[2023-03-07 22:54:00,033][286098] Saving configuration to /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/config.json... [2023-03-07 22:54:00,048][286098] Rollout worker 0 uses device cpu [2023-03-07 22:54:00,048][286098] Rollout worker 1 uses device cpu [2023-03-07 22:54:00,048][286098] Rollout worker 2 uses device cpu [2023-03-07 22:54:00,048][286098] Rollout worker 3 uses device cpu [2023-03-07 22:54:00,049][286098] Rollout worker 4 uses device cpu [2023-03-07 22:54:00,049][286098] Rollout worker 5 uses device cpu [2023-03-07 22:54:00,049][286098] Rollout worker 6 uses device cpu [2023-03-07 22:54:00,049][286098] Rollout worker 7 uses device cpu [2023-03-07 22:54:00,049][286098] In synchronous mode, we only accumulate one batch. Setting num_batches_to_accumulate to 1 [2023-03-07 22:54:00,059][286098] InferenceWorker_p0-w0: min num requests: 2 [2023-03-07 22:54:00,076][286098] Starting all processes... [2023-03-07 22:54:00,076][286098] Starting process learner_proc0 [2023-03-07 22:54:00,126][286098] Starting all processes... [2023-03-07 22:54:00,169][286098] Starting process inference_proc0-0 [2023-03-07 22:54:00,170][286098] Starting process rollout_proc0 [2023-03-07 22:54:00,170][286098] Starting process rollout_proc1 [2023-03-07 22:54:00,170][286098] Starting process rollout_proc2 [2023-03-07 22:54:00,171][286098] Starting process rollout_proc3 [2023-03-07 22:54:00,171][286098] Starting process rollout_proc4 [2023-03-07 22:54:00,171][286098] Starting process rollout_proc5 [2023-03-07 22:54:00,171][286098] Starting process rollout_proc6 [2023-03-07 22:54:00,172][286098] Starting process rollout_proc7 [2023-03-07 22:54:01,601][286341] Starting seed is not provided [2023-03-07 22:54:01,601][286341] Initializing actor-critic model on device cpu [2023-03-07 22:54:01,602][286341] RunningMeanStd input shape: (39,) [2023-03-07 22:54:01,602][286341] RunningMeanStd input shape: (1,) [2023-03-07 22:54:01,633][286390] Worker 6 uses CPU cores [24, 25, 26, 27] [2023-03-07 22:54:01,660][286341] Created Actor Critic model with architecture: [2023-03-07 22:54:01,660][286341] ActorCriticSharedWeights( (obs_normalizer): ObservationNormalizer( (running_mean_std): RunningMeanStdDictInPlace( (running_mean_std): ModuleDict( (obs): RunningMeanStdInPlace() ) ) ) (returns_normalizer): RecursiveScriptModule(original_name=RunningMeanStdInPlace) (encoder): MultiInputEncoder( (encoders): ModuleDict( (obs): MlpEncoder( (mlp_head): RecursiveScriptModule( original_name=Sequential (0): RecursiveScriptModule(original_name=Linear) (1): RecursiveScriptModule(original_name=Tanh) (2): RecursiveScriptModule(original_name=Linear) (3): RecursiveScriptModule(original_name=Tanh) ) ) ) ) (core): ModelCoreIdentity() (decoder): MlpDecoder( (mlp): Identity() ) (critic_linear): Linear(in_features=64, out_features=1, bias=True) (action_parameterization): ActionParameterizationContinuousNonAdaptiveStddev( (distribution_linear): Linear(in_features=64, out_features=4, bias=True) ) ) [2023-03-07 22:54:01,788][286391] Worker 3 uses CPU cores [12, 13, 14, 15] [2023-03-07 22:54:01,967][286341] Using optimizer [2023-03-07 22:54:01,967][286341] No checkpoints found [2023-03-07 22:54:01,967][286341] Did not load from checkpoint, starting from scratch! [2023-03-07 22:54:01,968][286341] Initialized policy 0 weights for model version 0 [2023-03-07 22:54:01,968][286341] LearnerWorker_p0 finished initialization! [2023-03-07 22:54:01,969][286389] RunningMeanStd input shape: (39,) [2023-03-07 22:54:01,970][286389] RunningMeanStd input shape: (1,) [2023-03-07 22:54:02,027][286098] Inference worker 0-0 is ready! [2023-03-07 22:54:02,027][286098] All inference workers are ready! Signal rollout workers to start! [2023-03-07 22:54:02,054][286387] Worker 5 uses CPU cores [20, 21, 22, 23] [2023-03-07 22:54:02,067][286393] Worker 7 uses CPU cores [28, 29, 30, 31] [2023-03-07 22:54:02,124][286388] Worker 1 uses CPU cores [4, 5, 6, 7] [2023-03-07 22:54:02,163][286386] Worker 0 uses CPU cores [0, 1, 2, 3] [2023-03-07 22:54:02,239][286385] Worker 4 uses CPU cores [16, 17, 18, 19] [2023-03-07 22:54:02,346][286392] Worker 2 uses CPU cores [8, 9, 10, 11] [2023-03-07 22:54:02,816][286098] 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) [2023-03-07 22:54:06,324][286390] Decorrelating experience for 0 frames... [2023-03-07 22:54:06,329][286391] Decorrelating experience for 0 frames... [2023-03-07 22:54:06,340][286390] Decorrelating experience for 64 frames... [2023-03-07 22:54:06,344][286391] Decorrelating experience for 64 frames... [2023-03-07 22:54:06,380][286390] Decorrelating experience for 128 frames... [2023-03-07 22:54:06,383][286391] Decorrelating experience for 128 frames... [2023-03-07 22:54:06,401][286387] Decorrelating experience for 0 frames... [2023-03-07 22:54:06,416][286387] Decorrelating experience for 64 frames... [2023-03-07 22:54:06,444][286390] Decorrelating experience for 192 frames... [2023-03-07 22:54:06,446][286388] Decorrelating experience for 0 frames... [2023-03-07 22:54:06,453][286391] Decorrelating experience for 192 frames... [2023-03-07 22:54:06,456][286393] Decorrelating experience for 0 frames... [2023-03-07 22:54:06,457][286387] Decorrelating experience for 128 frames... [2023-03-07 22:54:06,462][286388] Decorrelating experience for 64 frames... [2023-03-07 22:54:06,471][286393] Decorrelating experience for 64 frames... [2023-03-07 22:54:06,502][286388] Decorrelating experience for 128 frames... [2023-03-07 22:54:06,511][286393] Decorrelating experience for 128 frames... [2023-03-07 22:54:06,522][286387] Decorrelating experience for 192 frames... [2023-03-07 22:54:06,540][286386] Decorrelating experience for 0 frames... [2023-03-07 22:54:06,555][286386] Decorrelating experience for 64 frames... [2023-03-07 22:54:06,566][286388] Decorrelating experience for 192 frames... [2023-03-07 22:54:06,577][286393] Decorrelating experience for 192 frames... [2023-03-07 22:54:06,595][286386] Decorrelating experience for 128 frames... [2023-03-07 22:54:06,612][286385] Decorrelating experience for 0 frames... [2023-03-07 22:54:06,627][286385] Decorrelating experience for 64 frames... [2023-03-07 22:54:06,658][286386] Decorrelating experience for 192 frames... [2023-03-07 22:54:06,667][286385] Decorrelating experience for 128 frames... [2023-03-07 22:54:06,673][286392] Decorrelating experience for 0 frames... [2023-03-07 22:54:06,687][286392] Decorrelating experience for 64 frames... [2023-03-07 22:54:06,727][286392] Decorrelating experience for 128 frames... [2023-03-07 22:54:06,731][286385] Decorrelating experience for 192 frames... [2023-03-07 22:54:06,790][286392] Decorrelating experience for 192 frames... [2023-03-07 22:54:07,816][286098] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 0.0. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) [2023-03-07 22:54:10,730][286390] Decorrelating experience for 256 frames... [2023-03-07 22:54:10,738][286391] Decorrelating experience for 256 frames... [2023-03-07 22:54:10,802][286387] Decorrelating experience for 256 frames... [2023-03-07 22:54:10,835][286388] Decorrelating experience for 256 frames... [2023-03-07 22:54:10,846][286390] Decorrelating experience for 320 frames... [2023-03-07 22:54:10,851][286391] Decorrelating experience for 320 frames... [2023-03-07 22:54:10,873][286393] Decorrelating experience for 256 frames... [2023-03-07 22:54:10,914][286387] Decorrelating experience for 320 frames... [2023-03-07 22:54:10,929][286386] Decorrelating experience for 256 frames... [2023-03-07 22:54:10,948][286388] Decorrelating experience for 320 frames... [2023-03-07 22:54:10,983][286390] Decorrelating experience for 384 frames... [2023-03-07 22:54:10,986][286393] Decorrelating experience for 320 frames... [2023-03-07 22:54:10,987][286391] Decorrelating experience for 384 frames... [2023-03-07 22:54:11,008][286385] Decorrelating experience for 256 frames... [2023-03-07 22:54:11,041][286386] Decorrelating experience for 320 frames... [2023-03-07 22:54:11,063][286387] Decorrelating experience for 384 frames... [2023-03-07 22:54:11,065][286392] Decorrelating experience for 256 frames... [2023-03-07 22:54:11,094][286388] Decorrelating experience for 384 frames... [2023-03-07 22:54:11,119][286385] Decorrelating experience for 320 frames... [2023-03-07 22:54:11,122][286393] Decorrelating experience for 384 frames... [2023-03-07 22:54:11,144][286390] Decorrelating experience for 448 frames... [2023-03-07 22:54:11,158][286391] Decorrelating experience for 448 frames... [2023-03-07 22:54:11,173][286386] Decorrelating experience for 384 frames... [2023-03-07 22:54:11,178][286392] Decorrelating experience for 320 frames... [2023-03-07 22:54:11,222][286387] Decorrelating experience for 448 frames... [2023-03-07 22:54:11,253][286388] Decorrelating experience for 448 frames... [2023-03-07 22:54:11,254][286385] Decorrelating experience for 384 frames... [2023-03-07 22:54:11,285][286393] Decorrelating experience for 448 frames... [2023-03-07 22:54:11,314][286392] Decorrelating experience for 384 frames... [2023-03-07 22:54:11,332][286386] Decorrelating experience for 448 frames... [2023-03-07 22:54:11,412][286385] Decorrelating experience for 448 frames... [2023-03-07 22:54:11,476][286392] Decorrelating experience for 448 frames... [2023-03-07 22:54:12,816][286098] Fps is (10 sec: 819.2, 60 sec: 819.2, 300 sec: 819.2). Total num frames: 8192. Throughput: 0: 0.0. Samples: 0. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 22:54:12,817][286098] Avg episode reward: [(0, '48.761')] [2023-03-07 22:54:12,818][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000000016_8192.pth... [2023-03-07 22:54:15,159][286389] Updated weights for policy 0, policy_version 80 (0.0004) [2023-03-07 22:54:17,816][286098] Fps is (10 sec: 7372.9, 60 sec: 4915.2, 300 sec: 4915.2). Total num frames: 73728. Throughput: 0: 4529.6. Samples: 67944. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 22:54:17,816][286098] Avg episode reward: [(0, '360.191')] [2023-03-07 22:54:18,134][286389] Updated weights for policy 0, policy_version 160 (0.0003) [2023-03-07 22:54:20,055][286098] Heartbeat connected on Batcher_0 [2023-03-07 22:54:20,062][286098] Heartbeat connected on RolloutWorker_w0 [2023-03-07 22:54:20,064][286098] Heartbeat connected on RolloutWorker_w1 [2023-03-07 22:54:20,066][286098] Heartbeat connected on RolloutWorker_w2 [2023-03-07 22:54:20,067][286098] Heartbeat connected on RolloutWorker_w3 [2023-03-07 22:54:20,069][286098] Heartbeat connected on RolloutWorker_w4 [2023-03-07 22:54:20,071][286098] Heartbeat connected on RolloutWorker_w5 [2023-03-07 22:54:20,073][286098] Heartbeat connected on RolloutWorker_w6 [2023-03-07 22:54:20,075][286098] Heartbeat connected on RolloutWorker_w7 [2023-03-07 22:54:20,079][286098] Heartbeat connected on LearnerWorker_p0 [2023-03-07 22:54:20,081][286098] Heartbeat connected on InferenceWorker_p0-w0 [2023-03-07 22:54:21,320][286389] Updated weights for policy 0, policy_version 240 (0.0003) [2023-03-07 22:54:22,816][286098] Fps is (10 sec: 13107.4, 60 sec: 6963.2, 300 sec: 6963.2). Total num frames: 139264. Throughput: 0: 5325.4. Samples: 106508. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-07 22:54:22,816][286098] Avg episode reward: [(0, '455.530')] [2023-03-07 22:54:22,817][286341] Saving new best policy, reward=455.530! [2023-03-07 22:54:24,588][286389] Updated weights for policy 0, policy_version 320 (0.0003) [2023-03-07 22:54:27,816][286098] Fps is (10 sec: 12697.5, 60 sec: 8028.1, 300 sec: 8028.1). Total num frames: 200704. Throughput: 0: 7298.2. Samples: 182456. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 22:54:27,816][286098] Avg episode reward: [(0, '535.645')] [2023-03-07 22:54:27,840][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000000400_204800.pth... [2023-03-07 22:54:27,841][286389] Updated weights for policy 0, policy_version 400 (0.0003) [2023-03-07 22:54:27,843][286341] Saving new best policy, reward=535.645! [2023-03-07 22:54:31,146][286389] Updated weights for policy 0, policy_version 480 (0.0003) [2023-03-07 22:54:32,816][286098] Fps is (10 sec: 12288.0, 60 sec: 8738.1, 300 sec: 8738.1). Total num frames: 262144. Throughput: 0: 8559.5. Samples: 256784. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 22:54:32,816][286098] Avg episode reward: [(0, '665.236')] [2023-03-07 22:54:32,817][286341] Saving new best policy, reward=665.236! [2023-03-07 22:54:34,668][286389] Updated weights for policy 0, policy_version 560 (0.0003) [2023-03-07 22:54:37,816][286098] Fps is (10 sec: 11878.5, 60 sec: 9128.2, 300 sec: 9128.2). Total num frames: 319488. Throughput: 0: 8311.1. Samples: 290888. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 22:54:37,816][286098] Avg episode reward: [(0, '918.486')] [2023-03-07 22:54:37,817][286341] Saving new best policy, reward=918.486! [2023-03-07 22:54:38,495][286389] Updated weights for policy 0, policy_version 640 (0.0005) [2023-03-07 22:54:42,433][286389] Updated weights for policy 0, policy_version 720 (0.0005) [2023-03-07 22:54:42,816][286098] Fps is (10 sec: 11059.2, 60 sec: 9318.4, 300 sec: 9318.4). Total num frames: 372736. Throughput: 0: 8873.7. Samples: 354948. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-07 22:54:42,817][286098] Avg episode reward: [(0, '965.952')] [2023-03-07 22:54:42,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000000728_372736.pth... [2023-03-07 22:54:42,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000000016_8192.pth [2023-03-07 22:54:42,822][286341] Saving new best policy, reward=965.952! [2023-03-07 22:54:46,419][286389] Updated weights for policy 0, policy_version 800 (0.0005) [2023-03-07 22:54:47,816][286098] Fps is (10 sec: 10240.0, 60 sec: 9375.3, 300 sec: 9375.3). Total num frames: 421888. Throughput: 0: 9260.6. Samples: 416728. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 22:54:47,816][286098] Avg episode reward: [(0, '985.935')] [2023-03-07 22:54:47,817][286341] Saving new best policy, reward=985.935! [2023-03-07 22:54:50,370][286389] Updated weights for policy 0, policy_version 880 (0.0004) [2023-03-07 22:54:52,816][286098] Fps is (10 sec: 10240.0, 60 sec: 9502.7, 300 sec: 9502.7). Total num frames: 475136. Throughput: 0: 9941.0. Samples: 447344. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 22:54:52,816][286098] Avg episode reward: [(0, '974.754')] [2023-03-07 22:54:54,298][286389] Updated weights for policy 0, policy_version 960 (0.0005) [2023-03-07 22:54:57,816][286098] Fps is (10 sec: 10649.5, 60 sec: 9607.0, 300 sec: 9607.0). Total num frames: 528384. Throughput: 0: 11361.6. Samples: 511272. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-07 22:54:57,816][286098] Avg episode reward: [(0, '955.005')] [2023-03-07 22:54:57,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000001032_528384.pth... [2023-03-07 22:54:57,823][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000000400_204800.pth [2023-03-07 22:54:58,015][286389] Updated weights for policy 0, policy_version 1040 (0.0005) [2023-03-07 22:55:01,870][286389] Updated weights for policy 0, policy_version 1120 (0.0005) [2023-03-07 22:55:02,816][286098] Fps is (10 sec: 10649.6, 60 sec: 9693.9, 300 sec: 9693.9). Total num frames: 581632. Throughput: 0: 11282.5. Samples: 575656. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 22:55:02,816][286098] Avg episode reward: [(0, '950.175')] [2023-03-07 22:55:05,617][286389] Updated weights for policy 0, policy_version 1200 (0.0005) [2023-03-07 22:55:07,816][286098] Fps is (10 sec: 11059.3, 60 sec: 10649.6, 300 sec: 9830.4). Total num frames: 638976. Throughput: 0: 11153.1. Samples: 608396. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-07 22:55:07,816][286098] Avg episode reward: [(0, '954.814')] [2023-03-07 22:55:09,270][286389] Updated weights for policy 0, policy_version 1280 (0.0004) [2023-03-07 22:55:12,816][286098] Fps is (10 sec: 11059.1, 60 sec: 11400.6, 300 sec: 9888.9). Total num frames: 692224. Throughput: 0: 10950.8. Samples: 675240. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 22:55:12,816][286098] Avg episode reward: [(0, '1001.471')] [2023-03-07 22:55:12,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000001352_692224.pth... [2023-03-07 22:55:12,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000000728_372736.pth [2023-03-07 22:55:12,822][286341] Saving new best policy, reward=1001.471! [2023-03-07 22:55:12,939][286389] Updated weights for policy 0, policy_version 1360 (0.0004) [2023-03-07 22:55:16,586][286389] Updated weights for policy 0, policy_version 1440 (0.0005) [2023-03-07 22:55:17,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11264.0, 300 sec: 9994.3). Total num frames: 749568. Throughput: 0: 10795.5. Samples: 742580. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-07 22:55:17,816][286098] Avg episode reward: [(0, '990.077')] [2023-03-07 22:55:20,355][286389] Updated weights for policy 0, policy_version 1520 (0.0004) [2023-03-07 22:55:22,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11059.2, 300 sec: 10035.2). Total num frames: 802816. Throughput: 0: 10760.4. Samples: 775108. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 22:55:22,816][286098] Avg episode reward: [(0, '1011.731')] [2023-03-07 22:55:22,817][286341] Saving new best policy, reward=1011.731! [2023-03-07 22:55:24,481][286389] Updated weights for policy 0, policy_version 1600 (0.0005) [2023-03-07 22:55:27,816][286098] Fps is (10 sec: 10239.9, 60 sec: 10854.4, 300 sec: 10023.1). Total num frames: 851968. Throughput: 0: 10682.6. Samples: 835664. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 22:55:27,816][286098] Avg episode reward: [(0, '985.557')] [2023-03-07 22:55:27,850][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000001672_856064.pth... [2023-03-07 22:55:27,852][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000001032_528384.pth [2023-03-07 22:55:28,235][286389] Updated weights for policy 0, policy_version 1680 (0.0004) [2023-03-07 22:55:31,953][286389] Updated weights for policy 0, policy_version 1760 (0.0005) [2023-03-07 22:55:32,816][286098] Fps is (10 sec: 10649.7, 60 sec: 10786.1, 300 sec: 10103.5). Total num frames: 909312. Throughput: 0: 10788.7. Samples: 902220. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-07 22:55:32,816][286098] Avg episode reward: [(0, '904.764')] [2023-03-07 22:55:35,680][286389] Updated weights for policy 0, policy_version 1840 (0.0004) [2023-03-07 22:55:37,816][286098] Fps is (10 sec: 11059.3, 60 sec: 10717.9, 300 sec: 10132.2). Total num frames: 962560. Throughput: 0: 10851.4. Samples: 935660. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 22:55:37,816][286098] Avg episode reward: [(0, '920.027')] [2023-03-07 22:55:39,443][286389] Updated weights for policy 0, policy_version 1920 (0.0004) [2023-03-07 22:55:42,816][286098] Fps is (10 sec: 10649.6, 60 sec: 10717.9, 300 sec: 10158.1). Total num frames: 1015808. Throughput: 0: 10847.8. Samples: 999424. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 22:55:42,816][286098] Avg episode reward: [(0, '987.612')] [2023-03-07 22:55:42,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000001984_1015808.pth... [2023-03-07 22:55:42,821][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000001352_692224.pth [2023-03-07 22:55:43,484][286389] Updated weights for policy 0, policy_version 2000 (0.0005) [2023-03-07 22:55:47,547][286389] Updated weights for policy 0, policy_version 2080 (0.0005) [2023-03-07 22:55:47,816][286098] Fps is (10 sec: 10240.1, 60 sec: 10717.9, 300 sec: 10142.5). Total num frames: 1064960. Throughput: 0: 10775.7. Samples: 1060564. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 22:55:47,816][286098] Avg episode reward: [(0, '992.179')] [2023-03-07 22:55:51,711][286389] Updated weights for policy 0, policy_version 2160 (0.0005) [2023-03-07 22:55:52,816][286098] Fps is (10 sec: 9830.5, 60 sec: 10649.6, 300 sec: 10128.3). Total num frames: 1114112. Throughput: 0: 10693.4. Samples: 1089600. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-07 22:55:52,816][286098] Avg episode reward: [(0, '984.387')] [2023-03-07 22:55:55,830][286389] Updated weights for policy 0, policy_version 2240 (0.0005) [2023-03-07 22:55:57,816][286098] Fps is (10 sec: 9830.4, 60 sec: 10581.4, 300 sec: 10115.3). Total num frames: 1163264. Throughput: 0: 10532.4. Samples: 1149196. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 22:55:57,816][286098] Avg episode reward: [(0, '981.624')] [2023-03-07 22:55:57,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000002272_1163264.pth... [2023-03-07 22:55:57,821][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000001672_856064.pth [2023-03-07 22:55:59,950][286389] Updated weights for policy 0, policy_version 2320 (0.0005) [2023-03-07 22:56:02,816][286098] Fps is (10 sec: 9830.3, 60 sec: 10513.0, 300 sec: 10103.5). Total num frames: 1212416. Throughput: 0: 10346.1. Samples: 1208156. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 22:56:02,816][286098] Avg episode reward: [(0, '960.533')] [2023-03-07 22:56:04,271][286389] Updated weights for policy 0, policy_version 2400 (0.0005) [2023-03-07 22:56:07,816][286098] Fps is (10 sec: 9830.4, 60 sec: 10376.5, 300 sec: 10092.5). Total num frames: 1261568. Throughput: 0: 10257.7. Samples: 1236704. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-07 22:56:07,816][286098] Avg episode reward: [(0, '891.815')] [2023-03-07 22:56:08,562][286389] Updated weights for policy 0, policy_version 2480 (0.0005) [2023-03-07 22:56:12,816][286098] Fps is (10 sec: 9420.9, 60 sec: 10240.0, 300 sec: 10051.0). Total num frames: 1306624. Throughput: 0: 10190.6. Samples: 1294240. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 22:56:12,816][286098] Avg episode reward: [(0, '826.853')] [2023-03-07 22:56:12,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000002560_1310720.pth... [2023-03-07 22:56:12,820][286389] Updated weights for policy 0, policy_version 2560 (0.0005) [2023-03-07 22:56:12,821][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000001984_1015808.pth [2023-03-07 22:56:17,238][286389] Updated weights for policy 0, policy_version 2640 (0.0005) [2023-03-07 22:56:17,816][286098] Fps is (10 sec: 9420.8, 60 sec: 10103.5, 300 sec: 10042.8). Total num frames: 1355776. Throughput: 0: 9965.0. Samples: 1350644. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-07 22:56:17,827][286098] Avg episode reward: [(0, '946.683')] [2023-03-07 22:56:21,646][286389] Updated weights for policy 0, policy_version 2720 (0.0005) [2023-03-07 22:56:22,816][286098] Fps is (10 sec: 9420.7, 60 sec: 9966.9, 300 sec: 10005.9). Total num frames: 1400832. Throughput: 0: 9835.7. Samples: 1378268. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 22:56:22,816][286098] Avg episode reward: [(0, '1012.935')] [2023-03-07 22:56:22,817][286341] Saving new best policy, reward=1012.935! [2023-03-07 22:56:25,846][286389] Updated weights for policy 0, policy_version 2800 (0.0005) [2023-03-07 22:56:27,816][286098] Fps is (10 sec: 9420.7, 60 sec: 9966.9, 300 sec: 9999.9). Total num frames: 1449984. Throughput: 0: 9699.8. Samples: 1435916. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-07 22:56:27,827][286098] Avg episode reward: [(0, '1011.622')] [2023-03-07 22:56:27,838][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000002840_1454080.pth... [2023-03-07 22:56:27,839][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000002272_1163264.pth [2023-03-07 22:56:29,876][286389] Updated weights for policy 0, policy_version 2880 (0.0005) [2023-03-07 22:56:32,816][286098] Fps is (10 sec: 10240.0, 60 sec: 9898.7, 300 sec: 10021.5). Total num frames: 1503232. Throughput: 0: 9703.5. Samples: 1497224. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 22:56:32,832][286098] Avg episode reward: [(0, '1004.773')] [2023-03-07 22:56:33,847][286389] Updated weights for policy 0, policy_version 2960 (0.0004) [2023-03-07 22:56:37,816][286098] Fps is (10 sec: 10240.1, 60 sec: 9830.4, 300 sec: 10015.4). Total num frames: 1552384. Throughput: 0: 9738.3. Samples: 1527824. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 22:56:37,827][286098] Avg episode reward: [(0, '1019.443')] [2023-03-07 22:56:37,827][286341] Saving new best policy, reward=1019.443! [2023-03-07 22:56:37,938][286389] Updated weights for policy 0, policy_version 3040 (0.0005) [2023-03-07 22:56:41,882][286389] Updated weights for policy 0, policy_version 3120 (0.0004) [2023-03-07 22:56:42,816][286098] Fps is (10 sec: 10240.0, 60 sec: 9830.4, 300 sec: 10035.2). Total num frames: 1605632. Throughput: 0: 9775.6. Samples: 1589100. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 22:56:42,827][286098] Avg episode reward: [(0, '1023.617')] [2023-03-07 22:56:42,830][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000003136_1605632.pth... [2023-03-07 22:56:42,832][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000002560_1310720.pth [2023-03-07 22:56:42,833][286341] Saving new best policy, reward=1023.617! [2023-03-07 22:56:45,928][286389] Updated weights for policy 0, policy_version 3200 (0.0005) [2023-03-07 22:56:47,816][286098] Fps is (10 sec: 10240.0, 60 sec: 9830.4, 300 sec: 10029.0). Total num frames: 1654784. Throughput: 0: 9803.7. Samples: 1649324. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 22:56:47,816][286098] Avg episode reward: [(0, '1057.817')] [2023-03-07 22:56:47,817][286341] Saving new best policy, reward=1057.817! [2023-03-07 22:56:50,083][286389] Updated weights for policy 0, policy_version 3280 (0.0004) [2023-03-07 22:56:52,816][286098] Fps is (10 sec: 9830.4, 60 sec: 9830.4, 300 sec: 10023.2). Total num frames: 1703936. Throughput: 0: 9837.0. Samples: 1679368. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 22:56:52,816][286098] Avg episode reward: [(0, '1048.945')] [2023-03-07 22:56:54,390][286389] Updated weights for policy 0, policy_version 3360 (0.0005) [2023-03-07 22:56:57,816][286098] Fps is (10 sec: 9420.8, 60 sec: 9762.1, 300 sec: 9994.2). Total num frames: 1748992. Throughput: 0: 9831.1. Samples: 1736640. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-07 22:56:57,816][286098] Avg episode reward: [(0, '1047.817')] [2023-03-07 22:56:57,862][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000003424_1753088.pth... [2023-03-07 22:56:57,863][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000002840_1454080.pth [2023-03-07 22:56:58,667][286389] Updated weights for policy 0, policy_version 3440 (0.0005) [2023-03-07 22:57:02,611][286389] Updated weights for policy 0, policy_version 3520 (0.0005) [2023-03-07 22:57:02,816][286098] Fps is (10 sec: 9830.4, 60 sec: 9830.4, 300 sec: 10012.4). Total num frames: 1802240. Throughput: 0: 9912.7. Samples: 1796716. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 22:57:02,816][286098] Avg episode reward: [(0, '1094.594')] [2023-03-07 22:57:02,817][286341] Saving new best policy, reward=1094.594! [2023-03-07 22:57:06,394][286389] Updated weights for policy 0, policy_version 3600 (0.0005) [2023-03-07 22:57:07,816][286098] Fps is (10 sec: 10649.6, 60 sec: 9898.7, 300 sec: 10029.7). Total num frames: 1855488. Throughput: 0: 10017.4. Samples: 1829052. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 22:57:07,816][286098] Avg episode reward: [(0, '1170.773')] [2023-03-07 22:57:07,817][286341] Saving new best policy, reward=1170.773! [2023-03-07 22:57:10,395][286389] Updated weights for policy 0, policy_version 3680 (0.0005) [2023-03-07 22:57:12,816][286098] Fps is (10 sec: 10649.5, 60 sec: 10035.2, 300 sec: 10046.0). Total num frames: 1908736. Throughput: 0: 10121.5. Samples: 1891384. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-07 22:57:12,816][286098] Avg episode reward: [(0, '1065.543')] [2023-03-07 22:57:12,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000003728_1908736.pth... [2023-03-07 22:57:12,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000003136_1605632.pth [2023-03-07 22:57:14,366][286389] Updated weights for policy 0, policy_version 3760 (0.0004) [2023-03-07 22:57:17,816][286098] Fps is (10 sec: 10240.0, 60 sec: 10035.2, 300 sec: 10040.5). Total num frames: 1957888. Throughput: 0: 10145.2. Samples: 1953756. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-07 22:57:17,816][286098] Avg episode reward: [(0, '1069.946')] [2023-03-07 22:57:18,286][286389] Updated weights for policy 0, policy_version 3840 (0.0005) [2023-03-07 22:57:22,164][286389] Updated weights for policy 0, policy_version 3920 (0.0005) [2023-03-07 22:57:22,816][286098] Fps is (10 sec: 10240.0, 60 sec: 10171.7, 300 sec: 10055.7). Total num frames: 2011136. Throughput: 0: 10156.6. Samples: 1984872. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 22:57:22,816][286098] Avg episode reward: [(0, '1526.655')] [2023-03-07 22:57:22,817][286341] Saving new best policy, reward=1526.655! [2023-03-07 22:57:25,918][286389] Updated weights for policy 0, policy_version 4000 (0.0005) [2023-03-07 22:57:27,816][286098] Fps is (10 sec: 11059.1, 60 sec: 10308.3, 300 sec: 10090.1). Total num frames: 2068480. Throughput: 0: 10237.3. Samples: 2049780. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-07 22:57:27,816][286098] Avg episode reward: [(0, '1872.580')] [2023-03-07 22:57:27,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000004040_2068480.pth... [2023-03-07 22:57:27,821][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000003424_1753088.pth [2023-03-07 22:57:27,821][286341] Saving new best policy, reward=1872.580! [2023-03-07 22:57:29,690][286389] Updated weights for policy 0, policy_version 4080 (0.0005) [2023-03-07 22:57:32,816][286098] Fps is (10 sec: 11059.2, 60 sec: 10308.3, 300 sec: 10103.5). Total num frames: 2121728. Throughput: 0: 10351.1. Samples: 2115124. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 22:57:32,816][286098] Avg episode reward: [(0, '2368.325')] [2023-03-07 22:57:32,817][286341] Saving new best policy, reward=2368.325! [2023-03-07 22:57:33,382][286389] Updated weights for policy 0, policy_version 4160 (0.0005) [2023-03-07 22:57:37,086][286389] Updated weights for policy 0, policy_version 4240 (0.0005) [2023-03-07 22:57:37,816][286098] Fps is (10 sec: 10649.6, 60 sec: 10376.5, 300 sec: 10116.2). Total num frames: 2174976. Throughput: 0: 10420.0. Samples: 2148268. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 22:57:37,816][286098] Avg episode reward: [(0, '2753.947')] [2023-03-07 22:57:37,874][286341] Saving new best policy, reward=2753.947! [2023-03-07 22:57:41,034][286389] Updated weights for policy 0, policy_version 4320 (0.0005) [2023-03-07 22:57:42,816][286098] Fps is (10 sec: 10649.6, 60 sec: 10376.5, 300 sec: 10128.3). Total num frames: 2228224. Throughput: 0: 10561.6. Samples: 2211912. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 22:57:42,816][286098] Avg episode reward: [(0, '2825.284')] [2023-03-07 22:57:42,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000004352_2228224.pth... [2023-03-07 22:57:42,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000003728_1908736.pth [2023-03-07 22:57:42,823][286341] Saving new best policy, reward=2825.284! [2023-03-07 22:57:44,782][286389] Updated weights for policy 0, policy_version 4400 (0.0005) [2023-03-07 22:57:47,816][286098] Fps is (10 sec: 11059.2, 60 sec: 10513.1, 300 sec: 10158.1). Total num frames: 2285568. Throughput: 0: 10722.2. Samples: 2279216. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 22:57:47,816][286098] Avg episode reward: [(0, '3065.532')] [2023-03-07 22:57:47,817][286341] Saving new best policy, reward=3065.532! [2023-03-07 22:57:48,411][286389] Updated weights for policy 0, policy_version 4480 (0.0005) [2023-03-07 22:57:52,099][286389] Updated weights for policy 0, policy_version 4560 (0.0005) [2023-03-07 22:57:52,816][286098] Fps is (10 sec: 11059.1, 60 sec: 10581.3, 300 sec: 10168.8). Total num frames: 2338816. Throughput: 0: 10734.0. Samples: 2312084. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-07 22:57:52,816][286098] Avg episode reward: [(0, '3226.790')] [2023-03-07 22:57:52,831][286341] Saving new best policy, reward=3226.790! [2023-03-07 22:57:55,843][286389] Updated weights for policy 0, policy_version 4640 (0.0005) [2023-03-07 22:57:57,816][286098] Fps is (10 sec: 11059.1, 60 sec: 10786.1, 300 sec: 10196.4). Total num frames: 2396160. Throughput: 0: 10826.5. Samples: 2378576. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 22:57:57,816][286098] Avg episode reward: [(0, '3181.162')] [2023-03-07 22:57:57,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000004680_2396160.pth... [2023-03-07 22:57:57,823][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000004040_2068480.pth [2023-03-07 22:57:59,552][286389] Updated weights for policy 0, policy_version 4720 (0.0005) [2023-03-07 22:58:02,816][286098] Fps is (10 sec: 11059.3, 60 sec: 10786.1, 300 sec: 10205.9). Total num frames: 2449408. Throughput: 0: 10906.7. Samples: 2444560. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-07 22:58:02,816][286098] Avg episode reward: [(0, '3242.292')] [2023-03-07 22:58:02,817][286341] Saving new best policy, reward=3242.292! [2023-03-07 22:58:03,371][286389] Updated weights for policy 0, policy_version 4800 (0.0004) [2023-03-07 22:58:07,274][286389] Updated weights for policy 0, policy_version 4880 (0.0005) [2023-03-07 22:58:07,816][286098] Fps is (10 sec: 10649.6, 60 sec: 10786.1, 300 sec: 10214.9). Total num frames: 2502656. Throughput: 0: 10891.5. Samples: 2474992. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 22:58:07,816][286098] Avg episode reward: [(0, '2844.215')] [2023-03-07 22:58:11,171][286389] Updated weights for policy 0, policy_version 4960 (0.0005) [2023-03-07 22:58:12,816][286098] Fps is (10 sec: 10649.5, 60 sec: 10786.1, 300 sec: 10223.6). Total num frames: 2555904. Throughput: 0: 10867.9. Samples: 2538836. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 22:58:12,816][286098] Avg episode reward: [(0, '3108.261')] [2023-03-07 22:58:12,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000004992_2555904.pth... [2023-03-07 22:58:12,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000004352_2228224.pth [2023-03-07 22:58:15,131][286389] Updated weights for policy 0, policy_version 5040 (0.0005) [2023-03-07 22:58:17,816][286098] Fps is (10 sec: 10240.0, 60 sec: 10786.1, 300 sec: 10215.9). Total num frames: 2605056. Throughput: 0: 10798.0. Samples: 2601032. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-07 22:58:17,816][286098] Avg episode reward: [(0, '3610.742')] [2023-03-07 22:58:17,817][286341] Saving new best policy, reward=3610.742! [2023-03-07 22:58:19,036][286389] Updated weights for policy 0, policy_version 5120 (0.0005) [2023-03-07 22:58:22,816][286098] Fps is (10 sec: 10240.0, 60 sec: 10786.1, 300 sec: 10224.2). Total num frames: 2658304. Throughput: 0: 10738.4. Samples: 2631496. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 22:58:22,816][286098] Avg episode reward: [(0, '3857.887')] [2023-03-07 22:58:22,817][286341] Saving new best policy, reward=3857.887! [2023-03-07 22:58:23,016][286389] Updated weights for policy 0, policy_version 5200 (0.0005) [2023-03-07 22:58:26,930][286389] Updated weights for policy 0, policy_version 5280 (0.0005) [2023-03-07 22:58:27,816][286098] Fps is (10 sec: 10649.6, 60 sec: 10717.9, 300 sec: 10232.3). Total num frames: 2711552. Throughput: 0: 10739.0. Samples: 2695168. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 22:58:27,816][286098] Avg episode reward: [(0, '3938.533')] [2023-03-07 22:58:27,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000005296_2711552.pth... [2023-03-07 22:58:27,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000004680_2396160.pth [2023-03-07 22:58:27,822][286341] Saving new best policy, reward=3938.533! [2023-03-07 22:58:31,083][286389] Updated weights for policy 0, policy_version 5360 (0.0005) [2023-03-07 22:58:32,816][286098] Fps is (10 sec: 10240.0, 60 sec: 10649.6, 300 sec: 10224.8). Total num frames: 2760704. Throughput: 0: 10558.8. Samples: 2754360. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 22:58:32,816][286098] Avg episode reward: [(0, '3868.463')] [2023-03-07 22:58:35,131][286389] Updated weights for policy 0, policy_version 5440 (0.0005) [2023-03-07 22:58:37,816][286098] Fps is (10 sec: 9830.4, 60 sec: 10581.3, 300 sec: 10217.7). Total num frames: 2809856. Throughput: 0: 10497.0. Samples: 2784448. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 22:58:37,816][286098] Avg episode reward: [(0, '4075.022')] [2023-03-07 22:58:37,817][286341] Saving new best policy, reward=4075.022! [2023-03-07 22:58:39,237][286389] Updated weights for policy 0, policy_version 5520 (0.0005) [2023-03-07 22:58:42,816][286098] Fps is (10 sec: 9830.3, 60 sec: 10513.1, 300 sec: 10210.7). Total num frames: 2859008. Throughput: 0: 10366.8. Samples: 2845080. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-07 22:58:42,816][286098] Avg episode reward: [(0, '4241.863')] [2023-03-07 22:58:42,840][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000005592_2863104.pth... [2023-03-07 22:58:42,843][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000004992_2555904.pth [2023-03-07 22:58:42,843][286341] Saving new best policy, reward=4241.863! [2023-03-07 22:58:43,256][286389] Updated weights for policy 0, policy_version 5600 (0.0005) [2023-03-07 22:58:47,181][286389] Updated weights for policy 0, policy_version 5680 (0.0005) [2023-03-07 22:58:47,816][286098] Fps is (10 sec: 10240.0, 60 sec: 10444.8, 300 sec: 10218.4). Total num frames: 2912256. Throughput: 0: 10292.2. Samples: 2907708. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 22:58:47,816][286098] Avg episode reward: [(0, '4193.579')] [2023-03-07 22:58:50,753][286341] Early stopping after 2 epochs (8 sgd steps), loss delta 0.0000004 [2023-03-07 22:58:51,139][286389] Updated weights for policy 0, policy_version 5760 (0.0005) [2023-03-07 22:58:52,816][286098] Fps is (10 sec: 10649.7, 60 sec: 10444.8, 300 sec: 10225.9). Total num frames: 2965504. Throughput: 0: 10278.3. Samples: 2937516. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 22:58:52,816][286098] Avg episode reward: [(0, '4329.370')] [2023-03-07 22:58:52,817][286341] Saving new best policy, reward=4329.370! [2023-03-07 22:58:55,131][286389] Updated weights for policy 0, policy_version 5840 (0.0005) [2023-03-07 22:58:57,816][286098] Fps is (10 sec: 10240.1, 60 sec: 10308.3, 300 sec: 10219.2). Total num frames: 3014656. Throughput: 0: 10245.3. Samples: 2999872. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-07 22:58:57,816][286098] Avg episode reward: [(0, '4029.571')] [2023-03-07 22:58:57,863][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000005896_3018752.pth... [2023-03-07 22:58:57,865][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000005296_2711552.pth [2023-03-07 22:58:58,956][286389] Updated weights for policy 0, policy_version 5920 (0.0005) [2023-03-07 22:59:02,816][286098] Fps is (10 sec: 10240.0, 60 sec: 10308.3, 300 sec: 10399.7). Total num frames: 3067904. Throughput: 0: 10281.3. Samples: 3063692. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 22:59:02,816][286098] Avg episode reward: [(0, '3657.187')] [2023-03-07 22:59:02,967][286389] Updated weights for policy 0, policy_version 6000 (0.0005) [2023-03-07 22:59:07,139][286389] Updated weights for policy 0, policy_version 6080 (0.0005) [2023-03-07 22:59:07,816][286098] Fps is (10 sec: 10239.9, 60 sec: 10240.0, 300 sec: 10538.5). Total num frames: 3117056. Throughput: 0: 10248.1. Samples: 3092660. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 22:59:07,816][286098] Avg episode reward: [(0, '3654.817')] [2023-03-07 22:59:11,052][286389] Updated weights for policy 0, policy_version 6160 (0.0005) [2023-03-07 22:59:12,816][286098] Fps is (10 sec: 10239.9, 60 sec: 10240.0, 300 sec: 10496.9). Total num frames: 3170304. Throughput: 0: 10195.9. Samples: 3153984. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 22:59:12,817][286098] Avg episode reward: [(0, '3622.793')] [2023-03-07 22:59:12,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000006192_3170304.pth... [2023-03-07 22:59:12,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000005592_2863104.pth [2023-03-07 22:59:15,166][286389] Updated weights for policy 0, policy_version 6240 (0.0005) [2023-03-07 22:59:17,816][286098] Fps is (10 sec: 10240.0, 60 sec: 10240.0, 300 sec: 10441.3). Total num frames: 3219456. Throughput: 0: 10214.2. Samples: 3214000. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 22:59:17,827][286098] Avg episode reward: [(0, '3923.627')] [2023-03-07 22:59:19,332][286389] Updated weights for policy 0, policy_version 6320 (0.0005) [2023-03-07 22:59:22,816][286098] Fps is (10 sec: 9830.5, 60 sec: 10171.7, 300 sec: 10399.7). Total num frames: 3268608. Throughput: 0: 10206.2. Samples: 3243728. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 22:59:22,827][286098] Avg episode reward: [(0, '4094.725')] [2023-03-07 22:59:23,240][286389] Updated weights for policy 0, policy_version 6400 (0.0005) [2023-03-07 22:59:27,069][286389] Updated weights for policy 0, policy_version 6480 (0.0004) [2023-03-07 22:59:27,816][286098] Fps is (10 sec: 10240.1, 60 sec: 10171.8, 300 sec: 10371.9). Total num frames: 3321856. Throughput: 0: 10267.3. Samples: 3307108. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 22:59:27,827][286098] Avg episode reward: [(0, '4227.067')] [2023-03-07 22:59:27,849][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000006496_3325952.pth... [2023-03-07 22:59:27,851][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000005896_3018752.pth [2023-03-07 22:59:30,962][286389] Updated weights for policy 0, policy_version 6560 (0.0004) [2023-03-07 22:59:32,816][286098] Fps is (10 sec: 11059.2, 60 sec: 10308.3, 300 sec: 10371.9). Total num frames: 3379200. Throughput: 0: 10292.7. Samples: 3370880. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-07 22:59:32,816][286098] Avg episode reward: [(0, '4252.654')] [2023-03-07 22:59:34,776][286389] Updated weights for policy 0, policy_version 6640 (0.0005) [2023-03-07 22:59:37,816][286098] Fps is (10 sec: 11059.1, 60 sec: 10376.5, 300 sec: 10371.9). Total num frames: 3432448. Throughput: 0: 10345.9. Samples: 3403080. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 22:59:37,816][286098] Avg episode reward: [(0, '4335.542')] [2023-03-07 22:59:37,817][286341] Saving new best policy, reward=4335.542! [2023-03-07 22:59:38,450][286389] Updated weights for policy 0, policy_version 6720 (0.0005) [2023-03-07 22:59:42,211][286389] Updated weights for policy 0, policy_version 6800 (0.0005) [2023-03-07 22:59:42,816][286098] Fps is (10 sec: 10649.6, 60 sec: 10444.8, 300 sec: 10385.8). Total num frames: 3485696. Throughput: 0: 10431.8. Samples: 3469304. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-07 22:59:42,817][286098] Avg episode reward: [(0, '4351.386')] [2023-03-07 22:59:42,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000006808_3485696.pth... [2023-03-07 22:59:42,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000006192_3170304.pth [2023-03-07 22:59:42,823][286341] Saving new best policy, reward=4351.386! [2023-03-07 22:59:46,040][286389] Updated weights for policy 0, policy_version 6880 (0.0005) [2023-03-07 22:59:47,816][286098] Fps is (10 sec: 10649.6, 60 sec: 10444.8, 300 sec: 10385.8). Total num frames: 3538944. Throughput: 0: 10419.9. Samples: 3532588. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-07 22:59:47,816][286098] Avg episode reward: [(0, '4138.245')] [2023-03-07 22:59:50,223][286389] Updated weights for policy 0, policy_version 6960 (0.0004) [2023-03-07 22:59:52,816][286098] Fps is (10 sec: 10240.0, 60 sec: 10376.5, 300 sec: 10371.9). Total num frames: 3588096. Throughput: 0: 10431.5. Samples: 3562080. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 22:59:52,817][286098] Avg episode reward: [(0, '3955.603')] [2023-03-07 22:59:54,436][286389] Updated weights for policy 0, policy_version 7040 (0.0005) [2023-03-07 22:59:57,816][286098] Fps is (10 sec: 9830.3, 60 sec: 10376.5, 300 sec: 10358.0). Total num frames: 3637248. Throughput: 0: 10376.7. Samples: 3620936. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-07 22:59:57,816][286098] Avg episode reward: [(0, '4120.981')] [2023-03-07 22:59:57,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000007104_3637248.pth... [2023-03-07 22:59:57,821][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000006496_3325952.pth [2023-03-07 22:59:58,510][286389] Updated weights for policy 0, policy_version 7120 (0.0005) [2023-03-07 23:00:02,616][286389] Updated weights for policy 0, policy_version 7200 (0.0005) [2023-03-07 23:00:02,816][286098] Fps is (10 sec: 9830.4, 60 sec: 10308.3, 300 sec: 10330.2). Total num frames: 3686400. Throughput: 0: 10381.0. Samples: 3681144. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-07 23:00:02,816][286098] Avg episode reward: [(0, '4255.642')] [2023-03-07 23:00:06,431][286389] Updated weights for policy 0, policy_version 7280 (0.0004) [2023-03-07 23:00:07,816][286098] Fps is (10 sec: 10240.1, 60 sec: 10376.5, 300 sec: 10330.3). Total num frames: 3739648. Throughput: 0: 10395.4. Samples: 3711520. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-07 23:00:07,816][286098] Avg episode reward: [(0, '4314.272')] [2023-03-07 23:00:10,299][286389] Updated weights for policy 0, policy_version 7360 (0.0005) [2023-03-07 23:00:12,816][286098] Fps is (10 sec: 10649.6, 60 sec: 10376.5, 300 sec: 10316.4). Total num frames: 3792896. Throughput: 0: 10431.4. Samples: 3776520. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:00:12,816][286098] Avg episode reward: [(0, '4046.122')] [2023-03-07 23:00:12,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000007408_3792896.pth... [2023-03-07 23:00:12,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000006808_3485696.pth [2023-03-07 23:00:14,121][286389] Updated weights for policy 0, policy_version 7440 (0.0004) [2023-03-07 23:00:17,816][286098] Fps is (10 sec: 10649.6, 60 sec: 10444.8, 300 sec: 10316.4). Total num frames: 3846144. Throughput: 0: 10408.5. Samples: 3839264. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:00:17,816][286098] Avg episode reward: [(0, '4210.893')] [2023-03-07 23:00:18,201][286389] Updated weights for policy 0, policy_version 7520 (0.0005) [2023-03-07 23:00:22,547][286389] Updated weights for policy 0, policy_version 7600 (0.0005) [2023-03-07 23:00:22,816][286098] Fps is (10 sec: 9830.4, 60 sec: 10376.5, 300 sec: 10302.5). Total num frames: 3891200. Throughput: 0: 10325.0. Samples: 3867704. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-07 23:00:22,816][286098] Avg episode reward: [(0, '4092.930')] [2023-03-07 23:00:26,967][286389] Updated weights for policy 0, policy_version 7680 (0.0005) [2023-03-07 23:00:27,816][286098] Fps is (10 sec: 9011.2, 60 sec: 10240.0, 300 sec: 10260.8). Total num frames: 3936256. Throughput: 0: 10103.7. Samples: 3923968. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-07 23:00:27,816][286098] Avg episode reward: [(0, '4019.320')] [2023-03-07 23:00:27,822][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000007696_3940352.pth... [2023-03-07 23:00:27,823][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000007104_3637248.pth [2023-03-07 23:00:31,104][286389] Updated weights for policy 0, policy_version 7760 (0.0004) [2023-03-07 23:00:32,816][286098] Fps is (10 sec: 9830.5, 60 sec: 10171.7, 300 sec: 10260.8). Total num frames: 3989504. Throughput: 0: 10006.4. Samples: 3982876. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:00:32,816][286098] Avg episode reward: [(0, '4074.922')] [2023-03-07 23:00:35,023][286389] Updated weights for policy 0, policy_version 7840 (0.0005) [2023-03-07 23:00:37,816][286098] Fps is (10 sec: 10649.5, 60 sec: 10171.7, 300 sec: 10260.8). Total num frames: 4042752. Throughput: 0: 10046.7. Samples: 4014180. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:00:37,816][286098] Avg episode reward: [(0, '4160.614')] [2023-03-07 23:00:38,894][286389] Updated weights for policy 0, policy_version 7920 (0.0004) [2023-03-07 23:00:42,816][286098] Fps is (10 sec: 10239.9, 60 sec: 10103.5, 300 sec: 10260.8). Total num frames: 4091904. Throughput: 0: 10140.4. Samples: 4077252. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:00:42,827][286098] Avg episode reward: [(0, '4291.476')] [2023-03-07 23:00:42,830][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000007992_4091904.pth... [2023-03-07 23:00:42,831][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000007408_3792896.pth [2023-03-07 23:00:42,873][286389] Updated weights for policy 0, policy_version 8000 (0.0005) [2023-03-07 23:00:46,812][286389] Updated weights for policy 0, policy_version 8080 (0.0005) [2023-03-07 23:00:47,816][286098] Fps is (10 sec: 10240.0, 60 sec: 10103.5, 300 sec: 10274.7). Total num frames: 4145152. Throughput: 0: 10190.2. Samples: 4139704. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:00:47,816][286098] Avg episode reward: [(0, '4265.255')] [2023-03-07 23:00:50,618][286389] Updated weights for policy 0, policy_version 8160 (0.0003) [2023-03-07 23:00:52,816][286098] Fps is (10 sec: 10649.6, 60 sec: 10171.7, 300 sec: 10288.6). Total num frames: 4198400. Throughput: 0: 10235.8. Samples: 4172132. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:00:52,827][286098] Avg episode reward: [(0, '4148.336')] [2023-03-07 23:00:54,378][286389] Updated weights for policy 0, policy_version 8240 (0.0005) [2023-03-07 23:00:57,816][286098] Fps is (10 sec: 11059.1, 60 sec: 10308.3, 300 sec: 10316.4). Total num frames: 4255744. Throughput: 0: 10255.6. Samples: 4238024. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-07 23:00:57,816][286098] Avg episode reward: [(0, '4445.047')] [2023-03-07 23:00:57,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000008312_4255744.pth... [2023-03-07 23:00:57,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000007696_3940352.pth [2023-03-07 23:00:57,823][286341] Saving new best policy, reward=4445.047! [2023-03-07 23:00:58,039][286389] Updated weights for policy 0, policy_version 8320 (0.0004) [2023-03-07 23:01:01,687][286389] Updated weights for policy 0, policy_version 8400 (0.0004) [2023-03-07 23:01:02,816][286098] Fps is (10 sec: 11468.9, 60 sec: 10444.8, 300 sec: 10344.1). Total num frames: 4313088. Throughput: 0: 10348.8. Samples: 4304960. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-07 23:01:02,816][286098] Avg episode reward: [(0, '4474.223')] [2023-03-07 23:01:02,817][286341] Saving new best policy, reward=4474.223! [2023-03-07 23:01:05,235][286389] Updated weights for policy 0, policy_version 8480 (0.0004) [2023-03-07 23:01:07,816][286098] Fps is (10 sec: 11468.9, 60 sec: 10513.1, 300 sec: 10385.8). Total num frames: 4370432. Throughput: 0: 10489.6. Samples: 4339736. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-07 23:01:07,816][286098] Avg episode reward: [(0, '4393.375')] [2023-03-07 23:01:08,860][286389] Updated weights for policy 0, policy_version 8560 (0.0003) [2023-03-07 23:01:12,816][286098] Fps is (10 sec: 10649.6, 60 sec: 10444.8, 300 sec: 10385.8). Total num frames: 4419584. Throughput: 0: 10715.4. Samples: 4406160. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:01:12,816][286098] Avg episode reward: [(0, '4498.211')] [2023-03-07 23:01:12,818][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000008632_4419584.pth... [2023-03-07 23:01:12,820][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000007992_4091904.pth [2023-03-07 23:01:12,820][286341] Saving new best policy, reward=4498.211! [2023-03-07 23:01:12,861][286389] Updated weights for policy 0, policy_version 8640 (0.0005) [2023-03-07 23:01:17,014][286389] Updated weights for policy 0, policy_version 8720 (0.0005) [2023-03-07 23:01:17,816][286098] Fps is (10 sec: 9830.5, 60 sec: 10376.5, 300 sec: 10399.7). Total num frames: 4468736. Throughput: 0: 10710.1. Samples: 4464832. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:01:17,816][286098] Avg episode reward: [(0, '4400.513')] [2023-03-07 23:01:21,130][286389] Updated weights for policy 0, policy_version 8800 (0.0005) [2023-03-07 23:01:22,816][286098] Fps is (10 sec: 10240.0, 60 sec: 10513.1, 300 sec: 10413.6). Total num frames: 4521984. Throughput: 0: 10686.0. Samples: 4495048. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-07 23:01:22,816][286098] Avg episode reward: [(0, '4469.938')] [2023-03-07 23:01:25,111][286389] Updated weights for policy 0, policy_version 8880 (0.0004) [2023-03-07 23:01:27,816][286098] Fps is (10 sec: 10239.9, 60 sec: 10581.3, 300 sec: 10399.7). Total num frames: 4571136. Throughput: 0: 10656.8. Samples: 4556808. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:01:27,816][286098] Avg episode reward: [(0, '4433.814')] [2023-03-07 23:01:27,873][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000008936_4575232.pth... [2023-03-07 23:01:27,876][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000008312_4255744.pth [2023-03-07 23:01:28,995][286389] Updated weights for policy 0, policy_version 8960 (0.0004) [2023-03-07 23:01:32,728][286389] Updated weights for policy 0, policy_version 9040 (0.0003) [2023-03-07 23:01:32,816][286098] Fps is (10 sec: 10649.5, 60 sec: 10649.6, 300 sec: 10427.4). Total num frames: 4628480. Throughput: 0: 10713.1. Samples: 4621792. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-07 23:01:32,816][286098] Avg episode reward: [(0, '4407.700')] [2023-03-07 23:01:36,668][286389] Updated weights for policy 0, policy_version 9120 (0.0003) [2023-03-07 23:01:37,816][286098] Fps is (10 sec: 11059.2, 60 sec: 10649.6, 300 sec: 10427.4). Total num frames: 4681728. Throughput: 0: 10687.2. Samples: 4653056. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-07 23:01:37,816][286098] Avg episode reward: [(0, '4439.998')] [2023-03-07 23:01:40,510][286389] Updated weights for policy 0, policy_version 9200 (0.0003) [2023-03-07 23:01:42,816][286098] Fps is (10 sec: 10649.6, 60 sec: 10717.9, 300 sec: 10441.3). Total num frames: 4734976. Throughput: 0: 10614.8. Samples: 4715688. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:01:42,816][286098] Avg episode reward: [(0, '4461.680')] [2023-03-07 23:01:42,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000009248_4734976.pth... [2023-03-07 23:01:42,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000008632_4419584.pth [2023-03-07 23:01:44,238][286389] Updated weights for policy 0, policy_version 9280 (0.0003) [2023-03-07 23:01:47,789][286389] Updated weights for policy 0, policy_version 9360 (0.0003) [2023-03-07 23:01:47,816][286098] Fps is (10 sec: 11059.2, 60 sec: 10786.1, 300 sec: 10469.1). Total num frames: 4792320. Throughput: 0: 10648.5. Samples: 4784144. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:01:47,816][286098] Avg episode reward: [(0, '4169.248')] [2023-03-07 23:01:51,654][286389] Updated weights for policy 0, policy_version 9440 (0.0003) [2023-03-07 23:01:52,816][286098] Fps is (10 sec: 11059.3, 60 sec: 10786.1, 300 sec: 10496.9). Total num frames: 4845568. Throughput: 0: 10603.6. Samples: 4816896. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:01:52,816][286098] Avg episode reward: [(0, '4323.714')] [2023-03-07 23:01:55,400][286389] Updated weights for policy 0, policy_version 9520 (0.0004) [2023-03-07 23:01:57,816][286098] Fps is (10 sec: 10649.6, 60 sec: 10717.9, 300 sec: 10496.9). Total num frames: 4898816. Throughput: 0: 10573.3. Samples: 4881960. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:01:57,816][286098] Avg episode reward: [(0, '4399.527')] [2023-03-07 23:01:57,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000009568_4898816.pth... [2023-03-07 23:01:57,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000008936_4575232.pth [2023-03-07 23:01:59,282][286389] Updated weights for policy 0, policy_version 9600 (0.0005) [2023-03-07 23:02:02,816][286098] Fps is (10 sec: 10240.1, 60 sec: 10581.3, 300 sec: 10483.0). Total num frames: 4947968. Throughput: 0: 10653.8. Samples: 4944252. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:02:02,816][286098] Avg episode reward: [(0, '4288.199')] [2023-03-07 23:02:03,220][286389] Updated weights for policy 0, policy_version 9680 (0.0005) [2023-03-07 23:02:06,990][286389] Updated weights for policy 0, policy_version 9760 (0.0005) [2023-03-07 23:02:07,816][286098] Fps is (10 sec: 10649.6, 60 sec: 10581.3, 300 sec: 10496.9). Total num frames: 5005312. Throughput: 0: 10702.2. Samples: 4976648. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:02:07,816][286098] Avg episode reward: [(0, '4393.702')] [2023-03-07 23:02:10,613][286389] Updated weights for policy 0, policy_version 9840 (0.0003) [2023-03-07 23:02:12,816][286098] Fps is (10 sec: 11059.2, 60 sec: 10649.6, 300 sec: 10510.8). Total num frames: 5058560. Throughput: 0: 10796.5. Samples: 5042652. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-07 23:02:12,816][286098] Avg episode reward: [(0, '4381.741')] [2023-03-07 23:02:12,831][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000009888_5062656.pth... [2023-03-07 23:02:12,833][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000009248_4734976.pth [2023-03-07 23:02:14,272][286389] Updated weights for policy 0, policy_version 9920 (0.0003) [2023-03-07 23:02:17,816][286098] Fps is (10 sec: 11059.2, 60 sec: 10786.1, 300 sec: 10524.6). Total num frames: 5115904. Throughput: 0: 10813.7. Samples: 5108408. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-07 23:02:17,816][286098] Avg episode reward: [(0, '4399.224')] [2023-03-07 23:02:18,171][286389] Updated weights for policy 0, policy_version 10000 (0.0003) [2023-03-07 23:02:21,947][286389] Updated weights for policy 0, policy_version 10080 (0.0003) [2023-03-07 23:02:22,816][286098] Fps is (10 sec: 11059.2, 60 sec: 10786.1, 300 sec: 10510.8). Total num frames: 5169152. Throughput: 0: 10833.1. Samples: 5140544. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-07 23:02:22,816][286098] Avg episode reward: [(0, '4419.239')] [2023-03-07 23:02:25,769][286389] Updated weights for policy 0, policy_version 10160 (0.0003) [2023-03-07 23:02:27,816][286098] Fps is (10 sec: 10649.6, 60 sec: 10854.4, 300 sec: 10510.8). Total num frames: 5222400. Throughput: 0: 10881.3. Samples: 5205344. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:02:27,816][286098] Avg episode reward: [(0, '4430.230')] [2023-03-07 23:02:27,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000010200_5222400.pth... [2023-03-07 23:02:27,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000009568_4898816.pth [2023-03-07 23:02:29,594][286389] Updated weights for policy 0, policy_version 10240 (0.0003) [2023-03-07 23:02:32,816][286098] Fps is (10 sec: 10649.6, 60 sec: 10786.1, 300 sec: 10510.8). Total num frames: 5275648. Throughput: 0: 10776.0. Samples: 5269064. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:02:32,816][286098] Avg episode reward: [(0, '4400.092')] [2023-03-07 23:02:33,439][286389] Updated weights for policy 0, policy_version 10320 (0.0003) [2023-03-07 23:02:37,399][286389] Updated weights for policy 0, policy_version 10400 (0.0003) [2023-03-07 23:02:37,816][286098] Fps is (10 sec: 10649.6, 60 sec: 10786.1, 300 sec: 10510.8). Total num frames: 5328896. Throughput: 0: 10749.9. Samples: 5300640. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:02:37,816][286098] Avg episode reward: [(0, '4293.168')] [2023-03-07 23:02:41,177][286389] Updated weights for policy 0, policy_version 10480 (0.0004) [2023-03-07 23:02:42,816][286098] Fps is (10 sec: 10649.5, 60 sec: 10786.1, 300 sec: 10496.9). Total num frames: 5382144. Throughput: 0: 10721.6. Samples: 5364432. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:02:42,816][286098] Avg episode reward: [(0, '4100.770')] [2023-03-07 23:02:42,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000010512_5382144.pth... [2023-03-07 23:02:42,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000009888_5062656.pth [2023-03-07 23:02:45,013][286389] Updated weights for policy 0, policy_version 10560 (0.0003) [2023-03-07 23:02:47,816][286098] Fps is (10 sec: 10649.6, 60 sec: 10717.9, 300 sec: 10496.9). Total num frames: 5435392. Throughput: 0: 10763.8. Samples: 5428624. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:02:47,816][286098] Avg episode reward: [(0, '4353.989')] [2023-03-07 23:02:48,800][286389] Updated weights for policy 0, policy_version 10640 (0.0003) [2023-03-07 23:02:52,547][286389] Updated weights for policy 0, policy_version 10720 (0.0003) [2023-03-07 23:02:52,816][286098] Fps is (10 sec: 10649.7, 60 sec: 10717.9, 300 sec: 10483.0). Total num frames: 5488640. Throughput: 0: 10782.5. Samples: 5461860. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-07 23:02:52,816][286098] Avg episode reward: [(0, '4273.918')] [2023-03-07 23:02:56,164][286389] Updated weights for policy 0, policy_version 10800 (0.0003) [2023-03-07 23:02:57,816][286098] Fps is (10 sec: 11059.1, 60 sec: 10786.1, 300 sec: 10496.9). Total num frames: 5545984. Throughput: 0: 10804.4. Samples: 5528852. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-07 23:02:57,816][286098] Avg episode reward: [(0, '4456.444')] [2023-03-07 23:02:57,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000010832_5545984.pth... [2023-03-07 23:02:57,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000010200_5222400.pth [2023-03-07 23:02:59,896][286389] Updated weights for policy 0, policy_version 10880 (0.0003) [2023-03-07 23:03:02,816][286098] Fps is (10 sec: 11059.3, 60 sec: 10854.4, 300 sec: 10496.9). Total num frames: 5599232. Throughput: 0: 10816.2. Samples: 5595136. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-07 23:03:02,816][286098] Avg episode reward: [(0, '4486.216')] [2023-03-07 23:03:03,631][286389] Updated weights for policy 0, policy_version 10960 (0.0003) [2023-03-07 23:03:07,272][286389] Updated weights for policy 0, policy_version 11040 (0.0003) [2023-03-07 23:03:07,816][286098] Fps is (10 sec: 11059.2, 60 sec: 10854.4, 300 sec: 10510.8). Total num frames: 5656576. Throughput: 0: 10830.4. Samples: 5627912. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-07 23:03:07,816][286098] Avg episode reward: [(0, '4410.868')] [2023-03-07 23:03:10,957][286389] Updated weights for policy 0, policy_version 11120 (0.0003) [2023-03-07 23:03:12,816][286098] Fps is (10 sec: 11468.7, 60 sec: 10922.7, 300 sec: 10538.5). Total num frames: 5713920. Throughput: 0: 10870.3. Samples: 5694508. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:03:12,816][286098] Avg episode reward: [(0, '4241.109')] [2023-03-07 23:03:12,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000011160_5713920.pth... [2023-03-07 23:03:12,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000010512_5382144.pth [2023-03-07 23:03:14,569][286389] Updated weights for policy 0, policy_version 11200 (0.0003) [2023-03-07 23:03:17,816][286098] Fps is (10 sec: 11059.2, 60 sec: 10854.4, 300 sec: 10538.5). Total num frames: 5767168. Throughput: 0: 10928.6. Samples: 5760852. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:03:17,816][286098] Avg episode reward: [(0, '4113.864')] [2023-03-07 23:03:18,445][286389] Updated weights for policy 0, policy_version 11280 (0.0005) [2023-03-07 23:03:22,419][286389] Updated weights for policy 0, policy_version 11360 (0.0005) [2023-03-07 23:03:22,816][286098] Fps is (10 sec: 10240.0, 60 sec: 10786.1, 300 sec: 10524.6). Total num frames: 5816320. Throughput: 0: 10914.8. Samples: 5791808. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:03:22,816][286098] Avg episode reward: [(0, '4167.615')] [2023-03-07 23:03:26,306][286389] Updated weights for policy 0, policy_version 11440 (0.0005) [2023-03-07 23:03:27,816][286098] Fps is (10 sec: 10240.0, 60 sec: 10786.1, 300 sec: 10538.5). Total num frames: 5869568. Throughput: 0: 10894.4. Samples: 5854680. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-07 23:03:27,816][286098] Avg episode reward: [(0, '4219.217')] [2023-03-07 23:03:27,834][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000011472_5873664.pth... [2023-03-07 23:03:27,835][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000010832_5545984.pth [2023-03-07 23:03:30,166][286389] Updated weights for policy 0, policy_version 11520 (0.0005) [2023-03-07 23:03:32,816][286098] Fps is (10 sec: 10649.6, 60 sec: 10786.1, 300 sec: 10552.4). Total num frames: 5922816. Throughput: 0: 10886.4. Samples: 5918512. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-07 23:03:32,816][286098] Avg episode reward: [(0, '4362.613')] [2023-03-07 23:03:34,054][286389] Updated weights for policy 0, policy_version 11600 (0.0005) [2023-03-07 23:03:37,738][286389] Updated weights for policy 0, policy_version 11680 (0.0005) [2023-03-07 23:03:37,816][286098] Fps is (10 sec: 11059.2, 60 sec: 10854.4, 300 sec: 10580.2). Total num frames: 5980160. Throughput: 0: 10853.8. Samples: 5950284. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:03:37,816][286098] Avg episode reward: [(0, '4335.067')] [2023-03-07 23:03:41,316][286389] Updated weights for policy 0, policy_version 11760 (0.0005) [2023-03-07 23:03:42,816][286098] Fps is (10 sec: 11468.8, 60 sec: 10922.7, 300 sec: 10594.1). Total num frames: 6037504. Throughput: 0: 10875.4. Samples: 6018244. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:03:42,817][286098] Avg episode reward: [(0, '4364.056')] [2023-03-07 23:03:42,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000011792_6037504.pth... [2023-03-07 23:03:42,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000011160_5713920.pth [2023-03-07 23:03:44,858][286389] Updated weights for policy 0, policy_version 11840 (0.0005) [2023-03-07 23:03:47,816][286098] Fps is (10 sec: 11468.8, 60 sec: 10990.9, 300 sec: 10607.9). Total num frames: 6094848. Throughput: 0: 10939.7. Samples: 6087424. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-07 23:03:47,827][286098] Avg episode reward: [(0, '4303.961')] [2023-03-07 23:03:48,445][286389] Updated weights for policy 0, policy_version 11920 (0.0004) [2023-03-07 23:03:52,044][286389] Updated weights for policy 0, policy_version 12000 (0.0005) [2023-03-07 23:03:52,816][286098] Fps is (10 sec: 11468.9, 60 sec: 11059.2, 300 sec: 10635.7). Total num frames: 6152192. Throughput: 0: 10971.8. Samples: 6121644. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-07 23:03:52,827][286098] Avg episode reward: [(0, '4494.215')] [2023-03-07 23:03:55,719][286389] Updated weights for policy 0, policy_version 12080 (0.0005) [2023-03-07 23:03:57,816][286098] Fps is (10 sec: 11059.2, 60 sec: 10990.9, 300 sec: 10635.7). Total num frames: 6205440. Throughput: 0: 10990.1. Samples: 6189064. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-07 23:03:57,827][286098] Avg episode reward: [(0, '4518.321')] [2023-03-07 23:03:57,830][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000012120_6205440.pth... [2023-03-07 23:03:57,833][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000011472_5873664.pth [2023-03-07 23:03:57,834][286341] Saving new best policy, reward=4518.321! [2023-03-07 23:03:59,470][286389] Updated weights for policy 0, policy_version 12160 (0.0005) [2023-03-07 23:04:02,817][286098] Fps is (10 sec: 11057.5, 60 sec: 11058.9, 300 sec: 10663.4). Total num frames: 6262784. Throughput: 0: 10973.0. Samples: 6254656. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-07 23:04:02,828][286098] Avg episode reward: [(0, '4443.801')] [2023-03-07 23:04:03,190][286389] Updated weights for policy 0, policy_version 12240 (0.0004) [2023-03-07 23:04:06,959][286389] Updated weights for policy 0, policy_version 12320 (0.0004) [2023-03-07 23:04:07,816][286098] Fps is (10 sec: 11059.2, 60 sec: 10990.9, 300 sec: 10663.5). Total num frames: 6316032. Throughput: 0: 11013.7. Samples: 6287424. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-07 23:04:07,827][286098] Avg episode reward: [(0, '4490.549')] [2023-03-07 23:04:10,826][286389] Updated weights for policy 0, policy_version 12400 (0.0005) [2023-03-07 23:04:12,816][286098] Fps is (10 sec: 10651.2, 60 sec: 10922.7, 300 sec: 10677.4). Total num frames: 6369280. Throughput: 0: 11043.6. Samples: 6351640. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-07 23:04:12,827][286098] Avg episode reward: [(0, '4490.065')] [2023-03-07 23:04:12,830][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000012440_6369280.pth... [2023-03-07 23:04:12,833][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000011792_6037504.pth [2023-03-07 23:04:14,617][286389] Updated weights for policy 0, policy_version 12480 (0.0004) [2023-03-07 23:04:17,816][286098] Fps is (10 sec: 10649.6, 60 sec: 10922.7, 300 sec: 10691.3). Total num frames: 6422528. Throughput: 0: 11034.9. Samples: 6415084. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-07 23:04:17,827][286098] Avg episode reward: [(0, '4485.146')] [2023-03-07 23:04:18,535][286389] Updated weights for policy 0, policy_version 12560 (0.0005) [2023-03-07 23:04:22,548][286389] Updated weights for policy 0, policy_version 12640 (0.0005) [2023-03-07 23:04:22,816][286098] Fps is (10 sec: 10240.0, 60 sec: 10922.7, 300 sec: 10677.4). Total num frames: 6471680. Throughput: 0: 11031.2. Samples: 6446688. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-07 23:04:22,827][286098] Avg episode reward: [(0, '4484.279')] [2023-03-07 23:04:26,571][286389] Updated weights for policy 0, policy_version 12720 (0.0005) [2023-03-07 23:04:27,816][286098] Fps is (10 sec: 10240.0, 60 sec: 10922.7, 300 sec: 10663.5). Total num frames: 6524928. Throughput: 0: 10886.5. Samples: 6508136. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-07 23:04:27,827][286098] Avg episode reward: [(0, '4503.635')] [2023-03-07 23:04:27,831][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000012744_6524928.pth... [2023-03-07 23:04:27,833][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000012120_6205440.pth [2023-03-07 23:04:30,520][286389] Updated weights for policy 0, policy_version 12800 (0.0005) [2023-03-07 23:04:32,816][286098] Fps is (10 sec: 10240.0, 60 sec: 10854.4, 300 sec: 10649.6). Total num frames: 6574080. Throughput: 0: 10716.0. Samples: 6569644. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:04:32,816][286098] Avg episode reward: [(0, '4518.453')] [2023-03-07 23:04:32,817][286341] Saving new best policy, reward=4518.453! [2023-03-07 23:04:34,494][286389] Updated weights for policy 0, policy_version 12880 (0.0005) [2023-03-07 23:04:37,816][286098] Fps is (10 sec: 10240.0, 60 sec: 10786.1, 300 sec: 10649.6). Total num frames: 6627328. Throughput: 0: 10645.3. Samples: 6600684. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:04:37,816][286098] Avg episode reward: [(0, '4501.102')] [2023-03-07 23:04:38,370][286389] Updated weights for policy 0, policy_version 12960 (0.0005) [2023-03-07 23:04:42,164][286389] Updated weights for policy 0, policy_version 13040 (0.0005) [2023-03-07 23:04:42,816][286098] Fps is (10 sec: 10649.6, 60 sec: 10717.9, 300 sec: 10649.6). Total num frames: 6680576. Throughput: 0: 10566.8. Samples: 6664568. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:04:42,816][286098] Avg episode reward: [(0, '4460.561')] [2023-03-07 23:04:42,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000013048_6680576.pth... [2023-03-07 23:04:42,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000012440_6369280.pth [2023-03-07 23:04:46,063][286389] Updated weights for policy 0, policy_version 13120 (0.0005) [2023-03-07 23:04:47,816][286098] Fps is (10 sec: 10649.6, 60 sec: 10649.6, 300 sec: 10663.5). Total num frames: 6733824. Throughput: 0: 10515.1. Samples: 6727820. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:04:47,816][286098] Avg episode reward: [(0, '4513.852')] [2023-03-07 23:04:49,886][286389] Updated weights for policy 0, policy_version 13200 (0.0004) [2023-03-07 23:04:52,816][286098] Fps is (10 sec: 10649.6, 60 sec: 10581.3, 300 sec: 10677.4). Total num frames: 6787072. Throughput: 0: 10509.3. Samples: 6760344. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:04:52,816][286098] Avg episode reward: [(0, '4200.852')] [2023-03-07 23:04:53,783][286389] Updated weights for policy 0, policy_version 13280 (0.0005) [2023-03-07 23:04:57,755][286389] Updated weights for policy 0, policy_version 13360 (0.0005) [2023-03-07 23:04:57,816][286098] Fps is (10 sec: 10649.6, 60 sec: 10581.3, 300 sec: 10691.3). Total num frames: 6840320. Throughput: 0: 10485.7. Samples: 6823496. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:04:57,816][286098] Avg episode reward: [(0, '4512.090')] [2023-03-07 23:04:57,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000013360_6840320.pth... [2023-03-07 23:04:57,823][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000012744_6524928.pth [2023-03-07 23:05:01,466][286389] Updated weights for policy 0, policy_version 13440 (0.0004) [2023-03-07 23:05:02,816][286098] Fps is (10 sec: 10649.6, 60 sec: 10513.3, 300 sec: 10691.3). Total num frames: 6893568. Throughput: 0: 10512.2. Samples: 6888132. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:05:02,816][286098] Avg episode reward: [(0, '4455.154')] [2023-03-07 23:05:05,049][286389] Updated weights for policy 0, policy_version 13520 (0.0004) [2023-03-07 23:05:07,816][286098] Fps is (10 sec: 11059.3, 60 sec: 10581.3, 300 sec: 10705.1). Total num frames: 6950912. Throughput: 0: 10569.3. Samples: 6922304. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:05:07,816][286098] Avg episode reward: [(0, '4442.919')] [2023-03-07 23:05:08,554][286389] Updated weights for policy 0, policy_version 13600 (0.0004) [2023-03-07 23:05:12,074][286389] Updated weights for policy 0, policy_version 13680 (0.0004) [2023-03-07 23:05:12,816][286098] Fps is (10 sec: 11878.4, 60 sec: 10717.9, 300 sec: 10732.9). Total num frames: 7012352. Throughput: 0: 10751.3. Samples: 6991944. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-07 23:05:12,816][286098] Avg episode reward: [(0, '4463.156')] [2023-03-07 23:05:12,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000013696_7012352.pth... [2023-03-07 23:05:12,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000013048_6680576.pth [2023-03-07 23:05:15,569][286389] Updated weights for policy 0, policy_version 13760 (0.0004) [2023-03-07 23:05:17,816][286098] Fps is (10 sec: 11878.3, 60 sec: 10786.1, 300 sec: 10774.6). Total num frames: 7069696. Throughput: 0: 10947.7. Samples: 7062292. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-07 23:05:17,816][286098] Avg episode reward: [(0, '4492.564')] [2023-03-07 23:05:19,125][286389] Updated weights for policy 0, policy_version 13840 (0.0004) [2023-03-07 23:05:22,639][286389] Updated weights for policy 0, policy_version 13920 (0.0004) [2023-03-07 23:05:22,816][286098] Fps is (10 sec: 11468.8, 60 sec: 10922.7, 300 sec: 10816.2). Total num frames: 7127040. Throughput: 0: 11022.4. Samples: 7096692. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-07 23:05:22,816][286098] Avg episode reward: [(0, '4502.058')] [2023-03-07 23:05:26,166][286389] Updated weights for policy 0, policy_version 14000 (0.0005) [2023-03-07 23:05:27,816][286098] Fps is (10 sec: 11468.8, 60 sec: 10990.9, 300 sec: 10830.1). Total num frames: 7184384. Throughput: 0: 11168.4. Samples: 7167144. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-07 23:05:27,816][286098] Avg episode reward: [(0, '4487.269')] [2023-03-07 23:05:27,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000014032_7184384.pth... [2023-03-07 23:05:27,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000013360_6840320.pth [2023-03-07 23:05:29,625][286389] Updated weights for policy 0, policy_version 14080 (0.0004) [2023-03-07 23:05:32,816][286098] Fps is (10 sec: 11878.5, 60 sec: 11195.7, 300 sec: 10857.9). Total num frames: 7245824. Throughput: 0: 11331.5. Samples: 7237736. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-07 23:05:32,816][286098] Avg episode reward: [(0, '4544.856')] [2023-03-07 23:05:32,817][286341] Saving new best policy, reward=4544.856! [2023-03-07 23:05:33,037][286389] Updated weights for policy 0, policy_version 14160 (0.0004) [2023-03-07 23:05:36,451][286389] Updated weights for policy 0, policy_version 14240 (0.0004) [2023-03-07 23:05:37,816][286098] Fps is (10 sec: 12288.0, 60 sec: 11332.3, 300 sec: 10899.5). Total num frames: 7307264. Throughput: 0: 11425.6. Samples: 7274496. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-07 23:05:37,816][286098] Avg episode reward: [(0, '4419.749')] [2023-03-07 23:05:39,839][286389] Updated weights for policy 0, policy_version 14320 (0.0004) [2023-03-07 23:05:42,816][286098] Fps is (10 sec: 11878.3, 60 sec: 11400.5, 300 sec: 10913.4). Total num frames: 7364608. Throughput: 0: 11618.5. Samples: 7346328. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:05:42,816][286098] Avg episode reward: [(0, '4494.846')] [2023-03-07 23:05:42,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000014384_7364608.pth... [2023-03-07 23:05:42,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000013696_7012352.pth [2023-03-07 23:05:43,270][286389] Updated weights for policy 0, policy_version 14400 (0.0004) [2023-03-07 23:05:46,988][286389] Updated weights for policy 0, policy_version 14480 (0.0004) [2023-03-07 23:05:47,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11468.8, 300 sec: 10927.3). Total num frames: 7421952. Throughput: 0: 11694.8. Samples: 7414396. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:05:47,816][286098] Avg episode reward: [(0, '4236.737')] [2023-03-07 23:05:50,671][286389] Updated weights for policy 0, policy_version 14560 (0.0005) [2023-03-07 23:05:52,816][286098] Fps is (10 sec: 11059.3, 60 sec: 11468.8, 300 sec: 10913.4). Total num frames: 7475200. Throughput: 0: 11678.5. Samples: 7447836. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:05:52,827][286098] Avg episode reward: [(0, '4377.734')] [2023-03-07 23:05:54,208][286389] Updated weights for policy 0, policy_version 14640 (0.0005) [2023-03-07 23:05:57,675][286389] Updated weights for policy 0, policy_version 14720 (0.0005) [2023-03-07 23:05:57,816][286098] Fps is (10 sec: 11468.7, 60 sec: 11605.3, 300 sec: 10927.3). Total num frames: 7536640. Throughput: 0: 11679.7. Samples: 7517532. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-07 23:05:57,827][286098] Avg episode reward: [(0, '4408.379')] [2023-03-07 23:05:57,830][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000014720_7536640.pth... [2023-03-07 23:05:57,832][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000014032_7184384.pth [2023-03-07 23:06:01,044][286389] Updated weights for policy 0, policy_version 14800 (0.0004) [2023-03-07 23:06:02,816][286098] Fps is (10 sec: 12287.9, 60 sec: 11741.9, 300 sec: 10941.2). Total num frames: 7598080. Throughput: 0: 11724.6. Samples: 7589900. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-07 23:06:02,827][286098] Avg episode reward: [(0, '4392.692')] [2023-03-07 23:06:04,437][286389] Updated weights for policy 0, policy_version 14880 (0.0004) [2023-03-07 23:06:07,770][286389] Updated weights for policy 0, policy_version 14960 (0.0004) [2023-03-07 23:06:07,816][286098] Fps is (10 sec: 12288.1, 60 sec: 11810.1, 300 sec: 10982.8). Total num frames: 7659520. Throughput: 0: 11775.7. Samples: 7626600. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-07 23:06:07,827][286098] Avg episode reward: [(0, '4367.877')] [2023-03-07 23:06:11,085][286389] Updated weights for policy 0, policy_version 15040 (0.0004) [2023-03-07 23:06:12,816][286098] Fps is (10 sec: 12287.9, 60 sec: 11810.1, 300 sec: 11024.5). Total num frames: 7720960. Throughput: 0: 11847.6. Samples: 7700288. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-07 23:06:12,827][286098] Avg episode reward: [(0, '4519.365')] [2023-03-07 23:06:12,830][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000015080_7720960.pth... [2023-03-07 23:06:12,833][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000014384_7364608.pth [2023-03-07 23:06:14,406][286389] Updated weights for policy 0, policy_version 15120 (0.0004) [2023-03-07 23:06:17,714][286389] Updated weights for policy 0, policy_version 15200 (0.0004) [2023-03-07 23:06:17,816][286098] Fps is (10 sec: 12288.1, 60 sec: 11878.4, 300 sec: 11052.3). Total num frames: 7782400. Throughput: 0: 11921.8. Samples: 7774216. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:06:17,827][286098] Avg episode reward: [(0, '4524.986')] [2023-03-07 23:06:21,010][286389] Updated weights for policy 0, policy_version 15280 (0.0003) [2023-03-07 23:06:22,816][286098] Fps is (10 sec: 12288.1, 60 sec: 11946.7, 300 sec: 11093.9). Total num frames: 7843840. Throughput: 0: 11925.3. Samples: 7811136. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:06:22,827][286098] Avg episode reward: [(0, '4549.150')] [2023-03-07 23:06:22,827][286341] Saving new best policy, reward=4549.150! [2023-03-07 23:06:24,386][286389] Updated weights for policy 0, policy_version 15360 (0.0004) [2023-03-07 23:06:27,676][286389] Updated weights for policy 0, policy_version 15440 (0.0004) [2023-03-07 23:06:27,816][286098] Fps is (10 sec: 12287.9, 60 sec: 12014.9, 300 sec: 11107.8). Total num frames: 7905280. Throughput: 0: 11967.5. Samples: 7884864. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:06:27,817][286098] Avg episode reward: [(0, '4547.638')] [2023-03-07 23:06:27,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000015440_7905280.pth... [2023-03-07 23:06:27,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000014720_7536640.pth [2023-03-07 23:06:31,031][286389] Updated weights for policy 0, policy_version 15520 (0.0004) [2023-03-07 23:06:32,816][286098] Fps is (10 sec: 12288.0, 60 sec: 12014.9, 300 sec: 11135.6). Total num frames: 7966720. Throughput: 0: 12095.5. Samples: 7958696. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:06:32,816][286098] Avg episode reward: [(0, '4534.400')] [2023-03-07 23:06:34,402][286389] Updated weights for policy 0, policy_version 15600 (0.0004) [2023-03-07 23:06:37,708][286389] Updated weights for policy 0, policy_version 15680 (0.0004) [2023-03-07 23:06:37,816][286098] Fps is (10 sec: 12288.1, 60 sec: 12014.9, 300 sec: 11163.3). Total num frames: 8028160. Throughput: 0: 12169.3. Samples: 7995456. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-07 23:06:37,816][286098] Avg episode reward: [(0, '4539.009')] [2023-03-07 23:06:41,087][286389] Updated weights for policy 0, policy_version 15760 (0.0004) [2023-03-07 23:06:42,816][286098] Fps is (10 sec: 12288.1, 60 sec: 12083.2, 300 sec: 11177.2). Total num frames: 8089600. Throughput: 0: 12257.8. Samples: 8069132. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-07 23:06:42,816][286098] Avg episode reward: [(0, '4532.565')] [2023-03-07 23:06:42,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000015800_8089600.pth... [2023-03-07 23:06:42,821][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000015080_7720960.pth [2023-03-07 23:06:44,388][286389] Updated weights for policy 0, policy_version 15840 (0.0004) [2023-03-07 23:06:47,745][286389] Updated weights for policy 0, policy_version 15920 (0.0004) [2023-03-07 23:06:47,816][286098] Fps is (10 sec: 12288.1, 60 sec: 12151.5, 300 sec: 11205.0). Total num frames: 8151040. Throughput: 0: 12286.3. Samples: 8142784. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-07 23:06:47,816][286098] Avg episode reward: [(0, '4504.286')] [2023-03-07 23:06:51,071][286389] Updated weights for policy 0, policy_version 16000 (0.0005) [2023-03-07 23:06:52,816][286098] Fps is (10 sec: 11878.3, 60 sec: 12219.7, 300 sec: 11218.9). Total num frames: 8208384. Throughput: 0: 12289.3. Samples: 8179620. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-07 23:06:52,816][286098] Avg episode reward: [(0, '4500.810')] [2023-03-07 23:06:54,674][286389] Updated weights for policy 0, policy_version 16080 (0.0005) [2023-03-07 23:06:57,816][286098] Fps is (10 sec: 11468.7, 60 sec: 12151.5, 300 sec: 11246.6). Total num frames: 8265728. Throughput: 0: 12186.9. Samples: 8248700. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-07 23:06:57,816][286098] Avg episode reward: [(0, '4500.214')] [2023-03-07 23:06:57,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000016144_8265728.pth... [2023-03-07 23:06:57,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000015440_7905280.pth [2023-03-07 23:06:58,350][286389] Updated weights for policy 0, policy_version 16160 (0.0005) [2023-03-07 23:07:01,971][286389] Updated weights for policy 0, policy_version 16240 (0.0005) [2023-03-07 23:07:02,816][286098] Fps is (10 sec: 11468.8, 60 sec: 12083.2, 300 sec: 11246.6). Total num frames: 8323072. Throughput: 0: 12034.8. Samples: 8315784. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:07:02,816][286098] Avg episode reward: [(0, '4490.297')] [2023-03-07 23:07:05,626][286389] Updated weights for policy 0, policy_version 16320 (0.0005) [2023-03-07 23:07:07,816][286098] Fps is (10 sec: 11468.9, 60 sec: 12014.9, 300 sec: 11260.5). Total num frames: 8380416. Throughput: 0: 11971.2. Samples: 8349840. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:07:07,816][286098] Avg episode reward: [(0, '4529.038')] [2023-03-07 23:07:09,234][286389] Updated weights for policy 0, policy_version 16400 (0.0005) [2023-03-07 23:07:12,816][286098] Fps is (10 sec: 11059.1, 60 sec: 11878.4, 300 sec: 11246.6). Total num frames: 8433664. Throughput: 0: 11831.5. Samples: 8417280. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-07 23:07:12,816][286098] Avg episode reward: [(0, '4492.808')] [2023-03-07 23:07:12,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000016472_8433664.pth... [2023-03-07 23:07:12,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000015800_8089600.pth [2023-03-07 23:07:12,922][286389] Updated weights for policy 0, policy_version 16480 (0.0005) [2023-03-07 23:07:16,584][286389] Updated weights for policy 0, policy_version 16560 (0.0004) [2023-03-07 23:07:17,816][286098] Fps is (10 sec: 11059.1, 60 sec: 11810.1, 300 sec: 11260.5). Total num frames: 8491008. Throughput: 0: 11668.6. Samples: 8483784. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-07 23:07:17,816][286098] Avg episode reward: [(0, '4359.531')] [2023-03-07 23:07:20,330][286389] Updated weights for policy 0, policy_version 16640 (0.0004) [2023-03-07 23:07:22,816][286098] Fps is (10 sec: 11059.3, 60 sec: 11673.6, 300 sec: 11260.5). Total num frames: 8544256. Throughput: 0: 11587.7. Samples: 8516900. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-07 23:07:22,816][286098] Avg episode reward: [(0, '4431.968')] [2023-03-07 23:07:24,028][286389] Updated weights for policy 0, policy_version 16720 (0.0005) [2023-03-07 23:07:27,748][286389] Updated weights for policy 0, policy_version 16800 (0.0005) [2023-03-07 23:07:27,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11605.3, 300 sec: 11274.4). Total num frames: 8601600. Throughput: 0: 11429.8. Samples: 8583476. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:07:27,816][286098] Avg episode reward: [(0, '4421.085')] [2023-03-07 23:07:27,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000016800_8601600.pth... [2023-03-07 23:07:27,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000016144_8265728.pth [2023-03-07 23:07:31,445][286389] Updated weights for policy 0, policy_version 16880 (0.0005) [2023-03-07 23:07:32,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11468.8, 300 sec: 11274.4). Total num frames: 8654848. Throughput: 0: 11268.5. Samples: 8649868. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:07:32,816][286098] Avg episode reward: [(0, '4479.632')] [2023-03-07 23:07:35,074][286389] Updated weights for policy 0, policy_version 16960 (0.0005) [2023-03-07 23:07:37,816][286098] Fps is (10 sec: 11059.3, 60 sec: 11400.5, 300 sec: 11288.3). Total num frames: 8712192. Throughput: 0: 11198.0. Samples: 8683528. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:07:37,816][286098] Avg episode reward: [(0, '4487.145')] [2023-03-07 23:07:38,703][286389] Updated weights for policy 0, policy_version 17040 (0.0005) [2023-03-07 23:07:42,402][286389] Updated weights for policy 0, policy_version 17120 (0.0005) [2023-03-07 23:07:42,816][286098] Fps is (10 sec: 11468.7, 60 sec: 11332.3, 300 sec: 11302.2). Total num frames: 8769536. Throughput: 0: 11152.4. Samples: 8750556. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:07:42,816][286098] Avg episode reward: [(0, '4526.500')] [2023-03-07 23:07:42,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000017128_8769536.pth... [2023-03-07 23:07:42,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000016472_8433664.pth [2023-03-07 23:07:46,160][286389] Updated weights for policy 0, policy_version 17200 (0.0005) [2023-03-07 23:07:47,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11195.7, 300 sec: 11302.2). Total num frames: 8822784. Throughput: 0: 11120.0. Samples: 8816184. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:07:47,816][286098] Avg episode reward: [(0, '4518.015')] [2023-03-07 23:07:49,814][286389] Updated weights for policy 0, policy_version 17280 (0.0005) [2023-03-07 23:07:52,816][286098] Fps is (10 sec: 10649.7, 60 sec: 11127.5, 300 sec: 11288.3). Total num frames: 8876032. Throughput: 0: 11124.5. Samples: 8850444. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:07:52,816][286098] Avg episode reward: [(0, '4488.019')] [2023-03-07 23:07:53,559][286389] Updated weights for policy 0, policy_version 17360 (0.0005) [2023-03-07 23:07:57,258][286389] Updated weights for policy 0, policy_version 17440 (0.0005) [2023-03-07 23:07:57,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11127.5, 300 sec: 11302.2). Total num frames: 8933376. Throughput: 0: 11101.0. Samples: 8916824. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:07:57,816][286098] Avg episode reward: [(0, '4434.605')] [2023-03-07 23:07:57,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000017448_8933376.pth... [2023-03-07 23:07:57,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000016800_8601600.pth [2023-03-07 23:08:01,036][286389] Updated weights for policy 0, policy_version 17520 (0.0005) [2023-03-07 23:08:02,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11059.2, 300 sec: 11288.3). Total num frames: 8986624. Throughput: 0: 11073.9. Samples: 8982108. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:08:02,816][286098] Avg episode reward: [(0, '4377.972')] [2023-03-07 23:08:04,707][286389] Updated weights for policy 0, policy_version 17600 (0.0005) [2023-03-07 23:08:07,816][286098] Fps is (10 sec: 11059.3, 60 sec: 11059.2, 300 sec: 11288.3). Total num frames: 9043968. Throughput: 0: 11075.7. Samples: 9015308. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:08:07,816][286098] Avg episode reward: [(0, '4386.928')] [2023-03-07 23:08:08,435][286389] Updated weights for policy 0, policy_version 17680 (0.0005) [2023-03-07 23:08:12,083][286389] Updated weights for policy 0, policy_version 17760 (0.0004) [2023-03-07 23:08:12,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11059.2, 300 sec: 11288.3). Total num frames: 9097216. Throughput: 0: 11080.5. Samples: 9082096. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:08:12,816][286098] Avg episode reward: [(0, '4278.096')] [2023-03-07 23:08:12,859][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000017776_9101312.pth... [2023-03-07 23:08:12,860][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000017128_8769536.pth [2023-03-07 23:08:15,903][286389] Updated weights for policy 0, policy_version 17840 (0.0005) [2023-03-07 23:08:17,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11059.2, 300 sec: 11316.1). Total num frames: 9154560. Throughput: 0: 11041.0. Samples: 9146712. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-07 23:08:17,816][286098] Avg episode reward: [(0, '4399.736')] [2023-03-07 23:08:19,587][286389] Updated weights for policy 0, policy_version 17920 (0.0005) [2023-03-07 23:08:22,816][286098] Fps is (10 sec: 11059.1, 60 sec: 11059.2, 300 sec: 11316.1). Total num frames: 9207808. Throughput: 0: 11038.9. Samples: 9180280. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-07 23:08:22,816][286098] Avg episode reward: [(0, '4293.999')] [2023-03-07 23:08:23,223][286389] Updated weights for policy 0, policy_version 18000 (0.0005) [2023-03-07 23:08:26,987][286389] Updated weights for policy 0, policy_version 18080 (0.0005) [2023-03-07 23:08:27,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11059.2, 300 sec: 11330.0). Total num frames: 9265152. Throughput: 0: 11032.1. Samples: 9247000. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-07 23:08:27,816][286098] Avg episode reward: [(0, '4284.094')] [2023-03-07 23:08:27,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000018096_9265152.pth... [2023-03-07 23:08:27,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000017448_8933376.pth [2023-03-07 23:08:30,690][286389] Updated weights for policy 0, policy_version 18160 (0.0005) [2023-03-07 23:08:32,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11059.2, 300 sec: 11316.1). Total num frames: 9318400. Throughput: 0: 11049.7. Samples: 9313420. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-07 23:08:32,816][286098] Avg episode reward: [(0, '4484.139')] [2023-03-07 23:08:34,370][286389] Updated weights for policy 0, policy_version 18240 (0.0005) [2023-03-07 23:08:37,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11059.2, 300 sec: 11316.1). Total num frames: 9375744. Throughput: 0: 11035.9. Samples: 9347060. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-07 23:08:37,816][286098] Avg episode reward: [(0, '4465.281')] [2023-03-07 23:08:38,054][286389] Updated weights for policy 0, policy_version 18320 (0.0005) [2023-03-07 23:08:41,687][286389] Updated weights for policy 0, policy_version 18400 (0.0005) [2023-03-07 23:08:42,816][286098] Fps is (10 sec: 11468.7, 60 sec: 11059.2, 300 sec: 11316.1). Total num frames: 9433088. Throughput: 0: 11040.3. Samples: 9413636. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:08:42,816][286098] Avg episode reward: [(0, '4482.074')] [2023-03-07 23:08:42,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000018424_9433088.pth... [2023-03-07 23:08:42,821][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000017776_9101312.pth [2023-03-07 23:08:45,440][286389] Updated weights for policy 0, policy_version 18480 (0.0005) [2023-03-07 23:08:47,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11059.2, 300 sec: 11302.2). Total num frames: 9486336. Throughput: 0: 11052.2. Samples: 9479456. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:08:47,816][286098] Avg episode reward: [(0, '4531.051')] [2023-03-07 23:08:49,168][286389] Updated weights for policy 0, policy_version 18560 (0.0005) [2023-03-07 23:08:52,816][286098] Fps is (10 sec: 10649.7, 60 sec: 11059.2, 300 sec: 11302.2). Total num frames: 9539584. Throughput: 0: 11042.1. Samples: 9512204. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-07 23:08:52,816][286098] Avg episode reward: [(0, '4520.486')] [2023-03-07 23:08:52,955][286389] Updated weights for policy 0, policy_version 18640 (0.0005) [2023-03-07 23:08:56,728][286389] Updated weights for policy 0, policy_version 18720 (0.0005) [2023-03-07 23:08:57,816][286098] Fps is (10 sec: 10649.5, 60 sec: 10990.9, 300 sec: 11288.4). Total num frames: 9592832. Throughput: 0: 11003.3. Samples: 9577248. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-07 23:08:57,817][286098] Avg episode reward: [(0, '4526.342')] [2023-03-07 23:08:57,847][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000018744_9596928.pth... [2023-03-07 23:08:57,848][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000018096_9265152.pth [2023-03-07 23:09:00,560][286389] Updated weights for policy 0, policy_version 18800 (0.0005) [2023-03-07 23:09:02,816][286098] Fps is (10 sec: 10649.4, 60 sec: 10990.9, 300 sec: 11288.3). Total num frames: 9646080. Throughput: 0: 11007.4. Samples: 9642048. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-07 23:09:02,817][286098] Avg episode reward: [(0, '4399.308')] [2023-03-07 23:09:04,369][286389] Updated weights for policy 0, policy_version 18880 (0.0005) [2023-03-07 23:09:07,816][286098] Fps is (10 sec: 11059.3, 60 sec: 10990.9, 300 sec: 11302.2). Total num frames: 9703424. Throughput: 0: 10987.3. Samples: 9674708. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:09:07,816][286098] Avg episode reward: [(0, '4467.283')] [2023-03-07 23:09:08,106][286389] Updated weights for policy 0, policy_version 18960 (0.0005) [2023-03-07 23:09:11,889][286389] Updated weights for policy 0, policy_version 19040 (0.0005) [2023-03-07 23:09:12,816][286098] Fps is (10 sec: 11059.3, 60 sec: 10990.9, 300 sec: 11302.2). Total num frames: 9756672. Throughput: 0: 10961.9. Samples: 9740288. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:09:12,816][286098] Avg episode reward: [(0, '4497.092')] [2023-03-07 23:09:12,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000019056_9756672.pth... [2023-03-07 23:09:12,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000018424_9433088.pth [2023-03-07 23:09:15,688][286389] Updated weights for policy 0, policy_version 19120 (0.0005) [2023-03-07 23:09:17,816][286098] Fps is (10 sec: 10649.6, 60 sec: 10922.7, 300 sec: 11316.1). Total num frames: 9809920. Throughput: 0: 10914.8. Samples: 9804584. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:09:17,816][286098] Avg episode reward: [(0, '4419.619')] [2023-03-07 23:09:19,481][286389] Updated weights for policy 0, policy_version 19200 (0.0005) [2023-03-07 23:09:22,816][286098] Fps is (10 sec: 11059.3, 60 sec: 10991.0, 300 sec: 11330.0). Total num frames: 9867264. Throughput: 0: 10884.5. Samples: 9836860. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:09:22,816][286098] Avg episode reward: [(0, '4438.133')] [2023-03-07 23:09:23,108][286389] Updated weights for policy 0, policy_version 19280 (0.0004) [2023-03-07 23:09:26,539][286389] Updated weights for policy 0, policy_version 19360 (0.0004) [2023-03-07 23:09:27,816][286098] Fps is (10 sec: 11468.8, 60 sec: 10990.9, 300 sec: 11357.7). Total num frames: 9924608. Throughput: 0: 10963.8. Samples: 9907008. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:09:27,816][286098] Avg episode reward: [(0, '4523.050')] [2023-03-07 23:09:27,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000019384_9924608.pth... [2023-03-07 23:09:27,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000018744_9596928.pth [2023-03-07 23:09:30,029][286389] Updated weights for policy 0, policy_version 19440 (0.0004) [2023-03-07 23:09:32,816][286098] Fps is (10 sec: 11878.3, 60 sec: 11127.5, 300 sec: 11385.5). Total num frames: 9986048. Throughput: 0: 11076.1. Samples: 9977880. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-07 23:09:32,816][286098] Avg episode reward: [(0, '4512.392')] [2023-03-07 23:09:33,455][286389] Updated weights for policy 0, policy_version 19520 (0.0004) [2023-03-07 23:09:36,944][286389] Updated weights for policy 0, policy_version 19600 (0.0004) [2023-03-07 23:09:37,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11127.5, 300 sec: 11399.4). Total num frames: 10043392. Throughput: 0: 11127.5. Samples: 10012944. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-07 23:09:37,816][286098] Avg episode reward: [(0, '4500.235')] [2023-03-07 23:09:40,361][286389] Updated weights for policy 0, policy_version 19680 (0.0004) [2023-03-07 23:09:42,816][286098] Fps is (10 sec: 11878.5, 60 sec: 11195.8, 300 sec: 11427.1). Total num frames: 10104832. Throughput: 0: 11270.4. Samples: 10084416. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-07 23:09:42,816][286098] Avg episode reward: [(0, '4425.422')] [2023-03-07 23:09:42,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000019736_10104832.pth... [2023-03-07 23:09:42,820][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000019056_9756672.pth [2023-03-07 23:09:43,831][286389] Updated weights for policy 0, policy_version 19760 (0.0004) [2023-03-07 23:09:47,576][286389] Updated weights for policy 0, policy_version 19840 (0.0005) [2023-03-07 23:09:47,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11195.7, 300 sec: 11427.1). Total num frames: 10158080. Throughput: 0: 11356.3. Samples: 10153080. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:09:47,816][286098] Avg episode reward: [(0, '4225.384')] [2023-03-07 23:09:51,396][286389] Updated weights for policy 0, policy_version 19920 (0.0005) [2023-03-07 23:09:52,816][286098] Fps is (10 sec: 10649.6, 60 sec: 11195.7, 300 sec: 11427.1). Total num frames: 10211328. Throughput: 0: 11339.5. Samples: 10184984. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:09:52,816][286098] Avg episode reward: [(0, '4463.643')] [2023-03-07 23:09:54,957][286389] Updated weights for policy 0, policy_version 20000 (0.0005) [2023-03-07 23:09:57,816][286098] Fps is (10 sec: 11468.7, 60 sec: 11332.3, 300 sec: 11454.9). Total num frames: 10272768. Throughput: 0: 11396.0. Samples: 10253108. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:09:57,816][286098] Avg episode reward: [(0, '4470.534')] [2023-03-07 23:09:57,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000020064_10272768.pth... [2023-03-07 23:09:57,823][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000019384_9924608.pth [2023-03-07 23:09:58,378][286389] Updated weights for policy 0, policy_version 20080 (0.0004) [2023-03-07 23:10:01,895][286389] Updated weights for policy 0, policy_version 20160 (0.0004) [2023-03-07 23:10:02,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11400.6, 300 sec: 11454.9). Total num frames: 10330112. Throughput: 0: 11536.6. Samples: 10323732. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-07 23:10:02,816][286098] Avg episode reward: [(0, '4487.288')] [2023-03-07 23:10:05,341][286389] Updated weights for policy 0, policy_version 20240 (0.0004) [2023-03-07 23:10:07,816][286098] Fps is (10 sec: 11878.5, 60 sec: 11468.8, 300 sec: 11454.9). Total num frames: 10391552. Throughput: 0: 11605.5. Samples: 10359108. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-07 23:10:07,816][286098] Avg episode reward: [(0, '4502.789')] [2023-03-07 23:10:08,737][286389] Updated weights for policy 0, policy_version 20320 (0.0004) [2023-03-07 23:10:12,153][286389] Updated weights for policy 0, policy_version 20400 (0.0004) [2023-03-07 23:10:12,816][286098] Fps is (10 sec: 12288.1, 60 sec: 11605.4, 300 sec: 11468.8). Total num frames: 10452992. Throughput: 0: 11670.0. Samples: 10432156. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-07 23:10:12,816][286098] Avg episode reward: [(0, '4320.566')] [2023-03-07 23:10:12,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000020416_10452992.pth... [2023-03-07 23:10:12,820][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000019736_10104832.pth [2023-03-07 23:10:15,832][286389] Updated weights for policy 0, policy_version 20480 (0.0004) [2023-03-07 23:10:17,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11605.3, 300 sec: 11454.9). Total num frames: 10506240. Throughput: 0: 11578.9. Samples: 10498932. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:10:17,816][286098] Avg episode reward: [(0, '4425.024')] [2023-03-07 23:10:19,592][286389] Updated weights for policy 0, policy_version 20560 (0.0005) [2023-03-07 23:10:22,816][286098] Fps is (10 sec: 10649.5, 60 sec: 11537.1, 300 sec: 11441.0). Total num frames: 10559488. Throughput: 0: 11521.1. Samples: 10531392. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:10:22,816][286098] Avg episode reward: [(0, '4395.365')] [2023-03-07 23:10:23,414][286389] Updated weights for policy 0, policy_version 20640 (0.0004) [2023-03-07 23:10:27,243][286389] Updated weights for policy 0, policy_version 20720 (0.0005) [2023-03-07 23:10:27,816][286098] Fps is (10 sec: 10649.5, 60 sec: 11468.8, 300 sec: 11413.3). Total num frames: 10612736. Throughput: 0: 11377.8. Samples: 10596416. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:10:27,816][286098] Avg episode reward: [(0, '4446.752')] [2023-03-07 23:10:27,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000020728_10612736.pth... [2023-03-07 23:10:27,823][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000020064_10272768.pth [2023-03-07 23:10:31,074][286389] Updated weights for policy 0, policy_version 20800 (0.0005) [2023-03-07 23:10:32,816][286098] Fps is (10 sec: 10649.6, 60 sec: 11332.3, 300 sec: 11385.5). Total num frames: 10665984. Throughput: 0: 11285.9. Samples: 10660944. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:10:32,816][286098] Avg episode reward: [(0, '4419.520')] [2023-03-07 23:10:34,827][286389] Updated weights for policy 0, policy_version 20880 (0.0005) [2023-03-07 23:10:37,816][286098] Fps is (10 sec: 10649.6, 60 sec: 11264.0, 300 sec: 11371.6). Total num frames: 10719232. Throughput: 0: 11298.5. Samples: 10693416. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:10:37,817][286098] Avg episode reward: [(0, '4380.126')] [2023-03-07 23:10:38,560][286389] Updated weights for policy 0, policy_version 20960 (0.0005) [2023-03-07 23:10:42,284][286389] Updated weights for policy 0, policy_version 21040 (0.0004) [2023-03-07 23:10:42,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11195.7, 300 sec: 11371.6). Total num frames: 10776576. Throughput: 0: 11259.1. Samples: 10759768. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-07 23:10:42,816][286098] Avg episode reward: [(0, '4384.776')] [2023-03-07 23:10:42,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000021048_10776576.pth... [2023-03-07 23:10:42,823][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000020416_10452992.pth [2023-03-07 23:10:46,123][286389] Updated weights for policy 0, policy_version 21120 (0.0005) [2023-03-07 23:10:47,816][286098] Fps is (10 sec: 11059.3, 60 sec: 11195.7, 300 sec: 11371.6). Total num frames: 10829824. Throughput: 0: 11106.8. Samples: 10823536. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-07 23:10:47,816][286098] Avg episode reward: [(0, '4418.421')] [2023-03-07 23:10:49,997][286389] Updated weights for policy 0, policy_version 21200 (0.0004) [2023-03-07 23:10:52,816][286098] Fps is (10 sec: 10649.7, 60 sec: 11195.7, 300 sec: 11343.8). Total num frames: 10883072. Throughput: 0: 11017.2. Samples: 10854880. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-07 23:10:52,816][286098] Avg episode reward: [(0, '4501.336')] [2023-03-07 23:10:53,728][286389] Updated weights for policy 0, policy_version 21280 (0.0005) [2023-03-07 23:10:57,505][286389] Updated weights for policy 0, policy_version 21360 (0.0005) [2023-03-07 23:10:57,816][286098] Fps is (10 sec: 10649.5, 60 sec: 11059.2, 300 sec: 11316.1). Total num frames: 10936320. Throughput: 0: 10841.8. Samples: 10920040. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:10:57,816][286098] Avg episode reward: [(0, '4420.945')] [2023-03-07 23:10:57,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000021360_10936320.pth... [2023-03-07 23:10:57,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000020728_10612736.pth [2023-03-07 23:11:01,366][286389] Updated weights for policy 0, policy_version 21440 (0.0005) [2023-03-07 23:11:02,816][286098] Fps is (10 sec: 10649.5, 60 sec: 10990.9, 300 sec: 11288.3). Total num frames: 10989568. Throughput: 0: 10812.0. Samples: 10985472. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:11:02,827][286098] Avg episode reward: [(0, '4488.127')] [2023-03-07 23:11:05,114][286389] Updated weights for policy 0, policy_version 21520 (0.0005) [2023-03-07 23:11:07,816][286098] Fps is (10 sec: 11059.2, 60 sec: 10922.7, 300 sec: 11274.4). Total num frames: 11046912. Throughput: 0: 10818.8. Samples: 11018240. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:11:07,827][286098] Avg episode reward: [(0, '4570.458')] [2023-03-07 23:11:07,827][286341] Saving new best policy, reward=4570.458! [2023-03-07 23:11:08,886][286389] Updated weights for policy 0, policy_version 21600 (0.0005) [2023-03-07 23:11:12,776][286389] Updated weights for policy 0, policy_version 21680 (0.0006) [2023-03-07 23:11:12,816][286098] Fps is (10 sec: 11059.0, 60 sec: 10786.1, 300 sec: 11246.6). Total num frames: 11100160. Throughput: 0: 10797.1. Samples: 11082288. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:11:12,827][286098] Avg episode reward: [(0, '4534.832')] [2023-03-07 23:11:12,831][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000021680_11100160.pth... [2023-03-07 23:11:12,833][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000021048_10776576.pth [2023-03-07 23:11:16,290][286389] Updated weights for policy 0, policy_version 21760 (0.0004) [2023-03-07 23:11:17,816][286098] Fps is (10 sec: 11059.2, 60 sec: 10854.4, 300 sec: 11232.8). Total num frames: 11157504. Throughput: 0: 10869.9. Samples: 11150088. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:11:17,816][286098] Avg episode reward: [(0, '4311.978')] [2023-03-07 23:11:19,728][286389] Updated weights for policy 0, policy_version 21840 (0.0004) [2023-03-07 23:11:22,816][286098] Fps is (10 sec: 11469.0, 60 sec: 10922.7, 300 sec: 11218.9). Total num frames: 11214848. Throughput: 0: 10950.4. Samples: 11186184. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:11:22,816][286098] Avg episode reward: [(0, '4221.379')] [2023-03-07 23:11:23,350][286389] Updated weights for policy 0, policy_version 21920 (0.0005) [2023-03-07 23:11:26,877][286389] Updated weights for policy 0, policy_version 22000 (0.0005) [2023-03-07 23:11:27,816][286098] Fps is (10 sec: 11468.8, 60 sec: 10990.9, 300 sec: 11205.0). Total num frames: 11272192. Throughput: 0: 10993.5. Samples: 11254476. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-07 23:11:27,816][286098] Avg episode reward: [(0, '4390.582')] [2023-03-07 23:11:27,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000022016_11272192.pth... [2023-03-07 23:11:27,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000021360_10936320.pth [2023-03-07 23:11:30,401][286389] Updated weights for policy 0, policy_version 22080 (0.0004) [2023-03-07 23:11:32,816][286098] Fps is (10 sec: 11468.9, 60 sec: 11059.2, 300 sec: 11191.1). Total num frames: 11329536. Throughput: 0: 11132.1. Samples: 11324480. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-07 23:11:32,816][286098] Avg episode reward: [(0, '4233.855')] [2023-03-07 23:11:34,023][286389] Updated weights for policy 0, policy_version 22160 (0.0005) [2023-03-07 23:11:37,816][286098] Fps is (10 sec: 11059.1, 60 sec: 11059.2, 300 sec: 11163.3). Total num frames: 11382784. Throughput: 0: 11170.7. Samples: 11357564. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-07 23:11:37,817][286098] Avg episode reward: [(0, '4421.431')] [2023-03-07 23:11:37,862][286389] Updated weights for policy 0, policy_version 22240 (0.0005) [2023-03-07 23:11:41,542][286389] Updated weights for policy 0, policy_version 22320 (0.0005) [2023-03-07 23:11:42,816][286098] Fps is (10 sec: 11059.1, 60 sec: 11059.2, 300 sec: 11149.4). Total num frames: 11440128. Throughput: 0: 11160.5. Samples: 11422260. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-07 23:11:42,816][286098] Avg episode reward: [(0, '4522.142')] [2023-03-07 23:11:42,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000022344_11440128.pth... [2023-03-07 23:11:42,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000021680_11100160.pth [2023-03-07 23:11:44,976][286389] Updated weights for policy 0, policy_version 22400 (0.0005) [2023-03-07 23:11:47,816][286098] Fps is (10 sec: 11878.5, 60 sec: 11195.7, 300 sec: 11163.3). Total num frames: 11501568. Throughput: 0: 11288.2. Samples: 11493440. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-07 23:11:47,816][286098] Avg episode reward: [(0, '4482.687')] [2023-03-07 23:11:48,432][286389] Updated weights for policy 0, policy_version 22480 (0.0004) [2023-03-07 23:11:51,939][286389] Updated weights for policy 0, policy_version 22560 (0.0004) [2023-03-07 23:11:52,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11264.0, 300 sec: 11163.3). Total num frames: 11558912. Throughput: 0: 11354.7. Samples: 11529200. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-07 23:11:52,816][286098] Avg episode reward: [(0, '4504.297')] [2023-03-07 23:11:55,654][286389] Updated weights for policy 0, policy_version 22640 (0.0004) [2023-03-07 23:11:57,816][286098] Fps is (10 sec: 11059.1, 60 sec: 11264.0, 300 sec: 11149.4). Total num frames: 11612160. Throughput: 0: 11412.3. Samples: 11595840. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:11:57,817][286098] Avg episode reward: [(0, '4551.554')] [2023-03-07 23:11:57,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000022680_11612160.pth... [2023-03-07 23:11:57,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000022016_11272192.pth [2023-03-07 23:11:59,579][286389] Updated weights for policy 0, policy_version 22720 (0.0004) [2023-03-07 23:12:02,816][286098] Fps is (10 sec: 10649.6, 60 sec: 11264.0, 300 sec: 11135.6). Total num frames: 11665408. Throughput: 0: 11351.9. Samples: 11660924. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:12:02,816][286098] Avg episode reward: [(0, '4493.691')] [2023-03-07 23:12:03,304][286389] Updated weights for policy 0, policy_version 22800 (0.0004) [2023-03-07 23:12:06,920][286389] Updated weights for policy 0, policy_version 22880 (0.0004) [2023-03-07 23:12:07,816][286098] Fps is (10 sec: 11059.3, 60 sec: 11264.0, 300 sec: 11149.5). Total num frames: 11722752. Throughput: 0: 11281.2. Samples: 11693840. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:12:07,816][286098] Avg episode reward: [(0, '4486.480')] [2023-03-07 23:12:10,702][286389] Updated weights for policy 0, policy_version 22960 (0.0005) [2023-03-07 23:12:12,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11264.0, 300 sec: 11135.6). Total num frames: 11776000. Throughput: 0: 11225.5. Samples: 11759624. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:12:12,816][286098] Avg episode reward: [(0, '4530.873')] [2023-03-07 23:12:12,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000023000_11776000.pth... [2023-03-07 23:12:12,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000022344_11440128.pth [2023-03-07 23:12:14,456][286389] Updated weights for policy 0, policy_version 23040 (0.0006) [2023-03-07 23:12:17,816][286098] Fps is (10 sec: 10649.6, 60 sec: 11195.7, 300 sec: 11135.6). Total num frames: 11829248. Throughput: 0: 11122.9. Samples: 11825012. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:12:17,816][286098] Avg episode reward: [(0, '4528.010')] [2023-03-07 23:12:18,275][286389] Updated weights for policy 0, policy_version 23120 (0.0005) [2023-03-07 23:12:22,099][286389] Updated weights for policy 0, policy_version 23200 (0.0005) [2023-03-07 23:12:22,816][286098] Fps is (10 sec: 10649.7, 60 sec: 11127.5, 300 sec: 11121.7). Total num frames: 11882496. Throughput: 0: 11094.7. Samples: 11856824. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:12:22,816][286098] Avg episode reward: [(0, '4517.911')] [2023-03-07 23:12:25,863][286389] Updated weights for policy 0, policy_version 23280 (0.0005) [2023-03-07 23:12:27,816][286098] Fps is (10 sec: 11059.1, 60 sec: 11127.5, 300 sec: 11135.6). Total num frames: 11939840. Throughput: 0: 11096.6. Samples: 11921608. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:12:27,816][286098] Avg episode reward: [(0, '4543.045')] [2023-03-07 23:12:27,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000023320_11939840.pth... [2023-03-07 23:12:27,823][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000022680_11612160.pth [2023-03-07 23:12:29,493][286389] Updated weights for policy 0, policy_version 23360 (0.0005) [2023-03-07 23:12:32,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11127.5, 300 sec: 11135.6). Total num frames: 11997184. Throughput: 0: 11013.9. Samples: 11989064. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:12:32,816][286098] Avg episode reward: [(0, '4460.118')] [2023-03-07 23:12:33,182][286389] Updated weights for policy 0, policy_version 23440 (0.0005) [2023-03-07 23:12:36,719][286389] Updated weights for policy 0, policy_version 23520 (0.0004) [2023-03-07 23:12:37,816][286098] Fps is (10 sec: 11468.9, 60 sec: 11195.8, 300 sec: 11135.6). Total num frames: 12054528. Throughput: 0: 10965.3. Samples: 12022640. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:12:37,816][286098] Avg episode reward: [(0, '4468.586')] [2023-03-07 23:12:40,363][286389] Updated weights for policy 0, policy_version 23600 (0.0005) [2023-03-07 23:12:42,816][286098] Fps is (10 sec: 11059.1, 60 sec: 11127.5, 300 sec: 11135.6). Total num frames: 12107776. Throughput: 0: 11010.9. Samples: 12091332. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:12:42,816][286098] Avg episode reward: [(0, '4150.827')] [2023-03-07 23:12:42,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000023648_12107776.pth... [2023-03-07 23:12:42,823][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000023000_11776000.pth [2023-03-07 23:12:44,166][286389] Updated weights for policy 0, policy_version 23680 (0.0005) [2023-03-07 23:12:47,542][286389] Updated weights for policy 0, policy_version 23760 (0.0005) [2023-03-07 23:12:47,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11059.2, 300 sec: 11149.4). Total num frames: 12165120. Throughput: 0: 11091.1. Samples: 12160024. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:12:47,827][286098] Avg episode reward: [(0, '3728.095')] [2023-03-07 23:12:51,126][286389] Updated weights for policy 0, policy_version 23840 (0.0005) [2023-03-07 23:12:52,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11059.2, 300 sec: 11149.5). Total num frames: 12222464. Throughput: 0: 11110.0. Samples: 12193792. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:12:52,816][286098] Avg episode reward: [(0, '3897.527')] [2023-03-07 23:12:54,782][286389] Updated weights for policy 0, policy_version 23920 (0.0005) [2023-03-07 23:12:57,816][286098] Fps is (10 sec: 11468.9, 60 sec: 11127.5, 300 sec: 11163.3). Total num frames: 12279808. Throughput: 0: 11142.9. Samples: 12261052. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:12:57,827][286098] Avg episode reward: [(0, '4192.971')] [2023-03-07 23:12:57,830][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000023984_12279808.pth... [2023-03-07 23:12:57,833][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000023320_11939840.pth [2023-03-07 23:12:58,565][286389] Updated weights for policy 0, policy_version 24000 (0.0005) [2023-03-07 23:13:02,368][286389] Updated weights for policy 0, policy_version 24080 (0.0005) [2023-03-07 23:13:02,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11127.5, 300 sec: 11149.4). Total num frames: 12333056. Throughput: 0: 11124.1. Samples: 12325596. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:13:02,827][286098] Avg episode reward: [(0, '4457.610')] [2023-03-07 23:13:06,096][286389] Updated weights for policy 0, policy_version 24160 (0.0005) [2023-03-07 23:13:07,816][286098] Fps is (10 sec: 10649.5, 60 sec: 11059.2, 300 sec: 11149.4). Total num frames: 12386304. Throughput: 0: 11148.6. Samples: 12358512. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:13:07,816][286098] Avg episode reward: [(0, '4452.929')] [2023-03-07 23:13:09,875][286389] Updated weights for policy 0, policy_version 24240 (0.0005) [2023-03-07 23:13:12,816][286098] Fps is (10 sec: 10649.6, 60 sec: 11059.2, 300 sec: 11135.6). Total num frames: 12439552. Throughput: 0: 11148.0. Samples: 12423268. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:13:12,827][286098] Avg episode reward: [(0, '4304.000')] [2023-03-07 23:13:12,865][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000024304_12443648.pth... [2023-03-07 23:13:12,867][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000023648_12107776.pth [2023-03-07 23:13:13,651][286389] Updated weights for policy 0, policy_version 24320 (0.0005) [2023-03-07 23:13:17,368][286389] Updated weights for policy 0, policy_version 24400 (0.0006) [2023-03-07 23:13:17,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11127.5, 300 sec: 11149.5). Total num frames: 12496896. Throughput: 0: 11110.6. Samples: 12489040. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-07 23:13:17,827][286098] Avg episode reward: [(0, '4358.747')] [2023-03-07 23:13:21,023][286389] Updated weights for policy 0, policy_version 24480 (0.0005) [2023-03-07 23:13:22,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11127.5, 300 sec: 11135.6). Total num frames: 12550144. Throughput: 0: 11115.0. Samples: 12522816. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-07 23:13:22,816][286098] Avg episode reward: [(0, '4346.185')] [2023-03-07 23:13:24,563][286389] Updated weights for policy 0, policy_version 24560 (0.0005) [2023-03-07 23:13:27,816][286098] Fps is (10 sec: 11468.7, 60 sec: 11195.7, 300 sec: 11163.3). Total num frames: 12611584. Throughput: 0: 11130.4. Samples: 12592200. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-07 23:13:27,816][286098] Avg episode reward: [(0, '4201.803')] [2023-03-07 23:13:27,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000024632_12611584.pth... [2023-03-07 23:13:27,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000023984_12279808.pth [2023-03-07 23:13:28,053][286389] Updated weights for policy 0, policy_version 24640 (0.0005) [2023-03-07 23:13:31,478][286389] Updated weights for policy 0, policy_version 24720 (0.0005) [2023-03-07 23:13:32,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11195.7, 300 sec: 11163.3). Total num frames: 12668928. Throughput: 0: 11192.7. Samples: 12663696. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-07 23:13:32,816][286098] Avg episode reward: [(0, '4528.832')] [2023-03-07 23:13:34,938][286389] Updated weights for policy 0, policy_version 24800 (0.0005) [2023-03-07 23:13:37,816][286098] Fps is (10 sec: 11878.5, 60 sec: 11264.0, 300 sec: 11177.2). Total num frames: 12730368. Throughput: 0: 11225.8. Samples: 12698952. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:13:37,816][286098] Avg episode reward: [(0, '4458.665')] [2023-03-07 23:13:38,408][286389] Updated weights for policy 0, policy_version 24880 (0.0005) [2023-03-07 23:13:41,835][286389] Updated weights for policy 0, policy_version 24960 (0.0005) [2023-03-07 23:13:42,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11332.3, 300 sec: 11191.1). Total num frames: 12787712. Throughput: 0: 11319.4. Samples: 12770424. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:13:42,816][286098] Avg episode reward: [(0, '4526.610')] [2023-03-07 23:13:42,828][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000024984_12791808.pth... [2023-03-07 23:13:42,829][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000024304_12443648.pth [2023-03-07 23:13:45,260][286389] Updated weights for policy 0, policy_version 25040 (0.0005) [2023-03-07 23:13:47,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11400.5, 300 sec: 11218.9). Total num frames: 12849152. Throughput: 0: 11477.4. Samples: 12842080. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:13:47,816][286098] Avg episode reward: [(0, '4427.681')] [2023-03-07 23:13:48,671][286389] Updated weights for policy 0, policy_version 25120 (0.0004) [2023-03-07 23:13:52,260][286389] Updated weights for policy 0, policy_version 25200 (0.0005) [2023-03-07 23:13:52,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11400.5, 300 sec: 11232.8). Total num frames: 12906496. Throughput: 0: 11541.7. Samples: 12877888. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-07 23:13:52,816][286098] Avg episode reward: [(0, '4480.483')] [2023-03-07 23:13:55,636][286389] Updated weights for policy 0, policy_version 25280 (0.0004) [2023-03-07 23:13:57,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11468.8, 300 sec: 11260.5). Total num frames: 12967936. Throughput: 0: 11655.5. Samples: 12947768. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-07 23:13:57,816][286098] Avg episode reward: [(0, '4308.603')] [2023-03-07 23:13:57,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000025328_12967936.pth... [2023-03-07 23:13:57,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000024632_12611584.pth [2023-03-07 23:13:59,107][286389] Updated weights for policy 0, policy_version 25360 (0.0005) [2023-03-07 23:14:02,547][286389] Updated weights for policy 0, policy_version 25440 (0.0004) [2023-03-07 23:14:02,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11537.1, 300 sec: 11260.5). Total num frames: 13025280. Throughput: 0: 11790.7. Samples: 13019620. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-07 23:14:02,816][286098] Avg episode reward: [(0, '4166.518')] [2023-03-07 23:14:06,266][286389] Updated weights for policy 0, policy_version 25520 (0.0005) [2023-03-07 23:14:07,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11605.3, 300 sec: 11274.4). Total num frames: 13082624. Throughput: 0: 11783.7. Samples: 13053084. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-07 23:14:07,816][286098] Avg episode reward: [(0, '3984.764')] [2023-03-07 23:14:09,854][286389] Updated weights for policy 0, policy_version 25600 (0.0006) [2023-03-07 23:14:12,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11673.6, 300 sec: 11288.3). Total num frames: 13139968. Throughput: 0: 11762.9. Samples: 13121532. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-07 23:14:12,816][286098] Avg episode reward: [(0, '3952.515')] [2023-03-07 23:14:12,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000025664_13139968.pth... [2023-03-07 23:14:12,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000024984_12791808.pth [2023-03-07 23:14:13,286][286389] Updated weights for policy 0, policy_version 25680 (0.0005) [2023-03-07 23:14:16,690][286389] Updated weights for policy 0, policy_version 25760 (0.0004) [2023-03-07 23:14:17,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11741.9, 300 sec: 11302.2). Total num frames: 13201408. Throughput: 0: 11769.2. Samples: 13193312. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-07 23:14:17,816][286098] Avg episode reward: [(0, '3968.965')] [2023-03-07 23:14:20,124][286389] Updated weights for policy 0, policy_version 25840 (0.0004) [2023-03-07 23:14:22,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11810.1, 300 sec: 11302.2). Total num frames: 13258752. Throughput: 0: 11788.9. Samples: 13229452. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-07 23:14:22,816][286098] Avg episode reward: [(0, '4377.422')] [2023-03-07 23:14:23,787][286389] Updated weights for policy 0, policy_version 25920 (0.0005) [2023-03-07 23:14:27,476][286389] Updated weights for policy 0, policy_version 26000 (0.0005) [2023-03-07 23:14:27,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11673.6, 300 sec: 11274.4). Total num frames: 13312000. Throughput: 0: 11672.5. Samples: 13295688. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:14:27,816][286098] Avg episode reward: [(0, '4519.026')] [2023-03-07 23:14:27,877][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000026008_13316096.pth... [2023-03-07 23:14:27,879][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000025328_12967936.pth [2023-03-07 23:14:31,273][286389] Updated weights for policy 0, policy_version 26080 (0.0005) [2023-03-07 23:14:32,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11673.6, 300 sec: 11274.4). Total num frames: 13369344. Throughput: 0: 11549.2. Samples: 13361796. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:14:32,816][286098] Avg episode reward: [(0, '4475.182')] [2023-03-07 23:14:34,929][286389] Updated weights for policy 0, policy_version 26160 (0.0005) [2023-03-07 23:14:37,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11537.1, 300 sec: 11246.6). Total num frames: 13422592. Throughput: 0: 11499.5. Samples: 13395364. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:14:37,816][286098] Avg episode reward: [(0, '4439.801')] [2023-03-07 23:14:38,790][286389] Updated weights for policy 0, policy_version 26240 (0.0005) [2023-03-07 23:14:42,679][286389] Updated weights for policy 0, policy_version 26320 (0.0005) [2023-03-07 23:14:42,816][286098] Fps is (10 sec: 10649.5, 60 sec: 11468.8, 300 sec: 11246.6). Total num frames: 13475840. Throughput: 0: 11371.1. Samples: 13459468. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-07 23:14:42,816][286098] Avg episode reward: [(0, '4360.685')] [2023-03-07 23:14:42,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000026320_13475840.pth... [2023-03-07 23:14:42,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000025664_13139968.pth [2023-03-07 23:14:46,265][286389] Updated weights for policy 0, policy_version 26400 (0.0005) [2023-03-07 23:14:47,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11400.5, 300 sec: 11260.5). Total num frames: 13533184. Throughput: 0: 11244.7. Samples: 13525632. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-07 23:14:47,827][286098] Avg episode reward: [(0, '4430.005')] [2023-03-07 23:14:49,772][286389] Updated weights for policy 0, policy_version 26480 (0.0004) [2023-03-07 23:14:52,816][286098] Fps is (10 sec: 11059.3, 60 sec: 11332.3, 300 sec: 11232.8). Total num frames: 13586432. Throughput: 0: 11295.3. Samples: 13561372. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-07 23:14:52,827][286098] Avg episode reward: [(0, '4192.600')] [2023-03-07 23:14:53,611][286389] Updated weights for policy 0, policy_version 26560 (0.0005) [2023-03-07 23:14:57,303][286389] Updated weights for policy 0, policy_version 26640 (0.0005) [2023-03-07 23:14:57,816][286098] Fps is (10 sec: 11059.1, 60 sec: 11264.0, 300 sec: 11232.8). Total num frames: 13643776. Throughput: 0: 11239.1. Samples: 13627292. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-07 23:14:57,827][286098] Avg episode reward: [(0, '4159.195')] [2023-03-07 23:14:57,830][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000026648_13643776.pth... [2023-03-07 23:14:57,833][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000026008_13316096.pth [2023-03-07 23:15:01,037][286389] Updated weights for policy 0, policy_version 26720 (0.0005) [2023-03-07 23:15:02,816][286098] Fps is (10 sec: 11059.1, 60 sec: 11195.7, 300 sec: 11205.0). Total num frames: 13697024. Throughput: 0: 11083.5. Samples: 13692068. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:15:02,827][286098] Avg episode reward: [(0, '4441.433')] [2023-03-07 23:15:04,823][286389] Updated weights for policy 0, policy_version 26800 (0.0005) [2023-03-07 23:15:07,816][286098] Fps is (10 sec: 10649.7, 60 sec: 11127.5, 300 sec: 11177.2). Total num frames: 13750272. Throughput: 0: 10999.4. Samples: 13724424. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:15:07,827][286098] Avg episode reward: [(0, '4537.433')] [2023-03-07 23:15:08,624][286389] Updated weights for policy 0, policy_version 26880 (0.0005) [2023-03-07 23:15:12,413][286389] Updated weights for policy 0, policy_version 26960 (0.0005) [2023-03-07 23:15:12,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11127.5, 300 sec: 11191.1). Total num frames: 13807616. Throughput: 0: 10960.8. Samples: 13788924. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:15:12,827][286098] Avg episode reward: [(0, '4428.025')] [2023-03-07 23:15:12,830][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000026968_13807616.pth... [2023-03-07 23:15:12,832][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000026320_13475840.pth [2023-03-07 23:15:16,095][286389] Updated weights for policy 0, policy_version 27040 (0.0005) [2023-03-07 23:15:17,816][286098] Fps is (10 sec: 11059.2, 60 sec: 10990.9, 300 sec: 11191.1). Total num frames: 13860864. Throughput: 0: 10969.0. Samples: 13855400. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:15:17,827][286098] Avg episode reward: [(0, '4398.002')] [2023-03-07 23:15:19,896][286389] Updated weights for policy 0, policy_version 27120 (0.0005) [2023-03-07 23:15:22,816][286098] Fps is (10 sec: 10649.6, 60 sec: 10922.7, 300 sec: 11191.1). Total num frames: 13914112. Throughput: 0: 10933.5. Samples: 13887372. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-07 23:15:22,827][286098] Avg episode reward: [(0, '4442.697')] [2023-03-07 23:15:23,680][286389] Updated weights for policy 0, policy_version 27200 (0.0005) [2023-03-07 23:15:27,440][286389] Updated weights for policy 0, policy_version 27280 (0.0005) [2023-03-07 23:15:27,816][286098] Fps is (10 sec: 11059.1, 60 sec: 10990.9, 300 sec: 11205.0). Total num frames: 13971456. Throughput: 0: 10940.1. Samples: 13951772. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-07 23:15:27,816][286098] Avg episode reward: [(0, '4476.332')] [2023-03-07 23:15:27,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000027288_13971456.pth... [2023-03-07 23:15:27,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000026648_13643776.pth [2023-03-07 23:15:31,021][286389] Updated weights for policy 0, policy_version 27360 (0.0003) [2023-03-07 23:15:32,816][286098] Fps is (10 sec: 11468.8, 60 sec: 10990.9, 300 sec: 11218.9). Total num frames: 14028800. Throughput: 0: 11000.9. Samples: 14020672. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-07 23:15:32,816][286098] Avg episode reward: [(0, '4405.484')] [2023-03-07 23:15:34,630][286389] Updated weights for policy 0, policy_version 27440 (0.0003) [2023-03-07 23:15:37,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11059.2, 300 sec: 11218.9). Total num frames: 14086144. Throughput: 0: 10953.2. Samples: 14054268. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:15:37,816][286098] Avg episode reward: [(0, '4428.173')] [2023-03-07 23:15:38,108][286389] Updated weights for policy 0, policy_version 27520 (0.0003) [2023-03-07 23:15:41,569][286389] Updated weights for policy 0, policy_version 27600 (0.0003) [2023-03-07 23:15:42,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11127.5, 300 sec: 11232.8). Total num frames: 14143488. Throughput: 0: 11064.4. Samples: 14125188. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:15:42,816][286098] Avg episode reward: [(0, '4187.427')] [2023-03-07 23:15:42,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000027624_14143488.pth... [2023-03-07 23:15:42,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000026968_13807616.pth [2023-03-07 23:15:44,947][286389] Updated weights for policy 0, policy_version 27680 (0.0003) [2023-03-07 23:15:47,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11195.7, 300 sec: 11260.5). Total num frames: 14204928. Throughput: 0: 11216.4. Samples: 14196808. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:15:47,816][286098] Avg episode reward: [(0, '4467.994')] [2023-03-07 23:15:48,501][286389] Updated weights for policy 0, policy_version 27760 (0.0003) [2023-03-07 23:15:52,018][286389] Updated weights for policy 0, policy_version 27840 (0.0004) [2023-03-07 23:15:52,816][286098] Fps is (10 sec: 11878.5, 60 sec: 11264.0, 300 sec: 11274.4). Total num frames: 14262272. Throughput: 0: 11250.4. Samples: 14230692. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:15:52,827][286098] Avg episode reward: [(0, '4413.630')] [2023-03-07 23:15:55,724][286389] Updated weights for policy 0, policy_version 27920 (0.0005) [2023-03-07 23:15:57,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11195.7, 300 sec: 11274.4). Total num frames: 14315520. Throughput: 0: 11338.0. Samples: 14299136. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-07 23:15:57,827][286098] Avg episode reward: [(0, '4479.512')] [2023-03-07 23:15:57,830][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000027960_14315520.pth... [2023-03-07 23:15:57,833][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000027288_13971456.pth [2023-03-07 23:15:59,376][286389] Updated weights for policy 0, policy_version 28000 (0.0005) [2023-03-07 23:16:02,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11264.0, 300 sec: 11274.4). Total num frames: 14372864. Throughput: 0: 11331.6. Samples: 14365320. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-07 23:16:02,827][286098] Avg episode reward: [(0, '4487.645')] [2023-03-07 23:16:03,095][286389] Updated weights for policy 0, policy_version 28080 (0.0005) [2023-03-07 23:16:06,825][286389] Updated weights for policy 0, policy_version 28160 (0.0005) [2023-03-07 23:16:07,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11264.0, 300 sec: 11274.4). Total num frames: 14426112. Throughput: 0: 11350.7. Samples: 14398152. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-07 23:16:07,827][286098] Avg episode reward: [(0, '4523.901')] [2023-03-07 23:16:10,576][286389] Updated weights for policy 0, policy_version 28240 (0.0005) [2023-03-07 23:16:12,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11264.0, 300 sec: 11274.4). Total num frames: 14483456. Throughput: 0: 11396.4. Samples: 14464608. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-07 23:16:12,827][286098] Avg episode reward: [(0, '4476.227')] [2023-03-07 23:16:12,830][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000028288_14483456.pth... [2023-03-07 23:16:12,833][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000027624_14143488.pth [2023-03-07 23:16:14,020][286389] Updated weights for policy 0, policy_version 28320 (0.0003) [2023-03-07 23:16:17,584][286389] Updated weights for policy 0, policy_version 28400 (0.0003) [2023-03-07 23:16:17,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11332.3, 300 sec: 11274.4). Total num frames: 14540800. Throughput: 0: 11432.5. Samples: 14535136. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:16:17,827][286098] Avg episode reward: [(0, '4372.926')] [2023-03-07 23:16:21,079][286389] Updated weights for policy 0, policy_version 28480 (0.0003) [2023-03-07 23:16:22,816][286098] Fps is (10 sec: 11468.9, 60 sec: 11400.5, 300 sec: 11274.4). Total num frames: 14598144. Throughput: 0: 11469.8. Samples: 14570408. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:16:22,827][286098] Avg episode reward: [(0, '4207.326')] [2023-03-07 23:16:24,562][286389] Updated weights for policy 0, policy_version 28560 (0.0003) [2023-03-07 23:16:27,816][286098] Fps is (10 sec: 11878.3, 60 sec: 11468.8, 300 sec: 11288.3). Total num frames: 14659584. Throughput: 0: 11456.1. Samples: 14640712. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:16:27,816][286098] Avg episode reward: [(0, '4354.094')] [2023-03-07 23:16:27,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000028632_14659584.pth... [2023-03-07 23:16:27,821][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000027960_14315520.pth [2023-03-07 23:16:27,900][286389] Updated weights for policy 0, policy_version 28640 (0.0003) [2023-03-07 23:16:31,424][286389] Updated weights for policy 0, policy_version 28720 (0.0003) [2023-03-07 23:16:32,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11468.8, 300 sec: 11302.2). Total num frames: 14716928. Throughput: 0: 11449.3. Samples: 14712024. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-07 23:16:32,827][286098] Avg episode reward: [(0, '4222.324')] [2023-03-07 23:16:34,856][286389] Updated weights for policy 0, policy_version 28800 (0.0004) [2023-03-07 23:16:37,816][286098] Fps is (10 sec: 11878.5, 60 sec: 11537.1, 300 sec: 11316.1). Total num frames: 14778368. Throughput: 0: 11495.3. Samples: 14747980. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-07 23:16:37,827][286098] Avg episode reward: [(0, '4525.448')] [2023-03-07 23:16:38,296][286389] Updated weights for policy 0, policy_version 28880 (0.0003) [2023-03-07 23:16:41,724][286389] Updated weights for policy 0, policy_version 28960 (0.0003) [2023-03-07 23:16:42,816][286098] Fps is (10 sec: 12288.0, 60 sec: 11605.3, 300 sec: 11316.1). Total num frames: 14839808. Throughput: 0: 11560.0. Samples: 14819336. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-07 23:16:42,827][286098] Avg episode reward: [(0, '4401.482')] [2023-03-07 23:16:42,830][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000028984_14839808.pth... [2023-03-07 23:16:42,833][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000028288_14483456.pth [2023-03-07 23:16:45,292][286389] Updated weights for policy 0, policy_version 29040 (0.0003) [2023-03-07 23:16:47,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11537.1, 300 sec: 11316.1). Total num frames: 14897152. Throughput: 0: 11637.9. Samples: 14889024. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-07 23:16:47,827][286098] Avg episode reward: [(0, '4271.742')] [2023-03-07 23:16:48,792][286389] Updated weights for policy 0, policy_version 29120 (0.0003) [2023-03-07 23:16:52,136][286389] Updated weights for policy 0, policy_version 29200 (0.0003) [2023-03-07 23:16:52,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11537.1, 300 sec: 11330.0). Total num frames: 14954496. Throughput: 0: 11714.9. Samples: 14925324. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:16:52,818][286098] Avg episode reward: [(0, '4309.659')] [2023-03-07 23:16:55,651][286389] Updated weights for policy 0, policy_version 29280 (0.0004) [2023-03-07 23:16:57,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11605.3, 300 sec: 11343.8). Total num frames: 15011840. Throughput: 0: 11798.2. Samples: 14995528. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:16:57,827][286098] Avg episode reward: [(0, '4433.764')] [2023-03-07 23:16:57,830][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000029320_15011840.pth... [2023-03-07 23:16:57,833][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000028632_14659584.pth [2023-03-07 23:16:59,392][286389] Updated weights for policy 0, policy_version 29360 (0.0005) [2023-03-07 23:17:02,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11605.3, 300 sec: 11343.8). Total num frames: 15069184. Throughput: 0: 11719.0. Samples: 15062492. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:17:02,816][286098] Avg episode reward: [(0, '4484.394')] [2023-03-07 23:17:03,016][286389] Updated weights for policy 0, policy_version 29440 (0.0004) [2023-03-07 23:17:06,583][286389] Updated weights for policy 0, policy_version 29520 (0.0004) [2023-03-07 23:17:07,816][286098] Fps is (10 sec: 11468.9, 60 sec: 11673.6, 300 sec: 11357.7). Total num frames: 15126528. Throughput: 0: 11721.1. Samples: 15097856. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:17:07,816][286098] Avg episode reward: [(0, '4277.563')] [2023-03-07 23:17:10,348][286389] Updated weights for policy 0, policy_version 29600 (0.0005) [2023-03-07 23:17:12,816][286098] Fps is (10 sec: 11059.1, 60 sec: 11605.3, 300 sec: 11357.7). Total num frames: 15179776. Throughput: 0: 11615.1. Samples: 15163392. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-07 23:17:12,816][286098] Avg episode reward: [(0, '4246.419')] [2023-03-07 23:17:12,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000029648_15179776.pth... [2023-03-07 23:17:12,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000028984_14839808.pth [2023-03-07 23:17:14,174][286389] Updated weights for policy 0, policy_version 29680 (0.0005) [2023-03-07 23:17:17,816][286098] Fps is (10 sec: 10649.6, 60 sec: 11537.1, 300 sec: 11357.7). Total num frames: 15233024. Throughput: 0: 11464.4. Samples: 15227924. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-07 23:17:17,816][286098] Avg episode reward: [(0, '4305.473')] [2023-03-07 23:17:17,932][286389] Updated weights for policy 0, policy_version 29760 (0.0005) [2023-03-07 23:17:21,722][286389] Updated weights for policy 0, policy_version 29840 (0.0005) [2023-03-07 23:17:22,816][286098] Fps is (10 sec: 10649.7, 60 sec: 11468.8, 300 sec: 11343.8). Total num frames: 15286272. Throughput: 0: 11392.8. Samples: 15260656. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-07 23:17:22,816][286098] Avg episode reward: [(0, '4402.138')] [2023-03-07 23:17:25,426][286389] Updated weights for policy 0, policy_version 29920 (0.0005) [2023-03-07 23:17:27,816][286098] Fps is (10 sec: 11059.1, 60 sec: 11400.5, 300 sec: 11343.8). Total num frames: 15343616. Throughput: 0: 11262.5. Samples: 15326148. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-07 23:17:27,816][286098] Avg episode reward: [(0, '4506.554')] [2023-03-07 23:17:27,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000029968_15343616.pth... [2023-03-07 23:17:27,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000029320_15011840.pth [2023-03-07 23:17:29,139][286389] Updated weights for policy 0, policy_version 30000 (0.0005) [2023-03-07 23:17:32,778][286389] Updated weights for policy 0, policy_version 30080 (0.0005) [2023-03-07 23:17:32,816][286098] Fps is (10 sec: 11468.7, 60 sec: 11400.5, 300 sec: 11343.8). Total num frames: 15400960. Throughput: 0: 11195.7. Samples: 15392832. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:17:32,816][286098] Avg episode reward: [(0, '4542.313')] [2023-03-07 23:17:36,443][286389] Updated weights for policy 0, policy_version 30160 (0.0005) [2023-03-07 23:17:37,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11264.0, 300 sec: 11343.8). Total num frames: 15454208. Throughput: 0: 11134.0. Samples: 15426356. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:17:37,816][286098] Avg episode reward: [(0, '4531.625')] [2023-03-07 23:17:40,158][286389] Updated weights for policy 0, policy_version 30240 (0.0005) [2023-03-07 23:17:42,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11195.7, 300 sec: 11343.8). Total num frames: 15511552. Throughput: 0: 11053.3. Samples: 15492928. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:17:42,816][286098] Avg episode reward: [(0, '4505.820')] [2023-03-07 23:17:42,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000030296_15511552.pth... [2023-03-07 23:17:42,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000029648_15179776.pth [2023-03-07 23:17:43,864][286389] Updated weights for policy 0, policy_version 30320 (0.0005) [2023-03-07 23:17:47,283][286389] Updated weights for policy 0, policy_version 30400 (0.0005) [2023-03-07 23:17:47,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11195.7, 300 sec: 11343.8). Total num frames: 15568896. Throughput: 0: 11106.7. Samples: 15562292. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:17:47,816][286098] Avg episode reward: [(0, '4499.312')] [2023-03-07 23:17:50,769][286389] Updated weights for policy 0, policy_version 30480 (0.0005) [2023-03-07 23:17:52,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11195.7, 300 sec: 11343.8). Total num frames: 15626240. Throughput: 0: 11106.1. Samples: 15597632. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-07 23:17:52,816][286098] Avg episode reward: [(0, '4488.622')] [2023-03-07 23:17:54,532][286389] Updated weights for policy 0, policy_version 30560 (0.0005) [2023-03-07 23:17:57,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11127.5, 300 sec: 11343.8). Total num frames: 15679488. Throughput: 0: 11117.3. Samples: 15663672. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-07 23:17:57,816][286098] Avg episode reward: [(0, '4472.325')] [2023-03-07 23:17:57,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000030624_15679488.pth... [2023-03-07 23:17:57,821][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000029968_15343616.pth [2023-03-07 23:17:58,270][286389] Updated weights for policy 0, policy_version 30640 (0.0005) [2023-03-07 23:18:01,806][286389] Updated weights for policy 0, policy_version 30720 (0.0005) [2023-03-07 23:18:02,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11127.5, 300 sec: 11357.7). Total num frames: 15736832. Throughput: 0: 11197.5. Samples: 15731812. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-07 23:18:02,816][286098] Avg episode reward: [(0, '4529.519')] [2023-03-07 23:18:05,293][286389] Updated weights for policy 0, policy_version 30800 (0.0004) [2023-03-07 23:18:07,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11195.7, 300 sec: 11385.5). Total num frames: 15798272. Throughput: 0: 11241.9. Samples: 15766544. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-07 23:18:07,816][286098] Avg episode reward: [(0, '4540.586')] [2023-03-07 23:18:08,768][286389] Updated weights for policy 0, policy_version 30880 (0.0005) [2023-03-07 23:18:12,186][286389] Updated weights for policy 0, policy_version 30960 (0.0005) [2023-03-07 23:18:12,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11264.0, 300 sec: 11385.5). Total num frames: 15855616. Throughput: 0: 11374.6. Samples: 15838004. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-07 23:18:12,816][286098] Avg episode reward: [(0, '4519.356')] [2023-03-07 23:18:12,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000030968_15855616.pth... [2023-03-07 23:18:12,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000030296_15511552.pth [2023-03-07 23:18:15,903][286389] Updated weights for policy 0, policy_version 31040 (0.0005) [2023-03-07 23:18:17,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11332.3, 300 sec: 11399.4). Total num frames: 15912960. Throughput: 0: 11377.8. Samples: 15904832. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-07 23:18:17,816][286098] Avg episode reward: [(0, '4538.246')] [2023-03-07 23:18:19,686][286389] Updated weights for policy 0, policy_version 31120 (0.0005) [2023-03-07 23:18:22,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11332.3, 300 sec: 11371.6). Total num frames: 15966208. Throughput: 0: 11359.7. Samples: 15937544. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-07 23:18:22,816][286098] Avg episode reward: [(0, '4399.300')] [2023-03-07 23:18:23,555][286389] Updated weights for policy 0, policy_version 31200 (0.0005) [2023-03-07 23:18:27,275][286389] Updated weights for policy 0, policy_version 31280 (0.0005) [2023-03-07 23:18:27,816][286098] Fps is (10 sec: 10649.5, 60 sec: 11264.0, 300 sec: 11357.7). Total num frames: 16019456. Throughput: 0: 11320.9. Samples: 16002368. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-07 23:18:27,816][286098] Avg episode reward: [(0, '4315.408')] [2023-03-07 23:18:27,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000031288_16019456.pth... [2023-03-07 23:18:27,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000030624_15679488.pth [2023-03-07 23:18:31,075][286389] Updated weights for policy 0, policy_version 31360 (0.0005) [2023-03-07 23:18:32,816][286098] Fps is (10 sec: 10649.6, 60 sec: 11195.7, 300 sec: 11330.0). Total num frames: 16072704. Throughput: 0: 11228.5. Samples: 16067572. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-07 23:18:32,816][286098] Avg episode reward: [(0, '4456.009')] [2023-03-07 23:18:34,924][286389] Updated weights for policy 0, policy_version 31440 (0.0005) [2023-03-07 23:18:37,816][286098] Fps is (10 sec: 10649.7, 60 sec: 11195.7, 300 sec: 11316.1). Total num frames: 16125952. Throughput: 0: 11138.1. Samples: 16098848. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-07 23:18:37,816][286098] Avg episode reward: [(0, '4494.343')] [2023-03-07 23:18:38,678][286389] Updated weights for policy 0, policy_version 31520 (0.0005) [2023-03-07 23:18:42,208][286389] Updated weights for policy 0, policy_version 31600 (0.0005) [2023-03-07 23:18:42,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11195.7, 300 sec: 11302.2). Total num frames: 16183296. Throughput: 0: 11164.9. Samples: 16166092. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-07 23:18:42,816][286098] Avg episode reward: [(0, '4480.647')] [2023-03-07 23:18:42,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000031608_16183296.pth... [2023-03-07 23:18:42,823][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000030968_15855616.pth [2023-03-07 23:18:45,919][286389] Updated weights for policy 0, policy_version 31680 (0.0005) [2023-03-07 23:18:47,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11195.7, 300 sec: 11302.2). Total num frames: 16240640. Throughput: 0: 11126.7. Samples: 16232512. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-07 23:18:47,816][286098] Avg episode reward: [(0, '4515.009')] [2023-03-07 23:18:49,707][286389] Updated weights for policy 0, policy_version 31760 (0.0005) [2023-03-07 23:18:52,816][286098] Fps is (10 sec: 11059.3, 60 sec: 11127.5, 300 sec: 11274.4). Total num frames: 16293888. Throughput: 0: 11083.0. Samples: 16265280. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:18:52,816][286098] Avg episode reward: [(0, '4478.006')] [2023-03-07 23:18:53,410][286389] Updated weights for policy 0, policy_version 31840 (0.0005) [2023-03-07 23:18:57,278][286389] Updated weights for policy 0, policy_version 31920 (0.0005) [2023-03-07 23:18:57,816][286098] Fps is (10 sec: 10649.5, 60 sec: 11127.5, 300 sec: 11260.5). Total num frames: 16347136. Throughput: 0: 10949.9. Samples: 16330752. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:18:57,816][286098] Avg episode reward: [(0, '4480.937')] [2023-03-07 23:18:57,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000031928_16347136.pth... [2023-03-07 23:18:57,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000031288_16019456.pth [2023-03-07 23:19:00,875][286389] Updated weights for policy 0, policy_version 32000 (0.0005) [2023-03-07 23:19:02,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11127.5, 300 sec: 11260.5). Total num frames: 16404480. Throughput: 0: 10969.3. Samples: 16398448. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:19:02,816][286098] Avg episode reward: [(0, '4514.955')] [2023-03-07 23:19:04,301][286389] Updated weights for policy 0, policy_version 32080 (0.0004) [2023-03-07 23:19:07,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11059.2, 300 sec: 11260.5). Total num frames: 16461824. Throughput: 0: 11030.6. Samples: 16433920. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:19:07,816][286098] Avg episode reward: [(0, '4434.702')] [2023-03-07 23:19:07,943][286389] Updated weights for policy 0, policy_version 32160 (0.0005) [2023-03-07 23:19:11,626][286389] Updated weights for policy 0, policy_version 32240 (0.0005) [2023-03-07 23:19:12,816][286098] Fps is (10 sec: 11468.7, 60 sec: 11059.2, 300 sec: 11246.6). Total num frames: 16519168. Throughput: 0: 11063.3. Samples: 16500216. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-07 23:19:12,816][286098] Avg episode reward: [(0, '4235.572')] [2023-03-07 23:19:12,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000032264_16519168.pth... [2023-03-07 23:19:12,821][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000031608_16183296.pth [2023-03-07 23:19:15,262][286389] Updated weights for policy 0, policy_version 32320 (0.0005) [2023-03-07 23:19:17,816][286098] Fps is (10 sec: 11059.2, 60 sec: 10990.9, 300 sec: 11232.8). Total num frames: 16572416. Throughput: 0: 11115.1. Samples: 16567752. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-07 23:19:17,816][286098] Avg episode reward: [(0, '4401.129')] [2023-03-07 23:19:18,987][286389] Updated weights for policy 0, policy_version 32400 (0.0005) [2023-03-07 23:19:22,675][286389] Updated weights for policy 0, policy_version 32480 (0.0005) [2023-03-07 23:19:22,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11059.2, 300 sec: 11246.6). Total num frames: 16629760. Throughput: 0: 11160.9. Samples: 16601088. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-07 23:19:22,816][286098] Avg episode reward: [(0, '4441.262')] [2023-03-07 23:19:26,432][286389] Updated weights for policy 0, policy_version 32560 (0.0005) [2023-03-07 23:19:27,816][286098] Fps is (10 sec: 11059.1, 60 sec: 11059.2, 300 sec: 11232.8). Total num frames: 16683008. Throughput: 0: 11124.5. Samples: 16666696. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-07 23:19:27,816][286098] Avg episode reward: [(0, '4130.791')] [2023-03-07 23:19:27,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000032584_16683008.pth... [2023-03-07 23:19:27,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000031928_16347136.pth [2023-03-07 23:19:29,929][286389] Updated weights for policy 0, policy_version 32640 (0.0005) [2023-03-07 23:19:32,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11195.7, 300 sec: 11260.5). Total num frames: 16744448. Throughput: 0: 11214.4. Samples: 16737160. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-07 23:19:32,816][286098] Avg episode reward: [(0, '4184.546')] [2023-03-07 23:19:33,354][286389] Updated weights for policy 0, policy_version 32720 (0.0005) [2023-03-07 23:19:36,782][286389] Updated weights for policy 0, policy_version 32800 (0.0005) [2023-03-07 23:19:37,816][286098] Fps is (10 sec: 12288.1, 60 sec: 11332.3, 300 sec: 11288.3). Total num frames: 16805888. Throughput: 0: 11285.5. Samples: 16773128. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-07 23:19:37,816][286098] Avg episode reward: [(0, '4470.772')] [2023-03-07 23:19:40,120][286389] Updated weights for policy 0, policy_version 32880 (0.0004) [2023-03-07 23:19:42,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11332.3, 300 sec: 11288.3). Total num frames: 16863232. Throughput: 0: 11451.1. Samples: 16846052. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-07 23:19:42,817][286098] Avg episode reward: [(0, '4550.938')] [2023-03-07 23:19:42,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000032944_16867328.pth... [2023-03-07 23:19:42,821][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000032264_16519168.pth [2023-03-07 23:19:43,471][286389] Updated weights for policy 0, policy_version 32960 (0.0004) [2023-03-07 23:19:46,830][286389] Updated weights for policy 0, policy_version 33040 (0.0005) [2023-03-07 23:19:47,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11400.5, 300 sec: 11316.1). Total num frames: 16924672. Throughput: 0: 11580.1. Samples: 16919552. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-07 23:19:47,816][286098] Avg episode reward: [(0, '4511.656')] [2023-03-07 23:19:50,217][286389] Updated weights for policy 0, policy_version 33120 (0.0005) [2023-03-07 23:19:52,816][286098] Fps is (10 sec: 12288.0, 60 sec: 11537.1, 300 sec: 11330.0). Total num frames: 16986112. Throughput: 0: 11589.2. Samples: 16955436. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-07 23:19:52,816][286098] Avg episode reward: [(0, '4567.552')] [2023-03-07 23:19:53,707][286389] Updated weights for policy 0, policy_version 33200 (0.0005) [2023-03-07 23:19:57,110][286389] Updated weights for policy 0, policy_version 33280 (0.0004) [2023-03-07 23:19:57,816][286098] Fps is (10 sec: 12288.0, 60 sec: 11673.6, 300 sec: 11357.7). Total num frames: 17047552. Throughput: 0: 11698.0. Samples: 17026628. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:19:57,816][286098] Avg episode reward: [(0, '4491.745')] [2023-03-07 23:19:57,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000033296_17047552.pth... [2023-03-07 23:19:57,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000032584_16683008.pth [2023-03-07 23:20:00,582][286389] Updated weights for policy 0, policy_version 33360 (0.0005) [2023-03-07 23:20:02,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11673.6, 300 sec: 11371.6). Total num frames: 17104896. Throughput: 0: 11776.6. Samples: 17097700. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:20:02,816][286098] Avg episode reward: [(0, '4513.818')] [2023-03-07 23:20:04,069][286389] Updated weights for policy 0, policy_version 33440 (0.0005) [2023-03-07 23:20:07,458][286389] Updated weights for policy 0, policy_version 33520 (0.0004) [2023-03-07 23:20:07,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11741.9, 300 sec: 11385.5). Total num frames: 17166336. Throughput: 0: 11833.1. Samples: 17133576. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:20:07,816][286098] Avg episode reward: [(0, '4520.645')] [2023-03-07 23:20:10,837][286389] Updated weights for policy 0, policy_version 33600 (0.0004) [2023-03-07 23:20:12,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11741.9, 300 sec: 11399.4). Total num frames: 17223680. Throughput: 0: 11984.3. Samples: 17205988. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:20:12,816][286098] Avg episode reward: [(0, '4487.079')] [2023-03-07 23:20:12,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000033640_17223680.pth... [2023-03-07 23:20:12,823][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000032944_16867328.pth [2023-03-07 23:20:14,370][286389] Updated weights for policy 0, policy_version 33680 (0.0005) [2023-03-07 23:20:17,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11810.1, 300 sec: 11413.3). Total num frames: 17281024. Throughput: 0: 11905.4. Samples: 17272904. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:20:17,816][286098] Avg episode reward: [(0, '4501.556')] [2023-03-07 23:20:18,159][286389] Updated weights for policy 0, policy_version 33760 (0.0005) [2023-03-07 23:20:21,874][286389] Updated weights for policy 0, policy_version 33840 (0.0005) [2023-03-07 23:20:22,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11741.9, 300 sec: 11399.4). Total num frames: 17334272. Throughput: 0: 11834.3. Samples: 17305672. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:20:22,816][286098] Avg episode reward: [(0, '4511.138')] [2023-03-07 23:20:25,362][286389] Updated weights for policy 0, policy_version 33920 (0.0004) [2023-03-07 23:20:27,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11810.1, 300 sec: 11399.4). Total num frames: 17391616. Throughput: 0: 11759.7. Samples: 17375240. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:20:27,816][286098] Avg episode reward: [(0, '4492.769')] [2023-03-07 23:20:27,839][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000033976_17395712.pth... [2023-03-07 23:20:27,840][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000033296_17047552.pth [2023-03-07 23:20:28,845][286389] Updated weights for policy 0, policy_version 34000 (0.0005) [2023-03-07 23:20:32,410][286389] Updated weights for policy 0, policy_version 34080 (0.0005) [2023-03-07 23:20:32,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11810.1, 300 sec: 11413.3). Total num frames: 17453056. Throughput: 0: 11675.0. Samples: 17444928. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:20:32,816][286098] Avg episode reward: [(0, '4468.721')] [2023-03-07 23:20:35,824][286389] Updated weights for policy 0, policy_version 34160 (0.0004) [2023-03-07 23:20:37,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11741.9, 300 sec: 11413.3). Total num frames: 17510400. Throughput: 0: 11675.0. Samples: 17480812. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:20:37,816][286098] Avg episode reward: [(0, '4446.212')] [2023-03-07 23:20:39,217][286389] Updated weights for policy 0, policy_version 34240 (0.0004) [2023-03-07 23:20:42,695][286389] Updated weights for policy 0, policy_version 34320 (0.0005) [2023-03-07 23:20:42,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11810.1, 300 sec: 11413.3). Total num frames: 17571840. Throughput: 0: 11681.7. Samples: 17552304. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-07 23:20:42,816][286098] Avg episode reward: [(0, '4444.897')] [2023-03-07 23:20:42,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000034320_17571840.pth... [2023-03-07 23:20:42,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000033640_17223680.pth [2023-03-07 23:20:46,075][286389] Updated weights for policy 0, policy_version 34400 (0.0004) [2023-03-07 23:20:47,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11741.9, 300 sec: 11413.3). Total num frames: 17629184. Throughput: 0: 11699.5. Samples: 17624176. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-07 23:20:47,817][286098] Avg episode reward: [(0, '4496.814')] [2023-03-07 23:20:49,731][286389] Updated weights for policy 0, policy_version 34480 (0.0005) [2023-03-07 23:20:52,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11673.6, 300 sec: 11427.1). Total num frames: 17686528. Throughput: 0: 11650.7. Samples: 17657856. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-07 23:20:52,816][286098] Avg episode reward: [(0, '4506.182')] [2023-03-07 23:20:53,346][286389] Updated weights for policy 0, policy_version 34560 (0.0005) [2023-03-07 23:20:56,767][286389] Updated weights for policy 0, policy_version 34640 (0.0005) [2023-03-07 23:20:57,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11673.6, 300 sec: 11441.0). Total num frames: 17747968. Throughput: 0: 11584.3. Samples: 17727280. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-07 23:20:57,816][286098] Avg episode reward: [(0, '4538.948')] [2023-03-07 23:20:57,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000034664_17747968.pth... [2023-03-07 23:20:57,821][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000033976_17395712.pth [2023-03-07 23:21:00,260][286389] Updated weights for policy 0, policy_version 34720 (0.0005) [2023-03-07 23:21:02,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11673.6, 300 sec: 11454.9). Total num frames: 17805312. Throughput: 0: 11678.0. Samples: 17798412. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-07 23:21:02,816][286098] Avg episode reward: [(0, '4550.095')] [2023-03-07 23:21:03,721][286389] Updated weights for policy 0, policy_version 34800 (0.0005) [2023-03-07 23:21:07,245][286389] Updated weights for policy 0, policy_version 34880 (0.0005) [2023-03-07 23:21:07,816][286098] Fps is (10 sec: 11468.9, 60 sec: 11605.3, 300 sec: 11454.9). Total num frames: 17862656. Throughput: 0: 11730.8. Samples: 17833556. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-07 23:21:07,816][286098] Avg episode reward: [(0, '4520.702')] [2023-03-07 23:21:10,682][286389] Updated weights for policy 0, policy_version 34960 (0.0005) [2023-03-07 23:21:12,816][286098] Fps is (10 sec: 11878.3, 60 sec: 11673.6, 300 sec: 11468.8). Total num frames: 17924096. Throughput: 0: 11744.1. Samples: 17903724. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-07 23:21:12,816][286098] Avg episode reward: [(0, '4546.199')] [2023-03-07 23:21:12,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000035008_17924096.pth... [2023-03-07 23:21:12,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000034320_17571840.pth [2023-03-07 23:21:14,092][286389] Updated weights for policy 0, policy_version 35040 (0.0005) [2023-03-07 23:21:17,532][286389] Updated weights for policy 0, policy_version 35120 (0.0005) [2023-03-07 23:21:17,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11673.6, 300 sec: 11468.8). Total num frames: 17981440. Throughput: 0: 11791.8. Samples: 17975560. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-07 23:21:17,816][286098] Avg episode reward: [(0, '4532.760')] [2023-03-07 23:21:21,000][286389] Updated weights for policy 0, policy_version 35200 (0.0005) [2023-03-07 23:21:22,816][286098] Fps is (10 sec: 11878.5, 60 sec: 11810.1, 300 sec: 11468.8). Total num frames: 18042880. Throughput: 0: 11792.4. Samples: 18011468. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-07 23:21:22,816][286098] Avg episode reward: [(0, '4343.896')] [2023-03-07 23:21:24,472][286389] Updated weights for policy 0, policy_version 35280 (0.0005) [2023-03-07 23:21:27,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11810.2, 300 sec: 11468.8). Total num frames: 18100224. Throughput: 0: 11780.0. Samples: 18082404. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:21:27,816][286098] Avg episode reward: [(0, '4418.786')] [2023-03-07 23:21:27,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000035352_18100224.pth... [2023-03-07 23:21:27,821][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000034664_17747968.pth [2023-03-07 23:21:27,899][286389] Updated weights for policy 0, policy_version 35360 (0.0004) [2023-03-07 23:21:31,443][286389] Updated weights for policy 0, policy_version 35440 (0.0005) [2023-03-07 23:21:32,816][286098] Fps is (10 sec: 11468.7, 60 sec: 11741.9, 300 sec: 11454.9). Total num frames: 18157568. Throughput: 0: 11756.9. Samples: 18153236. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:21:32,816][286098] Avg episode reward: [(0, '4257.909')] [2023-03-07 23:21:34,841][286389] Updated weights for policy 0, policy_version 35520 (0.0004) [2023-03-07 23:21:37,816][286098] Fps is (10 sec: 11878.3, 60 sec: 11810.1, 300 sec: 11454.9). Total num frames: 18219008. Throughput: 0: 11801.8. Samples: 18188936. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:21:37,816][286098] Avg episode reward: [(0, '3651.314')] [2023-03-07 23:21:38,265][286389] Updated weights for policy 0, policy_version 35600 (0.0005) [2023-03-07 23:21:41,691][286389] Updated weights for policy 0, policy_version 35680 (0.0005) [2023-03-07 23:21:42,816][286098] Fps is (10 sec: 12288.0, 60 sec: 11810.1, 300 sec: 11468.8). Total num frames: 18280448. Throughput: 0: 11839.6. Samples: 18260064. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:21:42,816][286098] Avg episode reward: [(0, '4002.613')] [2023-03-07 23:21:42,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000035704_18280448.pth... [2023-03-07 23:21:42,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000035008_17924096.pth [2023-03-07 23:21:45,119][286389] Updated weights for policy 0, policy_version 35760 (0.0005) [2023-03-07 23:21:47,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11810.1, 300 sec: 11468.8). Total num frames: 18337792. Throughput: 0: 11865.9. Samples: 18332376. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-07 23:21:47,816][286098] Avg episode reward: [(0, '4161.796')] [2023-03-07 23:21:48,587][286389] Updated weights for policy 0, policy_version 35840 (0.0005) [2023-03-07 23:21:52,146][286389] Updated weights for policy 0, policy_version 35920 (0.0005) [2023-03-07 23:21:52,816][286098] Fps is (10 sec: 11468.9, 60 sec: 11810.1, 300 sec: 11468.8). Total num frames: 18395136. Throughput: 0: 11851.6. Samples: 18366880. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-07 23:21:52,816][286098] Avg episode reward: [(0, '4341.233')] [2023-03-07 23:21:55,705][286389] Updated weights for policy 0, policy_version 36000 (0.0005) [2023-03-07 23:21:57,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11741.9, 300 sec: 11468.8). Total num frames: 18452480. Throughput: 0: 11831.9. Samples: 18436160. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-07 23:21:57,816][286098] Avg episode reward: [(0, '4541.398')] [2023-03-07 23:21:57,826][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000036048_18456576.pth... [2023-03-07 23:21:57,828][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000035352_18100224.pth [2023-03-07 23:21:59,228][286389] Updated weights for policy 0, policy_version 36080 (0.0005) [2023-03-07 23:22:02,693][286389] Updated weights for policy 0, policy_version 36160 (0.0004) [2023-03-07 23:22:02,816][286098] Fps is (10 sec: 11878.3, 60 sec: 11810.1, 300 sec: 11482.7). Total num frames: 18513920. Throughput: 0: 11793.7. Samples: 18506276. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-07 23:22:02,817][286098] Avg episode reward: [(0, '4536.957')] [2023-03-07 23:22:06,160][286389] Updated weights for policy 0, policy_version 36240 (0.0004) [2023-03-07 23:22:07,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11810.1, 300 sec: 11496.6). Total num frames: 18571264. Throughput: 0: 11778.6. Samples: 18541504. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-07 23:22:07,816][286098] Avg episode reward: [(0, '4504.356')] [2023-03-07 23:22:09,666][286389] Updated weights for policy 0, policy_version 36320 (0.0004) [2023-03-07 23:22:12,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11810.1, 300 sec: 11524.3). Total num frames: 18632704. Throughput: 0: 11773.9. Samples: 18612232. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:22:12,816][286098] Avg episode reward: [(0, '4541.211')] [2023-03-07 23:22:12,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000036392_18632704.pth... [2023-03-07 23:22:12,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000035704_18280448.pth [2023-03-07 23:22:13,160][286389] Updated weights for policy 0, policy_version 36400 (0.0005) [2023-03-07 23:22:16,580][286389] Updated weights for policy 0, policy_version 36480 (0.0004) [2023-03-07 23:22:17,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11810.1, 300 sec: 11538.2). Total num frames: 18690048. Throughput: 0: 11778.3. Samples: 18683260. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:22:17,827][286098] Avg episode reward: [(0, '4534.802')] [2023-03-07 23:22:20,026][286389] Updated weights for policy 0, policy_version 36560 (0.0005) [2023-03-07 23:22:22,816][286098] Fps is (10 sec: 11878.5, 60 sec: 11810.1, 300 sec: 11552.1). Total num frames: 18751488. Throughput: 0: 11774.6. Samples: 18718792. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:22:22,827][286098] Avg episode reward: [(0, '4517.690')] [2023-03-07 23:22:23,458][286389] Updated weights for policy 0, policy_version 36640 (0.0004) [2023-03-07 23:22:26,921][286389] Updated weights for policy 0, policy_version 36720 (0.0005) [2023-03-07 23:22:27,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11810.1, 300 sec: 11552.1). Total num frames: 18808832. Throughput: 0: 11800.5. Samples: 18791088. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:22:27,827][286098] Avg episode reward: [(0, '4548.408')] [2023-03-07 23:22:27,830][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000036736_18808832.pth... [2023-03-07 23:22:27,833][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000036048_18456576.pth [2023-03-07 23:22:30,394][286389] Updated weights for policy 0, policy_version 36800 (0.0005) [2023-03-07 23:22:32,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11878.4, 300 sec: 11579.9). Total num frames: 18870272. Throughput: 0: 11762.8. Samples: 18861700. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:22:32,827][286098] Avg episode reward: [(0, '4554.118')] [2023-03-07 23:22:33,798][286389] Updated weights for policy 0, policy_version 36880 (0.0005) [2023-03-07 23:22:37,192][286389] Updated weights for policy 0, policy_version 36960 (0.0005) [2023-03-07 23:22:37,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11810.1, 300 sec: 11579.9). Total num frames: 18927616. Throughput: 0: 11801.2. Samples: 18897936. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:22:37,827][286098] Avg episode reward: [(0, '4492.348')] [2023-03-07 23:22:40,523][286389] Updated weights for policy 0, policy_version 37040 (0.0005) [2023-03-07 23:22:42,816][286098] Fps is (10 sec: 11878.3, 60 sec: 11810.1, 300 sec: 11593.8). Total num frames: 18989056. Throughput: 0: 11892.8. Samples: 18971336. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:22:42,827][286098] Avg episode reward: [(0, '4511.913')] [2023-03-07 23:22:42,830][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000037088_18989056.pth... [2023-03-07 23:22:42,833][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000036392_18632704.pth [2023-03-07 23:22:43,957][286389] Updated weights for policy 0, policy_version 37120 (0.0005) [2023-03-07 23:22:47,379][286389] Updated weights for policy 0, policy_version 37200 (0.0005) [2023-03-07 23:22:47,816][286098] Fps is (10 sec: 12288.0, 60 sec: 11878.4, 300 sec: 11607.6). Total num frames: 19050496. Throughput: 0: 11913.2. Samples: 19042368. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:22:47,827][286098] Avg episode reward: [(0, '4548.075')] [2023-03-07 23:22:50,787][286389] Updated weights for policy 0, policy_version 37280 (0.0004) [2023-03-07 23:22:52,816][286098] Fps is (10 sec: 12288.1, 60 sec: 11946.7, 300 sec: 11635.4). Total num frames: 19111936. Throughput: 0: 11937.6. Samples: 19078696. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:22:52,827][286098] Avg episode reward: [(0, '4539.119')] [2023-03-07 23:22:54,150][286389] Updated weights for policy 0, policy_version 37360 (0.0004) [2023-03-07 23:22:57,571][286389] Updated weights for policy 0, policy_version 37440 (0.0005) [2023-03-07 23:22:57,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11946.7, 300 sec: 11635.4). Total num frames: 19169280. Throughput: 0: 11970.0. Samples: 19150880. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:22:57,827][286098] Avg episode reward: [(0, '4540.776')] [2023-03-07 23:22:57,830][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000037440_19169280.pth... [2023-03-07 23:22:57,833][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000036736_18808832.pth [2023-03-07 23:23:00,985][286389] Updated weights for policy 0, policy_version 37520 (0.0005) [2023-03-07 23:23:02,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11946.7, 300 sec: 11635.4). Total num frames: 19230720. Throughput: 0: 11985.3. Samples: 19222600. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:23:02,816][286098] Avg episode reward: [(0, '4491.133')] [2023-03-07 23:23:04,440][286389] Updated weights for policy 0, policy_version 37600 (0.0005) [2023-03-07 23:23:07,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11946.7, 300 sec: 11635.4). Total num frames: 19288064. Throughput: 0: 12003.4. Samples: 19258944. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:23:07,816][286098] Avg episode reward: [(0, '4541.666')] [2023-03-07 23:23:07,860][286389] Updated weights for policy 0, policy_version 37680 (0.0005) [2023-03-07 23:23:11,477][286389] Updated weights for policy 0, policy_version 37760 (0.0005) [2023-03-07 23:23:12,816][286098] Fps is (10 sec: 11468.7, 60 sec: 11878.4, 300 sec: 11635.4). Total num frames: 19345408. Throughput: 0: 11948.5. Samples: 19328772. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:23:12,816][286098] Avg episode reward: [(0, '4540.653')] [2023-03-07 23:23:12,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000037784_19345408.pth... [2023-03-07 23:23:12,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000037088_18989056.pth [2023-03-07 23:23:15,098][286389] Updated weights for policy 0, policy_version 37840 (0.0005) [2023-03-07 23:23:17,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11878.4, 300 sec: 11649.3). Total num frames: 19402752. Throughput: 0: 11881.9. Samples: 19396388. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:23:17,816][286098] Avg episode reward: [(0, '4531.826')] [2023-03-07 23:23:18,577][286389] Updated weights for policy 0, policy_version 37920 (0.0005) [2023-03-07 23:23:21,984][286389] Updated weights for policy 0, policy_version 38000 (0.0005) [2023-03-07 23:23:22,816][286098] Fps is (10 sec: 11878.5, 60 sec: 11878.4, 300 sec: 11677.1). Total num frames: 19464192. Throughput: 0: 11875.6. Samples: 19432336. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:23:22,816][286098] Avg episode reward: [(0, '4370.143')] [2023-03-07 23:23:25,452][286389] Updated weights for policy 0, policy_version 38080 (0.0005) [2023-03-07 23:23:27,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11878.4, 300 sec: 11691.0). Total num frames: 19521536. Throughput: 0: 11849.2. Samples: 19504552. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:23:27,816][286098] Avg episode reward: [(0, '4330.137')] [2023-03-07 23:23:27,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000038128_19521536.pth... [2023-03-07 23:23:27,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000037440_19169280.pth [2023-03-07 23:23:28,983][286389] Updated weights for policy 0, policy_version 38160 (0.0005) [2023-03-07 23:23:32,418][286389] Updated weights for policy 0, policy_version 38240 (0.0004) [2023-03-07 23:23:32,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11878.4, 300 sec: 11718.7). Total num frames: 19582976. Throughput: 0: 11832.9. Samples: 19574848. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:23:32,816][286098] Avg episode reward: [(0, '4379.263')] [2023-03-07 23:23:35,989][286389] Updated weights for policy 0, policy_version 38320 (0.0005) [2023-03-07 23:23:37,816][286098] Fps is (10 sec: 11878.5, 60 sec: 11878.4, 300 sec: 11718.7). Total num frames: 19640320. Throughput: 0: 11781.9. Samples: 19608880. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:23:37,816][286098] Avg episode reward: [(0, '4411.525')] [2023-03-07 23:23:39,404][286389] Updated weights for policy 0, policy_version 38400 (0.0005) [2023-03-07 23:23:42,777][286389] Updated weights for policy 0, policy_version 38480 (0.0004) [2023-03-07 23:23:42,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11878.4, 300 sec: 11732.6). Total num frames: 19701760. Throughput: 0: 11788.1. Samples: 19681344. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:23:42,816][286098] Avg episode reward: [(0, '4447.536')] [2023-03-07 23:23:42,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000038480_19701760.pth... [2023-03-07 23:23:42,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000037784_19345408.pth [2023-03-07 23:23:46,092][286389] Updated weights for policy 0, policy_version 38560 (0.0004) [2023-03-07 23:23:47,816][286098] Fps is (10 sec: 12288.1, 60 sec: 11878.4, 300 sec: 11760.4). Total num frames: 19763200. Throughput: 0: 11816.0. Samples: 19754320. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:23:47,816][286098] Avg episode reward: [(0, '4528.032')] [2023-03-07 23:23:49,438][286389] Updated weights for policy 0, policy_version 38640 (0.0004) [2023-03-07 23:23:52,755][286389] Updated weights for policy 0, policy_version 38720 (0.0004) [2023-03-07 23:23:52,816][286098] Fps is (10 sec: 12288.0, 60 sec: 11878.4, 300 sec: 11788.1). Total num frames: 19824640. Throughput: 0: 11839.1. Samples: 19791704. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:23:52,816][286098] Avg episode reward: [(0, '4559.796')] [2023-03-07 23:23:56,080][286389] Updated weights for policy 0, policy_version 38800 (0.0004) [2023-03-07 23:23:57,816][286098] Fps is (10 sec: 12287.9, 60 sec: 11946.7, 300 sec: 11802.0). Total num frames: 19886080. Throughput: 0: 11929.8. Samples: 19865612. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:23:57,816][286098] Avg episode reward: [(0, '4545.257')] [2023-03-07 23:23:57,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000038840_19886080.pth... [2023-03-07 23:23:57,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000038128_19521536.pth [2023-03-07 23:23:59,353][286389] Updated weights for policy 0, policy_version 38880 (0.0004) [2023-03-07 23:24:02,749][286389] Updated weights for policy 0, policy_version 38960 (0.0005) [2023-03-07 23:24:02,816][286098] Fps is (10 sec: 12288.0, 60 sec: 11946.7, 300 sec: 11815.9). Total num frames: 19947520. Throughput: 0: 12065.3. Samples: 19939328. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:24:02,816][286098] Avg episode reward: [(0, '4532.329')] [2023-03-07 23:24:06,098][286389] Updated weights for policy 0, policy_version 39040 (0.0005) [2023-03-07 23:24:07,816][286098] Fps is (10 sec: 11878.3, 60 sec: 11946.7, 300 sec: 11815.9). Total num frames: 20004864. Throughput: 0: 12082.4. Samples: 19976044. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:24:07,817][286098] Avg episode reward: [(0, '4538.990')] [2023-03-07 23:24:09,605][286389] Updated weights for policy 0, policy_version 39120 (0.0005) [2023-03-07 23:24:12,816][286098] Fps is (10 sec: 11878.4, 60 sec: 12014.9, 300 sec: 11843.7). Total num frames: 20066304. Throughput: 0: 12029.7. Samples: 20045888. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:24:12,816][286098] Avg episode reward: [(0, '4519.003')] [2023-03-07 23:24:12,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000039192_20066304.pth... [2023-03-07 23:24:12,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000038480_19701760.pth [2023-03-07 23:24:13,063][286389] Updated weights for policy 0, policy_version 39200 (0.0005) [2023-03-07 23:24:16,566][286389] Updated weights for policy 0, policy_version 39280 (0.0005) [2023-03-07 23:24:17,816][286098] Fps is (10 sec: 11878.5, 60 sec: 12014.9, 300 sec: 11843.7). Total num frames: 20123648. Throughput: 0: 12051.5. Samples: 20117164. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:24:17,816][286098] Avg episode reward: [(0, '4541.125')] [2023-03-07 23:24:20,026][286389] Updated weights for policy 0, policy_version 39360 (0.0005) [2023-03-07 23:24:22,816][286098] Fps is (10 sec: 11878.4, 60 sec: 12014.9, 300 sec: 11871.5). Total num frames: 20185088. Throughput: 0: 12078.0. Samples: 20152392. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:24:22,816][286098] Avg episode reward: [(0, '4526.622')] [2023-03-07 23:24:23,496][286389] Updated weights for policy 0, policy_version 39440 (0.0004) [2023-03-07 23:24:26,956][286389] Updated weights for policy 0, policy_version 39520 (0.0004) [2023-03-07 23:24:27,816][286098] Fps is (10 sec: 11878.4, 60 sec: 12014.9, 300 sec: 11857.6). Total num frames: 20242432. Throughput: 0: 12033.3. Samples: 20222844. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:24:27,816][286098] Avg episode reward: [(0, '4501.110')] [2023-03-07 23:24:27,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000039536_20242432.pth... [2023-03-07 23:24:27,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000038840_19886080.pth [2023-03-07 23:24:30,429][286389] Updated weights for policy 0, policy_version 39600 (0.0005) [2023-03-07 23:24:32,816][286098] Fps is (10 sec: 11878.4, 60 sec: 12014.9, 300 sec: 11857.6). Total num frames: 20303872. Throughput: 0: 12005.9. Samples: 20294588. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:24:32,816][286098] Avg episode reward: [(0, '4545.838')] [2023-03-07 23:24:33,842][286389] Updated weights for policy 0, policy_version 39680 (0.0004) [2023-03-07 23:24:37,435][286389] Updated weights for policy 0, policy_version 39760 (0.0005) [2023-03-07 23:24:37,816][286098] Fps is (10 sec: 11878.5, 60 sec: 12014.9, 300 sec: 11857.6). Total num frames: 20361216. Throughput: 0: 11976.5. Samples: 20330644. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:24:37,816][286098] Avg episode reward: [(0, '4544.778')] [2023-03-07 23:24:41,040][286389] Updated weights for policy 0, policy_version 39840 (0.0005) [2023-03-07 23:24:42,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11946.7, 300 sec: 11843.7). Total num frames: 20418560. Throughput: 0: 11834.2. Samples: 20398152. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:24:42,816][286098] Avg episode reward: [(0, '4520.197')] [2023-03-07 23:24:42,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000039880_20418560.pth... [2023-03-07 23:24:42,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000039192_20066304.pth [2023-03-07 23:24:44,476][286389] Updated weights for policy 0, policy_version 39920 (0.0004) [2023-03-07 23:24:47,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11878.4, 300 sec: 11829.8). Total num frames: 20475904. Throughput: 0: 11801.2. Samples: 20470380. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:24:47,816][286098] Avg episode reward: [(0, '4518.452')] [2023-03-07 23:24:47,910][286389] Updated weights for policy 0, policy_version 40000 (0.0004) [2023-03-07 23:24:51,664][286389] Updated weights for policy 0, policy_version 40080 (0.0005) [2023-03-07 23:24:52,816][286098] Fps is (10 sec: 11468.9, 60 sec: 11810.1, 300 sec: 11815.9). Total num frames: 20533248. Throughput: 0: 11738.8. Samples: 20504288. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:24:52,816][286098] Avg episode reward: [(0, '4542.711')] [2023-03-07 23:24:55,310][286389] Updated weights for policy 0, policy_version 40160 (0.0005) [2023-03-07 23:24:57,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11673.6, 300 sec: 11802.0). Total num frames: 20586496. Throughput: 0: 11651.0. Samples: 20570184. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:24:57,816][286098] Avg episode reward: [(0, '4252.811')] [2023-03-07 23:24:57,878][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000040216_20590592.pth... [2023-03-07 23:24:57,880][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000039536_20242432.pth [2023-03-07 23:24:58,958][286389] Updated weights for policy 0, policy_version 40240 (0.0005) [2023-03-07 23:25:02,631][286389] Updated weights for policy 0, policy_version 40320 (0.0005) [2023-03-07 23:25:02,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11605.3, 300 sec: 11788.2). Total num frames: 20643840. Throughput: 0: 11569.0. Samples: 20637768. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-07 23:25:02,816][286098] Avg episode reward: [(0, '4285.409')] [2023-03-07 23:25:06,318][286389] Updated weights for policy 0, policy_version 40400 (0.0005) [2023-03-07 23:25:07,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11605.3, 300 sec: 11788.2). Total num frames: 20701184. Throughput: 0: 11527.5. Samples: 20671128. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-07 23:25:07,816][286098] Avg episode reward: [(0, '4423.162')] [2023-03-07 23:25:10,023][286389] Updated weights for policy 0, policy_version 40480 (0.0005) [2023-03-07 23:25:12,816][286098] Fps is (10 sec: 11059.1, 60 sec: 11468.8, 300 sec: 11774.3). Total num frames: 20754432. Throughput: 0: 11435.5. Samples: 20737440. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-07 23:25:12,816][286098] Avg episode reward: [(0, '4384.275')] [2023-03-07 23:25:12,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000040536_20754432.pth... [2023-03-07 23:25:12,823][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000039880_20418560.pth [2023-03-07 23:25:13,798][286389] Updated weights for policy 0, policy_version 40560 (0.0005) [2023-03-07 23:25:17,501][286389] Updated weights for policy 0, policy_version 40640 (0.0005) [2023-03-07 23:25:17,816][286098] Fps is (10 sec: 10649.6, 60 sec: 11400.5, 300 sec: 11774.3). Total num frames: 20807680. Throughput: 0: 11304.9. Samples: 20803308. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-07 23:25:17,816][286098] Avg episode reward: [(0, '4497.412')] [2023-03-07 23:25:21,293][286389] Updated weights for policy 0, policy_version 40720 (0.0005) [2023-03-07 23:25:22,816][286098] Fps is (10 sec: 11059.3, 60 sec: 11332.3, 300 sec: 11774.3). Total num frames: 20865024. Throughput: 0: 11225.8. Samples: 20835804. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-07 23:25:22,816][286098] Avg episode reward: [(0, '4551.165')] [2023-03-07 23:25:24,771][286389] Updated weights for policy 0, policy_version 40800 (0.0004) [2023-03-07 23:25:27,816][286098] Fps is (10 sec: 11468.7, 60 sec: 11332.3, 300 sec: 11760.4). Total num frames: 20922368. Throughput: 0: 11246.6. Samples: 20904248. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:25:27,816][286098] Avg episode reward: [(0, '4551.878')] [2023-03-07 23:25:27,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000040864_20922368.pth... [2023-03-07 23:25:27,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000040216_20590592.pth [2023-03-07 23:25:28,394][286389] Updated weights for policy 0, policy_version 40880 (0.0005) [2023-03-07 23:25:31,969][286389] Updated weights for policy 0, policy_version 40960 (0.0004) [2023-03-07 23:25:32,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11264.0, 300 sec: 11760.4). Total num frames: 20979712. Throughput: 0: 11156.3. Samples: 20972412. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:25:32,816][286098] Avg episode reward: [(0, '4555.280')] [2023-03-07 23:25:35,490][286389] Updated weights for policy 0, policy_version 41040 (0.0005) [2023-03-07 23:25:37,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11264.0, 300 sec: 11746.5). Total num frames: 21037056. Throughput: 0: 11186.0. Samples: 21007660. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:25:37,816][286098] Avg episode reward: [(0, '4477.421')] [2023-03-07 23:25:39,016][286389] Updated weights for policy 0, policy_version 41120 (0.0004) [2023-03-07 23:25:42,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11195.7, 300 sec: 11732.6). Total num frames: 21090304. Throughput: 0: 11237.0. Samples: 21075852. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:25:42,816][286098] Avg episode reward: [(0, '4545.783')] [2023-03-07 23:25:42,826][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000041200_21094400.pth... [2023-03-07 23:25:42,827][286389] Updated weights for policy 0, policy_version 41200 (0.0005) [2023-03-07 23:25:42,828][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000040536_20754432.pth [2023-03-07 23:25:46,646][286389] Updated weights for policy 0, policy_version 41280 (0.0005) [2023-03-07 23:25:47,816][286098] Fps is (10 sec: 10649.6, 60 sec: 11127.5, 300 sec: 11718.7). Total num frames: 21143552. Throughput: 0: 11150.2. Samples: 21139528. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:25:47,816][286098] Avg episode reward: [(0, '4546.480')] [2023-03-07 23:25:50,553][286389] Updated weights for policy 0, policy_version 41360 (0.0005) [2023-03-07 23:25:52,816][286098] Fps is (10 sec: 10649.6, 60 sec: 11059.2, 300 sec: 11691.0). Total num frames: 21196800. Throughput: 0: 11121.6. Samples: 21171600. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:25:52,827][286098] Avg episode reward: [(0, '4516.911')] [2023-03-07 23:25:54,353][286389] Updated weights for policy 0, policy_version 41440 (0.0005) [2023-03-07 23:25:57,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11127.5, 300 sec: 11691.0). Total num frames: 21254144. Throughput: 0: 11089.6. Samples: 21236472. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:25:57,827][286098] Avg episode reward: [(0, '4526.406')] [2023-03-07 23:25:57,830][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000041512_21254144.pth... [2023-03-07 23:25:57,833][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000040864_20922368.pth [2023-03-07 23:25:58,024][286389] Updated weights for policy 0, policy_version 41520 (0.0005) [2023-03-07 23:26:01,719][286389] Updated weights for policy 0, policy_version 41600 (0.0005) [2023-03-07 23:26:02,816][286098] Fps is (10 sec: 11468.7, 60 sec: 11127.4, 300 sec: 11691.0). Total num frames: 21311488. Throughput: 0: 11111.0. Samples: 21303304. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:26:02,827][286098] Avg episode reward: [(0, '4535.469')] [2023-03-07 23:26:05,444][286389] Updated weights for policy 0, policy_version 41680 (0.0005) [2023-03-07 23:26:07,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11059.2, 300 sec: 11663.2). Total num frames: 21364736. Throughput: 0: 11118.3. Samples: 21336128. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:26:07,816][286098] Avg episode reward: [(0, '4533.109')] [2023-03-07 23:26:09,215][286389] Updated weights for policy 0, policy_version 41760 (0.0005) [2023-03-07 23:26:12,816][286098] Fps is (10 sec: 10649.6, 60 sec: 11059.2, 300 sec: 11649.3). Total num frames: 21417984. Throughput: 0: 11042.4. Samples: 21401156. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:26:12,816][286098] Avg episode reward: [(0, '4506.608')] [2023-03-07 23:26:12,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000041832_21417984.pth... [2023-03-07 23:26:12,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000041200_21094400.pth [2023-03-07 23:26:13,050][286389] Updated weights for policy 0, policy_version 41840 (0.0005) [2023-03-07 23:26:16,820][286389] Updated weights for policy 0, policy_version 41920 (0.0005) [2023-03-07 23:26:17,816][286098] Fps is (10 sec: 10649.6, 60 sec: 11059.2, 300 sec: 11621.5). Total num frames: 21471232. Throughput: 0: 10969.0. Samples: 21466016. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:26:17,816][286098] Avg episode reward: [(0, '4466.844')] [2023-03-07 23:26:20,563][286389] Updated weights for policy 0, policy_version 42000 (0.0005) [2023-03-07 23:26:22,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11059.2, 300 sec: 11621.5). Total num frames: 21528576. Throughput: 0: 10912.4. Samples: 21498720. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:26:22,817][286098] Avg episode reward: [(0, '4494.606')] [2023-03-07 23:26:24,266][286389] Updated weights for policy 0, policy_version 42080 (0.0005) [2023-03-07 23:26:27,816][286098] Fps is (10 sec: 11059.2, 60 sec: 10990.9, 300 sec: 11607.6). Total num frames: 21581824. Throughput: 0: 10879.7. Samples: 21565440. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:26:27,816][286098] Avg episode reward: [(0, '4291.395')] [2023-03-07 23:26:27,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000042152_21581824.pth... [2023-03-07 23:26:27,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000041512_21254144.pth [2023-03-07 23:26:28,012][286389] Updated weights for policy 0, policy_version 42160 (0.0005) [2023-03-07 23:26:31,763][286389] Updated weights for policy 0, policy_version 42240 (0.0005) [2023-03-07 23:26:32,816][286098] Fps is (10 sec: 10649.6, 60 sec: 10922.7, 300 sec: 11579.9). Total num frames: 21635072. Throughput: 0: 10915.3. Samples: 21630716. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:26:32,817][286098] Avg episode reward: [(0, '4077.543')] [2023-03-07 23:26:35,506][286389] Updated weights for policy 0, policy_version 42320 (0.0005) [2023-03-07 23:26:37,816][286098] Fps is (10 sec: 11059.2, 60 sec: 10922.7, 300 sec: 11566.0). Total num frames: 21692416. Throughput: 0: 10933.5. Samples: 21663608. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:26:37,816][286098] Avg episode reward: [(0, '4472.380')] [2023-03-07 23:26:39,266][286389] Updated weights for policy 0, policy_version 42400 (0.0005) [2023-03-07 23:26:42,816][286098] Fps is (10 sec: 11059.2, 60 sec: 10922.7, 300 sec: 11552.1). Total num frames: 21745664. Throughput: 0: 10943.6. Samples: 21728932. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:26:42,817][286098] Avg episode reward: [(0, '4494.178')] [2023-03-07 23:26:42,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000042472_21745664.pth... [2023-03-07 23:26:42,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000041832_21417984.pth [2023-03-07 23:26:42,964][286389] Updated weights for policy 0, policy_version 42480 (0.0005) [2023-03-07 23:26:46,397][286389] Updated weights for policy 0, policy_version 42560 (0.0004) [2023-03-07 23:26:47,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11059.2, 300 sec: 11566.0). Total num frames: 21807104. Throughput: 0: 11013.5. Samples: 21798912. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-07 23:26:47,816][286098] Avg episode reward: [(0, '3660.425')] [2023-03-07 23:26:49,890][286389] Updated weights for policy 0, policy_version 42640 (0.0004) [2023-03-07 23:26:52,816][286098] Fps is (10 sec: 11878.5, 60 sec: 11127.5, 300 sec: 11566.0). Total num frames: 21864448. Throughput: 0: 11058.8. Samples: 21833776. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-07 23:26:52,816][286098] Avg episode reward: [(0, '4362.700')] [2023-03-07 23:26:53,435][286389] Updated weights for policy 0, policy_version 42720 (0.0004) [2023-03-07 23:26:56,881][286389] Updated weights for policy 0, policy_version 42800 (0.0004) [2023-03-07 23:26:57,816][286098] Fps is (10 sec: 11468.7, 60 sec: 11127.5, 300 sec: 11552.1). Total num frames: 21921792. Throughput: 0: 11167.3. Samples: 21903684. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-07 23:26:57,816][286098] Avg episode reward: [(0, '4540.089')] [2023-03-07 23:26:57,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000042816_21921792.pth... [2023-03-07 23:26:57,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000042152_21581824.pth [2023-03-07 23:27:00,531][286389] Updated weights for policy 0, policy_version 42880 (0.0005) [2023-03-07 23:27:02,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11127.5, 300 sec: 11552.1). Total num frames: 21979136. Throughput: 0: 11226.8. Samples: 21971220. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-07 23:27:02,816][286098] Avg episode reward: [(0, '4549.004')] [2023-03-07 23:27:04,255][286389] Updated weights for policy 0, policy_version 42960 (0.0005) [2023-03-07 23:27:07,816][286098] Fps is (10 sec: 11059.3, 60 sec: 11127.5, 300 sec: 11524.3). Total num frames: 22032384. Throughput: 0: 11226.5. Samples: 22003912. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-07 23:27:07,816][286098] Avg episode reward: [(0, '4511.278')] [2023-03-07 23:27:08,055][286389] Updated weights for policy 0, policy_version 43040 (0.0005) [2023-03-07 23:27:11,863][286389] Updated weights for policy 0, policy_version 43120 (0.0005) [2023-03-07 23:27:12,816][286098] Fps is (10 sec: 10649.5, 60 sec: 11127.5, 300 sec: 11510.5). Total num frames: 22085632. Throughput: 0: 11194.3. Samples: 22069184. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-07 23:27:12,816][286098] Avg episode reward: [(0, '4547.863')] [2023-03-07 23:27:12,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000043136_22085632.pth... [2023-03-07 23:27:12,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000042472_21745664.pth [2023-03-07 23:27:15,627][286389] Updated weights for policy 0, policy_version 43200 (0.0005) [2023-03-07 23:27:17,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11195.7, 300 sec: 11496.6). Total num frames: 22142976. Throughput: 0: 11202.9. Samples: 22134848. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-07 23:27:17,816][286098] Avg episode reward: [(0, '4552.099')] [2023-03-07 23:27:19,176][286389] Updated weights for policy 0, policy_version 43280 (0.0004) [2023-03-07 23:27:22,816][286098] Fps is (10 sec: 11059.3, 60 sec: 11127.5, 300 sec: 11482.7). Total num frames: 22196224. Throughput: 0: 11238.6. Samples: 22169344. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-07 23:27:22,816][286098] Avg episode reward: [(0, '4507.979')] [2023-03-07 23:27:22,821][286389] Updated weights for policy 0, policy_version 43360 (0.0004) [2023-03-07 23:27:26,314][286389] Updated weights for policy 0, policy_version 43440 (0.0003) [2023-03-07 23:27:27,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11264.0, 300 sec: 11482.7). Total num frames: 22257664. Throughput: 0: 11310.3. Samples: 22237896. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-07 23:27:27,816][286098] Avg episode reward: [(0, '4515.324')] [2023-03-07 23:27:27,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000043472_22257664.pth... [2023-03-07 23:27:27,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000042816_21921792.pth [2023-03-07 23:27:29,762][286389] Updated weights for policy 0, policy_version 43520 (0.0003) [2023-03-07 23:27:32,816][286098] Fps is (10 sec: 11878.3, 60 sec: 11332.3, 300 sec: 11482.7). Total num frames: 22315008. Throughput: 0: 11344.8. Samples: 22309428. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-07 23:27:32,816][286098] Avg episode reward: [(0, '4519.016')] [2023-03-07 23:27:33,256][286389] Updated weights for policy 0, policy_version 43600 (0.0003) [2023-03-07 23:27:36,745][286389] Updated weights for policy 0, policy_version 43680 (0.0005) [2023-03-07 23:27:37,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11400.5, 300 sec: 11482.7). Total num frames: 22376448. Throughput: 0: 11340.3. Samples: 22344088. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-07 23:27:37,816][286098] Avg episode reward: [(0, '4526.716')] [2023-03-07 23:27:40,242][286389] Updated weights for policy 0, policy_version 43760 (0.0004) [2023-03-07 23:27:42,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11400.5, 300 sec: 11454.9). Total num frames: 22429696. Throughput: 0: 11345.4. Samples: 22414228. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-07 23:27:42,816][286098] Avg episode reward: [(0, '4560.408')] [2023-03-07 23:27:42,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000043808_22429696.pth... [2023-03-07 23:27:42,821][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000043136_22085632.pth [2023-03-07 23:27:43,930][286389] Updated weights for policy 0, policy_version 43840 (0.0005) [2023-03-07 23:27:47,458][286389] Updated weights for policy 0, policy_version 43920 (0.0003) [2023-03-07 23:27:47,816][286098] Fps is (10 sec: 11059.3, 60 sec: 11332.3, 300 sec: 11441.0). Total num frames: 22487040. Throughput: 0: 11364.2. Samples: 22482608. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-07 23:27:47,816][286098] Avg episode reward: [(0, '4551.700')] [2023-03-07 23:27:51,135][286389] Updated weights for policy 0, policy_version 44000 (0.0004) [2023-03-07 23:27:52,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11332.3, 300 sec: 11441.0). Total num frames: 22544384. Throughput: 0: 11374.9. Samples: 22515784. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-07 23:27:52,816][286098] Avg episode reward: [(0, '4466.764')] [2023-03-07 23:27:54,825][286389] Updated weights for policy 0, policy_version 44080 (0.0005) [2023-03-07 23:27:57,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11264.0, 300 sec: 11413.3). Total num frames: 22597632. Throughput: 0: 11405.8. Samples: 22582444. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-07 23:27:57,816][286098] Avg episode reward: [(0, '4477.513')] [2023-03-07 23:27:57,832][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000044144_22601728.pth... [2023-03-07 23:27:57,834][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000043472_22257664.pth [2023-03-07 23:27:58,578][286389] Updated weights for policy 0, policy_version 44160 (0.0005) [2023-03-07 23:28:02,188][286389] Updated weights for policy 0, policy_version 44240 (0.0005) [2023-03-07 23:28:02,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11264.0, 300 sec: 11413.3). Total num frames: 22654976. Throughput: 0: 11445.8. Samples: 22649908. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-07 23:28:02,816][286098] Avg episode reward: [(0, '4537.284')] [2023-03-07 23:28:05,874][286389] Updated weights for policy 0, policy_version 44320 (0.0005) [2023-03-07 23:28:07,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11332.3, 300 sec: 11413.3). Total num frames: 22712320. Throughput: 0: 11422.2. Samples: 22683344. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-07 23:28:07,816][286098] Avg episode reward: [(0, '4524.842')] [2023-03-07 23:28:09,546][286389] Updated weights for policy 0, policy_version 44400 (0.0005) [2023-03-07 23:28:12,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11332.3, 300 sec: 11399.4). Total num frames: 22765568. Throughput: 0: 11363.4. Samples: 22749248. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:28:12,816][286098] Avg episode reward: [(0, '4509.310')] [2023-03-07 23:28:12,839][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000044472_22769664.pth... [2023-03-07 23:28:12,840][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000043808_22429696.pth [2023-03-07 23:28:13,224][286389] Updated weights for policy 0, policy_version 44480 (0.0005) [2023-03-07 23:28:16,875][286389] Updated weights for policy 0, policy_version 44560 (0.0005) [2023-03-07 23:28:17,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11332.3, 300 sec: 11385.5). Total num frames: 22822912. Throughput: 0: 11276.0. Samples: 22816848. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:28:17,816][286098] Avg episode reward: [(0, '4531.376')] [2023-03-07 23:28:20,515][286389] Updated weights for policy 0, policy_version 44640 (0.0005) [2023-03-07 23:28:22,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11400.5, 300 sec: 11385.5). Total num frames: 22880256. Throughput: 0: 11264.1. Samples: 22850972. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:28:22,816][286098] Avg episode reward: [(0, '4532.045')] [2023-03-07 23:28:24,227][286389] Updated weights for policy 0, policy_version 44720 (0.0005) [2023-03-07 23:28:27,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11264.0, 300 sec: 11357.7). Total num frames: 22933504. Throughput: 0: 11176.8. Samples: 22917184. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:28:27,816][286098] Avg episode reward: [(0, '4546.523')] [2023-03-07 23:28:27,884][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000044800_22937600.pth... [2023-03-07 23:28:27,885][286389] Updated weights for policy 0, policy_version 44800 (0.0005) [2023-03-07 23:28:27,897][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000044144_22601728.pth [2023-03-07 23:28:31,308][286389] Updated weights for policy 0, policy_version 44880 (0.0004) [2023-03-07 23:28:32,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11332.3, 300 sec: 11371.6). Total num frames: 22994944. Throughput: 0: 11204.8. Samples: 22986824. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:28:32,816][286098] Avg episode reward: [(0, '4559.660')] [2023-03-07 23:28:34,938][286389] Updated weights for policy 0, policy_version 44960 (0.0005) [2023-03-07 23:28:37,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11195.7, 300 sec: 11343.8). Total num frames: 23048192. Throughput: 0: 11225.2. Samples: 23020920. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:28:37,816][286098] Avg episode reward: [(0, '4553.899')] [2023-03-07 23:28:38,590][286389] Updated weights for policy 0, policy_version 45040 (0.0005) [2023-03-07 23:28:42,262][286389] Updated weights for policy 0, policy_version 45120 (0.0005) [2023-03-07 23:28:42,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11264.0, 300 sec: 11329.9). Total num frames: 23105536. Throughput: 0: 11240.4. Samples: 23088264. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:28:42,816][286098] Avg episode reward: [(0, '4565.234')] [2023-03-07 23:28:42,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000045128_23105536.pth... [2023-03-07 23:28:42,823][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000044472_22769664.pth [2023-03-07 23:28:45,930][286389] Updated weights for policy 0, policy_version 45200 (0.0005) [2023-03-07 23:28:47,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11195.7, 300 sec: 11302.2). Total num frames: 23158784. Throughput: 0: 11217.6. Samples: 23154700. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:28:47,816][286098] Avg episode reward: [(0, '4569.880')] [2023-03-07 23:28:49,682][286389] Updated weights for policy 0, policy_version 45280 (0.0005) [2023-03-07 23:28:52,816][286098] Fps is (10 sec: 11059.3, 60 sec: 11195.7, 300 sec: 11288.3). Total num frames: 23216128. Throughput: 0: 11203.9. Samples: 23187520. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:28:52,816][286098] Avg episode reward: [(0, '4532.995')] [2023-03-07 23:28:53,403][286389] Updated weights for policy 0, policy_version 45360 (0.0005) [2023-03-07 23:28:57,043][286389] Updated weights for policy 0, policy_version 45440 (0.0005) [2023-03-07 23:28:57,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11264.0, 300 sec: 11274.4). Total num frames: 23273472. Throughput: 0: 11224.1. Samples: 23254332. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:28:57,816][286098] Avg episode reward: [(0, '4408.253')] [2023-03-07 23:28:57,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000045456_23273472.pth... [2023-03-07 23:28:57,821][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000044800_22937600.pth [2023-03-07 23:29:00,765][286389] Updated weights for policy 0, policy_version 45520 (0.0005) [2023-03-07 23:29:02,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11195.7, 300 sec: 11260.5). Total num frames: 23326720. Throughput: 0: 11198.8. Samples: 23320796. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:29:02,816][286098] Avg episode reward: [(0, '4556.277')] [2023-03-07 23:29:04,428][286389] Updated weights for policy 0, policy_version 45600 (0.0005) [2023-03-07 23:29:07,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11195.7, 300 sec: 11246.6). Total num frames: 23384064. Throughput: 0: 11198.6. Samples: 23354908. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-07 23:29:07,816][286098] Avg episode reward: [(0, '4539.960')] [2023-03-07 23:29:08,011][286389] Updated weights for policy 0, policy_version 45680 (0.0005) [2023-03-07 23:29:11,730][286389] Updated weights for policy 0, policy_version 45760 (0.0005) [2023-03-07 23:29:12,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11264.0, 300 sec: 11246.6). Total num frames: 23441408. Throughput: 0: 11205.7. Samples: 23421440. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-07 23:29:12,816][286098] Avg episode reward: [(0, '4481.408')] [2023-03-07 23:29:12,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000045784_23441408.pth... [2023-03-07 23:29:12,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000045128_23105536.pth [2023-03-07 23:29:15,366][286389] Updated weights for policy 0, policy_version 45840 (0.0005) [2023-03-07 23:29:17,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11195.7, 300 sec: 11218.9). Total num frames: 23494656. Throughput: 0: 11173.9. Samples: 23489648. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-07 23:29:17,816][286098] Avg episode reward: [(0, '4481.879')] [2023-03-07 23:29:19,043][286389] Updated weights for policy 0, policy_version 45920 (0.0005) [2023-03-07 23:29:22,680][286389] Updated weights for policy 0, policy_version 46000 (0.0005) [2023-03-07 23:29:22,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11195.7, 300 sec: 11218.9). Total num frames: 23552000. Throughput: 0: 11155.2. Samples: 23522904. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-07 23:29:22,816][286098] Avg episode reward: [(0, '4507.333')] [2023-03-07 23:29:26,133][286389] Updated weights for policy 0, policy_version 46080 (0.0005) [2023-03-07 23:29:27,816][286098] Fps is (10 sec: 11468.7, 60 sec: 11264.0, 300 sec: 11205.0). Total num frames: 23609344. Throughput: 0: 11202.9. Samples: 23592396. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-07 23:29:27,816][286098] Avg episode reward: [(0, '4503.719')] [2023-03-07 23:29:27,833][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000046120_23613440.pth... [2023-03-07 23:29:27,835][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000045456_23273472.pth [2023-03-07 23:29:29,524][286389] Updated weights for policy 0, policy_version 46160 (0.0004) [2023-03-07 23:29:32,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11264.0, 300 sec: 11218.9). Total num frames: 23670784. Throughput: 0: 11301.1. Samples: 23663248. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-07 23:29:32,816][286098] Avg episode reward: [(0, '4532.058')] [2023-03-07 23:29:33,098][286389] Updated weights for policy 0, policy_version 46240 (0.0005) [2023-03-07 23:29:36,417][286389] Updated weights for policy 0, policy_version 46320 (0.0004) [2023-03-07 23:29:37,816][286098] Fps is (10 sec: 12288.0, 60 sec: 11400.5, 300 sec: 11232.8). Total num frames: 23732224. Throughput: 0: 11373.7. Samples: 23699336. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-07 23:29:37,816][286098] Avg episode reward: [(0, '4440.199')] [2023-03-07 23:29:39,755][286389] Updated weights for policy 0, policy_version 46400 (0.0004) [2023-03-07 23:29:42,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11400.5, 300 sec: 11232.8). Total num frames: 23789568. Throughput: 0: 11526.6. Samples: 23773028. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-07 23:29:42,816][286098] Avg episode reward: [(0, '4480.917')] [2023-03-07 23:29:42,855][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000046472_23793664.pth... [2023-03-07 23:29:42,856][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000045784_23441408.pth [2023-03-07 23:29:43,208][286389] Updated weights for policy 0, policy_version 46480 (0.0005) [2023-03-07 23:29:46,654][286389] Updated weights for policy 0, policy_version 46560 (0.0005) [2023-03-07 23:29:47,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11537.1, 300 sec: 11246.6). Total num frames: 23851008. Throughput: 0: 11602.1. Samples: 23842888. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-07 23:29:47,816][286098] Avg episode reward: [(0, '4513.628')] [2023-03-07 23:29:50,334][286389] Updated weights for policy 0, policy_version 46640 (0.0005) [2023-03-07 23:29:52,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11468.8, 300 sec: 11246.6). Total num frames: 23904256. Throughput: 0: 11593.7. Samples: 23876624. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-07 23:29:52,816][286098] Avg episode reward: [(0, '4472.622')] [2023-03-07 23:29:53,985][286389] Updated weights for policy 0, policy_version 46720 (0.0005) [2023-03-07 23:29:57,619][286389] Updated weights for policy 0, policy_version 46800 (0.0005) [2023-03-07 23:29:57,816][286098] Fps is (10 sec: 11059.1, 60 sec: 11468.8, 300 sec: 11246.6). Total num frames: 23961600. Throughput: 0: 11618.0. Samples: 23944248. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-07 23:29:57,816][286098] Avg episode reward: [(0, '4510.691')] [2023-03-07 23:29:57,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000046800_23961600.pth... [2023-03-07 23:29:57,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000046120_23613440.pth [2023-03-07 23:30:01,212][286389] Updated weights for policy 0, policy_version 46880 (0.0005) [2023-03-07 23:30:02,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11537.1, 300 sec: 11246.6). Total num frames: 24018944. Throughput: 0: 11612.2. Samples: 24012196. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-07 23:30:02,816][286098] Avg episode reward: [(0, '4284.420')] [2023-03-07 23:30:04,814][286389] Updated weights for policy 0, policy_version 46960 (0.0004) [2023-03-07 23:30:07,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11537.1, 300 sec: 11260.5). Total num frames: 24076288. Throughput: 0: 11644.4. Samples: 24046900. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:30:07,816][286098] Avg episode reward: [(0, '4468.596')] [2023-03-07 23:30:08,351][286389] Updated weights for policy 0, policy_version 47040 (0.0005) [2023-03-07 23:30:12,012][286389] Updated weights for policy 0, policy_version 47120 (0.0005) [2023-03-07 23:30:12,816][286098] Fps is (10 sec: 11468.7, 60 sec: 11537.1, 300 sec: 11274.4). Total num frames: 24133632. Throughput: 0: 11608.4. Samples: 24114776. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:30:12,816][286098] Avg episode reward: [(0, '4345.410')] [2023-03-07 23:30:12,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000047136_24133632.pth... [2023-03-07 23:30:12,821][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000046472_23793664.pth [2023-03-07 23:30:15,541][286389] Updated weights for policy 0, policy_version 47200 (0.0005) [2023-03-07 23:30:17,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11605.3, 300 sec: 11274.4). Total num frames: 24190976. Throughput: 0: 11586.8. Samples: 24184652. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:30:17,816][286098] Avg episode reward: [(0, '4527.605')] [2023-03-07 23:30:18,949][286389] Updated weights for policy 0, policy_version 47280 (0.0005) [2023-03-07 23:30:22,288][286389] Updated weights for policy 0, policy_version 47360 (0.0004) [2023-03-07 23:30:22,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11673.6, 300 sec: 11288.3). Total num frames: 24252416. Throughput: 0: 11586.0. Samples: 24220704. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:30:22,816][286098] Avg episode reward: [(0, '4454.514')] [2023-03-07 23:30:25,652][286389] Updated weights for policy 0, policy_version 47440 (0.0005) [2023-03-07 23:30:27,816][286098] Fps is (10 sec: 12287.9, 60 sec: 11741.9, 300 sec: 11302.2). Total num frames: 24313856. Throughput: 0: 11572.3. Samples: 24293784. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:30:27,817][286098] Avg episode reward: [(0, '4531.908')] [2023-03-07 23:30:27,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000047488_24313856.pth... [2023-03-07 23:30:27,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000046800_23961600.pth [2023-03-07 23:30:29,104][286389] Updated weights for policy 0, policy_version 47520 (0.0005) [2023-03-07 23:30:32,435][286389] Updated weights for policy 0, policy_version 47600 (0.0004) [2023-03-07 23:30:32,816][286098] Fps is (10 sec: 12288.0, 60 sec: 11741.9, 300 sec: 11316.1). Total num frames: 24375296. Throughput: 0: 11645.4. Samples: 24366932. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:30:32,816][286098] Avg episode reward: [(0, '4486.537')] [2023-03-07 23:30:35,794][286389] Updated weights for policy 0, policy_version 47680 (0.0004) [2023-03-07 23:30:37,816][286098] Fps is (10 sec: 11878.5, 60 sec: 11673.6, 300 sec: 11330.0). Total num frames: 24432640. Throughput: 0: 11714.0. Samples: 24403752. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:30:37,816][286098] Avg episode reward: [(0, '4518.559')] [2023-03-07 23:30:39,211][286389] Updated weights for policy 0, policy_version 47760 (0.0005) [2023-03-07 23:30:42,550][286389] Updated weights for policy 0, policy_version 47840 (0.0004) [2023-03-07 23:30:42,816][286098] Fps is (10 sec: 11878.3, 60 sec: 11741.9, 300 sec: 11357.7). Total num frames: 24494080. Throughput: 0: 11811.2. Samples: 24475752. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:30:42,816][286098] Avg episode reward: [(0, '4519.348')] [2023-03-07 23:30:42,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000047840_24494080.pth... [2023-03-07 23:30:42,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000047136_24133632.pth [2023-03-07 23:30:45,963][286389] Updated weights for policy 0, policy_version 47920 (0.0005) [2023-03-07 23:30:47,816][286098] Fps is (10 sec: 12288.0, 60 sec: 11741.9, 300 sec: 11385.5). Total num frames: 24555520. Throughput: 0: 11913.0. Samples: 24548280. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:30:47,816][286098] Avg episode reward: [(0, '4512.113')] [2023-03-07 23:30:49,241][286389] Updated weights for policy 0, policy_version 48000 (0.0004) [2023-03-07 23:30:52,614][286389] Updated weights for policy 0, policy_version 48080 (0.0005) [2023-03-07 23:30:52,816][286098] Fps is (10 sec: 12288.1, 60 sec: 11878.4, 300 sec: 11399.4). Total num frames: 24616960. Throughput: 0: 11975.9. Samples: 24585816. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:30:52,816][286098] Avg episode reward: [(0, '4426.262')] [2023-03-07 23:30:55,965][286389] Updated weights for policy 0, policy_version 48160 (0.0004) [2023-03-07 23:30:57,816][286098] Fps is (10 sec: 12288.0, 60 sec: 11946.7, 300 sec: 11413.3). Total num frames: 24678400. Throughput: 0: 12091.6. Samples: 24658896. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:30:57,816][286098] Avg episode reward: [(0, '4474.569')] [2023-03-07 23:30:57,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000048200_24678400.pth... [2023-03-07 23:30:57,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000047488_24313856.pth [2023-03-07 23:30:59,373][286389] Updated weights for policy 0, policy_version 48240 (0.0005) [2023-03-07 23:31:02,725][286389] Updated weights for policy 0, policy_version 48320 (0.0004) [2023-03-07 23:31:02,816][286098] Fps is (10 sec: 12288.0, 60 sec: 12014.9, 300 sec: 11441.0). Total num frames: 24739840. Throughput: 0: 12156.9. Samples: 24731712. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:31:02,816][286098] Avg episode reward: [(0, '4477.959')] [2023-03-07 23:31:06,005][286389] Updated weights for policy 0, policy_version 48400 (0.0004) [2023-03-07 23:31:07,816][286098] Fps is (10 sec: 12288.0, 60 sec: 12083.2, 300 sec: 11468.8). Total num frames: 24801280. Throughput: 0: 12188.5. Samples: 24769188. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:31:07,816][286098] Avg episode reward: [(0, '4506.553')] [2023-03-07 23:31:09,374][286389] Updated weights for policy 0, policy_version 48480 (0.0005) [2023-03-07 23:31:12,816][286098] Fps is (10 sec: 12288.0, 60 sec: 12151.5, 300 sec: 11496.6). Total num frames: 24862720. Throughput: 0: 12188.1. Samples: 24842248. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:31:12,816][286389] Updated weights for policy 0, policy_version 48560 (0.0005) [2023-03-07 23:31:12,816][286098] Avg episode reward: [(0, '4488.090')] [2023-03-07 23:31:12,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000048560_24862720.pth... [2023-03-07 23:31:12,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000047840_24494080.pth [2023-03-07 23:31:16,166][286389] Updated weights for policy 0, policy_version 48640 (0.0004) [2023-03-07 23:31:17,816][286098] Fps is (10 sec: 11878.5, 60 sec: 12151.5, 300 sec: 11496.6). Total num frames: 24920064. Throughput: 0: 12178.7. Samples: 24914972. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:31:17,827][286098] Avg episode reward: [(0, '4443.436')] [2023-03-07 23:31:19,527][286389] Updated weights for policy 0, policy_version 48720 (0.0005) [2023-03-07 23:31:22,816][286098] Fps is (10 sec: 11878.4, 60 sec: 12151.5, 300 sec: 11524.3). Total num frames: 24981504. Throughput: 0: 12166.2. Samples: 24951232. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:31:22,827][286098] Avg episode reward: [(0, '4493.442')] [2023-03-07 23:31:22,854][286389] Updated weights for policy 0, policy_version 48800 (0.0004) [2023-03-07 23:31:26,241][286389] Updated weights for policy 0, policy_version 48880 (0.0005) [2023-03-07 23:31:27,816][286098] Fps is (10 sec: 12287.9, 60 sec: 12151.5, 300 sec: 11552.1). Total num frames: 25042944. Throughput: 0: 12184.2. Samples: 25024040. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:31:27,827][286098] Avg episode reward: [(0, '4418.847')] [2023-03-07 23:31:27,831][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000048912_25042944.pth... [2023-03-07 23:31:27,833][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000048200_24678400.pth [2023-03-07 23:31:29,626][286389] Updated weights for policy 0, policy_version 48960 (0.0004) [2023-03-07 23:31:32,816][286098] Fps is (10 sec: 12288.0, 60 sec: 12151.5, 300 sec: 11566.0). Total num frames: 25104384. Throughput: 0: 12209.6. Samples: 25097712. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:31:32,827][286098] Avg episode reward: [(0, '4449.746')] [2023-03-07 23:31:32,928][286389] Updated weights for policy 0, policy_version 49040 (0.0004) [2023-03-07 23:31:36,329][286389] Updated weights for policy 0, policy_version 49120 (0.0005) [2023-03-07 23:31:37,816][286098] Fps is (10 sec: 12288.1, 60 sec: 12219.7, 300 sec: 11593.8). Total num frames: 25165824. Throughput: 0: 12182.1. Samples: 25134012. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-07 23:31:37,827][286098] Avg episode reward: [(0, '4367.083')] [2023-03-07 23:31:39,740][286389] Updated weights for policy 0, policy_version 49200 (0.0005) [2023-03-07 23:31:42,816][286098] Fps is (10 sec: 12288.0, 60 sec: 12219.7, 300 sec: 11593.8). Total num frames: 25227264. Throughput: 0: 12172.4. Samples: 25206656. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-07 23:31:42,827][286098] Avg episode reward: [(0, '4474.622')] [2023-03-07 23:31:42,830][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000049272_25227264.pth... [2023-03-07 23:31:42,833][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000048560_24862720.pth [2023-03-07 23:31:43,073][286389] Updated weights for policy 0, policy_version 49280 (0.0004) [2023-03-07 23:31:46,684][286389] Updated weights for policy 0, policy_version 49360 (0.0004) [2023-03-07 23:31:47,816][286098] Fps is (10 sec: 11878.4, 60 sec: 12151.5, 300 sec: 11593.8). Total num frames: 25284608. Throughput: 0: 12112.8. Samples: 25276788. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-07 23:31:47,827][286098] Avg episode reward: [(0, '4508.917')] [2023-03-07 23:31:50,128][286389] Updated weights for policy 0, policy_version 49440 (0.0003) [2023-03-07 23:31:52,816][286098] Fps is (10 sec: 11468.9, 60 sec: 12083.2, 300 sec: 11593.8). Total num frames: 25341952. Throughput: 0: 12078.0. Samples: 25312696. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-07 23:31:52,827][286098] Avg episode reward: [(0, '4508.657')] [2023-03-07 23:31:53,601][286389] Updated weights for policy 0, policy_version 49520 (0.0003) [2023-03-07 23:31:56,980][286389] Updated weights for policy 0, policy_version 49600 (0.0003) [2023-03-07 23:31:57,816][286098] Fps is (10 sec: 11878.3, 60 sec: 12083.2, 300 sec: 11607.6). Total num frames: 25403392. Throughput: 0: 12019.2. Samples: 25383112. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-07 23:31:57,827][286098] Avg episode reward: [(0, '4473.740')] [2023-03-07 23:31:57,830][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000049616_25403392.pth... [2023-03-07 23:31:57,833][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000048912_25042944.pth [2023-03-07 23:32:00,473][286389] Updated weights for policy 0, policy_version 49680 (0.0003) [2023-03-07 23:32:02,816][286098] Fps is (10 sec: 11878.4, 60 sec: 12014.9, 300 sec: 11621.5). Total num frames: 25460736. Throughput: 0: 12009.0. Samples: 25455376. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-07 23:32:02,816][286098] Avg episode reward: [(0, '4426.175')] [2023-03-07 23:32:03,913][286389] Updated weights for policy 0, policy_version 49760 (0.0003) [2023-03-07 23:32:07,337][286389] Updated weights for policy 0, policy_version 49840 (0.0003) [2023-03-07 23:32:07,816][286098] Fps is (10 sec: 11878.5, 60 sec: 12014.9, 300 sec: 11649.3). Total num frames: 25522176. Throughput: 0: 12001.0. Samples: 25491276. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-07 23:32:07,816][286098] Avg episode reward: [(0, '4509.288')] [2023-03-07 23:32:10,759][286389] Updated weights for policy 0, policy_version 49920 (0.0003) [2023-03-07 23:32:12,816][286098] Fps is (10 sec: 11878.5, 60 sec: 11946.7, 300 sec: 11649.3). Total num frames: 25579520. Throughput: 0: 11979.0. Samples: 25563092. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-07 23:32:12,816][286098] Avg episode reward: [(0, '4344.750')] [2023-03-07 23:32:12,840][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000049968_25583616.pth... [2023-03-07 23:32:12,842][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000049272_25227264.pth [2023-03-07 23:32:14,203][286389] Updated weights for policy 0, policy_version 50000 (0.0003) [2023-03-07 23:32:17,744][286389] Updated weights for policy 0, policy_version 50080 (0.0004) [2023-03-07 23:32:17,816][286098] Fps is (10 sec: 11878.4, 60 sec: 12014.9, 300 sec: 11677.1). Total num frames: 25640960. Throughput: 0: 11891.6. Samples: 25632832. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-07 23:32:17,816][286098] Avg episode reward: [(0, '4366.729')] [2023-03-07 23:32:21,168][286389] Updated weights for policy 0, policy_version 50160 (0.0005) [2023-03-07 23:32:22,816][286098] Fps is (10 sec: 12287.9, 60 sec: 12014.9, 300 sec: 11677.1). Total num frames: 25702400. Throughput: 0: 11875.6. Samples: 25668412. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-07 23:32:22,816][286098] Avg episode reward: [(0, '4486.683')] [2023-03-07 23:32:24,463][286389] Updated weights for policy 0, policy_version 50240 (0.0004) [2023-03-07 23:32:27,792][286389] Updated weights for policy 0, policy_version 50320 (0.0004) [2023-03-07 23:32:27,816][286098] Fps is (10 sec: 12288.0, 60 sec: 12014.9, 300 sec: 11691.0). Total num frames: 25763840. Throughput: 0: 11926.1. Samples: 25743332. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-07 23:32:27,816][286098] Avg episode reward: [(0, '4574.741')] [2023-03-07 23:32:27,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000050320_25763840.pth... [2023-03-07 23:32:27,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000049616_25403392.pth [2023-03-07 23:32:27,822][286341] Saving new best policy, reward=4574.741! [2023-03-07 23:32:31,168][286389] Updated weights for policy 0, policy_version 50400 (0.0005) [2023-03-07 23:32:32,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11946.7, 300 sec: 11677.1). Total num frames: 25821184. Throughput: 0: 11978.7. Samples: 25815828. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-07 23:32:32,816][286098] Avg episode reward: [(0, '4565.072')] [2023-03-07 23:32:34,475][286389] Updated weights for policy 0, policy_version 50480 (0.0004) [2023-03-07 23:32:37,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11946.7, 300 sec: 11704.8). Total num frames: 25882624. Throughput: 0: 12012.4. Samples: 25853256. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-07 23:32:37,816][286098] Avg episode reward: [(0, '4545.091')] [2023-03-07 23:32:37,823][286389] Updated weights for policy 0, policy_version 50560 (0.0004) [2023-03-07 23:32:41,172][286389] Updated weights for policy 0, policy_version 50640 (0.0004) [2023-03-07 23:32:42,816][286098] Fps is (10 sec: 12288.0, 60 sec: 11946.7, 300 sec: 11718.7). Total num frames: 25944064. Throughput: 0: 12080.2. Samples: 25926720. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-07 23:32:42,816][286098] Avg episode reward: [(0, '4568.957')] [2023-03-07 23:32:42,846][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000050680_25948160.pth... [2023-03-07 23:32:42,848][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000049968_25583616.pth [2023-03-07 23:32:44,556][286389] Updated weights for policy 0, policy_version 50720 (0.0005) [2023-03-07 23:32:47,816][286098] Fps is (10 sec: 12288.0, 60 sec: 12014.9, 300 sec: 11732.6). Total num frames: 26005504. Throughput: 0: 12084.3. Samples: 25999168. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-07 23:32:47,816][286098] Avg episode reward: [(0, '4563.109')] [2023-03-07 23:32:47,902][286389] Updated weights for policy 0, policy_version 50800 (0.0004) [2023-03-07 23:32:51,255][286389] Updated weights for policy 0, policy_version 50880 (0.0004) [2023-03-07 23:32:52,816][286098] Fps is (10 sec: 12288.0, 60 sec: 12083.2, 300 sec: 11760.4). Total num frames: 26066944. Throughput: 0: 12099.2. Samples: 26035740. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-07 23:32:52,816][286098] Avg episode reward: [(0, '4533.630')] [2023-03-07 23:32:54,814][286389] Updated weights for policy 0, policy_version 50960 (0.0005) [2023-03-07 23:32:57,816][286098] Fps is (10 sec: 11878.3, 60 sec: 12014.9, 300 sec: 11760.4). Total num frames: 26124288. Throughput: 0: 12079.0. Samples: 26106648. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-07 23:32:57,816][286098] Avg episode reward: [(0, '4563.428')] [2023-03-07 23:32:57,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000051024_26124288.pth... [2023-03-07 23:32:57,821][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000050320_25763840.pth [2023-03-07 23:32:58,218][286389] Updated weights for policy 0, policy_version 51040 (0.0003) [2023-03-07 23:33:01,644][286389] Updated weights for policy 0, policy_version 51120 (0.0003) [2023-03-07 23:33:02,816][286098] Fps is (10 sec: 11878.4, 60 sec: 12083.2, 300 sec: 11774.3). Total num frames: 26185728. Throughput: 0: 12124.1. Samples: 26178416. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-07 23:33:02,816][286098] Avg episode reward: [(0, '4561.606')] [2023-03-07 23:33:05,028][286389] Updated weights for policy 0, policy_version 51200 (0.0003) [2023-03-07 23:33:07,816][286098] Fps is (10 sec: 12288.1, 60 sec: 12083.2, 300 sec: 11802.0). Total num frames: 26247168. Throughput: 0: 12134.7. Samples: 26214472. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-07 23:33:07,816][286098] Avg episode reward: [(0, '4550.881')] [2023-03-07 23:33:08,499][286389] Updated weights for policy 0, policy_version 51280 (0.0003) [2023-03-07 23:33:11,914][286389] Updated weights for policy 0, policy_version 51360 (0.0003) [2023-03-07 23:33:12,816][286098] Fps is (10 sec: 11878.3, 60 sec: 12083.2, 300 sec: 11802.0). Total num frames: 26304512. Throughput: 0: 12059.8. Samples: 26286024. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:33:12,816][286098] Avg episode reward: [(0, '4580.803')] [2023-03-07 23:33:12,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000051376_26304512.pth... [2023-03-07 23:33:12,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000050680_25948160.pth [2023-03-07 23:33:12,822][286341] Saving new best policy, reward=4580.803! [2023-03-07 23:33:15,508][286389] Updated weights for policy 0, policy_version 51440 (0.0005) [2023-03-07 23:33:17,816][286098] Fps is (10 sec: 11468.8, 60 sec: 12014.9, 300 sec: 11802.0). Total num frames: 26361856. Throughput: 0: 11978.5. Samples: 26354860. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:33:17,816][286098] Avg episode reward: [(0, '4526.774')] [2023-03-07 23:33:19,170][286389] Updated weights for policy 0, policy_version 51520 (0.0005) [2023-03-07 23:33:22,816][286098] Fps is (10 sec: 11059.3, 60 sec: 11878.4, 300 sec: 11802.0). Total num frames: 26415104. Throughput: 0: 11877.1. Samples: 26387724. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:33:22,816][286098] Avg episode reward: [(0, '4041.249')] [2023-03-07 23:33:22,861][286389] Updated weights for policy 0, policy_version 51600 (0.0005) [2023-03-07 23:33:26,461][286389] Updated weights for policy 0, policy_version 51680 (0.0004) [2023-03-07 23:33:27,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11810.1, 300 sec: 11788.1). Total num frames: 26472448. Throughput: 0: 11760.9. Samples: 26455960. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:33:27,816][286098] Avg episode reward: [(0, '4335.971')] [2023-03-07 23:33:27,822][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000051712_26476544.pth... [2023-03-07 23:33:27,824][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000051024_26124288.pth [2023-03-07 23:33:29,914][286389] Updated weights for policy 0, policy_version 51760 (0.0003) [2023-03-07 23:33:32,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11878.4, 300 sec: 11815.9). Total num frames: 26533888. Throughput: 0: 11702.2. Samples: 26525768. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:33:32,827][286098] Avg episode reward: [(0, '4354.760')] [2023-03-07 23:33:33,458][286389] Updated weights for policy 0, policy_version 51840 (0.0005) [2023-03-07 23:33:36,861][286389] Updated weights for policy 0, policy_version 51920 (0.0005) [2023-03-07 23:33:37,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11810.1, 300 sec: 11815.9). Total num frames: 26591232. Throughput: 0: 11679.5. Samples: 26561316. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:33:37,827][286098] Avg episode reward: [(0, '4428.622')] [2023-03-07 23:33:40,274][286389] Updated weights for policy 0, policy_version 52000 (0.0005) [2023-03-07 23:33:42,816][286098] Fps is (10 sec: 11878.3, 60 sec: 11810.1, 300 sec: 11843.7). Total num frames: 26652672. Throughput: 0: 11716.2. Samples: 26633876. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:33:42,827][286098] Avg episode reward: [(0, '4501.825')] [2023-03-07 23:33:42,830][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000052056_26652672.pth... [2023-03-07 23:33:42,833][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000051376_26304512.pth [2023-03-07 23:33:43,791][286389] Updated weights for policy 0, policy_version 52080 (0.0005) [2023-03-07 23:33:47,487][286389] Updated weights for policy 0, policy_version 52160 (0.0005) [2023-03-07 23:33:47,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11673.6, 300 sec: 11829.8). Total num frames: 26705920. Throughput: 0: 11630.5. Samples: 26701788. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:33:47,827][286098] Avg episode reward: [(0, '4293.766')] [2023-03-07 23:33:51,171][286389] Updated weights for policy 0, policy_version 52240 (0.0005) [2023-03-07 23:33:52,816][286098] Fps is (10 sec: 11059.3, 60 sec: 11605.3, 300 sec: 11829.8). Total num frames: 26763264. Throughput: 0: 11559.6. Samples: 26734656. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:33:52,827][286098] Avg episode reward: [(0, '4379.657')] [2023-03-07 23:33:54,851][286389] Updated weights for policy 0, policy_version 52320 (0.0005) [2023-03-07 23:33:57,816][286098] Fps is (10 sec: 11059.1, 60 sec: 11537.1, 300 sec: 11829.8). Total num frames: 26816512. Throughput: 0: 11442.1. Samples: 26800920. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:33:57,827][286098] Avg episode reward: [(0, '4514.954')] [2023-03-07 23:33:57,842][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000052384_26820608.pth... [2023-03-07 23:33:57,844][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000051712_26476544.pth [2023-03-07 23:33:58,592][286389] Updated weights for policy 0, policy_version 52400 (0.0005) [2023-03-07 23:34:02,318][286389] Updated weights for policy 0, policy_version 52480 (0.0005) [2023-03-07 23:34:02,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11468.8, 300 sec: 11829.8). Total num frames: 26873856. Throughput: 0: 11374.6. Samples: 26866716. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:34:02,816][286098] Avg episode reward: [(0, '4495.467')] [2023-03-07 23:34:06,007][286389] Updated weights for policy 0, policy_version 52560 (0.0004) [2023-03-07 23:34:07,816][286098] Fps is (10 sec: 11059.3, 60 sec: 11332.3, 300 sec: 11815.9). Total num frames: 26927104. Throughput: 0: 11382.3. Samples: 26899928. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:34:07,816][286098] Avg episode reward: [(0, '4569.911')] [2023-03-07 23:34:09,816][286389] Updated weights for policy 0, policy_version 52640 (0.0005) [2023-03-07 23:34:12,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11332.3, 300 sec: 11829.8). Total num frames: 26984448. Throughput: 0: 11326.7. Samples: 26965660. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:34:12,816][286098] Avg episode reward: [(0, '4562.201')] [2023-03-07 23:34:12,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000052704_26984448.pth... [2023-03-07 23:34:12,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000052056_26652672.pth [2023-03-07 23:34:13,460][286389] Updated weights for policy 0, policy_version 52720 (0.0005) [2023-03-07 23:34:17,201][286389] Updated weights for policy 0, policy_version 52800 (0.0005) [2023-03-07 23:34:17,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11264.0, 300 sec: 11815.9). Total num frames: 27037696. Throughput: 0: 11262.0. Samples: 27032560. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-07 23:34:17,816][286098] Avg episode reward: [(0, '4566.047')] [2023-03-07 23:34:20,864][286389] Updated weights for policy 0, policy_version 52880 (0.0005) [2023-03-07 23:34:22,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11332.3, 300 sec: 11815.9). Total num frames: 27095040. Throughput: 0: 11219.0. Samples: 27066172. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-07 23:34:22,816][286098] Avg episode reward: [(0, '4557.320')] [2023-03-07 23:34:24,313][286389] Updated weights for policy 0, policy_version 52960 (0.0005) [2023-03-07 23:34:27,661][286389] Updated weights for policy 0, policy_version 53040 (0.0005) [2023-03-07 23:34:27,816][286098] Fps is (10 sec: 11878.3, 60 sec: 11400.5, 300 sec: 11815.9). Total num frames: 27156480. Throughput: 0: 11183.0. Samples: 27137112. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-07 23:34:27,816][286098] Avg episode reward: [(0, '4449.347')] [2023-03-07 23:34:27,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000053040_27156480.pth... [2023-03-07 23:34:27,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000052384_26820608.pth [2023-03-07 23:34:31,130][286389] Updated weights for policy 0, policy_version 53120 (0.0005) [2023-03-07 23:34:32,816][286098] Fps is (10 sec: 11878.5, 60 sec: 11332.3, 300 sec: 11802.0). Total num frames: 27213824. Throughput: 0: 11259.4. Samples: 27208460. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-07 23:34:32,816][286098] Avg episode reward: [(0, '4549.829')] [2023-03-07 23:34:34,604][286389] Updated weights for policy 0, policy_version 53200 (0.0005) [2023-03-07 23:34:37,816][286098] Fps is (10 sec: 11878.5, 60 sec: 11400.5, 300 sec: 11815.9). Total num frames: 27275264. Throughput: 0: 11309.4. Samples: 27243580. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-07 23:34:37,816][286098] Avg episode reward: [(0, '4503.770')] [2023-03-07 23:34:38,015][286389] Updated weights for policy 0, policy_version 53280 (0.0004) [2023-03-07 23:34:41,421][286389] Updated weights for policy 0, policy_version 53360 (0.0004) [2023-03-07 23:34:42,816][286098] Fps is (10 sec: 12287.9, 60 sec: 11400.5, 300 sec: 11815.9). Total num frames: 27336704. Throughput: 0: 11450.5. Samples: 27316192. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-07 23:34:42,827][286098] Avg episode reward: [(0, '4528.573')] [2023-03-07 23:34:42,830][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000053392_27336704.pth... [2023-03-07 23:34:42,833][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000052704_26984448.pth [2023-03-07 23:34:44,928][286389] Updated weights for policy 0, policy_version 53440 (0.0005) [2023-03-07 23:34:47,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11400.5, 300 sec: 11815.9). Total num frames: 27389952. Throughput: 0: 11520.4. Samples: 27385132. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-07 23:34:47,827][286098] Avg episode reward: [(0, '4502.581')] [2023-03-07 23:34:48,643][286389] Updated weights for policy 0, policy_version 53520 (0.0005) [2023-03-07 23:34:52,230][286389] Updated weights for policy 0, policy_version 53600 (0.0004) [2023-03-07 23:34:52,816][286098] Fps is (10 sec: 11059.3, 60 sec: 11400.5, 300 sec: 11815.9). Total num frames: 27447296. Throughput: 0: 11528.0. Samples: 27418688. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:34:52,827][286098] Avg episode reward: [(0, '4355.443')] [2023-03-07 23:34:55,947][286389] Updated weights for policy 0, policy_version 53680 (0.0005) [2023-03-07 23:34:57,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11468.8, 300 sec: 11815.9). Total num frames: 27504640. Throughput: 0: 11549.7. Samples: 27485396. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:34:57,827][286098] Avg episode reward: [(0, '4168.229')] [2023-03-07 23:34:57,830][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000053720_27504640.pth... [2023-03-07 23:34:57,832][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000053040_27156480.pth [2023-03-07 23:34:59,611][286389] Updated weights for policy 0, policy_version 53760 (0.0005) [2023-03-07 23:35:02,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11400.5, 300 sec: 11802.0). Total num frames: 27557888. Throughput: 0: 11550.6. Samples: 27552336. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:35:02,827][286098] Avg episode reward: [(0, '4516.473')] [2023-03-07 23:35:03,296][286389] Updated weights for policy 0, policy_version 53840 (0.0005) [2023-03-07 23:35:07,022][286389] Updated weights for policy 0, policy_version 53920 (0.0005) [2023-03-07 23:35:07,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11468.8, 300 sec: 11802.0). Total num frames: 27615232. Throughput: 0: 11538.0. Samples: 27585380. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:35:07,827][286098] Avg episode reward: [(0, '4573.045')] [2023-03-07 23:35:10,711][286389] Updated weights for policy 0, policy_version 54000 (0.0005) [2023-03-07 23:35:12,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11400.5, 300 sec: 11788.1). Total num frames: 27668480. Throughput: 0: 11444.5. Samples: 27652112. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:35:12,827][286098] Avg episode reward: [(0, '4534.622')] [2023-03-07 23:35:12,830][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000054040_27668480.pth... [2023-03-07 23:35:12,833][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000053392_27336704.pth [2023-03-07 23:35:14,492][286389] Updated weights for policy 0, policy_version 54080 (0.0005) [2023-03-07 23:35:17,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11468.8, 300 sec: 11774.3). Total num frames: 27725824. Throughput: 0: 11316.4. Samples: 27717696. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:35:17,827][286098] Avg episode reward: [(0, '4531.316')] [2023-03-07 23:35:18,167][286389] Updated weights for policy 0, policy_version 54160 (0.0005) [2023-03-07 23:35:21,865][286389] Updated weights for policy 0, policy_version 54240 (0.0005) [2023-03-07 23:35:22,816][286098] Fps is (10 sec: 11059.3, 60 sec: 11400.5, 300 sec: 11746.5). Total num frames: 27779072. Throughput: 0: 11269.9. Samples: 27750724. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-07 23:35:22,827][286098] Avg episode reward: [(0, '4475.180')] [2023-03-07 23:35:25,640][286389] Updated weights for policy 0, policy_version 54320 (0.0005) [2023-03-07 23:35:27,816][286098] Fps is (10 sec: 10649.6, 60 sec: 11264.0, 300 sec: 11718.7). Total num frames: 27832320. Throughput: 0: 11107.0. Samples: 27816008. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-07 23:35:27,816][286098] Avg episode reward: [(0, '4521.899')] [2023-03-07 23:35:27,847][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000054368_27836416.pth... [2023-03-07 23:35:27,848][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000053720_27504640.pth [2023-03-07 23:35:29,312][286389] Updated weights for policy 0, policy_version 54400 (0.0005) [2023-03-07 23:35:32,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11264.0, 300 sec: 11718.7). Total num frames: 27889664. Throughput: 0: 11106.2. Samples: 27884912. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-07 23:35:32,816][286098] Avg episode reward: [(0, '4363.773')] [2023-03-07 23:35:32,935][286389] Updated weights for policy 0, policy_version 54480 (0.0005) [2023-03-07 23:35:36,565][286389] Updated weights for policy 0, policy_version 54560 (0.0005) [2023-03-07 23:35:37,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11195.7, 300 sec: 11704.8). Total num frames: 27947008. Throughput: 0: 11103.6. Samples: 27918348. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-07 23:35:37,816][286098] Avg episode reward: [(0, '4412.448')] [2023-03-07 23:35:40,276][286389] Updated weights for policy 0, policy_version 54640 (0.0005) [2023-03-07 23:35:42,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11059.2, 300 sec: 11677.1). Total num frames: 28000256. Throughput: 0: 11091.3. Samples: 27984504. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-07 23:35:42,816][286098] Avg episode reward: [(0, '4493.432')] [2023-03-07 23:35:42,854][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000054696_28004352.pth... [2023-03-07 23:35:42,856][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000054040_27668480.pth [2023-03-07 23:35:43,912][286389] Updated weights for policy 0, policy_version 54720 (0.0005) [2023-03-07 23:35:47,587][286389] Updated weights for policy 0, policy_version 54800 (0.0005) [2023-03-07 23:35:47,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11127.5, 300 sec: 11663.2). Total num frames: 28057600. Throughput: 0: 11103.9. Samples: 28052012. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-07 23:35:47,816][286098] Avg episode reward: [(0, '4539.160')] [2023-03-07 23:35:51,200][286389] Updated weights for policy 0, policy_version 54880 (0.0005) [2023-03-07 23:35:52,816][286098] Fps is (10 sec: 11468.7, 60 sec: 11127.5, 300 sec: 11649.3). Total num frames: 28114944. Throughput: 0: 11119.4. Samples: 28085752. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-07 23:35:52,827][286098] Avg episode reward: [(0, '4559.337')] [2023-03-07 23:35:54,729][286389] Updated weights for policy 0, policy_version 54960 (0.0005) [2023-03-07 23:35:57,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11127.5, 300 sec: 11635.4). Total num frames: 28172288. Throughput: 0: 11170.2. Samples: 28154772. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:35:57,827][286098] Avg episode reward: [(0, '4557.003')] [2023-03-07 23:35:57,830][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000055024_28172288.pth... [2023-03-07 23:35:57,833][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000054368_27836416.pth [2023-03-07 23:35:58,203][286389] Updated weights for policy 0, policy_version 55040 (0.0005) [2023-03-07 23:36:01,516][286389] Updated weights for policy 0, policy_version 55120 (0.0004) [2023-03-07 23:36:02,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11264.0, 300 sec: 11635.4). Total num frames: 28233728. Throughput: 0: 11342.8. Samples: 28228124. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:36:02,827][286098] Avg episode reward: [(0, '4561.698')] [2023-03-07 23:36:04,832][286389] Updated weights for policy 0, policy_version 55200 (0.0004) [2023-03-07 23:36:07,816][286098] Fps is (10 sec: 12697.7, 60 sec: 11400.5, 300 sec: 11649.3). Total num frames: 28299264. Throughput: 0: 11433.2. Samples: 28265216. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:36:07,827][286098] Avg episode reward: [(0, '4587.421')] [2023-03-07 23:36:07,827][286341] Saving new best policy, reward=4587.421! [2023-03-07 23:36:08,145][286389] Updated weights for policy 0, policy_version 55280 (0.0004) [2023-03-07 23:36:11,755][286389] Updated weights for policy 0, policy_version 55360 (0.0005) [2023-03-07 23:36:12,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11400.5, 300 sec: 11635.4). Total num frames: 28352512. Throughput: 0: 11562.7. Samples: 28336332. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:36:12,827][286098] Avg episode reward: [(0, '4548.338')] [2023-03-07 23:36:12,851][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000055384_28356608.pth... [2023-03-07 23:36:12,852][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000054696_28004352.pth [2023-03-07 23:36:15,456][286389] Updated weights for policy 0, policy_version 55440 (0.0005) [2023-03-07 23:36:17,816][286098] Fps is (10 sec: 11059.1, 60 sec: 11400.5, 300 sec: 11621.5). Total num frames: 28409856. Throughput: 0: 11503.0. Samples: 28402548. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:36:17,827][286098] Avg episode reward: [(0, '4524.417')] [2023-03-07 23:36:19,123][286389] Updated weights for policy 0, policy_version 55520 (0.0005) [2023-03-07 23:36:22,715][286389] Updated weights for policy 0, policy_version 55600 (0.0004) [2023-03-07 23:36:22,816][286098] Fps is (10 sec: 11468.7, 60 sec: 11468.8, 300 sec: 11607.6). Total num frames: 28467200. Throughput: 0: 11538.0. Samples: 28437560. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:36:22,827][286098] Avg episode reward: [(0, '4480.339')] [2023-03-07 23:36:26,461][286389] Updated weights for policy 0, policy_version 55680 (0.0005) [2023-03-07 23:36:27,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11468.8, 300 sec: 11579.9). Total num frames: 28520448. Throughput: 0: 11545.7. Samples: 28504064. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:36:27,827][286098] Avg episode reward: [(0, '4580.921')] [2023-03-07 23:36:27,830][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000055704_28520448.pth... [2023-03-07 23:36:27,833][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000055024_28172288.pth [2023-03-07 23:36:30,112][286389] Updated weights for policy 0, policy_version 55760 (0.0005) [2023-03-07 23:36:32,816][286098] Fps is (10 sec: 11059.3, 60 sec: 11468.8, 300 sec: 11566.0). Total num frames: 28577792. Throughput: 0: 11551.8. Samples: 28571844. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:36:32,827][286098] Avg episode reward: [(0, '4537.386')] [2023-03-07 23:36:33,743][286389] Updated weights for policy 0, policy_version 55840 (0.0005) [2023-03-07 23:36:37,149][286389] Updated weights for policy 0, policy_version 55920 (0.0005) [2023-03-07 23:36:37,816][286098] Fps is (10 sec: 11878.5, 60 sec: 11537.1, 300 sec: 11566.0). Total num frames: 28639232. Throughput: 0: 11555.4. Samples: 28605744. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:36:37,816][286098] Avg episode reward: [(0, '4500.963')] [2023-03-07 23:36:40,719][286389] Updated weights for policy 0, policy_version 56000 (0.0005) [2023-03-07 23:36:42,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11537.0, 300 sec: 11552.1). Total num frames: 28692480. Throughput: 0: 11585.1. Samples: 28676104. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:36:42,816][286098] Avg episode reward: [(0, '4568.980')] [2023-03-07 23:36:42,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000056040_28692480.pth... [2023-03-07 23:36:42,823][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000055384_28356608.pth [2023-03-07 23:36:44,417][286389] Updated weights for policy 0, policy_version 56080 (0.0005) [2023-03-07 23:36:47,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11537.1, 300 sec: 11552.1). Total num frames: 28749824. Throughput: 0: 11442.7. Samples: 28743044. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:36:47,816][286098] Avg episode reward: [(0, '4573.178')] [2023-03-07 23:36:47,959][286389] Updated weights for policy 0, policy_version 56160 (0.0004) [2023-03-07 23:36:51,467][286389] Updated weights for policy 0, policy_version 56240 (0.0003) [2023-03-07 23:36:52,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11537.1, 300 sec: 11538.2). Total num frames: 28807168. Throughput: 0: 11407.6. Samples: 28778560. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:36:52,816][286098] Avg episode reward: [(0, '4541.151')] [2023-03-07 23:36:55,112][286389] Updated weights for policy 0, policy_version 56320 (0.0005) [2023-03-07 23:36:57,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11537.1, 300 sec: 11538.2). Total num frames: 28864512. Throughput: 0: 11345.2. Samples: 28846864. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:36:57,816][286098] Avg episode reward: [(0, '4574.172')] [2023-03-07 23:36:57,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000056376_28864512.pth... [2023-03-07 23:36:57,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000055704_28520448.pth [2023-03-07 23:36:58,675][286389] Updated weights for policy 0, policy_version 56400 (0.0005) [2023-03-07 23:37:02,137][286389] Updated weights for policy 0, policy_version 56480 (0.0004) [2023-03-07 23:37:02,816][286098] Fps is (10 sec: 11878.6, 60 sec: 11537.1, 300 sec: 11538.2). Total num frames: 28925952. Throughput: 0: 11435.9. Samples: 28917164. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:37:02,816][286098] Avg episode reward: [(0, '4530.626')] [2023-03-07 23:37:05,789][286389] Updated weights for policy 0, policy_version 56560 (0.0005) [2023-03-07 23:37:07,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11332.3, 300 sec: 11524.3). Total num frames: 28979200. Throughput: 0: 11400.9. Samples: 28950600. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-07 23:37:07,816][286098] Avg episode reward: [(0, '4476.583')] [2023-03-07 23:37:09,486][286389] Updated weights for policy 0, policy_version 56640 (0.0005) [2023-03-07 23:37:12,816][286098] Fps is (10 sec: 11059.0, 60 sec: 11400.5, 300 sec: 11510.5). Total num frames: 29036544. Throughput: 0: 11393.3. Samples: 29016764. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-07 23:37:12,816][286098] Avg episode reward: [(0, '4566.309')] [2023-03-07 23:37:12,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000056712_29036544.pth... [2023-03-07 23:37:12,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000056040_28692480.pth [2023-03-07 23:37:13,183][286389] Updated weights for policy 0, policy_version 56720 (0.0005) [2023-03-07 23:37:16,804][286389] Updated weights for policy 0, policy_version 56800 (0.0005) [2023-03-07 23:37:17,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11332.3, 300 sec: 11482.7). Total num frames: 29089792. Throughput: 0: 11399.6. Samples: 29084824. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-07 23:37:17,816][286098] Avg episode reward: [(0, '4562.126')] [2023-03-07 23:37:20,313][286389] Updated weights for policy 0, policy_version 56880 (0.0004) [2023-03-07 23:37:22,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11400.5, 300 sec: 11482.7). Total num frames: 29151232. Throughput: 0: 11416.6. Samples: 29119492. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-07 23:37:22,816][286098] Avg episode reward: [(0, '4571.520')] [2023-03-07 23:37:23,712][286389] Updated weights for policy 0, policy_version 56960 (0.0003) [2023-03-07 23:37:27,063][286389] Updated weights for policy 0, policy_version 57040 (0.0003) [2023-03-07 23:37:27,816][286098] Fps is (10 sec: 12287.9, 60 sec: 11537.1, 300 sec: 11496.6). Total num frames: 29212672. Throughput: 0: 11468.9. Samples: 29192204. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-07 23:37:27,816][286098] Avg episode reward: [(0, '4582.444')] [2023-03-07 23:37:27,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000057056_29212672.pth... [2023-03-07 23:37:27,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000056376_28864512.pth [2023-03-07 23:37:30,446][286389] Updated weights for policy 0, policy_version 57120 (0.0003) [2023-03-07 23:37:32,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11537.1, 300 sec: 11482.7). Total num frames: 29270016. Throughput: 0: 11607.0. Samples: 29265360. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-07 23:37:32,816][286098] Avg episode reward: [(0, '4574.329')] [2023-03-07 23:37:33,988][286389] Updated weights for policy 0, policy_version 57200 (0.0005) [2023-03-07 23:37:37,659][286389] Updated weights for policy 0, policy_version 57280 (0.0005) [2023-03-07 23:37:37,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11468.8, 300 sec: 11468.8). Total num frames: 29327360. Throughput: 0: 11559.8. Samples: 29298752. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-07 23:37:37,816][286098] Avg episode reward: [(0, '4570.566')] [2023-03-07 23:37:41,264][286389] Updated weights for policy 0, policy_version 57360 (0.0005) [2023-03-07 23:37:42,816][286098] Fps is (10 sec: 11468.7, 60 sec: 11537.1, 300 sec: 11454.9). Total num frames: 29384704. Throughput: 0: 11546.5. Samples: 29366456. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-07 23:37:42,816][286098] Avg episode reward: [(0, '4556.223')] [2023-03-07 23:37:42,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000057392_29384704.pth... [2023-03-07 23:37:42,823][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000056712_29036544.pth [2023-03-07 23:37:44,923][286389] Updated weights for policy 0, policy_version 57440 (0.0005) [2023-03-07 23:37:47,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11468.8, 300 sec: 11427.1). Total num frames: 29437952. Throughput: 0: 11482.4. Samples: 29433872. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-07 23:37:47,816][286098] Avg episode reward: [(0, '4554.792')] [2023-03-07 23:37:48,572][286389] Updated weights for policy 0, policy_version 57520 (0.0005) [2023-03-07 23:37:52,265][286389] Updated weights for policy 0, policy_version 57600 (0.0005) [2023-03-07 23:37:52,816][286098] Fps is (10 sec: 11059.3, 60 sec: 11468.8, 300 sec: 11427.1). Total num frames: 29495296. Throughput: 0: 11468.6. Samples: 29466688. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-07 23:37:52,816][286098] Avg episode reward: [(0, '4503.053')] [2023-03-07 23:37:55,934][286389] Updated weights for policy 0, policy_version 57680 (0.0005) [2023-03-07 23:37:57,816][286098] Fps is (10 sec: 11468.7, 60 sec: 11468.8, 300 sec: 11413.3). Total num frames: 29552640. Throughput: 0: 11486.9. Samples: 29533676. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-07 23:37:57,816][286098] Avg episode reward: [(0, '4567.991')] [2023-03-07 23:37:57,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000057720_29552640.pth... [2023-03-07 23:37:57,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000057056_29212672.pth [2023-03-07 23:37:59,555][286389] Updated weights for policy 0, policy_version 57760 (0.0004) [2023-03-07 23:38:02,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11332.2, 300 sec: 11385.5). Total num frames: 29605888. Throughput: 0: 11488.2. Samples: 29601792. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-07 23:38:02,816][286098] Avg episode reward: [(0, '4507.925')] [2023-03-07 23:38:03,176][286389] Updated weights for policy 0, policy_version 57840 (0.0005) [2023-03-07 23:38:06,780][286389] Updated weights for policy 0, policy_version 57920 (0.0005) [2023-03-07 23:38:07,816][286098] Fps is (10 sec: 11059.4, 60 sec: 11400.6, 300 sec: 11385.5). Total num frames: 29663232. Throughput: 0: 11452.3. Samples: 29634844. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-07 23:38:07,816][286098] Avg episode reward: [(0, '4490.659')] [2023-03-07 23:38:10,403][286389] Updated weights for policy 0, policy_version 58000 (0.0005) [2023-03-07 23:38:12,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11400.5, 300 sec: 11385.5). Total num frames: 29720576. Throughput: 0: 11367.1. Samples: 29703724. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-07 23:38:12,816][286098] Avg episode reward: [(0, '4525.694')] [2023-03-07 23:38:12,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000058048_29720576.pth... [2023-03-07 23:38:12,823][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000057392_29384704.pth [2023-03-07 23:38:14,038][286389] Updated weights for policy 0, policy_version 58080 (0.0005) [2023-03-07 23:38:17,495][286389] Updated weights for policy 0, policy_version 58160 (0.0004) [2023-03-07 23:38:17,816][286098] Fps is (10 sec: 11468.7, 60 sec: 11468.8, 300 sec: 11399.4). Total num frames: 29777920. Throughput: 0: 11283.7. Samples: 29773128. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:38:17,817][286098] Avg episode reward: [(0, '4506.803')] [2023-03-07 23:38:21,035][286389] Updated weights for policy 0, policy_version 58240 (0.0004) [2023-03-07 23:38:22,816][286098] Fps is (10 sec: 11468.7, 60 sec: 11400.5, 300 sec: 11399.4). Total num frames: 29835264. Throughput: 0: 11320.1. Samples: 29808156. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:38:22,817][286098] Avg episode reward: [(0, '4562.294')] [2023-03-07 23:38:24,718][286389] Updated weights for policy 0, policy_version 58320 (0.0005) [2023-03-07 23:38:27,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11332.3, 300 sec: 11385.5). Total num frames: 29892608. Throughput: 0: 11315.6. Samples: 29875656. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:38:27,816][286098] Avg episode reward: [(0, '4567.661')] [2023-03-07 23:38:27,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000058384_29892608.pth... [2023-03-07 23:38:27,823][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000057720_29552640.pth [2023-03-07 23:38:28,332][286389] Updated weights for policy 0, policy_version 58400 (0.0005) [2023-03-07 23:38:32,024][286389] Updated weights for policy 0, policy_version 58480 (0.0005) [2023-03-07 23:38:32,816][286098] Fps is (10 sec: 11468.9, 60 sec: 11332.3, 300 sec: 11385.5). Total num frames: 29949952. Throughput: 0: 11288.3. Samples: 29941844. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:38:32,816][286098] Avg episode reward: [(0, '4542.279')] [2023-03-07 23:38:35,645][286389] Updated weights for policy 0, policy_version 58560 (0.0005) [2023-03-07 23:38:37,816][286098] Fps is (10 sec: 11059.3, 60 sec: 11264.0, 300 sec: 11357.7). Total num frames: 30003200. Throughput: 0: 11322.1. Samples: 29976184. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:38:37,816][286098] Avg episode reward: [(0, '4567.166')] [2023-03-07 23:38:39,376][286389] Updated weights for policy 0, policy_version 58640 (0.0005) [2023-03-07 23:38:42,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11264.0, 300 sec: 11371.6). Total num frames: 30060544. Throughput: 0: 11304.1. Samples: 30042360. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:38:42,816][286098] Avg episode reward: [(0, '4573.267')] [2023-03-07 23:38:42,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000058712_30060544.pth... [2023-03-07 23:38:42,823][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000058048_29720576.pth [2023-03-07 23:38:43,146][286389] Updated weights for policy 0, policy_version 58720 (0.0005) [2023-03-07 23:38:46,788][286389] Updated weights for policy 0, policy_version 58800 (0.0005) [2023-03-07 23:38:47,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11264.0, 300 sec: 11357.7). Total num frames: 30113792. Throughput: 0: 11272.4. Samples: 30109048. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:38:47,816][286098] Avg episode reward: [(0, '4547.307')] [2023-03-07 23:38:50,479][286389] Updated weights for policy 0, policy_version 58880 (0.0005) [2023-03-07 23:38:52,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11264.0, 300 sec: 11371.6). Total num frames: 30171136. Throughput: 0: 11280.4. Samples: 30142464. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:38:52,816][286098] Avg episode reward: [(0, '4469.859')] [2023-03-07 23:38:54,194][286389] Updated weights for policy 0, policy_version 58960 (0.0005) [2023-03-07 23:38:57,710][286389] Updated weights for policy 0, policy_version 59040 (0.0005) [2023-03-07 23:38:57,816][286098] Fps is (10 sec: 11468.7, 60 sec: 11264.0, 300 sec: 11371.6). Total num frames: 30228480. Throughput: 0: 11232.2. Samples: 30209172. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-07 23:38:57,816][286098] Avg episode reward: [(0, '4533.361')] [2023-03-07 23:38:57,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000059040_30228480.pth... [2023-03-07 23:38:57,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000058384_29892608.pth [2023-03-07 23:39:01,357][286389] Updated weights for policy 0, policy_version 59120 (0.0005) [2023-03-07 23:39:02,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11332.3, 300 sec: 11385.5). Total num frames: 30285824. Throughput: 0: 11212.6. Samples: 30277696. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-07 23:39:02,816][286098] Avg episode reward: [(0, '4547.677')] [2023-03-07 23:39:05,028][286389] Updated weights for policy 0, policy_version 59200 (0.0005) [2023-03-07 23:39:07,816][286098] Fps is (10 sec: 11059.3, 60 sec: 11264.0, 300 sec: 11371.6). Total num frames: 30339072. Throughput: 0: 11162.6. Samples: 30310472. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-07 23:39:07,816][286098] Avg episode reward: [(0, '4498.462')] [2023-03-07 23:39:08,691][286389] Updated weights for policy 0, policy_version 59280 (0.0005) [2023-03-07 23:39:12,353][286389] Updated weights for policy 0, policy_version 59360 (0.0005) [2023-03-07 23:39:12,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11264.0, 300 sec: 11385.5). Total num frames: 30396416. Throughput: 0: 11147.1. Samples: 30377276. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-07 23:39:12,816][286098] Avg episode reward: [(0, '4529.512')] [2023-03-07 23:39:12,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000059368_30396416.pth... [2023-03-07 23:39:12,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000058712_30060544.pth [2023-03-07 23:39:16,003][286389] Updated weights for policy 0, policy_version 59440 (0.0005) [2023-03-07 23:39:17,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11264.0, 300 sec: 11385.5). Total num frames: 30453760. Throughput: 0: 11193.9. Samples: 30445568. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-07 23:39:17,816][286098] Avg episode reward: [(0, '4549.941')] [2023-03-07 23:39:19,623][286389] Updated weights for policy 0, policy_version 59520 (0.0004) [2023-03-07 23:39:22,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11195.8, 300 sec: 11357.7). Total num frames: 30507008. Throughput: 0: 11171.2. Samples: 30478888. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-07 23:39:22,826][286098] Avg episode reward: [(0, '4521.888')] [2023-03-07 23:39:23,268][286389] Updated weights for policy 0, policy_version 59600 (0.0004) [2023-03-07 23:39:26,763][286389] Updated weights for policy 0, policy_version 59680 (0.0004) [2023-03-07 23:39:27,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11264.0, 300 sec: 11371.6). Total num frames: 30568448. Throughput: 0: 11235.7. Samples: 30547968. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-07 23:39:27,816][286098] Avg episode reward: [(0, '4555.242')] [2023-03-07 23:39:27,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000059704_30568448.pth... [2023-03-07 23:39:27,821][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000059040_30228480.pth [2023-03-07 23:39:30,005][286389] Updated weights for policy 0, policy_version 59760 (0.0003) [2023-03-07 23:39:32,816][286098] Fps is (10 sec: 12288.1, 60 sec: 11332.3, 300 sec: 11371.6). Total num frames: 30629888. Throughput: 0: 11405.1. Samples: 30622276. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:39:32,816][286098] Avg episode reward: [(0, '4557.967')] [2023-03-07 23:39:33,395][286389] Updated weights for policy 0, policy_version 59840 (0.0003) [2023-03-07 23:39:36,773][286389] Updated weights for policy 0, policy_version 59920 (0.0003) [2023-03-07 23:39:37,816][286098] Fps is (10 sec: 11878.5, 60 sec: 11400.5, 300 sec: 11357.7). Total num frames: 30687232. Throughput: 0: 11455.9. Samples: 30657980. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:39:37,816][286098] Avg episode reward: [(0, '4563.676')] [2023-03-07 23:39:40,175][286389] Updated weights for policy 0, policy_version 60000 (0.0003) [2023-03-07 23:39:42,816][286098] Fps is (10 sec: 11878.3, 60 sec: 11468.8, 300 sec: 11385.5). Total num frames: 30748672. Throughput: 0: 11597.2. Samples: 30731048. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:39:42,816][286098] Avg episode reward: [(0, '4557.347')] [2023-03-07 23:39:42,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000060056_30748672.pth... [2023-03-07 23:39:42,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000059368_30396416.pth [2023-03-07 23:39:43,653][286389] Updated weights for policy 0, policy_version 60080 (0.0004) [2023-03-07 23:39:47,055][286389] Updated weights for policy 0, policy_version 60160 (0.0003) [2023-03-07 23:39:47,816][286098] Fps is (10 sec: 12287.8, 60 sec: 11605.3, 300 sec: 11399.4). Total num frames: 30810112. Throughput: 0: 11649.6. Samples: 30801928. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:39:47,816][286098] Avg episode reward: [(0, '4462.538')] [2023-03-07 23:39:50,361][286389] Updated weights for policy 0, policy_version 60240 (0.0003) [2023-03-07 23:39:52,816][286098] Fps is (10 sec: 12288.0, 60 sec: 11673.6, 300 sec: 11413.3). Total num frames: 30871552. Throughput: 0: 11749.3. Samples: 30839192. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:39:52,816][286098] Avg episode reward: [(0, '4379.394')] [2023-03-07 23:39:53,791][286389] Updated weights for policy 0, policy_version 60320 (0.0004) [2023-03-07 23:39:57,315][286389] Updated weights for policy 0, policy_version 60400 (0.0004) [2023-03-07 23:39:57,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11673.6, 300 sec: 11427.1). Total num frames: 30928896. Throughput: 0: 11880.1. Samples: 30911880. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:39:57,816][286098] Avg episode reward: [(0, '4452.162')] [2023-03-07 23:39:57,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000060408_30928896.pth... [2023-03-07 23:39:57,823][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000059704_30568448.pth [2023-03-07 23:40:01,014][286389] Updated weights for policy 0, policy_version 60480 (0.0005) [2023-03-07 23:40:02,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11605.3, 300 sec: 11413.3). Total num frames: 30982144. Throughput: 0: 11829.9. Samples: 30977916. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:40:02,816][286098] Avg episode reward: [(0, '4484.923')] [2023-03-07 23:40:04,704][286389] Updated weights for policy 0, policy_version 60560 (0.0005) [2023-03-07 23:40:07,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11673.6, 300 sec: 11427.1). Total num frames: 31039488. Throughput: 0: 11821.2. Samples: 31010840. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:40:07,816][286098] Avg episode reward: [(0, '4562.261')] [2023-03-07 23:40:08,399][286389] Updated weights for policy 0, policy_version 60640 (0.0005) [2023-03-07 23:40:11,947][286389] Updated weights for policy 0, policy_version 60720 (0.0005) [2023-03-07 23:40:12,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11673.6, 300 sec: 11427.1). Total num frames: 31096832. Throughput: 0: 11802.5. Samples: 31079080. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:40:12,816][286098] Avg episode reward: [(0, '4561.567')] [2023-03-07 23:40:12,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000060736_31096832.pth... [2023-03-07 23:40:12,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000060056_30748672.pth [2023-03-07 23:40:15,553][286389] Updated weights for policy 0, policy_version 60800 (0.0005) [2023-03-07 23:40:17,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11673.6, 300 sec: 11441.0). Total num frames: 31154176. Throughput: 0: 11655.3. Samples: 31146764. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:40:17,816][286098] Avg episode reward: [(0, '4533.541')] [2023-03-07 23:40:19,186][286389] Updated weights for policy 0, policy_version 60880 (0.0005) [2023-03-07 23:40:22,816][286098] Fps is (10 sec: 11059.4, 60 sec: 11673.6, 300 sec: 11441.0). Total num frames: 31207424. Throughput: 0: 11625.2. Samples: 31181112. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:40:22,827][286098] Avg episode reward: [(0, '4518.851')] [2023-03-07 23:40:22,861][286389] Updated weights for policy 0, policy_version 60960 (0.0005) [2023-03-07 23:40:26,476][286389] Updated weights for policy 0, policy_version 61040 (0.0005) [2023-03-07 23:40:27,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11605.3, 300 sec: 11441.0). Total num frames: 31264768. Throughput: 0: 11496.4. Samples: 31248384. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:40:27,827][286098] Avg episode reward: [(0, '4551.139')] [2023-03-07 23:40:27,830][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000061064_31264768.pth... [2023-03-07 23:40:27,831][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000060408_30928896.pth [2023-03-07 23:40:29,896][286389] Updated weights for policy 0, policy_version 61120 (0.0005) [2023-03-07 23:40:32,816][286098] Fps is (10 sec: 11878.3, 60 sec: 11605.3, 300 sec: 11454.9). Total num frames: 31326208. Throughput: 0: 11470.2. Samples: 31318088. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:40:32,827][286098] Avg episode reward: [(0, '4514.703')] [2023-03-07 23:40:33,468][286389] Updated weights for policy 0, policy_version 61200 (0.0005) [2023-03-07 23:40:36,952][286389] Updated weights for policy 0, policy_version 61280 (0.0005) [2023-03-07 23:40:37,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11605.3, 300 sec: 11468.8). Total num frames: 31383552. Throughput: 0: 11392.7. Samples: 31351864. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:40:37,827][286098] Avg episode reward: [(0, '4571.717')] [2023-03-07 23:40:40,321][286389] Updated weights for policy 0, policy_version 61360 (0.0004) [2023-03-07 23:40:42,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11605.3, 300 sec: 11482.7). Total num frames: 31444992. Throughput: 0: 11395.4. Samples: 31424672. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:40:42,827][286098] Avg episode reward: [(0, '4428.407')] [2023-03-07 23:40:42,831][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000061416_31444992.pth... [2023-03-07 23:40:42,833][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000060736_31096832.pth [2023-03-07 23:40:43,710][286389] Updated weights for policy 0, policy_version 61440 (0.0005) [2023-03-07 23:40:47,396][286389] Updated weights for policy 0, policy_version 61520 (0.0005) [2023-03-07 23:40:47,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11537.1, 300 sec: 11482.7). Total num frames: 31502336. Throughput: 0: 11477.0. Samples: 31494380. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:40:47,816][286098] Avg episode reward: [(0, '4425.240')] [2023-03-07 23:40:51,042][286389] Updated weights for policy 0, policy_version 61600 (0.0005) [2023-03-07 23:40:52,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11400.5, 300 sec: 11468.8). Total num frames: 31555584. Throughput: 0: 11489.2. Samples: 31527856. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:40:52,822][286098] Avg episode reward: [(0, '4349.567')] [2023-03-07 23:40:54,641][286389] Updated weights for policy 0, policy_version 61680 (0.0005) [2023-03-07 23:40:57,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11400.5, 300 sec: 11454.9). Total num frames: 31612928. Throughput: 0: 11500.6. Samples: 31596608. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:40:57,816][286098] Avg episode reward: [(0, '4576.963')] [2023-03-07 23:40:57,881][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000061752_31617024.pth... [2023-03-07 23:40:57,883][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000061064_31264768.pth [2023-03-07 23:40:58,241][286389] Updated weights for policy 0, policy_version 61760 (0.0005) [2023-03-07 23:41:01,950][286389] Updated weights for policy 0, policy_version 61840 (0.0005) [2023-03-07 23:41:02,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11468.8, 300 sec: 11427.1). Total num frames: 31670272. Throughput: 0: 11478.2. Samples: 31663284. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:41:02,817][286098] Avg episode reward: [(0, '4581.750')] [2023-03-07 23:41:05,638][286389] Updated weights for policy 0, policy_version 61920 (0.0005) [2023-03-07 23:41:07,816][286098] Fps is (10 sec: 11059.4, 60 sec: 11400.6, 300 sec: 11427.1). Total num frames: 31723520. Throughput: 0: 11447.1. Samples: 31696232. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:41:07,816][286098] Avg episode reward: [(0, '4571.946')] [2023-03-07 23:41:09,326][286389] Updated weights for policy 0, policy_version 62000 (0.0005) [2023-03-07 23:41:12,816][286098] Fps is (10 sec: 11059.3, 60 sec: 11400.5, 300 sec: 11427.1). Total num frames: 31780864. Throughput: 0: 11452.6. Samples: 31763748. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:41:12,827][286098] Avg episode reward: [(0, '4523.163')] [2023-03-07 23:41:12,830][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000062072_31780864.pth... [2023-03-07 23:41:12,833][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000061416_31444992.pth [2023-03-07 23:41:12,984][286389] Updated weights for policy 0, policy_version 62080 (0.0005) [2023-03-07 23:41:16,694][286389] Updated weights for policy 0, policy_version 62160 (0.0005) [2023-03-07 23:41:17,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11400.5, 300 sec: 11427.2). Total num frames: 31838208. Throughput: 0: 11377.6. Samples: 31830080. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:41:17,827][286098] Avg episode reward: [(0, '4586.782')] [2023-03-07 23:41:20,414][286389] Updated weights for policy 0, policy_version 62240 (0.0006) [2023-03-07 23:41:22,816][286098] Fps is (10 sec: 11059.1, 60 sec: 11400.5, 300 sec: 11427.1). Total num frames: 31891456. Throughput: 0: 11355.4. Samples: 31862856. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:41:22,816][286098] Avg episode reward: [(0, '4571.537')] [2023-03-07 23:41:24,044][286389] Updated weights for policy 0, policy_version 62320 (0.0005) [2023-03-07 23:41:27,816][286098] Fps is (10 sec: 10649.5, 60 sec: 11332.3, 300 sec: 11413.3). Total num frames: 31944704. Throughput: 0: 11227.6. Samples: 31929916. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-07 23:41:27,816][286098] Avg episode reward: [(0, '4557.439')] [2023-03-07 23:41:27,842][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000062400_31948800.pth... [2023-03-07 23:41:27,842][286389] Updated weights for policy 0, policy_version 62400 (0.0005) [2023-03-07 23:41:27,843][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000061752_31617024.pth [2023-03-07 23:41:31,446][286389] Updated weights for policy 0, policy_version 62480 (0.0005) [2023-03-07 23:41:32,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11264.0, 300 sec: 11399.4). Total num frames: 32002048. Throughput: 0: 11173.2. Samples: 31997176. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-07 23:41:32,816][286098] Avg episode reward: [(0, '4560.050')] [2023-03-07 23:41:34,873][286389] Updated weights for policy 0, policy_version 62560 (0.0004) [2023-03-07 23:41:37,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11332.3, 300 sec: 11427.1). Total num frames: 32063488. Throughput: 0: 11223.6. Samples: 32032920. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-07 23:41:37,816][286098] Avg episode reward: [(0, '4453.822')] [2023-03-07 23:41:38,324][286389] Updated weights for policy 0, policy_version 62640 (0.0005) [2023-03-07 23:41:41,632][286389] Updated weights for policy 0, policy_version 62720 (0.0004) [2023-03-07 23:41:42,816][286098] Fps is (10 sec: 12288.0, 60 sec: 11332.3, 300 sec: 11441.0). Total num frames: 32124928. Throughput: 0: 11314.5. Samples: 32105760. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-07 23:41:42,816][286098] Avg episode reward: [(0, '4501.970')] [2023-03-07 23:41:42,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000062744_32124928.pth... [2023-03-07 23:41:42,823][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000062072_31780864.pth [2023-03-07 23:41:44,934][286389] Updated weights for policy 0, policy_version 62800 (0.0004) [2023-03-07 23:41:47,816][286098] Fps is (10 sec: 12288.0, 60 sec: 11400.5, 300 sec: 11454.9). Total num frames: 32186368. Throughput: 0: 11454.8. Samples: 32178752. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-07 23:41:47,816][286098] Avg episode reward: [(0, '4090.252')] [2023-03-07 23:41:48,356][286389] Updated weights for policy 0, policy_version 62880 (0.0005) [2023-03-07 23:41:51,694][286389] Updated weights for policy 0, policy_version 62960 (0.0005) [2023-03-07 23:41:52,816][286098] Fps is (10 sec: 12288.0, 60 sec: 11537.1, 300 sec: 11468.8). Total num frames: 32247808. Throughput: 0: 11536.8. Samples: 32215388. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-07 23:41:52,816][286098] Avg episode reward: [(0, '3618.279')] [2023-03-07 23:41:54,945][286389] Updated weights for policy 0, policy_version 63040 (0.0005) [2023-03-07 23:41:57,816][286098] Fps is (10 sec: 12288.0, 60 sec: 11605.3, 300 sec: 11468.8). Total num frames: 32309248. Throughput: 0: 11698.2. Samples: 32290168. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-07 23:41:57,816][286098] Avg episode reward: [(0, '2780.971')] [2023-03-07 23:41:57,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000063104_32309248.pth... [2023-03-07 23:41:57,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000062400_31948800.pth [2023-03-07 23:41:58,238][286389] Updated weights for policy 0, policy_version 63120 (0.0005) [2023-03-07 23:42:01,715][286389] Updated weights for policy 0, policy_version 63200 (0.0005) [2023-03-07 23:42:02,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11605.3, 300 sec: 11482.7). Total num frames: 32366592. Throughput: 0: 11831.6. Samples: 32362504. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-07 23:42:02,816][286098] Avg episode reward: [(0, '2746.274')] [2023-03-07 23:42:05,379][286389] Updated weights for policy 0, policy_version 63280 (0.0006) [2023-03-07 23:42:07,816][286098] Fps is (10 sec: 11878.3, 60 sec: 11741.8, 300 sec: 11496.6). Total num frames: 32428032. Throughput: 0: 11835.3. Samples: 32395444. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-07 23:42:07,817][286098] Avg episode reward: [(0, '3116.687')] [2023-03-07 23:42:08,880][286389] Updated weights for policy 0, policy_version 63360 (0.0005) [2023-03-07 23:42:12,566][286389] Updated weights for policy 0, policy_version 63440 (0.0005) [2023-03-07 23:42:12,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11673.6, 300 sec: 11496.6). Total num frames: 32481280. Throughput: 0: 11889.9. Samples: 32464960. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-07 23:42:12,816][286098] Avg episode reward: [(0, '3746.136')] [2023-03-07 23:42:12,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000063440_32481280.pth... [2023-03-07 23:42:12,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000062744_32124928.pth [2023-03-07 23:42:16,140][286389] Updated weights for policy 0, policy_version 63520 (0.0005) [2023-03-07 23:42:17,816][286098] Fps is (10 sec: 11468.9, 60 sec: 11741.9, 300 sec: 11496.6). Total num frames: 32542720. Throughput: 0: 11923.6. Samples: 32533736. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-07 23:42:17,816][286098] Avg episode reward: [(0, '4143.476')] [2023-03-07 23:42:19,595][286389] Updated weights for policy 0, policy_version 63600 (0.0003) [2023-03-07 23:42:22,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11741.9, 300 sec: 11468.8). Total num frames: 32595968. Throughput: 0: 11892.5. Samples: 32568084. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-07 23:42:22,816][286098] Avg episode reward: [(0, '4270.859')] [2023-03-07 23:42:23,227][286389] Updated weights for policy 0, policy_version 63680 (0.0004) [2023-03-07 23:42:26,697][286389] Updated weights for policy 0, policy_version 63760 (0.0004) [2023-03-07 23:42:27,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11878.4, 300 sec: 11482.7). Total num frames: 32657408. Throughput: 0: 11806.0. Samples: 32637028. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-07 23:42:27,816][286098] Avg episode reward: [(0, '4211.366')] [2023-03-07 23:42:27,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000063784_32657408.pth... [2023-03-07 23:42:27,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000063104_32309248.pth [2023-03-07 23:42:30,331][286389] Updated weights for policy 0, policy_version 63840 (0.0005) [2023-03-07 23:42:32,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11810.1, 300 sec: 11468.8). Total num frames: 32710656. Throughput: 0: 11724.3. Samples: 32706344. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-07 23:42:32,816][286098] Avg episode reward: [(0, '4460.110')] [2023-03-07 23:42:33,984][286389] Updated weights for policy 0, policy_version 63920 (0.0005) [2023-03-07 23:42:37,637][286389] Updated weights for policy 0, policy_version 64000 (0.0006) [2023-03-07 23:42:37,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11741.9, 300 sec: 11468.8). Total num frames: 32768000. Throughput: 0: 11643.3. Samples: 32739336. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-07 23:42:37,816][286098] Avg episode reward: [(0, '4429.176')] [2023-03-07 23:42:41,195][286389] Updated weights for policy 0, policy_version 64080 (0.0003) [2023-03-07 23:42:42,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11673.6, 300 sec: 11482.7). Total num frames: 32825344. Throughput: 0: 11493.4. Samples: 32807372. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:42:42,816][286098] Avg episode reward: [(0, '4468.321')] [2023-03-07 23:42:42,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000064112_32825344.pth... [2023-03-07 23:42:42,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000063440_32481280.pth [2023-03-07 23:42:44,604][286389] Updated weights for policy 0, policy_version 64160 (0.0003) [2023-03-07 23:42:47,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11673.6, 300 sec: 11496.6). Total num frames: 32886784. Throughput: 0: 11506.0. Samples: 32880272. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:42:47,816][286098] Avg episode reward: [(0, '4524.442')] [2023-03-07 23:42:47,924][286389] Updated weights for policy 0, policy_version 64240 (0.0003) [2023-03-07 23:42:51,370][286389] Updated weights for policy 0, policy_version 64320 (0.0003) [2023-03-07 23:42:52,816][286098] Fps is (10 sec: 12288.1, 60 sec: 11673.6, 300 sec: 11510.5). Total num frames: 32948224. Throughput: 0: 11564.8. Samples: 32915860. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:42:52,816][286098] Avg episode reward: [(0, '4537.279')] [2023-03-07 23:42:54,935][286389] Updated weights for policy 0, policy_version 64400 (0.0005) [2023-03-07 23:42:57,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11537.1, 300 sec: 11510.5). Total num frames: 33001472. Throughput: 0: 11559.8. Samples: 32985152. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:42:57,816][286098] Avg episode reward: [(0, '4441.467')] [2023-03-07 23:42:57,879][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000064464_33005568.pth... [2023-03-07 23:42:57,880][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000063784_32657408.pth [2023-03-07 23:42:58,617][286389] Updated weights for policy 0, policy_version 64480 (0.0005) [2023-03-07 23:43:02,306][286389] Updated weights for policy 0, policy_version 64560 (0.0005) [2023-03-07 23:43:02,816][286098] Fps is (10 sec: 11059.1, 60 sec: 11537.1, 300 sec: 11510.5). Total num frames: 33058816. Throughput: 0: 11514.6. Samples: 33051892. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:43:02,816][286098] Avg episode reward: [(0, '4513.054')] [2023-03-07 23:43:06,012][286389] Updated weights for policy 0, policy_version 64640 (0.0005) [2023-03-07 23:43:07,816][286098] Fps is (10 sec: 11059.1, 60 sec: 11400.5, 300 sec: 11496.6). Total num frames: 33112064. Throughput: 0: 11511.2. Samples: 33086088. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:43:07,817][286098] Avg episode reward: [(0, '4542.324')] [2023-03-07 23:43:09,636][286389] Updated weights for policy 0, policy_version 64720 (0.0004) [2023-03-07 23:43:12,816][286098] Fps is (10 sec: 11468.7, 60 sec: 11537.1, 300 sec: 11510.5). Total num frames: 33173504. Throughput: 0: 11470.9. Samples: 33153220. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:43:12,816][286098] Avg episode reward: [(0, '4537.170')] [2023-03-07 23:43:12,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000064792_33173504.pth... [2023-03-07 23:43:12,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000064112_32825344.pth [2023-03-07 23:43:13,086][286389] Updated weights for policy 0, policy_version 64800 (0.0003) [2023-03-07 23:43:16,539][286389] Updated weights for policy 0, policy_version 64880 (0.0003) [2023-03-07 23:43:17,816][286098] Fps is (10 sec: 11878.5, 60 sec: 11468.8, 300 sec: 11510.5). Total num frames: 33230848. Throughput: 0: 11523.2. Samples: 33224888. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:43:17,816][286098] Avg episode reward: [(0, '4536.525')] [2023-03-07 23:43:20,095][286389] Updated weights for policy 0, policy_version 64960 (0.0003) [2023-03-07 23:43:22,816][286098] Fps is (10 sec: 11468.7, 60 sec: 11537.1, 300 sec: 11510.5). Total num frames: 33288192. Throughput: 0: 11559.7. Samples: 33259524. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-07 23:43:22,817][286098] Avg episode reward: [(0, '4499.904')] [2023-03-07 23:43:23,519][286389] Updated weights for policy 0, policy_version 65040 (0.0003) [2023-03-07 23:43:26,958][286389] Updated weights for policy 0, policy_version 65120 (0.0004) [2023-03-07 23:43:27,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11537.1, 300 sec: 11524.3). Total num frames: 33349632. Throughput: 0: 11635.4. Samples: 33330964. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-07 23:43:27,816][286098] Avg episode reward: [(0, '4493.069')] [2023-03-07 23:43:27,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000065136_33349632.pth... [2023-03-07 23:43:27,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000064464_33005568.pth [2023-03-07 23:43:30,380][286389] Updated weights for policy 0, policy_version 65200 (0.0004) [2023-03-07 23:43:32,816][286098] Fps is (10 sec: 12288.1, 60 sec: 11673.6, 300 sec: 11552.1). Total num frames: 33411072. Throughput: 0: 11613.9. Samples: 33402896. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-07 23:43:32,816][286098] Avg episode reward: [(0, '4315.877')] [2023-03-07 23:43:33,742][286389] Updated weights for policy 0, policy_version 65280 (0.0004) [2023-03-07 23:43:37,154][286389] Updated weights for policy 0, policy_version 65360 (0.0005) [2023-03-07 23:43:37,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11673.6, 300 sec: 11552.1). Total num frames: 33468416. Throughput: 0: 11632.7. Samples: 33439332. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-07 23:43:37,816][286098] Avg episode reward: [(0, '4299.033')] [2023-03-07 23:43:40,594][286389] Updated weights for policy 0, policy_version 65440 (0.0005) [2023-03-07 23:43:42,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11741.9, 300 sec: 11579.9). Total num frames: 33529856. Throughput: 0: 11687.3. Samples: 33511080. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-07 23:43:42,816][286098] Avg episode reward: [(0, '4166.787')] [2023-03-07 23:43:42,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000065488_33529856.pth... [2023-03-07 23:43:42,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000064792_33173504.pth [2023-03-07 23:43:44,005][286389] Updated weights for policy 0, policy_version 65520 (0.0005) [2023-03-07 23:43:47,412][286389] Updated weights for policy 0, policy_version 65600 (0.0004) [2023-03-07 23:43:47,816][286098] Fps is (10 sec: 12288.0, 60 sec: 11741.9, 300 sec: 11593.8). Total num frames: 33591296. Throughput: 0: 11806.1. Samples: 33583168. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-07 23:43:47,816][286098] Avg episode reward: [(0, '4280.325')] [2023-03-07 23:43:50,851][286389] Updated weights for policy 0, policy_version 65680 (0.0005) [2023-03-07 23:43:52,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11673.6, 300 sec: 11593.8). Total num frames: 33648640. Throughput: 0: 11849.7. Samples: 33619324. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-07 23:43:52,816][286098] Avg episode reward: [(0, '4408.207')] [2023-03-07 23:43:54,225][286389] Updated weights for policy 0, policy_version 65760 (0.0004) [2023-03-07 23:43:57,624][286389] Updated weights for policy 0, policy_version 65840 (0.0004) [2023-03-07 23:43:57,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11810.1, 300 sec: 11607.6). Total num frames: 33710080. Throughput: 0: 11953.0. Samples: 33691104. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-07 23:43:57,816][286098] Avg episode reward: [(0, '4516.354')] [2023-03-07 23:43:57,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000065840_33710080.pth... [2023-03-07 23:43:57,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000065136_33349632.pth [2023-03-07 23:44:01,066][286389] Updated weights for policy 0, policy_version 65920 (0.0005) [2023-03-07 23:44:02,816][286098] Fps is (10 sec: 11878.3, 60 sec: 11810.1, 300 sec: 11621.5). Total num frames: 33767424. Throughput: 0: 11950.3. Samples: 33762652. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-07 23:44:02,817][286098] Avg episode reward: [(0, '4511.132')] [2023-03-07 23:44:04,652][286389] Updated weights for policy 0, policy_version 66000 (0.0005) [2023-03-07 23:44:07,816][286098] Fps is (10 sec: 11468.9, 60 sec: 11878.4, 300 sec: 11621.5). Total num frames: 33824768. Throughput: 0: 11925.5. Samples: 33796168. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-07 23:44:07,816][286098] Avg episode reward: [(0, '4570.255')] [2023-03-07 23:44:08,355][286389] Updated weights for policy 0, policy_version 66080 (0.0005) [2023-03-07 23:44:12,117][286389] Updated weights for policy 0, policy_version 66160 (0.0005) [2023-03-07 23:44:12,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11741.9, 300 sec: 11607.6). Total num frames: 33878016. Throughput: 0: 11802.9. Samples: 33862096. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-07 23:44:12,816][286098] Avg episode reward: [(0, '4566.355')] [2023-03-07 23:44:12,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000066168_33878016.pth... [2023-03-07 23:44:12,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000065488_33529856.pth [2023-03-07 23:44:15,885][286389] Updated weights for policy 0, policy_version 66240 (0.0005) [2023-03-07 23:44:17,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11741.9, 300 sec: 11621.5). Total num frames: 33935360. Throughput: 0: 11657.7. Samples: 33927492. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-07 23:44:17,816][286098] Avg episode reward: [(0, '4522.576')] [2023-03-07 23:44:19,584][286389] Updated weights for policy 0, policy_version 66320 (0.0005) [2023-03-07 23:44:22,816][286098] Fps is (10 sec: 11059.3, 60 sec: 11673.6, 300 sec: 11593.8). Total num frames: 33988608. Throughput: 0: 11591.5. Samples: 33960948. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-07 23:44:22,816][286098] Avg episode reward: [(0, '4566.054')] [2023-03-07 23:44:23,368][286389] Updated weights for policy 0, policy_version 66400 (0.0005) [2023-03-07 23:44:27,045][286389] Updated weights for policy 0, policy_version 66480 (0.0005) [2023-03-07 23:44:27,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11605.3, 300 sec: 11579.9). Total num frames: 34045952. Throughput: 0: 11455.0. Samples: 34026556. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-07 23:44:27,816][286098] Avg episode reward: [(0, '4547.367')] [2023-03-07 23:44:27,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000066496_34045952.pth... [2023-03-07 23:44:27,821][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000065840_33710080.pth [2023-03-07 23:44:30,732][286389] Updated weights for policy 0, policy_version 66560 (0.0005) [2023-03-07 23:44:32,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11468.8, 300 sec: 11566.0). Total num frames: 34099200. Throughput: 0: 11357.3. Samples: 34094244. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-07 23:44:32,816][286098] Avg episode reward: [(0, '4575.374')] [2023-03-07 23:44:34,345][286389] Updated weights for policy 0, policy_version 66640 (0.0005) [2023-03-07 23:44:37,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11468.8, 300 sec: 11552.1). Total num frames: 34156544. Throughput: 0: 11301.1. Samples: 34127872. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-07 23:44:37,816][286098] Avg episode reward: [(0, '4579.532')] [2023-03-07 23:44:38,023][286389] Updated weights for policy 0, policy_version 66720 (0.0005) [2023-03-07 23:44:41,785][286389] Updated weights for policy 0, policy_version 66800 (0.0005) [2023-03-07 23:44:42,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11332.3, 300 sec: 11524.3). Total num frames: 34209792. Throughput: 0: 11163.9. Samples: 34193480. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-07 23:44:42,816][286098] Avg episode reward: [(0, '4569.389')] [2023-03-07 23:44:42,847][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000066824_34213888.pth... [2023-03-07 23:44:42,849][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000066168_33878016.pth [2023-03-07 23:44:45,357][286389] Updated weights for policy 0, policy_version 66880 (0.0005) [2023-03-07 23:44:47,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11264.0, 300 sec: 11510.5). Total num frames: 34267136. Throughput: 0: 11106.1. Samples: 34262424. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-07 23:44:47,816][286098] Avg episode reward: [(0, '4567.115')] [2023-03-07 23:44:48,974][286389] Updated weights for policy 0, policy_version 66960 (0.0005) [2023-03-07 23:44:52,643][286389] Updated weights for policy 0, policy_version 67040 (0.0005) [2023-03-07 23:44:52,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11264.0, 300 sec: 11510.5). Total num frames: 34324480. Throughput: 0: 11104.5. Samples: 34295872. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-07 23:44:52,816][286098] Avg episode reward: [(0, '4565.966')] [2023-03-07 23:44:56,250][286389] Updated weights for policy 0, policy_version 67120 (0.0004) [2023-03-07 23:44:57,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11195.7, 300 sec: 11524.3). Total num frames: 34381824. Throughput: 0: 11140.4. Samples: 34363412. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-07 23:44:57,816][286098] Avg episode reward: [(0, '4507.382')] [2023-03-07 23:44:57,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000067152_34381824.pth... [2023-03-07 23:44:57,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000066496_34045952.pth [2023-03-07 23:44:59,871][286389] Updated weights for policy 0, policy_version 67200 (0.0005) [2023-03-07 23:45:02,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11195.8, 300 sec: 11524.3). Total num frames: 34439168. Throughput: 0: 11245.8. Samples: 34433552. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-07 23:45:02,816][286098] Avg episode reward: [(0, '4393.609')] [2023-03-07 23:45:03,198][286389] Updated weights for policy 0, policy_version 67280 (0.0003) [2023-03-07 23:45:06,702][286389] Updated weights for policy 0, policy_version 67360 (0.0004) [2023-03-07 23:45:07,816][286098] Fps is (10 sec: 11878.5, 60 sec: 11264.0, 300 sec: 11538.2). Total num frames: 34500608. Throughput: 0: 11289.2. Samples: 34468960. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-07 23:45:07,816][286098] Avg episode reward: [(0, '4548.931')] [2023-03-07 23:45:10,428][286389] Updated weights for policy 0, policy_version 67440 (0.0005) [2023-03-07 23:45:12,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11264.0, 300 sec: 11524.3). Total num frames: 34553856. Throughput: 0: 11339.5. Samples: 34536832. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-07 23:45:12,816][286098] Avg episode reward: [(0, '4528.380')] [2023-03-07 23:45:12,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000067488_34553856.pth... [2023-03-07 23:45:12,820][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000066824_34213888.pth [2023-03-07 23:45:13,950][286389] Updated weights for policy 0, policy_version 67520 (0.0005) [2023-03-07 23:45:17,581][286389] Updated weights for policy 0, policy_version 67600 (0.0005) [2023-03-07 23:45:17,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11264.0, 300 sec: 11538.2). Total num frames: 34611200. Throughput: 0: 11359.8. Samples: 34605436. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-07 23:45:17,816][286098] Avg episode reward: [(0, '4561.872')] [2023-03-07 23:45:21,246][286389] Updated weights for policy 0, policy_version 67680 (0.0005) [2023-03-07 23:45:22,816][286098] Fps is (10 sec: 11468.7, 60 sec: 11332.3, 300 sec: 11538.2). Total num frames: 34668544. Throughput: 0: 11373.3. Samples: 34639672. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-07 23:45:22,816][286098] Avg episode reward: [(0, '4575.631')] [2023-03-07 23:45:24,893][286389] Updated weights for policy 0, policy_version 67760 (0.0005) [2023-03-07 23:45:27,816][286098] Fps is (10 sec: 11059.1, 60 sec: 11264.0, 300 sec: 11510.5). Total num frames: 34721792. Throughput: 0: 11390.5. Samples: 34706052. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:45:27,816][286098] Avg episode reward: [(0, '4501.252')] [2023-03-07 23:45:27,823][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000067824_34725888.pth... [2023-03-07 23:45:27,825][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000067152_34381824.pth [2023-03-07 23:45:28,578][286389] Updated weights for policy 0, policy_version 67840 (0.0005) [2023-03-07 23:45:32,254][286389] Updated weights for policy 0, policy_version 67920 (0.0005) [2023-03-07 23:45:32,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11332.3, 300 sec: 11510.5). Total num frames: 34779136. Throughput: 0: 11339.2. Samples: 34772688. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:45:32,817][286098] Avg episode reward: [(0, '4483.351')] [2023-03-07 23:45:35,864][286389] Updated weights for policy 0, policy_version 68000 (0.0005) [2023-03-07 23:45:37,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11332.3, 300 sec: 11496.6). Total num frames: 34836480. Throughput: 0: 11360.0. Samples: 34807072. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:45:37,816][286098] Avg episode reward: [(0, '4443.080')] [2023-03-07 23:45:39,524][286389] Updated weights for policy 0, policy_version 68080 (0.0005) [2023-03-07 23:45:42,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11332.2, 300 sec: 11482.7). Total num frames: 34889728. Throughput: 0: 11337.6. Samples: 34873604. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:45:42,816][286098] Avg episode reward: [(0, '4533.269')] [2023-03-07 23:45:42,832][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000068152_34893824.pth... [2023-03-07 23:45:42,834][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000067488_34553856.pth [2023-03-07 23:45:43,210][286389] Updated weights for policy 0, policy_version 68160 (0.0005) [2023-03-07 23:45:46,804][286389] Updated weights for policy 0, policy_version 68240 (0.0005) [2023-03-07 23:45:47,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11332.3, 300 sec: 11496.6). Total num frames: 34947072. Throughput: 0: 11302.3. Samples: 34942156. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:45:47,816][286098] Avg episode reward: [(0, '4568.538')] [2023-03-07 23:45:50,438][286389] Updated weights for policy 0, policy_version 68320 (0.0005) [2023-03-07 23:45:52,816][286098] Fps is (10 sec: 11468.9, 60 sec: 11332.3, 300 sec: 11496.6). Total num frames: 35004416. Throughput: 0: 11263.5. Samples: 34975816. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:45:52,827][286098] Avg episode reward: [(0, '4562.043')] [2023-03-07 23:45:54,092][286389] Updated weights for policy 0, policy_version 68400 (0.0005) [2023-03-07 23:45:57,764][286389] Updated weights for policy 0, policy_version 68480 (0.0005) [2023-03-07 23:45:57,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11332.3, 300 sec: 11496.6). Total num frames: 35061760. Throughput: 0: 11249.8. Samples: 35043076. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:45:57,827][286098] Avg episode reward: [(0, '4545.463')] [2023-03-07 23:45:57,830][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000068480_35061760.pth... [2023-03-07 23:45:57,833][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000067824_34725888.pth [2023-03-07 23:46:01,372][286389] Updated weights for policy 0, policy_version 68560 (0.0005) [2023-03-07 23:46:02,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11332.3, 300 sec: 11510.5). Total num frames: 35119104. Throughput: 0: 11232.8. Samples: 35110912. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:46:02,816][286098] Avg episode reward: [(0, '4547.618')] [2023-03-07 23:46:05,064][286389] Updated weights for policy 0, policy_version 68640 (0.0005) [2023-03-07 23:46:07,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11195.7, 300 sec: 11496.6). Total num frames: 35172352. Throughput: 0: 11201.6. Samples: 35143744. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:46:07,816][286098] Avg episode reward: [(0, '4451.639')] [2023-03-07 23:46:08,715][286389] Updated weights for policy 0, policy_version 68720 (0.0005) [2023-03-07 23:46:12,041][286389] Updated weights for policy 0, policy_version 68800 (0.0004) [2023-03-07 23:46:12,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11332.3, 300 sec: 11510.5). Total num frames: 35233792. Throughput: 0: 11274.1. Samples: 35213384. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:46:12,816][286098] Avg episode reward: [(0, '4550.677')] [2023-03-07 23:46:12,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000068816_35233792.pth... [2023-03-07 23:46:12,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000068152_34893824.pth [2023-03-07 23:46:15,363][286389] Updated weights for policy 0, policy_version 68880 (0.0004) [2023-03-07 23:46:17,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11332.3, 300 sec: 11524.3). Total num frames: 35291136. Throughput: 0: 11398.3. Samples: 35285612. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:46:17,816][286098] Avg episode reward: [(0, '4535.161')] [2023-03-07 23:46:19,002][286389] Updated weights for policy 0, policy_version 68960 (0.0005) [2023-03-07 23:46:22,615][286389] Updated weights for policy 0, policy_version 69040 (0.0005) [2023-03-07 23:46:22,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11332.3, 300 sec: 11538.2). Total num frames: 35348480. Throughput: 0: 11394.3. Samples: 35319816. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:46:22,816][286098] Avg episode reward: [(0, '4235.331')] [2023-03-07 23:46:26,292][286389] Updated weights for policy 0, policy_version 69120 (0.0005) [2023-03-07 23:46:27,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11400.5, 300 sec: 11538.2). Total num frames: 35405824. Throughput: 0: 11412.5. Samples: 35387168. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:46:27,816][286098] Avg episode reward: [(0, '4519.976')] [2023-03-07 23:46:27,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000069152_35405824.pth... [2023-03-07 23:46:27,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000068480_35061760.pth [2023-03-07 23:46:29,943][286389] Updated weights for policy 0, policy_version 69200 (0.0005) [2023-03-07 23:46:32,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11400.5, 300 sec: 11524.3). Total num frames: 35463168. Throughput: 0: 11396.3. Samples: 35454988. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:46:32,816][286098] Avg episode reward: [(0, '4575.805')] [2023-03-07 23:46:33,536][286389] Updated weights for policy 0, policy_version 69280 (0.0006) [2023-03-07 23:46:37,138][286389] Updated weights for policy 0, policy_version 69360 (0.0005) [2023-03-07 23:46:37,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11332.3, 300 sec: 11496.6). Total num frames: 35516416. Throughput: 0: 11389.0. Samples: 35488320. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:46:37,816][286098] Avg episode reward: [(0, '4555.186')] [2023-03-07 23:46:40,592][286389] Updated weights for policy 0, policy_version 69440 (0.0005) [2023-03-07 23:46:42,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11468.8, 300 sec: 11496.6). Total num frames: 35577856. Throughput: 0: 11460.6. Samples: 35558804. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:46:42,816][286098] Avg episode reward: [(0, '4507.037')] [2023-03-07 23:46:42,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000069488_35577856.pth... [2023-03-07 23:46:42,823][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000068816_35233792.pth [2023-03-07 23:46:43,944][286389] Updated weights for policy 0, policy_version 69520 (0.0005) [2023-03-07 23:46:47,289][286389] Updated weights for policy 0, policy_version 69600 (0.0004) [2023-03-07 23:46:47,816][286098] Fps is (10 sec: 12288.0, 60 sec: 11537.1, 300 sec: 11496.6). Total num frames: 35639296. Throughput: 0: 11574.8. Samples: 35631780. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:46:47,816][286098] Avg episode reward: [(0, '3676.710')] [2023-03-07 23:46:50,626][286389] Updated weights for policy 0, policy_version 69680 (0.0005) [2023-03-07 23:46:52,816][286098] Fps is (10 sec: 12288.0, 60 sec: 11605.3, 300 sec: 11496.6). Total num frames: 35700736. Throughput: 0: 11688.4. Samples: 35669720. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:46:52,816][286098] Avg episode reward: [(0, '3807.529')] [2023-03-07 23:46:53,992][286389] Updated weights for policy 0, policy_version 69760 (0.0005) [2023-03-07 23:46:57,289][286389] Updated weights for policy 0, policy_version 69840 (0.0004) [2023-03-07 23:46:57,816][286098] Fps is (10 sec: 12288.0, 60 sec: 11673.6, 300 sec: 11510.5). Total num frames: 35762176. Throughput: 0: 11762.7. Samples: 35742708. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:46:57,817][286098] Avg episode reward: [(0, '3974.072')] [2023-03-07 23:46:57,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000069848_35762176.pth... [2023-03-07 23:46:57,823][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000069152_35405824.pth [2023-03-07 23:47:00,606][286389] Updated weights for policy 0, policy_version 69920 (0.0004) [2023-03-07 23:47:02,816][286098] Fps is (10 sec: 12288.0, 60 sec: 11741.9, 300 sec: 11510.5). Total num frames: 35823616. Throughput: 0: 11805.9. Samples: 35816876. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:47:02,816][286098] Avg episode reward: [(0, '4014.654')] [2023-03-07 23:47:03,888][286389] Updated weights for policy 0, policy_version 70000 (0.0004) [2023-03-07 23:47:07,416][286389] Updated weights for policy 0, policy_version 70080 (0.0005) [2023-03-07 23:47:07,816][286098] Fps is (10 sec: 12288.1, 60 sec: 11878.4, 300 sec: 11538.2). Total num frames: 35885056. Throughput: 0: 11868.6. Samples: 35853904. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:47:07,816][286098] Avg episode reward: [(0, '4203.328')] [2023-03-07 23:47:10,820][286389] Updated weights for policy 0, policy_version 70160 (0.0004) [2023-03-07 23:47:12,816][286098] Fps is (10 sec: 11878.3, 60 sec: 11810.1, 300 sec: 11524.3). Total num frames: 35942400. Throughput: 0: 11950.8. Samples: 35924952. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:47:12,816][286098] Avg episode reward: [(0, '4380.093')] [2023-03-07 23:47:12,830][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000070208_35946496.pth... [2023-03-07 23:47:12,832][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000069488_35577856.pth [2023-03-07 23:47:14,314][286389] Updated weights for policy 0, policy_version 70240 (0.0005) [2023-03-07 23:47:17,768][286389] Updated weights for policy 0, policy_version 70320 (0.0004) [2023-03-07 23:47:17,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11878.4, 300 sec: 11552.1). Total num frames: 36003840. Throughput: 0: 12016.1. Samples: 35995712. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:47:17,816][286098] Avg episode reward: [(0, '4352.343')] [2023-03-07 23:47:21,162][286389] Updated weights for policy 0, policy_version 70400 (0.0003) [2023-03-07 23:47:22,816][286098] Fps is (10 sec: 11878.5, 60 sec: 11878.4, 300 sec: 11538.2). Total num frames: 36061184. Throughput: 0: 12087.2. Samples: 36032244. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:47:22,816][286098] Avg episode reward: [(0, '4403.088')] [2023-03-07 23:47:24,779][286389] Updated weights for policy 0, policy_version 70480 (0.0005) [2023-03-07 23:47:27,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11878.4, 300 sec: 11552.1). Total num frames: 36118528. Throughput: 0: 12023.7. Samples: 36099872. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:47:27,817][286098] Avg episode reward: [(0, '4476.671')] [2023-03-07 23:47:27,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000070544_36118528.pth... [2023-03-07 23:47:27,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000069848_35762176.pth [2023-03-07 23:47:28,468][286389] Updated weights for policy 0, policy_version 70560 (0.0005) [2023-03-07 23:47:32,179][286389] Updated weights for policy 0, policy_version 70640 (0.0005) [2023-03-07 23:47:32,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11810.1, 300 sec: 11538.2). Total num frames: 36171776. Throughput: 0: 11895.4. Samples: 36167072. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:47:32,816][286098] Avg episode reward: [(0, '4290.564')] [2023-03-07 23:47:35,827][286389] Updated weights for policy 0, policy_version 70720 (0.0005) [2023-03-07 23:47:37,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11878.4, 300 sec: 11538.2). Total num frames: 36229120. Throughput: 0: 11794.0. Samples: 36200448. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-07 23:47:37,816][286098] Avg episode reward: [(0, '4452.363')] [2023-03-07 23:47:39,404][286389] Updated weights for policy 0, policy_version 70800 (0.0005) [2023-03-07 23:47:42,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11810.1, 300 sec: 11524.3). Total num frames: 36286464. Throughput: 0: 11691.3. Samples: 36268816. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-07 23:47:42,817][286098] Avg episode reward: [(0, '4499.983')] [2023-03-07 23:47:42,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000070872_36286464.pth... [2023-03-07 23:47:42,823][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000070208_35946496.pth [2023-03-07 23:47:43,008][286389] Updated weights for policy 0, policy_version 70880 (0.0005) [2023-03-07 23:47:46,421][286389] Updated weights for policy 0, policy_version 70960 (0.0004) [2023-03-07 23:47:47,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11810.1, 300 sec: 11524.3). Total num frames: 36347904. Throughput: 0: 11605.4. Samples: 36339120. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-07 23:47:47,816][286098] Avg episode reward: [(0, '4408.618')] [2023-03-07 23:47:49,803][286389] Updated weights for policy 0, policy_version 71040 (0.0003) [2023-03-07 23:47:52,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11741.9, 300 sec: 11538.2). Total num frames: 36405248. Throughput: 0: 11598.8. Samples: 36375852. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-07 23:47:52,816][286098] Avg episode reward: [(0, '4506.118')] [2023-03-07 23:47:53,276][286389] Updated weights for policy 0, policy_version 71120 (0.0003) [2023-03-07 23:47:56,610][286389] Updated weights for policy 0, policy_version 71200 (0.0004) [2023-03-07 23:47:57,816][286098] Fps is (10 sec: 11878.3, 60 sec: 11741.9, 300 sec: 11552.1). Total num frames: 36466688. Throughput: 0: 11622.3. Samples: 36447956. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-07 23:47:57,817][286098] Avg episode reward: [(0, '4515.205')] [2023-03-07 23:47:57,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000071224_36466688.pth... [2023-03-07 23:47:57,823][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000070544_36118528.pth [2023-03-07 23:47:59,936][286389] Updated weights for policy 0, policy_version 71280 (0.0004) [2023-03-07 23:48:02,816][286098] Fps is (10 sec: 12288.0, 60 sec: 11741.9, 300 sec: 11579.9). Total num frames: 36528128. Throughput: 0: 11665.8. Samples: 36520672. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-07 23:48:02,816][286098] Avg episode reward: [(0, '4519.172')] [2023-03-07 23:48:03,417][286389] Updated weights for policy 0, policy_version 71360 (0.0005) [2023-03-07 23:48:07,075][286389] Updated weights for policy 0, policy_version 71440 (0.0005) [2023-03-07 23:48:07,816][286098] Fps is (10 sec: 11468.9, 60 sec: 11605.3, 300 sec: 11552.1). Total num frames: 36581376. Throughput: 0: 11615.1. Samples: 36554924. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-07 23:48:07,816][286098] Avg episode reward: [(0, '4499.962')] [2023-03-07 23:48:10,598][286389] Updated weights for policy 0, policy_version 71520 (0.0005) [2023-03-07 23:48:12,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11673.6, 300 sec: 11566.0). Total num frames: 36642816. Throughput: 0: 11639.1. Samples: 36623632. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-07 23:48:12,817][286098] Avg episode reward: [(0, '4424.615')] [2023-03-07 23:48:12,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000071568_36642816.pth... [2023-03-07 23:48:12,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000070872_36286464.pth [2023-03-07 23:48:13,955][286389] Updated weights for policy 0, policy_version 71600 (0.0005) [2023-03-07 23:48:17,347][286389] Updated weights for policy 0, policy_version 71680 (0.0005) [2023-03-07 23:48:17,816][286098] Fps is (10 sec: 12288.0, 60 sec: 11673.6, 300 sec: 11579.9). Total num frames: 36704256. Throughput: 0: 11764.4. Samples: 36696468. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-07 23:48:17,816][286098] Avg episode reward: [(0, '4548.136')] [2023-03-07 23:48:20,746][286389] Updated weights for policy 0, policy_version 71760 (0.0005) [2023-03-07 23:48:22,816][286098] Fps is (10 sec: 12288.0, 60 sec: 11741.9, 300 sec: 11579.9). Total num frames: 36765696. Throughput: 0: 11834.3. Samples: 36732992. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-07 23:48:22,816][286098] Avg episode reward: [(0, '4388.341')] [2023-03-07 23:48:24,161][286389] Updated weights for policy 0, policy_version 71840 (0.0005) [2023-03-07 23:48:27,710][286389] Updated weights for policy 0, policy_version 71920 (0.0005) [2023-03-07 23:48:27,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11741.9, 300 sec: 11566.0). Total num frames: 36823040. Throughput: 0: 11879.2. Samples: 36803380. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-07 23:48:27,816][286098] Avg episode reward: [(0, '4420.340')] [2023-03-07 23:48:27,818][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000071920_36823040.pth... [2023-03-07 23:48:27,821][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000071224_36466688.pth [2023-03-07 23:48:31,117][286389] Updated weights for policy 0, policy_version 72000 (0.0004) [2023-03-07 23:48:32,816][286098] Fps is (10 sec: 11468.9, 60 sec: 11810.1, 300 sec: 11566.0). Total num frames: 36880384. Throughput: 0: 11909.6. Samples: 36875052. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-07 23:48:32,816][286098] Avg episode reward: [(0, '4544.677')] [2023-03-07 23:48:34,505][286389] Updated weights for policy 0, policy_version 72080 (0.0005) [2023-03-07 23:48:37,816][286098] Fps is (10 sec: 11878.3, 60 sec: 11878.4, 300 sec: 11566.0). Total num frames: 36941824. Throughput: 0: 11915.6. Samples: 36912052. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-07 23:48:37,816][286098] Avg episode reward: [(0, '4545.585')] [2023-03-07 23:48:37,884][286389] Updated weights for policy 0, policy_version 72160 (0.0004) [2023-03-07 23:48:41,295][286389] Updated weights for policy 0, policy_version 72240 (0.0004) [2023-03-07 23:48:42,816][286098] Fps is (10 sec: 12287.9, 60 sec: 11946.7, 300 sec: 11566.0). Total num frames: 37003264. Throughput: 0: 11909.6. Samples: 36983888. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-07 23:48:42,816][286098] Avg episode reward: [(0, '4529.129')] [2023-03-07 23:48:42,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000072272_37003264.pth... [2023-03-07 23:48:42,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000071568_36642816.pth [2023-03-07 23:48:44,822][286389] Updated weights for policy 0, policy_version 72320 (0.0005) [2023-03-07 23:48:47,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11878.4, 300 sec: 11566.0). Total num frames: 37060608. Throughput: 0: 11851.4. Samples: 37053984. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-07 23:48:47,816][286098] Avg episode reward: [(0, '4543.721')] [2023-03-07 23:48:48,357][286389] Updated weights for policy 0, policy_version 72400 (0.0005) [2023-03-07 23:48:52,004][286389] Updated weights for policy 0, policy_version 72480 (0.0005) [2023-03-07 23:48:52,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11878.4, 300 sec: 11552.1). Total num frames: 37117952. Throughput: 0: 11846.7. Samples: 37088024. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-07 23:48:52,816][286098] Avg episode reward: [(0, '4544.524')] [2023-03-07 23:48:55,450][286389] Updated weights for policy 0, policy_version 72560 (0.0005) [2023-03-07 23:48:57,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11878.4, 300 sec: 11566.0). Total num frames: 37179392. Throughput: 0: 11888.0. Samples: 37158592. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-07 23:48:57,816][286098] Avg episode reward: [(0, '4542.217')] [2023-03-07 23:48:57,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000072616_37179392.pth... [2023-03-07 23:48:57,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000071920_36823040.pth [2023-03-07 23:48:58,731][286389] Updated weights for policy 0, policy_version 72640 (0.0004) [2023-03-07 23:49:02,108][286389] Updated weights for policy 0, policy_version 72720 (0.0005) [2023-03-07 23:49:02,816][286098] Fps is (10 sec: 12288.0, 60 sec: 11878.4, 300 sec: 11579.9). Total num frames: 37240832. Throughput: 0: 11902.2. Samples: 37232068. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:49:02,816][286098] Avg episode reward: [(0, '4525.924')] [2023-03-07 23:49:05,495][286389] Updated weights for policy 0, policy_version 72800 (0.0005) [2023-03-07 23:49:07,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11946.7, 300 sec: 11593.8). Total num frames: 37298176. Throughput: 0: 11907.0. Samples: 37268808. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:49:07,816][286098] Avg episode reward: [(0, '4551.531')] [2023-03-07 23:49:08,854][286389] Updated weights for policy 0, policy_version 72880 (0.0004) [2023-03-07 23:49:12,116][286389] Updated weights for policy 0, policy_version 72960 (0.0004) [2023-03-07 23:49:12,816][286098] Fps is (10 sec: 12288.0, 60 sec: 12014.9, 300 sec: 11621.5). Total num frames: 37363712. Throughput: 0: 11983.2. Samples: 37342624. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:49:12,817][286098] Avg episode reward: [(0, '4525.835')] [2023-03-07 23:49:12,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000072976_37363712.pth... [2023-03-07 23:49:12,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000072272_37003264.pth [2023-03-07 23:49:15,632][286389] Updated weights for policy 0, policy_version 73040 (0.0005) [2023-03-07 23:49:17,816][286098] Fps is (10 sec: 11878.5, 60 sec: 11878.4, 300 sec: 11621.5). Total num frames: 37416960. Throughput: 0: 11951.4. Samples: 37412864. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:49:17,816][286098] Avg episode reward: [(0, '4538.920')] [2023-03-07 23:49:19,293][286389] Updated weights for policy 0, policy_version 73120 (0.0005) [2023-03-07 23:49:22,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11810.1, 300 sec: 11621.5). Total num frames: 37474304. Throughput: 0: 11859.6. Samples: 37445736. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:49:22,817][286098] Avg episode reward: [(0, '4528.650')] [2023-03-07 23:49:22,904][286389] Updated weights for policy 0, policy_version 73200 (0.0005) [2023-03-07 23:49:26,209][286389] Updated weights for policy 0, policy_version 73280 (0.0004) [2023-03-07 23:49:27,816][286098] Fps is (10 sec: 11878.3, 60 sec: 11878.4, 300 sec: 11649.3). Total num frames: 37535744. Throughput: 0: 11859.9. Samples: 37517584. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:49:27,816][286098] Avg episode reward: [(0, '4521.411')] [2023-03-07 23:49:27,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000073312_37535744.pth... [2023-03-07 23:49:27,821][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000072616_37179392.pth [2023-03-07 23:49:29,595][286389] Updated weights for policy 0, policy_version 73360 (0.0005) [2023-03-07 23:49:32,816][286098] Fps is (10 sec: 12288.1, 60 sec: 11946.7, 300 sec: 11663.2). Total num frames: 37597184. Throughput: 0: 11913.0. Samples: 37590068. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:49:32,816][286098] Avg episode reward: [(0, '4527.655')] [2023-03-07 23:49:32,963][286389] Updated weights for policy 0, policy_version 73440 (0.0005) [2023-03-07 23:49:36,234][286389] Updated weights for policy 0, policy_version 73520 (0.0004) [2023-03-07 23:49:37,816][286098] Fps is (10 sec: 12288.0, 60 sec: 11946.7, 300 sec: 11691.0). Total num frames: 37658624. Throughput: 0: 11997.9. Samples: 37627928. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:49:37,816][286098] Avg episode reward: [(0, '4504.073')] [2023-03-07 23:49:39,595][286389] Updated weights for policy 0, policy_version 73600 (0.0004) [2023-03-07 23:49:42,816][286098] Fps is (10 sec: 12287.9, 60 sec: 11946.7, 300 sec: 11704.8). Total num frames: 37720064. Throughput: 0: 12041.2. Samples: 37700448. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:49:42,817][286098] Avg episode reward: [(0, '4505.308')] [2023-03-07 23:49:42,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000073672_37720064.pth... [2023-03-07 23:49:42,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000072976_37363712.pth [2023-03-07 23:49:42,933][286389] Updated weights for policy 0, policy_version 73680 (0.0004) [2023-03-07 23:49:46,236][286389] Updated weights for policy 0, policy_version 73760 (0.0004) [2023-03-07 23:49:47,816][286098] Fps is (10 sec: 12288.0, 60 sec: 12014.9, 300 sec: 11718.7). Total num frames: 37781504. Throughput: 0: 12073.1. Samples: 37775356. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-07 23:49:47,816][286098] Avg episode reward: [(0, '4535.273')] [2023-03-07 23:49:49,536][286389] Updated weights for policy 0, policy_version 73840 (0.0004) [2023-03-07 23:49:52,803][286389] Updated weights for policy 0, policy_version 73920 (0.0003) [2023-03-07 23:49:52,816][286098] Fps is (10 sec: 12697.6, 60 sec: 12151.5, 300 sec: 11746.5). Total num frames: 37847040. Throughput: 0: 12078.6. Samples: 37812344. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-07 23:49:52,817][286098] Avg episode reward: [(0, '4542.137')] [2023-03-07 23:49:56,084][286389] Updated weights for policy 0, policy_version 74000 (0.0004) [2023-03-07 23:49:57,816][286098] Fps is (10 sec: 12697.5, 60 sec: 12151.5, 300 sec: 11760.4). Total num frames: 37908480. Throughput: 0: 12119.5. Samples: 37888000. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-07 23:49:57,816][286098] Avg episode reward: [(0, '4559.551')] [2023-03-07 23:49:57,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000074040_37908480.pth... [2023-03-07 23:49:57,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000073312_37535744.pth [2023-03-07 23:49:59,365][286389] Updated weights for policy 0, policy_version 74080 (0.0004) [2023-03-07 23:50:02,632][286389] Updated weights for policy 0, policy_version 74160 (0.0003) [2023-03-07 23:50:02,816][286098] Fps is (10 sec: 12288.0, 60 sec: 12151.5, 300 sec: 11760.4). Total num frames: 37969920. Throughput: 0: 12222.6. Samples: 37962880. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-07 23:50:02,816][286098] Avg episode reward: [(0, '4536.606')] [2023-03-07 23:50:05,939][286389] Updated weights for policy 0, policy_version 74240 (0.0004) [2023-03-07 23:50:07,816][286098] Fps is (10 sec: 12288.0, 60 sec: 12219.7, 300 sec: 11788.1). Total num frames: 38031360. Throughput: 0: 12310.9. Samples: 37999728. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-07 23:50:07,816][286098] Avg episode reward: [(0, '4539.948')] [2023-03-07 23:50:09,299][286389] Updated weights for policy 0, policy_version 74320 (0.0004) [2023-03-07 23:50:12,639][286389] Updated weights for policy 0, policy_version 74400 (0.0004) [2023-03-07 23:50:12,816][286098] Fps is (10 sec: 12288.0, 60 sec: 12151.5, 300 sec: 11802.0). Total num frames: 38092800. Throughput: 0: 12339.6. Samples: 38072864. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-07 23:50:12,816][286098] Avg episode reward: [(0, '4536.567')] [2023-03-07 23:50:12,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000074400_38092800.pth... [2023-03-07 23:50:12,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000073672_37720064.pth [2023-03-07 23:50:15,910][286389] Updated weights for policy 0, policy_version 74480 (0.0004) [2023-03-07 23:50:17,816][286098] Fps is (10 sec: 12288.1, 60 sec: 12288.0, 300 sec: 11815.9). Total num frames: 38154240. Throughput: 0: 12385.1. Samples: 38147396. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-07 23:50:17,816][286098] Avg episode reward: [(0, '4540.220')] [2023-03-07 23:50:19,215][286389] Updated weights for policy 0, policy_version 74560 (0.0004) [2023-03-07 23:50:22,536][286389] Updated weights for policy 0, policy_version 74640 (0.0004) [2023-03-07 23:50:22,816][286098] Fps is (10 sec: 12288.1, 60 sec: 12356.3, 300 sec: 11843.7). Total num frames: 38215680. Throughput: 0: 12374.1. Samples: 38184760. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-07 23:50:22,816][286098] Avg episode reward: [(0, '4518.500')] [2023-03-07 23:50:25,879][286389] Updated weights for policy 0, policy_version 74720 (0.0004) [2023-03-07 23:50:27,816][286098] Fps is (10 sec: 12287.9, 60 sec: 12356.3, 300 sec: 11857.6). Total num frames: 38277120. Throughput: 0: 12412.5. Samples: 38259012. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-07 23:50:27,816][286098] Avg episode reward: [(0, '4533.652')] [2023-03-07 23:50:27,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000074760_38277120.pth... [2023-03-07 23:50:27,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000074040_37908480.pth [2023-03-07 23:50:29,507][286389] Updated weights for policy 0, policy_version 74800 (0.0005) [2023-03-07 23:50:32,816][286098] Fps is (10 sec: 11878.4, 60 sec: 12288.0, 300 sec: 11857.6). Total num frames: 38334464. Throughput: 0: 12244.2. Samples: 38326344. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:50:32,816][286098] Avg episode reward: [(0, '4495.436')] [2023-03-07 23:50:33,118][286389] Updated weights for policy 0, policy_version 74880 (0.0005) [2023-03-07 23:50:36,668][286389] Updated weights for policy 0, policy_version 74960 (0.0005) [2023-03-07 23:50:37,816][286098] Fps is (10 sec: 11468.8, 60 sec: 12219.7, 300 sec: 11871.5). Total num frames: 38391808. Throughput: 0: 12198.9. Samples: 38361292. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:50:37,816][286098] Avg episode reward: [(0, '4545.974')] [2023-03-07 23:50:40,291][286389] Updated weights for policy 0, policy_version 75040 (0.0005) [2023-03-07 23:50:42,816][286098] Fps is (10 sec: 11468.7, 60 sec: 12151.5, 300 sec: 11871.5). Total num frames: 38449152. Throughput: 0: 12020.3. Samples: 38428912. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:50:42,816][286098] Avg episode reward: [(0, '4552.203')] [2023-03-07 23:50:42,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000075096_38449152.pth... [2023-03-07 23:50:42,821][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000074400_38092800.pth [2023-03-07 23:50:43,898][286389] Updated weights for policy 0, policy_version 75120 (0.0005) [2023-03-07 23:50:47,490][286389] Updated weights for policy 0, policy_version 75200 (0.0005) [2023-03-07 23:50:47,816][286098] Fps is (10 sec: 11059.2, 60 sec: 12014.9, 300 sec: 11857.6). Total num frames: 38502400. Throughput: 0: 11890.2. Samples: 38497940. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:50:47,816][286098] Avg episode reward: [(0, '4547.581')] [2023-03-07 23:50:51,028][286389] Updated weights for policy 0, policy_version 75280 (0.0005) [2023-03-07 23:50:52,816][286098] Fps is (10 sec: 11059.3, 60 sec: 11878.4, 300 sec: 11857.6). Total num frames: 38559744. Throughput: 0: 11817.4. Samples: 38531512. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:50:52,827][286098] Avg episode reward: [(0, '4545.556')] [2023-03-07 23:50:54,642][286389] Updated weights for policy 0, policy_version 75360 (0.0005) [2023-03-07 23:50:57,816][286098] Fps is (10 sec: 11468.6, 60 sec: 11810.1, 300 sec: 11857.6). Total num frames: 38617088. Throughput: 0: 11731.4. Samples: 38600776. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:50:57,827][286098] Avg episode reward: [(0, '4548.530')] [2023-03-07 23:50:57,831][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000075432_38621184.pth... [2023-03-07 23:50:57,832][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000074760_38277120.pth [2023-03-07 23:50:58,214][286389] Updated weights for policy 0, policy_version 75440 (0.0005) [2023-03-07 23:51:01,682][286389] Updated weights for policy 0, policy_version 75520 (0.0005) [2023-03-07 23:51:02,816][286098] Fps is (10 sec: 11878.3, 60 sec: 11810.1, 300 sec: 11885.3). Total num frames: 38678528. Throughput: 0: 11623.9. Samples: 38670472. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:51:02,827][286098] Avg episode reward: [(0, '4557.712')] [2023-03-07 23:51:05,034][286389] Updated weights for policy 0, policy_version 75600 (0.0004) [2023-03-07 23:51:07,816][286098] Fps is (10 sec: 11878.5, 60 sec: 11741.9, 300 sec: 11871.5). Total num frames: 38735872. Throughput: 0: 11611.4. Samples: 38707272. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:51:07,827][286098] Avg episode reward: [(0, '4567.104')] [2023-03-07 23:51:08,582][286389] Updated weights for policy 0, policy_version 75680 (0.0005) [2023-03-07 23:51:12,162][286389] Updated weights for policy 0, policy_version 75760 (0.0005) [2023-03-07 23:51:12,816][286098] Fps is (10 sec: 11468.7, 60 sec: 11673.6, 300 sec: 11871.5). Total num frames: 38793216. Throughput: 0: 11502.7. Samples: 38776636. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:51:12,827][286098] Avg episode reward: [(0, '4558.130')] [2023-03-07 23:51:12,870][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000075776_38797312.pth... [2023-03-07 23:51:12,872][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000075096_38449152.pth [2023-03-07 23:51:15,658][286389] Updated weights for policy 0, policy_version 75840 (0.0005) [2023-03-07 23:51:17,816][286098] Fps is (10 sec: 11468.9, 60 sec: 11605.3, 300 sec: 11871.5). Total num frames: 38850560. Throughput: 0: 11558.2. Samples: 38846464. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:51:17,827][286098] Avg episode reward: [(0, '4553.150')] [2023-03-07 23:51:19,272][286389] Updated weights for policy 0, policy_version 75920 (0.0005) [2023-03-07 23:51:22,795][286389] Updated weights for policy 0, policy_version 76000 (0.0005) [2023-03-07 23:51:22,816][286098] Fps is (10 sec: 11878.5, 60 sec: 11605.3, 300 sec: 11885.3). Total num frames: 38912000. Throughput: 0: 11527.6. Samples: 38880032. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-07 23:51:22,827][286098] Avg episode reward: [(0, '4541.396')] [2023-03-07 23:51:26,341][286389] Updated weights for policy 0, policy_version 76080 (0.0005) [2023-03-07 23:51:27,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11537.1, 300 sec: 11885.3). Total num frames: 38969344. Throughput: 0: 11574.0. Samples: 38949740. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-07 23:51:27,827][286098] Avg episode reward: [(0, '4564.597')] [2023-03-07 23:51:27,830][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000076112_38969344.pth... [2023-03-07 23:51:27,832][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000075432_38621184.pth [2023-03-07 23:51:29,942][286389] Updated weights for policy 0, policy_version 76160 (0.0004) [2023-03-07 23:51:32,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11537.1, 300 sec: 11899.2). Total num frames: 39026688. Throughput: 0: 11568.1. Samples: 39018504. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-07 23:51:32,827][286098] Avg episode reward: [(0, '4548.577')] [2023-03-07 23:51:33,502][286389] Updated weights for policy 0, policy_version 76240 (0.0004) [2023-03-07 23:51:37,104][286389] Updated weights for policy 0, policy_version 76320 (0.0005) [2023-03-07 23:51:37,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11537.1, 300 sec: 11885.3). Total num frames: 39084032. Throughput: 0: 11568.4. Samples: 39052092. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-07 23:51:37,827][286098] Avg episode reward: [(0, '4494.530')] [2023-03-07 23:51:40,671][286389] Updated weights for policy 0, policy_version 76400 (0.0005) [2023-03-07 23:51:42,816][286098] Fps is (10 sec: 11059.1, 60 sec: 11468.8, 300 sec: 11857.6). Total num frames: 39137280. Throughput: 0: 11563.7. Samples: 39121144. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-07 23:51:42,827][286098] Avg episode reward: [(0, '4537.567')] [2023-03-07 23:51:42,830][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000076448_39141376.pth... [2023-03-07 23:51:42,832][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000075776_38797312.pth [2023-03-07 23:51:44,295][286389] Updated weights for policy 0, policy_version 76480 (0.0005) [2023-03-07 23:51:47,724][286389] Updated weights for policy 0, policy_version 76560 (0.0005) [2023-03-07 23:51:47,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11605.3, 300 sec: 11857.6). Total num frames: 39198720. Throughput: 0: 11558.4. Samples: 39190600. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-07 23:51:47,827][286098] Avg episode reward: [(0, '4496.635')] [2023-03-07 23:51:51,239][286389] Updated weights for policy 0, policy_version 76640 (0.0005) [2023-03-07 23:51:52,816][286098] Fps is (10 sec: 11878.5, 60 sec: 11605.3, 300 sec: 11843.7). Total num frames: 39256064. Throughput: 0: 11545.6. Samples: 39226824. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-07 23:51:52,827][286098] Avg episode reward: [(0, '4526.957')] [2023-03-07 23:51:54,779][286389] Updated weights for policy 0, policy_version 76720 (0.0005) [2023-03-07 23:51:57,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11605.3, 300 sec: 11829.8). Total num frames: 39313408. Throughput: 0: 11520.1. Samples: 39295040. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-07 23:51:57,827][286098] Avg episode reward: [(0, '4528.694')] [2023-03-07 23:51:57,830][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000076784_39313408.pth... [2023-03-07 23:51:57,833][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000076112_38969344.pth [2023-03-07 23:51:58,377][286389] Updated weights for policy 0, policy_version 76800 (0.0005) [2023-03-07 23:52:01,936][286389] Updated weights for policy 0, policy_version 76880 (0.0005) [2023-03-07 23:52:02,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11537.1, 300 sec: 11815.9). Total num frames: 39370752. Throughput: 0: 11496.5. Samples: 39363808. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-07 23:52:02,816][286098] Avg episode reward: [(0, '4482.358')] [2023-03-07 23:52:05,543][286389] Updated weights for policy 0, policy_version 76960 (0.0005) [2023-03-07 23:52:07,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11537.1, 300 sec: 11815.9). Total num frames: 39428096. Throughput: 0: 11525.7. Samples: 39398688. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-07 23:52:07,816][286098] Avg episode reward: [(0, '4498.905')] [2023-03-07 23:52:09,039][286389] Updated weights for policy 0, policy_version 77040 (0.0005) [2023-03-07 23:52:12,611][286389] Updated weights for policy 0, policy_version 77120 (0.0005) [2023-03-07 23:52:12,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11537.1, 300 sec: 11802.0). Total num frames: 39485440. Throughput: 0: 11521.4. Samples: 39468204. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-07 23:52:12,817][286098] Avg episode reward: [(0, '4418.371')] [2023-03-07 23:52:12,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000077120_39485440.pth... [2023-03-07 23:52:12,823][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000076448_39141376.pth [2023-03-07 23:52:16,200][286389] Updated weights for policy 0, policy_version 77200 (0.0005) [2023-03-07 23:52:17,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11537.1, 300 sec: 11802.0). Total num frames: 39542784. Throughput: 0: 11511.8. Samples: 39536536. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-07 23:52:17,816][286098] Avg episode reward: [(0, '4539.689')] [2023-03-07 23:52:19,677][286389] Updated weights for policy 0, policy_version 77280 (0.0005) [2023-03-07 23:52:22,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11468.8, 300 sec: 11802.0). Total num frames: 39600128. Throughput: 0: 11542.8. Samples: 39571520. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-07 23:52:22,816][286098] Avg episode reward: [(0, '4407.381')] [2023-03-07 23:52:23,242][286389] Updated weights for policy 0, policy_version 77360 (0.0005) [2023-03-07 23:52:26,754][286389] Updated weights for policy 0, policy_version 77440 (0.0005) [2023-03-07 23:52:27,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11537.1, 300 sec: 11829.8). Total num frames: 39661568. Throughput: 0: 11554.5. Samples: 39641096. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-07 23:52:27,816][286098] Avg episode reward: [(0, '4525.027')] [2023-03-07 23:52:27,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000077464_39661568.pth... [2023-03-07 23:52:27,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000076784_39313408.pth [2023-03-07 23:52:30,022][286389] Updated weights for policy 0, policy_version 77520 (0.0004) [2023-03-07 23:52:32,816][286098] Fps is (10 sec: 12288.0, 60 sec: 11605.3, 300 sec: 11843.7). Total num frames: 39723008. Throughput: 0: 11664.0. Samples: 39715480. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-07 23:52:32,816][286098] Avg episode reward: [(0, '4507.003')] [2023-03-07 23:52:33,331][286389] Updated weights for policy 0, policy_version 77600 (0.0004) [2023-03-07 23:52:36,576][286389] Updated weights for policy 0, policy_version 77680 (0.0004) [2023-03-07 23:52:37,816][286098] Fps is (10 sec: 12288.0, 60 sec: 11673.6, 300 sec: 11857.6). Total num frames: 39784448. Throughput: 0: 11694.7. Samples: 39753084. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-07 23:52:37,816][286098] Avg episode reward: [(0, '4466.260')] [2023-03-07 23:52:39,720][286389] Updated weights for policy 0, policy_version 77760 (0.0003) [2023-03-07 23:52:42,816][286098] Fps is (10 sec: 12697.6, 60 sec: 11878.4, 300 sec: 11871.5). Total num frames: 39849984. Throughput: 0: 11878.4. Samples: 39829568. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-07 23:52:42,816][286098] Avg episode reward: [(0, '4497.351')] [2023-03-07 23:52:42,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000077832_39849984.pth... [2023-03-07 23:52:42,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000077120_39485440.pth [2023-03-07 23:52:42,995][286389] Updated weights for policy 0, policy_version 77840 (0.0004) [2023-03-07 23:52:46,288][286389] Updated weights for policy 0, policy_version 77920 (0.0004) [2023-03-07 23:52:47,816][286098] Fps is (10 sec: 12697.6, 60 sec: 11878.4, 300 sec: 11885.3). Total num frames: 39911424. Throughput: 0: 12026.8. Samples: 39905012. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-07 23:52:47,816][286098] Avg episode reward: [(0, '4225.152')] [2023-03-07 23:52:49,496][286389] Updated weights for policy 0, policy_version 78000 (0.0004) [2023-03-07 23:52:52,688][286389] Updated weights for policy 0, policy_version 78080 (0.0003) [2023-03-07 23:52:52,816][286098] Fps is (10 sec: 12697.6, 60 sec: 12014.9, 300 sec: 11899.2). Total num frames: 39976960. Throughput: 0: 12102.8. Samples: 39943312. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-07 23:52:52,816][286098] Avg episode reward: [(0, '3624.035')] [2023-03-07 23:52:55,926][286389] Updated weights for policy 0, policy_version 78160 (0.0004) [2023-03-07 23:52:57,816][286098] Fps is (10 sec: 12697.6, 60 sec: 12083.2, 300 sec: 11899.2). Total num frames: 40038400. Throughput: 0: 12252.8. Samples: 40019580. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-07 23:52:57,816][286098] Avg episode reward: [(0, '4476.873')] [2023-03-07 23:52:57,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000078200_40038400.pth... [2023-03-07 23:52:57,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000077464_39661568.pth [2023-03-07 23:52:59,191][286389] Updated weights for policy 0, policy_version 78240 (0.0004) [2023-03-07 23:53:02,499][286389] Updated weights for policy 0, policy_version 78320 (0.0004) [2023-03-07 23:53:02,816][286098] Fps is (10 sec: 12697.6, 60 sec: 12219.7, 300 sec: 11940.9). Total num frames: 40103936. Throughput: 0: 12408.6. Samples: 40094924. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-07 23:53:02,816][286098] Avg episode reward: [(0, '4380.583')] [2023-03-07 23:53:05,658][286389] Updated weights for policy 0, policy_version 78400 (0.0003) [2023-03-07 23:53:07,816][286098] Fps is (10 sec: 12697.6, 60 sec: 12288.0, 300 sec: 11940.9). Total num frames: 40165376. Throughput: 0: 12470.2. Samples: 40132680. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-07 23:53:07,816][286098] Avg episode reward: [(0, '4466.851')] [2023-03-07 23:53:08,934][286389] Updated weights for policy 0, policy_version 78480 (0.0004) [2023-03-07 23:53:12,200][286389] Updated weights for policy 0, policy_version 78560 (0.0004) [2023-03-07 23:53:12,816][286098] Fps is (10 sec: 12288.0, 60 sec: 12356.3, 300 sec: 11940.9). Total num frames: 40226816. Throughput: 0: 12610.6. Samples: 40208572. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-07 23:53:12,817][286098] Avg episode reward: [(0, '4482.814')] [2023-03-07 23:53:12,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000078568_40226816.pth... [2023-03-07 23:53:12,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000077832_39849984.pth [2023-03-07 23:53:15,550][286389] Updated weights for policy 0, policy_version 78640 (0.0004) [2023-03-07 23:53:17,816][286098] Fps is (10 sec: 12288.0, 60 sec: 12424.5, 300 sec: 11940.9). Total num frames: 40288256. Throughput: 0: 12595.6. Samples: 40282284. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-07 23:53:17,816][286098] Avg episode reward: [(0, '4455.224')] [2023-03-07 23:53:18,902][286389] Updated weights for policy 0, policy_version 78720 (0.0004) [2023-03-07 23:53:22,174][286389] Updated weights for policy 0, policy_version 78800 (0.0004) [2023-03-07 23:53:22,816][286098] Fps is (10 sec: 12697.6, 60 sec: 12561.1, 300 sec: 11968.6). Total num frames: 40353792. Throughput: 0: 12595.6. Samples: 40319888. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-07 23:53:22,827][286098] Avg episode reward: [(0, '4423.219')] [2023-03-07 23:53:25,434][286389] Updated weights for policy 0, policy_version 78880 (0.0004) [2023-03-07 23:53:27,816][286098] Fps is (10 sec: 12697.6, 60 sec: 12561.1, 300 sec: 11982.5). Total num frames: 40415232. Throughput: 0: 12559.6. Samples: 40394752. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-07 23:53:27,827][286098] Avg episode reward: [(0, '4483.447')] [2023-03-07 23:53:27,831][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000078936_40415232.pth... [2023-03-07 23:53:27,833][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000078200_40038400.pth [2023-03-07 23:53:28,755][286389] Updated weights for policy 0, policy_version 78960 (0.0004) [2023-03-07 23:53:32,070][286389] Updated weights for policy 0, policy_version 79040 (0.0004) [2023-03-07 23:53:32,413][286341] Early stopping after 2 epochs (8 sgd steps), loss delta 0.0000007 [2023-03-07 23:53:32,816][286098] Fps is (10 sec: 12288.0, 60 sec: 12561.1, 300 sec: 11982.5). Total num frames: 40476672. Throughput: 0: 12521.7. Samples: 40468488. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-07 23:53:32,827][286098] Avg episode reward: [(0, '4465.363')] [2023-03-07 23:53:35,408][286389] Updated weights for policy 0, policy_version 79120 (0.0004) [2023-03-07 23:53:37,816][286098] Fps is (10 sec: 12288.0, 60 sec: 12561.1, 300 sec: 11982.5). Total num frames: 40538112. Throughput: 0: 12488.5. Samples: 40505296. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-07 23:53:37,827][286098] Avg episode reward: [(0, '4512.367')] [2023-03-07 23:53:38,775][286389] Updated weights for policy 0, policy_version 79200 (0.0004) [2023-03-07 23:53:42,053][286389] Updated weights for policy 0, policy_version 79280 (0.0003) [2023-03-07 23:53:42,816][286098] Fps is (10 sec: 12288.0, 60 sec: 12492.8, 300 sec: 11996.4). Total num frames: 40599552. Throughput: 0: 12433.3. Samples: 40579080. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:53:42,827][286098] Avg episode reward: [(0, '4516.185')] [2023-03-07 23:53:42,831][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000079296_40599552.pth... [2023-03-07 23:53:42,833][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000078568_40226816.pth [2023-03-07 23:53:45,364][286389] Updated weights for policy 0, policy_version 79360 (0.0004) [2023-03-07 23:53:47,816][286098] Fps is (10 sec: 12288.0, 60 sec: 12492.8, 300 sec: 12010.3). Total num frames: 40660992. Throughput: 0: 12411.3. Samples: 40653432. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:53:47,827][286098] Avg episode reward: [(0, '4503.330')] [2023-03-07 23:53:48,676][286389] Updated weights for policy 0, policy_version 79440 (0.0004) [2023-03-07 23:53:51,952][286389] Updated weights for policy 0, policy_version 79520 (0.0003) [2023-03-07 23:53:52,816][286098] Fps is (10 sec: 12288.0, 60 sec: 12424.5, 300 sec: 12010.3). Total num frames: 40722432. Throughput: 0: 12387.9. Samples: 40690136. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:53:52,816][286098] Avg episode reward: [(0, '4490.808')] [2023-03-07 23:53:55,220][286389] Updated weights for policy 0, policy_version 79600 (0.0003) [2023-03-07 23:53:57,816][286098] Fps is (10 sec: 12287.9, 60 sec: 12424.5, 300 sec: 12010.3). Total num frames: 40783872. Throughput: 0: 12383.5. Samples: 40765828. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:53:57,827][286098] Avg episode reward: [(0, '4515.381')] [2023-03-07 23:53:57,830][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000079656_40783872.pth... [2023-03-07 23:53:57,832][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000078936_40415232.pth [2023-03-07 23:53:58,577][286389] Updated weights for policy 0, policy_version 79680 (0.0004) [2023-03-07 23:54:01,911][286389] Updated weights for policy 0, policy_version 79760 (0.0004) [2023-03-07 23:54:02,816][286098] Fps is (10 sec: 12288.1, 60 sec: 12356.3, 300 sec: 12024.2). Total num frames: 40845312. Throughput: 0: 12370.5. Samples: 40838956. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:54:02,827][286098] Avg episode reward: [(0, '4518.002')] [2023-03-07 23:54:05,260][286389] Updated weights for policy 0, policy_version 79840 (0.0004) [2023-03-07 23:54:07,816][286098] Fps is (10 sec: 12288.1, 60 sec: 12356.3, 300 sec: 12010.3). Total num frames: 40906752. Throughput: 0: 12344.6. Samples: 40875392. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:54:07,816][286098] Avg episode reward: [(0, '4484.296')] [2023-03-07 23:54:08,612][286389] Updated weights for policy 0, policy_version 79920 (0.0004) [2023-03-07 23:54:11,959][286389] Updated weights for policy 0, policy_version 80000 (0.0004) [2023-03-07 23:54:12,816][286098] Fps is (10 sec: 12287.9, 60 sec: 12356.3, 300 sec: 12038.1). Total num frames: 40968192. Throughput: 0: 12307.6. Samples: 40948592. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:54:12,827][286098] Avg episode reward: [(0, '4519.335')] [2023-03-07 23:54:12,830][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000080016_40968192.pth... [2023-03-07 23:54:12,832][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000079296_40599552.pth [2023-03-07 23:54:15,292][286389] Updated weights for policy 0, policy_version 80080 (0.0004) [2023-03-07 23:54:17,816][286098] Fps is (10 sec: 12288.0, 60 sec: 12356.3, 300 sec: 12052.0). Total num frames: 41029632. Throughput: 0: 12300.2. Samples: 41021996. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:54:17,827][286098] Avg episode reward: [(0, '4514.173')] [2023-03-07 23:54:18,601][286389] Updated weights for policy 0, policy_version 80160 (0.0003) [2023-03-07 23:54:21,956][286389] Updated weights for policy 0, policy_version 80240 (0.0004) [2023-03-07 23:54:22,816][286098] Fps is (10 sec: 12288.0, 60 sec: 12288.0, 300 sec: 12052.0). Total num frames: 41091072. Throughput: 0: 12312.6. Samples: 41059364. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:54:22,821][286098] Avg episode reward: [(0, '4515.056')] [2023-03-07 23:54:25,243][286389] Updated weights for policy 0, policy_version 80320 (0.0003) [2023-03-07 23:54:27,816][286098] Fps is (10 sec: 12287.9, 60 sec: 12288.0, 300 sec: 12052.0). Total num frames: 41152512. Throughput: 0: 12320.5. Samples: 41133504. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:54:27,827][286098] Avg episode reward: [(0, '4509.750')] [2023-03-07 23:54:27,830][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000080376_41152512.pth... [2023-03-07 23:54:27,833][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000079656_40783872.pth [2023-03-07 23:54:28,589][286389] Updated weights for policy 0, policy_version 80400 (0.0004) [2023-03-07 23:54:31,901][286389] Updated weights for policy 0, policy_version 80480 (0.0003) [2023-03-07 23:54:32,816][286098] Fps is (10 sec: 12288.0, 60 sec: 12288.0, 300 sec: 12052.0). Total num frames: 41213952. Throughput: 0: 12317.9. Samples: 41207736. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:54:32,827][286098] Avg episode reward: [(0, '4445.216')] [2023-03-07 23:54:35,283][286389] Updated weights for policy 0, policy_version 80560 (0.0004) [2023-03-07 23:54:37,816][286098] Fps is (10 sec: 12288.1, 60 sec: 12288.0, 300 sec: 12052.0). Total num frames: 41275392. Throughput: 0: 12306.4. Samples: 41243924. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:54:37,827][286098] Avg episode reward: [(0, '4096.419')] [2023-03-07 23:54:38,647][286389] Updated weights for policy 0, policy_version 80640 (0.0004) [2023-03-07 23:54:42,087][286389] Updated weights for policy 0, policy_version 80720 (0.0004) [2023-03-07 23:54:42,816][286098] Fps is (10 sec: 12287.9, 60 sec: 12288.0, 300 sec: 12052.0). Total num frames: 41336832. Throughput: 0: 12235.3. Samples: 41316416. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:54:42,827][286098] Avg episode reward: [(0, '4255.750')] [2023-03-07 23:54:42,831][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000080736_41336832.pth... [2023-03-07 23:54:42,833][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000080016_40968192.pth [2023-03-07 23:54:45,464][286389] Updated weights for policy 0, policy_version 80800 (0.0004) [2023-03-07 23:54:47,816][286098] Fps is (10 sec: 11878.3, 60 sec: 12219.7, 300 sec: 12024.2). Total num frames: 41394176. Throughput: 0: 12216.7. Samples: 41388708. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:54:47,827][286098] Avg episode reward: [(0, '4347.883')] [2023-03-07 23:54:48,857][286389] Updated weights for policy 0, policy_version 80880 (0.0004) [2023-03-07 23:54:52,332][286389] Updated weights for policy 0, policy_version 80960 (0.0005) [2023-03-07 23:54:52,816][286098] Fps is (10 sec: 11878.4, 60 sec: 12219.7, 300 sec: 12024.2). Total num frames: 41455616. Throughput: 0: 12211.0. Samples: 41424888. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:54:52,827][286098] Avg episode reward: [(0, '4360.375')] [2023-03-07 23:54:55,603][286389] Updated weights for policy 0, policy_version 81040 (0.0004) [2023-03-07 23:54:57,816][286098] Fps is (10 sec: 12288.0, 60 sec: 12219.7, 300 sec: 12024.2). Total num frames: 41517056. Throughput: 0: 12205.6. Samples: 41497844. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:54:57,827][286098] Avg episode reward: [(0, '4511.950')] [2023-03-07 23:54:57,831][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000081088_41517056.pth... [2023-03-07 23:54:57,833][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000080376_41152512.pth [2023-03-07 23:54:58,880][286389] Updated weights for policy 0, policy_version 81120 (0.0003) [2023-03-07 23:55:02,135][286389] Updated weights for policy 0, policy_version 81200 (0.0003) [2023-03-07 23:55:02,816][286098] Fps is (10 sec: 12697.7, 60 sec: 12288.0, 300 sec: 12038.1). Total num frames: 41582592. Throughput: 0: 12255.8. Samples: 41573508. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:55:02,827][286098] Avg episode reward: [(0, '4507.070')] [2023-03-07 23:55:05,450][286389] Updated weights for policy 0, policy_version 81280 (0.0003) [2023-03-07 23:55:07,816][286098] Fps is (10 sec: 12697.7, 60 sec: 12288.0, 300 sec: 12038.1). Total num frames: 41644032. Throughput: 0: 12259.5. Samples: 41611040. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:55:07,827][286098] Avg episode reward: [(0, '4525.045')] [2023-03-07 23:55:08,845][286389] Updated weights for policy 0, policy_version 81360 (0.0004) [2023-03-07 23:55:12,256][286389] Updated weights for policy 0, policy_version 81440 (0.0004) [2023-03-07 23:55:12,816][286098] Fps is (10 sec: 11878.4, 60 sec: 12219.7, 300 sec: 12024.2). Total num frames: 41701376. Throughput: 0: 12215.5. Samples: 41683200. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:55:12,827][286098] Avg episode reward: [(0, '4487.557')] [2023-03-07 23:55:12,830][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000081448_41701376.pth... [2023-03-07 23:55:12,832][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000080736_41336832.pth [2023-03-07 23:55:15,626][286389] Updated weights for policy 0, policy_version 81520 (0.0003) [2023-03-07 23:55:17,816][286098] Fps is (10 sec: 11878.4, 60 sec: 12219.7, 300 sec: 12024.2). Total num frames: 41762816. Throughput: 0: 12181.6. Samples: 41755908. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:55:17,827][286098] Avg episode reward: [(0, '4496.322')] [2023-03-07 23:55:18,946][286389] Updated weights for policy 0, policy_version 81600 (0.0004) [2023-03-07 23:55:22,538][286389] Updated weights for policy 0, policy_version 81680 (0.0005) [2023-03-07 23:55:22,816][286098] Fps is (10 sec: 11878.4, 60 sec: 12151.5, 300 sec: 12010.3). Total num frames: 41820160. Throughput: 0: 12178.9. Samples: 41791972. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-07 23:55:22,827][286098] Avg episode reward: [(0, '4486.808')] [2023-03-07 23:55:26,212][286389] Updated weights for policy 0, policy_version 81760 (0.0004) [2023-03-07 23:55:27,816][286098] Fps is (10 sec: 11468.8, 60 sec: 12083.2, 300 sec: 12010.3). Total num frames: 41877504. Throughput: 0: 12074.1. Samples: 41859752. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-07 23:55:27,827][286098] Avg episode reward: [(0, '4508.835')] [2023-03-07 23:55:27,831][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000081792_41877504.pth... [2023-03-07 23:55:27,833][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000081088_41517056.pth [2023-03-07 23:55:29,826][286389] Updated weights for policy 0, policy_version 81840 (0.0005) [2023-03-07 23:55:32,816][286098] Fps is (10 sec: 11468.8, 60 sec: 12014.9, 300 sec: 12010.3). Total num frames: 41934848. Throughput: 0: 11956.0. Samples: 41926728. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-07 23:55:32,816][286098] Avg episode reward: [(0, '4499.892')] [2023-03-07 23:55:33,510][286389] Updated weights for policy 0, policy_version 81920 (0.0005) [2023-03-07 23:55:37,163][286389] Updated weights for policy 0, policy_version 82000 (0.0005) [2023-03-07 23:55:37,816][286098] Fps is (10 sec: 11059.1, 60 sec: 11878.4, 300 sec: 11996.4). Total num frames: 41988096. Throughput: 0: 11889.7. Samples: 41959924. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-07 23:55:37,817][286098] Avg episode reward: [(0, '4498.584')] [2023-03-07 23:55:40,746][286389] Updated weights for policy 0, policy_version 82080 (0.0004) [2023-03-07 23:55:42,816][286098] Fps is (10 sec: 11059.1, 60 sec: 11810.1, 300 sec: 12010.3). Total num frames: 42045440. Throughput: 0: 11804.9. Samples: 42029064. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-07 23:55:42,816][286098] Avg episode reward: [(0, '4434.022')] [2023-03-07 23:55:42,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000082120_42045440.pth... [2023-03-07 23:55:42,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000081448_41701376.pth [2023-03-07 23:55:44,359][286389] Updated weights for policy 0, policy_version 82160 (0.0005) [2023-03-07 23:55:47,816][286098] Fps is (10 sec: 11469.0, 60 sec: 11810.1, 300 sec: 12010.3). Total num frames: 42102784. Throughput: 0: 11603.8. Samples: 42095680. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-07 23:55:47,816][286098] Avg episode reward: [(0, '4383.134')] [2023-03-07 23:55:48,014][286389] Updated weights for policy 0, policy_version 82240 (0.0005) [2023-03-07 23:55:51,595][286389] Updated weights for policy 0, policy_version 82320 (0.0005) [2023-03-07 23:55:52,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11741.9, 300 sec: 12010.3). Total num frames: 42160128. Throughput: 0: 11564.8. Samples: 42131456. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-07 23:55:52,827][286098] Avg episode reward: [(0, '4479.393')] [2023-03-07 23:55:55,114][286389] Updated weights for policy 0, policy_version 82400 (0.0005) [2023-03-07 23:55:57,816][286098] Fps is (10 sec: 11468.7, 60 sec: 11673.6, 300 sec: 11996.4). Total num frames: 42217472. Throughput: 0: 11473.6. Samples: 42199512. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-07 23:55:57,827][286098] Avg episode reward: [(0, '4491.370')] [2023-03-07 23:55:57,830][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000082456_42217472.pth... [2023-03-07 23:55:57,832][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000081792_41877504.pth [2023-03-07 23:55:58,824][286389] Updated weights for policy 0, policy_version 82480 (0.0005) [2023-03-07 23:56:02,418][286389] Updated weights for policy 0, policy_version 82560 (0.0005) [2023-03-07 23:56:02,816][286098] Fps is (10 sec: 11468.7, 60 sec: 11537.1, 300 sec: 11996.4). Total num frames: 42274816. Throughput: 0: 11350.6. Samples: 42266688. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-07 23:56:02,827][286098] Avg episode reward: [(0, '4516.788')] [2023-03-07 23:56:05,811][286389] Updated weights for policy 0, policy_version 82640 (0.0004) [2023-03-07 23:56:07,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11537.1, 300 sec: 12010.3). Total num frames: 42336256. Throughput: 0: 11358.7. Samples: 42303116. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-07 23:56:07,827][286098] Avg episode reward: [(0, '4457.165')] [2023-03-07 23:56:09,091][286389] Updated weights for policy 0, policy_version 82720 (0.0004) [2023-03-07 23:56:12,481][286389] Updated weights for policy 0, policy_version 82800 (0.0004) [2023-03-07 23:56:12,816][286098] Fps is (10 sec: 11878.5, 60 sec: 11537.1, 300 sec: 12010.3). Total num frames: 42393600. Throughput: 0: 11499.4. Samples: 42377224. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-07 23:56:12,827][286098] Avg episode reward: [(0, '4250.217')] [2023-03-07 23:56:12,855][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000082808_42397696.pth... [2023-03-07 23:56:12,857][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000082120_42045440.pth [2023-03-07 23:56:16,035][286389] Updated weights for policy 0, policy_version 82880 (0.0005) [2023-03-07 23:56:17,816][286098] Fps is (10 sec: 11468.9, 60 sec: 11468.8, 300 sec: 11996.4). Total num frames: 42450944. Throughput: 0: 11558.1. Samples: 42446844. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-07 23:56:17,827][286098] Avg episode reward: [(0, '4414.265')] [2023-03-07 23:56:19,687][286389] Updated weights for policy 0, policy_version 82960 (0.0005) [2023-03-07 23:56:22,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11468.8, 300 sec: 11996.4). Total num frames: 42508288. Throughput: 0: 11550.2. Samples: 42479680. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-07 23:56:22,827][286098] Avg episode reward: [(0, '4362.436')] [2023-03-07 23:56:23,226][286389] Updated weights for policy 0, policy_version 83040 (0.0005) [2023-03-07 23:56:26,828][286389] Updated weights for policy 0, policy_version 83120 (0.0005) [2023-03-07 23:56:27,816][286098] Fps is (10 sec: 11468.7, 60 sec: 11468.8, 300 sec: 11996.4). Total num frames: 42565632. Throughput: 0: 11559.8. Samples: 42549256. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-07 23:56:27,827][286098] Avg episode reward: [(0, '4438.734')] [2023-03-07 23:56:27,830][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000083136_42565632.pth... [2023-03-07 23:56:27,833][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000082456_42217472.pth [2023-03-07 23:56:30,467][286389] Updated weights for policy 0, policy_version 83200 (0.0005) [2023-03-07 23:56:32,816][286098] Fps is (10 sec: 11468.7, 60 sec: 11468.8, 300 sec: 11996.4). Total num frames: 42622976. Throughput: 0: 11558.9. Samples: 42615832. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-07 23:56:32,827][286098] Avg episode reward: [(0, '4381.541')] [2023-03-07 23:56:34,062][286389] Updated weights for policy 0, policy_version 83280 (0.0005) [2023-03-07 23:56:37,707][286389] Updated weights for policy 0, policy_version 83360 (0.0004) [2023-03-07 23:56:37,816][286098] Fps is (10 sec: 11468.9, 60 sec: 11537.1, 300 sec: 12010.3). Total num frames: 42680320. Throughput: 0: 11554.2. Samples: 42651396. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-07 23:56:37,827][286098] Avg episode reward: [(0, '4464.048')] [2023-03-07 23:56:41,314][286389] Updated weights for policy 0, policy_version 83440 (0.0004) [2023-03-07 23:56:42,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11537.1, 300 sec: 11996.4). Total num frames: 42737664. Throughput: 0: 11536.9. Samples: 42718672. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-07 23:56:42,827][286098] Avg episode reward: [(0, '4485.297')] [2023-03-07 23:56:42,830][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000083472_42737664.pth... [2023-03-07 23:56:42,832][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000082808_42397696.pth [2023-03-07 23:56:44,907][286389] Updated weights for policy 0, policy_version 83520 (0.0005) [2023-03-07 23:56:47,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11468.8, 300 sec: 11982.5). Total num frames: 42790912. Throughput: 0: 11551.8. Samples: 42786520. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-07 23:56:47,816][286098] Avg episode reward: [(0, '4481.927')] [2023-03-07 23:56:48,606][286389] Updated weights for policy 0, policy_version 83600 (0.0005) [2023-03-07 23:56:52,314][286389] Updated weights for policy 0, policy_version 83680 (0.0005) [2023-03-07 23:56:52,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11468.8, 300 sec: 11982.5). Total num frames: 42848256. Throughput: 0: 11477.3. Samples: 42819592. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-07 23:56:52,816][286098] Avg episode reward: [(0, '4472.284')] [2023-03-07 23:56:56,141][286389] Updated weights for policy 0, policy_version 83760 (0.0005) [2023-03-07 23:56:57,816][286098] Fps is (10 sec: 11059.1, 60 sec: 11400.5, 300 sec: 11968.6). Total num frames: 42901504. Throughput: 0: 11275.8. Samples: 42884636. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-07 23:56:57,817][286098] Avg episode reward: [(0, '4377.978')] [2023-03-07 23:56:57,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000083792_42901504.pth... [2023-03-07 23:56:57,823][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000083136_42565632.pth [2023-03-07 23:56:59,852][286389] Updated weights for policy 0, policy_version 83840 (0.0005) [2023-03-07 23:57:02,816][286098] Fps is (10 sec: 10649.6, 60 sec: 11332.3, 300 sec: 11954.8). Total num frames: 42954752. Throughput: 0: 11192.4. Samples: 42950504. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:57:02,816][286098] Avg episode reward: [(0, '4356.992')] [2023-03-07 23:57:03,674][286389] Updated weights for policy 0, policy_version 83920 (0.0005) [2023-03-07 23:57:07,417][286389] Updated weights for policy 0, policy_version 84000 (0.0005) [2023-03-07 23:57:07,816][286098] Fps is (10 sec: 11059.3, 60 sec: 11264.0, 300 sec: 11954.8). Total num frames: 43012096. Throughput: 0: 11178.2. Samples: 42982700. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:57:07,816][286098] Avg episode reward: [(0, '4345.670')] [2023-03-07 23:57:11,130][286389] Updated weights for policy 0, policy_version 84080 (0.0005) [2023-03-07 23:57:12,816][286098] Fps is (10 sec: 11059.1, 60 sec: 11195.7, 300 sec: 11940.9). Total num frames: 43065344. Throughput: 0: 11095.3. Samples: 43048544. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:57:12,816][286098] Avg episode reward: [(0, '4336.727')] [2023-03-07 23:57:12,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000084112_43065344.pth... [2023-03-07 23:57:12,823][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000083472_42737664.pth [2023-03-07 23:57:14,848][286389] Updated weights for policy 0, policy_version 84160 (0.0005) [2023-03-07 23:57:17,816][286098] Fps is (10 sec: 11059.1, 60 sec: 11195.7, 300 sec: 11940.9). Total num frames: 43122688. Throughput: 0: 11083.7. Samples: 43114600. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:57:17,816][286098] Avg episode reward: [(0, '4460.443')] [2023-03-07 23:57:18,544][286389] Updated weights for policy 0, policy_version 84240 (0.0005) [2023-03-07 23:57:22,286][286389] Updated weights for policy 0, policy_version 84320 (0.0005) [2023-03-07 23:57:22,816][286098] Fps is (10 sec: 11059.3, 60 sec: 11127.5, 300 sec: 11913.1). Total num frames: 43175936. Throughput: 0: 11023.7. Samples: 43147464. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:57:22,816][286098] Avg episode reward: [(0, '4495.162')] [2023-03-07 23:57:26,097][286389] Updated weights for policy 0, policy_version 84400 (0.0004) [2023-03-07 23:57:27,816][286098] Fps is (10 sec: 10649.6, 60 sec: 11059.2, 300 sec: 11885.3). Total num frames: 43229184. Throughput: 0: 10975.5. Samples: 43212572. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:57:27,816][286098] Avg episode reward: [(0, '4459.561')] [2023-03-07 23:57:27,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000084432_43229184.pth... [2023-03-07 23:57:27,823][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000083792_42901504.pth [2023-03-07 23:57:29,944][286389] Updated weights for policy 0, policy_version 84480 (0.0005) [2023-03-07 23:57:32,816][286098] Fps is (10 sec: 11059.1, 60 sec: 11059.2, 300 sec: 11871.5). Total num frames: 43286528. Throughput: 0: 10930.8. Samples: 43278408. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:57:32,816][286098] Avg episode reward: [(0, '4434.452')] [2023-03-07 23:57:33,476][286389] Updated weights for policy 0, policy_version 84560 (0.0003) [2023-03-07 23:57:37,138][286389] Updated weights for policy 0, policy_version 84640 (0.0004) [2023-03-07 23:57:37,816][286098] Fps is (10 sec: 11059.3, 60 sec: 10990.9, 300 sec: 11829.8). Total num frames: 43339776. Throughput: 0: 10942.7. Samples: 43312016. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:57:37,816][286098] Avg episode reward: [(0, '4492.382')] [2023-03-07 23:57:40,815][286389] Updated weights for policy 0, policy_version 84720 (0.0005) [2023-03-07 23:57:42,816][286098] Fps is (10 sec: 11059.2, 60 sec: 10990.9, 300 sec: 11815.9). Total num frames: 43397120. Throughput: 0: 11000.1. Samples: 43379640. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:57:42,816][286098] Avg episode reward: [(0, '4334.502')] [2023-03-07 23:57:42,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000084760_43397120.pth... [2023-03-07 23:57:42,823][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000084112_43065344.pth [2023-03-07 23:57:44,457][286389] Updated weights for policy 0, policy_version 84800 (0.0004) [2023-03-07 23:57:47,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11059.2, 300 sec: 11788.1). Total num frames: 43454464. Throughput: 0: 11021.2. Samples: 43446460. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:57:47,816][286098] Avg episode reward: [(0, '4357.319')] [2023-03-07 23:57:48,133][286389] Updated weights for policy 0, policy_version 84880 (0.0004) [2023-03-07 23:57:51,850][286389] Updated weights for policy 0, policy_version 84960 (0.0004) [2023-03-07 23:57:52,816][286098] Fps is (10 sec: 11059.3, 60 sec: 10990.9, 300 sec: 11760.4). Total num frames: 43507712. Throughput: 0: 11042.8. Samples: 43479628. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:57:52,816][286098] Avg episode reward: [(0, '4422.811')] [2023-03-07 23:57:55,564][286389] Updated weights for policy 0, policy_version 85040 (0.0005) [2023-03-07 23:57:57,816][286098] Fps is (10 sec: 10649.6, 60 sec: 10990.9, 300 sec: 11718.7). Total num frames: 43560960. Throughput: 0: 11054.4. Samples: 43545992. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:57:57,816][286098] Avg episode reward: [(0, '4398.967')] [2023-03-07 23:57:57,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000085080_43560960.pth... [2023-03-07 23:57:57,823][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000084432_43229184.pth [2023-03-07 23:57:59,549][286389] Updated weights for policy 0, policy_version 85120 (0.0004) [2023-03-07 23:58:02,816][286098] Fps is (10 sec: 10649.6, 60 sec: 10990.9, 300 sec: 11691.0). Total num frames: 43614208. Throughput: 0: 10964.2. Samples: 43607988. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:58:02,816][286098] Avg episode reward: [(0, '4474.735')] [2023-03-07 23:58:03,470][286389] Updated weights for policy 0, policy_version 85200 (0.0004) [2023-03-07 23:58:07,491][286389] Updated weights for policy 0, policy_version 85280 (0.0005) [2023-03-07 23:58:07,816][286098] Fps is (10 sec: 10240.1, 60 sec: 10854.4, 300 sec: 11649.3). Total num frames: 43663360. Throughput: 0: 10919.6. Samples: 43638848. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:58:07,816][286098] Avg episode reward: [(0, '4475.907')] [2023-03-07 23:58:11,551][286389] Updated weights for policy 0, policy_version 85360 (0.0005) [2023-03-07 23:58:12,816][286098] Fps is (10 sec: 10239.9, 60 sec: 10854.4, 300 sec: 11621.5). Total num frames: 43716608. Throughput: 0: 10829.9. Samples: 43699916. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:58:12,816][286098] Avg episode reward: [(0, '4468.662')] [2023-03-07 23:58:12,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000085384_43716608.pth... [2023-03-07 23:58:12,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000084760_43397120.pth [2023-03-07 23:58:15,514][286389] Updated weights for policy 0, policy_version 85440 (0.0005) [2023-03-07 23:58:17,816][286098] Fps is (10 sec: 10240.0, 60 sec: 10717.9, 300 sec: 11566.0). Total num frames: 43765760. Throughput: 0: 10739.2. Samples: 43761672. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:58:17,816][286098] Avg episode reward: [(0, '4428.725')] [2023-03-07 23:58:19,507][286389] Updated weights for policy 0, policy_version 85520 (0.0005) [2023-03-07 23:58:22,816][286098] Fps is (10 sec: 10240.0, 60 sec: 10717.9, 300 sec: 11538.2). Total num frames: 43819008. Throughput: 0: 10666.2. Samples: 43791996. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:58:22,816][286098] Avg episode reward: [(0, '4467.371')] [2023-03-07 23:58:23,437][286389] Updated weights for policy 0, policy_version 85600 (0.0005) [2023-03-07 23:58:27,136][286389] Updated weights for policy 0, policy_version 85680 (0.0004) [2023-03-07 23:58:27,816][286098] Fps is (10 sec: 10649.6, 60 sec: 10717.9, 300 sec: 11510.5). Total num frames: 43872256. Throughput: 0: 10584.4. Samples: 43855936. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:58:27,816][286098] Avg episode reward: [(0, '4413.004')] [2023-03-07 23:58:27,852][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000085696_43876352.pth... [2023-03-07 23:58:27,854][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000085080_43560960.pth [2023-03-07 23:58:30,736][286389] Updated weights for policy 0, policy_version 85760 (0.0004) [2023-03-07 23:58:32,816][286098] Fps is (10 sec: 11059.2, 60 sec: 10717.9, 300 sec: 11496.6). Total num frames: 43929600. Throughput: 0: 10622.5. Samples: 43924472. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:58:32,816][286098] Avg episode reward: [(0, '4456.203')] [2023-03-07 23:58:34,327][286389] Updated weights for policy 0, policy_version 85840 (0.0004) [2023-03-07 23:58:37,816][286098] Fps is (10 sec: 11468.8, 60 sec: 10786.1, 300 sec: 11482.7). Total num frames: 43986944. Throughput: 0: 10638.1. Samples: 43958344. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:58:37,816][286098] Avg episode reward: [(0, '4491.373')] [2023-03-07 23:58:37,945][286389] Updated weights for policy 0, policy_version 85920 (0.0005) [2023-03-07 23:58:41,532][286389] Updated weights for policy 0, policy_version 86000 (0.0005) [2023-03-07 23:58:42,816][286098] Fps is (10 sec: 11468.8, 60 sec: 10786.1, 300 sec: 11468.8). Total num frames: 44044288. Throughput: 0: 10681.0. Samples: 44026636. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:58:42,816][286098] Avg episode reward: [(0, '4531.587')] [2023-03-07 23:58:42,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000086024_44044288.pth... [2023-03-07 23:58:42,823][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000085384_43716608.pth [2023-03-07 23:58:45,287][286389] Updated weights for policy 0, policy_version 86080 (0.0005) [2023-03-07 23:58:47,816][286098] Fps is (10 sec: 11468.8, 60 sec: 10786.1, 300 sec: 11454.9). Total num frames: 44101632. Throughput: 0: 10788.2. Samples: 44093456. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:58:47,816][286098] Avg episode reward: [(0, '4517.903')] [2023-03-07 23:58:48,871][286389] Updated weights for policy 0, policy_version 86160 (0.0004) [2023-03-07 23:58:52,608][286389] Updated weights for policy 0, policy_version 86240 (0.0005) [2023-03-07 23:58:52,816][286098] Fps is (10 sec: 11059.3, 60 sec: 10786.1, 300 sec: 11427.2). Total num frames: 44154880. Throughput: 0: 10849.0. Samples: 44127052. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:58:52,816][286098] Avg episode reward: [(0, '4532.105')] [2023-03-07 23:58:56,495][286389] Updated weights for policy 0, policy_version 86320 (0.0005) [2023-03-07 23:58:57,816][286098] Fps is (10 sec: 10649.5, 60 sec: 10786.1, 300 sec: 11399.4). Total num frames: 44208128. Throughput: 0: 10929.5. Samples: 44191744. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:58:57,816][286098] Avg episode reward: [(0, '4529.665')] [2023-03-07 23:58:57,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000086344_44208128.pth... [2023-03-07 23:58:57,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000085696_43876352.pth [2023-03-07 23:59:00,044][286389] Updated weights for policy 0, policy_version 86400 (0.0005) [2023-03-07 23:59:02,816][286098] Fps is (10 sec: 11468.7, 60 sec: 10922.7, 300 sec: 11399.4). Total num frames: 44269568. Throughput: 0: 11105.9. Samples: 44261440. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:59:02,816][286098] Avg episode reward: [(0, '4522.326')] [2023-03-07 23:59:03,416][286389] Updated weights for policy 0, policy_version 86480 (0.0004) [2023-03-07 23:59:06,735][286389] Updated weights for policy 0, policy_version 86560 (0.0004) [2023-03-07 23:59:07,816][286098] Fps is (10 sec: 12288.1, 60 sec: 11127.5, 300 sec: 11399.4). Total num frames: 44331008. Throughput: 0: 11244.9. Samples: 44298016. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:59:07,816][286098] Avg episode reward: [(0, '4526.574')] [2023-03-07 23:59:10,066][286389] Updated weights for policy 0, policy_version 86640 (0.0004) [2023-03-07 23:59:12,816][286098] Fps is (10 sec: 12288.0, 60 sec: 11264.0, 300 sec: 11399.4). Total num frames: 44392448. Throughput: 0: 11468.8. Samples: 44372032. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:59:12,816][286098] Avg episode reward: [(0, '4524.013')] [2023-03-07 23:59:12,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000086704_44392448.pth... [2023-03-07 23:59:12,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000086024_44044288.pth [2023-03-07 23:59:13,407][286389] Updated weights for policy 0, policy_version 86720 (0.0005) [2023-03-07 23:59:16,746][286389] Updated weights for policy 0, policy_version 86800 (0.0004) [2023-03-07 23:59:17,816][286098] Fps is (10 sec: 12288.0, 60 sec: 11468.8, 300 sec: 11399.4). Total num frames: 44453888. Throughput: 0: 11582.8. Samples: 44445696. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:59:17,816][286098] Avg episode reward: [(0, '4524.455')] [2023-03-07 23:59:20,088][286389] Updated weights for policy 0, policy_version 86880 (0.0004) [2023-03-07 23:59:22,816][286098] Fps is (10 sec: 12288.0, 60 sec: 11605.3, 300 sec: 11399.4). Total num frames: 44515328. Throughput: 0: 11644.3. Samples: 44482336. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:59:22,816][286098] Avg episode reward: [(0, '4499.339')] [2023-03-07 23:59:23,435][286389] Updated weights for policy 0, policy_version 86960 (0.0005) [2023-03-07 23:59:26,746][286389] Updated weights for policy 0, policy_version 87040 (0.0005) [2023-03-07 23:59:27,816][286098] Fps is (10 sec: 12288.0, 60 sec: 11741.9, 300 sec: 11399.4). Total num frames: 44576768. Throughput: 0: 11770.2. Samples: 44556296. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:59:27,816][286098] Avg episode reward: [(0, '4498.026')] [2023-03-07 23:59:27,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000087064_44576768.pth... [2023-03-07 23:59:27,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000086344_44208128.pth [2023-03-07 23:59:30,129][286389] Updated weights for policy 0, policy_version 87120 (0.0005) [2023-03-07 23:59:32,816][286098] Fps is (10 sec: 12288.0, 60 sec: 11810.1, 300 sec: 11399.4). Total num frames: 44638208. Throughput: 0: 11910.1. Samples: 44629408. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:59:32,816][286098] Avg episode reward: [(0, '4520.990')] [2023-03-07 23:59:33,421][286389] Updated weights for policy 0, policy_version 87200 (0.0004) [2023-03-07 23:59:36,788][286389] Updated weights for policy 0, policy_version 87280 (0.0005) [2023-03-07 23:59:37,816][286098] Fps is (10 sec: 12287.9, 60 sec: 11878.4, 300 sec: 11399.4). Total num frames: 44699648. Throughput: 0: 11981.2. Samples: 44666208. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:59:37,816][286098] Avg episode reward: [(0, '4517.776')] [2023-03-07 23:59:40,180][286389] Updated weights for policy 0, policy_version 87360 (0.0005) [2023-03-07 23:59:42,816][286098] Fps is (10 sec: 11878.2, 60 sec: 11878.4, 300 sec: 11399.4). Total num frames: 44756992. Throughput: 0: 12172.3. Samples: 44739500. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:59:42,817][286098] Avg episode reward: [(0, '4495.310')] [2023-03-07 23:59:42,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000087416_44756992.pth... [2023-03-07 23:59:42,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000086704_44392448.pth [2023-03-07 23:59:43,732][286389] Updated weights for policy 0, policy_version 87440 (0.0005) [2023-03-07 23:59:47,280][286389] Updated weights for policy 0, policy_version 87520 (0.0005) [2023-03-07 23:59:47,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11878.4, 300 sec: 11385.5). Total num frames: 44814336. Throughput: 0: 12135.7. Samples: 44807548. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:59:47,816][286098] Avg episode reward: [(0, '4483.136')] [2023-03-07 23:59:50,922][286389] Updated weights for policy 0, policy_version 87600 (0.0005) [2023-03-07 23:59:52,816][286098] Fps is (10 sec: 11468.9, 60 sec: 11946.7, 300 sec: 11371.6). Total num frames: 44871680. Throughput: 0: 12083.6. Samples: 44841780. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:59:52,816][286098] Avg episode reward: [(0, '4501.251')] [2023-03-07 23:59:54,443][286389] Updated weights for policy 0, policy_version 87680 (0.0005) [2023-03-07 23:59:57,816][286098] Fps is (10 sec: 11468.7, 60 sec: 12014.9, 300 sec: 11343.8). Total num frames: 44929024. Throughput: 0: 11992.1. Samples: 44911676. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-07 23:59:57,816][286098] Avg episode reward: [(0, '4478.424')] [2023-03-07 23:59:57,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000087752_44929024.pth... [2023-03-07 23:59:57,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000087064_44576768.pth [2023-03-07 23:59:57,885][286389] Updated weights for policy 0, policy_version 87760 (0.0005) [2023-03-08 00:00:01,222][286389] Updated weights for policy 0, policy_version 87840 (0.0003) [2023-03-08 00:00:02,816][286098] Fps is (10 sec: 11878.4, 60 sec: 12014.9, 300 sec: 11343.8). Total num frames: 44990464. Throughput: 0: 11958.6. Samples: 44983832. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:00:02,816][286098] Avg episode reward: [(0, '4503.781')] [2023-03-08 00:00:04,579][286389] Updated weights for policy 0, policy_version 87920 (0.0003) [2023-03-08 00:00:07,816][286098] Fps is (10 sec: 11878.5, 60 sec: 11946.7, 300 sec: 11343.8). Total num frames: 45047808. Throughput: 0: 11958.9. Samples: 45020488. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:00:07,827][286098] Avg episode reward: [(0, '4487.272')] [2023-03-08 00:00:08,163][286389] Updated weights for policy 0, policy_version 88000 (0.0005) [2023-03-08 00:00:11,639][286389] Updated weights for policy 0, policy_version 88080 (0.0004) [2023-03-08 00:00:12,816][286098] Fps is (10 sec: 11878.3, 60 sec: 11946.7, 300 sec: 11343.8). Total num frames: 45109248. Throughput: 0: 11851.7. Samples: 45089624. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:00:12,827][286098] Avg episode reward: [(0, '4444.853')] [2023-03-08 00:00:12,830][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000088104_45109248.pth... [2023-03-08 00:00:12,833][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000087416_44756992.pth [2023-03-08 00:00:15,066][286389] Updated weights for policy 0, policy_version 88160 (0.0004) [2023-03-08 00:00:17,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11878.4, 300 sec: 11343.8). Total num frames: 45166592. Throughput: 0: 11798.0. Samples: 45160320. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:00:17,827][286098] Avg episode reward: [(0, '4514.875')] [2023-03-08 00:00:18,771][286389] Updated weights for policy 0, policy_version 88240 (0.0005) [2023-03-08 00:00:22,402][286389] Updated weights for policy 0, policy_version 88320 (0.0005) [2023-03-08 00:00:22,816][286098] Fps is (10 sec: 11468.9, 60 sec: 11810.1, 300 sec: 11343.8). Total num frames: 45223936. Throughput: 0: 11719.2. Samples: 45193572. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:00:22,816][286098] Avg episode reward: [(0, '4435.890')] [2023-03-08 00:00:26,080][286389] Updated weights for policy 0, policy_version 88400 (0.0005) [2023-03-08 00:00:27,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11673.6, 300 sec: 11329.9). Total num frames: 45277184. Throughput: 0: 11584.6. Samples: 45260808. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:00:27,816][286098] Avg episode reward: [(0, '4500.998')] [2023-03-08 00:00:27,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000088432_45277184.pth... [2023-03-08 00:00:27,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000087752_44929024.pth [2023-03-08 00:00:29,556][286389] Updated weights for policy 0, policy_version 88480 (0.0004) [2023-03-08 00:00:32,816][286098] Fps is (10 sec: 11468.7, 60 sec: 11673.6, 300 sec: 11357.7). Total num frames: 45338624. Throughput: 0: 11650.7. Samples: 45331828. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 00:00:32,817][286098] Avg episode reward: [(0, '4505.806')] [2023-03-08 00:00:32,991][286389] Updated weights for policy 0, policy_version 88560 (0.0004) [2023-03-08 00:00:36,471][286389] Updated weights for policy 0, policy_version 88640 (0.0004) [2023-03-08 00:00:37,816][286098] Fps is (10 sec: 11878.5, 60 sec: 11605.3, 300 sec: 11357.7). Total num frames: 45395968. Throughput: 0: 11679.7. Samples: 45367368. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 00:00:37,816][286098] Avg episode reward: [(0, '4460.359')] [2023-03-08 00:00:40,150][286389] Updated weights for policy 0, policy_version 88720 (0.0005) [2023-03-08 00:00:42,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11605.3, 300 sec: 11357.7). Total num frames: 45453312. Throughput: 0: 11639.2. Samples: 45435440. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 00:00:42,816][286098] Avg episode reward: [(0, '4384.871')] [2023-03-08 00:00:42,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000088776_45453312.pth... [2023-03-08 00:00:42,823][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000088104_45109248.pth [2023-03-08 00:00:43,709][286389] Updated weights for policy 0, policy_version 88800 (0.0005) [2023-03-08 00:00:47,296][286389] Updated weights for policy 0, policy_version 88880 (0.0005) [2023-03-08 00:00:47,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11605.3, 300 sec: 11357.7). Total num frames: 45510656. Throughput: 0: 11552.3. Samples: 45503684. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 00:00:47,816][286098] Avg episode reward: [(0, '4433.960')] [2023-03-08 00:00:50,882][286389] Updated weights for policy 0, policy_version 88960 (0.0005) [2023-03-08 00:00:52,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11605.3, 300 sec: 11357.7). Total num frames: 45568000. Throughput: 0: 11510.7. Samples: 45538472. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 00:00:52,827][286098] Avg episode reward: [(0, '4491.188')] [2023-03-08 00:00:54,437][286389] Updated weights for policy 0, policy_version 89040 (0.0005) [2023-03-08 00:00:57,816][286098] Fps is (10 sec: 11468.7, 60 sec: 11605.3, 300 sec: 11357.7). Total num frames: 45625344. Throughput: 0: 11504.9. Samples: 45607344. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 00:00:57,816][286098] Avg episode reward: [(0, '4505.637')] [2023-03-08 00:00:57,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000089112_45625344.pth... [2023-03-08 00:00:57,823][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000088432_45277184.pth [2023-03-08 00:00:57,983][286389] Updated weights for policy 0, policy_version 89120 (0.0005) [2023-03-08 00:01:01,530][286389] Updated weights for policy 0, policy_version 89200 (0.0005) [2023-03-08 00:01:02,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11537.1, 300 sec: 11343.8). Total num frames: 45682688. Throughput: 0: 11463.0. Samples: 45676156. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 00:01:02,816][286098] Avg episode reward: [(0, '4447.387')] [2023-03-08 00:01:05,099][286389] Updated weights for policy 0, policy_version 89280 (0.0005) [2023-03-08 00:01:07,816][286098] Fps is (10 sec: 11468.9, 60 sec: 11537.1, 300 sec: 11343.8). Total num frames: 45740032. Throughput: 0: 11506.4. Samples: 45711360. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 00:01:07,816][286098] Avg episode reward: [(0, '4448.543')] [2023-03-08 00:01:08,701][286389] Updated weights for policy 0, policy_version 89360 (0.0005) [2023-03-08 00:01:12,285][286389] Updated weights for policy 0, policy_version 89440 (0.0004) [2023-03-08 00:01:12,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11468.8, 300 sec: 11343.8). Total num frames: 45797376. Throughput: 0: 11513.2. Samples: 45778900. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 00:01:12,817][286098] Avg episode reward: [(0, '4465.574')] [2023-03-08 00:01:12,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000089448_45797376.pth... [2023-03-08 00:01:12,823][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000088776_45453312.pth [2023-03-08 00:01:15,570][286389] Updated weights for policy 0, policy_version 89520 (0.0004) [2023-03-08 00:01:17,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11537.1, 300 sec: 11357.7). Total num frames: 45858816. Throughput: 0: 11577.1. Samples: 45852796. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 00:01:17,816][286098] Avg episode reward: [(0, '4491.464')] [2023-03-08 00:01:18,850][286389] Updated weights for policy 0, policy_version 89600 (0.0004) [2023-03-08 00:01:22,185][286389] Updated weights for policy 0, policy_version 89680 (0.0004) [2023-03-08 00:01:22,816][286098] Fps is (10 sec: 12288.0, 60 sec: 11605.3, 300 sec: 11371.6). Total num frames: 45920256. Throughput: 0: 11608.9. Samples: 45889768. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 00:01:22,816][286098] Avg episode reward: [(0, '4479.261')] [2023-03-08 00:01:25,463][286389] Updated weights for policy 0, policy_version 89760 (0.0004) [2023-03-08 00:01:27,816][286098] Fps is (10 sec: 12697.5, 60 sec: 11810.1, 300 sec: 11399.4). Total num frames: 45985792. Throughput: 0: 11766.4. Samples: 45964928. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:01:27,816][286098] Avg episode reward: [(0, '4481.749')] [2023-03-08 00:01:27,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000089816_45985792.pth... [2023-03-08 00:01:27,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000089112_45625344.pth [2023-03-08 00:01:28,775][286389] Updated weights for policy 0, policy_version 89840 (0.0004) [2023-03-08 00:01:32,047][286389] Updated weights for policy 0, policy_version 89920 (0.0003) [2023-03-08 00:01:32,816][286098] Fps is (10 sec: 12697.7, 60 sec: 11810.1, 300 sec: 11413.3). Total num frames: 46047232. Throughput: 0: 11898.2. Samples: 46039104. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:01:32,816][286098] Avg episode reward: [(0, '4464.466')] [2023-03-08 00:01:35,312][286389] Updated weights for policy 0, policy_version 90000 (0.0004) [2023-03-08 00:01:37,816][286098] Fps is (10 sec: 12288.0, 60 sec: 11878.4, 300 sec: 11427.1). Total num frames: 46108672. Throughput: 0: 11959.5. Samples: 46076648. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:01:37,816][286098] Avg episode reward: [(0, '4469.643')] [2023-03-08 00:01:38,842][286389] Updated weights for policy 0, policy_version 90080 (0.0004) [2023-03-08 00:01:42,424][286389] Updated weights for policy 0, policy_version 90160 (0.0005) [2023-03-08 00:01:42,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11878.4, 300 sec: 11441.0). Total num frames: 46166016. Throughput: 0: 11973.2. Samples: 46146136. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:01:42,816][286098] Avg episode reward: [(0, '4471.970')] [2023-03-08 00:01:42,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000090168_46166016.pth... [2023-03-08 00:01:42,821][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000089448_45797376.pth [2023-03-08 00:01:46,023][286389] Updated weights for policy 0, policy_version 90240 (0.0005) [2023-03-08 00:01:47,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11810.1, 300 sec: 11427.1). Total num frames: 46219264. Throughput: 0: 11978.0. Samples: 46215168. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:01:47,816][286098] Avg episode reward: [(0, '4464.943')] [2023-03-08 00:01:49,587][286389] Updated weights for policy 0, policy_version 90320 (0.0005) [2023-03-08 00:01:52,816][286098] Fps is (10 sec: 11059.3, 60 sec: 11810.1, 300 sec: 11441.0). Total num frames: 46276608. Throughput: 0: 11956.6. Samples: 46249408. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:01:52,827][286098] Avg episode reward: [(0, '4485.244')] [2023-03-08 00:01:53,266][286389] Updated weights for policy 0, policy_version 90400 (0.0005) [2023-03-08 00:01:56,871][286389] Updated weights for policy 0, policy_version 90480 (0.0005) [2023-03-08 00:01:57,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11810.1, 300 sec: 11454.9). Total num frames: 46333952. Throughput: 0: 11968.8. Samples: 46317496. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:01:57,827][286098] Avg episode reward: [(0, '4474.225')] [2023-03-08 00:01:57,830][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000090496_46333952.pth... [2023-03-08 00:01:57,833][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000089816_45985792.pth [2023-03-08 00:02:00,473][286389] Updated weights for policy 0, policy_version 90560 (0.0005) [2023-03-08 00:02:02,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11810.1, 300 sec: 11454.9). Total num frames: 46391296. Throughput: 0: 11809.7. Samples: 46384232. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:02:02,827][286098] Avg episode reward: [(0, '4468.980')] [2023-03-08 00:02:04,045][286389] Updated weights for policy 0, policy_version 90640 (0.0005) [2023-03-08 00:02:07,334][286389] Updated weights for policy 0, policy_version 90720 (0.0004) [2023-03-08 00:02:07,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11878.4, 300 sec: 11482.7). Total num frames: 46452736. Throughput: 0: 11784.0. Samples: 46420048. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:02:07,827][286098] Avg episode reward: [(0, '4445.306')] [2023-03-08 00:02:10,677][286389] Updated weights for policy 0, policy_version 90800 (0.0004) [2023-03-08 00:02:12,816][286098] Fps is (10 sec: 12288.0, 60 sec: 11946.7, 300 sec: 11496.6). Total num frames: 46514176. Throughput: 0: 11752.7. Samples: 46493800. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:02:12,827][286098] Avg episode reward: [(0, '4409.701')] [2023-03-08 00:02:12,831][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000090848_46514176.pth... [2023-03-08 00:02:12,833][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000090168_46166016.pth [2023-03-08 00:02:14,139][286389] Updated weights for policy 0, policy_version 90880 (0.0004) [2023-03-08 00:02:17,453][286389] Updated weights for policy 0, policy_version 90960 (0.0004) [2023-03-08 00:02:17,816][286098] Fps is (10 sec: 12288.0, 60 sec: 11946.7, 300 sec: 11524.3). Total num frames: 46575616. Throughput: 0: 11733.6. Samples: 46567116. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:02:17,827][286098] Avg episode reward: [(0, '4422.846')] [2023-03-08 00:02:20,716][286389] Updated weights for policy 0, policy_version 91040 (0.0004) [2023-03-08 00:02:22,816][286098] Fps is (10 sec: 12288.0, 60 sec: 11946.7, 300 sec: 11552.1). Total num frames: 46637056. Throughput: 0: 11722.0. Samples: 46604140. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:02:22,818][286098] Avg episode reward: [(0, '4381.083')] [2023-03-08 00:02:24,122][286389] Updated weights for policy 0, policy_version 91120 (0.0004) [2023-03-08 00:02:27,500][286389] Updated weights for policy 0, policy_version 91200 (0.0004) [2023-03-08 00:02:27,816][286098] Fps is (10 sec: 11878.3, 60 sec: 11810.1, 300 sec: 11552.1). Total num frames: 46694400. Throughput: 0: 11786.3. Samples: 46676520. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:02:27,827][286098] Avg episode reward: [(0, '4183.987')] [2023-03-08 00:02:27,830][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000091208_46698496.pth... [2023-03-08 00:02:27,833][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000090496_46333952.pth [2023-03-08 00:02:31,106][286389] Updated weights for policy 0, policy_version 91280 (0.0005) [2023-03-08 00:02:32,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11741.9, 300 sec: 11566.0). Total num frames: 46751744. Throughput: 0: 11816.1. Samples: 46746892. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:02:32,827][286098] Avg episode reward: [(0, '4214.000')] [2023-03-08 00:02:34,711][286389] Updated weights for policy 0, policy_version 91360 (0.0005) [2023-03-08 00:02:37,816][286098] Fps is (10 sec: 11468.9, 60 sec: 11673.6, 300 sec: 11566.0). Total num frames: 46809088. Throughput: 0: 11801.6. Samples: 46780480. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:02:37,816][286098] Avg episode reward: [(0, '4343.833')] [2023-03-08 00:02:38,290][286389] Updated weights for policy 0, policy_version 91440 (0.0005) [2023-03-08 00:02:41,949][286389] Updated weights for policy 0, policy_version 91520 (0.0005) [2023-03-08 00:02:42,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11673.6, 300 sec: 11566.0). Total num frames: 46866432. Throughput: 0: 11808.8. Samples: 46848892. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:02:42,827][286098] Avg episode reward: [(0, '4437.533')] [2023-03-08 00:02:42,830][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000091536_46866432.pth... [2023-03-08 00:02:42,833][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000090848_46514176.pth [2023-03-08 00:02:45,624][286389] Updated weights for policy 0, policy_version 91600 (0.0005) [2023-03-08 00:02:47,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11741.9, 300 sec: 11579.9). Total num frames: 46923776. Throughput: 0: 11808.0. Samples: 46915592. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:02:47,816][286098] Avg episode reward: [(0, '4445.762')] [2023-03-08 00:02:49,291][286389] Updated weights for policy 0, policy_version 91680 (0.0005) [2023-03-08 00:02:52,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11673.6, 300 sec: 11579.9). Total num frames: 46977024. Throughput: 0: 11746.7. Samples: 46948648. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:02:52,816][286098] Avg episode reward: [(0, '4466.947')] [2023-03-08 00:02:52,875][286389] Updated weights for policy 0, policy_version 91760 (0.0005) [2023-03-08 00:02:56,411][286389] Updated weights for policy 0, policy_version 91840 (0.0005) [2023-03-08 00:02:57,816][286098] Fps is (10 sec: 11059.1, 60 sec: 11673.6, 300 sec: 11593.8). Total num frames: 47034368. Throughput: 0: 11649.9. Samples: 47018048. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:02:57,816][286098] Avg episode reward: [(0, '4485.929')] [2023-03-08 00:02:57,826][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000091872_47038464.pth... [2023-03-08 00:02:57,828][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000091208_46698496.pth [2023-03-08 00:03:00,013][286389] Updated weights for policy 0, policy_version 91920 (0.0005) [2023-03-08 00:03:02,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11673.6, 300 sec: 11621.5). Total num frames: 47091712. Throughput: 0: 11549.8. Samples: 47086856. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:03:02,827][286098] Avg episode reward: [(0, '4440.884')] [2023-03-08 00:03:03,575][286389] Updated weights for policy 0, policy_version 92000 (0.0005) [2023-03-08 00:03:07,234][286389] Updated weights for policy 0, policy_version 92080 (0.0005) [2023-03-08 00:03:07,816][286098] Fps is (10 sec: 11468.9, 60 sec: 11605.3, 300 sec: 11635.4). Total num frames: 47149056. Throughput: 0: 11473.5. Samples: 47120448. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:03:07,827][286098] Avg episode reward: [(0, '4461.545')] [2023-03-08 00:03:10,820][286389] Updated weights for policy 0, policy_version 92160 (0.0005) [2023-03-08 00:03:12,816][286098] Fps is (10 sec: 11468.7, 60 sec: 11537.1, 300 sec: 11663.2). Total num frames: 47206400. Throughput: 0: 11388.4. Samples: 47188996. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:03:12,827][286098] Avg episode reward: [(0, '4399.018')] [2023-03-08 00:03:12,830][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000092200_47206400.pth... [2023-03-08 00:03:12,832][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000091536_46866432.pth [2023-03-08 00:03:14,215][286389] Updated weights for policy 0, policy_version 92240 (0.0004) [2023-03-08 00:03:17,589][286389] Updated weights for policy 0, policy_version 92320 (0.0004) [2023-03-08 00:03:17,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11537.1, 300 sec: 11691.0). Total num frames: 47267840. Throughput: 0: 11445.2. Samples: 47261928. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:03:17,827][286098] Avg episode reward: [(0, '4401.790')] [2023-03-08 00:03:21,046][286389] Updated weights for policy 0, policy_version 92400 (0.0004) [2023-03-08 00:03:22,816][286098] Fps is (10 sec: 11878.5, 60 sec: 11468.8, 300 sec: 11704.8). Total num frames: 47325184. Throughput: 0: 11495.2. Samples: 47297764. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:03:22,827][286098] Avg episode reward: [(0, '4264.247')] [2023-03-08 00:03:24,651][286389] Updated weights for policy 0, policy_version 92480 (0.0005) [2023-03-08 00:03:27,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11468.8, 300 sec: 11704.8). Total num frames: 47382528. Throughput: 0: 11492.1. Samples: 47366036. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:03:27,827][286098] Avg episode reward: [(0, '4242.763')] [2023-03-08 00:03:27,831][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000092544_47382528.pth... [2023-03-08 00:03:27,833][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000091872_47038464.pth [2023-03-08 00:03:28,279][286389] Updated weights for policy 0, policy_version 92560 (0.0005) [2023-03-08 00:03:31,959][286389] Updated weights for policy 0, policy_version 92640 (0.0005) [2023-03-08 00:03:32,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11468.8, 300 sec: 11704.8). Total num frames: 47439872. Throughput: 0: 11491.6. Samples: 47432716. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:03:32,827][286098] Avg episode reward: [(0, '4166.072')] [2023-03-08 00:03:35,542][286389] Updated weights for policy 0, policy_version 92720 (0.0005) [2023-03-08 00:03:37,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11468.8, 300 sec: 11704.8). Total num frames: 47497216. Throughput: 0: 11526.9. Samples: 47467356. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:03:37,827][286098] Avg episode reward: [(0, '4237.471')] [2023-03-08 00:03:39,118][286389] Updated weights for policy 0, policy_version 92800 (0.0005) [2023-03-08 00:03:42,659][286389] Updated weights for policy 0, policy_version 92880 (0.0005) [2023-03-08 00:03:42,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11468.8, 300 sec: 11704.8). Total num frames: 47554560. Throughput: 0: 11517.5. Samples: 47536336. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:03:42,827][286098] Avg episode reward: [(0, '4243.135')] [2023-03-08 00:03:42,830][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000092880_47554560.pth... [2023-03-08 00:03:42,833][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000092200_47206400.pth [2023-03-08 00:03:45,943][286389] Updated weights for policy 0, policy_version 92960 (0.0004) [2023-03-08 00:03:47,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11537.1, 300 sec: 11732.6). Total num frames: 47616000. Throughput: 0: 11612.7. Samples: 47609428. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:03:47,827][286098] Avg episode reward: [(0, '4278.530')] [2023-03-08 00:03:49,253][286389] Updated weights for policy 0, policy_version 93040 (0.0005) [2023-03-08 00:03:52,736][286389] Updated weights for policy 0, policy_version 93120 (0.0005) [2023-03-08 00:03:52,816][286098] Fps is (10 sec: 12288.0, 60 sec: 11673.6, 300 sec: 11760.4). Total num frames: 47677440. Throughput: 0: 11685.8. Samples: 47646308. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:03:52,827][286098] Avg episode reward: [(0, '4212.863')] [2023-03-08 00:03:56,283][286389] Updated weights for policy 0, policy_version 93200 (0.0005) [2023-03-08 00:03:57,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11673.6, 300 sec: 11746.5). Total num frames: 47734784. Throughput: 0: 11700.8. Samples: 47715532. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:03:57,827][286098] Avg episode reward: [(0, '4253.281')] [2023-03-08 00:03:57,830][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000093232_47734784.pth... [2023-03-08 00:03:57,833][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000092544_47382528.pth [2023-03-08 00:03:59,803][286389] Updated weights for policy 0, policy_version 93280 (0.0005) [2023-03-08 00:04:02,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11673.6, 300 sec: 11732.6). Total num frames: 47792128. Throughput: 0: 11660.5. Samples: 47786648. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:04:02,816][286098] Avg episode reward: [(0, '4357.675')] [2023-03-08 00:04:03,283][286389] Updated weights for policy 0, policy_version 93360 (0.0004) [2023-03-08 00:04:06,797][286389] Updated weights for policy 0, policy_version 93440 (0.0005) [2023-03-08 00:04:07,816][286098] Fps is (10 sec: 11468.9, 60 sec: 11673.6, 300 sec: 11718.7). Total num frames: 47849472. Throughput: 0: 11624.6. Samples: 47820872. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:04:07,816][286098] Avg episode reward: [(0, '4289.547')] [2023-03-08 00:04:10,467][286389] Updated weights for policy 0, policy_version 93520 (0.0005) [2023-03-08 00:04:12,816][286098] Fps is (10 sec: 11468.7, 60 sec: 11673.6, 300 sec: 11704.8). Total num frames: 47906816. Throughput: 0: 11634.5. Samples: 47889588. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:04:12,816][286098] Avg episode reward: [(0, '4300.012')] [2023-03-08 00:04:12,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000093568_47906816.pth... [2023-03-08 00:04:12,823][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000092880_47554560.pth [2023-03-08 00:04:13,976][286389] Updated weights for policy 0, policy_version 93600 (0.0005) [2023-03-08 00:04:17,380][286389] Updated weights for policy 0, policy_version 93680 (0.0004) [2023-03-08 00:04:17,816][286098] Fps is (10 sec: 11878.3, 60 sec: 11673.6, 300 sec: 11704.8). Total num frames: 47968256. Throughput: 0: 11720.3. Samples: 47960128. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:04:17,816][286098] Avg episode reward: [(0, '4257.842')] [2023-03-08 00:04:20,690][286389] Updated weights for policy 0, policy_version 93760 (0.0004) [2023-03-08 00:04:22,816][286098] Fps is (10 sec: 11878.5, 60 sec: 11673.6, 300 sec: 11691.0). Total num frames: 48025600. Throughput: 0: 11776.7. Samples: 47997308. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:04:22,816][286098] Avg episode reward: [(0, '4296.292')] [2023-03-08 00:04:24,312][286389] Updated weights for policy 0, policy_version 93840 (0.0005) [2023-03-08 00:04:27,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11673.6, 300 sec: 11677.1). Total num frames: 48082944. Throughput: 0: 11782.7. Samples: 48066560. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:04:27,816][286098] Avg episode reward: [(0, '4061.311')] [2023-03-08 00:04:27,825][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000093920_48087040.pth... [2023-03-08 00:04:27,826][286389] Updated weights for policy 0, policy_version 93920 (0.0005) [2023-03-08 00:04:27,827][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000093232_47734784.pth [2023-03-08 00:04:31,352][286389] Updated weights for policy 0, policy_version 94000 (0.0005) [2023-03-08 00:04:32,816][286098] Fps is (10 sec: 11878.5, 60 sec: 11741.9, 300 sec: 11677.1). Total num frames: 48144384. Throughput: 0: 11707.5. Samples: 48136264. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:04:32,816][286098] Avg episode reward: [(0, '4233.049')] [2023-03-08 00:04:34,815][286389] Updated weights for policy 0, policy_version 94080 (0.0005) [2023-03-08 00:04:37,816][286098] Fps is (10 sec: 12288.1, 60 sec: 11810.1, 300 sec: 11691.0). Total num frames: 48205824. Throughput: 0: 11684.4. Samples: 48172104. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:04:37,816][286098] Avg episode reward: [(0, '4231.648')] [2023-03-08 00:04:38,125][286389] Updated weights for policy 0, policy_version 94160 (0.0004) [2023-03-08 00:04:41,599][286389] Updated weights for policy 0, policy_version 94240 (0.0005) [2023-03-08 00:04:42,816][286098] Fps is (10 sec: 11878.3, 60 sec: 11810.1, 300 sec: 11691.0). Total num frames: 48263168. Throughput: 0: 11752.6. Samples: 48244400. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:04:42,816][286098] Avg episode reward: [(0, '4285.803')] [2023-03-08 00:04:42,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000094264_48263168.pth... [2023-03-08 00:04:42,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000093568_47906816.pth [2023-03-08 00:04:44,911][286389] Updated weights for policy 0, policy_version 94320 (0.0004) [2023-03-08 00:04:47,816][286098] Fps is (10 sec: 11878.3, 60 sec: 11810.1, 300 sec: 11704.8). Total num frames: 48324608. Throughput: 0: 11824.9. Samples: 48318768. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:04:47,816][286098] Avg episode reward: [(0, '4315.723')] [2023-03-08 00:04:48,190][286389] Updated weights for policy 0, policy_version 94400 (0.0004) [2023-03-08 00:04:51,555][286389] Updated weights for policy 0, policy_version 94480 (0.0004) [2023-03-08 00:04:52,816][286098] Fps is (10 sec: 12288.0, 60 sec: 11810.1, 300 sec: 11718.7). Total num frames: 48386048. Throughput: 0: 11878.3. Samples: 48355396. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:04:52,816][286098] Avg episode reward: [(0, '4180.388')] [2023-03-08 00:04:55,067][286389] Updated weights for policy 0, policy_version 94560 (0.0004) [2023-03-08 00:04:57,816][286098] Fps is (10 sec: 11878.3, 60 sec: 11810.1, 300 sec: 11704.8). Total num frames: 48443392. Throughput: 0: 11934.0. Samples: 48426620. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:04:57,816][286098] Avg episode reward: [(0, '4205.930')] [2023-03-08 00:04:57,871][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000094624_48447488.pth... [2023-03-08 00:04:57,872][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000093920_48087040.pth [2023-03-08 00:04:58,606][286389] Updated weights for policy 0, policy_version 94640 (0.0005) [2023-03-08 00:05:02,139][286389] Updated weights for policy 0, policy_version 94720 (0.0005) [2023-03-08 00:05:02,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11810.1, 300 sec: 11704.8). Total num frames: 48500736. Throughput: 0: 11910.9. Samples: 48496120. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:05:02,816][286098] Avg episode reward: [(0, '4100.285')] [2023-03-08 00:05:05,654][286389] Updated weights for policy 0, policy_version 94800 (0.0005) [2023-03-08 00:05:07,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11810.1, 300 sec: 11691.0). Total num frames: 48558080. Throughput: 0: 11854.4. Samples: 48530756. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:05:07,816][286098] Avg episode reward: [(0, '3921.097')] [2023-03-08 00:05:09,380][286389] Updated weights for policy 0, policy_version 94880 (0.0005) [2023-03-08 00:05:12,816][286098] Fps is (10 sec: 11468.7, 60 sec: 11810.1, 300 sec: 11691.0). Total num frames: 48615424. Throughput: 0: 11806.0. Samples: 48597832. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 00:05:12,816][286098] Avg episode reward: [(0, '3888.853')] [2023-03-08 00:05:12,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000094952_48615424.pth... [2023-03-08 00:05:12,823][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000094264_48263168.pth [2023-03-08 00:05:13,041][286389] Updated weights for policy 0, policy_version 94960 (0.0005) [2023-03-08 00:05:16,602][286389] Updated weights for policy 0, policy_version 95040 (0.0005) [2023-03-08 00:05:17,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11741.9, 300 sec: 11691.0). Total num frames: 48672768. Throughput: 0: 11761.7. Samples: 48665540. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 00:05:17,816][286098] Avg episode reward: [(0, '3984.111')] [2023-03-08 00:05:20,074][286389] Updated weights for policy 0, policy_version 95120 (0.0005) [2023-03-08 00:05:22,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11741.9, 300 sec: 11704.8). Total num frames: 48730112. Throughput: 0: 11763.3. Samples: 48701452. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 00:05:22,816][286098] Avg episode reward: [(0, '4110.993')] [2023-03-08 00:05:23,663][286389] Updated weights for policy 0, policy_version 95200 (0.0004) [2023-03-08 00:05:27,277][286389] Updated weights for policy 0, policy_version 95280 (0.0005) [2023-03-08 00:05:27,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11741.9, 300 sec: 11691.0). Total num frames: 48787456. Throughput: 0: 11672.3. Samples: 48769656. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 00:05:27,817][286098] Avg episode reward: [(0, '4013.049')] [2023-03-08 00:05:27,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000095288_48787456.pth... [2023-03-08 00:05:27,823][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000094624_48447488.pth [2023-03-08 00:05:30,920][286389] Updated weights for policy 0, policy_version 95360 (0.0005) [2023-03-08 00:05:32,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11673.6, 300 sec: 11691.0). Total num frames: 48844800. Throughput: 0: 11514.1. Samples: 48836904. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 00:05:32,816][286098] Avg episode reward: [(0, '4130.019')] [2023-03-08 00:05:34,477][286389] Updated weights for policy 0, policy_version 95440 (0.0005) [2023-03-08 00:05:37,816][286098] Fps is (10 sec: 11468.9, 60 sec: 11605.3, 300 sec: 11691.0). Total num frames: 48902144. Throughput: 0: 11479.6. Samples: 48871976. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 00:05:37,816][286098] Avg episode reward: [(0, '4180.982')] [2023-03-08 00:05:38,060][286389] Updated weights for policy 0, policy_version 95520 (0.0005) [2023-03-08 00:05:41,540][286389] Updated weights for policy 0, policy_version 95600 (0.0004) [2023-03-08 00:05:42,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11605.3, 300 sec: 11691.0). Total num frames: 48959488. Throughput: 0: 11425.3. Samples: 48940760. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 00:05:42,816][286098] Avg episode reward: [(0, '4190.824')] [2023-03-08 00:05:42,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000095624_48959488.pth... [2023-03-08 00:05:42,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000094952_48615424.pth [2023-03-08 00:05:44,910][286389] Updated weights for policy 0, policy_version 95680 (0.0004) [2023-03-08 00:05:47,816][286098] Fps is (10 sec: 11878.5, 60 sec: 11605.3, 300 sec: 11704.8). Total num frames: 49020928. Throughput: 0: 11526.8. Samples: 49014824. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 00:05:47,816][286098] Avg episode reward: [(0, '4307.148')] [2023-03-08 00:05:48,270][286389] Updated weights for policy 0, policy_version 95760 (0.0004) [2023-03-08 00:05:51,590][286389] Updated weights for policy 0, policy_version 95840 (0.0004) [2023-03-08 00:05:52,816][286098] Fps is (10 sec: 12288.1, 60 sec: 11605.3, 300 sec: 11718.7). Total num frames: 49082368. Throughput: 0: 11557.6. Samples: 49050848. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 00:05:52,827][286098] Avg episode reward: [(0, '4357.126')] [2023-03-08 00:05:54,855][286389] Updated weights for policy 0, policy_version 95920 (0.0004) [2023-03-08 00:05:57,816][286098] Fps is (10 sec: 12288.0, 60 sec: 11673.6, 300 sec: 11732.6). Total num frames: 49143808. Throughput: 0: 11734.2. Samples: 49125868. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 00:05:57,827][286098] Avg episode reward: [(0, '4460.908')] [2023-03-08 00:05:57,845][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000095992_49147904.pth... [2023-03-08 00:05:57,847][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000095288_48787456.pth [2023-03-08 00:05:58,174][286389] Updated weights for policy 0, policy_version 96000 (0.0005) [2023-03-08 00:06:01,479][286389] Updated weights for policy 0, policy_version 96080 (0.0004) [2023-03-08 00:06:02,816][286098] Fps is (10 sec: 12697.6, 60 sec: 11810.1, 300 sec: 11760.4). Total num frames: 49209344. Throughput: 0: 11887.9. Samples: 49200496. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 00:06:02,827][286098] Avg episode reward: [(0, '4456.992')] [2023-03-08 00:06:04,744][286389] Updated weights for policy 0, policy_version 96160 (0.0003) [2023-03-08 00:06:07,816][286098] Fps is (10 sec: 12697.5, 60 sec: 11878.4, 300 sec: 11774.3). Total num frames: 49270784. Throughput: 0: 11925.1. Samples: 49238080. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 00:06:07,827][286098] Avg episode reward: [(0, '4451.984')] [2023-03-08 00:06:08,066][286389] Updated weights for policy 0, policy_version 96240 (0.0004) [2023-03-08 00:06:11,383][286389] Updated weights for policy 0, policy_version 96320 (0.0004) [2023-03-08 00:06:12,816][286098] Fps is (10 sec: 12288.0, 60 sec: 11946.7, 300 sec: 11774.3). Total num frames: 49332224. Throughput: 0: 12048.7. Samples: 49311848. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 00:06:12,827][286098] Avg episode reward: [(0, '4442.095')] [2023-03-08 00:06:12,830][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000096352_49332224.pth... [2023-03-08 00:06:12,832][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000095624_48959488.pth [2023-03-08 00:06:14,658][286389] Updated weights for policy 0, policy_version 96400 (0.0004) [2023-03-08 00:06:17,816][286098] Fps is (10 sec: 12288.0, 60 sec: 12014.9, 300 sec: 11774.3). Total num frames: 49393664. Throughput: 0: 12233.5. Samples: 49387412. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 00:06:17,827][286098] Avg episode reward: [(0, '4489.041')] [2023-03-08 00:06:17,882][286389] Updated weights for policy 0, policy_version 96480 (0.0003) [2023-03-08 00:06:21,160][286389] Updated weights for policy 0, policy_version 96560 (0.0003) [2023-03-08 00:06:22,816][286098] Fps is (10 sec: 12697.6, 60 sec: 12151.5, 300 sec: 11774.3). Total num frames: 49459200. Throughput: 0: 12282.6. Samples: 49424692. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 00:06:22,827][286098] Avg episode reward: [(0, '4510.142')] [2023-03-08 00:06:24,460][286389] Updated weights for policy 0, policy_version 96640 (0.0004) [2023-03-08 00:06:27,813][286389] Updated weights for policy 0, policy_version 96720 (0.0004) [2023-03-08 00:06:27,816][286098] Fps is (10 sec: 12697.6, 60 sec: 12219.8, 300 sec: 11774.3). Total num frames: 49520640. Throughput: 0: 12411.8. Samples: 49499288. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 00:06:27,816][286098] Avg episode reward: [(0, '4517.042')] [2023-03-08 00:06:27,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000096720_49520640.pth... [2023-03-08 00:06:27,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000095992_49147904.pth [2023-03-08 00:06:31,216][286389] Updated weights for policy 0, policy_version 96800 (0.0004) [2023-03-08 00:06:32,816][286098] Fps is (10 sec: 11878.5, 60 sec: 12219.8, 300 sec: 11760.4). Total num frames: 49577984. Throughput: 0: 12384.3. Samples: 49572116. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 00:06:32,816][286098] Avg episode reward: [(0, '4522.296')] [2023-03-08 00:06:34,500][286389] Updated weights for policy 0, policy_version 96880 (0.0004) [2023-03-08 00:06:37,745][286389] Updated weights for policy 0, policy_version 96960 (0.0004) [2023-03-08 00:06:37,816][286098] Fps is (10 sec: 12288.0, 60 sec: 12356.3, 300 sec: 11788.2). Total num frames: 49643520. Throughput: 0: 12418.7. Samples: 49609688. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 00:06:37,816][286098] Avg episode reward: [(0, '4521.218')] [2023-03-08 00:06:41,006][286389] Updated weights for policy 0, policy_version 97040 (0.0004) [2023-03-08 00:06:42,816][286098] Fps is (10 sec: 12697.4, 60 sec: 12424.5, 300 sec: 11815.9). Total num frames: 49704960. Throughput: 0: 12421.7. Samples: 49684848. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 00:06:42,817][286098] Avg episode reward: [(0, '4524.740')] [2023-03-08 00:06:42,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000097080_49704960.pth... [2023-03-08 00:06:42,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000096352_49332224.pth [2023-03-08 00:06:44,298][286389] Updated weights for policy 0, policy_version 97120 (0.0004) [2023-03-08 00:06:47,621][286389] Updated weights for policy 0, policy_version 97200 (0.0004) [2023-03-08 00:06:47,816][286098] Fps is (10 sec: 12288.1, 60 sec: 12424.5, 300 sec: 11829.8). Total num frames: 49766400. Throughput: 0: 12415.7. Samples: 49759200. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 00:06:47,816][286098] Avg episode reward: [(0, '4529.088')] [2023-03-08 00:06:50,961][286389] Updated weights for policy 0, policy_version 97280 (0.0004) [2023-03-08 00:06:52,816][286098] Fps is (10 sec: 12288.1, 60 sec: 12424.5, 300 sec: 11843.7). Total num frames: 49827840. Throughput: 0: 12406.3. Samples: 49796364. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 00:06:52,816][286098] Avg episode reward: [(0, '4533.526')] [2023-03-08 00:06:54,378][286389] Updated weights for policy 0, policy_version 97360 (0.0005) [2023-03-08 00:06:57,664][286389] Updated weights for policy 0, policy_version 97440 (0.0003) [2023-03-08 00:06:57,816][286098] Fps is (10 sec: 12288.0, 60 sec: 12424.5, 300 sec: 11857.6). Total num frames: 49889280. Throughput: 0: 12379.6. Samples: 49868928. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 00:06:57,816][286098] Avg episode reward: [(0, '4508.264')] [2023-03-08 00:06:57,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000097440_49889280.pth... [2023-03-08 00:06:57,821][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000096720_49520640.pth [2023-03-08 00:07:01,071][286389] Updated weights for policy 0, policy_version 97520 (0.0004) [2023-03-08 00:07:02,816][286098] Fps is (10 sec: 12288.0, 60 sec: 12356.3, 300 sec: 11857.6). Total num frames: 49950720. Throughput: 0: 12336.1. Samples: 49942536. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 00:07:02,816][286098] Avg episode reward: [(0, '4507.010')] [2023-03-08 00:07:04,379][286389] Updated weights for policy 0, policy_version 97600 (0.0003) [2023-03-08 00:07:07,670][286389] Updated weights for policy 0, policy_version 97680 (0.0004) [2023-03-08 00:07:07,816][286098] Fps is (10 sec: 12288.0, 60 sec: 12356.3, 300 sec: 11857.6). Total num frames: 50012160. Throughput: 0: 12334.6. Samples: 49979748. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:07:07,816][286098] Avg episode reward: [(0, '4436.660')] [2023-03-08 00:07:11,004][286389] Updated weights for policy 0, policy_version 97760 (0.0004) [2023-03-08 00:07:12,816][286098] Fps is (10 sec: 12287.9, 60 sec: 12356.3, 300 sec: 11857.6). Total num frames: 50073600. Throughput: 0: 12316.1. Samples: 50053512. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:07:12,816][286098] Avg episode reward: [(0, '4495.702')] [2023-03-08 00:07:12,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000097800_50073600.pth... [2023-03-08 00:07:12,821][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000097080_49704960.pth [2023-03-08 00:07:14,348][286389] Updated weights for policy 0, policy_version 97840 (0.0004) [2023-03-08 00:07:17,691][286389] Updated weights for policy 0, policy_version 97920 (0.0004) [2023-03-08 00:07:17,816][286098] Fps is (10 sec: 12287.9, 60 sec: 12356.3, 300 sec: 11857.6). Total num frames: 50135040. Throughput: 0: 12334.6. Samples: 50127176. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:07:17,816][286098] Avg episode reward: [(0, '4485.969')] [2023-03-08 00:07:21,063][286389] Updated weights for policy 0, policy_version 98000 (0.0004) [2023-03-08 00:07:22,816][286098] Fps is (10 sec: 12288.0, 60 sec: 12288.0, 300 sec: 11871.5). Total num frames: 50196480. Throughput: 0: 12312.0. Samples: 50163728. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:07:22,816][286098] Avg episode reward: [(0, '4530.670')] [2023-03-08 00:07:24,463][286389] Updated weights for policy 0, policy_version 98080 (0.0004) [2023-03-08 00:07:27,739][286389] Updated weights for policy 0, policy_version 98160 (0.0004) [2023-03-08 00:07:27,816][286098] Fps is (10 sec: 12287.9, 60 sec: 12288.0, 300 sec: 11885.3). Total num frames: 50257920. Throughput: 0: 12267.6. Samples: 50236892. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:07:27,816][286098] Avg episode reward: [(0, '4471.298')] [2023-03-08 00:07:27,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000098160_50257920.pth... [2023-03-08 00:07:27,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000097440_49889280.pth [2023-03-08 00:07:31,027][286389] Updated weights for policy 0, policy_version 98240 (0.0004) [2023-03-08 00:07:32,816][286098] Fps is (10 sec: 12288.0, 60 sec: 12356.3, 300 sec: 11899.2). Total num frames: 50319360. Throughput: 0: 12267.5. Samples: 50311240. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:07:32,816][286098] Avg episode reward: [(0, '4484.004')] [2023-03-08 00:07:34,324][286389] Updated weights for policy 0, policy_version 98320 (0.0004) [2023-03-08 00:07:37,706][286389] Updated weights for policy 0, policy_version 98400 (0.0004) [2023-03-08 00:07:37,816][286098] Fps is (10 sec: 12288.1, 60 sec: 12288.0, 300 sec: 11913.1). Total num frames: 50380800. Throughput: 0: 12274.0. Samples: 50348696. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:07:37,816][286098] Avg episode reward: [(0, '4510.436')] [2023-03-08 00:07:41,015][286389] Updated weights for policy 0, policy_version 98480 (0.0004) [2023-03-08 00:07:42,816][286098] Fps is (10 sec: 12287.9, 60 sec: 12288.0, 300 sec: 11927.0). Total num frames: 50442240. Throughput: 0: 12290.2. Samples: 50421988. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:07:42,816][286098] Avg episode reward: [(0, '4532.543')] [2023-03-08 00:07:42,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000098520_50442240.pth... [2023-03-08 00:07:42,823][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000097800_50073600.pth [2023-03-08 00:07:44,267][286389] Updated weights for policy 0, policy_version 98560 (0.0004) [2023-03-08 00:07:47,621][286389] Updated weights for policy 0, policy_version 98640 (0.0004) [2023-03-08 00:07:47,816][286098] Fps is (10 sec: 12288.0, 60 sec: 12288.0, 300 sec: 11954.8). Total num frames: 50503680. Throughput: 0: 12314.3. Samples: 50496680. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:07:47,816][286098] Avg episode reward: [(0, '4542.601')] [2023-03-08 00:07:50,959][286389] Updated weights for policy 0, policy_version 98720 (0.0004) [2023-03-08 00:07:52,816][286098] Fps is (10 sec: 12288.1, 60 sec: 12288.0, 300 sec: 11968.7). Total num frames: 50565120. Throughput: 0: 12307.3. Samples: 50533576. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:07:52,816][286098] Avg episode reward: [(0, '4545.876')] [2023-03-08 00:07:54,288][286389] Updated weights for policy 0, policy_version 98800 (0.0004) [2023-03-08 00:07:57,607][286389] Updated weights for policy 0, policy_version 98880 (0.0004) [2023-03-08 00:07:57,816][286098] Fps is (10 sec: 12288.0, 60 sec: 12288.0, 300 sec: 11982.5). Total num frames: 50626560. Throughput: 0: 12289.2. Samples: 50606528. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:07:57,816][286098] Avg episode reward: [(0, '4501.040')] [2023-03-08 00:07:57,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000098880_50626560.pth... [2023-03-08 00:07:57,823][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000098160_50257920.pth [2023-03-08 00:08:00,972][286389] Updated weights for policy 0, policy_version 98960 (0.0004) [2023-03-08 00:08:02,816][286098] Fps is (10 sec: 12288.1, 60 sec: 12288.0, 300 sec: 11996.4). Total num frames: 50688000. Throughput: 0: 12303.5. Samples: 50680832. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:08:02,816][286098] Avg episode reward: [(0, '4480.448')] [2023-03-08 00:08:04,242][286389] Updated weights for policy 0, policy_version 99040 (0.0004) [2023-03-08 00:08:07,640][286389] Updated weights for policy 0, policy_version 99120 (0.0004) [2023-03-08 00:08:07,816][286098] Fps is (10 sec: 12288.1, 60 sec: 12288.0, 300 sec: 12010.3). Total num frames: 50749440. Throughput: 0: 12318.9. Samples: 50718076. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 00:08:07,816][286098] Avg episode reward: [(0, '4475.676')] [2023-03-08 00:08:10,952][286389] Updated weights for policy 0, policy_version 99200 (0.0004) [2023-03-08 00:08:12,816][286098] Fps is (10 sec: 12287.9, 60 sec: 12288.0, 300 sec: 12010.3). Total num frames: 50810880. Throughput: 0: 12324.2. Samples: 50791480. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 00:08:12,816][286098] Avg episode reward: [(0, '4445.320')] [2023-03-08 00:08:12,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000099240_50810880.pth... [2023-03-08 00:08:12,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000098520_50442240.pth [2023-03-08 00:08:14,338][286389] Updated weights for policy 0, policy_version 99280 (0.0004) [2023-03-08 00:08:17,656][286389] Updated weights for policy 0, policy_version 99360 (0.0004) [2023-03-08 00:08:17,816][286098] Fps is (10 sec: 12288.0, 60 sec: 12288.0, 300 sec: 12024.2). Total num frames: 50872320. Throughput: 0: 12298.1. Samples: 50864652. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 00:08:17,816][286098] Avg episode reward: [(0, '4419.937')] [2023-03-08 00:08:21,011][286389] Updated weights for policy 0, policy_version 99440 (0.0004) [2023-03-08 00:08:22,816][286098] Fps is (10 sec: 12288.1, 60 sec: 12288.0, 300 sec: 12038.1). Total num frames: 50933760. Throughput: 0: 12290.3. Samples: 50901760. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 00:08:22,816][286098] Avg episode reward: [(0, '4467.878')] [2023-03-08 00:08:24,320][286389] Updated weights for policy 0, policy_version 99520 (0.0004) [2023-03-08 00:08:27,638][286389] Updated weights for policy 0, policy_version 99600 (0.0004) [2023-03-08 00:08:27,816][286098] Fps is (10 sec: 12288.0, 60 sec: 12288.0, 300 sec: 12052.0). Total num frames: 50995200. Throughput: 0: 12296.0. Samples: 50975308. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 00:08:27,816][286098] Avg episode reward: [(0, '4407.353')] [2023-03-08 00:08:27,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000099600_50995200.pth... [2023-03-08 00:08:27,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000098880_50626560.pth [2023-03-08 00:08:30,956][286389] Updated weights for policy 0, policy_version 99680 (0.0004) [2023-03-08 00:08:32,816][286098] Fps is (10 sec: 12288.0, 60 sec: 12288.0, 300 sec: 12065.8). Total num frames: 51056640. Throughput: 0: 12286.2. Samples: 51049556. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 00:08:32,816][286098] Avg episode reward: [(0, '4441.149')] [2023-03-08 00:08:34,249][286389] Updated weights for policy 0, policy_version 99760 (0.0004) [2023-03-08 00:08:37,583][286389] Updated weights for policy 0, policy_version 99840 (0.0004) [2023-03-08 00:08:37,816][286098] Fps is (10 sec: 12288.1, 60 sec: 12288.0, 300 sec: 12079.7). Total num frames: 51118080. Throughput: 0: 12304.4. Samples: 51087272. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 00:08:37,816][286098] Avg episode reward: [(0, '4472.360')] [2023-03-08 00:08:40,827][286389] Updated weights for policy 0, policy_version 99920 (0.0004) [2023-03-08 00:08:42,816][286098] Fps is (10 sec: 12288.0, 60 sec: 12288.0, 300 sec: 12079.7). Total num frames: 51179520. Throughput: 0: 12344.4. Samples: 51162024. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 00:08:42,816][286098] Avg episode reward: [(0, '4455.801')] [2023-03-08 00:08:42,827][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000099968_51183616.pth... [2023-03-08 00:08:42,828][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000099240_50810880.pth [2023-03-08 00:08:44,181][286389] Updated weights for policy 0, policy_version 100000 (0.0004) [2023-03-08 00:08:47,647][286389] Updated weights for policy 0, policy_version 100080 (0.0003) [2023-03-08 00:08:47,816][286098] Fps is (10 sec: 12287.9, 60 sec: 12288.0, 300 sec: 12079.7). Total num frames: 51240960. Throughput: 0: 12298.4. Samples: 51234260. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 00:08:47,816][286098] Avg episode reward: [(0, '4316.679')] [2023-03-08 00:08:51,001][286389] Updated weights for policy 0, policy_version 100160 (0.0003) [2023-03-08 00:08:52,816][286098] Fps is (10 sec: 12288.0, 60 sec: 12288.0, 300 sec: 12093.6). Total num frames: 51302400. Throughput: 0: 12274.5. Samples: 51270428. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 00:08:52,816][286098] Avg episode reward: [(0, '4331.683')] [2023-03-08 00:08:54,450][286389] Updated weights for policy 0, policy_version 100240 (0.0003) [2023-03-08 00:08:57,816][286098] Fps is (10 sec: 11878.4, 60 sec: 12219.7, 300 sec: 12093.6). Total num frames: 51359744. Throughput: 0: 12240.3. Samples: 51342292. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 00:08:57,816][286098] Avg episode reward: [(0, '4492.271')] [2023-03-08 00:08:57,827][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000100320_51363840.pth... [2023-03-08 00:08:57,827][286389] Updated weights for policy 0, policy_version 100320 (0.0003) [2023-03-08 00:08:57,829][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000099600_50995200.pth [2023-03-08 00:09:01,203][286389] Updated weights for policy 0, policy_version 100400 (0.0004) [2023-03-08 00:09:02,816][286098] Fps is (10 sec: 11878.4, 60 sec: 12219.7, 300 sec: 12107.5). Total num frames: 51421184. Throughput: 0: 12219.8. Samples: 51414544. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 00:09:02,816][286098] Avg episode reward: [(0, '4518.277')] [2023-03-08 00:09:04,572][286389] Updated weights for policy 0, policy_version 100480 (0.0004) [2023-03-08 00:09:07,816][286098] Fps is (10 sec: 12288.0, 60 sec: 12219.7, 300 sec: 12121.4). Total num frames: 51482624. Throughput: 0: 12216.8. Samples: 51451516. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 00:09:07,816][286098] Avg episode reward: [(0, '4502.483')] [2023-03-08 00:09:07,960][286389] Updated weights for policy 0, policy_version 100560 (0.0003) [2023-03-08 00:09:11,526][286389] Updated weights for policy 0, policy_version 100640 (0.0003) [2023-03-08 00:09:12,816][286098] Fps is (10 sec: 11878.4, 60 sec: 12151.5, 300 sec: 12107.5). Total num frames: 51539968. Throughput: 0: 12171.9. Samples: 51523044. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 00:09:12,816][286098] Avg episode reward: [(0, '4508.632')] [2023-03-08 00:09:12,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000100664_51539968.pth... [2023-03-08 00:09:12,820][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000099968_51183616.pth [2023-03-08 00:09:15,036][286389] Updated weights for policy 0, policy_version 100720 (0.0005) [2023-03-08 00:09:17,816][286098] Fps is (10 sec: 11468.8, 60 sec: 12083.2, 300 sec: 12107.5). Total num frames: 51597312. Throughput: 0: 12057.4. Samples: 51592140. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 00:09:17,816][286098] Avg episode reward: [(0, '4477.566')] [2023-03-08 00:09:18,572][286389] Updated weights for policy 0, policy_version 100800 (0.0005) [2023-03-08 00:09:22,055][286389] Updated weights for policy 0, policy_version 100880 (0.0005) [2023-03-08 00:09:22,816][286098] Fps is (10 sec: 11878.4, 60 sec: 12083.2, 300 sec: 12121.4). Total num frames: 51658752. Throughput: 0: 11995.4. Samples: 51627064. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 00:09:22,816][286098] Avg episode reward: [(0, '4499.939')] [2023-03-08 00:09:25,426][286389] Updated weights for policy 0, policy_version 100960 (0.0005) [2023-03-08 00:09:27,816][286098] Fps is (10 sec: 11878.3, 60 sec: 12014.9, 300 sec: 12107.5). Total num frames: 51716096. Throughput: 0: 11937.2. Samples: 51699200. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 00:09:27,816][286098] Avg episode reward: [(0, '4512.291')] [2023-03-08 00:09:27,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000101008_51716096.pth... [2023-03-08 00:09:27,821][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000100320_51363840.pth [2023-03-08 00:09:28,948][286389] Updated weights for policy 0, policy_version 101040 (0.0005) [2023-03-08 00:09:32,520][286389] Updated weights for policy 0, policy_version 101120 (0.0005) [2023-03-08 00:09:32,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11946.7, 300 sec: 12093.6). Total num frames: 51773440. Throughput: 0: 11878.8. Samples: 51768804. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 00:09:32,816][286098] Avg episode reward: [(0, '4471.352')] [2023-03-08 00:09:36,186][286389] Updated weights for policy 0, policy_version 101200 (0.0005) [2023-03-08 00:09:37,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11878.4, 300 sec: 12093.6). Total num frames: 51830784. Throughput: 0: 11816.6. Samples: 51802176. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 00:09:37,816][286098] Avg episode reward: [(0, '4492.777')] [2023-03-08 00:09:39,773][286389] Updated weights for policy 0, policy_version 101280 (0.0005) [2023-03-08 00:09:42,816][286098] Fps is (10 sec: 11468.7, 60 sec: 11810.1, 300 sec: 12079.7). Total num frames: 51888128. Throughput: 0: 11728.3. Samples: 51870068. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 00:09:42,816][286098] Avg episode reward: [(0, '4506.005')] [2023-03-08 00:09:42,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000101344_51888128.pth... [2023-03-08 00:09:42,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000100664_51539968.pth [2023-03-08 00:09:43,371][286389] Updated weights for policy 0, policy_version 101360 (0.0005) [2023-03-08 00:09:46,990][286389] Updated weights for policy 0, policy_version 101440 (0.0005) [2023-03-08 00:09:47,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11741.9, 300 sec: 12065.8). Total num frames: 51945472. Throughput: 0: 11629.6. Samples: 51937876. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 00:09:47,816][286098] Avg episode reward: [(0, '4524.373')] [2023-03-08 00:09:50,332][286389] Updated weights for policy 0, policy_version 101520 (0.0004) [2023-03-08 00:09:52,816][286098] Fps is (10 sec: 11878.5, 60 sec: 11741.9, 300 sec: 12079.7). Total num frames: 52006912. Throughput: 0: 11628.0. Samples: 51974776. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 00:09:52,816][286098] Avg episode reward: [(0, '4537.018')] [2023-03-08 00:09:53,636][286389] Updated weights for policy 0, policy_version 101600 (0.0004) [2023-03-08 00:09:56,911][286389] Updated weights for policy 0, policy_version 101680 (0.0004) [2023-03-08 00:09:57,816][286098] Fps is (10 sec: 12288.0, 60 sec: 11810.1, 300 sec: 12093.6). Total num frames: 52068352. Throughput: 0: 11705.2. Samples: 52049780. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 00:09:57,816][286098] Avg episode reward: [(0, '4502.764')] [2023-03-08 00:09:57,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000101696_52068352.pth... [2023-03-08 00:09:57,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000101008_51716096.pth [2023-03-08 00:10:00,508][286389] Updated weights for policy 0, policy_version 101760 (0.0005) [2023-03-08 00:10:02,816][286098] Fps is (10 sec: 12288.0, 60 sec: 11810.1, 300 sec: 12107.5). Total num frames: 52129792. Throughput: 0: 11738.3. Samples: 52120364. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 00:10:02,816][286098] Avg episode reward: [(0, '4487.031')] [2023-03-08 00:10:03,809][286389] Updated weights for policy 0, policy_version 101840 (0.0004) [2023-03-08 00:10:07,123][286389] Updated weights for policy 0, policy_version 101920 (0.0004) [2023-03-08 00:10:07,816][286098] Fps is (10 sec: 12288.0, 60 sec: 11810.1, 300 sec: 12121.4). Total num frames: 52191232. Throughput: 0: 11793.2. Samples: 52157760. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 00:10:07,816][286098] Avg episode reward: [(0, '4540.908')] [2023-03-08 00:10:10,481][286389] Updated weights for policy 0, policy_version 102000 (0.0005) [2023-03-08 00:10:12,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11810.1, 300 sec: 12121.4). Total num frames: 52248576. Throughput: 0: 11828.5. Samples: 52231480. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 00:10:12,816][286098] Avg episode reward: [(0, '4537.114')] [2023-03-08 00:10:12,834][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000102056_52252672.pth... [2023-03-08 00:10:12,835][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000101344_51888128.pth [2023-03-08 00:10:13,821][286389] Updated weights for policy 0, policy_version 102080 (0.0005) [2023-03-08 00:10:17,108][286389] Updated weights for policy 0, policy_version 102160 (0.0004) [2023-03-08 00:10:17,816][286098] Fps is (10 sec: 12288.0, 60 sec: 11946.7, 300 sec: 12149.2). Total num frames: 52314112. Throughput: 0: 11923.5. Samples: 52305360. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 00:10:17,816][286098] Avg episode reward: [(0, '4528.622')] [2023-03-08 00:10:20,441][286389] Updated weights for policy 0, policy_version 102240 (0.0004) [2023-03-08 00:10:22,816][286098] Fps is (10 sec: 12697.6, 60 sec: 11946.7, 300 sec: 12163.0). Total num frames: 52375552. Throughput: 0: 12006.8. Samples: 52342484. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 00:10:22,816][286098] Avg episode reward: [(0, '4538.459')] [2023-03-08 00:10:23,760][286389] Updated weights for policy 0, policy_version 102320 (0.0003) [2023-03-08 00:10:27,189][286389] Updated weights for policy 0, policy_version 102400 (0.0003) [2023-03-08 00:10:27,816][286098] Fps is (10 sec: 11878.5, 60 sec: 11946.7, 300 sec: 12163.0). Total num frames: 52432896. Throughput: 0: 12105.0. Samples: 52414792. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 00:10:27,816][286098] Avg episode reward: [(0, '4537.898')] [2023-03-08 00:10:27,822][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000102416_52436992.pth... [2023-03-08 00:10:27,824][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000101696_52068352.pth [2023-03-08 00:10:30,542][286389] Updated weights for policy 0, policy_version 102480 (0.0004) [2023-03-08 00:10:32,816][286098] Fps is (10 sec: 11878.5, 60 sec: 12014.9, 300 sec: 12176.9). Total num frames: 52494336. Throughput: 0: 12207.8. Samples: 52487228. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 00:10:32,816][286098] Avg episode reward: [(0, '4543.234')] [2023-03-08 00:10:34,167][286389] Updated weights for policy 0, policy_version 102560 (0.0005) [2023-03-08 00:10:37,800][286389] Updated weights for policy 0, policy_version 102640 (0.0005) [2023-03-08 00:10:37,816][286098] Fps is (10 sec: 11878.3, 60 sec: 12014.9, 300 sec: 12176.9). Total num frames: 52551680. Throughput: 0: 12133.6. Samples: 52520788. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 00:10:37,816][286098] Avg episode reward: [(0, '4545.724')] [2023-03-08 00:10:41,352][286389] Updated weights for policy 0, policy_version 102720 (0.0005) [2023-03-08 00:10:42,816][286098] Fps is (10 sec: 11468.8, 60 sec: 12015.0, 300 sec: 12163.0). Total num frames: 52609024. Throughput: 0: 11981.9. Samples: 52588964. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 00:10:42,816][286098] Avg episode reward: [(0, '4539.139')] [2023-03-08 00:10:42,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000102752_52609024.pth... [2023-03-08 00:10:42,821][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000102056_52252672.pth [2023-03-08 00:10:44,926][286389] Updated weights for policy 0, policy_version 102800 (0.0005) [2023-03-08 00:10:47,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11946.7, 300 sec: 12135.3). Total num frames: 52662272. Throughput: 0: 11945.9. Samples: 52657928. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 00:10:47,816][286098] Avg episode reward: [(0, '4416.393')] [2023-03-08 00:10:48,631][286389] Updated weights for policy 0, policy_version 102880 (0.0005) [2023-03-08 00:10:52,258][286389] Updated weights for policy 0, policy_version 102960 (0.0005) [2023-03-08 00:10:52,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11878.4, 300 sec: 12121.4). Total num frames: 52719616. Throughput: 0: 11848.5. Samples: 52690944. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 00:10:52,827][286098] Avg episode reward: [(0, '4274.160')] [2023-03-08 00:10:55,745][286389] Updated weights for policy 0, policy_version 103040 (0.0005) [2023-03-08 00:10:57,816][286098] Fps is (10 sec: 11878.3, 60 sec: 11878.4, 300 sec: 12107.5). Total num frames: 52781056. Throughput: 0: 11759.1. Samples: 52760640. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 00:10:57,827][286098] Avg episode reward: [(0, '4478.675')] [2023-03-08 00:10:57,830][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000103088_52781056.pth... [2023-03-08 00:10:57,833][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000102416_52436992.pth [2023-03-08 00:10:59,160][286389] Updated weights for policy 0, policy_version 103120 (0.0005) [2023-03-08 00:11:02,775][286389] Updated weights for policy 0, policy_version 103200 (0.0005) [2023-03-08 00:11:02,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11810.1, 300 sec: 12093.6). Total num frames: 52838400. Throughput: 0: 11663.3. Samples: 52830208. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 00:11:02,827][286098] Avg episode reward: [(0, '4544.170')] [2023-03-08 00:11:06,127][286389] Updated weights for policy 0, policy_version 103280 (0.0005) [2023-03-08 00:11:07,816][286098] Fps is (10 sec: 11468.9, 60 sec: 11741.9, 300 sec: 12079.7). Total num frames: 52895744. Throughput: 0: 11655.7. Samples: 52866992. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 00:11:07,827][286098] Avg episode reward: [(0, '4519.067')] [2023-03-08 00:11:09,535][286389] Updated weights for policy 0, policy_version 103360 (0.0005) [2023-03-08 00:11:12,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11810.1, 300 sec: 12079.7). Total num frames: 52957184. Throughput: 0: 11648.8. Samples: 52938988. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 00:11:12,816][286098] Avg episode reward: [(0, '4555.816')] [2023-03-08 00:11:12,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000103432_52957184.pth... [2023-03-08 00:11:12,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000102752_52609024.pth [2023-03-08 00:11:12,911][286389] Updated weights for policy 0, policy_version 103440 (0.0005) [2023-03-08 00:11:16,276][286389] Updated weights for policy 0, policy_version 103520 (0.0005) [2023-03-08 00:11:17,816][286098] Fps is (10 sec: 12287.9, 60 sec: 11741.9, 300 sec: 12065.8). Total num frames: 53018624. Throughput: 0: 11638.3. Samples: 53010952. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 00:11:17,816][286098] Avg episode reward: [(0, '4540.548')] [2023-03-08 00:11:19,895][286389] Updated weights for policy 0, policy_version 103600 (0.0005) [2023-03-08 00:11:22,816][286098] Fps is (10 sec: 11878.3, 60 sec: 11673.6, 300 sec: 12052.0). Total num frames: 53075968. Throughput: 0: 11650.5. Samples: 53045060. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 00:11:22,817][286098] Avg episode reward: [(0, '4537.716')] [2023-03-08 00:11:23,474][286389] Updated weights for policy 0, policy_version 103680 (0.0005) [2023-03-08 00:11:27,071][286389] Updated weights for policy 0, policy_version 103760 (0.0005) [2023-03-08 00:11:27,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11673.6, 300 sec: 12052.0). Total num frames: 53133312. Throughput: 0: 11663.2. Samples: 53113808. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 00:11:27,816][286098] Avg episode reward: [(0, '4538.262')] [2023-03-08 00:11:27,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000103776_53133312.pth... [2023-03-08 00:11:27,821][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000103088_52781056.pth [2023-03-08 00:11:30,587][286389] Updated weights for policy 0, policy_version 103840 (0.0005) [2023-03-08 00:11:32,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11605.3, 300 sec: 12024.2). Total num frames: 53190656. Throughput: 0: 11701.3. Samples: 53184488. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 00:11:32,816][286098] Avg episode reward: [(0, '4509.694')] [2023-03-08 00:11:33,978][286389] Updated weights for policy 0, policy_version 103920 (0.0004) [2023-03-08 00:11:37,603][286389] Updated weights for policy 0, policy_version 104000 (0.0005) [2023-03-08 00:11:37,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11605.3, 300 sec: 12010.3). Total num frames: 53248000. Throughput: 0: 11741.9. Samples: 53219328. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 00:11:37,827][286098] Avg episode reward: [(0, '4549.345')] [2023-03-08 00:11:41,286][286389] Updated weights for policy 0, policy_version 104080 (0.0005) [2023-03-08 00:11:42,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11605.3, 300 sec: 11996.4). Total num frames: 53305344. Throughput: 0: 11689.0. Samples: 53286644. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 00:11:42,827][286098] Avg episode reward: [(0, '4545.408')] [2023-03-08 00:11:42,830][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000104112_53305344.pth... [2023-03-08 00:11:42,833][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000103432_52957184.pth [2023-03-08 00:11:45,005][286389] Updated weights for policy 0, policy_version 104160 (0.0005) [2023-03-08 00:11:47,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11605.3, 300 sec: 11968.6). Total num frames: 53358592. Throughput: 0: 11634.2. Samples: 53353748. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 00:11:47,827][286098] Avg episode reward: [(0, '4542.017')] [2023-03-08 00:11:48,636][286389] Updated weights for policy 0, policy_version 104240 (0.0005) [2023-03-08 00:11:52,351][286389] Updated weights for policy 0, policy_version 104320 (0.0005) [2023-03-08 00:11:52,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11605.3, 300 sec: 11954.8). Total num frames: 53415936. Throughput: 0: 11561.6. Samples: 53387264. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 00:11:52,827][286098] Avg episode reward: [(0, '4516.693')] [2023-03-08 00:11:56,001][286389] Updated weights for policy 0, policy_version 104400 (0.0005) [2023-03-08 00:11:57,816][286098] Fps is (10 sec: 11059.1, 60 sec: 11468.8, 300 sec: 11927.0). Total num frames: 53469184. Throughput: 0: 11428.1. Samples: 53453252. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 00:11:57,827][286098] Avg episode reward: [(0, '4501.868')] [2023-03-08 00:11:57,831][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000104440_53473280.pth... [2023-03-08 00:11:57,833][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000103776_53133312.pth [2023-03-08 00:11:59,588][286389] Updated weights for policy 0, policy_version 104480 (0.0005) [2023-03-08 00:12:02,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11537.1, 300 sec: 11927.0). Total num frames: 53530624. Throughput: 0: 11366.2. Samples: 53522432. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 00:12:02,827][286098] Avg episode reward: [(0, '4550.220')] [2023-03-08 00:12:03,163][286389] Updated weights for policy 0, policy_version 104560 (0.0005) [2023-03-08 00:12:06,753][286389] Updated weights for policy 0, policy_version 104640 (0.0005) [2023-03-08 00:12:07,816][286098] Fps is (10 sec: 11468.9, 60 sec: 11468.8, 300 sec: 11899.2). Total num frames: 53583872. Throughput: 0: 11359.4. Samples: 53556232. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:12:07,827][286098] Avg episode reward: [(0, '4556.692')] [2023-03-08 00:12:10,347][286389] Updated weights for policy 0, policy_version 104720 (0.0005) [2023-03-08 00:12:12,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11400.5, 300 sec: 11885.3). Total num frames: 53641216. Throughput: 0: 11357.5. Samples: 53624896. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:12:12,827][286098] Avg episode reward: [(0, '4557.655')] [2023-03-08 00:12:12,829][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000104768_53641216.pth... [2023-03-08 00:12:12,832][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000104112_53305344.pth [2023-03-08 00:12:14,015][286389] Updated weights for policy 0, policy_version 104800 (0.0005) [2023-03-08 00:12:17,615][286389] Updated weights for policy 0, policy_version 104880 (0.0005) [2023-03-08 00:12:17,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11332.3, 300 sec: 11871.5). Total num frames: 53698560. Throughput: 0: 11284.8. Samples: 53692304. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:12:17,827][286098] Avg episode reward: [(0, '4552.172')] [2023-03-08 00:12:21,307][286389] Updated weights for policy 0, policy_version 104960 (0.0005) [2023-03-08 00:12:22,816][286098] Fps is (10 sec: 11468.9, 60 sec: 11332.3, 300 sec: 11857.6). Total num frames: 53755904. Throughput: 0: 11264.5. Samples: 53726232. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:12:22,827][286098] Avg episode reward: [(0, '4527.642')] [2023-03-08 00:12:24,884][286389] Updated weights for policy 0, policy_version 105040 (0.0005) [2023-03-08 00:12:27,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11332.3, 300 sec: 11843.7). Total num frames: 53813248. Throughput: 0: 11262.0. Samples: 53793432. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:12:27,827][286098] Avg episode reward: [(0, '4511.816')] [2023-03-08 00:12:27,830][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000105104_53813248.pth... [2023-03-08 00:12:27,832][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000104440_53473280.pth [2023-03-08 00:12:28,512][286389] Updated weights for policy 0, policy_version 105120 (0.0005) [2023-03-08 00:12:32,101][286389] Updated weights for policy 0, policy_version 105200 (0.0005) [2023-03-08 00:12:32,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11264.0, 300 sec: 11815.9). Total num frames: 53866496. Throughput: 0: 11303.4. Samples: 53862400. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:12:32,816][286098] Avg episode reward: [(0, '4528.557')] [2023-03-08 00:12:35,755][286389] Updated weights for policy 0, policy_version 105280 (0.0005) [2023-03-08 00:12:37,816][286098] Fps is (10 sec: 11059.3, 60 sec: 11264.0, 300 sec: 11802.0). Total num frames: 53923840. Throughput: 0: 11288.4. Samples: 53895240. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:12:37,816][286098] Avg episode reward: [(0, '4539.858')] [2023-03-08 00:12:39,351][286389] Updated weights for policy 0, policy_version 105360 (0.0005) [2023-03-08 00:12:42,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11264.0, 300 sec: 11788.1). Total num frames: 53981184. Throughput: 0: 11358.1. Samples: 53964364. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:12:42,816][286098] Avg episode reward: [(0, '4555.042')] [2023-03-08 00:12:42,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000105432_53981184.pth... [2023-03-08 00:12:42,821][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000104768_53641216.pth [2023-03-08 00:12:42,979][286389] Updated weights for policy 0, policy_version 105440 (0.0005) [2023-03-08 00:12:46,635][286389] Updated weights for policy 0, policy_version 105520 (0.0005) [2023-03-08 00:12:47,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11332.3, 300 sec: 11774.3). Total num frames: 54038528. Throughput: 0: 11302.2. Samples: 54031028. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:12:47,816][286098] Avg episode reward: [(0, '4554.925')] [2023-03-08 00:12:50,256][286389] Updated weights for policy 0, policy_version 105600 (0.0005) [2023-03-08 00:12:52,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11332.3, 300 sec: 11760.4). Total num frames: 54095872. Throughput: 0: 11309.2. Samples: 54065148. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:12:52,816][286098] Avg episode reward: [(0, '4507.255')] [2023-03-08 00:12:53,856][286389] Updated weights for policy 0, policy_version 105680 (0.0005) [2023-03-08 00:12:57,542][286389] Updated weights for policy 0, policy_version 105760 (0.0005) [2023-03-08 00:12:57,816][286098] Fps is (10 sec: 11059.1, 60 sec: 11332.3, 300 sec: 11732.6). Total num frames: 54149120. Throughput: 0: 11286.8. Samples: 54132800. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:12:57,816][286098] Avg episode reward: [(0, '4530.630')] [2023-03-08 00:12:57,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000105760_54149120.pth... [2023-03-08 00:12:57,823][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000105104_53813248.pth [2023-03-08 00:13:01,102][286389] Updated weights for policy 0, policy_version 105840 (0.0005) [2023-03-08 00:13:02,816][286098] Fps is (10 sec: 11059.3, 60 sec: 11264.0, 300 sec: 11718.7). Total num frames: 54206464. Throughput: 0: 11299.2. Samples: 54200768. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:13:02,816][286098] Avg episode reward: [(0, '4553.467')] [2023-03-08 00:13:04,816][286389] Updated weights for policy 0, policy_version 105920 (0.0005) [2023-03-08 00:13:07,816][286098] Fps is (10 sec: 11468.9, 60 sec: 11332.3, 300 sec: 11704.8). Total num frames: 54263808. Throughput: 0: 11287.2. Samples: 54234156. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:13:07,816][286098] Avg episode reward: [(0, '4557.174')] [2023-03-08 00:13:08,409][286389] Updated weights for policy 0, policy_version 106000 (0.0005) [2023-03-08 00:13:12,124][286389] Updated weights for policy 0, policy_version 106080 (0.0005) [2023-03-08 00:13:12,816][286098] Fps is (10 sec: 11059.1, 60 sec: 11264.0, 300 sec: 11677.1). Total num frames: 54317056. Throughput: 0: 11281.2. Samples: 54301088. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:13:12,816][286098] Avg episode reward: [(0, '4557.561')] [2023-03-08 00:13:12,851][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000106096_54321152.pth... [2023-03-08 00:13:12,853][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000105432_53981184.pth [2023-03-08 00:13:15,669][286389] Updated weights for policy 0, policy_version 106160 (0.0004) [2023-03-08 00:13:17,816][286098] Fps is (10 sec: 11468.7, 60 sec: 11332.3, 300 sec: 11677.1). Total num frames: 54378496. Throughput: 0: 11310.4. Samples: 54371368. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:13:17,816][286098] Avg episode reward: [(0, '4561.418')] [2023-03-08 00:13:18,923][286389] Updated weights for policy 0, policy_version 106240 (0.0003) [2023-03-08 00:13:22,276][286389] Updated weights for policy 0, policy_version 106320 (0.0004) [2023-03-08 00:13:22,816][286098] Fps is (10 sec: 12288.0, 60 sec: 11400.5, 300 sec: 11677.1). Total num frames: 54439936. Throughput: 0: 11406.0. Samples: 54408512. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:13:22,816][286098] Avg episode reward: [(0, '4567.564')] [2023-03-08 00:13:25,697][286389] Updated weights for policy 0, policy_version 106400 (0.0004) [2023-03-08 00:13:27,816][286098] Fps is (10 sec: 12288.0, 60 sec: 11468.8, 300 sec: 11677.1). Total num frames: 54501376. Throughput: 0: 11479.9. Samples: 54480960. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:13:27,816][286098] Avg episode reward: [(0, '4561.929')] [2023-03-08 00:13:27,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000106448_54501376.pth... [2023-03-08 00:13:27,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000105760_54149120.pth [2023-03-08 00:13:29,106][286389] Updated weights for policy 0, policy_version 106480 (0.0004) [2023-03-08 00:13:32,462][286389] Updated weights for policy 0, policy_version 106560 (0.0004) [2023-03-08 00:13:32,816][286098] Fps is (10 sec: 12288.0, 60 sec: 11605.3, 300 sec: 11677.1). Total num frames: 54562816. Throughput: 0: 11621.4. Samples: 54553992. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:13:32,816][286098] Avg episode reward: [(0, '4561.175')] [2023-03-08 00:13:35,829][286389] Updated weights for policy 0, policy_version 106640 (0.0004) [2023-03-08 00:13:37,816][286098] Fps is (10 sec: 11878.3, 60 sec: 11605.3, 300 sec: 11663.2). Total num frames: 54620160. Throughput: 0: 11681.8. Samples: 54590828. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:13:37,816][286098] Avg episode reward: [(0, '4562.422')] [2023-03-08 00:13:39,366][286389] Updated weights for policy 0, policy_version 106720 (0.0005) [2023-03-08 00:13:42,816][286098] Fps is (10 sec: 11468.7, 60 sec: 11605.3, 300 sec: 11649.3). Total num frames: 54677504. Throughput: 0: 11704.9. Samples: 54659520. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:13:42,816][286098] Avg episode reward: [(0, '4562.070')] [2023-03-08 00:13:42,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000106792_54677504.pth... [2023-03-08 00:13:42,823][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000106096_54321152.pth [2023-03-08 00:13:43,040][286389] Updated weights for policy 0, policy_version 106800 (0.0005) [2023-03-08 00:13:46,671][286389] Updated weights for policy 0, policy_version 106880 (0.0005) [2023-03-08 00:13:47,816][286098] Fps is (10 sec: 11468.9, 60 sec: 11605.3, 300 sec: 11635.4). Total num frames: 54734848. Throughput: 0: 11687.8. Samples: 54726720. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:13:47,816][286098] Avg episode reward: [(0, '4559.153')] [2023-03-08 00:13:50,350][286389] Updated weights for policy 0, policy_version 106960 (0.0004) [2023-03-08 00:13:52,816][286098] Fps is (10 sec: 11059.3, 60 sec: 11537.1, 300 sec: 11621.5). Total num frames: 54788096. Throughput: 0: 11684.6. Samples: 54759964. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:13:52,816][286098] Avg episode reward: [(0, '4570.223')] [2023-03-08 00:13:54,040][286389] Updated weights for policy 0, policy_version 107040 (0.0005) [2023-03-08 00:13:57,708][286389] Updated weights for policy 0, policy_version 107120 (0.0005) [2023-03-08 00:13:57,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11605.3, 300 sec: 11607.6). Total num frames: 54845440. Throughput: 0: 11681.4. Samples: 54826748. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:13:57,816][286098] Avg episode reward: [(0, '4574.361')] [2023-03-08 00:13:57,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000107120_54845440.pth... [2023-03-08 00:13:57,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000106448_54501376.pth [2023-03-08 00:14:01,396][286389] Updated weights for policy 0, policy_version 107200 (0.0005) [2023-03-08 00:14:02,816][286098] Fps is (10 sec: 11059.0, 60 sec: 11537.0, 300 sec: 11579.9). Total num frames: 54898688. Throughput: 0: 11626.0. Samples: 54894540. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:14:02,817][286098] Avg episode reward: [(0, '4567.245')] [2023-03-08 00:14:05,027][286389] Updated weights for policy 0, policy_version 107280 (0.0005) [2023-03-08 00:14:07,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11537.1, 300 sec: 11579.9). Total num frames: 54956032. Throughput: 0: 11531.6. Samples: 54927432. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:14:07,816][286098] Avg episode reward: [(0, '4565.498')] [2023-03-08 00:14:08,732][286389] Updated weights for policy 0, policy_version 107360 (0.0005) [2023-03-08 00:14:12,412][286389] Updated weights for policy 0, policy_version 107440 (0.0005) [2023-03-08 00:14:12,816][286098] Fps is (10 sec: 11468.9, 60 sec: 11605.3, 300 sec: 11579.9). Total num frames: 55013376. Throughput: 0: 11397.7. Samples: 54993856. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 00:14:12,816][286098] Avg episode reward: [(0, '4568.573')] [2023-03-08 00:14:12,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000107448_55013376.pth... [2023-03-08 00:14:12,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000106792_54677504.pth [2023-03-08 00:14:16,087][286389] Updated weights for policy 0, policy_version 107520 (0.0005) [2023-03-08 00:14:17,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11468.8, 300 sec: 11552.1). Total num frames: 55066624. Throughput: 0: 11285.5. Samples: 55061840. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 00:14:17,816][286098] Avg episode reward: [(0, '4570.512')] [2023-03-08 00:14:19,748][286389] Updated weights for policy 0, policy_version 107600 (0.0005) [2023-03-08 00:14:22,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11468.8, 300 sec: 11566.0). Total num frames: 55128064. Throughput: 0: 11210.1. Samples: 55095280. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 00:14:22,827][286098] Avg episode reward: [(0, '4568.326')] [2023-03-08 00:14:23,142][286389] Updated weights for policy 0, policy_version 107680 (0.0004) [2023-03-08 00:14:26,545][286389] Updated weights for policy 0, policy_version 107760 (0.0004) [2023-03-08 00:14:27,816][286098] Fps is (10 sec: 11878.3, 60 sec: 11400.5, 300 sec: 11566.0). Total num frames: 55185408. Throughput: 0: 11292.5. Samples: 55167684. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 00:14:27,827][286098] Avg episode reward: [(0, '4566.923')] [2023-03-08 00:14:27,832][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000107792_55189504.pth... [2023-03-08 00:14:27,833][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000107120_54845440.pth [2023-03-08 00:14:29,843][286389] Updated weights for policy 0, policy_version 107840 (0.0004) [2023-03-08 00:14:32,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11400.5, 300 sec: 11579.9). Total num frames: 55246848. Throughput: 0: 11412.3. Samples: 55240276. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 00:14:32,827][286098] Avg episode reward: [(0, '4568.547')] [2023-03-08 00:14:33,260][286389] Updated weights for policy 0, policy_version 107920 (0.0004) [2023-03-08 00:14:36,591][286389] Updated weights for policy 0, policy_version 108000 (0.0005) [2023-03-08 00:14:37,816][286098] Fps is (10 sec: 12288.1, 60 sec: 11468.8, 300 sec: 11593.8). Total num frames: 55308288. Throughput: 0: 11489.1. Samples: 55276972. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 00:14:37,827][286098] Avg episode reward: [(0, '4569.668')] [2023-03-08 00:14:39,995][286389] Updated weights for policy 0, policy_version 108080 (0.0004) [2023-03-08 00:14:42,816][286098] Fps is (10 sec: 12288.0, 60 sec: 11537.1, 300 sec: 11607.6). Total num frames: 55369728. Throughput: 0: 11617.3. Samples: 55349528. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 00:14:42,827][286098] Avg episode reward: [(0, '4570.912')] [2023-03-08 00:14:42,831][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000108144_55369728.pth... [2023-03-08 00:14:42,833][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000107448_55013376.pth [2023-03-08 00:14:43,330][286389] Updated weights for policy 0, policy_version 108160 (0.0004) [2023-03-08 00:14:46,668][286389] Updated weights for policy 0, policy_version 108240 (0.0004) [2023-03-08 00:14:47,816][286098] Fps is (10 sec: 12287.9, 60 sec: 11605.3, 300 sec: 11607.6). Total num frames: 55431168. Throughput: 0: 11756.5. Samples: 55423580. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 00:14:47,816][286098] Avg episode reward: [(0, '4553.106')] [2023-03-08 00:14:50,084][286389] Updated weights for policy 0, policy_version 108320 (0.0004) [2023-03-08 00:14:52,816][286098] Fps is (10 sec: 12288.1, 60 sec: 11741.9, 300 sec: 11607.6). Total num frames: 55492608. Throughput: 0: 11831.5. Samples: 55459848. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 00:14:52,827][286098] Avg episode reward: [(0, '4547.723')] [2023-03-08 00:14:53,415][286389] Updated weights for policy 0, policy_version 108400 (0.0004) [2023-03-08 00:14:56,836][286389] Updated weights for policy 0, policy_version 108480 (0.0004) [2023-03-08 00:14:57,816][286098] Fps is (10 sec: 11878.3, 60 sec: 11741.8, 300 sec: 11593.8). Total num frames: 55549952. Throughput: 0: 11971.4. Samples: 55532568. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 00:14:57,827][286098] Avg episode reward: [(0, '4535.030')] [2023-03-08 00:14:57,859][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000108504_55554048.pth... [2023-03-08 00:14:57,861][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000107792_55189504.pth [2023-03-08 00:15:00,223][286389] Updated weights for policy 0, policy_version 108560 (0.0004) [2023-03-08 00:15:02,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11878.4, 300 sec: 11593.8). Total num frames: 55611392. Throughput: 0: 12042.9. Samples: 55603772. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 00:15:02,816][286098] Avg episode reward: [(0, '4553.348')] [2023-03-08 00:15:03,834][286389] Updated weights for policy 0, policy_version 108640 (0.0004) [2023-03-08 00:15:07,312][286389] Updated weights for policy 0, policy_version 108720 (0.0004) [2023-03-08 00:15:07,816][286098] Fps is (10 sec: 11878.5, 60 sec: 11878.4, 300 sec: 11593.8). Total num frames: 55668736. Throughput: 0: 12048.8. Samples: 55637476. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 00:15:07,816][286098] Avg episode reward: [(0, '4559.154')] [2023-03-08 00:15:10,660][286389] Updated weights for policy 0, policy_version 108800 (0.0004) [2023-03-08 00:15:12,816][286098] Fps is (10 sec: 11878.3, 60 sec: 11946.7, 300 sec: 11579.9). Total num frames: 55730176. Throughput: 0: 12052.7. Samples: 55710056. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 00:15:12,816][286098] Avg episode reward: [(0, '4556.142')] [2023-03-08 00:15:12,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000108848_55730176.pth... [2023-03-08 00:15:12,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000108144_55369728.pth [2023-03-08 00:15:14,052][286389] Updated weights for policy 0, policy_version 108880 (0.0004) [2023-03-08 00:15:17,449][286389] Updated weights for policy 0, policy_version 108960 (0.0004) [2023-03-08 00:15:17,816][286098] Fps is (10 sec: 12288.0, 60 sec: 12083.2, 300 sec: 11579.9). Total num frames: 55791616. Throughput: 0: 12070.0. Samples: 55783424. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 00:15:17,816][286098] Avg episode reward: [(0, '4558.809')] [2023-03-08 00:15:20,745][286389] Updated weights for policy 0, policy_version 109040 (0.0004) [2023-03-08 00:15:22,816][286098] Fps is (10 sec: 12288.0, 60 sec: 12083.2, 300 sec: 11593.8). Total num frames: 55853056. Throughput: 0: 12072.2. Samples: 55820220. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 00:15:22,816][286098] Avg episode reward: [(0, '4561.472')] [2023-03-08 00:15:24,111][286389] Updated weights for policy 0, policy_version 109120 (0.0004) [2023-03-08 00:15:27,492][286389] Updated weights for policy 0, policy_version 109200 (0.0004) [2023-03-08 00:15:27,816][286098] Fps is (10 sec: 11878.3, 60 sec: 12083.2, 300 sec: 11579.9). Total num frames: 55910400. Throughput: 0: 12078.0. Samples: 55893040. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 00:15:27,816][286098] Avg episode reward: [(0, '4551.296')] [2023-03-08 00:15:27,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000109208_55914496.pth... [2023-03-08 00:15:27,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000108504_55554048.pth [2023-03-08 00:15:30,819][286389] Updated weights for policy 0, policy_version 109280 (0.0003) [2023-03-08 00:15:32,816][286098] Fps is (10 sec: 11878.4, 60 sec: 12083.2, 300 sec: 11593.8). Total num frames: 55971840. Throughput: 0: 12065.6. Samples: 55966532. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 00:15:32,816][286098] Avg episode reward: [(0, '4552.625')] [2023-03-08 00:15:34,212][286389] Updated weights for policy 0, policy_version 109360 (0.0004) [2023-03-08 00:15:37,816][286098] Fps is (10 sec: 11878.4, 60 sec: 12014.9, 300 sec: 11593.8). Total num frames: 56029184. Throughput: 0: 12052.2. Samples: 56002200. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 00:15:37,816][286098] Avg episode reward: [(0, '4558.555')] [2023-03-08 00:15:37,848][286389] Updated weights for policy 0, policy_version 109440 (0.0005) [2023-03-08 00:15:41,555][286389] Updated weights for policy 0, policy_version 109520 (0.0005) [2023-03-08 00:15:42,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11946.7, 300 sec: 11607.6). Total num frames: 56086528. Throughput: 0: 11921.9. Samples: 56069052. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 00:15:42,816][286098] Avg episode reward: [(0, '4566.200')] [2023-03-08 00:15:42,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000109544_56086528.pth... [2023-03-08 00:15:42,823][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000108848_55730176.pth [2023-03-08 00:15:45,170][286389] Updated weights for policy 0, policy_version 109600 (0.0004) [2023-03-08 00:15:47,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11878.4, 300 sec: 11607.6). Total num frames: 56143872. Throughput: 0: 11837.9. Samples: 56136476. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 00:15:47,816][286098] Avg episode reward: [(0, '4546.609')] [2023-03-08 00:15:48,787][286389] Updated weights for policy 0, policy_version 109680 (0.0005) [2023-03-08 00:15:52,436][286389] Updated weights for policy 0, policy_version 109760 (0.0005) [2023-03-08 00:15:52,816][286098] Fps is (10 sec: 11468.9, 60 sec: 11810.1, 300 sec: 11593.8). Total num frames: 56201216. Throughput: 0: 11855.7. Samples: 56170980. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 00:15:52,827][286098] Avg episode reward: [(0, '4553.861')] [2023-03-08 00:15:56,051][286389] Updated weights for policy 0, policy_version 109840 (0.0004) [2023-03-08 00:15:57,816][286098] Fps is (10 sec: 11059.1, 60 sec: 11741.9, 300 sec: 11579.9). Total num frames: 56254464. Throughput: 0: 11735.3. Samples: 56238144. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 00:15:57,827][286098] Avg episode reward: [(0, '4555.347')] [2023-03-08 00:15:57,872][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000109880_56258560.pth... [2023-03-08 00:15:57,874][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000109208_55914496.pth [2023-03-08 00:15:59,752][286389] Updated weights for policy 0, policy_version 109920 (0.0003) [2023-03-08 00:16:02,816][286098] Fps is (10 sec: 11059.1, 60 sec: 11673.6, 300 sec: 11579.9). Total num frames: 56311808. Throughput: 0: 11589.8. Samples: 56304964. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 00:16:02,827][286098] Avg episode reward: [(0, '4556.515')] [2023-03-08 00:16:03,386][286389] Updated weights for policy 0, policy_version 110000 (0.0005) [2023-03-08 00:16:06,994][286389] Updated weights for policy 0, policy_version 110080 (0.0005) [2023-03-08 00:16:07,816][286098] Fps is (10 sec: 11468.9, 60 sec: 11673.6, 300 sec: 11566.0). Total num frames: 56369152. Throughput: 0: 11535.4. Samples: 56339312. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 00:16:07,827][286098] Avg episode reward: [(0, '4536.121')] [2023-03-08 00:16:10,632][286389] Updated weights for policy 0, policy_version 110160 (0.0005) [2023-03-08 00:16:12,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11605.3, 300 sec: 11552.1). Total num frames: 56426496. Throughput: 0: 11412.6. Samples: 56406608. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 00:16:12,827][286098] Avg episode reward: [(0, '4567.027')] [2023-03-08 00:16:12,830][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000110208_56426496.pth... [2023-03-08 00:16:12,832][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000109544_56086528.pth [2023-03-08 00:16:14,284][286389] Updated weights for policy 0, policy_version 110240 (0.0005) [2023-03-08 00:16:17,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11468.8, 300 sec: 11538.2). Total num frames: 56479744. Throughput: 0: 11292.9. Samples: 56474712. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 00:16:17,816][286098] Avg episode reward: [(0, '4568.871')] [2023-03-08 00:16:17,910][286389] Updated weights for policy 0, policy_version 110320 (0.0005) [2023-03-08 00:16:21,587][286389] Updated weights for policy 0, policy_version 110400 (0.0005) [2023-03-08 00:16:22,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11400.5, 300 sec: 11538.2). Total num frames: 56537088. Throughput: 0: 11249.4. Samples: 56508424. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 00:16:22,816][286098] Avg episode reward: [(0, '4545.295')] [2023-03-08 00:16:25,324][286389] Updated weights for policy 0, policy_version 110480 (0.0005) [2023-03-08 00:16:27,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11332.3, 300 sec: 11524.3). Total num frames: 56590336. Throughput: 0: 11221.4. Samples: 56574016. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 00:16:27,816][286098] Avg episode reward: [(0, '4523.221')] [2023-03-08 00:16:27,821][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000110528_56590336.pth... [2023-03-08 00:16:27,824][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000109880_56258560.pth [2023-03-08 00:16:29,034][286389] Updated weights for policy 0, policy_version 110560 (0.0005) [2023-03-08 00:16:32,741][286389] Updated weights for policy 0, policy_version 110640 (0.0005) [2023-03-08 00:16:32,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11264.0, 300 sec: 11524.3). Total num frames: 56647680. Throughput: 0: 11190.2. Samples: 56640036. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 00:16:32,816][286098] Avg episode reward: [(0, '4530.483')] [2023-03-08 00:16:36,376][286389] Updated weights for policy 0, policy_version 110720 (0.0005) [2023-03-08 00:16:37,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11264.0, 300 sec: 11524.3). Total num frames: 56705024. Throughput: 0: 11171.9. Samples: 56673716. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 00:16:37,816][286098] Avg episode reward: [(0, '4546.943')] [2023-03-08 00:16:39,803][286389] Updated weights for policy 0, policy_version 110800 (0.0004) [2023-03-08 00:16:42,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11264.0, 300 sec: 11538.2). Total num frames: 56762368. Throughput: 0: 11249.0. Samples: 56744348. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 00:16:42,816][286098] Avg episode reward: [(0, '4444.498')] [2023-03-08 00:16:42,821][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000110864_56762368.pth... [2023-03-08 00:16:42,823][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000110208_56426496.pth [2023-03-08 00:16:43,270][286389] Updated weights for policy 0, policy_version 110880 (0.0004) [2023-03-08 00:16:46,840][286389] Updated weights for policy 0, policy_version 110960 (0.0005) [2023-03-08 00:16:47,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11264.0, 300 sec: 11538.2). Total num frames: 56819712. Throughput: 0: 11321.3. Samples: 56814424. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 00:16:47,816][286098] Avg episode reward: [(0, '4550.438')] [2023-03-08 00:16:50,540][286389] Updated weights for policy 0, policy_version 111040 (0.0004) [2023-03-08 00:16:52,816][286098] Fps is (10 sec: 11468.9, 60 sec: 11264.0, 300 sec: 11552.1). Total num frames: 56877056. Throughput: 0: 11296.8. Samples: 56847668. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 00:16:52,816][286098] Avg episode reward: [(0, '4485.925')] [2023-03-08 00:16:54,272][286389] Updated weights for policy 0, policy_version 111120 (0.0005) [2023-03-08 00:16:57,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11264.0, 300 sec: 11524.3). Total num frames: 56930304. Throughput: 0: 11262.2. Samples: 56913408. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 00:16:57,816][286098] Avg episode reward: [(0, '4458.971')] [2023-03-08 00:16:57,821][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000111192_56930304.pth... [2023-03-08 00:16:57,823][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000110528_56590336.pth [2023-03-08 00:16:57,950][286389] Updated weights for policy 0, policy_version 111200 (0.0005) [2023-03-08 00:17:01,634][286389] Updated weights for policy 0, policy_version 111280 (0.0005) [2023-03-08 00:17:02,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11264.0, 300 sec: 11538.2). Total num frames: 56987648. Throughput: 0: 11221.3. Samples: 56979668. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 00:17:02,816][286098] Avg episode reward: [(0, '4375.001')] [2023-03-08 00:17:05,304][286389] Updated weights for policy 0, policy_version 111360 (0.0005) [2023-03-08 00:17:07,816][286098] Fps is (10 sec: 11059.4, 60 sec: 11195.8, 300 sec: 11524.3). Total num frames: 57040896. Throughput: 0: 11223.8. Samples: 57013492. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 00:17:07,816][286098] Avg episode reward: [(0, '4531.487')] [2023-03-08 00:17:08,927][286389] Updated weights for policy 0, policy_version 111440 (0.0005) [2023-03-08 00:17:12,606][286389] Updated weights for policy 0, policy_version 111520 (0.0005) [2023-03-08 00:17:12,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11195.7, 300 sec: 11524.3). Total num frames: 57098240. Throughput: 0: 11285.3. Samples: 57081856. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 00:17:12,816][286098] Avg episode reward: [(0, '4548.843')] [2023-03-08 00:17:12,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000111520_57098240.pth... [2023-03-08 00:17:12,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000110864_56762368.pth [2023-03-08 00:17:16,258][286389] Updated weights for policy 0, policy_version 111600 (0.0005) [2023-03-08 00:17:17,816][286098] Fps is (10 sec: 11468.7, 60 sec: 11264.0, 300 sec: 11524.3). Total num frames: 57155584. Throughput: 0: 11291.3. Samples: 57148144. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 00:17:17,816][286098] Avg episode reward: [(0, '4507.377')] [2023-03-08 00:17:19,895][286389] Updated weights for policy 0, policy_version 111680 (0.0005) [2023-03-08 00:17:22,816][286098] Fps is (10 sec: 11468.9, 60 sec: 11264.0, 300 sec: 11524.3). Total num frames: 57212928. Throughput: 0: 11300.7. Samples: 57182244. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 00:17:22,827][286098] Avg episode reward: [(0, '4436.608')] [2023-03-08 00:17:23,487][286389] Updated weights for policy 0, policy_version 111760 (0.0004) [2023-03-08 00:17:27,070][286389] Updated weights for policy 0, policy_version 111840 (0.0004) [2023-03-08 00:17:27,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11264.0, 300 sec: 11524.3). Total num frames: 57266176. Throughput: 0: 11257.3. Samples: 57250924. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 00:17:27,827][286098] Avg episode reward: [(0, '4520.978')] [2023-03-08 00:17:27,829][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000111856_57270272.pth... [2023-03-08 00:17:27,831][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000111192_56930304.pth [2023-03-08 00:17:30,674][286389] Updated weights for policy 0, policy_version 111920 (0.0005) [2023-03-08 00:17:32,816][286098] Fps is (10 sec: 11059.1, 60 sec: 11264.0, 300 sec: 11524.3). Total num frames: 57323520. Throughput: 0: 11198.2. Samples: 57318344. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 00:17:32,816][286098] Avg episode reward: [(0, '4530.089')] [2023-03-08 00:17:34,359][286389] Updated weights for policy 0, policy_version 112000 (0.0005) [2023-03-08 00:17:37,816][286098] Fps is (10 sec: 11468.7, 60 sec: 11264.0, 300 sec: 11524.3). Total num frames: 57380864. Throughput: 0: 11213.1. Samples: 57352256. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 00:17:37,817][286098] Avg episode reward: [(0, '4564.156')] [2023-03-08 00:17:38,022][286389] Updated weights for policy 0, policy_version 112080 (0.0005) [2023-03-08 00:17:41,662][286389] Updated weights for policy 0, policy_version 112160 (0.0005) [2023-03-08 00:17:42,816][286098] Fps is (10 sec: 11468.7, 60 sec: 11264.0, 300 sec: 11524.3). Total num frames: 57438208. Throughput: 0: 11247.7. Samples: 57419556. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 00:17:42,817][286098] Avg episode reward: [(0, '4567.580')] [2023-03-08 00:17:42,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000112184_57438208.pth... [2023-03-08 00:17:42,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000111520_57098240.pth [2023-03-08 00:17:45,409][286389] Updated weights for policy 0, policy_version 112240 (0.0005) [2023-03-08 00:17:47,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11264.0, 300 sec: 11524.3). Total num frames: 57495552. Throughput: 0: 11276.6. Samples: 57487116. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 00:17:47,816][286098] Avg episode reward: [(0, '4574.908')] [2023-03-08 00:17:48,789][286389] Updated weights for policy 0, policy_version 112320 (0.0005) [2023-03-08 00:17:52,251][286389] Updated weights for policy 0, policy_version 112400 (0.0005) [2023-03-08 00:17:52,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11264.0, 300 sec: 11538.2). Total num frames: 57552896. Throughput: 0: 11331.9. Samples: 57523428. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 00:17:52,816][286098] Avg episode reward: [(0, '4480.990')] [2023-03-08 00:17:55,920][286389] Updated weights for policy 0, policy_version 112480 (0.0005) [2023-03-08 00:17:57,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11332.3, 300 sec: 11538.2). Total num frames: 57610240. Throughput: 0: 11323.9. Samples: 57591432. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 00:17:57,816][286098] Avg episode reward: [(0, '4558.247')] [2023-03-08 00:17:57,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000112520_57610240.pth... [2023-03-08 00:17:57,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000111856_57270272.pth [2023-03-08 00:17:59,527][286389] Updated weights for policy 0, policy_version 112560 (0.0005) [2023-03-08 00:18:02,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11264.0, 300 sec: 11524.3). Total num frames: 57663488. Throughput: 0: 11361.1. Samples: 57659392. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 00:18:02,816][286098] Avg episode reward: [(0, '4497.348')] [2023-03-08 00:18:03,250][286389] Updated weights for policy 0, policy_version 112640 (0.0005) [2023-03-08 00:18:06,971][286389] Updated weights for policy 0, policy_version 112720 (0.0005) [2023-03-08 00:18:07,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11332.2, 300 sec: 11538.2). Total num frames: 57720832. Throughput: 0: 11331.4. Samples: 57692160. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 00:18:07,816][286098] Avg episode reward: [(0, '4562.409')] [2023-03-08 00:18:10,433][286389] Updated weights for policy 0, policy_version 112800 (0.0005) [2023-03-08 00:18:12,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11400.5, 300 sec: 11538.2). Total num frames: 57782272. Throughput: 0: 11341.9. Samples: 57761312. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:18:12,816][286098] Avg episode reward: [(0, '4440.258')] [2023-03-08 00:18:12,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000112856_57782272.pth... [2023-03-08 00:18:12,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000112184_57438208.pth [2023-03-08 00:18:13,787][286389] Updated weights for policy 0, policy_version 112880 (0.0004) [2023-03-08 00:18:17,130][286389] Updated weights for policy 0, policy_version 112960 (0.0005) [2023-03-08 00:18:17,816][286098] Fps is (10 sec: 12288.0, 60 sec: 11468.8, 300 sec: 11538.2). Total num frames: 57843712. Throughput: 0: 11478.5. Samples: 57834876. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:18:17,816][286098] Avg episode reward: [(0, '4444.520')] [2023-03-08 00:18:20,390][286389] Updated weights for policy 0, policy_version 113040 (0.0005) [2023-03-08 00:18:22,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11468.8, 300 sec: 11524.3). Total num frames: 57901056. Throughput: 0: 11559.8. Samples: 57872448. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:18:22,816][286098] Avg episode reward: [(0, '4386.903')] [2023-03-08 00:18:23,994][286389] Updated weights for policy 0, policy_version 113120 (0.0005) [2023-03-08 00:18:27,683][286389] Updated weights for policy 0, policy_version 113200 (0.0005) [2023-03-08 00:18:27,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11537.0, 300 sec: 11510.5). Total num frames: 57958400. Throughput: 0: 11584.2. Samples: 57940844. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:18:27,816][286098] Avg episode reward: [(0, '4121.543')] [2023-03-08 00:18:27,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000113200_57958400.pth... [2023-03-08 00:18:27,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000112520_57610240.pth [2023-03-08 00:18:30,975][286389] Updated weights for policy 0, policy_version 113280 (0.0003) [2023-03-08 00:18:32,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11605.3, 300 sec: 11524.3). Total num frames: 58019840. Throughput: 0: 11668.5. Samples: 58012200. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:18:32,816][286098] Avg episode reward: [(0, '4117.488')] [2023-03-08 00:18:34,312][286389] Updated weights for policy 0, policy_version 113360 (0.0004) [2023-03-08 00:18:37,717][286389] Updated weights for policy 0, policy_version 113440 (0.0003) [2023-03-08 00:18:37,816][286098] Fps is (10 sec: 12288.0, 60 sec: 11673.6, 300 sec: 11538.2). Total num frames: 58081280. Throughput: 0: 11678.2. Samples: 58048948. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:18:37,816][286098] Avg episode reward: [(0, '4108.173')] [2023-03-08 00:18:41,079][286389] Updated weights for policy 0, policy_version 113520 (0.0004) [2023-03-08 00:18:42,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11673.6, 300 sec: 11538.2). Total num frames: 58138624. Throughput: 0: 11795.9. Samples: 58122248. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:18:42,816][286098] Avg episode reward: [(0, '4150.435')] [2023-03-08 00:18:42,847][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000113560_58142720.pth... [2023-03-08 00:18:42,850][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000112856_57782272.pth [2023-03-08 00:18:44,483][286389] Updated weights for policy 0, policy_version 113600 (0.0004) [2023-03-08 00:18:47,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11741.9, 300 sec: 11566.0). Total num frames: 58200064. Throughput: 0: 11834.3. Samples: 58191936. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:18:47,816][286098] Avg episode reward: [(0, '4021.447')] [2023-03-08 00:18:48,143][286389] Updated weights for policy 0, policy_version 113680 (0.0005) [2023-03-08 00:18:51,814][286389] Updated weights for policy 0, policy_version 113760 (0.0005) [2023-03-08 00:18:52,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11673.6, 300 sec: 11552.1). Total num frames: 58253312. Throughput: 0: 11849.1. Samples: 58225368. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:18:52,816][286098] Avg episode reward: [(0, '4209.585')] [2023-03-08 00:18:55,376][286389] Updated weights for policy 0, policy_version 113840 (0.0005) [2023-03-08 00:18:57,816][286098] Fps is (10 sec: 11059.1, 60 sec: 11673.6, 300 sec: 11566.0). Total num frames: 58310656. Throughput: 0: 11844.1. Samples: 58294296. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:18:57,816][286098] Avg episode reward: [(0, '4201.099')] [2023-03-08 00:18:57,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000113888_58310656.pth... [2023-03-08 00:18:57,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000113200_57958400.pth [2023-03-08 00:18:58,991][286389] Updated weights for policy 0, policy_version 113920 (0.0005) [2023-03-08 00:19:02,538][286389] Updated weights for policy 0, policy_version 114000 (0.0004) [2023-03-08 00:19:02,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11741.9, 300 sec: 11566.0). Total num frames: 58368000. Throughput: 0: 11717.2. Samples: 58362148. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:19:02,816][286098] Avg episode reward: [(0, '4301.912')] [2023-03-08 00:19:06,052][286389] Updated weights for policy 0, policy_version 114080 (0.0003) [2023-03-08 00:19:07,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11810.1, 300 sec: 11579.9). Total num frames: 58429440. Throughput: 0: 11651.0. Samples: 58396744. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:19:07,816][286098] Avg episode reward: [(0, '4470.242')] [2023-03-08 00:19:09,508][286389] Updated weights for policy 0, policy_version 114160 (0.0004) [2023-03-08 00:19:12,816][286098] Fps is (10 sec: 11878.5, 60 sec: 11741.9, 300 sec: 11593.8). Total num frames: 58486784. Throughput: 0: 11734.2. Samples: 58468880. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:19:12,816][286098] Avg episode reward: [(0, '4467.145')] [2023-03-08 00:19:12,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000114232_58486784.pth... [2023-03-08 00:19:12,821][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000113560_58142720.pth [2023-03-08 00:19:12,885][286389] Updated weights for policy 0, policy_version 114240 (0.0003) [2023-03-08 00:19:16,406][286389] Updated weights for policy 0, policy_version 114320 (0.0005) [2023-03-08 00:19:17,816][286098] Fps is (10 sec: 11468.9, 60 sec: 11673.6, 300 sec: 11579.9). Total num frames: 58544128. Throughput: 0: 11729.9. Samples: 58540044. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:19:17,816][286098] Avg episode reward: [(0, '4523.995')] [2023-03-08 00:19:20,016][286389] Updated weights for policy 0, policy_version 114400 (0.0005) [2023-03-08 00:19:22,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11673.6, 300 sec: 11579.9). Total num frames: 58601472. Throughput: 0: 11645.9. Samples: 58573012. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:19:22,816][286098] Avg episode reward: [(0, '4543.550')] [2023-03-08 00:19:23,499][286389] Updated weights for policy 0, policy_version 114480 (0.0005) [2023-03-08 00:19:27,050][286389] Updated weights for policy 0, policy_version 114560 (0.0005) [2023-03-08 00:19:27,816][286098] Fps is (10 sec: 11878.3, 60 sec: 11741.9, 300 sec: 11579.9). Total num frames: 58662912. Throughput: 0: 11580.5. Samples: 58643372. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:19:27,816][286098] Avg episode reward: [(0, '4578.603')] [2023-03-08 00:19:27,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000114576_58662912.pth... [2023-03-08 00:19:27,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000113888_58310656.pth [2023-03-08 00:19:30,588][286389] Updated weights for policy 0, policy_version 114640 (0.0004) [2023-03-08 00:19:32,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11605.3, 300 sec: 11552.1). Total num frames: 58716160. Throughput: 0: 11559.8. Samples: 58712128. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:19:32,816][286098] Avg episode reward: [(0, '4530.917')] [2023-03-08 00:19:34,316][286389] Updated weights for policy 0, policy_version 114720 (0.0004) [2023-03-08 00:19:37,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11537.1, 300 sec: 11538.2). Total num frames: 58773504. Throughput: 0: 11543.8. Samples: 58744840. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:19:37,816][286098] Avg episode reward: [(0, '4496.377')] [2023-03-08 00:19:38,056][286389] Updated weights for policy 0, policy_version 114800 (0.0005) [2023-03-08 00:19:41,770][286389] Updated weights for policy 0, policy_version 114880 (0.0005) [2023-03-08 00:19:42,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11468.8, 300 sec: 11510.5). Total num frames: 58826752. Throughput: 0: 11469.9. Samples: 58810440. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:19:42,816][286098] Avg episode reward: [(0, '4464.440')] [2023-03-08 00:19:42,878][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000114904_58830848.pth... [2023-03-08 00:19:42,879][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000114232_58486784.pth [2023-03-08 00:19:45,323][286389] Updated weights for policy 0, policy_version 114960 (0.0005) [2023-03-08 00:19:47,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11468.8, 300 sec: 11510.5). Total num frames: 58888192. Throughput: 0: 11492.1. Samples: 58879292. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:19:47,816][286098] Avg episode reward: [(0, '4566.645')] [2023-03-08 00:19:48,869][286389] Updated weights for policy 0, policy_version 115040 (0.0004) [2023-03-08 00:19:52,358][286389] Updated weights for policy 0, policy_version 115120 (0.0003) [2023-03-08 00:19:52,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11537.1, 300 sec: 11510.5). Total num frames: 58945536. Throughput: 0: 11503.8. Samples: 58914416. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:19:52,816][286098] Avg episode reward: [(0, '4544.061')] [2023-03-08 00:19:55,866][286389] Updated weights for policy 0, policy_version 115200 (0.0003) [2023-03-08 00:19:57,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11537.1, 300 sec: 11496.6). Total num frames: 59002880. Throughput: 0: 11462.9. Samples: 58984712. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:19:57,816][286098] Avg episode reward: [(0, '4531.414')] [2023-03-08 00:19:57,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000115240_59002880.pth... [2023-03-08 00:19:57,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000114576_58662912.pth [2023-03-08 00:19:59,198][286389] Updated weights for policy 0, policy_version 115280 (0.0003) [2023-03-08 00:20:02,734][286389] Updated weights for policy 0, policy_version 115360 (0.0004) [2023-03-08 00:20:02,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11605.3, 300 sec: 11510.5). Total num frames: 59064320. Throughput: 0: 11479.0. Samples: 59056600. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:20:02,816][286098] Avg episode reward: [(0, '4445.533')] [2023-03-08 00:20:06,209][286389] Updated weights for policy 0, policy_version 115440 (0.0003) [2023-03-08 00:20:07,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11537.1, 300 sec: 11496.6). Total num frames: 59121664. Throughput: 0: 11532.4. Samples: 59091972. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:20:07,816][286098] Avg episode reward: [(0, '4497.057')] [2023-03-08 00:20:09,559][286389] Updated weights for policy 0, policy_version 115520 (0.0003) [2023-03-08 00:20:12,816][286098] Fps is (10 sec: 11878.3, 60 sec: 11605.3, 300 sec: 11496.6). Total num frames: 59183104. Throughput: 0: 11573.3. Samples: 59164172. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:20:12,816][286098] Avg episode reward: [(0, '4520.325')] [2023-03-08 00:20:12,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000115592_59183104.pth... [2023-03-08 00:20:12,823][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000114904_58830848.pth [2023-03-08 00:20:13,016][286389] Updated weights for policy 0, policy_version 115600 (0.0003) [2023-03-08 00:20:16,348][286389] Updated weights for policy 0, policy_version 115680 (0.0003) [2023-03-08 00:20:17,816][286098] Fps is (10 sec: 12288.0, 60 sec: 11673.6, 300 sec: 11496.6). Total num frames: 59244544. Throughput: 0: 11660.2. Samples: 59236836. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 00:20:17,816][286098] Avg episode reward: [(0, '4364.428')] [2023-03-08 00:20:19,823][286389] Updated weights for policy 0, policy_version 115760 (0.0004) [2023-03-08 00:20:22,816][286098] Fps is (10 sec: 11878.5, 60 sec: 11673.6, 300 sec: 11496.6). Total num frames: 59301888. Throughput: 0: 11716.6. Samples: 59272088. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 00:20:22,816][286098] Avg episode reward: [(0, '4428.292')] [2023-03-08 00:20:23,485][286389] Updated weights for policy 0, policy_version 115840 (0.0005) [2023-03-08 00:20:27,132][286389] Updated weights for policy 0, policy_version 115920 (0.0005) [2023-03-08 00:20:27,816][286098] Fps is (10 sec: 11059.0, 60 sec: 11537.0, 300 sec: 11468.8). Total num frames: 59355136. Throughput: 0: 11741.6. Samples: 59338816. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 00:20:27,817][286098] Avg episode reward: [(0, '4511.755')] [2023-03-08 00:20:27,837][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000115936_59359232.pth... [2023-03-08 00:20:27,838][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000115240_59002880.pth [2023-03-08 00:20:30,555][286389] Updated weights for policy 0, policy_version 116000 (0.0005) [2023-03-08 00:20:32,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11673.6, 300 sec: 11482.7). Total num frames: 59416576. Throughput: 0: 11789.5. Samples: 59409820. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 00:20:32,816][286098] Avg episode reward: [(0, '4522.728')] [2023-03-08 00:20:33,918][286389] Updated weights for policy 0, policy_version 116080 (0.0004) [2023-03-08 00:20:37,245][286389] Updated weights for policy 0, policy_version 116160 (0.0004) [2023-03-08 00:20:37,816][286098] Fps is (10 sec: 12288.3, 60 sec: 11741.9, 300 sec: 11496.6). Total num frames: 59478016. Throughput: 0: 11835.0. Samples: 59446992. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 00:20:37,816][286098] Avg episode reward: [(0, '4567.698')] [2023-03-08 00:20:40,622][286389] Updated weights for policy 0, policy_version 116240 (0.0003) [2023-03-08 00:20:42,816][286098] Fps is (10 sec: 12287.9, 60 sec: 11878.4, 300 sec: 11510.5). Total num frames: 59539456. Throughput: 0: 11889.9. Samples: 59519756. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 00:20:42,816][286098] Avg episode reward: [(0, '4567.882')] [2023-03-08 00:20:42,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000116288_59539456.pth... [2023-03-08 00:20:42,823][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000115592_59183104.pth [2023-03-08 00:20:44,098][286389] Updated weights for policy 0, policy_version 116320 (0.0003) [2023-03-08 00:20:47,665][286389] Updated weights for policy 0, policy_version 116400 (0.0004) [2023-03-08 00:20:47,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11810.1, 300 sec: 11510.5). Total num frames: 59596800. Throughput: 0: 11840.2. Samples: 59589408. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 00:20:47,816][286098] Avg episode reward: [(0, '4575.228')] [2023-03-08 00:20:51,348][286389] Updated weights for policy 0, policy_version 116480 (0.0005) [2023-03-08 00:20:52,816][286098] Fps is (10 sec: 11059.1, 60 sec: 11741.9, 300 sec: 11510.5). Total num frames: 59650048. Throughput: 0: 11808.2. Samples: 59623344. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 00:20:52,817][286098] Avg episode reward: [(0, '4568.783')] [2023-03-08 00:20:55,074][286389] Updated weights for policy 0, policy_version 116560 (0.0006) [2023-03-08 00:20:57,816][286098] Fps is (10 sec: 11059.1, 60 sec: 11741.9, 300 sec: 11510.5). Total num frames: 59707392. Throughput: 0: 11682.1. Samples: 59689868. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 00:20:57,816][286098] Avg episode reward: [(0, '4583.187')] [2023-03-08 00:20:57,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000116616_59707392.pth... [2023-03-08 00:20:57,823][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000115936_59359232.pth [2023-03-08 00:20:58,770][286389] Updated weights for policy 0, policy_version 116640 (0.0005) [2023-03-08 00:21:02,248][286389] Updated weights for policy 0, policy_version 116720 (0.0003) [2023-03-08 00:21:02,816][286098] Fps is (10 sec: 11468.9, 60 sec: 11673.6, 300 sec: 11510.5). Total num frames: 59764736. Throughput: 0: 11585.9. Samples: 59758200. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 00:21:02,816][286098] Avg episode reward: [(0, '4573.768')] [2023-03-08 00:21:05,683][286389] Updated weights for policy 0, policy_version 116800 (0.0003) [2023-03-08 00:21:07,816][286098] Fps is (10 sec: 11468.9, 60 sec: 11673.6, 300 sec: 11510.5). Total num frames: 59822080. Throughput: 0: 11603.1. Samples: 59794228. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 00:21:07,816][286098] Avg episode reward: [(0, '4408.522')] [2023-03-08 00:21:09,293][286389] Updated weights for policy 0, policy_version 116880 (0.0004) [2023-03-08 00:21:12,816][286098] Fps is (10 sec: 11468.7, 60 sec: 11605.3, 300 sec: 11524.3). Total num frames: 59879424. Throughput: 0: 11649.8. Samples: 59863056. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 00:21:12,816][286098] Avg episode reward: [(0, '4311.394')] [2023-03-08 00:21:12,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000116952_59879424.pth... [2023-03-08 00:21:12,823][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000116288_59539456.pth [2023-03-08 00:21:12,934][286389] Updated weights for policy 0, policy_version 116960 (0.0004) [2023-03-08 00:21:16,599][286389] Updated weights for policy 0, policy_version 117040 (0.0006) [2023-03-08 00:21:17,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11537.1, 300 sec: 11524.3). Total num frames: 59936768. Throughput: 0: 11554.4. Samples: 59929768. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 00:21:17,827][286098] Avg episode reward: [(0, '4351.423')] [2023-03-08 00:21:20,326][286389] Updated weights for policy 0, policy_version 117120 (0.0005) [2023-03-08 00:21:22,816][286098] Fps is (10 sec: 11059.3, 60 sec: 11468.8, 300 sec: 11524.3). Total num frames: 59990016. Throughput: 0: 11461.4. Samples: 59962756. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 00:21:22,827][286098] Avg episode reward: [(0, '4361.800')] [2023-03-08 00:21:24,112][286389] Updated weights for policy 0, policy_version 117200 (0.0005) [2023-03-08 00:21:27,683][286389] Updated weights for policy 0, policy_version 117280 (0.0004) [2023-03-08 00:21:27,816][286098] Fps is (10 sec: 11059.1, 60 sec: 11537.1, 300 sec: 11524.3). Total num frames: 60047360. Throughput: 0: 11294.5. Samples: 60028008. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 00:21:27,827][286098] Avg episode reward: [(0, '4535.637')] [2023-03-08 00:21:27,830][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000117280_60047360.pth... [2023-03-08 00:21:27,833][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000116616_59707392.pth [2023-03-08 00:21:31,259][286389] Updated weights for policy 0, policy_version 117360 (0.0004) [2023-03-08 00:21:32,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11468.8, 300 sec: 11524.3). Total num frames: 60104704. Throughput: 0: 11277.8. Samples: 60096908. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 00:21:32,827][286098] Avg episode reward: [(0, '4573.202')] [2023-03-08 00:21:34,910][286389] Updated weights for policy 0, policy_version 117440 (0.0005) [2023-03-08 00:21:37,816][286098] Fps is (10 sec: 11059.1, 60 sec: 11332.2, 300 sec: 11510.5). Total num frames: 60157952. Throughput: 0: 11283.2. Samples: 60131088. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 00:21:37,827][286098] Avg episode reward: [(0, '4584.427')] [2023-03-08 00:21:38,616][286389] Updated weights for policy 0, policy_version 117520 (0.0005) [2023-03-08 00:21:42,326][286389] Updated weights for policy 0, policy_version 117600 (0.0004) [2023-03-08 00:21:42,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11264.0, 300 sec: 11510.5). Total num frames: 60215296. Throughput: 0: 11276.7. Samples: 60197320. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 00:21:42,827][286098] Avg episode reward: [(0, '4548.637')] [2023-03-08 00:21:42,831][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000117608_60215296.pth... [2023-03-08 00:21:42,833][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000116952_59879424.pth [2023-03-08 00:21:45,775][286389] Updated weights for policy 0, policy_version 117680 (0.0004) [2023-03-08 00:21:47,816][286098] Fps is (10 sec: 11469.0, 60 sec: 11264.0, 300 sec: 11510.5). Total num frames: 60272640. Throughput: 0: 11319.3. Samples: 60267568. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 00:21:47,827][286098] Avg episode reward: [(0, '4570.165')] [2023-03-08 00:21:49,273][286389] Updated weights for policy 0, policy_version 117760 (0.0003) [2023-03-08 00:21:52,776][286389] Updated weights for policy 0, policy_version 117840 (0.0005) [2023-03-08 00:21:52,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11400.5, 300 sec: 11538.2). Total num frames: 60334080. Throughput: 0: 11293.2. Samples: 60302420. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 00:21:52,816][286098] Avg episode reward: [(0, '4479.355')] [2023-03-08 00:21:56,160][286389] Updated weights for policy 0, policy_version 117920 (0.0004) [2023-03-08 00:21:57,816][286098] Fps is (10 sec: 11878.3, 60 sec: 11400.5, 300 sec: 11538.2). Total num frames: 60391424. Throughput: 0: 11349.1. Samples: 60373764. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 00:21:57,827][286098] Avg episode reward: [(0, '4556.279')] [2023-03-08 00:21:57,830][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000117952_60391424.pth... [2023-03-08 00:21:57,833][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000117280_60047360.pth [2023-03-08 00:21:59,620][286389] Updated weights for policy 0, policy_version 118000 (0.0005) [2023-03-08 00:22:02,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11468.8, 300 sec: 11566.0). Total num frames: 60452864. Throughput: 0: 11443.7. Samples: 60444736. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 00:22:02,816][286098] Avg episode reward: [(0, '4533.627')] [2023-03-08 00:22:03,040][286389] Updated weights for policy 0, policy_version 118080 (0.0004) [2023-03-08 00:22:06,533][286389] Updated weights for policy 0, policy_version 118160 (0.0005) [2023-03-08 00:22:07,816][286098] Fps is (10 sec: 11878.5, 60 sec: 11468.8, 300 sec: 11566.0). Total num frames: 60510208. Throughput: 0: 11510.1. Samples: 60480712. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 00:22:07,816][286098] Avg episode reward: [(0, '4577.219')] [2023-03-08 00:22:10,176][286389] Updated weights for policy 0, policy_version 118240 (0.0005) [2023-03-08 00:22:12,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11468.8, 300 sec: 11566.0). Total num frames: 60567552. Throughput: 0: 11562.3. Samples: 60548312. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 00:22:12,816][286098] Avg episode reward: [(0, '4533.518')] [2023-03-08 00:22:12,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000118296_60567552.pth... [2023-03-08 00:22:12,821][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000117608_60215296.pth [2023-03-08 00:22:13,831][286389] Updated weights for policy 0, policy_version 118320 (0.0005) [2023-03-08 00:22:17,285][286389] Updated weights for policy 0, policy_version 118400 (0.0005) [2023-03-08 00:22:17,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11468.8, 300 sec: 11566.0). Total num frames: 60624896. Throughput: 0: 11575.3. Samples: 60617796. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:22:17,816][286098] Avg episode reward: [(0, '4570.253')] [2023-03-08 00:22:20,720][286389] Updated weights for policy 0, policy_version 118480 (0.0005) [2023-03-08 00:22:22,816][286098] Fps is (10 sec: 11468.9, 60 sec: 11537.1, 300 sec: 11579.9). Total num frames: 60682240. Throughput: 0: 11612.3. Samples: 60653640. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:22:22,816][286098] Avg episode reward: [(0, '4543.925')] [2023-03-08 00:22:24,238][286389] Updated weights for policy 0, policy_version 118560 (0.0005) [2023-03-08 00:22:27,719][286389] Updated weights for policy 0, policy_version 118640 (0.0005) [2023-03-08 00:22:27,816][286098] Fps is (10 sec: 11878.3, 60 sec: 11605.3, 300 sec: 11593.8). Total num frames: 60743680. Throughput: 0: 11703.7. Samples: 60723988. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:22:27,816][286098] Avg episode reward: [(0, '4573.836')] [2023-03-08 00:22:27,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000118640_60743680.pth... [2023-03-08 00:22:27,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000117952_60391424.pth [2023-03-08 00:22:31,088][286389] Updated weights for policy 0, policy_version 118720 (0.0004) [2023-03-08 00:22:32,816][286098] Fps is (10 sec: 12287.9, 60 sec: 11673.6, 300 sec: 11607.6). Total num frames: 60805120. Throughput: 0: 11747.1. Samples: 60796188. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:22:32,817][286098] Avg episode reward: [(0, '4570.280')] [2023-03-08 00:22:34,481][286389] Updated weights for policy 0, policy_version 118800 (0.0004) [2023-03-08 00:22:37,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11741.9, 300 sec: 11607.6). Total num frames: 60862464. Throughput: 0: 11784.8. Samples: 60832736. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:22:37,816][286098] Avg episode reward: [(0, '4539.648')] [2023-03-08 00:22:37,900][286389] Updated weights for policy 0, policy_version 118880 (0.0004) [2023-03-08 00:22:41,372][286389] Updated weights for policy 0, policy_version 118960 (0.0005) [2023-03-08 00:22:42,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11810.1, 300 sec: 11621.5). Total num frames: 60923904. Throughput: 0: 11773.2. Samples: 60903560. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:22:42,816][286098] Avg episode reward: [(0, '4568.921')] [2023-03-08 00:22:42,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000118992_60923904.pth... [2023-03-08 00:22:42,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000118296_60567552.pth [2023-03-08 00:22:44,737][286389] Updated weights for policy 0, policy_version 119040 (0.0004) [2023-03-08 00:22:47,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11810.1, 300 sec: 11621.5). Total num frames: 60981248. Throughput: 0: 11798.6. Samples: 60975672. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:22:47,816][286098] Avg episode reward: [(0, '4568.954')] [2023-03-08 00:22:48,264][286389] Updated weights for policy 0, policy_version 119120 (0.0005) [2023-03-08 00:22:51,704][286389] Updated weights for policy 0, policy_version 119200 (0.0004) [2023-03-08 00:22:52,816][286098] Fps is (10 sec: 11878.5, 60 sec: 11810.1, 300 sec: 11635.4). Total num frames: 61042688. Throughput: 0: 11773.7. Samples: 61010528. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:22:52,816][286098] Avg episode reward: [(0, '4571.821')] [2023-03-08 00:22:55,196][286389] Updated weights for policy 0, policy_version 119280 (0.0005) [2023-03-08 00:22:57,816][286098] Fps is (10 sec: 11878.3, 60 sec: 11810.1, 300 sec: 11649.3). Total num frames: 61100032. Throughput: 0: 11839.5. Samples: 61081092. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:22:57,817][286098] Avg episode reward: [(0, '4576.013')] [2023-03-08 00:22:57,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000119336_61100032.pth... [2023-03-08 00:22:57,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000118640_60743680.pth [2023-03-08 00:22:58,718][286389] Updated weights for policy 0, policy_version 119360 (0.0005) [2023-03-08 00:23:02,103][286389] Updated weights for policy 0, policy_version 119440 (0.0004) [2023-03-08 00:23:02,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11810.1, 300 sec: 11663.2). Total num frames: 61161472. Throughput: 0: 11899.4. Samples: 61153268. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:23:02,816][286098] Avg episode reward: [(0, '4559.464')] [2023-03-08 00:23:05,541][286389] Updated weights for policy 0, policy_version 119520 (0.0005) [2023-03-08 00:23:07,816][286098] Fps is (10 sec: 11878.5, 60 sec: 11810.1, 300 sec: 11649.3). Total num frames: 61218816. Throughput: 0: 11883.1. Samples: 61188380. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:23:07,816][286098] Avg episode reward: [(0, '4567.677')] [2023-03-08 00:23:08,971][286389] Updated weights for policy 0, policy_version 119600 (0.0004) [2023-03-08 00:23:12,411][286389] Updated weights for policy 0, policy_version 119680 (0.0005) [2023-03-08 00:23:12,816][286098] Fps is (10 sec: 11878.3, 60 sec: 11878.4, 300 sec: 11649.3). Total num frames: 61280256. Throughput: 0: 11908.0. Samples: 61259848. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:23:12,827][286098] Avg episode reward: [(0, '4572.556')] [2023-03-08 00:23:12,830][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000119688_61280256.pth... [2023-03-08 00:23:12,833][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000118992_60923904.pth [2023-03-08 00:23:15,900][286389] Updated weights for policy 0, policy_version 119760 (0.0005) [2023-03-08 00:23:17,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11878.4, 300 sec: 11649.3). Total num frames: 61337600. Throughput: 0: 11892.4. Samples: 61331344. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:23:17,827][286098] Avg episode reward: [(0, '4575.469')] [2023-03-08 00:23:19,303][286389] Updated weights for policy 0, policy_version 119840 (0.0004) [2023-03-08 00:23:22,755][286389] Updated weights for policy 0, policy_version 119920 (0.0004) [2023-03-08 00:23:22,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11946.7, 300 sec: 11663.2). Total num frames: 61399040. Throughput: 0: 11869.5. Samples: 61366864. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 00:23:22,827][286098] Avg episode reward: [(0, '4570.565')] [2023-03-08 00:23:26,244][286389] Updated weights for policy 0, policy_version 120000 (0.0005) [2023-03-08 00:23:27,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11878.4, 300 sec: 11649.3). Total num frames: 61456384. Throughput: 0: 11872.4. Samples: 61437816. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 00:23:27,827][286098] Avg episode reward: [(0, '4562.918')] [2023-03-08 00:23:27,830][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000120032_61456384.pth... [2023-03-08 00:23:27,832][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000119336_61100032.pth [2023-03-08 00:23:29,651][286389] Updated weights for policy 0, policy_version 120080 (0.0004) [2023-03-08 00:23:32,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11878.4, 300 sec: 11649.3). Total num frames: 61517824. Throughput: 0: 11866.0. Samples: 61509640. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 00:23:32,816][286098] Avg episode reward: [(0, '4506.578')] [2023-03-08 00:23:33,141][286389] Updated weights for policy 0, policy_version 120160 (0.0005) [2023-03-08 00:23:36,643][286389] Updated weights for policy 0, policy_version 120240 (0.0005) [2023-03-08 00:23:37,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11878.4, 300 sec: 11649.3). Total num frames: 61575168. Throughput: 0: 11888.4. Samples: 61545508. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 00:23:37,816][286098] Avg episode reward: [(0, '4544.766')] [2023-03-08 00:23:40,326][286389] Updated weights for policy 0, policy_version 120320 (0.0005) [2023-03-08 00:23:42,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11741.9, 300 sec: 11621.5). Total num frames: 61628416. Throughput: 0: 11800.3. Samples: 61612104. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 00:23:42,816][286098] Avg episode reward: [(0, '4516.542')] [2023-03-08 00:23:42,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000120368_61628416.pth... [2023-03-08 00:23:42,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000119688_61280256.pth [2023-03-08 00:23:43,965][286389] Updated weights for policy 0, policy_version 120400 (0.0005) [2023-03-08 00:23:47,421][286389] Updated weights for policy 0, policy_version 120480 (0.0005) [2023-03-08 00:23:47,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11810.1, 300 sec: 11649.3). Total num frames: 61689856. Throughput: 0: 11742.1. Samples: 61681664. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 00:23:47,816][286098] Avg episode reward: [(0, '4394.461')] [2023-03-08 00:23:50,827][286389] Updated weights for policy 0, policy_version 120560 (0.0004) [2023-03-08 00:23:52,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11741.9, 300 sec: 11649.3). Total num frames: 61747200. Throughput: 0: 11766.7. Samples: 61717880. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 00:23:52,816][286098] Avg episode reward: [(0, '4549.681')] [2023-03-08 00:23:54,277][286389] Updated weights for policy 0, policy_version 120640 (0.0004) [2023-03-08 00:23:57,705][286389] Updated weights for policy 0, policy_version 120720 (0.0005) [2023-03-08 00:23:57,816][286098] Fps is (10 sec: 11878.3, 60 sec: 11810.1, 300 sec: 11663.2). Total num frames: 61808640. Throughput: 0: 11752.7. Samples: 61788720. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 00:23:57,816][286098] Avg episode reward: [(0, '4545.096')] [2023-03-08 00:23:57,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000120720_61808640.pth... [2023-03-08 00:23:57,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000120032_61456384.pth [2023-03-08 00:24:01,161][286389] Updated weights for policy 0, policy_version 120800 (0.0005) [2023-03-08 00:24:02,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11741.9, 300 sec: 11649.3). Total num frames: 61865984. Throughput: 0: 11753.7. Samples: 61860260. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 00:24:02,816][286098] Avg episode reward: [(0, '4540.543')] [2023-03-08 00:24:04,590][286389] Updated weights for policy 0, policy_version 120880 (0.0004) [2023-03-08 00:24:07,816][286098] Fps is (10 sec: 11878.5, 60 sec: 11810.1, 300 sec: 11663.2). Total num frames: 61927424. Throughput: 0: 11760.7. Samples: 61896096. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 00:24:07,816][286098] Avg episode reward: [(0, '4438.100')] [2023-03-08 00:24:08,076][286389] Updated weights for policy 0, policy_version 120960 (0.0005) [2023-03-08 00:24:11,741][286389] Updated weights for policy 0, policy_version 121040 (0.0006) [2023-03-08 00:24:12,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11673.6, 300 sec: 11649.3). Total num frames: 61980672. Throughput: 0: 11708.5. Samples: 61964700. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 00:24:12,816][286098] Avg episode reward: [(0, '4430.319')] [2023-03-08 00:24:12,843][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000121064_61984768.pth... [2023-03-08 00:24:12,844][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000120368_61628416.pth [2023-03-08 00:24:15,474][286389] Updated weights for policy 0, policy_version 121120 (0.0005) [2023-03-08 00:24:17,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11673.6, 300 sec: 11649.3). Total num frames: 62038016. Throughput: 0: 11578.5. Samples: 62030672. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 00:24:17,816][286098] Avg episode reward: [(0, '4465.734')] [2023-03-08 00:24:19,155][286389] Updated weights for policy 0, policy_version 121200 (0.0005) [2023-03-08 00:24:22,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11537.1, 300 sec: 11621.5). Total num frames: 62091264. Throughput: 0: 11522.2. Samples: 62064008. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:24:22,816][286098] Avg episode reward: [(0, '4397.646')] [2023-03-08 00:24:22,860][286389] Updated weights for policy 0, policy_version 121280 (0.0006) [2023-03-08 00:24:26,594][286389] Updated weights for policy 0, policy_version 121360 (0.0005) [2023-03-08 00:24:27,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11537.1, 300 sec: 11635.4). Total num frames: 62148608. Throughput: 0: 11525.8. Samples: 62130764. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:24:27,816][286098] Avg episode reward: [(0, '4387.668')] [2023-03-08 00:24:27,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000121384_62148608.pth... [2023-03-08 00:24:27,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000120720_61808640.pth [2023-03-08 00:24:30,332][286389] Updated weights for policy 0, policy_version 121440 (0.0005) [2023-03-08 00:24:32,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11400.5, 300 sec: 11621.5). Total num frames: 62201856. Throughput: 0: 11438.5. Samples: 62196396. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:24:32,816][286098] Avg episode reward: [(0, '4413.397')] [2023-03-08 00:24:34,038][286389] Updated weights for policy 0, policy_version 121520 (0.0005) [2023-03-08 00:24:37,794][286389] Updated weights for policy 0, policy_version 121600 (0.0006) [2023-03-08 00:24:37,816][286098] Fps is (10 sec: 11059.3, 60 sec: 11400.5, 300 sec: 11635.4). Total num frames: 62259200. Throughput: 0: 11387.1. Samples: 62230300. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:24:37,816][286098] Avg episode reward: [(0, '4397.766')] [2023-03-08 00:24:41,562][286389] Updated weights for policy 0, policy_version 121680 (0.0005) [2023-03-08 00:24:42,816][286098] Fps is (10 sec: 11059.1, 60 sec: 11400.5, 300 sec: 11607.6). Total num frames: 62312448. Throughput: 0: 11263.0. Samples: 62295556. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:24:42,816][286098] Avg episode reward: [(0, '4477.725')] [2023-03-08 00:24:42,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000121704_62312448.pth... [2023-03-08 00:24:42,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000121064_61984768.pth [2023-03-08 00:24:45,322][286389] Updated weights for policy 0, policy_version 121760 (0.0006) [2023-03-08 00:24:47,816][286098] Fps is (10 sec: 10649.6, 60 sec: 11264.0, 300 sec: 11593.8). Total num frames: 62365696. Throughput: 0: 11112.4. Samples: 62360320. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:24:47,816][286098] Avg episode reward: [(0, '4477.188')] [2023-03-08 00:24:49,067][286389] Updated weights for policy 0, policy_version 121840 (0.0006) [2023-03-08 00:24:52,766][286389] Updated weights for policy 0, policy_version 121920 (0.0005) [2023-03-08 00:24:52,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11264.0, 300 sec: 11593.8). Total num frames: 62423040. Throughput: 0: 11050.5. Samples: 62393368. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:24:52,816][286098] Avg episode reward: [(0, '4424.351')] [2023-03-08 00:24:56,478][286389] Updated weights for policy 0, policy_version 122000 (0.0005) [2023-03-08 00:24:57,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11127.5, 300 sec: 11566.0). Total num frames: 62476288. Throughput: 0: 11004.5. Samples: 62459904. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:24:57,816][286098] Avg episode reward: [(0, '4558.174')] [2023-03-08 00:24:57,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000122024_62476288.pth... [2023-03-08 00:24:57,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000121384_62148608.pth [2023-03-08 00:25:00,095][286389] Updated weights for policy 0, policy_version 122080 (0.0005) [2023-03-08 00:25:02,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11127.5, 300 sec: 11566.0). Total num frames: 62533632. Throughput: 0: 10998.8. Samples: 62525620. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:25:02,827][286098] Avg episode reward: [(0, '4479.887')] [2023-03-08 00:25:03,745][286389] Updated weights for policy 0, policy_version 122160 (0.0005) [2023-03-08 00:25:07,370][286389] Updated weights for policy 0, policy_version 122240 (0.0005) [2023-03-08 00:25:07,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11059.2, 300 sec: 11552.1). Total num frames: 62590976. Throughput: 0: 11067.6. Samples: 62562052. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:25:07,827][286098] Avg episode reward: [(0, '4265.658')] [2023-03-08 00:25:11,055][286389] Updated weights for policy 0, policy_version 122320 (0.0005) [2023-03-08 00:25:12,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11059.2, 300 sec: 11524.3). Total num frames: 62644224. Throughput: 0: 11047.6. Samples: 62627904. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:25:12,827][286098] Avg episode reward: [(0, '4434.162')] [2023-03-08 00:25:12,829][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000122352_62644224.pth... [2023-03-08 00:25:12,831][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000121704_62312448.pth [2023-03-08 00:25:14,680][286389] Updated weights for policy 0, policy_version 122400 (0.0004) [2023-03-08 00:25:17,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11127.5, 300 sec: 11538.2). Total num frames: 62705664. Throughput: 0: 11136.4. Samples: 62697536. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:25:17,827][286098] Avg episode reward: [(0, '4483.497')] [2023-03-08 00:25:18,047][286389] Updated weights for policy 0, policy_version 122480 (0.0003) [2023-03-08 00:25:21,556][286389] Updated weights for policy 0, policy_version 122560 (0.0004) [2023-03-08 00:25:22,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11195.7, 300 sec: 11552.1). Total num frames: 62763008. Throughput: 0: 11191.7. Samples: 62733928. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:25:22,827][286098] Avg episode reward: [(0, '4395.252')] [2023-03-08 00:25:25,309][286389] Updated weights for policy 0, policy_version 122640 (0.0005) [2023-03-08 00:25:27,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11127.5, 300 sec: 11524.3). Total num frames: 62816256. Throughput: 0: 11207.2. Samples: 62799880. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:25:27,827][286098] Avg episode reward: [(0, '4406.211')] [2023-03-08 00:25:27,830][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000122688_62816256.pth... [2023-03-08 00:25:27,833][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000122024_62476288.pth [2023-03-08 00:25:29,067][286389] Updated weights for policy 0, policy_version 122720 (0.0005) [2023-03-08 00:25:32,761][286389] Updated weights for policy 0, policy_version 122800 (0.0005) [2023-03-08 00:25:32,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11195.7, 300 sec: 11510.5). Total num frames: 62873600. Throughput: 0: 11225.6. Samples: 62865472. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:25:32,827][286098] Avg episode reward: [(0, '4541.421')] [2023-03-08 00:25:36,204][286389] Updated weights for policy 0, policy_version 122880 (0.0005) [2023-03-08 00:25:37,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11195.7, 300 sec: 11496.6). Total num frames: 62930944. Throughput: 0: 11281.7. Samples: 62901044. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:25:37,827][286098] Avg episode reward: [(0, '4539.666')] [2023-03-08 00:25:39,622][286389] Updated weights for policy 0, policy_version 122960 (0.0005) [2023-03-08 00:25:42,816][286098] Fps is (10 sec: 11878.3, 60 sec: 11332.3, 300 sec: 11510.5). Total num frames: 62992384. Throughput: 0: 11402.0. Samples: 62972996. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:25:42,827][286098] Avg episode reward: [(0, '4550.445')] [2023-03-08 00:25:42,830][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000123032_62992384.pth... [2023-03-08 00:25:42,833][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000122352_62644224.pth [2023-03-08 00:25:42,952][286389] Updated weights for policy 0, policy_version 123040 (0.0004) [2023-03-08 00:25:46,428][286389] Updated weights for policy 0, policy_version 123120 (0.0005) [2023-03-08 00:25:47,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11400.5, 300 sec: 11524.3). Total num frames: 63049728. Throughput: 0: 11539.7. Samples: 63044908. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:25:47,816][286098] Avg episode reward: [(0, '4512.543')] [2023-03-08 00:25:50,090][286389] Updated weights for policy 0, policy_version 123200 (0.0005) [2023-03-08 00:25:52,816][286098] Fps is (10 sec: 11468.9, 60 sec: 11400.5, 300 sec: 11524.3). Total num frames: 63107072. Throughput: 0: 11474.6. Samples: 63078408. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:25:52,827][286098] Avg episode reward: [(0, '4490.727')] [2023-03-08 00:25:53,786][286389] Updated weights for policy 0, policy_version 123280 (0.0005) [2023-03-08 00:25:57,555][286389] Updated weights for policy 0, policy_version 123360 (0.0005) [2023-03-08 00:25:57,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11400.5, 300 sec: 11510.5). Total num frames: 63160320. Throughput: 0: 11469.0. Samples: 63144008. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:25:57,827][286098] Avg episode reward: [(0, '4488.599')] [2023-03-08 00:25:57,830][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000123360_63160320.pth... [2023-03-08 00:25:57,833][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000122688_62816256.pth [2023-03-08 00:26:00,953][286389] Updated weights for policy 0, policy_version 123440 (0.0004) [2023-03-08 00:26:02,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11468.8, 300 sec: 11524.3). Total num frames: 63221760. Throughput: 0: 11483.3. Samples: 63214284. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:26:02,816][286098] Avg episode reward: [(0, '4523.774')] [2023-03-08 00:26:04,365][286389] Updated weights for policy 0, policy_version 123520 (0.0004) [2023-03-08 00:26:07,737][286389] Updated weights for policy 0, policy_version 123600 (0.0004) [2023-03-08 00:26:07,816][286098] Fps is (10 sec: 12287.9, 60 sec: 11537.1, 300 sec: 11538.2). Total num frames: 63283200. Throughput: 0: 11478.3. Samples: 63250452. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:26:07,817][286098] Avg episode reward: [(0, '4543.882')] [2023-03-08 00:26:11,130][286389] Updated weights for policy 0, policy_version 123680 (0.0005) [2023-03-08 00:26:12,816][286098] Fps is (10 sec: 11878.3, 60 sec: 11605.3, 300 sec: 11538.2). Total num frames: 63340544. Throughput: 0: 11636.7. Samples: 63323532. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:26:12,816][286098] Avg episode reward: [(0, '4553.029')] [2023-03-08 00:26:12,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000123712_63340544.pth... [2023-03-08 00:26:12,820][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000123032_62992384.pth [2023-03-08 00:26:14,607][286389] Updated weights for policy 0, policy_version 123760 (0.0004) [2023-03-08 00:26:17,816][286098] Fps is (10 sec: 11878.5, 60 sec: 11605.3, 300 sec: 11566.0). Total num frames: 63401984. Throughput: 0: 11741.9. Samples: 63393856. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:26:17,827][286098] Avg episode reward: [(0, '4562.623')] [2023-03-08 00:26:18,081][286389] Updated weights for policy 0, policy_version 123840 (0.0005) [2023-03-08 00:26:21,491][286389] Updated weights for policy 0, policy_version 123920 (0.0004) [2023-03-08 00:26:22,816][286098] Fps is (10 sec: 11878.5, 60 sec: 11605.3, 300 sec: 11566.0). Total num frames: 63459328. Throughput: 0: 11750.8. Samples: 63429832. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:26:22,827][286098] Avg episode reward: [(0, '4557.078')] [2023-03-08 00:26:24,930][286389] Updated weights for policy 0, policy_version 124000 (0.0005) [2023-03-08 00:26:27,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11741.9, 300 sec: 11579.9). Total num frames: 63520768. Throughput: 0: 11737.3. Samples: 63501176. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 00:26:27,827][286098] Avg episode reward: [(0, '4561.415')] [2023-03-08 00:26:27,830][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000124064_63520768.pth... [2023-03-08 00:26:27,832][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000123360_63160320.pth [2023-03-08 00:26:28,476][286389] Updated weights for policy 0, policy_version 124080 (0.0004) [2023-03-08 00:26:31,982][286389] Updated weights for policy 0, policy_version 124160 (0.0003) [2023-03-08 00:26:32,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11741.9, 300 sec: 11593.8). Total num frames: 63578112. Throughput: 0: 11682.9. Samples: 63570640. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 00:26:32,827][286098] Avg episode reward: [(0, '4526.066')] [2023-03-08 00:26:35,524][286389] Updated weights for policy 0, policy_version 124240 (0.0004) [2023-03-08 00:26:37,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11741.9, 300 sec: 11593.8). Total num frames: 63635456. Throughput: 0: 11721.3. Samples: 63605868. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 00:26:37,827][286098] Avg episode reward: [(0, '4564.341')] [2023-03-08 00:26:38,959][286389] Updated weights for policy 0, policy_version 124320 (0.0003) [2023-03-08 00:26:42,721][286389] Updated weights for policy 0, policy_version 124400 (0.0005) [2023-03-08 00:26:42,816][286098] Fps is (10 sec: 11468.7, 60 sec: 11673.6, 300 sec: 11593.8). Total num frames: 63692800. Throughput: 0: 11793.7. Samples: 63674724. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 00:26:42,827][286098] Avg episode reward: [(0, '4499.923')] [2023-03-08 00:26:42,830][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000124400_63692800.pth... [2023-03-08 00:26:42,833][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000123712_63340544.pth [2023-03-08 00:26:46,491][286389] Updated weights for policy 0, policy_version 124480 (0.0005) [2023-03-08 00:26:47,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11605.3, 300 sec: 11566.0). Total num frames: 63746048. Throughput: 0: 11689.6. Samples: 63740316. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 00:26:47,827][286098] Avg episode reward: [(0, '4536.145')] [2023-03-08 00:26:50,250][286389] Updated weights for policy 0, policy_version 124560 (0.0005) [2023-03-08 00:26:52,816][286098] Fps is (10 sec: 10649.7, 60 sec: 11537.1, 300 sec: 11552.1). Total num frames: 63799296. Throughput: 0: 11611.9. Samples: 63772988. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 00:26:52,827][286098] Avg episode reward: [(0, '4476.382')] [2023-03-08 00:26:53,958][286389] Updated weights for policy 0, policy_version 124640 (0.0005) [2023-03-08 00:26:57,700][286389] Updated weights for policy 0, policy_version 124720 (0.0005) [2023-03-08 00:26:57,816][286098] Fps is (10 sec: 11059.1, 60 sec: 11605.3, 300 sec: 11538.2). Total num frames: 63856640. Throughput: 0: 11449.0. Samples: 63838736. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 00:26:57,827][286098] Avg episode reward: [(0, '4058.900')] [2023-03-08 00:26:57,830][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000124720_63856640.pth... [2023-03-08 00:26:57,833][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000124064_63520768.pth [2023-03-08 00:27:01,503][286389] Updated weights for policy 0, policy_version 124800 (0.0005) [2023-03-08 00:27:02,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11468.8, 300 sec: 11524.3). Total num frames: 63909888. Throughput: 0: 11337.0. Samples: 63904020. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 00:27:02,827][286098] Avg episode reward: [(0, '4491.305')] [2023-03-08 00:27:05,142][286389] Updated weights for policy 0, policy_version 124880 (0.0005) [2023-03-08 00:27:07,816][286098] Fps is (10 sec: 11059.3, 60 sec: 11400.5, 300 sec: 11524.3). Total num frames: 63967232. Throughput: 0: 11293.1. Samples: 63938020. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 00:27:07,827][286098] Avg episode reward: [(0, '4341.220')] [2023-03-08 00:27:08,986][286389] Updated weights for policy 0, policy_version 124960 (0.0005) [2023-03-08 00:27:12,702][286389] Updated weights for policy 0, policy_version 125040 (0.0005) [2023-03-08 00:27:12,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11332.3, 300 sec: 11510.5). Total num frames: 64020480. Throughput: 0: 11148.1. Samples: 64002840. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 00:27:12,827][286098] Avg episode reward: [(0, '4564.000')] [2023-03-08 00:27:12,830][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000125040_64020480.pth... [2023-03-08 00:27:12,833][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000124400_63692800.pth [2023-03-08 00:27:16,402][286389] Updated weights for policy 0, policy_version 125120 (0.0005) [2023-03-08 00:27:17,816][286098] Fps is (10 sec: 10649.6, 60 sec: 11195.7, 300 sec: 11496.6). Total num frames: 64073728. Throughput: 0: 11076.0. Samples: 64069060. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 00:27:17,816][286098] Avg episode reward: [(0, '4529.987')] [2023-03-08 00:27:20,106][286389] Updated weights for policy 0, policy_version 125200 (0.0005) [2023-03-08 00:27:22,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11195.7, 300 sec: 11482.7). Total num frames: 64131072. Throughput: 0: 11034.0. Samples: 64102400. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 00:27:22,816][286098] Avg episode reward: [(0, '4567.270')] [2023-03-08 00:27:23,876][286389] Updated weights for policy 0, policy_version 125280 (0.0005) [2023-03-08 00:27:27,515][286389] Updated weights for policy 0, policy_version 125360 (0.0006) [2023-03-08 00:27:27,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11059.2, 300 sec: 11454.9). Total num frames: 64184320. Throughput: 0: 10960.5. Samples: 64167944. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:27:27,816][286098] Avg episode reward: [(0, '4522.016')] [2023-03-08 00:27:27,878][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000125368_64188416.pth... [2023-03-08 00:27:27,881][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000124720_63856640.pth [2023-03-08 00:27:31,227][286389] Updated weights for policy 0, policy_version 125440 (0.0005) [2023-03-08 00:27:32,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11059.2, 300 sec: 11454.9). Total num frames: 64241664. Throughput: 0: 10990.8. Samples: 64234904. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:27:32,816][286098] Avg episode reward: [(0, '4497.517')] [2023-03-08 00:27:34,936][286389] Updated weights for policy 0, policy_version 125520 (0.0005) [2023-03-08 00:27:37,816][286098] Fps is (10 sec: 11059.2, 60 sec: 10990.9, 300 sec: 11427.1). Total num frames: 64294912. Throughput: 0: 10990.7. Samples: 64267572. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:27:37,816][286098] Avg episode reward: [(0, '4504.898')] [2023-03-08 00:27:38,542][286389] Updated weights for policy 0, policy_version 125600 (0.0005) [2023-03-08 00:27:41,987][286389] Updated weights for policy 0, policy_version 125680 (0.0003) [2023-03-08 00:27:42,816][286098] Fps is (10 sec: 11468.7, 60 sec: 11059.2, 300 sec: 11441.0). Total num frames: 64356352. Throughput: 0: 11065.8. Samples: 64336696. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:27:42,816][286098] Avg episode reward: [(0, '4544.912')] [2023-03-08 00:27:42,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000125696_64356352.pth... [2023-03-08 00:27:42,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000125040_64020480.pth [2023-03-08 00:27:45,479][286389] Updated weights for policy 0, policy_version 125760 (0.0003) [2023-03-08 00:27:47,816][286098] Fps is (10 sec: 12288.0, 60 sec: 11195.7, 300 sec: 11441.0). Total num frames: 64417792. Throughput: 0: 11212.5. Samples: 64408584. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:27:47,816][286098] Avg episode reward: [(0, '4552.118')] [2023-03-08 00:27:48,829][286389] Updated weights for policy 0, policy_version 125840 (0.0003) [2023-03-08 00:27:52,532][286389] Updated weights for policy 0, policy_version 125920 (0.0005) [2023-03-08 00:27:52,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11195.7, 300 sec: 11427.1). Total num frames: 64471040. Throughput: 0: 11232.3. Samples: 64443472. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:27:52,816][286098] Avg episode reward: [(0, '4522.831')] [2023-03-08 00:27:55,979][286389] Updated weights for policy 0, policy_version 126000 (0.0003) [2023-03-08 00:27:57,816][286098] Fps is (10 sec: 11468.7, 60 sec: 11264.0, 300 sec: 11427.1). Total num frames: 64532480. Throughput: 0: 11332.2. Samples: 64512788. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:27:57,816][286098] Avg episode reward: [(0, '4485.279')] [2023-03-08 00:27:57,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000126040_64532480.pth... [2023-03-08 00:27:57,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000125368_64188416.pth [2023-03-08 00:27:59,490][286389] Updated weights for policy 0, policy_version 126080 (0.0004) [2023-03-08 00:28:02,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11332.3, 300 sec: 11427.1). Total num frames: 64589824. Throughput: 0: 11395.4. Samples: 64581852. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:28:02,816][286098] Avg episode reward: [(0, '4484.292')] [2023-03-08 00:28:03,104][286389] Updated weights for policy 0, policy_version 126160 (0.0005) [2023-03-08 00:28:06,782][286389] Updated weights for policy 0, policy_version 126240 (0.0005) [2023-03-08 00:28:07,816][286098] Fps is (10 sec: 11059.3, 60 sec: 11264.0, 300 sec: 11399.4). Total num frames: 64643072. Throughput: 0: 11393.4. Samples: 64615104. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:28:07,816][286098] Avg episode reward: [(0, '4515.458')] [2023-03-08 00:28:10,440][286389] Updated weights for policy 0, policy_version 126320 (0.0005) [2023-03-08 00:28:12,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11332.3, 300 sec: 11399.4). Total num frames: 64700416. Throughput: 0: 11466.3. Samples: 64683928. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:28:12,816][286098] Avg episode reward: [(0, '4533.474')] [2023-03-08 00:28:12,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000126368_64700416.pth... [2023-03-08 00:28:12,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000125696_64356352.pth [2023-03-08 00:28:13,950][286389] Updated weights for policy 0, policy_version 126400 (0.0004) [2023-03-08 00:28:17,396][286389] Updated weights for policy 0, policy_version 126480 (0.0003) [2023-03-08 00:28:17,816][286098] Fps is (10 sec: 11878.3, 60 sec: 11468.8, 300 sec: 11399.4). Total num frames: 64761856. Throughput: 0: 11529.4. Samples: 64753728. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:28:17,816][286098] Avg episode reward: [(0, '4556.014')] [2023-03-08 00:28:20,844][286389] Updated weights for policy 0, policy_version 126560 (0.0004) [2023-03-08 00:28:22,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11468.8, 300 sec: 11399.4). Total num frames: 64819200. Throughput: 0: 11599.8. Samples: 64789564. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:28:22,816][286098] Avg episode reward: [(0, '4543.806')] [2023-03-08 00:28:24,350][286389] Updated weights for policy 0, policy_version 126640 (0.0004) [2023-03-08 00:28:27,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11537.1, 300 sec: 11385.5). Total num frames: 64876544. Throughput: 0: 11626.2. Samples: 64859876. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 00:28:27,816][286098] Avg episode reward: [(0, '4528.269')] [2023-03-08 00:28:27,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000126712_64876544.pth... [2023-03-08 00:28:27,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000126040_64532480.pth [2023-03-08 00:28:27,909][286389] Updated weights for policy 0, policy_version 126720 (0.0005) [2023-03-08 00:28:31,355][286389] Updated weights for policy 0, policy_version 126800 (0.0004) [2023-03-08 00:28:32,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11605.3, 300 sec: 11399.4). Total num frames: 64937984. Throughput: 0: 11583.8. Samples: 64929856. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 00:28:32,816][286098] Avg episode reward: [(0, '4537.234')] [2023-03-08 00:28:34,704][286389] Updated weights for policy 0, policy_version 126880 (0.0003) [2023-03-08 00:28:37,816][286098] Fps is (10 sec: 12288.0, 60 sec: 11741.9, 300 sec: 11427.1). Total num frames: 64999424. Throughput: 0: 11627.7. Samples: 64966720. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 00:28:37,816][286098] Avg episode reward: [(0, '4543.958')] [2023-03-08 00:28:38,105][286389] Updated weights for policy 0, policy_version 126960 (0.0003) [2023-03-08 00:28:41,577][286389] Updated weights for policy 0, policy_version 127040 (0.0004) [2023-03-08 00:28:42,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11673.6, 300 sec: 11413.3). Total num frames: 65056768. Throughput: 0: 11694.8. Samples: 65039052. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 00:28:42,816][286098] Avg episode reward: [(0, '4372.972')] [2023-03-08 00:28:42,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000127064_65056768.pth... [2023-03-08 00:28:42,821][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000126368_64700416.pth [2023-03-08 00:28:44,858][286389] Updated weights for policy 0, policy_version 127120 (0.0003) [2023-03-08 00:28:47,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11673.6, 300 sec: 11427.1). Total num frames: 65118208. Throughput: 0: 11777.2. Samples: 65111828. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 00:28:47,816][286098] Avg episode reward: [(0, '4391.313')] [2023-03-08 00:28:48,246][286389] Updated weights for policy 0, policy_version 127200 (0.0003) [2023-03-08 00:28:51,863][286389] Updated weights for policy 0, policy_version 127280 (0.0005) [2023-03-08 00:28:52,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11741.9, 300 sec: 11413.3). Total num frames: 65175552. Throughput: 0: 11829.9. Samples: 65147448. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 00:28:52,816][286098] Avg episode reward: [(0, '4457.497')] [2023-03-08 00:28:55,491][286389] Updated weights for policy 0, policy_version 127360 (0.0005) [2023-03-08 00:28:57,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11673.6, 300 sec: 11413.3). Total num frames: 65232896. Throughput: 0: 11797.4. Samples: 65214812. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 00:28:57,816][286098] Avg episode reward: [(0, '4547.400')] [2023-03-08 00:28:57,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000127408_65232896.pth... [2023-03-08 00:28:57,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000126712_64876544.pth [2023-03-08 00:28:59,134][286389] Updated weights for policy 0, policy_version 127440 (0.0006) [2023-03-08 00:29:02,528][286389] Updated weights for policy 0, policy_version 127520 (0.0004) [2023-03-08 00:29:02,816][286098] Fps is (10 sec: 11468.9, 60 sec: 11673.6, 300 sec: 11399.4). Total num frames: 65290240. Throughput: 0: 11795.5. Samples: 65284524. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 00:29:02,816][286098] Avg episode reward: [(0, '4556.815')] [2023-03-08 00:29:05,931][286389] Updated weights for policy 0, policy_version 127600 (0.0003) [2023-03-08 00:29:07,816][286098] Fps is (10 sec: 11878.5, 60 sec: 11810.1, 300 sec: 11427.1). Total num frames: 65351680. Throughput: 0: 11793.3. Samples: 65320264. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 00:29:07,816][286098] Avg episode reward: [(0, '4509.221')] [2023-03-08 00:29:09,435][286389] Updated weights for policy 0, policy_version 127680 (0.0003) [2023-03-08 00:29:12,816][286098] Fps is (10 sec: 11878.3, 60 sec: 11810.1, 300 sec: 11427.1). Total num frames: 65409024. Throughput: 0: 11824.4. Samples: 65391972. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 00:29:12,816][286098] Avg episode reward: [(0, '4456.562')] [2023-03-08 00:29:12,826][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000127760_65413120.pth... [2023-03-08 00:29:12,827][286389] Updated weights for policy 0, policy_version 127760 (0.0003) [2023-03-08 00:29:12,829][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000127064_65056768.pth [2023-03-08 00:29:16,123][286389] Updated weights for policy 0, policy_version 127840 (0.0003) [2023-03-08 00:29:17,816][286098] Fps is (10 sec: 12288.0, 60 sec: 11878.4, 300 sec: 11468.8). Total num frames: 65474560. Throughput: 0: 11918.2. Samples: 65466176. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 00:29:17,816][286098] Avg episode reward: [(0, '4461.561')] [2023-03-08 00:29:19,455][286389] Updated weights for policy 0, policy_version 127920 (0.0004) [2023-03-08 00:29:22,816][286098] Fps is (10 sec: 12288.0, 60 sec: 11878.4, 300 sec: 11468.8). Total num frames: 65531904. Throughput: 0: 11903.1. Samples: 65502360. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 00:29:22,816][286098] Avg episode reward: [(0, '4525.144')] [2023-03-08 00:29:23,058][286389] Updated weights for policy 0, policy_version 128000 (0.0006) [2023-03-08 00:29:26,747][286389] Updated weights for policy 0, policy_version 128080 (0.0005) [2023-03-08 00:29:27,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11810.1, 300 sec: 11468.8). Total num frames: 65585152. Throughput: 0: 11786.0. Samples: 65569420. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 00:29:27,816][286098] Avg episode reward: [(0, '4487.894')] [2023-03-08 00:29:27,873][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000128104_65589248.pth... [2023-03-08 00:29:27,875][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000127408_65232896.pth [2023-03-08 00:29:30,471][286389] Updated weights for policy 0, policy_version 128160 (0.0006) [2023-03-08 00:29:32,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11741.9, 300 sec: 11468.8). Total num frames: 65642496. Throughput: 0: 11634.5. Samples: 65635380. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 00:29:32,816][286098] Avg episode reward: [(0, '4194.900')] [2023-03-08 00:29:34,160][286389] Updated weights for policy 0, policy_version 128240 (0.0006) [2023-03-08 00:29:37,704][286389] Updated weights for policy 0, policy_version 128320 (0.0004) [2023-03-08 00:29:37,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11673.6, 300 sec: 11482.7). Total num frames: 65699840. Throughput: 0: 11583.5. Samples: 65668704. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 00:29:37,816][286098] Avg episode reward: [(0, '4472.234')] [2023-03-08 00:29:41,153][286389] Updated weights for policy 0, policy_version 128400 (0.0003) [2023-03-08 00:29:42,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11673.6, 300 sec: 11496.6). Total num frames: 65757184. Throughput: 0: 11661.3. Samples: 65739572. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 00:29:42,816][286098] Avg episode reward: [(0, '4537.761')] [2023-03-08 00:29:42,818][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000128432_65757184.pth... [2023-03-08 00:29:42,821][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000127760_65413120.pth [2023-03-08 00:29:44,715][286389] Updated weights for policy 0, policy_version 128480 (0.0005) [2023-03-08 00:29:47,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11605.3, 300 sec: 11496.6). Total num frames: 65814528. Throughput: 0: 11625.5. Samples: 65807672. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 00:29:47,827][286098] Avg episode reward: [(0, '4553.769')] [2023-03-08 00:29:48,433][286389] Updated weights for policy 0, policy_version 128560 (0.0005) [2023-03-08 00:29:52,055][286389] Updated weights for policy 0, policy_version 128640 (0.0005) [2023-03-08 00:29:52,816][286098] Fps is (10 sec: 11468.7, 60 sec: 11605.3, 300 sec: 11510.5). Total num frames: 65871872. Throughput: 0: 11582.7. Samples: 65841488. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 00:29:52,827][286098] Avg episode reward: [(0, '4500.172')] [2023-03-08 00:29:55,696][286389] Updated weights for policy 0, policy_version 128720 (0.0004) [2023-03-08 00:29:57,816][286098] Fps is (10 sec: 11468.5, 60 sec: 11605.3, 300 sec: 11510.4). Total num frames: 65929216. Throughput: 0: 11485.0. Samples: 65908800. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 00:29:57,827][286098] Avg episode reward: [(0, '4522.743')] [2023-03-08 00:29:57,831][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000128768_65929216.pth... [2023-03-08 00:29:57,834][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000128104_65589248.pth [2023-03-08 00:29:59,200][286389] Updated weights for policy 0, policy_version 128800 (0.0004) [2023-03-08 00:30:02,587][286389] Updated weights for policy 0, policy_version 128880 (0.0004) [2023-03-08 00:30:02,816][286098] Fps is (10 sec: 11468.9, 60 sec: 11605.3, 300 sec: 11510.5). Total num frames: 65986560. Throughput: 0: 11416.7. Samples: 65979928. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 00:30:02,827][286098] Avg episode reward: [(0, '4493.893')] [2023-03-08 00:30:05,968][286389] Updated weights for policy 0, policy_version 128960 (0.0003) [2023-03-08 00:30:07,816][286098] Fps is (10 sec: 11878.6, 60 sec: 11605.3, 300 sec: 11538.2). Total num frames: 66048000. Throughput: 0: 11422.3. Samples: 66016364. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 00:30:07,827][286098] Avg episode reward: [(0, '4537.570')] [2023-03-08 00:30:09,268][286389] Updated weights for policy 0, policy_version 129040 (0.0003) [2023-03-08 00:30:12,654][286389] Updated weights for policy 0, policy_version 129120 (0.0003) [2023-03-08 00:30:12,816][286098] Fps is (10 sec: 12288.0, 60 sec: 11673.6, 300 sec: 11538.2). Total num frames: 66109440. Throughput: 0: 11558.6. Samples: 66089556. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 00:30:12,827][286098] Avg episode reward: [(0, '4548.485')] [2023-03-08 00:30:12,830][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000129120_66109440.pth... [2023-03-08 00:30:12,832][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000128432_65757184.pth [2023-03-08 00:30:15,970][286389] Updated weights for policy 0, policy_version 129200 (0.0003) [2023-03-08 00:30:17,816][286098] Fps is (10 sec: 12288.1, 60 sec: 11605.3, 300 sec: 11552.1). Total num frames: 66170880. Throughput: 0: 11722.6. Samples: 66162896. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 00:30:17,827][286098] Avg episode reward: [(0, '4535.248')] [2023-03-08 00:30:19,359][286389] Updated weights for policy 0, policy_version 129280 (0.0003) [2023-03-08 00:30:22,698][286389] Updated weights for policy 0, policy_version 129360 (0.0004) [2023-03-08 00:30:22,816][286098] Fps is (10 sec: 12288.0, 60 sec: 11673.6, 300 sec: 11579.9). Total num frames: 66232320. Throughput: 0: 11802.8. Samples: 66199832. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 00:30:22,827][286098] Avg episode reward: [(0, '4521.731')] [2023-03-08 00:30:26,064][286389] Updated weights for policy 0, policy_version 129440 (0.0005) [2023-03-08 00:30:27,816][286098] Fps is (10 sec: 12287.9, 60 sec: 11810.1, 300 sec: 11593.8). Total num frames: 66293760. Throughput: 0: 11861.6. Samples: 66273344. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 00:30:27,827][286098] Avg episode reward: [(0, '4568.175')] [2023-03-08 00:30:27,830][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000129480_66293760.pth... [2023-03-08 00:30:27,833][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000128768_65929216.pth [2023-03-08 00:30:29,427][286389] Updated weights for policy 0, policy_version 129520 (0.0005) [2023-03-08 00:30:32,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11810.1, 300 sec: 11593.8). Total num frames: 66351104. Throughput: 0: 11930.3. Samples: 66344536. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:30:32,827][286098] Avg episode reward: [(0, '4558.355')] [2023-03-08 00:30:33,044][286389] Updated weights for policy 0, policy_version 129600 (0.0005) [2023-03-08 00:30:36,648][286389] Updated weights for policy 0, policy_version 129680 (0.0006) [2023-03-08 00:30:37,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11810.1, 300 sec: 11579.9). Total num frames: 66408448. Throughput: 0: 11934.4. Samples: 66378536. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:30:37,827][286098] Avg episode reward: [(0, '4563.623')] [2023-03-08 00:30:40,306][286389] Updated weights for policy 0, policy_version 129760 (0.0006) [2023-03-08 00:30:42,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11810.1, 300 sec: 11579.9). Total num frames: 66465792. Throughput: 0: 11924.8. Samples: 66445416. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:30:42,827][286098] Avg episode reward: [(0, '4534.069')] [2023-03-08 00:30:42,830][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000129816_66465792.pth... [2023-03-08 00:30:42,833][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000129120_66109440.pth [2023-03-08 00:30:43,789][286389] Updated weights for policy 0, policy_version 129840 (0.0005) [2023-03-08 00:30:47,321][286389] Updated weights for policy 0, policy_version 129920 (0.0005) [2023-03-08 00:30:47,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11810.1, 300 sec: 11579.9). Total num frames: 66523136. Throughput: 0: 11906.9. Samples: 66515736. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:30:47,816][286098] Avg episode reward: [(0, '4566.618')] [2023-03-08 00:30:51,000][286389] Updated weights for policy 0, policy_version 130000 (0.0005) [2023-03-08 00:30:52,816][286098] Fps is (10 sec: 11468.9, 60 sec: 11810.2, 300 sec: 11593.8). Total num frames: 66580480. Throughput: 0: 11850.6. Samples: 66549640. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:30:52,816][286098] Avg episode reward: [(0, '4482.620')] [2023-03-08 00:30:54,665][286389] Updated weights for policy 0, policy_version 130080 (0.0006) [2023-03-08 00:30:57,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11741.9, 300 sec: 11566.0). Total num frames: 66633728. Throughput: 0: 11728.6. Samples: 66617344. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:30:57,816][286098] Avg episode reward: [(0, '4564.004')] [2023-03-08 00:30:57,864][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000130152_66637824.pth... [2023-03-08 00:30:57,865][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000129480_66293760.pth [2023-03-08 00:30:58,215][286389] Updated weights for policy 0, policy_version 130160 (0.0005) [2023-03-08 00:31:01,875][286389] Updated weights for policy 0, policy_version 130240 (0.0006) [2023-03-08 00:31:02,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11741.9, 300 sec: 11552.1). Total num frames: 66691072. Throughput: 0: 11603.5. Samples: 66685052. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:31:02,827][286098] Avg episode reward: [(0, '4562.588')] [2023-03-08 00:31:05,568][286389] Updated weights for policy 0, policy_version 130320 (0.0006) [2023-03-08 00:31:07,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11673.6, 300 sec: 11552.1). Total num frames: 66748416. Throughput: 0: 11526.7. Samples: 66718532. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:31:07,827][286098] Avg episode reward: [(0, '4540.034')] [2023-03-08 00:31:08,933][286389] Updated weights for policy 0, policy_version 130400 (0.0005) [2023-03-08 00:31:12,214][286389] Updated weights for policy 0, policy_version 130480 (0.0004) [2023-03-08 00:31:12,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11673.6, 300 sec: 11552.1). Total num frames: 66809856. Throughput: 0: 11518.0. Samples: 66791656. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:31:12,827][286098] Avg episode reward: [(0, '4434.966')] [2023-03-08 00:31:12,830][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000130488_66809856.pth... [2023-03-08 00:31:12,833][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000129816_66465792.pth [2023-03-08 00:31:15,721][286389] Updated weights for policy 0, policy_version 130560 (0.0005) [2023-03-08 00:31:17,816][286098] Fps is (10 sec: 12288.0, 60 sec: 11673.6, 300 sec: 11566.0). Total num frames: 66871296. Throughput: 0: 11520.7. Samples: 66862968. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:31:17,827][286098] Avg episode reward: [(0, '4428.293')] [2023-03-08 00:31:19,307][286389] Updated weights for policy 0, policy_version 130640 (0.0005) [2023-03-08 00:31:22,816][286098] Fps is (10 sec: 11468.9, 60 sec: 11537.1, 300 sec: 11538.2). Total num frames: 66924544. Throughput: 0: 11498.0. Samples: 66895944. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:31:22,827][286098] Avg episode reward: [(0, '4539.710')] [2023-03-08 00:31:22,928][286389] Updated weights for policy 0, policy_version 130720 (0.0006) [2023-03-08 00:31:26,544][286389] Updated weights for policy 0, policy_version 130800 (0.0005) [2023-03-08 00:31:27,816][286098] Fps is (10 sec: 11059.1, 60 sec: 11468.8, 300 sec: 11538.2). Total num frames: 66981888. Throughput: 0: 11540.2. Samples: 66964724. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:31:27,827][286098] Avg episode reward: [(0, '4539.211')] [2023-03-08 00:31:27,831][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000130824_66981888.pth... [2023-03-08 00:31:27,833][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000130152_66637824.pth [2023-03-08 00:31:29,982][286389] Updated weights for policy 0, policy_version 130880 (0.0004) [2023-03-08 00:31:32,816][286098] Fps is (10 sec: 11878.3, 60 sec: 11537.1, 300 sec: 11552.1). Total num frames: 67043328. Throughput: 0: 11543.8. Samples: 67035208. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:31:32,827][286098] Avg episode reward: [(0, '4557.966')] [2023-03-08 00:31:33,367][286389] Updated weights for policy 0, policy_version 130960 (0.0003) [2023-03-08 00:31:36,739][286389] Updated weights for policy 0, policy_version 131040 (0.0004) [2023-03-08 00:31:37,816][286098] Fps is (10 sec: 12288.1, 60 sec: 11605.3, 300 sec: 11566.0). Total num frames: 67104768. Throughput: 0: 11609.4. Samples: 67072064. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:31:37,816][286098] Avg episode reward: [(0, '4549.959')] [2023-03-08 00:31:40,113][286389] Updated weights for policy 0, policy_version 131120 (0.0005) [2023-03-08 00:31:42,816][286098] Fps is (10 sec: 12287.9, 60 sec: 11673.6, 300 sec: 11593.8). Total num frames: 67166208. Throughput: 0: 11741.3. Samples: 67145704. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:31:42,827][286098] Avg episode reward: [(0, '4575.839')] [2023-03-08 00:31:42,831][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000131184_67166208.pth... [2023-03-08 00:31:42,833][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000130488_66809856.pth [2023-03-08 00:31:43,417][286389] Updated weights for policy 0, policy_version 131200 (0.0004) [2023-03-08 00:31:46,763][286389] Updated weights for policy 0, policy_version 131280 (0.0004) [2023-03-08 00:31:47,816][286098] Fps is (10 sec: 12288.0, 60 sec: 11741.9, 300 sec: 11621.5). Total num frames: 67227648. Throughput: 0: 11872.3. Samples: 67219304. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:31:47,827][286098] Avg episode reward: [(0, '4526.762')] [2023-03-08 00:31:50,083][286389] Updated weights for policy 0, policy_version 131360 (0.0004) [2023-03-08 00:31:52,816][286098] Fps is (10 sec: 12288.0, 60 sec: 11810.1, 300 sec: 11635.4). Total num frames: 67289088. Throughput: 0: 11951.0. Samples: 67256328. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:31:52,816][286098] Avg episode reward: [(0, '4364.584')] [2023-03-08 00:31:53,396][286389] Updated weights for policy 0, policy_version 131440 (0.0004) [2023-03-08 00:31:56,767][286389] Updated weights for policy 0, policy_version 131520 (0.0005) [2023-03-08 00:31:57,816][286098] Fps is (10 sec: 12287.9, 60 sec: 11946.7, 300 sec: 11663.2). Total num frames: 67350528. Throughput: 0: 11954.5. Samples: 67329608. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:31:57,827][286098] Avg episode reward: [(0, '4338.369')] [2023-03-08 00:31:57,830][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000131544_67350528.pth... [2023-03-08 00:31:57,833][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000130824_66981888.pth [2023-03-08 00:32:00,100][286389] Updated weights for policy 0, policy_version 131600 (0.0003) [2023-03-08 00:32:02,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11946.7, 300 sec: 11663.2). Total num frames: 67407872. Throughput: 0: 11978.6. Samples: 67402004. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:32:02,827][286098] Avg episode reward: [(0, '3983.895')] [2023-03-08 00:32:03,711][286389] Updated weights for policy 0, policy_version 131680 (0.0004) [2023-03-08 00:32:07,103][286389] Updated weights for policy 0, policy_version 131760 (0.0004) [2023-03-08 00:32:07,816][286098] Fps is (10 sec: 11878.4, 60 sec: 12014.9, 300 sec: 11691.0). Total num frames: 67469312. Throughput: 0: 12006.1. Samples: 67436220. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:32:07,816][286098] Avg episode reward: [(0, '4351.987')] [2023-03-08 00:32:10,485][286389] Updated weights for policy 0, policy_version 131840 (0.0004) [2023-03-08 00:32:12,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11946.7, 300 sec: 11704.8). Total num frames: 67526656. Throughput: 0: 12094.0. Samples: 67508952. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:32:12,816][286098] Avg episode reward: [(0, '4364.659')] [2023-03-08 00:32:12,847][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000131896_67530752.pth... [2023-03-08 00:32:12,848][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000131184_67166208.pth [2023-03-08 00:32:13,866][286389] Updated weights for policy 0, policy_version 131920 (0.0004) [2023-03-08 00:32:17,191][286389] Updated weights for policy 0, policy_version 132000 (0.0005) [2023-03-08 00:32:17,816][286098] Fps is (10 sec: 11878.5, 60 sec: 11946.7, 300 sec: 11718.7). Total num frames: 67588096. Throughput: 0: 12164.5. Samples: 67582608. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:32:17,816][286098] Avg episode reward: [(0, '4308.873')] [2023-03-08 00:32:20,891][286389] Updated weights for policy 0, policy_version 132080 (0.0005) [2023-03-08 00:32:22,816][286098] Fps is (10 sec: 11878.4, 60 sec: 12014.9, 300 sec: 11732.6). Total num frames: 67645440. Throughput: 0: 12101.7. Samples: 67616640. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:32:22,816][286098] Avg episode reward: [(0, '4342.309')] [2023-03-08 00:32:24,585][286389] Updated weights for policy 0, policy_version 132160 (0.0005) [2023-03-08 00:32:27,816][286098] Fps is (10 sec: 11468.8, 60 sec: 12015.0, 300 sec: 11732.6). Total num frames: 67702784. Throughput: 0: 11930.3. Samples: 67682568. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:32:27,816][286098] Avg episode reward: [(0, '4426.023')] [2023-03-08 00:32:27,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000132232_67702784.pth... [2023-03-08 00:32:27,821][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000131544_67350528.pth [2023-03-08 00:32:28,142][286389] Updated weights for policy 0, policy_version 132240 (0.0005) [2023-03-08 00:32:31,771][286389] Updated weights for policy 0, policy_version 132320 (0.0005) [2023-03-08 00:32:32,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11878.4, 300 sec: 11732.6). Total num frames: 67756032. Throughput: 0: 11828.9. Samples: 67751604. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:32:32,816][286098] Avg episode reward: [(0, '4516.795')] [2023-03-08 00:32:35,423][286389] Updated weights for policy 0, policy_version 132400 (0.0005) [2023-03-08 00:32:37,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11810.1, 300 sec: 11718.7). Total num frames: 67813376. Throughput: 0: 11743.1. Samples: 67784768. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:32:37,816][286098] Avg episode reward: [(0, '4421.507')] [2023-03-08 00:32:39,055][286389] Updated weights for policy 0, policy_version 132480 (0.0005) [2023-03-08 00:32:42,575][286389] Updated weights for policy 0, policy_version 132560 (0.0004) [2023-03-08 00:32:42,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11741.9, 300 sec: 11704.8). Total num frames: 67870720. Throughput: 0: 11621.2. Samples: 67852564. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:32:42,817][286098] Avg episode reward: [(0, '4419.769')] [2023-03-08 00:32:42,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000132560_67870720.pth... [2023-03-08 00:32:42,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000131896_67530752.pth [2023-03-08 00:32:46,026][286389] Updated weights for policy 0, policy_version 132640 (0.0004) [2023-03-08 00:32:47,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11741.9, 300 sec: 11732.6). Total num frames: 67932160. Throughput: 0: 11600.6. Samples: 67924032. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:32:47,816][286098] Avg episode reward: [(0, '4443.260')] [2023-03-08 00:32:49,366][286389] Updated weights for policy 0, policy_version 132720 (0.0004) [2023-03-08 00:32:52,713][286389] Updated weights for policy 0, policy_version 132800 (0.0004) [2023-03-08 00:32:52,816][286098] Fps is (10 sec: 12288.1, 60 sec: 11741.9, 300 sec: 11732.6). Total num frames: 67993600. Throughput: 0: 11659.7. Samples: 67960904. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:32:52,816][286098] Avg episode reward: [(0, '4445.057')] [2023-03-08 00:32:56,019][286389] Updated weights for policy 0, policy_version 132880 (0.0003) [2023-03-08 00:32:57,816][286098] Fps is (10 sec: 12288.0, 60 sec: 11741.9, 300 sec: 11746.5). Total num frames: 68055040. Throughput: 0: 11683.7. Samples: 68034720. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:32:57,816][286098] Avg episode reward: [(0, '4561.837')] [2023-03-08 00:32:57,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000132920_68055040.pth... [2023-03-08 00:32:57,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000132232_67702784.pth [2023-03-08 00:32:59,428][286389] Updated weights for policy 0, policy_version 132960 (0.0004) [2023-03-08 00:33:02,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11741.9, 300 sec: 11760.4). Total num frames: 68112384. Throughput: 0: 11624.4. Samples: 68105704. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:33:02,816][286098] Avg episode reward: [(0, '4476.161')] [2023-03-08 00:33:03,008][286389] Updated weights for policy 0, policy_version 133040 (0.0005) [2023-03-08 00:33:06,409][286389] Updated weights for policy 0, policy_version 133120 (0.0004) [2023-03-08 00:33:07,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11741.9, 300 sec: 11774.3). Total num frames: 68173824. Throughput: 0: 11655.3. Samples: 68141128. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:33:07,816][286098] Avg episode reward: [(0, '4428.102')] [2023-03-08 00:33:09,823][286389] Updated weights for policy 0, policy_version 133200 (0.0004) [2023-03-08 00:33:12,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11741.9, 300 sec: 11760.4). Total num frames: 68231168. Throughput: 0: 11788.3. Samples: 68213040. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:33:12,816][286098] Avg episode reward: [(0, '4441.511')] [2023-03-08 00:33:12,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000133264_68231168.pth... [2023-03-08 00:33:12,823][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000132560_67870720.pth [2023-03-08 00:33:13,263][286389] Updated weights for policy 0, policy_version 133280 (0.0004) [2023-03-08 00:33:16,610][286389] Updated weights for policy 0, policy_version 133360 (0.0004) [2023-03-08 00:33:17,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11741.9, 300 sec: 11774.3). Total num frames: 68292608. Throughput: 0: 11865.3. Samples: 68285540. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:33:17,816][286098] Avg episode reward: [(0, '4499.119')] [2023-03-08 00:33:19,997][286389] Updated weights for policy 0, policy_version 133440 (0.0004) [2023-03-08 00:33:22,816][286098] Fps is (10 sec: 11878.5, 60 sec: 11741.9, 300 sec: 11774.3). Total num frames: 68349952. Throughput: 0: 11933.7. Samples: 68321784. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:33:22,816][286098] Avg episode reward: [(0, '4517.632')] [2023-03-08 00:33:23,655][286389] Updated weights for policy 0, policy_version 133520 (0.0005) [2023-03-08 00:33:27,076][286389] Updated weights for policy 0, policy_version 133600 (0.0004) [2023-03-08 00:33:27,816][286098] Fps is (10 sec: 11878.3, 60 sec: 11810.1, 300 sec: 11774.3). Total num frames: 68411392. Throughput: 0: 11964.9. Samples: 68390984. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:33:27,816][286098] Avg episode reward: [(0, '4516.897')] [2023-03-08 00:33:27,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000133616_68411392.pth... [2023-03-08 00:33:27,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000132920_68055040.pth [2023-03-08 00:33:30,398][286389] Updated weights for policy 0, policy_version 133680 (0.0004) [2023-03-08 00:33:32,816][286098] Fps is (10 sec: 12287.9, 60 sec: 11946.7, 300 sec: 11774.3). Total num frames: 68472832. Throughput: 0: 12014.9. Samples: 68464704. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:33:32,816][286098] Avg episode reward: [(0, '4551.483')] [2023-03-08 00:33:33,723][286389] Updated weights for policy 0, policy_version 133760 (0.0003) [2023-03-08 00:33:37,146][286389] Updated weights for policy 0, policy_version 133840 (0.0004) [2023-03-08 00:33:37,816][286098] Fps is (10 sec: 12288.1, 60 sec: 12014.9, 300 sec: 11788.2). Total num frames: 68534272. Throughput: 0: 12014.9. Samples: 68501576. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:33:37,816][286098] Avg episode reward: [(0, '4493.299')] [2023-03-08 00:33:40,529][286389] Updated weights for policy 0, policy_version 133920 (0.0004) [2023-03-08 00:33:42,816][286098] Fps is (10 sec: 11878.3, 60 sec: 12014.9, 300 sec: 11774.3). Total num frames: 68591616. Throughput: 0: 11978.0. Samples: 68573732. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:33:42,817][286098] Avg episode reward: [(0, '4497.991')] [2023-03-08 00:33:42,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000133968_68591616.pth... [2023-03-08 00:33:42,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000133264_68231168.pth [2023-03-08 00:33:43,851][286389] Updated weights for policy 0, policy_version 134000 (0.0004) [2023-03-08 00:33:47,129][286389] Updated weights for policy 0, policy_version 134080 (0.0003) [2023-03-08 00:33:47,816][286098] Fps is (10 sec: 11878.4, 60 sec: 12014.9, 300 sec: 11788.1). Total num frames: 68653056. Throughput: 0: 12052.0. Samples: 68648044. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:33:47,816][286098] Avg episode reward: [(0, '4561.289')] [2023-03-08 00:33:50,524][286389] Updated weights for policy 0, policy_version 134160 (0.0004) [2023-03-08 00:33:52,816][286098] Fps is (10 sec: 12288.1, 60 sec: 12014.9, 300 sec: 11802.0). Total num frames: 68714496. Throughput: 0: 12068.5. Samples: 68684212. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:33:52,816][286098] Avg episode reward: [(0, '4467.857')] [2023-03-08 00:33:53,932][286389] Updated weights for policy 0, policy_version 134240 (0.0004) [2023-03-08 00:33:57,389][286389] Updated weights for policy 0, policy_version 134320 (0.0004) [2023-03-08 00:33:57,816][286098] Fps is (10 sec: 12287.9, 60 sec: 12014.9, 300 sec: 11815.9). Total num frames: 68775936. Throughput: 0: 12060.2. Samples: 68755748. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:33:57,817][286098] Avg episode reward: [(0, '4526.153')] [2023-03-08 00:33:57,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000134328_68775936.pth... [2023-03-08 00:33:57,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000133616_68411392.pth [2023-03-08 00:34:00,772][286389] Updated weights for policy 0, policy_version 134400 (0.0004) [2023-03-08 00:34:02,816][286098] Fps is (10 sec: 11878.3, 60 sec: 12014.9, 300 sec: 11802.0). Total num frames: 68833280. Throughput: 0: 12056.0. Samples: 68828060. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:34:02,816][286098] Avg episode reward: [(0, '4568.712')] [2023-03-08 00:34:04,173][286389] Updated weights for policy 0, policy_version 134480 (0.0004) [2023-03-08 00:34:07,473][286389] Updated weights for policy 0, policy_version 134560 (0.0004) [2023-03-08 00:34:07,816][286098] Fps is (10 sec: 12288.0, 60 sec: 12083.2, 300 sec: 11829.8). Total num frames: 68898816. Throughput: 0: 12070.5. Samples: 68864956. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:34:07,816][286098] Avg episode reward: [(0, '4511.473')] [2023-03-08 00:34:10,786][286389] Updated weights for policy 0, policy_version 134640 (0.0004) [2023-03-08 00:34:12,816][286098] Fps is (10 sec: 12697.5, 60 sec: 12151.5, 300 sec: 11815.9). Total num frames: 68960256. Throughput: 0: 12186.7. Samples: 68939384. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:34:12,817][286098] Avg episode reward: [(0, '4467.331')] [2023-03-08 00:34:12,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000134688_68960256.pth... [2023-03-08 00:34:12,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000133968_68591616.pth [2023-03-08 00:34:14,142][286389] Updated weights for policy 0, policy_version 134720 (0.0004) [2023-03-08 00:34:17,570][286389] Updated weights for policy 0, policy_version 134800 (0.0004) [2023-03-08 00:34:17,816][286098] Fps is (10 sec: 11878.4, 60 sec: 12083.2, 300 sec: 11815.9). Total num frames: 69017600. Throughput: 0: 12156.3. Samples: 69011736. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:34:17,816][286098] Avg episode reward: [(0, '4457.123')] [2023-03-08 00:34:20,937][286389] Updated weights for policy 0, policy_version 134880 (0.0004) [2023-03-08 00:34:22,816][286098] Fps is (10 sec: 11878.5, 60 sec: 12151.5, 300 sec: 11843.7). Total num frames: 69079040. Throughput: 0: 12133.8. Samples: 69047596. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:34:22,816][286098] Avg episode reward: [(0, '4540.868')] [2023-03-08 00:34:24,306][286389] Updated weights for policy 0, policy_version 134960 (0.0004) [2023-03-08 00:34:27,594][286389] Updated weights for policy 0, policy_version 135040 (0.0004) [2023-03-08 00:34:27,816][286098] Fps is (10 sec: 12288.0, 60 sec: 12151.5, 300 sec: 11857.6). Total num frames: 69140480. Throughput: 0: 12166.1. Samples: 69121204. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:34:27,816][286098] Avg episode reward: [(0, '4509.041')] [2023-03-08 00:34:27,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000135040_69140480.pth... [2023-03-08 00:34:27,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000134328_68775936.pth [2023-03-08 00:34:30,999][286389] Updated weights for policy 0, policy_version 135120 (0.0004) [2023-03-08 00:34:32,816][286098] Fps is (10 sec: 12288.0, 60 sec: 12151.5, 300 sec: 11871.5). Total num frames: 69201920. Throughput: 0: 12130.4. Samples: 69193912. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:34:32,816][286098] Avg episode reward: [(0, '4519.032')] [2023-03-08 00:34:34,382][286389] Updated weights for policy 0, policy_version 135200 (0.0004) [2023-03-08 00:34:37,816][286098] Fps is (10 sec: 11878.5, 60 sec: 12083.2, 300 sec: 11871.5). Total num frames: 69259264. Throughput: 0: 12138.7. Samples: 69230452. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:34:37,816][286098] Avg episode reward: [(0, '4518.608')] [2023-03-08 00:34:38,094][286389] Updated weights for policy 0, policy_version 135280 (0.0005) [2023-03-08 00:34:41,791][286389] Updated weights for policy 0, policy_version 135360 (0.0004) [2023-03-08 00:34:42,816][286098] Fps is (10 sec: 11059.1, 60 sec: 12014.9, 300 sec: 11857.6). Total num frames: 69312512. Throughput: 0: 12009.9. Samples: 69296192. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:34:42,816][286098] Avg episode reward: [(0, '4463.177')] [2023-03-08 00:34:42,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000135376_69312512.pth... [2023-03-08 00:34:42,823][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000134688_68960256.pth [2023-03-08 00:34:45,539][286389] Updated weights for policy 0, policy_version 135440 (0.0005) [2023-03-08 00:34:47,816][286098] Fps is (10 sec: 11059.1, 60 sec: 11946.7, 300 sec: 11857.6). Total num frames: 69369856. Throughput: 0: 11870.3. Samples: 69362224. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:34:47,816][286098] Avg episode reward: [(0, '4523.493')] [2023-03-08 00:34:49,202][286389] Updated weights for policy 0, policy_version 135520 (0.0005) [2023-03-08 00:34:52,816][286098] Fps is (10 sec: 11059.3, 60 sec: 11810.1, 300 sec: 11843.7). Total num frames: 69423104. Throughput: 0: 11793.1. Samples: 69395644. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:34:52,816][286098] Avg episode reward: [(0, '4534.903')] [2023-03-08 00:34:52,904][286389] Updated weights for policy 0, policy_version 135600 (0.0005) [2023-03-08 00:34:56,580][286389] Updated weights for policy 0, policy_version 135680 (0.0005) [2023-03-08 00:34:57,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11741.9, 300 sec: 11843.7). Total num frames: 69480448. Throughput: 0: 11638.4. Samples: 69463112. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:34:57,816][286098] Avg episode reward: [(0, '4396.182')] [2023-03-08 00:34:57,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000135704_69480448.pth... [2023-03-08 00:34:57,823][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000135040_69140480.pth [2023-03-08 00:35:00,196][286389] Updated weights for policy 0, policy_version 135760 (0.0005) [2023-03-08 00:35:02,816][286098] Fps is (10 sec: 11468.7, 60 sec: 11741.9, 300 sec: 11829.8). Total num frames: 69537792. Throughput: 0: 11525.3. Samples: 69530376. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:35:02,816][286098] Avg episode reward: [(0, '4411.381')] [2023-03-08 00:35:03,789][286389] Updated weights for policy 0, policy_version 135840 (0.0005) [2023-03-08 00:35:07,475][286389] Updated weights for policy 0, policy_version 135920 (0.0005) [2023-03-08 00:35:07,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11537.1, 300 sec: 11802.0). Total num frames: 69591040. Throughput: 0: 11480.9. Samples: 69564236. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:35:07,816][286098] Avg episode reward: [(0, '4344.643')] [2023-03-08 00:35:11,102][286389] Updated weights for policy 0, policy_version 136000 (0.0005) [2023-03-08 00:35:12,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11468.8, 300 sec: 11788.1). Total num frames: 69648384. Throughput: 0: 11351.0. Samples: 69632000. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:35:12,816][286098] Avg episode reward: [(0, '4329.890')] [2023-03-08 00:35:12,881][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000136040_69652480.pth... [2023-03-08 00:35:12,884][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000135376_69312512.pth [2023-03-08 00:35:14,739][286389] Updated weights for policy 0, policy_version 136080 (0.0004) [2023-03-08 00:35:17,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11468.8, 300 sec: 11774.3). Total num frames: 69705728. Throughput: 0: 11204.3. Samples: 69698108. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:35:17,816][286098] Avg episode reward: [(0, '4404.811')] [2023-03-08 00:35:18,451][286389] Updated weights for policy 0, policy_version 136160 (0.0005) [2023-03-08 00:35:22,047][286389] Updated weights for policy 0, policy_version 136240 (0.0005) [2023-03-08 00:35:22,816][286098] Fps is (10 sec: 11468.9, 60 sec: 11400.5, 300 sec: 11760.4). Total num frames: 69763072. Throughput: 0: 11150.8. Samples: 69732240. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:35:22,816][286098] Avg episode reward: [(0, '4439.638')] [2023-03-08 00:35:25,778][286389] Updated weights for policy 0, policy_version 136320 (0.0005) [2023-03-08 00:35:27,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11264.0, 300 sec: 11746.5). Total num frames: 69816320. Throughput: 0: 11184.9. Samples: 69799512. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:35:27,816][286098] Avg episode reward: [(0, '4439.421')] [2023-03-08 00:35:27,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000136360_69816320.pth... [2023-03-08 00:35:27,823][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000135704_69480448.pth [2023-03-08 00:35:29,428][286389] Updated weights for policy 0, policy_version 136400 (0.0004) [2023-03-08 00:35:32,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11195.7, 300 sec: 11746.5). Total num frames: 69873664. Throughput: 0: 11184.9. Samples: 69865544. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:35:32,816][286098] Avg episode reward: [(0, '4355.627')] [2023-03-08 00:35:33,150][286389] Updated weights for policy 0, policy_version 136480 (0.0005) [2023-03-08 00:35:36,745][286389] Updated weights for policy 0, policy_version 136560 (0.0005) [2023-03-08 00:35:37,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11127.5, 300 sec: 11732.6). Total num frames: 69926912. Throughput: 0: 11196.7. Samples: 69899496. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:35:37,816][286098] Avg episode reward: [(0, '4242.267')] [2023-03-08 00:35:40,342][286389] Updated weights for policy 0, policy_version 136640 (0.0005) [2023-03-08 00:35:42,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11195.7, 300 sec: 11732.6). Total num frames: 69984256. Throughput: 0: 11217.3. Samples: 69967892. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:35:42,817][286098] Avg episode reward: [(0, '4227.041')] [2023-03-08 00:35:42,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000136688_69984256.pth... [2023-03-08 00:35:42,823][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000136040_69652480.pth [2023-03-08 00:35:44,038][286389] Updated weights for policy 0, policy_version 136720 (0.0005) [2023-03-08 00:35:47,774][286389] Updated weights for policy 0, policy_version 136800 (0.0005) [2023-03-08 00:35:47,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11195.7, 300 sec: 11732.6). Total num frames: 70041600. Throughput: 0: 11180.9. Samples: 70033516. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 00:35:47,816][286098] Avg episode reward: [(0, '4169.385')] [2023-03-08 00:35:51,443][286389] Updated weights for policy 0, policy_version 136880 (0.0005) [2023-03-08 00:35:52,816][286098] Fps is (10 sec: 11059.3, 60 sec: 11195.7, 300 sec: 11732.6). Total num frames: 70094848. Throughput: 0: 11166.0. Samples: 70066704. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 00:35:52,816][286098] Avg episode reward: [(0, '4223.451')] [2023-03-08 00:35:54,975][286389] Updated weights for policy 0, policy_version 136960 (0.0005) [2023-03-08 00:35:57,816][286098] Fps is (10 sec: 11468.7, 60 sec: 11264.0, 300 sec: 11746.5). Total num frames: 70156288. Throughput: 0: 11212.0. Samples: 70136540. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 00:35:57,816][286098] Avg episode reward: [(0, '4350.394')] [2023-03-08 00:35:57,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000137024_70156288.pth... [2023-03-08 00:35:57,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000136360_69816320.pth [2023-03-08 00:35:58,334][286389] Updated weights for policy 0, policy_version 137040 (0.0004) [2023-03-08 00:36:01,723][286389] Updated weights for policy 0, policy_version 137120 (0.0004) [2023-03-08 00:36:02,816][286098] Fps is (10 sec: 12287.9, 60 sec: 11332.3, 300 sec: 11760.4). Total num frames: 70217728. Throughput: 0: 11366.5. Samples: 70209600. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 00:36:02,816][286098] Avg episode reward: [(0, '4350.798')] [2023-03-08 00:36:05,243][286389] Updated weights for policy 0, policy_version 137200 (0.0004) [2023-03-08 00:36:07,816][286098] Fps is (10 sec: 11878.5, 60 sec: 11400.5, 300 sec: 11746.5). Total num frames: 70275072. Throughput: 0: 11386.4. Samples: 70244628. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 00:36:07,816][286098] Avg episode reward: [(0, '4510.607')] [2023-03-08 00:36:08,884][286389] Updated weights for policy 0, policy_version 137280 (0.0005) [2023-03-08 00:36:12,619][286389] Updated weights for policy 0, policy_version 137360 (0.0005) [2023-03-08 00:36:12,816][286098] Fps is (10 sec: 11059.1, 60 sec: 11332.3, 300 sec: 11718.7). Total num frames: 70328320. Throughput: 0: 11383.5. Samples: 70311768. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 00:36:12,827][286098] Avg episode reward: [(0, '4536.736')] [2023-03-08 00:36:12,830][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000137360_70328320.pth... [2023-03-08 00:36:12,833][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000136688_69984256.pth [2023-03-08 00:36:16,235][286389] Updated weights for policy 0, policy_version 137440 (0.0005) [2023-03-08 00:36:17,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11332.3, 300 sec: 11732.6). Total num frames: 70385664. Throughput: 0: 11403.9. Samples: 70378720. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 00:36:17,827][286098] Avg episode reward: [(0, '4533.775')] [2023-03-08 00:36:19,892][286389] Updated weights for policy 0, policy_version 137520 (0.0005) [2023-03-08 00:36:22,816][286098] Fps is (10 sec: 11468.9, 60 sec: 11332.3, 300 sec: 11732.6). Total num frames: 70443008. Throughput: 0: 11391.7. Samples: 70412120. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 00:36:22,827][286098] Avg episode reward: [(0, '4532.810')] [2023-03-08 00:36:23,512][286389] Updated weights for policy 0, policy_version 137600 (0.0005) [2023-03-08 00:36:27,195][286389] Updated weights for policy 0, policy_version 137680 (0.0005) [2023-03-08 00:36:27,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11332.3, 300 sec: 11704.8). Total num frames: 70496256. Throughput: 0: 11377.5. Samples: 70479880. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 00:36:27,827][286098] Avg episode reward: [(0, '4512.674')] [2023-03-08 00:36:27,830][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000137688_70496256.pth... [2023-03-08 00:36:27,833][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000137024_70156288.pth [2023-03-08 00:36:30,785][286389] Updated weights for policy 0, policy_version 137760 (0.0005) [2023-03-08 00:36:32,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11332.3, 300 sec: 11691.0). Total num frames: 70553600. Throughput: 0: 11430.7. Samples: 70547896. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 00:36:32,827][286098] Avg episode reward: [(0, '4520.538')] [2023-03-08 00:36:34,372][286389] Updated weights for policy 0, policy_version 137840 (0.0005) [2023-03-08 00:36:37,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11400.5, 300 sec: 11677.1). Total num frames: 70610944. Throughput: 0: 11456.1. Samples: 70582228. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 00:36:37,827][286098] Avg episode reward: [(0, '4546.194')] [2023-03-08 00:36:38,078][286389] Updated weights for policy 0, policy_version 137920 (0.0005) [2023-03-08 00:36:41,682][286389] Updated weights for policy 0, policy_version 138000 (0.0005) [2023-03-08 00:36:42,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11400.5, 300 sec: 11663.2). Total num frames: 70668288. Throughput: 0: 11381.2. Samples: 70648692. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 00:36:42,827][286098] Avg episode reward: [(0, '4500.848')] [2023-03-08 00:36:42,830][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000138024_70668288.pth... [2023-03-08 00:36:42,833][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000137360_70328320.pth [2023-03-08 00:36:45,127][286389] Updated weights for policy 0, policy_version 138080 (0.0003) [2023-03-08 00:36:47,816][286098] Fps is (10 sec: 11878.3, 60 sec: 11468.8, 300 sec: 11663.2). Total num frames: 70729728. Throughput: 0: 11364.1. Samples: 70720984. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 00:36:47,827][286098] Avg episode reward: [(0, '4530.675')] [2023-03-08 00:36:48,435][286389] Updated weights for policy 0, policy_version 138160 (0.0003) [2023-03-08 00:36:51,837][286389] Updated weights for policy 0, policy_version 138240 (0.0003) [2023-03-08 00:36:52,816][286098] Fps is (10 sec: 12288.0, 60 sec: 11605.3, 300 sec: 11663.2). Total num frames: 70791168. Throughput: 0: 11399.6. Samples: 70757612. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 00:36:52,827][286098] Avg episode reward: [(0, '4513.988')] [2023-03-08 00:36:55,225][286389] Updated weights for policy 0, policy_version 138320 (0.0003) [2023-03-08 00:36:57,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11537.1, 300 sec: 11663.2). Total num frames: 70848512. Throughput: 0: 11512.5. Samples: 70829828. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 00:36:57,827][286098] Avg episode reward: [(0, '4527.779')] [2023-03-08 00:36:57,830][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000138376_70848512.pth... [2023-03-08 00:36:57,832][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000137688_70496256.pth [2023-03-08 00:36:58,674][286389] Updated weights for policy 0, policy_version 138400 (0.0003) [2023-03-08 00:37:02,149][286389] Updated weights for policy 0, policy_version 138480 (0.0005) [2023-03-08 00:37:02,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11468.8, 300 sec: 11649.3). Total num frames: 70905856. Throughput: 0: 11605.2. Samples: 70900952. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 00:37:02,816][286098] Avg episode reward: [(0, '4489.899')] [2023-03-08 00:37:05,487][286389] Updated weights for policy 0, policy_version 138560 (0.0004) [2023-03-08 00:37:07,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11537.1, 300 sec: 11663.2). Total num frames: 70967296. Throughput: 0: 11678.0. Samples: 70937632. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 00:37:07,816][286098] Avg episode reward: [(0, '4493.976')] [2023-03-08 00:37:08,869][286389] Updated weights for policy 0, policy_version 138640 (0.0004) [2023-03-08 00:37:12,239][286389] Updated weights for policy 0, policy_version 138720 (0.0005) [2023-03-08 00:37:12,816][286098] Fps is (10 sec: 12288.0, 60 sec: 11673.6, 300 sec: 11663.2). Total num frames: 71028736. Throughput: 0: 11785.0. Samples: 71010204. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 00:37:12,816][286098] Avg episode reward: [(0, '4469.155')] [2023-03-08 00:37:12,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000138728_71028736.pth... [2023-03-08 00:37:12,821][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000138024_70668288.pth [2023-03-08 00:37:15,569][286389] Updated weights for policy 0, policy_version 138800 (0.0004) [2023-03-08 00:37:17,816][286098] Fps is (10 sec: 12288.0, 60 sec: 11741.9, 300 sec: 11677.1). Total num frames: 71090176. Throughput: 0: 11879.1. Samples: 71082456. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 00:37:17,816][286098] Avg episode reward: [(0, '4508.380')] [2023-03-08 00:37:19,266][286389] Updated weights for policy 0, policy_version 138880 (0.0005) [2023-03-08 00:37:22,816][286098] Fps is (10 sec: 11468.9, 60 sec: 11673.6, 300 sec: 11663.2). Total num frames: 71143424. Throughput: 0: 11841.1. Samples: 71115076. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 00:37:22,816][286098] Avg episode reward: [(0, '4502.147')] [2023-03-08 00:37:22,875][286389] Updated weights for policy 0, policy_version 138960 (0.0004) [2023-03-08 00:37:26,579][286389] Updated weights for policy 0, policy_version 139040 (0.0006) [2023-03-08 00:37:27,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11741.9, 300 sec: 11677.1). Total num frames: 71200768. Throughput: 0: 11877.4. Samples: 71183176. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 00:37:27,816][286098] Avg episode reward: [(0, '4549.738')] [2023-03-08 00:37:27,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000139064_71200768.pth... [2023-03-08 00:37:27,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000138376_70848512.pth [2023-03-08 00:37:30,182][286389] Updated weights for policy 0, policy_version 139120 (0.0005) [2023-03-08 00:37:32,816][286098] Fps is (10 sec: 11468.6, 60 sec: 11741.9, 300 sec: 11677.1). Total num frames: 71258112. Throughput: 0: 11765.5. Samples: 71250432. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 00:37:32,817][286098] Avg episode reward: [(0, '4515.327')] [2023-03-08 00:37:33,782][286389] Updated weights for policy 0, policy_version 139200 (0.0005) [2023-03-08 00:37:37,504][286389] Updated weights for policy 0, policy_version 139280 (0.0005) [2023-03-08 00:37:37,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11673.6, 300 sec: 11663.2). Total num frames: 71311360. Throughput: 0: 11712.0. Samples: 71284652. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 00:37:37,816][286098] Avg episode reward: [(0, '4555.183')] [2023-03-08 00:37:41,186][286389] Updated weights for policy 0, policy_version 139360 (0.0005) [2023-03-08 00:37:42,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11673.6, 300 sec: 11649.3). Total num frames: 71368704. Throughput: 0: 11588.2. Samples: 71351296. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 00:37:42,816][286098] Avg episode reward: [(0, '4552.362')] [2023-03-08 00:37:42,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000139392_71368704.pth... [2023-03-08 00:37:42,823][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000138728_71028736.pth [2023-03-08 00:37:44,827][286389] Updated weights for policy 0, policy_version 139440 (0.0005) [2023-03-08 00:37:47,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11605.3, 300 sec: 11635.4). Total num frames: 71426048. Throughput: 0: 11488.4. Samples: 71417928. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 00:37:47,816][286098] Avg episode reward: [(0, '4563.707')] [2023-03-08 00:37:48,481][286389] Updated weights for policy 0, policy_version 139520 (0.0005) [2023-03-08 00:37:51,906][286389] Updated weights for policy 0, policy_version 139600 (0.0003) [2023-03-08 00:37:52,816][286098] Fps is (10 sec: 11468.9, 60 sec: 11537.1, 300 sec: 11621.5). Total num frames: 71483392. Throughput: 0: 11447.9. Samples: 71452788. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 00:37:52,816][286098] Avg episode reward: [(0, '4518.607')] [2023-03-08 00:37:55,318][286389] Updated weights for policy 0, policy_version 139680 (0.0003) [2023-03-08 00:37:57,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11605.3, 300 sec: 11635.4). Total num frames: 71544832. Throughput: 0: 11432.9. Samples: 71524684. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 00:37:57,816][286098] Avg episode reward: [(0, '4513.718')] [2023-03-08 00:37:57,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000139736_71544832.pth... [2023-03-08 00:37:57,821][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000139064_71200768.pth [2023-03-08 00:37:58,769][286389] Updated weights for policy 0, policy_version 139760 (0.0003) [2023-03-08 00:38:02,143][286389] Updated weights for policy 0, policy_version 139840 (0.0003) [2023-03-08 00:38:02,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11605.3, 300 sec: 11621.5). Total num frames: 71602176. Throughput: 0: 11451.0. Samples: 71597752. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 00:38:02,816][286098] Avg episode reward: [(0, '4471.548')] [2023-03-08 00:38:05,619][286389] Updated weights for policy 0, policy_version 139920 (0.0004) [2023-03-08 00:38:07,816][286098] Fps is (10 sec: 11878.5, 60 sec: 11605.3, 300 sec: 11635.4). Total num frames: 71663616. Throughput: 0: 11486.2. Samples: 71631956. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 00:38:07,816][286098] Avg episode reward: [(0, '4460.378')] [2023-03-08 00:38:09,081][286389] Updated weights for policy 0, policy_version 140000 (0.0005) [2023-03-08 00:38:12,650][286389] Updated weights for policy 0, policy_version 140080 (0.0005) [2023-03-08 00:38:12,816][286098] Fps is (10 sec: 11878.3, 60 sec: 11537.1, 300 sec: 11621.5). Total num frames: 71720960. Throughput: 0: 11539.3. Samples: 71702444. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 00:38:12,816][286098] Avg episode reward: [(0, '4412.348')] [2023-03-08 00:38:12,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000140080_71720960.pth... [2023-03-08 00:38:12,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000139392_71368704.pth [2023-03-08 00:38:16,174][286389] Updated weights for policy 0, policy_version 140160 (0.0005) [2023-03-08 00:38:17,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11468.8, 300 sec: 11621.5). Total num frames: 71778304. Throughput: 0: 11594.5. Samples: 71772184. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 00:38:17,816][286098] Avg episode reward: [(0, '4539.296')] [2023-03-08 00:38:19,776][286389] Updated weights for policy 0, policy_version 140240 (0.0005) [2023-03-08 00:38:22,816][286098] Fps is (10 sec: 11468.9, 60 sec: 11537.1, 300 sec: 11607.7). Total num frames: 71835648. Throughput: 0: 11598.1. Samples: 71806568. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 00:38:22,816][286098] Avg episode reward: [(0, '4541.024')] [2023-03-08 00:38:23,411][286389] Updated weights for policy 0, policy_version 140320 (0.0006) [2023-03-08 00:38:26,965][286389] Updated weights for policy 0, policy_version 140400 (0.0005) [2023-03-08 00:38:27,816][286098] Fps is (10 sec: 11468.7, 60 sec: 11537.1, 300 sec: 11593.8). Total num frames: 71892992. Throughput: 0: 11624.6. Samples: 71874404. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 00:38:27,816][286098] Avg episode reward: [(0, '4509.657')] [2023-03-08 00:38:27,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000140416_71892992.pth... [2023-03-08 00:38:27,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000139736_71544832.pth [2023-03-08 00:38:30,592][286389] Updated weights for policy 0, policy_version 140480 (0.0006) [2023-03-08 00:38:32,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11537.1, 300 sec: 11579.9). Total num frames: 71950336. Throughput: 0: 11650.7. Samples: 71942208. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 00:38:32,816][286098] Avg episode reward: [(0, '4491.780')] [2023-03-08 00:38:34,246][286389] Updated weights for policy 0, policy_version 140560 (0.0006) [2023-03-08 00:38:37,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11537.1, 300 sec: 11566.0). Total num frames: 72003584. Throughput: 0: 11612.2. Samples: 71975336. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 00:38:37,816][286098] Avg episode reward: [(0, '4576.513')] [2023-03-08 00:38:37,950][286389] Updated weights for policy 0, policy_version 140640 (0.0005) [2023-03-08 00:38:41,698][286389] Updated weights for policy 0, policy_version 140720 (0.0005) [2023-03-08 00:38:42,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11537.1, 300 sec: 11552.1). Total num frames: 72060928. Throughput: 0: 11487.1. Samples: 72041604. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 00:38:42,816][286098] Avg episode reward: [(0, '4570.766')] [2023-03-08 00:38:42,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000140744_72060928.pth... [2023-03-08 00:38:42,821][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000140080_71720960.pth [2023-03-08 00:38:45,327][286389] Updated weights for policy 0, policy_version 140800 (0.0005) [2023-03-08 00:38:47,816][286098] Fps is (10 sec: 11059.3, 60 sec: 11468.8, 300 sec: 11524.3). Total num frames: 72114176. Throughput: 0: 11365.2. Samples: 72109184. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 00:38:47,816][286098] Avg episode reward: [(0, '4569.810')] [2023-03-08 00:38:48,962][286389] Updated weights for policy 0, policy_version 140880 (0.0005) [2023-03-08 00:38:52,551][286389] Updated weights for policy 0, policy_version 140960 (0.0004) [2023-03-08 00:38:52,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11468.8, 300 sec: 11510.5). Total num frames: 72171520. Throughput: 0: 11353.3. Samples: 72142856. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:38:52,816][286098] Avg episode reward: [(0, '4567.274')] [2023-03-08 00:38:55,973][286389] Updated weights for policy 0, policy_version 141040 (0.0003) [2023-03-08 00:38:57,816][286098] Fps is (10 sec: 11878.3, 60 sec: 11468.8, 300 sec: 11524.3). Total num frames: 72232960. Throughput: 0: 11353.5. Samples: 72213352. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:38:57,816][286098] Avg episode reward: [(0, '4574.532')] [2023-03-08 00:38:57,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000141080_72232960.pth... [2023-03-08 00:38:57,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000140416_71892992.pth [2023-03-08 00:38:59,494][286389] Updated weights for policy 0, policy_version 141120 (0.0003) [2023-03-08 00:39:02,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11468.8, 300 sec: 11496.6). Total num frames: 72290304. Throughput: 0: 11347.3. Samples: 72282812. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:39:02,816][286098] Avg episode reward: [(0, '4573.729')] [2023-03-08 00:39:03,051][286389] Updated weights for policy 0, policy_version 141200 (0.0004) [2023-03-08 00:39:06,760][286389] Updated weights for policy 0, policy_version 141280 (0.0005) [2023-03-08 00:39:07,816][286098] Fps is (10 sec: 11059.3, 60 sec: 11332.3, 300 sec: 11468.8). Total num frames: 72343552. Throughput: 0: 11345.3. Samples: 72317108. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:39:07,816][286098] Avg episode reward: [(0, '4572.333')] [2023-03-08 00:39:10,458][286389] Updated weights for policy 0, policy_version 141360 (0.0005) [2023-03-08 00:39:12,816][286098] Fps is (10 sec: 11059.1, 60 sec: 11332.3, 300 sec: 11468.8). Total num frames: 72400896. Throughput: 0: 11311.3. Samples: 72383412. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:39:12,816][286098] Avg episode reward: [(0, '4577.260')] [2023-03-08 00:39:12,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000141408_72400896.pth... [2023-03-08 00:39:12,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000140744_72060928.pth [2023-03-08 00:39:14,159][286389] Updated weights for policy 0, policy_version 141440 (0.0005) [2023-03-08 00:39:17,627][286389] Updated weights for policy 0, policy_version 141520 (0.0004) [2023-03-08 00:39:17,816][286098] Fps is (10 sec: 11468.7, 60 sec: 11332.3, 300 sec: 11454.9). Total num frames: 72458240. Throughput: 0: 11301.6. Samples: 72450780. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:39:17,816][286098] Avg episode reward: [(0, '4550.936')] [2023-03-08 00:39:20,937][286389] Updated weights for policy 0, policy_version 141600 (0.0003) [2023-03-08 00:39:22,816][286098] Fps is (10 sec: 11878.5, 60 sec: 11400.5, 300 sec: 11454.9). Total num frames: 72519680. Throughput: 0: 11397.2. Samples: 72488212. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:39:22,816][286098] Avg episode reward: [(0, '4568.081')] [2023-03-08 00:39:24,563][286389] Updated weights for policy 0, policy_version 141680 (0.0004) [2023-03-08 00:39:27,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11332.3, 300 sec: 11427.1). Total num frames: 72572928. Throughput: 0: 11445.0. Samples: 72556628. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:39:27,816][286098] Avg episode reward: [(0, '4578.029')] [2023-03-08 00:39:27,839][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000141752_72577024.pth... [2023-03-08 00:39:27,841][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000141080_72232960.pth [2023-03-08 00:39:28,191][286389] Updated weights for policy 0, policy_version 141760 (0.0005) [2023-03-08 00:39:31,826][286389] Updated weights for policy 0, policy_version 141840 (0.0004) [2023-03-08 00:39:32,816][286098] Fps is (10 sec: 11059.1, 60 sec: 11332.2, 300 sec: 11427.1). Total num frames: 72630272. Throughput: 0: 11462.1. Samples: 72624980. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:39:32,816][286098] Avg episode reward: [(0, '4576.184')] [2023-03-08 00:39:35,450][286389] Updated weights for policy 0, policy_version 141920 (0.0005) [2023-03-08 00:39:37,816][286098] Fps is (10 sec: 11468.7, 60 sec: 11400.5, 300 sec: 11441.0). Total num frames: 72687616. Throughput: 0: 11468.8. Samples: 72658952. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:39:37,816][286098] Avg episode reward: [(0, '4565.637')] [2023-03-08 00:39:39,092][286389] Updated weights for policy 0, policy_version 142000 (0.0005) [2023-03-08 00:39:42,663][286389] Updated weights for policy 0, policy_version 142080 (0.0005) [2023-03-08 00:39:42,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11400.5, 300 sec: 11441.0). Total num frames: 72744960. Throughput: 0: 11411.7. Samples: 72726880. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:39:42,816][286098] Avg episode reward: [(0, '4534.325')] [2023-03-08 00:39:42,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000142080_72744960.pth... [2023-03-08 00:39:42,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000141408_72400896.pth [2023-03-08 00:39:46,358][286389] Updated weights for policy 0, policy_version 142160 (0.0005) [2023-03-08 00:39:47,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11400.5, 300 sec: 11441.0). Total num frames: 72798208. Throughput: 0: 11362.5. Samples: 72794124. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:39:47,816][286098] Avg episode reward: [(0, '4563.855')] [2023-03-08 00:39:49,989][286389] Updated weights for policy 0, policy_version 142240 (0.0005) [2023-03-08 00:39:52,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11400.5, 300 sec: 11441.0). Total num frames: 72855552. Throughput: 0: 11342.1. Samples: 72827504. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:39:52,816][286098] Avg episode reward: [(0, '4509.125')] [2023-03-08 00:39:53,682][286389] Updated weights for policy 0, policy_version 142320 (0.0005) [2023-03-08 00:39:57,239][286389] Updated weights for policy 0, policy_version 142400 (0.0005) [2023-03-08 00:39:57,816][286098] Fps is (10 sec: 11468.9, 60 sec: 11332.3, 300 sec: 11441.0). Total num frames: 72912896. Throughput: 0: 11385.4. Samples: 72895756. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 00:39:57,816][286098] Avg episode reward: [(0, '4566.925')] [2023-03-08 00:39:57,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000142408_72912896.pth... [2023-03-08 00:39:57,823][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000141752_72577024.pth [2023-03-08 00:40:00,988][286389] Updated weights for policy 0, policy_version 142480 (0.0005) [2023-03-08 00:40:02,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11332.3, 300 sec: 11454.9). Total num frames: 72970240. Throughput: 0: 11362.9. Samples: 72962112. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 00:40:02,816][286098] Avg episode reward: [(0, '4576.931')] [2023-03-08 00:40:04,627][286389] Updated weights for policy 0, policy_version 142560 (0.0005) [2023-03-08 00:40:07,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11332.2, 300 sec: 11441.0). Total num frames: 73023488. Throughput: 0: 11271.6. Samples: 72995436. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 00:40:07,816][286098] Avg episode reward: [(0, '4577.453')] [2023-03-08 00:40:08,222][286389] Updated weights for policy 0, policy_version 142640 (0.0005) [2023-03-08 00:40:11,795][286389] Updated weights for policy 0, policy_version 142720 (0.0005) [2023-03-08 00:40:12,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11332.3, 300 sec: 11441.0). Total num frames: 73080832. Throughput: 0: 11285.0. Samples: 73064456. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 00:40:12,816][286098] Avg episode reward: [(0, '4571.970')] [2023-03-08 00:40:12,875][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000142744_73084928.pth... [2023-03-08 00:40:12,877][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000142080_72744960.pth [2023-03-08 00:40:15,400][286389] Updated weights for policy 0, policy_version 142800 (0.0005) [2023-03-08 00:40:17,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11332.3, 300 sec: 11441.0). Total num frames: 73138176. Throughput: 0: 11284.7. Samples: 73132792. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 00:40:17,816][286098] Avg episode reward: [(0, '4576.704')] [2023-03-08 00:40:19,071][286389] Updated weights for policy 0, policy_version 142880 (0.0005) [2023-03-08 00:40:22,704][286389] Updated weights for policy 0, policy_version 142960 (0.0005) [2023-03-08 00:40:22,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11264.0, 300 sec: 11454.9). Total num frames: 73195520. Throughput: 0: 11270.1. Samples: 73166108. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 00:40:22,816][286098] Avg episode reward: [(0, '4570.392')] [2023-03-08 00:40:26,314][286389] Updated weights for policy 0, policy_version 143040 (0.0005) [2023-03-08 00:40:27,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11332.2, 300 sec: 11454.9). Total num frames: 73252864. Throughput: 0: 11264.1. Samples: 73233764. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 00:40:27,816][286098] Avg episode reward: [(0, '4579.600')] [2023-03-08 00:40:27,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000143072_73252864.pth... [2023-03-08 00:40:27,821][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000142408_72912896.pth [2023-03-08 00:40:29,911][286389] Updated weights for policy 0, policy_version 143120 (0.0005) [2023-03-08 00:40:32,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11332.3, 300 sec: 11468.8). Total num frames: 73310208. Throughput: 0: 11286.8. Samples: 73302028. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 00:40:32,816][286098] Avg episode reward: [(0, '4576.742')] [2023-03-08 00:40:33,547][286389] Updated weights for policy 0, policy_version 143200 (0.0005) [2023-03-08 00:40:37,231][286389] Updated weights for policy 0, policy_version 143280 (0.0005) [2023-03-08 00:40:37,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11264.0, 300 sec: 11454.9). Total num frames: 73363456. Throughput: 0: 11280.2. Samples: 73335112. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 00:40:37,816][286098] Avg episode reward: [(0, '4570.217')] [2023-03-08 00:40:40,848][286389] Updated weights for policy 0, policy_version 143360 (0.0005) [2023-03-08 00:40:42,816][286098] Fps is (10 sec: 11059.1, 60 sec: 11264.0, 300 sec: 11454.9). Total num frames: 73420800. Throughput: 0: 11274.4. Samples: 73403104. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 00:40:42,816][286098] Avg episode reward: [(0, '4568.795')] [2023-03-08 00:40:42,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000143400_73420800.pth... [2023-03-08 00:40:42,823][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000142744_73084928.pth [2023-03-08 00:40:44,436][286389] Updated weights for policy 0, policy_version 143440 (0.0005) [2023-03-08 00:40:47,816][286098] Fps is (10 sec: 11468.9, 60 sec: 11332.3, 300 sec: 11468.8). Total num frames: 73478144. Throughput: 0: 11292.6. Samples: 73470276. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 00:40:47,816][286098] Avg episode reward: [(0, '4577.006')] [2023-03-08 00:40:48,124][286389] Updated weights for policy 0, policy_version 143520 (0.0005) [2023-03-08 00:40:51,691][286389] Updated weights for policy 0, policy_version 143600 (0.0005) [2023-03-08 00:40:52,816][286098] Fps is (10 sec: 11468.9, 60 sec: 11332.3, 300 sec: 11454.9). Total num frames: 73535488. Throughput: 0: 11301.9. Samples: 73504020. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 00:40:52,827][286098] Avg episode reward: [(0, '4568.338')] [2023-03-08 00:40:55,311][286389] Updated weights for policy 0, policy_version 143680 (0.0005) [2023-03-08 00:40:57,816][286098] Fps is (10 sec: 11059.1, 60 sec: 11264.0, 300 sec: 11427.1). Total num frames: 73588736. Throughput: 0: 11288.2. Samples: 73572424. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-08 00:40:57,827][286098] Avg episode reward: [(0, '4577.006')] [2023-03-08 00:40:57,830][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000143728_73588736.pth... [2023-03-08 00:40:57,833][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000143072_73252864.pth [2023-03-08 00:40:58,975][286389] Updated weights for policy 0, policy_version 143760 (0.0005) [2023-03-08 00:41:02,590][286389] Updated weights for policy 0, policy_version 143840 (0.0004) [2023-03-08 00:41:02,816][286098] Fps is (10 sec: 11059.3, 60 sec: 11264.0, 300 sec: 11427.1). Total num frames: 73646080. Throughput: 0: 11276.8. Samples: 73640248. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:41:02,827][286098] Avg episode reward: [(0, '4555.969')] [2023-03-08 00:41:06,282][286389] Updated weights for policy 0, policy_version 143920 (0.0005) [2023-03-08 00:41:07,816][286098] Fps is (10 sec: 11468.9, 60 sec: 11332.3, 300 sec: 11441.0). Total num frames: 73703424. Throughput: 0: 11297.5. Samples: 73674496. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:41:07,827][286098] Avg episode reward: [(0, '4549.876')] [2023-03-08 00:41:09,882][286389] Updated weights for policy 0, policy_version 144000 (0.0005) [2023-03-08 00:41:12,816][286098] Fps is (10 sec: 11468.7, 60 sec: 11332.3, 300 sec: 11441.0). Total num frames: 73760768. Throughput: 0: 11281.9. Samples: 73741448. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:41:12,827][286098] Avg episode reward: [(0, '4582.420')] [2023-03-08 00:41:12,830][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000144064_73760768.pth... [2023-03-08 00:41:12,833][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000143400_73420800.pth [2023-03-08 00:41:13,444][286389] Updated weights for policy 0, policy_version 144080 (0.0005) [2023-03-08 00:41:17,084][286389] Updated weights for policy 0, policy_version 144160 (0.0004) [2023-03-08 00:41:17,816][286098] Fps is (10 sec: 11059.0, 60 sec: 11264.0, 300 sec: 11427.1). Total num frames: 73814016. Throughput: 0: 11286.6. Samples: 73809928. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:41:17,827][286098] Avg episode reward: [(0, '4559.635')] [2023-03-08 00:41:20,772][286389] Updated weights for policy 0, policy_version 144240 (0.0005) [2023-03-08 00:41:22,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11264.0, 300 sec: 11441.0). Total num frames: 73871360. Throughput: 0: 11281.1. Samples: 73842760. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:41:22,827][286098] Avg episode reward: [(0, '4571.747')] [2023-03-08 00:41:24,477][286389] Updated weights for policy 0, policy_version 144320 (0.0005) [2023-03-08 00:41:27,816][286098] Fps is (10 sec: 11469.0, 60 sec: 11264.0, 300 sec: 11441.0). Total num frames: 73928704. Throughput: 0: 11243.7. Samples: 73909068. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:41:27,827][286098] Avg episode reward: [(0, '4580.648')] [2023-03-08 00:41:27,830][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000144392_73928704.pth... [2023-03-08 00:41:27,832][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000143728_73588736.pth [2023-03-08 00:41:28,163][286389] Updated weights for policy 0, policy_version 144400 (0.0005) [2023-03-08 00:41:31,811][286389] Updated weights for policy 0, policy_version 144480 (0.0005) [2023-03-08 00:41:32,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11195.7, 300 sec: 11427.1). Total num frames: 73981952. Throughput: 0: 11259.0. Samples: 73976932. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:41:32,827][286098] Avg episode reward: [(0, '4575.014')] [2023-03-08 00:41:35,431][286389] Updated weights for policy 0, policy_version 144560 (0.0005) [2023-03-08 00:41:37,816][286098] Fps is (10 sec: 11059.1, 60 sec: 11264.0, 300 sec: 11427.1). Total num frames: 74039296. Throughput: 0: 11259.3. Samples: 74010688. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:41:37,827][286098] Avg episode reward: [(0, '4572.046')] [2023-03-08 00:41:39,089][286389] Updated weights for policy 0, policy_version 144640 (0.0005) [2023-03-08 00:41:42,735][286389] Updated weights for policy 0, policy_version 144720 (0.0005) [2023-03-08 00:41:42,816][286098] Fps is (10 sec: 11468.7, 60 sec: 11264.0, 300 sec: 11413.3). Total num frames: 74096640. Throughput: 0: 11241.6. Samples: 74078296. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:41:42,827][286098] Avg episode reward: [(0, '4580.212')] [2023-03-08 00:41:42,830][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000144720_74096640.pth... [2023-03-08 00:41:42,833][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000144064_73760768.pth [2023-03-08 00:41:46,427][286389] Updated weights for policy 0, policy_version 144800 (0.0005) [2023-03-08 00:41:47,816][286098] Fps is (10 sec: 11059.3, 60 sec: 11195.7, 300 sec: 11385.5). Total num frames: 74149888. Throughput: 0: 11223.8. Samples: 74145320. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:41:47,827][286098] Avg episode reward: [(0, '4532.333')] [2023-03-08 00:41:50,012][286389] Updated weights for policy 0, policy_version 144880 (0.0005) [2023-03-08 00:41:52,816][286098] Fps is (10 sec: 11059.3, 60 sec: 11195.7, 300 sec: 11385.5). Total num frames: 74207232. Throughput: 0: 11207.5. Samples: 74178836. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:41:52,827][286098] Avg episode reward: [(0, '4517.998')] [2023-03-08 00:41:53,690][286389] Updated weights for policy 0, policy_version 144960 (0.0005) [2023-03-08 00:41:57,231][286389] Updated weights for policy 0, policy_version 145040 (0.0005) [2023-03-08 00:41:57,816][286098] Fps is (10 sec: 11468.6, 60 sec: 11264.0, 300 sec: 11385.5). Total num frames: 74264576. Throughput: 0: 11252.1. Samples: 74247792. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:41:57,817][286098] Avg episode reward: [(0, '4529.639')] [2023-03-08 00:41:57,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000145048_74264576.pth... [2023-03-08 00:41:57,823][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000144392_73928704.pth [2023-03-08 00:42:00,915][286389] Updated weights for policy 0, policy_version 145120 (0.0005) [2023-03-08 00:42:02,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11264.0, 300 sec: 11371.6). Total num frames: 74321920. Throughput: 0: 11207.2. Samples: 74314252. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 00:42:02,816][286098] Avg episode reward: [(0, '4498.821')] [2023-03-08 00:42:04,511][286389] Updated weights for policy 0, policy_version 145200 (0.0004) [2023-03-08 00:42:07,816][286098] Fps is (10 sec: 11469.0, 60 sec: 11264.0, 300 sec: 11357.7). Total num frames: 74379264. Throughput: 0: 11239.6. Samples: 74348540. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 00:42:07,816][286098] Avg episode reward: [(0, '4537.389')] [2023-03-08 00:42:08,120][286389] Updated weights for policy 0, policy_version 145280 (0.0005) [2023-03-08 00:42:11,707][286389] Updated weights for policy 0, policy_version 145360 (0.0005) [2023-03-08 00:42:12,816][286098] Fps is (10 sec: 11468.7, 60 sec: 11264.0, 300 sec: 11343.8). Total num frames: 74436608. Throughput: 0: 11275.8. Samples: 74416480. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 00:42:12,817][286098] Avg episode reward: [(0, '4570.721')] [2023-03-08 00:42:12,821][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000145384_74436608.pth... [2023-03-08 00:42:12,823][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000144720_74096640.pth [2023-03-08 00:42:15,356][286389] Updated weights for policy 0, policy_version 145440 (0.0005) [2023-03-08 00:42:17,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11264.0, 300 sec: 11343.8). Total num frames: 74489856. Throughput: 0: 11274.0. Samples: 74484260. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 00:42:17,816][286098] Avg episode reward: [(0, '4559.975')] [2023-03-08 00:42:19,122][286389] Updated weights for policy 0, policy_version 145520 (0.0005) [2023-03-08 00:42:22,740][286389] Updated weights for policy 0, policy_version 145600 (0.0005) [2023-03-08 00:42:22,816][286098] Fps is (10 sec: 11059.3, 60 sec: 11264.0, 300 sec: 11343.8). Total num frames: 74547200. Throughput: 0: 11240.1. Samples: 74516492. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 00:42:22,816][286098] Avg episode reward: [(0, '4569.714')] [2023-03-08 00:42:26,375][286389] Updated weights for policy 0, policy_version 145680 (0.0005) [2023-03-08 00:42:27,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11195.7, 300 sec: 11330.0). Total num frames: 74600448. Throughput: 0: 11249.6. Samples: 74584528. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 00:42:27,816][286098] Avg episode reward: [(0, '4573.137')] [2023-03-08 00:42:27,818][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000145704_74600448.pth... [2023-03-08 00:42:27,821][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000145048_74264576.pth [2023-03-08 00:42:30,111][286389] Updated weights for policy 0, policy_version 145760 (0.0005) [2023-03-08 00:42:32,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11264.0, 300 sec: 11343.8). Total num frames: 74657792. Throughput: 0: 11233.3. Samples: 74650820. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 00:42:32,816][286098] Avg episode reward: [(0, '4573.037')] [2023-03-08 00:42:33,820][286389] Updated weights for policy 0, policy_version 145840 (0.0005) [2023-03-08 00:42:37,438][286389] Updated weights for policy 0, policy_version 145920 (0.0005) [2023-03-08 00:42:37,816][286098] Fps is (10 sec: 11468.7, 60 sec: 11264.0, 300 sec: 11343.8). Total num frames: 74715136. Throughput: 0: 11232.1. Samples: 74684280. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 00:42:37,817][286098] Avg episode reward: [(0, '4570.425')] [2023-03-08 00:42:40,988][286389] Updated weights for policy 0, policy_version 146000 (0.0005) [2023-03-08 00:42:42,816][286098] Fps is (10 sec: 11059.1, 60 sec: 11195.7, 300 sec: 11330.0). Total num frames: 74768384. Throughput: 0: 11219.0. Samples: 74752648. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 00:42:42,816][286098] Avg episode reward: [(0, '4583.870')] [2023-03-08 00:42:42,842][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000146040_74772480.pth... [2023-03-08 00:42:42,843][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000145384_74436608.pth [2023-03-08 00:42:44,694][286389] Updated weights for policy 0, policy_version 146080 (0.0005) [2023-03-08 00:42:47,816][286098] Fps is (10 sec: 11059.3, 60 sec: 11264.0, 300 sec: 11330.0). Total num frames: 74825728. Throughput: 0: 11228.7. Samples: 74819544. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 00:42:47,816][286098] Avg episode reward: [(0, '4574.372')] [2023-03-08 00:42:48,310][286389] Updated weights for policy 0, policy_version 146160 (0.0005) [2023-03-08 00:42:51,903][286389] Updated weights for policy 0, policy_version 146240 (0.0005) [2023-03-08 00:42:52,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11264.0, 300 sec: 11316.1). Total num frames: 74883072. Throughput: 0: 11236.2. Samples: 74854168. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 00:42:52,816][286098] Avg episode reward: [(0, '4554.294')] [2023-03-08 00:42:55,503][286389] Updated weights for policy 0, policy_version 146320 (0.0005) [2023-03-08 00:42:57,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11264.0, 300 sec: 11316.1). Total num frames: 74940416. Throughput: 0: 11239.4. Samples: 74922252. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 00:42:57,816][286098] Avg episode reward: [(0, '4581.640')] [2023-03-08 00:42:57,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000146368_74940416.pth... [2023-03-08 00:42:57,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000145704_74600448.pth [2023-03-08 00:42:59,192][286389] Updated weights for policy 0, policy_version 146400 (0.0005) [2023-03-08 00:43:02,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11195.7, 300 sec: 11288.3). Total num frames: 74993664. Throughput: 0: 11226.2. Samples: 74989440. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 00:43:02,816][286098] Avg episode reward: [(0, '4578.344')] [2023-03-08 00:43:02,835][286389] Updated weights for policy 0, policy_version 146480 (0.0005) [2023-03-08 00:43:06,515][286389] Updated weights for policy 0, policy_version 146560 (0.0005) [2023-03-08 00:43:07,816][286098] Fps is (10 sec: 11059.3, 60 sec: 11195.7, 300 sec: 11288.3). Total num frames: 75051008. Throughput: 0: 11241.2. Samples: 75022344. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:43:07,816][286098] Avg episode reward: [(0, '4578.012')] [2023-03-08 00:43:10,172][286389] Updated weights for policy 0, policy_version 146640 (0.0005) [2023-03-08 00:43:12,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11195.7, 300 sec: 11288.3). Total num frames: 75108352. Throughput: 0: 11230.2. Samples: 75089888. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:43:12,816][286098] Avg episode reward: [(0, '4581.363')] [2023-03-08 00:43:12,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000146696_75108352.pth... [2023-03-08 00:43:12,823][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000146040_74772480.pth [2023-03-08 00:43:13,874][286389] Updated weights for policy 0, policy_version 146720 (0.0005) [2023-03-08 00:43:17,558][286389] Updated weights for policy 0, policy_version 146800 (0.0005) [2023-03-08 00:43:17,816][286098] Fps is (10 sec: 11059.1, 60 sec: 11195.7, 300 sec: 11274.4). Total num frames: 75161600. Throughput: 0: 11235.0. Samples: 75156396. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:43:17,816][286098] Avg episode reward: [(0, '4581.840')] [2023-03-08 00:43:21,235][286389] Updated weights for policy 0, policy_version 146880 (0.0005) [2023-03-08 00:43:22,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11195.7, 300 sec: 11274.4). Total num frames: 75218944. Throughput: 0: 11230.2. Samples: 75189636. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:43:22,816][286098] Avg episode reward: [(0, '4579.365')] [2023-03-08 00:43:24,920][286389] Updated weights for policy 0, policy_version 146960 (0.0005) [2023-03-08 00:43:27,816][286098] Fps is (10 sec: 11059.1, 60 sec: 11195.7, 300 sec: 11260.5). Total num frames: 75272192. Throughput: 0: 11188.6. Samples: 75256136. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:43:27,817][286098] Avg episode reward: [(0, '4576.964')] [2023-03-08 00:43:27,837][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000147024_75276288.pth... [2023-03-08 00:43:27,839][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000146368_74940416.pth [2023-03-08 00:43:28,578][286389] Updated weights for policy 0, policy_version 147040 (0.0005) [2023-03-08 00:43:32,176][286389] Updated weights for policy 0, policy_version 147120 (0.0005) [2023-03-08 00:43:32,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11195.7, 300 sec: 11274.4). Total num frames: 75329536. Throughput: 0: 11215.8. Samples: 75324256. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:43:32,816][286098] Avg episode reward: [(0, '4570.652')] [2023-03-08 00:43:35,846][286389] Updated weights for policy 0, policy_version 147200 (0.0004) [2023-03-08 00:43:37,816][286098] Fps is (10 sec: 11468.9, 60 sec: 11195.7, 300 sec: 11274.4). Total num frames: 75386880. Throughput: 0: 11197.8. Samples: 75358068. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:43:37,816][286098] Avg episode reward: [(0, '4556.435')] [2023-03-08 00:43:39,435][286389] Updated weights for policy 0, policy_version 147280 (0.0003) [2023-03-08 00:43:42,816][286098] Fps is (10 sec: 11468.9, 60 sec: 11264.0, 300 sec: 11288.3). Total num frames: 75444224. Throughput: 0: 11176.2. Samples: 75425180. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:43:42,816][286098] Avg episode reward: [(0, '4570.301')] [2023-03-08 00:43:42,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000147352_75444224.pth... [2023-03-08 00:43:42,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000146696_75108352.pth [2023-03-08 00:43:43,114][286389] Updated weights for policy 0, policy_version 147360 (0.0005) [2023-03-08 00:43:46,692][286389] Updated weights for policy 0, policy_version 147440 (0.0005) [2023-03-08 00:43:47,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11264.0, 300 sec: 11288.3). Total num frames: 75501568. Throughput: 0: 11200.2. Samples: 75493448. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:43:47,816][286098] Avg episode reward: [(0, '4574.037')] [2023-03-08 00:43:50,296][286389] Updated weights for policy 0, policy_version 147520 (0.0004) [2023-03-08 00:43:52,816][286098] Fps is (10 sec: 11059.1, 60 sec: 11195.7, 300 sec: 11260.5). Total num frames: 75554816. Throughput: 0: 11224.8. Samples: 75527460. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:43:52,816][286098] Avg episode reward: [(0, '4575.789')] [2023-03-08 00:43:53,920][286389] Updated weights for policy 0, policy_version 147600 (0.0004) [2023-03-08 00:43:57,555][286389] Updated weights for policy 0, policy_version 147680 (0.0005) [2023-03-08 00:43:57,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11195.7, 300 sec: 11260.5). Total num frames: 75612160. Throughput: 0: 11242.2. Samples: 75595788. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:43:57,817][286098] Avg episode reward: [(0, '4485.801')] [2023-03-08 00:43:57,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000147680_75612160.pth... [2023-03-08 00:43:57,823][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000147024_75276288.pth [2023-03-08 00:44:01,156][286389] Updated weights for policy 0, policy_version 147760 (0.0005) [2023-03-08 00:44:02,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11264.0, 300 sec: 11274.4). Total num frames: 75669504. Throughput: 0: 11267.2. Samples: 75663420. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:44:02,816][286098] Avg episode reward: [(0, '4571.979')] [2023-03-08 00:44:04,777][286389] Updated weights for policy 0, policy_version 147840 (0.0005) [2023-03-08 00:44:07,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11264.0, 300 sec: 11274.4). Total num frames: 75726848. Throughput: 0: 11292.3. Samples: 75697788. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:44:07,816][286098] Avg episode reward: [(0, '4567.284')] [2023-03-08 00:44:08,411][286389] Updated weights for policy 0, policy_version 147920 (0.0005) [2023-03-08 00:44:12,078][286389] Updated weights for policy 0, policy_version 148000 (0.0005) [2023-03-08 00:44:12,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11264.0, 300 sec: 11274.4). Total num frames: 75784192. Throughput: 0: 11287.4. Samples: 75764068. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:44:12,816][286098] Avg episode reward: [(0, '4573.336')] [2023-03-08 00:44:12,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000148016_75784192.pth... [2023-03-08 00:44:12,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000147352_75444224.pth [2023-03-08 00:44:15,775][286389] Updated weights for policy 0, policy_version 148080 (0.0005) [2023-03-08 00:44:17,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11264.0, 300 sec: 11246.6). Total num frames: 75837440. Throughput: 0: 11283.6. Samples: 75832016. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:44:17,816][286098] Avg episode reward: [(0, '4571.603')] [2023-03-08 00:44:19,385][286389] Updated weights for policy 0, policy_version 148160 (0.0005) [2023-03-08 00:44:22,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11264.0, 300 sec: 11260.5). Total num frames: 75894784. Throughput: 0: 11290.0. Samples: 75866120. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:44:22,816][286098] Avg episode reward: [(0, '4565.193')] [2023-03-08 00:44:23,010][286389] Updated weights for policy 0, policy_version 148240 (0.0005) [2023-03-08 00:44:26,702][286389] Updated weights for policy 0, policy_version 148320 (0.0005) [2023-03-08 00:44:27,816][286098] Fps is (10 sec: 11468.9, 60 sec: 11332.3, 300 sec: 11260.5). Total num frames: 75952128. Throughput: 0: 11280.9. Samples: 75932820. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:44:27,816][286098] Avg episode reward: [(0, '4561.028')] [2023-03-08 00:44:27,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000148344_75952128.pth... [2023-03-08 00:44:27,820][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000147680_75612160.pth [2023-03-08 00:44:30,335][286389] Updated weights for policy 0, policy_version 148400 (0.0005) [2023-03-08 00:44:32,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11332.3, 300 sec: 11260.5). Total num frames: 76009472. Throughput: 0: 11285.2. Samples: 76001280. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:44:32,827][286098] Avg episode reward: [(0, '4563.981')] [2023-03-08 00:44:33,882][286389] Updated weights for policy 0, policy_version 148480 (0.0005) [2023-03-08 00:44:37,518][286389] Updated weights for policy 0, policy_version 148560 (0.0005) [2023-03-08 00:44:37,816][286098] Fps is (10 sec: 11059.1, 60 sec: 11264.0, 300 sec: 11246.6). Total num frames: 76062720. Throughput: 0: 11280.1. Samples: 76035064. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:44:37,827][286098] Avg episode reward: [(0, '4563.355')] [2023-03-08 00:44:41,131][286389] Updated weights for policy 0, policy_version 148640 (0.0005) [2023-03-08 00:44:42,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11264.0, 300 sec: 11260.5). Total num frames: 76120064. Throughput: 0: 11281.3. Samples: 76103448. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:44:42,827][286098] Avg episode reward: [(0, '4563.120')] [2023-03-08 00:44:42,830][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000148672_76120064.pth... [2023-03-08 00:44:42,833][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000148016_75784192.pth [2023-03-08 00:44:44,739][286389] Updated weights for policy 0, policy_version 148720 (0.0005) [2023-03-08 00:44:47,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11264.0, 300 sec: 11260.5). Total num frames: 76177408. Throughput: 0: 11278.7. Samples: 76170960. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:44:47,827][286098] Avg episode reward: [(0, '4557.708')] [2023-03-08 00:44:48,355][286389] Updated weights for policy 0, policy_version 148800 (0.0005) [2023-03-08 00:44:51,975][286389] Updated weights for policy 0, policy_version 148880 (0.0005) [2023-03-08 00:44:52,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11332.3, 300 sec: 11260.5). Total num frames: 76234752. Throughput: 0: 11281.0. Samples: 76205432. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:44:52,827][286098] Avg episode reward: [(0, '4561.406')] [2023-03-08 00:44:55,579][286389] Updated weights for policy 0, policy_version 148960 (0.0005) [2023-03-08 00:44:57,816][286098] Fps is (10 sec: 11468.7, 60 sec: 11332.3, 300 sec: 11260.5). Total num frames: 76292096. Throughput: 0: 11306.1. Samples: 76272844. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:44:57,827][286098] Avg episode reward: [(0, '4566.137')] [2023-03-08 00:44:57,830][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000149008_76292096.pth... [2023-03-08 00:44:57,832][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000148344_75952128.pth [2023-03-08 00:44:59,177][286389] Updated weights for policy 0, policy_version 149040 (0.0005) [2023-03-08 00:45:02,799][286389] Updated weights for policy 0, policy_version 149120 (0.0005) [2023-03-08 00:45:02,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11332.3, 300 sec: 11274.4). Total num frames: 76349440. Throughput: 0: 11317.7. Samples: 76341312. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:45:02,827][286098] Avg episode reward: [(0, '4556.941')] [2023-03-08 00:45:06,439][286389] Updated weights for policy 0, policy_version 149200 (0.0005) [2023-03-08 00:45:07,816][286098] Fps is (10 sec: 11059.3, 60 sec: 11264.0, 300 sec: 11260.5). Total num frames: 76402688. Throughput: 0: 11298.4. Samples: 76374548. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:45:07,827][286098] Avg episode reward: [(0, '4565.952')] [2023-03-08 00:45:10,085][286389] Updated weights for policy 0, policy_version 149280 (0.0005) [2023-03-08 00:45:12,816][286098] Fps is (10 sec: 11059.1, 60 sec: 11264.0, 300 sec: 11260.5). Total num frames: 76460032. Throughput: 0: 11341.3. Samples: 76443180. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:45:12,827][286098] Avg episode reward: [(0, '4561.442')] [2023-03-08 00:45:12,830][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000149336_76460032.pth... [2023-03-08 00:45:12,833][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000148672_76120064.pth [2023-03-08 00:45:13,718][286389] Updated weights for policy 0, policy_version 149360 (0.0005) [2023-03-08 00:45:17,380][286389] Updated weights for policy 0, policy_version 149440 (0.0005) [2023-03-08 00:45:17,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11332.3, 300 sec: 11260.5). Total num frames: 76517376. Throughput: 0: 11294.2. Samples: 76509520. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:45:17,827][286098] Avg episode reward: [(0, '4563.370')] [2023-03-08 00:45:21,008][286389] Updated weights for policy 0, policy_version 149520 (0.0005) [2023-03-08 00:45:22,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11264.0, 300 sec: 11246.6). Total num frames: 76570624. Throughput: 0: 11295.8. Samples: 76543376. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:45:22,827][286098] Avg episode reward: [(0, '4559.488')] [2023-03-08 00:45:24,639][286389] Updated weights for policy 0, policy_version 149600 (0.0005) [2023-03-08 00:45:27,816][286098] Fps is (10 sec: 11468.7, 60 sec: 11332.2, 300 sec: 11260.5). Total num frames: 76632064. Throughput: 0: 11293.3. Samples: 76611648. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:45:27,827][286098] Avg episode reward: [(0, '4556.157')] [2023-03-08 00:45:27,830][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000149672_76632064.pth... [2023-03-08 00:45:27,833][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000149008_76292096.pth [2023-03-08 00:45:28,022][286389] Updated weights for policy 0, policy_version 149680 (0.0004) [2023-03-08 00:45:31,327][286389] Updated weights for policy 0, policy_version 149760 (0.0004) [2023-03-08 00:45:32,816][286098] Fps is (10 sec: 12288.1, 60 sec: 11400.5, 300 sec: 11288.3). Total num frames: 76693504. Throughput: 0: 11436.6. Samples: 76685608. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:45:32,816][286098] Avg episode reward: [(0, '4561.463')] [2023-03-08 00:45:34,647][286389] Updated weights for policy 0, policy_version 149840 (0.0003) [2023-03-08 00:45:37,816][286098] Fps is (10 sec: 12288.1, 60 sec: 11537.1, 300 sec: 11302.2). Total num frames: 76754944. Throughput: 0: 11503.6. Samples: 76723096. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:45:37,816][286098] Avg episode reward: [(0, '4563.867')] [2023-03-08 00:45:37,980][286389] Updated weights for policy 0, policy_version 149920 (0.0004) [2023-03-08 00:45:41,267][286389] Updated weights for policy 0, policy_version 150000 (0.0004) [2023-03-08 00:45:42,816][286098] Fps is (10 sec: 12287.9, 60 sec: 11605.3, 300 sec: 11316.1). Total num frames: 76816384. Throughput: 0: 11655.6. Samples: 76797344. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:45:42,816][286098] Avg episode reward: [(0, '4561.717')] [2023-03-08 00:45:42,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000150032_76816384.pth... [2023-03-08 00:45:42,821][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000149336_76460032.pth [2023-03-08 00:45:44,527][286389] Updated weights for policy 0, policy_version 150080 (0.0003) [2023-03-08 00:45:47,816][286098] Fps is (10 sec: 12288.0, 60 sec: 11673.6, 300 sec: 11330.0). Total num frames: 76877824. Throughput: 0: 11783.5. Samples: 76871568. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:45:47,816][286098] Avg episode reward: [(0, '4563.979')] [2023-03-08 00:45:47,880][286389] Updated weights for policy 0, policy_version 150160 (0.0004) [2023-03-08 00:45:51,193][286389] Updated weights for policy 0, policy_version 150240 (0.0003) [2023-03-08 00:45:52,816][286098] Fps is (10 sec: 12288.1, 60 sec: 11741.9, 300 sec: 11357.7). Total num frames: 76939264. Throughput: 0: 11867.4. Samples: 76908580. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:45:52,816][286098] Avg episode reward: [(0, '4566.700')] [2023-03-08 00:45:54,526][286389] Updated weights for policy 0, policy_version 150320 (0.0004) [2023-03-08 00:45:57,816][286098] Fps is (10 sec: 12288.0, 60 sec: 11810.1, 300 sec: 11371.6). Total num frames: 77000704. Throughput: 0: 11986.1. Samples: 76982556. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:45:57,827][286098] Avg episode reward: [(0, '4564.338')] [2023-03-08 00:45:57,831][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000150392_77000704.pth... [2023-03-08 00:45:57,833][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000149672_76632064.pth [2023-03-08 00:45:57,878][286389] Updated weights for policy 0, policy_version 150400 (0.0004) [2023-03-08 00:46:01,153][286389] Updated weights for policy 0, policy_version 150480 (0.0004) [2023-03-08 00:46:02,816][286098] Fps is (10 sec: 12697.7, 60 sec: 11946.7, 300 sec: 11399.4). Total num frames: 77066240. Throughput: 0: 12160.6. Samples: 77056748. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:46:02,827][286098] Avg episode reward: [(0, '4560.782')] [2023-03-08 00:46:04,508][286389] Updated weights for policy 0, policy_version 150560 (0.0004) [2023-03-08 00:46:07,812][286389] Updated weights for policy 0, policy_version 150640 (0.0004) [2023-03-08 00:46:07,816][286098] Fps is (10 sec: 12697.6, 60 sec: 12083.2, 300 sec: 11413.3). Total num frames: 77127680. Throughput: 0: 12231.0. Samples: 77093772. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:46:07,827][286098] Avg episode reward: [(0, '4557.389')] [2023-03-08 00:46:11,130][286389] Updated weights for policy 0, policy_version 150720 (0.0004) [2023-03-08 00:46:12,816][286098] Fps is (10 sec: 12287.8, 60 sec: 12151.5, 300 sec: 11441.0). Total num frames: 77189120. Throughput: 0: 12365.3. Samples: 77168088. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:46:12,827][286098] Avg episode reward: [(0, '4565.760')] [2023-03-08 00:46:12,830][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000150760_77189120.pth... [2023-03-08 00:46:12,833][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000150032_76816384.pth [2023-03-08 00:46:14,455][286389] Updated weights for policy 0, policy_version 150800 (0.0004) [2023-03-08 00:46:17,807][286389] Updated weights for policy 0, policy_version 150880 (0.0004) [2023-03-08 00:46:17,816][286098] Fps is (10 sec: 12287.9, 60 sec: 12219.7, 300 sec: 11454.9). Total num frames: 77250560. Throughput: 0: 12368.1. Samples: 77242176. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:46:17,827][286098] Avg episode reward: [(0, '4567.010')] [2023-03-08 00:46:21,148][286389] Updated weights for policy 0, policy_version 150960 (0.0004) [2023-03-08 00:46:22,816][286098] Fps is (10 sec: 12288.1, 60 sec: 12356.3, 300 sec: 11468.8). Total num frames: 77312000. Throughput: 0: 12342.4. Samples: 77278504. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:46:22,827][286098] Avg episode reward: [(0, '4566.622')] [2023-03-08 00:46:24,449][286389] Updated weights for policy 0, policy_version 151040 (0.0004) [2023-03-08 00:46:27,797][286389] Updated weights for policy 0, policy_version 151120 (0.0004) [2023-03-08 00:46:27,816][286098] Fps is (10 sec: 12288.0, 60 sec: 12356.3, 300 sec: 11496.6). Total num frames: 77373440. Throughput: 0: 12330.1. Samples: 77352200. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:46:27,827][286098] Avg episode reward: [(0, '4564.362')] [2023-03-08 00:46:27,830][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000151120_77373440.pth... [2023-03-08 00:46:27,833][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000150392_77000704.pth [2023-03-08 00:46:31,044][286389] Updated weights for policy 0, policy_version 151200 (0.0003) [2023-03-08 00:46:32,816][286098] Fps is (10 sec: 12288.0, 60 sec: 12356.3, 300 sec: 11510.5). Total num frames: 77434880. Throughput: 0: 12337.4. Samples: 77426752. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:46:32,827][286098] Avg episode reward: [(0, '4564.727')] [2023-03-08 00:46:34,388][286389] Updated weights for policy 0, policy_version 151280 (0.0004) [2023-03-08 00:46:37,816][286098] Fps is (10 sec: 11878.4, 60 sec: 12288.0, 300 sec: 11510.5). Total num frames: 77492224. Throughput: 0: 12334.7. Samples: 77463640. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:46:37,827][286098] Avg episode reward: [(0, '4568.813')] [2023-03-08 00:46:38,015][286389] Updated weights for policy 0, policy_version 151360 (0.0004) [2023-03-08 00:46:41,648][286389] Updated weights for policy 0, policy_version 151440 (0.0005) [2023-03-08 00:46:42,816][286098] Fps is (10 sec: 11468.8, 60 sec: 12219.7, 300 sec: 11524.3). Total num frames: 77549568. Throughput: 0: 12184.0. Samples: 77530836. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:46:42,827][286098] Avg episode reward: [(0, '4553.783')] [2023-03-08 00:46:42,830][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000151464_77549568.pth... [2023-03-08 00:46:42,833][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000150760_77189120.pth [2023-03-08 00:46:44,949][286389] Updated weights for policy 0, policy_version 151520 (0.0004) [2023-03-08 00:46:47,816][286098] Fps is (10 sec: 11878.4, 60 sec: 12219.7, 300 sec: 11538.2). Total num frames: 77611008. Throughput: 0: 12150.2. Samples: 77603508. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:46:47,816][286098] Avg episode reward: [(0, '4433.986')] [2023-03-08 00:46:48,311][286389] Updated weights for policy 0, policy_version 151600 (0.0004) [2023-03-08 00:46:51,678][286389] Updated weights for policy 0, policy_version 151680 (0.0004) [2023-03-08 00:46:52,816][286098] Fps is (10 sec: 12288.0, 60 sec: 12219.7, 300 sec: 11552.1). Total num frames: 77672448. Throughput: 0: 12145.0. Samples: 77640296. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:46:52,816][286098] Avg episode reward: [(0, '4440.282')] [2023-03-08 00:46:55,235][286389] Updated weights for policy 0, policy_version 151760 (0.0005) [2023-03-08 00:46:57,816][286098] Fps is (10 sec: 11468.7, 60 sec: 12083.2, 300 sec: 11538.2). Total num frames: 77725696. Throughput: 0: 12058.2. Samples: 77710708. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:46:57,817][286098] Avg episode reward: [(0, '4524.083')] [2023-03-08 00:46:57,822][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000151816_77729792.pth... [2023-03-08 00:46:57,824][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000151120_77373440.pth [2023-03-08 00:46:58,853][286389] Updated weights for policy 0, policy_version 151840 (0.0005) [2023-03-08 00:47:02,216][286389] Updated weights for policy 0, policy_version 151920 (0.0004) [2023-03-08 00:47:02,816][286098] Fps is (10 sec: 11468.8, 60 sec: 12014.9, 300 sec: 11552.1). Total num frames: 77787136. Throughput: 0: 11969.4. Samples: 77780800. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:47:02,816][286098] Avg episode reward: [(0, '4530.978')] [2023-03-08 00:47:05,550][286389] Updated weights for policy 0, policy_version 152000 (0.0005) [2023-03-08 00:47:07,816][286098] Fps is (10 sec: 12288.2, 60 sec: 12015.0, 300 sec: 11566.0). Total num frames: 77848576. Throughput: 0: 11988.9. Samples: 77818004. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:47:07,816][286098] Avg episode reward: [(0, '4561.223')] [2023-03-08 00:47:08,850][286389] Updated weights for policy 0, policy_version 152080 (0.0004) [2023-03-08 00:47:12,145][286389] Updated weights for policy 0, policy_version 152160 (0.0003) [2023-03-08 00:47:12,816][286098] Fps is (10 sec: 12697.6, 60 sec: 12083.2, 300 sec: 11607.6). Total num frames: 77914112. Throughput: 0: 12007.1. Samples: 77892520. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:47:12,816][286098] Avg episode reward: [(0, '4559.926')] [2023-03-08 00:47:12,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000152176_77914112.pth... [2023-03-08 00:47:12,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000151464_77549568.pth [2023-03-08 00:47:15,500][286389] Updated weights for policy 0, policy_version 152240 (0.0003) [2023-03-08 00:47:17,816][286098] Fps is (10 sec: 12288.0, 60 sec: 12015.0, 300 sec: 11607.7). Total num frames: 77971456. Throughput: 0: 11967.3. Samples: 77965280. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:47:17,816][286098] Avg episode reward: [(0, '4559.230')] [2023-03-08 00:47:18,965][286389] Updated weights for policy 0, policy_version 152320 (0.0004) [2023-03-08 00:47:22,674][286389] Updated weights for policy 0, policy_version 152400 (0.0005) [2023-03-08 00:47:22,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11946.7, 300 sec: 11621.5). Total num frames: 78028800. Throughput: 0: 11922.1. Samples: 78000136. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:47:22,816][286098] Avg episode reward: [(0, '4541.011')] [2023-03-08 00:47:26,223][286389] Updated weights for policy 0, policy_version 152480 (0.0005) [2023-03-08 00:47:27,816][286098] Fps is (10 sec: 11468.7, 60 sec: 11878.4, 300 sec: 11621.5). Total num frames: 78086144. Throughput: 0: 11933.6. Samples: 78067848. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:47:27,816][286098] Avg episode reward: [(0, '4566.761')] [2023-03-08 00:47:27,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000152512_78086144.pth... [2023-03-08 00:47:27,823][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000151816_77729792.pth [2023-03-08 00:47:29,820][286389] Updated weights for policy 0, policy_version 152560 (0.0004) [2023-03-08 00:47:32,816][286098] Fps is (10 sec: 11468.7, 60 sec: 11810.1, 300 sec: 11621.5). Total num frames: 78143488. Throughput: 0: 11829.6. Samples: 78135840. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:47:32,816][286098] Avg episode reward: [(0, '4557.893')] [2023-03-08 00:47:33,427][286389] Updated weights for policy 0, policy_version 152640 (0.0005) [2023-03-08 00:47:37,083][286389] Updated weights for policy 0, policy_version 152720 (0.0005) [2023-03-08 00:47:37,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11810.1, 300 sec: 11635.4). Total num frames: 78200832. Throughput: 0: 11779.7. Samples: 78170384. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:47:37,816][286098] Avg episode reward: [(0, '4545.320')] [2023-03-08 00:47:40,706][286389] Updated weights for policy 0, policy_version 152800 (0.0005) [2023-03-08 00:47:42,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11741.9, 300 sec: 11621.5). Total num frames: 78254080. Throughput: 0: 11711.1. Samples: 78237708. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:47:42,816][286098] Avg episode reward: [(0, '4545.855')] [2023-03-08 00:47:42,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000152840_78254080.pth... [2023-03-08 00:47:42,823][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000152176_77914112.pth [2023-03-08 00:47:44,288][286389] Updated weights for policy 0, policy_version 152880 (0.0005) [2023-03-08 00:47:47,816][286098] Fps is (10 sec: 11059.3, 60 sec: 11673.6, 300 sec: 11621.5). Total num frames: 78311424. Throughput: 0: 11679.4. Samples: 78306372. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:47:47,816][286098] Avg episode reward: [(0, '4564.505')] [2023-03-08 00:47:47,903][286389] Updated weights for policy 0, policy_version 152960 (0.0005) [2023-03-08 00:47:51,453][286389] Updated weights for policy 0, policy_version 153040 (0.0005) [2023-03-08 00:47:52,816][286098] Fps is (10 sec: 11468.9, 60 sec: 11605.4, 300 sec: 11621.5). Total num frames: 78368768. Throughput: 0: 11607.2. Samples: 78340328. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:47:52,816][286098] Avg episode reward: [(0, '4569.355')] [2023-03-08 00:47:55,054][286389] Updated weights for policy 0, policy_version 153120 (0.0005) [2023-03-08 00:47:57,816][286098] Fps is (10 sec: 11468.7, 60 sec: 11673.6, 300 sec: 11635.4). Total num frames: 78426112. Throughput: 0: 11482.5. Samples: 78409232. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:47:57,816][286098] Avg episode reward: [(0, '4562.046')] [2023-03-08 00:47:57,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000153176_78426112.pth... [2023-03-08 00:47:57,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000152512_78086144.pth [2023-03-08 00:47:58,675][286389] Updated weights for policy 0, policy_version 153200 (0.0005) [2023-03-08 00:48:02,355][286389] Updated weights for policy 0, policy_version 153280 (0.0004) [2023-03-08 00:48:02,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11605.3, 300 sec: 11635.4). Total num frames: 78483456. Throughput: 0: 11343.9. Samples: 78475756. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:48:02,816][286098] Avg episode reward: [(0, '4439.981')] [2023-03-08 00:48:05,932][286389] Updated weights for policy 0, policy_version 153360 (0.0005) [2023-03-08 00:48:07,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11537.1, 300 sec: 11635.4). Total num frames: 78540800. Throughput: 0: 11349.2. Samples: 78510848. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:48:07,816][286098] Avg episode reward: [(0, '4490.657')] [2023-03-08 00:48:09,535][286389] Updated weights for policy 0, policy_version 153440 (0.0005) [2023-03-08 00:48:12,816][286098] Fps is (10 sec: 11468.7, 60 sec: 11400.5, 300 sec: 11649.3). Total num frames: 78598144. Throughput: 0: 11351.9. Samples: 78578684. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:48:12,816][286098] Avg episode reward: [(0, '4550.915')] [2023-03-08 00:48:12,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000153512_78598144.pth... [2023-03-08 00:48:12,821][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000152840_78254080.pth [2023-03-08 00:48:13,100][286389] Updated weights for policy 0, policy_version 153520 (0.0005) [2023-03-08 00:48:16,699][286389] Updated weights for policy 0, policy_version 153600 (0.0005) [2023-03-08 00:48:17,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11400.5, 300 sec: 11649.3). Total num frames: 78655488. Throughput: 0: 11366.0. Samples: 78647308. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:48:17,816][286098] Avg episode reward: [(0, '4538.779')] [2023-03-08 00:48:20,272][286389] Updated weights for policy 0, policy_version 153680 (0.0005) [2023-03-08 00:48:22,816][286098] Fps is (10 sec: 11468.9, 60 sec: 11400.5, 300 sec: 11663.2). Total num frames: 78712832. Throughput: 0: 11363.5. Samples: 78681740. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:48:22,816][286098] Avg episode reward: [(0, '4558.401')] [2023-03-08 00:48:23,870][286389] Updated weights for policy 0, policy_version 153760 (0.0005) [2023-03-08 00:48:27,503][286389] Updated weights for policy 0, policy_version 153840 (0.0005) [2023-03-08 00:48:27,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11332.3, 300 sec: 11649.3). Total num frames: 78766080. Throughput: 0: 11378.9. Samples: 78749760. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:48:27,816][286098] Avg episode reward: [(0, '4564.957')] [2023-03-08 00:48:27,875][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000153848_78770176.pth... [2023-03-08 00:48:27,876][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000153176_78426112.pth [2023-03-08 00:48:31,049][286389] Updated weights for policy 0, policy_version 153920 (0.0005) [2023-03-08 00:48:32,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11332.3, 300 sec: 11649.3). Total num frames: 78823424. Throughput: 0: 11381.9. Samples: 78818556. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:48:32,816][286098] Avg episode reward: [(0, '4565.545')] [2023-03-08 00:48:34,657][286389] Updated weights for policy 0, policy_version 154000 (0.0005) [2023-03-08 00:48:37,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11332.3, 300 sec: 11649.3). Total num frames: 78880768. Throughput: 0: 11380.4. Samples: 78852444. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:48:37,816][286098] Avg episode reward: [(0, '4551.782')] [2023-03-08 00:48:38,256][286389] Updated weights for policy 0, policy_version 154080 (0.0005) [2023-03-08 00:48:41,892][286389] Updated weights for policy 0, policy_version 154160 (0.0005) [2023-03-08 00:48:42,816][286098] Fps is (10 sec: 11468.7, 60 sec: 11400.5, 300 sec: 11649.3). Total num frames: 78938112. Throughput: 0: 11348.1. Samples: 78919896. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:48:42,816][286098] Avg episode reward: [(0, '4562.524')] [2023-03-08 00:48:42,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000154176_78938112.pth... [2023-03-08 00:48:42,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000153512_78598144.pth [2023-03-08 00:48:45,449][286389] Updated weights for policy 0, policy_version 154240 (0.0005) [2023-03-08 00:48:47,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11400.5, 300 sec: 11663.2). Total num frames: 78995456. Throughput: 0: 11393.5. Samples: 78988464. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:48:47,816][286098] Avg episode reward: [(0, '4512.221')] [2023-03-08 00:48:49,131][286389] Updated weights for policy 0, policy_version 154320 (0.0005) [2023-03-08 00:48:52,619][286389] Updated weights for policy 0, policy_version 154400 (0.0005) [2023-03-08 00:48:52,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11400.5, 300 sec: 11663.2). Total num frames: 79052800. Throughput: 0: 11383.5. Samples: 79023104. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:48:52,816][286098] Avg episode reward: [(0, '4564.915')] [2023-03-08 00:48:56,200][286389] Updated weights for policy 0, policy_version 154480 (0.0005) [2023-03-08 00:48:57,816][286098] Fps is (10 sec: 11468.7, 60 sec: 11400.5, 300 sec: 11663.2). Total num frames: 79110144. Throughput: 0: 11411.4. Samples: 79092196. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:48:57,816][286098] Avg episode reward: [(0, '4563.375')] [2023-03-08 00:48:57,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000154512_79110144.pth... [2023-03-08 00:48:57,823][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000153848_78770176.pth [2023-03-08 00:48:59,764][286389] Updated weights for policy 0, policy_version 154560 (0.0005) [2023-03-08 00:49:02,816][286098] Fps is (10 sec: 11468.9, 60 sec: 11400.5, 300 sec: 11663.2). Total num frames: 79167488. Throughput: 0: 11426.0. Samples: 79161476. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:49:02,816][286098] Avg episode reward: [(0, '4540.490')] [2023-03-08 00:49:03,314][286389] Updated weights for policy 0, policy_version 154640 (0.0005) [2023-03-08 00:49:06,972][286389] Updated weights for policy 0, policy_version 154720 (0.0005) [2023-03-08 00:49:07,816][286098] Fps is (10 sec: 11468.9, 60 sec: 11400.5, 300 sec: 11663.2). Total num frames: 79224832. Throughput: 0: 11426.0. Samples: 79195912. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:49:07,816][286098] Avg episode reward: [(0, '4465.516')] [2023-03-08 00:49:10,604][286389] Updated weights for policy 0, policy_version 154800 (0.0005) [2023-03-08 00:49:12,816][286098] Fps is (10 sec: 11468.7, 60 sec: 11400.5, 300 sec: 11677.1). Total num frames: 79282176. Throughput: 0: 11400.5. Samples: 79262784. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:49:12,816][286098] Avg episode reward: [(0, '4483.805')] [2023-03-08 00:49:12,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000154848_79282176.pth... [2023-03-08 00:49:12,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000154176_78938112.pth [2023-03-08 00:49:14,138][286389] Updated weights for policy 0, policy_version 154880 (0.0005) [2023-03-08 00:49:17,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11332.3, 300 sec: 11663.2). Total num frames: 79335424. Throughput: 0: 11394.9. Samples: 79331328. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:49:17,816][286098] Avg episode reward: [(0, '4479.184')] [2023-03-08 00:49:17,827][286389] Updated weights for policy 0, policy_version 154960 (0.0005) [2023-03-08 00:49:21,419][286389] Updated weights for policy 0, policy_version 155040 (0.0005) [2023-03-08 00:49:22,816][286098] Fps is (10 sec: 11059.3, 60 sec: 11332.3, 300 sec: 11663.2). Total num frames: 79392768. Throughput: 0: 11399.5. Samples: 79365424. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:49:22,816][286098] Avg episode reward: [(0, '4480.493')] [2023-03-08 00:49:25,055][286389] Updated weights for policy 0, policy_version 155120 (0.0005) [2023-03-08 00:49:27,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11400.5, 300 sec: 11663.2). Total num frames: 79450112. Throughput: 0: 11417.3. Samples: 79433676. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:49:27,816][286098] Avg episode reward: [(0, '4537.731')] [2023-03-08 00:49:27,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000155176_79450112.pth... [2023-03-08 00:49:27,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000154512_79110144.pth [2023-03-08 00:49:28,597][286389] Updated weights for policy 0, policy_version 155200 (0.0005) [2023-03-08 00:49:31,944][286389] Updated weights for policy 0, policy_version 155280 (0.0004) [2023-03-08 00:49:32,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11468.8, 300 sec: 11691.0). Total num frames: 79511552. Throughput: 0: 11466.9. Samples: 79504476. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:49:32,816][286098] Avg episode reward: [(0, '4538.603')] [2023-03-08 00:49:35,396][286389] Updated weights for policy 0, policy_version 155360 (0.0005) [2023-03-08 00:49:37,816][286098] Fps is (10 sec: 12288.0, 60 sec: 11537.1, 300 sec: 11704.8). Total num frames: 79572992. Throughput: 0: 11493.0. Samples: 79540288. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:49:37,816][286098] Avg episode reward: [(0, '4543.716')] [2023-03-08 00:49:38,766][286389] Updated weights for policy 0, policy_version 155440 (0.0005) [2023-03-08 00:49:42,151][286389] Updated weights for policy 0, policy_version 155520 (0.0005) [2023-03-08 00:49:42,816][286098] Fps is (10 sec: 12288.1, 60 sec: 11605.3, 300 sec: 11718.7). Total num frames: 79634432. Throughput: 0: 11584.3. Samples: 79613488. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:49:42,816][286098] Avg episode reward: [(0, '4380.468')] [2023-03-08 00:49:42,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000155536_79634432.pth... [2023-03-08 00:49:42,821][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000154848_79282176.pth [2023-03-08 00:49:45,655][286389] Updated weights for policy 0, policy_version 155600 (0.0005) [2023-03-08 00:49:47,816][286098] Fps is (10 sec: 11468.9, 60 sec: 11537.1, 300 sec: 11704.8). Total num frames: 79687680. Throughput: 0: 11602.7. Samples: 79683596. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:49:47,816][286098] Avg episode reward: [(0, '4381.686')] [2023-03-08 00:49:49,181][286389] Updated weights for policy 0, policy_version 155680 (0.0004) [2023-03-08 00:49:52,672][286389] Updated weights for policy 0, policy_version 155760 (0.0004) [2023-03-08 00:49:52,816][286098] Fps is (10 sec: 11468.7, 60 sec: 11605.3, 300 sec: 11718.7). Total num frames: 79749120. Throughput: 0: 11610.7. Samples: 79718392. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:49:52,816][286098] Avg episode reward: [(0, '4550.538')] [2023-03-08 00:49:56,213][286389] Updated weights for policy 0, policy_version 155840 (0.0005) [2023-03-08 00:49:57,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11605.3, 300 sec: 11718.7). Total num frames: 79806464. Throughput: 0: 11678.4. Samples: 79788312. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:49:57,816][286098] Avg episode reward: [(0, '4555.663')] [2023-03-08 00:49:57,837][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000155880_79810560.pth... [2023-03-08 00:49:57,839][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000155176_79450112.pth [2023-03-08 00:49:59,518][286389] Updated weights for policy 0, policy_version 155920 (0.0004) [2023-03-08 00:50:02,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11673.6, 300 sec: 11746.5). Total num frames: 79867904. Throughput: 0: 11786.1. Samples: 79861704. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:50:02,816][286098] Avg episode reward: [(0, '4558.954')] [2023-03-08 00:50:02,968][286389] Updated weights for policy 0, policy_version 156000 (0.0005) [2023-03-08 00:50:06,561][286389] Updated weights for policy 0, policy_version 156080 (0.0005) [2023-03-08 00:50:07,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11673.6, 300 sec: 11746.5). Total num frames: 79925248. Throughput: 0: 11788.9. Samples: 79895924. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:50:07,816][286098] Avg episode reward: [(0, '4563.761')] [2023-03-08 00:50:10,135][286389] Updated weights for policy 0, policy_version 156160 (0.0005) [2023-03-08 00:50:12,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11741.9, 300 sec: 11760.4). Total num frames: 79986688. Throughput: 0: 11811.4. Samples: 79965188. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:50:12,816][286098] Avg episode reward: [(0, '4543.127')] [2023-03-08 00:50:12,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000156224_79986688.pth... [2023-03-08 00:50:12,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000155536_79634432.pth [2023-03-08 00:50:13,465][286389] Updated weights for policy 0, policy_version 156240 (0.0004) [2023-03-08 00:50:17,103][286389] Updated weights for policy 0, policy_version 156320 (0.0005) [2023-03-08 00:50:17,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11741.9, 300 sec: 11760.4). Total num frames: 80039936. Throughput: 0: 11807.9. Samples: 80035832. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:50:17,816][286098] Avg episode reward: [(0, '4521.568')] [2023-03-08 00:50:20,741][286389] Updated weights for policy 0, policy_version 156400 (0.0005) [2023-03-08 00:50:22,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11810.1, 300 sec: 11760.4). Total num frames: 80101376. Throughput: 0: 11755.6. Samples: 80069288. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:50:22,816][286098] Avg episode reward: [(0, '4528.062')] [2023-03-08 00:50:24,084][286389] Updated weights for policy 0, policy_version 156480 (0.0004) [2023-03-08 00:50:27,460][286389] Updated weights for policy 0, policy_version 156560 (0.0003) [2023-03-08 00:50:27,816][286098] Fps is (10 sec: 12288.0, 60 sec: 11878.4, 300 sec: 11760.4). Total num frames: 80162816. Throughput: 0: 11743.6. Samples: 80141952. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:50:27,816][286098] Avg episode reward: [(0, '4564.306')] [2023-03-08 00:50:27,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000156568_80162816.pth... [2023-03-08 00:50:27,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000155880_79810560.pth [2023-03-08 00:50:30,891][286389] Updated weights for policy 0, policy_version 156640 (0.0003) [2023-03-08 00:50:32,816][286098] Fps is (10 sec: 11878.5, 60 sec: 11810.1, 300 sec: 11746.5). Total num frames: 80220160. Throughput: 0: 11782.1. Samples: 80213792. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:50:32,816][286098] Avg episode reward: [(0, '4549.251')] [2023-03-08 00:50:34,288][286389] Updated weights for policy 0, policy_version 156720 (0.0003) [2023-03-08 00:50:37,700][286389] Updated weights for policy 0, policy_version 156800 (0.0003) [2023-03-08 00:50:37,816][286098] Fps is (10 sec: 11878.3, 60 sec: 11810.1, 300 sec: 11746.5). Total num frames: 80281600. Throughput: 0: 11804.2. Samples: 80249580. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:50:37,816][286098] Avg episode reward: [(0, '4557.692')] [2023-03-08 00:50:41,100][286389] Updated weights for policy 0, policy_version 156880 (0.0004) [2023-03-08 00:50:42,816][286098] Fps is (10 sec: 12287.9, 60 sec: 11810.1, 300 sec: 11746.5). Total num frames: 80343040. Throughput: 0: 11862.1. Samples: 80322108. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:50:42,816][286098] Avg episode reward: [(0, '4563.129')] [2023-03-08 00:50:42,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000156920_80343040.pth... [2023-03-08 00:50:42,823][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000156224_79986688.pth [2023-03-08 00:50:44,559][286389] Updated weights for policy 0, policy_version 156960 (0.0003) [2023-03-08 00:50:47,816][286098] Fps is (10 sec: 11878.3, 60 sec: 11878.4, 300 sec: 11732.6). Total num frames: 80400384. Throughput: 0: 11825.5. Samples: 80393852. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:50:47,817][286098] Avg episode reward: [(0, '4544.677')] [2023-03-08 00:50:47,920][286389] Updated weights for policy 0, policy_version 157040 (0.0004) [2023-03-08 00:50:51,460][286389] Updated weights for policy 0, policy_version 157120 (0.0005) [2023-03-08 00:50:52,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11810.1, 300 sec: 11718.7). Total num frames: 80457728. Throughput: 0: 11868.2. Samples: 80429992. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:50:52,827][286098] Avg episode reward: [(0, '4562.190')] [2023-03-08 00:50:54,874][286389] Updated weights for policy 0, policy_version 157200 (0.0004) [2023-03-08 00:50:57,816][286098] Fps is (10 sec: 11878.5, 60 sec: 11878.4, 300 sec: 11704.8). Total num frames: 80519168. Throughput: 0: 11878.4. Samples: 80499716. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:50:57,827][286098] Avg episode reward: [(0, '4563.376')] [2023-03-08 00:50:57,830][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000157264_80519168.pth... [2023-03-08 00:50:57,833][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000156568_80162816.pth [2023-03-08 00:50:58,458][286389] Updated weights for policy 0, policy_version 157280 (0.0005) [2023-03-08 00:51:01,812][286389] Updated weights for policy 0, policy_version 157360 (0.0005) [2023-03-08 00:51:02,816][286098] Fps is (10 sec: 12288.0, 60 sec: 11878.4, 300 sec: 11704.8). Total num frames: 80580608. Throughput: 0: 11909.7. Samples: 80571768. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:51:02,827][286098] Avg episode reward: [(0, '4565.586')] [2023-03-08 00:51:05,051][286389] Updated weights for policy 0, policy_version 157440 (0.0004) [2023-03-08 00:51:07,816][286098] Fps is (10 sec: 12288.1, 60 sec: 11946.7, 300 sec: 11704.8). Total num frames: 80642048. Throughput: 0: 12001.3. Samples: 80609344. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:51:07,827][286098] Avg episode reward: [(0, '4565.897')] [2023-03-08 00:51:08,406][286389] Updated weights for policy 0, policy_version 157520 (0.0005) [2023-03-08 00:51:11,788][286389] Updated weights for policy 0, policy_version 157600 (0.0005) [2023-03-08 00:51:12,816][286098] Fps is (10 sec: 12288.0, 60 sec: 11946.7, 300 sec: 11704.8). Total num frames: 80703488. Throughput: 0: 12008.8. Samples: 80682348. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:51:12,827][286098] Avg episode reward: [(0, '4564.838')] [2023-03-08 00:51:12,830][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000157624_80703488.pth... [2023-03-08 00:51:12,832][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000156920_80343040.pth [2023-03-08 00:51:15,116][286389] Updated weights for policy 0, policy_version 157680 (0.0004) [2023-03-08 00:51:17,816][286098] Fps is (10 sec: 11878.4, 60 sec: 12014.9, 300 sec: 11691.0). Total num frames: 80760832. Throughput: 0: 12048.9. Samples: 80755992. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:51:17,827][286098] Avg episode reward: [(0, '4562.433')] [2023-03-08 00:51:18,481][286389] Updated weights for policy 0, policy_version 157760 (0.0005) [2023-03-08 00:51:21,930][286389] Updated weights for policy 0, policy_version 157840 (0.0005) [2023-03-08 00:51:22,816][286098] Fps is (10 sec: 11878.5, 60 sec: 12014.9, 300 sec: 11691.0). Total num frames: 80822272. Throughput: 0: 12080.5. Samples: 80793200. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:51:22,827][286098] Avg episode reward: [(0, '4558.632')] [2023-03-08 00:51:25,557][286389] Updated weights for policy 0, policy_version 157920 (0.0005) [2023-03-08 00:51:27,816][286098] Fps is (10 sec: 11878.3, 60 sec: 11946.7, 300 sec: 11677.1). Total num frames: 80879616. Throughput: 0: 11972.6. Samples: 80860876. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:51:27,827][286098] Avg episode reward: [(0, '4558.973')] [2023-03-08 00:51:27,830][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000157968_80879616.pth... [2023-03-08 00:51:27,833][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000157264_80519168.pth [2023-03-08 00:51:29,175][286389] Updated weights for policy 0, policy_version 158000 (0.0005) [2023-03-08 00:51:32,616][286389] Updated weights for policy 0, policy_version 158080 (0.0003) [2023-03-08 00:51:32,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11946.7, 300 sec: 11677.1). Total num frames: 80936960. Throughput: 0: 11921.0. Samples: 80930296. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:51:32,827][286098] Avg episode reward: [(0, '4564.183')] [2023-03-08 00:51:35,878][286389] Updated weights for policy 0, policy_version 158160 (0.0003) [2023-03-08 00:51:37,816][286098] Fps is (10 sec: 11878.5, 60 sec: 11946.7, 300 sec: 11691.0). Total num frames: 80998400. Throughput: 0: 11936.6. Samples: 80967140. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:51:37,816][286098] Avg episode reward: [(0, '4557.899')] [2023-03-08 00:51:39,287][286389] Updated weights for policy 0, policy_version 158240 (0.0003) [2023-03-08 00:51:42,664][286389] Updated weights for policy 0, policy_version 158320 (0.0003) [2023-03-08 00:51:42,816][286098] Fps is (10 sec: 12287.9, 60 sec: 11946.7, 300 sec: 11691.0). Total num frames: 81059840. Throughput: 0: 12008.8. Samples: 81040112. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:51:42,816][286098] Avg episode reward: [(0, '4561.197')] [2023-03-08 00:51:42,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000158320_81059840.pth... [2023-03-08 00:51:42,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000157624_80703488.pth [2023-03-08 00:51:46,064][286389] Updated weights for policy 0, policy_version 158400 (0.0003) [2023-03-08 00:51:47,816][286098] Fps is (10 sec: 12288.0, 60 sec: 12014.9, 300 sec: 11691.0). Total num frames: 81121280. Throughput: 0: 12030.9. Samples: 81113160. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:51:47,827][286098] Avg episode reward: [(0, '4565.166')] [2023-03-08 00:51:49,317][286389] Updated weights for policy 0, policy_version 158480 (0.0003) [2023-03-08 00:51:52,775][286389] Updated weights for policy 0, policy_version 158560 (0.0004) [2023-03-08 00:51:52,816][286098] Fps is (10 sec: 12288.1, 60 sec: 12083.2, 300 sec: 11718.7). Total num frames: 81182720. Throughput: 0: 12029.4. Samples: 81150668. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:51:52,827][286098] Avg episode reward: [(0, '4563.735')] [2023-03-08 00:51:56,235][286389] Updated weights for policy 0, policy_version 158640 (0.0004) [2023-03-08 00:51:57,816][286098] Fps is (10 sec: 11878.3, 60 sec: 12014.9, 300 sec: 11704.8). Total num frames: 81240064. Throughput: 0: 11992.8. Samples: 81222024. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:51:57,827][286098] Avg episode reward: [(0, '4574.388')] [2023-03-08 00:51:57,831][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000158672_81240064.pth... [2023-03-08 00:51:57,833][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000157968_80879616.pth [2023-03-08 00:51:59,669][286389] Updated weights for policy 0, policy_version 158720 (0.0004) [2023-03-08 00:52:02,816][286098] Fps is (10 sec: 11878.4, 60 sec: 12014.9, 300 sec: 11704.8). Total num frames: 81301504. Throughput: 0: 11940.7. Samples: 81293324. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:52:02,827][286098] Avg episode reward: [(0, '4565.345')] [2023-03-08 00:52:03,112][286389] Updated weights for policy 0, policy_version 158800 (0.0003) [2023-03-08 00:52:06,407][286389] Updated weights for policy 0, policy_version 158880 (0.0003) [2023-03-08 00:52:07,816][286098] Fps is (10 sec: 12288.1, 60 sec: 12014.9, 300 sec: 11691.0). Total num frames: 81362944. Throughput: 0: 11934.2. Samples: 81330240. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:52:07,827][286098] Avg episode reward: [(0, '4536.730')] [2023-03-08 00:52:09,699][286389] Updated weights for policy 0, policy_version 158960 (0.0003) [2023-03-08 00:52:12,816][286098] Fps is (10 sec: 12288.0, 60 sec: 12014.9, 300 sec: 11704.8). Total num frames: 81424384. Throughput: 0: 12067.3. Samples: 81403904. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:52:12,827][286098] Avg episode reward: [(0, '4499.897')] [2023-03-08 00:52:12,830][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000159032_81424384.pth... [2023-03-08 00:52:12,831][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000158320_81059840.pth [2023-03-08 00:52:13,050][286389] Updated weights for policy 0, policy_version 159040 (0.0003) [2023-03-08 00:52:16,446][286389] Updated weights for policy 0, policy_version 159120 (0.0003) [2023-03-08 00:52:17,816][286098] Fps is (10 sec: 12288.0, 60 sec: 12083.2, 300 sec: 11718.7). Total num frames: 81485824. Throughput: 0: 12158.2. Samples: 81477416. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:52:17,827][286098] Avg episode reward: [(0, '4530.999')] [2023-03-08 00:52:19,799][286389] Updated weights for policy 0, policy_version 159200 (0.0003) [2023-03-08 00:52:22,816][286098] Fps is (10 sec: 12288.1, 60 sec: 12083.2, 300 sec: 11732.6). Total num frames: 81547264. Throughput: 0: 12147.8. Samples: 81513792. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:52:22,827][286098] Avg episode reward: [(0, '4551.734')] [2023-03-08 00:52:23,081][286389] Updated weights for policy 0, policy_version 159280 (0.0003) [2023-03-08 00:52:26,547][286389] Updated weights for policy 0, policy_version 159360 (0.0003) [2023-03-08 00:52:27,816][286098] Fps is (10 sec: 11878.4, 60 sec: 12083.2, 300 sec: 11732.6). Total num frames: 81604608. Throughput: 0: 12148.5. Samples: 81586792. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:52:27,827][286098] Avg episode reward: [(0, '4556.260')] [2023-03-08 00:52:27,830][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000159384_81604608.pth... [2023-03-08 00:52:27,833][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000158672_81240064.pth [2023-03-08 00:52:29,948][286389] Updated weights for policy 0, policy_version 159440 (0.0003) [2023-03-08 00:52:32,816][286098] Fps is (10 sec: 11878.4, 60 sec: 12151.5, 300 sec: 11746.5). Total num frames: 81666048. Throughput: 0: 12106.0. Samples: 81657928. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:52:32,827][286098] Avg episode reward: [(0, '4548.662')] [2023-03-08 00:52:33,396][286389] Updated weights for policy 0, policy_version 159520 (0.0003) [2023-03-08 00:52:36,755][286389] Updated weights for policy 0, policy_version 159600 (0.0003) [2023-03-08 00:52:37,816][286098] Fps is (10 sec: 12288.1, 60 sec: 12151.5, 300 sec: 11774.3). Total num frames: 81727488. Throughput: 0: 12076.0. Samples: 81694088. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:52:37,816][286098] Avg episode reward: [(0, '4495.451')] [2023-03-08 00:52:40,111][286389] Updated weights for policy 0, policy_version 159680 (0.0003) [2023-03-08 00:52:42,816][286098] Fps is (10 sec: 11878.4, 60 sec: 12083.2, 300 sec: 11774.3). Total num frames: 81784832. Throughput: 0: 12120.0. Samples: 81767424. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 00:52:42,827][286098] Avg episode reward: [(0, '4562.088')] [2023-03-08 00:52:42,830][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000159736_81784832.pth... [2023-03-08 00:52:42,833][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000159032_81424384.pth [2023-03-08 00:52:43,517][286389] Updated weights for policy 0, policy_version 159760 (0.0003) [2023-03-08 00:52:46,871][286389] Updated weights for policy 0, policy_version 159840 (0.0003) [2023-03-08 00:52:47,816][286098] Fps is (10 sec: 11878.4, 60 sec: 12083.2, 300 sec: 11788.1). Total num frames: 81846272. Throughput: 0: 12155.4. Samples: 81840316. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 00:52:47,827][286098] Avg episode reward: [(0, '4557.684')] [2023-03-08 00:52:50,167][286389] Updated weights for policy 0, policy_version 159920 (0.0003) [2023-03-08 00:52:52,816][286098] Fps is (10 sec: 12288.1, 60 sec: 12083.2, 300 sec: 11802.0). Total num frames: 81907712. Throughput: 0: 12162.6. Samples: 81877556. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 00:52:52,816][286098] Avg episode reward: [(0, '4565.442')] [2023-03-08 00:52:53,531][286389] Updated weights for policy 0, policy_version 160000 (0.0003) [2023-03-08 00:52:56,945][286389] Updated weights for policy 0, policy_version 160080 (0.0003) [2023-03-08 00:52:57,816][286098] Fps is (10 sec: 12288.0, 60 sec: 12151.5, 300 sec: 11815.9). Total num frames: 81969152. Throughput: 0: 12144.1. Samples: 81950388. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 00:52:57,816][286098] Avg episode reward: [(0, '4563.186')] [2023-03-08 00:52:57,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000160096_81969152.pth... [2023-03-08 00:52:57,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000159384_81604608.pth [2023-03-08 00:53:00,345][286389] Updated weights for policy 0, policy_version 160160 (0.0003) [2023-03-08 00:53:02,816][286098] Fps is (10 sec: 12287.9, 60 sec: 12151.5, 300 sec: 11829.8). Total num frames: 82030592. Throughput: 0: 12128.4. Samples: 82023196. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 00:53:02,816][286098] Avg episode reward: [(0, '4565.851')] [2023-03-08 00:53:03,627][286389] Updated weights for policy 0, policy_version 160240 (0.0003) [2023-03-08 00:53:07,020][286389] Updated weights for policy 0, policy_version 160320 (0.0003) [2023-03-08 00:53:07,816][286098] Fps is (10 sec: 12288.0, 60 sec: 12151.5, 300 sec: 11843.7). Total num frames: 82092032. Throughput: 0: 12127.9. Samples: 82059548. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 00:53:07,816][286098] Avg episode reward: [(0, '4555.812')] [2023-03-08 00:53:10,528][286389] Updated weights for policy 0, policy_version 160400 (0.0005) [2023-03-08 00:53:12,816][286098] Fps is (10 sec: 11878.4, 60 sec: 12083.2, 300 sec: 11843.7). Total num frames: 82149376. Throughput: 0: 12091.6. Samples: 82130912. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 00:53:12,816][286098] Avg episode reward: [(0, '4535.547')] [2023-03-08 00:53:12,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000160448_82149376.pth... [2023-03-08 00:53:12,821][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000159736_81784832.pth [2023-03-08 00:53:14,227][286389] Updated weights for policy 0, policy_version 160480 (0.0005) [2023-03-08 00:53:17,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11946.7, 300 sec: 11829.8). Total num frames: 82202624. Throughput: 0: 12006.9. Samples: 82198240. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 00:53:17,816][286098] Avg episode reward: [(0, '4535.593')] [2023-03-08 00:53:17,871][286389] Updated weights for policy 0, policy_version 160560 (0.0005) [2023-03-08 00:53:21,548][286389] Updated weights for policy 0, policy_version 160640 (0.0005) [2023-03-08 00:53:22,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11878.4, 300 sec: 11843.7). Total num frames: 82259968. Throughput: 0: 11939.4. Samples: 82231360. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 00:53:22,816][286098] Avg episode reward: [(0, '4540.980')] [2023-03-08 00:53:25,045][286389] Updated weights for policy 0, policy_version 160720 (0.0005) [2023-03-08 00:53:27,816][286098] Fps is (10 sec: 11468.7, 60 sec: 11878.4, 300 sec: 11843.7). Total num frames: 82317312. Throughput: 0: 11841.1. Samples: 82300272. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 00:53:27,816][286098] Avg episode reward: [(0, '4551.562')] [2023-03-08 00:53:27,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000160776_82317312.pth... [2023-03-08 00:53:27,823][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000160096_81969152.pth [2023-03-08 00:53:28,650][286389] Updated weights for policy 0, policy_version 160800 (0.0005) [2023-03-08 00:53:32,085][286389] Updated weights for policy 0, policy_version 160880 (0.0004) [2023-03-08 00:53:32,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11878.4, 300 sec: 11857.6). Total num frames: 82378752. Throughput: 0: 11778.7. Samples: 82370356. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 00:53:32,816][286098] Avg episode reward: [(0, '4560.028')] [2023-03-08 00:53:35,344][286389] Updated weights for policy 0, policy_version 160960 (0.0004) [2023-03-08 00:53:37,816][286098] Fps is (10 sec: 12288.1, 60 sec: 11878.4, 300 sec: 11871.5). Total num frames: 82440192. Throughput: 0: 11777.1. Samples: 82407528. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 00:53:37,816][286098] Avg episode reward: [(0, '4508.757')] [2023-03-08 00:53:38,738][286389] Updated weights for policy 0, policy_version 161040 (0.0005) [2023-03-08 00:53:42,092][286389] Updated weights for policy 0, policy_version 161120 (0.0004) [2023-03-08 00:53:42,816][286098] Fps is (10 sec: 12288.0, 60 sec: 11946.7, 300 sec: 11885.3). Total num frames: 82501632. Throughput: 0: 11793.1. Samples: 82481076. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 00:53:42,816][286098] Avg episode reward: [(0, '4544.247')] [2023-03-08 00:53:42,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000161136_82501632.pth... [2023-03-08 00:53:42,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000160448_82149376.pth [2023-03-08 00:53:45,650][286389] Updated weights for policy 0, policy_version 161200 (0.0005) [2023-03-08 00:53:47,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11810.1, 300 sec: 11871.5). Total num frames: 82554880. Throughput: 0: 11723.0. Samples: 82550732. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:53:47,816][286098] Avg episode reward: [(0, '4558.120')] [2023-03-08 00:53:49,350][286389] Updated weights for policy 0, policy_version 161280 (0.0005) [2023-03-08 00:53:52,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11741.9, 300 sec: 11871.5). Total num frames: 82612224. Throughput: 0: 11644.5. Samples: 82583552. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:53:52,816][286098] Avg episode reward: [(0, '4553.891')] [2023-03-08 00:53:52,950][286389] Updated weights for policy 0, policy_version 161360 (0.0005) [2023-03-08 00:53:56,645][286389] Updated weights for policy 0, policy_version 161440 (0.0005) [2023-03-08 00:53:57,816][286098] Fps is (10 sec: 11468.7, 60 sec: 11673.6, 300 sec: 11871.5). Total num frames: 82669568. Throughput: 0: 11556.3. Samples: 82650948. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:53:57,816][286098] Avg episode reward: [(0, '4515.800')] [2023-03-08 00:53:57,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000161464_82669568.pth... [2023-03-08 00:53:57,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000160776_82317312.pth [2023-03-08 00:54:00,061][286389] Updated weights for policy 0, policy_version 161520 (0.0005) [2023-03-08 00:54:02,816][286098] Fps is (10 sec: 11878.5, 60 sec: 11673.6, 300 sec: 11885.3). Total num frames: 82731008. Throughput: 0: 11658.9. Samples: 82722888. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:54:02,816][286098] Avg episode reward: [(0, '4587.817')] [2023-03-08 00:54:02,817][286341] Saving new best policy, reward=4587.817! [2023-03-08 00:54:03,459][286389] Updated weights for policy 0, policy_version 161600 (0.0005) [2023-03-08 00:54:07,014][286389] Updated weights for policy 0, policy_version 161680 (0.0004) [2023-03-08 00:54:07,816][286098] Fps is (10 sec: 11878.5, 60 sec: 11605.3, 300 sec: 11885.3). Total num frames: 82788352. Throughput: 0: 11693.5. Samples: 82757568. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:54:07,816][286098] Avg episode reward: [(0, '4549.176')] [2023-03-08 00:54:10,606][286389] Updated weights for policy 0, policy_version 161760 (0.0005) [2023-03-08 00:54:12,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11537.1, 300 sec: 11885.3). Total num frames: 82841600. Throughput: 0: 11680.6. Samples: 82825900. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:54:12,816][286098] Avg episode reward: [(0, '4544.251')] [2023-03-08 00:54:12,834][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000161808_82845696.pth... [2023-03-08 00:54:12,836][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000161136_82501632.pth [2023-03-08 00:54:14,341][286389] Updated weights for policy 0, policy_version 161840 (0.0005) [2023-03-08 00:54:17,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11605.3, 300 sec: 11885.3). Total num frames: 82898944. Throughput: 0: 11590.7. Samples: 82891936. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:54:17,816][286098] Avg episode reward: [(0, '4471.606')] [2023-03-08 00:54:18,039][286389] Updated weights for policy 0, policy_version 161920 (0.0005) [2023-03-08 00:54:21,727][286389] Updated weights for policy 0, policy_version 162000 (0.0005) [2023-03-08 00:54:22,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11537.1, 300 sec: 11871.5). Total num frames: 82952192. Throughput: 0: 11506.6. Samples: 82925324. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:54:22,816][286098] Avg episode reward: [(0, '4285.246')] [2023-03-08 00:54:25,411][286389] Updated weights for policy 0, policy_version 162080 (0.0005) [2023-03-08 00:54:27,816][286098] Fps is (10 sec: 11059.1, 60 sec: 11537.1, 300 sec: 11857.6). Total num frames: 83009536. Throughput: 0: 11370.6. Samples: 82992752. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:54:27,816][286098] Avg episode reward: [(0, '4412.040')] [2023-03-08 00:54:27,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000162128_83009536.pth... [2023-03-08 00:54:27,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000161464_82669568.pth [2023-03-08 00:54:29,018][286389] Updated weights for policy 0, policy_version 162160 (0.0005) [2023-03-08 00:54:32,560][286389] Updated weights for policy 0, policy_version 162240 (0.0005) [2023-03-08 00:54:32,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11468.8, 300 sec: 11843.7). Total num frames: 83066880. Throughput: 0: 11321.4. Samples: 83060196. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:54:32,816][286098] Avg episode reward: [(0, '4478.713')] [2023-03-08 00:54:35,903][286389] Updated weights for policy 0, policy_version 162320 (0.0004) [2023-03-08 00:54:37,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11468.8, 300 sec: 11843.7). Total num frames: 83128320. Throughput: 0: 11416.8. Samples: 83097308. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:54:37,816][286098] Avg episode reward: [(0, '4481.373')] [2023-03-08 00:54:39,300][286389] Updated weights for policy 0, policy_version 162400 (0.0005) [2023-03-08 00:54:42,685][286389] Updated weights for policy 0, policy_version 162480 (0.0005) [2023-03-08 00:54:42,816][286098] Fps is (10 sec: 12287.9, 60 sec: 11468.8, 300 sec: 11871.5). Total num frames: 83189760. Throughput: 0: 11536.6. Samples: 83170096. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:54:42,816][286098] Avg episode reward: [(0, '4563.720')] [2023-03-08 00:54:42,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000162480_83189760.pth... [2023-03-08 00:54:42,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000161808_82845696.pth [2023-03-08 00:54:46,021][286389] Updated weights for policy 0, policy_version 162560 (0.0004) [2023-03-08 00:54:47,816][286098] Fps is (10 sec: 12288.0, 60 sec: 11605.3, 300 sec: 11871.5). Total num frames: 83251200. Throughput: 0: 11559.8. Samples: 83243080. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:54:47,816][286098] Avg episode reward: [(0, '4486.041')] [2023-03-08 00:54:49,417][286389] Updated weights for policy 0, policy_version 162640 (0.0005) [2023-03-08 00:54:52,816][286098] Fps is (10 sec: 11878.5, 60 sec: 11605.3, 300 sec: 11871.5). Total num frames: 83308544. Throughput: 0: 11602.8. Samples: 83279696. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:54:52,816][286098] Avg episode reward: [(0, '4535.490')] [2023-03-08 00:54:52,926][286389] Updated weights for policy 0, policy_version 162720 (0.0005) [2023-03-08 00:54:56,274][286389] Updated weights for policy 0, policy_version 162800 (0.0003) [2023-03-08 00:54:57,816][286098] Fps is (10 sec: 11878.3, 60 sec: 11673.6, 300 sec: 11871.5). Total num frames: 83369984. Throughput: 0: 11662.3. Samples: 83350704. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:54:57,817][286098] Avg episode reward: [(0, '4525.540')] [2023-03-08 00:54:57,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000162832_83369984.pth... [2023-03-08 00:54:57,823][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000162128_83009536.pth [2023-03-08 00:54:59,715][286389] Updated weights for policy 0, policy_version 162880 (0.0005) [2023-03-08 00:55:02,816][286098] Fps is (10 sec: 12288.1, 60 sec: 11673.6, 300 sec: 11885.3). Total num frames: 83431424. Throughput: 0: 11803.0. Samples: 83423072. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:55:02,816][286098] Avg episode reward: [(0, '4426.631')] [2023-03-08 00:55:03,131][286389] Updated weights for policy 0, policy_version 162960 (0.0005) [2023-03-08 00:55:06,486][286389] Updated weights for policy 0, policy_version 163040 (0.0004) [2023-03-08 00:55:07,816][286098] Fps is (10 sec: 11878.5, 60 sec: 11673.6, 300 sec: 11871.5). Total num frames: 83488768. Throughput: 0: 11868.2. Samples: 83459392. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:55:07,816][286098] Avg episode reward: [(0, '4479.861')] [2023-03-08 00:55:09,929][286389] Updated weights for policy 0, policy_version 163120 (0.0005) [2023-03-08 00:55:12,816][286098] Fps is (10 sec: 11878.3, 60 sec: 11810.1, 300 sec: 11899.2). Total num frames: 83550208. Throughput: 0: 11964.6. Samples: 83531160. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:55:12,817][286098] Avg episode reward: [(0, '4521.603')] [2023-03-08 00:55:12,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000163184_83550208.pth... [2023-03-08 00:55:12,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000162480_83189760.pth [2023-03-08 00:55:13,268][286389] Updated weights for policy 0, policy_version 163200 (0.0004) [2023-03-08 00:55:16,667][286389] Updated weights for policy 0, policy_version 163280 (0.0004) [2023-03-08 00:55:17,816][286098] Fps is (10 sec: 12288.0, 60 sec: 11878.4, 300 sec: 11899.2). Total num frames: 83611648. Throughput: 0: 12077.8. Samples: 83603696. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:55:17,816][286098] Avg episode reward: [(0, '4522.161')] [2023-03-08 00:55:20,053][286389] Updated weights for policy 0, policy_version 163360 (0.0004) [2023-03-08 00:55:22,816][286098] Fps is (10 sec: 12288.0, 60 sec: 12014.9, 300 sec: 11899.2). Total num frames: 83673088. Throughput: 0: 12068.4. Samples: 83640384. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:55:22,816][286098] Avg episode reward: [(0, '4509.658')] [2023-03-08 00:55:23,494][286389] Updated weights for policy 0, policy_version 163440 (0.0004) [2023-03-08 00:55:27,191][286389] Updated weights for policy 0, policy_version 163520 (0.0005) [2023-03-08 00:55:27,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11946.7, 300 sec: 11885.3). Total num frames: 83726336. Throughput: 0: 11996.8. Samples: 83709952. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:55:27,816][286098] Avg episode reward: [(0, '4510.568')] [2023-03-08 00:55:27,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000163528_83726336.pth... [2023-03-08 00:55:27,823][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000162832_83369984.pth [2023-03-08 00:55:30,711][286389] Updated weights for policy 0, policy_version 163600 (0.0004) [2023-03-08 00:55:32,816][286098] Fps is (10 sec: 11468.8, 60 sec: 12014.9, 300 sec: 11885.3). Total num frames: 83787776. Throughput: 0: 11923.7. Samples: 83779648. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:55:32,816][286098] Avg episode reward: [(0, '4515.433')] [2023-03-08 00:55:34,063][286389] Updated weights for policy 0, policy_version 163680 (0.0004) [2023-03-08 00:55:37,583][286389] Updated weights for policy 0, policy_version 163760 (0.0005) [2023-03-08 00:55:37,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11946.7, 300 sec: 11871.5). Total num frames: 83845120. Throughput: 0: 11917.4. Samples: 83815980. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:55:37,816][286098] Avg episode reward: [(0, '4482.545')] [2023-03-08 00:55:40,911][286389] Updated weights for policy 0, policy_version 163840 (0.0004) [2023-03-08 00:55:42,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11946.7, 300 sec: 11885.3). Total num frames: 83906560. Throughput: 0: 11933.1. Samples: 83887692. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:55:42,816][286098] Avg episode reward: [(0, '4454.831')] [2023-03-08 00:55:42,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000163880_83906560.pth... [2023-03-08 00:55:42,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000163184_83550208.pth [2023-03-08 00:55:44,217][286389] Updated weights for policy 0, policy_version 163920 (0.0003) [2023-03-08 00:55:47,556][286389] Updated weights for policy 0, policy_version 164000 (0.0004) [2023-03-08 00:55:47,816][286098] Fps is (10 sec: 12288.0, 60 sec: 11946.7, 300 sec: 11899.2). Total num frames: 83968000. Throughput: 0: 11971.1. Samples: 83961772. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:55:47,816][286098] Avg episode reward: [(0, '4461.249')] [2023-03-08 00:55:50,895][286389] Updated weights for policy 0, policy_version 164080 (0.0004) [2023-03-08 00:55:52,816][286098] Fps is (10 sec: 12288.0, 60 sec: 12014.9, 300 sec: 11899.2). Total num frames: 84029440. Throughput: 0: 11989.4. Samples: 83998916. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:55:52,827][286098] Avg episode reward: [(0, '4514.089')] [2023-03-08 00:55:54,435][286389] Updated weights for policy 0, policy_version 164160 (0.0004) [2023-03-08 00:55:57,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11946.7, 300 sec: 11885.3). Total num frames: 84086784. Throughput: 0: 11959.4. Samples: 84069332. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:55:57,827][286098] Avg episode reward: [(0, '4471.175')] [2023-03-08 00:55:57,831][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000164232_84086784.pth... [2023-03-08 00:55:57,833][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000163528_83726336.pth [2023-03-08 00:55:58,026][286389] Updated weights for policy 0, policy_version 164240 (0.0004) [2023-03-08 00:56:01,714][286389] Updated weights for policy 0, policy_version 164320 (0.0005) [2023-03-08 00:56:02,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11810.1, 300 sec: 11857.6). Total num frames: 84140032. Throughput: 0: 11827.8. Samples: 84135948. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:56:02,827][286098] Avg episode reward: [(0, '4526.808')] [2023-03-08 00:56:05,381][286389] Updated weights for policy 0, policy_version 164400 (0.0005) [2023-03-08 00:56:07,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11810.1, 300 sec: 11843.7). Total num frames: 84197376. Throughput: 0: 11742.0. Samples: 84168776. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:56:07,827][286098] Avg episode reward: [(0, '4462.582')] [2023-03-08 00:56:08,987][286389] Updated weights for policy 0, policy_version 164480 (0.0005) [2023-03-08 00:56:12,664][286389] Updated weights for policy 0, policy_version 164560 (0.0005) [2023-03-08 00:56:12,816][286098] Fps is (10 sec: 11468.7, 60 sec: 11741.9, 300 sec: 11843.7). Total num frames: 84254720. Throughput: 0: 11715.4. Samples: 84237144. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:56:12,827][286098] Avg episode reward: [(0, '4512.184')] [2023-03-08 00:56:12,830][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000164560_84254720.pth... [2023-03-08 00:56:12,833][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000163880_83906560.pth [2023-03-08 00:56:16,315][286389] Updated weights for policy 0, policy_version 164640 (0.0005) [2023-03-08 00:56:17,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11673.6, 300 sec: 11829.8). Total num frames: 84312064. Throughput: 0: 11649.6. Samples: 84303880. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:56:17,827][286098] Avg episode reward: [(0, '4457.145')] [2023-03-08 00:56:19,823][286389] Updated weights for policy 0, policy_version 164720 (0.0005) [2023-03-08 00:56:22,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11605.3, 300 sec: 11829.8). Total num frames: 84369408. Throughput: 0: 11638.8. Samples: 84339724. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:56:22,827][286098] Avg episode reward: [(0, '4445.031')] [2023-03-08 00:56:23,493][286389] Updated weights for policy 0, policy_version 164800 (0.0005) [2023-03-08 00:56:26,883][286389] Updated weights for policy 0, policy_version 164880 (0.0005) [2023-03-08 00:56:27,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11673.6, 300 sec: 11829.8). Total num frames: 84426752. Throughput: 0: 11576.6. Samples: 84408640. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:56:27,827][286098] Avg episode reward: [(0, '4454.353')] [2023-03-08 00:56:27,831][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000164896_84426752.pth... [2023-03-08 00:56:27,833][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000164232_84086784.pth [2023-03-08 00:56:30,243][286389] Updated weights for policy 0, policy_version 164960 (0.0004) [2023-03-08 00:56:32,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11673.6, 300 sec: 11829.8). Total num frames: 84488192. Throughput: 0: 11574.6. Samples: 84482628. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:56:32,816][286098] Avg episode reward: [(0, '4500.676')] [2023-03-08 00:56:33,465][286389] Updated weights for policy 0, policy_version 165040 (0.0004) [2023-03-08 00:56:36,805][286389] Updated weights for policy 0, policy_version 165120 (0.0004) [2023-03-08 00:56:37,816][286098] Fps is (10 sec: 12697.6, 60 sec: 11810.1, 300 sec: 11843.7). Total num frames: 84553728. Throughput: 0: 11598.2. Samples: 84520836. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:56:37,816][286098] Avg episode reward: [(0, '4528.620')] [2023-03-08 00:56:40,127][286389] Updated weights for policy 0, policy_version 165200 (0.0004) [2023-03-08 00:56:42,816][286098] Fps is (10 sec: 12697.6, 60 sec: 11810.1, 300 sec: 11843.7). Total num frames: 84615168. Throughput: 0: 11659.6. Samples: 84594012. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:56:42,816][286098] Avg episode reward: [(0, '4460.300')] [2023-03-08 00:56:42,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000165264_84615168.pth... [2023-03-08 00:56:42,823][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000164560_84254720.pth [2023-03-08 00:56:43,480][286389] Updated weights for policy 0, policy_version 165280 (0.0005) [2023-03-08 00:56:46,831][286389] Updated weights for policy 0, policy_version 165360 (0.0004) [2023-03-08 00:56:47,816][286098] Fps is (10 sec: 12288.0, 60 sec: 11810.1, 300 sec: 11843.7). Total num frames: 84676608. Throughput: 0: 11810.9. Samples: 84667440. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:56:47,816][286098] Avg episode reward: [(0, '4430.600')] [2023-03-08 00:56:50,138][286389] Updated weights for policy 0, policy_version 165440 (0.0004) [2023-03-08 00:56:52,816][286098] Fps is (10 sec: 12288.0, 60 sec: 11810.1, 300 sec: 11857.6). Total num frames: 84738048. Throughput: 0: 11899.6. Samples: 84704260. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 00:56:52,816][286098] Avg episode reward: [(0, '4509.637')] [2023-03-08 00:56:53,425][286389] Updated weights for policy 0, policy_version 165520 (0.0004) [2023-03-08 00:56:56,698][286389] Updated weights for policy 0, policy_version 165600 (0.0004) [2023-03-08 00:56:57,816][286098] Fps is (10 sec: 12287.9, 60 sec: 11878.4, 300 sec: 11857.6). Total num frames: 84799488. Throughput: 0: 12042.8. Samples: 84779072. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 00:56:57,816][286098] Avg episode reward: [(0, '4510.077')] [2023-03-08 00:56:57,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000165624_84799488.pth... [2023-03-08 00:56:57,823][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000164896_84426752.pth [2023-03-08 00:57:00,024][286389] Updated weights for policy 0, policy_version 165680 (0.0004) [2023-03-08 00:57:02,816][286098] Fps is (10 sec: 12288.0, 60 sec: 12014.9, 300 sec: 11857.6). Total num frames: 84860928. Throughput: 0: 12209.0. Samples: 84853284. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 00:57:02,816][286098] Avg episode reward: [(0, '4504.972')] [2023-03-08 00:57:03,314][286389] Updated weights for policy 0, policy_version 165760 (0.0004) [2023-03-08 00:57:06,619][286389] Updated weights for policy 0, policy_version 165840 (0.0004) [2023-03-08 00:57:07,816][286098] Fps is (10 sec: 12288.1, 60 sec: 12083.2, 300 sec: 11857.6). Total num frames: 84922368. Throughput: 0: 12235.4. Samples: 84890316. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 00:57:07,816][286098] Avg episode reward: [(0, '4411.228')] [2023-03-08 00:57:10,158][286389] Updated weights for policy 0, policy_version 165920 (0.0005) [2023-03-08 00:57:12,816][286098] Fps is (10 sec: 11878.4, 60 sec: 12083.2, 300 sec: 11843.7). Total num frames: 84979712. Throughput: 0: 12281.5. Samples: 84961308. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 00:57:12,816][286098] Avg episode reward: [(0, '4528.189')] [2023-03-08 00:57:12,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000165976_84979712.pth... [2023-03-08 00:57:12,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000165264_84615168.pth [2023-03-08 00:57:13,528][286389] Updated weights for policy 0, policy_version 166000 (0.0005) [2023-03-08 00:57:16,872][286389] Updated weights for policy 0, policy_version 166080 (0.0005) [2023-03-08 00:57:17,816][286098] Fps is (10 sec: 11878.4, 60 sec: 12151.5, 300 sec: 11843.7). Total num frames: 85041152. Throughput: 0: 12284.4. Samples: 85035428. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 00:57:17,816][286098] Avg episode reward: [(0, '4419.725')] [2023-03-08 00:57:20,136][286389] Updated weights for policy 0, policy_version 166160 (0.0004) [2023-03-08 00:57:22,816][286098] Fps is (10 sec: 12697.6, 60 sec: 12288.0, 300 sec: 11871.5). Total num frames: 85106688. Throughput: 0: 12267.6. Samples: 85072880. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 00:57:22,816][286098] Avg episode reward: [(0, '4429.197')] [2023-03-08 00:57:23,361][286389] Updated weights for policy 0, policy_version 166240 (0.0004) [2023-03-08 00:57:26,727][286389] Updated weights for policy 0, policy_version 166320 (0.0005) [2023-03-08 00:57:27,816][286098] Fps is (10 sec: 12697.6, 60 sec: 12356.3, 300 sec: 11871.5). Total num frames: 85168128. Throughput: 0: 12304.4. Samples: 85147712. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 00:57:27,817][286098] Avg episode reward: [(0, '4482.674')] [2023-03-08 00:57:27,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000166344_85168128.pth... [2023-03-08 00:57:27,823][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000165624_84799488.pth [2023-03-08 00:57:30,080][286389] Updated weights for policy 0, policy_version 166400 (0.0005) [2023-03-08 00:57:32,816][286098] Fps is (10 sec: 12288.0, 60 sec: 12356.3, 300 sec: 11871.5). Total num frames: 85229568. Throughput: 0: 12311.3. Samples: 85221448. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 00:57:32,827][286098] Avg episode reward: [(0, '4474.739')] [2023-03-08 00:57:33,380][286389] Updated weights for policy 0, policy_version 166480 (0.0004) [2023-03-08 00:57:36,678][286389] Updated weights for policy 0, policy_version 166560 (0.0004) [2023-03-08 00:57:37,816][286098] Fps is (10 sec: 12288.0, 60 sec: 12288.0, 300 sec: 11885.3). Total num frames: 85291008. Throughput: 0: 12319.6. Samples: 85258640. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 00:57:37,827][286098] Avg episode reward: [(0, '4515.725')] [2023-03-08 00:57:40,045][286389] Updated weights for policy 0, policy_version 166640 (0.0005) [2023-03-08 00:57:42,816][286098] Fps is (10 sec: 12288.0, 60 sec: 12288.0, 300 sec: 11885.3). Total num frames: 85352448. Throughput: 0: 12288.0. Samples: 85332032. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 00:57:42,827][286098] Avg episode reward: [(0, '4510.505')] [2023-03-08 00:57:42,831][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000166704_85352448.pth... [2023-03-08 00:57:42,833][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000165976_84979712.pth [2023-03-08 00:57:43,401][286389] Updated weights for policy 0, policy_version 166720 (0.0005) [2023-03-08 00:57:46,791][286389] Updated weights for policy 0, policy_version 166800 (0.0005) [2023-03-08 00:57:47,816][286098] Fps is (10 sec: 12288.0, 60 sec: 12288.0, 300 sec: 11885.3). Total num frames: 85413888. Throughput: 0: 12263.7. Samples: 85405152. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 00:57:47,816][286098] Avg episode reward: [(0, '4512.265')] [2023-03-08 00:57:50,098][286389] Updated weights for policy 0, policy_version 166880 (0.0004) [2023-03-08 00:57:52,816][286098] Fps is (10 sec: 12288.0, 60 sec: 12288.0, 300 sec: 11885.3). Total num frames: 85475328. Throughput: 0: 12265.2. Samples: 85442248. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 00:57:52,816][286098] Avg episode reward: [(0, '4504.633')] [2023-03-08 00:57:53,448][286389] Updated weights for policy 0, policy_version 166960 (0.0005) [2023-03-08 00:57:56,765][286389] Updated weights for policy 0, policy_version 167040 (0.0005) [2023-03-08 00:57:57,816][286098] Fps is (10 sec: 12288.0, 60 sec: 12288.0, 300 sec: 11885.3). Total num frames: 85536768. Throughput: 0: 12322.3. Samples: 85515812. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 00:57:57,816][286098] Avg episode reward: [(0, '4495.231')] [2023-03-08 00:57:57,821][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000167064_85536768.pth... [2023-03-08 00:57:57,823][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000166344_85168128.pth [2023-03-08 00:58:00,139][286389] Updated weights for policy 0, policy_version 167120 (0.0005) [2023-03-08 00:58:02,816][286098] Fps is (10 sec: 11878.4, 60 sec: 12219.7, 300 sec: 11871.5). Total num frames: 85594112. Throughput: 0: 12300.0. Samples: 85588928. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 00:58:02,816][286098] Avg episode reward: [(0, '4498.786')] [2023-03-08 00:58:03,488][286389] Updated weights for policy 0, policy_version 167200 (0.0005) [2023-03-08 00:58:06,782][286389] Updated weights for policy 0, policy_version 167280 (0.0004) [2023-03-08 00:58:07,816][286098] Fps is (10 sec: 12288.1, 60 sec: 12288.0, 300 sec: 11899.2). Total num frames: 85659648. Throughput: 0: 12297.6. Samples: 85626272. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 00:58:07,816][286098] Avg episode reward: [(0, '4507.415')] [2023-03-08 00:58:10,158][286389] Updated weights for policy 0, policy_version 167360 (0.0005) [2023-03-08 00:58:12,816][286098] Fps is (10 sec: 12697.5, 60 sec: 12356.3, 300 sec: 11927.0). Total num frames: 85721088. Throughput: 0: 12263.8. Samples: 85699584. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 00:58:12,817][286098] Avg episode reward: [(0, '4506.108')] [2023-03-08 00:58:12,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000167424_85721088.pth... [2023-03-08 00:58:12,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000166704_85352448.pth [2023-03-08 00:58:13,438][286389] Updated weights for policy 0, policy_version 167440 (0.0004) [2023-03-08 00:58:16,821][286389] Updated weights for policy 0, policy_version 167520 (0.0004) [2023-03-08 00:58:17,816][286098] Fps is (10 sec: 12287.9, 60 sec: 12356.3, 300 sec: 11940.9). Total num frames: 85782528. Throughput: 0: 12263.3. Samples: 85773296. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 00:58:17,816][286098] Avg episode reward: [(0, '4515.709')] [2023-03-08 00:58:20,106][286389] Updated weights for policy 0, policy_version 167600 (0.0003) [2023-03-08 00:58:22,816][286098] Fps is (10 sec: 11878.5, 60 sec: 12219.7, 300 sec: 11940.9). Total num frames: 85839872. Throughput: 0: 12278.7. Samples: 85811180. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 00:58:22,816][286098] Avg episode reward: [(0, '4497.337')] [2023-03-08 00:58:23,496][286389] Updated weights for policy 0, policy_version 167680 (0.0004) [2023-03-08 00:58:26,776][286389] Updated weights for policy 0, policy_version 167760 (0.0004) [2023-03-08 00:58:27,816][286098] Fps is (10 sec: 12288.0, 60 sec: 12288.0, 300 sec: 11954.8). Total num frames: 85905408. Throughput: 0: 12264.4. Samples: 85883928. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 00:58:27,816][286098] Avg episode reward: [(0, '4494.464')] [2023-03-08 00:58:27,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000167784_85905408.pth... [2023-03-08 00:58:27,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000167064_85536768.pth [2023-03-08 00:58:30,159][286389] Updated weights for policy 0, policy_version 167840 (0.0005) [2023-03-08 00:58:32,816][286098] Fps is (10 sec: 12288.0, 60 sec: 12219.7, 300 sec: 11940.9). Total num frames: 85962752. Throughput: 0: 12270.8. Samples: 85957340. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 00:58:32,816][286098] Avg episode reward: [(0, '4448.073')] [2023-03-08 00:58:33,528][286389] Updated weights for policy 0, policy_version 167920 (0.0004) [2023-03-08 00:58:36,900][286389] Updated weights for policy 0, policy_version 168000 (0.0005) [2023-03-08 00:58:37,816][286098] Fps is (10 sec: 11878.4, 60 sec: 12219.7, 300 sec: 11940.9). Total num frames: 86024192. Throughput: 0: 12255.4. Samples: 85993740. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 00:58:37,816][286098] Avg episode reward: [(0, '4497.574')] [2023-03-08 00:58:40,270][286389] Updated weights for policy 0, policy_version 168080 (0.0005) [2023-03-08 00:58:42,816][286098] Fps is (10 sec: 12288.1, 60 sec: 12219.8, 300 sec: 11968.7). Total num frames: 86085632. Throughput: 0: 12229.3. Samples: 86066128. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 00:58:42,816][286098] Avg episode reward: [(0, '4404.503')] [2023-03-08 00:58:42,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000168136_86085632.pth... [2023-03-08 00:58:42,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000167424_85721088.pth [2023-03-08 00:58:43,599][286389] Updated weights for policy 0, policy_version 168160 (0.0004) [2023-03-08 00:58:46,937][286389] Updated weights for policy 0, policy_version 168240 (0.0005) [2023-03-08 00:58:47,816][286098] Fps is (10 sec: 12288.0, 60 sec: 12219.7, 300 sec: 11982.5). Total num frames: 86147072. Throughput: 0: 12248.3. Samples: 86140100. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 00:58:47,816][286098] Avg episode reward: [(0, '4464.366')] [2023-03-08 00:58:50,204][286389] Updated weights for policy 0, policy_version 168320 (0.0004) [2023-03-08 00:58:52,816][286098] Fps is (10 sec: 12287.9, 60 sec: 12219.7, 300 sec: 11996.4). Total num frames: 86208512. Throughput: 0: 12261.6. Samples: 86178044. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 00:58:52,816][286098] Avg episode reward: [(0, '4472.316')] [2023-03-08 00:58:53,518][286389] Updated weights for policy 0, policy_version 168400 (0.0004) [2023-03-08 00:58:56,907][286389] Updated weights for policy 0, policy_version 168480 (0.0005) [2023-03-08 00:58:57,816][286098] Fps is (10 sec: 12288.0, 60 sec: 12219.7, 300 sec: 11996.4). Total num frames: 86269952. Throughput: 0: 12266.4. Samples: 86251572. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 00:58:57,816][286098] Avg episode reward: [(0, '4457.293')] [2023-03-08 00:58:57,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000168496_86269952.pth... [2023-03-08 00:58:57,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000167784_85905408.pth [2023-03-08 00:59:00,294][286389] Updated weights for policy 0, policy_version 168560 (0.0005) [2023-03-08 00:59:02,816][286098] Fps is (10 sec: 12288.0, 60 sec: 12288.0, 300 sec: 12010.3). Total num frames: 86331392. Throughput: 0: 12259.9. Samples: 86324992. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 00:59:02,816][286098] Avg episode reward: [(0, '4497.584')] [2023-03-08 00:59:03,572][286389] Updated weights for policy 0, policy_version 168640 (0.0004) [2023-03-08 00:59:06,995][286389] Updated weights for policy 0, policy_version 168720 (0.0005) [2023-03-08 00:59:07,816][286098] Fps is (10 sec: 12288.0, 60 sec: 12219.7, 300 sec: 12038.1). Total num frames: 86392832. Throughput: 0: 12233.6. Samples: 86361692. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 00:59:07,816][286098] Avg episode reward: [(0, '4489.193')] [2023-03-08 00:59:10,598][286389] Updated weights for policy 0, policy_version 168800 (0.0005) [2023-03-08 00:59:12,816][286098] Fps is (10 sec: 11878.3, 60 sec: 12151.5, 300 sec: 12038.1). Total num frames: 86450176. Throughput: 0: 12149.1. Samples: 86430636. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 00:59:12,816][286098] Avg episode reward: [(0, '4461.473')] [2023-03-08 00:59:12,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000168848_86450176.pth... [2023-03-08 00:59:12,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000168136_86085632.pth [2023-03-08 00:59:14,186][286389] Updated weights for policy 0, policy_version 168880 (0.0005) [2023-03-08 00:59:17,763][286389] Updated weights for policy 0, policy_version 168960 (0.0005) [2023-03-08 00:59:17,816][286098] Fps is (10 sec: 11468.7, 60 sec: 12083.2, 300 sec: 12052.0). Total num frames: 86507520. Throughput: 0: 12045.6. Samples: 86499392. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 00:59:17,817][286098] Avg episode reward: [(0, '4491.883')] [2023-03-08 00:59:21,288][286389] Updated weights for policy 0, policy_version 169040 (0.0005) [2023-03-08 00:59:22,816][286098] Fps is (10 sec: 11468.8, 60 sec: 12083.2, 300 sec: 12052.0). Total num frames: 86564864. Throughput: 0: 12029.8. Samples: 86535080. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 00:59:22,816][286098] Avg episode reward: [(0, '4470.213')] [2023-03-08 00:59:24,872][286389] Updated weights for policy 0, policy_version 169120 (0.0005) [2023-03-08 00:59:27,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11946.7, 300 sec: 12052.0). Total num frames: 86622208. Throughput: 0: 11918.8. Samples: 86602476. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 00:59:27,816][286098] Avg episode reward: [(0, '4472.456')] [2023-03-08 00:59:27,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000169184_86622208.pth... [2023-03-08 00:59:27,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000168496_86269952.pth [2023-03-08 00:59:28,491][286389] Updated weights for policy 0, policy_version 169200 (0.0005) [2023-03-08 00:59:31,953][286389] Updated weights for policy 0, policy_version 169280 (0.0004) [2023-03-08 00:59:32,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11946.7, 300 sec: 12038.1). Total num frames: 86679552. Throughput: 0: 11827.1. Samples: 86672320. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 00:59:32,816][286098] Avg episode reward: [(0, '4405.446')] [2023-03-08 00:59:35,372][286389] Updated weights for policy 0, policy_version 169360 (0.0004) [2023-03-08 00:59:37,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11946.7, 300 sec: 12038.1). Total num frames: 86740992. Throughput: 0: 11784.3. Samples: 86708336. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 00:59:37,816][286098] Avg episode reward: [(0, '4483.381')] [2023-03-08 00:59:38,691][286389] Updated weights for policy 0, policy_version 169440 (0.0004) [2023-03-08 00:59:41,972][286389] Updated weights for policy 0, policy_version 169520 (0.0004) [2023-03-08 00:59:42,816][286098] Fps is (10 sec: 12288.0, 60 sec: 11946.7, 300 sec: 12038.1). Total num frames: 86802432. Throughput: 0: 11791.3. Samples: 86782180. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 00:59:42,816][286098] Avg episode reward: [(0, '4474.840')] [2023-03-08 00:59:42,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000169536_86802432.pth... [2023-03-08 00:59:42,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000168848_86450176.pth [2023-03-08 00:59:45,246][286389] Updated weights for policy 0, policy_version 169600 (0.0004) [2023-03-08 00:59:47,816][286098] Fps is (10 sec: 12288.0, 60 sec: 11946.7, 300 sec: 12052.0). Total num frames: 86863872. Throughput: 0: 11815.0. Samples: 86856668. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 00:59:47,816][286098] Avg episode reward: [(0, '4504.050')] [2023-03-08 00:59:48,655][286389] Updated weights for policy 0, policy_version 169680 (0.0005) [2023-03-08 00:59:52,047][286389] Updated weights for policy 0, policy_version 169760 (0.0005) [2023-03-08 00:59:52,816][286098] Fps is (10 sec: 12288.0, 60 sec: 11946.7, 300 sec: 12052.0). Total num frames: 86925312. Throughput: 0: 11812.5. Samples: 86893256. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 00:59:52,816][286098] Avg episode reward: [(0, '4510.636')] [2023-03-08 00:59:55,433][286389] Updated weights for policy 0, policy_version 169840 (0.0005) [2023-03-08 00:59:57,816][286098] Fps is (10 sec: 12287.9, 60 sec: 11946.7, 300 sec: 12052.0). Total num frames: 86986752. Throughput: 0: 11902.3. Samples: 86966240. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 00:59:57,816][286098] Avg episode reward: [(0, '4499.734')] [2023-03-08 00:59:57,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000169896_86986752.pth... [2023-03-08 00:59:57,821][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000169184_86622208.pth [2023-03-08 00:59:58,806][286389] Updated weights for policy 0, policy_version 169920 (0.0004) [2023-03-08 01:00:02,360][286389] Updated weights for policy 0, policy_version 170000 (0.0005) [2023-03-08 01:00:02,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11878.4, 300 sec: 12052.0). Total num frames: 87044096. Throughput: 0: 11933.6. Samples: 87036404. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 01:00:02,816][286098] Avg episode reward: [(0, '4498.443')] [2023-03-08 01:00:06,036][286389] Updated weights for policy 0, policy_version 170080 (0.0005) [2023-03-08 01:00:07,816][286098] Fps is (10 sec: 11059.3, 60 sec: 11741.9, 300 sec: 12024.2). Total num frames: 87097344. Throughput: 0: 11887.3. Samples: 87070008. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 01:00:07,816][286098] Avg episode reward: [(0, '4460.016')] [2023-03-08 01:00:09,639][286389] Updated weights for policy 0, policy_version 170160 (0.0005) [2023-03-08 01:00:12,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11741.9, 300 sec: 12010.3). Total num frames: 87154688. Throughput: 0: 11908.7. Samples: 87138368. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 01:00:12,816][286098] Avg episode reward: [(0, '4483.506')] [2023-03-08 01:00:12,862][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000170232_87158784.pth... [2023-03-08 01:00:12,864][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000169536_86802432.pth [2023-03-08 01:00:13,243][286389] Updated weights for policy 0, policy_version 170240 (0.0005) [2023-03-08 01:00:16,846][286389] Updated weights for policy 0, policy_version 170320 (0.0005) [2023-03-08 01:00:17,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11741.9, 300 sec: 11996.4). Total num frames: 87212032. Throughput: 0: 11875.9. Samples: 87206736. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 01:00:17,816][286098] Avg episode reward: [(0, '4516.729')] [2023-03-08 01:00:20,218][286389] Updated weights for policy 0, policy_version 170400 (0.0003) [2023-03-08 01:00:22,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11810.1, 300 sec: 12024.2). Total num frames: 87273472. Throughput: 0: 11877.4. Samples: 87242820. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 01:00:22,816][286098] Avg episode reward: [(0, '4452.366')] [2023-03-08 01:00:23,604][286389] Updated weights for policy 0, policy_version 170480 (0.0003) [2023-03-08 01:00:26,965][286389] Updated weights for policy 0, policy_version 170560 (0.0003) [2023-03-08 01:00:27,816][286098] Fps is (10 sec: 12287.9, 60 sec: 11878.4, 300 sec: 12024.2). Total num frames: 87334912. Throughput: 0: 11846.6. Samples: 87315276. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 01:00:27,816][286098] Avg episode reward: [(0, '4481.853')] [2023-03-08 01:00:27,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000170576_87334912.pth... [2023-03-08 01:00:27,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000169896_86986752.pth [2023-03-08 01:00:30,300][286389] Updated weights for policy 0, policy_version 170640 (0.0003) [2023-03-08 01:00:32,816][286098] Fps is (10 sec: 12288.0, 60 sec: 11946.7, 300 sec: 12038.1). Total num frames: 87396352. Throughput: 0: 11819.5. Samples: 87388544. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 01:00:32,816][286098] Avg episode reward: [(0, '4515.265')] [2023-03-08 01:00:33,789][286389] Updated weights for policy 0, policy_version 170720 (0.0003) [2023-03-08 01:00:37,085][286389] Updated weights for policy 0, policy_version 170800 (0.0003) [2023-03-08 01:00:37,816][286098] Fps is (10 sec: 12288.0, 60 sec: 11946.7, 300 sec: 12038.1). Total num frames: 87457792. Throughput: 0: 11817.1. Samples: 87425024. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 01:00:37,816][286098] Avg episode reward: [(0, '4504.726')] [2023-03-08 01:00:40,361][286389] Updated weights for policy 0, policy_version 170880 (0.0003) [2023-03-08 01:00:42,816][286098] Fps is (10 sec: 12288.0, 60 sec: 11946.7, 300 sec: 12038.1). Total num frames: 87519232. Throughput: 0: 11835.2. Samples: 87498824. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 01:00:42,816][286098] Avg episode reward: [(0, '4519.573')] [2023-03-08 01:00:42,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000170936_87519232.pth... [2023-03-08 01:00:42,821][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000170232_87158784.pth [2023-03-08 01:00:43,829][286389] Updated weights for policy 0, policy_version 170960 (0.0003) [2023-03-08 01:00:47,200][286389] Updated weights for policy 0, policy_version 171040 (0.0003) [2023-03-08 01:00:47,816][286098] Fps is (10 sec: 11878.5, 60 sec: 11878.4, 300 sec: 12024.2). Total num frames: 87576576. Throughput: 0: 11874.9. Samples: 87570772. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 01:00:47,816][286098] Avg episode reward: [(0, '4498.989')] [2023-03-08 01:00:50,774][286389] Updated weights for policy 0, policy_version 171120 (0.0005) [2023-03-08 01:00:52,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11810.1, 300 sec: 12024.2). Total num frames: 87633920. Throughput: 0: 11895.6. Samples: 87605312. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 01:00:52,827][286098] Avg episode reward: [(0, '4497.561')] [2023-03-08 01:00:54,319][286389] Updated weights for policy 0, policy_version 171200 (0.0005) [2023-03-08 01:00:57,816][286098] Fps is (10 sec: 11468.7, 60 sec: 11741.9, 300 sec: 12038.1). Total num frames: 87691264. Throughput: 0: 11912.1. Samples: 87674412. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 01:00:57,827][286098] Avg episode reward: [(0, '4492.576')] [2023-03-08 01:00:57,830][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000171272_87691264.pth... [2023-03-08 01:00:57,833][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000170576_87334912.pth [2023-03-08 01:00:57,984][286389] Updated weights for policy 0, policy_version 171280 (0.0005) [2023-03-08 01:01:01,524][286389] Updated weights for policy 0, policy_version 171360 (0.0005) [2023-03-08 01:01:02,816][286098] Fps is (10 sec: 11468.9, 60 sec: 11741.9, 300 sec: 12038.1). Total num frames: 87748608. Throughput: 0: 11907.6. Samples: 87742576. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 01:01:02,827][286098] Avg episode reward: [(0, '4480.547')] [2023-03-08 01:01:05,162][286389] Updated weights for policy 0, policy_version 171440 (0.0005) [2023-03-08 01:01:07,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11810.1, 300 sec: 12038.1). Total num frames: 87805952. Throughput: 0: 11865.5. Samples: 87776768. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 01:01:07,827][286098] Avg episode reward: [(0, '4484.122')] [2023-03-08 01:01:08,651][286389] Updated weights for policy 0, policy_version 171520 (0.0005) [2023-03-08 01:01:12,194][286389] Updated weights for policy 0, policy_version 171600 (0.0004) [2023-03-08 01:01:12,816][286098] Fps is (10 sec: 11468.7, 60 sec: 11810.1, 300 sec: 12038.1). Total num frames: 87863296. Throughput: 0: 11798.6. Samples: 87846212. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 01:01:12,827][286098] Avg episode reward: [(0, '4437.962')] [2023-03-08 01:01:12,829][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000171608_87863296.pth... [2023-03-08 01:01:12,831][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000170936_87519232.pth [2023-03-08 01:01:15,561][286389] Updated weights for policy 0, policy_version 171680 (0.0005) [2023-03-08 01:01:17,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11878.4, 300 sec: 12052.0). Total num frames: 87924736. Throughput: 0: 11766.1. Samples: 87918016. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 01:01:17,827][286098] Avg episode reward: [(0, '4459.793')] [2023-03-08 01:01:18,929][286389] Updated weights for policy 0, policy_version 171760 (0.0005) [2023-03-08 01:01:22,218][286389] Updated weights for policy 0, policy_version 171840 (0.0004) [2023-03-08 01:01:22,816][286098] Fps is (10 sec: 12288.0, 60 sec: 11878.4, 300 sec: 12065.8). Total num frames: 87986176. Throughput: 0: 11780.1. Samples: 87955128. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 01:01:22,816][286098] Avg episode reward: [(0, '4487.466')] [2023-03-08 01:01:25,549][286389] Updated weights for policy 0, policy_version 171920 (0.0004) [2023-03-08 01:01:27,816][286098] Fps is (10 sec: 12287.9, 60 sec: 11878.4, 300 sec: 12065.8). Total num frames: 88047616. Throughput: 0: 11785.0. Samples: 88029148. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 01:01:27,816][286098] Avg episode reward: [(0, '4466.596')] [2023-03-08 01:01:27,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000171968_88047616.pth... [2023-03-08 01:01:27,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000171272_87691264.pth [2023-03-08 01:01:29,037][286389] Updated weights for policy 0, policy_version 172000 (0.0005) [2023-03-08 01:01:32,704][286389] Updated weights for policy 0, policy_version 172080 (0.0005) [2023-03-08 01:01:32,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11810.1, 300 sec: 12038.1). Total num frames: 88104960. Throughput: 0: 11705.3. Samples: 88097512. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 01:01:32,827][286098] Avg episode reward: [(0, '4448.766')] [2023-03-08 01:01:36,295][286389] Updated weights for policy 0, policy_version 172160 (0.0005) [2023-03-08 01:01:37,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11741.9, 300 sec: 12024.2). Total num frames: 88162304. Throughput: 0: 11690.1. Samples: 88131368. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 01:01:37,816][286098] Avg episode reward: [(0, '4448.213')] [2023-03-08 01:01:39,922][286389] Updated weights for policy 0, policy_version 172240 (0.0005) [2023-03-08 01:01:42,816][286098] Fps is (10 sec: 11468.7, 60 sec: 11673.6, 300 sec: 12010.3). Total num frames: 88219648. Throughput: 0: 11672.3. Samples: 88199664. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 01:01:42,827][286098] Avg episode reward: [(0, '4456.113')] [2023-03-08 01:01:42,831][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000172304_88219648.pth... [2023-03-08 01:01:42,834][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000171608_87863296.pth [2023-03-08 01:01:43,495][286389] Updated weights for policy 0, policy_version 172320 (0.0005) [2023-03-08 01:01:47,151][286389] Updated weights for policy 0, policy_version 172400 (0.0005) [2023-03-08 01:01:47,816][286098] Fps is (10 sec: 11059.3, 60 sec: 11605.3, 300 sec: 11982.5). Total num frames: 88272896. Throughput: 0: 11686.0. Samples: 88268448. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 01:01:47,827][286098] Avg episode reward: [(0, '4462.945')] [2023-03-08 01:01:50,750][286389] Updated weights for policy 0, policy_version 172480 (0.0005) [2023-03-08 01:01:52,816][286098] Fps is (10 sec: 11059.3, 60 sec: 11605.3, 300 sec: 11968.7). Total num frames: 88330240. Throughput: 0: 11663.9. Samples: 88301644. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 01:01:52,826][286098] Avg episode reward: [(0, '4472.827')] [2023-03-08 01:01:54,196][286389] Updated weights for policy 0, policy_version 172560 (0.0005) [2023-03-08 01:01:57,533][286389] Updated weights for policy 0, policy_version 172640 (0.0004) [2023-03-08 01:01:57,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11673.6, 300 sec: 11968.7). Total num frames: 88391680. Throughput: 0: 11721.0. Samples: 88373656. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 01:01:57,827][286098] Avg episode reward: [(0, '4370.608')] [2023-03-08 01:01:57,882][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000172648_88395776.pth... [2023-03-08 01:01:57,884][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000171968_88047616.pth [2023-03-08 01:02:01,098][286389] Updated weights for policy 0, policy_version 172720 (0.0005) [2023-03-08 01:02:02,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11673.6, 300 sec: 11954.8). Total num frames: 88449024. Throughput: 0: 11688.8. Samples: 88444012. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 01:02:02,827][286098] Avg episode reward: [(0, '4407.894')] [2023-03-08 01:02:04,682][286389] Updated weights for policy 0, policy_version 172800 (0.0005) [2023-03-08 01:02:07,816][286098] Fps is (10 sec: 11878.3, 60 sec: 11741.9, 300 sec: 11968.7). Total num frames: 88510464. Throughput: 0: 11614.2. Samples: 88477768. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 01:02:07,827][286098] Avg episode reward: [(0, '4402.697')] [2023-03-08 01:02:08,099][286389] Updated weights for policy 0, policy_version 172880 (0.0004) [2023-03-08 01:02:11,554][286389] Updated weights for policy 0, policy_version 172960 (0.0004) [2023-03-08 01:02:12,816][286098] Fps is (10 sec: 11878.3, 60 sec: 11741.9, 300 sec: 11954.8). Total num frames: 88567808. Throughput: 0: 11584.8. Samples: 88550464. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 01:02:12,827][286098] Avg episode reward: [(0, '4380.112')] [2023-03-08 01:02:12,830][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000172984_88567808.pth... [2023-03-08 01:02:12,833][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000172304_88219648.pth [2023-03-08 01:02:15,184][286389] Updated weights for policy 0, policy_version 173040 (0.0005) [2023-03-08 01:02:17,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11673.6, 300 sec: 11927.0). Total num frames: 88625152. Throughput: 0: 11550.9. Samples: 88617304. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 01:02:17,827][286098] Avg episode reward: [(0, '4263.047')] [2023-03-08 01:02:18,807][286389] Updated weights for policy 0, policy_version 173120 (0.0005) [2023-03-08 01:02:22,446][286389] Updated weights for policy 0, policy_version 173200 (0.0005) [2023-03-08 01:02:22,816][286098] Fps is (10 sec: 11059.3, 60 sec: 11537.1, 300 sec: 11899.2). Total num frames: 88678400. Throughput: 0: 11566.1. Samples: 88651840. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 01:02:22,827][286098] Avg episode reward: [(0, '4173.643')] [2023-03-08 01:02:26,103][286389] Updated weights for policy 0, policy_version 173280 (0.0005) [2023-03-08 01:02:27,816][286098] Fps is (10 sec: 11059.1, 60 sec: 11468.8, 300 sec: 11885.3). Total num frames: 88735744. Throughput: 0: 11548.8. Samples: 88719360. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 01:02:27,827][286098] Avg episode reward: [(0, '4321.207')] [2023-03-08 01:02:27,864][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000173320_88739840.pth... [2023-03-08 01:02:27,866][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000172648_88395776.pth [2023-03-08 01:02:29,544][286389] Updated weights for policy 0, policy_version 173360 (0.0003) [2023-03-08 01:02:32,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11537.1, 300 sec: 11885.3). Total num frames: 88797184. Throughput: 0: 11604.7. Samples: 88790660. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 01:02:32,827][286098] Avg episode reward: [(0, '4260.015')] [2023-03-08 01:02:32,973][286389] Updated weights for policy 0, policy_version 173440 (0.0003) [2023-03-08 01:02:36,500][286389] Updated weights for policy 0, policy_version 173520 (0.0005) [2023-03-08 01:02:37,816][286098] Fps is (10 sec: 12288.1, 60 sec: 11605.3, 300 sec: 11885.3). Total num frames: 88858624. Throughput: 0: 11648.3. Samples: 88825816. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 01:02:37,816][286098] Avg episode reward: [(0, '4108.149')] [2023-03-08 01:02:39,872][286389] Updated weights for policy 0, policy_version 173600 (0.0003) [2023-03-08 01:02:42,816][286098] Fps is (10 sec: 11878.3, 60 sec: 11605.3, 300 sec: 11871.5). Total num frames: 88915968. Throughput: 0: 11629.8. Samples: 88896996. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 01:02:42,816][286098] Avg episode reward: [(0, '4146.710')] [2023-03-08 01:02:42,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000173664_88915968.pth... [2023-03-08 01:02:42,821][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000172984_88567808.pth [2023-03-08 01:02:43,275][286389] Updated weights for policy 0, policy_version 173680 (0.0003) [2023-03-08 01:02:46,632][286389] Updated weights for policy 0, policy_version 173760 (0.0003) [2023-03-08 01:02:47,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11741.9, 300 sec: 11871.5). Total num frames: 88977408. Throughput: 0: 11700.6. Samples: 88970540. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 01:02:47,816][286098] Avg episode reward: [(0, '4088.166')] [2023-03-08 01:02:50,073][286389] Updated weights for policy 0, policy_version 173840 (0.0005) [2023-03-08 01:02:52,816][286098] Fps is (10 sec: 11878.5, 60 sec: 11741.9, 300 sec: 11857.6). Total num frames: 89034752. Throughput: 0: 11741.7. Samples: 89006144. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 01:02:52,816][286098] Avg episode reward: [(0, '4029.219')] [2023-03-08 01:02:53,599][286389] Updated weights for policy 0, policy_version 173920 (0.0005) [2023-03-08 01:02:57,148][286389] Updated weights for policy 0, policy_version 174000 (0.0005) [2023-03-08 01:02:57,816][286098] Fps is (10 sec: 11468.7, 60 sec: 11673.6, 300 sec: 11857.6). Total num frames: 89092096. Throughput: 0: 11672.2. Samples: 89075712. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 01:02:57,816][286098] Avg episode reward: [(0, '3987.979')] [2023-03-08 01:02:57,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000174008_89092096.pth... [2023-03-08 01:02:57,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000173320_88739840.pth [2023-03-08 01:03:00,719][286389] Updated weights for policy 0, policy_version 174080 (0.0005) [2023-03-08 01:03:02,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11673.6, 300 sec: 11829.8). Total num frames: 89149440. Throughput: 0: 11723.2. Samples: 89144848. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 01:03:02,816][286098] Avg episode reward: [(0, '3876.171')] [2023-03-08 01:03:04,303][286389] Updated weights for policy 0, policy_version 174160 (0.0005) [2023-03-08 01:03:07,805][286389] Updated weights for policy 0, policy_version 174240 (0.0004) [2023-03-08 01:03:07,816][286098] Fps is (10 sec: 11878.5, 60 sec: 11673.6, 300 sec: 11829.8). Total num frames: 89210880. Throughput: 0: 11699.9. Samples: 89178336. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 01:03:07,816][286098] Avg episode reward: [(0, '3872.674')] [2023-03-08 01:03:11,405][286389] Updated weights for policy 0, policy_version 174320 (0.0005) [2023-03-08 01:03:12,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11673.6, 300 sec: 11815.9). Total num frames: 89268224. Throughput: 0: 11742.2. Samples: 89247760. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 01:03:12,816][286098] Avg episode reward: [(0, '3920.877')] [2023-03-08 01:03:12,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000174352_89268224.pth... [2023-03-08 01:03:12,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000173664_88915968.pth [2023-03-08 01:03:14,699][286389] Updated weights for policy 0, policy_version 174400 (0.0004) [2023-03-08 01:03:17,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11741.9, 300 sec: 11829.8). Total num frames: 89329664. Throughput: 0: 11797.4. Samples: 89321544. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 01:03:17,816][286098] Avg episode reward: [(0, '3738.955')] [2023-03-08 01:03:17,988][286389] Updated weights for policy 0, policy_version 174480 (0.0004) [2023-03-08 01:03:21,288][286389] Updated weights for policy 0, policy_version 174560 (0.0004) [2023-03-08 01:03:22,816][286098] Fps is (10 sec: 12288.0, 60 sec: 11878.4, 300 sec: 11815.9). Total num frames: 89391104. Throughput: 0: 11853.7. Samples: 89359232. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-08 01:03:22,816][286098] Avg episode reward: [(0, '3750.926')] [2023-03-08 01:03:24,620][286389] Updated weights for policy 0, policy_version 174640 (0.0003) [2023-03-08 01:03:27,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11878.4, 300 sec: 11815.9). Total num frames: 89448448. Throughput: 0: 11890.6. Samples: 89432072. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 01:03:27,816][286098] Avg episode reward: [(0, '3814.611')] [2023-03-08 01:03:27,875][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000174712_89452544.pth... [2023-03-08 01:03:27,876][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000174008_89092096.pth [2023-03-08 01:03:28,248][286389] Updated weights for policy 0, policy_version 174720 (0.0005) [2023-03-08 01:03:31,934][286389] Updated weights for policy 0, policy_version 174800 (0.0005) [2023-03-08 01:03:32,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11810.1, 300 sec: 11802.0). Total num frames: 89505792. Throughput: 0: 11745.6. Samples: 89499092. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 01:03:32,816][286098] Avg episode reward: [(0, '3678.926')] [2023-03-08 01:03:35,611][286389] Updated weights for policy 0, policy_version 174880 (0.0005) [2023-03-08 01:03:37,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11741.9, 300 sec: 11788.1). Total num frames: 89563136. Throughput: 0: 11704.2. Samples: 89532832. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 01:03:37,816][286098] Avg episode reward: [(0, '3846.709')] [2023-03-08 01:03:39,087][286389] Updated weights for policy 0, policy_version 174960 (0.0005) [2023-03-08 01:03:42,421][286389] Updated weights for policy 0, policy_version 175040 (0.0005) [2023-03-08 01:03:42,816][286098] Fps is (10 sec: 11878.3, 60 sec: 11810.1, 300 sec: 11788.1). Total num frames: 89624576. Throughput: 0: 11740.6. Samples: 89604040. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 01:03:42,816][286098] Avg episode reward: [(0, '3801.996')] [2023-03-08 01:03:42,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000175048_89624576.pth... [2023-03-08 01:03:42,823][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000174352_89268224.pth [2023-03-08 01:03:45,691][286389] Updated weights for policy 0, policy_version 175120 (0.0005) [2023-03-08 01:03:47,816][286098] Fps is (10 sec: 12288.0, 60 sec: 11810.1, 300 sec: 11788.1). Total num frames: 89686016. Throughput: 0: 11873.2. Samples: 89679144. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 01:03:47,816][286098] Avg episode reward: [(0, '3838.322')] [2023-03-08 01:03:48,862][286389] Updated weights for policy 0, policy_version 175200 (0.0004) [2023-03-08 01:03:52,111][286389] Updated weights for policy 0, policy_version 175280 (0.0004) [2023-03-08 01:03:52,816][286098] Fps is (10 sec: 12697.6, 60 sec: 11946.7, 300 sec: 11802.0). Total num frames: 89751552. Throughput: 0: 11992.1. Samples: 89717980. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 01:03:52,816][286098] Avg episode reward: [(0, '3688.991')] [2023-03-08 01:03:55,369][286389] Updated weights for policy 0, policy_version 175360 (0.0004) [2023-03-08 01:03:57,816][286098] Fps is (10 sec: 12697.6, 60 sec: 12014.9, 300 sec: 11802.0). Total num frames: 89812992. Throughput: 0: 12110.0. Samples: 89792712. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 01:03:57,816][286098] Avg episode reward: [(0, '3774.546')] [2023-03-08 01:03:57,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000175416_89812992.pth... [2023-03-08 01:03:57,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000174712_89452544.pth [2023-03-08 01:03:58,714][286389] Updated weights for policy 0, policy_version 175440 (0.0005) [2023-03-08 01:04:02,004][286389] Updated weights for policy 0, policy_version 175520 (0.0003) [2023-03-08 01:04:02,816][286098] Fps is (10 sec: 12288.0, 60 sec: 12083.2, 300 sec: 11802.0). Total num frames: 89874432. Throughput: 0: 12113.2. Samples: 89866640. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 01:04:02,816][286098] Avg episode reward: [(0, '3964.849')] [2023-03-08 01:04:05,253][286389] Updated weights for policy 0, policy_version 175600 (0.0004) [2023-03-08 01:04:07,816][286098] Fps is (10 sec: 12288.0, 60 sec: 12083.2, 300 sec: 11815.9). Total num frames: 89935872. Throughput: 0: 12121.5. Samples: 89904700. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 01:04:07,816][286098] Avg episode reward: [(0, '4028.806')] [2023-03-08 01:04:08,639][286389] Updated weights for policy 0, policy_version 175680 (0.0004) [2023-03-08 01:04:12,012][286389] Updated weights for policy 0, policy_version 175760 (0.0003) [2023-03-08 01:04:12,816][286098] Fps is (10 sec: 12288.0, 60 sec: 12151.5, 300 sec: 11829.8). Total num frames: 89997312. Throughput: 0: 12107.9. Samples: 89976928. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 01:04:12,816][286098] Avg episode reward: [(0, '3849.510')] [2023-03-08 01:04:12,821][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000175776_89997312.pth... [2023-03-08 01:04:12,823][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000175048_89624576.pth [2023-03-08 01:04:15,320][286389] Updated weights for policy 0, policy_version 175840 (0.0003) [2023-03-08 01:04:17,816][286098] Fps is (10 sec: 12288.0, 60 sec: 12151.5, 300 sec: 11843.7). Total num frames: 90058752. Throughput: 0: 12282.7. Samples: 90051812. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 01:04:17,816][286098] Avg episode reward: [(0, '3744.067')] [2023-03-08 01:04:18,668][286389] Updated weights for policy 0, policy_version 175920 (0.0003) [2023-03-08 01:04:22,145][286389] Updated weights for policy 0, policy_version 176000 (0.0003) [2023-03-08 01:04:22,816][286098] Fps is (10 sec: 12288.0, 60 sec: 12151.5, 300 sec: 11857.6). Total num frames: 90120192. Throughput: 0: 12319.2. Samples: 90087196. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 01:04:22,816][286098] Avg episode reward: [(0, '3875.377')] [2023-03-08 01:04:25,494][286389] Updated weights for policy 0, policy_version 176080 (0.0003) [2023-03-08 01:04:27,816][286098] Fps is (10 sec: 11878.3, 60 sec: 12151.4, 300 sec: 11857.6). Total num frames: 90177536. Throughput: 0: 12351.3. Samples: 90159848. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-08 01:04:27,816][286098] Avg episode reward: [(0, '4017.176')] [2023-03-08 01:04:27,843][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000176136_90181632.pth... [2023-03-08 01:04:27,845][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000175416_89812992.pth [2023-03-08 01:04:28,844][286389] Updated weights for policy 0, policy_version 176160 (0.0003) [2023-03-08 01:04:32,372][286389] Updated weights for policy 0, policy_version 176240 (0.0005) [2023-03-08 01:04:32,816][286098] Fps is (10 sec: 11878.5, 60 sec: 12219.7, 300 sec: 11857.6). Total num frames: 90238976. Throughput: 0: 12266.5. Samples: 90231136. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 01:04:32,816][286098] Avg episode reward: [(0, '3957.853')] [2023-03-08 01:04:36,045][286389] Updated weights for policy 0, policy_version 176320 (0.0005) [2023-03-08 01:04:37,816][286098] Fps is (10 sec: 11468.8, 60 sec: 12151.5, 300 sec: 11829.8). Total num frames: 90292224. Throughput: 0: 12138.9. Samples: 90264232. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 01:04:37,817][286098] Avg episode reward: [(0, '3834.435')] [2023-03-08 01:04:39,687][286389] Updated weights for policy 0, policy_version 176400 (0.0005) [2023-03-08 01:04:42,816][286098] Fps is (10 sec: 11059.2, 60 sec: 12083.2, 300 sec: 11815.9). Total num frames: 90349568. Throughput: 0: 12004.6. Samples: 90332916. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 01:04:42,816][286098] Avg episode reward: [(0, '3990.461')] [2023-03-08 01:04:42,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000176464_90349568.pth... [2023-03-08 01:04:42,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000175776_89997312.pth [2023-03-08 01:04:43,298][286389] Updated weights for policy 0, policy_version 176480 (0.0005) [2023-03-08 01:04:46,942][286389] Updated weights for policy 0, policy_version 176560 (0.0005) [2023-03-08 01:04:47,816][286098] Fps is (10 sec: 11468.9, 60 sec: 12014.9, 300 sec: 11802.0). Total num frames: 90406912. Throughput: 0: 11853.1. Samples: 90400028. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 01:04:47,816][286098] Avg episode reward: [(0, '3918.650')] [2023-03-08 01:04:50,595][286389] Updated weights for policy 0, policy_version 176640 (0.0005) [2023-03-08 01:04:52,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11810.1, 300 sec: 11774.3). Total num frames: 90460160. Throughput: 0: 11766.1. Samples: 90434172. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 01:04:52,816][286098] Avg episode reward: [(0, '3738.725')] [2023-03-08 01:04:54,302][286389] Updated weights for policy 0, policy_version 176720 (0.0005) [2023-03-08 01:04:57,816][286098] Fps is (10 sec: 11059.1, 60 sec: 11741.9, 300 sec: 11774.3). Total num frames: 90517504. Throughput: 0: 11648.1. Samples: 90501092. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 01:04:57,816][286098] Avg episode reward: [(0, '3858.387')] [2023-03-08 01:04:57,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000176792_90517504.pth... [2023-03-08 01:04:57,823][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000176136_90181632.pth [2023-03-08 01:04:57,900][286389] Updated weights for policy 0, policy_version 176800 (0.0005) [2023-03-08 01:05:01,555][286389] Updated weights for policy 0, policy_version 176880 (0.0005) [2023-03-08 01:05:02,816][286098] Fps is (10 sec: 11468.7, 60 sec: 11673.6, 300 sec: 11788.1). Total num frames: 90574848. Throughput: 0: 11467.6. Samples: 90567856. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 01:05:02,816][286098] Avg episode reward: [(0, '3642.272')] [2023-03-08 01:05:05,307][286389] Updated weights for policy 0, policy_version 176960 (0.0005) [2023-03-08 01:05:07,816][286098] Fps is (10 sec: 11468.9, 60 sec: 11605.4, 300 sec: 11788.2). Total num frames: 90632192. Throughput: 0: 11415.6. Samples: 90600896. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 01:05:07,816][286098] Avg episode reward: [(0, '3951.221')] [2023-03-08 01:05:08,869][286389] Updated weights for policy 0, policy_version 177040 (0.0005) [2023-03-08 01:05:12,499][286389] Updated weights for policy 0, policy_version 177120 (0.0005) [2023-03-08 01:05:12,816][286098] Fps is (10 sec: 11059.0, 60 sec: 11468.8, 300 sec: 11774.3). Total num frames: 90685440. Throughput: 0: 11317.1. Samples: 90669120. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 01:05:12,817][286098] Avg episode reward: [(0, '4037.641')] [2023-03-08 01:05:12,851][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000177128_90689536.pth... [2023-03-08 01:05:12,853][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000176464_90349568.pth [2023-03-08 01:05:16,189][286389] Updated weights for policy 0, policy_version 177200 (0.0005) [2023-03-08 01:05:17,816][286098] Fps is (10 sec: 11059.1, 60 sec: 11400.5, 300 sec: 11760.4). Total num frames: 90742784. Throughput: 0: 11234.4. Samples: 90736684. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 01:05:17,816][286098] Avg episode reward: [(0, '3914.514')] [2023-03-08 01:05:19,746][286389] Updated weights for policy 0, policy_version 177280 (0.0005) [2023-03-08 01:05:22,816][286098] Fps is (10 sec: 11469.0, 60 sec: 11332.3, 300 sec: 11746.5). Total num frames: 90800128. Throughput: 0: 11271.8. Samples: 90771464. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 01:05:22,816][286098] Avg episode reward: [(0, '4054.116')] [2023-03-08 01:05:23,295][286389] Updated weights for policy 0, policy_version 177360 (0.0005) [2023-03-08 01:05:26,878][286389] Updated weights for policy 0, policy_version 177440 (0.0005) [2023-03-08 01:05:27,816][286098] Fps is (10 sec: 11468.7, 60 sec: 11332.3, 300 sec: 11732.6). Total num frames: 90857472. Throughput: 0: 11276.7. Samples: 90840368. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 01:05:27,816][286098] Avg episode reward: [(0, '3977.197')] [2023-03-08 01:05:27,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000177456_90857472.pth... [2023-03-08 01:05:27,823][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000176792_90517504.pth [2023-03-08 01:05:30,474][286389] Updated weights for policy 0, policy_version 177520 (0.0005) [2023-03-08 01:05:32,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11332.3, 300 sec: 11732.6). Total num frames: 90918912. Throughput: 0: 11339.2. Samples: 90910292. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 01:05:32,816][286098] Avg episode reward: [(0, '3961.630')] [2023-03-08 01:05:33,777][286389] Updated weights for policy 0, policy_version 177600 (0.0005) [2023-03-08 01:05:37,108][286389] Updated weights for policy 0, policy_version 177680 (0.0005) [2023-03-08 01:05:37,816][286098] Fps is (10 sec: 12288.1, 60 sec: 11468.8, 300 sec: 11732.6). Total num frames: 90980352. Throughput: 0: 11400.4. Samples: 90947188. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 01:05:37,816][286098] Avg episode reward: [(0, '3858.528')] [2023-03-08 01:05:40,405][286389] Updated weights for policy 0, policy_version 177760 (0.0004) [2023-03-08 01:05:42,816][286098] Fps is (10 sec: 12287.9, 60 sec: 11537.1, 300 sec: 11746.5). Total num frames: 91041792. Throughput: 0: 11562.1. Samples: 91021384. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 01:05:42,816][286098] Avg episode reward: [(0, '3929.650')] [2023-03-08 01:05:42,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000177816_91041792.pth... [2023-03-08 01:05:42,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000177128_90689536.pth [2023-03-08 01:05:43,656][286389] Updated weights for policy 0, policy_version 177840 (0.0004) [2023-03-08 01:05:46,905][286389] Updated weights for policy 0, policy_version 177920 (0.0004) [2023-03-08 01:05:47,816][286098] Fps is (10 sec: 12288.1, 60 sec: 11605.3, 300 sec: 11760.4). Total num frames: 91103232. Throughput: 0: 11754.9. Samples: 91096824. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 01:05:47,816][286098] Avg episode reward: [(0, '3959.345')] [2023-03-08 01:05:50,128][286389] Updated weights for policy 0, policy_version 178000 (0.0004) [2023-03-08 01:05:52,816][286098] Fps is (10 sec: 12697.6, 60 sec: 11810.1, 300 sec: 11788.2). Total num frames: 91168768. Throughput: 0: 11878.2. Samples: 91135416. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 01:05:52,824][286098] Avg episode reward: [(0, '3934.269')] [2023-03-08 01:05:53,437][286389] Updated weights for policy 0, policy_version 178080 (0.0005) [2023-03-08 01:05:56,695][286389] Updated weights for policy 0, policy_version 178160 (0.0004) [2023-03-08 01:05:57,816][286098] Fps is (10 sec: 12697.4, 60 sec: 11878.4, 300 sec: 11802.0). Total num frames: 91230208. Throughput: 0: 12015.0. Samples: 91209792. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 01:05:57,816][286098] Avg episode reward: [(0, '3541.151')] [2023-03-08 01:05:57,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000178184_91230208.pth... [2023-03-08 01:05:57,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000177456_90857472.pth [2023-03-08 01:05:59,962][286389] Updated weights for policy 0, policy_version 178240 (0.0004) [2023-03-08 01:06:02,816][286098] Fps is (10 sec: 12288.0, 60 sec: 11946.7, 300 sec: 11815.9). Total num frames: 91291648. Throughput: 0: 12199.1. Samples: 91285644. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 01:06:02,816][286098] Avg episode reward: [(0, '3595.153')] [2023-03-08 01:06:03,185][286389] Updated weights for policy 0, policy_version 178320 (0.0004) [2023-03-08 01:06:06,465][286389] Updated weights for policy 0, policy_version 178400 (0.0004) [2023-03-08 01:06:07,816][286098] Fps is (10 sec: 12288.1, 60 sec: 12014.9, 300 sec: 11829.8). Total num frames: 91353088. Throughput: 0: 12264.4. Samples: 91323364. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 01:06:07,816][286098] Avg episode reward: [(0, '3724.214')] [2023-03-08 01:06:09,780][286389] Updated weights for policy 0, policy_version 178480 (0.0005) [2023-03-08 01:06:12,816][286098] Fps is (10 sec: 12697.6, 60 sec: 12219.8, 300 sec: 11843.7). Total num frames: 91418624. Throughput: 0: 12394.7. Samples: 91398128. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 01:06:12,816][286098] Avg episode reward: [(0, '3653.042')] [2023-03-08 01:06:12,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000178552_91418624.pth... [2023-03-08 01:06:12,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000177816_91041792.pth [2023-03-08 01:06:13,062][286389] Updated weights for policy 0, policy_version 178560 (0.0004) [2023-03-08 01:06:16,302][286389] Updated weights for policy 0, policy_version 178640 (0.0004) [2023-03-08 01:06:17,816][286098] Fps is (10 sec: 12697.6, 60 sec: 12288.0, 300 sec: 11843.7). Total num frames: 91480064. Throughput: 0: 12485.1. Samples: 91472124. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 01:06:17,816][286098] Avg episode reward: [(0, '3873.440')] [2023-03-08 01:06:19,650][286389] Updated weights for policy 0, policy_version 178720 (0.0005) [2023-03-08 01:06:22,816][286098] Fps is (10 sec: 12288.0, 60 sec: 12356.3, 300 sec: 11843.7). Total num frames: 91541504. Throughput: 0: 12499.9. Samples: 91509684. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 01:06:22,816][286098] Avg episode reward: [(0, '3828.021')] [2023-03-08 01:06:22,863][286389] Updated weights for policy 0, policy_version 178800 (0.0004) [2023-03-08 01:06:26,263][286389] Updated weights for policy 0, policy_version 178880 (0.0004) [2023-03-08 01:06:27,816][286098] Fps is (10 sec: 12288.0, 60 sec: 12424.5, 300 sec: 11857.6). Total num frames: 91602944. Throughput: 0: 12510.1. Samples: 91584340. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 01:06:27,816][286098] Avg episode reward: [(0, '3937.030')] [2023-03-08 01:06:27,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000178912_91602944.pth... [2023-03-08 01:06:27,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000178184_91230208.pth [2023-03-08 01:06:29,891][286389] Updated weights for policy 0, policy_version 178960 (0.0005) [2023-03-08 01:06:32,816][286098] Fps is (10 sec: 11878.3, 60 sec: 12356.2, 300 sec: 11857.6). Total num frames: 91660288. Throughput: 0: 12340.9. Samples: 91652168. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 01:06:32,827][286098] Avg episode reward: [(0, '4093.585')] [2023-03-08 01:06:33,507][286389] Updated weights for policy 0, policy_version 179040 (0.0005) [2023-03-08 01:06:37,088][286389] Updated weights for policy 0, policy_version 179120 (0.0005) [2023-03-08 01:06:37,816][286098] Fps is (10 sec: 11468.7, 60 sec: 12288.0, 300 sec: 11857.6). Total num frames: 91717632. Throughput: 0: 12239.1. Samples: 91686176. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 01:06:37,827][286098] Avg episode reward: [(0, '4188.282')] [2023-03-08 01:06:40,541][286389] Updated weights for policy 0, policy_version 179200 (0.0005) [2023-03-08 01:06:42,816][286098] Fps is (10 sec: 11468.9, 60 sec: 12219.7, 300 sec: 11871.5). Total num frames: 91774976. Throughput: 0: 12150.3. Samples: 91756556. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 01:06:42,827][286098] Avg episode reward: [(0, '4218.067')] [2023-03-08 01:06:42,871][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000179256_91779072.pth... [2023-03-08 01:06:42,874][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000178552_91418624.pth [2023-03-08 01:06:43,818][286389] Updated weights for policy 0, policy_version 179280 (0.0003) [2023-03-08 01:06:47,154][286389] Updated weights for policy 0, policy_version 179360 (0.0003) [2023-03-08 01:06:47,816][286098] Fps is (10 sec: 11878.5, 60 sec: 12219.7, 300 sec: 11885.3). Total num frames: 91836416. Throughput: 0: 12125.0. Samples: 91831268. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 01:06:47,827][286098] Avg episode reward: [(0, '4264.802')] [2023-03-08 01:06:50,637][286389] Updated weights for policy 0, policy_version 179440 (0.0005) [2023-03-08 01:06:52,816][286098] Fps is (10 sec: 12288.1, 60 sec: 12151.5, 300 sec: 11885.3). Total num frames: 91897856. Throughput: 0: 12085.2. Samples: 91867196. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 01:06:52,827][286098] Avg episode reward: [(0, '4213.889')] [2023-03-08 01:06:54,169][286389] Updated weights for policy 0, policy_version 179520 (0.0005) [2023-03-08 01:06:57,713][286389] Updated weights for policy 0, policy_version 179600 (0.0005) [2023-03-08 01:06:57,816][286098] Fps is (10 sec: 11878.4, 60 sec: 12083.2, 300 sec: 11885.3). Total num frames: 91955200. Throughput: 0: 11940.0. Samples: 91935428. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 01:06:57,827][286098] Avg episode reward: [(0, '4233.949')] [2023-03-08 01:06:57,830][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000179600_91955200.pth... [2023-03-08 01:06:57,832][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000178912_91602944.pth [2023-03-08 01:07:01,168][286389] Updated weights for policy 0, policy_version 179680 (0.0003) [2023-03-08 01:07:02,816][286098] Fps is (10 sec: 11468.8, 60 sec: 12014.9, 300 sec: 11871.5). Total num frames: 92012544. Throughput: 0: 11892.5. Samples: 92007284. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 01:07:02,827][286098] Avg episode reward: [(0, '4271.496')] [2023-03-08 01:07:04,616][286389] Updated weights for policy 0, policy_version 179760 (0.0003) [2023-03-08 01:07:07,816][286098] Fps is (10 sec: 11878.5, 60 sec: 12014.9, 300 sec: 11885.3). Total num frames: 92073984. Throughput: 0: 11844.4. Samples: 92042680. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 01:07:07,827][286098] Avg episode reward: [(0, '4220.166')] [2023-03-08 01:07:07,979][286389] Updated weights for policy 0, policy_version 179840 (0.0003) [2023-03-08 01:07:11,232][286389] Updated weights for policy 0, policy_version 179920 (0.0003) [2023-03-08 01:07:12,816][286098] Fps is (10 sec: 12287.9, 60 sec: 11946.7, 300 sec: 11899.2). Total num frames: 92135424. Throughput: 0: 11841.7. Samples: 92117216. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 01:07:12,827][286098] Avg episode reward: [(0, '4240.395')] [2023-03-08 01:07:12,830][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000179952_92135424.pth... [2023-03-08 01:07:12,833][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000179256_91779072.pth [2023-03-08 01:07:14,580][286389] Updated weights for policy 0, policy_version 180000 (0.0003) [2023-03-08 01:07:17,816][286098] Fps is (10 sec: 12288.0, 60 sec: 11946.7, 300 sec: 11927.0). Total num frames: 92196864. Throughput: 0: 11942.7. Samples: 92189588. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 01:07:17,827][286098] Avg episode reward: [(0, '4261.963')] [2023-03-08 01:07:17,965][286389] Updated weights for policy 0, policy_version 180080 (0.0003) [2023-03-08 01:07:21,281][286389] Updated weights for policy 0, policy_version 180160 (0.0003) [2023-03-08 01:07:22,816][286098] Fps is (10 sec: 12288.0, 60 sec: 11946.7, 300 sec: 11940.9). Total num frames: 92258304. Throughput: 0: 12025.7. Samples: 92227332. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 01:07:22,827][286098] Avg episode reward: [(0, '4252.841')] [2023-03-08 01:07:24,549][286389] Updated weights for policy 0, policy_version 180240 (0.0003) [2023-03-08 01:07:27,816][286098] Fps is (10 sec: 12288.0, 60 sec: 11946.7, 300 sec: 11940.9). Total num frames: 92319744. Throughput: 0: 12093.1. Samples: 92300744. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 01:07:27,827][286098] Avg episode reward: [(0, '4215.799')] [2023-03-08 01:07:27,830][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000180312_92319744.pth... [2023-03-08 01:07:27,832][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000179600_91955200.pth [2023-03-08 01:07:27,897][286389] Updated weights for policy 0, policy_version 180320 (0.0003) [2023-03-08 01:07:31,309][286389] Updated weights for policy 0, policy_version 180400 (0.0003) [2023-03-08 01:07:32,816][286098] Fps is (10 sec: 12288.1, 60 sec: 12015.0, 300 sec: 11940.9). Total num frames: 92381184. Throughput: 0: 12070.3. Samples: 92374432. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 01:07:32,816][286098] Avg episode reward: [(0, '4129.011')] [2023-03-08 01:07:34,490][286389] Updated weights for policy 0, policy_version 180480 (0.0003) [2023-03-08 01:07:37,787][286389] Updated weights for policy 0, policy_version 180560 (0.0003) [2023-03-08 01:07:37,816][286098] Fps is (10 sec: 12697.6, 60 sec: 12151.5, 300 sec: 11968.7). Total num frames: 92446720. Throughput: 0: 12131.8. Samples: 92413128. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 01:07:37,816][286098] Avg episode reward: [(0, '4193.660')] [2023-03-08 01:07:41,102][286389] Updated weights for policy 0, policy_version 180640 (0.0003) [2023-03-08 01:07:42,816][286098] Fps is (10 sec: 12697.5, 60 sec: 12219.7, 300 sec: 11968.6). Total num frames: 92508160. Throughput: 0: 12266.8. Samples: 92487432. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 01:07:42,816][286098] Avg episode reward: [(0, '4170.280')] [2023-03-08 01:07:42,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000180680_92508160.pth... [2023-03-08 01:07:42,823][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000179952_92135424.pth [2023-03-08 01:07:44,502][286389] Updated weights for policy 0, policy_version 180720 (0.0003) [2023-03-08 01:07:47,816][286098] Fps is (10 sec: 11878.4, 60 sec: 12151.5, 300 sec: 11968.7). Total num frames: 92565504. Throughput: 0: 12271.1. Samples: 92559484. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 01:07:47,816][286098] Avg episode reward: [(0, '4349.630')] [2023-03-08 01:07:47,840][286389] Updated weights for policy 0, policy_version 180800 (0.0003) [2023-03-08 01:07:51,139][286389] Updated weights for policy 0, policy_version 180880 (0.0003) [2023-03-08 01:07:52,816][286098] Fps is (10 sec: 11878.5, 60 sec: 12151.5, 300 sec: 11982.5). Total num frames: 92626944. Throughput: 0: 12326.5. Samples: 92597372. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 01:07:52,816][286098] Avg episode reward: [(0, '4342.471')] [2023-03-08 01:07:54,578][286389] Updated weights for policy 0, policy_version 180960 (0.0003) [2023-03-08 01:07:57,816][286098] Fps is (10 sec: 12288.0, 60 sec: 12219.7, 300 sec: 11996.4). Total num frames: 92688384. Throughput: 0: 12296.4. Samples: 92670552. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 01:07:57,816][286098] Avg episode reward: [(0, '4353.964')] [2023-03-08 01:07:57,818][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000181032_92688384.pth... [2023-03-08 01:07:57,820][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000180312_92319744.pth [2023-03-08 01:07:57,893][286389] Updated weights for policy 0, policy_version 181040 (0.0003) [2023-03-08 01:08:01,324][286389] Updated weights for policy 0, policy_version 181120 (0.0003) [2023-03-08 01:08:02,816][286098] Fps is (10 sec: 12288.0, 60 sec: 12288.0, 300 sec: 11996.4). Total num frames: 92749824. Throughput: 0: 12275.6. Samples: 92741988. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 01:08:02,816][286098] Avg episode reward: [(0, '4376.390')] [2023-03-08 01:08:04,712][286389] Updated weights for policy 0, policy_version 181200 (0.0003) [2023-03-08 01:08:07,816][286098] Fps is (10 sec: 12288.0, 60 sec: 12288.0, 300 sec: 12010.3). Total num frames: 92811264. Throughput: 0: 12249.5. Samples: 92778560. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 01:08:07,816][286098] Avg episode reward: [(0, '4408.932')] [2023-03-08 01:08:08,014][286389] Updated weights for policy 0, policy_version 181280 (0.0003) [2023-03-08 01:08:11,333][286389] Updated weights for policy 0, policy_version 181360 (0.0005) [2023-03-08 01:08:12,816][286098] Fps is (10 sec: 12287.9, 60 sec: 12288.0, 300 sec: 12010.3). Total num frames: 92872704. Throughput: 0: 12267.6. Samples: 92852788. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 01:08:12,816][286098] Avg episode reward: [(0, '4422.919')] [2023-03-08 01:08:12,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000181392_92872704.pth... [2023-03-08 01:08:12,821][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000180680_92508160.pth [2023-03-08 01:08:14,631][286389] Updated weights for policy 0, policy_version 181440 (0.0004) [2023-03-08 01:08:17,816][286098] Fps is (10 sec: 12288.0, 60 sec: 12288.0, 300 sec: 12010.3). Total num frames: 92934144. Throughput: 0: 12276.3. Samples: 92926864. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 01:08:17,816][286098] Avg episode reward: [(0, '4414.768')] [2023-03-08 01:08:17,956][286389] Updated weights for policy 0, policy_version 181520 (0.0003) [2023-03-08 01:08:21,423][286389] Updated weights for policy 0, policy_version 181600 (0.0003) [2023-03-08 01:08:22,816][286098] Fps is (10 sec: 12288.1, 60 sec: 12288.0, 300 sec: 12024.2). Total num frames: 92995584. Throughput: 0: 12216.9. Samples: 92962888. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 01:08:22,816][286098] Avg episode reward: [(0, '4430.936')] [2023-03-08 01:08:24,706][286389] Updated weights for policy 0, policy_version 181680 (0.0004) [2023-03-08 01:08:27,816][286098] Fps is (10 sec: 12288.0, 60 sec: 12288.0, 300 sec: 12038.1). Total num frames: 93057024. Throughput: 0: 12205.8. Samples: 93036692. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 01:08:27,816][286098] Avg episode reward: [(0, '4435.766')] [2023-03-08 01:08:27,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000181752_93057024.pth... [2023-03-08 01:08:27,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000181032_92688384.pth [2023-03-08 01:08:28,042][286389] Updated weights for policy 0, policy_version 181760 (0.0005) [2023-03-08 01:08:31,307][286389] Updated weights for policy 0, policy_version 181840 (0.0004) [2023-03-08 01:08:32,816][286098] Fps is (10 sec: 12288.1, 60 sec: 12288.0, 300 sec: 12052.0). Total num frames: 93118464. Throughput: 0: 12269.2. Samples: 93111600. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 01:08:32,816][286098] Avg episode reward: [(0, '4429.678')] [2023-03-08 01:08:34,576][286389] Updated weights for policy 0, policy_version 181920 (0.0004) [2023-03-08 01:08:37,816][286098] Fps is (10 sec: 12288.1, 60 sec: 12219.7, 300 sec: 12052.0). Total num frames: 93179904. Throughput: 0: 12251.2. Samples: 93148676. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 01:08:37,816][286098] Avg episode reward: [(0, '4446.222')] [2023-03-08 01:08:37,856][286389] Updated weights for policy 0, policy_version 182000 (0.0005) [2023-03-08 01:08:41,255][286389] Updated weights for policy 0, policy_version 182080 (0.0005) [2023-03-08 01:08:42,816][286098] Fps is (10 sec: 12287.9, 60 sec: 12219.7, 300 sec: 12052.0). Total num frames: 93241344. Throughput: 0: 12269.5. Samples: 93222680. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 01:08:42,816][286098] Avg episode reward: [(0, '4445.012')] [2023-03-08 01:08:42,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000182112_93241344.pth... [2023-03-08 01:08:42,823][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000181392_92872704.pth [2023-03-08 01:08:44,624][286389] Updated weights for policy 0, policy_version 182160 (0.0005) [2023-03-08 01:08:47,816][286098] Fps is (10 sec: 12288.0, 60 sec: 12288.0, 300 sec: 12038.1). Total num frames: 93302784. Throughput: 0: 12303.8. Samples: 93295660. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 01:08:47,816][286098] Avg episode reward: [(0, '4461.527')] [2023-03-08 01:08:47,988][286389] Updated weights for policy 0, policy_version 182240 (0.0004) [2023-03-08 01:08:51,302][286389] Updated weights for policy 0, policy_version 182320 (0.0004) [2023-03-08 01:08:52,816][286098] Fps is (10 sec: 12288.1, 60 sec: 12288.0, 300 sec: 12038.1). Total num frames: 93364224. Throughput: 0: 12311.5. Samples: 93332576. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 01:08:52,816][286098] Avg episode reward: [(0, '4398.310')] [2023-03-08 01:08:54,706][286389] Updated weights for policy 0, policy_version 182400 (0.0004) [2023-03-08 01:08:57,816][286098] Fps is (10 sec: 11878.3, 60 sec: 12219.7, 300 sec: 12024.2). Total num frames: 93421568. Throughput: 0: 12265.6. Samples: 93404740. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 01:08:57,817][286098] Avg episode reward: [(0, '4301.941')] [2023-03-08 01:08:57,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000182464_93421568.pth... [2023-03-08 01:08:57,823][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000181752_93057024.pth [2023-03-08 01:08:58,290][286389] Updated weights for policy 0, policy_version 182480 (0.0005) [2023-03-08 01:09:01,899][286389] Updated weights for policy 0, policy_version 182560 (0.0005) [2023-03-08 01:09:02,816][286098] Fps is (10 sec: 11468.7, 60 sec: 12151.5, 300 sec: 12010.3). Total num frames: 93478912. Throughput: 0: 12126.0. Samples: 93472536. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 01:09:02,816][286098] Avg episode reward: [(0, '4382.894')] [2023-03-08 01:09:05,540][286389] Updated weights for policy 0, policy_version 182640 (0.0005) [2023-03-08 01:09:07,816][286098] Fps is (10 sec: 11468.9, 60 sec: 12083.2, 300 sec: 11996.4). Total num frames: 93536256. Throughput: 0: 12080.4. Samples: 93506504. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 01:09:07,816][286098] Avg episode reward: [(0, '4429.205')] [2023-03-08 01:09:09,172][286389] Updated weights for policy 0, policy_version 182720 (0.0005) [2023-03-08 01:09:12,766][286389] Updated weights for policy 0, policy_version 182800 (0.0005) [2023-03-08 01:09:12,816][286098] Fps is (10 sec: 11468.8, 60 sec: 12014.9, 300 sec: 11982.5). Total num frames: 93593600. Throughput: 0: 11941.2. Samples: 93574048. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 01:09:12,816][286098] Avg episode reward: [(0, '4305.146')] [2023-03-08 01:09:12,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000182800_93593600.pth... [2023-03-08 01:09:12,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000182112_93241344.pth [2023-03-08 01:09:16,402][286389] Updated weights for policy 0, policy_version 182880 (0.0005) [2023-03-08 01:09:17,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11878.4, 300 sec: 11954.8). Total num frames: 93646848. Throughput: 0: 11795.9. Samples: 93642416. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 01:09:17,816][286098] Avg episode reward: [(0, '4301.662')] [2023-03-08 01:09:19,995][286389] Updated weights for policy 0, policy_version 182960 (0.0005) [2023-03-08 01:09:22,816][286098] Fps is (10 sec: 11059.3, 60 sec: 11810.1, 300 sec: 11954.8). Total num frames: 93704192. Throughput: 0: 11719.6. Samples: 93676056. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 01:09:22,816][286098] Avg episode reward: [(0, '4164.489')] [2023-03-08 01:09:23,632][286389] Updated weights for policy 0, policy_version 183040 (0.0005) [2023-03-08 01:09:27,284][286389] Updated weights for policy 0, policy_version 183120 (0.0005) [2023-03-08 01:09:27,816][286098] Fps is (10 sec: 11468.7, 60 sec: 11741.9, 300 sec: 11940.9). Total num frames: 93761536. Throughput: 0: 11595.5. Samples: 93744476. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 01:09:27,816][286098] Avg episode reward: [(0, '4122.030')] [2023-03-08 01:09:27,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000183128_93761536.pth... [2023-03-08 01:09:27,823][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000182464_93421568.pth [2023-03-08 01:09:30,867][286389] Updated weights for policy 0, policy_version 183200 (0.0005) [2023-03-08 01:09:32,816][286098] Fps is (10 sec: 11468.7, 60 sec: 11673.6, 300 sec: 11954.8). Total num frames: 93818880. Throughput: 0: 11469.2. Samples: 93811776. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 01:09:32,816][286098] Avg episode reward: [(0, '4112.230')] [2023-03-08 01:09:34,428][286389] Updated weights for policy 0, policy_version 183280 (0.0005) [2023-03-08 01:09:37,802][286389] Updated weights for policy 0, policy_version 183360 (0.0003) [2023-03-08 01:09:37,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11673.6, 300 sec: 11968.6). Total num frames: 93880320. Throughput: 0: 11444.3. Samples: 93847572. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 01:09:37,816][286098] Avg episode reward: [(0, '4216.315')] [2023-03-08 01:09:41,397][286389] Updated weights for policy 0, policy_version 183440 (0.0005) [2023-03-08 01:09:42,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11537.1, 300 sec: 11954.8). Total num frames: 93933568. Throughput: 0: 11389.3. Samples: 93917256. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 01:09:42,816][286098] Avg episode reward: [(0, '4303.444')] [2023-03-08 01:09:42,832][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000183472_93937664.pth... [2023-03-08 01:09:42,834][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000182800_93593600.pth [2023-03-08 01:09:45,031][286389] Updated weights for policy 0, policy_version 183520 (0.0005) [2023-03-08 01:09:47,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11468.8, 300 sec: 11968.7). Total num frames: 93990912. Throughput: 0: 11402.7. Samples: 93985656. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 01:09:47,816][286098] Avg episode reward: [(0, '4231.214')] [2023-03-08 01:09:48,638][286389] Updated weights for policy 0, policy_version 183600 (0.0005) [2023-03-08 01:09:52,310][286389] Updated weights for policy 0, policy_version 183680 (0.0005) [2023-03-08 01:09:52,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11400.5, 300 sec: 11968.7). Total num frames: 94048256. Throughput: 0: 11402.0. Samples: 94019596. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 01:09:52,816][286098] Avg episode reward: [(0, '4357.610')] [2023-03-08 01:09:55,804][286389] Updated weights for policy 0, policy_version 183760 (0.0005) [2023-03-08 01:09:57,816][286098] Fps is (10 sec: 11468.7, 60 sec: 11400.5, 300 sec: 11968.6). Total num frames: 94105600. Throughput: 0: 11431.1. Samples: 94088448. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 01:09:57,816][286098] Avg episode reward: [(0, '4411.702')] [2023-03-08 01:09:57,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000183800_94105600.pth... [2023-03-08 01:09:57,823][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000183128_93761536.pth [2023-03-08 01:09:59,468][286389] Updated weights for policy 0, policy_version 183840 (0.0005) [2023-03-08 01:10:02,816][286098] Fps is (10 sec: 11059.3, 60 sec: 11332.3, 300 sec: 11954.8). Total num frames: 94158848. Throughput: 0: 11385.2. Samples: 94154752. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 01:10:02,816][286098] Avg episode reward: [(0, '4472.989')] [2023-03-08 01:10:03,203][286389] Updated weights for policy 0, policy_version 183920 (0.0005) [2023-03-08 01:10:06,836][286389] Updated weights for policy 0, policy_version 184000 (0.0005) [2023-03-08 01:10:07,816][286098] Fps is (10 sec: 11059.3, 60 sec: 11332.3, 300 sec: 11968.7). Total num frames: 94216192. Throughput: 0: 11367.3. Samples: 94187584. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 01:10:07,816][286098] Avg episode reward: [(0, '4249.023')] [2023-03-08 01:10:10,494][286389] Updated weights for policy 0, policy_version 184080 (0.0005) [2023-03-08 01:10:12,816][286098] Fps is (10 sec: 11468.7, 60 sec: 11332.3, 300 sec: 11968.7). Total num frames: 94273536. Throughput: 0: 11361.3. Samples: 94255732. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 01:10:12,816][286098] Avg episode reward: [(0, '4284.704')] [2023-03-08 01:10:12,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000184128_94273536.pth... [2023-03-08 01:10:12,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000183472_93937664.pth [2023-03-08 01:10:13,961][286389] Updated weights for policy 0, policy_version 184160 (0.0005) [2023-03-08 01:10:17,310][286389] Updated weights for policy 0, policy_version 184240 (0.0005) [2023-03-08 01:10:17,816][286098] Fps is (10 sec: 11878.4, 60 sec: 11468.8, 300 sec: 11982.5). Total num frames: 94334976. Throughput: 0: 11465.6. Samples: 94327728. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 01:10:17,816][286098] Avg episode reward: [(0, '4284.635')] [2023-03-08 01:10:20,653][286389] Updated weights for policy 0, policy_version 184320 (0.0004) [2023-03-08 01:10:22,816][286098] Fps is (10 sec: 12288.1, 60 sec: 11537.1, 300 sec: 11996.4). Total num frames: 94396416. Throughput: 0: 11484.7. Samples: 94364384. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 01:10:22,816][286098] Avg episode reward: [(0, '4396.089')] [2023-03-08 01:10:23,853][286389] Updated weights for policy 0, policy_version 184400 (0.0004) [2023-03-08 01:10:27,275][286389] Updated weights for policy 0, policy_version 184480 (0.0005) [2023-03-08 01:10:27,816][286098] Fps is (10 sec: 12287.9, 60 sec: 11605.3, 300 sec: 11996.4). Total num frames: 94457856. Throughput: 0: 11593.9. Samples: 94438984. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 01:10:27,816][286098] Avg episode reward: [(0, '4389.719')] [2023-03-08 01:10:27,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000184488_94457856.pth... [2023-03-08 01:10:27,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000183800_94105600.pth [2023-03-08 01:10:30,745][286389] Updated weights for policy 0, policy_version 184560 (0.0004) [2023-03-08 01:10:32,816][286098] Fps is (10 sec: 12287.9, 60 sec: 11673.6, 300 sec: 11996.4). Total num frames: 94519296. Throughput: 0: 11678.2. Samples: 94511176. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 01:10:32,816][286098] Avg episode reward: [(0, '4436.544')] [2023-03-08 01:10:34,076][286389] Updated weights for policy 0, policy_version 184640 (0.0003) [2023-03-08 01:10:37,414][286389] Updated weights for policy 0, policy_version 184720 (0.0003) [2023-03-08 01:10:37,816][286098] Fps is (10 sec: 12288.1, 60 sec: 11673.6, 300 sec: 11996.4). Total num frames: 94580736. Throughput: 0: 11736.3. Samples: 94547728. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 01:10:37,816][286098] Avg episode reward: [(0, '4451.046')] [2023-03-08 01:10:40,782][286389] Updated weights for policy 0, policy_version 184800 (0.0003) [2023-03-08 01:10:42,816][286098] Fps is (10 sec: 12287.9, 60 sec: 11810.1, 300 sec: 11996.4). Total num frames: 94642176. Throughput: 0: 11840.7. Samples: 94621280. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 01:10:42,816][286098] Avg episode reward: [(0, '4472.959')] [2023-03-08 01:10:42,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000184848_94642176.pth... [2023-03-08 01:10:42,821][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000184128_94273536.pth [2023-03-08 01:10:44,052][286389] Updated weights for policy 0, policy_version 184880 (0.0003) [2023-03-08 01:10:47,421][286389] Updated weights for policy 0, policy_version 184960 (0.0003) [2023-03-08 01:10:47,816][286098] Fps is (10 sec: 12288.0, 60 sec: 11878.4, 300 sec: 11982.5). Total num frames: 94703616. Throughput: 0: 12014.9. Samples: 94695424. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 01:10:47,816][286098] Avg episode reward: [(0, '4472.915')] [2023-03-08 01:10:50,812][286389] Updated weights for policy 0, policy_version 185040 (0.0003) [2023-03-08 01:10:52,816][286098] Fps is (10 sec: 11878.5, 60 sec: 11878.4, 300 sec: 11968.7). Total num frames: 94760960. Throughput: 0: 12088.7. Samples: 94731576. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 01:10:52,827][286098] Avg episode reward: [(0, '4431.177')] [2023-03-08 01:10:54,159][286389] Updated weights for policy 0, policy_version 185120 (0.0003) [2023-03-08 01:10:57,466][286389] Updated weights for policy 0, policy_version 185200 (0.0003) [2023-03-08 01:10:57,816][286098] Fps is (10 sec: 12287.9, 60 sec: 12014.9, 300 sec: 11982.5). Total num frames: 94826496. Throughput: 0: 12198.7. Samples: 94804672. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 01:10:57,816][286098] Avg episode reward: [(0, '4461.443')] [2023-03-08 01:10:57,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000185208_94826496.pth... [2023-03-08 01:10:57,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000184488_94457856.pth [2023-03-08 01:11:00,750][286389] Updated weights for policy 0, policy_version 185280 (0.0003) [2023-03-08 01:11:02,816][286098] Fps is (10 sec: 12697.6, 60 sec: 12151.5, 300 sec: 11982.5). Total num frames: 94887936. Throughput: 0: 12267.0. Samples: 94879744. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-08 01:11:02,816][286098] Avg episode reward: [(0, '4367.457')] [2023-03-08 01:11:04,068][286389] Updated weights for policy 0, policy_version 185360 (0.0003) [2023-03-08 01:11:07,422][286389] Updated weights for policy 0, policy_version 185440 (0.0004) [2023-03-08 01:11:07,816][286098] Fps is (10 sec: 12288.1, 60 sec: 12219.7, 300 sec: 11968.7). Total num frames: 94949376. Throughput: 0: 12273.0. Samples: 94916672. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 01:11:07,816][286098] Avg episode reward: [(0, '4381.309')] [2023-03-08 01:11:10,783][286389] Updated weights for policy 0, policy_version 185520 (0.0004) [2023-03-08 01:11:12,816][286098] Fps is (10 sec: 11878.3, 60 sec: 12219.7, 300 sec: 11954.8). Total num frames: 95006720. Throughput: 0: 12242.1. Samples: 94989880. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 01:11:12,816][286098] Avg episode reward: [(0, '4361.832')] [2023-03-08 01:11:12,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000185560_95006720.pth... [2023-03-08 01:11:12,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000184848_94642176.pth [2023-03-08 01:11:14,471][286389] Updated weights for policy 0, policy_version 185600 (0.0005) [2023-03-08 01:11:17,816][286098] Fps is (10 sec: 11468.8, 60 sec: 12151.5, 300 sec: 11940.9). Total num frames: 95064064. Throughput: 0: 12105.8. Samples: 95055936. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 01:11:17,816][286098] Avg episode reward: [(0, '4450.369')] [2023-03-08 01:11:18,131][286389] Updated weights for policy 0, policy_version 185680 (0.0005) [2023-03-08 01:11:21,712][286389] Updated weights for policy 0, policy_version 185760 (0.0005) [2023-03-08 01:11:22,816][286098] Fps is (10 sec: 11468.8, 60 sec: 12083.2, 300 sec: 11927.0). Total num frames: 95121408. Throughput: 0: 12054.8. Samples: 95090196. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 01:11:22,816][286098] Avg episode reward: [(0, '4499.962')] [2023-03-08 01:11:25,274][286389] Updated weights for policy 0, policy_version 185840 (0.0005) [2023-03-08 01:11:27,816][286098] Fps is (10 sec: 11468.7, 60 sec: 12014.9, 300 sec: 11927.0). Total num frames: 95178752. Throughput: 0: 11938.2. Samples: 95158500. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 01:11:27,817][286098] Avg episode reward: [(0, '4435.731')] [2023-03-08 01:11:27,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000185896_95178752.pth... [2023-03-08 01:11:27,821][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000185208_94826496.pth [2023-03-08 01:11:28,902][286389] Updated weights for policy 0, policy_version 185920 (0.0005) [2023-03-08 01:11:32,506][286389] Updated weights for policy 0, policy_version 186000 (0.0005) [2023-03-08 01:11:32,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11878.4, 300 sec: 11913.1). Total num frames: 95232000. Throughput: 0: 11824.3. Samples: 95227516. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 01:11:32,816][286098] Avg episode reward: [(0, '4411.695')] [2023-03-08 01:11:36,144][286389] Updated weights for policy 0, policy_version 186080 (0.0005) [2023-03-08 01:11:37,816][286098] Fps is (10 sec: 11059.3, 60 sec: 11810.1, 300 sec: 11913.1). Total num frames: 95289344. Throughput: 0: 11759.1. Samples: 95260736. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 01:11:37,816][286098] Avg episode reward: [(0, '4425.313')] [2023-03-08 01:11:39,806][286389] Updated weights for policy 0, policy_version 186160 (0.0005) [2023-03-08 01:11:42,816][286098] Fps is (10 sec: 11468.7, 60 sec: 11741.9, 300 sec: 11899.2). Total num frames: 95346688. Throughput: 0: 11639.0. Samples: 95328428. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 01:11:42,817][286098] Avg episode reward: [(0, '4296.612')] [2023-03-08 01:11:42,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000186224_95346688.pth... [2023-03-08 01:11:42,823][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000185560_95006720.pth [2023-03-08 01:11:43,356][286389] Updated weights for policy 0, policy_version 186240 (0.0005) [2023-03-08 01:11:46,944][286389] Updated weights for policy 0, policy_version 186320 (0.0005) [2023-03-08 01:11:47,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11673.6, 300 sec: 11885.3). Total num frames: 95404032. Throughput: 0: 11499.1. Samples: 95397204. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 01:11:47,816][286098] Avg episode reward: [(0, '4521.089')] [2023-03-08 01:11:50,495][286389] Updated weights for policy 0, policy_version 186400 (0.0005) [2023-03-08 01:11:52,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11673.6, 300 sec: 11885.3). Total num frames: 95461376. Throughput: 0: 11461.5. Samples: 95432440. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 01:11:52,816][286098] Avg episode reward: [(0, '4267.940')] [2023-03-08 01:11:54,132][286389] Updated weights for policy 0, policy_version 186480 (0.0005) [2023-03-08 01:11:57,724][286389] Updated weights for policy 0, policy_version 186560 (0.0005) [2023-03-08 01:11:57,816][286098] Fps is (10 sec: 11468.7, 60 sec: 11537.1, 300 sec: 11885.3). Total num frames: 95518720. Throughput: 0: 11326.7. Samples: 95499580. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 01:11:57,817][286098] Avg episode reward: [(0, '4448.945')] [2023-03-08 01:11:57,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000186560_95518720.pth... [2023-03-08 01:11:57,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000185896_95178752.pth [2023-03-08 01:12:01,479][286389] Updated weights for policy 0, policy_version 186640 (0.0005) [2023-03-08 01:12:02,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11400.5, 300 sec: 11857.6). Total num frames: 95571968. Throughput: 0: 11347.2. Samples: 95566560. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 01:12:02,816][286098] Avg episode reward: [(0, '4469.796')] [2023-03-08 01:12:05,097][286389] Updated weights for policy 0, policy_version 186720 (0.0005) [2023-03-08 01:12:07,816][286098] Fps is (10 sec: 11059.3, 60 sec: 11332.3, 300 sec: 11843.7). Total num frames: 95629312. Throughput: 0: 11343.2. Samples: 95600640. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-08 01:12:07,816][286098] Avg episode reward: [(0, '4518.780')] [2023-03-08 01:12:08,706][286389] Updated weights for policy 0, policy_version 186800 (0.0005) [2023-03-08 01:12:12,166][286389] Updated weights for policy 0, policy_version 186880 (0.0005) [2023-03-08 01:12:12,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11332.3, 300 sec: 11829.8). Total num frames: 95686656. Throughput: 0: 11346.5. Samples: 95669092. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 01:12:12,816][286098] Avg episode reward: [(0, '4520.578')] [2023-03-08 01:12:12,836][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000186896_95690752.pth... [2023-03-08 01:12:12,837][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000186224_95346688.pth [2023-03-08 01:12:15,745][286389] Updated weights for policy 0, policy_version 186960 (0.0005) [2023-03-08 01:12:17,816][286098] Fps is (10 sec: 11468.9, 60 sec: 11332.3, 300 sec: 11815.9). Total num frames: 95744000. Throughput: 0: 11357.7. Samples: 95738612. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 01:12:17,816][286098] Avg episode reward: [(0, '4517.888')] [2023-03-08 01:12:19,412][286389] Updated weights for policy 0, policy_version 187040 (0.0005) [2023-03-08 01:12:22,816][286098] Fps is (10 sec: 11468.9, 60 sec: 11332.3, 300 sec: 11802.0). Total num frames: 95801344. Throughput: 0: 11375.2. Samples: 95772620. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 01:12:22,816][286098] Avg episode reward: [(0, '4457.591')] [2023-03-08 01:12:22,848][286389] Updated weights for policy 0, policy_version 187120 (0.0005) [2023-03-08 01:12:26,090][286389] Updated weights for policy 0, policy_version 187200 (0.0004) [2023-03-08 01:12:27,816][286098] Fps is (10 sec: 12287.9, 60 sec: 11468.8, 300 sec: 11815.9). Total num frames: 95866880. Throughput: 0: 11504.7. Samples: 95846140. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 01:12:27,816][286098] Avg episode reward: [(0, '4525.238')] [2023-03-08 01:12:27,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000187240_95866880.pth... [2023-03-08 01:12:27,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000186560_95518720.pth [2023-03-08 01:12:29,483][286389] Updated weights for policy 0, policy_version 187280 (0.0005) [2023-03-08 01:12:32,816][286098] Fps is (10 sec: 12288.0, 60 sec: 11537.1, 300 sec: 11788.2). Total num frames: 95924224. Throughput: 0: 11595.2. Samples: 95918988. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 01:12:32,816][286098] Avg episode reward: [(0, '4529.628')] [2023-03-08 01:12:32,845][286389] Updated weights for policy 0, policy_version 187360 (0.0004) [2023-03-08 01:12:36,154][286389] Updated weights for policy 0, policy_version 187440 (0.0004) [2023-03-08 01:12:37,816][286098] Fps is (10 sec: 12288.1, 60 sec: 11673.6, 300 sec: 11802.0). Total num frames: 95989760. Throughput: 0: 11624.0. Samples: 95955520. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 01:12:37,816][286098] Avg episode reward: [(0, '4529.303')] [2023-03-08 01:12:39,440][286389] Updated weights for policy 0, policy_version 187520 (0.0004) [2023-03-08 01:12:42,671][286389] Updated weights for policy 0, policy_version 187600 (0.0003) [2023-03-08 01:12:42,816][286098] Fps is (10 sec: 12697.5, 60 sec: 11741.9, 300 sec: 11815.9). Total num frames: 96051200. Throughput: 0: 11803.1. Samples: 96030720. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 01:12:42,816][286098] Avg episode reward: [(0, '4525.495')] [2023-03-08 01:12:42,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000187600_96051200.pth... [2023-03-08 01:12:42,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000186896_95690752.pth [2023-03-08 01:12:46,006][286389] Updated weights for policy 0, policy_version 187680 (0.0004) [2023-03-08 01:12:47,816][286098] Fps is (10 sec: 12287.9, 60 sec: 11810.2, 300 sec: 11815.9). Total num frames: 96112640. Throughput: 0: 11955.4. Samples: 96104552. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 01:12:47,816][286098] Avg episode reward: [(0, '4528.499')] [2023-03-08 01:12:49,286][286389] Updated weights for policy 0, policy_version 187760 (0.0004) [2023-03-08 01:12:52,628][286389] Updated weights for policy 0, policy_version 187840 (0.0004) [2023-03-08 01:12:52,816][286098] Fps is (10 sec: 12288.0, 60 sec: 11878.4, 300 sec: 11815.9). Total num frames: 96174080. Throughput: 0: 12042.2. Samples: 96142540. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 01:12:52,816][286098] Avg episode reward: [(0, '4537.940')] [2023-03-08 01:12:55,994][286389] Updated weights for policy 0, policy_version 187920 (0.0004) [2023-03-08 01:12:57,816][286098] Fps is (10 sec: 11878.3, 60 sec: 11878.4, 300 sec: 11802.0). Total num frames: 96231424. Throughput: 0: 12144.4. Samples: 96215588. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 01:12:57,816][286098] Avg episode reward: [(0, '4534.481')] [2023-03-08 01:12:57,846][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000187960_96235520.pth... [2023-03-08 01:12:57,847][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000187240_95866880.pth [2023-03-08 01:12:59,633][286389] Updated weights for policy 0, policy_version 188000 (0.0005) [2023-03-08 01:13:02,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11946.7, 300 sec: 11788.1). Total num frames: 96288768. Throughput: 0: 12118.0. Samples: 96283924. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 01:13:02,816][286098] Avg episode reward: [(0, '4531.409')] [2023-03-08 01:13:03,274][286389] Updated weights for policy 0, policy_version 188080 (0.0005) [2023-03-08 01:13:06,887][286389] Updated weights for policy 0, policy_version 188160 (0.0005) [2023-03-08 01:13:07,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11946.7, 300 sec: 11774.3). Total num frames: 96346112. Throughput: 0: 12107.1. Samples: 96317440. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 01:13:07,816][286098] Avg episode reward: [(0, '4532.579')] [2023-03-08 01:13:10,487][286389] Updated weights for policy 0, policy_version 188240 (0.0005) [2023-03-08 01:13:12,816][286098] Fps is (10 sec: 11468.7, 60 sec: 11946.7, 300 sec: 11760.4). Total num frames: 96403456. Throughput: 0: 11993.3. Samples: 96385840. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 01:13:12,816][286098] Avg episode reward: [(0, '4530.258')] [2023-03-08 01:13:12,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000188288_96403456.pth... [2023-03-08 01:13:12,823][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000187600_96051200.pth [2023-03-08 01:13:14,027][286389] Updated weights for policy 0, policy_version 188320 (0.0005) [2023-03-08 01:13:17,663][286389] Updated weights for policy 0, policy_version 188400 (0.0005) [2023-03-08 01:13:17,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11946.6, 300 sec: 11746.5). Total num frames: 96460800. Throughput: 0: 11899.9. Samples: 96454484. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 01:13:17,816][286098] Avg episode reward: [(0, '4536.664')] [2023-03-08 01:13:21,299][286389] Updated weights for policy 0, policy_version 188480 (0.0005) [2023-03-08 01:13:22,816][286098] Fps is (10 sec: 11468.9, 60 sec: 11946.7, 300 sec: 11732.6). Total num frames: 96518144. Throughput: 0: 11827.8. Samples: 96487772. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 01:13:22,816][286098] Avg episode reward: [(0, '4535.419')] [2023-03-08 01:13:24,913][286389] Updated weights for policy 0, policy_version 188560 (0.0005) [2023-03-08 01:13:27,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11741.9, 300 sec: 11704.8). Total num frames: 96571392. Throughput: 0: 11662.7. Samples: 96555540. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 01:13:27,816][286098] Avg episode reward: [(0, '4531.338')] [2023-03-08 01:13:27,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000188624_96575488.pth... [2023-03-08 01:13:27,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000187960_96235520.pth [2023-03-08 01:13:28,556][286389] Updated weights for policy 0, policy_version 188640 (0.0005) [2023-03-08 01:13:32,132][286389] Updated weights for policy 0, policy_version 188720 (0.0005) [2023-03-08 01:13:32,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11741.8, 300 sec: 11691.0). Total num frames: 96628736. Throughput: 0: 11547.7. Samples: 96624200. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 01:13:32,816][286098] Avg episode reward: [(0, '4536.824')] [2023-03-08 01:13:35,702][286389] Updated weights for policy 0, policy_version 188800 (0.0005) [2023-03-08 01:13:37,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11605.3, 300 sec: 11677.1). Total num frames: 96686080. Throughput: 0: 11448.1. Samples: 96657704. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 01:13:37,817][286098] Avg episode reward: [(0, '4537.071')] [2023-03-08 01:13:39,298][286389] Updated weights for policy 0, policy_version 188880 (0.0005) [2023-03-08 01:13:42,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11537.1, 300 sec: 11663.2). Total num frames: 96743424. Throughput: 0: 11357.6. Samples: 96726680. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 01:13:42,816][286098] Avg episode reward: [(0, '4534.418')] [2023-03-08 01:13:42,821][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000188952_96743424.pth... [2023-03-08 01:13:42,823][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000188288_96403456.pth [2023-03-08 01:13:42,951][286389] Updated weights for policy 0, policy_version 188960 (0.0005) [2023-03-08 01:13:46,510][286389] Updated weights for policy 0, policy_version 189040 (0.0005) [2023-03-08 01:13:47,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11468.8, 300 sec: 11649.3). Total num frames: 96800768. Throughput: 0: 11362.8. Samples: 96795248. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 01:13:47,816][286098] Avg episode reward: [(0, '4534.393')] [2023-03-08 01:13:50,098][286389] Updated weights for policy 0, policy_version 189120 (0.0005) [2023-03-08 01:13:52,816][286098] Fps is (10 sec: 11468.9, 60 sec: 11400.5, 300 sec: 11649.3). Total num frames: 96858112. Throughput: 0: 11377.8. Samples: 96829440. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 01:13:52,816][286098] Avg episode reward: [(0, '4537.910')] [2023-03-08 01:13:53,740][286389] Updated weights for policy 0, policy_version 189200 (0.0005) [2023-03-08 01:13:57,406][286389] Updated weights for policy 0, policy_version 189280 (0.0005) [2023-03-08 01:13:57,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11400.5, 300 sec: 11649.3). Total num frames: 96915456. Throughput: 0: 11337.1. Samples: 96896008. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 01:13:57,816][286098] Avg episode reward: [(0, '4545.367')] [2023-03-08 01:13:57,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000189288_96915456.pth... [2023-03-08 01:13:57,823][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000188624_96575488.pth [2023-03-08 01:14:00,988][286389] Updated weights for policy 0, policy_version 189360 (0.0005) [2023-03-08 01:14:02,816][286098] Fps is (10 sec: 11468.7, 60 sec: 11400.5, 300 sec: 11649.3). Total num frames: 96972800. Throughput: 0: 11337.5. Samples: 96964672. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 01:14:02,816][286098] Avg episode reward: [(0, '4549.232')] [2023-03-08 01:14:04,598][286389] Updated weights for policy 0, policy_version 189440 (0.0005) [2023-03-08 01:14:07,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11332.3, 300 sec: 11635.4). Total num frames: 97026048. Throughput: 0: 11354.3. Samples: 96998716. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 01:14:07,816][286098] Avg episode reward: [(0, '4548.971')] [2023-03-08 01:14:08,218][286389] Updated weights for policy 0, policy_version 189520 (0.0005) [2023-03-08 01:14:11,959][286389] Updated weights for policy 0, policy_version 189600 (0.0005) [2023-03-08 01:14:12,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11332.3, 300 sec: 11649.3). Total num frames: 97083392. Throughput: 0: 11339.4. Samples: 97065812. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 01:14:12,816][286098] Avg episode reward: [(0, '4549.249')] [2023-03-08 01:14:12,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000189616_97083392.pth... [2023-03-08 01:14:12,823][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000188952_96743424.pth [2023-03-08 01:14:15,575][286389] Updated weights for policy 0, policy_version 189680 (0.0005) [2023-03-08 01:14:17,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11332.3, 300 sec: 11649.3). Total num frames: 97140736. Throughput: 0: 11298.0. Samples: 97132608. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 01:14:17,816][286098] Avg episode reward: [(0, '4545.650')] [2023-03-08 01:14:19,197][286389] Updated weights for policy 0, policy_version 189760 (0.0005) [2023-03-08 01:14:22,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11264.0, 300 sec: 11635.4). Total num frames: 97193984. Throughput: 0: 11317.4. Samples: 97166988. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 01:14:22,816][286098] Avg episode reward: [(0, '4538.350')] [2023-03-08 01:14:22,886][286389] Updated weights for policy 0, policy_version 189840 (0.0004) [2023-03-08 01:14:26,536][286389] Updated weights for policy 0, policy_version 189920 (0.0005) [2023-03-08 01:14:27,816][286098] Fps is (10 sec: 11059.1, 60 sec: 11332.3, 300 sec: 11635.4). Total num frames: 97251328. Throughput: 0: 11280.2. Samples: 97234288. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 01:14:27,816][286098] Avg episode reward: [(0, '4553.429')] [2023-03-08 01:14:27,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000189944_97251328.pth... [2023-03-08 01:14:27,823][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000189288_96915456.pth [2023-03-08 01:14:30,086][286389] Updated weights for policy 0, policy_version 190000 (0.0005) [2023-03-08 01:14:32,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11332.3, 300 sec: 11621.5). Total num frames: 97308672. Throughput: 0: 11294.4. Samples: 97303496. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 01:14:32,827][286098] Avg episode reward: [(0, '4551.354')] [2023-03-08 01:14:33,531][286389] Updated weights for policy 0, policy_version 190080 (0.0004) [2023-03-08 01:14:36,828][286389] Updated weights for policy 0, policy_version 190160 (0.0004) [2023-03-08 01:14:37,816][286098] Fps is (10 sec: 11878.5, 60 sec: 11400.5, 300 sec: 11649.3). Total num frames: 97370112. Throughput: 0: 11343.4. Samples: 97339892. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 01:14:37,827][286098] Avg episode reward: [(0, '4548.714')] [2023-03-08 01:14:40,070][286389] Updated weights for policy 0, policy_version 190240 (0.0003) [2023-03-08 01:14:42,816][286098] Fps is (10 sec: 12697.5, 60 sec: 11537.1, 300 sec: 11677.1). Total num frames: 97435648. Throughput: 0: 11538.3. Samples: 97415232. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 01:14:42,827][286098] Avg episode reward: [(0, '4548.256')] [2023-03-08 01:14:42,830][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000190304_97435648.pth... [2023-03-08 01:14:42,832][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000189616_97083392.pth [2023-03-08 01:14:43,341][286389] Updated weights for policy 0, policy_version 190320 (0.0004) [2023-03-08 01:14:46,748][286389] Updated weights for policy 0, policy_version 190400 (0.0005) [2023-03-08 01:14:47,816][286098] Fps is (10 sec: 12697.6, 60 sec: 11605.3, 300 sec: 11691.0). Total num frames: 97497088. Throughput: 0: 11649.7. Samples: 97488908. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 01:14:47,827][286098] Avg episode reward: [(0, '4516.937')] [2023-03-08 01:14:50,039][286389] Updated weights for policy 0, policy_version 190480 (0.0004) [2023-03-08 01:14:52,816][286098] Fps is (10 sec: 12288.1, 60 sec: 11673.6, 300 sec: 11704.8). Total num frames: 97558528. Throughput: 0: 11713.7. Samples: 97525832. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 01:14:52,816][286098] Avg episode reward: [(0, '4541.553')] [2023-03-08 01:14:53,341][286389] Updated weights for policy 0, policy_version 190560 (0.0004) [2023-03-08 01:14:56,659][286389] Updated weights for policy 0, policy_version 190640 (0.0004) [2023-03-08 01:14:57,816][286098] Fps is (10 sec: 12288.0, 60 sec: 11741.9, 300 sec: 11732.6). Total num frames: 97619968. Throughput: 0: 11878.8. Samples: 97600360. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 01:14:57,816][286098] Avg episode reward: [(0, '4538.506')] [2023-03-08 01:14:57,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000190664_97619968.pth... [2023-03-08 01:14:57,823][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000189944_97251328.pth [2023-03-08 01:15:00,064][286389] Updated weights for policy 0, policy_version 190720 (0.0005) [2023-03-08 01:15:02,816][286098] Fps is (10 sec: 12288.1, 60 sec: 11810.1, 300 sec: 11746.5). Total num frames: 97681408. Throughput: 0: 12008.1. Samples: 97672972. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 01:15:02,816][286098] Avg episode reward: [(0, '4540.452')] [2023-03-08 01:15:03,458][286389] Updated weights for policy 0, policy_version 190800 (0.0005) [2023-03-08 01:15:06,735][286389] Updated weights for policy 0, policy_version 190880 (0.0003) [2023-03-08 01:15:07,816][286098] Fps is (10 sec: 12288.1, 60 sec: 11946.7, 300 sec: 11760.4). Total num frames: 97742848. Throughput: 0: 12060.8. Samples: 97709724. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 01:15:07,816][286098] Avg episode reward: [(0, '4542.457')] [2023-03-08 01:15:09,954][286389] Updated weights for policy 0, policy_version 190960 (0.0004) [2023-03-08 01:15:12,816][286098] Fps is (10 sec: 12288.0, 60 sec: 12015.0, 300 sec: 11760.4). Total num frames: 97804288. Throughput: 0: 12245.5. Samples: 97785336. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 01:15:12,816][286098] Avg episode reward: [(0, '4547.762')] [2023-03-08 01:15:12,851][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000191032_97808384.pth... [2023-03-08 01:15:12,852][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000190304_97435648.pth [2023-03-08 01:15:13,197][286389] Updated weights for policy 0, policy_version 191040 (0.0004) [2023-03-08 01:15:16,453][286389] Updated weights for policy 0, policy_version 191120 (0.0003) [2023-03-08 01:15:17,816][286098] Fps is (10 sec: 12697.6, 60 sec: 12151.5, 300 sec: 11774.3). Total num frames: 97869824. Throughput: 0: 12388.8. Samples: 97860992. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 01:15:17,816][286098] Avg episode reward: [(0, '4514.529')] [2023-03-08 01:15:19,851][286389] Updated weights for policy 0, policy_version 191200 (0.0004) [2023-03-08 01:15:22,816][286098] Fps is (10 sec: 12697.5, 60 sec: 12288.0, 300 sec: 11774.3). Total num frames: 97931264. Throughput: 0: 12380.3. Samples: 97897004. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 01:15:22,816][286098] Avg episode reward: [(0, '4534.016')] [2023-03-08 01:15:23,134][286389] Updated weights for policy 0, policy_version 191280 (0.0003) [2023-03-08 01:15:26,463][286389] Updated weights for policy 0, policy_version 191360 (0.0004) [2023-03-08 01:15:27,816][286098] Fps is (10 sec: 12287.9, 60 sec: 12356.3, 300 sec: 11774.3). Total num frames: 97992704. Throughput: 0: 12366.6. Samples: 97971728. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-08 01:15:27,816][286098] Avg episode reward: [(0, '4526.002')] [2023-03-08 01:15:27,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000191392_97992704.pth... [2023-03-08 01:15:27,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000190664_97619968.pth [2023-03-08 01:15:29,781][286389] Updated weights for policy 0, policy_version 191440 (0.0004) [2023-03-08 01:15:32,816][286098] Fps is (10 sec: 12288.0, 60 sec: 12424.5, 300 sec: 11774.3). Total num frames: 98054144. Throughput: 0: 12379.1. Samples: 98045968. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 01:15:32,816][286098] Avg episode reward: [(0, '4551.167')] [2023-03-08 01:15:33,059][286389] Updated weights for policy 0, policy_version 191520 (0.0004) [2023-03-08 01:15:36,342][286389] Updated weights for policy 0, policy_version 191600 (0.0003) [2023-03-08 01:15:37,816][286098] Fps is (10 sec: 12288.0, 60 sec: 12424.5, 300 sec: 11774.3). Total num frames: 98115584. Throughput: 0: 12390.2. Samples: 98083392. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 01:15:37,816][286098] Avg episode reward: [(0, '4552.812')] [2023-03-08 01:15:39,867][286389] Updated weights for policy 0, policy_version 191680 (0.0004) [2023-03-08 01:15:42,816][286098] Fps is (10 sec: 11878.3, 60 sec: 12288.0, 300 sec: 11760.4). Total num frames: 98172928. Throughput: 0: 12300.6. Samples: 98153888. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 01:15:42,816][286098] Avg episode reward: [(0, '4525.607')] [2023-03-08 01:15:42,819][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000191744_98172928.pth... [2023-03-08 01:15:42,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000191032_97808384.pth [2023-03-08 01:15:43,478][286389] Updated weights for policy 0, policy_version 191760 (0.0005) [2023-03-08 01:15:47,055][286389] Updated weights for policy 0, policy_version 191840 (0.0005) [2023-03-08 01:15:47,816][286098] Fps is (10 sec: 11468.9, 60 sec: 12219.7, 300 sec: 11760.4). Total num frames: 98230272. Throughput: 0: 12203.8. Samples: 98222144. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 01:15:47,816][286098] Avg episode reward: [(0, '4513.801')] [2023-03-08 01:15:50,721][286389] Updated weights for policy 0, policy_version 191920 (0.0005) [2023-03-08 01:15:52,816][286098] Fps is (10 sec: 11059.3, 60 sec: 12083.2, 300 sec: 11718.7). Total num frames: 98283520. Throughput: 0: 12135.7. Samples: 98255828. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 01:15:52,827][286098] Avg episode reward: [(0, '4557.522')] [2023-03-08 01:15:54,118][286389] Updated weights for policy 0, policy_version 192000 (0.0004) [2023-03-08 01:15:57,648][286389] Updated weights for policy 0, policy_version 192080 (0.0004) [2023-03-08 01:15:57,816][286098] Fps is (10 sec: 11468.7, 60 sec: 12083.2, 300 sec: 11718.7). Total num frames: 98344960. Throughput: 0: 12054.4. Samples: 98327784. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 01:15:57,827][286098] Avg episode reward: [(0, '4536.179')] [2023-03-08 01:15:57,830][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000192080_98344960.pth... [2023-03-08 01:15:57,833][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000191392_97992704.pth [2023-03-08 01:16:01,243][286389] Updated weights for policy 0, policy_version 192160 (0.0005) [2023-03-08 01:16:02,816][286098] Fps is (10 sec: 11878.3, 60 sec: 12014.9, 300 sec: 11704.8). Total num frames: 98402304. Throughput: 0: 11860.2. Samples: 98394700. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 01:16:02,827][286098] Avg episode reward: [(0, '4550.707')] [2023-03-08 01:16:04,867][286389] Updated weights for policy 0, policy_version 192240 (0.0005) [2023-03-08 01:16:07,816][286098] Fps is (10 sec: 11468.9, 60 sec: 11946.7, 300 sec: 11704.8). Total num frames: 98459648. Throughput: 0: 11826.3. Samples: 98429188. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 01:16:07,816][286098] Avg episode reward: [(0, '4530.964')] [2023-03-08 01:16:08,466][286389] Updated weights for policy 0, policy_version 192320 (0.0005) [2023-03-08 01:16:12,096][286389] Updated weights for policy 0, policy_version 192400 (0.0005) [2023-03-08 01:16:12,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11810.1, 300 sec: 11691.0). Total num frames: 98512896. Throughput: 0: 11666.9. Samples: 98496740. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 01:16:12,816][286098] Avg episode reward: [(0, '4537.329')] [2023-03-08 01:16:12,822][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000192416_98516992.pth... [2023-03-08 01:16:12,825][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000191744_98172928.pth [2023-03-08 01:16:15,740][286389] Updated weights for policy 0, policy_version 192480 (0.0005) [2023-03-08 01:16:17,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11673.6, 300 sec: 11691.0). Total num frames: 98570240. Throughput: 0: 11534.2. Samples: 98565008. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 01:16:17,816][286098] Avg episode reward: [(0, '4561.360')] [2023-03-08 01:16:19,352][286389] Updated weights for policy 0, policy_version 192560 (0.0005) [2023-03-08 01:16:22,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11605.3, 300 sec: 11691.0). Total num frames: 98627584. Throughput: 0: 11456.4. Samples: 98598928. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 01:16:22,816][286098] Avg episode reward: [(0, '4553.916')] [2023-03-08 01:16:22,920][286389] Updated weights for policy 0, policy_version 192640 (0.0005) [2023-03-08 01:16:26,518][286389] Updated weights for policy 0, policy_version 192720 (0.0004) [2023-03-08 01:16:27,816][286098] Fps is (10 sec: 11468.7, 60 sec: 11537.1, 300 sec: 11704.8). Total num frames: 98684928. Throughput: 0: 11415.3. Samples: 98667576. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 01:16:27,816][286098] Avg episode reward: [(0, '4535.762')] [2023-03-08 01:16:27,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000192744_98684928.pth... [2023-03-08 01:16:27,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000192080_98344960.pth [2023-03-08 01:16:30,135][286389] Updated weights for policy 0, policy_version 192800 (0.0005) [2023-03-08 01:16:32,816][286098] Fps is (10 sec: 11468.7, 60 sec: 11468.8, 300 sec: 11704.8). Total num frames: 98742272. Throughput: 0: 11409.1. Samples: 98735552. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-08 01:16:32,816][286098] Avg episode reward: [(0, '4563.220')] [2023-03-08 01:16:33,715][286389] Updated weights for policy 0, policy_version 192880 (0.0005) [2023-03-08 01:16:37,390][286389] Updated weights for policy 0, policy_version 192960 (0.0005) [2023-03-08 01:16:37,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11400.5, 300 sec: 11704.8). Total num frames: 98799616. Throughput: 0: 11420.7. Samples: 98769760. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 01:16:37,816][286098] Avg episode reward: [(0, '4534.329')] [2023-03-08 01:16:40,963][286389] Updated weights for policy 0, policy_version 193040 (0.0005) [2023-03-08 01:16:42,816][286098] Fps is (10 sec: 11059.1, 60 sec: 11332.3, 300 sec: 11691.0). Total num frames: 98852864. Throughput: 0: 11327.8. Samples: 98837536. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 01:16:42,817][286098] Avg episode reward: [(0, '4537.358')] [2023-03-08 01:16:42,830][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000193080_98856960.pth... [2023-03-08 01:16:42,831][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000192416_98516992.pth [2023-03-08 01:16:44,615][286389] Updated weights for policy 0, policy_version 193120 (0.0005) [2023-03-08 01:16:47,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11332.3, 300 sec: 11691.0). Total num frames: 98910208. Throughput: 0: 11360.9. Samples: 98905940. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 01:16:47,816][286098] Avg episode reward: [(0, '4564.812')] [2023-03-08 01:16:48,256][286389] Updated weights for policy 0, policy_version 193200 (0.0004) [2023-03-08 01:16:51,717][286389] Updated weights for policy 0, policy_version 193280 (0.0005) [2023-03-08 01:16:52,816][286098] Fps is (10 sec: 11878.5, 60 sec: 11468.8, 300 sec: 11704.8). Total num frames: 98971648. Throughput: 0: 11336.2. Samples: 98939316. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 01:16:52,816][286098] Avg episode reward: [(0, '4550.576')] [2023-03-08 01:16:55,084][286389] Updated weights for policy 0, policy_version 193360 (0.0004) [2023-03-08 01:16:57,816][286098] Fps is (10 sec: 12287.9, 60 sec: 11468.8, 300 sec: 11732.6). Total num frames: 99033088. Throughput: 0: 11460.9. Samples: 99012480. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 01:16:57,816][286098] Avg episode reward: [(0, '4552.597')] [2023-03-08 01:16:57,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000193424_99033088.pth... [2023-03-08 01:16:57,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000192744_98684928.pth [2023-03-08 01:16:58,433][286389] Updated weights for policy 0, policy_version 193440 (0.0004) [2023-03-08 01:17:01,774][286389] Updated weights for policy 0, policy_version 193520 (0.0004) [2023-03-08 01:17:02,816][286098] Fps is (10 sec: 12288.0, 60 sec: 11537.1, 300 sec: 11746.5). Total num frames: 99094528. Throughput: 0: 11578.1. Samples: 99086024. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 01:17:02,816][286098] Avg episode reward: [(0, '4538.111')] [2023-03-08 01:17:05,047][286389] Updated weights for policy 0, policy_version 193600 (0.0003) [2023-03-08 01:17:07,816][286098] Fps is (10 sec: 12288.1, 60 sec: 11605.3, 300 sec: 11760.4). Total num frames: 99155968. Throughput: 0: 11651.9. Samples: 99123264. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 01:17:07,816][286098] Avg episode reward: [(0, '4551.562')] [2023-03-08 01:17:08,437][286389] Updated weights for policy 0, policy_version 193680 (0.0004) [2023-03-08 01:17:11,834][286389] Updated weights for policy 0, policy_version 193760 (0.0004) [2023-03-08 01:17:12,816][286098] Fps is (10 sec: 11878.3, 60 sec: 11673.6, 300 sec: 11760.4). Total num frames: 99213312. Throughput: 0: 11741.6. Samples: 99195948. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 01:17:12,816][286098] Avg episode reward: [(0, '4528.466')] [2023-03-08 01:17:12,839][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000193784_99217408.pth... [2023-03-08 01:17:12,841][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000193080_98856960.pth [2023-03-08 01:17:15,162][286389] Updated weights for policy 0, policy_version 193840 (0.0004) [2023-03-08 01:17:17,816][286098] Fps is (10 sec: 12287.9, 60 sec: 11810.1, 300 sec: 11788.1). Total num frames: 99278848. Throughput: 0: 11868.9. Samples: 99269652. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 01:17:17,816][286098] Avg episode reward: [(0, '4565.869')] [2023-03-08 01:17:18,459][286389] Updated weights for policy 0, policy_version 193920 (0.0004) [2023-03-08 01:17:22,013][286389] Updated weights for policy 0, policy_version 194000 (0.0005) [2023-03-08 01:17:22,816][286098] Fps is (10 sec: 12288.2, 60 sec: 11810.1, 300 sec: 11760.4). Total num frames: 99336192. Throughput: 0: 11909.6. Samples: 99305692. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 01:17:22,816][286098] Avg episode reward: [(0, '4571.244')] [2023-03-08 01:17:25,633][286389] Updated weights for policy 0, policy_version 194080 (0.0005) [2023-03-08 01:17:27,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11741.9, 300 sec: 11746.5). Total num frames: 99389440. Throughput: 0: 11908.6. Samples: 99373420. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 01:17:27,816][286098] Avg episode reward: [(0, '4570.777')] [2023-03-08 01:17:27,882][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000194128_99393536.pth... [2023-03-08 01:17:27,884][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000193424_99033088.pth [2023-03-08 01:17:29,383][286389] Updated weights for policy 0, policy_version 194160 (0.0005) [2023-03-08 01:17:32,816][286098] Fps is (10 sec: 11059.2, 60 sec: 11741.9, 300 sec: 11718.7). Total num frames: 99446784. Throughput: 0: 11876.5. Samples: 99440380. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 01:17:32,816][286098] Avg episode reward: [(0, '4567.678')] [2023-03-08 01:17:33,030][286389] Updated weights for policy 0, policy_version 194240 (0.0005) [2023-03-08 01:17:36,643][286389] Updated weights for policy 0, policy_version 194320 (0.0005) [2023-03-08 01:17:37,816][286098] Fps is (10 sec: 11468.9, 60 sec: 11741.9, 300 sec: 11704.8). Total num frames: 99504128. Throughput: 0: 11888.3. Samples: 99474288. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 01:17:37,816][286098] Avg episode reward: [(0, '4566.032')] [2023-03-08 01:17:40,283][286389] Updated weights for policy 0, policy_version 194400 (0.0005) [2023-03-08 01:17:42,816][286098] Fps is (10 sec: 11059.0, 60 sec: 11741.9, 300 sec: 11677.1). Total num frames: 99557376. Throughput: 0: 11758.4. Samples: 99541608. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 01:17:42,817][286098] Avg episode reward: [(0, '4552.689')] [2023-03-08 01:17:42,848][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000194456_99561472.pth... [2023-03-08 01:17:42,849][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000193784_99217408.pth [2023-03-08 01:17:43,955][286389] Updated weights for policy 0, policy_version 194480 (0.0005) [2023-03-08 01:17:47,302][286389] Updated weights for policy 0, policy_version 194560 (0.0004) [2023-03-08 01:17:47,816][286098] Fps is (10 sec: 11468.8, 60 sec: 11810.1, 300 sec: 11677.1). Total num frames: 99618816. Throughput: 0: 11682.4. Samples: 99611732. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 01:17:47,816][286098] Avg episode reward: [(0, '4567.128')] [2023-03-08 01:17:50,726][286389] Updated weights for policy 0, policy_version 194640 (0.0004) [2023-03-08 01:17:52,816][286098] Fps is (10 sec: 12288.2, 60 sec: 11810.1, 300 sec: 11691.0). Total num frames: 99680256. Throughput: 0: 11655.9. Samples: 99647780. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 01:17:52,816][286098] Avg episode reward: [(0, '4567.958')] [2023-03-08 01:17:54,115][286389] Updated weights for policy 0, policy_version 194720 (0.0004) [2023-03-08 01:17:57,417][286389] Updated weights for policy 0, policy_version 194800 (0.0004) [2023-03-08 01:17:57,816][286098] Fps is (10 sec: 12287.9, 60 sec: 11810.1, 300 sec: 11704.8). Total num frames: 99741696. Throughput: 0: 11672.6. Samples: 99721216. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 01:17:57,816][286098] Avg episode reward: [(0, '4569.831')] [2023-03-08 01:17:57,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000194808_99741696.pth... [2023-03-08 01:17:57,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000194128_99393536.pth [2023-03-08 01:18:00,726][286389] Updated weights for policy 0, policy_version 194880 (0.0004) [2023-03-08 01:18:02,816][286098] Fps is (10 sec: 12288.0, 60 sec: 11810.1, 300 sec: 11718.7). Total num frames: 99803136. Throughput: 0: 11674.6. Samples: 99795008. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 01:18:02,816][286098] Avg episode reward: [(0, '4567.959')] [2023-03-08 01:18:04,053][286389] Updated weights for policy 0, policy_version 194960 (0.0004) [2023-03-08 01:18:07,331][286389] Updated weights for policy 0, policy_version 195040 (0.0004) [2023-03-08 01:18:07,816][286098] Fps is (10 sec: 12288.1, 60 sec: 11810.1, 300 sec: 11732.6). Total num frames: 99864576. Throughput: 0: 11695.7. Samples: 99832000. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 01:18:07,816][286098] Avg episode reward: [(0, '4562.901')] [2023-03-08 01:18:10,595][286389] Updated weights for policy 0, policy_version 195120 (0.0003) [2023-03-08 01:18:12,816][286098] Fps is (10 sec: 12288.0, 60 sec: 11878.4, 300 sec: 11746.5). Total num frames: 99926016. Throughput: 0: 11863.4. Samples: 99907272. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 01:18:12,816][286098] Avg episode reward: [(0, '4569.972')] [2023-03-08 01:18:12,820][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000195168_99926016.pth... [2023-03-08 01:18:12,822][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000194456_99561472.pth [2023-03-08 01:18:13,884][286389] Updated weights for policy 0, policy_version 195200 (0.0003) [2023-03-08 01:18:17,183][286389] Updated weights for policy 0, policy_version 195280 (0.0004) [2023-03-08 01:18:17,816][286098] Fps is (10 sec: 12288.0, 60 sec: 11810.1, 300 sec: 11760.4). Total num frames: 99987456. Throughput: 0: 12036.4. Samples: 99982020. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-08 01:18:17,816][286098] Avg episode reward: [(0, '4567.401')] [2023-03-08 01:18:18,907][286341] Early stopping after 2 epochs (8 sgd steps), loss delta 0.0000000 [2023-03-08 01:18:19,251][286341] Early stopping after 2 epochs (8 sgd steps), loss delta 0.0000000 [2023-03-08 01:18:19,252][286391] Stopping RolloutWorker_w3... [2023-03-08 01:18:19,252][286385] Stopping RolloutWorker_w4... [2023-03-08 01:18:19,252][286387] Stopping RolloutWorker_w5... [2023-03-08 01:18:19,252][286392] Stopping RolloutWorker_w2... [2023-03-08 01:18:19,252][286390] Stopping RolloutWorker_w6... [2023-03-08 01:18:19,252][286388] Stopping RolloutWorker_w1... [2023-03-08 01:18:19,252][286386] Stopping RolloutWorker_w0... [2023-03-08 01:18:19,252][286391] Loop rollout_proc3_evt_loop terminating... [2023-03-08 01:18:19,252][286385] Loop rollout_proc4_evt_loop terminating... [2023-03-08 01:18:19,252][286387] Loop rollout_proc5_evt_loop terminating... [2023-03-08 01:18:19,252][286388] Loop rollout_proc1_evt_loop terminating... [2023-03-08 01:18:19,252][286392] Loop rollout_proc2_evt_loop terminating... [2023-03-08 01:18:19,252][286390] Loop rollout_proc6_evt_loop terminating... [2023-03-08 01:18:19,252][286393] Stopping RolloutWorker_w7... [2023-03-08 01:18:19,252][286386] Loop rollout_proc0_evt_loop terminating... [2023-03-08 01:18:19,252][286341] Stopping Batcher_0... [2023-03-08 01:18:19,252][286098] Component RolloutWorker_w3 stopped! [2023-03-08 01:18:19,252][286393] Loop rollout_proc7_evt_loop terminating... [2023-03-08 01:18:19,252][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000195328_100007936.pth... [2023-03-08 01:18:19,253][286098] Component RolloutWorker_w5 stopped! [2023-03-08 01:18:19,253][286098] Component RolloutWorker_w4 stopped! [2023-03-08 01:18:19,253][286098] Component RolloutWorker_w2 stopped! [2023-03-08 01:18:19,254][286098] Component RolloutWorker_w6 stopped! [2023-03-08 01:18:19,254][286098] Component RolloutWorker_w1 stopped! [2023-03-08 01:18:19,254][286098] Component RolloutWorker_w0 stopped! [2023-03-08 01:18:19,254][286098] Component Batcher_0 stopped! [2023-03-08 01:18:19,253][286341] Loop batcher_evt_loop terminating... [2023-03-08 01:18:19,255][286098] Component RolloutWorker_w7 stopped! [2023-03-08 01:18:19,255][286341] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000194808_99741696.pth [2023-03-08 01:18:19,256][286341] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/door-open-v2/checkpoint_p0/checkpoint_000195328_100007936.pth... [2023-03-08 01:18:19,258][286341] Stopping LearnerWorker_p0... [2023-03-08 01:18:19,258][286341] Loop learner_proc0_evt_loop terminating... [2023-03-08 01:18:19,258][286098] Component LearnerWorker_p0 stopped! [2023-03-08 01:18:19,275][286389] Weights refcount: 2 0 [2023-03-08 01:18:19,276][286389] Stopping InferenceWorker_p0-w0... [2023-03-08 01:18:19,276][286389] Loop inference_proc0-0_evt_loop terminating... [2023-03-08 01:18:19,277][286098] Component InferenceWorker_p0-w0 stopped! [2023-03-08 01:18:19,277][286098] Waiting for process learner_proc0 to stop... [2023-03-08 01:18:19,687][286098] Waiting for process inference_proc0-0 to join... [2023-03-08 01:18:19,690][286098] Waiting for process rollout_proc0 to join... [2023-03-08 01:18:19,690][286098] Waiting for process rollout_proc1 to join... [2023-03-08 01:18:19,691][286098] Waiting for process rollout_proc2 to join... [2023-03-08 01:18:19,696][286098] Waiting for process rollout_proc3 to join... [2023-03-08 01:18:19,696][286098] Waiting for process rollout_proc4 to join... [2023-03-08 01:18:19,697][286098] Waiting for process rollout_proc5 to join... [2023-03-08 01:18:19,697][286098] Waiting for process rollout_proc6 to join... [2023-03-08 01:18:19,697][286098] Waiting for process rollout_proc7 to join... [2023-03-08 01:18:19,697][286098] Batcher 0 profile tree view: batching: 17.5338, releasing_batches: 14.9577 [2023-03-08 01:18:19,697][286098] InferenceWorker_p0-w0 profile tree view: wait_policy: 0.0000 wait_policy_total: 3016.4761 update_model: 96.6727 weight_update: 0.0004 one_step: 0.0011 handle_policy_step: 4935.0239 deserialize: 209.3524, stack: 50.6389, obs_to_device_normalize: 880.4847, forward: 2442.9967, send_messages: 363.5881 prepare_outputs: 560.2644 to_cpu: 87.1523 [2023-03-08 01:18:19,698][286098] Learner 0 profile tree view: misc: 0.0953, prepare_batch: 86.7800 train: 1132.7044 epoch_init: 0.3809, minibatch_init: 11.5436, losses_postprocess: 11.5214, kl_divergence: 4.1268, after_optimizer: 4.7964 calculate_losses: 465.1356 losses_init: 0.4152, forward_head: 230.6211, bptt_initial: 1.1917, bptt: 1.2014, tail: 108.9874, advantages_returns: 8.4484, losses: 100.7709 update: 619.8562 clip: 54.0328 [2023-03-08 01:18:19,698][286098] RolloutWorker_w0 profile tree view: wait_for_trajectories: 2.6042, enqueue_policy_requests: 124.8115, env_step: 5763.0305, overhead: 302.0410, complete_rollouts: 3.1209 save_policy_outputs: 320.5816 split_output_tensors: 157.8028 [2023-03-08 01:18:19,698][286098] RolloutWorker_w7 profile tree view: wait_for_trajectories: 2.7786, enqueue_policy_requests: 125.7068, env_step: 5847.0645, overhead: 309.3186, complete_rollouts: 3.1367 save_policy_outputs: 319.2586 split_output_tensors: 157.5116 [2023-03-08 01:18:19,698][286098] Loop Runner_EvtLoop terminating... [2023-03-08 01:18:19,698][286098] Runner profile tree view: main_loop: 8659.6230 [2023-03-08 01:18:19,699][286098] Collected {0: 100007936}, FPS: 11548.8