, 300 sec: 12185.6). Total num frames: 974848. Throughput: 0: 12635.1. Samples: 946240. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:00:11,076][282552] Avg episode reward: [(0, '407.933')] +[2023-07-17 01:00:11,077][282793] Saving new best policy, reward=407.933! +[2023-07-17 01:00:11,680][282837] Updated weights for policy 0, policy_version 1920 (0.0005) +[2023-07-17 01:00:14,981][282837] Updated weights for policy 0, policy_version 2000 (0.0005) +[2023-07-17 01:00:16,076][282552] Fps is (10 sec: 12697.5, 60 sec: 12629.3, 300 sec: 12191.6). Total num frames: 1036288. Throughput: 0: 12570.5. Samples: 1020340. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:00:16,076][282552] Avg episode reward: [(0, '418.999')] +[2023-07-17 01:00:16,079][282793] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000002024_1036288.pth... +[2023-07-17 01:00:16,082][282793] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000001288_659456.pth +[2023-07-17 01:00:16,082][282793] Saving new best policy, reward=418.999! +[2023-07-17 01:00:18,253][282837] Updated weights for policy 0, policy_version 2080 (0.0005) +[2023-07-17 01:00:21,076][282552] Fps is (10 sec: 12288.0, 60 sec: 12561.1, 300 sec: 12197.0). Total num frames: 1097728. Throughput: 0: 12547.5. Samples: 1093696. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:00:21,076][282552] Avg episode reward: [(0, '430.710')] +[2023-07-17 01:00:21,076][282793] Saving new best policy, reward=430.710! +[2023-07-17 01:00:21,691][282837] Updated weights for policy 0, policy_version 2160 (0.0005) +[2023-07-17 01:00:24,917][282837] Updated weights for policy 0, policy_version 2240 (0.0003) +[2023-07-17 01:00:26,076][282552] Fps is (10 sec: 12288.1, 60 sec: 12561.1, 300 sec: 12201.8). Total num frames: 1159168. Throughput: 0: 12559.6. Samples: 1131556. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) +[2023-07-17 01:00:26,076][282552] Avg episode reward: [(0, '420.650')] +[2023-07-17 01:00:28,194][282837] Updated weights for policy 0, policy_version 2320 (0.0003) +[2023-07-17 01:00:31,076][282552] Fps is (10 sec: 12287.9, 60 sec: 12561.1, 300 sec: 12206.1). Total num frames: 1220608. Throughput: 0: 12526.1. Samples: 1206064. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:00:31,076][282552] Avg episode reward: [(0, '416.878')] +[2023-07-17 01:00:31,079][282793] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000002384_1220608.pth... +[2023-07-17 01:00:31,082][282793] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000001656_847872.pth +[2023-07-17 01:00:31,546][282837] Updated weights for policy 0, policy_version 2400 (0.0005) +[2023-07-17 01:00:34,905][282837] Updated weights for policy 0, policy_version 2480 (0.0005) +[2023-07-17 01:00:36,076][282552] Fps is (10 sec: 12288.0, 60 sec: 12492.8, 300 sec: 12210.0). Total num frames: 1282048. Throughput: 0: 12465.3. Samples: 1278856. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:00:36,076][282552] Avg episode reward: [(0, '440.415')] +[2023-07-17 01:00:36,077][282793] Saving new best policy, reward=440.415! +[2023-07-17 01:00:38,333][282837] Updated weights for policy 0, policy_version 2560 (0.0005) +[2023-07-17 01:00:41,076][282552] Fps is (10 sec: 12288.0, 60 sec: 12492.8, 300 sec: 12213.5). Total num frames: 1343488. Throughput: 0: 12382.7. Samples: 1314980. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) +[2023-07-17 01:00:41,076][282552] Avg episode reward: [(0, '475.952')] +[2023-07-17 01:00:41,077][282793] Saving new best policy, reward=475.952! +[2023-07-17 01:00:41,523][282837] Updated weights for policy 0, policy_version 2640 (0.0004) +[2023-07-17 01:00:44,610][282837] Updated weights for policy 0, policy_version 2720 (0.0004) +[2023-07-17 01:00:46,076][282552] Fps is (10 sec: 12697.5, 60 sec: 12492.8, 300 sec: 12252.4). Total num frames: 1409024. Throughput: 0: 12478.8. Samples: 1393668. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:00:46,076][282552] Avg episode reward: [(0, '513.982')] +[2023-07-17 01:00:46,079][282793] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000002752_1409024.pth... +[2023-07-17 01:00:46,082][282793] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000002024_1036288.pth +[2023-07-17 01:00:46,082][282793] Saving new best policy, reward=513.982! +[2023-07-17 01:00:47,661][282837] Updated weights for policy 0, policy_version 2800 (0.0004) +[2023-07-17 01:00:50,783][282837] Updated weights for policy 0, policy_version 2880 (0.0004) +[2023-07-17 01:00:51,076][282552] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12288.0). Total num frames: 1474560. Throughput: 0: 12555.7. Samples: 1473824. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:00:51,076][282552] Avg episode reward: [(0, '558.701')] +[2023-07-17 01:00:51,101][282793] Saving new best policy, reward=558.701! +[2023-07-17 01:00:53,851][282837] Updated weights for policy 0, policy_version 2960 (0.0004) +[2023-07-17 01:00:56,076][282552] Fps is (10 sec: 13516.9, 60 sec: 12629.3, 300 sec: 12353.5). Total num frames: 1544192. Throughput: 0: 12602.7. Samples: 1513360. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:00:56,076][282552] Avg episode reward: [(0, '602.753')] +[2023-07-17 01:00:56,076][282793] Saving new best policy, reward=602.753! +[2023-07-17 01:00:56,909][282837] Updated weights for policy 0, policy_version 3040 (0.0004) +[2023-07-17 01:01:00,016][282837] Updated weights for policy 0, policy_version 3120 (0.0004) +[2023-07-17 01:01:01,076][282552] Fps is (10 sec: 13516.7, 60 sec: 12697.6, 300 sec: 12382.5). Total num frames: 1609728. Throughput: 0: 12734.8. Samples: 1593408. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) +[2023-07-17 01:01:01,076][282552] Avg episode reward: [(0, '622.329')] +[2023-07-17 01:01:01,079][282793] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000003144_1609728.pth... +[2023-07-17 01:01:01,082][282793] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000002384_1220608.pth +[2023-07-17 01:01:01,082][282793] Saving new best policy, reward=622.329! +[2023-07-17 01:01:03,036][282837] Updated weights for policy 0, policy_version 3200 (0.0004) +[2023-07-17 01:01:06,051][282837] Updated weights for policy 0, policy_version 3280 (0.0003) +[2023-07-17 01:01:06,076][282552] Fps is (10 sec: 13516.8, 60 sec: 12834.1, 300 sec: 12439.7). Total num frames: 1679360. Throughput: 0: 12917.8. Samples: 1674996. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) +[2023-07-17 01:01:06,076][282552] Avg episode reward: [(0, '605.799')] +[2023-07-17 01:01:09,067][282837] Updated weights for policy 0, policy_version 3360 (0.0003) +[2023-07-17 01:01:11,076][282552] Fps is (10 sec: 13516.8, 60 sec: 12834.1, 300 sec: 12463.5). Total num frames: 1744896. Throughput: 0: 12981.4. Samples: 1715720. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:01:11,076][282552] Avg episode reward: [(0, '600.102')] +[2023-07-17 01:01:12,085][282837] Updated weights for policy 0, policy_version 3440 (0.0003) +[2023-07-17 01:01:15,144][282837] Updated weights for policy 0, policy_version 3520 (0.0004) +[2023-07-17 01:01:16,076][282552] Fps is (10 sec: 13516.7, 60 sec: 12970.7, 300 sec: 12514.0). Total num frames: 1814528. Throughput: 0: 13128.3. Samples: 1796836. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:01:16,076][282552] Avg episode reward: [(0, '618.598')] +[2023-07-17 01:01:16,079][282793] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000003544_1814528.pth... +[2023-07-17 01:01:16,081][282793] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000002752_1409024.pth +[2023-07-17 01:01:18,168][282837] Updated weights for policy 0, policy_version 3600 (0.0004) +[2023-07-17 01:01:21,076][282552] Fps is (10 sec: 13516.9, 60 sec: 13038.9, 300 sec: 12533.8). Total num frames: 1880064. Throughput: 0: 13290.5. Samples: 1876928. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:01:21,076][282552] Avg episode reward: [(0, '624.420')] +[2023-07-17 01:01:21,077][282793] Saving new best policy, reward=624.420! +[2023-07-17 01:01:21,198][282837] Updated weights for policy 0, policy_version 3680 (0.0003) +[2023-07-17 01:01:24,205][282837] Updated weights for policy 0, policy_version 3760 (0.0003) +[2023-07-17 01:01:26,076][282552] Fps is (10 sec: 13516.9, 60 sec: 13175.5, 300 sec: 12578.7). Total num frames: 1949696. Throughput: 0: 13409.1. Samples: 1918388. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:01:26,076][282552] Avg episode reward: [(0, '644.988')] +[2023-07-17 01:01:26,077][282793] Saving new best policy, reward=644.988! +[2023-07-17 01:01:27,168][282837] Updated weights for policy 0, policy_version 3840 (0.0003) +[2023-07-17 01:01:30,224][282837] Updated weights for policy 0, policy_version 3920 (0.0004) +[2023-07-17 01:01:31,076][282552] Fps is (10 sec: 13516.7, 60 sec: 13243.7, 300 sec: 12595.2). Total num frames: 2015232. Throughput: 0: 13478.2. Samples: 2000188. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:01:31,076][282552] Avg episode reward: [(0, '642.490')] +[2023-07-17 01:01:31,079][282793] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000003936_2015232.pth... +[2023-07-17 01:01:31,082][282793] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000003144_1609728.pth +[2023-07-17 01:01:33,297][282837] Updated weights for policy 0, policy_version 4000 (0.0004) +[2023-07-17 01:01:36,076][282552] Fps is (10 sec: 13516.8, 60 sec: 13380.3, 300 sec: 12635.5). Total num frames: 2084864. Throughput: 0: 13478.6. Samples: 2080360. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) +[2023-07-17 01:01:36,076][282552] Avg episode reward: [(0, '651.017')] +[2023-07-17 01:01:36,077][282793] Saving new best policy, reward=651.017! +[2023-07-17 01:01:36,331][282837] Updated weights for policy 0, policy_version 4080 (0.0003) +[2023-07-17 01:01:39,457][282837] Updated weights for policy 0, policy_version 4160 (0.0004) +[2023-07-17 01:01:41,076][282552] Fps is (10 sec: 13107.1, 60 sec: 13380.2, 300 sec: 12625.3). Total num frames: 2146304. Throughput: 0: 13504.9. Samples: 2121084. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:01:41,076][282552] Avg episode reward: [(0, '649.867')] +[2023-07-17 01:01:42,859][282837] Updated weights for policy 0, policy_version 4240 (0.0005) +[2023-07-17 01:01:46,076][282552] Fps is (10 sec: 12287.9, 60 sec: 13312.0, 300 sec: 12615.7). Total num frames: 2207744. Throughput: 0: 13333.4. Samples: 2193412. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:01:46,076][282552] Avg episode reward: [(0, '645.971')] +[2023-07-17 01:01:46,079][282793] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000004312_2207744.pth... +[2023-07-17 01:01:46,082][282793] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000003544_1814528.pth +[2023-07-17 01:01:46,235][282837] Updated weights for policy 0, policy_version 4320 (0.0005) +[2023-07-17 01:01:49,513][282837] Updated weights for policy 0, policy_version 4400 (0.0005) +[2023-07-17 01:01:51,076][282552] Fps is (10 sec: 12288.0, 60 sec: 13243.7, 300 sec: 12606.6). Total num frames: 2269184. Throughput: 0: 13188.2. Samples: 2268468. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:01:51,076][282552] Avg episode reward: [(0, '649.296')] +[2023-07-17 01:01:52,752][282837] Updated weights for policy 0, policy_version 4480 (0.0005) +[2023-07-17 01:01:55,769][282837] Updated weights for policy 0, policy_version 4560 (0.0004) +[2023-07-17 01:01:56,076][282552] Fps is (10 sec: 12697.7, 60 sec: 13175.5, 300 sec: 12620.1). Total num frames: 2334720. Throughput: 0: 13119.8. Samples: 2306112. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:01:56,076][282552] Avg episode reward: [(0, '659.737')] +[2023-07-17 01:01:56,080][282793] Saving new best policy, reward=659.737! +[2023-07-17 01:01:58,738][282837] Updated weights for policy 0, policy_version 4640 (0.0004) +[2023-07-17 01:02:01,076][282552] Fps is (10 sec: 13516.9, 60 sec: 13243.7, 300 sec: 12654.5). Total num frames: 2404352. Throughput: 0: 13159.1. Samples: 2388996. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:02:01,076][282552] Avg episode reward: [(0, '654.797')] +[2023-07-17 01:02:01,079][282793] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000004696_2404352.pth... +[2023-07-17 01:02:01,082][282793] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000003936_2015232.pth +[2023-07-17 01:02:01,725][282837] Updated weights for policy 0, policy_version 4720 (0.0004) +[2023-07-17 01:02:04,950][282837] Updated weights for policy 0, policy_version 4800 (0.0005) +[2023-07-17 01:02:06,076][282552] Fps is (10 sec: 13516.7, 60 sec: 13175.5, 300 sec: 12666.1). Total num frames: 2469888. Throughput: 0: 13110.1. Samples: 2466884. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:02:06,076][282552] Avg episode reward: [(0, '657.554')] +[2023-07-17 01:02:08,174][282837] Updated weights for policy 0, policy_version 4880 (0.0004) +[2023-07-17 01:02:11,076][282552] Fps is (10 sec: 12697.8, 60 sec: 13107.2, 300 sec: 12656.6). Total num frames: 2531328. Throughput: 0: 13045.5. Samples: 2505436. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:02:11,077][282552] Avg episode reward: [(0, '666.713')] +[2023-07-17 01:02:11,077][282793] Saving new best policy, reward=666.713! +[2023-07-17 01:02:11,472][282837] Updated weights for policy 0, policy_version 4960 (0.0005) +[2023-07-17 01:02:14,777][282837] Updated weights for policy 0, policy_version 5040 (0.0005) +[2023-07-17 01:02:16,076][282552] Fps is (10 sec: 12288.0, 60 sec: 12970.7, 300 sec: 12647.7). Total num frames: 2592768. Throughput: 0: 12890.9. Samples: 2580276. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) +[2023-07-17 01:02:16,076][282552] Avg episode reward: [(0, '673.059')] +[2023-07-17 01:02:16,127][282793] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000005072_2596864.pth... +[2023-07-17 01:02:16,130][282793] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000004312_2207744.pth +[2023-07-17 01:02:16,130][282793] Saving new best policy, reward=673.059! +[2023-07-17 01:02:18,128][282837] Updated weights for policy 0, policy_version 5120 (0.0005) +[2023-07-17 01:02:21,077][282552] Fps is (10 sec: 12695.6, 60 sec: 12970.3, 300 sec: 12658.5). Total num frames: 2658304. Throughput: 0: 12751.8. Samples: 2654208. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:02:21,078][282552] Avg episode reward: [(0, '650.662')] +[2023-07-17 01:02:21,388][282837] Updated weights for policy 0, policy_version 5200 (0.0005) +[2023-07-17 01:02:24,623][282837] Updated weights for policy 0, policy_version 5280 (0.0005) +[2023-07-17 01:02:26,076][282552] Fps is (10 sec: 12697.6, 60 sec: 12834.1, 300 sec: 12650.0). Total num frames: 2719744. Throughput: 0: 12688.3. Samples: 2692056. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:02:26,076][282552] Avg episode reward: [(0, '665.412')] +[2023-07-17 01:02:27,791][282837] Updated weights for policy 0, policy_version 5360 (0.0005) +[2023-07-17 01:02:31,061][282837] Updated weights for policy 0, policy_version 5440 (0.0005) +[2023-07-17 01:02:31,076][282552] Fps is (10 sec: 12699.4, 60 sec: 12834.1, 300 sec: 12660.4). Total num frames: 2785280. Throughput: 0: 12786.9. Samples: 2768824. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:02:31,076][282552] Avg episode reward: [(0, '657.113')] +[2023-07-17 01:02:31,079][282793] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000005440_2785280.pth... +[2023-07-17 01:02:31,081][282793] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000004696_2404352.pth +[2023-07-17 01:02:34,325][282837] Updated weights for policy 0, policy_version 5520 (0.0005) +[2023-07-17 01:02:36,076][282552] Fps is (10 sec: 12697.6, 60 sec: 12697.6, 300 sec: 12652.1). Total num frames: 2846720. Throughput: 0: 12781.3. Samples: 2843624. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:02:36,076][282552] Avg episode reward: [(0, '625.309')] +[2023-07-17 01:02:37,569][282837] Updated weights for policy 0, policy_version 5600 (0.0005) +[2023-07-17 01:02:40,619][282837] Updated weights for policy 0, policy_version 5680 (0.0004) +[2023-07-17 01:02:41,076][282552] Fps is (10 sec: 12697.7, 60 sec: 12765.9, 300 sec: 12662.0). Total num frames: 2912256. Throughput: 0: 12789.2. Samples: 2881624. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:02:41,076][282552] Avg episode reward: [(0, '650.636')] +[2023-07-17 01:02:43,632][282837] Updated weights for policy 0, policy_version 5760 (0.0004) +[2023-07-17 01:02:46,076][282552] Fps is (10 sec: 13516.6, 60 sec: 12902.4, 300 sec: 12688.9). Total num frames: 2981888. Throughput: 0: 12773.1. Samples: 2963788. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) +[2023-07-17 01:02:46,076][282552] Avg episode reward: [(0, '634.147')] +[2023-07-17 01:02:46,079][282793] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000005824_2981888.pth... +[2023-07-17 01:02:46,082][282793] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000005072_2596864.pth +[2023-07-17 01:02:46,709][282837] Updated weights for policy 0, policy_version 5840 (0.0004) +[2023-07-17 01:02:50,032][282837] Updated weights for policy 0, policy_version 5920 (0.0005) +[2023-07-17 01:02:51,076][282552] Fps is (10 sec: 13107.1, 60 sec: 12902.4, 300 sec: 12680.5). Total num frames: 3043328. Throughput: 0: 12719.0. Samples: 3039240. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:02:51,076][282552] Avg episode reward: [(0, '640.333')] +[2023-07-17 01:02:53,291][282837] Updated weights for policy 0, policy_version 6000 (0.0005) +[2023-07-17 01:02:56,076][282552] Fps is (10 sec: 12288.1, 60 sec: 12834.1, 300 sec: 12672.5). Total num frames: 3104768. Throughput: 0: 12697.4. Samples: 3076820. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:02:56,076][282552] Avg episode reward: [(0, '631.320')] +[2023-07-17 01:02:56,528][282837] Updated weights for policy 0, policy_version 6080 (0.0005) +[2023-07-17 01:02:59,847][282837] Updated weights for policy 0, policy_version 6160 (0.0005) +[2023-07-17 01:03:01,076][282552] Fps is (10 sec: 12288.1, 60 sec: 12697.6, 300 sec: 12664.8). Total num frames: 3166208. Throughput: 0: 12709.4. Samples: 3152200. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:03:01,076][282552] Avg episode reward: [(0, '656.100')] +[2023-07-17 01:03:01,111][282793] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000006192_3170304.pth... +[2023-07-17 01:03:01,114][282793] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000005440_2785280.pth +[2023-07-17 01:03:03,040][282837] Updated weights for policy 0, policy_version 6240 (0.0005) +[2023-07-17 01:03:06,076][282552] Fps is (10 sec: 12697.6, 60 sec: 12697.6, 300 sec: 12673.5). Total num frames: 3231744. Throughput: 0: 12761.9. Samples: 3228476. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) +[2023-07-17 01:03:06,076][282552] Avg episode reward: [(0, '657.684')] +[2023-07-17 01:03:06,275][282837] Updated weights for policy 0, policy_version 6320 (0.0005) +[2023-07-17 01:03:09,281][282837] Updated weights for policy 0, policy_version 6400 (0.0004) +[2023-07-17 01:03:11,076][282552] Fps is (10 sec: 13107.1, 60 sec: 12765.8, 300 sec: 12681.8). Total num frames: 3297280. Throughput: 0: 12813.7. Samples: 3268672. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) +[2023-07-17 01:03:11,076][282552] Avg episode reward: [(0, '660.023')] +[2023-07-17 01:03:12,265][282837] Updated weights for policy 0, policy_version 6480 (0.0004) +[2023-07-17 01:03:15,275][282837] Updated weights for policy 0, policy_version 6560 (0.0004) +[2023-07-17 01:03:16,076][282552] Fps is (10 sec: 13516.7, 60 sec: 12902.4, 300 sec: 12705.3). Total num frames: 3366912. Throughput: 0: 12935.6. Samples: 3350928. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) +[2023-07-17 01:03:16,076][282552] Avg episode reward: [(0, '663.295')] +[2023-07-17 01:03:16,079][282793] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000006576_3366912.pth... +[2023-07-17 01:03:16,082][282793] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000005824_2981888.pth +[2023-07-17 01:03:18,381][282837] Updated weights for policy 0, policy_version 6640 (0.0004) +[2023-07-17 01:03:21,076][282552] Fps is (10 sec: 13516.9, 60 sec: 12902.7, 300 sec: 12712.8). Total num frames: 3432448. Throughput: 0: 12995.4. Samples: 3428416. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:03:21,076][282552] Avg episode reward: [(0, '642.669')] +[2023-07-17 01:03:21,705][282837] Updated weights for policy 0, policy_version 6720 (0.0005) +[2023-07-17 01:03:25,017][282837] Updated weights for policy 0, policy_version 6800 (0.0005) +[2023-07-17 01:03:26,076][282552] Fps is (10 sec: 12697.7, 60 sec: 12902.4, 300 sec: 12705.1). Total num frames: 3493888. Throughput: 0: 12968.9. Samples: 3465224. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:03:26,076][282552] Avg episode reward: [(0, '662.239')] +[2023-07-17 01:03:28,335][282837] Updated weights for policy 0, policy_version 6880 (0.0005) +[2023-07-17 01:03:31,076][282552] Fps is (10 sec: 12287.8, 60 sec: 12834.1, 300 sec: 12697.6). Total num frames: 3555328. Throughput: 0: 12784.6. Samples: 3539096. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:03:31,076][282552] Avg episode reward: [(0, '657.500')] +[2023-07-17 01:03:31,080][282793] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000006944_3555328.pth... +[2023-07-17 01:03:31,083][282793] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000006192_3170304.pth +[2023-07-17 01:03:31,721][282837] Updated weights for policy 0, policy_version 6960 (0.0005) +[2023-07-17 01:03:34,965][282837] Updated weights for policy 0, policy_version 7040 (0.0005) +[2023-07-17 01:03:36,076][282552] Fps is (10 sec: 12288.0, 60 sec: 12834.1, 300 sec: 12690.4). Total num frames: 3616768. Throughput: 0: 12767.3. Samples: 3613768. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:03:36,077][282552] Avg episode reward: [(0, '676.598')] +[2023-07-17 01:03:36,077][282793] Saving new best policy, reward=676.598! +[2023-07-17 01:03:38,299][282837] Updated weights for policy 0, policy_version 7120 (0.0005) +[2023-07-17 01:03:41,076][282552] Fps is (10 sec: 12288.1, 60 sec: 12765.9, 300 sec: 12683.5). Total num frames: 3678208. Throughput: 0: 12748.3. Samples: 3650496. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:03:41,076][282552] Avg episode reward: [(0, '677.070')] +[2023-07-17 01:03:41,077][282793] Saving new best policy, reward=677.070! +[2023-07-17 01:03:41,529][282837] Updated weights for policy 0, policy_version 7200 (0.0005) +[2023-07-17 01:03:44,858][282837] Updated weights for policy 0, policy_version 7280 (0.0005) +[2023-07-17 01:03:46,076][282552] Fps is (10 sec: 12288.0, 60 sec: 12629.3, 300 sec: 12676.8). Total num frames: 3739648. Throughput: 0: 12737.1. Samples: 3725372. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) +[2023-07-17 01:03:46,076][282552] Avg episode reward: [(0, '651.907')] +[2023-07-17 01:03:46,079][282793] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000007304_3739648.pth... +[2023-07-17 01:03:46,082][282793] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000006576_3366912.pth +[2023-07-17 01:03:48,165][282837] Updated weights for policy 0, policy_version 7360 (0.0005) +[2023-07-17 01:03:51,076][282552] Fps is (10 sec: 12288.0, 60 sec: 12629.3, 300 sec: 12843.4). Total num frames: 3801088. Throughput: 0: 12723.8. Samples: 3801048. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:03:51,076][282552] Avg episode reward: [(0, '652.771')] +[2023-07-17 01:03:51,395][282837] Updated weights for policy 0, policy_version 7440 (0.0005) +[2023-07-17 01:03:54,741][282837] Updated weights for policy 0, policy_version 7520 (0.0005) +[2023-07-17 01:03:56,076][282552] Fps is (10 sec: 12697.7, 60 sec: 12697.6, 300 sec: 12843.4). Total num frames: 3866624. Throughput: 0: 12646.6. Samples: 3837768. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:03:56,076][282552] Avg episode reward: [(0, '673.450')] +[2023-07-17 01:03:57,941][282837] Updated weights for policy 0, policy_version 7600 (0.0005) +[2023-07-17 01:04:01,076][282552] Fps is (10 sec: 12697.5, 60 sec: 12697.6, 300 sec: 12815.6). Total num frames: 3928064. Throughput: 0: 12496.8. Samples: 3913284. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:04:01,076][282552] Avg episode reward: [(0, '660.238')] +[2023-07-17 01:04:01,079][282793] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000007672_3928064.pth... +[2023-07-17 01:04:01,082][282793] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000006944_3555328.pth +[2023-07-17 01:04:01,152][282837] Updated weights for policy 0, policy_version 7680 (0.0005) +[2023-07-17 01:04:04,458][282837] Updated weights for policy 0, policy_version 7760 (0.0005) +[2023-07-17 01:04:06,076][282552] Fps is (10 sec: 12697.6, 60 sec: 12697.6, 300 sec: 12815.6). Total num frames: 3993600. Throughput: 0: 12462.7. Samples: 3989236. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:04:06,076][282552] Avg episode reward: [(0, '679.934')] +[2023-07-17 01:04:06,077][282793] Saving new best policy, reward=679.934! +[2023-07-17 01:04:07,740][282837] Updated weights for policy 0, policy_version 7840 (0.0005) +[2023-07-17 01:04:11,035][282837] Updated weights for policy 0, policy_version 7920 (0.0005) +[2023-07-17 01:04:11,076][282552] Fps is (10 sec: 12697.7, 60 sec: 12629.3, 300 sec: 12801.7). Total num frames: 4055040. Throughput: 0: 12470.0. Samples: 4026376. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:04:11,076][282552] Avg episode reward: [(0, '680.158')] +[2023-07-17 01:04:11,077][282793] Saving new best policy, reward=680.158! +[2023-07-17 01:04:14,375][282837] Updated weights for policy 0, policy_version 8000 (0.0005) +[2023-07-17 01:04:16,076][282552] Fps is (10 sec: 12287.9, 60 sec: 12492.8, 300 sec: 12787.8). Total num frames: 4116480. Throughput: 0: 12467.0. Samples: 4100112. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) +[2023-07-17 01:04:16,076][282552] Avg episode reward: [(0, '671.737')] +[2023-07-17 01:04:16,079][282793] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000008040_4116480.pth... +[2023-07-17 01:04:16,082][282793] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000007304_3739648.pth +[2023-07-17 01:04:17,633][282837] Updated weights for policy 0, policy_version 8080 (0.0005) +[2023-07-17 01:04:20,979][282837] Updated weights for policy 0, policy_version 8160 (0.0005) +[2023-07-17 01:04:21,076][282552] Fps is (10 sec: 12288.0, 60 sec: 12424.5, 300 sec: 12787.9). Total num frames: 4177920. Throughput: 0: 12451.7. Samples: 4174092. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) +[2023-07-17 01:04:21,076][282552] Avg episode reward: [(0, '645.231')] +[2023-07-17 01:04:24,255][282837] Updated weights for policy 0, policy_version 8240 (0.0005) +[2023-07-17 01:04:26,076][282552] Fps is (10 sec: 12288.0, 60 sec: 12424.5, 300 sec: 12787.9). Total num frames: 4239360. Throughput: 0: 12479.7. Samples: 4212084. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) +[2023-07-17 01:04:26,076][282552] Avg episode reward: [(0, '667.245')] +[2023-07-17 01:04:27,524][282837] Updated weights for policy 0, policy_version 8320 (0.0005) +[2023-07-17 01:04:30,781][282837] Updated weights for policy 0, policy_version 8400 (0.0005) +[2023-07-17 01:04:31,076][282552] Fps is (10 sec: 12288.0, 60 sec: 12424.6, 300 sec: 12774.0). Total num frames: 4300800. Throughput: 0: 12501.7. Samples: 4287948. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:04:31,076][282552] Avg episode reward: [(0, '671.681')] +[2023-07-17 01:04:31,118][282793] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000008408_4304896.pth... +[2023-07-17 01:04:31,120][282793] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000007672_3928064.pth +[2023-07-17 01:04:34,083][282837] Updated weights for policy 0, policy_version 8480 (0.0005) +[2023-07-17 01:04:36,076][282552] Fps is (10 sec: 12288.1, 60 sec: 12424.5, 300 sec: 12774.0). Total num frames: 4362240. Throughput: 0: 12470.9. Samples: 4362240. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:04:36,077][282552] Avg episode reward: [(0, '664.889')] +[2023-07-17 01:04:37,376][282837] Updated weights for policy 0, policy_version 8560 (0.0005) +[2023-07-17 01:04:40,612][282837] Updated weights for policy 0, policy_version 8640 (0.0005) +[2023-07-17 01:04:41,076][282552] Fps is (10 sec: 12697.5, 60 sec: 12492.8, 300 sec: 12774.0). Total num frames: 4427776. Throughput: 0: 12475.9. Samples: 4399184. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:04:41,077][282552] Avg episode reward: [(0, '666.769')] +[2023-07-17 01:04:43,887][282837] Updated weights for policy 0, policy_version 8720 (0.0005) +[2023-07-17 01:04:46,076][282552] Fps is (10 sec: 12697.4, 60 sec: 12492.8, 300 sec: 12774.0). Total num frames: 4489216. Throughput: 0: 12489.1. Samples: 4475292. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) +[2023-07-17 01:04:46,076][282552] Avg episode reward: [(0, '632.678')] +[2023-07-17 01:04:46,080][282793] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000008768_4489216.pth... +[2023-07-17 01:04:46,083][282793] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000008040_4116480.pth +[2023-07-17 01:04:47,170][282837] Updated weights for policy 0, policy_version 8800 (0.0005) +[2023-07-17 01:04:50,553][282837] Updated weights for policy 0, policy_version 8880 (0.0005) +[2023-07-17 01:04:51,076][282552] Fps is (10 sec: 12288.0, 60 sec: 12492.8, 300 sec: 12760.1). Total num frames: 4550656. Throughput: 0: 12429.9. Samples: 4548580. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) +[2023-07-17 01:04:51,077][282552] Avg episode reward: [(0, '664.028')] +[2023-07-17 01:04:53,809][282837] Updated weights for policy 0, policy_version 8960 (0.0005) +[2023-07-17 01:04:56,076][282552] Fps is (10 sec: 12697.7, 60 sec: 12492.8, 300 sec: 12774.0). Total num frames: 4616192. Throughput: 0: 12449.4. Samples: 4586600. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) +[2023-07-17 01:04:56,077][282552] Avg episode reward: [(0, '677.608')] +[2023-07-17 01:04:56,855][282837] Updated weights for policy 0, policy_version 9040 (0.0004) +[2023-07-17 01:04:59,854][282837] Updated weights for policy 0, policy_version 9120 (0.0004) +[2023-07-17 01:05:01,076][282552] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12787.8). Total num frames: 4681728. Throughput: 0: 12600.2. Samples: 4667120. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) +[2023-07-17 01:05:01,076][282552] Avg episode reward: [(0, '658.428')] +[2023-07-17 01:05:01,100][282793] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000009152_4685824.pth... +[2023-07-17 01:05:01,102][282793] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000008408_4304896.pth +[2023-07-17 01:05:03,062][282837] Updated weights for policy 0, policy_version 9200 (0.0005) +[2023-07-17 01:05:06,076][282552] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12787.8). Total num frames: 4747264. Throughput: 0: 12665.4. Samples: 4744036. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) +[2023-07-17 01:05:06,077][282552] Avg episode reward: [(0, '678.010')] +[2023-07-17 01:05:06,275][282837] Updated weights for policy 0, policy_version 9280 (0.0005) +[2023-07-17 01:05:09,517][282837] Updated weights for policy 0, policy_version 9360 (0.0005) +[2023-07-17 01:05:11,076][282552] Fps is (10 sec: 12697.7, 60 sec: 12561.1, 300 sec: 12787.9). Total num frames: 4808704. Throughput: 0: 12668.5. Samples: 4782164. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) +[2023-07-17 01:05:11,076][282552] Avg episode reward: [(0, '678.393')] +[2023-07-17 01:05:12,731][282837] Updated weights for policy 0, policy_version 9440 (0.0005) +[2023-07-17 01:05:15,764][282837] Updated weights for policy 0, policy_version 9520 (0.0004) +[2023-07-17 01:05:16,076][282552] Fps is (10 sec: 13107.2, 60 sec: 12697.6, 300 sec: 12815.6). Total num frames: 4878336. Throughput: 0: 12696.5. Samples: 4859292. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) +[2023-07-17 01:05:16,079][282552] Avg episode reward: [(0, '679.252')] +[2023-07-17 01:05:16,083][282793] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000009528_4878336.pth... +[2023-07-17 01:05:16,085][282793] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000008768_4489216.pth +[2023-07-17 01:05:18,759][282837] Updated weights for policy 0, policy_version 9600 (0.0004) +[2023-07-17 01:05:21,076][282552] Fps is (10 sec: 13516.7, 60 sec: 12765.9, 300 sec: 12829.5). Total num frames: 4943872. Throughput: 0: 12874.9. Samples: 4941612. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) +[2023-07-17 01:05:21,076][282552] Avg episode reward: [(0, '683.733')] +[2023-07-17 01:05:21,077][282793] Saving new best policy, reward=683.733! +[2023-07-17 01:05:21,718][282837] Updated weights for policy 0, policy_version 9680 (0.0003) +[2023-07-17 01:05:24,812][282837] Updated weights for policy 0, policy_version 9760 (0.0004) +[2023-07-17 01:05:26,076][282552] Fps is (10 sec: 13107.2, 60 sec: 12834.1, 300 sec: 12843.4). Total num frames: 5009408. Throughput: 0: 12959.8. Samples: 4982376. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:05:26,076][282552] Avg episode reward: [(0, '647.254')] +[2023-07-17 01:05:28,084][282837] Updated weights for policy 0, policy_version 9840 (0.0005) +[2023-07-17 01:05:31,076][282552] Fps is (10 sec: 13107.1, 60 sec: 12902.4, 300 sec: 12857.3). Total num frames: 5074944. Throughput: 0: 12961.9. Samples: 5058576. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) +[2023-07-17 01:05:31,076][282552] Avg episode reward: [(0, '671.903')] +[2023-07-17 01:05:31,079][282793] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000009912_5074944.pth... +[2023-07-17 01:05:31,082][282793] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000009152_4685824.pth +[2023-07-17 01:05:31,350][282837] Updated weights for policy 0, policy_version 9920 (0.0004) +[2023-07-17 01:05:34,685][282837] Updated weights for policy 0, policy_version 10000 (0.0005) +[2023-07-17 01:05:36,076][282552] Fps is (10 sec: 12697.5, 60 sec: 12902.4, 300 sec: 12857.3). Total num frames: 5136384. Throughput: 0: 12977.5. Samples: 5132568. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) +[2023-07-17 01:05:36,076][282552] Avg episode reward: [(0, '682.368')] +[2023-07-17 01:05:37,967][282837] Updated weights for policy 0, policy_version 10080 (0.0005) +[2023-07-17 01:05:41,076][282552] Fps is (10 sec: 12288.1, 60 sec: 12834.1, 300 sec: 12843.4). Total num frames: 5197824. Throughput: 0: 12971.1. Samples: 5170300. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:05:41,076][282552] Avg episode reward: [(0, '681.830')] +[2023-07-17 01:05:41,088][282837] Updated weights for policy 0, policy_version 10160 (0.0004) +[2023-07-17 01:05:44,126][282837] Updated weights for policy 0, policy_version 10240 (0.0004) +[2023-07-17 01:05:46,076][282552] Fps is (10 sec: 13107.4, 60 sec: 12970.7, 300 sec: 12857.3). Total num frames: 5267456. Throughput: 0: 12978.2. Samples: 5251136. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:05:46,076][282552] Avg episode reward: [(0, '688.027')] +[2023-07-17 01:05:46,078][282793] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000010288_5267456.pth... +[2023-07-17 01:05:46,081][282793] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000009528_4878336.pth +[2023-07-17 01:05:46,081][282793] Saving new best policy, reward=688.027! +[2023-07-17 01:05:47,133][282837] Updated weights for policy 0, policy_version 10320 (0.0004) +[2023-07-17 01:05:50,077][282837] Updated weights for policy 0, policy_version 10400 (0.0004) +[2023-07-17 01:05:51,076][282552] Fps is (10 sec: 13926.3, 60 sec: 13107.2, 300 sec: 12857.3). Total num frames: 5337088. Throughput: 0: 13089.5. Samples: 5333064. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:05:51,076][282552] Avg episode reward: [(0, '681.936')] +[2023-07-17 01:05:53,095][282837] Updated weights for policy 0, policy_version 10480 (0.0003) +[2023-07-17 01:05:56,066][282837] Updated weights for policy 0, policy_version 10560 (0.0004) +[2023-07-17 01:05:56,076][282552] Fps is (10 sec: 13926.3, 60 sec: 13175.5, 300 sec: 12871.2). Total num frames: 5406720. Throughput: 0: 13152.4. Samples: 5374024. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) +[2023-07-17 01:05:56,076][282552] Avg episode reward: [(0, '688.342')] +[2023-07-17 01:05:56,077][282793] Saving new best policy, reward=688.342! +[2023-07-17 01:05:59,023][282837] Updated weights for policy 0, policy_version 10640 (0.0003) +[2023-07-17 01:06:01,076][282552] Fps is (10 sec: 13516.7, 60 sec: 13175.5, 300 sec: 12857.3). Total num frames: 5472256. Throughput: 0: 13286.2. Samples: 5457172. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) +[2023-07-17 01:06:01,076][282552] Avg episode reward: [(0, '681.239')] +[2023-07-17 01:06:01,079][282793] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000010688_5472256.pth... +[2023-07-17 01:06:01,081][282793] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000009912_5074944.pth +[2023-07-17 01:06:02,020][282837] Updated weights for policy 0, policy_version 10720 (0.0003) +[2023-07-17 01:06:05,026][282837] Updated weights for policy 0, policy_version 10800 (0.0004) +[2023-07-17 01:06:06,076][282552] Fps is (10 sec: 13516.9, 60 sec: 13243.7, 300 sec: 12871.2). Total num frames: 5541888. Throughput: 0: 13272.6. Samples: 5538880. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:06:06,076][282552] Avg episode reward: [(0, '681.149')] +[2023-07-17 01:06:08,009][282837] Updated weights for policy 0, policy_version 10880 (0.0003) +[2023-07-17 01:06:11,061][282837] Updated weights for policy 0, policy_version 10960 (0.0004) +[2023-07-17 01:06:11,076][282552] Fps is (10 sec: 13926.5, 60 sec: 13380.3, 300 sec: 12871.2). Total num frames: 5611520. Throughput: 0: 13264.3. Samples: 5579268. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:06:11,076][282552] Avg episode reward: [(0, '691.366')] +[2023-07-17 01:06:11,077][282793] Saving new best policy, reward=691.366! +[2023-07-17 01:06:14,105][282837] Updated weights for policy 0, policy_version 11040 (0.0004) +[2023-07-17 01:06:16,076][282552] Fps is (10 sec: 13516.7, 60 sec: 13312.0, 300 sec: 12871.2). Total num frames: 5677056. Throughput: 0: 13379.4. Samples: 5660648. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:06:16,076][282552] Avg episode reward: [(0, '680.164')] +[2023-07-17 01:06:16,080][282793] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000011088_5677056.pth... +[2023-07-17 01:06:16,082][282793] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000010288_5267456.pth +[2023-07-17 01:06:17,142][282837] Updated weights for policy 0, policy_version 11120 (0.0004) +[2023-07-17 01:06:20,124][282837] Updated weights for policy 0, policy_version 11200 (0.0004) +[2023-07-17 01:06:21,076][282552] Fps is (10 sec: 13516.8, 60 sec: 13380.3, 300 sec: 12871.2). Total num frames: 5746688. Throughput: 0: 13556.3. Samples: 5742600. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) +[2023-07-17 01:06:21,076][282552] Avg episode reward: [(0, '687.547')] +[2023-07-17 01:06:23,230][282837] Updated weights for policy 0, policy_version 11280 (0.0004) +[2023-07-17 01:06:26,076][282552] Fps is (10 sec: 13516.8, 60 sec: 13380.3, 300 sec: 12871.2). Total num frames: 5812224. Throughput: 0: 13592.6. Samples: 5781968. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) +[2023-07-17 01:06:26,077][282552] Avg episode reward: [(0, '684.267')] +[2023-07-17 01:06:26,338][282837] Updated weights for policy 0, policy_version 11360 (0.0004) +[2023-07-17 01:06:29,622][282837] Updated weights for policy 0, policy_version 11440 (0.0005) +[2023-07-17 01:06:31,076][282552] Fps is (10 sec: 12697.4, 60 sec: 13312.0, 300 sec: 12843.4). Total num frames: 5873664. Throughput: 0: 13489.1. Samples: 5858148. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) +[2023-07-17 01:06:31,076][282552] Avg episode reward: [(0, '664.341')] +[2023-07-17 01:06:31,080][282793] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000011472_5873664.pth... +[2023-07-17 01:06:31,083][282793] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000010688_5472256.pth +[2023-07-17 01:06:32,883][282837] Updated weights for policy 0, policy_version 11520 (0.0005) +[2023-07-17 01:06:36,076][282552] Fps is (10 sec: 12288.1, 60 sec: 13312.0, 300 sec: 12843.4). Total num frames: 5935104. Throughput: 0: 13326.0. Samples: 5932732. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) +[2023-07-17 01:06:36,082][282552] Avg episode reward: [(0, '682.667')] +[2023-07-17 01:06:36,227][282837] Updated weights for policy 0, policy_version 11600 (0.0005) +[2023-07-17 01:06:39,522][282837] Updated weights for policy 0, policy_version 11680 (0.0005) +[2023-07-17 01:06:41,076][282552] Fps is (10 sec: 12288.1, 60 sec: 13312.0, 300 sec: 12843.4). Total num frames: 5996544. Throughput: 0: 13243.6. Samples: 5969988. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:06:41,101][282552] Avg episode reward: [(0, '687.134')] +[2023-07-17 01:06:42,755][282837] Updated weights for policy 0, policy_version 11760 (0.0005) +[2023-07-17 01:06:45,899][282837] Updated weights for policy 0, policy_version 11840 (0.0005) +[2023-07-17 01:06:46,076][282552] Fps is (10 sec: 12697.5, 60 sec: 13243.7, 300 sec: 12857.3). Total num frames: 6062080. Throughput: 0: 13079.7. Samples: 6045760. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:06:46,106][282552] Avg episode reward: [(0, '670.815')] +[2023-07-17 01:06:46,109][282793] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000011840_6062080.pth... +[2023-07-17 01:06:46,112][282793] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000011088_5677056.pth +[2023-07-17 01:06:48,886][282837] Updated weights for policy 0, policy_version 11920 (0.0003) +[2023-07-17 01:06:51,076][282552] Fps is (10 sec: 13516.8, 60 sec: 13243.7, 300 sec: 12871.2). Total num frames: 6131712. Throughput: 0: 13087.3. Samples: 6127808. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) +[2023-07-17 01:06:51,171][282552] Avg episode reward: [(0, '676.630')] +[2023-07-17 01:06:51,830][282837] Updated weights for policy 0, policy_version 12000 (0.0004) +[2023-07-17 01:06:54,859][282837] Updated weights for policy 0, policy_version 12080 (0.0004) +[2023-07-17 01:06:56,076][282552] Fps is (10 sec: 13926.4, 60 sec: 13243.7, 300 sec: 12871.2). Total num frames: 6201344. Throughput: 0: 13101.4. Samples: 6168832. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) +[2023-07-17 01:06:56,085][282552] Avg episode reward: [(0, '692.943')] +[2023-07-17 01:06:56,085][282793] Saving new best policy, reward=692.943! +[2023-07-17 01:06:57,879][282837] Updated weights for policy 0, policy_version 12160 (0.0004) +[2023-07-17 01:07:00,914][282837] Updated weights for policy 0, policy_version 12240 (0.0004) +[2023-07-17 01:07:01,076][282552] Fps is (10 sec: 13516.8, 60 sec: 13243.7, 300 sec: 12871.2). Total num frames: 6266880. Throughput: 0: 13107.9. Samples: 6250504. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:07:01,076][282552] Avg episode reward: [(0, '681.597')] +[2023-07-17 01:07:01,079][282793] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000012240_6266880.pth... +[2023-07-17 01:07:01,082][282793] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000011472_5873664.pth +[2023-07-17 01:07:03,848][282837] Updated weights for policy 0, policy_version 12320 (0.0003) +[2023-07-17 01:07:06,076][282552] Fps is (10 sec: 13516.8, 60 sec: 13243.7, 300 sec: 12898.9). Total num frames: 6336512. Throughput: 0: 13129.9. Samples: 6333448. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:07:06,076][282552] Avg episode reward: [(0, '672.264')] +[2023-07-17 01:07:06,824][282837] Updated weights for policy 0, policy_version 12400 (0.0004) +[2023-07-17 01:07:10,088][282837] Updated weights for policy 0, policy_version 12480 (0.0005) +[2023-07-17 01:07:11,076][282552] Fps is (10 sec: 13107.4, 60 sec: 13107.2, 300 sec: 12898.9). Total num frames: 6397952. Throughput: 0: 13135.9. Samples: 6373084. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:07:11,076][282552] Avg episode reward: [(0, '681.789')] +[2023-07-17 01:07:13,395][282837] Updated weights for policy 0, policy_version 12560 (0.0005) +[2023-07-17 01:07:16,076][282552] Fps is (10 sec: 12697.6, 60 sec: 13107.2, 300 sec: 12899.0). Total num frames: 6463488. Throughput: 0: 13089.5. Samples: 6447176. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) +[2023-07-17 01:07:16,076][282552] Avg episode reward: [(0, '689.432')] +[2023-07-17 01:07:16,079][282793] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000012624_6463488.pth... +[2023-07-17 01:07:16,082][282793] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000011840_6062080.pth +[2023-07-17 01:07:16,517][282837] Updated weights for policy 0, policy_version 12640 (0.0004) +[2023-07-17 01:07:19,516][282837] Updated weights for policy 0, policy_version 12720 (0.0003) +[2023-07-17 01:07:21,076][282552] Fps is (10 sec: 13516.7, 60 sec: 13107.2, 300 sec: 12926.7). Total num frames: 6533120. Throughput: 0: 13251.1. Samples: 6529032. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) +[2023-07-17 01:07:21,076][282552] Avg episode reward: [(0, '683.192')] +[2023-07-17 01:07:22,548][282837] Updated weights for policy 0, policy_version 12800 (0.0004) +[2023-07-17 01:07:25,608][282837] Updated weights for policy 0, policy_version 12880 (0.0004) +[2023-07-17 01:07:26,076][282552] Fps is (10 sec: 13516.8, 60 sec: 13107.2, 300 sec: 12926.7). Total num frames: 6598656. Throughput: 0: 13317.0. Samples: 6569252. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) +[2023-07-17 01:07:26,076][282552] Avg episode reward: [(0, '698.210')] +[2023-07-17 01:07:26,077][282793] Saving new best policy, reward=698.210! +[2023-07-17 01:07:28,899][282837] Updated weights for policy 0, policy_version 12960 (0.0005) +[2023-07-17 01:07:31,076][282552] Fps is (10 sec: 12697.6, 60 sec: 13107.2, 300 sec: 12926.7). Total num frames: 6660096. Throughput: 0: 13327.1. Samples: 6645480. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) +[2023-07-17 01:07:31,076][282552] Avg episode reward: [(0, '681.959')] +[2023-07-17 01:07:31,079][282793] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000013008_6660096.pth... +[2023-07-17 01:07:31,082][282793] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000012240_6266880.pth +[2023-07-17 01:07:32,235][282837] Updated weights for policy 0, policy_version 13040 (0.0005) +[2023-07-17 01:07:35,580][282837] Updated weights for policy 0, policy_version 13120 (0.0005) +[2023-07-17 01:07:36,076][282552] Fps is (10 sec: 12288.0, 60 sec: 13107.2, 300 sec: 12912.8). Total num frames: 6721536. Throughput: 0: 13133.6. Samples: 6718820. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:07:36,076][282552] Avg episode reward: [(0, '693.352')] +[2023-07-17 01:07:38,742][282837] Updated weights for policy 0, policy_version 13200 (0.0005) +[2023-07-17 01:07:41,076][282552] Fps is (10 sec: 12697.6, 60 sec: 13175.5, 300 sec: 12898.9). Total num frames: 6787072. Throughput: 0: 13101.5. Samples: 6758400. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:07:41,076][282552] Avg episode reward: [(0, '688.886')] +[2023-07-17 01:07:41,908][282837] Updated weights for policy 0, policy_version 13280 (0.0004) +[2023-07-17 01:07:44,997][282837] Updated weights for policy 0, policy_version 13360 (0.0004) +[2023-07-17 01:07:46,076][282552] Fps is (10 sec: 13107.1, 60 sec: 13175.5, 300 sec: 12912.8). Total num frames: 6852608. Throughput: 0: 13017.4. Samples: 6836288. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) +[2023-07-17 01:07:46,076][282552] Avg episode reward: [(0, '663.792')] +[2023-07-17 01:07:46,079][282793] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000013384_6852608.pth... +[2023-07-17 01:07:46,082][282793] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000012624_6463488.pth +[2023-07-17 01:07:48,152][282837] Updated weights for policy 0, policy_version 13440 (0.0005) +[2023-07-17 01:07:51,076][282552] Fps is (10 sec: 12697.6, 60 sec: 13038.9, 300 sec: 12912.8). Total num frames: 6914048. Throughput: 0: 12868.4. Samples: 6912528. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) +[2023-07-17 01:07:51,076][282552] Avg episode reward: [(0, '692.977')] +[2023-07-17 01:07:51,513][282837] Updated weights for policy 0, policy_version 13520 (0.0005) +[2023-07-17 01:07:54,647][282837] Updated weights for policy 0, policy_version 13600 (0.0005) +[2023-07-17 01:07:56,076][282552] Fps is (10 sec: 12697.7, 60 sec: 12970.7, 300 sec: 12926.7). Total num frames: 6979584. Throughput: 0: 12834.2. Samples: 6950624. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) +[2023-07-17 01:07:56,076][282552] Avg episode reward: [(0, '690.973')] +[2023-07-17 01:07:57,773][282837] Updated weights for policy 0, policy_version 13680 (0.0004) +[2023-07-17 01:08:01,076][282552] Fps is (10 sec: 12697.6, 60 sec: 12902.4, 300 sec: 12912.8). Total num frames: 7041024. Throughput: 0: 12917.8. Samples: 7028476. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) +[2023-07-17 01:08:01,076][282552] Avg episode reward: [(0, '677.018')] +[2023-07-17 01:08:01,098][282793] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000013760_7045120.pth... +[2023-07-17 01:08:01,098][282837] Updated weights for policy 0, policy_version 13760 (0.0005) +[2023-07-17 01:08:01,101][282793] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000013008_6660096.pth +[2023-07-17 01:08:04,259][282837] Updated weights for policy 0, policy_version 13840 (0.0005) +[2023-07-17 01:08:06,076][282552] Fps is (10 sec: 12697.6, 60 sec: 12834.1, 300 sec: 12912.8). Total num frames: 7106560. Throughput: 0: 12788.4. Samples: 7104512. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:08:06,076][282552] Avg episode reward: [(0, '685.102')] +[2023-07-17 01:08:07,562][282837] Updated weights for policy 0, policy_version 13920 (0.0005) +[2023-07-17 01:08:10,821][282837] Updated weights for policy 0, policy_version 14000 (0.0005) +[2023-07-17 01:08:11,076][282552] Fps is (10 sec: 12697.6, 60 sec: 12834.1, 300 sec: 12885.0). Total num frames: 7168000. Throughput: 0: 12707.1. Samples: 7141072. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:08:11,076][282552] Avg episode reward: [(0, '684.898')] +[2023-07-17 01:08:14,154][282837] Updated weights for policy 0, policy_version 14080 (0.0005) +[2023-07-17 01:08:16,076][282552] Fps is (10 sec: 12697.6, 60 sec: 12834.1, 300 sec: 12885.0). Total num frames: 7233536. Throughput: 0: 12673.0. Samples: 7215764. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:08:16,076][282552] Avg episode reward: [(0, '678.208')] +[2023-07-17 01:08:16,080][282793] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000014128_7233536.pth... +[2023-07-17 01:08:16,083][282793] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000013384_6852608.pth +[2023-07-17 01:08:17,280][282837] Updated weights for policy 0, policy_version 14160 (0.0005) +[2023-07-17 01:08:20,543][282837] Updated weights for policy 0, policy_version 14240 (0.0005) +[2023-07-17 01:08:21,076][282552] Fps is (10 sec: 12697.6, 60 sec: 12697.6, 300 sec: 12885.0). Total num frames: 7294976. Throughput: 0: 12759.1. Samples: 7292980. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:08:21,076][282552] Avg episode reward: [(0, '690.106')] +[2023-07-17 01:08:23,849][282837] Updated weights for policy 0, policy_version 14320 (0.0005) +[2023-07-17 01:08:26,076][282552] Fps is (10 sec: 12288.1, 60 sec: 12629.3, 300 sec: 12885.0). Total num frames: 7356416. Throughput: 0: 12705.1. Samples: 7330128. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:08:26,076][282552] Avg episode reward: [(0, '701.951')] +[2023-07-17 01:08:26,077][282793] Saving new best policy, reward=701.951! +[2023-07-17 01:08:27,186][282837] Updated weights for policy 0, policy_version 14400 (0.0005) +[2023-07-17 01:08:30,461][282837] Updated weights for policy 0, policy_version 14480 (0.0005) +[2023-07-17 01:08:31,076][282552] Fps is (10 sec: 12287.9, 60 sec: 12629.3, 300 sec: 12885.0). Total num frames: 7417856. Throughput: 0: 12622.7. Samples: 7404308. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:08:31,076][282552] Avg episode reward: [(0, '695.955')] +[2023-07-17 01:08:31,126][282793] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000014496_7421952.pth... +[2023-07-17 01:08:31,129][282793] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000013760_7045120.pth +[2023-07-17 01:08:33,724][282837] Updated weights for policy 0, policy_version 14560 (0.0005) +[2023-07-17 01:08:36,076][282552] Fps is (10 sec: 12697.5, 60 sec: 12697.6, 300 sec: 12898.9). Total num frames: 7483392. Throughput: 0: 12596.3. Samples: 7479360. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) +[2023-07-17 01:08:36,076][282552] Avg episode reward: [(0, '695.928')] +[2023-07-17 01:08:37,089][282837] Updated weights for policy 0, policy_version 14640 (0.0006) +[2023-07-17 01:08:40,240][282837] Updated weights for policy 0, policy_version 14720 (0.0004) +[2023-07-17 01:08:41,076][282552] Fps is (10 sec: 12697.6, 60 sec: 12629.3, 300 sec: 12898.9). Total num frames: 7544832. Throughput: 0: 12568.9. Samples: 7516224. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) +[2023-07-17 01:08:41,076][282552] Avg episode reward: [(0, '690.756')] +[2023-07-17 01:08:43,285][282837] Updated weights for policy 0, policy_version 14800 (0.0004) +[2023-07-17 01:08:46,076][282552] Fps is (10 sec: 13107.2, 60 sec: 12697.6, 300 sec: 12926.7). Total num frames: 7614464. Throughput: 0: 12623.3. Samples: 7596524. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) +[2023-07-17 01:08:46,076][282552] Avg episode reward: [(0, '697.330')] +[2023-07-17 01:08:46,080][282793] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000014872_7614464.pth... +[2023-07-17 01:08:46,083][282793] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000014128_7233536.pth +[2023-07-17 01:08:46,331][282837] Updated weights for policy 0, policy_version 14880 (0.0004) +[2023-07-17 01:08:49,367][282837] Updated weights for policy 0, policy_version 14960 (0.0004) +[2023-07-17 01:08:51,076][282552] Fps is (10 sec: 13517.0, 60 sec: 12765.9, 300 sec: 12926.7). Total num frames: 7680000. Throughput: 0: 12743.0. Samples: 7677944. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:08:51,076][282552] Avg episode reward: [(0, '691.711')] +[2023-07-17 01:08:52,419][282837] Updated weights for policy 0, policy_version 15040 (0.0004) +[2023-07-17 01:08:55,449][282837] Updated weights for policy 0, policy_version 15120 (0.0004) +[2023-07-17 01:08:56,076][282552] Fps is (10 sec: 13516.9, 60 sec: 12834.1, 300 sec: 12954.5). Total num frames: 7749632. Throughput: 0: 12821.1. Samples: 7718020. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:08:56,076][282552] Avg episode reward: [(0, '684.251')] +[2023-07-17 01:08:58,468][282837] Updated weights for policy 0, policy_version 15200 (0.0004) +[2023-07-17 01:09:01,076][282552] Fps is (10 sec: 13516.6, 60 sec: 12902.4, 300 sec: 12954.5). Total num frames: 7815168. Throughput: 0: 12957.4. Samples: 7798848. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) +[2023-07-17 01:09:01,076][282552] Avg episode reward: [(0, '691.913')] +[2023-07-17 01:09:01,080][282793] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000015264_7815168.pth... +[2023-07-17 01:09:01,083][282793] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000014496_7421952.pth +[2023-07-17 01:09:01,500][282837] Updated weights for policy 0, policy_version 15280 (0.0004) +[2023-07-17 01:09:04,507][282837] Updated weights for policy 0, policy_version 15360 (0.0004) +[2023-07-17 01:09:06,076][282552] Fps is (10 sec: 13516.7, 60 sec: 12970.7, 300 sec: 12982.2). Total num frames: 7884800. Throughput: 0: 13061.9. Samples: 7880768. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) +[2023-07-17 01:09:06,076][282552] Avg episode reward: [(0, '691.680')] +[2023-07-17 01:09:07,525][282837] Updated weights for policy 0, policy_version 15440 (0.0004) +[2023-07-17 01:09:10,559][282837] Updated weights for policy 0, policy_version 15520 (0.0004) +[2023-07-17 01:09:11,076][282552] Fps is (10 sec: 13516.9, 60 sec: 13038.9, 300 sec: 12996.1). Total num frames: 7950336. Throughput: 0: 13143.7. Samples: 7921592. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:09:11,076][282552] Avg episode reward: [(0, '683.722')] +[2023-07-17 01:09:13,636][282837] Updated weights for policy 0, policy_version 15600 (0.0004) +[2023-07-17 01:09:16,076][282552] Fps is (10 sec: 13516.8, 60 sec: 13107.2, 300 sec: 13023.9). Total num frames: 8019968. Throughput: 0: 13271.6. Samples: 8001532. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:09:16,076][282552] Avg episode reward: [(0, '698.612')] +[2023-07-17 01:09:16,080][282793] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000015664_8019968.pth... +[2023-07-17 01:09:16,083][282793] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000014872_7614464.pth +[2023-07-17 01:09:16,703][282837] Updated weights for policy 0, policy_version 15680 (0.0004) +[2023-07-17 01:09:19,833][282837] Updated weights for policy 0, policy_version 15760 (0.0004) +[2023-07-17 01:09:21,076][282552] Fps is (10 sec: 13516.8, 60 sec: 13175.5, 300 sec: 13037.8). Total num frames: 8085504. Throughput: 0: 13380.3. Samples: 8081472. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:09:21,076][282552] Avg episode reward: [(0, '677.698')] +[2023-07-17 01:09:22,814][282837] Updated weights for policy 0, policy_version 15840 (0.0004) +[2023-07-17 01:09:25,836][282837] Updated weights for policy 0, policy_version 15920 (0.0004) +[2023-07-17 01:09:26,076][282552] Fps is (10 sec: 13107.3, 60 sec: 13243.7, 300 sec: 13051.7). Total num frames: 8151040. Throughput: 0: 13468.2. Samples: 8122292. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:09:26,076][282552] Avg episode reward: [(0, '698.138')] +[2023-07-17 01:09:28,836][282837] Updated weights for policy 0, policy_version 16000 (0.0004) +[2023-07-17 01:09:31,076][282552] Fps is (10 sec: 13516.6, 60 sec: 13380.2, 300 sec: 13079.4). Total num frames: 8220672. Throughput: 0: 13503.6. Samples: 8204188. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:09:31,076][282552] Avg episode reward: [(0, '693.007')] +[2023-07-17 01:09:31,080][282793] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000016056_8220672.pth... +[2023-07-17 01:09:31,083][282793] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000015264_7815168.pth +[2023-07-17 01:09:31,906][282837] Updated weights for policy 0, policy_version 16080 (0.0004) +[2023-07-17 01:09:34,934][282837] Updated weights for policy 0, policy_version 16160 (0.0004) +[2023-07-17 01:09:36,076][282552] Fps is (10 sec: 13516.7, 60 sec: 13380.3, 300 sec: 13079.4). Total num frames: 8286208. Throughput: 0: 13483.6. Samples: 8284708. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:09:36,076][282552] Avg episode reward: [(0, '691.482')] +[2023-07-17 01:09:37,937][282837] Updated weights for policy 0, policy_version 16240 (0.0004) +[2023-07-17 01:09:41,030][282837] Updated weights for policy 0, policy_version 16320 (0.0004) +[2023-07-17 01:09:41,076][282552] Fps is (10 sec: 13516.9, 60 sec: 13516.8, 300 sec: 13107.2). Total num frames: 8355840. Throughput: 0: 13491.4. Samples: 8325136. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:09:41,076][282552] Avg episode reward: [(0, '691.942')] +[2023-07-17 01:09:44,073][282837] Updated weights for policy 0, policy_version 16400 (0.0004) +[2023-07-17 01:09:46,076][282552] Fps is (10 sec: 13516.6, 60 sec: 13448.5, 300 sec: 13121.1). Total num frames: 8421376. Throughput: 0: 13471.3. Samples: 8405056. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:09:46,076][282552] Avg episode reward: [(0, '697.139')] +[2023-07-17 01:09:46,080][282793] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000016448_8421376.pth... +[2023-07-17 01:09:46,083][282793] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000015664_8019968.pth +[2023-07-17 01:09:47,160][282837] Updated weights for policy 0, policy_version 16480 (0.0004) +[2023-07-17 01:09:50,310][282837] Updated weights for policy 0, policy_version 16560 (0.0005) +[2023-07-17 01:09:51,076][282552] Fps is (10 sec: 13107.2, 60 sec: 13448.5, 300 sec: 13121.1). Total num frames: 8486912. Throughput: 0: 13406.5. Samples: 8484060. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:09:51,077][282552] Avg episode reward: [(0, '695.236')] +[2023-07-17 01:09:53,307][282837] Updated weights for policy 0, policy_version 16640 (0.0004) +[2023-07-17 01:09:56,076][282552] Fps is (10 sec: 13107.4, 60 sec: 13380.3, 300 sec: 13121.1). Total num frames: 8552448. Throughput: 0: 13410.7. Samples: 8525076. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) +[2023-07-17 01:09:56,077][282552] Avg episode reward: [(0, '688.670')] +[2023-07-17 01:09:56,404][282837] Updated weights for policy 0, policy_version 16720 (0.0004) +[2023-07-17 01:09:59,459][282837] Updated weights for policy 0, policy_version 16800 (0.0004) +[2023-07-17 01:10:01,076][282552] Fps is (10 sec: 13516.7, 60 sec: 13448.5, 300 sec: 13135.0). Total num frames: 8622080. Throughput: 0: 13410.2. Samples: 8604992. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) +[2023-07-17 01:10:01,077][282552] Avg episode reward: [(0, '696.934')] +[2023-07-17 01:10:01,081][282793] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000016840_8622080.pth... +[2023-07-17 01:10:01,083][282793] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000016056_8220672.pth +[2023-07-17 01:10:02,612][282837] Updated weights for policy 0, policy_version 16880 (0.0005) +[2023-07-17 01:10:05,686][282837] Updated weights for policy 0, policy_version 16960 (0.0004) +[2023-07-17 01:10:06,076][282552] Fps is (10 sec: 13516.8, 60 sec: 13380.3, 300 sec: 13148.9). Total num frames: 8687616. Throughput: 0: 13380.4. Samples: 8683592. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) +[2023-07-17 01:10:06,077][282552] Avg episode reward: [(0, '682.925')] +[2023-07-17 01:10:09,004][282837] Updated weights for policy 0, policy_version 17040 (0.0005) +[2023-07-17 01:10:11,076][282552] Fps is (10 sec: 12697.6, 60 sec: 13312.0, 300 sec: 13121.1). Total num frames: 8749056. Throughput: 0: 13292.7. Samples: 8720464. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:10:11,077][282552] Avg episode reward: [(0, '677.719')] +[2023-07-17 01:10:12,164][282837] Updated weights for policy 0, policy_version 17120 (0.0005) +[2023-07-17 01:10:15,490][282837] Updated weights for policy 0, policy_version 17200 (0.0005) +[2023-07-17 01:10:16,076][282552] Fps is (10 sec: 12287.9, 60 sec: 13175.5, 300 sec: 13107.2). Total num frames: 8810496. Throughput: 0: 13166.3. Samples: 8796672. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:10:16,077][282552] Avg episode reward: [(0, '694.952')] +[2023-07-17 01:10:16,080][282793] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000017208_8810496.pth... +[2023-07-17 01:10:16,083][282793] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000016448_8421376.pth +[2023-07-17 01:10:18,799][282837] Updated weights for policy 0, policy_version 17280 (0.0005) +[2023-07-17 01:10:21,076][282552] Fps is (10 sec: 12288.0, 60 sec: 13107.2, 300 sec: 13093.3). Total num frames: 8871936. Throughput: 0: 13015.5. Samples: 8870404. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) +[2023-07-17 01:10:21,077][282552] Avg episode reward: [(0, '688.326')] +[2023-07-17 01:10:22,211][282837] Updated weights for policy 0, policy_version 17360 (0.0006) +[2023-07-17 01:10:25,664][282837] Updated weights for policy 0, policy_version 17440 (0.0005) +[2023-07-17 01:10:26,076][282552] Fps is (10 sec: 12288.1, 60 sec: 13038.9, 300 sec: 13079.4). Total num frames: 8933376. Throughput: 0: 12905.1. Samples: 8905864. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) +[2023-07-17 01:10:26,080][282552] Avg episode reward: [(0, '690.637')] +[2023-07-17 01:10:28,969][282837] Updated weights for policy 0, policy_version 17520 (0.0005) +[2023-07-17 01:10:31,076][282552] Fps is (10 sec: 12287.9, 60 sec: 12902.4, 300 sec: 13079.4). Total num frames: 8994816. Throughput: 0: 12771.5. Samples: 8979772. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) +[2023-07-17 01:10:31,086][282552] Avg episode reward: [(0, '675.311')] +[2023-07-17 01:10:31,116][282793] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000017576_8998912.pth... +[2023-07-17 01:10:31,118][282793] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000016840_8622080.pth +[2023-07-17 01:10:32,012][282837] Updated weights for policy 0, policy_version 17600 (0.0004) +[2023-07-17 01:10:35,117][282837] Updated weights for policy 0, policy_version 17680 (0.0004) +[2023-07-17 01:10:36,076][282552] Fps is (10 sec: 12697.6, 60 sec: 12902.4, 300 sec: 13093.3). Total num frames: 9060352. Throughput: 0: 12798.6. Samples: 9059996. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) +[2023-07-17 01:10:36,077][282552] Avg episode reward: [(0, '685.667')] +[2023-07-17 01:10:38,223][282837] Updated weights for policy 0, policy_version 17760 (0.0004) +[2023-07-17 01:10:41,076][282552] Fps is (10 sec: 13516.9, 60 sec: 12902.4, 300 sec: 13093.3). Total num frames: 9129984. Throughput: 0: 12759.4. Samples: 9099248. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) +[2023-07-17 01:10:41,077][282552] Avg episode reward: [(0, '685.753')] +[2023-07-17 01:10:41,316][282837] Updated weights for policy 0, policy_version 17840 (0.0004) +[2023-07-17 01:10:44,450][282837] Updated weights for policy 0, policy_version 17920 (0.0004) +[2023-07-17 01:10:46,076][282552] Fps is (10 sec: 13516.6, 60 sec: 12902.4, 300 sec: 13079.4). Total num frames: 9195520. Throughput: 0: 12746.1. Samples: 9178568. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:10:46,076][282552] Avg episode reward: [(0, '682.046')] +[2023-07-17 01:10:46,080][282793] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000017960_9195520.pth... +[2023-07-17 01:10:46,082][282793] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000017208_8810496.pth +[2023-07-17 01:10:47,613][282837] Updated weights for policy 0, policy_version 18000 (0.0005) +[2023-07-17 01:10:50,761][282837] Updated weights for policy 0, policy_version 18080 (0.0004) +[2023-07-17 01:10:51,076][282552] Fps is (10 sec: 12697.6, 60 sec: 12834.1, 300 sec: 13051.7). Total num frames: 9256960. Throughput: 0: 12725.2. Samples: 9256228. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:10:51,076][282552] Avg episode reward: [(0, '674.266')] +[2023-07-17 01:10:54,052][282837] Updated weights for policy 0, policy_version 18160 (0.0004) +[2023-07-17 01:10:56,076][282552] Fps is (10 sec: 12697.8, 60 sec: 12834.2, 300 sec: 13051.7). Total num frames: 9322496. Throughput: 0: 12741.5. Samples: 9293832. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:10:56,076][282552] Avg episode reward: [(0, '662.766')] +[2023-07-17 01:10:57,503][282837] Updated weights for policy 0, policy_version 18240 (0.0005) +[2023-07-17 01:11:00,976][282837] Updated weights for policy 0, policy_version 18320 (0.0004) +[2023-07-17 01:11:01,076][282552] Fps is (10 sec: 12288.0, 60 sec: 12629.3, 300 sec: 13010.0). Total num frames: 9379840. Throughput: 0: 12631.7. Samples: 9365096. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) +[2023-07-17 01:11:01,076][282552] Avg episode reward: [(0, '674.368')] +[2023-07-17 01:11:01,079][282793] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000018320_9379840.pth... +[2023-07-17 01:11:01,082][282793] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000017576_8998912.pth +[2023-07-17 01:11:04,458][282837] Updated weights for policy 0, policy_version 18400 (0.0005) +[2023-07-17 01:11:06,076][282552] Fps is (10 sec: 11468.8, 60 sec: 12492.8, 300 sec: 12968.4). Total num frames: 9437184. Throughput: 0: 12558.0. Samples: 9435512. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) +[2023-07-17 01:11:06,076][282552] Avg episode reward: [(0, '683.792')] +[2023-07-17 01:11:08,029][282837] Updated weights for policy 0, policy_version 18480 (0.0005) +[2023-07-17 01:11:11,076][282552] Fps is (10 sec: 11468.9, 60 sec: 12424.5, 300 sec: 12940.6). Total num frames: 9494528. Throughput: 0: 12535.5. Samples: 9469960. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) +[2023-07-17 01:11:11,076][282552] Avg episode reward: [(0, '672.574')] +[2023-07-17 01:11:11,509][282837] Updated weights for policy 0, policy_version 18560 (0.0005) +[2023-07-17 01:11:14,743][282837] Updated weights for policy 0, policy_version 18640 (0.0004) +[2023-07-17 01:11:16,076][282552] Fps is (10 sec: 11878.2, 60 sec: 12424.5, 300 sec: 12912.8). Total num frames: 9555968. Throughput: 0: 12531.3. Samples: 9543680. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) +[2023-07-17 01:11:16,076][282552] Avg episode reward: [(0, '674.587')] +[2023-07-17 01:11:16,096][282793] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000018672_9560064.pth... +[2023-07-17 01:11:16,098][282793] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000017960_9195520.pth +[2023-07-17 01:11:18,220][282837] Updated weights for policy 0, policy_version 18720 (0.0005) +[2023-07-17 01:11:21,076][282552] Fps is (10 sec: 12288.0, 60 sec: 12424.5, 300 sec: 12898.9). Total num frames: 9617408. Throughput: 0: 12303.4. Samples: 9613648. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) +[2023-07-17 01:11:21,076][282552] Avg episode reward: [(0, '663.003')] +[2023-07-17 01:11:21,663][282837] Updated weights for policy 0, policy_version 18800 (0.0005) +[2023-07-17 01:11:25,168][282837] Updated weights for policy 0, policy_version 18880 (0.0005) +[2023-07-17 01:11:26,076][282552] Fps is (10 sec: 11878.5, 60 sec: 12356.3, 300 sec: 12885.0). Total num frames: 9674752. Throughput: 0: 12234.3. Samples: 9649792. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:11:26,076][282552] Avg episode reward: [(0, '663.278')] +[2023-07-17 01:11:28,406][282837] Updated weights for policy 0, policy_version 18960 (0.0004) +[2023-07-17 01:11:31,076][282552] Fps is (10 sec: 12287.9, 60 sec: 12424.5, 300 sec: 12898.9). Total num frames: 9740288. Throughput: 0: 12120.2. Samples: 9723976. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) +[2023-07-17 01:11:31,077][282552] Avg episode reward: [(0, '670.419')] +[2023-07-17 01:11:31,080][282793] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000019024_9740288.pth... +[2023-07-17 01:11:31,083][282793] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000018320_9379840.pth +[2023-07-17 01:11:31,575][282837] Updated weights for policy 0, policy_version 19040 (0.0004) +[2023-07-17 01:11:34,752][282837] Updated weights for policy 0, policy_version 19120 (0.0003) +[2023-07-17 01:11:36,076][282552] Fps is (10 sec: 13107.2, 60 sec: 12424.5, 300 sec: 12912.8). Total num frames: 9805824. Throughput: 0: 12123.8. Samples: 9801800. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) +[2023-07-17 01:11:36,076][282552] Avg episode reward: [(0, '655.986')] +[2023-07-17 01:11:37,897][282837] Updated weights for policy 0, policy_version 19200 (0.0004) +[2023-07-17 01:11:41,076][282552] Fps is (10 sec: 12697.6, 60 sec: 12288.0, 300 sec: 12898.9). Total num frames: 9867264. Throughput: 0: 12141.0. Samples: 9840180. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) +[2023-07-17 01:11:41,076][282552] Avg episode reward: [(0, '658.884')] +[2023-07-17 01:11:41,347][282837] Updated weights for policy 0, policy_version 19280 (0.0005) +[2023-07-17 01:11:44,682][282837] Updated weights for policy 0, policy_version 19360 (0.0004) +[2023-07-17 01:11:46,076][282552] Fps is (10 sec: 12287.9, 60 sec: 12219.7, 300 sec: 12871.2). Total num frames: 9928704. Throughput: 0: 12162.1. Samples: 9912392. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) +[2023-07-17 01:11:46,076][282552] Avg episode reward: [(0, '661.463')] +[2023-07-17 01:11:46,079][282793] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000019392_9928704.pth... +[2023-07-17 01:11:46,082][282793] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000018672_9560064.pth +[2023-07-17 01:11:47,883][282837] Updated weights for policy 0, policy_version 19440 (0.0004) +[2023-07-17 01:11:51,076][282552] Fps is (10 sec: 12288.0, 60 sec: 12219.7, 300 sec: 12843.4). Total num frames: 9990144. Throughput: 0: 12308.0. Samples: 9989372. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) +[2023-07-17 01:11:51,076][282552] Avg episode reward: [(0, '640.055')] +[2023-07-17 01:11:51,099][282837] Updated weights for policy 0, policy_version 19520 (0.0004) +[2023-07-17 01:11:51,736][282793] Early stopping after 2 epochs (8 sgd steps), loss delta 0.0000006 +[2023-07-17 01:11:52,079][282793] Early stopping after 2 epochs (8 sgd steps), loss delta 0.0000000 +[2023-07-17 01:11:52,080][282839] Stopping RolloutWorker_w3... +[2023-07-17 01:11:52,080][282842] Stopping RolloutWorker_w4... +[2023-07-17 01:11:52,080][282838] Stopping RolloutWorker_w1... +[2023-07-17 01:11:52,080][282906] Stopping RolloutWorker_w6... +[2023-07-17 01:11:52,080][282843] Stopping RolloutWorker_w5... +[2023-07-17 01:11:52,080][282938] Stopping RolloutWorker_w7... +[2023-07-17 01:11:52,080][282839] Loop rollout_proc3_evt_loop terminating... +[2023-07-17 01:11:52,080][282841] Stopping RolloutWorker_w0... +[2023-07-17 01:11:52,080][282842] Loop rollout_proc4_evt_loop terminating... +[2023-07-17 01:11:52,080][282840] Stopping RolloutWorker_w2... +[2023-07-17 01:11:52,080][282838] Loop rollout_proc1_evt_loop terminating... +[2023-07-17 01:11:52,080][282843] Loop rollout_proc5_evt_loop terminating... +[2023-07-17 01:11:52,080][282938] Loop rollout_proc7_evt_loop terminating... +[2023-07-17 01:11:52,080][282906] Loop rollout_proc6_evt_loop terminating... +[2023-07-17 01:11:52,080][282841] Loop rollout_proc0_evt_loop terminating... +[2023-07-17 01:11:52,080][282840] Loop rollout_proc2_evt_loop terminating... +[2023-07-17 01:11:52,080][282552] Component RolloutWorker_w3 stopped! +[2023-07-17 01:11:52,080][282552] Component RolloutWorker_w4 stopped! +[2023-07-17 01:11:52,081][282793] Stopping Batcher_0... +[2023-07-17 01:11:52,081][282552] Component RolloutWorker_w6 stopped! +[2023-07-17 01:11:52,081][282552] Component RolloutWorker_w1 stopped! +[2023-07-17 01:11:52,081][282793] Loop batcher_evt_loop terminating... +[2023-07-17 01:11:52,081][282552] Component RolloutWorker_w5 stopped! +[2023-07-17 01:11:52,081][282793] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000019544_10006528.pth... +[2023-07-17 01:11:52,081][282552] Component RolloutWorker_w7 stopped! +[2023-07-17 01:11:52,082][282552] Component RolloutWorker_w2 stopped! +[2023-07-17 01:11:52,082][282552] Component RolloutWorker_w0 stopped! +[2023-07-17 01:11:52,082][282552] Component Batcher_0 stopped! +[2023-07-17 01:11:52,084][282793] Removing /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000019024_9740288.pth +[2023-07-17 01:11:52,084][282793] Saving /home/qgallouedec/data/gia/data/envs/metaworld/train_dir/handle-pull-v2/checkpoint_p0/checkpoint_000019544_10006528.pth... +[2023-07-17 01:11:52,087][282793] Stopping LearnerWorker_p0... +[2023-07-17 01:11:52,087][282793] Loop learner_proc0_evt_loop terminating... +[2023-07-17 01:11:52,087][282552] Component LearnerWorker_p0 stopped! +[2023-07-17 01:11:52,147][282837] Weights refcount: 2 0 +[2023-07-17 01:11:52,148][282837] Stopping InferenceWorker_p0-w0... +[2023-07-17 01:11:52,148][282837] Loop inference_proc0-0_evt_loop terminating... +[2023-07-17 01:11:52,148][282552] Component InferenceWorker_p0-w0 stopped! +[2023-07-17 01:11:52,149][282552] Waiting for process learner_proc0 to stop... +[2023-07-17 01:11:52,671][282552] Waiting for process inference_proc0-0 to join... +[2023-07-17 01:11:52,685][282552] Waiting for process rollout_proc0 to join... +[2023-07-17 01:11:52,685][282552] Waiting for process rollout_proc1 to join... +[2023-07-17 01:11:52,686][282552] Waiting for process rollout_proc2 to join... +[2023-07-17 01:11:52,686][282552] Waiting for process rollout_proc3 to join... +[2023-07-17 01:11:52,686][282552] Waiting for process rollout_proc4 to join... +[2023-07-17 01:11:52,686][282552] Waiting for process rollout_proc5 to join... +[2023-07-17 01:11:52,686][282552] Waiting for process rollout_proc6 to join... +[2023-07-17 01:11:52,687][282552] Waiting for process rollout_proc7 to join... +[2023-07-17 01:11:52,687][282552] Batcher 0 profile tree view: +batching: 1.8804, releasing_batches: 1.6128 +[2023-07-17 01:11:52,687][282552] InferenceWorker_p0-w0 profile tree view: wait_policy: 0.0051 - wait_policy_total: 421.5973 -update_model: 13.1788 - weight_update: 0.0005 -one_step: 0.0007 - handle_policy_step: 592.4808 - deserialize: 24.7075, stack: 6.4417, obs_to_device_normalize: 106.6355, forward: 293.1758, send_messages: 43.8183 - prepare_outputs: 66.2444 - to_cpu: 9.9873 -[2023-07-08 20:58:40,690][1071413] Learner 0 profile tree view: -misc: 0.0094, prepare_batch: 8.3159 -train: 85.1681 - epoch_init: 0.0346, minibatch_init: 1.1616, losses_postprocess: 1.2487, kl_divergence: 0.4023, after_optimizer: 0.6137 - calculate_losses: 35.9214 - losses_init: 0.0295, forward_head: 13.7429, bptt_initial: 0.1298, bptt: 0.1182, tail: 10.4276, advantages_returns: 0.8090, losses: 9.3915 - update: 44.3507 - clip: 5.3692 -[2023-07-08 20:58:40,690][1071413] RolloutWorker_w0 profile tree view: -wait_for_trajectories: 0.4529, enqueue_policy_requests: 14.8099, env_step: 679.7015, overhead: 21.5225, complete_rollouts: 0.3780 -save_policy_outputs: 42.6078 - split_output_tensors: 14.4850 -[2023-07-08 20:58:40,690][1071413] RolloutWorker_w7 profile tree view: -wait_for_trajectories: 0.4194, enqueue_policy_requests: 14.3810, env_step: 676.2376, overhead: 20.9526, complete_rollouts: 0.3733 -save_policy_outputs: 42.0422 - split_output_tensors: 14.4068 -[2023-07-08 20:58:40,690][1071413] Loop Runner_EvtLoop terminating... -[2023-07-08 20:58:40,691][1071413] Runner profile tree view: -main_loop: 1101.9105 -[2023-07-08 20:58:40,691][1071413] Collected {0: 10006528}, FPS: 9081.1 + wait_policy_total: 249.1565 +update_model: 10.4113 + weight_update: 0.0004 +one_step: 0.0006 + handle_policy_step: 467.4119 + deserialize: 19.4563, stack: 5.0258, obs_to_device_normalize: 83.6510, forward: 230.3643, send_messages: 35.1240 + prepare_outputs: 53.9527 + to_cpu: 8.4434 +[2023-07-17 01:11:52,687][282552] Learner 0 profile tree view: +misc: 0.0111, prepare_batch: 9.4728 +train: 97.0761 + epoch_init: 0.0350, minibatch_init: 1.3525, losses_postprocess: 1.3032, kl_divergence: 0.4451, after_optimizer: 0.6024 + calculate_losses: 41.3156 + losses_init: 0.0310, forward_head: 16.1613, bptt_initial: 0.1423, bptt: 0.1351, tail: 11.6182, advantages_returns: 0.8984, losses: 10.8798 + update: 50.4074 + clip: 5.9868 +[2023-07-17 01:11:52,687][282552] RolloutWorker_w0 profile tree view: +wait_for_trajectories: 0.2909, enqueue_policy_requests: 12.4082, env_step: 517.5566, overhead: 19.0742, complete_rollouts: 0.3268 +save_policy_outputs: 37.9754 + split_output_tensors: 13.2060 +[2023-07-17 01:11:52,687][282552] RolloutWorker_w7 profile tree view: +wait_for_trajectories: 0.2701, enqueue_policy_requests: 12.5336, env_step: 521.0286, overhead: 19.4311, complete_rollouts: 0.3252 +save_policy_outputs: 38.2645 + split_output_tensors: 13.2006 +[2023-07-17 01:11:52,688][282552] Loop Runner_EvtLoop terminating... +[2023-07-17 01:11:52,688][282552] Runner profile tree view: +main_loop: 784.5779 +[2023-07-17 01:11:52,688][282552] Collected {0: 10006528}, FPS: 12754.0