[2023-03-11 10:31:55,507][04011] Saving configuration to /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/config.json... [2023-03-11 10:31:55,530][04011] Rollout worker 0 uses device cpu [2023-03-11 10:31:55,530][04011] Rollout worker 1 uses device cpu [2023-03-11 10:31:55,530][04011] Rollout worker 2 uses device cpu [2023-03-11 10:31:55,530][04011] Rollout worker 3 uses device cpu [2023-03-11 10:31:55,530][04011] Rollout worker 4 uses device cpu [2023-03-11 10:31:55,530][04011] Rollout worker 5 uses device cpu [2023-03-11 10:31:55,531][04011] Rollout worker 6 uses device cpu [2023-03-11 10:31:55,531][04011] Rollout worker 7 uses device cpu [2023-03-11 10:31:55,531][04011] In synchronous mode, we only accumulate one batch. Setting num_batches_to_accumulate to 1 [2023-03-11 10:31:55,553][04011] InferenceWorker_p0-w0: min num requests: 2 [2023-03-11 10:31:55,569][04011] Starting all processes... [2023-03-11 10:31:55,569][04011] Starting process learner_proc0 [2023-03-11 10:31:55,619][04011] Starting all processes... [2023-03-11 10:31:55,649][04011] Starting process inference_proc0-0 [2023-03-11 10:31:55,654][04011] Starting process rollout_proc0 [2023-03-11 10:31:55,655][04011] Starting process rollout_proc1 [2023-03-11 10:31:55,655][04011] Starting process rollout_proc2 [2023-03-11 10:31:55,655][04011] Starting process rollout_proc3 [2023-03-11 10:31:55,655][04011] Starting process rollout_proc4 [2023-03-11 10:31:55,655][04011] Starting process rollout_proc5 [2023-03-11 10:31:55,655][04011] Starting process rollout_proc6 [2023-03-11 10:31:55,656][04011] Starting process rollout_proc7 [2023-03-11 10:31:57,059][04300] Worker 2 uses CPU cores [8, 9, 10, 11] [2023-03-11 10:31:57,069][04254] Starting seed is not provided [2023-03-11 10:31:57,069][04254] Initializing actor-critic model on device cpu [2023-03-11 10:31:57,069][04254] RunningMeanStd input shape: (39,) [2023-03-11 10:31:57,070][04254] RunningMeanStd input shape: (1,) [2023-03-11 10:31:57,162][04254] Created Actor Critic model with architecture: [2023-03-11 10:31:57,162][04254] 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) ) ) [2023-03-11 10:31:57,304][04303] Worker 4 uses CPU cores [16, 17, 18, 19] [2023-03-11 10:31:57,364][04299] Worker 1 uses CPU cores [4, 5, 6, 7] [2023-03-11 10:31:57,459][04254] Using optimizer [2023-03-11 10:31:57,459][04254] No checkpoints found [2023-03-11 10:31:57,459][04254] Did not load from checkpoint, starting from scratch! [2023-03-11 10:31:57,459][04254] Initialized policy 0 weights for model version 0 [2023-03-11 10:31:57,460][04254] LearnerWorker_p0 finished initialization! [2023-03-11 10:31:57,461][04298] RunningMeanStd input shape: (39,) [2023-03-11 10:31:57,461][04298] RunningMeanStd input shape: (1,) [2023-03-11 10:31:57,518][04011] Inference worker 0-0 is ready! [2023-03-11 10:31:57,518][04011] All inference workers are ready! Signal rollout workers to start! [2023-03-11 10:31:57,532][04301] Worker 0 uses CPU cores [0, 1, 2, 3] [2023-03-11 10:31:57,561][04306] Worker 6 uses CPU cores [24, 25, 26, 27] [2023-03-11 10:31:57,637][04304] Worker 5 uses CPU cores [20, 21, 22, 23] [2023-03-11 10:31:57,722][04307] Worker 7 uses CPU cores [28, 29, 30, 31] [2023-03-11 10:31:57,811][04011] 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) [2023-03-11 10:31:57,878][04302] Worker 3 uses CPU cores [12, 13, 14, 15] [2023-03-11 10:32:02,811][04011] 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) [2023-03-11 10:32:02,970][04303] Decorrelating experience for 0 frames... [2023-03-11 10:32:02,971][04299] Decorrelating experience for 0 frames... [2023-03-11 10:32:02,985][04303] Decorrelating experience for 64 frames... [2023-03-11 10:32:02,986][04299] Decorrelating experience for 64 frames... [2023-03-11 10:32:03,003][04300] Decorrelating experience for 0 frames... [2023-03-11 10:32:03,018][04300] Decorrelating experience for 64 frames... [2023-03-11 10:32:03,035][04301] Decorrelating experience for 0 frames... [2023-03-11 10:32:03,038][04299] Decorrelating experience for 128 frames... [2023-03-11 10:32:03,038][04303] Decorrelating experience for 128 frames... [2023-03-11 10:32:03,050][04301] Decorrelating experience for 64 frames... [2023-03-11 10:32:03,060][04300] Decorrelating experience for 128 frames... [2023-03-11 10:32:03,092][04301] Decorrelating experience for 128 frames... [2023-03-11 10:32:03,106][04299] Decorrelating experience for 192 frames... [2023-03-11 10:32:03,106][04303] Decorrelating experience for 192 frames... [2023-03-11 10:32:03,132][04300] Decorrelating experience for 192 frames... [2023-03-11 10:32:03,145][04304] Decorrelating experience for 0 frames... [2023-03-11 10:32:03,148][04306] Decorrelating experience for 0 frames... [2023-03-11 10:32:03,159][04301] Decorrelating experience for 192 frames... [2023-03-11 10:32:03,160][04304] Decorrelating experience for 64 frames... [2023-03-11 10:32:03,163][04306] Decorrelating experience for 64 frames... [2023-03-11 10:32:03,202][04304] Decorrelating experience for 128 frames... [2023-03-11 10:32:03,205][04306] Decorrelating experience for 128 frames... [2023-03-11 10:32:03,241][04307] Decorrelating experience for 0 frames... [2023-03-11 10:32:03,256][04307] Decorrelating experience for 64 frames... [2023-03-11 10:32:03,270][04304] Decorrelating experience for 192 frames... [2023-03-11 10:32:03,273][04306] Decorrelating experience for 192 frames... [2023-03-11 10:32:03,299][04307] Decorrelating experience for 128 frames... [2023-03-11 10:32:03,368][04307] Decorrelating experience for 192 frames... [2023-03-11 10:32:03,383][04302] Decorrelating experience for 0 frames... [2023-03-11 10:32:03,397][04302] Decorrelating experience for 64 frames... [2023-03-11 10:32:03,439][04302] Decorrelating experience for 128 frames... [2023-03-11 10:32:03,507][04302] Decorrelating experience for 192 frames... [2023-03-11 10:32:07,811][04011] 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) [2023-03-11 10:32:07,818][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000000000_0.pth... [2023-03-11 10:32:08,622][04303] Decorrelating experience for 256 frames... [2023-03-11 10:32:08,622][04300] Decorrelating experience for 256 frames... [2023-03-11 10:32:08,623][04299] Decorrelating experience for 256 frames... [2023-03-11 10:32:08,649][04301] Decorrelating experience for 256 frames... [2023-03-11 10:32:08,743][04300] Decorrelating experience for 320 frames... [2023-03-11 10:32:08,745][04303] Decorrelating experience for 320 frames... [2023-03-11 10:32:08,747][04299] Decorrelating experience for 320 frames... [2023-03-11 10:32:08,769][04301] Decorrelating experience for 320 frames... [2023-03-11 10:32:08,781][04304] Decorrelating experience for 256 frames... [2023-03-11 10:32:08,855][04306] Decorrelating experience for 256 frames... [2023-03-11 10:32:08,865][04307] Decorrelating experience for 256 frames... [2023-03-11 10:32:08,891][04300] Decorrelating experience for 384 frames... [2023-03-11 10:32:08,894][04303] Decorrelating experience for 384 frames... [2023-03-11 10:32:08,897][04299] Decorrelating experience for 384 frames... [2023-03-11 10:32:08,903][04304] Decorrelating experience for 320 frames... [2023-03-11 10:32:08,922][04301] Decorrelating experience for 384 frames... [2023-03-11 10:32:08,979][04306] Decorrelating experience for 320 frames... [2023-03-11 10:32:08,988][04307] Decorrelating experience for 320 frames... [2023-03-11 10:32:09,000][04302] Decorrelating experience for 256 frames... [2023-03-11 10:32:09,052][04304] Decorrelating experience for 384 frames... [2023-03-11 10:32:09,064][04300] Decorrelating experience for 448 frames... [2023-03-11 10:32:09,067][04303] Decorrelating experience for 448 frames... [2023-03-11 10:32:09,078][04299] Decorrelating experience for 448 frames... [2023-03-11 10:32:09,092][04301] Decorrelating experience for 448 frames... [2023-03-11 10:32:09,120][04302] Decorrelating experience for 320 frames... [2023-03-11 10:32:09,128][04306] Decorrelating experience for 384 frames... [2023-03-11 10:32:09,135][04307] Decorrelating experience for 384 frames... [2023-03-11 10:32:09,231][04304] Decorrelating experience for 448 frames... [2023-03-11 10:32:09,266][04302] Decorrelating experience for 384 frames... [2023-03-11 10:32:09,303][04306] Decorrelating experience for 448 frames... [2023-03-11 10:32:09,311][04307] Decorrelating experience for 448 frames... [2023-03-11 10:32:09,447][04302] Decorrelating experience for 448 frames... [2023-03-11 10:32:12,811][04011] Fps is (10 sec: 3686.4, 60 sec: 2457.6, 300 sec: 2457.6). Total num frames: 36864. Throughput: 0: 2193.6. Samples: 32904. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:32:12,818][04011] Avg episode reward: [(0, '0.000')] [2023-03-11 10:32:13,106][04298] Updated weights for policy 0, policy_version 80 (0.0004) [2023-03-11 10:32:15,549][04011] Heartbeat connected on Batcher_0 [2023-03-11 10:32:15,551][04011] Heartbeat connected on LearnerWorker_p0 [2023-03-11 10:32:15,554][04011] Heartbeat connected on InferenceWorker_p0-w0 [2023-03-11 10:32:15,557][04011] Heartbeat connected on RolloutWorker_w0 [2023-03-11 10:32:15,560][04011] Heartbeat connected on RolloutWorker_w1 [2023-03-11 10:32:15,562][04011] Heartbeat connected on RolloutWorker_w2 [2023-03-11 10:32:15,564][04011] Heartbeat connected on RolloutWorker_w3 [2023-03-11 10:32:15,566][04011] Heartbeat connected on RolloutWorker_w4 [2023-03-11 10:32:15,567][04011] Heartbeat connected on RolloutWorker_w5 [2023-03-11 10:32:15,569][04011] Heartbeat connected on RolloutWorker_w6 [2023-03-11 10:32:15,572][04011] Heartbeat connected on RolloutWorker_w7 [2023-03-11 10:32:16,026][04298] Updated weights for policy 0, policy_version 160 (0.0003) [2023-03-11 10:32:17,811][04011] Fps is (10 sec: 10240.1, 60 sec: 5120.0, 300 sec: 5120.0). Total num frames: 102400. Throughput: 0: 3762.2. Samples: 75244. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:32:17,822][04011] Avg episode reward: [(0, '0.000')] [2023-03-11 10:32:17,831][04254] Saving new best policy, reward=0.000! [2023-03-11 10:32:19,075][04298] Updated weights for policy 0, policy_version 240 (0.0004) [2023-03-11 10:32:22,104][04298] Updated weights for policy 0, policy_version 320 (0.0004) [2023-03-11 10:32:22,811][04011] Fps is (10 sec: 13516.8, 60 sec: 6881.3, 300 sec: 6881.3). Total num frames: 172032. Throughput: 0: 6238.4. Samples: 155960. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-11 10:32:22,820][04011] Avg episode reward: [(0, '0.000')] [2023-03-11 10:32:22,823][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000000336_172032.pth... [2023-03-11 10:32:25,132][04298] Updated weights for policy 0, policy_version 400 (0.0005) [2023-03-11 10:32:27,811][04011] Fps is (10 sec: 13516.8, 60 sec: 7918.9, 300 sec: 7918.9). Total num frames: 237568. Throughput: 0: 7921.3. Samples: 237640. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:32:27,811][04011] Avg episode reward: [(0, '0.000')] [2023-03-11 10:32:28,126][04298] Updated weights for policy 0, policy_version 480 (0.0004) [2023-03-11 10:32:31,130][04298] Updated weights for policy 0, policy_version 560 (0.0004) [2023-03-11 10:32:32,811][04011] Fps is (10 sec: 13516.9, 60 sec: 8777.1, 300 sec: 8777.1). Total num frames: 307200. Throughput: 0: 7959.8. Samples: 278592. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:32:32,811][04011] Avg episode reward: [(0, '0.000')] [2023-03-11 10:32:34,249][04298] Updated weights for policy 0, policy_version 640 (0.0004) [2023-03-11 10:32:37,350][04298] Updated weights for policy 0, policy_version 720 (0.0004) [2023-03-11 10:32:37,811][04011] Fps is (10 sec: 13516.7, 60 sec: 9318.4, 300 sec: 9318.4). Total num frames: 372736. Throughput: 0: 8964.9. Samples: 358596. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-11 10:32:37,811][04011] Avg episode reward: [(0, '0.000')] [2023-03-11 10:32:37,814][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000000728_372736.pth... [2023-03-11 10:32:37,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000000000_0.pth [2023-03-11 10:32:40,503][04298] Updated weights for policy 0, policy_version 800 (0.0004) [2023-03-11 10:32:42,811][04011] Fps is (10 sec: 12697.5, 60 sec: 9648.3, 300 sec: 9648.3). Total num frames: 434176. Throughput: 0: 9612.7. Samples: 432572. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:32:42,812][04011] Avg episode reward: [(0, '0.000')] [2023-03-11 10:32:44,112][04298] Updated weights for policy 0, policy_version 880 (0.0005) [2023-03-11 10:32:47,811][04011] Fps is (10 sec: 11468.8, 60 sec: 9748.5, 300 sec: 9748.5). Total num frames: 487424. Throughput: 0: 10376.6. Samples: 466944. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-11 10:32:47,822][04011] Avg episode reward: [(0, '0.000')] [2023-03-11 10:32:47,866][04298] Updated weights for policy 0, policy_version 960 (0.0005) [2023-03-11 10:32:51,303][04298] Updated weights for policy 0, policy_version 1040 (0.0005) [2023-03-11 10:32:52,811][04011] Fps is (10 sec: 11468.7, 60 sec: 9979.3, 300 sec: 9979.3). Total num frames: 548864. Throughput: 0: 11905.1. Samples: 535732. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:32:52,822][04011] Avg episode reward: [(0, '0.000')] [2023-03-11 10:32:52,825][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000001072_548864.pth... [2023-03-11 10:32:52,827][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000000336_172032.pth [2023-03-11 10:32:54,830][04298] Updated weights for policy 0, policy_version 1120 (0.0004) [2023-03-11 10:32:57,811][04011] Fps is (10 sec: 11878.4, 60 sec: 10103.5, 300 sec: 10103.5). Total num frames: 606208. Throughput: 0: 12689.9. Samples: 603948. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:32:57,822][04011] Avg episode reward: [(0, '0.000')] [2023-03-11 10:32:58,443][04298] Updated weights for policy 0, policy_version 1200 (0.0005) [2023-03-11 10:33:02,068][04298] Updated weights for policy 0, policy_version 1280 (0.0005) [2023-03-11 10:33:02,811][04011] Fps is (10 sec: 11469.0, 60 sec: 11059.2, 300 sec: 10208.5). Total num frames: 663552. Throughput: 0: 12518.6. Samples: 638580. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-11 10:33:02,811][04011] Avg episode reward: [(0, '0.000')] [2023-03-11 10:33:05,573][04298] Updated weights for policy 0, policy_version 1360 (0.0004) [2023-03-11 10:33:07,811][04011] Fps is (10 sec: 11468.7, 60 sec: 12014.9, 300 sec: 10298.5). Total num frames: 720896. Throughput: 0: 12271.6. Samples: 708184. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-11 10:33:07,812][04011] Avg episode reward: [(0, '0.000')] [2023-03-11 10:33:07,814][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000001408_720896.pth... [2023-03-11 10:33:07,816][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000000728_372736.pth [2023-03-11 10:33:09,034][04298] Updated weights for policy 0, policy_version 1440 (0.0004) [2023-03-11 10:33:12,454][04298] Updated weights for policy 0, policy_version 1520 (0.0004) [2023-03-11 10:33:12,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12424.5, 300 sec: 10431.1). Total num frames: 782336. Throughput: 0: 12036.1. Samples: 779264. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:33:12,811][04011] Avg episode reward: [(0, '0.000')] [2023-03-11 10:33:15,919][04298] Updated weights for policy 0, policy_version 1600 (0.0004) [2023-03-11 10:33:17,811][04011] Fps is (10 sec: 11878.5, 60 sec: 12288.0, 300 sec: 10496.0). Total num frames: 839680. Throughput: 0: 11916.6. Samples: 814840. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-11 10:33:17,811][04011] Avg episode reward: [(0, '0.000')] [2023-03-11 10:33:19,420][04298] Updated weights for policy 0, policy_version 1680 (0.0004) [2023-03-11 10:33:22,811][04011] Fps is (10 sec: 11468.7, 60 sec: 12083.2, 300 sec: 10553.2). Total num frames: 897024. Throughput: 0: 11691.8. Samples: 884728. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:33:22,811][04011] Avg episode reward: [(0, '0.000')] [2023-03-11 10:33:22,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000001752_897024.pth... [2023-03-11 10:33:22,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000001072_548864.pth [2023-03-11 10:33:23,133][04298] Updated weights for policy 0, policy_version 1760 (0.0005) [2023-03-11 10:33:26,937][04298] Updated weights for policy 0, policy_version 1840 (0.0005) [2023-03-11 10:33:27,811][04011] Fps is (10 sec: 11059.2, 60 sec: 11878.4, 300 sec: 10558.6). Total num frames: 950272. Throughput: 0: 11479.4. Samples: 949144. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:33:27,811][04011] Avg episode reward: [(0, '0.000')] [2023-03-11 10:33:30,727][04298] Updated weights for policy 0, policy_version 1920 (0.0005) [2023-03-11 10:33:32,811][04011] Fps is (10 sec: 10649.6, 60 sec: 11605.3, 300 sec: 10563.4). Total num frames: 1003520. Throughput: 0: 11435.3. Samples: 981532. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-11 10:33:32,811][04011] Avg episode reward: [(0, '0.000')] [2023-03-11 10:33:34,657][04298] Updated weights for policy 0, policy_version 2000 (0.0005) [2023-03-11 10:33:37,811][04011] Fps is (10 sec: 10649.4, 60 sec: 11400.5, 300 sec: 10567.7). Total num frames: 1056768. Throughput: 0: 11295.6. Samples: 1044036. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-11 10:33:37,812][04011] Avg episode reward: [(0, '0.000')] [2023-03-11 10:33:37,816][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000002064_1056768.pth... [2023-03-11 10:33:37,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000001408_720896.pth [2023-03-11 10:33:38,584][04298] Updated weights for policy 0, policy_version 2080 (0.0005) [2023-03-11 10:33:42,467][04298] Updated weights for policy 0, policy_version 2160 (0.0005) [2023-03-11 10:33:42,811][04011] Fps is (10 sec: 10240.1, 60 sec: 11195.8, 300 sec: 10532.6). Total num frames: 1105920. Throughput: 0: 11172.4. Samples: 1106704. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-11 10:33:42,811][04011] Avg episode reward: [(0, '0.000')] [2023-03-11 10:33:46,289][04298] Updated weights for policy 0, policy_version 2240 (0.0005) [2023-03-11 10:33:47,811][04011] Fps is (10 sec: 10649.7, 60 sec: 11264.0, 300 sec: 10575.1). Total num frames: 1163264. Throughput: 0: 11115.1. Samples: 1138760. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:33:47,822][04011] Avg episode reward: [(0, '0.000')] [2023-03-11 10:33:50,184][04298] Updated weights for policy 0, policy_version 2320 (0.0005) [2023-03-11 10:33:52,811][04011] Fps is (10 sec: 10649.5, 60 sec: 11059.2, 300 sec: 10542.7). Total num frames: 1212416. Throughput: 0: 10987.3. Samples: 1202612. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 10:33:52,822][04011] Avg episode reward: [(0, '0.000')] [2023-03-11 10:33:52,849][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000002376_1216512.pth... [2023-03-11 10:33:52,850][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000001752_897024.pth [2023-03-11 10:33:53,969][04298] Updated weights for policy 0, policy_version 2400 (0.0004) [2023-03-11 10:33:57,779][04298] Updated weights for policy 0, policy_version 2480 (0.0005) [2023-03-11 10:33:57,811][04011] Fps is (10 sec: 10649.7, 60 sec: 11059.2, 300 sec: 10581.3). Total num frames: 1269760. Throughput: 0: 10844.4. Samples: 1267264. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-11 10:33:57,822][04011] Avg episode reward: [(0, '0.000')] [2023-03-11 10:34:01,551][04298] Updated weights for policy 0, policy_version 2560 (0.0005) [2023-03-11 10:34:02,811][04011] Fps is (10 sec: 11059.2, 60 sec: 10990.9, 300 sec: 10584.1). Total num frames: 1323008. Throughput: 0: 10766.0. Samples: 1299312. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-11 10:34:02,822][04011] Avg episode reward: [(0, '0.000')] [2023-03-11 10:34:05,324][04298] Updated weights for policy 0, policy_version 2640 (0.0005) [2023-03-11 10:34:07,811][04011] Fps is (10 sec: 10649.6, 60 sec: 10922.7, 300 sec: 10586.6). Total num frames: 1376256. Throughput: 0: 10680.4. Samples: 1365348. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-11 10:34:07,822][04011] Avg episode reward: [(0, '0.000')] [2023-03-11 10:34:07,824][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000002696_1380352.pth... [2023-03-11 10:34:07,826][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000002064_1056768.pth [2023-03-11 10:34:08,949][04298] Updated weights for policy 0, policy_version 2720 (0.0005) [2023-03-11 10:34:12,647][04298] Updated weights for policy 0, policy_version 2800 (0.0005) [2023-03-11 10:34:12,811][04011] Fps is (10 sec: 11059.3, 60 sec: 10854.4, 300 sec: 10619.3). Total num frames: 1433600. Throughput: 0: 10751.5. Samples: 1432960. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-11 10:34:12,811][04011] Avg episode reward: [(0, '0.000')] [2023-03-11 10:34:16,307][04298] Updated weights for policy 0, policy_version 2880 (0.0004) [2023-03-11 10:34:17,811][04011] Fps is (10 sec: 11468.8, 60 sec: 10854.4, 300 sec: 10649.6). Total num frames: 1490944. Throughput: 0: 10775.7. Samples: 1466440. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-11 10:34:17,812][04011] Avg episode reward: [(0, '0.000')] [2023-03-11 10:34:19,989][04298] Updated weights for policy 0, policy_version 2960 (0.0005) [2023-03-11 10:34:22,811][04011] Fps is (10 sec: 11468.8, 60 sec: 10854.4, 300 sec: 10677.8). Total num frames: 1548288. Throughput: 0: 10909.1. Samples: 1534944. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:34:22,811][04011] Avg episode reward: [(0, '0.000')] [2023-03-11 10:34:22,814][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000003024_1548288.pth... [2023-03-11 10:34:22,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000002376_1216512.pth [2023-03-11 10:34:23,328][04298] Updated weights for policy 0, policy_version 3040 (0.0004) [2023-03-11 10:34:27,014][04298] Updated weights for policy 0, policy_version 3120 (0.0005) [2023-03-11 10:34:27,811][04011] Fps is (10 sec: 11468.8, 60 sec: 10922.7, 300 sec: 10704.2). Total num frames: 1605632. Throughput: 0: 11037.2. Samples: 1603380. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:34:27,811][04011] Avg episode reward: [(0, '0.000')] [2023-03-11 10:34:30,855][04298] Updated weights for policy 0, policy_version 3200 (0.0005) [2023-03-11 10:34:32,811][04011] Fps is (10 sec: 11059.2, 60 sec: 10922.7, 300 sec: 10702.5). Total num frames: 1658880. Throughput: 0: 11028.7. Samples: 1635048. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-11 10:34:32,811][04011] Avg episode reward: [(0, '0.000')] [2023-03-11 10:34:34,668][04298] Updated weights for policy 0, policy_version 3280 (0.0004) [2023-03-11 10:34:37,811][04011] Fps is (10 sec: 10649.6, 60 sec: 10922.7, 300 sec: 10700.8). Total num frames: 1712128. Throughput: 0: 11054.0. Samples: 1700040. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-11 10:34:37,822][04011] Avg episode reward: [(0, '0.000')] [2023-03-11 10:34:37,825][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000003344_1712128.pth... [2023-03-11 10:34:37,828][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000002696_1380352.pth [2023-03-11 10:34:38,432][04298] Updated weights for policy 0, policy_version 3360 (0.0005) [2023-03-11 10:34:42,224][04298] Updated weights for policy 0, policy_version 3440 (0.0005) [2023-03-11 10:34:42,811][04011] Fps is (10 sec: 10649.7, 60 sec: 10990.9, 300 sec: 10699.3). Total num frames: 1765376. Throughput: 0: 11069.4. Samples: 1765384. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:34:42,822][04011] Avg episode reward: [(0, '0.000')] [2023-03-11 10:34:45,997][04298] Updated weights for policy 0, policy_version 3520 (0.0005) [2023-03-11 10:34:47,811][04011] Fps is (10 sec: 10649.6, 60 sec: 10922.7, 300 sec: 10697.8). Total num frames: 1818624. Throughput: 0: 11075.7. Samples: 1797720. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:34:47,822][04011] Avg episode reward: [(0, '0.000')] [2023-03-11 10:34:49,771][04298] Updated weights for policy 0, policy_version 3600 (0.0003) [2023-03-11 10:34:52,811][04011] Fps is (10 sec: 10649.6, 60 sec: 10991.0, 300 sec: 10696.4). Total num frames: 1871872. Throughput: 0: 11056.4. Samples: 1862884. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-11 10:34:52,811][04011] Avg episode reward: [(0, '0.000')] [2023-03-11 10:34:52,832][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000003664_1875968.pth... [2023-03-11 10:34:52,834][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000003024_1548288.pth [2023-03-11 10:34:53,580][04298] Updated weights for policy 0, policy_version 3680 (0.0005) [2023-03-11 10:34:57,263][04298] Updated weights for policy 0, policy_version 3760 (0.0005) [2023-03-11 10:34:57,811][04011] Fps is (10 sec: 11059.3, 60 sec: 10990.9, 300 sec: 10717.9). Total num frames: 1929216. Throughput: 0: 11018.8. Samples: 1928804. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:34:57,811][04011] Avg episode reward: [(0, '0.000')] [2023-03-11 10:35:00,956][04298] Updated weights for policy 0, policy_version 3840 (0.0005) [2023-03-11 10:35:02,811][04011] Fps is (10 sec: 11468.7, 60 sec: 11059.2, 300 sec: 10738.2). Total num frames: 1986560. Throughput: 0: 11012.1. Samples: 1961984. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:35:02,811][04011] Avg episode reward: [(0, '0.001')] [2023-03-11 10:35:04,520][04298] Updated weights for policy 0, policy_version 3920 (0.0004) [2023-03-11 10:35:07,811][04011] Fps is (10 sec: 11468.6, 60 sec: 11127.5, 300 sec: 10757.4). Total num frames: 2043904. Throughput: 0: 11034.2. Samples: 2031484. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-11 10:35:07,812][04011] Avg episode reward: [(0, '0.000')] [2023-03-11 10:35:07,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000003992_2043904.pth... [2023-03-11 10:35:07,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000003344_1712128.pth [2023-03-11 10:35:07,966][04298] Updated weights for policy 0, policy_version 4000 (0.0005) [2023-03-11 10:35:11,361][04298] Updated weights for policy 0, policy_version 4080 (0.0004) [2023-03-11 10:35:12,811][04011] Fps is (10 sec: 11878.4, 60 sec: 11195.7, 300 sec: 10796.6). Total num frames: 2105344. Throughput: 0: 11121.0. Samples: 2103824. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:35:12,811][04011] Avg episode reward: [(0, '0.000')] [2023-03-11 10:35:14,715][04298] Updated weights for policy 0, policy_version 4160 (0.0004) [2023-03-11 10:35:17,811][04011] Fps is (10 sec: 11878.5, 60 sec: 11195.7, 300 sec: 10813.4). Total num frames: 2162688. Throughput: 0: 11222.6. Samples: 2140064. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:35:17,811][04011] Avg episode reward: [(0, '0.002')] [2023-03-11 10:35:17,812][04254] Saving new best policy, reward=0.002! [2023-03-11 10:35:18,198][04298] Updated weights for policy 0, policy_version 4240 (0.0005) [2023-03-11 10:35:21,718][04298] Updated weights for policy 0, policy_version 4320 (0.0005) [2023-03-11 10:35:22,811][04011] Fps is (10 sec: 11878.4, 60 sec: 11264.0, 300 sec: 10849.4). Total num frames: 2224128. Throughput: 0: 11339.8. Samples: 2210332. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-11 10:35:22,811][04011] Avg episode reward: [(0, '0.002')] [2023-03-11 10:35:22,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000004344_2224128.pth... [2023-03-11 10:35:22,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000003664_1875968.pth [2023-03-11 10:35:25,153][04298] Updated weights for policy 0, policy_version 4400 (0.0005) [2023-03-11 10:35:27,811][04011] Fps is (10 sec: 11878.4, 60 sec: 11264.0, 300 sec: 10864.2). Total num frames: 2281472. Throughput: 0: 11470.2. Samples: 2281544. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:35:27,811][04011] Avg episode reward: [(0, '0.000')] [2023-03-11 10:35:28,530][04298] Updated weights for policy 0, policy_version 4480 (0.0004) [2023-03-11 10:35:32,088][04298] Updated weights for policy 0, policy_version 4560 (0.0004) [2023-03-11 10:35:32,811][04011] Fps is (10 sec: 11878.5, 60 sec: 11400.5, 300 sec: 10897.3). Total num frames: 2342912. Throughput: 0: 11546.1. Samples: 2317292. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-11 10:35:32,811][04011] Avg episode reward: [(0, '0.000')] [2023-03-11 10:35:35,848][04298] Updated weights for policy 0, policy_version 4640 (0.0005) [2023-03-11 10:35:37,811][04011] Fps is (10 sec: 11468.8, 60 sec: 11400.5, 300 sec: 10891.6). Total num frames: 2396160. Throughput: 0: 11578.9. Samples: 2383936. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-11 10:35:37,811][04011] Avg episode reward: [(0, '0.000')] [2023-03-11 10:35:37,814][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000004680_2396160.pth... [2023-03-11 10:35:37,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000003992_2043904.pth [2023-03-11 10:35:39,294][04298] Updated weights for policy 0, policy_version 4720 (0.0005) [2023-03-11 10:35:42,759][04298] Updated weights for policy 0, policy_version 4800 (0.0004) [2023-03-11 10:35:42,811][04011] Fps is (10 sec: 11468.7, 60 sec: 11537.1, 300 sec: 10922.7). Total num frames: 2457600. Throughput: 0: 11705.9. Samples: 2455572. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:35:42,811][04011] Avg episode reward: [(0, '0.000')] [2023-03-11 10:35:46,281][04298] Updated weights for policy 0, policy_version 4880 (0.0004) [2023-03-11 10:35:47,811][04011] Fps is (10 sec: 11878.4, 60 sec: 11605.3, 300 sec: 10934.5). Total num frames: 2514944. Throughput: 0: 11743.3. Samples: 2490432. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-11 10:35:47,811][04011] Avg episode reward: [(0, '0.000')] [2023-03-11 10:35:49,707][04298] Updated weights for policy 0, policy_version 4960 (0.0005) [2023-03-11 10:35:52,811][04011] Fps is (10 sec: 11878.4, 60 sec: 11741.8, 300 sec: 10963.3). Total num frames: 2576384. Throughput: 0: 11810.6. Samples: 2562960. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 10:35:52,812][04011] Avg episode reward: [(0, '0.001')] [2023-03-11 10:35:52,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000005032_2576384.pth... [2023-03-11 10:35:52,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000004344_2224128.pth [2023-03-11 10:35:53,011][04298] Updated weights for policy 0, policy_version 5040 (0.0005) [2023-03-11 10:35:56,402][04298] Updated weights for policy 0, policy_version 5120 (0.0004) [2023-03-11 10:35:57,811][04011] Fps is (10 sec: 12288.0, 60 sec: 11810.1, 300 sec: 10990.9). Total num frames: 2637824. Throughput: 0: 11796.4. Samples: 2634660. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:35:57,811][04011] Avg episode reward: [(0, '0.004')] [2023-03-11 10:35:57,812][04254] Saving new best policy, reward=0.004! [2023-03-11 10:35:59,768][04298] Updated weights for policy 0, policy_version 5200 (0.0004) [2023-03-11 10:36:02,811][04011] Fps is (10 sec: 11878.5, 60 sec: 11810.1, 300 sec: 11000.7). Total num frames: 2695168. Throughput: 0: 11825.0. Samples: 2672188. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:36:02,811][04011] Avg episode reward: [(0, '0.000')] [2023-03-11 10:36:03,150][04298] Updated weights for policy 0, policy_version 5280 (0.0004) [2023-03-11 10:36:06,536][04298] Updated weights for policy 0, policy_version 5360 (0.0004) [2023-03-11 10:36:07,811][04011] Fps is (10 sec: 11878.3, 60 sec: 11878.4, 300 sec: 11026.4). Total num frames: 2756608. Throughput: 0: 11867.8. Samples: 2744384. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-11 10:36:07,811][04011] Avg episode reward: [(0, '0.001')] [2023-03-11 10:36:07,814][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000005384_2756608.pth... [2023-03-11 10:36:07,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000004680_2396160.pth [2023-03-11 10:36:09,958][04298] Updated weights for policy 0, policy_version 5440 (0.0004) [2023-03-11 10:36:12,811][04011] Fps is (10 sec: 12288.0, 60 sec: 11878.4, 300 sec: 11051.2). Total num frames: 2818048. Throughput: 0: 11873.3. Samples: 2815840. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:36:12,811][04011] Avg episode reward: [(0, '0.000')] [2023-03-11 10:36:13,415][04298] Updated weights for policy 0, policy_version 5520 (0.0005) [2023-03-11 10:36:16,804][04298] Updated weights for policy 0, policy_version 5600 (0.0004) [2023-03-11 10:36:17,811][04011] Fps is (10 sec: 11878.6, 60 sec: 11878.4, 300 sec: 11059.2). Total num frames: 2875392. Throughput: 0: 11868.9. Samples: 2851392. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:36:17,811][04011] Avg episode reward: [(0, '0.000')] [2023-03-11 10:36:20,374][04298] Updated weights for policy 0, policy_version 5680 (0.0005) [2023-03-11 10:36:22,811][04011] Fps is (10 sec: 11468.7, 60 sec: 11810.1, 300 sec: 11066.9). Total num frames: 2932736. Throughput: 0: 11959.7. Samples: 2922124. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:36:22,811][04011] Avg episode reward: [(0, '0.000')] [2023-03-11 10:36:22,814][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000005728_2932736.pth... [2023-03-11 10:36:22,816][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000005032_2576384.pth [2023-03-11 10:36:23,902][04298] Updated weights for policy 0, policy_version 5760 (0.0005) [2023-03-11 10:36:27,264][04298] Updated weights for policy 0, policy_version 5840 (0.0004) [2023-03-11 10:36:27,811][04011] Fps is (10 sec: 11878.4, 60 sec: 11878.4, 300 sec: 11089.5). Total num frames: 2994176. Throughput: 0: 11963.7. Samples: 2993936. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:36:27,811][04011] Avg episode reward: [(0, '0.000')] [2023-03-11 10:36:30,715][04298] Updated weights for policy 0, policy_version 5920 (0.0004) [2023-03-11 10:36:32,811][04011] Fps is (10 sec: 11878.4, 60 sec: 11810.1, 300 sec: 11096.4). Total num frames: 3051520. Throughput: 0: 11966.0. Samples: 3028904. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:36:32,812][04011] Avg episode reward: [(0, '0.000')] [2023-03-11 10:36:34,366][04298] Updated weights for policy 0, policy_version 6000 (0.0005) [2023-03-11 10:36:37,811][04011] Fps is (10 sec: 11468.7, 60 sec: 11878.4, 300 sec: 11103.1). Total num frames: 3108864. Throughput: 0: 11859.7. Samples: 3096648. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:36:37,812][04011] Avg episode reward: [(0, '0.000')] [2023-03-11 10:36:37,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000006072_3108864.pth... [2023-03-11 10:36:37,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000005384_2756608.pth [2023-03-11 10:36:38,044][04298] Updated weights for policy 0, policy_version 6080 (0.0005) [2023-03-11 10:36:41,951][04298] Updated weights for policy 0, policy_version 6160 (0.0005) [2023-03-11 10:36:42,811][04011] Fps is (10 sec: 11059.2, 60 sec: 11741.9, 300 sec: 11095.1). Total num frames: 3162112. Throughput: 0: 11698.0. Samples: 3161072. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-11 10:36:42,812][04011] Avg episode reward: [(0, '0.000')] [2023-03-11 10:36:45,673][04298] Updated weights for policy 0, policy_version 6240 (0.0004) [2023-03-11 10:36:47,811][04011] Fps is (10 sec: 10649.7, 60 sec: 11673.6, 300 sec: 11087.4). Total num frames: 3215360. Throughput: 0: 11599.6. Samples: 3194168. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-11 10:36:47,811][04011] Avg episode reward: [(0, '0.028')] [2023-03-11 10:36:47,812][04254] Saving new best policy, reward=0.028! [2023-03-11 10:36:49,401][04298] Updated weights for policy 0, policy_version 6320 (0.0005) [2023-03-11 10:36:52,811][04011] Fps is (10 sec: 11059.3, 60 sec: 11605.4, 300 sec: 11093.9). Total num frames: 3272704. Throughput: 0: 11465.3. Samples: 3260320. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:36:52,811][04011] Avg episode reward: [(0, '0.000')] [2023-03-11 10:36:52,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000006392_3272704.pth... [2023-03-11 10:36:52,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000005728_2932736.pth [2023-03-11 10:36:53,100][04298] Updated weights for policy 0, policy_version 6400 (0.0005) [2023-03-11 10:36:56,820][04298] Updated weights for policy 0, policy_version 6480 (0.0004) [2023-03-11 10:36:57,811][04011] Fps is (10 sec: 11059.2, 60 sec: 11468.8, 300 sec: 11274.4). Total num frames: 3325952. Throughput: 0: 11335.8. Samples: 3325952. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:36:57,811][04011] Avg episode reward: [(0, '0.000')] [2023-03-11 10:37:00,512][04298] Updated weights for policy 0, policy_version 6560 (0.0004) [2023-03-11 10:37:02,811][04011] Fps is (10 sec: 11059.1, 60 sec: 11468.8, 300 sec: 11468.8). Total num frames: 3383296. Throughput: 0: 11277.0. Samples: 3358860. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:37:02,811][04011] Avg episode reward: [(0, '0.000')] [2023-03-11 10:37:04,169][04298] Updated weights for policy 0, policy_version 6640 (0.0005) [2023-03-11 10:37:07,811][04011] Fps is (10 sec: 11059.2, 60 sec: 11332.3, 300 sec: 11524.3). Total num frames: 3436544. Throughput: 0: 11204.1. Samples: 3426308. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-11 10:37:07,812][04011] Avg episode reward: [(0, '0.001')] [2023-03-11 10:37:07,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000006712_3436544.pth... [2023-03-11 10:37:07,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000006072_3108864.pth [2023-03-11 10:37:07,901][04298] Updated weights for policy 0, policy_version 6720 (0.0005) [2023-03-11 10:37:11,510][04298] Updated weights for policy 0, policy_version 6800 (0.0005) [2023-03-11 10:37:12,811][04011] Fps is (10 sec: 11059.1, 60 sec: 11264.0, 300 sec: 11496.6). Total num frames: 3493888. Throughput: 0: 11109.6. Samples: 3493868. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-11 10:37:12,812][04011] Avg episode reward: [(0, '0.016')] [2023-03-11 10:37:15,181][04298] Updated weights for policy 0, policy_version 6880 (0.0005) [2023-03-11 10:37:17,811][04011] Fps is (10 sec: 11468.9, 60 sec: 11264.0, 300 sec: 11454.9). Total num frames: 3551232. Throughput: 0: 11062.8. Samples: 3526728. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-11 10:37:17,811][04011] Avg episode reward: [(0, '0.000')] [2023-03-11 10:37:18,830][04298] Updated weights for policy 0, policy_version 6960 (0.0005) [2023-03-11 10:37:22,226][04298] Updated weights for policy 0, policy_version 7040 (0.0005) [2023-03-11 10:37:22,811][04011] Fps is (10 sec: 11468.8, 60 sec: 11264.0, 300 sec: 11427.1). Total num frames: 3608576. Throughput: 0: 11100.3. Samples: 3596160. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-11 10:37:22,812][04011] Avg episode reward: [(0, '0.000')] [2023-03-11 10:37:22,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000007048_3608576.pth... [2023-03-11 10:37:22,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000006392_3272704.pth [2023-03-11 10:37:25,872][04298] Updated weights for policy 0, policy_version 7120 (0.0005) [2023-03-11 10:37:27,811][04011] Fps is (10 sec: 11468.7, 60 sec: 11195.7, 300 sec: 11385.5). Total num frames: 3665920. Throughput: 0: 11175.0. Samples: 3663948. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:37:27,811][04011] Avg episode reward: [(0, '0.000')] [2023-03-11 10:37:29,527][04298] Updated weights for policy 0, policy_version 7200 (0.0005) [2023-03-11 10:37:32,811][04011] Fps is (10 sec: 11059.2, 60 sec: 11127.5, 300 sec: 11343.8). Total num frames: 3719168. Throughput: 0: 11204.8. Samples: 3698384. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:37:32,812][04011] Avg episode reward: [(0, '0.000')] [2023-03-11 10:37:33,204][04298] Updated weights for policy 0, policy_version 7280 (0.0005) [2023-03-11 10:37:36,687][04298] Updated weights for policy 0, policy_version 7360 (0.0004) [2023-03-11 10:37:37,811][04011] Fps is (10 sec: 11468.8, 60 sec: 11195.7, 300 sec: 11343.8). Total num frames: 3780608. Throughput: 0: 11251.4. Samples: 3766636. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:37:37,811][04011] Avg episode reward: [(0, '0.000')] [2023-03-11 10:37:37,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000007384_3780608.pth... [2023-03-11 10:37:37,816][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000006712_3436544.pth [2023-03-11 10:37:40,509][04298] Updated weights for policy 0, policy_version 7440 (0.0005) [2023-03-11 10:37:42,811][04011] Fps is (10 sec: 11468.8, 60 sec: 11195.7, 300 sec: 11343.8). Total num frames: 3833856. Throughput: 0: 11254.5. Samples: 3832404. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:37:42,811][04011] Avg episode reward: [(0, '0.000')] [2023-03-11 10:37:44,235][04298] Updated weights for policy 0, policy_version 7520 (0.0005) [2023-03-11 10:37:47,811][04011] Fps is (10 sec: 10649.6, 60 sec: 11195.7, 300 sec: 11316.1). Total num frames: 3887104. Throughput: 0: 11224.1. Samples: 3863944. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:37:47,811][04011] Avg episode reward: [(0, '0.105')] [2023-03-11 10:37:47,812][04254] Saving new best policy, reward=0.105! [2023-03-11 10:37:48,084][04298] Updated weights for policy 0, policy_version 7600 (0.0005) [2023-03-11 10:37:51,731][04298] Updated weights for policy 0, policy_version 7680 (0.0005) [2023-03-11 10:37:52,811][04011] Fps is (10 sec: 11059.3, 60 sec: 11195.7, 300 sec: 11316.1). Total num frames: 3944448. Throughput: 0: 11201.7. Samples: 3930384. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-11 10:37:52,811][04011] Avg episode reward: [(0, '0.000')] [2023-03-11 10:37:52,814][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000007704_3944448.pth... [2023-03-11 10:37:52,815][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000007048_3608576.pth [2023-03-11 10:37:55,415][04298] Updated weights for policy 0, policy_version 7760 (0.0003) [2023-03-11 10:37:57,811][04011] Fps is (10 sec: 11059.2, 60 sec: 11195.7, 300 sec: 11302.2). Total num frames: 3997696. Throughput: 0: 11188.9. Samples: 3997368. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:37:57,811][04011] Avg episode reward: [(0, '0.000')] [2023-03-11 10:37:59,107][04298] Updated weights for policy 0, policy_version 7840 (0.0003) [2023-03-11 10:38:02,656][04298] Updated weights for policy 0, policy_version 7920 (0.0003) [2023-03-11 10:38:02,811][04011] Fps is (10 sec: 11059.1, 60 sec: 11195.7, 300 sec: 11302.2). Total num frames: 4055040. Throughput: 0: 11200.7. Samples: 4030760. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:38:02,811][04011] Avg episode reward: [(0, '0.017')] [2023-03-11 10:38:06,580][04298] Updated weights for policy 0, policy_version 8000 (0.0003) [2023-03-11 10:38:07,811][04011] Fps is (10 sec: 11059.1, 60 sec: 11195.7, 300 sec: 11274.4). Total num frames: 4108288. Throughput: 0: 11107.6. Samples: 4096000. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:38:07,812][04011] Avg episode reward: [(0, '0.000')] [2023-03-11 10:38:07,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000008024_4108288.pth... [2023-03-11 10:38:07,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000007384_3780608.pth [2023-03-11 10:38:10,327][04298] Updated weights for policy 0, policy_version 8080 (0.0003) [2023-03-11 10:38:12,811][04011] Fps is (10 sec: 10649.6, 60 sec: 11127.5, 300 sec: 11260.5). Total num frames: 4161536. Throughput: 0: 11070.4. Samples: 4162116. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:38:12,812][04011] Avg episode reward: [(0, '0.000')] [2023-03-11 10:38:13,961][04298] Updated weights for policy 0, policy_version 8160 (0.0003) [2023-03-11 10:38:17,663][04298] Updated weights for policy 0, policy_version 8240 (0.0003) [2023-03-11 10:38:17,811][04011] Fps is (10 sec: 11059.2, 60 sec: 11127.5, 300 sec: 11260.5). Total num frames: 4218880. Throughput: 0: 11052.7. Samples: 4195756. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:38:17,811][04011] Avg episode reward: [(0, '0.005')] [2023-03-11 10:38:21,444][04298] Updated weights for policy 0, policy_version 8320 (0.0003) [2023-03-11 10:38:22,811][04011] Fps is (10 sec: 11059.2, 60 sec: 11059.2, 300 sec: 11260.5). Total num frames: 4272128. Throughput: 0: 10986.5. Samples: 4261028. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-11 10:38:22,812][04011] Avg episode reward: [(0, '0.000')] [2023-03-11 10:38:22,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000008344_4272128.pth... [2023-03-11 10:38:22,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000007704_3944448.pth [2023-03-11 10:38:25,132][04298] Updated weights for policy 0, policy_version 8400 (0.0003) [2023-03-11 10:38:27,811][04011] Fps is (10 sec: 11059.2, 60 sec: 11059.2, 300 sec: 11274.4). Total num frames: 4329472. Throughput: 0: 11002.8. Samples: 4327528. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-11 10:38:27,812][04011] Avg episode reward: [(0, '0.000')] [2023-03-11 10:38:28,901][04298] Updated weights for policy 0, policy_version 8480 (0.0003) [2023-03-11 10:38:32,748][04298] Updated weights for policy 0, policy_version 8560 (0.0003) [2023-03-11 10:38:32,811][04011] Fps is (10 sec: 11059.2, 60 sec: 11059.2, 300 sec: 11274.4). Total num frames: 4382720. Throughput: 0: 11007.6. Samples: 4359284. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-11 10:38:32,811][04011] Avg episode reward: [(0, '0.003')] [2023-03-11 10:38:36,488][04298] Updated weights for policy 0, policy_version 8640 (0.0003) [2023-03-11 10:38:37,811][04011] Fps is (10 sec: 10649.6, 60 sec: 10922.7, 300 sec: 11288.3). Total num frames: 4435968. Throughput: 0: 10973.3. Samples: 4424184. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-11 10:38:37,812][04011] Avg episode reward: [(0, '0.005')] [2023-03-11 10:38:37,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000008664_4435968.pth... [2023-03-11 10:38:37,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000008024_4108288.pth [2023-03-11 10:38:40,226][04298] Updated weights for policy 0, policy_version 8720 (0.0003) [2023-03-11 10:38:42,811][04011] Fps is (10 sec: 10649.6, 60 sec: 10922.7, 300 sec: 11274.4). Total num frames: 4489216. Throughput: 0: 10931.6. Samples: 4489288. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:38:42,811][04011] Avg episode reward: [(0, '0.018')] [2023-03-11 10:38:44,097][04298] Updated weights for policy 0, policy_version 8800 (0.0004) [2023-03-11 10:38:47,807][04298] Updated weights for policy 0, policy_version 8880 (0.0003) [2023-03-11 10:38:47,811][04011] Fps is (10 sec: 11059.3, 60 sec: 10990.9, 300 sec: 11302.2). Total num frames: 4546560. Throughput: 0: 10916.1. Samples: 4521984. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-11 10:38:47,811][04011] Avg episode reward: [(0, '0.000')] [2023-03-11 10:38:51,520][04298] Updated weights for policy 0, policy_version 8960 (0.0004) [2023-03-11 10:38:52,811][04011] Fps is (10 sec: 11059.1, 60 sec: 10922.6, 300 sec: 11288.3). Total num frames: 4599808. Throughput: 0: 10924.3. Samples: 4587592. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-11 10:38:52,812][04011] Avg episode reward: [(0, '0.011')] [2023-03-11 10:38:52,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000008984_4599808.pth... [2023-03-11 10:38:52,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000008344_4272128.pth [2023-03-11 10:38:55,169][04298] Updated weights for policy 0, policy_version 9040 (0.0004) [2023-03-11 10:38:57,811][04011] Fps is (10 sec: 11059.1, 60 sec: 10990.9, 300 sec: 11302.2). Total num frames: 4657152. Throughput: 0: 10973.0. Samples: 4655900. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-11 10:38:57,811][04011] Avg episode reward: [(0, '0.006')] [2023-03-11 10:38:58,848][04298] Updated weights for policy 0, policy_version 9120 (0.0004) [2023-03-11 10:39:02,608][04298] Updated weights for policy 0, policy_version 9200 (0.0003) [2023-03-11 10:39:02,811][04011] Fps is (10 sec: 11059.3, 60 sec: 10922.7, 300 sec: 11302.2). Total num frames: 4710400. Throughput: 0: 10930.3. Samples: 4687620. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-11 10:39:02,811][04011] Avg episode reward: [(0, '0.035')] [2023-03-11 10:39:06,299][04298] Updated weights for policy 0, policy_version 9280 (0.0004) [2023-03-11 10:39:07,811][04011] Fps is (10 sec: 10649.5, 60 sec: 10922.7, 300 sec: 11288.3). Total num frames: 4763648. Throughput: 0: 10968.3. Samples: 4754604. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-11 10:39:07,812][04011] Avg episode reward: [(0, '0.008')] [2023-03-11 10:39:07,837][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000009312_4767744.pth... [2023-03-11 10:39:07,839][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000008664_4435968.pth [2023-03-11 10:39:10,031][04298] Updated weights for policy 0, policy_version 9360 (0.0003) [2023-03-11 10:39:12,811][04011] Fps is (10 sec: 11059.2, 60 sec: 10990.9, 300 sec: 11288.3). Total num frames: 4820992. Throughput: 0: 10986.3. Samples: 4821912. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-11 10:39:12,812][04011] Avg episode reward: [(0, '0.033')] [2023-03-11 10:39:13,482][04298] Updated weights for policy 0, policy_version 9440 (0.0003) [2023-03-11 10:39:16,973][04298] Updated weights for policy 0, policy_version 9520 (0.0003) [2023-03-11 10:39:17,811][04011] Fps is (10 sec: 11878.5, 60 sec: 11059.2, 300 sec: 11302.2). Total num frames: 4882432. Throughput: 0: 11064.5. Samples: 4857188. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-11 10:39:17,811][04011] Avg episode reward: [(0, '0.108')] [2023-03-11 10:39:17,812][04254] Saving new best policy, reward=0.108! [2023-03-11 10:39:20,531][04298] Updated weights for policy 0, policy_version 9600 (0.0003) [2023-03-11 10:39:22,811][04011] Fps is (10 sec: 11878.4, 60 sec: 11127.5, 300 sec: 11302.2). Total num frames: 4939776. Throughput: 0: 11181.8. Samples: 4927364. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-11 10:39:22,812][04011] Avg episode reward: [(0, '0.062')] [2023-03-11 10:39:22,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000009648_4939776.pth... [2023-03-11 10:39:22,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000008984_4599808.pth [2023-03-11 10:39:24,337][04298] Updated weights for policy 0, policy_version 9680 (0.0003) [2023-03-11 10:39:27,811][04011] Fps is (10 sec: 11059.2, 60 sec: 11059.2, 300 sec: 11302.2). Total num frames: 4993024. Throughput: 0: 11146.3. Samples: 4990872. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-11 10:39:27,812][04011] Avg episode reward: [(0, '0.060')] [2023-03-11 10:39:28,138][04298] Updated weights for policy 0, policy_version 9760 (0.0003) [2023-03-11 10:39:31,900][04298] Updated weights for policy 0, policy_version 9840 (0.0003) [2023-03-11 10:39:32,811][04011] Fps is (10 sec: 10649.7, 60 sec: 11059.2, 300 sec: 11302.2). Total num frames: 5046272. Throughput: 0: 11156.6. Samples: 5024032. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-11 10:39:32,811][04011] Avg episode reward: [(0, '0.084')] [2023-03-11 10:39:35,813][04298] Updated weights for policy 0, policy_version 9920 (0.0003) [2023-03-11 10:39:37,811][04011] Fps is (10 sec: 10649.6, 60 sec: 11059.2, 300 sec: 11302.2). Total num frames: 5099520. Throughput: 0: 11102.6. Samples: 5087208. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:39:37,812][04011] Avg episode reward: [(0, '0.054')] [2023-03-11 10:39:37,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000009960_5099520.pth... [2023-03-11 10:39:37,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000009312_4767744.pth [2023-03-11 10:39:39,695][04298] Updated weights for policy 0, policy_version 10000 (0.0004) [2023-03-11 10:39:42,811][04011] Fps is (10 sec: 10239.9, 60 sec: 10990.9, 300 sec: 11288.3). Total num frames: 5148672. Throughput: 0: 10966.4. Samples: 5149388. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:39:42,812][04011] Avg episode reward: [(0, '0.113')] [2023-03-11 10:39:42,858][04254] Saving new best policy, reward=0.113! [2023-03-11 10:39:43,673][04298] Updated weights for policy 0, policy_version 10080 (0.0005) [2023-03-11 10:39:47,565][04298] Updated weights for policy 0, policy_version 10160 (0.0005) [2023-03-11 10:39:47,811][04011] Fps is (10 sec: 10240.0, 60 sec: 10922.7, 300 sec: 11288.3). Total num frames: 5201920. Throughput: 0: 10945.3. Samples: 5180160. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:39:47,812][04011] Avg episode reward: [(0, '0.149')] [2023-03-11 10:39:47,812][04254] Saving new best policy, reward=0.149! [2023-03-11 10:39:51,431][04298] Updated weights for policy 0, policy_version 10240 (0.0005) [2023-03-11 10:39:52,811][04011] Fps is (10 sec: 10649.6, 60 sec: 10922.7, 300 sec: 11274.4). Total num frames: 5255168. Throughput: 0: 10874.5. Samples: 5243956. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:39:52,812][04011] Avg episode reward: [(0, '0.108')] [2023-03-11 10:39:52,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000010264_5255168.pth... [2023-03-11 10:39:52,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000009648_4939776.pth [2023-03-11 10:39:55,318][04298] Updated weights for policy 0, policy_version 10320 (0.0005) [2023-03-11 10:39:57,811][04011] Fps is (10 sec: 10649.6, 60 sec: 10854.4, 300 sec: 11260.5). Total num frames: 5308416. Throughput: 0: 10812.8. Samples: 5308488. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:39:57,811][04011] Avg episode reward: [(0, '0.119')] [2023-03-11 10:39:58,917][04298] Updated weights for policy 0, policy_version 10400 (0.0005) [2023-03-11 10:40:02,458][04298] Updated weights for policy 0, policy_version 10480 (0.0004) [2023-03-11 10:40:02,811][04011] Fps is (10 sec: 11059.2, 60 sec: 10922.7, 300 sec: 11260.5). Total num frames: 5365760. Throughput: 0: 10822.9. Samples: 5344220. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:40:02,812][04011] Avg episode reward: [(0, '0.211')] [2023-03-11 10:40:02,842][04254] Saving new best policy, reward=0.211! [2023-03-11 10:40:06,091][04298] Updated weights for policy 0, policy_version 10560 (0.0004) [2023-03-11 10:40:07,811][04011] Fps is (10 sec: 11468.7, 60 sec: 10990.9, 300 sec: 11246.6). Total num frames: 5423104. Throughput: 0: 10770.6. Samples: 5412040. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:40:07,812][04011] Avg episode reward: [(0, '0.059')] [2023-03-11 10:40:07,837][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000010600_5427200.pth... [2023-03-11 10:40:07,838][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000009960_5099520.pth [2023-03-11 10:40:09,690][04298] Updated weights for policy 0, policy_version 10640 (0.0004) [2023-03-11 10:40:12,811][04011] Fps is (10 sec: 11468.8, 60 sec: 10990.9, 300 sec: 11246.6). Total num frames: 5480448. Throughput: 0: 10879.7. Samples: 5480460. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:40:12,812][04011] Avg episode reward: [(0, '0.000')] [2023-03-11 10:40:13,268][04298] Updated weights for policy 0, policy_version 10720 (0.0004) [2023-03-11 10:40:16,895][04298] Updated weights for policy 0, policy_version 10800 (0.0004) [2023-03-11 10:40:17,811][04011] Fps is (10 sec: 11468.9, 60 sec: 10922.7, 300 sec: 11232.8). Total num frames: 5537792. Throughput: 0: 10902.5. Samples: 5514644. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:40:17,811][04011] Avg episode reward: [(0, '0.000')] [2023-03-11 10:40:20,566][04298] Updated weights for policy 0, policy_version 10880 (0.0005) [2023-03-11 10:40:22,811][04011] Fps is (10 sec: 11468.7, 60 sec: 10922.7, 300 sec: 11232.8). Total num frames: 5595136. Throughput: 0: 10996.6. Samples: 5582056. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:40:22,812][04011] Avg episode reward: [(0, '0.000')] [2023-03-11 10:40:22,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000010928_5595136.pth... [2023-03-11 10:40:22,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000010264_5255168.pth [2023-03-11 10:40:24,108][04298] Updated weights for policy 0, policy_version 10960 (0.0004) [2023-03-11 10:40:27,615][04298] Updated weights for policy 0, policy_version 11040 (0.0005) [2023-03-11 10:40:27,811][04011] Fps is (10 sec: 11468.8, 60 sec: 10990.9, 300 sec: 11218.9). Total num frames: 5652480. Throughput: 0: 11177.8. Samples: 5652388. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-11 10:40:27,811][04011] Avg episode reward: [(0, '0.000')] [2023-03-11 10:40:31,156][04298] Updated weights for policy 0, policy_version 11120 (0.0004) [2023-03-11 10:40:32,811][04011] Fps is (10 sec: 11468.9, 60 sec: 11059.2, 300 sec: 11232.8). Total num frames: 5709824. Throughput: 0: 11254.3. Samples: 5686604. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:40:32,811][04011] Avg episode reward: [(0, '0.000')] [2023-03-11 10:40:35,019][04298] Updated weights for policy 0, policy_version 11200 (0.0005) [2023-03-11 10:40:37,811][04011] Fps is (10 sec: 11059.2, 60 sec: 11059.2, 300 sec: 11205.0). Total num frames: 5763072. Throughput: 0: 11263.0. Samples: 5750792. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:40:37,811][04011] Avg episode reward: [(0, '0.000')] [2023-03-11 10:40:37,814][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000011256_5763072.pth... [2023-03-11 10:40:37,816][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000010600_5427200.pth [2023-03-11 10:40:38,906][04298] Updated weights for policy 0, policy_version 11280 (0.0005) [2023-03-11 10:40:42,773][04298] Updated weights for policy 0, policy_version 11360 (0.0005) [2023-03-11 10:40:42,811][04011] Fps is (10 sec: 10649.5, 60 sec: 11127.5, 300 sec: 11191.1). Total num frames: 5816320. Throughput: 0: 11240.4. Samples: 5814308. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:40:42,812][04011] Avg episode reward: [(0, '0.000')] [2023-03-11 10:40:46,519][04298] Updated weights for policy 0, policy_version 11440 (0.0005) [2023-03-11 10:40:47,811][04011] Fps is (10 sec: 10649.7, 60 sec: 11127.5, 300 sec: 11163.3). Total num frames: 5869568. Throughput: 0: 11166.1. Samples: 5846692. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:40:47,818][04011] Avg episode reward: [(0, '0.000')] [2023-03-11 10:40:50,420][04298] Updated weights for policy 0, policy_version 11520 (0.0005) [2023-03-11 10:40:52,811][04011] Fps is (10 sec: 10649.6, 60 sec: 11127.5, 300 sec: 11135.6). Total num frames: 5922816. Throughput: 0: 11077.5. Samples: 5910528. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 10:40:52,822][04011] Avg episode reward: [(0, '0.000')] [2023-03-11 10:40:52,825][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000011568_5922816.pth... [2023-03-11 10:40:52,828][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000010928_5595136.pth [2023-03-11 10:40:54,320][04298] Updated weights for policy 0, policy_version 11600 (0.0005) [2023-03-11 10:40:57,811][04011] Fps is (10 sec: 10240.0, 60 sec: 11059.2, 300 sec: 11107.8). Total num frames: 5971968. Throughput: 0: 10922.6. Samples: 5971976. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 10:40:57,822][04011] Avg episode reward: [(0, '0.000')] [2023-03-11 10:40:58,363][04298] Updated weights for policy 0, policy_version 11680 (0.0005) [2023-03-11 10:41:02,247][04298] Updated weights for policy 0, policy_version 11760 (0.0005) [2023-03-11 10:41:02,811][04011] Fps is (10 sec: 10240.0, 60 sec: 10990.9, 300 sec: 11080.0). Total num frames: 6025216. Throughput: 0: 10860.7. Samples: 6003376. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:41:02,822][04011] Avg episode reward: [(0, '0.006')] [2023-03-11 10:41:06,076][04298] Updated weights for policy 0, policy_version 11840 (0.0005) [2023-03-11 10:41:07,811][04011] Fps is (10 sec: 10649.6, 60 sec: 10922.7, 300 sec: 11052.3). Total num frames: 6078464. Throughput: 0: 10785.4. Samples: 6067400. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:41:07,822][04011] Avg episode reward: [(0, '0.000')] [2023-03-11 10:41:07,825][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000011872_6078464.pth... [2023-03-11 10:41:07,828][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000011256_5763072.pth [2023-03-11 10:41:09,880][04298] Updated weights for policy 0, policy_version 11920 (0.0005) [2023-03-11 10:41:12,811][04011] Fps is (10 sec: 10649.5, 60 sec: 10854.4, 300 sec: 11038.4). Total num frames: 6131712. Throughput: 0: 10645.0. Samples: 6131412. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:41:12,812][04011] Avg episode reward: [(0, '0.000')] [2023-03-11 10:41:13,726][04298] Updated weights for policy 0, policy_version 12000 (0.0005) [2023-03-11 10:41:17,303][04298] Updated weights for policy 0, policy_version 12080 (0.0004) [2023-03-11 10:41:17,811][04011] Fps is (10 sec: 11059.2, 60 sec: 10854.4, 300 sec: 11038.4). Total num frames: 6189056. Throughput: 0: 10621.0. Samples: 6164552. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:41:17,812][04011] Avg episode reward: [(0, '0.000')] [2023-03-11 10:41:20,826][04298] Updated weights for policy 0, policy_version 12160 (0.0004) [2023-03-11 10:41:22,811][04011] Fps is (10 sec: 11468.8, 60 sec: 10854.4, 300 sec: 11024.5). Total num frames: 6246400. Throughput: 0: 10740.6. Samples: 6234120. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:41:22,811][04011] Avg episode reward: [(0, '0.000')] [2023-03-11 10:41:22,814][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000012200_6246400.pth... [2023-03-11 10:41:22,816][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000011568_5922816.pth [2023-03-11 10:41:24,380][04298] Updated weights for policy 0, policy_version 12240 (0.0004) [2023-03-11 10:41:27,811][04011] Fps is (10 sec: 11468.8, 60 sec: 10854.4, 300 sec: 11024.5). Total num frames: 6303744. Throughput: 0: 10875.5. Samples: 6303704. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-11 10:41:27,812][04011] Avg episode reward: [(0, '0.000')] [2023-03-11 10:41:27,945][04298] Updated weights for policy 0, policy_version 12320 (0.0004) [2023-03-11 10:41:31,591][04298] Updated weights for policy 0, policy_version 12400 (0.0005) [2023-03-11 10:41:32,811][04011] Fps is (10 sec: 11468.8, 60 sec: 10854.4, 300 sec: 11024.5). Total num frames: 6361088. Throughput: 0: 10895.2. Samples: 6336976. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-11 10:41:32,811][04011] Avg episode reward: [(0, '0.000')] [2023-03-11 10:41:35,436][04298] Updated weights for policy 0, policy_version 12480 (0.0005) [2023-03-11 10:41:37,811][04011] Fps is (10 sec: 11059.1, 60 sec: 10854.4, 300 sec: 11024.5). Total num frames: 6414336. Throughput: 0: 10922.8. Samples: 6402056. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:41:37,812][04011] Avg episode reward: [(0, '0.000')] [2023-03-11 10:41:37,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000012528_6414336.pth... [2023-03-11 10:41:37,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000011872_6078464.pth [2023-03-11 10:41:39,188][04298] Updated weights for policy 0, policy_version 12560 (0.0005) [2023-03-11 10:41:42,811][04011] Fps is (10 sec: 10649.6, 60 sec: 10854.4, 300 sec: 11024.5). Total num frames: 6467584. Throughput: 0: 11004.3. Samples: 6467168. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:41:42,812][04011] Avg episode reward: [(0, '0.000')] [2023-03-11 10:41:43,069][04298] Updated weights for policy 0, policy_version 12640 (0.0005) [2023-03-11 10:41:46,948][04298] Updated weights for policy 0, policy_version 12720 (0.0005) [2023-03-11 10:41:47,811][04011] Fps is (10 sec: 10649.7, 60 sec: 10854.4, 300 sec: 11010.6). Total num frames: 6520832. Throughput: 0: 10990.8. Samples: 6497964. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:41:47,812][04011] Avg episode reward: [(0, '0.000')] [2023-03-11 10:41:50,845][04298] Updated weights for policy 0, policy_version 12800 (0.0005) [2023-03-11 10:41:52,811][04011] Fps is (10 sec: 10240.0, 60 sec: 10786.1, 300 sec: 10996.7). Total num frames: 6569984. Throughput: 0: 10981.6. Samples: 6561572. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:41:52,822][04011] Avg episode reward: [(0, '0.000')] [2023-03-11 10:41:52,877][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000012840_6574080.pth... [2023-03-11 10:41:52,879][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000012200_6246400.pth [2023-03-11 10:41:54,815][04298] Updated weights for policy 0, policy_version 12880 (0.0005) [2023-03-11 10:41:57,811][04011] Fps is (10 sec: 10240.0, 60 sec: 10854.4, 300 sec: 10982.8). Total num frames: 6623232. Throughput: 0: 10904.5. Samples: 6622116. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:41:57,822][04011] Avg episode reward: [(0, '0.000')] [2023-03-11 10:41:58,844][04298] Updated weights for policy 0, policy_version 12960 (0.0005) [2023-03-11 10:42:02,690][04298] Updated weights for policy 0, policy_version 13040 (0.0005) [2023-03-11 10:42:02,811][04011] Fps is (10 sec: 10649.7, 60 sec: 10854.4, 300 sec: 10982.8). Total num frames: 6676480. Throughput: 0: 10878.7. Samples: 6654092. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:42:02,822][04011] Avg episode reward: [(0, '0.000')] [2023-03-11 10:42:06,537][04298] Updated weights for policy 0, policy_version 13120 (0.0005) [2023-03-11 10:42:07,811][04011] Fps is (10 sec: 10649.6, 60 sec: 10854.4, 300 sec: 10969.0). Total num frames: 6729728. Throughput: 0: 10742.0. Samples: 6717512. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:42:07,822][04011] Avg episode reward: [(0, '0.015')] [2023-03-11 10:42:07,825][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000013144_6729728.pth... [2023-03-11 10:42:07,827][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000012528_6414336.pth [2023-03-11 10:42:10,516][04298] Updated weights for policy 0, policy_version 13200 (0.0005) [2023-03-11 10:42:12,811][04011] Fps is (10 sec: 10649.6, 60 sec: 10854.4, 300 sec: 10955.1). Total num frames: 6782976. Throughput: 0: 10584.5. Samples: 6780008. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:42:12,811][04011] Avg episode reward: [(0, '0.015')] [2023-03-11 10:42:14,319][04298] Updated weights for policy 0, policy_version 13280 (0.0005) [2023-03-11 10:42:17,811][04011] Fps is (10 sec: 10649.6, 60 sec: 10786.1, 300 sec: 10941.2). Total num frames: 6836224. Throughput: 0: 10574.1. Samples: 6812808. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-11 10:42:17,812][04011] Avg episode reward: [(0, '0.034')] [2023-03-11 10:42:18,071][04298] Updated weights for policy 0, policy_version 13360 (0.0005) [2023-03-11 10:42:21,646][04298] Updated weights for policy 0, policy_version 13440 (0.0004) [2023-03-11 10:42:22,811][04011] Fps is (10 sec: 11059.1, 60 sec: 10786.1, 300 sec: 10941.2). Total num frames: 6893568. Throughput: 0: 10624.4. Samples: 6880152. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-11 10:42:22,812][04011] Avg episode reward: [(0, '0.083')] [2023-03-11 10:42:22,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000013464_6893568.pth... [2023-03-11 10:42:22,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000012840_6574080.pth [2023-03-11 10:42:25,324][04298] Updated weights for policy 0, policy_version 13520 (0.0003) [2023-03-11 10:42:27,811][04011] Fps is (10 sec: 11059.2, 60 sec: 10717.9, 300 sec: 10941.2). Total num frames: 6946816. Throughput: 0: 10626.9. Samples: 6945380. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:42:27,812][04011] Avg episode reward: [(0, '0.060')] [2023-03-11 10:42:29,415][04298] Updated weights for policy 0, policy_version 13600 (0.0003) [2023-03-11 10:42:32,811][04011] Fps is (10 sec: 10240.1, 60 sec: 10581.4, 300 sec: 10899.5). Total num frames: 6995968. Throughput: 0: 10611.7. Samples: 6975488. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:42:32,811][04011] Avg episode reward: [(0, '0.000')] [2023-03-11 10:42:33,313][04298] Updated weights for policy 0, policy_version 13680 (0.0004) [2023-03-11 10:42:37,183][04298] Updated weights for policy 0, policy_version 13760 (0.0005) [2023-03-11 10:42:37,811][04011] Fps is (10 sec: 10240.0, 60 sec: 10581.3, 300 sec: 10899.5). Total num frames: 7049216. Throughput: 0: 10593.5. Samples: 7038280. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:42:37,811][04011] Avg episode reward: [(0, '0.000')] [2023-03-11 10:42:37,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000013768_7049216.pth... [2023-03-11 10:42:37,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000013144_6729728.pth [2023-03-11 10:42:41,088][04298] Updated weights for policy 0, policy_version 13840 (0.0005) [2023-03-11 10:42:42,811][04011] Fps is (10 sec: 10649.5, 60 sec: 10581.3, 300 sec: 10899.5). Total num frames: 7102464. Throughput: 0: 10652.7. Samples: 7101488. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:42:42,811][04011] Avg episode reward: [(0, '0.000')] [2023-03-11 10:42:45,119][04298] Updated weights for policy 0, policy_version 13920 (0.0005) [2023-03-11 10:42:47,811][04011] Fps is (10 sec: 10240.0, 60 sec: 10513.1, 300 sec: 10871.8). Total num frames: 7151616. Throughput: 0: 10602.6. Samples: 7131208. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-11 10:42:47,811][04011] Avg episode reward: [(0, '0.000')] [2023-03-11 10:42:49,165][04298] Updated weights for policy 0, policy_version 14000 (0.0004) [2023-03-11 10:42:52,811][04011] Fps is (10 sec: 9830.4, 60 sec: 10513.1, 300 sec: 10857.9). Total num frames: 7200768. Throughput: 0: 10557.0. Samples: 7192576. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-11 10:42:52,811][04011] Avg episode reward: [(0, '0.000')] [2023-03-11 10:42:52,840][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000014072_7204864.pth... [2023-03-11 10:42:52,842][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000013464_6893568.pth [2023-03-11 10:42:53,249][04298] Updated weights for policy 0, policy_version 14080 (0.0005) [2023-03-11 10:42:57,204][04298] Updated weights for policy 0, policy_version 14160 (0.0005) [2023-03-11 10:42:57,811][04011] Fps is (10 sec: 10240.0, 60 sec: 10513.1, 300 sec: 10844.0). Total num frames: 7254016. Throughput: 0: 10533.5. Samples: 7254016. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:42:57,811][04011] Avg episode reward: [(0, '0.000')] [2023-03-11 10:43:01,353][04298] Updated weights for policy 0, policy_version 14240 (0.0005) [2023-03-11 10:43:02,811][04011] Fps is (10 sec: 10240.0, 60 sec: 10444.8, 300 sec: 10830.1). Total num frames: 7303168. Throughput: 0: 10443.4. Samples: 7282760. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:43:02,811][04011] Avg episode reward: [(0, '0.000')] [2023-03-11 10:43:05,195][04298] Updated weights for policy 0, policy_version 14320 (0.0005) [2023-03-11 10:43:07,811][04011] Fps is (10 sec: 10239.9, 60 sec: 10444.8, 300 sec: 10830.1). Total num frames: 7356416. Throughput: 0: 10362.8. Samples: 7346480. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:43:07,812][04011] Avg episode reward: [(0, '0.000')] [2023-03-11 10:43:07,816][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000014368_7356416.pth... [2023-03-11 10:43:07,819][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000013768_7049216.pth [2023-03-11 10:43:09,119][04298] Updated weights for policy 0, policy_version 14400 (0.0005) [2023-03-11 10:43:12,811][04011] Fps is (10 sec: 10649.6, 60 sec: 10444.8, 300 sec: 10816.2). Total num frames: 7409664. Throughput: 0: 10270.4. Samples: 7407548. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:43:12,811][04011] Avg episode reward: [(0, '0.000')] [2023-03-11 10:43:13,187][04298] Updated weights for policy 0, policy_version 14480 (0.0005) [2023-03-11 10:43:17,161][04298] Updated weights for policy 0, policy_version 14560 (0.0005) [2023-03-11 10:43:17,811][04011] Fps is (10 sec: 10240.1, 60 sec: 10376.5, 300 sec: 10802.3). Total num frames: 7458816. Throughput: 0: 10287.1. Samples: 7438408. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:43:17,811][04011] Avg episode reward: [(0, '0.000')] [2023-03-11 10:43:21,248][04298] Updated weights for policy 0, policy_version 14640 (0.0005) [2023-03-11 10:43:22,811][04011] Fps is (10 sec: 9830.4, 60 sec: 10240.0, 300 sec: 10774.6). Total num frames: 7507968. Throughput: 0: 10248.7. Samples: 7499472. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:43:22,811][04011] Avg episode reward: [(0, '0.000')] [2023-03-11 10:43:22,848][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000014672_7512064.pth... [2023-03-11 10:43:22,849][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000014072_7204864.pth [2023-03-11 10:43:25,277][04298] Updated weights for policy 0, policy_version 14720 (0.0005) [2023-03-11 10:43:27,811][04011] Fps is (10 sec: 10239.9, 60 sec: 10240.0, 300 sec: 10774.6). Total num frames: 7561216. Throughput: 0: 10175.5. Samples: 7559384. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:43:27,811][04011] Avg episode reward: [(0, '0.005')] [2023-03-11 10:43:29,309][04298] Updated weights for policy 0, policy_version 14800 (0.0005) [2023-03-11 10:43:32,811][04011] Fps is (10 sec: 10649.6, 60 sec: 10308.3, 300 sec: 10774.6). Total num frames: 7614464. Throughput: 0: 10199.7. Samples: 7590196. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-11 10:43:32,811][04011] Avg episode reward: [(0, '0.012')] [2023-03-11 10:43:33,193][04298] Updated weights for policy 0, policy_version 14880 (0.0005) [2023-03-11 10:43:37,230][04298] Updated weights for policy 0, policy_version 14960 (0.0005) [2023-03-11 10:43:37,811][04011] Fps is (10 sec: 10240.0, 60 sec: 10240.0, 300 sec: 10760.7). Total num frames: 7663616. Throughput: 0: 10219.0. Samples: 7652432. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-11 10:43:37,811][04011] Avg episode reward: [(0, '0.059')] [2023-03-11 10:43:37,814][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000014968_7663616.pth... [2023-03-11 10:43:37,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000014368_7356416.pth [2023-03-11 10:43:41,199][04298] Updated weights for policy 0, policy_version 15040 (0.0005) [2023-03-11 10:43:42,811][04011] Fps is (10 sec: 9830.4, 60 sec: 10171.7, 300 sec: 10732.9). Total num frames: 7712768. Throughput: 0: 10210.0. Samples: 7713464. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-11 10:43:42,811][04011] Avg episode reward: [(0, '0.026')] [2023-03-11 10:43:45,244][04298] Updated weights for policy 0, policy_version 15120 (0.0005) [2023-03-11 10:43:47,811][04011] Fps is (10 sec: 10240.0, 60 sec: 10240.0, 300 sec: 10732.9). Total num frames: 7766016. Throughput: 0: 10279.6. Samples: 7745344. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-11 10:43:47,811][04011] Avg episode reward: [(0, '0.086')] [2023-03-11 10:43:49,119][04298] Updated weights for policy 0, policy_version 15200 (0.0005) [2023-03-11 10:43:52,811][04011] Fps is (10 sec: 10649.5, 60 sec: 10308.2, 300 sec: 10719.0). Total num frames: 7819264. Throughput: 0: 10237.6. Samples: 7807172. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-11 10:43:52,812][04011] Avg episode reward: [(0, '0.072')] [2023-03-11 10:43:52,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000015272_7819264.pth... [2023-03-11 10:43:52,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000014672_7512064.pth [2023-03-11 10:43:53,084][04298] Updated weights for policy 0, policy_version 15280 (0.0005) [2023-03-11 10:43:57,072][04298] Updated weights for policy 0, policy_version 15360 (0.0005) [2023-03-11 10:43:57,811][04011] Fps is (10 sec: 10240.0, 60 sec: 10240.0, 300 sec: 10705.1). Total num frames: 7868416. Throughput: 0: 10259.1. Samples: 7869208. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-11 10:43:57,812][04011] Avg episode reward: [(0, '0.177')] [2023-03-11 10:44:01,011][04298] Updated weights for policy 0, policy_version 15440 (0.0005) [2023-03-11 10:44:02,811][04011] Fps is (10 sec: 10240.1, 60 sec: 10308.3, 300 sec: 10705.1). Total num frames: 7921664. Throughput: 0: 10283.6. Samples: 7901168. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-11 10:44:02,811][04011] Avg episode reward: [(0, '0.148')] [2023-03-11 10:44:04,820][04298] Updated weights for policy 0, policy_version 15520 (0.0005) [2023-03-11 10:44:07,811][04011] Fps is (10 sec: 10649.6, 60 sec: 10308.3, 300 sec: 10691.3). Total num frames: 7974912. Throughput: 0: 10345.8. Samples: 7965036. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-11 10:44:07,811][04011] Avg episode reward: [(0, '0.332')] [2023-03-11 10:44:07,831][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000015584_7979008.pth... [2023-03-11 10:44:07,833][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000014968_7663616.pth [2023-03-11 10:44:07,833][04254] Saving new best policy, reward=0.332! [2023-03-11 10:44:08,596][04298] Updated weights for policy 0, policy_version 15600 (0.0005) [2023-03-11 10:44:12,298][04298] Updated weights for policy 0, policy_version 15680 (0.0005) [2023-03-11 10:44:12,811][04011] Fps is (10 sec: 11059.2, 60 sec: 10376.5, 300 sec: 10677.4). Total num frames: 8032256. Throughput: 0: 10490.2. Samples: 8031444. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-11 10:44:12,811][04011] Avg episode reward: [(0, '0.412')] [2023-03-11 10:44:12,812][04254] Saving new best policy, reward=0.412! [2023-03-11 10:44:15,943][04298] Updated weights for policy 0, policy_version 15760 (0.0005) [2023-03-11 10:44:17,811][04011] Fps is (10 sec: 11468.8, 60 sec: 10513.1, 300 sec: 10677.4). Total num frames: 8089600. Throughput: 0: 10544.3. Samples: 8064692. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:44:17,811][04011] Avg episode reward: [(0, '0.182')] [2023-03-11 10:44:19,554][04298] Updated weights for policy 0, policy_version 15840 (0.0005) [2023-03-11 10:44:22,811][04011] Fps is (10 sec: 11059.1, 60 sec: 10581.3, 300 sec: 10677.4). Total num frames: 8142848. Throughput: 0: 10626.6. Samples: 8130632. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:44:22,812][04011] Avg episode reward: [(0, '0.732')] [2023-03-11 10:44:22,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000015904_8142848.pth... [2023-03-11 10:44:22,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000015272_7819264.pth [2023-03-11 10:44:22,818][04254] Saving new best policy, reward=0.732! [2023-03-11 10:44:23,454][04298] Updated weights for policy 0, policy_version 15920 (0.0005) [2023-03-11 10:44:27,256][04298] Updated weights for policy 0, policy_version 16000 (0.0006) [2023-03-11 10:44:27,811][04011] Fps is (10 sec: 10649.6, 60 sec: 10581.3, 300 sec: 10677.4). Total num frames: 8196096. Throughput: 0: 10716.9. Samples: 8195724. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:44:27,812][04011] Avg episode reward: [(0, '0.763')] [2023-03-11 10:44:27,812][04254] Saving new best policy, reward=0.763! [2023-03-11 10:44:30,838][04298] Updated weights for policy 0, policy_version 16080 (0.0005) [2023-03-11 10:44:32,811][04011] Fps is (10 sec: 11059.3, 60 sec: 10649.6, 300 sec: 10691.3). Total num frames: 8253440. Throughput: 0: 10755.1. Samples: 8229324. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:44:32,811][04011] Avg episode reward: [(0, '1.465')] [2023-03-11 10:44:32,812][04254] Saving new best policy, reward=1.465! [2023-03-11 10:44:34,479][04298] Updated weights for policy 0, policy_version 16160 (0.0005) [2023-03-11 10:44:37,811][04011] Fps is (10 sec: 11468.8, 60 sec: 10786.1, 300 sec: 10719.0). Total num frames: 8310784. Throughput: 0: 10902.1. Samples: 8297768. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-11 10:44:37,811][04011] Avg episode reward: [(0, '0.592')] [2023-03-11 10:44:37,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000016232_8310784.pth... [2023-03-11 10:44:37,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000015584_7979008.pth [2023-03-11 10:44:38,079][04298] Updated weights for policy 0, policy_version 16240 (0.0005) [2023-03-11 10:44:41,663][04298] Updated weights for policy 0, policy_version 16320 (0.0004) [2023-03-11 10:44:42,811][04011] Fps is (10 sec: 11059.2, 60 sec: 10854.4, 300 sec: 10719.0). Total num frames: 8364032. Throughput: 0: 11031.3. Samples: 8365616. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-11 10:44:42,811][04011] Avg episode reward: [(0, '1.152')] [2023-03-11 10:44:45,347][04298] Updated weights for policy 0, policy_version 16400 (0.0004) [2023-03-11 10:44:47,811][04011] Fps is (10 sec: 11468.9, 60 sec: 10990.9, 300 sec: 10746.8). Total num frames: 8425472. Throughput: 0: 11071.6. Samples: 8399392. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-11 10:44:47,811][04011] Avg episode reward: [(0, '1.206')] [2023-03-11 10:44:48,689][04298] Updated weights for policy 0, policy_version 16480 (0.0004) [2023-03-11 10:44:52,246][04298] Updated weights for policy 0, policy_version 16560 (0.0005) [2023-03-11 10:44:52,811][04011] Fps is (10 sec: 11878.4, 60 sec: 11059.2, 300 sec: 10760.7). Total num frames: 8482816. Throughput: 0: 11234.8. Samples: 8470600. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-11 10:44:52,811][04011] Avg episode reward: [(0, '1.477')] [2023-03-11 10:44:52,814][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000016568_8482816.pth... [2023-03-11 10:44:52,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000015904_8142848.pth [2023-03-11 10:44:52,817][04254] Saving new best policy, reward=1.477! [2023-03-11 10:44:55,956][04298] Updated weights for policy 0, policy_version 16640 (0.0006) [2023-03-11 10:44:57,811][04011] Fps is (10 sec: 11059.2, 60 sec: 11127.5, 300 sec: 10746.8). Total num frames: 8536064. Throughput: 0: 11236.8. Samples: 8537100. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-11 10:44:57,812][04011] Avg episode reward: [(0, '2.231')] [2023-03-11 10:44:57,832][04254] Saving new best policy, reward=2.231! [2023-03-11 10:44:59,704][04298] Updated weights for policy 0, policy_version 16720 (0.0005) [2023-03-11 10:45:02,811][04011] Fps is (10 sec: 11059.2, 60 sec: 11195.7, 300 sec: 10746.8). Total num frames: 8593408. Throughput: 0: 11221.0. Samples: 8569636. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 10:45:02,812][04011] Avg episode reward: [(0, '3.741')] [2023-03-11 10:45:02,812][04254] Saving new best policy, reward=3.741! [2023-03-11 10:45:03,553][04298] Updated weights for policy 0, policy_version 16800 (0.0005) [2023-03-11 10:45:07,516][04298] Updated weights for policy 0, policy_version 16880 (0.0005) [2023-03-11 10:45:07,811][04011] Fps is (10 sec: 10649.6, 60 sec: 11127.5, 300 sec: 10719.0). Total num frames: 8642560. Throughput: 0: 11150.3. Samples: 8632396. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 10:45:07,812][04011] Avg episode reward: [(0, '2.969')] [2023-03-11 10:45:07,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000016880_8642560.pth... [2023-03-11 10:45:07,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000016232_8310784.pth [2023-03-11 10:45:11,261][04298] Updated weights for policy 0, policy_version 16960 (0.0005) [2023-03-11 10:45:12,811][04011] Fps is (10 sec: 10649.6, 60 sec: 11127.5, 300 sec: 10719.0). Total num frames: 8699904. Throughput: 0: 11192.5. Samples: 8699388. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:45:12,811][04011] Avg episode reward: [(0, '3.122')] [2023-03-11 10:45:14,768][04298] Updated weights for policy 0, policy_version 17040 (0.0005) [2023-03-11 10:45:17,811][04011] Fps is (10 sec: 11468.8, 60 sec: 11127.5, 300 sec: 10719.0). Total num frames: 8757248. Throughput: 0: 11187.1. Samples: 8732744. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:45:17,812][04011] Avg episode reward: [(0, '3.115')] [2023-03-11 10:45:18,570][04298] Updated weights for policy 0, policy_version 17120 (0.0005) [2023-03-11 10:45:22,427][04298] Updated weights for policy 0, policy_version 17200 (0.0006) [2023-03-11 10:45:22,811][04011] Fps is (10 sec: 10649.7, 60 sec: 11059.2, 300 sec: 10691.3). Total num frames: 8806400. Throughput: 0: 11121.1. Samples: 8798216. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:45:22,811][04011] Avg episode reward: [(0, '2.998')] [2023-03-11 10:45:22,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000017208_8810496.pth... [2023-03-11 10:45:22,816][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000016568_8482816.pth [2023-03-11 10:45:26,427][04298] Updated weights for policy 0, policy_version 17280 (0.0005) [2023-03-11 10:45:27,811][04011] Fps is (10 sec: 10240.1, 60 sec: 11059.2, 300 sec: 10677.4). Total num frames: 8859648. Throughput: 0: 10969.4. Samples: 8859240. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:45:27,811][04011] Avg episode reward: [(0, '2.802')] [2023-03-11 10:45:30,293][04298] Updated weights for policy 0, policy_version 17360 (0.0005) [2023-03-11 10:45:32,811][04011] Fps is (10 sec: 10649.6, 60 sec: 10990.9, 300 sec: 10677.4). Total num frames: 8912896. Throughput: 0: 10941.8. Samples: 8891772. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:45:32,811][04011] Avg episode reward: [(0, '3.891')] [2023-03-11 10:45:32,812][04254] Saving new best policy, reward=3.891! [2023-03-11 10:45:34,121][04298] Updated weights for policy 0, policy_version 17440 (0.0005) [2023-03-11 10:45:37,699][04298] Updated weights for policy 0, policy_version 17520 (0.0005) [2023-03-11 10:45:37,811][04011] Fps is (10 sec: 11059.1, 60 sec: 10990.9, 300 sec: 10691.3). Total num frames: 8970240. Throughput: 0: 10803.5. Samples: 8956756. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-11 10:45:37,811][04011] Avg episode reward: [(0, '3.884')] [2023-03-11 10:45:37,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000017520_8970240.pth... [2023-03-11 10:45:37,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000016880_8642560.pth [2023-03-11 10:45:41,353][04298] Updated weights for policy 0, policy_version 17600 (0.0005) [2023-03-11 10:45:42,811][04011] Fps is (10 sec: 11059.2, 60 sec: 10990.9, 300 sec: 10691.3). Total num frames: 9023488. Throughput: 0: 10819.8. Samples: 9023992. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-11 10:45:42,811][04011] Avg episode reward: [(0, '4.770')] [2023-03-11 10:45:42,812][04254] Saving new best policy, reward=4.770! [2023-03-11 10:45:44,950][04298] Updated weights for policy 0, policy_version 17680 (0.0005) [2023-03-11 10:45:47,811][04011] Fps is (10 sec: 11468.8, 60 sec: 10990.9, 300 sec: 10719.0). Total num frames: 9084928. Throughput: 0: 10879.1. Samples: 9059196. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-11 10:45:47,811][04011] Avg episode reward: [(0, '6.516')] [2023-03-11 10:45:47,812][04254] Saving new best policy, reward=6.516! [2023-03-11 10:45:48,428][04298] Updated weights for policy 0, policy_version 17760 (0.0003) [2023-03-11 10:45:52,251][04298] Updated weights for policy 0, policy_version 17840 (0.0004) [2023-03-11 10:45:52,811][04011] Fps is (10 sec: 11468.7, 60 sec: 10922.7, 300 sec: 10732.9). Total num frames: 9138176. Throughput: 0: 10975.2. Samples: 9126280. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:45:52,811][04011] Avg episode reward: [(0, '7.451')] [2023-03-11 10:45:52,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000017848_9138176.pth... [2023-03-11 10:45:52,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000017208_8810496.pth [2023-03-11 10:45:52,818][04254] Saving new best policy, reward=7.451! [2023-03-11 10:45:56,165][04298] Updated weights for policy 0, policy_version 17920 (0.0005) [2023-03-11 10:45:57,811][04011] Fps is (10 sec: 10649.7, 60 sec: 10922.7, 300 sec: 10732.9). Total num frames: 9191424. Throughput: 0: 10898.4. Samples: 9189816. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:45:57,811][04011] Avg episode reward: [(0, '4.975')] [2023-03-11 10:45:59,972][04298] Updated weights for policy 0, policy_version 18000 (0.0005) [2023-03-11 10:46:02,811][04011] Fps is (10 sec: 10649.7, 60 sec: 10854.4, 300 sec: 10732.9). Total num frames: 9244672. Throughput: 0: 10885.2. Samples: 9222576. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:46:02,811][04011] Avg episode reward: [(0, '6.366')] [2023-03-11 10:46:03,828][04298] Updated weights for policy 0, policy_version 18080 (0.0005) [2023-03-11 10:46:07,571][04298] Updated weights for policy 0, policy_version 18160 (0.0005) [2023-03-11 10:46:07,811][04011] Fps is (10 sec: 10649.5, 60 sec: 10922.7, 300 sec: 10732.9). Total num frames: 9297920. Throughput: 0: 10870.8. Samples: 9287404. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:46:07,811][04011] Avg episode reward: [(0, '8.945')] [2023-03-11 10:46:07,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000018160_9297920.pth... [2023-03-11 10:46:07,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000017520_8970240.pth [2023-03-11 10:46:07,818][04254] Saving new best policy, reward=8.945! [2023-03-11 10:46:11,288][04298] Updated weights for policy 0, policy_version 18240 (0.0005) [2023-03-11 10:46:12,811][04011] Fps is (10 sec: 11059.2, 60 sec: 10922.7, 300 sec: 10732.9). Total num frames: 9355264. Throughput: 0: 10964.7. Samples: 9352652. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:46:12,811][04011] Avg episode reward: [(0, '8.769')] [2023-03-11 10:46:15,056][04298] Updated weights for policy 0, policy_version 18320 (0.0005) [2023-03-11 10:46:17,811][04011] Fps is (10 sec: 11059.3, 60 sec: 10854.4, 300 sec: 10719.0). Total num frames: 9408512. Throughput: 0: 10959.7. Samples: 9384960. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:46:17,811][04011] Avg episode reward: [(0, '5.980')] [2023-03-11 10:46:18,846][04298] Updated weights for policy 0, policy_version 18400 (0.0005) [2023-03-11 10:46:22,318][04298] Updated weights for policy 0, policy_version 18480 (0.0004) [2023-03-11 10:46:22,811][04011] Fps is (10 sec: 11059.1, 60 sec: 10990.9, 300 sec: 10719.0). Total num frames: 9465856. Throughput: 0: 11027.0. Samples: 9452972. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:46:22,812][04011] Avg episode reward: [(0, '8.660')] [2023-03-11 10:46:22,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000018488_9465856.pth... [2023-03-11 10:46:22,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000017848_9138176.pth [2023-03-11 10:46:25,799][04298] Updated weights for policy 0, policy_version 18560 (0.0004) [2023-03-11 10:46:27,811][04011] Fps is (10 sec: 11468.7, 60 sec: 11059.2, 300 sec: 10719.0). Total num frames: 9523200. Throughput: 0: 11094.9. Samples: 9523264. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:46:27,811][04011] Avg episode reward: [(0, '11.620')] [2023-03-11 10:46:27,812][04254] Saving new best policy, reward=11.620! [2023-03-11 10:46:29,295][04298] Updated weights for policy 0, policy_version 18640 (0.0005) [2023-03-11 10:46:32,676][04298] Updated weights for policy 0, policy_version 18720 (0.0004) [2023-03-11 10:46:32,811][04011] Fps is (10 sec: 11878.6, 60 sec: 11195.7, 300 sec: 10746.8). Total num frames: 9584640. Throughput: 0: 11112.8. Samples: 9559272. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:46:32,811][04011] Avg episode reward: [(0, '14.222')] [2023-03-11 10:46:32,812][04254] Saving new best policy, reward=14.222! [2023-03-11 10:46:36,023][04298] Updated weights for policy 0, policy_version 18800 (0.0004) [2023-03-11 10:46:37,811][04011] Fps is (10 sec: 12288.0, 60 sec: 11264.0, 300 sec: 10774.6). Total num frames: 9646080. Throughput: 0: 11237.2. Samples: 9631956. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:46:37,811][04011] Avg episode reward: [(0, '15.827')] [2023-03-11 10:46:37,814][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000018840_9646080.pth... [2023-03-11 10:46:37,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000018160_9297920.pth [2023-03-11 10:46:37,817][04254] Saving new best policy, reward=15.827! [2023-03-11 10:46:39,478][04298] Updated weights for policy 0, policy_version 18880 (0.0004) [2023-03-11 10:46:42,811][04011] Fps is (10 sec: 11878.3, 60 sec: 11332.3, 300 sec: 10788.4). Total num frames: 9703424. Throughput: 0: 11413.5. Samples: 9703424. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:46:42,812][04011] Avg episode reward: [(0, '13.739')] [2023-03-11 10:46:42,906][04298] Updated weights for policy 0, policy_version 18960 (0.0004) [2023-03-11 10:46:46,137][04298] Updated weights for policy 0, policy_version 19040 (0.0004) [2023-03-11 10:46:47,811][04011] Fps is (10 sec: 11878.4, 60 sec: 11332.3, 300 sec: 10830.1). Total num frames: 9764864. Throughput: 0: 11509.1. Samples: 9740488. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:46:47,812][04011] Avg episode reward: [(0, '16.210')] [2023-03-11 10:46:47,812][04254] Saving new best policy, reward=16.210! [2023-03-11 10:46:49,772][04298] Updated weights for policy 0, policy_version 19120 (0.0005) [2023-03-11 10:46:52,811][04011] Fps is (10 sec: 11878.3, 60 sec: 11400.5, 300 sec: 10844.0). Total num frames: 9822208. Throughput: 0: 11612.9. Samples: 9809984. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:46:52,811][04011] Avg episode reward: [(0, '16.735')] [2023-03-11 10:46:52,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000019184_9822208.pth... [2023-03-11 10:46:52,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000018488_9465856.pth [2023-03-11 10:46:52,818][04254] Saving new best policy, reward=16.735! [2023-03-11 10:46:53,329][04298] Updated weights for policy 0, policy_version 19200 (0.0005) [2023-03-11 10:46:56,925][04298] Updated weights for policy 0, policy_version 19280 (0.0006) [2023-03-11 10:46:57,811][04011] Fps is (10 sec: 11468.8, 60 sec: 11468.8, 300 sec: 10857.9). Total num frames: 9879552. Throughput: 0: 11685.1. Samples: 9878484. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:46:57,811][04011] Avg episode reward: [(0, '18.394')] [2023-03-11 10:46:57,812][04254] Saving new best policy, reward=18.394! [2023-03-11 10:47:00,727][04298] Updated weights for policy 0, policy_version 19360 (0.0005) [2023-03-11 10:47:02,811][04011] Fps is (10 sec: 11059.3, 60 sec: 11468.8, 300 sec: 10857.9). Total num frames: 9932800. Throughput: 0: 11687.3. Samples: 9910888. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:47:02,811][04011] Avg episode reward: [(0, '16.815')] [2023-03-11 10:47:04,547][04298] Updated weights for policy 0, policy_version 19440 (0.0005) [2023-03-11 10:47:07,811][04011] Fps is (10 sec: 10649.6, 60 sec: 11468.8, 300 sec: 10857.9). Total num frames: 9986048. Throughput: 0: 11616.1. Samples: 9975696. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:47:07,811][04011] Avg episode reward: [(0, '20.869')] [2023-03-11 10:47:07,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000019504_9986048.pth... [2023-03-11 10:47:07,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000018840_9646080.pth [2023-03-11 10:47:07,819][04254] Saving new best policy, reward=20.869! [2023-03-11 10:47:08,291][04298] Updated weights for policy 0, policy_version 19520 (0.0006) [2023-03-11 10:47:11,932][04298] Updated weights for policy 0, policy_version 19600 (0.0005) [2023-03-11 10:47:12,811][04011] Fps is (10 sec: 11059.2, 60 sec: 11468.8, 300 sec: 10871.8). Total num frames: 10043392. Throughput: 0: 11542.9. Samples: 10042696. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:47:12,811][04011] Avg episode reward: [(0, '19.137')] [2023-03-11 10:47:15,405][04298] Updated weights for policy 0, policy_version 19680 (0.0005) [2023-03-11 10:47:17,811][04011] Fps is (10 sec: 11468.9, 60 sec: 11537.1, 300 sec: 10871.8). Total num frames: 10100736. Throughput: 0: 11529.2. Samples: 10078084. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:47:17,811][04011] Avg episode reward: [(0, '18.874')] [2023-03-11 10:47:18,899][04298] Updated weights for policy 0, policy_version 19760 (0.0005) [2023-03-11 10:47:22,455][04298] Updated weights for policy 0, policy_version 19840 (0.0006) [2023-03-11 10:47:22,811][04011] Fps is (10 sec: 11878.2, 60 sec: 11605.3, 300 sec: 10899.5). Total num frames: 10162176. Throughput: 0: 11468.1. Samples: 10148024. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:47:22,812][04011] Avg episode reward: [(0, '22.995')] [2023-03-11 10:47:22,817][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000019848_10162176.pth... [2023-03-11 10:47:22,819][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000019184_9822208.pth [2023-03-11 10:47:22,819][04254] Saving new best policy, reward=22.995! [2023-03-11 10:47:26,024][04298] Updated weights for policy 0, policy_version 19920 (0.0005) [2023-03-11 10:47:27,811][04011] Fps is (10 sec: 11878.3, 60 sec: 11605.3, 300 sec: 10927.3). Total num frames: 10219520. Throughput: 0: 11404.0. Samples: 10216604. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:47:27,812][04011] Avg episode reward: [(0, '22.203')] [2023-03-11 10:47:29,515][04298] Updated weights for policy 0, policy_version 20000 (0.0005) [2023-03-11 10:47:32,811][04011] Fps is (10 sec: 11469.1, 60 sec: 11537.1, 300 sec: 10941.2). Total num frames: 10276864. Throughput: 0: 11374.8. Samples: 10252352. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:47:32,811][04011] Avg episode reward: [(0, '23.019')] [2023-03-11 10:47:32,812][04254] Saving new best policy, reward=23.019! [2023-03-11 10:47:33,037][04298] Updated weights for policy 0, policy_version 20080 (0.0005) [2023-03-11 10:47:36,561][04298] Updated weights for policy 0, policy_version 20160 (0.0005) [2023-03-11 10:47:37,811][04011] Fps is (10 sec: 11468.8, 60 sec: 11468.8, 300 sec: 10955.1). Total num frames: 10334208. Throughput: 0: 11377.8. Samples: 10321984. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:47:37,812][04011] Avg episode reward: [(0, '21.777')] [2023-03-11 10:47:37,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000020184_10334208.pth... [2023-03-11 10:47:37,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000019504_9986048.pth [2023-03-11 10:47:40,081][04298] Updated weights for policy 0, policy_version 20240 (0.0005) [2023-03-11 10:47:42,811][04011] Fps is (10 sec: 11468.7, 60 sec: 11468.8, 300 sec: 10982.8). Total num frames: 10391552. Throughput: 0: 11408.2. Samples: 10391852. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:47:42,812][04011] Avg episode reward: [(0, '23.283')] [2023-03-11 10:47:42,850][04254] Saving new best policy, reward=23.283! [2023-03-11 10:47:43,561][04298] Updated weights for policy 0, policy_version 20320 (0.0005) [2023-03-11 10:47:47,157][04298] Updated weights for policy 0, policy_version 20400 (0.0005) [2023-03-11 10:47:47,811][04011] Fps is (10 sec: 11468.9, 60 sec: 11400.5, 300 sec: 11010.6). Total num frames: 10448896. Throughput: 0: 11483.0. Samples: 10427624. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:47:47,811][04011] Avg episode reward: [(0, '24.419')] [2023-03-11 10:47:47,812][04254] Saving new best policy, reward=24.419! [2023-03-11 10:47:50,784][04298] Updated weights for policy 0, policy_version 20480 (0.0005) [2023-03-11 10:47:52,811][04011] Fps is (10 sec: 11468.8, 60 sec: 11400.5, 300 sec: 11024.5). Total num frames: 10506240. Throughput: 0: 11522.2. Samples: 10494196. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:47:52,811][04011] Avg episode reward: [(0, '25.210')] [2023-03-11 10:47:52,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000020520_10506240.pth... [2023-03-11 10:47:52,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000019848_10162176.pth [2023-03-11 10:47:52,818][04254] Saving new best policy, reward=25.210! [2023-03-11 10:47:54,320][04298] Updated weights for policy 0, policy_version 20560 (0.0005) [2023-03-11 10:47:57,750][04298] Updated weights for policy 0, policy_version 20640 (0.0005) [2023-03-11 10:47:57,811][04011] Fps is (10 sec: 11878.3, 60 sec: 11468.8, 300 sec: 11066.1). Total num frames: 10567680. Throughput: 0: 11614.4. Samples: 10565344. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:47:57,822][04011] Avg episode reward: [(0, '24.761')] [2023-03-11 10:48:01,251][04298] Updated weights for policy 0, policy_version 20720 (0.0005) [2023-03-11 10:48:02,811][04011] Fps is (10 sec: 11878.5, 60 sec: 11537.1, 300 sec: 11080.0). Total num frames: 10625024. Throughput: 0: 11609.7. Samples: 10600520. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:48:02,821][04011] Avg episode reward: [(0, '26.619')] [2023-03-11 10:48:02,821][04254] Saving new best policy, reward=26.619! [2023-03-11 10:48:04,807][04298] Updated weights for policy 0, policy_version 20800 (0.0005) [2023-03-11 10:48:07,811][04011] Fps is (10 sec: 11468.8, 60 sec: 11605.3, 300 sec: 11093.9). Total num frames: 10682368. Throughput: 0: 11601.6. Samples: 10670092. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:48:07,822][04011] Avg episode reward: [(0, '23.193')] [2023-03-11 10:48:07,825][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000020864_10682368.pth... [2023-03-11 10:48:07,828][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000020184_10334208.pth [2023-03-11 10:48:08,310][04298] Updated weights for policy 0, policy_version 20880 (0.0005) [2023-03-11 10:48:12,001][04298] Updated weights for policy 0, policy_version 20960 (0.0005) [2023-03-11 10:48:12,811][04011] Fps is (10 sec: 11468.8, 60 sec: 11605.3, 300 sec: 11121.7). Total num frames: 10739712. Throughput: 0: 11595.1. Samples: 10738384. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:48:12,822][04011] Avg episode reward: [(0, '25.881')] [2023-03-11 10:48:15,548][04298] Updated weights for policy 0, policy_version 21040 (0.0005) [2023-03-11 10:48:17,811][04011] Fps is (10 sec: 11468.8, 60 sec: 11605.3, 300 sec: 11149.4). Total num frames: 10797056. Throughput: 0: 11559.8. Samples: 10772544. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:48:17,822][04011] Avg episode reward: [(0, '27.050')] [2023-03-11 10:48:17,823][04254] Saving new best policy, reward=27.050! [2023-03-11 10:48:19,032][04298] Updated weights for policy 0, policy_version 21120 (0.0005) [2023-03-11 10:48:22,508][04298] Updated weights for policy 0, policy_version 21200 (0.0005) [2023-03-11 10:48:22,811][04011] Fps is (10 sec: 11468.6, 60 sec: 11537.1, 300 sec: 11163.3). Total num frames: 10854400. Throughput: 0: 11593.2. Samples: 10843680. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:48:22,822][04011] Avg episode reward: [(0, '22.252')] [2023-03-11 10:48:22,845][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000021208_10858496.pth... [2023-03-11 10:48:22,846][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000020520_10506240.pth [2023-03-11 10:48:25,888][04298] Updated weights for policy 0, policy_version 21280 (0.0006) [2023-03-11 10:48:27,811][04011] Fps is (10 sec: 11878.4, 60 sec: 11605.3, 300 sec: 11191.1). Total num frames: 10915840. Throughput: 0: 11634.2. Samples: 10915392. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:48:27,822][04011] Avg episode reward: [(0, '24.853')] [2023-03-11 10:48:29,322][04298] Updated weights for policy 0, policy_version 21360 (0.0005) [2023-03-11 10:48:32,733][04298] Updated weights for policy 0, policy_version 21440 (0.0005) [2023-03-11 10:48:32,811][04011] Fps is (10 sec: 12288.2, 60 sec: 11673.6, 300 sec: 11232.8). Total num frames: 10977280. Throughput: 0: 11651.0. Samples: 10951920. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:48:32,822][04011] Avg episode reward: [(0, '26.146')] [2023-03-11 10:48:36,264][04298] Updated weights for policy 0, policy_version 21520 (0.0005) [2023-03-11 10:48:37,811][04011] Fps is (10 sec: 11878.4, 60 sec: 11673.6, 300 sec: 11260.5). Total num frames: 11034624. Throughput: 0: 11734.9. Samples: 11022268. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 10:48:37,822][04011] Avg episode reward: [(0, '27.981')] [2023-03-11 10:48:37,826][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000021552_11034624.pth... [2023-03-11 10:48:37,828][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000020864_10682368.pth [2023-03-11 10:48:37,829][04254] Saving new best policy, reward=27.981! [2023-03-11 10:48:39,642][04298] Updated weights for policy 0, policy_version 21600 (0.0006) [2023-03-11 10:48:42,811][04011] Fps is (10 sec: 11878.4, 60 sec: 11741.9, 300 sec: 11288.3). Total num frames: 11096064. Throughput: 0: 11760.6. Samples: 11094572. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 10:48:42,811][04011] Avg episode reward: [(0, '29.481')] [2023-03-11 10:48:42,812][04254] Saving new best policy, reward=29.481! [2023-03-11 10:48:43,048][04298] Updated weights for policy 0, policy_version 21680 (0.0005) [2023-03-11 10:48:46,419][04298] Updated weights for policy 0, policy_version 21760 (0.0005) [2023-03-11 10:48:47,811][04011] Fps is (10 sec: 11878.5, 60 sec: 11741.9, 300 sec: 11302.2). Total num frames: 11153408. Throughput: 0: 11786.6. Samples: 11130916. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 10:48:47,811][04011] Avg episode reward: [(0, '28.139')] [2023-03-11 10:48:49,908][04298] Updated weights for policy 0, policy_version 21840 (0.0005) [2023-03-11 10:48:52,811][04011] Fps is (10 sec: 11878.3, 60 sec: 11810.1, 300 sec: 11343.8). Total num frames: 11214848. Throughput: 0: 11832.8. Samples: 11202568. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:48:52,812][04011] Avg episode reward: [(0, '28.114')] [2023-03-11 10:48:52,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000021904_11214848.pth... [2023-03-11 10:48:52,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000021208_10858496.pth [2023-03-11 10:48:53,236][04298] Updated weights for policy 0, policy_version 21920 (0.0005) [2023-03-11 10:48:56,633][04298] Updated weights for policy 0, policy_version 22000 (0.0005) [2023-03-11 10:48:57,811][04011] Fps is (10 sec: 12288.0, 60 sec: 11810.1, 300 sec: 11371.6). Total num frames: 11276288. Throughput: 0: 11936.8. Samples: 11275540. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:48:57,822][04011] Avg episode reward: [(0, '27.491')] [2023-03-11 10:49:00,038][04298] Updated weights for policy 0, policy_version 22080 (0.0005) [2023-03-11 10:49:02,811][04011] Fps is (10 sec: 12287.9, 60 sec: 11878.4, 300 sec: 11399.4). Total num frames: 11337728. Throughput: 0: 11972.1. Samples: 11311288. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:49:02,812][04011] Avg episode reward: [(0, '25.922')] [2023-03-11 10:49:03,524][04298] Updated weights for policy 0, policy_version 22160 (0.0005) [2023-03-11 10:49:06,965][04298] Updated weights for policy 0, policy_version 22240 (0.0005) [2023-03-11 10:49:07,811][04011] Fps is (10 sec: 11878.3, 60 sec: 11878.4, 300 sec: 11399.4). Total num frames: 11395072. Throughput: 0: 11973.0. Samples: 11382464. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:49:07,811][04011] Avg episode reward: [(0, '23.839')] [2023-03-11 10:49:07,814][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000022256_11395072.pth... [2023-03-11 10:49:07,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000021552_11034624.pth [2023-03-11 10:49:10,433][04298] Updated weights for policy 0, policy_version 22320 (0.0005) [2023-03-11 10:49:12,811][04011] Fps is (10 sec: 11468.9, 60 sec: 11878.4, 300 sec: 11399.4). Total num frames: 11452416. Throughput: 0: 11941.1. Samples: 11452740. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:49:12,811][04011] Avg episode reward: [(0, '27.520')] [2023-03-11 10:49:13,894][04298] Updated weights for policy 0, policy_version 22400 (0.0005) [2023-03-11 10:49:17,380][04298] Updated weights for policy 0, policy_version 22480 (0.0005) [2023-03-11 10:49:17,811][04011] Fps is (10 sec: 11878.4, 60 sec: 11946.7, 300 sec: 11427.1). Total num frames: 11513856. Throughput: 0: 11928.9. Samples: 11488720. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:49:17,812][04011] Avg episode reward: [(0, '27.844')] [2023-03-11 10:49:20,831][04298] Updated weights for policy 0, policy_version 22560 (0.0005) [2023-03-11 10:49:22,811][04011] Fps is (10 sec: 11878.3, 60 sec: 11946.7, 300 sec: 11441.0). Total num frames: 11571200. Throughput: 0: 11927.0. Samples: 11558984. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:49:22,811][04011] Avg episode reward: [(0, '27.597')] [2023-03-11 10:49:22,814][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000022600_11571200.pth... [2023-03-11 10:49:22,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000021904_11214848.pth [2023-03-11 10:49:24,344][04298] Updated weights for policy 0, policy_version 22640 (0.0005) [2023-03-11 10:49:27,788][04298] Updated weights for policy 0, policy_version 22720 (0.0005) [2023-03-11 10:49:27,811][04011] Fps is (10 sec: 11878.5, 60 sec: 11946.7, 300 sec: 11454.9). Total num frames: 11632640. Throughput: 0: 11897.9. Samples: 11629976. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:49:27,811][04011] Avg episode reward: [(0, '27.280')] [2023-03-11 10:49:31,273][04298] Updated weights for policy 0, policy_version 22800 (0.0005) [2023-03-11 10:49:32,811][04011] Fps is (10 sec: 11878.5, 60 sec: 11878.4, 300 sec: 11454.9). Total num frames: 11689984. Throughput: 0: 11879.0. Samples: 11665472. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:49:32,811][04011] Avg episode reward: [(0, '22.086')] [2023-03-11 10:49:34,796][04298] Updated weights for policy 0, policy_version 22880 (0.0005) [2023-03-11 10:49:37,811][04011] Fps is (10 sec: 11468.7, 60 sec: 11878.4, 300 sec: 11468.8). Total num frames: 11747328. Throughput: 0: 11834.1. Samples: 11735104. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-11 10:49:37,812][04011] Avg episode reward: [(0, '27.128')] [2023-03-11 10:49:37,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000022944_11747328.pth... [2023-03-11 10:49:37,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000022256_11395072.pth [2023-03-11 10:49:38,298][04298] Updated weights for policy 0, policy_version 22960 (0.0005) [2023-03-11 10:49:41,741][04298] Updated weights for policy 0, policy_version 23040 (0.0005) [2023-03-11 10:49:42,811][04011] Fps is (10 sec: 11878.3, 60 sec: 11878.4, 300 sec: 11468.8). Total num frames: 11808768. Throughput: 0: 11801.9. Samples: 11806628. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-11 10:49:42,812][04011] Avg episode reward: [(0, '27.130')] [2023-03-11 10:49:45,160][04298] Updated weights for policy 0, policy_version 23120 (0.0005) [2023-03-11 10:49:47,811][04011] Fps is (10 sec: 11878.5, 60 sec: 11878.4, 300 sec: 11468.8). Total num frames: 11866112. Throughput: 0: 11786.3. Samples: 11841672. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-11 10:49:47,811][04011] Avg episode reward: [(0, '27.460')] [2023-03-11 10:49:48,597][04298] Updated weights for policy 0, policy_version 23200 (0.0005) [2023-03-11 10:49:51,926][04298] Updated weights for policy 0, policy_version 23280 (0.0005) [2023-03-11 10:49:52,811][04011] Fps is (10 sec: 11878.3, 60 sec: 11878.4, 300 sec: 11496.6). Total num frames: 11927552. Throughput: 0: 11837.8. Samples: 11915164. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:49:52,812][04011] Avg episode reward: [(0, '29.206')] [2023-03-11 10:49:52,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000023296_11927552.pth... [2023-03-11 10:49:52,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000022600_11571200.pth [2023-03-11 10:49:55,275][04298] Updated weights for policy 0, policy_version 23360 (0.0005) [2023-03-11 10:49:57,811][04011] Fps is (10 sec: 12287.9, 60 sec: 11878.4, 300 sec: 11510.5). Total num frames: 11988992. Throughput: 0: 11911.2. Samples: 11988744. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:49:57,812][04011] Avg episode reward: [(0, '28.848')] [2023-03-11 10:49:58,653][04298] Updated weights for policy 0, policy_version 23440 (0.0005) [2023-03-11 10:50:02,087][04298] Updated weights for policy 0, policy_version 23520 (0.0005) [2023-03-11 10:50:02,811][04011] Fps is (10 sec: 12288.2, 60 sec: 11878.4, 300 sec: 11552.1). Total num frames: 12050432. Throughput: 0: 11891.9. Samples: 12023856. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:50:02,811][04011] Avg episode reward: [(0, '21.906')] [2023-03-11 10:50:05,512][04298] Updated weights for policy 0, policy_version 23600 (0.0005) [2023-03-11 10:50:07,811][04011] Fps is (10 sec: 11878.4, 60 sec: 11878.4, 300 sec: 11552.1). Total num frames: 12107776. Throughput: 0: 11923.9. Samples: 12095560. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:50:07,811][04011] Avg episode reward: [(0, '27.896')] [2023-03-11 10:50:07,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000023648_12107776.pth... [2023-03-11 10:50:07,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000022944_11747328.pth [2023-03-11 10:50:08,929][04298] Updated weights for policy 0, policy_version 23680 (0.0005) [2023-03-11 10:50:12,461][04298] Updated weights for policy 0, policy_version 23760 (0.0005) [2023-03-11 10:50:12,811][04011] Fps is (10 sec: 11468.6, 60 sec: 11878.4, 300 sec: 11552.1). Total num frames: 12165120. Throughput: 0: 11912.4. Samples: 12166036. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:50:12,812][04011] Avg episode reward: [(0, '26.738')] [2023-03-11 10:50:16,033][04298] Updated weights for policy 0, policy_version 23840 (0.0005) [2023-03-11 10:50:17,811][04011] Fps is (10 sec: 11878.5, 60 sec: 11878.4, 300 sec: 11593.8). Total num frames: 12226560. Throughput: 0: 11895.1. Samples: 12200752. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:50:17,811][04011] Avg episode reward: [(0, '30.254')] [2023-03-11 10:50:17,812][04254] Saving new best policy, reward=30.254! [2023-03-11 10:50:19,504][04298] Updated weights for policy 0, policy_version 23920 (0.0005) [2023-03-11 10:50:22,811][04011] Fps is (10 sec: 11878.4, 60 sec: 11878.4, 300 sec: 11607.6). Total num frames: 12283904. Throughput: 0: 11923.9. Samples: 12271680. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:50:22,812][04011] Avg episode reward: [(0, '28.258')] [2023-03-11 10:50:22,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000023992_12283904.pth... [2023-03-11 10:50:22,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000023296_11927552.pth [2023-03-11 10:50:22,905][04298] Updated weights for policy 0, policy_version 24000 (0.0005) [2023-03-11 10:50:26,347][04298] Updated weights for policy 0, policy_version 24080 (0.0005) [2023-03-11 10:50:27,811][04011] Fps is (10 sec: 11878.4, 60 sec: 11878.4, 300 sec: 11635.4). Total num frames: 12345344. Throughput: 0: 11925.0. Samples: 12343252. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:50:27,811][04011] Avg episode reward: [(0, '14.069')] [2023-03-11 10:50:29,721][04298] Updated weights for policy 0, policy_version 24160 (0.0005) [2023-03-11 10:50:32,811][04011] Fps is (10 sec: 12288.1, 60 sec: 11946.7, 300 sec: 11649.3). Total num frames: 12406784. Throughput: 0: 11966.2. Samples: 12380152. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:50:32,811][04011] Avg episode reward: [(0, '25.358')] [2023-03-11 10:50:32,991][04298] Updated weights for policy 0, policy_version 24240 (0.0004) [2023-03-11 10:50:36,139][04298] Updated weights for policy 0, policy_version 24320 (0.0004) [2023-03-11 10:50:37,811][04011] Fps is (10 sec: 12697.5, 60 sec: 12083.2, 300 sec: 11691.0). Total num frames: 12472320. Throughput: 0: 12042.4. Samples: 12457072. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-11 10:50:37,811][04011] Avg episode reward: [(0, '26.762')] [2023-03-11 10:50:37,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000024360_12472320.pth... [2023-03-11 10:50:37,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000023648_12107776.pth [2023-03-11 10:50:39,401][04298] Updated weights for policy 0, policy_version 24400 (0.0004) [2023-03-11 10:50:42,760][04298] Updated weights for policy 0, policy_version 24480 (0.0004) [2023-03-11 10:50:42,811][04011] Fps is (10 sec: 12697.5, 60 sec: 12083.2, 300 sec: 11691.0). Total num frames: 12533760. Throughput: 0: 12048.1. Samples: 12530908. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-11 10:50:42,811][04011] Avg episode reward: [(0, '23.275')] [2023-03-11 10:50:46,036][04298] Updated weights for policy 0, policy_version 24560 (0.0004) [2023-03-11 10:50:47,811][04011] Fps is (10 sec: 12288.1, 60 sec: 12151.5, 300 sec: 11718.7). Total num frames: 12595200. Throughput: 0: 12102.0. Samples: 12568448. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-11 10:50:47,811][04011] Avg episode reward: [(0, '7.023')] [2023-03-11 10:50:49,260][04298] Updated weights for policy 0, policy_version 24640 (0.0004) [2023-03-11 10:50:52,498][04298] Updated weights for policy 0, policy_version 24720 (0.0004) [2023-03-11 10:50:52,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12151.5, 300 sec: 11746.5). Total num frames: 12656640. Throughput: 0: 12195.6. Samples: 12644360. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-11 10:50:52,811][04011] Avg episode reward: [(0, '0.300')] [2023-03-11 10:50:52,814][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000024728_12660736.pth... [2023-03-11 10:50:52,816][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000023992_12283904.pth [2023-03-11 10:50:55,750][04298] Updated weights for policy 0, policy_version 24800 (0.0004) [2023-03-11 10:50:57,811][04011] Fps is (10 sec: 12697.6, 60 sec: 12219.7, 300 sec: 11788.1). Total num frames: 12722176. Throughput: 0: 12306.4. Samples: 12719824. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:50:57,811][04011] Avg episode reward: [(0, '0.155')] [2023-03-11 10:50:59,011][04298] Updated weights for policy 0, policy_version 24880 (0.0004) [2023-03-11 10:51:02,294][04298] Updated weights for policy 0, policy_version 24960 (0.0004) [2023-03-11 10:51:02,811][04011] Fps is (10 sec: 12697.6, 60 sec: 12219.7, 300 sec: 11815.9). Total num frames: 12783616. Throughput: 0: 12389.2. Samples: 12758268. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:51:02,811][04011] Avg episode reward: [(0, '1.040')] [2023-03-11 10:51:05,568][04298] Updated weights for policy 0, policy_version 25040 (0.0004) [2023-03-11 10:51:07,811][04011] Fps is (10 sec: 12287.9, 60 sec: 12288.0, 300 sec: 11829.8). Total num frames: 12845056. Throughput: 0: 12467.1. Samples: 12832700. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:51:07,812][04011] Avg episode reward: [(0, '1.429')] [2023-03-11 10:51:07,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000025088_12845056.pth... [2023-03-11 10:51:07,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000024360_12472320.pth [2023-03-11 10:51:08,916][04298] Updated weights for policy 0, policy_version 25120 (0.0004) [2023-03-11 10:51:12,257][04298] Updated weights for policy 0, policy_version 25200 (0.0004) [2023-03-11 10:51:12,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12356.3, 300 sec: 11857.6). Total num frames: 12906496. Throughput: 0: 12515.5. Samples: 12906448. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:51:12,811][04011] Avg episode reward: [(0, '3.877')] [2023-03-11 10:51:15,572][04298] Updated weights for policy 0, policy_version 25280 (0.0004) [2023-03-11 10:51:17,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12356.2, 300 sec: 11871.5). Total num frames: 12967936. Throughput: 0: 12514.4. Samples: 12943300. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:51:17,811][04011] Avg episode reward: [(0, '13.841')] [2023-03-11 10:51:18,899][04298] Updated weights for policy 0, policy_version 25360 (0.0004) [2023-03-11 10:51:22,181][04298] Updated weights for policy 0, policy_version 25440 (0.0004) [2023-03-11 10:51:22,811][04011] Fps is (10 sec: 12697.5, 60 sec: 12492.8, 300 sec: 11899.2). Total num frames: 13033472. Throughput: 0: 12446.4. Samples: 13017160. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:51:22,811][04011] Avg episode reward: [(0, '8.208')] [2023-03-11 10:51:22,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000025456_13033472.pth... [2023-03-11 10:51:22,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000024728_12660736.pth [2023-03-11 10:51:25,413][04298] Updated weights for policy 0, policy_version 25520 (0.0004) [2023-03-11 10:51:27,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12424.5, 300 sec: 11885.3). Total num frames: 13090816. Throughput: 0: 12444.0. Samples: 13090888. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 10:51:27,811][04011] Avg episode reward: [(0, '13.736')] [2023-03-11 10:51:28,929][04298] Updated weights for policy 0, policy_version 25600 (0.0005) [2023-03-11 10:51:32,384][04298] Updated weights for policy 0, policy_version 25680 (0.0005) [2023-03-11 10:51:32,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12424.5, 300 sec: 11885.3). Total num frames: 13152256. Throughput: 0: 12416.5. Samples: 13127192. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 10:51:32,811][04011] Avg episode reward: [(0, '19.150')] [2023-03-11 10:51:35,764][04298] Updated weights for policy 0, policy_version 25760 (0.0005) [2023-03-11 10:51:37,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12356.3, 300 sec: 11899.2). Total num frames: 13213696. Throughput: 0: 12331.6. Samples: 13199284. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 10:51:37,811][04011] Avg episode reward: [(0, '17.867')] [2023-03-11 10:51:37,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000025808_13213696.pth... [2023-03-11 10:51:37,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000025088_12845056.pth [2023-03-11 10:51:39,093][04298] Updated weights for policy 0, policy_version 25840 (0.0005) [2023-03-11 10:51:42,527][04298] Updated weights for policy 0, policy_version 25920 (0.0005) [2023-03-11 10:51:42,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12288.0, 300 sec: 11885.3). Total num frames: 13271040. Throughput: 0: 12250.8. Samples: 13271112. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 10:51:42,811][04011] Avg episode reward: [(0, '22.542')] [2023-03-11 10:51:45,937][04298] Updated weights for policy 0, policy_version 26000 (0.0005) [2023-03-11 10:51:47,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12288.0, 300 sec: 11899.2). Total num frames: 13332480. Throughput: 0: 12214.1. Samples: 13307904. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:51:47,811][04011] Avg episode reward: [(0, '22.316')] [2023-03-11 10:51:49,476][04298] Updated weights for policy 0, policy_version 26080 (0.0005) [2023-03-11 10:51:52,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12219.7, 300 sec: 11899.2). Total num frames: 13389824. Throughput: 0: 12108.9. Samples: 13377600. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:51:52,811][04011] Avg episode reward: [(0, '21.482')] [2023-03-11 10:51:52,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000026152_13389824.pth... [2023-03-11 10:51:52,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000025456_13033472.pth [2023-03-11 10:51:52,905][04298] Updated weights for policy 0, policy_version 26160 (0.0005) [2023-03-11 10:51:56,012][04298] Updated weights for policy 0, policy_version 26240 (0.0004) [2023-03-11 10:51:57,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12219.7, 300 sec: 11940.9). Total num frames: 13455360. Throughput: 0: 12195.3. Samples: 13455236. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:51:57,822][04011] Avg episode reward: [(0, '26.759')] [2023-03-11 10:51:59,133][04298] Updated weights for policy 0, policy_version 26320 (0.0004) [2023-03-11 10:52:02,162][04298] Updated weights for policy 0, policy_version 26400 (0.0004) [2023-03-11 10:52:02,811][04011] Fps is (10 sec: 13516.8, 60 sec: 12356.3, 300 sec: 11996.4). Total num frames: 13524992. Throughput: 0: 12277.3. Samples: 13495780. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:52:02,811][04011] Avg episode reward: [(0, '27.725')] [2023-03-11 10:52:05,159][04298] Updated weights for policy 0, policy_version 26480 (0.0004) [2023-03-11 10:52:07,811][04011] Fps is (10 sec: 13516.8, 60 sec: 12424.5, 300 sec: 12024.2). Total num frames: 13590528. Throughput: 0: 12421.4. Samples: 13576124. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:52:07,812][04011] Avg episode reward: [(0, '28.916')] [2023-03-11 10:52:07,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000026544_13590528.pth... [2023-03-11 10:52:07,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000025808_13213696.pth [2023-03-11 10:52:08,264][04298] Updated weights for policy 0, policy_version 26560 (0.0004) [2023-03-11 10:52:11,248][04298] Updated weights for policy 0, policy_version 26640 (0.0004) [2023-03-11 10:52:12,811][04011] Fps is (10 sec: 13107.2, 60 sec: 12492.8, 300 sec: 12052.0). Total num frames: 13656064. Throughput: 0: 12566.0. Samples: 13656360. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:52:12,812][04011] Avg episode reward: [(0, '29.044')] [2023-03-11 10:52:14,386][04298] Updated weights for policy 0, policy_version 26720 (0.0005) [2023-03-11 10:52:17,448][04298] Updated weights for policy 0, policy_version 26800 (0.0004) [2023-03-11 10:52:17,811][04011] Fps is (10 sec: 13516.9, 60 sec: 12629.3, 300 sec: 12079.7). Total num frames: 13725696. Throughput: 0: 12639.9. Samples: 13695988. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:52:17,811][04011] Avg episode reward: [(0, '29.429')] [2023-03-11 10:52:20,598][04298] Updated weights for policy 0, policy_version 26880 (0.0005) [2023-03-11 10:52:22,811][04011] Fps is (10 sec: 13516.8, 60 sec: 12629.3, 300 sec: 12107.5). Total num frames: 13791232. Throughput: 0: 12790.6. Samples: 13774860. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:52:22,811][04011] Avg episode reward: [(0, '29.501')] [2023-03-11 10:52:22,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000026936_13791232.pth... [2023-03-11 10:52:22,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000026152_13389824.pth [2023-03-11 10:52:23,743][04298] Updated weights for policy 0, policy_version 26960 (0.0005) [2023-03-11 10:52:26,848][04298] Updated weights for policy 0, policy_version 27040 (0.0005) [2023-03-11 10:52:27,811][04011] Fps is (10 sec: 13107.2, 60 sec: 12765.9, 300 sec: 12135.3). Total num frames: 13856768. Throughput: 0: 12949.2. Samples: 13853824. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:52:27,811][04011] Avg episode reward: [(0, '30.416')] [2023-03-11 10:52:27,812][04254] Saving new best policy, reward=30.416! [2023-03-11 10:52:29,934][04298] Updated weights for policy 0, policy_version 27120 (0.0004) [2023-03-11 10:52:32,811][04011] Fps is (10 sec: 13107.2, 60 sec: 12834.1, 300 sec: 12163.0). Total num frames: 13922304. Throughput: 0: 13017.8. Samples: 13893704. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:52:32,811][04011] Avg episode reward: [(0, '30.447')] [2023-03-11 10:52:32,812][04254] Saving new best policy, reward=30.447! [2023-03-11 10:52:32,996][04298] Updated weights for policy 0, policy_version 27200 (0.0004) [2023-03-11 10:52:36,037][04298] Updated weights for policy 0, policy_version 27280 (0.0004) [2023-03-11 10:52:37,811][04011] Fps is (10 sec: 13107.2, 60 sec: 12902.4, 300 sec: 12190.8). Total num frames: 13987840. Throughput: 0: 13262.3. Samples: 13974404. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:52:37,811][04011] Avg episode reward: [(0, '26.766')] [2023-03-11 10:52:37,814][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000027320_13987840.pth... [2023-03-11 10:52:37,816][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000026544_13590528.pth [2023-03-11 10:52:39,118][04298] Updated weights for policy 0, policy_version 27360 (0.0004) [2023-03-11 10:52:42,222][04298] Updated weights for policy 0, policy_version 27440 (0.0004) [2023-03-11 10:52:42,811][04011] Fps is (10 sec: 13107.1, 60 sec: 13038.9, 300 sec: 12218.6). Total num frames: 14053376. Throughput: 0: 13293.6. Samples: 14053448. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:52:42,812][04011] Avg episode reward: [(0, '30.006')] [2023-03-11 10:52:45,332][04298] Updated weights for policy 0, policy_version 27520 (0.0004) [2023-03-11 10:52:47,811][04011] Fps is (10 sec: 13516.8, 60 sec: 13175.5, 300 sec: 12260.2). Total num frames: 14123008. Throughput: 0: 13276.2. Samples: 14093208. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:52:47,812][04011] Avg episode reward: [(0, '29.812')] [2023-03-11 10:52:48,330][04298] Updated weights for policy 0, policy_version 27600 (0.0004) [2023-03-11 10:52:51,410][04298] Updated weights for policy 0, policy_version 27680 (0.0004) [2023-03-11 10:52:52,811][04011] Fps is (10 sec: 13516.8, 60 sec: 13312.0, 300 sec: 12274.1). Total num frames: 14188544. Throughput: 0: 13286.6. Samples: 14174020. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:52:52,812][04011] Avg episode reward: [(0, '31.096')] [2023-03-11 10:52:52,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000027712_14188544.pth... [2023-03-11 10:52:52,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000026936_13791232.pth [2023-03-11 10:52:52,818][04254] Saving new best policy, reward=31.096! [2023-03-11 10:52:54,572][04298] Updated weights for policy 0, policy_version 27760 (0.0005) [2023-03-11 10:52:57,693][04298] Updated weights for policy 0, policy_version 27840 (0.0004) [2023-03-11 10:52:57,811][04011] Fps is (10 sec: 13107.2, 60 sec: 13312.0, 300 sec: 12301.9). Total num frames: 14254080. Throughput: 0: 13245.6. Samples: 14252412. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:52:57,812][04011] Avg episode reward: [(0, '19.706')] [2023-03-11 10:53:00,855][04298] Updated weights for policy 0, policy_version 27920 (0.0004) [2023-03-11 10:53:02,811][04011] Fps is (10 sec: 13107.3, 60 sec: 13243.7, 300 sec: 12329.7). Total num frames: 14319616. Throughput: 0: 13222.8. Samples: 14291016. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:53:02,811][04011] Avg episode reward: [(0, '3.494')] [2023-03-11 10:53:04,042][04298] Updated weights for policy 0, policy_version 28000 (0.0005) [2023-03-11 10:53:07,205][04298] Updated weights for policy 0, policy_version 28080 (0.0004) [2023-03-11 10:53:07,811][04011] Fps is (10 sec: 12697.7, 60 sec: 13175.5, 300 sec: 12343.5). Total num frames: 14381056. Throughput: 0: 13195.9. Samples: 14368676. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:53:07,811][04011] Avg episode reward: [(0, '24.874')] [2023-03-11 10:53:07,844][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000028096_14385152.pth... [2023-03-11 10:53:07,845][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000027320_13987840.pth [2023-03-11 10:53:10,343][04298] Updated weights for policy 0, policy_version 28160 (0.0004) [2023-03-11 10:53:12,811][04011] Fps is (10 sec: 12697.6, 60 sec: 13175.5, 300 sec: 12371.3). Total num frames: 14446592. Throughput: 0: 13174.0. Samples: 14446656. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:53:12,811][04011] Avg episode reward: [(0, '24.518')] [2023-03-11 10:53:13,476][04298] Updated weights for policy 0, policy_version 28240 (0.0004) [2023-03-11 10:53:16,641][04298] Updated weights for policy 0, policy_version 28320 (0.0005) [2023-03-11 10:53:17,811][04011] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12399.1). Total num frames: 14512128. Throughput: 0: 13151.8. Samples: 14485536. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:53:17,812][04011] Avg episode reward: [(0, '28.223')] [2023-03-11 10:53:19,751][04298] Updated weights for policy 0, policy_version 28400 (0.0004) [2023-03-11 10:53:22,811][04011] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12413.0). Total num frames: 14577664. Throughput: 0: 13112.0. Samples: 14564444. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:53:22,812][04011] Avg episode reward: [(0, '30.040')] [2023-03-11 10:53:22,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000028472_14577664.pth... [2023-03-11 10:53:22,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000027712_14188544.pth [2023-03-11 10:53:22,914][04298] Updated weights for policy 0, policy_version 28480 (0.0005) [2023-03-11 10:53:26,414][04298] Updated weights for policy 0, policy_version 28560 (0.0005) [2023-03-11 10:53:27,811][04011] Fps is (10 sec: 12697.6, 60 sec: 13038.9, 300 sec: 12413.0). Total num frames: 14639104. Throughput: 0: 12992.8. Samples: 14638124. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:53:27,812][04011] Avg episode reward: [(0, '26.088')] [2023-03-11 10:53:29,644][04298] Updated weights for policy 0, policy_version 28640 (0.0004) [2023-03-11 10:53:32,789][04298] Updated weights for policy 0, policy_version 28720 (0.0005) [2023-03-11 10:53:32,811][04011] Fps is (10 sec: 12697.7, 60 sec: 13038.9, 300 sec: 12440.7). Total num frames: 14704640. Throughput: 0: 12950.2. Samples: 14675968. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:53:32,811][04011] Avg episode reward: [(0, '19.976')] [2023-03-11 10:53:35,943][04298] Updated weights for policy 0, policy_version 28800 (0.0004) [2023-03-11 10:53:37,811][04011] Fps is (10 sec: 12697.5, 60 sec: 12970.6, 300 sec: 12440.7). Total num frames: 14766080. Throughput: 0: 12871.7. Samples: 14753248. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-11 10:53:37,812][04011] Avg episode reward: [(0, '30.209')] [2023-03-11 10:53:37,827][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000028848_14770176.pth... [2023-03-11 10:53:37,829][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000028096_14385152.pth [2023-03-11 10:53:39,114][04298] Updated weights for policy 0, policy_version 28880 (0.0004) [2023-03-11 10:53:42,352][04298] Updated weights for policy 0, policy_version 28960 (0.0003) [2023-03-11 10:53:42,811][04011] Fps is (10 sec: 12697.6, 60 sec: 12970.7, 300 sec: 12468.5). Total num frames: 14831616. Throughput: 0: 12843.6. Samples: 14830372. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-11 10:53:42,812][04011] Avg episode reward: [(0, '30.389')] [2023-03-11 10:53:45,520][04298] Updated weights for policy 0, policy_version 29040 (0.0003) [2023-03-11 10:53:47,811][04011] Fps is (10 sec: 13107.2, 60 sec: 12902.4, 300 sec: 12482.4). Total num frames: 14897152. Throughput: 0: 12833.9. Samples: 14868544. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-11 10:53:47,812][04011] Avg episode reward: [(0, '27.957')] [2023-03-11 10:53:48,683][04298] Updated weights for policy 0, policy_version 29120 (0.0003) [2023-03-11 10:53:51,840][04298] Updated weights for policy 0, policy_version 29200 (0.0003) [2023-03-11 10:53:52,811][04011] Fps is (10 sec: 13107.2, 60 sec: 12902.4, 300 sec: 12496.3). Total num frames: 14962688. Throughput: 0: 12837.7. Samples: 14946376. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-11 10:53:52,812][04011] Avg episode reward: [(0, '31.363')] [2023-03-11 10:53:52,814][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000029224_14962688.pth... [2023-03-11 10:53:52,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000028472_14577664.pth [2023-03-11 10:53:52,818][04254] Saving new best policy, reward=31.363! [2023-03-11 10:53:55,020][04298] Updated weights for policy 0, policy_version 29280 (0.0003) [2023-03-11 10:53:57,811][04011] Fps is (10 sec: 12697.6, 60 sec: 12834.1, 300 sec: 12496.3). Total num frames: 15024128. Throughput: 0: 12834.3. Samples: 15024200. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:53:57,812][04011] Avg episode reward: [(0, '30.711')] [2023-03-11 10:53:58,156][04298] Updated weights for policy 0, policy_version 29360 (0.0003) [2023-03-11 10:54:01,193][04298] Updated weights for policy 0, policy_version 29440 (0.0003) [2023-03-11 10:54:02,811][04011] Fps is (10 sec: 13107.2, 60 sec: 12902.4, 300 sec: 12537.9). Total num frames: 15093760. Throughput: 0: 12865.6. Samples: 15064488. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:54:02,812][04011] Avg episode reward: [(0, '26.683')] [2023-03-11 10:54:04,307][04298] Updated weights for policy 0, policy_version 29520 (0.0003) [2023-03-11 10:54:07,335][04298] Updated weights for policy 0, policy_version 29600 (0.0003) [2023-03-11 10:54:07,811][04011] Fps is (10 sec: 13516.7, 60 sec: 12970.6, 300 sec: 12565.7). Total num frames: 15159296. Throughput: 0: 12896.4. Samples: 15144784. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:54:07,812][04011] Avg episode reward: [(0, '17.610')] [2023-03-11 10:54:07,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000029608_15159296.pth... [2023-03-11 10:54:07,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000028848_14770176.pth [2023-03-11 10:54:10,517][04298] Updated weights for policy 0, policy_version 29680 (0.0003) [2023-03-11 10:54:12,811][04011] Fps is (10 sec: 13107.2, 60 sec: 12970.7, 300 sec: 12579.6). Total num frames: 15224832. Throughput: 0: 12986.8. Samples: 15222528. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:54:12,811][04011] Avg episode reward: [(0, '24.207')] [2023-03-11 10:54:13,663][04298] Updated weights for policy 0, policy_version 29760 (0.0003) [2023-03-11 10:54:16,923][04298] Updated weights for policy 0, policy_version 29840 (0.0005) [2023-03-11 10:54:17,811][04011] Fps is (10 sec: 12697.6, 60 sec: 12902.4, 300 sec: 12593.5). Total num frames: 15286272. Throughput: 0: 13016.4. Samples: 15261708. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:54:17,812][04011] Avg episode reward: [(0, '28.845')] [2023-03-11 10:54:20,369][04298] Updated weights for policy 0, policy_version 29920 (0.0005) [2023-03-11 10:54:22,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12834.1, 300 sec: 12593.5). Total num frames: 15347712. Throughput: 0: 12884.4. Samples: 15333044. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:54:22,811][04011] Avg episode reward: [(0, '23.661')] [2023-03-11 10:54:22,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000029976_15347712.pth... [2023-03-11 10:54:22,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000029224_14962688.pth [2023-03-11 10:54:23,804][04298] Updated weights for policy 0, policy_version 30000 (0.0005) [2023-03-11 10:54:27,355][04298] Updated weights for policy 0, policy_version 30080 (0.0005) [2023-03-11 10:54:27,811][04011] Fps is (10 sec: 11878.5, 60 sec: 12765.9, 300 sec: 12593.5). Total num frames: 15405056. Throughput: 0: 12737.3. Samples: 15403548. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:54:27,811][04011] Avg episode reward: [(0, '11.422')] [2023-03-11 10:54:30,883][04298] Updated weights for policy 0, policy_version 30160 (0.0005) [2023-03-11 10:54:32,811][04011] Fps is (10 sec: 11468.8, 60 sec: 12629.3, 300 sec: 12593.5). Total num frames: 15462400. Throughput: 0: 12652.3. Samples: 15437896. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-11 10:54:32,811][04011] Avg episode reward: [(0, '24.996')] [2023-03-11 10:54:34,276][04298] Updated weights for policy 0, policy_version 30240 (0.0005) [2023-03-11 10:54:37,804][04298] Updated weights for policy 0, policy_version 30320 (0.0005) [2023-03-11 10:54:37,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12629.3, 300 sec: 12593.5). Total num frames: 15523840. Throughput: 0: 12506.0. Samples: 15509144. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-11 10:54:37,811][04011] Avg episode reward: [(0, '30.137')] [2023-03-11 10:54:37,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000030320_15523840.pth... [2023-03-11 10:54:37,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000029608_15159296.pth [2023-03-11 10:54:41,236][04298] Updated weights for policy 0, policy_version 30400 (0.0005) [2023-03-11 10:54:42,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12492.8, 300 sec: 12593.5). Total num frames: 15581184. Throughput: 0: 12377.8. Samples: 15581200. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-11 10:54:42,811][04011] Avg episode reward: [(0, '28.859')] [2023-03-11 10:54:44,618][04298] Updated weights for policy 0, policy_version 30480 (0.0005) [2023-03-11 10:54:47,811][04011] Fps is (10 sec: 11878.5, 60 sec: 12424.5, 300 sec: 12593.5). Total num frames: 15642624. Throughput: 0: 12280.6. Samples: 15617112. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-11 10:54:47,811][04011] Avg episode reward: [(0, '29.339')] [2023-03-11 10:54:48,040][04298] Updated weights for policy 0, policy_version 30560 (0.0005) [2023-03-11 10:54:51,452][04298] Updated weights for policy 0, policy_version 30640 (0.0005) [2023-03-11 10:54:52,811][04011] Fps is (10 sec: 12287.9, 60 sec: 12356.3, 300 sec: 12593.5). Total num frames: 15704064. Throughput: 0: 12089.3. Samples: 15688804. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:54:52,812][04011] Avg episode reward: [(0, '28.224')] [2023-03-11 10:54:52,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000030672_15704064.pth... [2023-03-11 10:54:52,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000029976_15347712.pth [2023-03-11 10:54:54,568][04298] Updated weights for policy 0, policy_version 30720 (0.0004) [2023-03-11 10:54:57,668][04298] Updated weights for policy 0, policy_version 30800 (0.0004) [2023-03-11 10:54:57,811][04011] Fps is (10 sec: 12697.5, 60 sec: 12424.5, 300 sec: 12607.3). Total num frames: 15769600. Throughput: 0: 12125.5. Samples: 15768176. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:54:57,812][04011] Avg episode reward: [(0, '30.829')] [2023-03-11 10:55:00,736][04298] Updated weights for policy 0, policy_version 30880 (0.0004) [2023-03-11 10:55:02,811][04011] Fps is (10 sec: 13107.4, 60 sec: 12356.3, 300 sec: 12635.1). Total num frames: 15835136. Throughput: 0: 12152.7. Samples: 15808576. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:55:02,811][04011] Avg episode reward: [(0, '20.819')] [2023-03-11 10:55:04,152][04298] Updated weights for policy 0, policy_version 30960 (0.0005) [2023-03-11 10:55:07,560][04298] Updated weights for policy 0, policy_version 31040 (0.0005) [2023-03-11 10:55:07,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12219.7, 300 sec: 12635.1). Total num frames: 15892480. Throughput: 0: 12159.0. Samples: 15880200. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:55:07,812][04011] Avg episode reward: [(0, '30.771')] [2023-03-11 10:55:07,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000031040_15892480.pth... [2023-03-11 10:55:07,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000030320_15523840.pth [2023-03-11 10:55:10,719][04298] Updated weights for policy 0, policy_version 31120 (0.0004) [2023-03-11 10:55:12,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12219.7, 300 sec: 12649.0). Total num frames: 15958016. Throughput: 0: 12275.5. Samples: 15955944. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:55:12,811][04011] Avg episode reward: [(0, '30.604')] [2023-03-11 10:55:14,105][04298] Updated weights for policy 0, policy_version 31200 (0.0005) [2023-03-11 10:55:17,556][04298] Updated weights for policy 0, policy_version 31280 (0.0005) [2023-03-11 10:55:17,811][04011] Fps is (10 sec: 12288.1, 60 sec: 12151.5, 300 sec: 12649.0). Total num frames: 16015360. Throughput: 0: 12288.0. Samples: 15990856. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:55:17,811][04011] Avg episode reward: [(0, '30.537')] [2023-03-11 10:55:21,061][04298] Updated weights for policy 0, policy_version 31360 (0.0005) [2023-03-11 10:55:22,811][04011] Fps is (10 sec: 11878.3, 60 sec: 12151.5, 300 sec: 12649.0). Total num frames: 16076800. Throughput: 0: 12299.1. Samples: 16062604. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:55:22,811][04011] Avg episode reward: [(0, '29.748')] [2023-03-11 10:55:22,814][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000031400_16076800.pth... [2023-03-11 10:55:22,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000030672_15704064.pth [2023-03-11 10:55:24,519][04298] Updated weights for policy 0, policy_version 31440 (0.0005) [2023-03-11 10:55:27,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12151.5, 300 sec: 12635.1). Total num frames: 16134144. Throughput: 0: 12285.7. Samples: 16134056. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:55:27,811][04011] Avg episode reward: [(0, '29.817')] [2023-03-11 10:55:27,920][04298] Updated weights for policy 0, policy_version 31520 (0.0005) [2023-03-11 10:55:31,219][04298] Updated weights for policy 0, policy_version 31600 (0.0005) [2023-03-11 10:55:32,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12219.7, 300 sec: 12621.2). Total num frames: 16195584. Throughput: 0: 12310.2. Samples: 16171072. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:55:32,812][04011] Avg episode reward: [(0, '29.608')] [2023-03-11 10:55:34,451][04298] Updated weights for policy 0, policy_version 31680 (0.0004) [2023-03-11 10:55:37,606][04298] Updated weights for policy 0, policy_version 31760 (0.0004) [2023-03-11 10:55:37,811][04011] Fps is (10 sec: 12697.6, 60 sec: 12288.0, 300 sec: 12635.1). Total num frames: 16261120. Throughput: 0: 12418.5. Samples: 16247636. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 10:55:37,811][04011] Avg episode reward: [(0, '30.127')] [2023-03-11 10:55:37,814][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000031760_16261120.pth... [2023-03-11 10:55:37,816][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000031040_15892480.pth [2023-03-11 10:55:40,721][04298] Updated weights for policy 0, policy_version 31840 (0.0004) [2023-03-11 10:55:42,811][04011] Fps is (10 sec: 13107.2, 60 sec: 12424.5, 300 sec: 12649.0). Total num frames: 16326656. Throughput: 0: 12396.2. Samples: 16326004. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 10:55:42,812][04011] Avg episode reward: [(0, '27.044')] [2023-03-11 10:55:43,841][04298] Updated weights for policy 0, policy_version 31920 (0.0004) [2023-03-11 10:55:47,213][04298] Updated weights for policy 0, policy_version 32000 (0.0005) [2023-03-11 10:55:47,811][04011] Fps is (10 sec: 12697.6, 60 sec: 12424.5, 300 sec: 12649.0). Total num frames: 16388096. Throughput: 0: 12333.5. Samples: 16363584. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 10:55:47,822][04011] Avg episode reward: [(0, '29.426')] [2023-03-11 10:55:50,605][04298] Updated weights for policy 0, policy_version 32080 (0.0005) [2023-03-11 10:55:52,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12424.5, 300 sec: 12635.1). Total num frames: 16449536. Throughput: 0: 12357.2. Samples: 16436276. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 10:55:52,822][04011] Avg episode reward: [(0, '31.102')] [2023-03-11 10:55:52,825][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000032128_16449536.pth... [2023-03-11 10:55:52,827][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000031400_16076800.pth [2023-03-11 10:55:54,109][04298] Updated weights for policy 0, policy_version 32160 (0.0005) [2023-03-11 10:55:57,558][04298] Updated weights for policy 0, policy_version 32240 (0.0005) [2023-03-11 10:55:57,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12288.0, 300 sec: 12621.2). Total num frames: 16506880. Throughput: 0: 12244.4. Samples: 16506944. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:55:57,822][04011] Avg episode reward: [(0, '30.970')] [2023-03-11 10:56:00,948][04298] Updated weights for policy 0, policy_version 32320 (0.0005) [2023-03-11 10:56:02,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12219.7, 300 sec: 12621.2). Total num frames: 16568320. Throughput: 0: 12281.4. Samples: 16543520. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:56:02,822][04011] Avg episode reward: [(0, '31.629')] [2023-03-11 10:56:02,822][04254] Saving new best policy, reward=31.629! [2023-03-11 10:56:04,330][04298] Updated weights for policy 0, policy_version 32400 (0.0005) [2023-03-11 10:56:07,711][04298] Updated weights for policy 0, policy_version 32480 (0.0005) [2023-03-11 10:56:07,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12288.0, 300 sec: 12621.2). Total num frames: 16629760. Throughput: 0: 12298.9. Samples: 16616056. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:56:07,822][04011] Avg episode reward: [(0, '31.849')] [2023-03-11 10:56:07,825][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000032480_16629760.pth... [2023-03-11 10:56:07,828][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000031760_16261120.pth [2023-03-11 10:56:07,828][04254] Saving new best policy, reward=31.849! [2023-03-11 10:56:11,072][04298] Updated weights for policy 0, policy_version 32560 (0.0005) [2023-03-11 10:56:12,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12219.7, 300 sec: 12621.2). Total num frames: 16691200. Throughput: 0: 12310.5. Samples: 16688028. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:56:12,822][04011] Avg episode reward: [(0, '30.883')] [2023-03-11 10:56:14,472][04298] Updated weights for policy 0, policy_version 32640 (0.0005) [2023-03-11 10:56:17,811][04011] Fps is (10 sec: 11878.5, 60 sec: 12219.7, 300 sec: 12593.5). Total num frames: 16748544. Throughput: 0: 12296.9. Samples: 16724432. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-11 10:56:17,811][04011] Avg episode reward: [(0, '30.940')] [2023-03-11 10:56:17,896][04298] Updated weights for policy 0, policy_version 32720 (0.0005) [2023-03-11 10:56:21,423][04298] Updated weights for policy 0, policy_version 32800 (0.0005) [2023-03-11 10:56:22,811][04011] Fps is (10 sec: 11468.9, 60 sec: 12151.5, 300 sec: 12593.5). Total num frames: 16805888. Throughput: 0: 12168.6. Samples: 16795224. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-11 10:56:22,811][04011] Avg episode reward: [(0, '22.646')] [2023-03-11 10:56:22,826][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000032832_16809984.pth... [2023-03-11 10:56:22,829][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000032128_16449536.pth [2023-03-11 10:56:24,884][04298] Updated weights for policy 0, policy_version 32880 (0.0005) [2023-03-11 10:56:27,811][04011] Fps is (10 sec: 11878.5, 60 sec: 12219.7, 300 sec: 12593.5). Total num frames: 16867328. Throughput: 0: 12030.9. Samples: 16867392. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-11 10:56:27,811][04011] Avg episode reward: [(0, '28.101')] [2023-03-11 10:56:28,250][04298] Updated weights for policy 0, policy_version 32960 (0.0005) [2023-03-11 10:56:31,656][04298] Updated weights for policy 0, policy_version 33040 (0.0005) [2023-03-11 10:56:32,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12219.7, 300 sec: 12593.5). Total num frames: 16928768. Throughput: 0: 11997.5. Samples: 16903472. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-11 10:56:32,811][04011] Avg episode reward: [(0, '30.236')] [2023-03-11 10:56:35,013][04298] Updated weights for policy 0, policy_version 33120 (0.0005) [2023-03-11 10:56:37,811][04011] Fps is (10 sec: 12287.9, 60 sec: 12151.5, 300 sec: 12607.3). Total num frames: 16990208. Throughput: 0: 11983.8. Samples: 16975548. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-11 10:56:37,811][04011] Avg episode reward: [(0, '31.522')] [2023-03-11 10:56:37,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000033184_16990208.pth... [2023-03-11 10:56:37,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000032480_16629760.pth [2023-03-11 10:56:38,447][04298] Updated weights for policy 0, policy_version 33200 (0.0005) [2023-03-11 10:56:41,919][04298] Updated weights for policy 0, policy_version 33280 (0.0005) [2023-03-11 10:56:42,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12014.9, 300 sec: 12593.5). Total num frames: 17047552. Throughput: 0: 12006.7. Samples: 17047244. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-11 10:56:42,811][04011] Avg episode reward: [(0, '30.098')] [2023-03-11 10:56:45,320][04298] Updated weights for policy 0, policy_version 33360 (0.0005) [2023-03-11 10:56:47,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12014.9, 300 sec: 12607.4). Total num frames: 17108992. Throughput: 0: 12004.4. Samples: 17083720. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-11 10:56:47,811][04011] Avg episode reward: [(0, '31.121')] [2023-03-11 10:56:48,822][04298] Updated weights for policy 0, policy_version 33440 (0.0005) [2023-03-11 10:56:52,184][04298] Updated weights for policy 0, policy_version 33520 (0.0005) [2023-03-11 10:56:52,811][04011] Fps is (10 sec: 11878.3, 60 sec: 11946.7, 300 sec: 12579.6). Total num frames: 17166336. Throughput: 0: 11961.5. Samples: 17154324. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-11 10:56:52,811][04011] Avg episode reward: [(0, '30.946')] [2023-03-11 10:56:52,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000033528_17166336.pth... [2023-03-11 10:56:52,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000032832_16809984.pth [2023-03-11 10:56:55,533][04298] Updated weights for policy 0, policy_version 33600 (0.0005) [2023-03-11 10:56:57,811][04011] Fps is (10 sec: 11878.3, 60 sec: 12014.9, 300 sec: 12551.8). Total num frames: 17227776. Throughput: 0: 11981.1. Samples: 17227176. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-11 10:56:57,812][04011] Avg episode reward: [(0, '31.318')] [2023-03-11 10:56:59,089][04298] Updated weights for policy 0, policy_version 33680 (0.0005) [2023-03-11 10:57:02,487][04298] Updated weights for policy 0, policy_version 33760 (0.0005) [2023-03-11 10:57:02,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12014.9, 300 sec: 12537.9). Total num frames: 17289216. Throughput: 0: 11950.2. Samples: 17262192. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:57:02,812][04011] Avg episode reward: [(0, '14.404')] [2023-03-11 10:57:05,868][04298] Updated weights for policy 0, policy_version 33840 (0.0005) [2023-03-11 10:57:07,811][04011] Fps is (10 sec: 11878.4, 60 sec: 11946.7, 300 sec: 12510.2). Total num frames: 17346560. Throughput: 0: 11980.2. Samples: 17334336. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:57:07,812][04011] Avg episode reward: [(0, '1.927')] [2023-03-11 10:57:07,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000033880_17346560.pth... [2023-03-11 10:57:07,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000033184_16990208.pth [2023-03-11 10:57:09,300][04298] Updated weights for policy 0, policy_version 33920 (0.0005) [2023-03-11 10:57:12,788][04298] Updated weights for policy 0, policy_version 34000 (0.0005) [2023-03-11 10:57:12,811][04011] Fps is (10 sec: 11878.4, 60 sec: 11946.7, 300 sec: 12482.4). Total num frames: 17408000. Throughput: 0: 11949.6. Samples: 17405124. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:57:12,811][04011] Avg episode reward: [(0, '7.898')] [2023-03-11 10:57:16,252][04298] Updated weights for policy 0, policy_version 34080 (0.0005) [2023-03-11 10:57:17,811][04011] Fps is (10 sec: 11878.4, 60 sec: 11946.7, 300 sec: 12454.6). Total num frames: 17465344. Throughput: 0: 11941.3. Samples: 17440832. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:57:17,811][04011] Avg episode reward: [(0, '31.655')] [2023-03-11 10:57:19,609][04298] Updated weights for policy 0, policy_version 34160 (0.0005) [2023-03-11 10:57:22,811][04011] Fps is (10 sec: 11878.3, 60 sec: 12014.9, 300 sec: 12440.7). Total num frames: 17526784. Throughput: 0: 11944.3. Samples: 17513044. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:57:22,812][04011] Avg episode reward: [(0, '28.462')] [2023-03-11 10:57:22,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000034232_17526784.pth... [2023-03-11 10:57:22,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000033528_17166336.pth [2023-03-11 10:57:23,108][04298] Updated weights for policy 0, policy_version 34240 (0.0005) [2023-03-11 10:57:26,561][04298] Updated weights for policy 0, policy_version 34320 (0.0005) [2023-03-11 10:57:27,811][04011] Fps is (10 sec: 11878.4, 60 sec: 11946.6, 300 sec: 12413.0). Total num frames: 17584128. Throughput: 0: 11930.7. Samples: 17584128. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:57:27,811][04011] Avg episode reward: [(0, '25.487')] [2023-03-11 10:57:30,141][04298] Updated weights for policy 0, policy_version 34400 (0.0005) [2023-03-11 10:57:32,811][04011] Fps is (10 sec: 11468.8, 60 sec: 11878.4, 300 sec: 12385.2). Total num frames: 17641472. Throughput: 0: 11864.3. Samples: 17617616. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:57:32,812][04011] Avg episode reward: [(0, '28.656')] [2023-03-11 10:57:33,627][04298] Updated weights for policy 0, policy_version 34480 (0.0005) [2023-03-11 10:57:36,724][04298] Updated weights for policy 0, policy_version 34560 (0.0004) [2023-03-11 10:57:37,811][04011] Fps is (10 sec: 12288.0, 60 sec: 11946.7, 300 sec: 12385.2). Total num frames: 17707008. Throughput: 0: 11947.9. Samples: 17691980. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:57:37,812][04011] Avg episode reward: [(0, '31.673')] [2023-03-11 10:57:37,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000034584_17707008.pth... [2023-03-11 10:57:37,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000033880_17346560.pth [2023-03-11 10:57:39,816][04298] Updated weights for policy 0, policy_version 34640 (0.0003) [2023-03-11 10:57:42,811][04011] Fps is (10 sec: 13107.3, 60 sec: 12083.2, 300 sec: 12371.3). Total num frames: 17772544. Throughput: 0: 12056.6. Samples: 17769724. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:57:42,811][04011] Avg episode reward: [(0, '27.731')] [2023-03-11 10:57:43,164][04298] Updated weights for policy 0, policy_version 34720 (0.0004) [2023-03-11 10:57:46,641][04298] Updated weights for policy 0, policy_version 34800 (0.0005) [2023-03-11 10:57:47,811][04011] Fps is (10 sec: 12288.1, 60 sec: 12014.9, 300 sec: 12343.5). Total num frames: 17829888. Throughput: 0: 12069.6. Samples: 17805324. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:57:47,812][04011] Avg episode reward: [(0, '25.752')] [2023-03-11 10:57:50,100][04298] Updated weights for policy 0, policy_version 34880 (0.0005) [2023-03-11 10:57:52,811][04011] Fps is (10 sec: 11878.3, 60 sec: 12083.2, 300 sec: 12329.7). Total num frames: 17891328. Throughput: 0: 12031.3. Samples: 17875744. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:57:52,811][04011] Avg episode reward: [(0, '22.502')] [2023-03-11 10:57:52,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000034944_17891328.pth... [2023-03-11 10:57:52,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000034232_17526784.pth [2023-03-11 10:57:53,465][04298] Updated weights for policy 0, policy_version 34960 (0.0005) [2023-03-11 10:57:56,685][04298] Updated weights for policy 0, policy_version 35040 (0.0004) [2023-03-11 10:57:57,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12083.2, 300 sec: 12315.8). Total num frames: 17952768. Throughput: 0: 12154.3. Samples: 17952068. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:57:57,811][04011] Avg episode reward: [(0, '30.533')] [2023-03-11 10:57:59,864][04298] Updated weights for policy 0, policy_version 35120 (0.0004) [2023-03-11 10:58:02,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12083.2, 300 sec: 12315.8). Total num frames: 18014208. Throughput: 0: 12197.2. Samples: 17989704. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:58:02,811][04011] Avg episode reward: [(0, '28.600')] [2023-03-11 10:58:03,253][04298] Updated weights for policy 0, policy_version 35200 (0.0005) [2023-03-11 10:58:06,700][04298] Updated weights for policy 0, policy_version 35280 (0.0005) [2023-03-11 10:58:07,811][04011] Fps is (10 sec: 12287.9, 60 sec: 12151.5, 300 sec: 12301.9). Total num frames: 18075648. Throughput: 0: 12188.7. Samples: 18061536. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-11 10:58:07,812][04011] Avg episode reward: [(0, '25.053')] [2023-03-11 10:58:07,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000035304_18075648.pth... [2023-03-11 10:58:07,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000034584_17707008.pth [2023-03-11 10:58:10,180][04298] Updated weights for policy 0, policy_version 35360 (0.0005) [2023-03-11 10:58:12,811][04011] Fps is (10 sec: 11878.3, 60 sec: 12083.2, 300 sec: 12274.1). Total num frames: 18132992. Throughput: 0: 12206.6. Samples: 18133424. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-11 10:58:12,812][04011] Avg episode reward: [(0, '32.594')] [2023-03-11 10:58:12,817][04254] Saving new best policy, reward=32.594! [2023-03-11 10:58:13,525][04298] Updated weights for policy 0, policy_version 35440 (0.0005) [2023-03-11 10:58:16,947][04298] Updated weights for policy 0, policy_version 35520 (0.0005) [2023-03-11 10:58:17,811][04011] Fps is (10 sec: 11878.5, 60 sec: 12151.5, 300 sec: 12260.2). Total num frames: 18194432. Throughput: 0: 12271.7. Samples: 18169840. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-11 10:58:17,811][04011] Avg episode reward: [(0, '19.172')] [2023-03-11 10:58:20,333][04298] Updated weights for policy 0, policy_version 35600 (0.0005) [2023-03-11 10:58:22,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12151.5, 300 sec: 12260.2). Total num frames: 18255872. Throughput: 0: 12204.1. Samples: 18241164. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-11 10:58:22,811][04011] Avg episode reward: [(0, '1.514')] [2023-03-11 10:58:22,814][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000035656_18255872.pth... [2023-03-11 10:58:22,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000034944_17891328.pth [2023-03-11 10:58:23,653][04298] Updated weights for policy 0, policy_version 35680 (0.0004) [2023-03-11 10:58:26,897][04298] Updated weights for policy 0, policy_version 35760 (0.0004) [2023-03-11 10:58:27,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12219.7, 300 sec: 12246.3). Total num frames: 18317312. Throughput: 0: 12168.6. Samples: 18317312. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-11 10:58:27,811][04011] Avg episode reward: [(0, '8.293')] [2023-03-11 10:58:30,353][04298] Updated weights for policy 0, policy_version 35840 (0.0005) [2023-03-11 10:58:32,811][04011] Fps is (10 sec: 12288.1, 60 sec: 12288.0, 300 sec: 12246.3). Total num frames: 18378752. Throughput: 0: 12163.4. Samples: 18352676. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-11 10:58:32,811][04011] Avg episode reward: [(0, '12.721')] [2023-03-11 10:58:33,700][04298] Updated weights for policy 0, policy_version 35920 (0.0005) [2023-03-11 10:58:37,156][04298] Updated weights for policy 0, policy_version 36000 (0.0005) [2023-03-11 10:58:37,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12151.5, 300 sec: 12218.6). Total num frames: 18436096. Throughput: 0: 12196.9. Samples: 18424604. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-11 10:58:37,811][04011] Avg episode reward: [(0, '20.359')] [2023-03-11 10:58:37,852][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000036016_18440192.pth... [2023-03-11 10:58:37,853][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000035304_18075648.pth [2023-03-11 10:58:40,637][04298] Updated weights for policy 0, policy_version 36080 (0.0005) [2023-03-11 10:58:42,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12083.2, 300 sec: 12204.7). Total num frames: 18497536. Throughput: 0: 12115.5. Samples: 18497264. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-11 10:58:42,811][04011] Avg episode reward: [(0, '28.751')] [2023-03-11 10:58:44,016][04298] Updated weights for policy 0, policy_version 36160 (0.0005) [2023-03-11 10:58:47,456][04298] Updated weights for policy 0, policy_version 36240 (0.0005) [2023-03-11 10:58:47,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12151.5, 300 sec: 12190.8). Total num frames: 18558976. Throughput: 0: 12054.3. Samples: 18532148. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-11 10:58:47,811][04011] Avg episode reward: [(0, '30.073')] [2023-03-11 10:58:50,646][04298] Updated weights for policy 0, policy_version 36320 (0.0004) [2023-03-11 10:58:52,811][04011] Fps is (10 sec: 12697.5, 60 sec: 12219.7, 300 sec: 12204.7). Total num frames: 18624512. Throughput: 0: 12146.8. Samples: 18608144. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:58:52,812][04011] Avg episode reward: [(0, '31.255')] [2023-03-11 10:58:52,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000036376_18624512.pth... [2023-03-11 10:58:52,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000035656_18255872.pth [2023-03-11 10:58:53,733][04298] Updated weights for policy 0, policy_version 36400 (0.0005) [2023-03-11 10:58:56,829][04298] Updated weights for policy 0, policy_version 36480 (0.0004) [2023-03-11 10:58:57,811][04011] Fps is (10 sec: 13107.2, 60 sec: 12288.0, 300 sec: 12190.8). Total num frames: 18690048. Throughput: 0: 12314.6. Samples: 18687580. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:58:57,811][04011] Avg episode reward: [(0, '31.105')] [2023-03-11 10:58:59,862][04298] Updated weights for policy 0, policy_version 36560 (0.0004) [2023-03-11 10:59:02,811][04011] Fps is (10 sec: 12697.8, 60 sec: 12288.0, 300 sec: 12176.9). Total num frames: 18751488. Throughput: 0: 12384.3. Samples: 18727132. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:59:02,811][04011] Avg episode reward: [(0, '29.044')] [2023-03-11 10:59:03,208][04298] Updated weights for policy 0, policy_version 36640 (0.0004) [2023-03-11 10:59:06,600][04298] Updated weights for policy 0, policy_version 36720 (0.0005) [2023-03-11 10:59:07,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12288.0, 300 sec: 12163.0). Total num frames: 18812928. Throughput: 0: 12432.8. Samples: 18800640. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:59:07,811][04011] Avg episode reward: [(0, '31.225')] [2023-03-11 10:59:07,814][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000036744_18812928.pth... [2023-03-11 10:59:07,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000036016_18440192.pth [2023-03-11 10:59:10,027][04298] Updated weights for policy 0, policy_version 36800 (0.0005) [2023-03-11 10:59:12,811][04011] Fps is (10 sec: 12287.9, 60 sec: 12356.3, 300 sec: 12163.0). Total num frames: 18874368. Throughput: 0: 12322.6. Samples: 18871828. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:59:12,811][04011] Avg episode reward: [(0, '31.202')] [2023-03-11 10:59:13,496][04298] Updated weights for policy 0, policy_version 36880 (0.0005) [2023-03-11 10:59:16,885][04298] Updated weights for policy 0, policy_version 36960 (0.0005) [2023-03-11 10:59:17,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12288.0, 300 sec: 12149.2). Total num frames: 18931712. Throughput: 0: 12339.2. Samples: 18907940. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:59:17,811][04011] Avg episode reward: [(0, '31.390')] [2023-03-11 10:59:20,324][04298] Updated weights for policy 0, policy_version 37040 (0.0005) [2023-03-11 10:59:22,811][04011] Fps is (10 sec: 11878.3, 60 sec: 12288.0, 300 sec: 12163.0). Total num frames: 18993152. Throughput: 0: 12328.2. Samples: 18979376. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:59:22,812][04011] Avg episode reward: [(0, '31.033')] [2023-03-11 10:59:22,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000037096_18993152.pth... [2023-03-11 10:59:22,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000036376_18624512.pth [2023-03-11 10:59:23,761][04298] Updated weights for policy 0, policy_version 37120 (0.0005) [2023-03-11 10:59:27,183][04298] Updated weights for policy 0, policy_version 37200 (0.0005) [2023-03-11 10:59:27,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12219.7, 300 sec: 12163.0). Total num frames: 19050496. Throughput: 0: 12298.3. Samples: 19050688. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:59:27,812][04011] Avg episode reward: [(0, '30.195')] [2023-03-11 10:59:30,481][04298] Updated weights for policy 0, policy_version 37280 (0.0004) [2023-03-11 10:59:32,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12288.0, 300 sec: 12176.9). Total num frames: 19116032. Throughput: 0: 12346.8. Samples: 19087756. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:59:32,811][04011] Avg episode reward: [(0, '31.577')] [2023-03-11 10:59:33,592][04298] Updated weights for policy 0, policy_version 37360 (0.0004) [2023-03-11 10:59:36,693][04298] Updated weights for policy 0, policy_version 37440 (0.0004) [2023-03-11 10:59:37,811][04011] Fps is (10 sec: 13107.2, 60 sec: 12424.5, 300 sec: 12204.7). Total num frames: 19181568. Throughput: 0: 12434.9. Samples: 19167716. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:59:37,812][04011] Avg episode reward: [(0, '31.115')] [2023-03-11 10:59:37,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000037464_19181568.pth... [2023-03-11 10:59:37,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000036744_18812928.pth [2023-03-11 10:59:39,845][04298] Updated weights for policy 0, policy_version 37520 (0.0004) [2023-03-11 10:59:42,811][04011] Fps is (10 sec: 12697.6, 60 sec: 12424.5, 300 sec: 12204.7). Total num frames: 19243008. Throughput: 0: 12344.4. Samples: 19243080. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:59:42,811][04011] Avg episode reward: [(0, '31.966')] [2023-03-11 10:59:43,211][04298] Updated weights for policy 0, policy_version 37600 (0.0005) [2023-03-11 10:59:46,648][04298] Updated weights for policy 0, policy_version 37680 (0.0005) [2023-03-11 10:59:47,811][04011] Fps is (10 sec: 12288.1, 60 sec: 12424.5, 300 sec: 12204.7). Total num frames: 19304448. Throughput: 0: 12279.4. Samples: 19279708. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:59:47,811][04011] Avg episode reward: [(0, '31.064')] [2023-03-11 10:59:50,047][04298] Updated weights for policy 0, policy_version 37760 (0.0005) [2023-03-11 10:59:52,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12288.0, 300 sec: 12176.9). Total num frames: 19361792. Throughput: 0: 12205.7. Samples: 19349896. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:59:52,812][04011] Avg episode reward: [(0, '32.015')] [2023-03-11 10:59:52,816][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000037816_19361792.pth... [2023-03-11 10:59:52,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000037096_18993152.pth [2023-03-11 10:59:53,572][04298] Updated weights for policy 0, policy_version 37840 (0.0005) [2023-03-11 10:59:57,025][04298] Updated weights for policy 0, policy_version 37920 (0.0006) [2023-03-11 10:59:57,811][04011] Fps is (10 sec: 11878.5, 60 sec: 12219.7, 300 sec: 12163.0). Total num frames: 19423232. Throughput: 0: 12207.8. Samples: 19421176. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 10:59:57,811][04011] Avg episode reward: [(0, '31.819')] [2023-03-11 11:00:00,403][04298] Updated weights for policy 0, policy_version 38000 (0.0005) [2023-03-11 11:00:02,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12219.7, 300 sec: 12176.9). Total num frames: 19484672. Throughput: 0: 12222.8. Samples: 19457968. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:00:02,812][04011] Avg episode reward: [(0, '31.364')] [2023-03-11 11:00:03,597][04298] Updated weights for policy 0, policy_version 38080 (0.0005) [2023-03-11 11:00:06,655][04298] Updated weights for policy 0, policy_version 38160 (0.0004) [2023-03-11 11:00:07,811][04011] Fps is (10 sec: 12697.5, 60 sec: 12288.0, 300 sec: 12176.9). Total num frames: 19550208. Throughput: 0: 12377.2. Samples: 19536348. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:00:07,812][04011] Avg episode reward: [(0, '32.050')] [2023-03-11 11:00:07,816][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000038184_19550208.pth... [2023-03-11 11:00:07,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000037464_19181568.pth [2023-03-11 11:00:09,924][04298] Updated weights for policy 0, policy_version 38240 (0.0005) [2023-03-11 11:00:12,811][04011] Fps is (10 sec: 13107.3, 60 sec: 12356.3, 300 sec: 12204.7). Total num frames: 19615744. Throughput: 0: 12485.3. Samples: 19612524. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:00:12,811][04011] Avg episode reward: [(0, '31.732')] [2023-03-11 11:00:13,116][04298] Updated weights for policy 0, policy_version 38320 (0.0005) [2023-03-11 11:00:16,222][04298] Updated weights for policy 0, policy_version 38400 (0.0004) [2023-03-11 11:00:17,811][04011] Fps is (10 sec: 13107.3, 60 sec: 12492.8, 300 sec: 12218.6). Total num frames: 19681280. Throughput: 0: 12546.9. Samples: 19652368. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:00:17,811][04011] Avg episode reward: [(0, '31.355')] [2023-03-11 11:00:19,348][04298] Updated weights for policy 0, policy_version 38480 (0.0004) [2023-03-11 11:00:22,469][04298] Updated weights for policy 0, policy_version 38560 (0.0004) [2023-03-11 11:00:22,811][04011] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12246.3). Total num frames: 19746816. Throughput: 0: 12506.2. Samples: 19730496. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:00:22,811][04011] Avg episode reward: [(0, '30.605')] [2023-03-11 11:00:22,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000038568_19746816.pth... [2023-03-11 11:00:22,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000037816_19361792.pth [2023-03-11 11:00:25,742][04298] Updated weights for policy 0, policy_version 38640 (0.0004) [2023-03-11 11:00:27,811][04011] Fps is (10 sec: 12697.6, 60 sec: 12629.3, 300 sec: 12246.3). Total num frames: 19808256. Throughput: 0: 12530.8. Samples: 19806968. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:00:27,812][04011] Avg episode reward: [(0, '9.162')] [2023-03-11 11:00:29,031][04298] Updated weights for policy 0, policy_version 38720 (0.0005) [2023-03-11 11:00:32,353][04298] Updated weights for policy 0, policy_version 38800 (0.0005) [2023-03-11 11:00:32,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12561.1, 300 sec: 12232.5). Total num frames: 19869696. Throughput: 0: 12511.6. Samples: 19842732. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-11 11:00:32,812][04011] Avg episode reward: [(0, '9.508')] [2023-03-11 11:00:35,513][04298] Updated weights for policy 0, policy_version 38880 (0.0004) [2023-03-11 11:00:37,811][04011] Fps is (10 sec: 12697.6, 60 sec: 12561.1, 300 sec: 12232.5). Total num frames: 19935232. Throughput: 0: 12661.6. Samples: 19919668. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-11 11:00:37,812][04011] Avg episode reward: [(0, '8.191')] [2023-03-11 11:00:37,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000038936_19935232.pth... [2023-03-11 11:00:37,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000038184_19550208.pth [2023-03-11 11:00:38,695][04298] Updated weights for policy 0, policy_version 38960 (0.0004) [2023-03-11 11:00:41,855][04298] Updated weights for policy 0, policy_version 39040 (0.0005) [2023-03-11 11:00:42,811][04011] Fps is (10 sec: 12697.6, 60 sec: 12561.1, 300 sec: 12232.5). Total num frames: 19996672. Throughput: 0: 12792.4. Samples: 19996836. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-11 11:00:42,812][04011] Avg episode reward: [(0, '14.907')] [2023-03-11 11:00:45,054][04298] Updated weights for policy 0, policy_version 39120 (0.0005) [2023-03-11 11:00:47,811][04011] Fps is (10 sec: 12697.6, 60 sec: 12629.3, 300 sec: 12246.3). Total num frames: 20062208. Throughput: 0: 12845.5. Samples: 20036016. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-11 11:00:47,822][04011] Avg episode reward: [(0, '19.484')] [2023-03-11 11:00:48,154][04298] Updated weights for policy 0, policy_version 39200 (0.0004) [2023-03-11 11:00:51,319][04298] Updated weights for policy 0, policy_version 39280 (0.0004) [2023-03-11 11:00:52,811][04011] Fps is (10 sec: 13107.2, 60 sec: 12765.9, 300 sec: 12274.1). Total num frames: 20127744. Throughput: 0: 12847.8. Samples: 20114500. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-11 11:00:52,822][04011] Avg episode reward: [(0, '25.869')] [2023-03-11 11:00:52,826][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000039312_20127744.pth... [2023-03-11 11:00:52,827][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000038568_19746816.pth [2023-03-11 11:00:54,438][04298] Updated weights for policy 0, policy_version 39360 (0.0004) [2023-03-11 11:00:57,497][04298] Updated weights for policy 0, policy_version 39440 (0.0004) [2023-03-11 11:00:57,811][04011] Fps is (10 sec: 13107.2, 60 sec: 12834.1, 300 sec: 12288.0). Total num frames: 20193280. Throughput: 0: 12914.3. Samples: 20193668. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:00:57,822][04011] Avg episode reward: [(0, '26.193')] [2023-03-11 11:01:00,654][04298] Updated weights for policy 0, policy_version 39520 (0.0004) [2023-03-11 11:01:02,811][04011] Fps is (10 sec: 13107.2, 60 sec: 12902.4, 300 sec: 12301.9). Total num frames: 20258816. Throughput: 0: 12905.5. Samples: 20233116. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:01:02,822][04011] Avg episode reward: [(0, '26.335')] [2023-03-11 11:01:03,804][04298] Updated weights for policy 0, policy_version 39600 (0.0004) [2023-03-11 11:01:06,904][04298] Updated weights for policy 0, policy_version 39680 (0.0004) [2023-03-11 11:01:07,811][04011] Fps is (10 sec: 13107.2, 60 sec: 12902.4, 300 sec: 12315.8). Total num frames: 20324352. Throughput: 0: 12917.1. Samples: 20311764. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:01:07,822][04011] Avg episode reward: [(0, '27.702')] [2023-03-11 11:01:07,828][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000039704_20328448.pth... [2023-03-11 11:01:07,830][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000038936_19935232.pth [2023-03-11 11:01:09,993][04298] Updated weights for policy 0, policy_version 39760 (0.0004) [2023-03-11 11:01:12,811][04011] Fps is (10 sec: 13516.8, 60 sec: 12970.7, 300 sec: 12357.4). Total num frames: 20393984. Throughput: 0: 12961.0. Samples: 20390212. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:01:12,822][04011] Avg episode reward: [(0, '26.345')] [2023-03-11 11:01:13,125][04298] Updated weights for policy 0, policy_version 39840 (0.0004) [2023-03-11 11:01:16,230][04298] Updated weights for policy 0, policy_version 39920 (0.0004) [2023-03-11 11:01:17,811][04011] Fps is (10 sec: 13516.9, 60 sec: 12970.7, 300 sec: 12385.2). Total num frames: 20459520. Throughput: 0: 13049.0. Samples: 20429936. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:01:17,822][04011] Avg episode reward: [(0, '30.211')] [2023-03-11 11:01:19,315][04298] Updated weights for policy 0, policy_version 40000 (0.0005) [2023-03-11 11:01:22,448][04298] Updated weights for policy 0, policy_version 40080 (0.0005) [2023-03-11 11:01:22,811][04011] Fps is (10 sec: 13107.2, 60 sec: 12970.7, 300 sec: 12399.1). Total num frames: 20525056. Throughput: 0: 13091.3. Samples: 20508776. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-11 11:01:22,822][04011] Avg episode reward: [(0, '31.547')] [2023-03-11 11:01:22,826][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000040088_20525056.pth... [2023-03-11 11:01:22,828][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000039312_20127744.pth [2023-03-11 11:01:25,482][04298] Updated weights for policy 0, policy_version 40160 (0.0004) [2023-03-11 11:01:27,811][04011] Fps is (10 sec: 13107.3, 60 sec: 13038.9, 300 sec: 12413.0). Total num frames: 20590592. Throughput: 0: 13158.6. Samples: 20588972. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-11 11:01:27,822][04011] Avg episode reward: [(0, '31.559')] [2023-03-11 11:01:28,568][04298] Updated weights for policy 0, policy_version 40240 (0.0004) [2023-03-11 11:01:31,624][04298] Updated weights for policy 0, policy_version 40320 (0.0004) [2023-03-11 11:01:32,811][04011] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12426.8). Total num frames: 20656128. Throughput: 0: 13182.6. Samples: 20629232. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-11 11:01:32,822][04011] Avg episode reward: [(0, '32.223')] [2023-03-11 11:01:34,767][04298] Updated weights for policy 0, policy_version 40400 (0.0005) [2023-03-11 11:01:37,811][04011] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12454.6). Total num frames: 20721664. Throughput: 0: 13211.6. Samples: 20709020. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-11 11:01:37,822][04011] Avg episode reward: [(0, '31.103')] [2023-03-11 11:01:37,835][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000040480_20725760.pth... [2023-03-11 11:01:37,836][04298] Updated weights for policy 0, policy_version 40480 (0.0004) [2023-03-11 11:01:37,837][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000039704_20328448.pth [2023-03-11 11:01:40,837][04298] Updated weights for policy 0, policy_version 40560 (0.0004) [2023-03-11 11:01:42,811][04011] Fps is (10 sec: 13516.8, 60 sec: 13243.7, 300 sec: 12482.4). Total num frames: 20791296. Throughput: 0: 13223.4. Samples: 20788720. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-11 11:01:42,822][04011] Avg episode reward: [(0, '30.270')] [2023-03-11 11:01:44,089][04298] Updated weights for policy 0, policy_version 40640 (0.0005) [2023-03-11 11:01:47,628][04298] Updated weights for policy 0, policy_version 40720 (0.0005) [2023-03-11 11:01:47,811][04011] Fps is (10 sec: 12697.6, 60 sec: 13107.2, 300 sec: 12482.4). Total num frames: 20848640. Throughput: 0: 13145.7. Samples: 20824672. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:01:47,811][04011] Avg episode reward: [(0, '31.019')] [2023-03-11 11:01:50,930][04298] Updated weights for policy 0, policy_version 40800 (0.0005) [2023-03-11 11:01:52,811][04011] Fps is (10 sec: 11878.4, 60 sec: 13039.0, 300 sec: 12482.4). Total num frames: 20910080. Throughput: 0: 13023.0. Samples: 20897800. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:01:52,811][04011] Avg episode reward: [(0, '31.771')] [2023-03-11 11:01:52,825][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000040848_20914176.pth... [2023-03-11 11:01:52,826][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000040088_20525056.pth [2023-03-11 11:01:54,015][04298] Updated weights for policy 0, policy_version 40880 (0.0004) [2023-03-11 11:01:57,115][04298] Updated weights for policy 0, policy_version 40960 (0.0004) [2023-03-11 11:01:57,811][04011] Fps is (10 sec: 13107.3, 60 sec: 13107.2, 300 sec: 12510.2). Total num frames: 20979712. Throughput: 0: 13049.0. Samples: 20977416. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:01:57,811][04011] Avg episode reward: [(0, '30.772')] [2023-03-11 11:02:00,188][04298] Updated weights for policy 0, policy_version 41040 (0.0004) [2023-03-11 11:02:02,811][04011] Fps is (10 sec: 13516.8, 60 sec: 13107.2, 300 sec: 12537.9). Total num frames: 21045248. Throughput: 0: 13038.8. Samples: 21016680. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:02:02,811][04011] Avg episode reward: [(0, '31.124')] [2023-03-11 11:02:03,279][04298] Updated weights for policy 0, policy_version 41120 (0.0003) [2023-03-11 11:02:06,330][04298] Updated weights for policy 0, policy_version 41200 (0.0003) [2023-03-11 11:02:07,811][04011] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12551.8). Total num frames: 21110784. Throughput: 0: 13080.1. Samples: 21097380. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:02:07,812][04011] Avg episode reward: [(0, '32.044')] [2023-03-11 11:02:07,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000041232_21110784.pth... [2023-03-11 11:02:07,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000040480_20725760.pth [2023-03-11 11:02:09,414][04298] Updated weights for policy 0, policy_version 41280 (0.0004) [2023-03-11 11:02:12,584][04298] Updated weights for policy 0, policy_version 41360 (0.0004) [2023-03-11 11:02:12,811][04011] Fps is (10 sec: 13107.2, 60 sec: 13038.9, 300 sec: 12579.6). Total num frames: 21176320. Throughput: 0: 13052.2. Samples: 21176320. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:02:12,812][04011] Avg episode reward: [(0, '30.836')] [2023-03-11 11:02:15,596][04298] Updated weights for policy 0, policy_version 41440 (0.0003) [2023-03-11 11:02:17,811][04011] Fps is (10 sec: 13516.9, 60 sec: 13107.2, 300 sec: 12607.4). Total num frames: 21245952. Throughput: 0: 13053.5. Samples: 21216640. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:02:17,811][04011] Avg episode reward: [(0, '30.987')] [2023-03-11 11:02:18,644][04298] Updated weights for policy 0, policy_version 41520 (0.0003) [2023-03-11 11:02:21,847][04298] Updated weights for policy 0, policy_version 41600 (0.0004) [2023-03-11 11:02:22,811][04011] Fps is (10 sec: 13107.1, 60 sec: 13038.9, 300 sec: 12621.2). Total num frames: 21307392. Throughput: 0: 13032.8. Samples: 21295496. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:02:22,812][04011] Avg episode reward: [(0, '31.088')] [2023-03-11 11:02:22,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000041616_21307392.pth... [2023-03-11 11:02:22,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000040848_20914176.pth [2023-03-11 11:02:25,379][04298] Updated weights for policy 0, policy_version 41680 (0.0004) [2023-03-11 11:02:27,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12970.7, 300 sec: 12635.1). Total num frames: 21368832. Throughput: 0: 12824.0. Samples: 21365800. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:02:27,811][04011] Avg episode reward: [(0, '29.277')] [2023-03-11 11:02:28,830][04298] Updated weights for policy 0, policy_version 41760 (0.0003) [2023-03-11 11:02:32,243][04298] Updated weights for policy 0, policy_version 41840 (0.0005) [2023-03-11 11:02:32,811][04011] Fps is (10 sec: 11878.5, 60 sec: 12834.1, 300 sec: 12607.4). Total num frames: 21426176. Throughput: 0: 12822.2. Samples: 21401672. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:02:32,811][04011] Avg episode reward: [(0, '27.515')] [2023-03-11 11:02:35,767][04298] Updated weights for policy 0, policy_version 41920 (0.0005) [2023-03-11 11:02:37,811][04011] Fps is (10 sec: 11468.7, 60 sec: 12697.6, 300 sec: 12579.6). Total num frames: 21483520. Throughput: 0: 12760.2. Samples: 21472012. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:02:37,812][04011] Avg episode reward: [(0, '27.215')] [2023-03-11 11:02:37,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000041960_21483520.pth... [2023-03-11 11:02:37,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000041232_21110784.pth [2023-03-11 11:02:39,270][04298] Updated weights for policy 0, policy_version 42000 (0.0005) [2023-03-11 11:02:42,757][04298] Updated weights for policy 0, policy_version 42080 (0.0005) [2023-03-11 11:02:42,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12561.1, 300 sec: 12593.5). Total num frames: 21544960. Throughput: 0: 12557.7. Samples: 21542512. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:02:42,811][04011] Avg episode reward: [(0, '24.782')] [2023-03-11 11:02:46,299][04298] Updated weights for policy 0, policy_version 42160 (0.0004) [2023-03-11 11:02:47,811][04011] Fps is (10 sec: 11878.5, 60 sec: 12561.1, 300 sec: 12579.6). Total num frames: 21602304. Throughput: 0: 12468.0. Samples: 21577740. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:02:47,812][04011] Avg episode reward: [(0, '27.233')] [2023-03-11 11:02:49,765][04298] Updated weights for policy 0, policy_version 42240 (0.0005) [2023-03-11 11:02:52,811][04011] Fps is (10 sec: 11468.8, 60 sec: 12492.8, 300 sec: 12565.7). Total num frames: 21659648. Throughput: 0: 12229.0. Samples: 21647684. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:02:52,811][04011] Avg episode reward: [(0, '28.146')] [2023-03-11 11:02:52,825][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000042312_21663744.pth... [2023-03-11 11:02:52,828][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000041616_21307392.pth [2023-03-11 11:02:53,195][04298] Updated weights for policy 0, policy_version 42320 (0.0004) [2023-03-11 11:02:56,663][04298] Updated weights for policy 0, policy_version 42400 (0.0004) [2023-03-11 11:02:57,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12356.3, 300 sec: 12565.7). Total num frames: 21721088. Throughput: 0: 12077.8. Samples: 21719820. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:02:57,812][04011] Avg episode reward: [(0, '28.816')] [2023-03-11 11:03:00,044][04298] Updated weights for policy 0, policy_version 42480 (0.0005) [2023-03-11 11:03:02,811][04011] Fps is (10 sec: 12287.9, 60 sec: 12288.0, 300 sec: 12565.7). Total num frames: 21782528. Throughput: 0: 11991.0. Samples: 21756236. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:03:02,812][04011] Avg episode reward: [(0, '30.268')] [2023-03-11 11:03:03,423][04298] Updated weights for policy 0, policy_version 42560 (0.0005) [2023-03-11 11:03:06,928][04298] Updated weights for policy 0, policy_version 42640 (0.0005) [2023-03-11 11:03:07,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12151.5, 300 sec: 12565.7). Total num frames: 21839872. Throughput: 0: 11824.4. Samples: 21827596. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-11 11:03:07,812][04011] Avg episode reward: [(0, '30.349')] [2023-03-11 11:03:07,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000042656_21839872.pth... [2023-03-11 11:03:07,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000041960_21483520.pth [2023-03-11 11:03:10,395][04298] Updated weights for policy 0, policy_version 42720 (0.0005) [2023-03-11 11:03:12,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12083.2, 300 sec: 12565.7). Total num frames: 21901312. Throughput: 0: 11858.5. Samples: 21899432. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-11 11:03:12,811][04011] Avg episode reward: [(0, '26.955')] [2023-03-11 11:03:13,712][04298] Updated weights for policy 0, policy_version 42800 (0.0005) [2023-03-11 11:03:17,253][04298] Updated weights for policy 0, policy_version 42880 (0.0005) [2023-03-11 11:03:17,811][04011] Fps is (10 sec: 11878.4, 60 sec: 11878.4, 300 sec: 12551.8). Total num frames: 21958656. Throughput: 0: 11835.2. Samples: 21934256. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-11 11:03:17,812][04011] Avg episode reward: [(0, '18.860')] [2023-03-11 11:03:20,736][04298] Updated weights for policy 0, policy_version 42960 (0.0005) [2023-03-11 11:03:22,811][04011] Fps is (10 sec: 11878.3, 60 sec: 11878.4, 300 sec: 12551.8). Total num frames: 22020096. Throughput: 0: 11837.9. Samples: 22004716. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-11 11:03:22,812][04011] Avg episode reward: [(0, '14.528')] [2023-03-11 11:03:22,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000043008_22020096.pth... [2023-03-11 11:03:22,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000042312_21663744.pth [2023-03-11 11:03:24,217][04298] Updated weights for policy 0, policy_version 43040 (0.0005) [2023-03-11 11:03:27,650][04298] Updated weights for policy 0, policy_version 43120 (0.0005) [2023-03-11 11:03:27,811][04011] Fps is (10 sec: 11878.4, 60 sec: 11810.1, 300 sec: 12537.9). Total num frames: 22077440. Throughput: 0: 11875.5. Samples: 22076912. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-11 11:03:27,811][04011] Avg episode reward: [(0, '24.834')] [2023-03-11 11:03:31,157][04298] Updated weights for policy 0, policy_version 43200 (0.0005) [2023-03-11 11:03:32,811][04011] Fps is (10 sec: 11468.9, 60 sec: 11810.1, 300 sec: 12537.9). Total num frames: 22134784. Throughput: 0: 11856.8. Samples: 22111296. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:03:32,811][04011] Avg episode reward: [(0, '28.540')] [2023-03-11 11:03:34,588][04298] Updated weights for policy 0, policy_version 43280 (0.0005) [2023-03-11 11:03:37,811][04011] Fps is (10 sec: 11878.4, 60 sec: 11878.4, 300 sec: 12537.9). Total num frames: 22196224. Throughput: 0: 11905.2. Samples: 22183420. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:03:37,820][04011] Avg episode reward: [(0, '29.883')] [2023-03-11 11:03:37,824][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000043352_22196224.pth... [2023-03-11 11:03:37,827][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000042656_21839872.pth [2023-03-11 11:03:38,071][04298] Updated weights for policy 0, policy_version 43360 (0.0005) [2023-03-11 11:03:41,540][04298] Updated weights for policy 0, policy_version 43440 (0.0005) [2023-03-11 11:03:42,811][04011] Fps is (10 sec: 11878.4, 60 sec: 11810.1, 300 sec: 12524.0). Total num frames: 22253568. Throughput: 0: 11861.1. Samples: 22253568. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:03:42,822][04011] Avg episode reward: [(0, '29.859')] [2023-03-11 11:03:45,044][04298] Updated weights for policy 0, policy_version 43520 (0.0005) [2023-03-11 11:03:47,811][04011] Fps is (10 sec: 11878.5, 60 sec: 11878.4, 300 sec: 12510.2). Total num frames: 22315008. Throughput: 0: 11818.0. Samples: 22288044. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:03:47,822][04011] Avg episode reward: [(0, '29.271')] [2023-03-11 11:03:48,436][04298] Updated weights for policy 0, policy_version 43600 (0.0004) [2023-03-11 11:03:51,795][04298] Updated weights for policy 0, policy_version 43680 (0.0005) [2023-03-11 11:03:52,811][04011] Fps is (10 sec: 11878.5, 60 sec: 11878.4, 300 sec: 12482.4). Total num frames: 22372352. Throughput: 0: 11860.8. Samples: 22361332. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:03:52,822][04011] Avg episode reward: [(0, '30.947')] [2023-03-11 11:03:52,825][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000043704_22376448.pth... [2023-03-11 11:03:52,827][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000043008_22020096.pth [2023-03-11 11:03:55,264][04298] Updated weights for policy 0, policy_version 43760 (0.0005) [2023-03-11 11:03:57,811][04011] Fps is (10 sec: 11878.4, 60 sec: 11878.4, 300 sec: 12482.4). Total num frames: 22433792. Throughput: 0: 11855.1. Samples: 22432912. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:03:57,822][04011] Avg episode reward: [(0, '30.704')] [2023-03-11 11:03:58,611][04298] Updated weights for policy 0, policy_version 43840 (0.0005) [2023-03-11 11:04:01,812][04298] Updated weights for policy 0, policy_version 43920 (0.0004) [2023-03-11 11:04:02,811][04011] Fps is (10 sec: 12697.6, 60 sec: 11946.7, 300 sec: 12496.3). Total num frames: 22499328. Throughput: 0: 11921.6. Samples: 22470728. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-11 11:04:02,811][04011] Avg episode reward: [(0, '30.548')] [2023-03-11 11:04:05,072][04298] Updated weights for policy 0, policy_version 44000 (0.0004) [2023-03-11 11:04:07,811][04011] Fps is (10 sec: 12287.8, 60 sec: 11946.7, 300 sec: 12482.4). Total num frames: 22556672. Throughput: 0: 12020.3. Samples: 22545632. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-11 11:04:07,812][04011] Avg episode reward: [(0, '31.514')] [2023-03-11 11:04:07,821][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000044064_22560768.pth... [2023-03-11 11:04:07,822][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000043352_22196224.pth [2023-03-11 11:04:08,500][04298] Updated weights for policy 0, policy_version 44080 (0.0005) [2023-03-11 11:04:11,766][04298] Updated weights for policy 0, policy_version 44160 (0.0005) [2023-03-11 11:04:12,811][04011] Fps is (10 sec: 12288.1, 60 sec: 12014.9, 300 sec: 12510.2). Total num frames: 22622208. Throughput: 0: 12067.3. Samples: 22619940. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-11 11:04:12,811][04011] Avg episode reward: [(0, '31.485')] [2023-03-11 11:04:14,860][04298] Updated weights for policy 0, policy_version 44240 (0.0004) [2023-03-11 11:04:17,811][04011] Fps is (10 sec: 13107.4, 60 sec: 12151.5, 300 sec: 12524.0). Total num frames: 22687744. Throughput: 0: 12182.8. Samples: 22659524. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-11 11:04:17,811][04011] Avg episode reward: [(0, '30.580')] [2023-03-11 11:04:17,981][04298] Updated weights for policy 0, policy_version 44320 (0.0004) [2023-03-11 11:04:21,364][04298] Updated weights for policy 0, policy_version 44400 (0.0005) [2023-03-11 11:04:22,811][04011] Fps is (10 sec: 12697.5, 60 sec: 12151.5, 300 sec: 12537.9). Total num frames: 22749184. Throughput: 0: 12267.3. Samples: 22735448. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-11 11:04:22,811][04011] Avg episode reward: [(0, '19.575')] [2023-03-11 11:04:22,814][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000044432_22749184.pth... [2023-03-11 11:04:22,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000043704_22376448.pth [2023-03-11 11:04:24,799][04298] Updated weights for policy 0, policy_version 44480 (0.0005) [2023-03-11 11:04:27,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12151.5, 300 sec: 12510.2). Total num frames: 22806528. Throughput: 0: 12289.4. Samples: 22806592. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:04:27,811][04011] Avg episode reward: [(0, '31.315')] [2023-03-11 11:04:28,247][04298] Updated weights for policy 0, policy_version 44560 (0.0005) [2023-03-11 11:04:31,726][04298] Updated weights for policy 0, policy_version 44640 (0.0005) [2023-03-11 11:04:32,811][04011] Fps is (10 sec: 11878.5, 60 sec: 12219.7, 300 sec: 12496.3). Total num frames: 22867968. Throughput: 0: 12324.4. Samples: 22842644. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:04:32,811][04011] Avg episode reward: [(0, '27.429')] [2023-03-11 11:04:35,168][04298] Updated weights for policy 0, policy_version 44720 (0.0005) [2023-03-11 11:04:37,811][04011] Fps is (10 sec: 11878.3, 60 sec: 12151.5, 300 sec: 12482.4). Total num frames: 22925312. Throughput: 0: 12260.2. Samples: 22913040. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:04:37,812][04011] Avg episode reward: [(0, '27.023')] [2023-03-11 11:04:37,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000044776_22925312.pth... [2023-03-11 11:04:37,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000044064_22560768.pth [2023-03-11 11:04:38,618][04298] Updated weights for policy 0, policy_version 44800 (0.0005) [2023-03-11 11:04:42,052][04298] Updated weights for policy 0, policy_version 44880 (0.0005) [2023-03-11 11:04:42,811][04011] Fps is (10 sec: 11878.5, 60 sec: 12219.7, 300 sec: 12482.4). Total num frames: 22986752. Throughput: 0: 12263.2. Samples: 22984756. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:04:42,811][04011] Avg episode reward: [(0, '29.523')] [2023-03-11 11:04:45,446][04298] Updated weights for policy 0, policy_version 44960 (0.0005) [2023-03-11 11:04:47,811][04011] Fps is (10 sec: 12288.1, 60 sec: 12219.7, 300 sec: 12496.3). Total num frames: 23048192. Throughput: 0: 12222.6. Samples: 23020744. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:04:47,811][04011] Avg episode reward: [(0, '29.626')] [2023-03-11 11:04:48,832][04298] Updated weights for policy 0, policy_version 45040 (0.0005) [2023-03-11 11:04:52,248][04298] Updated weights for policy 0, policy_version 45120 (0.0005) [2023-03-11 11:04:52,811][04011] Fps is (10 sec: 11878.3, 60 sec: 12219.7, 300 sec: 12482.4). Total num frames: 23105536. Throughput: 0: 12169.5. Samples: 23093256. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:04:52,811][04011] Avg episode reward: [(0, '30.549')] [2023-03-11 11:04:52,814][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000045128_23105536.pth... [2023-03-11 11:04:52,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000044432_22749184.pth [2023-03-11 11:04:55,545][04298] Updated weights for policy 0, policy_version 45200 (0.0004) [2023-03-11 11:04:57,811][04011] Fps is (10 sec: 12287.9, 60 sec: 12288.0, 300 sec: 12496.3). Total num frames: 23171072. Throughput: 0: 12189.0. Samples: 23168444. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-11 11:04:57,811][04011] Avg episode reward: [(0, '31.157')] [2023-03-11 11:04:58,686][04298] Updated weights for policy 0, policy_version 45280 (0.0003) [2023-03-11 11:05:01,881][04298] Updated weights for policy 0, policy_version 45360 (0.0003) [2023-03-11 11:05:02,811][04011] Fps is (10 sec: 12697.6, 60 sec: 12219.7, 300 sec: 12482.4). Total num frames: 23232512. Throughput: 0: 12186.9. Samples: 23207936. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-11 11:05:02,811][04011] Avg episode reward: [(0, '31.374')] [2023-03-11 11:05:05,104][04298] Updated weights for policy 0, policy_version 45440 (0.0003) [2023-03-11 11:05:07,811][04011] Fps is (10 sec: 12697.6, 60 sec: 12356.3, 300 sec: 12482.4). Total num frames: 23298048. Throughput: 0: 12196.7. Samples: 23284300. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-11 11:05:07,812][04011] Avg episode reward: [(0, '31.127')] [2023-03-11 11:05:07,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000045504_23298048.pth... [2023-03-11 11:05:07,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000044776_22925312.pth [2023-03-11 11:05:08,252][04298] Updated weights for policy 0, policy_version 45520 (0.0003) [2023-03-11 11:05:11,401][04298] Updated weights for policy 0, policy_version 45600 (0.0003) [2023-03-11 11:05:12,811][04011] Fps is (10 sec: 13107.2, 60 sec: 12356.3, 300 sec: 12482.4). Total num frames: 23363584. Throughput: 0: 12330.5. Samples: 23361464. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-11 11:05:12,811][04011] Avg episode reward: [(0, '31.404')] [2023-03-11 11:05:14,735][04298] Updated weights for policy 0, policy_version 45680 (0.0004) [2023-03-11 11:05:17,811][04011] Fps is (10 sec: 12697.7, 60 sec: 12288.0, 300 sec: 12468.5). Total num frames: 23425024. Throughput: 0: 12354.2. Samples: 23398584. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-11 11:05:17,811][04011] Avg episode reward: [(0, '31.346')] [2023-03-11 11:05:18,043][04298] Updated weights for policy 0, policy_version 45760 (0.0005) [2023-03-11 11:05:21,475][04298] Updated weights for policy 0, policy_version 45840 (0.0005) [2023-03-11 11:05:22,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12219.7, 300 sec: 12454.6). Total num frames: 23482368. Throughput: 0: 12394.1. Samples: 23470776. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-11 11:05:22,811][04011] Avg episode reward: [(0, '29.731')] [2023-03-11 11:05:22,852][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000045872_23486464.pth... [2023-03-11 11:05:22,853][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000045128_23105536.pth [2023-03-11 11:05:24,960][04298] Updated weights for policy 0, policy_version 45920 (0.0006) [2023-03-11 11:05:27,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12288.0, 300 sec: 12454.6). Total num frames: 23543808. Throughput: 0: 12420.3. Samples: 23543672. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-11 11:05:27,811][04011] Avg episode reward: [(0, '28.674')] [2023-03-11 11:05:28,280][04298] Updated weights for policy 0, policy_version 46000 (0.0005) [2023-03-11 11:05:31,754][04298] Updated weights for policy 0, policy_version 46080 (0.0005) [2023-03-11 11:05:32,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12288.0, 300 sec: 12440.7). Total num frames: 23605248. Throughput: 0: 12411.4. Samples: 23579256. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-11 11:05:32,811][04011] Avg episode reward: [(0, '29.723')] [2023-03-11 11:05:35,229][04298] Updated weights for policy 0, policy_version 46160 (0.0005) [2023-03-11 11:05:37,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12288.0, 300 sec: 12426.8). Total num frames: 23662592. Throughput: 0: 12373.5. Samples: 23650064. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-11 11:05:37,811][04011] Avg episode reward: [(0, '21.939')] [2023-03-11 11:05:37,814][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000046216_23662592.pth... [2023-03-11 11:05:37,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000045504_23298048.pth [2023-03-11 11:05:38,696][04298] Updated weights for policy 0, policy_version 46240 (0.0006) [2023-03-11 11:05:42,205][04298] Updated weights for policy 0, policy_version 46320 (0.0006) [2023-03-11 11:05:42,811][04011] Fps is (10 sec: 11468.8, 60 sec: 12219.7, 300 sec: 12399.1). Total num frames: 23719936. Throughput: 0: 12257.1. Samples: 23720012. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-11 11:05:42,822][04011] Avg episode reward: [(0, '24.043')] [2023-03-11 11:05:45,656][04298] Updated weights for policy 0, policy_version 46400 (0.0005) [2023-03-11 11:05:47,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12219.7, 300 sec: 12385.2). Total num frames: 23781376. Throughput: 0: 12181.9. Samples: 23756120. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-11 11:05:47,822][04011] Avg episode reward: [(0, '28.988')] [2023-03-11 11:05:49,097][04298] Updated weights for policy 0, policy_version 46480 (0.0005) [2023-03-11 11:05:52,508][04298] Updated weights for policy 0, policy_version 46560 (0.0005) [2023-03-11 11:05:52,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12219.7, 300 sec: 12357.4). Total num frames: 23838720. Throughput: 0: 12050.4. Samples: 23826568. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-11 11:05:52,822][04011] Avg episode reward: [(0, '28.985')] [2023-03-11 11:05:52,864][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000046568_23842816.pth... [2023-03-11 11:05:52,866][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000045872_23486464.pth [2023-03-11 11:05:55,812][04298] Updated weights for policy 0, policy_version 46640 (0.0005) [2023-03-11 11:05:57,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12219.7, 300 sec: 12357.4). Total num frames: 23904256. Throughput: 0: 12051.5. Samples: 23903780. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:05:57,822][04011] Avg episode reward: [(0, '30.888')] [2023-03-11 11:05:58,853][04298] Updated weights for policy 0, policy_version 46720 (0.0004) [2023-03-11 11:06:01,974][04298] Updated weights for policy 0, policy_version 46800 (0.0004) [2023-03-11 11:06:02,811][04011] Fps is (10 sec: 13107.2, 60 sec: 12288.0, 300 sec: 12357.4). Total num frames: 23969792. Throughput: 0: 12096.3. Samples: 23942920. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:06:02,822][04011] Avg episode reward: [(0, '28.647')] [2023-03-11 11:06:05,046][04298] Updated weights for policy 0, policy_version 46880 (0.0004) [2023-03-11 11:06:07,811][04011] Fps is (10 sec: 13107.1, 60 sec: 12288.0, 300 sec: 12343.5). Total num frames: 24035328. Throughput: 0: 12272.1. Samples: 24023020. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:06:07,822][04011] Avg episode reward: [(0, '30.719')] [2023-03-11 11:06:07,824][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000046944_24035328.pth... [2023-03-11 11:06:07,826][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000046216_23662592.pth [2023-03-11 11:06:08,209][04298] Updated weights for policy 0, policy_version 46960 (0.0005) [2023-03-11 11:06:11,274][04298] Updated weights for policy 0, policy_version 47040 (0.0005) [2023-03-11 11:06:12,811][04011] Fps is (10 sec: 13107.3, 60 sec: 12288.0, 300 sec: 12343.5). Total num frames: 24100864. Throughput: 0: 12383.7. Samples: 24100940. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:06:12,822][04011] Avg episode reward: [(0, '30.151')] [2023-03-11 11:06:14,357][04298] Updated weights for policy 0, policy_version 47120 (0.0004) [2023-03-11 11:06:17,467][04298] Updated weights for policy 0, policy_version 47200 (0.0004) [2023-03-11 11:06:17,811][04011] Fps is (10 sec: 13516.8, 60 sec: 12424.5, 300 sec: 12357.4). Total num frames: 24170496. Throughput: 0: 12490.4. Samples: 24141324. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:06:17,822][04011] Avg episode reward: [(0, '31.610')] [2023-03-11 11:06:20,545][04298] Updated weights for policy 0, policy_version 47280 (0.0004) [2023-03-11 11:06:22,811][04011] Fps is (10 sec: 13107.1, 60 sec: 12492.8, 300 sec: 12343.5). Total num frames: 24231936. Throughput: 0: 12672.7. Samples: 24220336. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:06:22,812][04011] Avg episode reward: [(0, '31.030')] [2023-03-11 11:06:22,845][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000047336_24236032.pth... [2023-03-11 11:06:22,847][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000046568_23842816.pth [2023-03-11 11:06:23,888][04298] Updated weights for policy 0, policy_version 47360 (0.0005) [2023-03-11 11:06:27,077][04298] Updated weights for policy 0, policy_version 47440 (0.0004) [2023-03-11 11:06:27,811][04011] Fps is (10 sec: 12697.6, 60 sec: 12561.1, 300 sec: 12343.5). Total num frames: 24297472. Throughput: 0: 12791.2. Samples: 24295616. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:06:27,812][04011] Avg episode reward: [(0, '23.994')] [2023-03-11 11:06:30,207][04298] Updated weights for policy 0, policy_version 47520 (0.0005) [2023-03-11 11:06:32,811][04011] Fps is (10 sec: 13107.3, 60 sec: 12629.3, 300 sec: 12343.5). Total num frames: 24363008. Throughput: 0: 12850.8. Samples: 24334408. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:06:32,811][04011] Avg episode reward: [(0, '2.469')] [2023-03-11 11:06:33,278][04298] Updated weights for policy 0, policy_version 47600 (0.0004) [2023-03-11 11:06:36,382][04298] Updated weights for policy 0, policy_version 47680 (0.0004) [2023-03-11 11:06:37,811][04011] Fps is (10 sec: 13107.2, 60 sec: 12765.9, 300 sec: 12329.7). Total num frames: 24428544. Throughput: 0: 13065.1. Samples: 24414500. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:06:37,812][04011] Avg episode reward: [(0, '24.007')] [2023-03-11 11:06:37,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000047712_24428544.pth... [2023-03-11 11:06:37,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000046944_24035328.pth [2023-03-11 11:06:39,506][04298] Updated weights for policy 0, policy_version 47760 (0.0004) [2023-03-11 11:06:42,558][04298] Updated weights for policy 0, policy_version 47840 (0.0004) [2023-03-11 11:06:42,811][04011] Fps is (10 sec: 13107.2, 60 sec: 12902.4, 300 sec: 12357.4). Total num frames: 24494080. Throughput: 0: 13118.1. Samples: 24494096. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:06:42,811][04011] Avg episode reward: [(0, '30.762')] [2023-03-11 11:06:45,715][04298] Updated weights for policy 0, policy_version 47920 (0.0004) [2023-03-11 11:06:47,811][04011] Fps is (10 sec: 13107.2, 60 sec: 12970.7, 300 sec: 12371.3). Total num frames: 24559616. Throughput: 0: 13111.3. Samples: 24532928. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:06:47,811][04011] Avg episode reward: [(0, '32.130')] [2023-03-11 11:06:48,828][04298] Updated weights for policy 0, policy_version 48000 (0.0004) [2023-03-11 11:06:51,858][04298] Updated weights for policy 0, policy_version 48080 (0.0003) [2023-03-11 11:06:52,811][04011] Fps is (10 sec: 13516.8, 60 sec: 13175.5, 300 sec: 12371.3). Total num frames: 24629248. Throughput: 0: 13107.8. Samples: 24612872. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:06:52,812][04011] Avg episode reward: [(0, '31.548')] [2023-03-11 11:06:52,814][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000048104_24629248.pth... [2023-03-11 11:06:52,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000047336_24236032.pth [2023-03-11 11:06:54,971][04298] Updated weights for policy 0, policy_version 48160 (0.0004) [2023-03-11 11:06:57,811][04011] Fps is (10 sec: 13516.8, 60 sec: 13175.5, 300 sec: 12371.3). Total num frames: 24694784. Throughput: 0: 13117.8. Samples: 24691240. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:06:57,811][04011] Avg episode reward: [(0, '31.088')] [2023-03-11 11:06:58,098][04298] Updated weights for policy 0, policy_version 48240 (0.0004) [2023-03-11 11:07:01,279][04298] Updated weights for policy 0, policy_version 48320 (0.0004) [2023-03-11 11:07:02,811][04011] Fps is (10 sec: 12697.7, 60 sec: 13107.2, 300 sec: 12357.4). Total num frames: 24756224. Throughput: 0: 13117.7. Samples: 24731620. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:07:02,811][04011] Avg episode reward: [(0, '31.573')] [2023-03-11 11:07:04,645][04298] Updated weights for policy 0, policy_version 48400 (0.0005) [2023-03-11 11:07:07,811][04011] Fps is (10 sec: 12287.9, 60 sec: 13038.9, 300 sec: 12343.5). Total num frames: 24817664. Throughput: 0: 12976.4. Samples: 24804276. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:07:07,812][04011] Avg episode reward: [(0, '30.733')] [2023-03-11 11:07:07,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000048472_24817664.pth... [2023-03-11 11:07:07,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000047712_24428544.pth [2023-03-11 11:07:08,014][04298] Updated weights for policy 0, policy_version 48480 (0.0005) [2023-03-11 11:07:11,354][04298] Updated weights for policy 0, policy_version 48560 (0.0005) [2023-03-11 11:07:12,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12970.7, 300 sec: 12315.8). Total num frames: 24879104. Throughput: 0: 12929.0. Samples: 24877420. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:07:12,811][04011] Avg episode reward: [(0, '32.001')] [2023-03-11 11:07:14,753][04298] Updated weights for policy 0, policy_version 48640 (0.0005) [2023-03-11 11:07:17,811][04011] Fps is (10 sec: 11878.5, 60 sec: 12765.9, 300 sec: 12301.9). Total num frames: 24936448. Throughput: 0: 12850.6. Samples: 24912684. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:07:17,811][04011] Avg episode reward: [(0, '31.312')] [2023-03-11 11:07:18,247][04298] Updated weights for policy 0, policy_version 48720 (0.0005) [2023-03-11 11:07:21,704][04298] Updated weights for policy 0, policy_version 48800 (0.0005) [2023-03-11 11:07:22,811][04011] Fps is (10 sec: 11878.3, 60 sec: 12765.9, 300 sec: 12301.9). Total num frames: 24997888. Throughput: 0: 12659.9. Samples: 24984196. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:07:22,812][04011] Avg episode reward: [(0, '30.190')] [2023-03-11 11:07:22,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000048824_24997888.pth... [2023-03-11 11:07:22,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000048104_24629248.pth [2023-03-11 11:07:25,075][04298] Updated weights for policy 0, policy_version 48880 (0.0005) [2023-03-11 11:07:27,811][04011] Fps is (10 sec: 11878.5, 60 sec: 12629.4, 300 sec: 12301.9). Total num frames: 25055232. Throughput: 0: 12491.8. Samples: 25056224. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-11 11:07:27,811][04011] Avg episode reward: [(0, '27.650')] [2023-03-11 11:07:28,480][04298] Updated weights for policy 0, policy_version 48960 (0.0005) [2023-03-11 11:07:31,899][04298] Updated weights for policy 0, policy_version 49040 (0.0005) [2023-03-11 11:07:32,811][04011] Fps is (10 sec: 11878.5, 60 sec: 12561.1, 300 sec: 12315.8). Total num frames: 25116672. Throughput: 0: 12428.6. Samples: 25092212. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-11 11:07:32,811][04011] Avg episode reward: [(0, '30.266')] [2023-03-11 11:07:35,214][04298] Updated weights for policy 0, policy_version 49120 (0.0005) [2023-03-11 11:07:37,811][04011] Fps is (10 sec: 12287.9, 60 sec: 12492.8, 300 sec: 12315.8). Total num frames: 25178112. Throughput: 0: 12287.5. Samples: 25165808. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-11 11:07:37,811][04011] Avg episode reward: [(0, '31.046')] [2023-03-11 11:07:37,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000049176_25178112.pth... [2023-03-11 11:07:37,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000048472_24817664.pth [2023-03-11 11:07:38,613][04298] Updated weights for policy 0, policy_version 49200 (0.0005) [2023-03-11 11:07:41,975][04298] Updated weights for policy 0, policy_version 49280 (0.0005) [2023-03-11 11:07:42,811][04011] Fps is (10 sec: 12287.9, 60 sec: 12424.5, 300 sec: 12329.7). Total num frames: 25239552. Throughput: 0: 12162.1. Samples: 25238536. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-11 11:07:42,811][04011] Avg episode reward: [(0, '29.983')] [2023-03-11 11:07:45,475][04298] Updated weights for policy 0, policy_version 49360 (0.0005) [2023-03-11 11:07:47,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12288.0, 300 sec: 12329.7). Total num frames: 25296896. Throughput: 0: 12032.3. Samples: 25273072. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-11 11:07:47,811][04011] Avg episode reward: [(0, '27.147')] [2023-03-11 11:07:48,902][04298] Updated weights for policy 0, policy_version 49440 (0.0005) [2023-03-11 11:07:52,386][04298] Updated weights for policy 0, policy_version 49520 (0.0005) [2023-03-11 11:07:52,811][04011] Fps is (10 sec: 11878.3, 60 sec: 12151.5, 300 sec: 12329.7). Total num frames: 25358336. Throughput: 0: 12008.3. Samples: 25344648. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-11 11:07:52,814][04011] Avg episode reward: [(0, '28.848')] [2023-03-11 11:07:52,817][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000049528_25358336.pth... [2023-03-11 11:07:52,819][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000048824_24997888.pth [2023-03-11 11:07:55,754][04298] Updated weights for policy 0, policy_version 49600 (0.0005) [2023-03-11 11:07:57,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12014.9, 300 sec: 12315.8). Total num frames: 25415680. Throughput: 0: 11981.9. Samples: 25416604. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:07:57,822][04011] Avg episode reward: [(0, '25.924')] [2023-03-11 11:07:59,144][04298] Updated weights for policy 0, policy_version 49680 (0.0005) [2023-03-11 11:08:02,591][04298] Updated weights for policy 0, policy_version 49760 (0.0005) [2023-03-11 11:08:02,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12014.9, 300 sec: 12329.7). Total num frames: 25477120. Throughput: 0: 11998.6. Samples: 25452620. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:08:02,822][04011] Avg episode reward: [(0, '29.562')] [2023-03-11 11:08:05,996][04298] Updated weights for policy 0, policy_version 49840 (0.0005) [2023-03-11 11:08:07,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12014.9, 300 sec: 12329.7). Total num frames: 25538560. Throughput: 0: 12023.5. Samples: 25525252. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:08:07,822][04011] Avg episode reward: [(0, '30.600')] [2023-03-11 11:08:07,825][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000049880_25538560.pth... [2023-03-11 11:08:07,828][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000049176_25178112.pth [2023-03-11 11:08:09,311][04298] Updated weights for policy 0, policy_version 49920 (0.0004) [2023-03-11 11:08:12,732][04298] Updated weights for policy 0, policy_version 50000 (0.0005) [2023-03-11 11:08:12,811][04011] Fps is (10 sec: 12288.1, 60 sec: 12014.9, 300 sec: 12343.5). Total num frames: 25600000. Throughput: 0: 12037.9. Samples: 25597932. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:08:12,822][04011] Avg episode reward: [(0, '29.714')] [2023-03-11 11:08:16,115][04298] Updated weights for policy 0, policy_version 50080 (0.0005) [2023-03-11 11:08:17,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12014.9, 300 sec: 12329.7). Total num frames: 25657344. Throughput: 0: 12038.7. Samples: 25633956. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:08:17,822][04011] Avg episode reward: [(0, '30.469')] [2023-03-11 11:08:19,577][04298] Updated weights for policy 0, policy_version 50160 (0.0005) [2023-03-11 11:08:22,811][04011] Fps is (10 sec: 11878.3, 60 sec: 12014.9, 300 sec: 12343.5). Total num frames: 25718784. Throughput: 0: 12015.7. Samples: 25706516. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:08:22,822][04011] Avg episode reward: [(0, '31.302')] [2023-03-11 11:08:22,826][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000050232_25718784.pth... [2023-03-11 11:08:22,829][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000049528_25358336.pth [2023-03-11 11:08:22,937][04298] Updated weights for policy 0, policy_version 50240 (0.0005) [2023-03-11 11:08:26,369][04298] Updated weights for policy 0, policy_version 50320 (0.0005) [2023-03-11 11:08:27,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12083.2, 300 sec: 12357.4). Total num frames: 25780224. Throughput: 0: 11981.9. Samples: 25777720. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-11 11:08:27,822][04011] Avg episode reward: [(0, '31.601')] [2023-03-11 11:08:29,812][04298] Updated weights for policy 0, policy_version 50400 (0.0005) [2023-03-11 11:08:32,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12083.2, 300 sec: 12357.4). Total num frames: 25841664. Throughput: 0: 12033.3. Samples: 25814572. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-11 11:08:32,811][04011] Avg episode reward: [(0, '29.339')] [2023-03-11 11:08:32,891][04298] Updated weights for policy 0, policy_version 50480 (0.0003) [2023-03-11 11:08:36,033][04298] Updated weights for policy 0, policy_version 50560 (0.0004) [2023-03-11 11:08:37,811][04011] Fps is (10 sec: 12697.5, 60 sec: 12151.5, 300 sec: 12385.2). Total num frames: 25907200. Throughput: 0: 12192.7. Samples: 25893320. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-11 11:08:37,812][04011] Avg episode reward: [(0, '19.706')] [2023-03-11 11:08:37,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000050600_25907200.pth... [2023-03-11 11:08:37,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000049880_25538560.pth [2023-03-11 11:08:39,199][04298] Updated weights for policy 0, policy_version 50640 (0.0003) [2023-03-11 11:08:42,465][04298] Updated weights for policy 0, policy_version 50720 (0.0005) [2023-03-11 11:08:42,811][04011] Fps is (10 sec: 13107.3, 60 sec: 12219.7, 300 sec: 12399.1). Total num frames: 25972736. Throughput: 0: 12283.6. Samples: 25969364. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-11 11:08:42,811][04011] Avg episode reward: [(0, '10.639')] [2023-03-11 11:08:45,999][04298] Updated weights for policy 0, policy_version 50800 (0.0005) [2023-03-11 11:08:47,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12219.7, 300 sec: 12399.1). Total num frames: 26030080. Throughput: 0: 12279.9. Samples: 26005216. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-11 11:08:47,812][04011] Avg episode reward: [(0, '20.044')] [2023-03-11 11:08:49,497][04298] Updated weights for policy 0, policy_version 50880 (0.0005) [2023-03-11 11:08:52,811][04011] Fps is (10 sec: 11468.7, 60 sec: 12151.5, 300 sec: 12385.2). Total num frames: 26087424. Throughput: 0: 12221.1. Samples: 26075200. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-11 11:08:52,822][04011] Avg episode reward: [(0, '25.265')] [2023-03-11 11:08:52,825][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000050952_26087424.pth... [2023-03-11 11:08:52,828][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000050232_25718784.pth [2023-03-11 11:08:52,946][04298] Updated weights for policy 0, policy_version 50960 (0.0005) [2023-03-11 11:08:56,296][04298] Updated weights for policy 0, policy_version 51040 (0.0005) [2023-03-11 11:08:57,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12219.7, 300 sec: 12371.3). Total num frames: 26148864. Throughput: 0: 12242.9. Samples: 26148864. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-11 11:08:57,822][04011] Avg episode reward: [(0, '30.315')] [2023-03-11 11:08:59,671][04298] Updated weights for policy 0, policy_version 51120 (0.0005) [2023-03-11 11:09:02,811][04011] Fps is (10 sec: 12288.1, 60 sec: 12219.7, 300 sec: 12385.2). Total num frames: 26210304. Throughput: 0: 12223.8. Samples: 26184028. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:09:02,811][04011] Avg episode reward: [(0, '31.627')] [2023-03-11 11:09:03,075][04298] Updated weights for policy 0, policy_version 51200 (0.0005) [2023-03-11 11:09:06,557][04298] Updated weights for policy 0, policy_version 51280 (0.0005) [2023-03-11 11:09:07,811][04011] Fps is (10 sec: 11878.3, 60 sec: 12151.5, 300 sec: 12357.4). Total num frames: 26267648. Throughput: 0: 12197.9. Samples: 26255424. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:09:07,812][04011] Avg episode reward: [(0, '30.540')] [2023-03-11 11:09:07,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000051304_26267648.pth... [2023-03-11 11:09:07,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000050600_25907200.pth [2023-03-11 11:09:09,989][04298] Updated weights for policy 0, policy_version 51360 (0.0005) [2023-03-11 11:09:12,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12151.5, 300 sec: 12343.5). Total num frames: 26329088. Throughput: 0: 12227.1. Samples: 26327940. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:09:12,811][04011] Avg episode reward: [(0, '31.288')] [2023-03-11 11:09:13,340][04298] Updated weights for policy 0, policy_version 51440 (0.0005) [2023-03-11 11:09:16,796][04298] Updated weights for policy 0, policy_version 51520 (0.0005) [2023-03-11 11:09:17,811][04011] Fps is (10 sec: 11878.5, 60 sec: 12151.5, 300 sec: 12329.7). Total num frames: 26386432. Throughput: 0: 12208.0. Samples: 26363932. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:09:17,811][04011] Avg episode reward: [(0, '28.397')] [2023-03-11 11:09:20,257][04298] Updated weights for policy 0, policy_version 51600 (0.0005) [2023-03-11 11:09:22,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12151.5, 300 sec: 12343.5). Total num frames: 26447872. Throughput: 0: 12044.1. Samples: 26435304. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:09:22,811][04011] Avg episode reward: [(0, '28.689')] [2023-03-11 11:09:22,814][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000051656_26447872.pth... [2023-03-11 11:09:22,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000050952_26087424.pth [2023-03-11 11:09:23,716][04298] Updated weights for policy 0, policy_version 51680 (0.0005) [2023-03-11 11:09:27,048][04298] Updated weights for policy 0, policy_version 51760 (0.0005) [2023-03-11 11:09:27,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12151.5, 300 sec: 12343.5). Total num frames: 26509312. Throughput: 0: 11960.2. Samples: 26507572. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:09:27,811][04011] Avg episode reward: [(0, '30.887')] [2023-03-11 11:09:30,392][04298] Updated weights for policy 0, policy_version 51840 (0.0005) [2023-03-11 11:09:32,811][04011] Fps is (10 sec: 12288.1, 60 sec: 12151.5, 300 sec: 12357.4). Total num frames: 26570752. Throughput: 0: 11972.4. Samples: 26543972. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 11:09:32,811][04011] Avg episode reward: [(0, '31.448')] [2023-03-11 11:09:33,702][04298] Updated weights for policy 0, policy_version 51920 (0.0005) [2023-03-11 11:09:37,018][04298] Updated weights for policy 0, policy_version 52000 (0.0005) [2023-03-11 11:09:37,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12083.2, 300 sec: 12357.4). Total num frames: 26632192. Throughput: 0: 12075.7. Samples: 26618608. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 11:09:37,811][04011] Avg episode reward: [(0, '30.924')] [2023-03-11 11:09:37,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000052016_26632192.pth... [2023-03-11 11:09:37,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000051304_26267648.pth [2023-03-11 11:09:40,416][04298] Updated weights for policy 0, policy_version 52080 (0.0005) [2023-03-11 11:09:42,811][04011] Fps is (10 sec: 12287.9, 60 sec: 12014.9, 300 sec: 12357.4). Total num frames: 26693632. Throughput: 0: 12046.3. Samples: 26690948. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 11:09:42,812][04011] Avg episode reward: [(0, '30.267')] [2023-03-11 11:09:43,818][04298] Updated weights for policy 0, policy_version 52160 (0.0005) [2023-03-11 11:09:47,150][04298] Updated weights for policy 0, policy_version 52240 (0.0005) [2023-03-11 11:09:47,811][04011] Fps is (10 sec: 11878.5, 60 sec: 12014.9, 300 sec: 12357.4). Total num frames: 26750976. Throughput: 0: 12072.4. Samples: 26727288. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 11:09:47,811][04011] Avg episode reward: [(0, '17.769')] [2023-03-11 11:09:50,580][04298] Updated weights for policy 0, policy_version 52320 (0.0005) [2023-03-11 11:09:52,811][04011] Fps is (10 sec: 11878.5, 60 sec: 12083.2, 300 sec: 12343.5). Total num frames: 26812416. Throughput: 0: 12104.7. Samples: 26800136. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 11:09:52,811][04011] Avg episode reward: [(0, '19.069')] [2023-03-11 11:09:52,814][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000052368_26812416.pth... [2023-03-11 11:09:52,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000051656_26447872.pth [2023-03-11 11:09:53,957][04298] Updated weights for policy 0, policy_version 52400 (0.0005) [2023-03-11 11:09:57,360][04298] Updated weights for policy 0, policy_version 52480 (0.0004) [2023-03-11 11:09:57,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12083.2, 300 sec: 12343.5). Total num frames: 26873856. Throughput: 0: 12096.1. Samples: 26872264. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 11:09:57,811][04011] Avg episode reward: [(0, '29.560')] [2023-03-11 11:10:00,675][04298] Updated weights for policy 0, policy_version 52560 (0.0004) [2023-03-11 11:10:02,811][04011] Fps is (10 sec: 12287.9, 60 sec: 12083.2, 300 sec: 12329.7). Total num frames: 26935296. Throughput: 0: 12120.0. Samples: 26909332. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 11:10:02,812][04011] Avg episode reward: [(0, '29.729')] [2023-03-11 11:10:04,149][04298] Updated weights for policy 0, policy_version 52640 (0.0005) [2023-03-11 11:10:07,617][04298] Updated weights for policy 0, policy_version 52720 (0.0005) [2023-03-11 11:10:07,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12083.2, 300 sec: 12301.9). Total num frames: 26992640. Throughput: 0: 12112.4. Samples: 26980360. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:10:07,811][04011] Avg episode reward: [(0, '30.565')] [2023-03-11 11:10:07,814][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000052720_26992640.pth... [2023-03-11 11:10:07,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000052016_26632192.pth [2023-03-11 11:10:10,956][04298] Updated weights for policy 0, policy_version 52800 (0.0005) [2023-03-11 11:10:12,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12083.2, 300 sec: 12301.9). Total num frames: 27054080. Throughput: 0: 12102.9. Samples: 27052204. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:10:12,812][04011] Avg episode reward: [(0, '30.703')] [2023-03-11 11:10:14,449][04298] Updated weights for policy 0, policy_version 52880 (0.0005) [2023-03-11 11:10:17,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12083.2, 300 sec: 12301.9). Total num frames: 27111424. Throughput: 0: 12082.4. Samples: 27087680. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:10:17,811][04011] Avg episode reward: [(0, '12.099')] [2023-03-11 11:10:17,828][04298] Updated weights for policy 0, policy_version 52960 (0.0005) [2023-03-11 11:10:21,185][04298] Updated weights for policy 0, policy_version 53040 (0.0005) [2023-03-11 11:10:22,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12083.2, 300 sec: 12301.9). Total num frames: 27172864. Throughput: 0: 12045.2. Samples: 27160640. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:10:22,812][04011] Avg episode reward: [(0, '1.610')] [2023-03-11 11:10:22,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000053072_27172864.pth... [2023-03-11 11:10:22,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000052368_26812416.pth [2023-03-11 11:10:24,644][04298] Updated weights for policy 0, policy_version 53120 (0.0005) [2023-03-11 11:10:27,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12083.2, 300 sec: 12301.9). Total num frames: 27234304. Throughput: 0: 12023.6. Samples: 27232008. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:10:27,811][04011] Avg episode reward: [(0, '23.375')] [2023-03-11 11:10:28,079][04298] Updated weights for policy 0, policy_version 53200 (0.0005) [2023-03-11 11:10:31,553][04298] Updated weights for policy 0, policy_version 53280 (0.0005) [2023-03-11 11:10:32,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12014.9, 300 sec: 12301.9). Total num frames: 27291648. Throughput: 0: 11997.7. Samples: 27267184. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:10:32,811][04011] Avg episode reward: [(0, '24.530')] [2023-03-11 11:10:34,929][04298] Updated weights for policy 0, policy_version 53360 (0.0005) [2023-03-11 11:10:37,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12014.9, 300 sec: 12315.8). Total num frames: 27353088. Throughput: 0: 11988.3. Samples: 27339612. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:10:37,812][04011] Avg episode reward: [(0, '20.581')] [2023-03-11 11:10:37,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000053424_27353088.pth... [2023-03-11 11:10:37,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000052720_26992640.pth [2023-03-11 11:10:38,446][04298] Updated weights for policy 0, policy_version 53440 (0.0005) [2023-03-11 11:10:41,916][04298] Updated weights for policy 0, policy_version 53520 (0.0005) [2023-03-11 11:10:42,811][04011] Fps is (10 sec: 11878.4, 60 sec: 11946.7, 300 sec: 12301.9). Total num frames: 27410432. Throughput: 0: 11959.3. Samples: 27410432. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:10:42,811][04011] Avg episode reward: [(0, '18.259')] [2023-03-11 11:10:45,392][04298] Updated weights for policy 0, policy_version 53600 (0.0005) [2023-03-11 11:10:47,811][04011] Fps is (10 sec: 11468.9, 60 sec: 11946.7, 300 sec: 12301.9). Total num frames: 27467776. Throughput: 0: 11904.5. Samples: 27445032. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:10:47,822][04011] Avg episode reward: [(0, '20.876')] [2023-03-11 11:10:48,909][04298] Updated weights for policy 0, policy_version 53680 (0.0005) [2023-03-11 11:10:52,344][04298] Updated weights for policy 0, policy_version 53760 (0.0005) [2023-03-11 11:10:52,811][04011] Fps is (10 sec: 11878.3, 60 sec: 11946.7, 300 sec: 12288.0). Total num frames: 27529216. Throughput: 0: 11916.1. Samples: 27516584. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:10:52,822][04011] Avg episode reward: [(0, '22.963')] [2023-03-11 11:10:52,825][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000053768_27529216.pth... [2023-03-11 11:10:52,829][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000053072_27172864.pth [2023-03-11 11:10:55,939][04298] Updated weights for policy 0, policy_version 53840 (0.0005) [2023-03-11 11:10:57,811][04011] Fps is (10 sec: 11878.4, 60 sec: 11878.4, 300 sec: 12260.2). Total num frames: 27586560. Throughput: 0: 11847.9. Samples: 27585360. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:10:57,811][04011] Avg episode reward: [(0, '26.538')] [2023-03-11 11:10:59,448][04298] Updated weights for policy 0, policy_version 53920 (0.0005) [2023-03-11 11:11:02,811][04011] Fps is (10 sec: 11468.8, 60 sec: 11810.1, 300 sec: 12232.5). Total num frames: 27643904. Throughput: 0: 11816.0. Samples: 27619400. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:11:02,812][04011] Avg episode reward: [(0, '21.243')] [2023-03-11 11:11:02,956][04298] Updated weights for policy 0, policy_version 54000 (0.0005) [2023-03-11 11:11:06,389][04298] Updated weights for policy 0, policy_version 54080 (0.0005) [2023-03-11 11:11:07,811][04011] Fps is (10 sec: 11878.3, 60 sec: 11878.4, 300 sec: 12218.6). Total num frames: 27705344. Throughput: 0: 11787.2. Samples: 27691064. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:11:07,812][04011] Avg episode reward: [(0, '25.013')] [2023-03-11 11:11:07,814][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000054112_27705344.pth... [2023-03-11 11:11:07,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000053424_27353088.pth [2023-03-11 11:11:09,868][04298] Updated weights for policy 0, policy_version 54160 (0.0005) [2023-03-11 11:11:12,811][04011] Fps is (10 sec: 11878.4, 60 sec: 11810.1, 300 sec: 12176.9). Total num frames: 27762688. Throughput: 0: 11772.5. Samples: 27761772. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-11 11:11:12,811][04011] Avg episode reward: [(0, '22.674')] [2023-03-11 11:11:13,358][04298] Updated weights for policy 0, policy_version 54240 (0.0005) [2023-03-11 11:11:16,871][04298] Updated weights for policy 0, policy_version 54320 (0.0005) [2023-03-11 11:11:17,811][04011] Fps is (10 sec: 11468.9, 60 sec: 11810.1, 300 sec: 12163.0). Total num frames: 27820032. Throughput: 0: 11771.4. Samples: 27796896. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-11 11:11:17,811][04011] Avg episode reward: [(0, '15.337')] [2023-03-11 11:11:20,329][04298] Updated weights for policy 0, policy_version 54400 (0.0005) [2023-03-11 11:11:22,811][04011] Fps is (10 sec: 11878.4, 60 sec: 11810.1, 300 sec: 12149.2). Total num frames: 27881472. Throughput: 0: 11748.5. Samples: 27868292. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-11 11:11:22,811][04011] Avg episode reward: [(0, '18.296')] [2023-03-11 11:11:22,814][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000054456_27881472.pth... [2023-03-11 11:11:22,816][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000053768_27529216.pth [2023-03-11 11:11:23,563][04298] Updated weights for policy 0, policy_version 54480 (0.0004) [2023-03-11 11:11:26,961][04298] Updated weights for policy 0, policy_version 54560 (0.0005) [2023-03-11 11:11:27,811][04011] Fps is (10 sec: 12287.9, 60 sec: 11810.1, 300 sec: 12135.3). Total num frames: 27942912. Throughput: 0: 11832.8. Samples: 27942908. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-11 11:11:27,812][04011] Avg episode reward: [(0, '25.379')] [2023-03-11 11:11:30,296][04298] Updated weights for policy 0, policy_version 54640 (0.0004) [2023-03-11 11:11:32,811][04011] Fps is (10 sec: 12288.0, 60 sec: 11878.4, 300 sec: 12121.4). Total num frames: 28004352. Throughput: 0: 11876.7. Samples: 27979484. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-11 11:11:32,812][04011] Avg episode reward: [(0, '29.923')] [2023-03-11 11:11:33,663][04298] Updated weights for policy 0, policy_version 54720 (0.0005) [2023-03-11 11:11:37,096][04298] Updated weights for policy 0, policy_version 54800 (0.0005) [2023-03-11 11:11:37,811][04011] Fps is (10 sec: 12288.0, 60 sec: 11878.4, 300 sec: 12107.5). Total num frames: 28065792. Throughput: 0: 11877.8. Samples: 28051084. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-11 11:11:37,812][04011] Avg episode reward: [(0, '30.967')] [2023-03-11 11:11:37,814][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000054816_28065792.pth... [2023-03-11 11:11:37,816][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000054112_27705344.pth [2023-03-11 11:11:40,448][04298] Updated weights for policy 0, policy_version 54880 (0.0005) [2023-03-11 11:11:42,811][04011] Fps is (10 sec: 11878.3, 60 sec: 11878.4, 300 sec: 12079.7). Total num frames: 28123136. Throughput: 0: 11965.7. Samples: 28123820. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-11 11:11:42,812][04011] Avg episode reward: [(0, '29.887')] [2023-03-11 11:11:43,891][04298] Updated weights for policy 0, policy_version 54960 (0.0005) [2023-03-11 11:11:47,295][04298] Updated weights for policy 0, policy_version 55040 (0.0005) [2023-03-11 11:11:47,811][04011] Fps is (10 sec: 11878.4, 60 sec: 11946.7, 300 sec: 12052.0). Total num frames: 28184576. Throughput: 0: 12013.6. Samples: 28160012. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:11:47,812][04011] Avg episode reward: [(0, '31.346')] [2023-03-11 11:11:50,759][04298] Updated weights for policy 0, policy_version 55120 (0.0005) [2023-03-11 11:11:52,811][04011] Fps is (10 sec: 12287.9, 60 sec: 11946.6, 300 sec: 12038.1). Total num frames: 28246016. Throughput: 0: 12009.1. Samples: 28231476. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:11:52,812][04011] Avg episode reward: [(0, '31.452')] [2023-03-11 11:11:52,816][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000055168_28246016.pth... [2023-03-11 11:11:52,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000054456_27881472.pth [2023-03-11 11:11:54,047][04298] Updated weights for policy 0, policy_version 55200 (0.0005) [2023-03-11 11:11:57,528][04298] Updated weights for policy 0, policy_version 55280 (0.0004) [2023-03-11 11:11:57,811][04011] Fps is (10 sec: 11878.4, 60 sec: 11946.6, 300 sec: 12024.2). Total num frames: 28303360. Throughput: 0: 12036.9. Samples: 28303432. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:11:57,812][04011] Avg episode reward: [(0, '29.870')] [2023-03-11 11:12:00,949][04298] Updated weights for policy 0, policy_version 55360 (0.0004) [2023-03-11 11:12:02,811][04011] Fps is (10 sec: 11878.6, 60 sec: 12014.9, 300 sec: 12024.2). Total num frames: 28364800. Throughput: 0: 12064.7. Samples: 28339808. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:12:02,812][04011] Avg episode reward: [(0, '31.083')] [2023-03-11 11:12:04,371][04298] Updated weights for policy 0, policy_version 55440 (0.0005) [2023-03-11 11:12:07,762][04298] Updated weights for policy 0, policy_version 55520 (0.0004) [2023-03-11 11:12:07,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12014.9, 300 sec: 12024.2). Total num frames: 28426240. Throughput: 0: 12076.9. Samples: 28411752. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:12:07,811][04011] Avg episode reward: [(0, '30.034')] [2023-03-11 11:12:07,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000055520_28426240.pth... [2023-03-11 11:12:07,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000054816_28065792.pth [2023-03-11 11:12:11,052][04298] Updated weights for policy 0, policy_version 55600 (0.0005) [2023-03-11 11:12:12,811][04011] Fps is (10 sec: 12288.1, 60 sec: 12083.2, 300 sec: 12038.1). Total num frames: 28487680. Throughput: 0: 12046.1. Samples: 28484980. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:12:12,811][04011] Avg episode reward: [(0, '25.823')] [2023-03-11 11:12:14,327][04298] Updated weights for policy 0, policy_version 55680 (0.0005) [2023-03-11 11:12:17,461][04298] Updated weights for policy 0, policy_version 55760 (0.0004) [2023-03-11 11:12:17,811][04011] Fps is (10 sec: 12697.7, 60 sec: 12219.7, 300 sec: 12052.0). Total num frames: 28553216. Throughput: 0: 12104.8. Samples: 28524200. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:12:17,811][04011] Avg episode reward: [(0, '28.503')] [2023-03-11 11:12:20,703][04298] Updated weights for policy 0, policy_version 55840 (0.0005) [2023-03-11 11:12:22,811][04011] Fps is (10 sec: 12697.5, 60 sec: 12219.7, 300 sec: 12065.8). Total num frames: 28614656. Throughput: 0: 12221.9. Samples: 28601072. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-11 11:12:22,812][04011] Avg episode reward: [(0, '29.933')] [2023-03-11 11:12:22,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000055888_28614656.pth... [2023-03-11 11:12:22,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000055168_28246016.pth [2023-03-11 11:12:23,929][04298] Updated weights for policy 0, policy_version 55920 (0.0005) [2023-03-11 11:12:27,138][04298] Updated weights for policy 0, policy_version 56000 (0.0004) [2023-03-11 11:12:27,811][04011] Fps is (10 sec: 12697.5, 60 sec: 12288.0, 300 sec: 12079.7). Total num frames: 28680192. Throughput: 0: 12304.9. Samples: 28677540. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-11 11:12:27,811][04011] Avg episode reward: [(0, '30.449')] [2023-03-11 11:12:30,309][04298] Updated weights for policy 0, policy_version 56080 (0.0004) [2023-03-11 11:12:32,811][04011] Fps is (10 sec: 12697.7, 60 sec: 12288.0, 300 sec: 12079.7). Total num frames: 28741632. Throughput: 0: 12362.0. Samples: 28716300. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-11 11:12:32,811][04011] Avg episode reward: [(0, '31.457')] [2023-03-11 11:12:33,497][04298] Updated weights for policy 0, policy_version 56160 (0.0004) [2023-03-11 11:12:36,569][04298] Updated weights for policy 0, policy_version 56240 (0.0003) [2023-03-11 11:12:37,811][04011] Fps is (10 sec: 13107.2, 60 sec: 12424.5, 300 sec: 12107.5). Total num frames: 28811264. Throughput: 0: 12517.3. Samples: 28794752. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-11 11:12:37,812][04011] Avg episode reward: [(0, '31.439')] [2023-03-11 11:12:37,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000056272_28811264.pth... [2023-03-11 11:12:37,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000055520_28426240.pth [2023-03-11 11:12:39,655][04298] Updated weights for policy 0, policy_version 56320 (0.0003) [2023-03-11 11:12:42,811][04011] Fps is (10 sec: 13107.2, 60 sec: 12492.8, 300 sec: 12121.4). Total num frames: 28872704. Throughput: 0: 12652.1. Samples: 28872776. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-11 11:12:42,812][04011] Avg episode reward: [(0, '30.613')] [2023-03-11 11:12:42,864][04298] Updated weights for policy 0, policy_version 56400 (0.0004) [2023-03-11 11:12:45,939][04298] Updated weights for policy 0, policy_version 56480 (0.0004) [2023-03-11 11:12:47,811][04011] Fps is (10 sec: 12697.6, 60 sec: 12561.1, 300 sec: 12135.3). Total num frames: 28938240. Throughput: 0: 12730.2. Samples: 28912668. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-11 11:12:47,812][04011] Avg episode reward: [(0, '25.090')] [2023-03-11 11:12:49,098][04298] Updated weights for policy 0, policy_version 56560 (0.0004) [2023-03-11 11:12:52,153][04298] Updated weights for policy 0, policy_version 56640 (0.0004) [2023-03-11 11:12:52,811][04011] Fps is (10 sec: 13516.8, 60 sec: 12697.6, 300 sec: 12176.9). Total num frames: 29007872. Throughput: 0: 12884.4. Samples: 28991552. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-11 11:12:52,812][04011] Avg episode reward: [(0, '10.631')] [2023-03-11 11:12:52,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000056656_29007872.pth... [2023-03-11 11:12:52,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000055888_28614656.pth [2023-03-11 11:12:55,285][04298] Updated weights for policy 0, policy_version 56720 (0.0005) [2023-03-11 11:12:57,811][04011] Fps is (10 sec: 13516.9, 60 sec: 12834.2, 300 sec: 12190.8). Total num frames: 29073408. Throughput: 0: 13022.4. Samples: 29070988. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 11:12:57,811][04011] Avg episode reward: [(0, '28.391')] [2023-03-11 11:12:58,334][04298] Updated weights for policy 0, policy_version 56800 (0.0004) [2023-03-11 11:13:01,500][04298] Updated weights for policy 0, policy_version 56880 (0.0004) [2023-03-11 11:13:02,811][04011] Fps is (10 sec: 13107.2, 60 sec: 12902.4, 300 sec: 12204.7). Total num frames: 29138944. Throughput: 0: 13025.2. Samples: 29110336. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 11:13:02,812][04011] Avg episode reward: [(0, '29.743')] [2023-03-11 11:13:04,516][04298] Updated weights for policy 0, policy_version 56960 (0.0004) [2023-03-11 11:13:07,610][04298] Updated weights for policy 0, policy_version 57040 (0.0005) [2023-03-11 11:13:07,811][04011] Fps is (10 sec: 13107.1, 60 sec: 12970.7, 300 sec: 12218.6). Total num frames: 29204480. Throughput: 0: 13099.6. Samples: 29190552. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 11:13:07,812][04011] Avg episode reward: [(0, '30.912')] [2023-03-11 11:13:07,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000057040_29204480.pth... [2023-03-11 11:13:07,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000056272_28811264.pth [2023-03-11 11:13:10,762][04298] Updated weights for policy 0, policy_version 57120 (0.0005) [2023-03-11 11:13:12,811][04011] Fps is (10 sec: 13107.2, 60 sec: 13038.9, 300 sec: 12246.3). Total num frames: 29270016. Throughput: 0: 13155.1. Samples: 29269520. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 11:13:12,812][04011] Avg episode reward: [(0, '30.520')] [2023-03-11 11:13:13,804][04298] Updated weights for policy 0, policy_version 57200 (0.0004) [2023-03-11 11:13:16,872][04298] Updated weights for policy 0, policy_version 57280 (0.0004) [2023-03-11 11:13:17,811][04011] Fps is (10 sec: 13107.3, 60 sec: 13038.9, 300 sec: 12260.2). Total num frames: 29335552. Throughput: 0: 13187.2. Samples: 29309724. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 11:13:17,812][04011] Avg episode reward: [(0, '30.924')] [2023-03-11 11:13:19,986][04298] Updated weights for policy 0, policy_version 57360 (0.0004) [2023-03-11 11:13:22,811][04011] Fps is (10 sec: 13516.8, 60 sec: 13175.5, 300 sec: 12288.0). Total num frames: 29405184. Throughput: 0: 13202.5. Samples: 29388864. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 11:13:22,812][04011] Avg episode reward: [(0, '29.742')] [2023-03-11 11:13:22,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000057432_29405184.pth... [2023-03-11 11:13:22,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000056656_29007872.pth [2023-03-11 11:13:23,128][04298] Updated weights for policy 0, policy_version 57440 (0.0004) [2023-03-11 11:13:26,242][04298] Updated weights for policy 0, policy_version 57520 (0.0004) [2023-03-11 11:13:27,811][04011] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12288.0). Total num frames: 29466624. Throughput: 0: 13198.4. Samples: 29466704. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 11:13:27,811][04011] Avg episode reward: [(0, '29.340')] [2023-03-11 11:13:29,390][04298] Updated weights for policy 0, policy_version 57600 (0.0004) [2023-03-11 11:13:32,563][04298] Updated weights for policy 0, policy_version 57680 (0.0005) [2023-03-11 11:13:32,811][04011] Fps is (10 sec: 12697.6, 60 sec: 13175.5, 300 sec: 12288.0). Total num frames: 29532160. Throughput: 0: 13189.2. Samples: 29506180. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-11 11:13:32,812][04011] Avg episode reward: [(0, '29.884')] [2023-03-11 11:13:35,711][04298] Updated weights for policy 0, policy_version 57760 (0.0005) [2023-03-11 11:13:37,811][04011] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12288.0). Total num frames: 29597696. Throughput: 0: 13175.1. Samples: 29584432. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-11 11:13:37,812][04011] Avg episode reward: [(0, '31.627')] [2023-03-11 11:13:37,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000057808_29597696.pth... [2023-03-11 11:13:37,816][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000057040_29204480.pth [2023-03-11 11:13:38,826][04298] Updated weights for policy 0, policy_version 57840 (0.0004) [2023-03-11 11:13:42,034][04298] Updated weights for policy 0, policy_version 57920 (0.0005) [2023-03-11 11:13:42,811][04011] Fps is (10 sec: 13107.2, 60 sec: 13175.5, 300 sec: 12315.8). Total num frames: 29663232. Throughput: 0: 13133.8. Samples: 29662008. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-11 11:13:42,811][04011] Avg episode reward: [(0, '30.259')] [2023-03-11 11:13:45,120][04298] Updated weights for policy 0, policy_version 58000 (0.0004) [2023-03-11 11:13:47,811][04011] Fps is (10 sec: 13107.3, 60 sec: 13175.5, 300 sec: 12343.5). Total num frames: 29728768. Throughput: 0: 13135.2. Samples: 29701420. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-11 11:13:47,812][04011] Avg episode reward: [(0, '30.939')] [2023-03-11 11:13:48,191][04298] Updated weights for policy 0, policy_version 58080 (0.0004) [2023-03-11 11:13:51,261][04298] Updated weights for policy 0, policy_version 58160 (0.0004) [2023-03-11 11:13:52,811][04011] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12357.4). Total num frames: 29794304. Throughput: 0: 13143.8. Samples: 29782024. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-11 11:13:52,812][04011] Avg episode reward: [(0, '30.518')] [2023-03-11 11:13:52,822][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000058200_29798400.pth... [2023-03-11 11:13:52,823][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000057432_29405184.pth [2023-03-11 11:13:54,423][04298] Updated weights for policy 0, policy_version 58240 (0.0004) [2023-03-11 11:13:57,490][04298] Updated weights for policy 0, policy_version 58320 (0.0004) [2023-03-11 11:13:57,811][04011] Fps is (10 sec: 13516.9, 60 sec: 13175.5, 300 sec: 12385.2). Total num frames: 29863936. Throughput: 0: 13129.1. Samples: 29860328. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-11 11:13:57,811][04011] Avg episode reward: [(0, '17.268')] [2023-03-11 11:14:00,491][04298] Updated weights for policy 0, policy_version 58400 (0.0004) [2023-03-11 11:14:02,811][04011] Fps is (10 sec: 13516.9, 60 sec: 13175.5, 300 sec: 12413.0). Total num frames: 29929472. Throughput: 0: 13145.7. Samples: 29901280. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-11 11:14:02,811][04011] Avg episode reward: [(0, '28.060')] [2023-03-11 11:14:03,620][04298] Updated weights for policy 0, policy_version 58480 (0.0004) [2023-03-11 11:14:06,720][04298] Updated weights for policy 0, policy_version 58560 (0.0004) [2023-03-11 11:14:07,811][04011] Fps is (10 sec: 13107.1, 60 sec: 13175.5, 300 sec: 12426.8). Total num frames: 29995008. Throughput: 0: 13136.9. Samples: 29980024. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:14:07,812][04011] Avg episode reward: [(0, '20.482')] [2023-03-11 11:14:07,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000058584_29995008.pth... [2023-03-11 11:14:07,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000057808_29597696.pth [2023-03-11 11:14:09,769][04298] Updated weights for policy 0, policy_version 58640 (0.0004) [2023-03-11 11:14:12,811][04011] Fps is (10 sec: 13107.2, 60 sec: 13175.5, 300 sec: 12454.6). Total num frames: 30060544. Throughput: 0: 13198.0. Samples: 30060616. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:14:12,812][04011] Avg episode reward: [(0, '29.133')] [2023-03-11 11:14:12,846][04298] Updated weights for policy 0, policy_version 58720 (0.0004) [2023-03-11 11:14:15,924][04298] Updated weights for policy 0, policy_version 58800 (0.0004) [2023-03-11 11:14:17,811][04011] Fps is (10 sec: 13516.8, 60 sec: 13243.7, 300 sec: 12482.4). Total num frames: 30130176. Throughput: 0: 13222.0. Samples: 30101172. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:14:17,812][04011] Avg episode reward: [(0, '29.875')] [2023-03-11 11:14:18,947][04298] Updated weights for policy 0, policy_version 58880 (0.0004) [2023-03-11 11:14:22,038][04298] Updated weights for policy 0, policy_version 58960 (0.0004) [2023-03-11 11:14:22,811][04011] Fps is (10 sec: 13516.7, 60 sec: 13175.5, 300 sec: 12496.3). Total num frames: 30195712. Throughput: 0: 13257.6. Samples: 30181024. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:14:22,812][04011] Avg episode reward: [(0, '30.535')] [2023-03-11 11:14:22,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000058976_30195712.pth... [2023-03-11 11:14:22,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000058200_29798400.pth [2023-03-11 11:14:25,297][04298] Updated weights for policy 0, policy_version 59040 (0.0005) [2023-03-11 11:14:27,811][04011] Fps is (10 sec: 13107.3, 60 sec: 13243.7, 300 sec: 12510.2). Total num frames: 30261248. Throughput: 0: 13272.7. Samples: 30259280. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:14:27,811][04011] Avg episode reward: [(0, '30.143')] [2023-03-11 11:14:28,280][04298] Updated weights for policy 0, policy_version 59120 (0.0004) [2023-03-11 11:14:31,364][04298] Updated weights for policy 0, policy_version 59200 (0.0004) [2023-03-11 11:14:32,811][04011] Fps is (10 sec: 13107.3, 60 sec: 13243.7, 300 sec: 12524.0). Total num frames: 30326784. Throughput: 0: 13284.9. Samples: 30299240. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:14:32,811][04011] Avg episode reward: [(0, '31.199')] [2023-03-11 11:14:34,453][04298] Updated weights for policy 0, policy_version 59280 (0.0004) [2023-03-11 11:14:37,566][04298] Updated weights for policy 0, policy_version 59360 (0.0004) [2023-03-11 11:14:37,811][04011] Fps is (10 sec: 13107.2, 60 sec: 13243.7, 300 sec: 12537.9). Total num frames: 30392320. Throughput: 0: 13272.7. Samples: 30379296. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:14:37,812][04011] Avg episode reward: [(0, '30.954')] [2023-03-11 11:14:37,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000059360_30392320.pth... [2023-03-11 11:14:37,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000058584_29995008.pth [2023-03-11 11:14:40,685][04298] Updated weights for policy 0, policy_version 59440 (0.0005) [2023-03-11 11:14:42,811][04011] Fps is (10 sec: 13107.2, 60 sec: 13243.7, 300 sec: 12565.7). Total num frames: 30457856. Throughput: 0: 13278.2. Samples: 30457848. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-11 11:14:42,812][04011] Avg episode reward: [(0, '30.905')] [2023-03-11 11:14:43,825][04298] Updated weights for policy 0, policy_version 59520 (0.0004) [2023-03-11 11:14:46,892][04298] Updated weights for policy 0, policy_version 59600 (0.0004) [2023-03-11 11:14:47,811][04011] Fps is (10 sec: 13107.2, 60 sec: 13243.7, 300 sec: 12579.6). Total num frames: 30523392. Throughput: 0: 13235.5. Samples: 30496880. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-11 11:14:47,811][04011] Avg episode reward: [(0, '30.608')] [2023-03-11 11:14:50,047][04298] Updated weights for policy 0, policy_version 59680 (0.0005) [2023-03-11 11:14:52,811][04011] Fps is (10 sec: 13107.1, 60 sec: 13243.7, 300 sec: 12593.5). Total num frames: 30588928. Throughput: 0: 13250.8. Samples: 30576312. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-11 11:14:52,812][04011] Avg episode reward: [(0, '29.100')] [2023-03-11 11:14:52,841][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000059752_30593024.pth... [2023-03-11 11:14:52,842][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000058976_30195712.pth [2023-03-11 11:14:53,162][04298] Updated weights for policy 0, policy_version 59760 (0.0004) [2023-03-11 11:14:56,207][04298] Updated weights for policy 0, policy_version 59840 (0.0004) [2023-03-11 11:14:57,811][04011] Fps is (10 sec: 13516.8, 60 sec: 13243.7, 300 sec: 12621.2). Total num frames: 30658560. Throughput: 0: 13231.5. Samples: 30656032. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-11 11:14:57,812][04011] Avg episode reward: [(0, '30.558')] [2023-03-11 11:14:59,223][04298] Updated weights for policy 0, policy_version 59920 (0.0004) [2023-03-11 11:15:01,718][04254] Early stopping after 2 epochs (8 sgd steps), loss delta 0.0000006 [2023-03-11 11:15:02,322][04298] Updated weights for policy 0, policy_version 60000 (0.0005) [2023-03-11 11:15:02,811][04011] Fps is (10 sec: 13516.8, 60 sec: 13243.7, 300 sec: 12649.0). Total num frames: 30724096. Throughput: 0: 13207.0. Samples: 30695488. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-11 11:15:02,811][04011] Avg episode reward: [(0, '30.595')] [2023-03-11 11:15:05,439][04298] Updated weights for policy 0, policy_version 60080 (0.0004) [2023-03-11 11:15:07,811][04011] Fps is (10 sec: 13107.2, 60 sec: 13243.7, 300 sec: 12662.9). Total num frames: 30789632. Throughput: 0: 13203.4. Samples: 30775176. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-11 11:15:07,812][04011] Avg episode reward: [(0, '30.781')] [2023-03-11 11:15:07,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000060136_30789632.pth... [2023-03-11 11:15:07,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000059360_30392320.pth [2023-03-11 11:15:08,667][04298] Updated weights for policy 0, policy_version 60160 (0.0005) [2023-03-11 11:15:11,984][04298] Updated weights for policy 0, policy_version 60240 (0.0005) [2023-03-11 11:15:12,811][04011] Fps is (10 sec: 12697.6, 60 sec: 13175.5, 300 sec: 12676.8). Total num frames: 30851072. Throughput: 0: 13128.1. Samples: 30850044. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-11 11:15:12,812][04011] Avg episode reward: [(0, '28.922')] [2023-03-11 11:15:15,447][04298] Updated weights for policy 0, policy_version 60320 (0.0005) [2023-03-11 11:15:17,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12970.7, 300 sec: 12662.9). Total num frames: 30908416. Throughput: 0: 13017.6. Samples: 30885032. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-11 11:15:17,812][04011] Avg episode reward: [(0, '28.356')] [2023-03-11 11:15:18,939][04298] Updated weights for policy 0, policy_version 60400 (0.0005) [2023-03-11 11:15:22,306][04298] Updated weights for policy 0, policy_version 60480 (0.0005) [2023-03-11 11:15:22,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12902.4, 300 sec: 12662.9). Total num frames: 30969856. Throughput: 0: 12847.7. Samples: 30957444. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:15:22,812][04011] Avg episode reward: [(0, '30.891')] [2023-03-11 11:15:22,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000060488_30969856.pth... [2023-03-11 11:15:22,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000059752_30593024.pth [2023-03-11 11:15:25,737][04298] Updated weights for policy 0, policy_version 60560 (0.0006) [2023-03-11 11:15:27,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12765.9, 300 sec: 12662.9). Total num frames: 31027200. Throughput: 0: 12664.4. Samples: 31027744. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:15:27,812][04011] Avg episode reward: [(0, '29.476')] [2023-03-11 11:15:29,267][04298] Updated weights for policy 0, policy_version 60640 (0.0005) [2023-03-11 11:15:32,744][04298] Updated weights for policy 0, policy_version 60720 (0.0005) [2023-03-11 11:15:32,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12697.6, 300 sec: 12662.9). Total num frames: 31088640. Throughput: 0: 12589.8. Samples: 31063420. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:15:32,812][04011] Avg episode reward: [(0, '29.937')] [2023-03-11 11:15:36,070][04298] Updated weights for policy 0, policy_version 60800 (0.0005) [2023-03-11 11:15:37,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12629.3, 300 sec: 12676.8). Total num frames: 31150080. Throughput: 0: 12423.5. Samples: 31135368. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:15:37,812][04011] Avg episode reward: [(0, '29.910')] [2023-03-11 11:15:37,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000060840_31150080.pth... [2023-03-11 11:15:37,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000060136_30789632.pth [2023-03-11 11:15:39,452][04298] Updated weights for policy 0, policy_version 60880 (0.0005) [2023-03-11 11:15:42,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12492.8, 300 sec: 12676.8). Total num frames: 31207424. Throughput: 0: 12254.6. Samples: 31207488. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:15:42,811][04011] Avg episode reward: [(0, '27.795')] [2023-03-11 11:15:42,864][04298] Updated weights for policy 0, policy_version 60960 (0.0005) [2023-03-11 11:15:45,945][04298] Updated weights for policy 0, policy_version 61040 (0.0004) [2023-03-11 11:15:47,811][04011] Fps is (10 sec: 12697.6, 60 sec: 12561.1, 300 sec: 12704.5). Total num frames: 31277056. Throughput: 0: 12268.1. Samples: 31247552. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:15:47,822][04011] Avg episode reward: [(0, '30.862')] [2023-03-11 11:15:49,027][04298] Updated weights for policy 0, policy_version 61120 (0.0004) [2023-03-11 11:15:52,220][04298] Updated weights for policy 0, policy_version 61200 (0.0004) [2023-03-11 11:15:52,811][04011] Fps is (10 sec: 13107.1, 60 sec: 12492.8, 300 sec: 12718.4). Total num frames: 31338496. Throughput: 0: 12246.8. Samples: 31326284. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:15:52,822][04011] Avg episode reward: [(0, '30.866')] [2023-03-11 11:15:52,870][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000061216_31342592.pth... [2023-03-11 11:15:52,871][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000060488_30969856.pth [2023-03-11 11:15:55,340][04298] Updated weights for policy 0, policy_version 61280 (0.0004) [2023-03-11 11:15:57,811][04011] Fps is (10 sec: 13107.2, 60 sec: 12492.8, 300 sec: 12760.1). Total num frames: 31408128. Throughput: 0: 12328.3. Samples: 31404816. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:15:57,822][04011] Avg episode reward: [(0, '31.530')] [2023-03-11 11:15:58,437][04298] Updated weights for policy 0, policy_version 61360 (0.0004) [2023-03-11 11:16:01,616][04298] Updated weights for policy 0, policy_version 61440 (0.0003) [2023-03-11 11:16:02,811][04011] Fps is (10 sec: 13107.3, 60 sec: 12424.5, 300 sec: 12760.1). Total num frames: 31469568. Throughput: 0: 12415.7. Samples: 31443736. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:16:02,822][04011] Avg episode reward: [(0, '31.396')] [2023-03-11 11:16:04,693][04298] Updated weights for policy 0, policy_version 61520 (0.0003) [2023-03-11 11:16:07,786][04298] Updated weights for policy 0, policy_version 61600 (0.0003) [2023-03-11 11:16:07,811][04011] Fps is (10 sec: 13107.2, 60 sec: 12492.8, 300 sec: 12801.7). Total num frames: 31539200. Throughput: 0: 12565.2. Samples: 31522880. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:16:07,812][04011] Avg episode reward: [(0, '31.116')] [2023-03-11 11:16:07,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000061600_31539200.pth... [2023-03-11 11:16:07,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000060840_31150080.pth [2023-03-11 11:16:10,962][04298] Updated weights for policy 0, policy_version 61680 (0.0003) [2023-03-11 11:16:12,811][04011] Fps is (10 sec: 13107.2, 60 sec: 12492.8, 300 sec: 12815.6). Total num frames: 31600640. Throughput: 0: 12731.0. Samples: 31600640. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:16:12,822][04011] Avg episode reward: [(0, '30.612')] [2023-03-11 11:16:14,196][04298] Updated weights for policy 0, policy_version 61760 (0.0003) [2023-03-11 11:16:17,601][04298] Updated weights for policy 0, policy_version 61840 (0.0005) [2023-03-11 11:16:17,811][04011] Fps is (10 sec: 12288.1, 60 sec: 12561.1, 300 sec: 12815.6). Total num frames: 31662080. Throughput: 0: 12758.9. Samples: 31637568. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:16:17,822][04011] Avg episode reward: [(0, '30.581')] [2023-03-11 11:16:20,989][04298] Updated weights for policy 0, policy_version 61920 (0.0005) [2023-03-11 11:16:22,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12561.1, 300 sec: 12815.6). Total num frames: 31723520. Throughput: 0: 12774.1. Samples: 31710200. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:16:22,822][04011] Avg episode reward: [(0, '31.338')] [2023-03-11 11:16:22,825][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000061960_31723520.pth... [2023-03-11 11:16:22,828][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000061216_31342592.pth [2023-03-11 11:16:24,380][04298] Updated weights for policy 0, policy_version 62000 (0.0005) [2023-03-11 11:16:27,686][04298] Updated weights for policy 0, policy_version 62080 (0.0004) [2023-03-11 11:16:27,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12629.3, 300 sec: 12815.6). Total num frames: 31784960. Throughput: 0: 12790.9. Samples: 31783080. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:16:27,822][04011] Avg episode reward: [(0, '31.964')] [2023-03-11 11:16:30,802][04298] Updated weights for policy 0, policy_version 62160 (0.0003) [2023-03-11 11:16:32,811][04011] Fps is (10 sec: 12697.6, 60 sec: 12697.6, 300 sec: 12829.5). Total num frames: 31850496. Throughput: 0: 12768.1. Samples: 31822116. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:16:32,822][04011] Avg episode reward: [(0, '32.045')] [2023-03-11 11:16:34,022][04298] Updated weights for policy 0, policy_version 62240 (0.0003) [2023-03-11 11:16:37,209][04298] Updated weights for policy 0, policy_version 62320 (0.0004) [2023-03-11 11:16:37,811][04011] Fps is (10 sec: 12697.6, 60 sec: 12697.6, 300 sec: 12843.4). Total num frames: 31911936. Throughput: 0: 12742.9. Samples: 31899712. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:16:37,822][04011] Avg episode reward: [(0, '31.732')] [2023-03-11 11:16:37,825][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000062328_31911936.pth... [2023-03-11 11:16:37,828][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000061600_31539200.pth [2023-03-11 11:16:40,369][04298] Updated weights for policy 0, policy_version 62400 (0.0004) [2023-03-11 11:16:42,811][04011] Fps is (10 sec: 12697.5, 60 sec: 12834.1, 300 sec: 12857.3). Total num frames: 31977472. Throughput: 0: 12727.3. Samples: 31977544. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:16:42,812][04011] Avg episode reward: [(0, '28.031')] [2023-03-11 11:16:43,445][04298] Updated weights for policy 0, policy_version 62480 (0.0003) [2023-03-11 11:16:46,484][04298] Updated weights for policy 0, policy_version 62560 (0.0003) [2023-03-11 11:16:47,811][04011] Fps is (10 sec: 13516.8, 60 sec: 12834.1, 300 sec: 12885.1). Total num frames: 32047104. Throughput: 0: 12767.8. Samples: 32018288. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:16:47,811][04011] Avg episode reward: [(0, '29.950')] [2023-03-11 11:16:49,580][04298] Updated weights for policy 0, policy_version 62640 (0.0003) [2023-03-11 11:16:52,811][04011] Fps is (10 sec: 13107.1, 60 sec: 12834.1, 300 sec: 12898.9). Total num frames: 32108544. Throughput: 0: 12743.1. Samples: 32096320. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:16:52,812][04011] Avg episode reward: [(0, '31.663')] [2023-03-11 11:16:52,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000062712_32108544.pth... [2023-03-11 11:16:52,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000061960_31723520.pth [2023-03-11 11:16:52,886][04298] Updated weights for policy 0, policy_version 62720 (0.0004) [2023-03-11 11:16:56,258][04298] Updated weights for policy 0, policy_version 62800 (0.0004) [2023-03-11 11:16:57,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12697.6, 300 sec: 12898.9). Total num frames: 32169984. Throughput: 0: 12647.0. Samples: 32169756. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:16:57,812][04011] Avg episode reward: [(0, '28.859')] [2023-03-11 11:16:59,541][04298] Updated weights for policy 0, policy_version 62880 (0.0005) [2023-03-11 11:17:02,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12697.6, 300 sec: 12898.9). Total num frames: 32231424. Throughput: 0: 12652.1. Samples: 32206912. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:17:02,812][04011] Avg episode reward: [(0, '32.058')] [2023-03-11 11:17:02,997][04298] Updated weights for policy 0, policy_version 62960 (0.0005) [2023-03-11 11:17:06,297][04298] Updated weights for policy 0, policy_version 63040 (0.0005) [2023-03-11 11:17:07,811][04011] Fps is (10 sec: 12287.9, 60 sec: 12561.1, 300 sec: 12898.9). Total num frames: 32292864. Throughput: 0: 12662.4. Samples: 32280008. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:17:07,812][04011] Avg episode reward: [(0, '31.793')] [2023-03-11 11:17:07,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000063072_32292864.pth... [2023-03-11 11:17:07,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000062328_31911936.pth [2023-03-11 11:17:09,710][04298] Updated weights for policy 0, policy_version 63120 (0.0005) [2023-03-11 11:17:12,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12561.1, 300 sec: 12885.0). Total num frames: 32354304. Throughput: 0: 12632.2. Samples: 32351528. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:17:12,812][04011] Avg episode reward: [(0, '31.747')] [2023-03-11 11:17:13,104][04298] Updated weights for policy 0, policy_version 63200 (0.0005) [2023-03-11 11:17:16,412][04298] Updated weights for policy 0, policy_version 63280 (0.0005) [2023-03-11 11:17:17,811][04011] Fps is (10 sec: 12288.1, 60 sec: 12561.1, 300 sec: 12885.0). Total num frames: 32415744. Throughput: 0: 12612.5. Samples: 32389680. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:17:17,822][04011] Avg episode reward: [(0, '31.584')] [2023-03-11 11:17:19,787][04298] Updated weights for policy 0, policy_version 63360 (0.0005) [2023-03-11 11:17:22,811][04011] Fps is (10 sec: 11878.3, 60 sec: 12492.8, 300 sec: 12857.3). Total num frames: 32473088. Throughput: 0: 12476.7. Samples: 32461164. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:17:22,822][04011] Avg episode reward: [(0, '31.612')] [2023-03-11 11:17:22,825][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000063432_32477184.pth... [2023-03-11 11:17:22,827][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000062712_32108544.pth [2023-03-11 11:17:23,192][04298] Updated weights for policy 0, policy_version 63440 (0.0005) [2023-03-11 11:17:26,628][04298] Updated weights for policy 0, policy_version 63520 (0.0005) [2023-03-11 11:17:27,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12492.8, 300 sec: 12857.3). Total num frames: 32534528. Throughput: 0: 12352.7. Samples: 32533416. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:17:27,822][04011] Avg episode reward: [(0, '30.486')] [2023-03-11 11:17:30,076][04298] Updated weights for policy 0, policy_version 63600 (0.0005) [2023-03-11 11:17:32,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12424.5, 300 sec: 12829.5). Total num frames: 32595968. Throughput: 0: 12227.5. Samples: 32568524. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:17:32,822][04011] Avg episode reward: [(0, '30.501')] [2023-03-11 11:17:33,302][04298] Updated weights for policy 0, policy_version 63680 (0.0004) [2023-03-11 11:17:36,440][04298] Updated weights for policy 0, policy_version 63760 (0.0003) [2023-03-11 11:17:37,811][04011] Fps is (10 sec: 12697.5, 60 sec: 12492.8, 300 sec: 12843.4). Total num frames: 32661504. Throughput: 0: 12226.0. Samples: 32646488. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:17:37,822][04011] Avg episode reward: [(0, '31.381')] [2023-03-11 11:17:37,825][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000063792_32661504.pth... [2023-03-11 11:17:37,827][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000063072_32292864.pth [2023-03-11 11:17:39,514][04298] Updated weights for policy 0, policy_version 63840 (0.0003) [2023-03-11 11:17:42,718][04298] Updated weights for policy 0, policy_version 63920 (0.0003) [2023-03-11 11:17:42,811][04011] Fps is (10 sec: 13107.2, 60 sec: 12492.8, 300 sec: 12843.4). Total num frames: 32727040. Throughput: 0: 12335.2. Samples: 32724840. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:17:42,822][04011] Avg episode reward: [(0, '30.997')] [2023-03-11 11:17:45,866][04298] Updated weights for policy 0, policy_version 64000 (0.0003) [2023-03-11 11:17:47,811][04011] Fps is (10 sec: 12697.6, 60 sec: 12356.3, 300 sec: 12815.6). Total num frames: 32788480. Throughput: 0: 12379.0. Samples: 32763968. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:17:47,822][04011] Avg episode reward: [(0, '30.064')] [2023-03-11 11:17:49,070][04298] Updated weights for policy 0, policy_version 64080 (0.0003) [2023-03-11 11:17:52,258][04298] Updated weights for policy 0, policy_version 64160 (0.0003) [2023-03-11 11:17:52,811][04011] Fps is (10 sec: 12697.5, 60 sec: 12424.5, 300 sec: 12815.6). Total num frames: 32854016. Throughput: 0: 12464.8. Samples: 32840924. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:17:52,822][04011] Avg episode reward: [(0, '29.607')] [2023-03-11 11:17:52,825][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000064168_32854016.pth... [2023-03-11 11:17:52,828][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000063432_32477184.pth [2023-03-11 11:17:55,385][04298] Updated weights for policy 0, policy_version 64240 (0.0003) [2023-03-11 11:17:57,811][04011] Fps is (10 sec: 13107.3, 60 sec: 12492.8, 300 sec: 12815.6). Total num frames: 32919552. Throughput: 0: 12624.2. Samples: 32919616. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:17:57,811][04011] Avg episode reward: [(0, '31.275')] [2023-03-11 11:17:58,605][04298] Updated weights for policy 0, policy_version 64320 (0.0004) [2023-03-11 11:18:02,002][04298] Updated weights for policy 0, policy_version 64400 (0.0005) [2023-03-11 11:18:02,811][04011] Fps is (10 sec: 12697.7, 60 sec: 12492.8, 300 sec: 12801.7). Total num frames: 32980992. Throughput: 0: 12583.3. Samples: 32955928. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:18:02,811][04011] Avg episode reward: [(0, '30.050')] [2023-03-11 11:18:05,410][04298] Updated weights for policy 0, policy_version 64480 (0.0005) [2023-03-11 11:18:07,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12424.6, 300 sec: 12774.0). Total num frames: 33038336. Throughput: 0: 12573.5. Samples: 33026972. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:18:07,811][04011] Avg episode reward: [(0, '31.126')] [2023-03-11 11:18:07,814][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000064528_33038336.pth... [2023-03-11 11:18:07,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000063792_32661504.pth [2023-03-11 11:18:08,925][04298] Updated weights for policy 0, policy_version 64560 (0.0005) [2023-03-11 11:18:12,428][04298] Updated weights for policy 0, policy_version 64640 (0.0005) [2023-03-11 11:18:12,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12424.5, 300 sec: 12760.1). Total num frames: 33099776. Throughput: 0: 12529.2. Samples: 33097228. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:18:12,811][04011] Avg episode reward: [(0, '29.839')] [2023-03-11 11:18:15,812][04298] Updated weights for policy 0, policy_version 64720 (0.0005) [2023-03-11 11:18:17,811][04011] Fps is (10 sec: 11878.3, 60 sec: 12356.3, 300 sec: 12718.4). Total num frames: 33157120. Throughput: 0: 12546.0. Samples: 33133096. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:18:17,811][04011] Avg episode reward: [(0, '32.084')] [2023-03-11 11:18:19,228][04298] Updated weights for policy 0, policy_version 64800 (0.0005) [2023-03-11 11:18:22,536][04298] Updated weights for policy 0, policy_version 64880 (0.0004) [2023-03-11 11:18:22,811][04011] Fps is (10 sec: 11878.3, 60 sec: 12424.5, 300 sec: 12718.4). Total num frames: 33218560. Throughput: 0: 12441.1. Samples: 33206336. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:18:22,812][04011] Avg episode reward: [(0, '28.265')] [2023-03-11 11:18:22,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000064880_33218560.pth... [2023-03-11 11:18:22,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000064168_32854016.pth [2023-03-11 11:18:26,042][04298] Updated weights for policy 0, policy_version 64960 (0.0005) [2023-03-11 11:18:27,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12424.5, 300 sec: 12704.5). Total num frames: 33280000. Throughput: 0: 12308.5. Samples: 33278724. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:18:27,811][04011] Avg episode reward: [(0, '31.239')] [2023-03-11 11:18:29,205][04298] Updated weights for policy 0, policy_version 65040 (0.0005) [2023-03-11 11:18:32,331][04298] Updated weights for policy 0, policy_version 65120 (0.0004) [2023-03-11 11:18:32,811][04011] Fps is (10 sec: 12697.7, 60 sec: 12492.8, 300 sec: 12704.5). Total num frames: 33345536. Throughput: 0: 12305.2. Samples: 33317700. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:18:32,811][04011] Avg episode reward: [(0, '31.000')] [2023-03-11 11:18:35,401][04298] Updated weights for policy 0, policy_version 65200 (0.0004) [2023-03-11 11:18:37,811][04011] Fps is (10 sec: 12697.6, 60 sec: 12424.6, 300 sec: 12690.7). Total num frames: 33406976. Throughput: 0: 12327.2. Samples: 33395648. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:18:37,811][04011] Avg episode reward: [(0, '31.457')] [2023-03-11 11:18:37,821][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000065256_33411072.pth... [2023-03-11 11:18:37,823][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000064528_33038336.pth [2023-03-11 11:18:38,892][04298] Updated weights for policy 0, policy_version 65280 (0.0005) [2023-03-11 11:18:42,301][04298] Updated weights for policy 0, policy_version 65360 (0.0005) [2023-03-11 11:18:42,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12356.3, 300 sec: 12676.8). Total num frames: 33468416. Throughput: 0: 12184.2. Samples: 33467904. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:18:42,811][04011] Avg episode reward: [(0, '30.821')] [2023-03-11 11:18:45,807][04298] Updated weights for policy 0, policy_version 65440 (0.0005) [2023-03-11 11:18:47,811][04011] Fps is (10 sec: 11878.3, 60 sec: 12288.0, 300 sec: 12649.0). Total num frames: 33525760. Throughput: 0: 12135.4. Samples: 33502020. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:18:47,811][04011] Avg episode reward: [(0, '30.529')] [2023-03-11 11:18:49,284][04298] Updated weights for policy 0, policy_version 65520 (0.0005) [2023-03-11 11:18:52,673][04298] Updated weights for policy 0, policy_version 65600 (0.0005) [2023-03-11 11:18:52,811][04011] Fps is (10 sec: 11878.3, 60 sec: 12219.7, 300 sec: 12621.2). Total num frames: 33587200. Throughput: 0: 12169.7. Samples: 33574608. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:18:52,812][04011] Avg episode reward: [(0, '31.154')] [2023-03-11 11:18:52,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000065600_33587200.pth... [2023-03-11 11:18:52,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000064880_33218560.pth [2023-03-11 11:18:55,941][04298] Updated weights for policy 0, policy_version 65680 (0.0004) [2023-03-11 11:18:57,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12151.5, 300 sec: 12607.3). Total num frames: 33648640. Throughput: 0: 12253.8. Samples: 33648648. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:18:57,811][04011] Avg episode reward: [(0, '31.337')] [2023-03-11 11:18:59,267][04298] Updated weights for policy 0, policy_version 65760 (0.0005) [2023-03-11 11:19:02,559][04298] Updated weights for policy 0, policy_version 65840 (0.0004) [2023-03-11 11:19:02,811][04011] Fps is (10 sec: 12288.1, 60 sec: 12151.5, 300 sec: 12593.5). Total num frames: 33710080. Throughput: 0: 12260.3. Samples: 33684808. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:19:02,811][04011] Avg episode reward: [(0, '30.686')] [2023-03-11 11:19:05,616][04298] Updated weights for policy 0, policy_version 65920 (0.0003) [2023-03-11 11:19:07,811][04011] Fps is (10 sec: 13107.2, 60 sec: 12356.3, 300 sec: 12607.3). Total num frames: 33779712. Throughput: 0: 12379.0. Samples: 33763392. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:19:07,811][04011] Avg episode reward: [(0, '30.694')] [2023-03-11 11:19:07,814][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000065976_33779712.pth... [2023-03-11 11:19:07,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000065256_33411072.pth [2023-03-11 11:19:08,665][04298] Updated weights for policy 0, policy_version 66000 (0.0003) [2023-03-11 11:19:11,864][04298] Updated weights for policy 0, policy_version 66080 (0.0003) [2023-03-11 11:19:12,811][04011] Fps is (10 sec: 13107.2, 60 sec: 12356.3, 300 sec: 12579.6). Total num frames: 33841152. Throughput: 0: 12500.0. Samples: 33841224. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:19:12,811][04011] Avg episode reward: [(0, '30.198')] [2023-03-11 11:19:15,000][04298] Updated weights for policy 0, policy_version 66160 (0.0003) [2023-03-11 11:19:17,811][04011] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12593.5). Total num frames: 33910784. Throughput: 0: 12531.0. Samples: 33881596. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:19:17,822][04011] Avg episode reward: [(0, '31.023')] [2023-03-11 11:19:18,023][04298] Updated weights for policy 0, policy_version 66240 (0.0003) [2023-03-11 11:19:21,063][04298] Updated weights for policy 0, policy_version 66320 (0.0003) [2023-03-11 11:19:22,811][04011] Fps is (10 sec: 13516.7, 60 sec: 12629.3, 300 sec: 12593.5). Total num frames: 33976320. Throughput: 0: 12600.4. Samples: 33962668. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:19:22,822][04011] Avg episode reward: [(0, '31.601')] [2023-03-11 11:19:22,826][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000066360_33976320.pth... [2023-03-11 11:19:22,828][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000065600_33587200.pth [2023-03-11 11:19:24,194][04298] Updated weights for policy 0, policy_version 66400 (0.0003) [2023-03-11 11:19:27,245][04298] Updated weights for policy 0, policy_version 66480 (0.0004) [2023-03-11 11:19:27,811][04011] Fps is (10 sec: 13107.2, 60 sec: 12697.6, 300 sec: 12593.5). Total num frames: 34041856. Throughput: 0: 12755.9. Samples: 34041920. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:19:27,822][04011] Avg episode reward: [(0, '31.412')] [2023-03-11 11:19:30,517][04298] Updated weights for policy 0, policy_version 66560 (0.0005) [2023-03-11 11:19:32,811][04011] Fps is (10 sec: 12697.6, 60 sec: 12629.3, 300 sec: 12579.6). Total num frames: 34103296. Throughput: 0: 12817.2. Samples: 34078792. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:19:32,811][04011] Avg episode reward: [(0, '22.297')] [2023-03-11 11:19:34,085][04298] Updated weights for policy 0, policy_version 66640 (0.0005) [2023-03-11 11:19:37,581][04298] Updated weights for policy 0, policy_version 66720 (0.0005) [2023-03-11 11:19:37,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12561.0, 300 sec: 12551.8). Total num frames: 34160640. Throughput: 0: 12751.3. Samples: 34148416. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:19:37,822][04011] Avg episode reward: [(0, '10.809')] [2023-03-11 11:19:37,825][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000066720_34160640.pth... [2023-03-11 11:19:37,827][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000065976_33779712.pth [2023-03-11 11:19:40,896][04298] Updated weights for policy 0, policy_version 66800 (0.0004) [2023-03-11 11:19:42,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12629.3, 300 sec: 12551.8). Total num frames: 34226176. Throughput: 0: 12769.7. Samples: 34223284. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:19:42,822][04011] Avg episode reward: [(0, '31.288')] [2023-03-11 11:19:43,983][04298] Updated weights for policy 0, policy_version 66880 (0.0004) [2023-03-11 11:19:47,080][04298] Updated weights for policy 0, policy_version 66960 (0.0004) [2023-03-11 11:19:47,811][04011] Fps is (10 sec: 13107.2, 60 sec: 12765.9, 300 sec: 12551.8). Total num frames: 34291712. Throughput: 0: 12851.0. Samples: 34263104. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:19:47,812][04011] Avg episode reward: [(0, '30.440')] [2023-03-11 11:19:50,210][04298] Updated weights for policy 0, policy_version 67040 (0.0005) [2023-03-11 11:19:52,811][04011] Fps is (10 sec: 12697.6, 60 sec: 12765.9, 300 sec: 12524.0). Total num frames: 34353152. Throughput: 0: 12832.9. Samples: 34340872. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:19:52,822][04011] Avg episode reward: [(0, '31.953')] [2023-03-11 11:19:52,826][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000067096_34353152.pth... [2023-03-11 11:19:52,829][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000066360_33976320.pth [2023-03-11 11:19:53,681][04298] Updated weights for policy 0, policy_version 67120 (0.0005) [2023-03-11 11:19:57,149][04298] Updated weights for policy 0, policy_version 67200 (0.0005) [2023-03-11 11:19:57,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12697.6, 300 sec: 12496.3). Total num frames: 34410496. Throughput: 0: 12655.9. Samples: 34410740. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:19:57,812][04011] Avg episode reward: [(0, '31.715')] [2023-03-11 11:20:00,551][04298] Updated weights for policy 0, policy_version 67280 (0.0005) [2023-03-11 11:20:02,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12697.6, 300 sec: 12482.4). Total num frames: 34471936. Throughput: 0: 12573.9. Samples: 34447424. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:20:02,811][04011] Avg episode reward: [(0, '30.163')] [2023-03-11 11:20:03,876][04298] Updated weights for policy 0, policy_version 67360 (0.0005) [2023-03-11 11:20:07,052][04298] Updated weights for policy 0, policy_version 67440 (0.0004) [2023-03-11 11:20:07,811][04011] Fps is (10 sec: 12697.6, 60 sec: 12629.3, 300 sec: 12496.3). Total num frames: 34537472. Throughput: 0: 12468.4. Samples: 34523748. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:20:07,812][04011] Avg episode reward: [(0, '28.821')] [2023-03-11 11:20:07,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000067456_34537472.pth... [2023-03-11 11:20:07,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000066720_34160640.pth [2023-03-11 11:20:10,469][04298] Updated weights for policy 0, policy_version 67520 (0.0005) [2023-03-11 11:20:12,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12561.1, 300 sec: 12496.3). Total num frames: 34594816. Throughput: 0: 12286.8. Samples: 34594824. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:20:12,812][04011] Avg episode reward: [(0, '31.200')] [2023-03-11 11:20:13,797][04298] Updated weights for policy 0, policy_version 67600 (0.0004) [2023-03-11 11:20:17,156][04298] Updated weights for policy 0, policy_version 67680 (0.0005) [2023-03-11 11:20:17,811][04011] Fps is (10 sec: 11878.5, 60 sec: 12424.5, 300 sec: 12496.3). Total num frames: 34656256. Throughput: 0: 12318.8. Samples: 34633136. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:20:17,811][04011] Avg episode reward: [(0, '32.535')] [2023-03-11 11:20:20,591][04298] Updated weights for policy 0, policy_version 67760 (0.0005) [2023-03-11 11:20:22,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12356.3, 300 sec: 12510.2). Total num frames: 34717696. Throughput: 0: 12367.5. Samples: 34704952. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:20:22,812][04011] Avg episode reward: [(0, '27.644')] [2023-03-11 11:20:22,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000067808_34717696.pth... [2023-03-11 11:20:22,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000067096_34353152.pth [2023-03-11 11:20:24,032][04298] Updated weights for policy 0, policy_version 67840 (0.0005) [2023-03-11 11:20:27,348][04298] Updated weights for policy 0, policy_version 67920 (0.0005) [2023-03-11 11:20:27,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12288.0, 300 sec: 12510.2). Total num frames: 34779136. Throughput: 0: 12320.1. Samples: 34777688. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:20:27,811][04011] Avg episode reward: [(0, '31.377')] [2023-03-11 11:20:30,748][04298] Updated weights for policy 0, policy_version 68000 (0.0005) [2023-03-11 11:20:32,811][04011] Fps is (10 sec: 11878.5, 60 sec: 12219.7, 300 sec: 12496.3). Total num frames: 34836480. Throughput: 0: 12232.8. Samples: 34813580. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:20:32,811][04011] Avg episode reward: [(0, '30.944')] [2023-03-11 11:20:34,272][04298] Updated weights for policy 0, policy_version 68080 (0.0005) [2023-03-11 11:20:37,669][04298] Updated weights for policy 0, policy_version 68160 (0.0005) [2023-03-11 11:20:37,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12288.0, 300 sec: 12510.2). Total num frames: 34897920. Throughput: 0: 12091.9. Samples: 34885008. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:20:37,811][04011] Avg episode reward: [(0, '30.972')] [2023-03-11 11:20:37,814][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000068160_34897920.pth... [2023-03-11 11:20:37,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000067456_34537472.pth [2023-03-11 11:20:41,049][04298] Updated weights for policy 0, policy_version 68240 (0.0005) [2023-03-11 11:20:42,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12219.7, 300 sec: 12482.4). Total num frames: 34959360. Throughput: 0: 12130.1. Samples: 34956592. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:20:42,811][04011] Avg episode reward: [(0, '31.235')] [2023-03-11 11:20:44,355][04298] Updated weights for policy 0, policy_version 68320 (0.0004) [2023-03-11 11:20:47,531][04298] Updated weights for policy 0, policy_version 68400 (0.0004) [2023-03-11 11:20:47,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12151.5, 300 sec: 12482.4). Total num frames: 35020800. Throughput: 0: 12189.7. Samples: 34995960. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:20:47,822][04011] Avg episode reward: [(0, '29.590')] [2023-03-11 11:20:50,859][04298] Updated weights for policy 0, policy_version 68480 (0.0005) [2023-03-11 11:20:52,811][04011] Fps is (10 sec: 12287.9, 60 sec: 12151.5, 300 sec: 12454.6). Total num frames: 35082240. Throughput: 0: 12138.0. Samples: 35069960. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:20:52,822][04011] Avg episode reward: [(0, '30.376')] [2023-03-11 11:20:52,826][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000068520_35082240.pth... [2023-03-11 11:20:52,829][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000067808_34717696.pth [2023-03-11 11:20:54,317][04298] Updated weights for policy 0, policy_version 68560 (0.0005) [2023-03-11 11:20:57,811][04011] Fps is (10 sec: 11878.3, 60 sec: 12151.5, 300 sec: 12440.7). Total num frames: 35139584. Throughput: 0: 12120.4. Samples: 35140244. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:20:57,822][04011] Avg episode reward: [(0, '31.835')] [2023-03-11 11:20:57,836][04298] Updated weights for policy 0, policy_version 68640 (0.0005) [2023-03-11 11:21:01,299][04298] Updated weights for policy 0, policy_version 68720 (0.0005) [2023-03-11 11:21:02,811][04011] Fps is (10 sec: 11878.5, 60 sec: 12151.5, 300 sec: 12413.0). Total num frames: 35201024. Throughput: 0: 12057.0. Samples: 35175700. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:21:02,822][04011] Avg episode reward: [(0, '29.642')] [2023-03-11 11:21:04,764][04298] Updated weights for policy 0, policy_version 68800 (0.0005) [2023-03-11 11:21:07,811][04011] Fps is (10 sec: 11878.3, 60 sec: 12014.9, 300 sec: 12399.1). Total num frames: 35258368. Throughput: 0: 12026.8. Samples: 35246160. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:21:07,822][04011] Avg episode reward: [(0, '24.231')] [2023-03-11 11:21:07,841][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000068872_35262464.pth... [2023-03-11 11:21:07,843][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000068160_34897920.pth [2023-03-11 11:21:08,196][04298] Updated weights for policy 0, policy_version 68880 (0.0005) [2023-03-11 11:21:11,597][04298] Updated weights for policy 0, policy_version 68960 (0.0005) [2023-03-11 11:21:12,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12083.2, 300 sec: 12399.1). Total num frames: 35319808. Throughput: 0: 12037.9. Samples: 35319396. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:21:12,822][04011] Avg episode reward: [(0, '6.983')] [2023-03-11 11:21:15,041][04298] Updated weights for policy 0, policy_version 69040 (0.0005) [2023-03-11 11:21:17,811][04011] Fps is (10 sec: 11878.6, 60 sec: 12014.9, 300 sec: 12385.2). Total num frames: 35377152. Throughput: 0: 12020.3. Samples: 35354496. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:21:17,822][04011] Avg episode reward: [(0, '25.733')] [2023-03-11 11:21:18,544][04298] Updated weights for policy 0, policy_version 69120 (0.0005) [2023-03-11 11:21:22,013][04298] Updated weights for policy 0, policy_version 69200 (0.0005) [2023-03-11 11:21:22,811][04011] Fps is (10 sec: 11878.3, 60 sec: 12014.9, 300 sec: 12385.2). Total num frames: 35438592. Throughput: 0: 12002.8. Samples: 35425136. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-11 11:21:22,822][04011] Avg episode reward: [(0, '22.215')] [2023-03-11 11:21:22,825][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000069216_35438592.pth... [2023-03-11 11:21:22,828][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000068520_35082240.pth [2023-03-11 11:21:25,520][04298] Updated weights for policy 0, policy_version 69280 (0.0005) [2023-03-11 11:21:27,811][04011] Fps is (10 sec: 11878.4, 60 sec: 11946.7, 300 sec: 12357.4). Total num frames: 35495936. Throughput: 0: 11985.7. Samples: 35495948. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-11 11:21:27,811][04011] Avg episode reward: [(0, '28.402')] [2023-03-11 11:21:28,945][04298] Updated weights for policy 0, policy_version 69360 (0.0005) [2023-03-11 11:21:32,316][04298] Updated weights for policy 0, policy_version 69440 (0.0005) [2023-03-11 11:21:32,811][04011] Fps is (10 sec: 11878.5, 60 sec: 12014.9, 300 sec: 12357.4). Total num frames: 35557376. Throughput: 0: 11910.4. Samples: 35531928. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-11 11:21:32,811][04011] Avg episode reward: [(0, '28.360')] [2023-03-11 11:21:35,736][04298] Updated weights for policy 0, policy_version 69520 (0.0005) [2023-03-11 11:21:37,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12014.9, 300 sec: 12343.5). Total num frames: 35618816. Throughput: 0: 11861.6. Samples: 35603732. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-11 11:21:37,811][04011] Avg episode reward: [(0, '30.562')] [2023-03-11 11:21:37,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000069568_35618816.pth... [2023-03-11 11:21:37,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000068872_35262464.pth [2023-03-11 11:21:39,102][04298] Updated weights for policy 0, policy_version 69600 (0.0005) [2023-03-11 11:21:42,591][04298] Updated weights for policy 0, policy_version 69680 (0.0005) [2023-03-11 11:21:42,811][04011] Fps is (10 sec: 11878.3, 60 sec: 11946.7, 300 sec: 12301.9). Total num frames: 35676160. Throughput: 0: 11908.9. Samples: 35676144. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-11 11:21:42,812][04011] Avg episode reward: [(0, '30.814')] [2023-03-11 11:21:46,060][04298] Updated weights for policy 0, policy_version 69760 (0.0005) [2023-03-11 11:21:47,811][04011] Fps is (10 sec: 11878.4, 60 sec: 11946.7, 300 sec: 12301.9). Total num frames: 35737600. Throughput: 0: 11901.1. Samples: 35711248. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-11 11:21:47,812][04011] Avg episode reward: [(0, '31.946')] [2023-03-11 11:21:49,531][04298] Updated weights for policy 0, policy_version 69840 (0.0005) [2023-03-11 11:21:52,811][04011] Fps is (10 sec: 11878.4, 60 sec: 11878.4, 300 sec: 12288.0). Total num frames: 35794944. Throughput: 0: 11908.3. Samples: 35782032. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-11 11:21:52,812][04011] Avg episode reward: [(0, '30.956')] [2023-03-11 11:21:52,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000069912_35794944.pth... [2023-03-11 11:21:52,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000069216_35438592.pth [2023-03-11 11:21:52,984][04298] Updated weights for policy 0, policy_version 69920 (0.0005) [2023-03-11 11:21:56,442][04298] Updated weights for policy 0, policy_version 70000 (0.0005) [2023-03-11 11:21:57,811][04011] Fps is (10 sec: 11878.5, 60 sec: 11946.7, 300 sec: 12288.0). Total num frames: 35856384. Throughput: 0: 11868.1. Samples: 35853460. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-11 11:21:57,811][04011] Avg episode reward: [(0, '30.229')] [2023-03-11 11:21:59,860][04298] Updated weights for policy 0, policy_version 70080 (0.0005) [2023-03-11 11:22:02,811][04011] Fps is (10 sec: 11878.5, 60 sec: 11878.4, 300 sec: 12274.1). Total num frames: 35913728. Throughput: 0: 11882.7. Samples: 35889216. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-11 11:22:02,811][04011] Avg episode reward: [(0, '31.872')] [2023-03-11 11:22:03,281][04298] Updated weights for policy 0, policy_version 70160 (0.0005) [2023-03-11 11:22:06,620][04298] Updated weights for policy 0, policy_version 70240 (0.0005) [2023-03-11 11:22:07,811][04011] Fps is (10 sec: 11878.3, 60 sec: 11946.7, 300 sec: 12274.1). Total num frames: 35975168. Throughput: 0: 11939.1. Samples: 35962396. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-11 11:22:07,811][04011] Avg episode reward: [(0, '30.897')] [2023-03-11 11:22:07,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000070264_35975168.pth... [2023-03-11 11:22:07,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000069568_35618816.pth [2023-03-11 11:22:10,043][04298] Updated weights for policy 0, policy_version 70320 (0.0005) [2023-03-11 11:22:12,811][04011] Fps is (10 sec: 12287.9, 60 sec: 11946.7, 300 sec: 12274.1). Total num frames: 36036608. Throughput: 0: 11972.3. Samples: 36034704. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-11 11:22:12,811][04011] Avg episode reward: [(0, '29.707')] [2023-03-11 11:22:13,367][04298] Updated weights for policy 0, policy_version 70400 (0.0005) [2023-03-11 11:22:16,726][04298] Updated weights for policy 0, policy_version 70480 (0.0005) [2023-03-11 11:22:17,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12014.9, 300 sec: 12288.0). Total num frames: 36098048. Throughput: 0: 11982.0. Samples: 36071120. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-11 11:22:17,812][04011] Avg episode reward: [(0, '32.006')] [2023-03-11 11:22:20,054][04298] Updated weights for policy 0, policy_version 70560 (0.0004) [2023-03-11 11:22:22,811][04011] Fps is (10 sec: 12288.1, 60 sec: 12014.9, 300 sec: 12288.0). Total num frames: 36159488. Throughput: 0: 12015.4. Samples: 36144424. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-11 11:22:22,811][04011] Avg episode reward: [(0, '32.020')] [2023-03-11 11:22:22,814][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000070624_36159488.pth... [2023-03-11 11:22:22,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000069912_35794944.pth [2023-03-11 11:22:23,421][04298] Updated weights for policy 0, policy_version 70640 (0.0005) [2023-03-11 11:22:26,864][04298] Updated weights for policy 0, policy_version 70720 (0.0005) [2023-03-11 11:22:27,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12014.9, 300 sec: 12274.1). Total num frames: 36216832. Throughput: 0: 12016.7. Samples: 36216896. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-11 11:22:27,812][04011] Avg episode reward: [(0, '30.330')] [2023-03-11 11:22:30,319][04298] Updated weights for policy 0, policy_version 70800 (0.0005) [2023-03-11 11:22:32,811][04011] Fps is (10 sec: 11878.3, 60 sec: 12014.9, 300 sec: 12260.2). Total num frames: 36278272. Throughput: 0: 12033.6. Samples: 36252760. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-11 11:22:32,811][04011] Avg episode reward: [(0, '31.715')] [2023-03-11 11:22:33,668][04298] Updated weights for policy 0, policy_version 70880 (0.0005) [2023-03-11 11:22:37,208][04298] Updated weights for policy 0, policy_version 70960 (0.0006) [2023-03-11 11:22:37,811][04011] Fps is (10 sec: 11878.4, 60 sec: 11946.7, 300 sec: 12232.5). Total num frames: 36335616. Throughput: 0: 12040.0. Samples: 36323832. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-11 11:22:37,811][04011] Avg episode reward: [(0, '31.482')] [2023-03-11 11:22:37,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000070968_36335616.pth... [2023-03-11 11:22:37,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000070264_35975168.pth [2023-03-11 11:22:40,495][04298] Updated weights for policy 0, policy_version 71040 (0.0005) [2023-03-11 11:22:42,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12083.2, 300 sec: 12246.3). Total num frames: 36401152. Throughput: 0: 12143.6. Samples: 36399924. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-11 11:22:42,812][04011] Avg episode reward: [(0, '29.708')] [2023-03-11 11:22:43,707][04298] Updated weights for policy 0, policy_version 71120 (0.0004) [2023-03-11 11:22:47,119][04298] Updated weights for policy 0, policy_version 71200 (0.0005) [2023-03-11 11:22:47,811][04011] Fps is (10 sec: 12287.9, 60 sec: 12014.9, 300 sec: 12218.6). Total num frames: 36458496. Throughput: 0: 12144.3. Samples: 36435712. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-11 11:22:47,812][04011] Avg episode reward: [(0, '30.945')] [2023-03-11 11:22:50,555][04298] Updated weights for policy 0, policy_version 71280 (0.0006) [2023-03-11 11:22:52,811][04011] Fps is (10 sec: 11878.3, 60 sec: 12083.2, 300 sec: 12204.7). Total num frames: 36519936. Throughput: 0: 12113.7. Samples: 36507512. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-11 11:22:52,812][04011] Avg episode reward: [(0, '28.632')] [2023-03-11 11:22:52,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000071328_36519936.pth... [2023-03-11 11:22:52,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000070624_36159488.pth [2023-03-11 11:22:54,005][04298] Updated weights for policy 0, policy_version 71360 (0.0005) [2023-03-11 11:22:57,391][04298] Updated weights for policy 0, policy_version 71440 (0.0005) [2023-03-11 11:22:57,811][04011] Fps is (10 sec: 12288.1, 60 sec: 12083.2, 300 sec: 12204.7). Total num frames: 36581376. Throughput: 0: 12104.2. Samples: 36579392. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-11 11:22:57,811][04011] Avg episode reward: [(0, '31.715')] [2023-03-11 11:23:00,821][04298] Updated weights for policy 0, policy_version 71520 (0.0005) [2023-03-11 11:23:02,811][04011] Fps is (10 sec: 11878.5, 60 sec: 12083.2, 300 sec: 12204.7). Total num frames: 36638720. Throughput: 0: 12085.5. Samples: 36614968. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-11 11:23:02,811][04011] Avg episode reward: [(0, '32.106')] [2023-03-11 11:23:04,096][04298] Updated weights for policy 0, policy_version 71600 (0.0004) [2023-03-11 11:23:07,395][04298] Updated weights for policy 0, policy_version 71680 (0.0005) [2023-03-11 11:23:07,811][04011] Fps is (10 sec: 12287.9, 60 sec: 12151.5, 300 sec: 12218.6). Total num frames: 36704256. Throughput: 0: 12101.9. Samples: 36689012. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-11 11:23:07,812][04011] Avg episode reward: [(0, '32.055')] [2023-03-11 11:23:07,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000071688_36704256.pth... [2023-03-11 11:23:07,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000070968_36335616.pth [2023-03-11 11:23:10,470][04298] Updated weights for policy 0, policy_version 71760 (0.0004) [2023-03-11 11:23:12,811][04011] Fps is (10 sec: 13107.1, 60 sec: 12219.7, 300 sec: 12246.3). Total num frames: 36769792. Throughput: 0: 12275.9. Samples: 36769312. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-11 11:23:12,812][04011] Avg episode reward: [(0, '32.127')] [2023-03-11 11:23:13,527][04298] Updated weights for policy 0, policy_version 71840 (0.0004) [2023-03-11 11:23:16,767][04298] Updated weights for policy 0, policy_version 71920 (0.0005) [2023-03-11 11:23:17,811][04011] Fps is (10 sec: 13107.3, 60 sec: 12288.0, 300 sec: 12260.2). Total num frames: 36835328. Throughput: 0: 12310.2. Samples: 36806720. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-11 11:23:17,812][04011] Avg episode reward: [(0, '32.232')] [2023-03-11 11:23:19,785][04298] Updated weights for policy 0, policy_version 72000 (0.0004) [2023-03-11 11:23:22,811][04011] Fps is (10 sec: 13107.2, 60 sec: 12356.3, 300 sec: 12274.1). Total num frames: 36900864. Throughput: 0: 12522.5. Samples: 36887344. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-11 11:23:22,811][04011] Avg episode reward: [(0, '31.028')] [2023-03-11 11:23:22,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000072072_36900864.pth... [2023-03-11 11:23:22,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000071328_36519936.pth [2023-03-11 11:23:22,931][04298] Updated weights for policy 0, policy_version 72080 (0.0005) [2023-03-11 11:23:26,021][04298] Updated weights for policy 0, policy_version 72160 (0.0004) [2023-03-11 11:23:27,811][04011] Fps is (10 sec: 13107.2, 60 sec: 12492.8, 300 sec: 12274.1). Total num frames: 36966400. Throughput: 0: 12588.5. Samples: 36966408. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-11 11:23:27,811][04011] Avg episode reward: [(0, '30.402')] [2023-03-11 11:23:29,164][04298] Updated weights for policy 0, policy_version 72240 (0.0005) [2023-03-11 11:23:32,409][04298] Updated weights for policy 0, policy_version 72320 (0.0005) [2023-03-11 11:23:32,811][04011] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12288.0). Total num frames: 37031936. Throughput: 0: 12643.8. Samples: 37004680. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:23:32,811][04011] Avg episode reward: [(0, '30.601')] [2023-03-11 11:23:35,793][04298] Updated weights for policy 0, policy_version 72400 (0.0005) [2023-03-11 11:23:37,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12561.1, 300 sec: 12274.1). Total num frames: 37089280. Throughput: 0: 12681.8. Samples: 37078192. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:23:37,811][04011] Avg episode reward: [(0, '31.692')] [2023-03-11 11:23:37,835][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000072448_37093376.pth... [2023-03-11 11:23:37,837][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000071688_36704256.pth [2023-03-11 11:23:39,105][04298] Updated weights for policy 0, policy_version 72480 (0.0005) [2023-03-11 11:23:42,168][04298] Updated weights for policy 0, policy_version 72560 (0.0004) [2023-03-11 11:23:42,811][04011] Fps is (10 sec: 12697.7, 60 sec: 12629.3, 300 sec: 12315.8). Total num frames: 37158912. Throughput: 0: 12799.1. Samples: 37155352. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:23:42,811][04011] Avg episode reward: [(0, '31.488')] [2023-03-11 11:23:45,270][04298] Updated weights for policy 0, policy_version 72640 (0.0004) [2023-03-11 11:23:47,811][04011] Fps is (10 sec: 13516.8, 60 sec: 12765.9, 300 sec: 12329.7). Total num frames: 37224448. Throughput: 0: 12905.0. Samples: 37195692. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:23:47,811][04011] Avg episode reward: [(0, '32.012')] [2023-03-11 11:23:48,403][04298] Updated weights for policy 0, policy_version 72720 (0.0005) [2023-03-11 11:23:51,507][04298] Updated weights for policy 0, policy_version 72800 (0.0004) [2023-03-11 11:23:52,811][04011] Fps is (10 sec: 13107.1, 60 sec: 12834.1, 300 sec: 12343.5). Total num frames: 37289984. Throughput: 0: 12995.8. Samples: 37273824. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:23:52,812][04011] Avg episode reward: [(0, '31.901')] [2023-03-11 11:23:52,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000072832_37289984.pth... [2023-03-11 11:23:52,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000072072_36900864.pth [2023-03-11 11:23:54,673][04298] Updated weights for policy 0, policy_version 72880 (0.0005) [2023-03-11 11:23:57,811][04011] Fps is (10 sec: 12697.6, 60 sec: 12834.1, 300 sec: 12343.5). Total num frames: 37351424. Throughput: 0: 12883.7. Samples: 37349080. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:23:57,822][04011] Avg episode reward: [(0, '32.211')] [2023-03-11 11:23:58,121][04298] Updated weights for policy 0, policy_version 72960 (0.0005) [2023-03-11 11:24:01,509][04298] Updated weights for policy 0, policy_version 73040 (0.0005) [2023-03-11 11:24:02,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12834.1, 300 sec: 12301.9). Total num frames: 37408768. Throughput: 0: 12841.4. Samples: 37384584. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:24:02,811][04011] Avg episode reward: [(0, '32.264')] [2023-03-11 11:24:04,913][04298] Updated weights for policy 0, policy_version 73120 (0.0005) [2023-03-11 11:24:07,811][04011] Fps is (10 sec: 11878.3, 60 sec: 12765.9, 300 sec: 12301.9). Total num frames: 37470208. Throughput: 0: 12679.5. Samples: 37457920. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:24:07,822][04011] Avg episode reward: [(0, '30.824')] [2023-03-11 11:24:07,826][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000073184_37470208.pth... [2023-03-11 11:24:07,828][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000072448_37093376.pth [2023-03-11 11:24:08,300][04298] Updated weights for policy 0, policy_version 73200 (0.0004) [2023-03-11 11:24:11,832][04298] Updated weights for policy 0, policy_version 73280 (0.0005) [2023-03-11 11:24:12,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12629.3, 300 sec: 12260.2). Total num frames: 37527552. Throughput: 0: 12471.3. Samples: 37527616. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:24:12,822][04011] Avg episode reward: [(0, '31.305')] [2023-03-11 11:24:15,349][04298] Updated weights for policy 0, policy_version 73360 (0.0005) [2023-03-11 11:24:17,811][04011] Fps is (10 sec: 11878.5, 60 sec: 12561.1, 300 sec: 12246.3). Total num frames: 37588992. Throughput: 0: 12411.8. Samples: 37563212. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:24:17,811][04011] Avg episode reward: [(0, '32.246')] [2023-03-11 11:24:18,798][04298] Updated weights for policy 0, policy_version 73440 (0.0005) [2023-03-11 11:24:22,239][04298] Updated weights for policy 0, policy_version 73520 (0.0005) [2023-03-11 11:24:22,811][04011] Fps is (10 sec: 11878.3, 60 sec: 12424.5, 300 sec: 12218.6). Total num frames: 37646336. Throughput: 0: 12353.8. Samples: 37634112. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:24:22,822][04011] Avg episode reward: [(0, '31.366')] [2023-03-11 11:24:22,825][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000073528_37646336.pth... [2023-03-11 11:24:22,828][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000072832_37289984.pth [2023-03-11 11:24:25,776][04298] Updated weights for policy 0, policy_version 73600 (0.0005) [2023-03-11 11:24:27,811][04011] Fps is (10 sec: 11468.8, 60 sec: 12288.0, 300 sec: 12204.7). Total num frames: 37703680. Throughput: 0: 12197.3. Samples: 37704232. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:24:27,822][04011] Avg episode reward: [(0, '31.036')] [2023-03-11 11:24:29,245][04298] Updated weights for policy 0, policy_version 73680 (0.0005) [2023-03-11 11:24:32,636][04298] Updated weights for policy 0, policy_version 73760 (0.0005) [2023-03-11 11:24:32,811][04011] Fps is (10 sec: 11878.5, 60 sec: 12219.7, 300 sec: 12218.6). Total num frames: 37765120. Throughput: 0: 12107.8. Samples: 37740544. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:24:32,822][04011] Avg episode reward: [(0, '32.577')] [2023-03-11 11:24:35,977][04298] Updated weights for policy 0, policy_version 73840 (0.0005) [2023-03-11 11:24:37,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12288.0, 300 sec: 12204.7). Total num frames: 37826560. Throughput: 0: 11985.4. Samples: 37813168. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:24:37,822][04011] Avg episode reward: [(0, '30.942')] [2023-03-11 11:24:37,826][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000073880_37826560.pth... [2023-03-11 11:24:37,828][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000073184_37470208.pth [2023-03-11 11:24:39,357][04298] Updated weights for policy 0, policy_version 73920 (0.0005) [2023-03-11 11:24:42,717][04298] Updated weights for policy 0, policy_version 74000 (0.0005) [2023-03-11 11:24:42,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12151.5, 300 sec: 12190.8). Total num frames: 37888000. Throughput: 0: 11934.6. Samples: 37886136. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:24:42,822][04011] Avg episode reward: [(0, '31.438')] [2023-03-11 11:24:46,040][04298] Updated weights for policy 0, policy_version 74080 (0.0005) [2023-03-11 11:24:47,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12083.2, 300 sec: 12190.8). Total num frames: 37949440. Throughput: 0: 11973.2. Samples: 37923380. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:24:47,822][04011] Avg episode reward: [(0, '31.674')] [2023-03-11 11:24:49,345][04298] Updated weights for policy 0, policy_version 74160 (0.0004) [2023-03-11 11:24:52,645][04298] Updated weights for policy 0, policy_version 74240 (0.0005) [2023-03-11 11:24:52,811][04011] Fps is (10 sec: 12288.1, 60 sec: 12014.9, 300 sec: 12204.7). Total num frames: 38010880. Throughput: 0: 11972.8. Samples: 37996696. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:24:52,822][04011] Avg episode reward: [(0, '27.512')] [2023-03-11 11:24:52,825][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000074240_38010880.pth... [2023-03-11 11:24:52,827][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000073528_37646336.pth [2023-03-11 11:24:55,813][04298] Updated weights for policy 0, policy_version 74320 (0.0004) [2023-03-11 11:24:57,811][04011] Fps is (10 sec: 12288.1, 60 sec: 12014.9, 300 sec: 12204.7). Total num frames: 38072320. Throughput: 0: 12121.3. Samples: 38073072. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:24:57,811][04011] Avg episode reward: [(0, '20.061')] [2023-03-11 11:24:59,195][04254] Early stopping after 2 epochs (8 sgd steps), loss delta 0.0000010 [2023-03-11 11:24:59,196][04298] Updated weights for policy 0, policy_version 74400 (0.0005) [2023-03-11 11:25:02,593][04298] Updated weights for policy 0, policy_version 74480 (0.0005) [2023-03-11 11:25:02,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12083.2, 300 sec: 12190.8). Total num frames: 38133760. Throughput: 0: 12134.3. Samples: 38109256. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 11:25:02,811][04011] Avg episode reward: [(0, '25.470')] [2023-03-11 11:25:06,054][04298] Updated weights for policy 0, policy_version 74560 (0.0005) [2023-03-11 11:25:07,811][04011] Fps is (10 sec: 11878.2, 60 sec: 12014.9, 300 sec: 12190.8). Total num frames: 38191104. Throughput: 0: 12142.3. Samples: 38180516. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 11:25:07,812][04011] Avg episode reward: [(0, '26.856')] [2023-03-11 11:25:07,848][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000074600_38195200.pth... [2023-03-11 11:25:07,851][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000073880_37826560.pth [2023-03-11 11:25:09,604][04298] Updated weights for policy 0, policy_version 74640 (0.0005) [2023-03-11 11:25:12,811][04011] Fps is (10 sec: 11468.8, 60 sec: 12014.9, 300 sec: 12176.9). Total num frames: 38248448. Throughput: 0: 12109.9. Samples: 38249176. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 11:25:12,812][04011] Avg episode reward: [(0, '24.130')] [2023-03-11 11:25:13,197][04298] Updated weights for policy 0, policy_version 74720 (0.0004) [2023-03-11 11:25:16,613][04298] Updated weights for policy 0, policy_version 74800 (0.0005) [2023-03-11 11:25:17,811][04011] Fps is (10 sec: 11878.5, 60 sec: 12014.9, 300 sec: 12176.9). Total num frames: 38309888. Throughput: 0: 12106.2. Samples: 38285324. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 11:25:17,811][04011] Avg episode reward: [(0, '28.334')] [2023-03-11 11:25:20,116][04298] Updated weights for policy 0, policy_version 74880 (0.0005) [2023-03-11 11:25:22,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12083.2, 300 sec: 12176.9). Total num frames: 38371328. Throughput: 0: 12066.3. Samples: 38356152. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 11:25:22,812][04011] Avg episode reward: [(0, '28.825')] [2023-03-11 11:25:22,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000074944_38371328.pth... [2023-03-11 11:25:22,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000074240_38010880.pth [2023-03-11 11:25:23,496][04298] Updated weights for policy 0, policy_version 74960 (0.0005) [2023-03-11 11:25:26,661][04298] Updated weights for policy 0, policy_version 75040 (0.0004) [2023-03-11 11:25:27,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12151.5, 300 sec: 12190.8). Total num frames: 38432768. Throughput: 0: 12134.4. Samples: 38432184. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 11:25:27,812][04011] Avg episode reward: [(0, '27.840')] [2023-03-11 11:25:29,773][04298] Updated weights for policy 0, policy_version 75120 (0.0003) [2023-03-11 11:25:32,811][04011] Fps is (10 sec: 12697.6, 60 sec: 12219.7, 300 sec: 12204.7). Total num frames: 38498304. Throughput: 0: 12175.2. Samples: 38471264. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 11:25:32,811][04011] Avg episode reward: [(0, '28.461')] [2023-03-11 11:25:32,916][04298] Updated weights for policy 0, policy_version 75200 (0.0003) [2023-03-11 11:25:36,270][04298] Updated weights for policy 0, policy_version 75280 (0.0004) [2023-03-11 11:25:37,811][04011] Fps is (10 sec: 12697.6, 60 sec: 12219.7, 300 sec: 12204.7). Total num frames: 38559744. Throughput: 0: 12236.4. Samples: 38547332. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 11:25:37,811][04011] Avg episode reward: [(0, '24.895')] [2023-03-11 11:25:37,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000075312_38559744.pth... [2023-03-11 11:25:37,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000074600_38195200.pth [2023-03-11 11:25:39,706][04298] Updated weights for policy 0, policy_version 75360 (0.0005) [2023-03-11 11:25:42,811][04011] Fps is (10 sec: 12288.1, 60 sec: 12219.7, 300 sec: 12204.7). Total num frames: 38621184. Throughput: 0: 12144.0. Samples: 38619552. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 11:25:42,811][04011] Avg episode reward: [(0, '30.695')] [2023-03-11 11:25:42,968][04298] Updated weights for policy 0, policy_version 75440 (0.0004) [2023-03-11 11:25:46,057][04298] Updated weights for policy 0, policy_version 75520 (0.0003) [2023-03-11 11:25:47,811][04011] Fps is (10 sec: 12697.6, 60 sec: 12288.0, 300 sec: 12218.6). Total num frames: 38686720. Throughput: 0: 12225.1. Samples: 38659384. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 11:25:47,822][04011] Avg episode reward: [(0, '28.003')] [2023-03-11 11:25:49,262][04298] Updated weights for policy 0, policy_version 75600 (0.0003) [2023-03-11 11:25:52,697][04298] Updated weights for policy 0, policy_version 75680 (0.0005) [2023-03-11 11:25:52,811][04011] Fps is (10 sec: 12697.5, 60 sec: 12288.0, 300 sec: 12232.5). Total num frames: 38748160. Throughput: 0: 12329.7. Samples: 38735352. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 11:25:52,822][04011] Avg episode reward: [(0, '30.068')] [2023-03-11 11:25:52,825][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000075680_38748160.pth... [2023-03-11 11:25:52,828][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000074944_38371328.pth [2023-03-11 11:25:56,132][04298] Updated weights for policy 0, policy_version 75760 (0.0005) [2023-03-11 11:25:57,811][04011] Fps is (10 sec: 11878.3, 60 sec: 12219.7, 300 sec: 12218.6). Total num frames: 38805504. Throughput: 0: 12383.8. Samples: 38806448. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 11:25:57,822][04011] Avg episode reward: [(0, '30.813')] [2023-03-11 11:25:59,481][04298] Updated weights for policy 0, policy_version 75840 (0.0005) [2023-03-11 11:26:02,811][04011] Fps is (10 sec: 11878.5, 60 sec: 12219.8, 300 sec: 12232.5). Total num frames: 38866944. Throughput: 0: 12391.8. Samples: 38842956. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 11:26:02,818][04298] Updated weights for policy 0, policy_version 75920 (0.0005) [2023-03-11 11:26:02,822][04011] Avg episode reward: [(0, '29.891')] [2023-03-11 11:26:06,201][04298] Updated weights for policy 0, policy_version 76000 (0.0005) [2023-03-11 11:26:07,811][04011] Fps is (10 sec: 12288.1, 60 sec: 12288.0, 300 sec: 12232.5). Total num frames: 38928384. Throughput: 0: 12444.9. Samples: 38916172. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 11:26:07,822][04011] Avg episode reward: [(0, '31.174')] [2023-03-11 11:26:07,824][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000076032_38928384.pth... [2023-03-11 11:26:07,827][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000075312_38559744.pth [2023-03-11 11:26:09,620][04298] Updated weights for policy 0, policy_version 76080 (0.0005) [2023-03-11 11:26:12,811][04011] Fps is (10 sec: 12287.9, 60 sec: 12356.3, 300 sec: 12246.3). Total num frames: 38989824. Throughput: 0: 12368.4. Samples: 38988764. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 11:26:12,811][04011] Avg episode reward: [(0, '31.235')] [2023-03-11 11:26:12,967][04298] Updated weights for policy 0, policy_version 76160 (0.0004) [2023-03-11 11:26:16,152][04298] Updated weights for policy 0, policy_version 76240 (0.0004) [2023-03-11 11:26:17,811][04011] Fps is (10 sec: 12287.9, 60 sec: 12356.3, 300 sec: 12246.3). Total num frames: 39051264. Throughput: 0: 12361.6. Samples: 39027536. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 11:26:17,811][04011] Avg episode reward: [(0, '29.846')] [2023-03-11 11:26:19,599][04298] Updated weights for policy 0, policy_version 76320 (0.0005) [2023-03-11 11:26:22,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12356.3, 300 sec: 12260.2). Total num frames: 39112704. Throughput: 0: 12272.2. Samples: 39099580. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 11:26:22,811][04011] Avg episode reward: [(0, '29.843')] [2023-03-11 11:26:22,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000076392_39112704.pth... [2023-03-11 11:26:22,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000075680_38748160.pth [2023-03-11 11:26:23,048][04298] Updated weights for policy 0, policy_version 76400 (0.0005) [2023-03-11 11:26:26,432][04298] Updated weights for policy 0, policy_version 76480 (0.0005) [2023-03-11 11:26:27,811][04011] Fps is (10 sec: 12288.1, 60 sec: 12356.3, 300 sec: 12260.2). Total num frames: 39174144. Throughput: 0: 12279.1. Samples: 39172112. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 11:26:27,811][04011] Avg episode reward: [(0, '31.039')] [2023-03-11 11:26:29,746][04298] Updated weights for policy 0, policy_version 76560 (0.0005) [2023-03-11 11:26:32,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12219.7, 300 sec: 12246.3). Total num frames: 39231488. Throughput: 0: 12184.4. Samples: 39207680. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 11:26:32,811][04011] Avg episode reward: [(0, '28.501')] [2023-03-11 11:26:33,267][04298] Updated weights for policy 0, policy_version 76640 (0.0005) [2023-03-11 11:26:36,784][04298] Updated weights for policy 0, policy_version 76720 (0.0005) [2023-03-11 11:26:37,811][04011] Fps is (10 sec: 11878.3, 60 sec: 12219.7, 300 sec: 12260.2). Total num frames: 39292928. Throughput: 0: 12062.2. Samples: 39278152. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 11:26:37,812][04011] Avg episode reward: [(0, '30.581')] [2023-03-11 11:26:37,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000076744_39292928.pth... [2023-03-11 11:26:37,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000076032_38928384.pth [2023-03-11 11:26:40,149][04298] Updated weights for policy 0, policy_version 76800 (0.0005) [2023-03-11 11:26:42,811][04011] Fps is (10 sec: 12287.9, 60 sec: 12219.7, 300 sec: 12260.2). Total num frames: 39354368. Throughput: 0: 12099.7. Samples: 39350932. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 11:26:42,811][04011] Avg episode reward: [(0, '30.110')] [2023-03-11 11:26:43,488][04298] Updated weights for policy 0, policy_version 76880 (0.0004) [2023-03-11 11:26:46,956][04298] Updated weights for policy 0, policy_version 76960 (0.0005) [2023-03-11 11:26:47,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12083.2, 300 sec: 12260.2). Total num frames: 39411712. Throughput: 0: 12094.3. Samples: 39387200. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 11:26:47,811][04011] Avg episode reward: [(0, '29.408')] [2023-03-11 11:26:50,329][04298] Updated weights for policy 0, policy_version 77040 (0.0005) [2023-03-11 11:26:52,811][04011] Fps is (10 sec: 11878.3, 60 sec: 12083.2, 300 sec: 12260.2). Total num frames: 39473152. Throughput: 0: 12068.3. Samples: 39459248. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 11:26:52,812][04011] Avg episode reward: [(0, '30.018')] [2023-03-11 11:26:52,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000077096_39473152.pth... [2023-03-11 11:26:52,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000076392_39112704.pth [2023-03-11 11:26:53,676][04298] Updated weights for policy 0, policy_version 77120 (0.0005) [2023-03-11 11:26:57,108][04298] Updated weights for policy 0, policy_version 77200 (0.0005) [2023-03-11 11:26:57,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12151.5, 300 sec: 12274.1). Total num frames: 39534592. Throughput: 0: 12064.3. Samples: 39531656. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 11:26:57,811][04011] Avg episode reward: [(0, '29.847')] [2023-03-11 11:27:00,494][04298] Updated weights for policy 0, policy_version 77280 (0.0005) [2023-03-11 11:27:02,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12083.2, 300 sec: 12260.2). Total num frames: 39591936. Throughput: 0: 12003.3. Samples: 39567684. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 11:27:02,812][04011] Avg episode reward: [(0, '28.762')] [2023-03-11 11:27:03,912][04298] Updated weights for policy 0, policy_version 77360 (0.0005) [2023-03-11 11:27:07,413][04298] Updated weights for policy 0, policy_version 77440 (0.0005) [2023-03-11 11:27:07,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12083.2, 300 sec: 12260.2). Total num frames: 39653376. Throughput: 0: 12005.6. Samples: 39639832. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 11:27:07,811][04011] Avg episode reward: [(0, '30.333')] [2023-03-11 11:27:07,814][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000077448_39653376.pth... [2023-03-11 11:27:07,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000076744_39292928.pth [2023-03-11 11:27:10,788][04298] Updated weights for policy 0, policy_version 77520 (0.0005) [2023-03-11 11:27:12,811][04011] Fps is (10 sec: 11878.5, 60 sec: 12014.9, 300 sec: 12246.3). Total num frames: 39710720. Throughput: 0: 11970.9. Samples: 39710804. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 11:27:12,811][04011] Avg episode reward: [(0, '31.061')] [2023-03-11 11:27:14,295][04298] Updated weights for policy 0, policy_version 77600 (0.0005) [2023-03-11 11:27:17,689][04298] Updated weights for policy 0, policy_version 77680 (0.0005) [2023-03-11 11:27:17,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12014.9, 300 sec: 12246.3). Total num frames: 39772160. Throughput: 0: 11975.1. Samples: 39746560. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 11:27:17,811][04011] Avg episode reward: [(0, '30.636')] [2023-03-11 11:27:21,188][04298] Updated weights for policy 0, policy_version 77760 (0.0005) [2023-03-11 11:27:22,811][04011] Fps is (10 sec: 11878.4, 60 sec: 11946.7, 300 sec: 12246.3). Total num frames: 39829504. Throughput: 0: 11981.8. Samples: 39817332. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-11 11:27:22,811][04011] Avg episode reward: [(0, '30.910')] [2023-03-11 11:27:22,844][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000077800_39833600.pth... [2023-03-11 11:27:22,845][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000077096_39473152.pth [2023-03-11 11:27:24,475][04298] Updated weights for policy 0, policy_version 77840 (0.0005) [2023-03-11 11:27:27,811][04011] Fps is (10 sec: 11878.3, 60 sec: 11946.7, 300 sec: 12246.3). Total num frames: 39890944. Throughput: 0: 12014.0. Samples: 39891564. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-11 11:27:27,812][04011] Avg episode reward: [(0, '30.536')] [2023-03-11 11:27:27,838][04298] Updated weights for policy 0, policy_version 77920 (0.0005) [2023-03-11 11:27:31,228][04298] Updated weights for policy 0, policy_version 78000 (0.0005) [2023-03-11 11:27:32,811][04011] Fps is (10 sec: 12288.1, 60 sec: 12014.9, 300 sec: 12260.2). Total num frames: 39952384. Throughput: 0: 12015.0. Samples: 39927872. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-11 11:27:32,811][04011] Avg episode reward: [(0, '27.442')] [2023-03-11 11:27:34,674][04298] Updated weights for policy 0, policy_version 78080 (0.0005) [2023-03-11 11:27:37,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12014.9, 300 sec: 12246.3). Total num frames: 40013824. Throughput: 0: 11999.2. Samples: 39999212. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-11 11:27:37,811][04011] Avg episode reward: [(0, '13.999')] [2023-03-11 11:27:37,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000078152_40013824.pth... [2023-03-11 11:27:37,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000077448_39653376.pth [2023-03-11 11:27:38,149][04298] Updated weights for policy 0, policy_version 78160 (0.0005) [2023-03-11 11:27:41,566][04298] Updated weights for policy 0, policy_version 78240 (0.0005) [2023-03-11 11:27:42,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12014.9, 300 sec: 12260.2). Total num frames: 40075264. Throughput: 0: 11997.0. Samples: 40071520. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-11 11:27:42,811][04011] Avg episode reward: [(0, '29.906')] [2023-03-11 11:27:44,697][04298] Updated weights for policy 0, policy_version 78320 (0.0003) [2023-03-11 11:27:47,811][04011] Fps is (10 sec: 12288.1, 60 sec: 12083.2, 300 sec: 12260.2). Total num frames: 40136704. Throughput: 0: 12069.7. Samples: 40110820. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-11 11:27:47,811][04011] Avg episode reward: [(0, '31.166')] [2023-03-11 11:27:47,870][04298] Updated weights for policy 0, policy_version 78400 (0.0003) [2023-03-11 11:27:51,037][04298] Updated weights for policy 0, policy_version 78480 (0.0003) [2023-03-11 11:27:52,811][04011] Fps is (10 sec: 12697.5, 60 sec: 12151.5, 300 sec: 12274.1). Total num frames: 40202240. Throughput: 0: 12197.0. Samples: 40188696. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-11 11:27:52,811][04011] Avg episode reward: [(0, '30.643')] [2023-03-11 11:27:52,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000078520_40202240.pth... [2023-03-11 11:27:52,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000077800_39833600.pth [2023-03-11 11:27:54,126][04298] Updated weights for policy 0, policy_version 78560 (0.0003) [2023-03-11 11:27:57,390][04298] Updated weights for policy 0, policy_version 78640 (0.0004) [2023-03-11 11:27:57,811][04011] Fps is (10 sec: 13107.2, 60 sec: 12219.7, 300 sec: 12301.9). Total num frames: 40267776. Throughput: 0: 12334.8. Samples: 40265872. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-11 11:27:57,811][04011] Avg episode reward: [(0, '30.204')] [2023-03-11 11:28:00,679][04298] Updated weights for policy 0, policy_version 78720 (0.0004) [2023-03-11 11:28:02,811][04011] Fps is (10 sec: 12697.7, 60 sec: 12288.0, 300 sec: 12288.0). Total num frames: 40329216. Throughput: 0: 12376.6. Samples: 40303508. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-11 11:28:02,811][04011] Avg episode reward: [(0, '30.117')] [2023-03-11 11:28:03,774][04298] Updated weights for policy 0, policy_version 78800 (0.0004) [2023-03-11 11:28:06,851][04298] Updated weights for policy 0, policy_version 78880 (0.0004) [2023-03-11 11:28:07,811][04011] Fps is (10 sec: 13107.2, 60 sec: 12424.5, 300 sec: 12301.9). Total num frames: 40398848. Throughput: 0: 12560.1. Samples: 40382536. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-11 11:28:07,812][04011] Avg episode reward: [(0, '31.924')] [2023-03-11 11:28:07,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000078904_40398848.pth... [2023-03-11 11:28:07,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000078152_40013824.pth [2023-03-11 11:28:10,160][04298] Updated weights for policy 0, policy_version 78960 (0.0005) [2023-03-11 11:28:12,811][04011] Fps is (10 sec: 13107.1, 60 sec: 12492.8, 300 sec: 12288.0). Total num frames: 40460288. Throughput: 0: 12588.9. Samples: 40458064. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:28:12,811][04011] Avg episode reward: [(0, '30.994')] [2023-03-11 11:28:13,356][04298] Updated weights for policy 0, policy_version 79040 (0.0005) [2023-03-11 11:28:16,464][04298] Updated weights for policy 0, policy_version 79120 (0.0004) [2023-03-11 11:28:17,811][04011] Fps is (10 sec: 12697.6, 60 sec: 12561.1, 300 sec: 12288.0). Total num frames: 40525824. Throughput: 0: 12652.3. Samples: 40497224. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:28:17,811][04011] Avg episode reward: [(0, '31.216')] [2023-03-11 11:28:19,543][04298] Updated weights for policy 0, policy_version 79200 (0.0004) [2023-03-11 11:28:22,589][04298] Updated weights for policy 0, policy_version 79280 (0.0004) [2023-03-11 11:28:22,811][04011] Fps is (10 sec: 13107.2, 60 sec: 12697.6, 300 sec: 12288.0). Total num frames: 40591360. Throughput: 0: 12850.2. Samples: 40577472. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:28:22,811][04011] Avg episode reward: [(0, '30.938')] [2023-03-11 11:28:22,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000079280_40591360.pth... [2023-03-11 11:28:22,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000078520_40202240.pth [2023-03-11 11:28:25,694][04298] Updated weights for policy 0, policy_version 79360 (0.0004) [2023-03-11 11:28:27,811][04011] Fps is (10 sec: 13107.2, 60 sec: 12765.9, 300 sec: 12288.0). Total num frames: 40656896. Throughput: 0: 13004.5. Samples: 40656724. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:28:27,811][04011] Avg episode reward: [(0, '30.353')] [2023-03-11 11:28:28,940][04298] Updated weights for policy 0, policy_version 79440 (0.0005) [2023-03-11 11:28:32,332][04298] Updated weights for policy 0, policy_version 79520 (0.0005) [2023-03-11 11:28:32,811][04011] Fps is (10 sec: 12697.7, 60 sec: 12765.9, 300 sec: 12301.9). Total num frames: 40718336. Throughput: 0: 12954.4. Samples: 40693768. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:28:32,811][04011] Avg episode reward: [(0, '31.147')] [2023-03-11 11:28:35,736][04298] Updated weights for policy 0, policy_version 79600 (0.0005) [2023-03-11 11:28:37,811][04011] Fps is (10 sec: 12288.1, 60 sec: 12765.9, 300 sec: 12274.1). Total num frames: 40779776. Throughput: 0: 12792.2. Samples: 40764344. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:28:37,811][04011] Avg episode reward: [(0, '31.212')] [2023-03-11 11:28:37,814][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000079648_40779776.pth... [2023-03-11 11:28:37,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000078904_40398848.pth [2023-03-11 11:28:39,024][04298] Updated weights for policy 0, policy_version 79680 (0.0005) [2023-03-11 11:28:42,078][04298] Updated weights for policy 0, policy_version 79760 (0.0004) [2023-03-11 11:28:42,811][04011] Fps is (10 sec: 12697.5, 60 sec: 12834.1, 300 sec: 12274.1). Total num frames: 40845312. Throughput: 0: 12837.8. Samples: 40843572. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:28:42,811][04011] Avg episode reward: [(0, '30.994')] [2023-03-11 11:28:45,196][04298] Updated weights for policy 0, policy_version 79840 (0.0004) [2023-03-11 11:28:47,811][04011] Fps is (10 sec: 12697.5, 60 sec: 12834.1, 300 sec: 12260.2). Total num frames: 40906752. Throughput: 0: 12870.2. Samples: 40882668. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:28:47,811][04011] Avg episode reward: [(0, '30.685')] [2023-03-11 11:28:48,596][04298] Updated weights for policy 0, policy_version 79920 (0.0005) [2023-03-11 11:28:51,936][04298] Updated weights for policy 0, policy_version 80000 (0.0005) [2023-03-11 11:28:52,811][04011] Fps is (10 sec: 12287.9, 60 sec: 12765.9, 300 sec: 12260.2). Total num frames: 40968192. Throughput: 0: 12741.5. Samples: 40955904. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:28:52,811][04011] Avg episode reward: [(0, '29.823')] [2023-03-11 11:28:52,814][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000080016_40968192.pth... [2023-03-11 11:28:52,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000079280_40591360.pth [2023-03-11 11:28:55,272][04298] Updated weights for policy 0, policy_version 80080 (0.0005) [2023-03-11 11:28:57,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12697.6, 300 sec: 12274.1). Total num frames: 41029632. Throughput: 0: 12694.8. Samples: 41029332. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-11 11:28:57,811][04011] Avg episode reward: [(0, '30.458')] [2023-03-11 11:28:58,662][04298] Updated weights for policy 0, policy_version 80160 (0.0006) [2023-03-11 11:29:02,060][04298] Updated weights for policy 0, policy_version 80240 (0.0005) [2023-03-11 11:29:02,811][04011] Fps is (10 sec: 12288.1, 60 sec: 12697.6, 300 sec: 12274.1). Total num frames: 41091072. Throughput: 0: 12638.6. Samples: 41065960. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-11 11:29:02,811][04011] Avg episode reward: [(0, '30.713')] [2023-03-11 11:29:05,348][04298] Updated weights for policy 0, policy_version 80320 (0.0005) [2023-03-11 11:29:07,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12561.1, 300 sec: 12288.0). Total num frames: 41152512. Throughput: 0: 12460.1. Samples: 41138176. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-11 11:29:07,811][04011] Avg episode reward: [(0, '29.802')] [2023-03-11 11:29:07,814][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000080376_41152512.pth... [2023-03-11 11:29:07,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000079648_40779776.pth [2023-03-11 11:29:08,773][04298] Updated weights for policy 0, policy_version 80400 (0.0005) [2023-03-11 11:29:12,148][04298] Updated weights for policy 0, policy_version 80480 (0.0005) [2023-03-11 11:29:12,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12561.1, 300 sec: 12288.0). Total num frames: 41213952. Throughput: 0: 12310.6. Samples: 41210700. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-11 11:29:12,811][04011] Avg episode reward: [(0, '30.128')] [2023-03-11 11:29:15,211][04298] Updated weights for policy 0, policy_version 80560 (0.0004) [2023-03-11 11:29:17,811][04011] Fps is (10 sec: 12697.6, 60 sec: 12561.1, 300 sec: 12315.8). Total num frames: 41279488. Throughput: 0: 12380.2. Samples: 41250880. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-11 11:29:17,811][04011] Avg episode reward: [(0, '30.937')] [2023-03-11 11:29:18,332][04298] Updated weights for policy 0, policy_version 80640 (0.0004) [2023-03-11 11:29:21,358][04298] Updated weights for policy 0, policy_version 80720 (0.0004) [2023-03-11 11:29:22,811][04011] Fps is (10 sec: 13107.1, 60 sec: 12561.1, 300 sec: 12343.5). Total num frames: 41345024. Throughput: 0: 12601.6. Samples: 41331416. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-11 11:29:22,811][04011] Avg episode reward: [(0, '30.132')] [2023-03-11 11:29:22,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000080752_41345024.pth... [2023-03-11 11:29:22,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000080016_40968192.pth [2023-03-11 11:29:24,507][04298] Updated weights for policy 0, policy_version 80800 (0.0004) [2023-03-11 11:29:27,513][04298] Updated weights for policy 0, policy_version 80880 (0.0003) [2023-03-11 11:29:27,811][04011] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12357.4). Total num frames: 41410560. Throughput: 0: 12602.1. Samples: 41410668. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-11 11:29:27,822][04011] Avg episode reward: [(0, '30.367')] [2023-03-11 11:29:30,756][04298] Updated weights for policy 0, policy_version 80960 (0.0005) [2023-03-11 11:29:32,811][04011] Fps is (10 sec: 13107.3, 60 sec: 12629.3, 300 sec: 12371.3). Total num frames: 41476096. Throughput: 0: 12583.7. Samples: 41448936. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-11 11:29:32,822][04011] Avg episode reward: [(0, '30.880')] [2023-03-11 11:29:34,113][04298] Updated weights for policy 0, policy_version 81040 (0.0005) [2023-03-11 11:29:37,556][04298] Updated weights for policy 0, policy_version 81120 (0.0005) [2023-03-11 11:29:37,811][04011] Fps is (10 sec: 12287.9, 60 sec: 12561.0, 300 sec: 12357.4). Total num frames: 41533440. Throughput: 0: 12562.7. Samples: 41521224. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-11 11:29:37,822][04011] Avg episode reward: [(0, '31.278')] [2023-03-11 11:29:37,824][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000081120_41533440.pth... [2023-03-11 11:29:37,827][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000080376_41152512.pth [2023-03-11 11:29:40,633][04298] Updated weights for policy 0, policy_version 81200 (0.0004) [2023-03-11 11:29:42,811][04011] Fps is (10 sec: 12697.6, 60 sec: 12629.3, 300 sec: 12385.2). Total num frames: 41603072. Throughput: 0: 12682.1. Samples: 41600024. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-11 11:29:42,822][04011] Avg episode reward: [(0, '30.792')] [2023-03-11 11:29:43,723][04298] Updated weights for policy 0, policy_version 81280 (0.0004) [2023-03-11 11:29:46,819][04298] Updated weights for policy 0, policy_version 81360 (0.0004) [2023-03-11 11:29:47,811][04011] Fps is (10 sec: 13516.9, 60 sec: 12697.6, 300 sec: 12399.1). Total num frames: 41668608. Throughput: 0: 12744.9. Samples: 41639480. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:29:47,811][04011] Avg episode reward: [(0, '31.272')] [2023-03-11 11:29:49,840][04298] Updated weights for policy 0, policy_version 81440 (0.0003) [2023-03-11 11:29:52,811][04011] Fps is (10 sec: 13107.1, 60 sec: 12765.9, 300 sec: 12413.0). Total num frames: 41734144. Throughput: 0: 12921.8. Samples: 41719656. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:29:52,812][04011] Avg episode reward: [(0, '31.427')] [2023-03-11 11:29:52,814][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000081512_41734144.pth... [2023-03-11 11:29:52,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000080752_41345024.pth [2023-03-11 11:29:52,953][04298] Updated weights for policy 0, policy_version 81520 (0.0004) [2023-03-11 11:29:55,972][04298] Updated weights for policy 0, policy_version 81600 (0.0003) [2023-03-11 11:29:57,811][04011] Fps is (10 sec: 13107.3, 60 sec: 12834.1, 300 sec: 12426.8). Total num frames: 41799680. Throughput: 0: 13089.9. Samples: 41799744. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:29:57,811][04011] Avg episode reward: [(0, '31.483')] [2023-03-11 11:29:59,227][04298] Updated weights for policy 0, policy_version 81680 (0.0004) [2023-03-11 11:30:02,435][04298] Updated weights for policy 0, policy_version 81760 (0.0004) [2023-03-11 11:30:02,811][04011] Fps is (10 sec: 13107.3, 60 sec: 12902.4, 300 sec: 12454.6). Total num frames: 41865216. Throughput: 0: 13014.9. Samples: 41836552. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:30:02,811][04011] Avg episode reward: [(0, '31.729')] [2023-03-11 11:30:05,757][04298] Updated weights for policy 0, policy_version 81840 (0.0005) [2023-03-11 11:30:07,811][04011] Fps is (10 sec: 12287.9, 60 sec: 12834.1, 300 sec: 12454.6). Total num frames: 41922560. Throughput: 0: 12891.6. Samples: 41911540. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:30:07,812][04011] Avg episode reward: [(0, '31.278')] [2023-03-11 11:30:07,875][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000081888_41926656.pth... [2023-03-11 11:30:07,876][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000081120_41533440.pth [2023-03-11 11:30:09,228][04298] Updated weights for policy 0, policy_version 81920 (0.0005) [2023-03-11 11:30:12,575][04298] Updated weights for policy 0, policy_version 82000 (0.0005) [2023-03-11 11:30:12,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12834.1, 300 sec: 12454.6). Total num frames: 41984000. Throughput: 0: 12740.9. Samples: 41984008. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:30:12,811][04011] Avg episode reward: [(0, '30.190')] [2023-03-11 11:30:15,685][04298] Updated weights for policy 0, policy_version 82080 (0.0004) [2023-03-11 11:30:17,811][04011] Fps is (10 sec: 12697.7, 60 sec: 12834.1, 300 sec: 12468.5). Total num frames: 42049536. Throughput: 0: 12767.5. Samples: 42023472. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:30:17,811][04011] Avg episode reward: [(0, '31.195')] [2023-03-11 11:30:18,762][04298] Updated weights for policy 0, policy_version 82160 (0.0004) [2023-03-11 11:30:21,855][04298] Updated weights for policy 0, policy_version 82240 (0.0004) [2023-03-11 11:30:22,811][04011] Fps is (10 sec: 13516.7, 60 sec: 12902.4, 300 sec: 12496.3). Total num frames: 42119168. Throughput: 0: 12925.0. Samples: 42102848. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:30:22,811][04011] Avg episode reward: [(0, '30.829')] [2023-03-11 11:30:22,814][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000082264_42119168.pth... [2023-03-11 11:30:22,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000081512_41734144.pth [2023-03-11 11:30:24,924][04298] Updated weights for policy 0, policy_version 82320 (0.0004) [2023-03-11 11:30:27,811][04011] Fps is (10 sec: 13107.2, 60 sec: 12834.1, 300 sec: 12482.4). Total num frames: 42180608. Throughput: 0: 12902.0. Samples: 42180616. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:30:27,811][04011] Avg episode reward: [(0, '30.308')] [2023-03-11 11:30:28,256][04298] Updated weights for policy 0, policy_version 82400 (0.0005) [2023-03-11 11:30:31,688][04298] Updated weights for policy 0, policy_version 82480 (0.0005) [2023-03-11 11:30:32,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12765.9, 300 sec: 12482.4). Total num frames: 42242048. Throughput: 0: 12829.4. Samples: 42216804. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:30:32,811][04011] Avg episode reward: [(0, '30.862')] [2023-03-11 11:30:35,185][04298] Updated weights for policy 0, policy_version 82560 (0.0005) [2023-03-11 11:30:37,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12765.9, 300 sec: 12468.5). Total num frames: 42299392. Throughput: 0: 12611.6. Samples: 42287176. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-11 11:30:37,811][04011] Avg episode reward: [(0, '30.648')] [2023-03-11 11:30:37,814][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000082616_42299392.pth... [2023-03-11 11:30:37,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000081888_41926656.pth [2023-03-11 11:30:38,620][04298] Updated weights for policy 0, policy_version 82640 (0.0005) [2023-03-11 11:30:41,930][04298] Updated weights for policy 0, policy_version 82720 (0.0005) [2023-03-11 11:30:42,811][04011] Fps is (10 sec: 11878.5, 60 sec: 12629.3, 300 sec: 12454.6). Total num frames: 42360832. Throughput: 0: 12462.1. Samples: 42360540. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-11 11:30:42,811][04011] Avg episode reward: [(0, '30.708')] [2023-03-11 11:30:45,400][04298] Updated weights for policy 0, policy_version 82800 (0.0004) [2023-03-11 11:30:47,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12561.1, 300 sec: 12454.6). Total num frames: 42422272. Throughput: 0: 12424.8. Samples: 42395668. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-11 11:30:47,822][04011] Avg episode reward: [(0, '30.115')] [2023-03-11 11:30:48,786][04298] Updated weights for policy 0, policy_version 82880 (0.0005) [2023-03-11 11:30:52,245][04298] Updated weights for policy 0, policy_version 82960 (0.0005) [2023-03-11 11:30:52,811][04011] Fps is (10 sec: 11878.2, 60 sec: 12424.5, 300 sec: 12454.6). Total num frames: 42479616. Throughput: 0: 12351.0. Samples: 42467336. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-11 11:30:52,822][04011] Avg episode reward: [(0, '30.948')] [2023-03-11 11:30:52,826][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000082968_42479616.pth... [2023-03-11 11:30:52,829][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000082264_42119168.pth [2023-03-11 11:30:55,555][04298] Updated weights for policy 0, policy_version 83040 (0.0005) [2023-03-11 11:30:57,811][04011] Fps is (10 sec: 11878.3, 60 sec: 12356.2, 300 sec: 12454.6). Total num frames: 42541056. Throughput: 0: 12357.3. Samples: 42540088. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-11 11:30:57,812][04011] Avg episode reward: [(0, '31.272')] [2023-03-11 11:30:59,084][04298] Updated weights for policy 0, policy_version 83120 (0.0005) [2023-03-11 11:31:02,349][04298] Updated weights for policy 0, policy_version 83200 (0.0005) [2023-03-11 11:31:02,811][04011] Fps is (10 sec: 12288.1, 60 sec: 12288.0, 300 sec: 12454.6). Total num frames: 42602496. Throughput: 0: 12272.1. Samples: 42575716. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-11 11:31:02,812][04011] Avg episode reward: [(0, '31.556')] [2023-03-11 11:31:05,772][04298] Updated weights for policy 0, policy_version 83280 (0.0005) [2023-03-11 11:31:07,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12288.0, 300 sec: 12440.7). Total num frames: 42659840. Throughput: 0: 12134.7. Samples: 42648908. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-11 11:31:07,812][04011] Avg episode reward: [(0, '29.761')] [2023-03-11 11:31:07,881][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000083328_42663936.pth... [2023-03-11 11:31:07,884][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000082616_42299392.pth [2023-03-11 11:31:09,253][04298] Updated weights for policy 0, policy_version 83360 (0.0005) [2023-03-11 11:31:12,559][04298] Updated weights for policy 0, policy_version 83440 (0.0005) [2023-03-11 11:31:12,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12288.0, 300 sec: 12440.7). Total num frames: 42721280. Throughput: 0: 12014.7. Samples: 42721280. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-11 11:31:12,822][04011] Avg episode reward: [(0, '29.337')] [2023-03-11 11:31:15,865][04298] Updated weights for policy 0, policy_version 83520 (0.0004) [2023-03-11 11:31:17,811][04011] Fps is (10 sec: 12288.1, 60 sec: 12219.7, 300 sec: 12440.7). Total num frames: 42782720. Throughput: 0: 12030.1. Samples: 42758160. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-11 11:31:17,822][04011] Avg episode reward: [(0, '30.038')] [2023-03-11 11:31:19,135][04298] Updated weights for policy 0, policy_version 83600 (0.0005) [2023-03-11 11:31:22,248][04298] Updated weights for policy 0, policy_version 83680 (0.0004) [2023-03-11 11:31:22,811][04011] Fps is (10 sec: 12697.6, 60 sec: 12151.5, 300 sec: 12454.6). Total num frames: 42848256. Throughput: 0: 12185.9. Samples: 42835544. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-11 11:31:22,822][04011] Avg episode reward: [(0, '29.270')] [2023-03-11 11:31:22,841][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000083696_42852352.pth... [2023-03-11 11:31:22,842][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000082968_42479616.pth [2023-03-11 11:31:25,393][04298] Updated weights for policy 0, policy_version 83760 (0.0004) [2023-03-11 11:31:27,811][04011] Fps is (10 sec: 13107.3, 60 sec: 12219.7, 300 sec: 12482.4). Total num frames: 42913792. Throughput: 0: 12287.2. Samples: 42913464. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-11 11:31:27,822][04011] Avg episode reward: [(0, '26.803')] [2023-03-11 11:31:28,572][04298] Updated weights for policy 0, policy_version 83840 (0.0005) [2023-03-11 11:31:31,694][04298] Updated weights for policy 0, policy_version 83920 (0.0004) [2023-03-11 11:31:32,811][04011] Fps is (10 sec: 13107.3, 60 sec: 12288.0, 300 sec: 12496.3). Total num frames: 42979328. Throughput: 0: 12361.0. Samples: 42951912. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-11 11:31:32,822][04011] Avg episode reward: [(0, '31.449')] [2023-03-11 11:31:34,796][04298] Updated weights for policy 0, policy_version 84000 (0.0005) [2023-03-11 11:31:37,811][04011] Fps is (10 sec: 13107.1, 60 sec: 12424.5, 300 sec: 12510.2). Total num frames: 43044864. Throughput: 0: 12529.4. Samples: 43031156. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-11 11:31:37,822][04011] Avg episode reward: [(0, '31.468')] [2023-03-11 11:31:37,825][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000084072_43044864.pth... [2023-03-11 11:31:37,828][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000083328_42663936.pth [2023-03-11 11:31:37,890][04298] Updated weights for policy 0, policy_version 84080 (0.0005) [2023-03-11 11:31:40,963][04298] Updated weights for policy 0, policy_version 84160 (0.0004) [2023-03-11 11:31:42,811][04011] Fps is (10 sec: 13516.8, 60 sec: 12561.1, 300 sec: 12551.8). Total num frames: 43114496. Throughput: 0: 12692.5. Samples: 43111248. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-11 11:31:42,822][04011] Avg episode reward: [(0, '31.268')] [2023-03-11 11:31:44,000][04298] Updated weights for policy 0, policy_version 84240 (0.0004) [2023-03-11 11:31:47,093][04298] Updated weights for policy 0, policy_version 84320 (0.0004) [2023-03-11 11:31:47,811][04011] Fps is (10 sec: 13516.8, 60 sec: 12629.3, 300 sec: 12565.7). Total num frames: 43180032. Throughput: 0: 12793.5. Samples: 43151424. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-11 11:31:47,822][04011] Avg episode reward: [(0, '31.400')] [2023-03-11 11:31:50,146][04298] Updated weights for policy 0, policy_version 84400 (0.0004) [2023-03-11 11:31:52,811][04011] Fps is (10 sec: 13107.1, 60 sec: 12765.9, 300 sec: 12579.6). Total num frames: 43245568. Throughput: 0: 12938.5. Samples: 43231140. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-11 11:31:52,822][04011] Avg episode reward: [(0, '31.188')] [2023-03-11 11:31:52,825][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000084464_43245568.pth... [2023-03-11 11:31:52,827][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000083696_42852352.pth [2023-03-11 11:31:53,452][04298] Updated weights for policy 0, policy_version 84480 (0.0005) [2023-03-11 11:31:56,844][04298] Updated weights for policy 0, policy_version 84560 (0.0005) [2023-03-11 11:31:57,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12697.6, 300 sec: 12579.6). Total num frames: 43302912. Throughput: 0: 12926.6. Samples: 43302976. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-11 11:31:57,822][04011] Avg episode reward: [(0, '19.051')] [2023-03-11 11:32:00,184][04298] Updated weights for policy 0, policy_version 84640 (0.0005) [2023-03-11 11:32:02,811][04011] Fps is (10 sec: 12288.1, 60 sec: 12765.9, 300 sec: 12593.5). Total num frames: 43368448. Throughput: 0: 12930.1. Samples: 43340012. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-11 11:32:02,822][04011] Avg episode reward: [(0, '29.876')] [2023-03-11 11:32:03,284][04298] Updated weights for policy 0, policy_version 84720 (0.0003) [2023-03-11 11:32:06,467][04298] Updated weights for policy 0, policy_version 84800 (0.0004) [2023-03-11 11:32:07,811][04011] Fps is (10 sec: 13107.0, 60 sec: 12902.4, 300 sec: 12621.2). Total num frames: 43433984. Throughput: 0: 12952.7. Samples: 43418416. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-11 11:32:07,822][04011] Avg episode reward: [(0, '31.277')] [2023-03-11 11:32:07,825][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000084832_43433984.pth... [2023-03-11 11:32:07,827][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000084072_43044864.pth [2023-03-11 11:32:09,847][04298] Updated weights for policy 0, policy_version 84880 (0.0005) [2023-03-11 11:32:12,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12834.2, 300 sec: 12607.4). Total num frames: 43491328. Throughput: 0: 12842.9. Samples: 43491392. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-11 11:32:12,811][04011] Avg episode reward: [(0, '31.077')] [2023-03-11 11:32:13,217][04298] Updated weights for policy 0, policy_version 84960 (0.0006) [2023-03-11 11:32:16,627][04298] Updated weights for policy 0, policy_version 85040 (0.0005) [2023-03-11 11:32:17,811][04011] Fps is (10 sec: 11878.5, 60 sec: 12834.1, 300 sec: 12621.2). Total num frames: 43552768. Throughput: 0: 12806.4. Samples: 43528200. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-11 11:32:17,811][04011] Avg episode reward: [(0, '29.937')] [2023-03-11 11:32:20,079][04298] Updated weights for policy 0, policy_version 85120 (0.0005) [2023-03-11 11:32:22,811][04011] Fps is (10 sec: 12287.9, 60 sec: 12765.9, 300 sec: 12621.2). Total num frames: 43614208. Throughput: 0: 12627.3. Samples: 43599384. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-11 11:32:22,811][04011] Avg episode reward: [(0, '30.650')] [2023-03-11 11:32:22,814][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000085184_43614208.pth... [2023-03-11 11:32:22,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000084464_43245568.pth [2023-03-11 11:32:23,459][04298] Updated weights for policy 0, policy_version 85200 (0.0005) [2023-03-11 11:32:26,810][04298] Updated weights for policy 0, policy_version 85280 (0.0005) [2023-03-11 11:32:27,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12629.3, 300 sec: 12607.4). Total num frames: 43671552. Throughput: 0: 12452.8. Samples: 43671624. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-11 11:32:27,811][04011] Avg episode reward: [(0, '30.872')] [2023-03-11 11:32:30,196][04298] Updated weights for policy 0, policy_version 85360 (0.0005) [2023-03-11 11:32:32,811][04011] Fps is (10 sec: 11878.5, 60 sec: 12561.1, 300 sec: 12607.4). Total num frames: 43732992. Throughput: 0: 12379.2. Samples: 43708488. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-11 11:32:32,811][04011] Avg episode reward: [(0, '28.507')] [2023-03-11 11:32:33,498][04298] Updated weights for policy 0, policy_version 85440 (0.0005) [2023-03-11 11:32:36,819][04298] Updated weights for policy 0, policy_version 85520 (0.0004) [2023-03-11 11:32:37,811][04011] Fps is (10 sec: 12697.6, 60 sec: 12561.1, 300 sec: 12621.2). Total num frames: 43798528. Throughput: 0: 12255.0. Samples: 43782616. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-11 11:32:37,811][04011] Avg episode reward: [(0, '28.683')] [2023-03-11 11:32:37,814][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000085544_43798528.pth... [2023-03-11 11:32:37,816][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000084832_43433984.pth [2023-03-11 11:32:39,998][04298] Updated weights for policy 0, policy_version 85600 (0.0004) [2023-03-11 11:32:42,811][04011] Fps is (10 sec: 12697.6, 60 sec: 12424.5, 300 sec: 12621.2). Total num frames: 43859968. Throughput: 0: 12379.2. Samples: 43860040. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-11 11:32:42,811][04011] Avg episode reward: [(0, '27.380')] [2023-03-11 11:32:43,123][04298] Updated weights for policy 0, policy_version 85680 (0.0004) [2023-03-11 11:32:46,165][04298] Updated weights for policy 0, policy_version 85760 (0.0004) [2023-03-11 11:32:47,811][04011] Fps is (10 sec: 13107.2, 60 sec: 12492.8, 300 sec: 12635.1). Total num frames: 43929600. Throughput: 0: 12461.0. Samples: 43900756. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-11 11:32:47,811][04011] Avg episode reward: [(0, '28.348')] [2023-03-11 11:32:49,268][04298] Updated weights for policy 0, policy_version 85840 (0.0004) [2023-03-11 11:32:52,619][04298] Updated weights for policy 0, policy_version 85920 (0.0005) [2023-03-11 11:32:52,811][04011] Fps is (10 sec: 13107.1, 60 sec: 12424.5, 300 sec: 12621.2). Total num frames: 43991040. Throughput: 0: 12441.6. Samples: 43978288. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-11 11:32:52,811][04011] Avg episode reward: [(0, '29.376')] [2023-03-11 11:32:52,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000085920_43991040.pth... [2023-03-11 11:32:52,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000085184_43614208.pth [2023-03-11 11:32:56,004][04298] Updated weights for policy 0, policy_version 86000 (0.0005) [2023-03-11 11:32:57,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12492.8, 300 sec: 12621.2). Total num frames: 44052480. Throughput: 0: 12412.8. Samples: 44049968. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-11 11:32:57,811][04011] Avg episode reward: [(0, '30.036')] [2023-03-11 11:32:59,478][04298] Updated weights for policy 0, policy_version 86080 (0.0005) [2023-03-11 11:33:02,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12356.3, 300 sec: 12579.6). Total num frames: 44109824. Throughput: 0: 12392.8. Samples: 44085876. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-11 11:33:02,811][04011] Avg episode reward: [(0, '29.724')] [2023-03-11 11:33:02,943][04298] Updated weights for policy 0, policy_version 86160 (0.0006) [2023-03-11 11:33:06,231][04298] Updated weights for policy 0, policy_version 86240 (0.0005) [2023-03-11 11:33:07,811][04011] Fps is (10 sec: 11878.3, 60 sec: 12288.0, 300 sec: 12579.6). Total num frames: 44171264. Throughput: 0: 12435.4. Samples: 44158976. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-11 11:33:07,822][04011] Avg episode reward: [(0, '29.057')] [2023-03-11 11:33:07,825][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000086272_44171264.pth... [2023-03-11 11:33:07,827][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000085544_43798528.pth [2023-03-11 11:33:09,487][04298] Updated weights for policy 0, policy_version 86320 (0.0004) [2023-03-11 11:33:12,652][04298] Updated weights for policy 0, policy_version 86400 (0.0003) [2023-03-11 11:33:12,811][04011] Fps is (10 sec: 12697.6, 60 sec: 12424.5, 300 sec: 12579.6). Total num frames: 44236800. Throughput: 0: 12548.0. Samples: 44236284. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-11 11:33:12,822][04011] Avg episode reward: [(0, '28.674')] [2023-03-11 11:33:15,959][04298] Updated weights for policy 0, policy_version 86480 (0.0005) [2023-03-11 11:33:17,811][04011] Fps is (10 sec: 12697.7, 60 sec: 12424.5, 300 sec: 12565.7). Total num frames: 44298240. Throughput: 0: 12547.5. Samples: 44273124. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-11 11:33:17,822][04011] Avg episode reward: [(0, '28.726')] [2023-03-11 11:33:19,179][04298] Updated weights for policy 0, policy_version 86560 (0.0005) [2023-03-11 11:33:22,278][04298] Updated weights for policy 0, policy_version 86640 (0.0004) [2023-03-11 11:33:22,811][04011] Fps is (10 sec: 12697.6, 60 sec: 12492.8, 300 sec: 12565.7). Total num frames: 44363776. Throughput: 0: 12610.1. Samples: 44350072. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-11 11:33:22,822][04011] Avg episode reward: [(0, '29.879')] [2023-03-11 11:33:22,825][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000086648_44363776.pth... [2023-03-11 11:33:22,827][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000085920_43991040.pth [2023-03-11 11:33:25,318][04298] Updated weights for policy 0, policy_version 86720 (0.0004) [2023-03-11 11:33:27,811][04011] Fps is (10 sec: 13516.8, 60 sec: 12697.6, 300 sec: 12593.5). Total num frames: 44433408. Throughput: 0: 12661.4. Samples: 44429804. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-11 11:33:27,811][04011] Avg episode reward: [(0, '27.521')] [2023-03-11 11:33:28,401][04298] Updated weights for policy 0, policy_version 86800 (0.0004) [2023-03-11 11:33:31,510][04298] Updated weights for policy 0, policy_version 86880 (0.0004) [2023-03-11 11:33:32,811][04011] Fps is (10 sec: 13516.8, 60 sec: 12765.9, 300 sec: 12607.3). Total num frames: 44498944. Throughput: 0: 12652.5. Samples: 44470120. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-11 11:33:32,811][04011] Avg episode reward: [(0, '30.564')] [2023-03-11 11:33:34,570][04298] Updated weights for policy 0, policy_version 86960 (0.0004) [2023-03-11 11:33:37,811][04011] Fps is (10 sec: 12697.6, 60 sec: 12697.6, 300 sec: 12593.5). Total num frames: 44560384. Throughput: 0: 12663.8. Samples: 44548160. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-11 11:33:37,811][04011] Avg episode reward: [(0, '30.158')] [2023-03-11 11:33:37,814][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000087032_44560384.pth... [2023-03-11 11:33:37,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000086272_44171264.pth [2023-03-11 11:33:37,962][04298] Updated weights for policy 0, policy_version 87040 (0.0005) [2023-03-11 11:33:41,413][04298] Updated weights for policy 0, policy_version 87120 (0.0006) [2023-03-11 11:33:42,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12629.3, 300 sec: 12579.6). Total num frames: 44617728. Throughput: 0: 12638.7. Samples: 44618712. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-11 11:33:42,812][04011] Avg episode reward: [(0, '31.233')] [2023-03-11 11:33:44,673][04298] Updated weights for policy 0, policy_version 87200 (0.0005) [2023-03-11 11:33:47,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12561.1, 300 sec: 12593.5). Total num frames: 44683264. Throughput: 0: 12717.9. Samples: 44658184. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-11 11:33:47,812][04011] Avg episode reward: [(0, '30.169')] [2023-03-11 11:33:47,835][04298] Updated weights for policy 0, policy_version 87280 (0.0003) [2023-03-11 11:33:50,996][04298] Updated weights for policy 0, policy_version 87360 (0.0003) [2023-03-11 11:33:52,811][04011] Fps is (10 sec: 13107.1, 60 sec: 12629.3, 300 sec: 12607.3). Total num frames: 44748800. Throughput: 0: 12823.9. Samples: 44736052. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-11 11:33:52,812][04011] Avg episode reward: [(0, '31.586')] [2023-03-11 11:33:52,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000087408_44752896.pth... [2023-03-11 11:33:52,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000086648_44363776.pth [2023-03-11 11:33:54,097][04298] Updated weights for policy 0, policy_version 87440 (0.0004) [2023-03-11 11:33:57,224][04298] Updated weights for policy 0, policy_version 87520 (0.0004) [2023-03-11 11:33:57,811][04011] Fps is (10 sec: 13107.2, 60 sec: 12697.6, 300 sec: 12621.2). Total num frames: 44814336. Throughput: 0: 12847.2. Samples: 44814408. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-11 11:33:57,812][04011] Avg episode reward: [(0, '30.833')] [2023-03-11 11:34:00,379][04298] Updated weights for policy 0, policy_version 87600 (0.0005) [2023-03-11 11:34:02,811][04011] Fps is (10 sec: 13107.2, 60 sec: 12834.1, 300 sec: 12635.1). Total num frames: 44879872. Throughput: 0: 12893.3. Samples: 44853324. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-11 11:34:02,811][04011] Avg episode reward: [(0, '30.956')] [2023-03-11 11:34:03,760][04298] Updated weights for policy 0, policy_version 87680 (0.0005) [2023-03-11 11:34:07,160][04298] Updated weights for policy 0, policy_version 87760 (0.0005) [2023-03-11 11:34:07,811][04011] Fps is (10 sec: 12287.9, 60 sec: 12765.9, 300 sec: 12621.2). Total num frames: 44937216. Throughput: 0: 12779.7. Samples: 44925160. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:34:07,812][04011] Avg episode reward: [(0, '32.227')] [2023-03-11 11:34:07,843][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000087776_44941312.pth... [2023-03-11 11:34:07,844][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000087032_44560384.pth [2023-03-11 11:34:10,577][04298] Updated weights for policy 0, policy_version 87840 (0.0005) [2023-03-11 11:34:12,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12697.6, 300 sec: 12607.3). Total num frames: 44998656. Throughput: 0: 12636.6. Samples: 44998452. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:34:12,811][04011] Avg episode reward: [(0, '32.145')] [2023-03-11 11:34:13,920][04298] Updated weights for policy 0, policy_version 87920 (0.0005) [2023-03-11 11:34:17,279][04298] Updated weights for policy 0, policy_version 88000 (0.0005) [2023-03-11 11:34:17,811][04011] Fps is (10 sec: 12288.1, 60 sec: 12697.6, 300 sec: 12593.5). Total num frames: 45060096. Throughput: 0: 12551.4. Samples: 45034932. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:34:17,811][04011] Avg episode reward: [(0, '32.317')] [2023-03-11 11:34:20,364][04298] Updated weights for policy 0, policy_version 88080 (0.0004) [2023-03-11 11:34:22,811][04011] Fps is (10 sec: 12697.6, 60 sec: 12697.6, 300 sec: 12593.5). Total num frames: 45125632. Throughput: 0: 12543.2. Samples: 45112604. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:34:22,812][04011] Avg episode reward: [(0, '31.600')] [2023-03-11 11:34:22,847][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000088144_45129728.pth... [2023-03-11 11:34:22,850][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000087408_44752896.pth [2023-03-11 11:34:23,492][04298] Updated weights for policy 0, policy_version 88160 (0.0003) [2023-03-11 11:34:26,746][04298] Updated weights for policy 0, policy_version 88240 (0.0004) [2023-03-11 11:34:27,811][04011] Fps is (10 sec: 12697.6, 60 sec: 12561.1, 300 sec: 12579.6). Total num frames: 45187072. Throughput: 0: 12645.9. Samples: 45187776. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:34:27,811][04011] Avg episode reward: [(0, '31.528')] [2023-03-11 11:34:30,228][04298] Updated weights for policy 0, policy_version 88320 (0.0005) [2023-03-11 11:34:32,811][04011] Fps is (10 sec: 12288.1, 60 sec: 12492.8, 300 sec: 12593.5). Total num frames: 45248512. Throughput: 0: 12572.4. Samples: 45223944. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:34:32,811][04011] Avg episode reward: [(0, '31.103')] [2023-03-11 11:34:33,802][04298] Updated weights for policy 0, policy_version 88400 (0.0005) [2023-03-11 11:34:37,319][04298] Updated weights for policy 0, policy_version 88480 (0.0005) [2023-03-11 11:34:37,811][04011] Fps is (10 sec: 11878.3, 60 sec: 12424.5, 300 sec: 12551.8). Total num frames: 45305856. Throughput: 0: 12389.2. Samples: 45293568. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:34:37,812][04011] Avg episode reward: [(0, '29.073')] [2023-03-11 11:34:37,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000088488_45305856.pth... [2023-03-11 11:34:37,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000087776_44941312.pth [2023-03-11 11:34:40,680][04298] Updated weights for policy 0, policy_version 88560 (0.0005) [2023-03-11 11:34:42,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12492.8, 300 sec: 12537.9). Total num frames: 45367296. Throughput: 0: 12210.8. Samples: 45363896. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:34:42,811][04011] Avg episode reward: [(0, '25.234')] [2023-03-11 11:34:44,184][04298] Updated weights for policy 0, policy_version 88640 (0.0005) [2023-03-11 11:34:47,512][04298] Updated weights for policy 0, policy_version 88720 (0.0005) [2023-03-11 11:34:47,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12356.3, 300 sec: 12510.2). Total num frames: 45424640. Throughput: 0: 12158.6. Samples: 45400460. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:34:47,812][04011] Avg episode reward: [(0, '30.410')] [2023-03-11 11:34:50,941][04298] Updated weights for policy 0, policy_version 88800 (0.0005) [2023-03-11 11:34:52,811][04011] Fps is (10 sec: 11878.3, 60 sec: 12288.0, 300 sec: 12496.3). Total num frames: 45486080. Throughput: 0: 12190.4. Samples: 45473728. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:34:52,812][04011] Avg episode reward: [(0, '30.158')] [2023-03-11 11:34:52,816][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000088840_45486080.pth... [2023-03-11 11:34:52,819][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000088144_45129728.pth [2023-03-11 11:34:54,300][04298] Updated weights for policy 0, policy_version 88880 (0.0005) [2023-03-11 11:34:57,702][04298] Updated weights for policy 0, policy_version 88960 (0.0005) [2023-03-11 11:34:57,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12219.7, 300 sec: 12482.4). Total num frames: 45547520. Throughput: 0: 12173.5. Samples: 45546260. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:34:57,812][04011] Avg episode reward: [(0, '30.228')] [2023-03-11 11:35:01,085][04298] Updated weights for policy 0, policy_version 89040 (0.0005) [2023-03-11 11:35:02,811][04011] Fps is (10 sec: 12288.1, 60 sec: 12151.5, 300 sec: 12496.3). Total num frames: 45608960. Throughput: 0: 12171.4. Samples: 45582644. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:35:02,812][04011] Avg episode reward: [(0, '30.305')] [2023-03-11 11:35:04,469][04298] Updated weights for policy 0, policy_version 89120 (0.0005) [2023-03-11 11:35:07,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12151.5, 300 sec: 12482.4). Total num frames: 45666304. Throughput: 0: 12031.6. Samples: 45654024. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:35:07,812][04011] Avg episode reward: [(0, '30.980')] [2023-03-11 11:35:07,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000089192_45666304.pth... [2023-03-11 11:35:07,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000088488_45305856.pth [2023-03-11 11:35:07,935][04298] Updated weights for policy 0, policy_version 89200 (0.0005) [2023-03-11 11:35:11,416][04298] Updated weights for policy 0, policy_version 89280 (0.0005) [2023-03-11 11:35:12,811][04011] Fps is (10 sec: 11468.8, 60 sec: 12083.2, 300 sec: 12454.6). Total num frames: 45723648. Throughput: 0: 11925.0. Samples: 45724400. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:35:12,812][04011] Avg episode reward: [(0, '31.133')] [2023-03-11 11:35:14,844][04298] Updated weights for policy 0, policy_version 89360 (0.0005) [2023-03-11 11:35:17,811][04011] Fps is (10 sec: 11878.5, 60 sec: 12083.2, 300 sec: 12426.8). Total num frames: 45785088. Throughput: 0: 11944.6. Samples: 45761452. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:35:17,812][04011] Avg episode reward: [(0, '32.144')] [2023-03-11 11:35:18,184][04298] Updated weights for policy 0, policy_version 89440 (0.0005) [2023-03-11 11:35:21,674][04298] Updated weights for policy 0, policy_version 89520 (0.0005) [2023-03-11 11:35:22,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12014.9, 300 sec: 12426.8). Total num frames: 45846528. Throughput: 0: 11992.7. Samples: 45833240. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:35:22,812][04011] Avg episode reward: [(0, '32.137')] [2023-03-11 11:35:22,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000089544_45846528.pth... [2023-03-11 11:35:22,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000088840_45486080.pth [2023-03-11 11:35:25,205][04298] Updated weights for policy 0, policy_version 89600 (0.0005) [2023-03-11 11:35:27,811][04011] Fps is (10 sec: 11878.4, 60 sec: 11946.7, 300 sec: 12413.0). Total num frames: 45903872. Throughput: 0: 11999.5. Samples: 45903872. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:35:27,812][04011] Avg episode reward: [(0, '30.756')] [2023-03-11 11:35:28,651][04298] Updated weights for policy 0, policy_version 89680 (0.0005) [2023-03-11 11:35:31,950][04298] Updated weights for policy 0, policy_version 89760 (0.0005) [2023-03-11 11:35:32,811][04011] Fps is (10 sec: 11878.4, 60 sec: 11946.7, 300 sec: 12426.8). Total num frames: 45965312. Throughput: 0: 11980.4. Samples: 45939576. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:35:32,811][04011] Avg episode reward: [(0, '32.027')] [2023-03-11 11:35:35,161][04298] Updated weights for policy 0, policy_version 89840 (0.0004) [2023-03-11 11:35:37,811][04011] Fps is (10 sec: 12697.6, 60 sec: 12083.2, 300 sec: 12440.7). Total num frames: 46030848. Throughput: 0: 12046.4. Samples: 46015816. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:35:37,812][04011] Avg episode reward: [(0, '29.593')] [2023-03-11 11:35:37,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000089904_46030848.pth... [2023-03-11 11:35:37,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000089192_45666304.pth [2023-03-11 11:35:38,323][04298] Updated weights for policy 0, policy_version 89920 (0.0004) [2023-03-11 11:35:41,381][04298] Updated weights for policy 0, policy_version 90000 (0.0004) [2023-03-11 11:35:42,811][04011] Fps is (10 sec: 13107.2, 60 sec: 12151.5, 300 sec: 12454.6). Total num frames: 46096384. Throughput: 0: 12215.2. Samples: 46095944. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:35:42,811][04011] Avg episode reward: [(0, '31.982')] [2023-03-11 11:35:44,441][04298] Updated weights for policy 0, policy_version 90080 (0.0004) [2023-03-11 11:35:47,521][04298] Updated weights for policy 0, policy_version 90160 (0.0004) [2023-03-11 11:35:47,811][04011] Fps is (10 sec: 13107.2, 60 sec: 12288.0, 300 sec: 12482.4). Total num frames: 46161920. Throughput: 0: 12304.0. Samples: 46136324. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:35:47,811][04011] Avg episode reward: [(0, '31.887')] [2023-03-11 11:35:50,606][04298] Updated weights for policy 0, policy_version 90240 (0.0004) [2023-03-11 11:35:52,811][04011] Fps is (10 sec: 13516.8, 60 sec: 12424.6, 300 sec: 12510.2). Total num frames: 46231552. Throughput: 0: 12473.4. Samples: 46215328. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-11 11:35:52,811][04011] Avg episode reward: [(0, '31.873')] [2023-03-11 11:35:52,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000090296_46231552.pth... [2023-03-11 11:35:52,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000089544_45846528.pth [2023-03-11 11:35:53,688][04298] Updated weights for policy 0, policy_version 90320 (0.0004) [2023-03-11 11:35:56,830][04298] Updated weights for policy 0, policy_version 90400 (0.0004) [2023-03-11 11:35:57,811][04011] Fps is (10 sec: 13516.8, 60 sec: 12492.8, 300 sec: 12524.0). Total num frames: 46297088. Throughput: 0: 12669.6. Samples: 46294532. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-11 11:35:57,811][04011] Avg episode reward: [(0, '32.150')] [2023-03-11 11:36:00,033][04298] Updated weights for policy 0, policy_version 90480 (0.0004) [2023-03-11 11:36:02,811][04011] Fps is (10 sec: 12697.6, 60 sec: 12492.8, 300 sec: 12537.9). Total num frames: 46358528. Throughput: 0: 12686.4. Samples: 46332340. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-11 11:36:02,811][04011] Avg episode reward: [(0, '31.523')] [2023-03-11 11:36:03,465][04298] Updated weights for policy 0, policy_version 90560 (0.0005) [2023-03-11 11:36:06,696][04298] Updated weights for policy 0, policy_version 90640 (0.0004) [2023-03-11 11:36:07,811][04011] Fps is (10 sec: 12287.9, 60 sec: 12561.1, 300 sec: 12537.9). Total num frames: 46419968. Throughput: 0: 12730.9. Samples: 46406132. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-11 11:36:07,812][04011] Avg episode reward: [(0, '29.569')] [2023-03-11 11:36:07,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000090664_46419968.pth... [2023-03-11 11:36:07,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000089904_46030848.pth [2023-03-11 11:36:09,914][04298] Updated weights for policy 0, policy_version 90720 (0.0004) [2023-03-11 11:36:12,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12629.3, 300 sec: 12537.9). Total num frames: 46481408. Throughput: 0: 12840.7. Samples: 46481704. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-11 11:36:12,811][04011] Avg episode reward: [(0, '28.530')] [2023-03-11 11:36:13,145][04298] Updated weights for policy 0, policy_version 90800 (0.0004) [2023-03-11 11:36:16,212][04298] Updated weights for policy 0, policy_version 90880 (0.0004) [2023-03-11 11:36:17,811][04011] Fps is (10 sec: 12697.7, 60 sec: 12697.6, 300 sec: 12537.9). Total num frames: 46546944. Throughput: 0: 12948.7. Samples: 46522268. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-11 11:36:17,811][04011] Avg episode reward: [(0, '30.483')] [2023-03-11 11:36:19,362][04298] Updated weights for policy 0, policy_version 90960 (0.0004) [2023-03-11 11:36:22,389][04298] Updated weights for policy 0, policy_version 91040 (0.0004) [2023-03-11 11:36:22,811][04011] Fps is (10 sec: 13516.7, 60 sec: 12834.1, 300 sec: 12551.8). Total num frames: 46616576. Throughput: 0: 12995.1. Samples: 46600596. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-11 11:36:22,812][04011] Avg episode reward: [(0, '30.546')] [2023-03-11 11:36:22,814][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000091048_46616576.pth... [2023-03-11 11:36:22,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000090296_46231552.pth [2023-03-11 11:36:25,529][04298] Updated weights for policy 0, policy_version 91120 (0.0004) [2023-03-11 11:36:27,811][04011] Fps is (10 sec: 13107.2, 60 sec: 12902.4, 300 sec: 12537.9). Total num frames: 46678016. Throughput: 0: 12944.0. Samples: 46678424. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-11 11:36:27,811][04011] Avg episode reward: [(0, '29.968')] [2023-03-11 11:36:28,733][04298] Updated weights for policy 0, policy_version 91200 (0.0004) [2023-03-11 11:36:31,847][04298] Updated weights for policy 0, policy_version 91280 (0.0004) [2023-03-11 11:36:32,811][04011] Fps is (10 sec: 13107.3, 60 sec: 13038.9, 300 sec: 12551.8). Total num frames: 46747648. Throughput: 0: 12929.4. Samples: 46718148. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-11 11:36:32,811][04011] Avg episode reward: [(0, '31.959')] [2023-03-11 11:36:35,054][04298] Updated weights for policy 0, policy_version 91360 (0.0004) [2023-03-11 11:36:37,811][04011] Fps is (10 sec: 13107.1, 60 sec: 12970.7, 300 sec: 12524.0). Total num frames: 46809088. Throughput: 0: 12899.2. Samples: 46795792. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-11 11:36:37,812][04011] Avg episode reward: [(0, '31.520')] [2023-03-11 11:36:37,814][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000091424_46809088.pth... [2023-03-11 11:36:37,816][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000090664_46419968.pth [2023-03-11 11:36:38,194][04298] Updated weights for policy 0, policy_version 91440 (0.0004) [2023-03-11 11:36:41,263][04298] Updated weights for policy 0, policy_version 91520 (0.0004) [2023-03-11 11:36:42,811][04011] Fps is (10 sec: 13107.1, 60 sec: 13038.9, 300 sec: 12537.9). Total num frames: 46878720. Throughput: 0: 12905.9. Samples: 46875296. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-11 11:36:42,811][04011] Avg episode reward: [(0, '32.081')] [2023-03-11 11:36:44,280][04298] Updated weights for policy 0, policy_version 91600 (0.0003) [2023-03-11 11:36:47,421][04298] Updated weights for policy 0, policy_version 91680 (0.0005) [2023-03-11 11:36:47,811][04011] Fps is (10 sec: 13516.9, 60 sec: 13038.9, 300 sec: 12537.9). Total num frames: 46944256. Throughput: 0: 12962.6. Samples: 46915656. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-11 11:36:47,811][04011] Avg episode reward: [(0, '32.359')] [2023-03-11 11:36:50,490][04298] Updated weights for policy 0, policy_version 91760 (0.0004) [2023-03-11 11:36:52,811][04011] Fps is (10 sec: 13107.1, 60 sec: 12970.7, 300 sec: 12565.7). Total num frames: 47009792. Throughput: 0: 13090.1. Samples: 46995188. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-11 11:36:52,812][04011] Avg episode reward: [(0, '32.067')] [2023-03-11 11:36:52,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000091816_47009792.pth... [2023-03-11 11:36:52,816][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000091048_46616576.pth [2023-03-11 11:36:53,648][04298] Updated weights for policy 0, policy_version 91840 (0.0004) [2023-03-11 11:36:56,999][04298] Updated weights for policy 0, policy_version 91920 (0.0005) [2023-03-11 11:36:57,811][04011] Fps is (10 sec: 12697.6, 60 sec: 12902.4, 300 sec: 12551.8). Total num frames: 47071232. Throughput: 0: 13089.0. Samples: 47070708. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-11 11:36:57,812][04011] Avg episode reward: [(0, '32.215')] [2023-03-11 11:37:00,319][04298] Updated weights for policy 0, policy_version 92000 (0.0005) [2023-03-11 11:37:02,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12902.4, 300 sec: 12537.9). Total num frames: 47132672. Throughput: 0: 13002.4. Samples: 47107376. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-11 11:37:02,812][04011] Avg episode reward: [(0, '31.593')] [2023-03-11 11:37:03,604][04298] Updated weights for policy 0, policy_version 92080 (0.0005) [2023-03-11 11:37:07,052][04298] Updated weights for policy 0, policy_version 92160 (0.0005) [2023-03-11 11:37:07,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12902.4, 300 sec: 12551.8). Total num frames: 47194112. Throughput: 0: 12877.0. Samples: 47180060. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-11 11:37:07,811][04011] Avg episode reward: [(0, '32.128')] [2023-03-11 11:37:07,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000092176_47194112.pth... [2023-03-11 11:37:07,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000091424_46809088.pth [2023-03-11 11:37:10,372][04298] Updated weights for policy 0, policy_version 92240 (0.0005) [2023-03-11 11:37:12,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12902.4, 300 sec: 12551.8). Total num frames: 47255552. Throughput: 0: 12778.8. Samples: 47253472. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-11 11:37:12,812][04011] Avg episode reward: [(0, '31.994')] [2023-03-11 11:37:13,710][04298] Updated weights for policy 0, policy_version 92320 (0.0005) [2023-03-11 11:37:17,041][04298] Updated weights for policy 0, policy_version 92400 (0.0005) [2023-03-11 11:37:17,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12834.1, 300 sec: 12551.8). Total num frames: 47316992. Throughput: 0: 12717.5. Samples: 47290436. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-11 11:37:17,812][04011] Avg episode reward: [(0, '32.292')] [2023-03-11 11:37:20,284][04298] Updated weights for policy 0, policy_version 92480 (0.0004) [2023-03-11 11:37:22,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12697.6, 300 sec: 12565.7). Total num frames: 47378432. Throughput: 0: 12670.8. Samples: 47365976. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-11 11:37:22,811][04011] Avg episode reward: [(0, '28.788')] [2023-03-11 11:37:22,814][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000092536_47378432.pth... [2023-03-11 11:37:22,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000091816_47009792.pth [2023-03-11 11:37:23,697][04298] Updated weights for policy 0, policy_version 92560 (0.0005) [2023-03-11 11:37:27,171][04298] Updated weights for policy 0, policy_version 92640 (0.0005) [2023-03-11 11:37:27,811][04011] Fps is (10 sec: 11878.5, 60 sec: 12629.4, 300 sec: 12551.8). Total num frames: 47435776. Throughput: 0: 12461.0. Samples: 47436040. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-11 11:37:27,811][04011] Avg episode reward: [(0, '29.384')] [2023-03-11 11:37:30,451][04298] Updated weights for policy 0, policy_version 92720 (0.0005) [2023-03-11 11:37:32,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12492.8, 300 sec: 12537.9). Total num frames: 47497216. Throughput: 0: 12402.9. Samples: 47473784. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-11 11:37:32,811][04011] Avg episode reward: [(0, '31.812')] [2023-03-11 11:37:33,897][04298] Updated weights for policy 0, policy_version 92800 (0.0005) [2023-03-11 11:37:37,362][04298] Updated weights for policy 0, policy_version 92880 (0.0005) [2023-03-11 11:37:37,811][04011] Fps is (10 sec: 12287.9, 60 sec: 12492.8, 300 sec: 12537.9). Total num frames: 47558656. Throughput: 0: 12235.9. Samples: 47545804. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-11 11:37:37,811][04011] Avg episode reward: [(0, '30.958')] [2023-03-11 11:37:37,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000092888_47558656.pth... [2023-03-11 11:37:37,816][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000092176_47194112.pth [2023-03-11 11:37:40,804][04298] Updated weights for policy 0, policy_version 92960 (0.0005) [2023-03-11 11:37:42,811][04011] Fps is (10 sec: 11878.5, 60 sec: 12288.0, 300 sec: 12496.3). Total num frames: 47616000. Throughput: 0: 12135.8. Samples: 47616820. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-11 11:37:42,811][04011] Avg episode reward: [(0, '30.459')] [2023-03-11 11:37:44,134][04298] Updated weights for policy 0, policy_version 93040 (0.0005) [2023-03-11 11:37:47,282][04298] Updated weights for policy 0, policy_version 93120 (0.0003) [2023-03-11 11:37:47,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12288.0, 300 sec: 12510.2). Total num frames: 47681536. Throughput: 0: 12154.5. Samples: 47654328. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:37:47,811][04011] Avg episode reward: [(0, '28.346')] [2023-03-11 11:37:50,434][04298] Updated weights for policy 0, policy_version 93200 (0.0003) [2023-03-11 11:37:52,811][04011] Fps is (10 sec: 13107.0, 60 sec: 12288.0, 300 sec: 12524.0). Total num frames: 47747072. Throughput: 0: 12283.5. Samples: 47732820. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:37:52,812][04011] Avg episode reward: [(0, '31.613')] [2023-03-11 11:37:52,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000093256_47747072.pth... [2023-03-11 11:37:52,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000092536_47378432.pth [2023-03-11 11:37:53,609][04298] Updated weights for policy 0, policy_version 93280 (0.0003) [2023-03-11 11:37:56,814][04298] Updated weights for policy 0, policy_version 93360 (0.0003) [2023-03-11 11:37:57,811][04011] Fps is (10 sec: 13107.2, 60 sec: 12356.3, 300 sec: 12551.8). Total num frames: 47812608. Throughput: 0: 12350.2. Samples: 47809232. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:37:57,811][04011] Avg episode reward: [(0, '29.842')] [2023-03-11 11:38:00,052][04298] Updated weights for policy 0, policy_version 93440 (0.0004) [2023-03-11 11:38:02,811][04011] Fps is (10 sec: 12697.7, 60 sec: 12356.3, 300 sec: 12551.8). Total num frames: 47874048. Throughput: 0: 12380.9. Samples: 47847576. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:38:02,811][04011] Avg episode reward: [(0, '30.562')] [2023-03-11 11:38:03,203][04298] Updated weights for policy 0, policy_version 93520 (0.0003) [2023-03-11 11:38:06,537][04298] Updated weights for policy 0, policy_version 93600 (0.0005) [2023-03-11 11:38:07,811][04011] Fps is (10 sec: 12287.9, 60 sec: 12356.3, 300 sec: 12537.9). Total num frames: 47935488. Throughput: 0: 12384.2. Samples: 47923264. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:38:07,812][04011] Avg episode reward: [(0, '31.143')] [2023-03-11 11:38:07,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000093624_47935488.pth... [2023-03-11 11:38:07,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000092888_47558656.pth [2023-03-11 11:38:10,150][04298] Updated weights for policy 0, policy_version 93680 (0.0005) [2023-03-11 11:38:12,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12288.0, 300 sec: 12524.0). Total num frames: 47992832. Throughput: 0: 12373.3. Samples: 47992840. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:38:12,811][04011] Avg episode reward: [(0, '30.092')] [2023-03-11 11:38:13,635][04298] Updated weights for policy 0, policy_version 93760 (0.0005) [2023-03-11 11:38:16,959][04298] Updated weights for policy 0, policy_version 93840 (0.0005) [2023-03-11 11:38:17,811][04011] Fps is (10 sec: 11878.5, 60 sec: 12288.0, 300 sec: 12510.2). Total num frames: 48054272. Throughput: 0: 12344.7. Samples: 48029296. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:38:17,811][04011] Avg episode reward: [(0, '32.448')] [2023-03-11 11:38:20,394][04298] Updated weights for policy 0, policy_version 93920 (0.0005) [2023-03-11 11:38:22,811][04011] Fps is (10 sec: 11878.5, 60 sec: 12219.7, 300 sec: 12468.5). Total num frames: 48111616. Throughput: 0: 12330.0. Samples: 48100652. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:38:22,811][04011] Avg episode reward: [(0, '32.050')] [2023-03-11 11:38:22,840][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000093976_48115712.pth... [2023-03-11 11:38:22,843][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000093256_47747072.pth [2023-03-11 11:38:23,846][04298] Updated weights for policy 0, policy_version 94000 (0.0005) [2023-03-11 11:38:27,235][04298] Updated weights for policy 0, policy_version 94080 (0.0004) [2023-03-11 11:38:27,811][04011] Fps is (10 sec: 11878.5, 60 sec: 12288.0, 300 sec: 12454.6). Total num frames: 48173056. Throughput: 0: 12362.2. Samples: 48173120. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:38:27,811][04011] Avg episode reward: [(0, '32.129')] [2023-03-11 11:38:30,601][04298] Updated weights for policy 0, policy_version 94160 (0.0005) [2023-03-11 11:38:32,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12288.0, 300 sec: 12454.6). Total num frames: 48234496. Throughput: 0: 12345.8. Samples: 48209888. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:38:32,811][04011] Avg episode reward: [(0, '32.463')] [2023-03-11 11:38:34,058][04298] Updated weights for policy 0, policy_version 94240 (0.0005) [2023-03-11 11:38:37,462][04298] Updated weights for policy 0, policy_version 94320 (0.0005) [2023-03-11 11:38:37,811][04011] Fps is (10 sec: 11878.3, 60 sec: 12219.7, 300 sec: 12454.6). Total num frames: 48291840. Throughput: 0: 12183.8. Samples: 48281092. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:38:37,812][04011] Avg episode reward: [(0, '32.013')] [2023-03-11 11:38:37,824][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000094328_48295936.pth... [2023-03-11 11:38:37,826][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000093624_47935488.pth [2023-03-11 11:38:40,900][04298] Updated weights for policy 0, policy_version 94400 (0.0005) [2023-03-11 11:38:42,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12288.0, 300 sec: 12440.7). Total num frames: 48353280. Throughput: 0: 12090.2. Samples: 48353288. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 11:38:42,811][04011] Avg episode reward: [(0, '32.339')] [2023-03-11 11:38:44,257][04298] Updated weights for policy 0, policy_version 94480 (0.0005) [2023-03-11 11:38:47,749][04298] Updated weights for policy 0, policy_version 94560 (0.0004) [2023-03-11 11:38:47,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12219.7, 300 sec: 12426.8). Total num frames: 48414720. Throughput: 0: 12041.2. Samples: 48389428. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 11:38:47,811][04011] Avg episode reward: [(0, '32.090')] [2023-03-11 11:38:51,081][04298] Updated weights for policy 0, policy_version 94640 (0.0005) [2023-03-11 11:38:52,811][04011] Fps is (10 sec: 12287.9, 60 sec: 12151.5, 300 sec: 12413.0). Total num frames: 48476160. Throughput: 0: 11962.6. Samples: 48461580. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 11:38:52,812][04011] Avg episode reward: [(0, '31.958')] [2023-03-11 11:38:52,814][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000094680_48476160.pth... [2023-03-11 11:38:52,816][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000093976_48115712.pth [2023-03-11 11:38:54,470][04298] Updated weights for policy 0, policy_version 94720 (0.0005) [2023-03-11 11:38:57,798][04298] Updated weights for policy 0, policy_version 94800 (0.0005) [2023-03-11 11:38:57,811][04011] Fps is (10 sec: 12288.1, 60 sec: 12083.2, 300 sec: 12399.1). Total num frames: 48537600. Throughput: 0: 12037.0. Samples: 48534504. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 11:38:57,811][04011] Avg episode reward: [(0, '30.837')] [2023-03-11 11:39:01,136][04298] Updated weights for policy 0, policy_version 94880 (0.0005) [2023-03-11 11:39:02,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12014.9, 300 sec: 12399.1). Total num frames: 48594944. Throughput: 0: 12037.3. Samples: 48570976. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 11:39:02,811][04011] Avg episode reward: [(0, '30.259')] [2023-03-11 11:39:04,462][04298] Updated weights for policy 0, policy_version 94960 (0.0004) [2023-03-11 11:39:07,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12015.0, 300 sec: 12399.1). Total num frames: 48656384. Throughput: 0: 12104.2. Samples: 48645340. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 11:39:07,811][04011] Avg episode reward: [(0, '29.034')] [2023-03-11 11:39:07,816][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000095040_48660480.pth... [2023-03-11 11:39:07,816][04298] Updated weights for policy 0, policy_version 95040 (0.0005) [2023-03-11 11:39:07,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000094328_48295936.pth [2023-03-11 11:39:11,178][04298] Updated weights for policy 0, policy_version 95120 (0.0005) [2023-03-11 11:39:12,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12083.2, 300 sec: 12399.1). Total num frames: 48717824. Throughput: 0: 12105.9. Samples: 48717888. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 11:39:12,811][04011] Avg episode reward: [(0, '30.302')] [2023-03-11 11:39:14,602][04298] Updated weights for policy 0, policy_version 95200 (0.0004) [2023-03-11 11:39:17,811][04011] Fps is (10 sec: 12287.9, 60 sec: 12083.2, 300 sec: 12385.2). Total num frames: 48779264. Throughput: 0: 12082.7. Samples: 48753608. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 11:39:17,811][04011] Avg episode reward: [(0, '30.940')] [2023-03-11 11:39:17,981][04298] Updated weights for policy 0, policy_version 95280 (0.0005) [2023-03-11 11:39:21,443][04298] Updated weights for policy 0, policy_version 95360 (0.0005) [2023-03-11 11:39:22,811][04011] Fps is (10 sec: 11878.5, 60 sec: 12083.2, 300 sec: 12371.3). Total num frames: 48836608. Throughput: 0: 12100.4. Samples: 48825608. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 11:39:22,811][04011] Avg episode reward: [(0, '31.520')] [2023-03-11 11:39:22,835][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000095392_48840704.pth... [2023-03-11 11:39:22,837][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000094680_48476160.pth [2023-03-11 11:39:24,852][04298] Updated weights for policy 0, policy_version 95440 (0.0005) [2023-03-11 11:39:27,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12083.2, 300 sec: 12371.3). Total num frames: 48898048. Throughput: 0: 12105.8. Samples: 48898048. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 11:39:27,811][04011] Avg episode reward: [(0, '29.606')] [2023-03-11 11:39:28,305][04298] Updated weights for policy 0, policy_version 95520 (0.0005) [2023-03-11 11:39:31,745][04298] Updated weights for policy 0, policy_version 95600 (0.0005) [2023-03-11 11:39:32,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12083.2, 300 sec: 12385.2). Total num frames: 48959488. Throughput: 0: 12076.7. Samples: 48932880. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 11:39:32,811][04011] Avg episode reward: [(0, '30.803')] [2023-03-11 11:39:35,214][04298] Updated weights for policy 0, policy_version 95680 (0.0005) [2023-03-11 11:39:37,811][04011] Fps is (10 sec: 11878.5, 60 sec: 12083.2, 300 sec: 12371.3). Total num frames: 49016832. Throughput: 0: 12067.3. Samples: 49004608. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 11:39:37,811][04011] Avg episode reward: [(0, '30.915')] [2023-03-11 11:39:37,820][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000095744_49020928.pth... [2023-03-11 11:39:37,821][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000095040_48660480.pth [2023-03-11 11:39:38,496][04298] Updated weights for policy 0, policy_version 95760 (0.0005) [2023-03-11 11:39:41,888][04298] Updated weights for policy 0, policy_version 95840 (0.0005) [2023-03-11 11:39:42,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12083.2, 300 sec: 12385.2). Total num frames: 49078272. Throughput: 0: 12083.5. Samples: 49078260. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-11 11:39:42,811][04011] Avg episode reward: [(0, '31.359')] [2023-03-11 11:39:45,365][04298] Updated weights for policy 0, policy_version 95920 (0.0005) [2023-03-11 11:39:47,811][04011] Fps is (10 sec: 12287.9, 60 sec: 12083.2, 300 sec: 12385.2). Total num frames: 49139712. Throughput: 0: 12054.3. Samples: 49113420. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-11 11:39:47,811][04011] Avg episode reward: [(0, '31.057')] [2023-03-11 11:39:48,721][04298] Updated weights for policy 0, policy_version 96000 (0.0005) [2023-03-11 11:39:52,043][04298] Updated weights for policy 0, policy_version 96080 (0.0004) [2023-03-11 11:39:52,811][04011] Fps is (10 sec: 12287.9, 60 sec: 12083.2, 300 sec: 12385.2). Total num frames: 49201152. Throughput: 0: 12035.3. Samples: 49186932. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-11 11:39:52,812][04011] Avg episode reward: [(0, '31.653')] [2023-03-11 11:39:52,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000096096_49201152.pth... [2023-03-11 11:39:52,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000095392_48840704.pth [2023-03-11 11:39:55,416][04298] Updated weights for policy 0, policy_version 96160 (0.0005) [2023-03-11 11:39:57,811][04011] Fps is (10 sec: 11878.5, 60 sec: 12014.9, 300 sec: 12371.3). Total num frames: 49258496. Throughput: 0: 12015.1. Samples: 49258568. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-11 11:39:57,811][04011] Avg episode reward: [(0, '30.574')] [2023-03-11 11:39:58,934][04298] Updated weights for policy 0, policy_version 96240 (0.0005) [2023-03-11 11:40:02,400][04298] Updated weights for policy 0, policy_version 96320 (0.0005) [2023-03-11 11:40:02,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12083.2, 300 sec: 12385.2). Total num frames: 49319936. Throughput: 0: 12033.5. Samples: 49295116. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-11 11:40:02,812][04011] Avg episode reward: [(0, '31.993')] [2023-03-11 11:40:05,780][04298] Updated weights for policy 0, policy_version 96400 (0.0005) [2023-03-11 11:40:07,811][04011] Fps is (10 sec: 11878.3, 60 sec: 12014.9, 300 sec: 12385.2). Total num frames: 49377280. Throughput: 0: 12002.6. Samples: 49365728. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-11 11:40:07,812][04011] Avg episode reward: [(0, '31.747')] [2023-03-11 11:40:07,831][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000096448_49381376.pth... [2023-03-11 11:40:07,832][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000095744_49020928.pth [2023-03-11 11:40:09,244][04298] Updated weights for policy 0, policy_version 96480 (0.0005) [2023-03-11 11:40:12,759][04298] Updated weights for policy 0, policy_version 96560 (0.0005) [2023-03-11 11:40:12,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12014.9, 300 sec: 12385.2). Total num frames: 49438720. Throughput: 0: 11952.9. Samples: 49435928. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-11 11:40:12,812][04011] Avg episode reward: [(0, '29.943')] [2023-03-11 11:40:16,188][04298] Updated weights for policy 0, policy_version 96640 (0.0005) [2023-03-11 11:40:17,811][04011] Fps is (10 sec: 11878.5, 60 sec: 11946.7, 300 sec: 12371.3). Total num frames: 49496064. Throughput: 0: 11984.1. Samples: 49472164. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-11 11:40:17,812][04011] Avg episode reward: [(0, '32.409')] [2023-03-11 11:40:19,561][04298] Updated weights for policy 0, policy_version 96720 (0.0005) [2023-03-11 11:40:22,811][04011] Fps is (10 sec: 11878.3, 60 sec: 12014.9, 300 sec: 12385.2). Total num frames: 49557504. Throughput: 0: 12011.8. Samples: 49545140. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-11 11:40:22,812][04011] Avg episode reward: [(0, '31.497')] [2023-03-11 11:40:22,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000096792_49557504.pth... [2023-03-11 11:40:22,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000096096_49201152.pth [2023-03-11 11:40:22,968][04298] Updated weights for policy 0, policy_version 96800 (0.0005) [2023-03-11 11:40:26,473][04298] Updated weights for policy 0, policy_version 96880 (0.0005) [2023-03-11 11:40:27,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12014.9, 300 sec: 12385.2). Total num frames: 49618944. Throughput: 0: 11953.9. Samples: 49616188. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-11 11:40:27,812][04011] Avg episode reward: [(0, '31.491')] [2023-03-11 11:40:29,742][04298] Updated weights for policy 0, policy_version 96960 (0.0005) [2023-03-11 11:40:32,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12014.9, 300 sec: 12371.3). Total num frames: 49680384. Throughput: 0: 12016.4. Samples: 49654156. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-11 11:40:32,812][04011] Avg episode reward: [(0, '31.694')] [2023-03-11 11:40:33,116][04298] Updated weights for policy 0, policy_version 97040 (0.0005) [2023-03-11 11:40:36,487][04298] Updated weights for policy 0, policy_version 97120 (0.0005) [2023-03-11 11:40:37,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12014.9, 300 sec: 12343.5). Total num frames: 49737728. Throughput: 0: 11974.5. Samples: 49725784. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:40:37,811][04011] Avg episode reward: [(0, '31.550')] [2023-03-11 11:40:37,814][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000097152_49741824.pth... [2023-03-11 11:40:37,815][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000096448_49381376.pth [2023-03-11 11:40:39,793][04298] Updated weights for policy 0, policy_version 97200 (0.0005) [2023-03-11 11:40:42,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12014.9, 300 sec: 12329.7). Total num frames: 49799168. Throughput: 0: 12014.9. Samples: 49799240. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:40:42,812][04011] Avg episode reward: [(0, '32.263')] [2023-03-11 11:40:43,205][04298] Updated weights for policy 0, policy_version 97280 (0.0005) [2023-03-11 11:40:46,555][04298] Updated weights for policy 0, policy_version 97360 (0.0005) [2023-03-11 11:40:47,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12014.9, 300 sec: 12301.9). Total num frames: 49860608. Throughput: 0: 12021.8. Samples: 49836096. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:40:47,812][04011] Avg episode reward: [(0, '32.349')] [2023-03-11 11:40:49,993][04298] Updated weights for policy 0, policy_version 97440 (0.0005) [2023-03-11 11:40:52,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12014.9, 300 sec: 12288.0). Total num frames: 49922048. Throughput: 0: 12064.4. Samples: 49908628. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:40:52,812][04011] Avg episode reward: [(0, '32.441')] [2023-03-11 11:40:52,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000097504_49922048.pth... [2023-03-11 11:40:52,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000096792_49557504.pth [2023-03-11 11:40:53,352][04298] Updated weights for policy 0, policy_version 97520 (0.0005) [2023-03-11 11:40:56,682][04298] Updated weights for policy 0, policy_version 97600 (0.0005) [2023-03-11 11:40:57,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12083.2, 300 sec: 12288.0). Total num frames: 49983488. Throughput: 0: 12128.0. Samples: 49981688. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:40:57,812][04011] Avg episode reward: [(0, '32.207')] [2023-03-11 11:40:59,953][04298] Updated weights for policy 0, policy_version 97680 (0.0004) [2023-03-11 11:41:02,811][04011] Fps is (10 sec: 12288.1, 60 sec: 12083.2, 300 sec: 12288.0). Total num frames: 50044928. Throughput: 0: 12178.9. Samples: 50020216. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:41:02,812][04011] Avg episode reward: [(0, '32.417')] [2023-03-11 11:41:03,294][04298] Updated weights for policy 0, policy_version 97760 (0.0004) [2023-03-11 11:41:06,724][04298] Updated weights for policy 0, policy_version 97840 (0.0005) [2023-03-11 11:41:07,811][04011] Fps is (10 sec: 12287.9, 60 sec: 12151.5, 300 sec: 12288.0). Total num frames: 50106368. Throughput: 0: 12143.4. Samples: 50091592. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:41:07,812][04011] Avg episode reward: [(0, '32.570')] [2023-03-11 11:41:07,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000097864_50106368.pth... [2023-03-11 11:41:07,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000097152_49741824.pth [2023-03-11 11:41:10,132][04298] Updated weights for policy 0, policy_version 97920 (0.0004) [2023-03-11 11:41:12,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12151.5, 300 sec: 12274.1). Total num frames: 50167808. Throughput: 0: 12183.6. Samples: 50164452. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:41:12,812][04011] Avg episode reward: [(0, '32.431')] [2023-03-11 11:41:13,453][04298] Updated weights for policy 0, policy_version 98000 (0.0005) [2023-03-11 11:41:16,844][04298] Updated weights for policy 0, policy_version 98080 (0.0005) [2023-03-11 11:41:17,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12151.5, 300 sec: 12232.5). Total num frames: 50225152. Throughput: 0: 12144.3. Samples: 50200648. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:41:17,812][04011] Avg episode reward: [(0, '33.371')] [2023-03-11 11:41:17,812][04254] Saving new best policy, reward=33.371! [2023-03-11 11:41:20,252][04298] Updated weights for policy 0, policy_version 98160 (0.0004) [2023-03-11 11:41:22,811][04011] Fps is (10 sec: 11878.3, 60 sec: 12151.5, 300 sec: 12232.5). Total num frames: 50286592. Throughput: 0: 12189.5. Samples: 50274312. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:41:22,812][04011] Avg episode reward: [(0, '32.520')] [2023-03-11 11:41:22,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000098216_50286592.pth... [2023-03-11 11:41:22,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000097504_49922048.pth [2023-03-11 11:41:23,685][04298] Updated weights for policy 0, policy_version 98240 (0.0005) [2023-03-11 11:41:27,081][04298] Updated weights for policy 0, policy_version 98320 (0.0005) [2023-03-11 11:41:27,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12151.5, 300 sec: 12204.7). Total num frames: 50348032. Throughput: 0: 12144.8. Samples: 50345756. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:41:27,812][04011] Avg episode reward: [(0, '33.116')] [2023-03-11 11:41:30,484][04298] Updated weights for policy 0, policy_version 98400 (0.0005) [2023-03-11 11:41:32,811][04011] Fps is (10 sec: 12288.1, 60 sec: 12151.5, 300 sec: 12204.7). Total num frames: 50409472. Throughput: 0: 12117.6. Samples: 50381388. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:41:32,812][04011] Avg episode reward: [(0, '32.272')] [2023-03-11 11:41:33,807][04298] Updated weights for policy 0, policy_version 98480 (0.0005) [2023-03-11 11:41:37,253][04298] Updated weights for policy 0, policy_version 98560 (0.0005) [2023-03-11 11:41:37,811][04011] Fps is (10 sec: 11878.3, 60 sec: 12151.5, 300 sec: 12163.0). Total num frames: 50466816. Throughput: 0: 12131.3. Samples: 50454536. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:41:37,812][04011] Avg episode reward: [(0, '31.528')] [2023-03-11 11:41:37,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000098568_50466816.pth... [2023-03-11 11:41:37,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000097864_50106368.pth [2023-03-11 11:41:40,703][04298] Updated weights for policy 0, policy_version 98640 (0.0005) [2023-03-11 11:41:42,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12151.5, 300 sec: 12149.2). Total num frames: 50528256. Throughput: 0: 12089.5. Samples: 50525716. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:41:42,822][04011] Avg episode reward: [(0, '30.469')] [2023-03-11 11:41:44,132][04298] Updated weights for policy 0, policy_version 98720 (0.0005) [2023-03-11 11:41:47,577][04298] Updated weights for policy 0, policy_version 98800 (0.0005) [2023-03-11 11:41:47,811][04011] Fps is (10 sec: 11878.5, 60 sec: 12083.2, 300 sec: 12121.4). Total num frames: 50585600. Throughput: 0: 12019.4. Samples: 50561088. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:41:47,822][04011] Avg episode reward: [(0, '24.266')] [2023-03-11 11:41:50,997][04298] Updated weights for policy 0, policy_version 98880 (0.0005) [2023-03-11 11:41:52,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12083.2, 300 sec: 12121.4). Total num frames: 50647040. Throughput: 0: 12047.6. Samples: 50633732. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:41:52,822][04011] Avg episode reward: [(0, '23.763')] [2023-03-11 11:41:52,825][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000098920_50647040.pth... [2023-03-11 11:41:52,828][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000098216_50286592.pth [2023-03-11 11:41:54,401][04298] Updated weights for policy 0, policy_version 98960 (0.0004) [2023-03-11 11:41:57,702][04298] Updated weights for policy 0, policy_version 99040 (0.0005) [2023-03-11 11:41:57,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12083.2, 300 sec: 12121.4). Total num frames: 50708480. Throughput: 0: 12048.9. Samples: 50706652. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:41:57,811][04011] Avg episode reward: [(0, '31.473')] [2023-03-11 11:42:01,144][04298] Updated weights for policy 0, policy_version 99120 (0.0005) [2023-03-11 11:42:02,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12014.9, 300 sec: 12107.5). Total num frames: 50765824. Throughput: 0: 12035.6. Samples: 50742248. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:42:02,811][04011] Avg episode reward: [(0, '31.931')] [2023-03-11 11:42:04,477][04298] Updated weights for policy 0, policy_version 99200 (0.0004) [2023-03-11 11:42:07,754][04298] Updated weights for policy 0, policy_version 99280 (0.0005) [2023-03-11 11:42:07,811][04011] Fps is (10 sec: 12287.9, 60 sec: 12083.2, 300 sec: 12121.4). Total num frames: 50831360. Throughput: 0: 12048.4. Samples: 50816488. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:42:07,812][04011] Avg episode reward: [(0, '32.446')] [2023-03-11 11:42:07,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000099280_50831360.pth... [2023-03-11 11:42:07,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000098568_50466816.pth [2023-03-11 11:42:11,248][04298] Updated weights for policy 0, policy_version 99360 (0.0005) [2023-03-11 11:42:12,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12014.9, 300 sec: 12107.5). Total num frames: 50888704. Throughput: 0: 12064.5. Samples: 50888660. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:42:12,812][04011] Avg episode reward: [(0, '33.014')] [2023-03-11 11:42:14,654][04298] Updated weights for policy 0, policy_version 99440 (0.0005) [2023-03-11 11:42:17,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12083.2, 300 sec: 12107.5). Total num frames: 50950144. Throughput: 0: 12063.4. Samples: 50924240. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:42:17,812][04011] Avg episode reward: [(0, '31.810')] [2023-03-11 11:42:18,058][04298] Updated weights for policy 0, policy_version 99520 (0.0005) [2023-03-11 11:42:21,492][04298] Updated weights for policy 0, policy_version 99600 (0.0005) [2023-03-11 11:42:22,811][04011] Fps is (10 sec: 12287.9, 60 sec: 12083.2, 300 sec: 12121.4). Total num frames: 51011584. Throughput: 0: 12024.9. Samples: 50995656. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:42:22,812][04011] Avg episode reward: [(0, '31.634')] [2023-03-11 11:42:22,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000099632_51011584.pth... [2023-03-11 11:42:22,816][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000098920_50647040.pth [2023-03-11 11:42:24,851][04298] Updated weights for policy 0, policy_version 99680 (0.0005) [2023-03-11 11:42:27,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12014.9, 300 sec: 12107.5). Total num frames: 51068928. Throughput: 0: 12068.4. Samples: 51068796. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:42:27,812][04011] Avg episode reward: [(0, '32.286')] [2023-03-11 11:42:28,316][04298] Updated weights for policy 0, policy_version 99760 (0.0005) [2023-03-11 11:42:31,473][04298] Updated weights for policy 0, policy_version 99840 (0.0003) [2023-03-11 11:42:32,811][04011] Fps is (10 sec: 12288.1, 60 sec: 12083.2, 300 sec: 12121.4). Total num frames: 51134464. Throughput: 0: 12104.7. Samples: 51105800. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:42:32,811][04011] Avg episode reward: [(0, '31.874')] [2023-03-11 11:42:34,591][04298] Updated weights for policy 0, policy_version 99920 (0.0004) [2023-03-11 11:42:37,660][04298] Updated weights for policy 0, policy_version 100000 (0.0004) [2023-03-11 11:42:37,811][04011] Fps is (10 sec: 13107.2, 60 sec: 12219.7, 300 sec: 12149.1). Total num frames: 51200000. Throughput: 0: 12245.6. Samples: 51184784. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:42:37,812][04011] Avg episode reward: [(0, '32.006')] [2023-03-11 11:42:37,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000100000_51200000.pth... [2023-03-11 11:42:37,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000099280_50831360.pth [2023-03-11 11:42:40,809][04298] Updated weights for policy 0, policy_version 100080 (0.0004) [2023-03-11 11:42:42,811][04011] Fps is (10 sec: 13107.2, 60 sec: 12288.0, 300 sec: 12149.2). Total num frames: 51265536. Throughput: 0: 12386.0. Samples: 51264024. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:42:42,812][04011] Avg episode reward: [(0, '32.025')] [2023-03-11 11:42:43,996][04298] Updated weights for policy 0, policy_version 100160 (0.0004) [2023-03-11 11:42:47,334][04298] Updated weights for policy 0, policy_version 100240 (0.0005) [2023-03-11 11:42:47,811][04011] Fps is (10 sec: 12697.7, 60 sec: 12356.3, 300 sec: 12135.3). Total num frames: 51326976. Throughput: 0: 12399.3. Samples: 51300216. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:42:47,812][04011] Avg episode reward: [(0, '32.336')] [2023-03-11 11:42:50,760][04298] Updated weights for policy 0, policy_version 100320 (0.0004) [2023-03-11 11:42:52,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12356.3, 300 sec: 12121.4). Total num frames: 51388416. Throughput: 0: 12388.4. Samples: 51373968. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:42:52,812][04011] Avg episode reward: [(0, '31.630')] [2023-03-11 11:42:52,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000100368_51388416.pth... [2023-03-11 11:42:52,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000099632_51011584.pth [2023-03-11 11:42:54,062][04298] Updated weights for policy 0, policy_version 100400 (0.0004) [2023-03-11 11:42:57,380][04298] Updated weights for policy 0, policy_version 100480 (0.0004) [2023-03-11 11:42:57,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12356.3, 300 sec: 12121.4). Total num frames: 51449856. Throughput: 0: 12426.5. Samples: 51447852. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:42:57,812][04011] Avg episode reward: [(0, '32.111')] [2023-03-11 11:43:00,748][04298] Updated weights for policy 0, policy_version 100560 (0.0005) [2023-03-11 11:43:02,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12424.5, 300 sec: 12121.4). Total num frames: 51511296. Throughput: 0: 12443.7. Samples: 51484208. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:43:02,812][04011] Avg episode reward: [(0, '31.867')] [2023-03-11 11:43:04,105][04298] Updated weights for policy 0, policy_version 100640 (0.0005) [2023-03-11 11:43:07,527][04298] Updated weights for policy 0, policy_version 100720 (0.0005) [2023-03-11 11:43:07,811][04011] Fps is (10 sec: 11878.3, 60 sec: 12288.0, 300 sec: 12121.4). Total num frames: 51568640. Throughput: 0: 12469.0. Samples: 51556760. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:43:07,812][04011] Avg episode reward: [(0, '32.372')] [2023-03-11 11:43:07,880][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000100728_51572736.pth... [2023-03-11 11:43:07,881][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000100000_51200000.pth [2023-03-11 11:43:10,992][04298] Updated weights for policy 0, policy_version 100800 (0.0004) [2023-03-11 11:43:12,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12356.3, 300 sec: 12121.4). Total num frames: 51630080. Throughput: 0: 12439.8. Samples: 51628588. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:43:12,812][04011] Avg episode reward: [(0, '32.202')] [2023-03-11 11:43:14,256][04298] Updated weights for policy 0, policy_version 100880 (0.0004) [2023-03-11 11:43:17,358][04298] Updated weights for policy 0, policy_version 100960 (0.0004) [2023-03-11 11:43:17,811][04011] Fps is (10 sec: 12697.7, 60 sec: 12424.5, 300 sec: 12149.1). Total num frames: 51695616. Throughput: 0: 12489.6. Samples: 51667832. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:43:17,812][04011] Avg episode reward: [(0, '31.356')] [2023-03-11 11:43:20,473][04298] Updated weights for policy 0, policy_version 101040 (0.0004) [2023-03-11 11:43:22,811][04011] Fps is (10 sec: 13107.1, 60 sec: 12492.8, 300 sec: 12163.0). Total num frames: 51761152. Throughput: 0: 12470.6. Samples: 51745960. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:43:22,812][04011] Avg episode reward: [(0, '31.505')] [2023-03-11 11:43:22,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000101096_51761152.pth... [2023-03-11 11:43:22,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000100368_51388416.pth [2023-03-11 11:43:23,629][04298] Updated weights for policy 0, policy_version 101120 (0.0004) [2023-03-11 11:43:26,699][04298] Updated weights for policy 0, policy_version 101200 (0.0003) [2023-03-11 11:43:27,811][04011] Fps is (10 sec: 13107.2, 60 sec: 12629.3, 300 sec: 12176.9). Total num frames: 51826688. Throughput: 0: 12493.2. Samples: 51826220. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:43:27,812][04011] Avg episode reward: [(0, '30.274')] [2023-03-11 11:43:29,751][04298] Updated weights for policy 0, policy_version 101280 (0.0004) [2023-03-11 11:43:32,811][04011] Fps is (10 sec: 13107.3, 60 sec: 12629.3, 300 sec: 12204.7). Total num frames: 51892224. Throughput: 0: 12570.1. Samples: 51865872. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:43:32,812][04011] Avg episode reward: [(0, '31.500')] [2023-03-11 11:43:32,871][04298] Updated weights for policy 0, policy_version 101360 (0.0005) [2023-03-11 11:43:36,034][04298] Updated weights for policy 0, policy_version 101440 (0.0005) [2023-03-11 11:43:37,811][04011] Fps is (10 sec: 13107.3, 60 sec: 12629.3, 300 sec: 12218.6). Total num frames: 51957760. Throughput: 0: 12675.5. Samples: 51944364. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-11 11:43:37,811][04011] Avg episode reward: [(0, '29.315')] [2023-03-11 11:43:37,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000101480_51957760.pth... [2023-03-11 11:43:37,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000100728_51572736.pth [2023-03-11 11:43:39,161][04298] Updated weights for policy 0, policy_version 101520 (0.0004) [2023-03-11 11:43:42,146][04298] Updated weights for policy 0, policy_version 101600 (0.0004) [2023-03-11 11:43:42,811][04011] Fps is (10 sec: 13516.8, 60 sec: 12697.6, 300 sec: 12246.3). Total num frames: 52027392. Throughput: 0: 12810.1. Samples: 52024308. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-11 11:43:42,811][04011] Avg episode reward: [(0, '31.275')] [2023-03-11 11:43:45,323][04298] Updated weights for policy 0, policy_version 101680 (0.0005) [2023-03-11 11:43:47,811][04011] Fps is (10 sec: 13107.1, 60 sec: 12697.6, 300 sec: 12246.3). Total num frames: 52088832. Throughput: 0: 12870.8. Samples: 52063392. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-11 11:43:47,811][04011] Avg episode reward: [(0, '30.236')] [2023-03-11 11:43:48,428][04298] Updated weights for policy 0, policy_version 101760 (0.0005) [2023-03-11 11:43:51,492][04298] Updated weights for policy 0, policy_version 101840 (0.0004) [2023-03-11 11:43:52,811][04011] Fps is (10 sec: 13107.1, 60 sec: 12834.1, 300 sec: 12274.1). Total num frames: 52158464. Throughput: 0: 13017.5. Samples: 52142548. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-11 11:43:52,812][04011] Avg episode reward: [(0, '28.948')] [2023-03-11 11:43:52,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000101872_52158464.pth... [2023-03-11 11:43:52,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000101096_51761152.pth [2023-03-11 11:43:54,594][04298] Updated weights for policy 0, policy_version 101920 (0.0004) [2023-03-11 11:43:57,689][04298] Updated weights for policy 0, policy_version 102000 (0.0005) [2023-03-11 11:43:57,811][04011] Fps is (10 sec: 13516.8, 60 sec: 12902.4, 300 sec: 12301.9). Total num frames: 52224000. Throughput: 0: 13190.6. Samples: 52222164. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-11 11:43:57,811][04011] Avg episode reward: [(0, '31.542')] [2023-03-11 11:44:00,853][04298] Updated weights for policy 0, policy_version 102080 (0.0005) [2023-03-11 11:44:02,811][04011] Fps is (10 sec: 13107.3, 60 sec: 12970.7, 300 sec: 12315.8). Total num frames: 52289536. Throughput: 0: 13179.9. Samples: 52260928. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-11 11:44:02,811][04011] Avg episode reward: [(0, '31.008')] [2023-03-11 11:44:03,964][04298] Updated weights for policy 0, policy_version 102160 (0.0004) [2023-03-11 11:44:07,130][04298] Updated weights for policy 0, policy_version 102240 (0.0005) [2023-03-11 11:44:07,811][04011] Fps is (10 sec: 13107.1, 60 sec: 13107.2, 300 sec: 12329.7). Total num frames: 52355072. Throughput: 0: 13181.5. Samples: 52339128. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-11 11:44:07,812][04011] Avg episode reward: [(0, '29.688')] [2023-03-11 11:44:07,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000102256_52355072.pth... [2023-03-11 11:44:07,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000101480_51957760.pth [2023-03-11 11:44:10,243][04298] Updated weights for policy 0, policy_version 102320 (0.0004) [2023-03-11 11:44:12,811][04011] Fps is (10 sec: 13107.2, 60 sec: 13175.5, 300 sec: 12343.5). Total num frames: 52420608. Throughput: 0: 13142.1. Samples: 52417616. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-11 11:44:12,811][04011] Avg episode reward: [(0, '29.458')] [2023-03-11 11:44:13,402][04298] Updated weights for policy 0, policy_version 102400 (0.0005) [2023-03-11 11:44:16,784][04298] Updated weights for policy 0, policy_version 102480 (0.0005) [2023-03-11 11:44:17,811][04011] Fps is (10 sec: 12697.7, 60 sec: 13107.2, 300 sec: 12357.4). Total num frames: 52482048. Throughput: 0: 13095.5. Samples: 52455168. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-11 11:44:17,812][04011] Avg episode reward: [(0, '31.184')] [2023-03-11 11:44:20,024][04298] Updated weights for policy 0, policy_version 102560 (0.0005) [2023-03-11 11:44:22,811][04011] Fps is (10 sec: 12287.9, 60 sec: 13038.9, 300 sec: 12357.4). Total num frames: 52543488. Throughput: 0: 13029.8. Samples: 52530704. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-11 11:44:22,812][04011] Avg episode reward: [(0, '30.483')] [2023-03-11 11:44:22,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000102624_52543488.pth... [2023-03-11 11:44:22,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000101872_52158464.pth [2023-03-11 11:44:23,175][04298] Updated weights for policy 0, policy_version 102640 (0.0005) [2023-03-11 11:44:26,305][04298] Updated weights for policy 0, policy_version 102720 (0.0005) [2023-03-11 11:44:27,811][04011] Fps is (10 sec: 12697.6, 60 sec: 13038.9, 300 sec: 12371.3). Total num frames: 52609024. Throughput: 0: 12995.1. Samples: 52609088. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-11 11:44:27,812][04011] Avg episode reward: [(0, '28.367')] [2023-03-11 11:44:29,443][04298] Updated weights for policy 0, policy_version 102800 (0.0005) [2023-03-11 11:44:32,642][04298] Updated weights for policy 0, policy_version 102880 (0.0005) [2023-03-11 11:44:32,811][04011] Fps is (10 sec: 13107.2, 60 sec: 13038.9, 300 sec: 12399.1). Total num frames: 52674560. Throughput: 0: 12988.2. Samples: 52647860. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-11 11:44:32,811][04011] Avg episode reward: [(0, '22.421')] [2023-03-11 11:44:35,812][04298] Updated weights for policy 0, policy_version 102960 (0.0005) [2023-03-11 11:44:37,811][04011] Fps is (10 sec: 13107.2, 60 sec: 13038.9, 300 sec: 12413.0). Total num frames: 52740096. Throughput: 0: 12949.3. Samples: 52725264. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 11:44:37,812][04011] Avg episode reward: [(0, '29.291')] [2023-03-11 11:44:37,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000103008_52740096.pth... [2023-03-11 11:44:37,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000102256_52355072.pth [2023-03-11 11:44:38,911][04298] Updated weights for policy 0, policy_version 103040 (0.0005) [2023-03-11 11:44:42,040][04298] Updated weights for policy 0, policy_version 103120 (0.0005) [2023-03-11 11:44:42,811][04011] Fps is (10 sec: 13107.2, 60 sec: 12970.7, 300 sec: 12426.8). Total num frames: 52805632. Throughput: 0: 12929.5. Samples: 52803992. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 11:44:42,811][04011] Avg episode reward: [(0, '29.450')] [2023-03-11 11:44:45,328][04298] Updated weights for policy 0, policy_version 103200 (0.0005) [2023-03-11 11:44:47,811][04011] Fps is (10 sec: 12697.6, 60 sec: 12970.7, 300 sec: 12426.8). Total num frames: 52867072. Throughput: 0: 12898.4. Samples: 52841356. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 11:44:47,812][04011] Avg episode reward: [(0, '29.292')] [2023-03-11 11:44:48,812][04298] Updated weights for policy 0, policy_version 103280 (0.0005) [2023-03-11 11:44:52,284][04298] Updated weights for policy 0, policy_version 103360 (0.0006) [2023-03-11 11:44:52,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12765.9, 300 sec: 12426.8). Total num frames: 52924416. Throughput: 0: 12733.5. Samples: 52912136. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 11:44:52,811][04011] Avg episode reward: [(0, '28.571')] [2023-03-11 11:44:52,814][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000103368_52924416.pth... [2023-03-11 11:44:52,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000102624_52543488.pth [2023-03-11 11:44:55,756][04298] Updated weights for policy 0, policy_version 103440 (0.0005) [2023-03-11 11:44:57,811][04011] Fps is (10 sec: 11878.5, 60 sec: 12697.6, 300 sec: 12426.8). Total num frames: 52985856. Throughput: 0: 12552.3. Samples: 52982468. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 11:44:57,811][04011] Avg episode reward: [(0, '28.158')] [2023-03-11 11:44:59,116][04298] Updated weights for policy 0, policy_version 103520 (0.0005) [2023-03-11 11:45:02,573][04298] Updated weights for policy 0, policy_version 103600 (0.0005) [2023-03-11 11:45:02,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12561.1, 300 sec: 12426.8). Total num frames: 53043200. Throughput: 0: 12531.3. Samples: 53019076. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 11:45:02,811][04011] Avg episode reward: [(0, '30.052')] [2023-03-11 11:45:06,018][04298] Updated weights for policy 0, policy_version 103680 (0.0005) [2023-03-11 11:45:07,811][04011] Fps is (10 sec: 11878.3, 60 sec: 12492.8, 300 sec: 12426.8). Total num frames: 53104640. Throughput: 0: 12444.5. Samples: 53090708. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 11:45:07,812][04011] Avg episode reward: [(0, '29.092')] [2023-03-11 11:45:07,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000103720_53104640.pth... [2023-03-11 11:45:07,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000103008_52740096.pth [2023-03-11 11:45:09,290][04298] Updated weights for policy 0, policy_version 103760 (0.0005) [2023-03-11 11:45:12,473][04298] Updated weights for policy 0, policy_version 103840 (0.0005) [2023-03-11 11:45:12,811][04011] Fps is (10 sec: 12697.7, 60 sec: 12492.8, 300 sec: 12454.6). Total num frames: 53170176. Throughput: 0: 12395.2. Samples: 53166872. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 11:45:12,811][04011] Avg episode reward: [(0, '30.477')] [2023-03-11 11:45:15,546][04298] Updated weights for policy 0, policy_version 103920 (0.0004) [2023-03-11 11:45:17,811][04011] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12468.5). Total num frames: 53235712. Throughput: 0: 12427.7. Samples: 53207104. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 11:45:17,811][04011] Avg episode reward: [(0, '31.190')] [2023-03-11 11:45:18,583][04298] Updated weights for policy 0, policy_version 104000 (0.0005) [2023-03-11 11:45:21,877][04298] Updated weights for policy 0, policy_version 104080 (0.0005) [2023-03-11 11:45:22,811][04011] Fps is (10 sec: 12697.5, 60 sec: 12561.1, 300 sec: 12468.5). Total num frames: 53297152. Throughput: 0: 12437.0. Samples: 53284928. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 11:45:22,812][04011] Avg episode reward: [(0, '30.695')] [2023-03-11 11:45:22,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000104096_53297152.pth... [2023-03-11 11:45:22,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000103368_52924416.pth [2023-03-11 11:45:25,291][04298] Updated weights for policy 0, policy_version 104160 (0.0005) [2023-03-11 11:45:27,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12492.8, 300 sec: 12468.5). Total num frames: 53358592. Throughput: 0: 12298.4. Samples: 53357420. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 11:45:27,811][04011] Avg episode reward: [(0, '30.323')] [2023-03-11 11:45:28,696][04298] Updated weights for policy 0, policy_version 104240 (0.0005) [2023-03-11 11:45:32,212][04298] Updated weights for policy 0, policy_version 104320 (0.0005) [2023-03-11 11:45:32,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12356.3, 300 sec: 12468.5). Total num frames: 53415936. Throughput: 0: 12245.4. Samples: 53392400. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 11:45:32,812][04011] Avg episode reward: [(0, '30.777')] [2023-03-11 11:45:35,724][04298] Updated weights for policy 0, policy_version 104400 (0.0005) [2023-03-11 11:45:37,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12288.0, 300 sec: 12468.5). Total num frames: 53477376. Throughput: 0: 12248.3. Samples: 53463308. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 11:45:37,812][04011] Avg episode reward: [(0, '30.709')] [2023-03-11 11:45:37,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000104448_53477376.pth... [2023-03-11 11:45:37,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000103720_53104640.pth [2023-03-11 11:45:39,127][04298] Updated weights for policy 0, policy_version 104480 (0.0006) [2023-03-11 11:45:42,561][04298] Updated weights for policy 0, policy_version 104560 (0.0005) [2023-03-11 11:45:42,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12151.5, 300 sec: 12454.6). Total num frames: 53534720. Throughput: 0: 12273.7. Samples: 53534784. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 11:45:42,811][04011] Avg episode reward: [(0, '30.801')] [2023-03-11 11:45:46,097][04298] Updated weights for policy 0, policy_version 104640 (0.0005) [2023-03-11 11:45:47,811][04011] Fps is (10 sec: 11468.8, 60 sec: 12083.2, 300 sec: 12440.7). Total num frames: 53592064. Throughput: 0: 12240.9. Samples: 53569916. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 11:45:47,811][04011] Avg episode reward: [(0, '30.452')] [2023-03-11 11:45:49,599][04298] Updated weights for policy 0, policy_version 104720 (0.0005) [2023-03-11 11:45:52,811][04011] Fps is (10 sec: 11878.3, 60 sec: 12151.5, 300 sec: 12440.7). Total num frames: 53653504. Throughput: 0: 12221.2. Samples: 53640664. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 11:45:52,812][04011] Avg episode reward: [(0, '28.627')] [2023-03-11 11:45:52,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000104792_53653504.pth... [2023-03-11 11:45:52,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000104096_53297152.pth [2023-03-11 11:45:53,003][04298] Updated weights for policy 0, policy_version 104800 (0.0005) [2023-03-11 11:45:56,490][04298] Updated weights for policy 0, policy_version 104880 (0.0005) [2023-03-11 11:45:57,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12083.2, 300 sec: 12426.8). Total num frames: 53710848. Throughput: 0: 12093.0. Samples: 53711056. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 11:45:57,812][04011] Avg episode reward: [(0, '30.788')] [2023-03-11 11:45:59,967][04298] Updated weights for policy 0, policy_version 104960 (0.0005) [2023-03-11 11:46:02,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12151.5, 300 sec: 12426.8). Total num frames: 53772288. Throughput: 0: 12005.9. Samples: 53747372. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 11:46:02,811][04011] Avg episode reward: [(0, '31.465')] [2023-03-11 11:46:03,333][04298] Updated weights for policy 0, policy_version 105040 (0.0005) [2023-03-11 11:46:06,679][04298] Updated weights for policy 0, policy_version 105120 (0.0005) [2023-03-11 11:46:07,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12151.5, 300 sec: 12426.8). Total num frames: 53833728. Throughput: 0: 11889.0. Samples: 53819932. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 11:46:07,822][04011] Avg episode reward: [(0, '31.982')] [2023-03-11 11:46:07,825][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000105144_53833728.pth... [2023-03-11 11:46:07,828][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000104448_53477376.pth [2023-03-11 11:46:10,184][04298] Updated weights for policy 0, policy_version 105200 (0.0005) [2023-03-11 11:46:12,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12014.9, 300 sec: 12426.8). Total num frames: 53891072. Throughput: 0: 11855.8. Samples: 53890932. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 11:46:12,822][04011] Avg episode reward: [(0, '31.500')] [2023-03-11 11:46:13,661][04298] Updated weights for policy 0, policy_version 105280 (0.0005) [2023-03-11 11:46:16,817][04298] Updated weights for policy 0, policy_version 105360 (0.0004) [2023-03-11 11:46:17,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12014.9, 300 sec: 12440.7). Total num frames: 53956608. Throughput: 0: 11902.2. Samples: 53928000. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 11:46:17,822][04011] Avg episode reward: [(0, '31.055')] [2023-03-11 11:46:19,860][04298] Updated weights for policy 0, policy_version 105440 (0.0003) [2023-03-11 11:46:22,811][04011] Fps is (10 sec: 13107.2, 60 sec: 12083.2, 300 sec: 12454.6). Total num frames: 54022144. Throughput: 0: 12089.4. Samples: 54007332. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 11:46:22,822][04011] Avg episode reward: [(0, '31.962')] [2023-03-11 11:46:22,825][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000105512_54022144.pth... [2023-03-11 11:46:22,828][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000104792_53653504.pth [2023-03-11 11:46:22,910][04298] Updated weights for policy 0, policy_version 105520 (0.0003) [2023-03-11 11:46:25,937][04298] Updated weights for policy 0, policy_version 105600 (0.0003) [2023-03-11 11:46:27,811][04011] Fps is (10 sec: 13516.9, 60 sec: 12219.7, 300 sec: 12482.4). Total num frames: 54091776. Throughput: 0: 12307.3. Samples: 54088612. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 11:46:27,822][04011] Avg episode reward: [(0, '31.625')] [2023-03-11 11:46:29,051][04298] Updated weights for policy 0, policy_version 105680 (0.0004) [2023-03-11 11:46:32,160][04298] Updated weights for policy 0, policy_version 105760 (0.0004) [2023-03-11 11:46:32,811][04011] Fps is (10 sec: 13516.8, 60 sec: 12356.3, 300 sec: 12510.2). Total num frames: 54157312. Throughput: 0: 12406.0. Samples: 54128184. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 11:46:32,811][04011] Avg episode reward: [(0, '32.160')] [2023-03-11 11:46:35,573][04298] Updated weights for policy 0, policy_version 105840 (0.0005) [2023-03-11 11:46:37,811][04011] Fps is (10 sec: 12287.9, 60 sec: 12288.0, 300 sec: 12496.3). Total num frames: 54214656. Throughput: 0: 12469.8. Samples: 54201804. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 11:46:37,822][04011] Avg episode reward: [(0, '31.888')] [2023-03-11 11:46:37,825][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000105888_54214656.pth... [2023-03-11 11:46:37,828][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000105144_53833728.pth [2023-03-11 11:46:39,073][04298] Updated weights for policy 0, policy_version 105920 (0.0005) [2023-03-11 11:46:42,479][04298] Updated weights for policy 0, policy_version 106000 (0.0004) [2023-03-11 11:46:42,811][04011] Fps is (10 sec: 11468.8, 60 sec: 12288.0, 300 sec: 12496.3). Total num frames: 54272000. Throughput: 0: 12480.7. Samples: 54272688. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:46:42,822][04011] Avg episode reward: [(0, '31.029')] [2023-03-11 11:46:46,024][04298] Updated weights for policy 0, policy_version 106080 (0.0004) [2023-03-11 11:46:47,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12356.3, 300 sec: 12496.3). Total num frames: 54333440. Throughput: 0: 12448.1. Samples: 54307536. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:46:47,812][04011] Avg episode reward: [(0, '31.530')] [2023-03-11 11:46:49,376][04298] Updated weights for policy 0, policy_version 106160 (0.0005) [2023-03-11 11:46:52,811][04011] Fps is (10 sec: 11878.3, 60 sec: 12288.0, 300 sec: 12482.4). Total num frames: 54390784. Throughput: 0: 12418.5. Samples: 54378764. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:46:52,812][04011] Avg episode reward: [(0, '32.148')] [2023-03-11 11:46:52,852][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000106240_54394880.pth... [2023-03-11 11:46:52,852][04298] Updated weights for policy 0, policy_version 106240 (0.0005) [2023-03-11 11:46:52,853][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000105512_54022144.pth [2023-03-11 11:46:56,158][04298] Updated weights for policy 0, policy_version 106320 (0.0005) [2023-03-11 11:46:57,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12356.3, 300 sec: 12496.3). Total num frames: 54452224. Throughput: 0: 12474.8. Samples: 54452296. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:46:57,811][04011] Avg episode reward: [(0, '32.500')] [2023-03-11 11:46:59,520][04298] Updated weights for policy 0, policy_version 106400 (0.0004) [2023-03-11 11:47:02,811][04011] Fps is (10 sec: 12288.1, 60 sec: 12356.3, 300 sec: 12482.4). Total num frames: 54513664. Throughput: 0: 12457.8. Samples: 54488600. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:47:02,811][04011] Avg episode reward: [(0, '30.402')] [2023-03-11 11:47:03,045][04298] Updated weights for policy 0, policy_version 106480 (0.0005) [2023-03-11 11:47:06,495][04298] Updated weights for policy 0, policy_version 106560 (0.0005) [2023-03-11 11:47:07,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12288.0, 300 sec: 12482.4). Total num frames: 54571008. Throughput: 0: 12262.1. Samples: 54559128. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:47:07,812][04011] Avg episode reward: [(0, '31.118')] [2023-03-11 11:47:07,814][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000106584_54571008.pth... [2023-03-11 11:47:07,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000105888_54214656.pth [2023-03-11 11:47:10,043][04298] Updated weights for policy 0, policy_version 106640 (0.0005) [2023-03-11 11:47:12,811][04011] Fps is (10 sec: 11468.6, 60 sec: 12288.0, 300 sec: 12468.5). Total num frames: 54628352. Throughput: 0: 11998.7. Samples: 54628556. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:47:12,812][04011] Avg episode reward: [(0, '30.615')] [2023-03-11 11:47:13,529][04298] Updated weights for policy 0, policy_version 106720 (0.0005) [2023-03-11 11:47:16,911][04298] Updated weights for policy 0, policy_version 106800 (0.0005) [2023-03-11 11:47:17,811][04011] Fps is (10 sec: 11878.5, 60 sec: 12219.7, 300 sec: 12468.5). Total num frames: 54689792. Throughput: 0: 11935.6. Samples: 54665288. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:47:17,811][04011] Avg episode reward: [(0, '32.282')] [2023-03-11 11:47:20,389][04298] Updated weights for policy 0, policy_version 106880 (0.0005) [2023-03-11 11:47:22,811][04011] Fps is (10 sec: 12288.2, 60 sec: 12151.5, 300 sec: 12482.4). Total num frames: 54751232. Throughput: 0: 11868.4. Samples: 54735880. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:47:22,811][04011] Avg episode reward: [(0, '31.968')] [2023-03-11 11:47:22,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000106936_54751232.pth... [2023-03-11 11:47:22,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000106240_54394880.pth [2023-03-11 11:47:23,844][04298] Updated weights for policy 0, policy_version 106960 (0.0005) [2023-03-11 11:47:27,206][04298] Updated weights for policy 0, policy_version 107040 (0.0005) [2023-03-11 11:47:27,811][04011] Fps is (10 sec: 11878.4, 60 sec: 11946.7, 300 sec: 12454.6). Total num frames: 54808576. Throughput: 0: 11910.0. Samples: 54808640. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:47:27,811][04011] Avg episode reward: [(0, '30.050')] [2023-03-11 11:47:30,540][04298] Updated weights for policy 0, policy_version 107120 (0.0005) [2023-03-11 11:47:32,811][04011] Fps is (10 sec: 11878.3, 60 sec: 11878.4, 300 sec: 12440.7). Total num frames: 54870016. Throughput: 0: 11955.0. Samples: 54845512. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:47:32,812][04011] Avg episode reward: [(0, '28.871')] [2023-03-11 11:47:33,955][04298] Updated weights for policy 0, policy_version 107200 (0.0005) [2023-03-11 11:47:37,329][04298] Updated weights for policy 0, policy_version 107280 (0.0005) [2023-03-11 11:47:37,811][04011] Fps is (10 sec: 12287.9, 60 sec: 11946.7, 300 sec: 12426.8). Total num frames: 54931456. Throughput: 0: 11981.1. Samples: 54917912. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:47:37,811][04011] Avg episode reward: [(0, '31.553')] [2023-03-11 11:47:37,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000107288_54931456.pth... [2023-03-11 11:47:37,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000106584_54571008.pth [2023-03-11 11:47:40,825][04298] Updated weights for policy 0, policy_version 107360 (0.0005) [2023-03-11 11:47:42,811][04011] Fps is (10 sec: 11878.4, 60 sec: 11946.7, 300 sec: 12413.0). Total num frames: 54988800. Throughput: 0: 11922.7. Samples: 54988816. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-11 11:47:42,811][04011] Avg episode reward: [(0, '30.046')] [2023-03-11 11:47:44,317][04298] Updated weights for policy 0, policy_version 107440 (0.0005) [2023-03-11 11:47:47,698][04298] Updated weights for policy 0, policy_version 107520 (0.0005) [2023-03-11 11:47:47,811][04011] Fps is (10 sec: 11878.5, 60 sec: 11946.7, 300 sec: 12413.0). Total num frames: 55050240. Throughput: 0: 11889.8. Samples: 55023640. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-11 11:47:47,811][04011] Avg episode reward: [(0, '30.401')] [2023-03-11 11:47:51,076][04298] Updated weights for policy 0, policy_version 107600 (0.0005) [2023-03-11 11:47:52,811][04011] Fps is (10 sec: 11878.4, 60 sec: 11946.7, 300 sec: 12399.1). Total num frames: 55107584. Throughput: 0: 11938.6. Samples: 55096364. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-11 11:47:52,811][04011] Avg episode reward: [(0, '32.353')] [2023-03-11 11:47:52,857][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000107640_55111680.pth... [2023-03-11 11:47:52,858][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000106936_54751232.pth [2023-03-11 11:47:54,608][04298] Updated weights for policy 0, policy_version 107680 (0.0005) [2023-03-11 11:47:57,811][04011] Fps is (10 sec: 11878.4, 60 sec: 11946.7, 300 sec: 12399.1). Total num frames: 55169024. Throughput: 0: 11992.0. Samples: 55168196. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-11 11:47:57,811][04011] Avg episode reward: [(0, '32.214')] [2023-03-11 11:47:58,004][04298] Updated weights for policy 0, policy_version 107760 (0.0005) [2023-03-11 11:48:01,511][04298] Updated weights for policy 0, policy_version 107840 (0.0005) [2023-03-11 11:48:02,811][04011] Fps is (10 sec: 11878.4, 60 sec: 11878.4, 300 sec: 12399.1). Total num frames: 55226368. Throughput: 0: 11949.6. Samples: 55203020. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-11 11:48:02,811][04011] Avg episode reward: [(0, '30.720')] [2023-03-11 11:48:04,984][04298] Updated weights for policy 0, policy_version 107920 (0.0005) [2023-03-11 11:48:07,811][04011] Fps is (10 sec: 11878.4, 60 sec: 11946.7, 300 sec: 12399.1). Total num frames: 55287808. Throughput: 0: 11953.9. Samples: 55273808. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-11 11:48:07,812][04011] Avg episode reward: [(0, '31.627')] [2023-03-11 11:48:07,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000107984_55287808.pth... [2023-03-11 11:48:07,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000107288_54931456.pth [2023-03-11 11:48:08,349][04298] Updated weights for policy 0, policy_version 108000 (0.0005) [2023-03-11 11:48:11,773][04298] Updated weights for policy 0, policy_version 108080 (0.0005) [2023-03-11 11:48:12,811][04011] Fps is (10 sec: 12288.1, 60 sec: 12015.0, 300 sec: 12385.2). Total num frames: 55349248. Throughput: 0: 11947.8. Samples: 55346292. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-11 11:48:12,811][04011] Avg episode reward: [(0, '31.750')] [2023-03-11 11:48:15,215][04298] Updated weights for policy 0, policy_version 108160 (0.0004) [2023-03-11 11:48:17,811][04011] Fps is (10 sec: 11878.4, 60 sec: 11946.7, 300 sec: 12357.4). Total num frames: 55406592. Throughput: 0: 11923.7. Samples: 55382080. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-11 11:48:17,811][04011] Avg episode reward: [(0, '31.763')] [2023-03-11 11:48:18,636][04298] Updated weights for policy 0, policy_version 108240 (0.0005) [2023-03-11 11:48:22,031][04298] Updated weights for policy 0, policy_version 108320 (0.0005) [2023-03-11 11:48:22,811][04011] Fps is (10 sec: 11878.3, 60 sec: 11946.7, 300 sec: 12343.5). Total num frames: 55468032. Throughput: 0: 11917.7. Samples: 55454208. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-11 11:48:22,811][04011] Avg episode reward: [(0, '29.866')] [2023-03-11 11:48:22,814][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000108336_55468032.pth... [2023-03-11 11:48:22,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000107640_55111680.pth [2023-03-11 11:48:25,496][04298] Updated weights for policy 0, policy_version 108400 (0.0005) [2023-03-11 11:48:27,811][04011] Fps is (10 sec: 11878.5, 60 sec: 11946.7, 300 sec: 12315.8). Total num frames: 55525376. Throughput: 0: 11932.8. Samples: 55525792. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-11 11:48:27,811][04011] Avg episode reward: [(0, '32.844')] [2023-03-11 11:48:28,857][04298] Updated weights for policy 0, policy_version 108480 (0.0005) [2023-03-11 11:48:32,356][04298] Updated weights for policy 0, policy_version 108560 (0.0005) [2023-03-11 11:48:32,811][04011] Fps is (10 sec: 11878.4, 60 sec: 11946.7, 300 sec: 12301.9). Total num frames: 55586816. Throughput: 0: 11948.9. Samples: 55561340. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-11 11:48:32,812][04011] Avg episode reward: [(0, '32.533')] [2023-03-11 11:48:35,725][04298] Updated weights for policy 0, policy_version 108640 (0.0005) [2023-03-11 11:48:37,811][04011] Fps is (10 sec: 12287.8, 60 sec: 11946.7, 300 sec: 12274.1). Total num frames: 55648256. Throughput: 0: 11946.8. Samples: 55633972. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-11 11:48:37,812][04011] Avg episode reward: [(0, '32.545')] [2023-03-11 11:48:37,816][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000108688_55648256.pth... [2023-03-11 11:48:37,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000107984_55287808.pth [2023-03-11 11:48:39,147][04298] Updated weights for policy 0, policy_version 108720 (0.0004) [2023-03-11 11:48:42,545][04298] Updated weights for policy 0, policy_version 108800 (0.0005) [2023-03-11 11:48:42,811][04011] Fps is (10 sec: 11878.5, 60 sec: 11946.7, 300 sec: 12260.2). Total num frames: 55705600. Throughput: 0: 11943.7. Samples: 55705664. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 11:48:42,811][04011] Avg episode reward: [(0, '30.767')] [2023-03-11 11:48:46,033][04298] Updated weights for policy 0, policy_version 108880 (0.0005) [2023-03-11 11:48:47,811][04011] Fps is (10 sec: 11878.5, 60 sec: 11946.7, 300 sec: 12232.5). Total num frames: 55767040. Throughput: 0: 11957.8. Samples: 55741120. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 11:48:47,811][04011] Avg episode reward: [(0, '29.375')] [2023-03-11 11:48:49,392][04298] Updated weights for policy 0, policy_version 108960 (0.0005) [2023-03-11 11:48:52,811][04011] Fps is (10 sec: 11878.3, 60 sec: 11946.7, 300 sec: 12204.7). Total num frames: 55824384. Throughput: 0: 11984.5. Samples: 55813112. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 11:48:52,812][04011] Avg episode reward: [(0, '28.759')] [2023-03-11 11:48:52,831][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000109040_55828480.pth... [2023-03-11 11:48:52,832][04298] Updated weights for policy 0, policy_version 109040 (0.0005) [2023-03-11 11:48:52,833][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000108336_55468032.pth [2023-03-11 11:48:56,223][04298] Updated weights for policy 0, policy_version 109120 (0.0005) [2023-03-11 11:48:57,811][04011] Fps is (10 sec: 11878.4, 60 sec: 11946.7, 300 sec: 12190.8). Total num frames: 55885824. Throughput: 0: 11991.0. Samples: 55885888. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 11:48:57,811][04011] Avg episode reward: [(0, '27.673')] [2023-03-11 11:48:59,433][04298] Updated weights for policy 0, policy_version 109200 (0.0004) [2023-03-11 11:49:02,587][04298] Updated weights for policy 0, policy_version 109280 (0.0004) [2023-03-11 11:49:02,811][04011] Fps is (10 sec: 12697.7, 60 sec: 12083.2, 300 sec: 12190.8). Total num frames: 55951360. Throughput: 0: 12070.5. Samples: 55925252. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 11:49:02,811][04011] Avg episode reward: [(0, '27.752')] [2023-03-11 11:49:05,720][04298] Updated weights for policy 0, policy_version 109360 (0.0004) [2023-03-11 11:49:07,811][04011] Fps is (10 sec: 13107.1, 60 sec: 12151.5, 300 sec: 12190.8). Total num frames: 56016896. Throughput: 0: 12203.9. Samples: 56003384. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 11:49:07,811][04011] Avg episode reward: [(0, '28.283')] [2023-03-11 11:49:07,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000109408_56016896.pth... [2023-03-11 11:49:07,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000108688_55648256.pth [2023-03-11 11:49:08,851][04298] Updated weights for policy 0, policy_version 109440 (0.0004) [2023-03-11 11:49:11,964][04298] Updated weights for policy 0, policy_version 109520 (0.0004) [2023-03-11 11:49:12,811][04011] Fps is (10 sec: 13107.2, 60 sec: 12219.7, 300 sec: 12204.7). Total num frames: 56082432. Throughput: 0: 12359.4. Samples: 56081964. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 11:49:12,811][04011] Avg episode reward: [(0, '25.255')] [2023-03-11 11:49:15,059][04298] Updated weights for policy 0, policy_version 109600 (0.0004) [2023-03-11 11:49:17,811][04011] Fps is (10 sec: 13107.2, 60 sec: 12356.3, 300 sec: 12218.6). Total num frames: 56147968. Throughput: 0: 12452.3. Samples: 56121692. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 11:49:17,811][04011] Avg episode reward: [(0, '25.970')] [2023-03-11 11:49:18,303][04298] Updated weights for policy 0, policy_version 109680 (0.0004) [2023-03-11 11:49:21,589][04298] Updated weights for policy 0, policy_version 109760 (0.0004) [2023-03-11 11:49:22,811][04011] Fps is (10 sec: 12697.6, 60 sec: 12356.3, 300 sec: 12204.7). Total num frames: 56209408. Throughput: 0: 12513.6. Samples: 56197084. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 11:49:22,811][04011] Avg episode reward: [(0, '20.882')] [2023-03-11 11:49:22,814][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000109784_56209408.pth... [2023-03-11 11:49:22,815][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000109040_55828480.pth [2023-03-11 11:49:24,879][04298] Updated weights for policy 0, policy_version 109840 (0.0004) [2023-03-11 11:49:27,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12424.5, 300 sec: 12190.8). Total num frames: 56270848. Throughput: 0: 12561.1. Samples: 56270912. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 11:49:27,811][04011] Avg episode reward: [(0, '22.727')] [2023-03-11 11:49:28,164][04298] Updated weights for policy 0, policy_version 109920 (0.0004) [2023-03-11 11:49:31,400][04298] Updated weights for policy 0, policy_version 110000 (0.0005) [2023-03-11 11:49:32,811][04011] Fps is (10 sec: 12697.6, 60 sec: 12492.8, 300 sec: 12190.8). Total num frames: 56336384. Throughput: 0: 12623.8. Samples: 56309192. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 11:49:32,811][04011] Avg episode reward: [(0, '23.043')] [2023-03-11 11:49:34,640][04298] Updated weights for policy 0, policy_version 110080 (0.0004) [2023-03-11 11:49:37,811][04011] Fps is (10 sec: 12697.5, 60 sec: 12492.8, 300 sec: 12176.9). Total num frames: 56397824. Throughput: 0: 12710.0. Samples: 56385064. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 11:49:37,812][04011] Avg episode reward: [(0, '20.771')] [2023-03-11 11:49:37,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000110152_56397824.pth... [2023-03-11 11:49:37,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000109408_56016896.pth [2023-03-11 11:49:37,917][04298] Updated weights for policy 0, policy_version 110160 (0.0004) [2023-03-11 11:49:41,116][04298] Updated weights for policy 0, policy_version 110240 (0.0004) [2023-03-11 11:49:42,811][04011] Fps is (10 sec: 12697.6, 60 sec: 12629.3, 300 sec: 12190.8). Total num frames: 56463360. Throughput: 0: 12783.5. Samples: 56461144. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-11 11:49:42,811][04011] Avg episode reward: [(0, '22.057')] [2023-03-11 11:49:44,280][04298] Updated weights for policy 0, policy_version 110320 (0.0003) [2023-03-11 11:49:47,537][04298] Updated weights for policy 0, policy_version 110400 (0.0004) [2023-03-11 11:49:47,811][04011] Fps is (10 sec: 12697.7, 60 sec: 12629.3, 300 sec: 12204.7). Total num frames: 56524800. Throughput: 0: 12767.8. Samples: 56499804. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-11 11:49:47,811][04011] Avg episode reward: [(0, '20.339')] [2023-03-11 11:49:50,676][04298] Updated weights for policy 0, policy_version 110480 (0.0003) [2023-03-11 11:49:52,811][04011] Fps is (10 sec: 12697.6, 60 sec: 12765.9, 300 sec: 12218.6). Total num frames: 56590336. Throughput: 0: 12751.6. Samples: 56577208. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-11 11:49:52,812][04011] Avg episode reward: [(0, '24.305')] [2023-03-11 11:49:52,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000110528_56590336.pth... [2023-03-11 11:49:52,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000109784_56209408.pth [2023-03-11 11:49:53,878][04298] Updated weights for policy 0, policy_version 110560 (0.0004) [2023-03-11 11:49:57,169][04298] Updated weights for policy 0, policy_version 110640 (0.0004) [2023-03-11 11:49:57,811][04011] Fps is (10 sec: 13107.2, 60 sec: 12834.1, 300 sec: 12246.3). Total num frames: 56655872. Throughput: 0: 12669.3. Samples: 56652080. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-11 11:49:57,811][04011] Avg episode reward: [(0, '23.043')] [2023-03-11 11:50:00,370][04298] Updated weights for policy 0, policy_version 110720 (0.0004) [2023-03-11 11:50:02,811][04011] Fps is (10 sec: 12697.7, 60 sec: 12765.9, 300 sec: 12246.3). Total num frames: 56717312. Throughput: 0: 12653.4. Samples: 56691096. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-11 11:50:02,811][04011] Avg episode reward: [(0, '21.123')] [2023-03-11 11:50:03,603][04298] Updated weights for policy 0, policy_version 110800 (0.0004) [2023-03-11 11:50:06,834][04298] Updated weights for policy 0, policy_version 110880 (0.0004) [2023-03-11 11:50:07,811][04011] Fps is (10 sec: 12697.5, 60 sec: 12765.9, 300 sec: 12246.3). Total num frames: 56782848. Throughput: 0: 12658.1. Samples: 56766700. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-11 11:50:07,812][04011] Avg episode reward: [(0, '23.519')] [2023-03-11 11:50:07,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000110904_56782848.pth... [2023-03-11 11:50:07,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000110152_56397824.pth [2023-03-11 11:50:09,978][04298] Updated weights for policy 0, policy_version 110960 (0.0004) [2023-03-11 11:50:12,811][04011] Fps is (10 sec: 13107.2, 60 sec: 12765.9, 300 sec: 12246.3). Total num frames: 56848384. Throughput: 0: 12755.6. Samples: 56844912. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-11 11:50:12,811][04011] Avg episode reward: [(0, '30.232')] [2023-03-11 11:50:13,091][04298] Updated weights for policy 0, policy_version 111040 (0.0004) [2023-03-11 11:50:16,391][04298] Updated weights for policy 0, policy_version 111120 (0.0004) [2023-03-11 11:50:17,811][04011] Fps is (10 sec: 12697.6, 60 sec: 12697.6, 300 sec: 12246.3). Total num frames: 56909824. Throughput: 0: 12752.5. Samples: 56883052. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-11 11:50:17,811][04011] Avg episode reward: [(0, '25.014')] [2023-03-11 11:50:19,658][04298] Updated weights for policy 0, policy_version 111200 (0.0004) [2023-03-11 11:50:22,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12697.6, 300 sec: 12246.3). Total num frames: 56971264. Throughput: 0: 12755.0. Samples: 56959040. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-11 11:50:22,811][04011] Avg episode reward: [(0, '31.321')] [2023-03-11 11:50:22,823][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000111280_56975360.pth... [2023-03-11 11:50:22,824][04298] Updated weights for policy 0, policy_version 111280 (0.0004) [2023-03-11 11:50:22,825][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000110528_56590336.pth [2023-03-11 11:50:25,950][04298] Updated weights for policy 0, policy_version 111360 (0.0004) [2023-03-11 11:50:27,811][04011] Fps is (10 sec: 12697.6, 60 sec: 12765.9, 300 sec: 12274.1). Total num frames: 57036800. Throughput: 0: 12794.1. Samples: 57036876. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-11 11:50:27,811][04011] Avg episode reward: [(0, '31.603')] [2023-03-11 11:50:29,058][04298] Updated weights for policy 0, policy_version 111440 (0.0004) [2023-03-11 11:50:32,182][04298] Updated weights for policy 0, policy_version 111520 (0.0004) [2023-03-11 11:50:32,811][04011] Fps is (10 sec: 13107.1, 60 sec: 12765.9, 300 sec: 12288.0). Total num frames: 57102336. Throughput: 0: 12830.3. Samples: 57077168. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-11 11:50:32,811][04011] Avg episode reward: [(0, '32.001')] [2023-03-11 11:50:35,328][04298] Updated weights for policy 0, policy_version 111600 (0.0004) [2023-03-11 11:50:37,811][04011] Fps is (10 sec: 13107.1, 60 sec: 12834.1, 300 sec: 12315.8). Total num frames: 57167872. Throughput: 0: 12853.1. Samples: 57155596. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-11 11:50:37,812][04011] Avg episode reward: [(0, '31.678')] [2023-03-11 11:50:37,872][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000111664_57171968.pth... [2023-03-11 11:50:37,874][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000110904_56782848.pth [2023-03-11 11:50:38,588][04298] Updated weights for policy 0, policy_version 111680 (0.0004) [2023-03-11 11:50:41,876][04298] Updated weights for policy 0, policy_version 111760 (0.0004) [2023-03-11 11:50:42,811][04011] Fps is (10 sec: 12697.6, 60 sec: 12765.9, 300 sec: 12329.7). Total num frames: 57229312. Throughput: 0: 12828.8. Samples: 57229376. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:50:42,812][04011] Avg episode reward: [(0, '31.819')] [2023-03-11 11:50:45,263][04298] Updated weights for policy 0, policy_version 111840 (0.0005) [2023-03-11 11:50:47,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12765.9, 300 sec: 12329.7). Total num frames: 57290752. Throughput: 0: 12779.4. Samples: 57266168. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:50:47,822][04011] Avg episode reward: [(0, '31.931')] [2023-03-11 11:50:48,640][04298] Updated weights for policy 0, policy_version 111920 (0.0005) [2023-03-11 11:50:52,107][04298] Updated weights for policy 0, policy_version 112000 (0.0005) [2023-03-11 11:50:52,811][04011] Fps is (10 sec: 12287.9, 60 sec: 12697.6, 300 sec: 12343.5). Total num frames: 57352192. Throughput: 0: 12676.1. Samples: 57337124. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:50:52,812][04011] Avg episode reward: [(0, '28.657')] [2023-03-11 11:50:52,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000112016_57352192.pth... [2023-03-11 11:50:52,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000111280_56975360.pth [2023-03-11 11:50:55,468][04298] Updated weights for policy 0, policy_version 112080 (0.0005) [2023-03-11 11:50:57,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12629.3, 300 sec: 12343.5). Total num frames: 57413632. Throughput: 0: 12574.9. Samples: 57410784. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:50:57,811][04011] Avg episode reward: [(0, '30.762')] [2023-03-11 11:50:58,803][04298] Updated weights for policy 0, policy_version 112160 (0.0004) [2023-03-11 11:51:02,257][04298] Updated weights for policy 0, policy_version 112240 (0.0005) [2023-03-11 11:51:02,811][04011] Fps is (10 sec: 11878.5, 60 sec: 12561.1, 300 sec: 12329.7). Total num frames: 57470976. Throughput: 0: 12519.2. Samples: 57446416. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:51:02,811][04011] Avg episode reward: [(0, '31.316')] [2023-03-11 11:51:05,623][04298] Updated weights for policy 0, policy_version 112320 (0.0005) [2023-03-11 11:51:07,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12492.8, 300 sec: 12343.5). Total num frames: 57532416. Throughput: 0: 12453.0. Samples: 57519424. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:51:07,811][04011] Avg episode reward: [(0, '31.328')] [2023-03-11 11:51:07,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000112368_57532416.pth... [2023-03-11 11:51:07,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000111664_57171968.pth [2023-03-11 11:51:09,014][04298] Updated weights for policy 0, policy_version 112400 (0.0005) [2023-03-11 11:51:12,443][04298] Updated weights for policy 0, policy_version 112480 (0.0005) [2023-03-11 11:51:12,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12424.5, 300 sec: 12329.7). Total num frames: 57593856. Throughput: 0: 12315.4. Samples: 57591068. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:51:12,811][04011] Avg episode reward: [(0, '29.026')] [2023-03-11 11:51:15,848][04298] Updated weights for policy 0, policy_version 112560 (0.0005) [2023-03-11 11:51:17,811][04011] Fps is (10 sec: 11878.5, 60 sec: 12356.3, 300 sec: 12301.9). Total num frames: 57651200. Throughput: 0: 12212.5. Samples: 57626728. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:51:17,811][04011] Avg episode reward: [(0, '30.463')] [2023-03-11 11:51:19,262][04298] Updated weights for policy 0, policy_version 112640 (0.0005) [2023-03-11 11:51:22,635][04298] Updated weights for policy 0, policy_version 112720 (0.0005) [2023-03-11 11:51:22,811][04011] Fps is (10 sec: 11878.3, 60 sec: 12356.2, 300 sec: 12274.1). Total num frames: 57712640. Throughput: 0: 12101.3. Samples: 57700156. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:51:22,811][04011] Avg episode reward: [(0, '31.732')] [2023-03-11 11:51:22,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000112720_57712640.pth... [2023-03-11 11:51:22,816][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000112016_57352192.pth [2023-03-11 11:51:26,132][04298] Updated weights for policy 0, policy_version 112800 (0.0005) [2023-03-11 11:51:27,811][04011] Fps is (10 sec: 11878.3, 60 sec: 12219.7, 300 sec: 12246.3). Total num frames: 57769984. Throughput: 0: 12017.2. Samples: 57770148. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:51:27,812][04011] Avg episode reward: [(0, '32.618')] [2023-03-11 11:51:29,565][04298] Updated weights for policy 0, policy_version 112880 (0.0005) [2023-03-11 11:51:32,811][04011] Fps is (10 sec: 11878.5, 60 sec: 12151.5, 300 sec: 12260.2). Total num frames: 57831424. Throughput: 0: 11998.7. Samples: 57806108. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:51:32,811][04011] Avg episode reward: [(0, '31.746')] [2023-03-11 11:51:33,089][04298] Updated weights for policy 0, policy_version 112960 (0.0005) [2023-03-11 11:51:36,387][04298] Updated weights for policy 0, policy_version 113040 (0.0005) [2023-03-11 11:51:37,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12083.2, 300 sec: 12274.1). Total num frames: 57892864. Throughput: 0: 12035.4. Samples: 57878716. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:51:37,811][04011] Avg episode reward: [(0, '32.211')] [2023-03-11 11:51:37,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000113072_57892864.pth... [2023-03-11 11:51:37,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000112368_57532416.pth [2023-03-11 11:51:39,892][04298] Updated weights for policy 0, policy_version 113120 (0.0005) [2023-03-11 11:51:42,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12014.9, 300 sec: 12260.2). Total num frames: 57950208. Throughput: 0: 11987.2. Samples: 57950208. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:51:42,811][04011] Avg episode reward: [(0, '32.418')] [2023-03-11 11:51:43,304][04298] Updated weights for policy 0, policy_version 113200 (0.0005) [2023-03-11 11:51:46,684][04298] Updated weights for policy 0, policy_version 113280 (0.0005) [2023-03-11 11:51:47,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12014.9, 300 sec: 12274.1). Total num frames: 58011648. Throughput: 0: 11992.5. Samples: 57986080. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:51:47,811][04011] Avg episode reward: [(0, '32.457')] [2023-03-11 11:51:50,092][04298] Updated weights for policy 0, policy_version 113360 (0.0005) [2023-03-11 11:51:52,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12014.9, 300 sec: 12274.1). Total num frames: 58073088. Throughput: 0: 11962.5. Samples: 58057736. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:51:52,811][04011] Avg episode reward: [(0, '31.257')] [2023-03-11 11:51:52,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000113424_58073088.pth... [2023-03-11 11:51:52,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000112720_57712640.pth [2023-03-11 11:51:53,404][04298] Updated weights for policy 0, policy_version 113440 (0.0005) [2023-03-11 11:51:56,748][04298] Updated weights for policy 0, policy_version 113520 (0.0005) [2023-03-11 11:51:57,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12014.9, 300 sec: 12274.1). Total num frames: 58134528. Throughput: 0: 12024.0. Samples: 58132148. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:51:57,811][04011] Avg episode reward: [(0, '31.997')] [2023-03-11 11:52:00,057][04298] Updated weights for policy 0, policy_version 113600 (0.0005) [2023-03-11 11:52:02,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12083.2, 300 sec: 12288.0). Total num frames: 58195968. Throughput: 0: 12056.4. Samples: 58169268. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:52:02,811][04011] Avg episode reward: [(0, '30.884')] [2023-03-11 11:52:03,440][04298] Updated weights for policy 0, policy_version 113680 (0.0005) [2023-03-11 11:52:06,896][04298] Updated weights for policy 0, policy_version 113760 (0.0005) [2023-03-11 11:52:07,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12014.9, 300 sec: 12288.0). Total num frames: 58253312. Throughput: 0: 12020.7. Samples: 58241088. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:52:07,811][04011] Avg episode reward: [(0, '31.875')] [2023-03-11 11:52:07,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000113776_58253312.pth... [2023-03-11 11:52:07,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000113072_57892864.pth [2023-03-11 11:52:10,387][04298] Updated weights for policy 0, policy_version 113840 (0.0005) [2023-03-11 11:52:12,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12014.9, 300 sec: 12288.0). Total num frames: 58314752. Throughput: 0: 12050.5. Samples: 58312420. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:52:12,811][04011] Avg episode reward: [(0, '30.408')] [2023-03-11 11:52:13,845][04298] Updated weights for policy 0, policy_version 113920 (0.0005) [2023-03-11 11:52:17,248][04298] Updated weights for policy 0, policy_version 114000 (0.0005) [2023-03-11 11:52:17,811][04011] Fps is (10 sec: 11878.5, 60 sec: 12014.9, 300 sec: 12274.1). Total num frames: 58372096. Throughput: 0: 12031.4. Samples: 58347520. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:52:17,811][04011] Avg episode reward: [(0, '30.534')] [2023-03-11 11:52:20,644][04298] Updated weights for policy 0, policy_version 114080 (0.0005) [2023-03-11 11:52:22,811][04011] Fps is (10 sec: 11878.3, 60 sec: 12014.9, 300 sec: 12288.0). Total num frames: 58433536. Throughput: 0: 12032.1. Samples: 58420160. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:52:22,811][04011] Avg episode reward: [(0, '28.690')] [2023-03-11 11:52:22,814][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000114128_58433536.pth... [2023-03-11 11:52:22,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000113424_58073088.pth [2023-03-11 11:52:24,103][04298] Updated weights for policy 0, policy_version 114160 (0.0005) [2023-03-11 11:52:27,505][04298] Updated weights for policy 0, policy_version 114240 (0.0005) [2023-03-11 11:52:27,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12014.9, 300 sec: 12274.1). Total num frames: 58490880. Throughput: 0: 12020.5. Samples: 58491128. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:52:27,811][04011] Avg episode reward: [(0, '30.378')] [2023-03-11 11:52:30,983][04298] Updated weights for policy 0, policy_version 114320 (0.0005) [2023-03-11 11:52:32,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12014.9, 300 sec: 12274.1). Total num frames: 58552320. Throughput: 0: 12037.0. Samples: 58527744. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:52:32,811][04011] Avg episode reward: [(0, '30.746')] [2023-03-11 11:52:34,330][04298] Updated weights for policy 0, policy_version 114400 (0.0005) [2023-03-11 11:52:37,703][04298] Updated weights for policy 0, policy_version 114480 (0.0005) [2023-03-11 11:52:37,811][04011] Fps is (10 sec: 12287.9, 60 sec: 12014.9, 300 sec: 12288.0). Total num frames: 58613760. Throughput: 0: 12048.2. Samples: 58599904. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:52:37,811][04011] Avg episode reward: [(0, '32.005')] [2023-03-11 11:52:37,814][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000114480_58613760.pth... [2023-03-11 11:52:37,816][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000113776_58253312.pth [2023-03-11 11:52:40,947][04298] Updated weights for policy 0, policy_version 114560 (0.0005) [2023-03-11 11:52:42,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12083.2, 300 sec: 12288.0). Total num frames: 58675200. Throughput: 0: 12048.1. Samples: 58674312. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:52:42,811][04011] Avg episode reward: [(0, '31.980')] [2023-03-11 11:52:44,388][04298] Updated weights for policy 0, policy_version 114640 (0.0004) [2023-03-11 11:52:47,719][04298] Updated weights for policy 0, policy_version 114720 (0.0005) [2023-03-11 11:52:47,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12083.2, 300 sec: 12301.9). Total num frames: 58736640. Throughput: 0: 12009.2. Samples: 58709680. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:52:47,811][04011] Avg episode reward: [(0, '32.465')] [2023-03-11 11:52:51,124][04298] Updated weights for policy 0, policy_version 114800 (0.0005) [2023-03-11 11:52:52,811][04011] Fps is (10 sec: 11878.2, 60 sec: 12014.9, 300 sec: 12288.0). Total num frames: 58793984. Throughput: 0: 12037.5. Samples: 58782776. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:52:52,812][04011] Avg episode reward: [(0, '31.147')] [2023-03-11 11:52:52,875][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000114840_58798080.pth... [2023-03-11 11:52:52,877][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000114128_58433536.pth [2023-03-11 11:52:54,665][04298] Updated weights for policy 0, policy_version 114880 (0.0005) [2023-03-11 11:52:57,811][04011] Fps is (10 sec: 11468.8, 60 sec: 11946.7, 300 sec: 12288.0). Total num frames: 58851328. Throughput: 0: 11990.4. Samples: 58851988. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:52:57,811][04011] Avg episode reward: [(0, '32.337')] [2023-03-11 11:52:58,190][04298] Updated weights for policy 0, policy_version 114960 (0.0005) [2023-03-11 11:53:01,675][04298] Updated weights for policy 0, policy_version 115040 (0.0005) [2023-03-11 11:53:02,811][04011] Fps is (10 sec: 11878.5, 60 sec: 11946.7, 300 sec: 12288.0). Total num frames: 58912768. Throughput: 0: 12013.5. Samples: 58888128. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:53:02,812][04011] Avg episode reward: [(0, '31.549')] [2023-03-11 11:53:05,036][04298] Updated weights for policy 0, policy_version 115120 (0.0005) [2023-03-11 11:53:07,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12014.9, 300 sec: 12288.0). Total num frames: 58974208. Throughput: 0: 11989.2. Samples: 58959672. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:53:07,811][04011] Avg episode reward: [(0, '32.211')] [2023-03-11 11:53:07,814][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000115184_58974208.pth... [2023-03-11 11:53:07,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000114480_58613760.pth [2023-03-11 11:53:08,353][04298] Updated weights for policy 0, policy_version 115200 (0.0005) [2023-03-11 11:53:11,737][04298] Updated weights for policy 0, policy_version 115280 (0.0005) [2023-03-11 11:53:12,811][04011] Fps is (10 sec: 12288.1, 60 sec: 12014.9, 300 sec: 12301.9). Total num frames: 59035648. Throughput: 0: 12035.8. Samples: 59032740. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:53:12,811][04011] Avg episode reward: [(0, '32.331')] [2023-03-11 11:53:15,155][04298] Updated weights for policy 0, policy_version 115360 (0.0005) [2023-03-11 11:53:17,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12014.9, 300 sec: 12288.0). Total num frames: 59092992. Throughput: 0: 12016.5. Samples: 59068488. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:53:17,812][04011] Avg episode reward: [(0, '32.341')] [2023-03-11 11:53:18,680][04298] Updated weights for policy 0, policy_version 115440 (0.0005) [2023-03-11 11:53:22,097][04298] Updated weights for policy 0, policy_version 115520 (0.0005) [2023-03-11 11:53:22,811][04011] Fps is (10 sec: 11878.3, 60 sec: 12014.9, 300 sec: 12301.9). Total num frames: 59154432. Throughput: 0: 11995.3. Samples: 59139692. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:53:22,812][04011] Avg episode reward: [(0, '31.703')] [2023-03-11 11:53:22,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000115536_59154432.pth... [2023-03-11 11:53:22,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000114840_58798080.pth [2023-03-11 11:53:25,467][04298] Updated weights for policy 0, policy_version 115600 (0.0005) [2023-03-11 11:53:27,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12083.2, 300 sec: 12301.9). Total num frames: 59215872. Throughput: 0: 11988.9. Samples: 59213812. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:53:27,812][04011] Avg episode reward: [(0, '32.100')] [2023-03-11 11:53:28,613][04298] Updated weights for policy 0, policy_version 115680 (0.0004) [2023-03-11 11:53:31,960][04298] Updated weights for policy 0, policy_version 115760 (0.0005) [2023-03-11 11:53:32,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12083.2, 300 sec: 12301.9). Total num frames: 59277312. Throughput: 0: 12068.2. Samples: 59252748. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:53:32,812][04011] Avg episode reward: [(0, '32.630')] [2023-03-11 11:53:35,379][04298] Updated weights for policy 0, policy_version 115840 (0.0005) [2023-03-11 11:53:37,811][04011] Fps is (10 sec: 11878.5, 60 sec: 12014.9, 300 sec: 12301.9). Total num frames: 59334656. Throughput: 0: 12014.1. Samples: 59323408. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:53:37,811][04011] Avg episode reward: [(0, '32.165')] [2023-03-11 11:53:37,849][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000115896_59338752.pth... [2023-03-11 11:53:37,851][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000115184_58974208.pth [2023-03-11 11:53:38,878][04298] Updated weights for policy 0, policy_version 115920 (0.0005) [2023-03-11 11:53:42,408][04298] Updated weights for policy 0, policy_version 116000 (0.0005) [2023-03-11 11:53:42,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12014.9, 300 sec: 12301.9). Total num frames: 59396096. Throughput: 0: 12042.2. Samples: 59393888. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:53:42,811][04011] Avg episode reward: [(0, '31.747')] [2023-03-11 11:53:45,924][04298] Updated weights for policy 0, policy_version 116080 (0.0005) [2023-03-11 11:53:47,811][04011] Fps is (10 sec: 11878.4, 60 sec: 11946.7, 300 sec: 12301.9). Total num frames: 59453440. Throughput: 0: 12016.7. Samples: 59428880. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 11:53:47,811][04011] Avg episode reward: [(0, '31.951')] [2023-03-11 11:53:49,363][04298] Updated weights for policy 0, policy_version 116160 (0.0005) [2023-03-11 11:53:52,664][04298] Updated weights for policy 0, policy_version 116240 (0.0004) [2023-03-11 11:53:52,811][04011] Fps is (10 sec: 11878.3, 60 sec: 12014.9, 300 sec: 12301.9). Total num frames: 59514880. Throughput: 0: 11997.9. Samples: 59499576. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 11:53:52,812][04011] Avg episode reward: [(0, '32.775')] [2023-03-11 11:53:52,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000116240_59514880.pth... [2023-03-11 11:53:52,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000115536_59154432.pth [2023-03-11 11:53:55,826][04298] Updated weights for policy 0, policy_version 116320 (0.0003) [2023-03-11 11:53:57,811][04011] Fps is (10 sec: 12697.6, 60 sec: 12151.5, 300 sec: 12301.9). Total num frames: 59580416. Throughput: 0: 12125.5. Samples: 59578388. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 11:53:57,811][04011] Avg episode reward: [(0, '32.310')] [2023-03-11 11:53:58,948][04298] Updated weights for policy 0, policy_version 116400 (0.0004) [2023-03-11 11:54:02,056][04298] Updated weights for policy 0, policy_version 116480 (0.0004) [2023-03-11 11:54:02,811][04011] Fps is (10 sec: 13107.3, 60 sec: 12219.7, 300 sec: 12301.9). Total num frames: 59645952. Throughput: 0: 12215.9. Samples: 59618204. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 11:54:02,811][04011] Avg episode reward: [(0, '32.809')] [2023-03-11 11:54:05,141][04298] Updated weights for policy 0, policy_version 116560 (0.0004) [2023-03-11 11:54:07,811][04011] Fps is (10 sec: 12697.4, 60 sec: 12219.7, 300 sec: 12288.0). Total num frames: 59707392. Throughput: 0: 12348.1. Samples: 59695360. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 11:54:07,812][04011] Avg episode reward: [(0, '32.373')] [2023-03-11 11:54:07,869][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000116624_59711488.pth... [2023-03-11 11:54:07,871][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000115896_59338752.pth [2023-03-11 11:54:08,576][04298] Updated weights for policy 0, policy_version 116640 (0.0005) [2023-03-11 11:54:11,968][04298] Updated weights for policy 0, policy_version 116720 (0.0006) [2023-03-11 11:54:12,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12219.7, 300 sec: 12274.1). Total num frames: 59768832. Throughput: 0: 12311.9. Samples: 59767848. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 11:54:12,811][04011] Avg episode reward: [(0, '32.585')] [2023-03-11 11:54:15,408][04298] Updated weights for policy 0, policy_version 116800 (0.0006) [2023-03-11 11:54:17,811][04011] Fps is (10 sec: 12288.3, 60 sec: 12288.0, 300 sec: 12274.1). Total num frames: 59830272. Throughput: 0: 12238.2. Samples: 59803464. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 11:54:17,811][04011] Avg episode reward: [(0, '32.888')] [2023-03-11 11:54:18,849][04298] Updated weights for policy 0, policy_version 116880 (0.0006) [2023-03-11 11:54:22,294][04298] Updated weights for policy 0, policy_version 116960 (0.0006) [2023-03-11 11:54:22,811][04011] Fps is (10 sec: 11878.3, 60 sec: 12219.7, 300 sec: 12260.2). Total num frames: 59887616. Throughput: 0: 12264.9. Samples: 59875328. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 11:54:22,812][04011] Avg episode reward: [(0, '28.165')] [2023-03-11 11:54:22,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000116968_59887616.pth... [2023-03-11 11:54:22,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000116240_59514880.pth [2023-03-11 11:54:25,636][04298] Updated weights for policy 0, policy_version 117040 (0.0006) [2023-03-11 11:54:27,811][04011] Fps is (10 sec: 11878.3, 60 sec: 12219.7, 300 sec: 12246.3). Total num frames: 59949056. Throughput: 0: 12326.6. Samples: 59948584. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 11:54:27,811][04011] Avg episode reward: [(0, '31.689')] [2023-03-11 11:54:29,027][04298] Updated weights for policy 0, policy_version 117120 (0.0006) [2023-03-11 11:54:32,448][04298] Updated weights for policy 0, policy_version 117200 (0.0006) [2023-03-11 11:54:32,811][04011] Fps is (10 sec: 12288.1, 60 sec: 12219.8, 300 sec: 12246.4). Total num frames: 60010496. Throughput: 0: 12335.2. Samples: 59983964. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 11:54:32,811][04011] Avg episode reward: [(0, '32.997')] [2023-03-11 11:54:35,856][04298] Updated weights for policy 0, policy_version 117280 (0.0005) [2023-03-11 11:54:37,811][04011] Fps is (10 sec: 11878.2, 60 sec: 12219.7, 300 sec: 12218.6). Total num frames: 60067840. Throughput: 0: 12356.7. Samples: 60055628. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 11:54:37,812][04011] Avg episode reward: [(0, '31.629')] [2023-03-11 11:54:37,837][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000117328_60071936.pth... [2023-03-11 11:54:37,839][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000116624_59711488.pth [2023-03-11 11:54:39,212][04298] Updated weights for policy 0, policy_version 117360 (0.0005) [2023-03-11 11:54:42,697][04298] Updated weights for policy 0, policy_version 117440 (0.0006) [2023-03-11 11:54:42,811][04011] Fps is (10 sec: 11878.3, 60 sec: 12219.7, 300 sec: 12218.6). Total num frames: 60129280. Throughput: 0: 12213.5. Samples: 60127996. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 11:54:42,812][04011] Avg episode reward: [(0, '32.526')] [2023-03-11 11:54:46,001][04298] Updated weights for policy 0, policy_version 117520 (0.0004) [2023-03-11 11:54:47,811][04011] Fps is (10 sec: 12288.3, 60 sec: 12288.0, 300 sec: 12204.7). Total num frames: 60190720. Throughput: 0: 12162.9. Samples: 60165536. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:54:47,811][04011] Avg episode reward: [(0, '32.051')] [2023-03-11 11:54:49,364][04298] Updated weights for policy 0, policy_version 117600 (0.0005) [2023-03-11 11:54:52,811][04011] Fps is (10 sec: 11878.5, 60 sec: 12219.8, 300 sec: 12176.9). Total num frames: 60248064. Throughput: 0: 12031.3. Samples: 60236764. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:54:52,811][04011] Avg episode reward: [(0, '31.481')] [2023-03-11 11:54:52,812][04298] Updated weights for policy 0, policy_version 117680 (0.0006) [2023-03-11 11:54:52,813][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000117680_60252160.pth... [2023-03-11 11:54:52,815][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000116968_59887616.pth [2023-03-11 11:54:56,127][04298] Updated weights for policy 0, policy_version 117760 (0.0006) [2023-03-11 11:54:57,811][04011] Fps is (10 sec: 11878.3, 60 sec: 12151.5, 300 sec: 12176.9). Total num frames: 60309504. Throughput: 0: 12042.5. Samples: 60309760. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:54:57,812][04011] Avg episode reward: [(0, '30.326')] [2023-03-11 11:54:59,528][04298] Updated weights for policy 0, policy_version 117840 (0.0005) [2023-03-11 11:55:02,811][04011] Fps is (10 sec: 12287.9, 60 sec: 12083.2, 300 sec: 12163.0). Total num frames: 60370944. Throughput: 0: 12065.9. Samples: 60346432. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:55:02,812][04011] Avg episode reward: [(0, '32.776')] [2023-03-11 11:55:02,907][04298] Updated weights for policy 0, policy_version 117920 (0.0006) [2023-03-11 11:55:06,254][04298] Updated weights for policy 0, policy_version 118000 (0.0005) [2023-03-11 11:55:07,811][04011] Fps is (10 sec: 12288.1, 60 sec: 12083.2, 300 sec: 12149.2). Total num frames: 60432384. Throughput: 0: 12106.0. Samples: 60420096. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:55:07,812][04011] Avg episode reward: [(0, '33.151')] [2023-03-11 11:55:07,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000118032_60432384.pth... [2023-03-11 11:55:07,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000117328_60071936.pth [2023-03-11 11:55:09,743][04298] Updated weights for policy 0, policy_version 118080 (0.0006) [2023-03-11 11:55:12,811][04011] Fps is (10 sec: 11878.3, 60 sec: 12014.9, 300 sec: 12135.3). Total num frames: 60489728. Throughput: 0: 12036.5. Samples: 60490228. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:55:12,812][04011] Avg episode reward: [(0, '31.611')] [2023-03-11 11:55:13,148][04298] Updated weights for policy 0, policy_version 118160 (0.0005) [2023-03-11 11:55:16,624][04298] Updated weights for policy 0, policy_version 118240 (0.0005) [2023-03-11 11:55:17,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12014.9, 300 sec: 12135.3). Total num frames: 60551168. Throughput: 0: 12058.4. Samples: 60526592. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:55:17,811][04011] Avg episode reward: [(0, '32.318')] [2023-03-11 11:55:19,980][04298] Updated weights for policy 0, policy_version 118320 (0.0006) [2023-03-11 11:55:22,811][04011] Fps is (10 sec: 12288.1, 60 sec: 12083.2, 300 sec: 12121.4). Total num frames: 60612608. Throughput: 0: 12066.2. Samples: 60598604. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:55:22,811][04011] Avg episode reward: [(0, '32.734')] [2023-03-11 11:55:22,814][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000118384_60612608.pth... [2023-03-11 11:55:22,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000117680_60252160.pth [2023-03-11 11:55:23,510][04298] Updated weights for policy 0, policy_version 118400 (0.0005) [2023-03-11 11:55:26,939][04298] Updated weights for policy 0, policy_version 118480 (0.0005) [2023-03-11 11:55:27,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12014.9, 300 sec: 12093.6). Total num frames: 60669952. Throughput: 0: 12029.6. Samples: 60669328. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:55:27,811][04011] Avg episode reward: [(0, '28.550')] [2023-03-11 11:55:30,427][04298] Updated weights for policy 0, policy_version 118560 (0.0006) [2023-03-11 11:55:32,811][04011] Fps is (10 sec: 11878.5, 60 sec: 12014.9, 300 sec: 12079.7). Total num frames: 60731392. Throughput: 0: 11966.4. Samples: 60704024. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:55:32,811][04011] Avg episode reward: [(0, '16.673')] [2023-03-11 11:55:33,818][04298] Updated weights for policy 0, policy_version 118640 (0.0006) [2023-03-11 11:55:37,301][04298] Updated weights for policy 0, policy_version 118720 (0.0006) [2023-03-11 11:55:37,811][04011] Fps is (10 sec: 11878.3, 60 sec: 12015.0, 300 sec: 12065.8). Total num frames: 60788736. Throughput: 0: 11993.1. Samples: 60776456. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:55:37,812][04011] Avg episode reward: [(0, '32.294')] [2023-03-11 11:55:37,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000118728_60788736.pth... [2023-03-11 11:55:37,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000118032_60432384.pth [2023-03-11 11:55:40,800][04298] Updated weights for policy 0, policy_version 118800 (0.0005) [2023-03-11 11:55:42,811][04011] Fps is (10 sec: 11468.6, 60 sec: 11946.6, 300 sec: 12052.0). Total num frames: 60846080. Throughput: 0: 11920.0. Samples: 60846160. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:55:42,812][04011] Avg episode reward: [(0, '31.240')] [2023-03-11 11:55:44,233][04298] Updated weights for policy 0, policy_version 118880 (0.0005) [2023-03-11 11:55:47,653][04298] Updated weights for policy 0, policy_version 118960 (0.0005) [2023-03-11 11:55:47,811][04011] Fps is (10 sec: 11878.4, 60 sec: 11946.7, 300 sec: 12052.0). Total num frames: 60907520. Throughput: 0: 11912.8. Samples: 60882508. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:55:47,822][04011] Avg episode reward: [(0, '32.507')] [2023-03-11 11:55:50,960][04298] Updated weights for policy 0, policy_version 119040 (0.0005) [2023-03-11 11:55:52,811][04011] Fps is (10 sec: 12697.7, 60 sec: 12083.2, 300 sec: 12065.8). Total num frames: 60973056. Throughput: 0: 11925.3. Samples: 60956736. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:55:52,811][04011] Avg episode reward: [(0, '32.485')] [2023-03-11 11:55:52,814][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000119088_60973056.pth... [2023-03-11 11:55:52,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000118384_60612608.pth [2023-03-11 11:55:53,970][04298] Updated weights for policy 0, policy_version 119120 (0.0003) [2023-03-11 11:55:57,196][04298] Updated weights for policy 0, policy_version 119200 (0.0005) [2023-03-11 11:55:57,811][04011] Fps is (10 sec: 12697.5, 60 sec: 12083.2, 300 sec: 12079.7). Total num frames: 61034496. Throughput: 0: 12096.4. Samples: 61034568. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:55:57,812][04011] Avg episode reward: [(0, '32.351')] [2023-03-11 11:56:00,547][04298] Updated weights for policy 0, policy_version 119280 (0.0006) [2023-03-11 11:56:02,811][04011] Fps is (10 sec: 12288.1, 60 sec: 12083.2, 300 sec: 12079.7). Total num frames: 61095936. Throughput: 0: 12107.4. Samples: 61071424. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:56:02,811][04011] Avg episode reward: [(0, '31.597')] [2023-03-11 11:56:04,001][04298] Updated weights for policy 0, policy_version 119360 (0.0005) [2023-03-11 11:56:07,300][04298] Updated weights for policy 0, policy_version 119440 (0.0005) [2023-03-11 11:56:07,811][04011] Fps is (10 sec: 12288.1, 60 sec: 12083.2, 300 sec: 12079.7). Total num frames: 61157376. Throughput: 0: 12116.2. Samples: 61143832. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:56:07,812][04011] Avg episode reward: [(0, '31.601')] [2023-03-11 11:56:07,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000119448_61157376.pth... [2023-03-11 11:56:07,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000118728_60788736.pth [2023-03-11 11:56:10,745][04298] Updated weights for policy 0, policy_version 119520 (0.0006) [2023-03-11 11:56:12,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12151.5, 300 sec: 12093.6). Total num frames: 61218816. Throughput: 0: 12184.8. Samples: 61217644. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:56:12,811][04011] Avg episode reward: [(0, '31.528')] [2023-03-11 11:56:13,922][04298] Updated weights for policy 0, policy_version 119600 (0.0005) [2023-03-11 11:56:17,050][04298] Updated weights for policy 0, policy_version 119680 (0.0005) [2023-03-11 11:56:17,811][04011] Fps is (10 sec: 12697.6, 60 sec: 12219.7, 300 sec: 12107.5). Total num frames: 61284352. Throughput: 0: 12270.7. Samples: 61256208. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:56:17,811][04011] Avg episode reward: [(0, '31.783')] [2023-03-11 11:56:20,233][04298] Updated weights for policy 0, policy_version 119760 (0.0005) [2023-03-11 11:56:22,811][04011] Fps is (10 sec: 13107.2, 60 sec: 12288.0, 300 sec: 12135.3). Total num frames: 61349888. Throughput: 0: 12401.2. Samples: 61334508. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:56:22,811][04011] Avg episode reward: [(0, '31.672')] [2023-03-11 11:56:22,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000119824_61349888.pth... [2023-03-11 11:56:22,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000119088_60973056.pth [2023-03-11 11:56:23,349][04298] Updated weights for policy 0, policy_version 119840 (0.0004) [2023-03-11 11:56:26,879][04298] Updated weights for policy 0, policy_version 119920 (0.0006) [2023-03-11 11:56:27,811][04011] Fps is (10 sec: 12288.1, 60 sec: 12288.0, 300 sec: 12121.4). Total num frames: 61407232. Throughput: 0: 12469.7. Samples: 61407296. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:56:27,811][04011] Avg episode reward: [(0, '30.632')] [2023-03-11 11:56:30,197][04298] Updated weights for policy 0, policy_version 120000 (0.0006) [2023-03-11 11:56:32,811][04011] Fps is (10 sec: 11878.5, 60 sec: 12288.0, 300 sec: 12121.4). Total num frames: 61468672. Throughput: 0: 12481.2. Samples: 61444160. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:56:32,811][04011] Avg episode reward: [(0, '30.430')] [2023-03-11 11:56:33,595][04298] Updated weights for policy 0, policy_version 120080 (0.0006) [2023-03-11 11:56:36,949][04298] Updated weights for policy 0, policy_version 120160 (0.0005) [2023-03-11 11:56:37,811][04011] Fps is (10 sec: 12287.9, 60 sec: 12356.3, 300 sec: 12135.3). Total num frames: 61530112. Throughput: 0: 12458.1. Samples: 61517348. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:56:37,812][04011] Avg episode reward: [(0, '31.589')] [2023-03-11 11:56:37,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000120176_61530112.pth... [2023-03-11 11:56:37,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000119448_61157376.pth [2023-03-11 11:56:40,317][04298] Updated weights for policy 0, policy_version 120240 (0.0006) [2023-03-11 11:56:42,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12424.6, 300 sec: 12135.3). Total num frames: 61591552. Throughput: 0: 12332.6. Samples: 61589532. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:56:42,811][04011] Avg episode reward: [(0, '31.696')] [2023-03-11 11:56:43,757][04298] Updated weights for policy 0, policy_version 120320 (0.0006) [2023-03-11 11:56:47,188][04298] Updated weights for policy 0, policy_version 120400 (0.0006) [2023-03-11 11:56:47,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12356.3, 300 sec: 12121.4). Total num frames: 61648896. Throughput: 0: 12296.7. Samples: 61624776. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:56:47,811][04011] Avg episode reward: [(0, '31.783')] [2023-03-11 11:56:50,632][04298] Updated weights for policy 0, policy_version 120480 (0.0005) [2023-03-11 11:56:52,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12356.3, 300 sec: 12135.3). Total num frames: 61714432. Throughput: 0: 12317.3. Samples: 61698112. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:56:52,812][04011] Avg episode reward: [(0, '32.802')] [2023-03-11 11:56:52,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000120536_61714432.pth... [2023-03-11 11:56:52,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000119824_61349888.pth [2023-03-11 11:56:53,700][04298] Updated weights for policy 0, policy_version 120560 (0.0004) [2023-03-11 11:56:56,711][04298] Updated weights for policy 0, policy_version 120640 (0.0004) [2023-03-11 11:56:57,811][04011] Fps is (10 sec: 13107.2, 60 sec: 12424.6, 300 sec: 12149.2). Total num frames: 61779968. Throughput: 0: 12480.6. Samples: 61779272. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:56:57,811][04011] Avg episode reward: [(0, '32.216')] [2023-03-11 11:56:59,709][04298] Updated weights for policy 0, policy_version 120720 (0.0004) [2023-03-11 11:57:02,737][04298] Updated weights for policy 0, policy_version 120800 (0.0004) [2023-03-11 11:57:02,811][04011] Fps is (10 sec: 13516.8, 60 sec: 12561.1, 300 sec: 12190.8). Total num frames: 61849600. Throughput: 0: 12537.4. Samples: 61820392. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:57:02,811][04011] Avg episode reward: [(0, '32.627')] [2023-03-11 11:57:05,806][04298] Updated weights for policy 0, policy_version 120880 (0.0004) [2023-03-11 11:57:07,811][04011] Fps is (10 sec: 13516.7, 60 sec: 12629.3, 300 sec: 12204.7). Total num frames: 61915136. Throughput: 0: 12561.6. Samples: 61899780. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:57:07,811][04011] Avg episode reward: [(0, '32.644')] [2023-03-11 11:57:07,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000120928_61915136.pth... [2023-03-11 11:57:07,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000120176_61530112.pth [2023-03-11 11:57:08,904][04298] Updated weights for policy 0, policy_version 120960 (0.0004) [2023-03-11 11:57:11,929][04298] Updated weights for policy 0, policy_version 121040 (0.0004) [2023-03-11 11:57:12,811][04011] Fps is (10 sec: 13516.9, 60 sec: 12765.9, 300 sec: 12246.3). Total num frames: 61984768. Throughput: 0: 12743.3. Samples: 61980744. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:57:12,811][04011] Avg episode reward: [(0, '31.674')] [2023-03-11 11:57:14,905][04298] Updated weights for policy 0, policy_version 121120 (0.0004) [2023-03-11 11:57:17,811][04011] Fps is (10 sec: 13516.9, 60 sec: 12765.9, 300 sec: 12260.2). Total num frames: 62050304. Throughput: 0: 12834.3. Samples: 62021704. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:57:17,811][04011] Avg episode reward: [(0, '29.470')] [2023-03-11 11:57:18,041][04298] Updated weights for policy 0, policy_version 121200 (0.0005) [2023-03-11 11:57:21,183][04298] Updated weights for policy 0, policy_version 121280 (0.0004) [2023-03-11 11:57:22,811][04011] Fps is (10 sec: 13107.0, 60 sec: 12765.9, 300 sec: 12288.0). Total num frames: 62115840. Throughput: 0: 12945.2. Samples: 62099880. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:57:22,811][04011] Avg episode reward: [(0, '31.755')] [2023-03-11 11:57:22,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000121320_62115840.pth... [2023-03-11 11:57:22,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000120536_61714432.pth [2023-03-11 11:57:24,244][04298] Updated weights for policy 0, policy_version 121360 (0.0004) [2023-03-11 11:57:27,362][04298] Updated weights for policy 0, policy_version 121440 (0.0004) [2023-03-11 11:57:27,811][04011] Fps is (10 sec: 13107.2, 60 sec: 12902.4, 300 sec: 12301.9). Total num frames: 62181376. Throughput: 0: 13115.2. Samples: 62179716. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:57:27,811][04011] Avg episode reward: [(0, '32.711')] [2023-03-11 11:57:30,436][04298] Updated weights for policy 0, policy_version 121520 (0.0004) [2023-03-11 11:57:32,811][04011] Fps is (10 sec: 13107.3, 60 sec: 12970.7, 300 sec: 12315.8). Total num frames: 62246912. Throughput: 0: 13218.0. Samples: 62219584. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:57:32,811][04011] Avg episode reward: [(0, '33.034')] [2023-03-11 11:57:33,519][04298] Updated weights for policy 0, policy_version 121600 (0.0004) [2023-03-11 11:57:36,558][04298] Updated weights for policy 0, policy_version 121680 (0.0004) [2023-03-11 11:57:37,811][04011] Fps is (10 sec: 13516.9, 60 sec: 13107.2, 300 sec: 12343.5). Total num frames: 62316544. Throughput: 0: 13379.1. Samples: 62300168. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:57:37,811][04011] Avg episode reward: [(0, '32.449')] [2023-03-11 11:57:37,814][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000121712_62316544.pth... [2023-03-11 11:57:37,816][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000120928_61915136.pth [2023-03-11 11:57:39,682][04298] Updated weights for policy 0, policy_version 121760 (0.0005) [2023-03-11 11:57:42,811][04011] Fps is (10 sec: 13107.2, 60 sec: 13107.2, 300 sec: 12343.5). Total num frames: 62377984. Throughput: 0: 13309.7. Samples: 62378208. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:57:42,811][04011] Avg episode reward: [(0, '32.585')] [2023-03-11 11:57:42,827][04298] Updated weights for policy 0, policy_version 121840 (0.0004) [2023-03-11 11:57:45,842][04298] Updated weights for policy 0, policy_version 121920 (0.0004) [2023-03-11 11:57:47,811][04011] Fps is (10 sec: 13107.1, 60 sec: 13312.0, 300 sec: 12385.2). Total num frames: 62447616. Throughput: 0: 13302.6. Samples: 62419008. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:57:47,811][04011] Avg episode reward: [(0, '32.139')] [2023-03-11 11:57:48,926][04298] Updated weights for policy 0, policy_version 122000 (0.0005) [2023-03-11 11:57:52,007][04298] Updated weights for policy 0, policy_version 122080 (0.0004) [2023-03-11 11:57:52,811][04011] Fps is (10 sec: 13516.8, 60 sec: 13312.0, 300 sec: 12413.0). Total num frames: 62513152. Throughput: 0: 13315.2. Samples: 62498964. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-11 11:57:52,811][04011] Avg episode reward: [(0, '32.611')] [2023-03-11 11:57:52,814][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000122096_62513152.pth... [2023-03-11 11:57:52,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000121320_62115840.pth [2023-03-11 11:57:55,114][04298] Updated weights for policy 0, policy_version 122160 (0.0004) [2023-03-11 11:57:57,811][04011] Fps is (10 sec: 13107.3, 60 sec: 13312.0, 300 sec: 12426.9). Total num frames: 62578688. Throughput: 0: 13289.3. Samples: 62578764. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-11 11:57:57,811][04011] Avg episode reward: [(0, '32.380')] [2023-03-11 11:57:58,142][04298] Updated weights for policy 0, policy_version 122240 (0.0004) [2023-03-11 11:58:01,154][04298] Updated weights for policy 0, policy_version 122320 (0.0004) [2023-03-11 11:58:02,811][04011] Fps is (10 sec: 13516.8, 60 sec: 13312.0, 300 sec: 12454.6). Total num frames: 62648320. Throughput: 0: 13289.1. Samples: 62619712. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-11 11:58:02,811][04011] Avg episode reward: [(0, '32.094')] [2023-03-11 11:58:04,270][04298] Updated weights for policy 0, policy_version 122400 (0.0005) [2023-03-11 11:58:07,418][04298] Updated weights for policy 0, policy_version 122480 (0.0005) [2023-03-11 11:58:07,811][04011] Fps is (10 sec: 13516.7, 60 sec: 13312.0, 300 sec: 12468.5). Total num frames: 62713856. Throughput: 0: 13297.2. Samples: 62698256. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-11 11:58:07,811][04011] Avg episode reward: [(0, '31.805')] [2023-03-11 11:58:07,814][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000122488_62713856.pth... [2023-03-11 11:58:07,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000121712_62316544.pth [2023-03-11 11:58:10,503][04298] Updated weights for policy 0, policy_version 122560 (0.0004) [2023-03-11 11:58:12,811][04011] Fps is (10 sec: 13107.2, 60 sec: 13243.7, 300 sec: 12496.3). Total num frames: 62779392. Throughput: 0: 13300.9. Samples: 62778256. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-11 11:58:12,811][04011] Avg episode reward: [(0, '32.410')] [2023-03-11 11:58:13,552][04298] Updated weights for policy 0, policy_version 122640 (0.0004) [2023-03-11 11:58:16,670][04298] Updated weights for policy 0, policy_version 122720 (0.0005) [2023-03-11 11:58:17,811][04011] Fps is (10 sec: 13107.3, 60 sec: 13243.7, 300 sec: 12510.2). Total num frames: 62844928. Throughput: 0: 13290.8. Samples: 62817672. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-11 11:58:17,811][04011] Avg episode reward: [(0, '33.081')] [2023-03-11 11:58:19,766][04298] Updated weights for policy 0, policy_version 122800 (0.0004) [2023-03-11 11:58:22,811][04011] Fps is (10 sec: 13107.1, 60 sec: 13243.7, 300 sec: 12524.0). Total num frames: 62910464. Throughput: 0: 13276.0. Samples: 62897588. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-11 11:58:22,812][04011] Avg episode reward: [(0, '32.682')] [2023-03-11 11:58:22,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000122872_62910464.pth... [2023-03-11 11:58:22,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000122096_62513152.pth [2023-03-11 11:58:22,878][04298] Updated weights for policy 0, policy_version 122880 (0.0004) [2023-03-11 11:58:25,978][04298] Updated weights for policy 0, policy_version 122960 (0.0004) [2023-03-11 11:58:27,811][04011] Fps is (10 sec: 13516.8, 60 sec: 13312.0, 300 sec: 12551.8). Total num frames: 62980096. Throughput: 0: 13296.7. Samples: 62976560. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-11 11:58:27,812][04011] Avg episode reward: [(0, '32.493')] [2023-03-11 11:58:29,065][04298] Updated weights for policy 0, policy_version 123040 (0.0005) [2023-03-11 11:58:32,179][04298] Updated weights for policy 0, policy_version 123120 (0.0004) [2023-03-11 11:58:32,811][04011] Fps is (10 sec: 13107.2, 60 sec: 13243.7, 300 sec: 12565.7). Total num frames: 63041536. Throughput: 0: 13278.1. Samples: 63016524. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-11 11:58:32,812][04011] Avg episode reward: [(0, '32.294')] [2023-03-11 11:58:35,318][04298] Updated weights for policy 0, policy_version 123200 (0.0004) [2023-03-11 11:58:37,811][04011] Fps is (10 sec: 13107.1, 60 sec: 13243.7, 300 sec: 12593.5). Total num frames: 63111168. Throughput: 0: 13246.5. Samples: 63095056. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-11 11:58:37,811][04011] Avg episode reward: [(0, '32.578')] [2023-03-11 11:58:37,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000123264_63111168.pth... [2023-03-11 11:58:37,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000122488_62713856.pth [2023-03-11 11:58:38,354][04298] Updated weights for policy 0, policy_version 123280 (0.0004) [2023-03-11 11:58:41,445][04298] Updated weights for policy 0, policy_version 123360 (0.0004) [2023-03-11 11:58:42,811][04011] Fps is (10 sec: 13516.8, 60 sec: 13312.0, 300 sec: 12621.2). Total num frames: 63176704. Throughput: 0: 13261.0. Samples: 63175512. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-11 11:58:42,811][04011] Avg episode reward: [(0, '32.574')] [2023-03-11 11:58:44,507][04298] Updated weights for policy 0, policy_version 123440 (0.0004) [2023-03-11 11:58:47,627][04298] Updated weights for policy 0, policy_version 123520 (0.0005) [2023-03-11 11:58:47,811][04011] Fps is (10 sec: 13107.2, 60 sec: 13243.7, 300 sec: 12635.1). Total num frames: 63242240. Throughput: 0: 13224.9. Samples: 63214832. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-11 11:58:47,811][04011] Avg episode reward: [(0, '32.720')] [2023-03-11 11:58:50,714][04298] Updated weights for policy 0, policy_version 123600 (0.0004) [2023-03-11 11:58:52,811][04011] Fps is (10 sec: 13107.2, 60 sec: 13243.7, 300 sec: 12635.1). Total num frames: 63307776. Throughput: 0: 13250.4. Samples: 63294524. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-11 11:58:52,812][04011] Avg episode reward: [(0, '32.301')] [2023-03-11 11:58:52,814][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000123648_63307776.pth... [2023-03-11 11:58:52,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000122872_62910464.pth [2023-03-11 11:58:53,823][04298] Updated weights for policy 0, policy_version 123680 (0.0004) [2023-03-11 11:58:56,899][04298] Updated weights for policy 0, policy_version 123760 (0.0004) [2023-03-11 11:58:57,811][04011] Fps is (10 sec: 13516.8, 60 sec: 13312.0, 300 sec: 12649.0). Total num frames: 63377408. Throughput: 0: 13235.2. Samples: 63373840. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-11 11:58:57,811][04011] Avg episode reward: [(0, '32.187')] [2023-03-11 11:58:59,914][04298] Updated weights for policy 0, policy_version 123840 (0.0004) [2023-03-11 11:59:02,811][04011] Fps is (10 sec: 13516.9, 60 sec: 13243.7, 300 sec: 12662.9). Total num frames: 63442944. Throughput: 0: 13259.4. Samples: 63414344. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-11 11:59:02,811][04011] Avg episode reward: [(0, '32.202')] [2023-03-11 11:59:02,961][04298] Updated weights for policy 0, policy_version 123920 (0.0004) [2023-03-11 11:59:05,997][04298] Updated weights for policy 0, policy_version 124000 (0.0004) [2023-03-11 11:59:07,811][04011] Fps is (10 sec: 13107.2, 60 sec: 13243.7, 300 sec: 12676.8). Total num frames: 63508480. Throughput: 0: 13285.7. Samples: 63495444. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-11 11:59:07,811][04011] Avg episode reward: [(0, '32.213')] [2023-03-11 11:59:07,872][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000124048_63512576.pth... [2023-03-11 11:59:07,874][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000123264_63111168.pth [2023-03-11 11:59:09,097][04298] Updated weights for policy 0, policy_version 124080 (0.0005) [2023-03-11 11:59:12,178][04298] Updated weights for policy 0, policy_version 124160 (0.0004) [2023-03-11 11:59:12,811][04011] Fps is (10 sec: 13516.8, 60 sec: 13312.0, 300 sec: 12704.5). Total num frames: 63578112. Throughput: 0: 13285.1. Samples: 63574388. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-11 11:59:12,811][04011] Avg episode reward: [(0, '31.731')] [2023-03-11 11:59:15,209][04298] Updated weights for policy 0, policy_version 124240 (0.0004) [2023-03-11 11:59:17,811][04011] Fps is (10 sec: 13516.8, 60 sec: 13312.0, 300 sec: 12732.3). Total num frames: 63643648. Throughput: 0: 13304.6. Samples: 63615232. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-11 11:59:17,811][04011] Avg episode reward: [(0, '31.762')] [2023-03-11 11:59:18,270][04298] Updated weights for policy 0, policy_version 124320 (0.0004) [2023-03-11 11:59:21,595][04298] Updated weights for policy 0, policy_version 124400 (0.0005) [2023-03-11 11:59:22,811][04011] Fps is (10 sec: 13107.2, 60 sec: 13312.0, 300 sec: 12746.2). Total num frames: 63709184. Throughput: 0: 13270.5. Samples: 63692228. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-11 11:59:22,811][04011] Avg episode reward: [(0, '31.929')] [2023-03-11 11:59:22,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000124432_63709184.pth... [2023-03-11 11:59:22,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000123648_63307776.pth [2023-03-11 11:59:24,699][04298] Updated weights for policy 0, policy_version 124480 (0.0004) [2023-03-11 11:59:27,776][04298] Updated weights for policy 0, policy_version 124560 (0.0004) [2023-03-11 11:59:27,811][04011] Fps is (10 sec: 13107.2, 60 sec: 13243.7, 300 sec: 12760.1). Total num frames: 63774720. Throughput: 0: 13248.6. Samples: 63771700. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-11 11:59:27,811][04011] Avg episode reward: [(0, '32.208')] [2023-03-11 11:59:30,928][04298] Updated weights for policy 0, policy_version 124640 (0.0005) [2023-03-11 11:59:32,811][04011] Fps is (10 sec: 12697.7, 60 sec: 13243.7, 300 sec: 12774.0). Total num frames: 63836160. Throughput: 0: 13256.7. Samples: 63811384. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-11 11:59:32,811][04011] Avg episode reward: [(0, '32.100')] [2023-03-11 11:59:34,046][04298] Updated weights for policy 0, policy_version 124720 (0.0005) [2023-03-11 11:59:37,145][04298] Updated weights for policy 0, policy_version 124800 (0.0004) [2023-03-11 11:59:37,811][04011] Fps is (10 sec: 12697.7, 60 sec: 13175.5, 300 sec: 12787.9). Total num frames: 63901696. Throughput: 0: 13233.6. Samples: 63890036. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-11 11:59:37,811][04011] Avg episode reward: [(0, '31.918')] [2023-03-11 11:59:37,813][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000124808_63901696.pth... [2023-03-11 11:59:37,815][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000124048_63512576.pth [2023-03-11 11:59:40,383][04298] Updated weights for policy 0, policy_version 124880 (0.0004) [2023-03-11 11:59:42,811][04011] Fps is (10 sec: 13107.1, 60 sec: 13175.5, 300 sec: 12801.7). Total num frames: 63967232. Throughput: 0: 13155.6. Samples: 63965844. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-11 11:59:42,811][04011] Avg episode reward: [(0, '30.755')] [2023-03-11 11:59:43,573][04298] Updated weights for policy 0, policy_version 124960 (0.0005) [2023-03-11 11:59:46,683][04298] Updated weights for policy 0, policy_version 125040 (0.0005) [2023-03-11 11:59:47,811][04011] Fps is (10 sec: 13107.2, 60 sec: 13175.5, 300 sec: 12829.5). Total num frames: 64032768. Throughput: 0: 13138.6. Samples: 64005580. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-11 11:59:47,811][04011] Avg episode reward: [(0, '32.536')] [2023-03-11 11:59:49,757][04298] Updated weights for policy 0, policy_version 125120 (0.0004) [2023-03-11 11:59:52,811][04011] Fps is (10 sec: 12697.6, 60 sec: 13107.2, 300 sec: 12829.5). Total num frames: 64094208. Throughput: 0: 13057.4. Samples: 64083028. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-11 11:59:52,811][04011] Avg episode reward: [(0, '32.156')] [2023-03-11 11:59:52,876][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000125192_64098304.pth... [2023-03-11 11:59:52,878][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000124432_63709184.pth [2023-03-11 11:59:53,207][04298] Updated weights for policy 0, policy_version 125200 (0.0005) [2023-03-11 11:59:56,652][04298] Updated weights for policy 0, policy_version 125280 (0.0006) [2023-03-11 11:59:57,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12970.7, 300 sec: 12829.5). Total num frames: 64155648. Throughput: 0: 12887.6. Samples: 64154328. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 11:59:57,811][04011] Avg episode reward: [(0, '30.786')] [2023-03-11 12:00:00,046][04298] Updated weights for policy 0, policy_version 125360 (0.0005) [2023-03-11 12:00:02,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12902.4, 300 sec: 12829.5). Total num frames: 64217088. Throughput: 0: 12790.9. Samples: 64190824. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:00:02,811][04011] Avg episode reward: [(0, '31.848')] [2023-03-11 12:00:03,302][04298] Updated weights for policy 0, policy_version 125440 (0.0004) [2023-03-11 12:00:06,368][04298] Updated weights for policy 0, policy_version 125520 (0.0004) [2023-03-11 12:00:07,811][04011] Fps is (10 sec: 12697.5, 60 sec: 12902.4, 300 sec: 12857.3). Total num frames: 64282624. Throughput: 0: 12808.3. Samples: 64268600. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:00:07,812][04011] Avg episode reward: [(0, '32.376')] [2023-03-11 12:00:07,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000125552_64282624.pth... [2023-03-11 12:00:07,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000124808_63901696.pth [2023-03-11 12:00:09,416][04298] Updated weights for policy 0, policy_version 125600 (0.0004) [2023-03-11 12:00:12,430][04298] Updated weights for policy 0, policy_version 125680 (0.0004) [2023-03-11 12:00:12,811][04011] Fps is (10 sec: 13516.8, 60 sec: 12902.4, 300 sec: 12885.0). Total num frames: 64352256. Throughput: 0: 12844.1. Samples: 64349684. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:00:12,811][04011] Avg episode reward: [(0, '32.768')] [2023-03-11 12:00:15,527][04298] Updated weights for policy 0, policy_version 125760 (0.0005) [2023-03-11 12:00:17,811][04011] Fps is (10 sec: 13516.8, 60 sec: 12902.4, 300 sec: 12898.9). Total num frames: 64417792. Throughput: 0: 12840.2. Samples: 64389192. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:00:17,811][04011] Avg episode reward: [(0, '31.014')] [2023-03-11 12:00:18,585][04298] Updated weights for policy 0, policy_version 125840 (0.0004) [2023-03-11 12:00:21,628][04298] Updated weights for policy 0, policy_version 125920 (0.0004) [2023-03-11 12:00:22,811][04011] Fps is (10 sec: 13107.1, 60 sec: 12902.4, 300 sec: 12926.7). Total num frames: 64483328. Throughput: 0: 12885.8. Samples: 64469896. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:00:22,811][04011] Avg episode reward: [(0, '30.518')] [2023-03-11 12:00:22,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000125944_64483328.pth... [2023-03-11 12:00:22,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000125192_64098304.pth [2023-03-11 12:00:24,684][04298] Updated weights for policy 0, policy_version 126000 (0.0004) [2023-03-11 12:00:27,811][04011] Fps is (10 sec: 13107.2, 60 sec: 12902.4, 300 sec: 12940.6). Total num frames: 64548864. Throughput: 0: 12909.5. Samples: 64546772. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:00:27,811][04011] Avg episode reward: [(0, '31.780')] [2023-03-11 12:00:28,062][04298] Updated weights for policy 0, policy_version 126080 (0.0005) [2023-03-11 12:00:31,201][04298] Updated weights for policy 0, policy_version 126160 (0.0005) [2023-03-11 12:00:32,811][04011] Fps is (10 sec: 13107.3, 60 sec: 12970.7, 300 sec: 12968.4). Total num frames: 64614400. Throughput: 0: 12892.5. Samples: 64585744. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:00:32,811][04011] Avg episode reward: [(0, '31.907')] [2023-03-11 12:00:34,460][04298] Updated weights for policy 0, policy_version 126240 (0.0005) [2023-03-11 12:00:37,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12834.1, 300 sec: 12968.4). Total num frames: 64671744. Throughput: 0: 12830.5. Samples: 64660400. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:00:37,811][04011] Avg episode reward: [(0, '32.881')] [2023-03-11 12:00:37,864][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000126320_64675840.pth... [2023-03-11 12:00:37,864][04298] Updated weights for policy 0, policy_version 126320 (0.0005) [2023-03-11 12:00:37,865][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000125552_64282624.pth [2023-03-11 12:00:41,308][04298] Updated weights for policy 0, policy_version 126400 (0.0004) [2023-03-11 12:00:42,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12765.9, 300 sec: 12968.4). Total num frames: 64733184. Throughput: 0: 12850.8. Samples: 64732616. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:00:42,811][04011] Avg episode reward: [(0, '30.686')] [2023-03-11 12:00:44,535][04298] Updated weights for policy 0, policy_version 126480 (0.0005) [2023-03-11 12:00:47,667][04298] Updated weights for policy 0, policy_version 126560 (0.0004) [2023-03-11 12:00:47,811][04011] Fps is (10 sec: 12697.6, 60 sec: 12765.9, 300 sec: 12968.4). Total num frames: 64798720. Throughput: 0: 12895.3. Samples: 64771112. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:00:47,822][04011] Avg episode reward: [(0, '30.388')] [2023-03-11 12:00:50,769][04298] Updated weights for policy 0, policy_version 126640 (0.0004) [2023-03-11 12:00:52,811][04011] Fps is (10 sec: 13107.2, 60 sec: 12834.1, 300 sec: 12982.2). Total num frames: 64864256. Throughput: 0: 12934.9. Samples: 64850668. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:00:52,822][04011] Avg episode reward: [(0, '32.359')] [2023-03-11 12:00:52,825][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000126688_64864256.pth... [2023-03-11 12:00:52,828][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000125944_64483328.pth [2023-03-11 12:00:54,057][04298] Updated weights for policy 0, policy_version 126720 (0.0005) [2023-03-11 12:00:57,432][04298] Updated weights for policy 0, policy_version 126800 (0.0005) [2023-03-11 12:00:57,811][04011] Fps is (10 sec: 12697.5, 60 sec: 12834.1, 300 sec: 12982.2). Total num frames: 64925696. Throughput: 0: 12742.0. Samples: 64923072. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:00:57,812][04011] Avg episode reward: [(0, '31.923')] [2023-03-11 12:01:00,841][04298] Updated weights for policy 0, policy_version 126880 (0.0005) [2023-03-11 12:01:02,811][04011] Fps is (10 sec: 11878.3, 60 sec: 12765.9, 300 sec: 12968.4). Total num frames: 64983040. Throughput: 0: 12656.4. Samples: 64958732. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:01:02,812][04011] Avg episode reward: [(0, '30.835')] [2023-03-11 12:01:04,223][04298] Updated weights for policy 0, policy_version 126960 (0.0005) [2023-03-11 12:01:07,567][04298] Updated weights for policy 0, policy_version 127040 (0.0005) [2023-03-11 12:01:07,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12697.6, 300 sec: 12968.4). Total num frames: 65044480. Throughput: 0: 12496.9. Samples: 65032256. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:01:07,812][04011] Avg episode reward: [(0, '30.924')] [2023-03-11 12:01:07,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000127040_65044480.pth... [2023-03-11 12:01:07,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000126320_64675840.pth [2023-03-11 12:01:10,951][04298] Updated weights for policy 0, policy_version 127120 (0.0005) [2023-03-11 12:01:12,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12561.1, 300 sec: 12954.5). Total num frames: 65105920. Throughput: 0: 12394.6. Samples: 65104528. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:01:12,812][04011] Avg episode reward: [(0, '30.986')] [2023-03-11 12:01:14,389][04298] Updated weights for policy 0, policy_version 127200 (0.0005) [2023-03-11 12:01:17,811][04011] Fps is (10 sec: 11878.5, 60 sec: 12424.5, 300 sec: 12926.7). Total num frames: 65163264. Throughput: 0: 12316.3. Samples: 65139976. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:01:17,811][04011] Avg episode reward: [(0, '27.451')] [2023-03-11 12:01:17,823][04298] Updated weights for policy 0, policy_version 127280 (0.0005) [2023-03-11 12:01:21,260][04298] Updated weights for policy 0, policy_version 127360 (0.0006) [2023-03-11 12:01:22,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12356.3, 300 sec: 12940.6). Total num frames: 65224704. Throughput: 0: 12267.0. Samples: 65212416. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:01:22,811][04011] Avg episode reward: [(0, '29.824')] [2023-03-11 12:01:22,814][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000127392_65224704.pth... [2023-03-11 12:01:22,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000126688_64864256.pth [2023-03-11 12:01:24,588][04298] Updated weights for policy 0, policy_version 127440 (0.0005) [2023-03-11 12:01:27,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12288.0, 300 sec: 12940.6). Total num frames: 65286144. Throughput: 0: 12269.7. Samples: 65284752. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:01:27,811][04011] Avg episode reward: [(0, '30.665')] [2023-03-11 12:01:28,021][04298] Updated weights for policy 0, policy_version 127520 (0.0005) [2023-03-11 12:01:31,368][04298] Updated weights for policy 0, policy_version 127600 (0.0005) [2023-03-11 12:01:32,811][04011] Fps is (10 sec: 12288.1, 60 sec: 12219.7, 300 sec: 12940.6). Total num frames: 65347584. Throughput: 0: 12226.6. Samples: 65321308. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:01:32,811][04011] Avg episode reward: [(0, '31.083')] [2023-03-11 12:01:34,696][04298] Updated weights for policy 0, policy_version 127680 (0.0005) [2023-03-11 12:01:37,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12288.0, 300 sec: 12940.6). Total num frames: 65409024. Throughput: 0: 12125.6. Samples: 65396320. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:01:37,811][04011] Avg episode reward: [(0, '28.209')] [2023-03-11 12:01:37,814][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000127752_65409024.pth... [2023-03-11 12:01:37,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000127040_65044480.pth [2023-03-11 12:01:37,905][04298] Updated weights for policy 0, policy_version 127760 (0.0004) [2023-03-11 12:01:41,182][04298] Updated weights for policy 0, policy_version 127840 (0.0004) [2023-03-11 12:01:42,811][04011] Fps is (10 sec: 12287.9, 60 sec: 12288.0, 300 sec: 12954.5). Total num frames: 65470464. Throughput: 0: 12165.7. Samples: 65470528. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:01:42,811][04011] Avg episode reward: [(0, '19.482')] [2023-03-11 12:01:44,544][04298] Updated weights for policy 0, policy_version 127920 (0.0006) [2023-03-11 12:01:47,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12219.7, 300 sec: 12940.6). Total num frames: 65531904. Throughput: 0: 12192.5. Samples: 65507392. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:01:47,811][04011] Avg episode reward: [(0, '28.696')] [2023-03-11 12:01:47,944][04298] Updated weights for policy 0, policy_version 128000 (0.0006) [2023-03-11 12:01:51,069][04298] Updated weights for policy 0, policy_version 128080 (0.0003) [2023-03-11 12:01:52,811][04011] Fps is (10 sec: 12697.5, 60 sec: 12219.7, 300 sec: 12940.6). Total num frames: 65597440. Throughput: 0: 12251.3. Samples: 65583564. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:01:52,812][04011] Avg episode reward: [(0, '31.782')] [2023-03-11 12:01:52,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000128120_65597440.pth... [2023-03-11 12:01:52,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000127392_65224704.pth [2023-03-11 12:01:54,193][04298] Updated weights for policy 0, policy_version 128160 (0.0004) [2023-03-11 12:01:57,650][04298] Updated weights for policy 0, policy_version 128240 (0.0005) [2023-03-11 12:01:57,811][04011] Fps is (10 sec: 12697.6, 60 sec: 12219.7, 300 sec: 12912.8). Total num frames: 65658880. Throughput: 0: 12307.4. Samples: 65658360. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:01:57,811][04011] Avg episode reward: [(0, '32.071')] [2023-03-11 12:02:00,848][04298] Updated weights for policy 0, policy_version 128320 (0.0004) [2023-03-11 12:02:02,811][04011] Fps is (10 sec: 12288.2, 60 sec: 12288.0, 300 sec: 12898.9). Total num frames: 65720320. Throughput: 0: 12356.7. Samples: 65696028. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-11 12:02:02,811][04011] Avg episode reward: [(0, '31.289')] [2023-03-11 12:02:04,359][04298] Updated weights for policy 0, policy_version 128400 (0.0005) [2023-03-11 12:02:07,707][04298] Updated weights for policy 0, policy_version 128480 (0.0005) [2023-03-11 12:02:07,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12288.0, 300 sec: 12871.2). Total num frames: 65781760. Throughput: 0: 12337.7. Samples: 65767612. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-11 12:02:07,812][04011] Avg episode reward: [(0, '31.668')] [2023-03-11 12:02:07,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000128480_65781760.pth... [2023-03-11 12:02:07,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000127752_65409024.pth [2023-03-11 12:02:11,040][04298] Updated weights for policy 0, policy_version 128560 (0.0005) [2023-03-11 12:02:12,811][04011] Fps is (10 sec: 12287.9, 60 sec: 12288.0, 300 sec: 12857.3). Total num frames: 65843200. Throughput: 0: 12358.9. Samples: 65840904. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-11 12:02:12,811][04011] Avg episode reward: [(0, '31.672')] [2023-03-11 12:02:14,326][04298] Updated weights for policy 0, policy_version 128640 (0.0005) [2023-03-11 12:02:17,553][04298] Updated weights for policy 0, policy_version 128720 (0.0004) [2023-03-11 12:02:17,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12356.3, 300 sec: 12843.4). Total num frames: 65904640. Throughput: 0: 12408.5. Samples: 65879692. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-11 12:02:17,811][04011] Avg episode reward: [(0, '31.682')] [2023-03-11 12:02:20,917][04298] Updated weights for policy 0, policy_version 128800 (0.0006) [2023-03-11 12:02:22,811][04011] Fps is (10 sec: 12287.9, 60 sec: 12356.3, 300 sec: 12829.5). Total num frames: 65966080. Throughput: 0: 12388.5. Samples: 65953804. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-11 12:02:22,812][04011] Avg episode reward: [(0, '31.837')] [2023-03-11 12:02:22,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000128840_65966080.pth... [2023-03-11 12:02:22,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000128120_65597440.pth [2023-03-11 12:02:24,369][04298] Updated weights for policy 0, policy_version 128880 (0.0005) [2023-03-11 12:02:27,710][04298] Updated weights for policy 0, policy_version 128960 (0.0005) [2023-03-11 12:02:27,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12356.3, 300 sec: 12815.6). Total num frames: 66027520. Throughput: 0: 12346.0. Samples: 66026100. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-11 12:02:27,811][04011] Avg episode reward: [(0, '32.229')] [2023-03-11 12:02:31,093][04298] Updated weights for policy 0, policy_version 129040 (0.0005) [2023-03-11 12:02:32,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12288.0, 300 sec: 12774.0). Total num frames: 66084864. Throughput: 0: 12327.8. Samples: 66062144. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-11 12:02:32,811][04011] Avg episode reward: [(0, '32.040')] [2023-03-11 12:02:34,452][04298] Updated weights for policy 0, policy_version 129120 (0.0005) [2023-03-11 12:02:37,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12288.0, 300 sec: 12774.0). Total num frames: 66146304. Throughput: 0: 12238.8. Samples: 66134312. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-11 12:02:37,812][04011] Avg episode reward: [(0, '31.904')] [2023-03-11 12:02:37,840][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000129200_66150400.pth... [2023-03-11 12:02:37,840][04298] Updated weights for policy 0, policy_version 129200 (0.0006) [2023-03-11 12:02:37,841][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000128480_65781760.pth [2023-03-11 12:02:41,225][04298] Updated weights for policy 0, policy_version 129280 (0.0005) [2023-03-11 12:02:42,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12288.0, 300 sec: 12746.2). Total num frames: 66207744. Throughput: 0: 12210.8. Samples: 66207848. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-11 12:02:42,812][04011] Avg episode reward: [(0, '32.227')] [2023-03-11 12:02:44,556][04298] Updated weights for policy 0, policy_version 129360 (0.0004) [2023-03-11 12:02:47,811][04011] Fps is (10 sec: 12288.1, 60 sec: 12288.0, 300 sec: 12732.3). Total num frames: 66269184. Throughput: 0: 12190.8. Samples: 66244616. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-11 12:02:47,811][04011] Avg episode reward: [(0, '32.401')] [2023-03-11 12:02:47,967][04298] Updated weights for policy 0, policy_version 129440 (0.0005) [2023-03-11 12:02:51,364][04298] Updated weights for policy 0, policy_version 129520 (0.0005) [2023-03-11 12:02:52,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12219.7, 300 sec: 12718.4). Total num frames: 66330624. Throughput: 0: 12201.3. Samples: 66316668. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-11 12:02:52,811][04011] Avg episode reward: [(0, '32.281')] [2023-03-11 12:02:52,814][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000129552_66330624.pth... [2023-03-11 12:02:52,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000128840_65966080.pth [2023-03-11 12:02:54,766][04298] Updated weights for policy 0, policy_version 129600 (0.0005) [2023-03-11 12:02:57,811][04011] Fps is (10 sec: 11878.3, 60 sec: 12151.5, 300 sec: 12676.8). Total num frames: 66387968. Throughput: 0: 12178.4. Samples: 66388932. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-11 12:02:57,812][04011] Avg episode reward: [(0, '31.802')] [2023-03-11 12:02:58,157][04298] Updated weights for policy 0, policy_version 129680 (0.0005) [2023-03-11 12:03:01,543][04298] Updated weights for policy 0, policy_version 129760 (0.0005) [2023-03-11 12:03:02,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12151.4, 300 sec: 12662.9). Total num frames: 66449408. Throughput: 0: 12130.8. Samples: 66425576. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:03:02,811][04011] Avg episode reward: [(0, '30.732')] [2023-03-11 12:03:05,004][04298] Updated weights for policy 0, policy_version 129840 (0.0005) [2023-03-11 12:03:07,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12151.5, 300 sec: 12649.0). Total num frames: 66510848. Throughput: 0: 12076.1. Samples: 66497228. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:03:07,812][04011] Avg episode reward: [(0, '29.573')] [2023-03-11 12:03:07,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000129904_66510848.pth... [2023-03-11 12:03:07,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000129200_66150400.pth [2023-03-11 12:03:08,396][04298] Updated weights for policy 0, policy_version 129920 (0.0005) [2023-03-11 12:03:11,816][04298] Updated weights for policy 0, policy_version 130000 (0.0005) [2023-03-11 12:03:12,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12083.2, 300 sec: 12621.2). Total num frames: 66568192. Throughput: 0: 12052.5. Samples: 66568464. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:03:12,811][04011] Avg episode reward: [(0, '32.911')] [2023-03-11 12:03:15,258][04298] Updated weights for policy 0, policy_version 130080 (0.0005) [2023-03-11 12:03:17,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12083.2, 300 sec: 12607.4). Total num frames: 66629632. Throughput: 0: 12064.7. Samples: 66605056. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:03:17,812][04011] Avg episode reward: [(0, '32.307')] [2023-03-11 12:03:18,653][04298] Updated weights for policy 0, policy_version 130160 (0.0005) [2023-03-11 12:03:22,064][04298] Updated weights for policy 0, policy_version 130240 (0.0005) [2023-03-11 12:03:22,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12083.2, 300 sec: 12579.6). Total num frames: 66691072. Throughput: 0: 12048.1. Samples: 66676476. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:03:22,812][04011] Avg episode reward: [(0, '31.473')] [2023-03-11 12:03:22,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000130256_66691072.pth... [2023-03-11 12:03:22,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000129552_66330624.pth [2023-03-11 12:03:25,616][04298] Updated weights for policy 0, policy_version 130320 (0.0005) [2023-03-11 12:03:27,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12014.9, 300 sec: 12565.7). Total num frames: 66748416. Throughput: 0: 11967.5. Samples: 66746384. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:03:27,811][04011] Avg episode reward: [(0, '29.891')] [2023-03-11 12:03:29,183][04298] Updated weights for policy 0, policy_version 130400 (0.0005) [2023-03-11 12:03:32,784][04298] Updated weights for policy 0, policy_version 130480 (0.0005) [2023-03-11 12:03:32,811][04011] Fps is (10 sec: 11468.8, 60 sec: 12014.9, 300 sec: 12524.0). Total num frames: 66805760. Throughput: 0: 11912.6. Samples: 66780684. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:03:32,811][04011] Avg episode reward: [(0, '30.104')] [2023-03-11 12:03:36,185][04298] Updated weights for policy 0, policy_version 130560 (0.0005) [2023-03-11 12:03:37,811][04011] Fps is (10 sec: 11468.7, 60 sec: 11946.7, 300 sec: 12496.3). Total num frames: 66863104. Throughput: 0: 11873.0. Samples: 66850952. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:03:37,812][04011] Avg episode reward: [(0, '31.752')] [2023-03-11 12:03:37,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000130592_66863104.pth... [2023-03-11 12:03:37,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000129904_66510848.pth [2023-03-11 12:03:39,672][04298] Updated weights for policy 0, policy_version 130640 (0.0005) [2023-03-11 12:03:42,811][04011] Fps is (10 sec: 11878.4, 60 sec: 11946.7, 300 sec: 12482.4). Total num frames: 66924544. Throughput: 0: 11836.5. Samples: 66921572. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:03:42,811][04011] Avg episode reward: [(0, '31.253')] [2023-03-11 12:03:43,144][04298] Updated weights for policy 0, policy_version 130720 (0.0005) [2023-03-11 12:03:46,331][04298] Updated weights for policy 0, policy_version 130800 (0.0003) [2023-03-11 12:03:47,811][04011] Fps is (10 sec: 12288.0, 60 sec: 11946.7, 300 sec: 12468.5). Total num frames: 66985984. Throughput: 0: 11863.4. Samples: 66959428. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:03:47,811][04011] Avg episode reward: [(0, '29.232')] [2023-03-11 12:03:49,754][04298] Updated weights for policy 0, policy_version 130880 (0.0005) [2023-03-11 12:03:52,811][04011] Fps is (10 sec: 11878.3, 60 sec: 11878.4, 300 sec: 12426.8). Total num frames: 67043328. Throughput: 0: 11880.0. Samples: 67031828. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:03:52,812][04011] Avg episode reward: [(0, '32.000')] [2023-03-11 12:03:52,816][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000130952_67047424.pth... [2023-03-11 12:03:52,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000130256_66691072.pth [2023-03-11 12:03:53,163][04298] Updated weights for policy 0, policy_version 130960 (0.0005) [2023-03-11 12:03:56,629][04298] Updated weights for policy 0, policy_version 131040 (0.0005) [2023-03-11 12:03:57,811][04011] Fps is (10 sec: 11878.4, 60 sec: 11946.7, 300 sec: 12413.0). Total num frames: 67104768. Throughput: 0: 11900.7. Samples: 67103996. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:03:57,812][04011] Avg episode reward: [(0, '30.786')] [2023-03-11 12:04:00,043][04298] Updated weights for policy 0, policy_version 131120 (0.0005) [2023-03-11 12:04:02,811][04011] Fps is (10 sec: 12288.0, 60 sec: 11946.7, 300 sec: 12399.1). Total num frames: 67166208. Throughput: 0: 11875.6. Samples: 67139456. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:04:02,812][04011] Avg episode reward: [(0, '31.499')] [2023-03-11 12:04:03,293][04298] Updated weights for policy 0, policy_version 131200 (0.0004) [2023-03-11 12:04:06,488][04298] Updated weights for policy 0, policy_version 131280 (0.0003) [2023-03-11 12:04:07,811][04011] Fps is (10 sec: 12697.5, 60 sec: 12014.9, 300 sec: 12385.2). Total num frames: 67231744. Throughput: 0: 11982.2. Samples: 67215676. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:04:07,812][04011] Avg episode reward: [(0, '32.895')] [2023-03-11 12:04:07,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000131312_67231744.pth... [2023-03-11 12:04:07,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000130592_66863104.pth [2023-03-11 12:04:09,742][04298] Updated weights for policy 0, policy_version 131360 (0.0004) [2023-03-11 12:04:12,811][04011] Fps is (10 sec: 12697.7, 60 sec: 12083.2, 300 sec: 12371.3). Total num frames: 67293184. Throughput: 0: 12082.1. Samples: 67290076. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:04:12,811][04011] Avg episode reward: [(0, '32.079')] [2023-03-11 12:04:13,086][04298] Updated weights for policy 0, policy_version 131440 (0.0005) [2023-03-11 12:04:16,411][04298] Updated weights for policy 0, policy_version 131520 (0.0005) [2023-03-11 12:04:17,811][04011] Fps is (10 sec: 12288.1, 60 sec: 12083.2, 300 sec: 12357.4). Total num frames: 67354624. Throughput: 0: 12160.6. Samples: 67327912. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:04:17,812][04011] Avg episode reward: [(0, '32.443')] [2023-03-11 12:04:19,633][04298] Updated weights for policy 0, policy_version 131600 (0.0005) [2023-03-11 12:04:22,794][04298] Updated weights for policy 0, policy_version 131680 (0.0003) [2023-03-11 12:04:22,811][04011] Fps is (10 sec: 12697.5, 60 sec: 12151.5, 300 sec: 12357.4). Total num frames: 67420160. Throughput: 0: 12286.6. Samples: 67403848. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:04:22,812][04011] Avg episode reward: [(0, '31.474')] [2023-03-11 12:04:22,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000131680_67420160.pth... [2023-03-11 12:04:22,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000130952_67047424.pth [2023-03-11 12:04:26,045][04298] Updated weights for policy 0, policy_version 131760 (0.0005) [2023-03-11 12:04:27,811][04011] Fps is (10 sec: 12697.6, 60 sec: 12219.7, 300 sec: 12357.4). Total num frames: 67481600. Throughput: 0: 12434.7. Samples: 67481132. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:04:27,812][04011] Avg episode reward: [(0, '31.161')] [2023-03-11 12:04:29,225][04298] Updated weights for policy 0, policy_version 131840 (0.0003) [2023-03-11 12:04:32,432][04298] Updated weights for policy 0, policy_version 131920 (0.0003) [2023-03-11 12:04:32,811][04011] Fps is (10 sec: 12697.6, 60 sec: 12356.3, 300 sec: 12357.4). Total num frames: 67547136. Throughput: 0: 12424.6. Samples: 67518536. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:04:32,811][04011] Avg episode reward: [(0, '25.783')] [2023-03-11 12:04:35,535][04298] Updated weights for policy 0, policy_version 132000 (0.0003) [2023-03-11 12:04:37,811][04011] Fps is (10 sec: 13107.2, 60 sec: 12492.8, 300 sec: 12357.4). Total num frames: 67612672. Throughput: 0: 12551.4. Samples: 67596640. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:04:37,811][04011] Avg episode reward: [(0, '30.242')] [2023-03-11 12:04:37,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000132056_67612672.pth... [2023-03-11 12:04:37,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000131312_67231744.pth [2023-03-11 12:04:38,737][04298] Updated weights for policy 0, policy_version 132080 (0.0003) [2023-03-11 12:04:41,850][04298] Updated weights for policy 0, policy_version 132160 (0.0003) [2023-03-11 12:04:42,811][04011] Fps is (10 sec: 12697.7, 60 sec: 12492.8, 300 sec: 12343.5). Total num frames: 67674112. Throughput: 0: 12669.4. Samples: 67674120. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:04:42,811][04011] Avg episode reward: [(0, '31.848')] [2023-03-11 12:04:45,244][04298] Updated weights for policy 0, policy_version 132240 (0.0005) [2023-03-11 12:04:47,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12492.8, 300 sec: 12343.5). Total num frames: 67735552. Throughput: 0: 12700.6. Samples: 67710984. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:04:47,811][04011] Avg episode reward: [(0, '31.280')] [2023-03-11 12:04:48,592][04298] Updated weights for policy 0, policy_version 132320 (0.0005) [2023-03-11 12:04:51,963][04298] Updated weights for policy 0, policy_version 132400 (0.0005) [2023-03-11 12:04:52,811][04011] Fps is (10 sec: 12287.9, 60 sec: 12561.1, 300 sec: 12343.5). Total num frames: 67796992. Throughput: 0: 12628.4. Samples: 67783956. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:04:52,812][04011] Avg episode reward: [(0, '29.330')] [2023-03-11 12:04:52,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000132416_67796992.pth... [2023-03-11 12:04:52,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000131680_67420160.pth [2023-03-11 12:04:55,586][04298] Updated weights for policy 0, policy_version 132480 (0.0005) [2023-03-11 12:04:57,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12492.8, 300 sec: 12329.7). Total num frames: 67854336. Throughput: 0: 12508.5. Samples: 67852960. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:04:57,812][04011] Avg episode reward: [(0, '28.641')] [2023-03-11 12:04:59,014][04298] Updated weights for policy 0, policy_version 132560 (0.0005) [2023-03-11 12:05:02,263][04298] Updated weights for policy 0, policy_version 132640 (0.0005) [2023-03-11 12:05:02,811][04011] Fps is (10 sec: 11878.5, 60 sec: 12492.8, 300 sec: 12315.8). Total num frames: 67915776. Throughput: 0: 12470.3. Samples: 67889076. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:05:02,811][04011] Avg episode reward: [(0, '30.360')] [2023-03-11 12:05:05,569][04298] Updated weights for policy 0, policy_version 132720 (0.0005) [2023-03-11 12:05:07,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12424.5, 300 sec: 12288.0). Total num frames: 67977216. Throughput: 0: 12468.5. Samples: 67964928. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:05:07,811][04011] Avg episode reward: [(0, '29.094')] [2023-03-11 12:05:07,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000132768_67977216.pth... [2023-03-11 12:05:07,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000132056_67612672.pth [2023-03-11 12:05:08,906][04298] Updated weights for policy 0, policy_version 132800 (0.0005) [2023-03-11 12:05:12,075][04298] Updated weights for policy 0, policy_version 132880 (0.0004) [2023-03-11 12:05:12,811][04011] Fps is (10 sec: 12697.6, 60 sec: 12492.8, 300 sec: 12288.0). Total num frames: 68042752. Throughput: 0: 12429.5. Samples: 68040460. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:05:12,811][04011] Avg episode reward: [(0, '26.215')] [2023-03-11 12:05:15,303][04298] Updated weights for policy 0, policy_version 132960 (0.0004) [2023-03-11 12:05:17,811][04011] Fps is (10 sec: 12697.7, 60 sec: 12492.8, 300 sec: 12274.1). Total num frames: 68104192. Throughput: 0: 12459.6. Samples: 68079216. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:05:17,811][04011] Avg episode reward: [(0, '30.889')] [2023-03-11 12:05:18,474][04298] Updated weights for policy 0, policy_version 133040 (0.0005) [2023-03-11 12:05:21,695][04298] Updated weights for policy 0, policy_version 133120 (0.0005) [2023-03-11 12:05:22,811][04011] Fps is (10 sec: 12697.5, 60 sec: 12492.8, 300 sec: 12274.1). Total num frames: 68169728. Throughput: 0: 12426.8. Samples: 68155848. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:05:22,812][04011] Avg episode reward: [(0, '29.599')] [2023-03-11 12:05:22,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000133144_68169728.pth... [2023-03-11 12:05:22,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000132416_67796992.pth [2023-03-11 12:05:24,937][04298] Updated weights for policy 0, policy_version 133200 (0.0005) [2023-03-11 12:05:27,811][04011] Fps is (10 sec: 12697.6, 60 sec: 12492.8, 300 sec: 12260.2). Total num frames: 68231168. Throughput: 0: 12380.3. Samples: 68231232. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:05:27,811][04011] Avg episode reward: [(0, '30.878')] [2023-03-11 12:05:28,233][04298] Updated weights for policy 0, policy_version 133280 (0.0005) [2023-03-11 12:05:31,622][04298] Updated weights for policy 0, policy_version 133360 (0.0005) [2023-03-11 12:05:32,811][04011] Fps is (10 sec: 12288.1, 60 sec: 12424.5, 300 sec: 12274.1). Total num frames: 68292608. Throughput: 0: 12369.5. Samples: 68267612. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:05:32,812][04011] Avg episode reward: [(0, '32.358')] [2023-03-11 12:05:35,054][04298] Updated weights for policy 0, policy_version 133440 (0.0005) [2023-03-11 12:05:37,811][04011] Fps is (10 sec: 12287.9, 60 sec: 12356.3, 300 sec: 12274.1). Total num frames: 68354048. Throughput: 0: 12349.3. Samples: 68339672. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:05:37,811][04011] Avg episode reward: [(0, '31.764')] [2023-03-11 12:05:37,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000133504_68354048.pth... [2023-03-11 12:05:37,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000132768_67977216.pth [2023-03-11 12:05:38,420][04298] Updated weights for policy 0, policy_version 133520 (0.0005) [2023-03-11 12:05:41,796][04298] Updated weights for policy 0, policy_version 133600 (0.0005) [2023-03-11 12:05:42,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12288.0, 300 sec: 12246.3). Total num frames: 68411392. Throughput: 0: 12421.9. Samples: 68411944. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:05:42,811][04011] Avg episode reward: [(0, '30.798')] [2023-03-11 12:05:45,264][04298] Updated weights for policy 0, policy_version 133680 (0.0005) [2023-03-11 12:05:47,811][04011] Fps is (10 sec: 11878.3, 60 sec: 12288.0, 300 sec: 12232.5). Total num frames: 68472832. Throughput: 0: 12425.6. Samples: 68448228. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:05:47,822][04011] Avg episode reward: [(0, '30.377')] [2023-03-11 12:05:48,677][04298] Updated weights for policy 0, policy_version 133760 (0.0005) [2023-03-11 12:05:52,112][04298] Updated weights for policy 0, policy_version 133840 (0.0005) [2023-03-11 12:05:52,811][04011] Fps is (10 sec: 12287.9, 60 sec: 12288.0, 300 sec: 12232.5). Total num frames: 68534272. Throughput: 0: 12322.6. Samples: 68519444. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:05:52,822][04011] Avg episode reward: [(0, '28.359')] [2023-03-11 12:05:52,825][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000133856_68534272.pth... [2023-03-11 12:05:52,827][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000133144_68169728.pth [2023-03-11 12:05:55,577][04298] Updated weights for policy 0, policy_version 133920 (0.0005) [2023-03-11 12:05:57,811][04011] Fps is (10 sec: 11878.5, 60 sec: 12288.0, 300 sec: 12232.5). Total num frames: 68591616. Throughput: 0: 12226.8. Samples: 68590668. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:05:57,822][04011] Avg episode reward: [(0, '29.581')] [2023-03-11 12:05:58,984][04298] Updated weights for policy 0, policy_version 134000 (0.0005) [2023-03-11 12:06:02,052][04298] Updated weights for policy 0, policy_version 134080 (0.0004) [2023-03-11 12:06:02,811][04011] Fps is (10 sec: 12288.1, 60 sec: 12356.3, 300 sec: 12246.3). Total num frames: 68657152. Throughput: 0: 12207.4. Samples: 68628552. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:06:02,811][04011] Avg episode reward: [(0, '31.114')] [2023-03-11 12:06:05,137][04298] Updated weights for policy 0, policy_version 134160 (0.0004) [2023-03-11 12:06:07,811][04011] Fps is (10 sec: 13107.2, 60 sec: 12424.5, 300 sec: 12260.2). Total num frames: 68722688. Throughput: 0: 12274.1. Samples: 68708180. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:06:07,811][04011] Avg episode reward: [(0, '30.096')] [2023-03-11 12:06:07,814][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000134224_68722688.pth... [2023-03-11 12:06:07,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000133504_68354048.pth [2023-03-11 12:06:08,251][04298] Updated weights for policy 0, policy_version 134240 (0.0004) [2023-03-11 12:06:11,435][04298] Updated weights for policy 0, policy_version 134320 (0.0005) [2023-03-11 12:06:12,811][04011] Fps is (10 sec: 13107.1, 60 sec: 12424.5, 300 sec: 12288.0). Total num frames: 68788224. Throughput: 0: 12338.7. Samples: 68786476. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:06:12,811][04011] Avg episode reward: [(0, '30.116')] [2023-03-11 12:06:14,603][04298] Updated weights for policy 0, policy_version 134400 (0.0004) [2023-03-11 12:06:17,811][04011] Fps is (10 sec: 12697.6, 60 sec: 12424.5, 300 sec: 12288.0). Total num frames: 68849664. Throughput: 0: 12380.7. Samples: 68824744. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:06:17,812][04011] Avg episode reward: [(0, '28.739')] [2023-03-11 12:06:17,832][04298] Updated weights for policy 0, policy_version 134480 (0.0004) [2023-03-11 12:06:21,300][04298] Updated weights for policy 0, policy_version 134560 (0.0005) [2023-03-11 12:06:22,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12356.3, 300 sec: 12288.0). Total num frames: 68911104. Throughput: 0: 12412.1. Samples: 68898216. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:06:22,811][04011] Avg episode reward: [(0, '31.050')] [2023-03-11 12:06:22,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000134592_68911104.pth... [2023-03-11 12:06:22,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000133856_68534272.pth [2023-03-11 12:06:24,561][04298] Updated weights for policy 0, policy_version 134640 (0.0005) [2023-03-11 12:06:27,811][04011] Fps is (10 sec: 12288.1, 60 sec: 12356.3, 300 sec: 12288.0). Total num frames: 68972544. Throughput: 0: 12457.7. Samples: 68972540. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:06:27,811][04011] Avg episode reward: [(0, '30.663')] [2023-03-11 12:06:27,941][04298] Updated weights for policy 0, policy_version 134720 (0.0006) [2023-03-11 12:06:31,286][04298] Updated weights for policy 0, policy_version 134800 (0.0005) [2023-03-11 12:06:32,811][04011] Fps is (10 sec: 12288.1, 60 sec: 12356.3, 300 sec: 12288.0). Total num frames: 69033984. Throughput: 0: 12454.9. Samples: 69008696. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:06:32,811][04011] Avg episode reward: [(0, '29.625')] [2023-03-11 12:06:34,728][04298] Updated weights for policy 0, policy_version 134880 (0.0005) [2023-03-11 12:06:37,811][04011] Fps is (10 sec: 11878.3, 60 sec: 12288.0, 300 sec: 12274.1). Total num frames: 69091328. Throughput: 0: 12437.2. Samples: 69079116. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:06:37,819][04011] Avg episode reward: [(0, '31.074')] [2023-03-11 12:06:37,823][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000134944_69091328.pth... [2023-03-11 12:06:37,826][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000134224_68722688.pth [2023-03-11 12:06:38,294][04298] Updated weights for policy 0, policy_version 134960 (0.0005) [2023-03-11 12:06:41,652][04298] Updated weights for policy 0, policy_version 135040 (0.0005) [2023-03-11 12:06:42,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12356.3, 300 sec: 12274.1). Total num frames: 69152768. Throughput: 0: 12477.4. Samples: 69152152. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:06:42,822][04011] Avg episode reward: [(0, '31.288')] [2023-03-11 12:06:44,932][04298] Updated weights for policy 0, policy_version 135120 (0.0005) [2023-03-11 12:06:47,811][04011] Fps is (10 sec: 12697.7, 60 sec: 12424.5, 300 sec: 12274.1). Total num frames: 69218304. Throughput: 0: 12469.9. Samples: 69189696. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:06:47,822][04011] Avg episode reward: [(0, '30.080')] [2023-03-11 12:06:48,041][04298] Updated weights for policy 0, policy_version 135200 (0.0003) [2023-03-11 12:06:51,099][04298] Updated weights for policy 0, policy_version 135280 (0.0003) [2023-03-11 12:06:52,811][04011] Fps is (10 sec: 13107.1, 60 sec: 12492.8, 300 sec: 12288.0). Total num frames: 69283840. Throughput: 0: 12470.4. Samples: 69269348. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:06:52,822][04011] Avg episode reward: [(0, '32.450')] [2023-03-11 12:06:52,825][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000135320_69283840.pth... [2023-03-11 12:06:52,828][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000134592_68911104.pth [2023-03-11 12:06:54,231][04298] Updated weights for policy 0, policy_version 135360 (0.0004) [2023-03-11 12:06:57,421][04298] Updated weights for policy 0, policy_version 135440 (0.0004) [2023-03-11 12:06:57,811][04011] Fps is (10 sec: 13107.2, 60 sec: 12629.3, 300 sec: 12301.9). Total num frames: 69349376. Throughput: 0: 12455.3. Samples: 69346964. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:06:57,822][04011] Avg episode reward: [(0, '31.968')] [2023-03-11 12:07:00,617][04298] Updated weights for policy 0, policy_version 135520 (0.0004) [2023-03-11 12:07:02,811][04011] Fps is (10 sec: 12697.7, 60 sec: 12561.1, 300 sec: 12301.9). Total num frames: 69410816. Throughput: 0: 12457.1. Samples: 69385312. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:07:02,822][04011] Avg episode reward: [(0, '31.599')] [2023-03-11 12:07:03,856][04298] Updated weights for policy 0, policy_version 135600 (0.0004) [2023-03-11 12:07:07,276][04298] Updated weights for policy 0, policy_version 135680 (0.0005) [2023-03-11 12:07:07,811][04011] Fps is (10 sec: 12287.9, 60 sec: 12492.8, 300 sec: 12301.9). Total num frames: 69472256. Throughput: 0: 12477.8. Samples: 69459716. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:07:07,822][04011] Avg episode reward: [(0, '32.606')] [2023-03-11 12:07:07,825][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000135688_69472256.pth... [2023-03-11 12:07:07,828][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000134944_69091328.pth [2023-03-11 12:07:10,698][04298] Updated weights for policy 0, policy_version 135760 (0.0005) [2023-03-11 12:07:12,811][04011] Fps is (10 sec: 12287.9, 60 sec: 12424.5, 300 sec: 12301.9). Total num frames: 69533696. Throughput: 0: 12418.4. Samples: 69531368. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:07:12,822][04011] Avg episode reward: [(0, '32.004')] [2023-03-11 12:07:14,122][04298] Updated weights for policy 0, policy_version 135840 (0.0005) [2023-03-11 12:07:17,296][04298] Updated weights for policy 0, policy_version 135920 (0.0004) [2023-03-11 12:07:17,811][04011] Fps is (10 sec: 12288.1, 60 sec: 12424.5, 300 sec: 12301.9). Total num frames: 69595136. Throughput: 0: 12433.8. Samples: 69568216. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:07:17,822][04011] Avg episode reward: [(0, '31.463')] [2023-03-11 12:07:20,597][04298] Updated weights for policy 0, policy_version 136000 (0.0004) [2023-03-11 12:07:22,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12424.5, 300 sec: 12301.9). Total num frames: 69656576. Throughput: 0: 12543.4. Samples: 69643568. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:07:22,822][04011] Avg episode reward: [(0, '31.324')] [2023-03-11 12:07:22,825][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000136048_69656576.pth... [2023-03-11 12:07:22,828][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000135320_69283840.pth [2023-03-11 12:07:24,099][04298] Updated weights for policy 0, policy_version 136080 (0.0005) [2023-03-11 12:07:27,553][04298] Updated weights for policy 0, policy_version 136160 (0.0005) [2023-03-11 12:07:27,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12356.3, 300 sec: 12301.9). Total num frames: 69713920. Throughput: 0: 12485.1. Samples: 69713984. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:07:27,812][04011] Avg episode reward: [(0, '31.507')] [2023-03-11 12:07:31,017][04298] Updated weights for policy 0, policy_version 136240 (0.0005) [2023-03-11 12:07:32,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12356.3, 300 sec: 12301.9). Total num frames: 69775360. Throughput: 0: 12431.0. Samples: 69749092. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:07:32,811][04011] Avg episode reward: [(0, '31.802')] [2023-03-11 12:07:34,461][04298] Updated weights for policy 0, policy_version 136320 (0.0005) [2023-03-11 12:07:37,678][04298] Updated weights for policy 0, policy_version 136400 (0.0004) [2023-03-11 12:07:37,811][04011] Fps is (10 sec: 12287.9, 60 sec: 12424.5, 300 sec: 12301.9). Total num frames: 69836800. Throughput: 0: 12269.3. Samples: 69821468. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:07:37,812][04011] Avg episode reward: [(0, '31.679')] [2023-03-11 12:07:37,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000136400_69836800.pth... [2023-03-11 12:07:37,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000135688_69472256.pth [2023-03-11 12:07:40,873][04298] Updated weights for policy 0, policy_version 136480 (0.0003) [2023-03-11 12:07:42,811][04011] Fps is (10 sec: 12697.6, 60 sec: 12492.8, 300 sec: 12315.8). Total num frames: 69902336. Throughput: 0: 12260.5. Samples: 69898688. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:07:42,811][04011] Avg episode reward: [(0, '32.693')] [2023-03-11 12:07:44,051][04298] Updated weights for policy 0, policy_version 136560 (0.0003) [2023-03-11 12:07:47,285][04298] Updated weights for policy 0, policy_version 136640 (0.0004) [2023-03-11 12:07:47,811][04011] Fps is (10 sec: 12697.7, 60 sec: 12424.5, 300 sec: 12315.8). Total num frames: 69963776. Throughput: 0: 12293.7. Samples: 69938528. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:07:47,811][04011] Avg episode reward: [(0, '32.141')] [2023-03-11 12:07:50,540][04298] Updated weights for policy 0, policy_version 136720 (0.0004) [2023-03-11 12:07:52,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12356.3, 300 sec: 12329.7). Total num frames: 70025216. Throughput: 0: 12295.2. Samples: 70013000. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:07:52,811][04011] Avg episode reward: [(0, '31.866')] [2023-03-11 12:07:52,829][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000136776_70029312.pth... [2023-03-11 12:07:52,831][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000136048_69656576.pth [2023-03-11 12:07:53,781][04298] Updated weights for policy 0, policy_version 136800 (0.0004) [2023-03-11 12:07:56,916][04298] Updated weights for policy 0, policy_version 136880 (0.0003) [2023-03-11 12:07:57,811][04011] Fps is (10 sec: 12697.6, 60 sec: 12356.3, 300 sec: 12343.5). Total num frames: 70090752. Throughput: 0: 12432.2. Samples: 70090816. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:07:57,812][04011] Avg episode reward: [(0, '25.410')] [2023-03-11 12:08:00,087][04298] Updated weights for policy 0, policy_version 136960 (0.0003) [2023-03-11 12:08:02,811][04011] Fps is (10 sec: 13107.2, 60 sec: 12424.5, 300 sec: 12357.4). Total num frames: 70156288. Throughput: 0: 12468.1. Samples: 70129280. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:08:02,812][04011] Avg episode reward: [(0, '32.547')] [2023-03-11 12:08:03,344][04298] Updated weights for policy 0, policy_version 137040 (0.0005) [2023-03-11 12:08:06,672][04298] Updated weights for policy 0, policy_version 137120 (0.0005) [2023-03-11 12:08:07,811][04011] Fps is (10 sec: 12697.6, 60 sec: 12424.5, 300 sec: 12371.3). Total num frames: 70217728. Throughput: 0: 12454.4. Samples: 70204016. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:08:07,812][04011] Avg episode reward: [(0, '32.304')] [2023-03-11 12:08:07,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000137144_70217728.pth... [2023-03-11 12:08:07,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000136400_69836800.pth [2023-03-11 12:08:09,987][04298] Updated weights for policy 0, policy_version 137200 (0.0005) [2023-03-11 12:08:12,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12424.5, 300 sec: 12371.3). Total num frames: 70279168. Throughput: 0: 12563.9. Samples: 70279360. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:08:12,811][04011] Avg episode reward: [(0, '31.525')] [2023-03-11 12:08:13,127][04298] Updated weights for policy 0, policy_version 137280 (0.0003) [2023-03-11 12:08:16,389][04298] Updated weights for policy 0, policy_version 137360 (0.0004) [2023-03-11 12:08:17,811][04011] Fps is (10 sec: 12697.6, 60 sec: 12492.8, 300 sec: 12385.2). Total num frames: 70344704. Throughput: 0: 12634.0. Samples: 70317624. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:08:17,811][04011] Avg episode reward: [(0, '32.853')] [2023-03-11 12:08:19,650][04298] Updated weights for policy 0, policy_version 137440 (0.0003) [2023-03-11 12:08:22,811][04011] Fps is (10 sec: 12697.6, 60 sec: 12492.8, 300 sec: 12399.1). Total num frames: 70406144. Throughput: 0: 12714.4. Samples: 70393616. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:08:22,811][04011] Avg episode reward: [(0, '30.958')] [2023-03-11 12:08:22,849][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000137520_70410240.pth... [2023-03-11 12:08:22,850][04298] Updated weights for policy 0, policy_version 137520 (0.0003) [2023-03-11 12:08:22,851][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000136776_70029312.pth [2023-03-11 12:08:26,002][04298] Updated weights for policy 0, policy_version 137600 (0.0003) [2023-03-11 12:08:27,811][04011] Fps is (10 sec: 12697.6, 60 sec: 12629.3, 300 sec: 12426.8). Total num frames: 70471680. Throughput: 0: 12697.4. Samples: 70470072. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:08:27,811][04011] Avg episode reward: [(0, '29.275')] [2023-03-11 12:08:29,378][04298] Updated weights for policy 0, policy_version 137680 (0.0003) [2023-03-11 12:08:32,494][04298] Updated weights for policy 0, policy_version 137760 (0.0003) [2023-03-11 12:08:32,811][04011] Fps is (10 sec: 13107.2, 60 sec: 12697.6, 300 sec: 12454.6). Total num frames: 70537216. Throughput: 0: 12651.6. Samples: 70507848. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:08:32,811][04011] Avg episode reward: [(0, '30.415')] [2023-03-11 12:08:35,681][04298] Updated weights for policy 0, policy_version 137840 (0.0003) [2023-03-11 12:08:37,811][04011] Fps is (10 sec: 12697.6, 60 sec: 12697.6, 300 sec: 12454.6). Total num frames: 70598656. Throughput: 0: 12716.7. Samples: 70585252. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:08:37,812][04011] Avg episode reward: [(0, '29.569')] [2023-03-11 12:08:37,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000137888_70598656.pth... [2023-03-11 12:08:37,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000137144_70217728.pth [2023-03-11 12:08:38,898][04298] Updated weights for policy 0, policy_version 137920 (0.0003) [2023-03-11 12:08:42,125][04298] Updated weights for policy 0, policy_version 138000 (0.0004) [2023-03-11 12:08:42,811][04011] Fps is (10 sec: 12288.1, 60 sec: 12629.3, 300 sec: 12454.6). Total num frames: 70660096. Throughput: 0: 12667.0. Samples: 70660828. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:08:42,811][04011] Avg episode reward: [(0, '31.580')] [2023-03-11 12:08:45,600][04298] Updated weights for policy 0, policy_version 138080 (0.0005) [2023-03-11 12:08:47,811][04011] Fps is (10 sec: 12288.1, 60 sec: 12629.3, 300 sec: 12468.5). Total num frames: 70721536. Throughput: 0: 12613.6. Samples: 70696892. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:08:47,811][04011] Avg episode reward: [(0, '29.394')] [2023-03-11 12:08:48,948][04298] Updated weights for policy 0, policy_version 138160 (0.0005) [2023-03-11 12:08:52,257][04298] Updated weights for policy 0, policy_version 138240 (0.0005) [2023-03-11 12:08:52,811][04011] Fps is (10 sec: 12287.9, 60 sec: 12629.3, 300 sec: 12468.5). Total num frames: 70782976. Throughput: 0: 12591.5. Samples: 70770632. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:08:52,811][04011] Avg episode reward: [(0, '31.713')] [2023-03-11 12:08:52,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000138248_70782976.pth... [2023-03-11 12:08:52,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000137520_70410240.pth [2023-03-11 12:08:55,681][04298] Updated weights for policy 0, policy_version 138320 (0.0005) [2023-03-11 12:08:57,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12561.1, 300 sec: 12468.5). Total num frames: 70844416. Throughput: 0: 12510.1. Samples: 70842316. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:08:57,811][04011] Avg episode reward: [(0, '32.100')] [2023-03-11 12:08:59,168][04298] Updated weights for policy 0, policy_version 138400 (0.0005) [2023-03-11 12:09:02,475][04298] Updated weights for policy 0, policy_version 138480 (0.0004) [2023-03-11 12:09:02,811][04011] Fps is (10 sec: 12288.1, 60 sec: 12492.8, 300 sec: 12454.6). Total num frames: 70905856. Throughput: 0: 12434.8. Samples: 70877192. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:09:02,811][04011] Avg episode reward: [(0, '32.107')] [2023-03-11 12:09:05,736][04298] Updated weights for policy 0, policy_version 138560 (0.0005) [2023-03-11 12:09:07,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12492.8, 300 sec: 12454.6). Total num frames: 70967296. Throughput: 0: 12418.5. Samples: 70952448. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:09:07,811][04011] Avg episode reward: [(0, '32.706')] [2023-03-11 12:09:07,814][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000138608_70967296.pth... [2023-03-11 12:09:07,816][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000137888_70598656.pth [2023-03-11 12:09:09,120][04298] Updated weights for policy 0, policy_version 138640 (0.0005) [2023-03-11 12:09:12,426][04298] Updated weights for policy 0, policy_version 138720 (0.0005) [2023-03-11 12:09:12,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12492.8, 300 sec: 12454.6). Total num frames: 71028736. Throughput: 0: 12356.7. Samples: 71026124. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:09:12,811][04011] Avg episode reward: [(0, '33.110')] [2023-03-11 12:09:15,701][04298] Updated weights for policy 0, policy_version 138800 (0.0005) [2023-03-11 12:09:17,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12424.5, 300 sec: 12440.7). Total num frames: 71090176. Throughput: 0: 12356.8. Samples: 71063904. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:09:17,811][04011] Avg episode reward: [(0, '32.590')] [2023-03-11 12:09:18,983][04298] Updated weights for policy 0, policy_version 138880 (0.0005) [2023-03-11 12:09:22,292][04298] Updated weights for policy 0, policy_version 138960 (0.0005) [2023-03-11 12:09:22,811][04011] Fps is (10 sec: 12287.9, 60 sec: 12424.5, 300 sec: 12440.7). Total num frames: 71151616. Throughput: 0: 12303.0. Samples: 71138888. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:09:22,811][04011] Avg episode reward: [(0, '32.450')] [2023-03-11 12:09:22,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000138968_71151616.pth... [2023-03-11 12:09:22,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000138248_70782976.pth [2023-03-11 12:09:25,616][04298] Updated weights for policy 0, policy_version 139040 (0.0005) [2023-03-11 12:09:27,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12356.3, 300 sec: 12426.8). Total num frames: 71213056. Throughput: 0: 12257.6. Samples: 71212420. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:09:27,811][04011] Avg episode reward: [(0, '31.353')] [2023-03-11 12:09:28,952][04298] Updated weights for policy 0, policy_version 139120 (0.0005) [2023-03-11 12:09:32,343][04298] Updated weights for policy 0, policy_version 139200 (0.0005) [2023-03-11 12:09:32,811][04011] Fps is (10 sec: 12288.1, 60 sec: 12288.0, 300 sec: 12413.0). Total num frames: 71274496. Throughput: 0: 12273.1. Samples: 71249180. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:09:32,812][04011] Avg episode reward: [(0, '29.943')] [2023-03-11 12:09:35,741][04298] Updated weights for policy 0, policy_version 139280 (0.0005) [2023-03-11 12:09:37,811][04011] Fps is (10 sec: 11878.3, 60 sec: 12219.7, 300 sec: 12399.1). Total num frames: 71331840. Throughput: 0: 12223.5. Samples: 71320688. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:09:37,811][04011] Avg episode reward: [(0, '32.544')] [2023-03-11 12:09:37,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000139328_71335936.pth... [2023-03-11 12:09:37,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000138608_70967296.pth [2023-03-11 12:09:39,132][04298] Updated weights for policy 0, policy_version 139360 (0.0005) [2023-03-11 12:09:42,607][04298] Updated weights for policy 0, policy_version 139440 (0.0005) [2023-03-11 12:09:42,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12219.7, 300 sec: 12399.1). Total num frames: 71393280. Throughput: 0: 12241.8. Samples: 71393196. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:09:42,811][04011] Avg episode reward: [(0, '27.939')] [2023-03-11 12:09:45,984][04298] Updated weights for policy 0, policy_version 139520 (0.0005) [2023-03-11 12:09:47,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12219.7, 300 sec: 12399.1). Total num frames: 71454720. Throughput: 0: 12261.1. Samples: 71428940. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:09:47,811][04011] Avg episode reward: [(0, '30.972')] [2023-03-11 12:09:49,216][04298] Updated weights for policy 0, policy_version 139600 (0.0004) [2023-03-11 12:09:52,409][04298] Updated weights for policy 0, policy_version 139680 (0.0003) [2023-03-11 12:09:52,811][04011] Fps is (10 sec: 12697.5, 60 sec: 12288.0, 300 sec: 12426.8). Total num frames: 71520256. Throughput: 0: 12272.3. Samples: 71504704. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:09:52,812][04011] Avg episode reward: [(0, '27.999')] [2023-03-11 12:09:52,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000139688_71520256.pth... [2023-03-11 12:09:52,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000138968_71151616.pth [2023-03-11 12:09:55,650][04298] Updated weights for policy 0, policy_version 139760 (0.0004) [2023-03-11 12:09:57,811][04011] Fps is (10 sec: 12697.7, 60 sec: 12288.0, 300 sec: 12426.8). Total num frames: 71581696. Throughput: 0: 12323.1. Samples: 71580664. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:09:57,811][04011] Avg episode reward: [(0, '26.421')] [2023-03-11 12:09:58,975][04298] Updated weights for policy 0, policy_version 139840 (0.0003) [2023-03-11 12:10:02,130][04298] Updated weights for policy 0, policy_version 139920 (0.0003) [2023-03-11 12:10:02,811][04011] Fps is (10 sec: 12288.1, 60 sec: 12288.0, 300 sec: 12426.8). Total num frames: 71643136. Throughput: 0: 12315.7. Samples: 71618112. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:10:02,811][04011] Avg episode reward: [(0, '26.286')] [2023-03-11 12:10:05,532][04298] Updated weights for policy 0, policy_version 140000 (0.0004) [2023-03-11 12:10:07,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12288.0, 300 sec: 12413.0). Total num frames: 71704576. Throughput: 0: 12299.4. Samples: 71692360. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:10:07,811][04011] Avg episode reward: [(0, '23.994')] [2023-03-11 12:10:07,856][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000140056_71708672.pth... [2023-03-11 12:10:07,858][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000139328_71335936.pth [2023-03-11 12:10:08,845][04298] Updated weights for policy 0, policy_version 140080 (0.0003) [2023-03-11 12:10:12,115][04298] Updated weights for policy 0, policy_version 140160 (0.0003) [2023-03-11 12:10:12,811][04011] Fps is (10 sec: 12697.5, 60 sec: 12356.3, 300 sec: 12426.8). Total num frames: 71770112. Throughput: 0: 12326.8. Samples: 71767128. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:10:12,812][04011] Avg episode reward: [(0, '23.369')] [2023-03-11 12:10:15,509][04298] Updated weights for policy 0, policy_version 140240 (0.0005) [2023-03-11 12:10:17,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12288.0, 300 sec: 12399.1). Total num frames: 71827456. Throughput: 0: 12308.1. Samples: 71803044. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:10:17,811][04011] Avg episode reward: [(0, '22.703')] [2023-03-11 12:10:18,979][04298] Updated weights for policy 0, policy_version 140320 (0.0005) [2023-03-11 12:10:22,488][04298] Updated weights for policy 0, policy_version 140400 (0.0005) [2023-03-11 12:10:22,811][04011] Fps is (10 sec: 11468.8, 60 sec: 12219.7, 300 sec: 12385.2). Total num frames: 71884800. Throughput: 0: 12291.5. Samples: 71873804. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:10:22,811][04011] Avg episode reward: [(0, '21.803')] [2023-03-11 12:10:22,856][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000140408_71888896.pth... [2023-03-11 12:10:22,857][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000139688_71520256.pth [2023-03-11 12:10:26,032][04298] Updated weights for policy 0, policy_version 140480 (0.0005) [2023-03-11 12:10:27,811][04011] Fps is (10 sec: 11878.5, 60 sec: 12219.7, 300 sec: 12385.2). Total num frames: 71946240. Throughput: 0: 12228.2. Samples: 71943464. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:10:27,811][04011] Avg episode reward: [(0, '22.759')] [2023-03-11 12:10:29,457][04298] Updated weights for policy 0, policy_version 140560 (0.0005) [2023-03-11 12:10:32,811][04011] Fps is (10 sec: 11878.3, 60 sec: 12151.5, 300 sec: 12371.3). Total num frames: 72003584. Throughput: 0: 12228.2. Samples: 71979208. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:10:32,812][04011] Avg episode reward: [(0, '25.392')] [2023-03-11 12:10:33,023][04298] Updated weights for policy 0, policy_version 140640 (0.0005) [2023-03-11 12:10:36,615][04298] Updated weights for policy 0, policy_version 140720 (0.0005) [2023-03-11 12:10:37,811][04011] Fps is (10 sec: 11468.7, 60 sec: 12151.5, 300 sec: 12371.3). Total num frames: 72060928. Throughput: 0: 12082.1. Samples: 72048400. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:10:37,812][04011] Avg episode reward: [(0, '21.834')] [2023-03-11 12:10:37,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000140744_72060928.pth... [2023-03-11 12:10:37,820][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000140056_71708672.pth [2023-03-11 12:10:40,110][04298] Updated weights for policy 0, policy_version 140800 (0.0005) [2023-03-11 12:10:42,811][04011] Fps is (10 sec: 11468.8, 60 sec: 12083.2, 300 sec: 12357.4). Total num frames: 72118272. Throughput: 0: 11947.2. Samples: 72118288. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:10:42,811][04011] Avg episode reward: [(0, '22.198')] [2023-03-11 12:10:43,645][04298] Updated weights for policy 0, policy_version 140880 (0.0006) [2023-03-11 12:10:47,125][04298] Updated weights for policy 0, policy_version 140960 (0.0005) [2023-03-11 12:10:47,811][04011] Fps is (10 sec: 11468.8, 60 sec: 12014.9, 300 sec: 12343.5). Total num frames: 72175616. Throughput: 0: 11897.3. Samples: 72153492. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:10:47,822][04011] Avg episode reward: [(0, '19.615')] [2023-03-11 12:10:50,612][04298] Updated weights for policy 0, policy_version 141040 (0.0006) [2023-03-11 12:10:52,811][04011] Fps is (10 sec: 11878.3, 60 sec: 11946.7, 300 sec: 12357.4). Total num frames: 72237056. Throughput: 0: 11818.8. Samples: 72224208. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:10:52,822][04011] Avg episode reward: [(0, '20.334')] [2023-03-11 12:10:52,825][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000141088_72237056.pth... [2023-03-11 12:10:52,828][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000140408_71888896.pth [2023-03-11 12:10:54,156][04298] Updated weights for policy 0, policy_version 141120 (0.0005) [2023-03-11 12:10:57,596][04298] Updated weights for policy 0, policy_version 141200 (0.0005) [2023-03-11 12:10:57,811][04011] Fps is (10 sec: 11878.4, 60 sec: 11878.4, 300 sec: 12329.7). Total num frames: 72294400. Throughput: 0: 11717.2. Samples: 72294400. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:10:57,822][04011] Avg episode reward: [(0, '22.296')] [2023-03-11 12:11:01,160][04298] Updated weights for policy 0, policy_version 141280 (0.0005) [2023-03-11 12:11:02,811][04011] Fps is (10 sec: 11468.9, 60 sec: 11810.1, 300 sec: 12301.9). Total num frames: 72351744. Throughput: 0: 11677.5. Samples: 72328532. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:11:02,811][04011] Avg episode reward: [(0, '22.013')] [2023-03-11 12:11:04,802][04298] Updated weights for policy 0, policy_version 141360 (0.0005) [2023-03-11 12:11:07,811][04011] Fps is (10 sec: 11468.8, 60 sec: 11741.9, 300 sec: 12274.1). Total num frames: 72409088. Throughput: 0: 11623.5. Samples: 72396864. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:11:07,811][04011] Avg episode reward: [(0, '16.189')] [2023-03-11 12:11:07,814][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000141424_72409088.pth... [2023-03-11 12:11:07,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000140744_72060928.pth [2023-03-11 12:11:08,332][04298] Updated weights for policy 0, policy_version 141440 (0.0005) [2023-03-11 12:11:11,960][04298] Updated weights for policy 0, policy_version 141520 (0.0005) [2023-03-11 12:11:12,811][04011] Fps is (10 sec: 11468.9, 60 sec: 11605.3, 300 sec: 12260.2). Total num frames: 72466432. Throughput: 0: 11590.3. Samples: 72465028. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:11:12,811][04011] Avg episode reward: [(0, '14.966')] [2023-03-11 12:11:15,548][04298] Updated weights for policy 0, policy_version 141600 (0.0005) [2023-03-11 12:11:17,811][04011] Fps is (10 sec: 11468.8, 60 sec: 11605.3, 300 sec: 12246.3). Total num frames: 72523776. Throughput: 0: 11556.8. Samples: 72499264. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:11:17,811][04011] Avg episode reward: [(0, '18.092')] [2023-03-11 12:11:19,161][04298] Updated weights for policy 0, policy_version 141680 (0.0005) [2023-03-11 12:11:22,725][04298] Updated weights for policy 0, policy_version 141760 (0.0005) [2023-03-11 12:11:22,811][04011] Fps is (10 sec: 11468.7, 60 sec: 11605.3, 300 sec: 12232.5). Total num frames: 72581120. Throughput: 0: 11554.0. Samples: 72568332. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:11:22,812][04011] Avg episode reward: [(0, '18.461')] [2023-03-11 12:11:22,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000141760_72581120.pth... [2023-03-11 12:11:22,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000141088_72237056.pth [2023-03-11 12:11:26,317][04298] Updated weights for policy 0, policy_version 141840 (0.0005) [2023-03-11 12:11:27,811][04011] Fps is (10 sec: 11468.8, 60 sec: 11537.1, 300 sec: 12218.6). Total num frames: 72638464. Throughput: 0: 11505.8. Samples: 72636048. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:11:27,811][04011] Avg episode reward: [(0, '15.231')] [2023-03-11 12:11:29,941][04298] Updated weights for policy 0, policy_version 141920 (0.0005) [2023-03-11 12:11:32,811][04011] Fps is (10 sec: 11468.9, 60 sec: 11537.1, 300 sec: 12218.6). Total num frames: 72695808. Throughput: 0: 11488.5. Samples: 72670476. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:11:32,811][04011] Avg episode reward: [(0, '12.602')] [2023-03-11 12:11:33,488][04298] Updated weights for policy 0, policy_version 142000 (0.0005) [2023-03-11 12:11:36,939][04298] Updated weights for policy 0, policy_version 142080 (0.0005) [2023-03-11 12:11:37,811][04011] Fps is (10 sec: 11468.8, 60 sec: 11537.1, 300 sec: 12204.7). Total num frames: 72753152. Throughput: 0: 11478.9. Samples: 72740760. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:11:37,811][04011] Avg episode reward: [(0, '15.804')] [2023-03-11 12:11:37,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000142096_72753152.pth... [2023-03-11 12:11:37,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000141424_72409088.pth [2023-03-11 12:11:40,499][04298] Updated weights for policy 0, policy_version 142160 (0.0005) [2023-03-11 12:11:42,811][04011] Fps is (10 sec: 11468.8, 60 sec: 11537.1, 300 sec: 12176.9). Total num frames: 72810496. Throughput: 0: 11447.2. Samples: 72809524. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:11:42,811][04011] Avg episode reward: [(0, '15.812')] [2023-03-11 12:11:44,089][04298] Updated weights for policy 0, policy_version 142240 (0.0005) [2023-03-11 12:11:47,540][04298] Updated weights for policy 0, policy_version 142320 (0.0005) [2023-03-11 12:11:47,811][04011] Fps is (10 sec: 11468.8, 60 sec: 11537.1, 300 sec: 12149.2). Total num frames: 72867840. Throughput: 0: 11449.5. Samples: 72843760. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:11:47,812][04011] Avg episode reward: [(0, '14.055')] [2023-03-11 12:11:50,757][04298] Updated weights for policy 0, policy_version 142400 (0.0004) [2023-03-11 12:11:52,811][04011] Fps is (10 sec: 11878.4, 60 sec: 11537.1, 300 sec: 12135.3). Total num frames: 72929280. Throughput: 0: 11576.3. Samples: 72917796. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:11:52,812][04011] Avg episode reward: [(0, '20.155')] [2023-03-11 12:11:52,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000142440_72929280.pth... [2023-03-11 12:11:52,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000141760_72581120.pth [2023-03-11 12:11:54,258][04298] Updated weights for policy 0, policy_version 142480 (0.0005) [2023-03-11 12:11:57,701][04298] Updated weights for policy 0, policy_version 142560 (0.0005) [2023-03-11 12:11:57,811][04011] Fps is (10 sec: 12288.0, 60 sec: 11605.3, 300 sec: 12135.3). Total num frames: 72990720. Throughput: 0: 11641.2. Samples: 72988880. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:11:57,811][04011] Avg episode reward: [(0, '17.577')] [2023-03-11 12:12:01,195][04298] Updated weights for policy 0, policy_version 142640 (0.0005) [2023-03-11 12:12:02,811][04011] Fps is (10 sec: 11878.5, 60 sec: 11605.3, 300 sec: 12121.4). Total num frames: 73048064. Throughput: 0: 11650.8. Samples: 73023552. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:12:02,811][04011] Avg episode reward: [(0, '20.245')] [2023-03-11 12:12:04,413][04298] Updated weights for policy 0, policy_version 142720 (0.0004) [2023-03-11 12:12:07,588][04298] Updated weights for policy 0, policy_version 142800 (0.0004) [2023-03-11 12:12:07,811][04011] Fps is (10 sec: 12287.9, 60 sec: 11741.9, 300 sec: 12135.3). Total num frames: 73113600. Throughput: 0: 11818.7. Samples: 73100172. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:12:07,812][04011] Avg episode reward: [(0, '21.199')] [2023-03-11 12:12:07,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000142800_73113600.pth... [2023-03-11 12:12:07,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000142096_72753152.pth [2023-03-11 12:12:10,728][04298] Updated weights for policy 0, policy_version 142880 (0.0003) [2023-03-11 12:12:12,811][04011] Fps is (10 sec: 13107.2, 60 sec: 11878.4, 300 sec: 12149.2). Total num frames: 73179136. Throughput: 0: 12056.9. Samples: 73178608. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:12:12,811][04011] Avg episode reward: [(0, '23.494')] [2023-03-11 12:12:13,933][04298] Updated weights for policy 0, policy_version 142960 (0.0004) [2023-03-11 12:12:17,082][04298] Updated weights for policy 0, policy_version 143040 (0.0004) [2023-03-11 12:12:17,811][04011] Fps is (10 sec: 13107.3, 60 sec: 12014.9, 300 sec: 12163.0). Total num frames: 73244672. Throughput: 0: 12134.2. Samples: 73216516. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:12:17,811][04011] Avg episode reward: [(0, '22.078')] [2023-03-11 12:12:20,235][04298] Updated weights for policy 0, policy_version 143120 (0.0004) [2023-03-11 12:12:22,811][04011] Fps is (10 sec: 13107.2, 60 sec: 12151.5, 300 sec: 12190.8). Total num frames: 73310208. Throughput: 0: 12291.7. Samples: 73293888. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:12:22,811][04011] Avg episode reward: [(0, '22.865')] [2023-03-11 12:12:22,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000143184_73310208.pth... [2023-03-11 12:12:22,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000142440_72929280.pth [2023-03-11 12:12:23,422][04298] Updated weights for policy 0, policy_version 143200 (0.0004) [2023-03-11 12:12:26,573][04298] Updated weights for policy 0, policy_version 143280 (0.0004) [2023-03-11 12:12:27,811][04011] Fps is (10 sec: 12697.5, 60 sec: 12219.7, 300 sec: 12190.8). Total num frames: 73371648. Throughput: 0: 12491.8. Samples: 73371656. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:12:27,811][04011] Avg episode reward: [(0, '19.674')] [2023-03-11 12:12:29,695][04298] Updated weights for policy 0, policy_version 143360 (0.0003) [2023-03-11 12:12:32,811][04011] Fps is (10 sec: 12697.6, 60 sec: 12356.3, 300 sec: 12204.7). Total num frames: 73437184. Throughput: 0: 12617.2. Samples: 73411532. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:12:32,811][04011] Avg episode reward: [(0, '22.834')] [2023-03-11 12:12:32,902][04298] Updated weights for policy 0, policy_version 143440 (0.0003) [2023-03-11 12:12:36,065][04298] Updated weights for policy 0, policy_version 143520 (0.0004) [2023-03-11 12:12:37,811][04011] Fps is (10 sec: 13107.1, 60 sec: 12492.8, 300 sec: 12204.7). Total num frames: 73502720. Throughput: 0: 12685.4. Samples: 73488640. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:12:37,812][04011] Avg episode reward: [(0, '23.441')] [2023-03-11 12:12:37,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000143560_73502720.pth... [2023-03-11 12:12:37,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000142800_73113600.pth [2023-03-11 12:12:39,185][04298] Updated weights for policy 0, policy_version 143600 (0.0004) [2023-03-11 12:12:42,362][04298] Updated weights for policy 0, policy_version 143680 (0.0004) [2023-03-11 12:12:42,811][04011] Fps is (10 sec: 13107.1, 60 sec: 12629.3, 300 sec: 12218.6). Total num frames: 73568256. Throughput: 0: 12842.5. Samples: 73566792. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:12:42,812][04011] Avg episode reward: [(0, '21.663')] [2023-03-11 12:12:45,514][04298] Updated weights for policy 0, policy_version 143760 (0.0004) [2023-03-11 12:12:47,811][04011] Fps is (10 sec: 13107.3, 60 sec: 12765.9, 300 sec: 12232.5). Total num frames: 73633792. Throughput: 0: 12926.0. Samples: 73605224. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:12:47,811][04011] Avg episode reward: [(0, '24.508')] [2023-03-11 12:12:48,597][04298] Updated weights for policy 0, policy_version 143840 (0.0003) [2023-03-11 12:12:51,770][04298] Updated weights for policy 0, policy_version 143920 (0.0004) [2023-03-11 12:12:52,811][04011] Fps is (10 sec: 13107.2, 60 sec: 12834.1, 300 sec: 12232.5). Total num frames: 73699328. Throughput: 0: 12973.2. Samples: 73683964. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:12:52,812][04011] Avg episode reward: [(0, '19.582')] [2023-03-11 12:12:52,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000143944_73699328.pth... [2023-03-11 12:12:52,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000143184_73310208.pth [2023-03-11 12:12:54,897][04298] Updated weights for policy 0, policy_version 144000 (0.0004) [2023-03-11 12:12:57,811][04011] Fps is (10 sec: 13107.2, 60 sec: 12902.4, 300 sec: 12232.5). Total num frames: 73764864. Throughput: 0: 12994.7. Samples: 73763368. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:12:57,812][04011] Avg episode reward: [(0, '19.793')] [2023-03-11 12:12:58,036][04298] Updated weights for policy 0, policy_version 144080 (0.0004) [2023-03-11 12:13:01,218][04298] Updated weights for policy 0, policy_version 144160 (0.0004) [2023-03-11 12:13:02,811][04011] Fps is (10 sec: 13107.2, 60 sec: 13038.9, 300 sec: 12246.3). Total num frames: 73830400. Throughput: 0: 13004.9. Samples: 73801736. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:13:02,812][04011] Avg episode reward: [(0, '22.046')] [2023-03-11 12:13:04,332][04298] Updated weights for policy 0, policy_version 144240 (0.0003) [2023-03-11 12:13:07,464][04298] Updated weights for policy 0, policy_version 144320 (0.0004) [2023-03-11 12:13:07,811][04011] Fps is (10 sec: 13107.1, 60 sec: 13038.9, 300 sec: 12260.2). Total num frames: 73895936. Throughput: 0: 13021.3. Samples: 73879848. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:13:07,812][04011] Avg episode reward: [(0, '22.398')] [2023-03-11 12:13:07,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000144328_73895936.pth... [2023-03-11 12:13:07,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000143560_73502720.pth [2023-03-11 12:13:10,612][04298] Updated weights for policy 0, policy_version 144400 (0.0004) [2023-03-11 12:13:12,811][04011] Fps is (10 sec: 13107.2, 60 sec: 13038.9, 300 sec: 12260.2). Total num frames: 73961472. Throughput: 0: 13040.3. Samples: 73958472. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:13:12,812][04011] Avg episode reward: [(0, '21.348')] [2023-03-11 12:13:13,760][04298] Updated weights for policy 0, policy_version 144480 (0.0004) [2023-03-11 12:13:16,967][04298] Updated weights for policy 0, policy_version 144560 (0.0004) [2023-03-11 12:13:17,811][04011] Fps is (10 sec: 12697.7, 60 sec: 12970.7, 300 sec: 12260.2). Total num frames: 74022912. Throughput: 0: 13009.7. Samples: 73996968. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:13:17,811][04011] Avg episode reward: [(0, '20.298')] [2023-03-11 12:13:20,123][04298] Updated weights for policy 0, policy_version 144640 (0.0004) [2023-03-11 12:13:22,811][04011] Fps is (10 sec: 12697.6, 60 sec: 12970.7, 300 sec: 12260.2). Total num frames: 74088448. Throughput: 0: 13018.0. Samples: 74074448. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:13:22,812][04011] Avg episode reward: [(0, '22.185')] [2023-03-11 12:13:22,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000144704_74088448.pth... [2023-03-11 12:13:22,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000143944_73699328.pth [2023-03-11 12:13:23,280][04298] Updated weights for policy 0, policy_version 144720 (0.0004) [2023-03-11 12:13:26,517][04298] Updated weights for policy 0, policy_version 144800 (0.0004) [2023-03-11 12:13:27,811][04011] Fps is (10 sec: 13107.2, 60 sec: 13038.9, 300 sec: 12260.2). Total num frames: 74153984. Throughput: 0: 12987.4. Samples: 74151224. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:13:27,812][04011] Avg episode reward: [(0, '17.681')] [2023-03-11 12:13:29,677][04298] Updated weights for policy 0, policy_version 144880 (0.0004) [2023-03-11 12:13:32,811][04011] Fps is (10 sec: 12697.7, 60 sec: 12970.7, 300 sec: 12260.2). Total num frames: 74215424. Throughput: 0: 12995.0. Samples: 74190000. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:13:32,811][04011] Avg episode reward: [(0, '18.772')] [2023-03-11 12:13:32,841][04298] Updated weights for policy 0, policy_version 144960 (0.0004) [2023-03-11 12:13:36,037][04298] Updated weights for policy 0, policy_version 145040 (0.0005) [2023-03-11 12:13:37,811][04011] Fps is (10 sec: 12697.6, 60 sec: 12970.7, 300 sec: 12274.1). Total num frames: 74280960. Throughput: 0: 12970.0. Samples: 74267612. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:13:37,812][04011] Avg episode reward: [(0, '19.191')] [2023-03-11 12:13:37,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000145080_74280960.pth... [2023-03-11 12:13:37,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000144328_73895936.pth [2023-03-11 12:13:39,178][04298] Updated weights for policy 0, policy_version 145120 (0.0004) [2023-03-11 12:13:42,348][04298] Updated weights for policy 0, policy_version 145200 (0.0004) [2023-03-11 12:13:42,811][04011] Fps is (10 sec: 13107.1, 60 sec: 12970.7, 300 sec: 12288.0). Total num frames: 74346496. Throughput: 0: 12925.3. Samples: 74345008. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:13:42,811][04011] Avg episode reward: [(0, '16.317')] [2023-03-11 12:13:45,409][04298] Updated weights for policy 0, policy_version 145280 (0.0003) [2023-03-11 12:13:47,811][04011] Fps is (10 sec: 13107.2, 60 sec: 12970.7, 300 sec: 12301.9). Total num frames: 74412032. Throughput: 0: 12960.9. Samples: 74384976. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:13:47,822][04011] Avg episode reward: [(0, '16.464')] [2023-03-11 12:13:48,611][04298] Updated weights for policy 0, policy_version 145360 (0.0004) [2023-03-11 12:13:51,952][04298] Updated weights for policy 0, policy_version 145440 (0.0005) [2023-03-11 12:13:52,811][04011] Fps is (10 sec: 12697.5, 60 sec: 12902.4, 300 sec: 12301.9). Total num frames: 74473472. Throughput: 0: 12905.6. Samples: 74460600. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:13:52,822][04011] Avg episode reward: [(0, '18.912')] [2023-03-11 12:13:52,825][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000145456_74473472.pth... [2023-03-11 12:13:52,828][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000144704_74088448.pth [2023-03-11 12:13:55,162][04298] Updated weights for policy 0, policy_version 145520 (0.0004) [2023-03-11 12:13:57,811][04011] Fps is (10 sec: 12697.6, 60 sec: 12902.4, 300 sec: 12315.8). Total num frames: 74539008. Throughput: 0: 12840.9. Samples: 74536312. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:13:57,822][04011] Avg episode reward: [(0, '16.778')] [2023-03-11 12:13:58,414][04298] Updated weights for policy 0, policy_version 145600 (0.0004) [2023-03-11 12:14:01,660][04298] Updated weights for policy 0, policy_version 145680 (0.0004) [2023-03-11 12:14:02,811][04011] Fps is (10 sec: 12697.7, 60 sec: 12834.1, 300 sec: 12315.8). Total num frames: 74600448. Throughput: 0: 12838.8. Samples: 74574716. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:14:02,822][04011] Avg episode reward: [(0, '18.518')] [2023-03-11 12:14:04,945][04298] Updated weights for policy 0, policy_version 145760 (0.0004) [2023-03-11 12:14:07,811][04011] Fps is (10 sec: 12287.9, 60 sec: 12765.9, 300 sec: 12315.8). Total num frames: 74661888. Throughput: 0: 12781.4. Samples: 74649612. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:14:07,822][04011] Avg episode reward: [(0, '18.850')] [2023-03-11 12:14:07,825][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000145824_74661888.pth... [2023-03-11 12:14:07,828][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000145080_74280960.pth [2023-03-11 12:14:08,212][04298] Updated weights for policy 0, policy_version 145840 (0.0004) [2023-03-11 12:14:11,455][04298] Updated weights for policy 0, policy_version 145920 (0.0004) [2023-03-11 12:14:12,811][04011] Fps is (10 sec: 12697.6, 60 sec: 12765.9, 300 sec: 12329.7). Total num frames: 74727424. Throughput: 0: 12743.2. Samples: 74724668. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:14:12,822][04011] Avg episode reward: [(0, '18.423')] [2023-03-11 12:14:14,707][04298] Updated weights for policy 0, policy_version 146000 (0.0004) [2023-03-11 12:14:17,811][04011] Fps is (10 sec: 12697.7, 60 sec: 12765.9, 300 sec: 12329.7). Total num frames: 74788864. Throughput: 0: 12743.4. Samples: 74763452. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:14:17,812][04011] Avg episode reward: [(0, '21.657')] [2023-03-11 12:14:17,954][04298] Updated weights for policy 0, policy_version 146080 (0.0004) [2023-03-11 12:14:21,253][04298] Updated weights for policy 0, policy_version 146160 (0.0004) [2023-03-11 12:14:22,811][04011] Fps is (10 sec: 12287.9, 60 sec: 12697.6, 300 sec: 12329.7). Total num frames: 74850304. Throughput: 0: 12675.5. Samples: 74838008. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:14:22,822][04011] Avg episode reward: [(0, '19.596')] [2023-03-11 12:14:22,825][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000146192_74850304.pth... [2023-03-11 12:14:22,826][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000145456_74473472.pth [2023-03-11 12:14:24,555][04298] Updated weights for policy 0, policy_version 146240 (0.0004) [2023-03-11 12:14:27,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12629.3, 300 sec: 12329.7). Total num frames: 74911744. Throughput: 0: 12583.2. Samples: 74911252. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:14:27,822][04011] Avg episode reward: [(0, '17.979')] [2023-03-11 12:14:27,973][04298] Updated weights for policy 0, policy_version 146320 (0.0004) [2023-03-11 12:14:31,272][04298] Updated weights for policy 0, policy_version 146400 (0.0004) [2023-03-11 12:14:32,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12629.3, 300 sec: 12343.5). Total num frames: 74973184. Throughput: 0: 12521.8. Samples: 74948456. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:14:32,811][04011] Avg episode reward: [(0, '18.388')] [2023-03-11 12:14:34,672][04298] Updated weights for policy 0, policy_version 146480 (0.0004) [2023-03-11 12:14:37,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12561.1, 300 sec: 12343.5). Total num frames: 75034624. Throughput: 0: 12459.2. Samples: 75021264. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:14:37,822][04011] Avg episode reward: [(0, '16.861')] [2023-03-11 12:14:37,825][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000146552_75034624.pth... [2023-03-11 12:14:37,828][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000145824_74661888.pth [2023-03-11 12:14:37,975][04298] Updated weights for policy 0, policy_version 146560 (0.0004) [2023-03-11 12:14:41,394][04298] Updated weights for policy 0, policy_version 146640 (0.0004) [2023-03-11 12:14:42,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12424.5, 300 sec: 12329.7). Total num frames: 75091968. Throughput: 0: 12369.1. Samples: 75092924. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:14:42,822][04011] Avg episode reward: [(0, '17.147')] [2023-03-11 12:14:44,804][04298] Updated weights for policy 0, policy_version 146720 (0.0004) [2023-03-11 12:14:47,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12356.3, 300 sec: 12315.8). Total num frames: 75153408. Throughput: 0: 12325.2. Samples: 75129352. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:14:47,821][04011] Avg episode reward: [(0, '20.862')] [2023-03-11 12:14:48,288][04298] Updated weights for policy 0, policy_version 146800 (0.0005) [2023-03-11 12:14:51,590][04298] Updated weights for policy 0, policy_version 146880 (0.0004) [2023-03-11 12:14:52,811][04011] Fps is (10 sec: 12288.1, 60 sec: 12356.3, 300 sec: 12315.8). Total num frames: 75214848. Throughput: 0: 12283.0. Samples: 75202348. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:14:52,811][04011] Avg episode reward: [(0, '22.419')] [2023-03-11 12:14:52,814][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000146904_75214848.pth... [2023-03-11 12:14:52,816][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000146192_74850304.pth [2023-03-11 12:14:55,008][04298] Updated weights for policy 0, policy_version 146960 (0.0004) [2023-03-11 12:14:57,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12288.0, 300 sec: 12315.8). Total num frames: 75276288. Throughput: 0: 12202.4. Samples: 75273776. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:14:57,812][04011] Avg episode reward: [(0, '18.233')] [2023-03-11 12:14:58,422][04298] Updated weights for policy 0, policy_version 147040 (0.0004) [2023-03-11 12:15:01,910][04298] Updated weights for policy 0, policy_version 147120 (0.0004) [2023-03-11 12:15:02,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12219.7, 300 sec: 12301.9). Total num frames: 75333632. Throughput: 0: 12149.6. Samples: 75310184. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:15:02,812][04011] Avg episode reward: [(0, '21.546')] [2023-03-11 12:15:05,309][04298] Updated weights for policy 0, policy_version 147200 (0.0005) [2023-03-11 12:15:07,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12219.7, 300 sec: 12288.0). Total num frames: 75395072. Throughput: 0: 12081.8. Samples: 75381688. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:15:07,812][04011] Avg episode reward: [(0, '18.309')] [2023-03-11 12:15:07,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000147256_75395072.pth... [2023-03-11 12:15:07,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000146552_75034624.pth [2023-03-11 12:15:08,600][04298] Updated weights for policy 0, policy_version 147280 (0.0004) [2023-03-11 12:15:12,156][04298] Updated weights for policy 0, policy_version 147360 (0.0005) [2023-03-11 12:15:12,811][04011] Fps is (10 sec: 11878.5, 60 sec: 12083.2, 300 sec: 12288.0). Total num frames: 75452416. Throughput: 0: 12029.4. Samples: 75452576. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:15:12,811][04011] Avg episode reward: [(0, '18.409')] [2023-03-11 12:15:15,744][04298] Updated weights for policy 0, policy_version 147440 (0.0005) [2023-03-11 12:15:17,811][04011] Fps is (10 sec: 11468.8, 60 sec: 12014.9, 300 sec: 12288.0). Total num frames: 75509760. Throughput: 0: 11970.6. Samples: 75487132. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:15:17,812][04011] Avg episode reward: [(0, '22.833')] [2023-03-11 12:15:19,258][04298] Updated weights for policy 0, policy_version 147520 (0.0005) [2023-03-11 12:15:22,811][04011] Fps is (10 sec: 11468.8, 60 sec: 11946.7, 300 sec: 12274.1). Total num frames: 75567104. Throughput: 0: 11899.4. Samples: 75556736. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:15:22,811][04011] Avg episode reward: [(0, '21.243')] [2023-03-11 12:15:22,860][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000147600_75571200.pth... [2023-03-11 12:15:22,860][04298] Updated weights for policy 0, policy_version 147600 (0.0005) [2023-03-11 12:15:22,861][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000146904_75214848.pth [2023-03-11 12:15:26,495][04298] Updated weights for policy 0, policy_version 147680 (0.0005) [2023-03-11 12:15:27,811][04011] Fps is (10 sec: 11468.9, 60 sec: 11878.4, 300 sec: 12274.1). Total num frames: 75624448. Throughput: 0: 11812.0. Samples: 75624464. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:15:27,812][04011] Avg episode reward: [(0, '22.448')] [2023-03-11 12:15:30,075][04298] Updated weights for policy 0, policy_version 147760 (0.0005) [2023-03-11 12:15:32,811][04011] Fps is (10 sec: 11468.8, 60 sec: 11810.1, 300 sec: 12274.1). Total num frames: 75681792. Throughput: 0: 11765.8. Samples: 75658812. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:15:32,811][04011] Avg episode reward: [(0, '26.226')] [2023-03-11 12:15:33,580][04298] Updated weights for policy 0, policy_version 147840 (0.0005) [2023-03-11 12:15:37,182][04298] Updated weights for policy 0, policy_version 147920 (0.0005) [2023-03-11 12:15:37,811][04011] Fps is (10 sec: 11468.8, 60 sec: 11741.9, 300 sec: 12274.1). Total num frames: 75739136. Throughput: 0: 11677.3. Samples: 75727828. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:15:37,812][04011] Avg episode reward: [(0, '22.645')] [2023-03-11 12:15:37,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000147928_75739136.pth... [2023-03-11 12:15:37,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000147256_75395072.pth [2023-03-11 12:15:40,611][04298] Updated weights for policy 0, policy_version 148000 (0.0005) [2023-03-11 12:15:42,811][04011] Fps is (10 sec: 11878.3, 60 sec: 11810.1, 300 sec: 12288.0). Total num frames: 75800576. Throughput: 0: 11679.2. Samples: 75799340. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:15:42,811][04011] Avg episode reward: [(0, '25.775')] [2023-03-11 12:15:44,148][04298] Updated weights for policy 0, policy_version 148080 (0.0005) [2023-03-11 12:15:47,504][04298] Updated weights for policy 0, policy_version 148160 (0.0004) [2023-03-11 12:15:47,811][04011] Fps is (10 sec: 12288.1, 60 sec: 11810.1, 300 sec: 12288.0). Total num frames: 75862016. Throughput: 0: 11626.1. Samples: 75833360. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:15:47,822][04011] Avg episode reward: [(0, '23.066')] [2023-03-11 12:15:50,935][04298] Updated weights for policy 0, policy_version 148240 (0.0005) [2023-03-11 12:15:52,811][04011] Fps is (10 sec: 11878.4, 60 sec: 11741.9, 300 sec: 12288.0). Total num frames: 75919360. Throughput: 0: 11668.1. Samples: 75906752. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:15:52,812][04011] Avg episode reward: [(0, '24.576')] [2023-03-11 12:15:52,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000148280_75919360.pth... [2023-03-11 12:15:52,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000147600_75571200.pth [2023-03-11 12:15:54,464][04298] Updated weights for policy 0, policy_version 148320 (0.0006) [2023-03-11 12:15:57,811][04011] Fps is (10 sec: 11468.7, 60 sec: 11673.6, 300 sec: 12288.0). Total num frames: 75976704. Throughput: 0: 11648.7. Samples: 75976768. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:15:57,812][04011] Avg episode reward: [(0, '23.430')] [2023-03-11 12:15:57,888][04298] Updated weights for policy 0, policy_version 148400 (0.0005) [2023-03-11 12:16:01,313][04298] Updated weights for policy 0, policy_version 148480 (0.0005) [2023-03-11 12:16:02,811][04011] Fps is (10 sec: 11878.4, 60 sec: 11741.9, 300 sec: 12301.9). Total num frames: 76038144. Throughput: 0: 11678.2. Samples: 76012652. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:16:02,812][04011] Avg episode reward: [(0, '26.177')] [2023-03-11 12:16:04,803][04298] Updated weights for policy 0, policy_version 148560 (0.0006) [2023-03-11 12:16:07,811][04011] Fps is (10 sec: 11878.4, 60 sec: 11673.6, 300 sec: 12301.9). Total num frames: 76095488. Throughput: 0: 11699.4. Samples: 76083208. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:16:07,812][04011] Avg episode reward: [(0, '26.463')] [2023-03-11 12:16:07,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000148624_76095488.pth... [2023-03-11 12:16:07,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000147928_75739136.pth [2023-03-11 12:16:08,203][04298] Updated weights for policy 0, policy_version 148640 (0.0005) [2023-03-11 12:16:11,607][04298] Updated weights for policy 0, policy_version 148720 (0.0005) [2023-03-11 12:16:12,811][04011] Fps is (10 sec: 11878.5, 60 sec: 11741.9, 300 sec: 12315.8). Total num frames: 76156928. Throughput: 0: 11821.8. Samples: 76156444. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:16:12,811][04011] Avg episode reward: [(0, '27.026')] [2023-03-11 12:16:15,027][04298] Updated weights for policy 0, policy_version 148800 (0.0005) [2023-03-11 12:16:17,811][04011] Fps is (10 sec: 12288.1, 60 sec: 11810.1, 300 sec: 12329.7). Total num frames: 76218368. Throughput: 0: 11852.5. Samples: 76192176. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:16:17,811][04011] Avg episode reward: [(0, '27.935')] [2023-03-11 12:16:18,345][04298] Updated weights for policy 0, policy_version 148880 (0.0004) [2023-03-11 12:16:21,879][04298] Updated weights for policy 0, policy_version 148960 (0.0005) [2023-03-11 12:16:22,811][04011] Fps is (10 sec: 11878.2, 60 sec: 11810.1, 300 sec: 12329.7). Total num frames: 76275712. Throughput: 0: 11903.5. Samples: 76263488. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:16:22,812][04011] Avg episode reward: [(0, '27.563')] [2023-03-11 12:16:22,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000148976_76275712.pth... [2023-03-11 12:16:22,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000148280_75919360.pth [2023-03-11 12:16:25,313][04298] Updated weights for policy 0, policy_version 149040 (0.0006) [2023-03-11 12:16:27,811][04011] Fps is (10 sec: 11878.4, 60 sec: 11878.4, 300 sec: 12343.5). Total num frames: 76337152. Throughput: 0: 11919.2. Samples: 76335704. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:16:27,811][04011] Avg episode reward: [(0, '29.244')] [2023-03-11 12:16:28,728][04298] Updated weights for policy 0, policy_version 149120 (0.0005) [2023-03-11 12:16:32,214][04298] Updated weights for policy 0, policy_version 149200 (0.0005) [2023-03-11 12:16:32,811][04011] Fps is (10 sec: 11878.5, 60 sec: 11878.4, 300 sec: 12343.5). Total num frames: 76394496. Throughput: 0: 11946.8. Samples: 76370968. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:16:32,811][04011] Avg episode reward: [(0, '24.068')] [2023-03-11 12:16:35,406][04298] Updated weights for policy 0, policy_version 149280 (0.0005) [2023-03-11 12:16:37,811][04011] Fps is (10 sec: 12287.9, 60 sec: 12014.9, 300 sec: 12371.3). Total num frames: 76460032. Throughput: 0: 11968.5. Samples: 76445336. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:16:37,812][04011] Avg episode reward: [(0, '27.273')] [2023-03-11 12:16:37,814][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000149336_76460032.pth... [2023-03-11 12:16:37,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000148624_76095488.pth [2023-03-11 12:16:38,681][04298] Updated weights for policy 0, policy_version 149360 (0.0004) [2023-03-11 12:16:42,067][04298] Updated weights for policy 0, policy_version 149440 (0.0005) [2023-03-11 12:16:42,811][04011] Fps is (10 sec: 12697.7, 60 sec: 12014.9, 300 sec: 12385.2). Total num frames: 76521472. Throughput: 0: 12039.3. Samples: 76518536. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-11 12:16:42,811][04011] Avg episode reward: [(0, '27.257')] [2023-03-11 12:16:45,572][04298] Updated weights for policy 0, policy_version 149520 (0.0006) [2023-03-11 12:16:47,811][04011] Fps is (10 sec: 11878.5, 60 sec: 11946.7, 300 sec: 12371.3). Total num frames: 76578816. Throughput: 0: 12035.5. Samples: 76554248. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-11 12:16:47,812][04011] Avg episode reward: [(0, '27.397')] [2023-03-11 12:16:48,921][04298] Updated weights for policy 0, policy_version 149600 (0.0005) [2023-03-11 12:16:52,501][04298] Updated weights for policy 0, policy_version 149680 (0.0005) [2023-03-11 12:16:52,811][04011] Fps is (10 sec: 11468.6, 60 sec: 11946.7, 300 sec: 12357.4). Total num frames: 76636160. Throughput: 0: 12056.8. Samples: 76625764. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-11 12:16:52,812][04011] Avg episode reward: [(0, '30.051')] [2023-03-11 12:16:52,855][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000149688_76640256.pth... [2023-03-11 12:16:52,857][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000148976_76275712.pth [2023-03-11 12:16:55,992][04298] Updated weights for policy 0, policy_version 149760 (0.0005) [2023-03-11 12:16:57,811][04011] Fps is (10 sec: 11878.5, 60 sec: 12014.9, 300 sec: 12371.3). Total num frames: 76697600. Throughput: 0: 11987.7. Samples: 76695892. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-11 12:16:57,811][04011] Avg episode reward: [(0, '29.137')] [2023-03-11 12:16:59,371][04298] Updated weights for policy 0, policy_version 149840 (0.0005) [2023-03-11 12:17:02,740][04298] Updated weights for policy 0, policy_version 149920 (0.0004) [2023-03-11 12:17:02,811][04011] Fps is (10 sec: 12288.2, 60 sec: 12015.0, 300 sec: 12357.4). Total num frames: 76759040. Throughput: 0: 11993.7. Samples: 76731892. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-11 12:17:02,811][04011] Avg episode reward: [(0, '29.983')] [2023-03-11 12:17:06,253][04298] Updated weights for policy 0, policy_version 150000 (0.0005) [2023-03-11 12:17:07,811][04011] Fps is (10 sec: 11878.3, 60 sec: 12014.9, 300 sec: 12329.7). Total num frames: 76816384. Throughput: 0: 12013.5. Samples: 76804096. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-11 12:17:07,812][04011] Avg episode reward: [(0, '27.916')] [2023-03-11 12:17:07,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000150032_76816384.pth... [2023-03-11 12:17:07,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000149336_76460032.pth [2023-03-11 12:17:09,758][04298] Updated weights for policy 0, policy_version 150080 (0.0005) [2023-03-11 12:17:12,811][04011] Fps is (10 sec: 11878.3, 60 sec: 12014.9, 300 sec: 12315.8). Total num frames: 76877824. Throughput: 0: 11980.3. Samples: 76874816. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-11 12:17:12,812][04011] Avg episode reward: [(0, '30.508')] [2023-03-11 12:17:13,115][04298] Updated weights for policy 0, policy_version 150160 (0.0005) [2023-03-11 12:17:16,572][04298] Updated weights for policy 0, policy_version 150240 (0.0005) [2023-03-11 12:17:17,811][04011] Fps is (10 sec: 11878.4, 60 sec: 11946.7, 300 sec: 12288.0). Total num frames: 76935168. Throughput: 0: 11993.1. Samples: 76910656. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-11 12:17:17,811][04011] Avg episode reward: [(0, '31.396')] [2023-03-11 12:17:20,071][04298] Updated weights for policy 0, policy_version 150320 (0.0005) [2023-03-11 12:17:22,811][04011] Fps is (10 sec: 11468.7, 60 sec: 11946.7, 300 sec: 12274.1). Total num frames: 76992512. Throughput: 0: 11912.3. Samples: 76981388. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-11 12:17:22,812][04011] Avg episode reward: [(0, '30.116')] [2023-03-11 12:17:22,852][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000150384_76996608.pth... [2023-03-11 12:17:22,853][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000149688_76640256.pth [2023-03-11 12:17:23,549][04298] Updated weights for policy 0, policy_version 150400 (0.0005) [2023-03-11 12:17:27,008][04298] Updated weights for policy 0, policy_version 150480 (0.0005) [2023-03-11 12:17:27,811][04011] Fps is (10 sec: 11878.4, 60 sec: 11946.7, 300 sec: 12260.2). Total num frames: 77053952. Throughput: 0: 11857.0. Samples: 77052104. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-11 12:17:27,811][04011] Avg episode reward: [(0, '30.599')] [2023-03-11 12:17:30,444][04298] Updated weights for policy 0, policy_version 150560 (0.0005) [2023-03-11 12:17:32,811][04011] Fps is (10 sec: 12288.1, 60 sec: 12014.9, 300 sec: 12246.3). Total num frames: 77115392. Throughput: 0: 11861.1. Samples: 77088000. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-11 12:17:32,812][04011] Avg episode reward: [(0, '30.293')] [2023-03-11 12:17:33,836][04298] Updated weights for policy 0, policy_version 150640 (0.0005) [2023-03-11 12:17:37,359][04298] Updated weights for policy 0, policy_version 150720 (0.0005) [2023-03-11 12:17:37,811][04011] Fps is (10 sec: 11878.4, 60 sec: 11878.4, 300 sec: 12218.6). Total num frames: 77172736. Throughput: 0: 11875.7. Samples: 77160172. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-11 12:17:37,812][04011] Avg episode reward: [(0, '30.175')] [2023-03-11 12:17:37,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000150728_77172736.pth... [2023-03-11 12:17:37,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000150032_76816384.pth [2023-03-11 12:17:40,817][04298] Updated weights for policy 0, policy_version 150800 (0.0005) [2023-03-11 12:17:42,811][04011] Fps is (10 sec: 11468.9, 60 sec: 11810.1, 300 sec: 12190.8). Total num frames: 77230080. Throughput: 0: 11870.8. Samples: 77230080. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-11 12:17:42,811][04011] Avg episode reward: [(0, '26.885')] [2023-03-11 12:17:44,293][04298] Updated weights for policy 0, policy_version 150880 (0.0005) [2023-03-11 12:17:47,811][04011] Fps is (10 sec: 11468.8, 60 sec: 11810.1, 300 sec: 12163.0). Total num frames: 77287424. Throughput: 0: 11854.2. Samples: 77265332. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-11 12:17:47,812][04011] Avg episode reward: [(0, '29.473')] [2023-03-11 12:17:47,826][04298] Updated weights for policy 0, policy_version 150960 (0.0005) [2023-03-11 12:17:51,232][04298] Updated weights for policy 0, policy_version 151040 (0.0005) [2023-03-11 12:17:52,811][04011] Fps is (10 sec: 11878.4, 60 sec: 11878.4, 300 sec: 12149.2). Total num frames: 77348864. Throughput: 0: 11833.1. Samples: 77336584. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-11 12:17:52,811][04011] Avg episode reward: [(0, '29.704')] [2023-03-11 12:17:52,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000151072_77348864.pth... [2023-03-11 12:17:52,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000150384_76996608.pth [2023-03-11 12:17:54,718][04298] Updated weights for policy 0, policy_version 151120 (0.0005) [2023-03-11 12:17:57,811][04011] Fps is (10 sec: 12288.1, 60 sec: 11878.4, 300 sec: 12135.3). Total num frames: 77410304. Throughput: 0: 11848.5. Samples: 77407996. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-11 12:17:57,811][04011] Avg episode reward: [(0, '27.664')] [2023-03-11 12:17:58,081][04298] Updated weights for policy 0, policy_version 151200 (0.0005) [2023-03-11 12:18:01,565][04298] Updated weights for policy 0, policy_version 151280 (0.0005) [2023-03-11 12:18:02,811][04011] Fps is (10 sec: 11878.4, 60 sec: 11810.1, 300 sec: 12107.5). Total num frames: 77467648. Throughput: 0: 11833.1. Samples: 77443144. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-11 12:18:02,811][04011] Avg episode reward: [(0, '27.762')] [2023-03-11 12:18:04,908][04298] Updated weights for policy 0, policy_version 151360 (0.0005) [2023-03-11 12:18:07,811][04011] Fps is (10 sec: 11878.3, 60 sec: 11878.4, 300 sec: 12093.6). Total num frames: 77529088. Throughput: 0: 11898.1. Samples: 77516800. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-11 12:18:07,811][04011] Avg episode reward: [(0, '27.953')] [2023-03-11 12:18:07,840][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000151432_77533184.pth... [2023-03-11 12:18:07,842][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000150728_77172736.pth [2023-03-11 12:18:08,145][04298] Updated weights for policy 0, policy_version 151440 (0.0004) [2023-03-11 12:18:11,294][04298] Updated weights for policy 0, policy_version 151520 (0.0004) [2023-03-11 12:18:12,811][04011] Fps is (10 sec: 12697.5, 60 sec: 11946.7, 300 sec: 12107.5). Total num frames: 77594624. Throughput: 0: 12052.0. Samples: 77594444. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-11 12:18:12,811][04011] Avg episode reward: [(0, '27.465')] [2023-03-11 12:18:14,506][04298] Updated weights for policy 0, policy_version 151600 (0.0003) [2023-03-11 12:18:17,811][04011] Fps is (10 sec: 12697.6, 60 sec: 12014.9, 300 sec: 12093.6). Total num frames: 77656064. Throughput: 0: 12089.5. Samples: 77632028. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-11 12:18:17,812][04011] Avg episode reward: [(0, '23.357')] [2023-03-11 12:18:17,816][04298] Updated weights for policy 0, policy_version 151680 (0.0004) [2023-03-11 12:18:21,048][04298] Updated weights for policy 0, policy_version 151760 (0.0004) [2023-03-11 12:18:22,811][04011] Fps is (10 sec: 12697.6, 60 sec: 12151.5, 300 sec: 12093.6). Total num frames: 77721600. Throughput: 0: 12164.5. Samples: 77707572. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-11 12:18:22,811][04011] Avg episode reward: [(0, '24.261')] [2023-03-11 12:18:22,813][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000151800_77721600.pth... [2023-03-11 12:18:22,816][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000151072_77348864.pth [2023-03-11 12:18:24,200][04298] Updated weights for policy 0, policy_version 151840 (0.0004) [2023-03-11 12:18:27,476][04298] Updated weights for policy 0, policy_version 151920 (0.0004) [2023-03-11 12:18:27,811][04011] Fps is (10 sec: 13107.3, 60 sec: 12219.7, 300 sec: 12107.5). Total num frames: 77787136. Throughput: 0: 12303.6. Samples: 77783744. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-11 12:18:27,811][04011] Avg episode reward: [(0, '22.949')] [2023-03-11 12:18:30,667][04298] Updated weights for policy 0, policy_version 152000 (0.0005) [2023-03-11 12:18:32,811][04011] Fps is (10 sec: 12697.5, 60 sec: 12219.7, 300 sec: 12093.6). Total num frames: 77848576. Throughput: 0: 12383.1. Samples: 77822572. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-11 12:18:32,811][04011] Avg episode reward: [(0, '24.816')] [2023-03-11 12:18:34,018][04298] Updated weights for policy 0, policy_version 152080 (0.0004) [2023-03-11 12:18:37,318][04298] Updated weights for policy 0, policy_version 152160 (0.0004) [2023-03-11 12:18:37,811][04011] Fps is (10 sec: 12287.9, 60 sec: 12288.0, 300 sec: 12079.7). Total num frames: 77910016. Throughput: 0: 12434.6. Samples: 77896140. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-11 12:18:37,812][04011] Avg episode reward: [(0, '22.425')] [2023-03-11 12:18:37,816][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000152168_77910016.pth... [2023-03-11 12:18:37,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000151432_77533184.pth [2023-03-11 12:18:40,732][04298] Updated weights for policy 0, policy_version 152240 (0.0005) [2023-03-11 12:18:42,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12288.0, 300 sec: 12052.0). Total num frames: 77967360. Throughput: 0: 12436.3. Samples: 77967632. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-11 12:18:42,822][04011] Avg episode reward: [(0, '20.843')] [2023-03-11 12:18:44,276][04298] Updated weights for policy 0, policy_version 152320 (0.0005) [2023-03-11 12:18:47,695][04298] Updated weights for policy 0, policy_version 152400 (0.0005) [2023-03-11 12:18:47,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12356.3, 300 sec: 12052.0). Total num frames: 78028800. Throughput: 0: 12445.8. Samples: 78003204. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 12:18:47,822][04011] Avg episode reward: [(0, '17.918')] [2023-03-11 12:18:51,311][04298] Updated weights for policy 0, policy_version 152480 (0.0005) [2023-03-11 12:18:52,811][04011] Fps is (10 sec: 11878.5, 60 sec: 12288.0, 300 sec: 12024.2). Total num frames: 78086144. Throughput: 0: 12356.8. Samples: 78072856. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 12:18:52,822][04011] Avg episode reward: [(0, '19.998')] [2023-03-11 12:18:52,825][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000152512_78086144.pth... [2023-03-11 12:18:52,828][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000151800_77721600.pth [2023-03-11 12:18:55,039][04298] Updated weights for policy 0, policy_version 152560 (0.0005) [2023-03-11 12:18:57,811][04011] Fps is (10 sec: 11468.8, 60 sec: 12219.7, 300 sec: 12010.3). Total num frames: 78143488. Throughput: 0: 12122.0. Samples: 78139932. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 12:18:57,822][04011] Avg episode reward: [(0, '19.823')] [2023-03-11 12:18:58,420][04298] Updated weights for policy 0, policy_version 152640 (0.0005) [2023-03-11 12:19:01,692][04298] Updated weights for policy 0, policy_version 152720 (0.0004) [2023-03-11 12:19:02,811][04011] Fps is (10 sec: 11878.3, 60 sec: 12288.0, 300 sec: 12010.3). Total num frames: 78204928. Throughput: 0: 12170.0. Samples: 78179680. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 12:19:02,822][04011] Avg episode reward: [(0, '21.074')] [2023-03-11 12:19:05,264][04298] Updated weights for policy 0, policy_version 152800 (0.0005) [2023-03-11 12:19:07,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12219.7, 300 sec: 11982.5). Total num frames: 78262272. Throughput: 0: 12025.6. Samples: 78248724. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 12:19:07,822][04011] Avg episode reward: [(0, '23.109')] [2023-03-11 12:19:07,825][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000152856_78262272.pth... [2023-03-11 12:19:07,828][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000152168_77910016.pth [2023-03-11 12:19:08,712][04298] Updated weights for policy 0, policy_version 152880 (0.0005) [2023-03-11 12:19:12,252][04298] Updated weights for policy 0, policy_version 152960 (0.0005) [2023-03-11 12:19:12,811][04011] Fps is (10 sec: 11468.8, 60 sec: 12083.2, 300 sec: 11968.7). Total num frames: 78319616. Throughput: 0: 11908.3. Samples: 78319616. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 12:19:12,822][04011] Avg episode reward: [(0, '24.007')] [2023-03-11 12:19:15,726][04298] Updated weights for policy 0, policy_version 153040 (0.0005) [2023-03-11 12:19:17,811][04011] Fps is (10 sec: 11878.5, 60 sec: 12083.2, 300 sec: 11968.7). Total num frames: 78381056. Throughput: 0: 11820.6. Samples: 78354496. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 12:19:17,822][04011] Avg episode reward: [(0, '25.649')] [2023-03-11 12:19:19,153][04298] Updated weights for policy 0, policy_version 153120 (0.0005) [2023-03-11 12:19:22,583][04298] Updated weights for policy 0, policy_version 153200 (0.0005) [2023-03-11 12:19:22,811][04011] Fps is (10 sec: 11878.4, 60 sec: 11946.7, 300 sec: 11954.8). Total num frames: 78438400. Throughput: 0: 11770.6. Samples: 78425816. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 12:19:22,822][04011] Avg episode reward: [(0, '29.900')] [2023-03-11 12:19:22,826][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000153200_78438400.pth... [2023-03-11 12:19:22,828][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000152512_78086144.pth [2023-03-11 12:19:26,003][04298] Updated weights for policy 0, policy_version 153280 (0.0005) [2023-03-11 12:19:27,811][04011] Fps is (10 sec: 11878.3, 60 sec: 11878.4, 300 sec: 11954.8). Total num frames: 78499840. Throughput: 0: 11758.4. Samples: 78496760. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 12:19:27,822][04011] Avg episode reward: [(0, '28.538')] [2023-03-11 12:19:29,602][04298] Updated weights for policy 0, policy_version 153360 (0.0005) [2023-03-11 12:19:32,811][04011] Fps is (10 sec: 11878.4, 60 sec: 11810.1, 300 sec: 11940.9). Total num frames: 78557184. Throughput: 0: 11755.1. Samples: 78532184. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 12:19:32,822][04011] Avg episode reward: [(0, '26.938')] [2023-03-11 12:19:33,112][04298] Updated weights for policy 0, policy_version 153440 (0.0005) [2023-03-11 12:19:36,591][04298] Updated weights for policy 0, policy_version 153520 (0.0005) [2023-03-11 12:19:37,811][04011] Fps is (10 sec: 11468.8, 60 sec: 11741.9, 300 sec: 11940.9). Total num frames: 78614528. Throughput: 0: 11764.1. Samples: 78602240. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 12:19:37,822][04011] Avg episode reward: [(0, '25.816')] [2023-03-11 12:19:37,825][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000153544_78614528.pth... [2023-03-11 12:19:37,828][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000152856_78262272.pth [2023-03-11 12:19:40,038][04298] Updated weights for policy 0, policy_version 153600 (0.0005) [2023-03-11 12:19:42,811][04011] Fps is (10 sec: 11468.8, 60 sec: 11741.9, 300 sec: 11927.0). Total num frames: 78671872. Throughput: 0: 11844.1. Samples: 78672916. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 12:19:42,822][04011] Avg episode reward: [(0, '29.131')] [2023-03-11 12:19:43,510][04298] Updated weights for policy 0, policy_version 153680 (0.0005) [2023-03-11 12:19:47,085][04298] Updated weights for policy 0, policy_version 153760 (0.0005) [2023-03-11 12:19:47,811][04011] Fps is (10 sec: 11878.4, 60 sec: 11741.9, 300 sec: 11927.0). Total num frames: 78733312. Throughput: 0: 11735.2. Samples: 78707764. Policy #0 lag: (min: 5.0, avg: 5.0, max: 5.0) [2023-03-11 12:19:47,822][04011] Avg episode reward: [(0, '26.517')] [2023-03-11 12:19:50,645][04298] Updated weights for policy 0, policy_version 153840 (0.0005) [2023-03-11 12:19:52,811][04011] Fps is (10 sec: 11878.4, 60 sec: 11741.9, 300 sec: 11913.1). Total num frames: 78790656. Throughput: 0: 11739.9. Samples: 78777020. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-11 12:19:52,822][04011] Avg episode reward: [(0, '28.509')] [2023-03-11 12:19:52,825][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000153888_78790656.pth... [2023-03-11 12:19:52,828][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000153200_78438400.pth [2023-03-11 12:19:54,156][04298] Updated weights for policy 0, policy_version 153920 (0.0005) [2023-03-11 12:19:57,606][04298] Updated weights for policy 0, policy_version 154000 (0.0005) [2023-03-11 12:19:57,811][04011] Fps is (10 sec: 11468.9, 60 sec: 11741.9, 300 sec: 11913.1). Total num frames: 78848000. Throughput: 0: 11741.9. Samples: 78848000. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-11 12:19:57,811][04011] Avg episode reward: [(0, '26.118')] [2023-03-11 12:20:01,000][04298] Updated weights for policy 0, policy_version 154080 (0.0004) [2023-03-11 12:20:02,811][04011] Fps is (10 sec: 11878.5, 60 sec: 11741.9, 300 sec: 11913.1). Total num frames: 78909440. Throughput: 0: 11749.9. Samples: 78883244. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-11 12:20:02,811][04011] Avg episode reward: [(0, '25.516')] [2023-03-11 12:20:04,083][04298] Updated weights for policy 0, policy_version 154160 (0.0003) [2023-03-11 12:20:07,600][04298] Updated weights for policy 0, policy_version 154240 (0.0005) [2023-03-11 12:20:07,811][04011] Fps is (10 sec: 12288.0, 60 sec: 11810.1, 300 sec: 11927.0). Total num frames: 78970880. Throughput: 0: 11844.6. Samples: 78958824. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-11 12:20:07,811][04011] Avg episode reward: [(0, '26.065')] [2023-03-11 12:20:07,814][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000154240_78970880.pth... [2023-03-11 12:20:07,815][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000153544_78614528.pth [2023-03-11 12:20:11,051][04298] Updated weights for policy 0, policy_version 154320 (0.0004) [2023-03-11 12:20:12,811][04011] Fps is (10 sec: 11878.5, 60 sec: 11810.1, 300 sec: 11927.0). Total num frames: 79028224. Throughput: 0: 11827.8. Samples: 79029012. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-11 12:20:12,811][04011] Avg episode reward: [(0, '24.722')] [2023-03-11 12:20:14,574][04298] Updated weights for policy 0, policy_version 154400 (0.0005) [2023-03-11 12:20:17,811][04011] Fps is (10 sec: 11878.4, 60 sec: 11810.1, 300 sec: 11940.9). Total num frames: 79089664. Throughput: 0: 11838.8. Samples: 79064928. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-11 12:20:17,811][04011] Avg episode reward: [(0, '28.625')] [2023-03-11 12:20:18,015][04298] Updated weights for policy 0, policy_version 154480 (0.0005) [2023-03-11 12:20:21,500][04298] Updated weights for policy 0, policy_version 154560 (0.0005) [2023-03-11 12:20:22,811][04011] Fps is (10 sec: 11878.3, 60 sec: 11810.1, 300 sec: 11940.9). Total num frames: 79147008. Throughput: 0: 11839.6. Samples: 79135024. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-11 12:20:22,811][04011] Avg episode reward: [(0, '29.772')] [2023-03-11 12:20:22,814][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000154584_79147008.pth... [2023-03-11 12:20:22,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000153888_78790656.pth [2023-03-11 12:20:24,965][04298] Updated weights for policy 0, policy_version 154640 (0.0005) [2023-03-11 12:20:27,811][04011] Fps is (10 sec: 11878.3, 60 sec: 11810.1, 300 sec: 11954.8). Total num frames: 79208448. Throughput: 0: 11876.1. Samples: 79207340. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-11 12:20:27,811][04011] Avg episode reward: [(0, '25.654')] [2023-03-11 12:20:28,421][04298] Updated weights for policy 0, policy_version 154720 (0.0005) [2023-03-11 12:20:31,960][04298] Updated weights for policy 0, policy_version 154800 (0.0005) [2023-03-11 12:20:32,811][04011] Fps is (10 sec: 11878.5, 60 sec: 11810.1, 300 sec: 11954.8). Total num frames: 79265792. Throughput: 0: 11855.9. Samples: 79241280. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-11 12:20:32,811][04011] Avg episode reward: [(0, '25.240')] [2023-03-11 12:20:35,506][04298] Updated weights for policy 0, policy_version 154880 (0.0005) [2023-03-11 12:20:37,811][04011] Fps is (10 sec: 11468.8, 60 sec: 11810.1, 300 sec: 11940.9). Total num frames: 79323136. Throughput: 0: 11863.0. Samples: 79310856. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-11 12:20:37,811][04011] Avg episode reward: [(0, '28.445')] [2023-03-11 12:20:37,814][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000154928_79323136.pth... [2023-03-11 12:20:37,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000154240_78970880.pth [2023-03-11 12:20:39,091][04298] Updated weights for policy 0, policy_version 154960 (0.0005) [2023-03-11 12:20:42,633][04298] Updated weights for policy 0, policy_version 155040 (0.0005) [2023-03-11 12:20:42,811][04011] Fps is (10 sec: 11468.8, 60 sec: 11810.1, 300 sec: 11927.0). Total num frames: 79380480. Throughput: 0: 11826.6. Samples: 79380196. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-11 12:20:42,811][04011] Avg episode reward: [(0, '25.499')] [2023-03-11 12:20:46,167][04298] Updated weights for policy 0, policy_version 155120 (0.0005) [2023-03-11 12:20:47,811][04011] Fps is (10 sec: 11468.8, 60 sec: 11741.9, 300 sec: 11927.0). Total num frames: 79437824. Throughput: 0: 11806.5. Samples: 79414536. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-11 12:20:47,820][04011] Avg episode reward: [(0, '26.285')] [2023-03-11 12:20:49,772][04298] Updated weights for policy 0, policy_version 155200 (0.0005) [2023-03-11 12:20:52,811][04011] Fps is (10 sec: 11468.8, 60 sec: 11741.9, 300 sec: 11927.0). Total num frames: 79495168. Throughput: 0: 11647.3. Samples: 79482952. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-11 12:20:52,822][04011] Avg episode reward: [(0, '26.214')] [2023-03-11 12:20:52,824][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000155264_79495168.pth... [2023-03-11 12:20:52,826][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000154584_79147008.pth [2023-03-11 12:20:53,245][04298] Updated weights for policy 0, policy_version 155280 (0.0005) [2023-03-11 12:20:56,883][04298] Updated weights for policy 0, policy_version 155360 (0.0005) [2023-03-11 12:20:57,811][04011] Fps is (10 sec: 11468.8, 60 sec: 11741.9, 300 sec: 11913.1). Total num frames: 79552512. Throughput: 0: 11633.7. Samples: 79552528. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-11 12:20:57,822][04011] Avg episode reward: [(0, '22.875')] [2023-03-11 12:21:00,422][04298] Updated weights for policy 0, policy_version 155440 (0.0005) [2023-03-11 12:21:02,811][04011] Fps is (10 sec: 11468.8, 60 sec: 11673.6, 300 sec: 11913.1). Total num frames: 79609856. Throughput: 0: 11597.4. Samples: 79586812. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-11 12:21:02,811][04011] Avg episode reward: [(0, '20.231')] [2023-03-11 12:21:03,893][04298] Updated weights for policy 0, policy_version 155520 (0.0005) [2023-03-11 12:21:07,125][04298] Updated weights for policy 0, policy_version 155600 (0.0004) [2023-03-11 12:21:07,811][04011] Fps is (10 sec: 12287.9, 60 sec: 11741.8, 300 sec: 11927.0). Total num frames: 79675392. Throughput: 0: 11656.8. Samples: 79659580. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-11 12:21:07,812][04011] Avg episode reward: [(0, '25.203')] [2023-03-11 12:21:07,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000155616_79675392.pth... [2023-03-11 12:21:07,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000154928_79323136.pth [2023-03-11 12:21:10,610][04298] Updated weights for policy 0, policy_version 155680 (0.0005) [2023-03-11 12:21:12,811][04011] Fps is (10 sec: 12288.0, 60 sec: 11741.9, 300 sec: 11913.1). Total num frames: 79732736. Throughput: 0: 11628.6. Samples: 79730628. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-11 12:21:12,811][04011] Avg episode reward: [(0, '23.387')] [2023-03-11 12:21:14,236][04298] Updated weights for policy 0, policy_version 155760 (0.0005) [2023-03-11 12:21:17,777][04298] Updated weights for policy 0, policy_version 155840 (0.0005) [2023-03-11 12:21:17,811][04011] Fps is (10 sec: 11468.9, 60 sec: 11673.6, 300 sec: 11913.1). Total num frames: 79790080. Throughput: 0: 11624.0. Samples: 79764360. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-11 12:21:17,811][04011] Avg episode reward: [(0, '24.485')] [2023-03-11 12:21:21,317][04298] Updated weights for policy 0, policy_version 155920 (0.0005) [2023-03-11 12:21:22,811][04011] Fps is (10 sec: 11468.8, 60 sec: 11673.6, 300 sec: 11899.2). Total num frames: 79847424. Throughput: 0: 11628.1. Samples: 79834120. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-11 12:21:22,811][04011] Avg episode reward: [(0, '20.539')] [2023-03-11 12:21:22,814][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000155952_79847424.pth... [2023-03-11 12:21:22,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000155264_79495168.pth [2023-03-11 12:21:24,741][04298] Updated weights for policy 0, policy_version 156000 (0.0005) [2023-03-11 12:21:27,811][04011] Fps is (10 sec: 11878.4, 60 sec: 11673.6, 300 sec: 11913.1). Total num frames: 79908864. Throughput: 0: 11709.9. Samples: 79907140. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-11 12:21:27,811][04011] Avg episode reward: [(0, '20.087')] [2023-03-11 12:21:28,026][04298] Updated weights for policy 0, policy_version 156080 (0.0004) [2023-03-11 12:21:31,341][04298] Updated weights for policy 0, policy_version 156160 (0.0004) [2023-03-11 12:21:32,811][04011] Fps is (10 sec: 12288.0, 60 sec: 11741.9, 300 sec: 11899.2). Total num frames: 79970304. Throughput: 0: 11779.2. Samples: 79944600. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-11 12:21:32,811][04011] Avg episode reward: [(0, '18.432')] [2023-03-11 12:21:34,740][04298] Updated weights for policy 0, policy_version 156240 (0.0004) [2023-03-11 12:21:37,811][04011] Fps is (10 sec: 12287.9, 60 sec: 11810.1, 300 sec: 11899.2). Total num frames: 80031744. Throughput: 0: 11862.4. Samples: 80016760. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-11 12:21:37,822][04011] Avg episode reward: [(0, '18.192')] [2023-03-11 12:21:37,825][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000156312_80031744.pth... [2023-03-11 12:21:37,828][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000155616_79675392.pth [2023-03-11 12:21:38,060][04298] Updated weights for policy 0, policy_version 156320 (0.0004) [2023-03-11 12:21:41,547][04298] Updated weights for policy 0, policy_version 156400 (0.0005) [2023-03-11 12:21:42,811][04011] Fps is (10 sec: 11878.4, 60 sec: 11810.1, 300 sec: 11899.2). Total num frames: 80089088. Throughput: 0: 11897.3. Samples: 80087908. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-11 12:21:42,822][04011] Avg episode reward: [(0, '20.910')] [2023-03-11 12:21:45,336][04298] Updated weights for policy 0, policy_version 156480 (0.0005) [2023-03-11 12:21:47,811][04011] Fps is (10 sec: 11059.3, 60 sec: 11741.9, 300 sec: 11885.3). Total num frames: 80142336. Throughput: 0: 11857.7. Samples: 80120408. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-11 12:21:47,822][04011] Avg episode reward: [(0, '18.992')] [2023-03-11 12:21:49,147][04298] Updated weights for policy 0, policy_version 156560 (0.0005) [2023-03-11 12:21:52,700][04298] Updated weights for policy 0, policy_version 156640 (0.0004) [2023-03-11 12:21:52,811][04011] Fps is (10 sec: 11059.1, 60 sec: 11741.9, 300 sec: 11871.5). Total num frames: 80199680. Throughput: 0: 11728.1. Samples: 80187344. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-11 12:21:52,822][04011] Avg episode reward: [(0, '21.679')] [2023-03-11 12:21:52,826][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000156640_80199680.pth... [2023-03-11 12:21:52,828][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000155952_79847424.pth [2023-03-11 12:21:56,256][04298] Updated weights for policy 0, policy_version 156720 (0.0005) [2023-03-11 12:21:57,811][04011] Fps is (10 sec: 11468.8, 60 sec: 11741.9, 300 sec: 11857.6). Total num frames: 80257024. Throughput: 0: 11658.8. Samples: 80255272. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-11 12:21:57,822][04011] Avg episode reward: [(0, '21.900')] [2023-03-11 12:21:59,836][04298] Updated weights for policy 0, policy_version 156800 (0.0005) [2023-03-11 12:22:02,811][04011] Fps is (10 sec: 11468.8, 60 sec: 11741.9, 300 sec: 11857.6). Total num frames: 80314368. Throughput: 0: 11676.5. Samples: 80289804. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:22:02,822][04011] Avg episode reward: [(0, '24.437')] [2023-03-11 12:22:03,428][04298] Updated weights for policy 0, policy_version 156880 (0.0005) [2023-03-11 12:22:07,064][04298] Updated weights for policy 0, policy_version 156960 (0.0005) [2023-03-11 12:22:07,811][04011] Fps is (10 sec: 11468.8, 60 sec: 11605.4, 300 sec: 11843.7). Total num frames: 80371712. Throughput: 0: 11651.5. Samples: 80358436. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:22:07,822][04011] Avg episode reward: [(0, '24.250')] [2023-03-11 12:22:07,825][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000156976_80371712.pth... [2023-03-11 12:22:07,828][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000156312_80031744.pth [2023-03-11 12:22:10,567][04298] Updated weights for policy 0, policy_version 157040 (0.0005) [2023-03-11 12:22:12,811][04011] Fps is (10 sec: 11468.8, 60 sec: 11605.3, 300 sec: 11843.7). Total num frames: 80429056. Throughput: 0: 11568.3. Samples: 80427712. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:22:12,822][04011] Avg episode reward: [(0, '25.049')] [2023-03-11 12:22:14,101][04298] Updated weights for policy 0, policy_version 157120 (0.0005) [2023-03-11 12:22:17,659][04298] Updated weights for policy 0, policy_version 157200 (0.0005) [2023-03-11 12:22:17,811][04011] Fps is (10 sec: 11468.7, 60 sec: 11605.3, 300 sec: 11843.7). Total num frames: 80486400. Throughput: 0: 11494.0. Samples: 80461832. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:22:17,812][04011] Avg episode reward: [(0, '25.847')] [2023-03-11 12:22:21,164][04298] Updated weights for policy 0, policy_version 157280 (0.0005) [2023-03-11 12:22:22,811][04011] Fps is (10 sec: 11468.8, 60 sec: 11605.3, 300 sec: 11829.8). Total num frames: 80543744. Throughput: 0: 11439.3. Samples: 80531528. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:22:22,811][04011] Avg episode reward: [(0, '28.290')] [2023-03-11 12:22:22,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000157312_80543744.pth... [2023-03-11 12:22:22,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000156640_80199680.pth [2023-03-11 12:22:24,681][04298] Updated weights for policy 0, policy_version 157360 (0.0005) [2023-03-11 12:22:27,811][04011] Fps is (10 sec: 11468.9, 60 sec: 11537.1, 300 sec: 11815.9). Total num frames: 80601088. Throughput: 0: 11414.1. Samples: 80601544. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:22:27,811][04011] Avg episode reward: [(0, '27.188')] [2023-03-11 12:22:28,193][04298] Updated weights for policy 0, policy_version 157440 (0.0005) [2023-03-11 12:22:31,721][04298] Updated weights for policy 0, policy_version 157520 (0.0005) [2023-03-11 12:22:32,811][04011] Fps is (10 sec: 11878.4, 60 sec: 11537.1, 300 sec: 11829.8). Total num frames: 80662528. Throughput: 0: 11482.3. Samples: 80637112. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:22:32,811][04011] Avg episode reward: [(0, '27.066')] [2023-03-11 12:22:35,200][04298] Updated weights for policy 0, policy_version 157600 (0.0005) [2023-03-11 12:22:37,811][04011] Fps is (10 sec: 11878.3, 60 sec: 11468.8, 300 sec: 11829.8). Total num frames: 80719872. Throughput: 0: 11557.2. Samples: 80707416. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:22:37,811][04011] Avg episode reward: [(0, '32.102')] [2023-03-11 12:22:37,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000157656_80719872.pth... [2023-03-11 12:22:37,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000156976_80371712.pth [2023-03-11 12:22:38,810][04298] Updated weights for policy 0, policy_version 157680 (0.0005) [2023-03-11 12:22:42,385][04298] Updated weights for policy 0, policy_version 157760 (0.0005) [2023-03-11 12:22:42,811][04011] Fps is (10 sec: 11468.7, 60 sec: 11468.8, 300 sec: 11829.8). Total num frames: 80777216. Throughput: 0: 11555.1. Samples: 80775252. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:22:42,812][04011] Avg episode reward: [(0, '28.293')] [2023-03-11 12:22:46,068][04298] Updated weights for policy 0, policy_version 157840 (0.0005) [2023-03-11 12:22:47,811][04011] Fps is (10 sec: 11059.3, 60 sec: 11468.8, 300 sec: 11802.0). Total num frames: 80830464. Throughput: 0: 11528.7. Samples: 80808596. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:22:47,811][04011] Avg episode reward: [(0, '23.520')] [2023-03-11 12:22:49,681][04298] Updated weights for policy 0, policy_version 157920 (0.0005) [2023-03-11 12:22:52,811][04011] Fps is (10 sec: 11059.3, 60 sec: 11468.8, 300 sec: 11788.1). Total num frames: 80887808. Throughput: 0: 11516.9. Samples: 80876696. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:22:52,811][04011] Avg episode reward: [(0, '28.923')] [2023-03-11 12:22:52,852][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000157992_80891904.pth... [2023-03-11 12:22:52,853][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000157312_80543744.pth [2023-03-11 12:22:53,189][04298] Updated weights for policy 0, policy_version 158000 (0.0005) [2023-03-11 12:22:56,841][04298] Updated weights for policy 0, policy_version 158080 (0.0005) [2023-03-11 12:22:57,811][04011] Fps is (10 sec: 11468.7, 60 sec: 11468.8, 300 sec: 11788.1). Total num frames: 80945152. Throughput: 0: 11500.1. Samples: 80945216. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:22:57,811][04011] Avg episode reward: [(0, '29.021')] [2023-03-11 12:23:00,312][04298] Updated weights for policy 0, policy_version 158160 (0.0005) [2023-03-11 12:23:02,811][04011] Fps is (10 sec: 11468.7, 60 sec: 11468.8, 300 sec: 11774.3). Total num frames: 81002496. Throughput: 0: 11539.9. Samples: 80981128. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:23:02,811][04011] Avg episode reward: [(0, '30.135')] [2023-03-11 12:23:03,925][04298] Updated weights for policy 0, policy_version 158240 (0.0005) [2023-03-11 12:23:07,459][04298] Updated weights for policy 0, policy_version 158320 (0.0004) [2023-03-11 12:23:07,811][04011] Fps is (10 sec: 11878.4, 60 sec: 11537.1, 300 sec: 11760.4). Total num frames: 81063936. Throughput: 0: 11497.2. Samples: 81048904. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:23:07,812][04011] Avg episode reward: [(0, '31.519')] [2023-03-11 12:23:07,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000158328_81063936.pth... [2023-03-11 12:23:07,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000157656_80719872.pth [2023-03-11 12:23:11,016][04298] Updated weights for policy 0, policy_version 158400 (0.0005) [2023-03-11 12:23:12,811][04011] Fps is (10 sec: 11878.4, 60 sec: 11537.1, 300 sec: 11746.5). Total num frames: 81121280. Throughput: 0: 11474.9. Samples: 81117916. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:23:12,812][04011] Avg episode reward: [(0, '29.267')] [2023-03-11 12:23:14,601][04298] Updated weights for policy 0, policy_version 158480 (0.0005) [2023-03-11 12:23:17,811][04011] Fps is (10 sec: 11468.9, 60 sec: 11537.1, 300 sec: 11718.7). Total num frames: 81178624. Throughput: 0: 11480.4. Samples: 81153728. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:23:17,811][04011] Avg episode reward: [(0, '30.919')] [2023-03-11 12:23:18,055][04298] Updated weights for policy 0, policy_version 158560 (0.0005) [2023-03-11 12:23:21,789][04298] Updated weights for policy 0, policy_version 158640 (0.0005) [2023-03-11 12:23:22,811][04011] Fps is (10 sec: 11059.3, 60 sec: 11468.8, 300 sec: 11677.1). Total num frames: 81231872. Throughput: 0: 11406.2. Samples: 81220696. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:23:22,811][04011] Avg episode reward: [(0, '29.152')] [2023-03-11 12:23:22,864][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000158664_81235968.pth... [2023-03-11 12:23:22,865][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000157992_80891904.pth [2023-03-11 12:23:25,392][04298] Updated weights for policy 0, policy_version 158720 (0.0005) [2023-03-11 12:23:27,811][04011] Fps is (10 sec: 11059.2, 60 sec: 11468.8, 300 sec: 11663.2). Total num frames: 81289216. Throughput: 0: 11423.1. Samples: 81289288. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:23:27,811][04011] Avg episode reward: [(0, '29.313')] [2023-03-11 12:23:28,825][04298] Updated weights for policy 0, policy_version 158800 (0.0005) [2023-03-11 12:23:32,022][04298] Updated weights for policy 0, policy_version 158880 (0.0004) [2023-03-11 12:23:32,811][04011] Fps is (10 sec: 12288.0, 60 sec: 11537.1, 300 sec: 11677.1). Total num frames: 81354752. Throughput: 0: 11539.9. Samples: 81327892. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:23:32,811][04011] Avg episode reward: [(0, '29.608')] [2023-03-11 12:23:35,349][04298] Updated weights for policy 0, policy_version 158960 (0.0005) [2023-03-11 12:23:37,811][04011] Fps is (10 sec: 12697.5, 60 sec: 11605.3, 300 sec: 11691.0). Total num frames: 81416192. Throughput: 0: 11705.0. Samples: 81403424. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:23:37,811][04011] Avg episode reward: [(0, '29.436')] [2023-03-11 12:23:37,814][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000159016_81416192.pth... [2023-03-11 12:23:37,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000158328_81063936.pth [2023-03-11 12:23:38,538][04298] Updated weights for policy 0, policy_version 159040 (0.0004) [2023-03-11 12:23:41,870][04298] Updated weights for policy 0, policy_version 159120 (0.0004) [2023-03-11 12:23:42,811][04011] Fps is (10 sec: 12288.0, 60 sec: 11673.6, 300 sec: 11691.0). Total num frames: 81477632. Throughput: 0: 11836.2. Samples: 81477844. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:23:42,811][04011] Avg episode reward: [(0, '30.284')] [2023-03-11 12:23:45,205][04298] Updated weights for policy 0, policy_version 159200 (0.0004) [2023-03-11 12:23:47,811][04011] Fps is (10 sec: 12697.7, 60 sec: 11878.4, 300 sec: 11718.7). Total num frames: 81543168. Throughput: 0: 11854.2. Samples: 81514568. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:23:47,812][04011] Avg episode reward: [(0, '30.221')] [2023-03-11 12:23:48,474][04298] Updated weights for policy 0, policy_version 159280 (0.0004) [2023-03-11 12:23:51,928][04298] Updated weights for policy 0, policy_version 159360 (0.0005) [2023-03-11 12:23:52,811][04011] Fps is (10 sec: 12287.9, 60 sec: 11878.4, 300 sec: 11718.7). Total num frames: 81600512. Throughput: 0: 11985.1. Samples: 81588232. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:23:52,811][04011] Avg episode reward: [(0, '30.826')] [2023-03-11 12:23:52,814][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000159376_81600512.pth... [2023-03-11 12:23:52,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000158664_81235968.pth [2023-03-11 12:23:55,097][04298] Updated weights for policy 0, policy_version 159440 (0.0004) [2023-03-11 12:23:57,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12014.9, 300 sec: 11732.6). Total num frames: 81666048. Throughput: 0: 12142.3. Samples: 81664320. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:23:57,811][04011] Avg episode reward: [(0, '30.245')] [2023-03-11 12:23:58,285][04298] Updated weights for policy 0, policy_version 159520 (0.0004) [2023-03-11 12:24:01,341][04298] Updated weights for policy 0, policy_version 159600 (0.0003) [2023-03-11 12:24:02,811][04011] Fps is (10 sec: 13107.3, 60 sec: 12151.5, 300 sec: 11760.4). Total num frames: 81731584. Throughput: 0: 12234.8. Samples: 81704296. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:24:02,811][04011] Avg episode reward: [(0, '30.780')] [2023-03-11 12:24:04,417][04298] Updated weights for policy 0, policy_version 159680 (0.0004) [2023-03-11 12:24:07,538][04298] Updated weights for policy 0, policy_version 159760 (0.0004) [2023-03-11 12:24:07,811][04011] Fps is (10 sec: 13107.2, 60 sec: 12219.7, 300 sec: 11788.2). Total num frames: 81797120. Throughput: 0: 12525.9. Samples: 81784360. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:24:07,811][04011] Avg episode reward: [(0, '32.536')] [2023-03-11 12:24:07,836][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000159768_81801216.pth... [2023-03-11 12:24:07,838][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000159016_81416192.pth [2023-03-11 12:24:10,631][04298] Updated weights for policy 0, policy_version 159840 (0.0004) [2023-03-11 12:24:12,811][04011] Fps is (10 sec: 13107.2, 60 sec: 12356.3, 300 sec: 11802.0). Total num frames: 81862656. Throughput: 0: 12742.9. Samples: 81862720. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:24:12,811][04011] Avg episode reward: [(0, '32.774')] [2023-03-11 12:24:13,948][04298] Updated weights for policy 0, policy_version 159920 (0.0004) [2023-03-11 12:24:17,367][04298] Updated weights for policy 0, policy_version 160000 (0.0005) [2023-03-11 12:24:17,811][04011] Fps is (10 sec: 12697.5, 60 sec: 12424.5, 300 sec: 11815.9). Total num frames: 81924096. Throughput: 0: 12677.3. Samples: 81898372. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:24:17,812][04011] Avg episode reward: [(0, '33.121')] [2023-03-11 12:24:20,848][04298] Updated weights for policy 0, policy_version 160080 (0.0005) [2023-03-11 12:24:22,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12492.8, 300 sec: 11802.0). Total num frames: 81981440. Throughput: 0: 12571.9. Samples: 81969160. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:24:22,811][04011] Avg episode reward: [(0, '33.551')] [2023-03-11 12:24:22,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000160120_81981440.pth... [2023-03-11 12:24:22,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000159376_81600512.pth [2023-03-11 12:24:22,818][04254] Saving new best policy, reward=33.551! [2023-03-11 12:24:24,363][04298] Updated weights for policy 0, policy_version 160160 (0.0005) [2023-03-11 12:24:27,684][04298] Updated weights for policy 0, policy_version 160240 (0.0005) [2023-03-11 12:24:27,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12561.1, 300 sec: 11815.9). Total num frames: 82042880. Throughput: 0: 12529.7. Samples: 82041680. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:24:27,812][04011] Avg episode reward: [(0, '33.275')] [2023-03-11 12:24:31,025][04298] Updated weights for policy 0, policy_version 160320 (0.0005) [2023-03-11 12:24:32,811][04011] Fps is (10 sec: 12288.1, 60 sec: 12492.8, 300 sec: 11829.8). Total num frames: 82104320. Throughput: 0: 12533.3. Samples: 82078564. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:24:32,811][04011] Avg episode reward: [(0, '32.792')] [2023-03-11 12:24:34,436][04298] Updated weights for policy 0, policy_version 160400 (0.0005) [2023-03-11 12:24:37,771][04298] Updated weights for policy 0, policy_version 160480 (0.0004) [2023-03-11 12:24:37,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12492.8, 300 sec: 11843.7). Total num frames: 82165760. Throughput: 0: 12509.2. Samples: 82151148. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:24:37,812][04011] Avg episode reward: [(0, '33.446')] [2023-03-11 12:24:37,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000160480_82165760.pth... [2023-03-11 12:24:37,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000159768_81801216.pth [2023-03-11 12:24:41,173][04298] Updated weights for policy 0, policy_version 160560 (0.0005) [2023-03-11 12:24:42,811][04011] Fps is (10 sec: 11878.3, 60 sec: 12424.5, 300 sec: 11829.8). Total num frames: 82223104. Throughput: 0: 12419.0. Samples: 82223176. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:24:42,811][04011] Avg episode reward: [(0, '31.727')] [2023-03-11 12:24:44,555][04298] Updated weights for policy 0, policy_version 160640 (0.0005) [2023-03-11 12:24:47,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12356.3, 300 sec: 11843.7). Total num frames: 82284544. Throughput: 0: 12346.0. Samples: 82259868. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:24:47,812][04011] Avg episode reward: [(0, '32.546')] [2023-03-11 12:24:48,009][04298] Updated weights for policy 0, policy_version 160720 (0.0005) [2023-03-11 12:24:51,589][04298] Updated weights for policy 0, policy_version 160800 (0.0005) [2023-03-11 12:24:52,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12356.3, 300 sec: 11843.7). Total num frames: 82341888. Throughput: 0: 12116.3. Samples: 82329596. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:24:52,812][04011] Avg episode reward: [(0, '31.073')] [2023-03-11 12:24:52,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000160824_82341888.pth... [2023-03-11 12:24:52,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000160120_81981440.pth [2023-03-11 12:24:55,056][04298] Updated weights for policy 0, policy_version 160880 (0.0005) [2023-03-11 12:24:57,811][04011] Fps is (10 sec: 11468.8, 60 sec: 12219.7, 300 sec: 11829.8). Total num frames: 82399232. Throughput: 0: 11926.9. Samples: 82399432. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:24:57,811][04011] Avg episode reward: [(0, '32.135')] [2023-03-11 12:24:58,513][04298] Updated weights for policy 0, policy_version 160960 (0.0004) [2023-03-11 12:25:02,007][04298] Updated weights for policy 0, policy_version 161040 (0.0005) [2023-03-11 12:25:02,811][04011] Fps is (10 sec: 11878.5, 60 sec: 12151.5, 300 sec: 11829.8). Total num frames: 82460672. Throughput: 0: 11949.4. Samples: 82436096. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:25:02,811][04011] Avg episode reward: [(0, '31.545')] [2023-03-11 12:25:05,536][04298] Updated weights for policy 0, policy_version 161120 (0.0005) [2023-03-11 12:25:07,811][04011] Fps is (10 sec: 11878.3, 60 sec: 12014.9, 300 sec: 11829.8). Total num frames: 82518016. Throughput: 0: 11924.0. Samples: 82505740. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:25:07,812][04011] Avg episode reward: [(0, '26.806')] [2023-03-11 12:25:07,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000161168_82518016.pth... [2023-03-11 12:25:07,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000160480_82165760.pth [2023-03-11 12:25:09,077][04298] Updated weights for policy 0, policy_version 161200 (0.0005) [2023-03-11 12:25:12,499][04298] Updated weights for policy 0, policy_version 161280 (0.0004) [2023-03-11 12:25:12,811][04011] Fps is (10 sec: 11468.8, 60 sec: 11878.4, 300 sec: 11815.9). Total num frames: 82575360. Throughput: 0: 11866.5. Samples: 82575672. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:25:12,811][04011] Avg episode reward: [(0, '30.410')] [2023-03-11 12:25:16,053][04298] Updated weights for policy 0, policy_version 161360 (0.0005) [2023-03-11 12:25:17,811][04011] Fps is (10 sec: 11878.5, 60 sec: 11878.4, 300 sec: 11829.8). Total num frames: 82636800. Throughput: 0: 11821.9. Samples: 82610548. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:25:17,811][04011] Avg episode reward: [(0, '31.199')] [2023-03-11 12:25:19,528][04298] Updated weights for policy 0, policy_version 161440 (0.0005) [2023-03-11 12:25:22,811][04011] Fps is (10 sec: 11878.3, 60 sec: 11878.4, 300 sec: 11815.9). Total num frames: 82694144. Throughput: 0: 11776.5. Samples: 82681092. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:25:22,811][04011] Avg episode reward: [(0, '31.731')] [2023-03-11 12:25:22,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000161512_82694144.pth... [2023-03-11 12:25:22,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000160824_82341888.pth [2023-03-11 12:25:23,026][04298] Updated weights for policy 0, policy_version 161520 (0.0004) [2023-03-11 12:25:26,463][04298] Updated weights for policy 0, policy_version 161600 (0.0005) [2023-03-11 12:25:27,811][04011] Fps is (10 sec: 11468.8, 60 sec: 11810.1, 300 sec: 11815.9). Total num frames: 82751488. Throughput: 0: 11756.3. Samples: 82752208. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:25:27,811][04011] Avg episode reward: [(0, '29.650')] [2023-03-11 12:25:29,932][04298] Updated weights for policy 0, policy_version 161680 (0.0005) [2023-03-11 12:25:32,811][04011] Fps is (10 sec: 11878.5, 60 sec: 11810.1, 300 sec: 11829.8). Total num frames: 82812928. Throughput: 0: 11740.9. Samples: 82788208. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:25:32,811][04011] Avg episode reward: [(0, '30.492')] [2023-03-11 12:25:33,237][04298] Updated weights for policy 0, policy_version 161760 (0.0005) [2023-03-11 12:25:36,515][04298] Updated weights for policy 0, policy_version 161840 (0.0004) [2023-03-11 12:25:37,811][04011] Fps is (10 sec: 12697.5, 60 sec: 11878.4, 300 sec: 11857.6). Total num frames: 82878464. Throughput: 0: 11834.8. Samples: 82862164. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:25:37,811][04011] Avg episode reward: [(0, '30.927')] [2023-03-11 12:25:37,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000161872_82878464.pth... [2023-03-11 12:25:37,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000161168_82518016.pth [2023-03-11 12:25:39,623][04298] Updated weights for policy 0, policy_version 161920 (0.0004) [2023-03-11 12:25:42,770][04298] Updated weights for policy 0, policy_version 162000 (0.0004) [2023-03-11 12:25:42,811][04011] Fps is (10 sec: 13107.1, 60 sec: 12014.9, 300 sec: 11885.3). Total num frames: 82944000. Throughput: 0: 12029.8. Samples: 82940772. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:25:42,811][04011] Avg episode reward: [(0, '31.677')] [2023-03-11 12:25:45,941][04298] Updated weights for policy 0, policy_version 162080 (0.0004) [2023-03-11 12:25:47,811][04011] Fps is (10 sec: 13107.3, 60 sec: 12083.2, 300 sec: 11913.1). Total num frames: 83009536. Throughput: 0: 12087.0. Samples: 82980012. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:25:47,822][04011] Avg episode reward: [(0, '31.991')] [2023-03-11 12:25:49,104][04298] Updated weights for policy 0, policy_version 162160 (0.0004) [2023-03-11 12:25:52,320][04298] Updated weights for policy 0, policy_version 162240 (0.0004) [2023-03-11 12:25:52,811][04011] Fps is (10 sec: 12697.5, 60 sec: 12151.5, 300 sec: 11927.0). Total num frames: 83070976. Throughput: 0: 12281.0. Samples: 83058384. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:25:52,822][04011] Avg episode reward: [(0, '30.940')] [2023-03-11 12:25:52,825][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000162248_83070976.pth... [2023-03-11 12:25:52,828][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000161512_82694144.pth [2023-03-11 12:25:55,751][04298] Updated weights for policy 0, policy_version 162320 (0.0005) [2023-03-11 12:25:57,811][04011] Fps is (10 sec: 11878.5, 60 sec: 12151.5, 300 sec: 11927.0). Total num frames: 83128320. Throughput: 0: 12282.7. Samples: 83128392. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:25:57,811][04011] Avg episode reward: [(0, '31.627')] [2023-03-11 12:25:59,224][04298] Updated weights for policy 0, policy_version 162400 (0.0005) [2023-03-11 12:26:02,714][04298] Updated weights for policy 0, policy_version 162480 (0.0005) [2023-03-11 12:26:02,811][04011] Fps is (10 sec: 11878.5, 60 sec: 12151.5, 300 sec: 11913.1). Total num frames: 83189760. Throughput: 0: 12325.2. Samples: 83165184. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:26:02,811][04011] Avg episode reward: [(0, '31.279')] [2023-03-11 12:26:06,182][04298] Updated weights for policy 0, policy_version 162560 (0.0005) [2023-03-11 12:26:07,811][04011] Fps is (10 sec: 11878.2, 60 sec: 12151.5, 300 sec: 11913.1). Total num frames: 83247104. Throughput: 0: 12308.0. Samples: 83234952. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:26:07,812][04011] Avg episode reward: [(0, '33.861')] [2023-03-11 12:26:07,847][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000162600_83251200.pth... [2023-03-11 12:26:07,849][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000161872_82878464.pth [2023-03-11 12:26:07,849][04254] Saving new best policy, reward=33.861! [2023-03-11 12:26:09,567][04298] Updated weights for policy 0, policy_version 162640 (0.0004) [2023-03-11 12:26:12,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12219.7, 300 sec: 11927.0). Total num frames: 83308544. Throughput: 0: 12337.9. Samples: 83307412. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:26:12,811][04011] Avg episode reward: [(0, '32.339')] [2023-03-11 12:26:13,066][04298] Updated weights for policy 0, policy_version 162720 (0.0004) [2023-03-11 12:26:16,597][04298] Updated weights for policy 0, policy_version 162800 (0.0005) [2023-03-11 12:26:17,811][04011] Fps is (10 sec: 11878.5, 60 sec: 12151.5, 300 sec: 11927.0). Total num frames: 83365888. Throughput: 0: 12292.8. Samples: 83341384. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:26:17,811][04011] Avg episode reward: [(0, '31.522')] [2023-03-11 12:26:20,064][04298] Updated weights for policy 0, policy_version 162880 (0.0005) [2023-03-11 12:26:22,811][04011] Fps is (10 sec: 11468.7, 60 sec: 12151.5, 300 sec: 11913.1). Total num frames: 83423232. Throughput: 0: 12210.1. Samples: 83411620. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:26:22,812][04011] Avg episode reward: [(0, '30.626')] [2023-03-11 12:26:22,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000162936_83423232.pth... [2023-03-11 12:26:22,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000162248_83070976.pth [2023-03-11 12:26:23,589][04298] Updated weights for policy 0, policy_version 162960 (0.0005) [2023-03-11 12:26:26,948][04298] Updated weights for policy 0, policy_version 163040 (0.0004) [2023-03-11 12:26:27,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12219.7, 300 sec: 11913.1). Total num frames: 83484672. Throughput: 0: 12085.0. Samples: 83484596. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:26:27,812][04011] Avg episode reward: [(0, '32.419')] [2023-03-11 12:26:30,136][04298] Updated weights for policy 0, policy_version 163120 (0.0004) [2023-03-11 12:26:32,811][04011] Fps is (10 sec: 12288.1, 60 sec: 12219.7, 300 sec: 11913.1). Total num frames: 83546112. Throughput: 0: 12036.6. Samples: 83521660. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:26:32,812][04011] Avg episode reward: [(0, '31.607')] [2023-03-11 12:26:33,689][04298] Updated weights for policy 0, policy_version 163200 (0.0005) [2023-03-11 12:26:37,063][04298] Updated weights for policy 0, policy_version 163280 (0.0005) [2023-03-11 12:26:37,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12151.5, 300 sec: 11927.0). Total num frames: 83607552. Throughput: 0: 11889.2. Samples: 83593400. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:26:37,812][04011] Avg episode reward: [(0, '29.677')] [2023-03-11 12:26:37,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000163296_83607552.pth... [2023-03-11 12:26:37,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000162600_83251200.pth [2023-03-11 12:26:40,632][04298] Updated weights for policy 0, policy_version 163360 (0.0005) [2023-03-11 12:26:42,811][04011] Fps is (10 sec: 11878.5, 60 sec: 12014.9, 300 sec: 11940.9). Total num frames: 83664896. Throughput: 0: 11883.7. Samples: 83663160. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:26:42,811][04011] Avg episode reward: [(0, '32.094')] [2023-03-11 12:26:44,111][04298] Updated weights for policy 0, policy_version 163440 (0.0005) [2023-03-11 12:26:47,573][04298] Updated weights for policy 0, policy_version 163520 (0.0005) [2023-03-11 12:26:47,811][04011] Fps is (10 sec: 11468.8, 60 sec: 11878.4, 300 sec: 11940.9). Total num frames: 83722240. Throughput: 0: 11845.9. Samples: 83698248. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:26:47,811][04011] Avg episode reward: [(0, '30.800')] [2023-03-11 12:26:51,077][04298] Updated weights for policy 0, policy_version 163600 (0.0005) [2023-03-11 12:26:52,811][04011] Fps is (10 sec: 11468.7, 60 sec: 11810.1, 300 sec: 11940.9). Total num frames: 83779584. Throughput: 0: 11864.1. Samples: 83768836. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:26:52,812][04011] Avg episode reward: [(0, '31.111')] [2023-03-11 12:26:52,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000163640_83783680.pth... [2023-03-11 12:26:52,816][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000162936_83423232.pth [2023-03-11 12:26:54,521][04298] Updated weights for policy 0, policy_version 163680 (0.0005) [2023-03-11 12:26:57,811][04011] Fps is (10 sec: 11878.5, 60 sec: 11878.4, 300 sec: 11954.8). Total num frames: 83841024. Throughput: 0: 11836.4. Samples: 83840048. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:26:57,811][04011] Avg episode reward: [(0, '30.571')] [2023-03-11 12:26:58,008][04298] Updated weights for policy 0, policy_version 163760 (0.0005) [2023-03-11 12:27:01,491][04298] Updated weights for policy 0, policy_version 163840 (0.0005) [2023-03-11 12:27:02,811][04011] Fps is (10 sec: 11878.4, 60 sec: 11810.1, 300 sec: 11954.8). Total num frames: 83898368. Throughput: 0: 11845.4. Samples: 83874428. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:27:02,812][04011] Avg episode reward: [(0, '32.528')] [2023-03-11 12:27:04,828][04298] Updated weights for policy 0, policy_version 163920 (0.0005) [2023-03-11 12:27:07,811][04011] Fps is (10 sec: 11878.3, 60 sec: 11878.4, 300 sec: 11968.6). Total num frames: 83959808. Throughput: 0: 11919.2. Samples: 83947984. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:27:07,812][04011] Avg episode reward: [(0, '32.253')] [2023-03-11 12:27:07,832][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000163992_83963904.pth... [2023-03-11 12:27:07,834][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000163296_83607552.pth [2023-03-11 12:27:08,165][04298] Updated weights for policy 0, policy_version 164000 (0.0005) [2023-03-11 12:27:11,656][04298] Updated weights for policy 0, policy_version 164080 (0.0005) [2023-03-11 12:27:12,811][04011] Fps is (10 sec: 12288.0, 60 sec: 11878.4, 300 sec: 11982.5). Total num frames: 84021248. Throughput: 0: 11904.2. Samples: 84020284. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:27:12,811][04011] Avg episode reward: [(0, '31.637')] [2023-03-11 12:27:14,869][04298] Updated weights for policy 0, policy_version 164160 (0.0004) [2023-03-11 12:27:17,811][04011] Fps is (10 sec: 12697.6, 60 sec: 12014.9, 300 sec: 12010.3). Total num frames: 84086784. Throughput: 0: 11933.1. Samples: 84058648. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:27:17,812][04011] Avg episode reward: [(0, '30.744')] [2023-03-11 12:27:17,973][04298] Updated weights for policy 0, policy_version 164240 (0.0004) [2023-03-11 12:27:21,380][04298] Updated weights for policy 0, policy_version 164320 (0.0005) [2023-03-11 12:27:22,811][04011] Fps is (10 sec: 12697.6, 60 sec: 12083.2, 300 sec: 12024.2). Total num frames: 84148224. Throughput: 0: 12017.9. Samples: 84134204. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-11 12:27:22,811][04011] Avg episode reward: [(0, '30.972')] [2023-03-11 12:27:22,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000164352_84148224.pth... [2023-03-11 12:27:22,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000163640_83783680.pth [2023-03-11 12:27:24,578][04298] Updated weights for policy 0, policy_version 164400 (0.0004) [2023-03-11 12:27:27,654][04298] Updated weights for policy 0, policy_version 164480 (0.0004) [2023-03-11 12:27:27,811][04011] Fps is (10 sec: 12697.6, 60 sec: 12151.5, 300 sec: 12038.1). Total num frames: 84213760. Throughput: 0: 12200.5. Samples: 84212184. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-11 12:27:27,812][04011] Avg episode reward: [(0, '33.590')] [2023-03-11 12:27:30,755][04298] Updated weights for policy 0, policy_version 164560 (0.0004) [2023-03-11 12:27:32,811][04011] Fps is (10 sec: 13107.2, 60 sec: 12219.7, 300 sec: 12065.8). Total num frames: 84279296. Throughput: 0: 12303.9. Samples: 84251924. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-11 12:27:32,811][04011] Avg episode reward: [(0, '33.181')] [2023-03-11 12:27:33,854][04298] Updated weights for policy 0, policy_version 164640 (0.0004) [2023-03-11 12:27:36,953][04298] Updated weights for policy 0, policy_version 164720 (0.0005) [2023-03-11 12:27:37,811][04011] Fps is (10 sec: 13107.2, 60 sec: 12288.0, 300 sec: 12093.6). Total num frames: 84344832. Throughput: 0: 12505.4. Samples: 84331580. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-11 12:27:37,812][04011] Avg episode reward: [(0, '33.661')] [2023-03-11 12:27:37,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000164736_84344832.pth... [2023-03-11 12:27:37,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000163992_83963904.pth [2023-03-11 12:27:40,076][04298] Updated weights for policy 0, policy_version 164800 (0.0004) [2023-03-11 12:27:42,811][04011] Fps is (10 sec: 13107.2, 60 sec: 12424.5, 300 sec: 12135.3). Total num frames: 84410368. Throughput: 0: 12656.4. Samples: 84409588. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-11 12:27:42,811][04011] Avg episode reward: [(0, '32.306')] [2023-03-11 12:27:43,268][04298] Updated weights for policy 0, policy_version 164880 (0.0005) [2023-03-11 12:27:46,478][04298] Updated weights for policy 0, policy_version 164960 (0.0005) [2023-03-11 12:27:47,811][04011] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12163.0). Total num frames: 84475904. Throughput: 0: 12730.8. Samples: 84447312. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-11 12:27:47,811][04011] Avg episode reward: [(0, '31.510')] [2023-03-11 12:27:49,614][04298] Updated weights for policy 0, policy_version 165040 (0.0005) [2023-03-11 12:27:52,658][04298] Updated weights for policy 0, policy_version 165120 (0.0004) [2023-03-11 12:27:52,811][04011] Fps is (10 sec: 13107.2, 60 sec: 12697.6, 300 sec: 12190.8). Total num frames: 84541440. Throughput: 0: 12853.4. Samples: 84526388. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-11 12:27:52,811][04011] Avg episode reward: [(0, '30.694')] [2023-03-11 12:27:52,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000165120_84541440.pth... [2023-03-11 12:27:52,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000164352_84148224.pth [2023-03-11 12:27:55,841][04298] Updated weights for policy 0, policy_version 165200 (0.0005) [2023-03-11 12:27:57,811][04011] Fps is (10 sec: 12697.6, 60 sec: 12697.6, 300 sec: 12204.7). Total num frames: 84602880. Throughput: 0: 12946.8. Samples: 84602888. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-11 12:27:57,811][04011] Avg episode reward: [(0, '32.812')] [2023-03-11 12:27:59,256][04298] Updated weights for policy 0, policy_version 165280 (0.0005) [2023-03-11 12:28:02,459][04298] Updated weights for policy 0, policy_version 165360 (0.0004) [2023-03-11 12:28:02,811][04011] Fps is (10 sec: 12697.7, 60 sec: 12834.1, 300 sec: 12218.6). Total num frames: 84668416. Throughput: 0: 12914.7. Samples: 84639808. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-11 12:28:02,811][04011] Avg episode reward: [(0, '30.938')] [2023-03-11 12:28:05,559][04298] Updated weights for policy 0, policy_version 165440 (0.0004) [2023-03-11 12:28:07,811][04011] Fps is (10 sec: 13107.2, 60 sec: 12902.4, 300 sec: 12246.3). Total num frames: 84733952. Throughput: 0: 12965.2. Samples: 84717640. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-11 12:28:07,811][04011] Avg episode reward: [(0, '32.724')] [2023-03-11 12:28:07,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000165496_84733952.pth... [2023-03-11 12:28:07,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000164736_84344832.pth [2023-03-11 12:28:08,711][04298] Updated weights for policy 0, policy_version 165520 (0.0005) [2023-03-11 12:28:11,904][04298] Updated weights for policy 0, policy_version 165600 (0.0004) [2023-03-11 12:28:12,811][04011] Fps is (10 sec: 12697.6, 60 sec: 12902.4, 300 sec: 12260.2). Total num frames: 84795392. Throughput: 0: 12961.6. Samples: 84795456. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-11 12:28:12,811][04011] Avg episode reward: [(0, '31.843')] [2023-03-11 12:28:15,150][04298] Updated weights for policy 0, policy_version 165680 (0.0005) [2023-03-11 12:28:17,811][04011] Fps is (10 sec: 12697.6, 60 sec: 12902.4, 300 sec: 12301.9). Total num frames: 84860928. Throughput: 0: 12909.1. Samples: 84832832. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-11 12:28:17,811][04011] Avg episode reward: [(0, '31.827')] [2023-03-11 12:28:18,315][04298] Updated weights for policy 0, policy_version 165760 (0.0004) [2023-03-11 12:28:21,469][04298] Updated weights for policy 0, policy_version 165840 (0.0004) [2023-03-11 12:28:22,811][04011] Fps is (10 sec: 13107.1, 60 sec: 12970.7, 300 sec: 12329.7). Total num frames: 84926464. Throughput: 0: 12874.6. Samples: 84910936. Policy #0 lag: (min: 6.0, avg: 6.0, max: 6.0) [2023-03-11 12:28:22,812][04011] Avg episode reward: [(0, '32.894')] [2023-03-11 12:28:22,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000165872_84926464.pth... [2023-03-11 12:28:22,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000165120_84541440.pth [2023-03-11 12:28:24,600][04298] Updated weights for policy 0, policy_version 165920 (0.0004) [2023-03-11 12:28:27,737][04298] Updated weights for policy 0, policy_version 166000 (0.0005) [2023-03-11 12:28:27,811][04011] Fps is (10 sec: 13107.2, 60 sec: 12970.7, 300 sec: 12329.7). Total num frames: 84992000. Throughput: 0: 12883.1. Samples: 84989328. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:28:27,811][04011] Avg episode reward: [(0, '32.234')] [2023-03-11 12:28:30,952][04298] Updated weights for policy 0, policy_version 166080 (0.0005) [2023-03-11 12:28:32,811][04011] Fps is (10 sec: 13107.3, 60 sec: 12970.7, 300 sec: 12343.5). Total num frames: 85057536. Throughput: 0: 12897.1. Samples: 85027680. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:28:32,811][04011] Avg episode reward: [(0, '31.263')] [2023-03-11 12:28:34,033][04298] Updated weights for policy 0, policy_version 166160 (0.0004) [2023-03-11 12:28:37,135][04298] Updated weights for policy 0, policy_version 166240 (0.0004) [2023-03-11 12:28:37,811][04011] Fps is (10 sec: 13107.2, 60 sec: 12970.7, 300 sec: 12357.4). Total num frames: 85123072. Throughput: 0: 12897.0. Samples: 85106752. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:28:37,811][04011] Avg episode reward: [(0, '31.976')] [2023-03-11 12:28:37,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000166256_85123072.pth... [2023-03-11 12:28:37,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000165496_84733952.pth [2023-03-11 12:28:40,224][04298] Updated weights for policy 0, policy_version 166320 (0.0004) [2023-03-11 12:28:42,811][04011] Fps is (10 sec: 12697.5, 60 sec: 12902.4, 300 sec: 12343.5). Total num frames: 85184512. Throughput: 0: 12926.4. Samples: 85184576. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:28:42,811][04011] Avg episode reward: [(0, '32.330')] [2023-03-11 12:28:43,534][04298] Updated weights for policy 0, policy_version 166400 (0.0005) [2023-03-11 12:28:46,677][04298] Updated weights for policy 0, policy_version 166480 (0.0004) [2023-03-11 12:28:47,811][04011] Fps is (10 sec: 12697.6, 60 sec: 12902.4, 300 sec: 12371.3). Total num frames: 85250048. Throughput: 0: 12953.2. Samples: 85222700. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:28:47,811][04011] Avg episode reward: [(0, '30.926')] [2023-03-11 12:28:49,803][04298] Updated weights for policy 0, policy_version 166560 (0.0004) [2023-03-11 12:28:52,811][04011] Fps is (10 sec: 13107.1, 60 sec: 12902.4, 300 sec: 12371.3). Total num frames: 85315584. Throughput: 0: 12983.7. Samples: 85301908. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:28:52,812][04011] Avg episode reward: [(0, '31.662')] [2023-03-11 12:28:52,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000166632_85315584.pth... [2023-03-11 12:28:52,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000165872_84926464.pth [2023-03-11 12:28:52,966][04298] Updated weights for policy 0, policy_version 166640 (0.0004) [2023-03-11 12:28:56,157][04298] Updated weights for policy 0, policy_version 166720 (0.0005) [2023-03-11 12:28:57,811][04011] Fps is (10 sec: 13107.1, 60 sec: 12970.7, 300 sec: 12371.3). Total num frames: 85381120. Throughput: 0: 12958.3. Samples: 85378580. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:28:57,811][04011] Avg episode reward: [(0, '30.849')] [2023-03-11 12:28:59,298][04298] Updated weights for policy 0, policy_version 166800 (0.0005) [2023-03-11 12:29:02,336][04298] Updated weights for policy 0, policy_version 166880 (0.0004) [2023-03-11 12:29:02,811][04011] Fps is (10 sec: 13107.3, 60 sec: 12970.7, 300 sec: 12371.3). Total num frames: 85446656. Throughput: 0: 13005.1. Samples: 85418060. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:29:02,811][04011] Avg episode reward: [(0, '32.224')] [2023-03-11 12:29:05,470][04298] Updated weights for policy 0, policy_version 166960 (0.0004) [2023-03-11 12:29:07,811][04011] Fps is (10 sec: 13107.2, 60 sec: 12970.7, 300 sec: 12371.3). Total num frames: 85512192. Throughput: 0: 13043.8. Samples: 85497908. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:29:07,811][04011] Avg episode reward: [(0, '29.712')] [2023-03-11 12:29:07,814][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000167016_85512192.pth... [2023-03-11 12:29:07,816][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000166256_85123072.pth [2023-03-11 12:29:08,623][04298] Updated weights for policy 0, policy_version 167040 (0.0005) [2023-03-11 12:29:11,805][04298] Updated weights for policy 0, policy_version 167120 (0.0004) [2023-03-11 12:29:12,811][04011] Fps is (10 sec: 13107.2, 60 sec: 13038.9, 300 sec: 12385.2). Total num frames: 85577728. Throughput: 0: 13001.6. Samples: 85574400. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:29:12,811][04011] Avg episode reward: [(0, '29.527')] [2023-03-11 12:29:14,931][04298] Updated weights for policy 0, policy_version 167200 (0.0004) [2023-03-11 12:29:17,811][04011] Fps is (10 sec: 12697.7, 60 sec: 12970.7, 300 sec: 12399.1). Total num frames: 85639168. Throughput: 0: 13039.6. Samples: 85614460. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:29:17,811][04011] Avg episode reward: [(0, '31.202')] [2023-03-11 12:29:18,162][04298] Updated weights for policy 0, policy_version 167280 (0.0005) [2023-03-11 12:29:21,262][04298] Updated weights for policy 0, policy_version 167360 (0.0004) [2023-03-11 12:29:22,811][04011] Fps is (10 sec: 12697.5, 60 sec: 12970.7, 300 sec: 12413.0). Total num frames: 85704704. Throughput: 0: 13014.7. Samples: 85692416. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:29:22,812][04011] Avg episode reward: [(0, '31.999')] [2023-03-11 12:29:22,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000167392_85704704.pth... [2023-03-11 12:29:22,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000166632_85315584.pth [2023-03-11 12:29:24,431][04298] Updated weights for policy 0, policy_version 167440 (0.0004) [2023-03-11 12:29:27,609][04298] Updated weights for policy 0, policy_version 167520 (0.0005) [2023-03-11 12:29:27,811][04011] Fps is (10 sec: 13107.1, 60 sec: 12970.7, 300 sec: 12426.8). Total num frames: 85770240. Throughput: 0: 13005.6. Samples: 85769828. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:29:27,812][04011] Avg episode reward: [(0, '29.985')] [2023-03-11 12:29:30,679][04298] Updated weights for policy 0, policy_version 167600 (0.0004) [2023-03-11 12:29:32,811][04011] Fps is (10 sec: 13107.2, 60 sec: 12970.7, 300 sec: 12440.7). Total num frames: 85835776. Throughput: 0: 13042.6. Samples: 85809616. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:29:32,811][04011] Avg episode reward: [(0, '31.440')] [2023-03-11 12:29:33,953][04298] Updated weights for policy 0, policy_version 167680 (0.0005) [2023-03-11 12:29:37,031][04298] Updated weights for policy 0, policy_version 167760 (0.0004) [2023-03-11 12:29:37,811][04011] Fps is (10 sec: 13107.1, 60 sec: 12970.7, 300 sec: 12468.5). Total num frames: 85901312. Throughput: 0: 12995.6. Samples: 85886712. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:29:37,812][04011] Avg episode reward: [(0, '31.882')] [2023-03-11 12:29:37,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000167776_85901312.pth... [2023-03-11 12:29:37,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000167016_85512192.pth [2023-03-11 12:29:40,218][04298] Updated weights for policy 0, policy_version 167840 (0.0004) [2023-03-11 12:29:42,811][04011] Fps is (10 sec: 13107.3, 60 sec: 13038.9, 300 sec: 12482.4). Total num frames: 85966848. Throughput: 0: 13022.5. Samples: 85964592. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:29:42,811][04011] Avg episode reward: [(0, '32.233')] [2023-03-11 12:29:43,310][04298] Updated weights for policy 0, policy_version 167920 (0.0004) [2023-03-11 12:29:46,353][04298] Updated weights for policy 0, policy_version 168000 (0.0004) [2023-03-11 12:29:47,811][04011] Fps is (10 sec: 13107.3, 60 sec: 13038.9, 300 sec: 12510.2). Total num frames: 86032384. Throughput: 0: 13043.8. Samples: 86005032. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:29:47,811][04011] Avg episode reward: [(0, '33.067')] [2023-03-11 12:29:49,472][04298] Updated weights for policy 0, policy_version 168080 (0.0004) [2023-03-11 12:29:52,589][04298] Updated weights for policy 0, policy_version 168160 (0.0004) [2023-03-11 12:29:52,811][04011] Fps is (10 sec: 13107.1, 60 sec: 13038.9, 300 sec: 12537.9). Total num frames: 86097920. Throughput: 0: 13036.7. Samples: 86084560. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:29:52,811][04011] Avg episode reward: [(0, '31.720')] [2023-03-11 12:29:52,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000168160_86097920.pth... [2023-03-11 12:29:52,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000167392_85704704.pth [2023-03-11 12:29:56,015][04298] Updated weights for policy 0, policy_version 168240 (0.0005) [2023-03-11 12:29:57,811][04011] Fps is (10 sec: 12697.6, 60 sec: 12970.7, 300 sec: 12537.9). Total num frames: 86159360. Throughput: 0: 12944.9. Samples: 86156920. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:29:57,811][04011] Avg episode reward: [(0, '30.941')] [2023-03-11 12:29:59,520][04298] Updated weights for policy 0, policy_version 168320 (0.0005) [2023-03-11 12:30:02,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12834.1, 300 sec: 12537.9). Total num frames: 86216704. Throughput: 0: 12838.5. Samples: 86192192. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:30:02,811][04011] Avg episode reward: [(0, '32.355')] [2023-03-11 12:30:02,998][04298] Updated weights for policy 0, policy_version 168400 (0.0005) [2023-03-11 12:30:06,248][04298] Updated weights for policy 0, policy_version 168480 (0.0004) [2023-03-11 12:30:07,811][04011] Fps is (10 sec: 12287.9, 60 sec: 12834.1, 300 sec: 12565.7). Total num frames: 86282240. Throughput: 0: 12744.5. Samples: 86265920. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:30:07,812][04011] Avg episode reward: [(0, '31.933')] [2023-03-11 12:30:07,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000168520_86282240.pth... [2023-03-11 12:30:07,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000167776_85901312.pth [2023-03-11 12:30:09,378][04298] Updated weights for policy 0, policy_version 168560 (0.0004) [2023-03-11 12:30:12,573][04298] Updated weights for policy 0, policy_version 168640 (0.0005) [2023-03-11 12:30:12,811][04011] Fps is (10 sec: 12697.6, 60 sec: 12765.9, 300 sec: 12565.7). Total num frames: 86343680. Throughput: 0: 12748.3. Samples: 86343500. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:30:12,811][04011] Avg episode reward: [(0, '30.938')] [2023-03-11 12:30:15,779][04298] Updated weights for policy 0, policy_version 168720 (0.0005) [2023-03-11 12:30:17,811][04011] Fps is (10 sec: 12697.7, 60 sec: 12834.1, 300 sec: 12593.5). Total num frames: 86409216. Throughput: 0: 12716.1. Samples: 86381840. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:30:17,811][04011] Avg episode reward: [(0, '29.754')] [2023-03-11 12:30:18,917][04298] Updated weights for policy 0, policy_version 168800 (0.0005) [2023-03-11 12:30:22,058][04298] Updated weights for policy 0, policy_version 168880 (0.0004) [2023-03-11 12:30:22,811][04011] Fps is (10 sec: 13107.2, 60 sec: 12834.1, 300 sec: 12621.2). Total num frames: 86474752. Throughput: 0: 12738.2. Samples: 86459928. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:30:22,811][04011] Avg episode reward: [(0, '32.268')] [2023-03-11 12:30:22,814][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000168896_86474752.pth... [2023-03-11 12:30:22,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000168160_86097920.pth [2023-03-11 12:30:25,291][04298] Updated weights for policy 0, policy_version 168960 (0.0005) [2023-03-11 12:30:27,811][04011] Fps is (10 sec: 12697.5, 60 sec: 12765.9, 300 sec: 12621.2). Total num frames: 86536192. Throughput: 0: 12703.6. Samples: 86536256. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:30:27,811][04011] Avg episode reward: [(0, '32.011')] [2023-03-11 12:30:28,490][04298] Updated weights for policy 0, policy_version 169040 (0.0005) [2023-03-11 12:30:31,694][04298] Updated weights for policy 0, policy_version 169120 (0.0005) [2023-03-11 12:30:32,811][04011] Fps is (10 sec: 12697.6, 60 sec: 12765.9, 300 sec: 12621.2). Total num frames: 86601728. Throughput: 0: 12668.3. Samples: 86575104. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:30:32,811][04011] Avg episode reward: [(0, '30.758')] [2023-03-11 12:30:34,811][04298] Updated weights for policy 0, policy_version 169200 (0.0004) [2023-03-11 12:30:37,811][04011] Fps is (10 sec: 13107.1, 60 sec: 12765.9, 300 sec: 12621.2). Total num frames: 86667264. Throughput: 0: 12608.2. Samples: 86651928. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-11 12:30:37,812][04011] Avg episode reward: [(0, '31.753')] [2023-03-11 12:30:37,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000169272_86667264.pth... [2023-03-11 12:30:37,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000168520_86282240.pth [2023-03-11 12:30:37,980][04298] Updated weights for policy 0, policy_version 169280 (0.0005) [2023-03-11 12:30:41,138][04298] Updated weights for policy 0, policy_version 169360 (0.0005) [2023-03-11 12:30:42,811][04011] Fps is (10 sec: 12697.6, 60 sec: 12697.6, 300 sec: 12607.3). Total num frames: 86728704. Throughput: 0: 12715.5. Samples: 86729120. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-11 12:30:42,811][04011] Avg episode reward: [(0, '32.612')] [2023-03-11 12:30:44,532][04298] Updated weights for policy 0, policy_version 169440 (0.0005) [2023-03-11 12:30:47,811][04011] Fps is (10 sec: 12288.1, 60 sec: 12629.3, 300 sec: 12607.4). Total num frames: 86790144. Throughput: 0: 12742.0. Samples: 86765580. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-11 12:30:47,822][04011] Avg episode reward: [(0, '33.331')] [2023-03-11 12:30:47,885][04298] Updated weights for policy 0, policy_version 169520 (0.0005) [2023-03-11 12:30:51,296][04298] Updated weights for policy 0, policy_version 169600 (0.0005) [2023-03-11 12:30:52,811][04011] Fps is (10 sec: 12287.9, 60 sec: 12561.1, 300 sec: 12621.2). Total num frames: 86851584. Throughput: 0: 12729.9. Samples: 86838768. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-11 12:30:52,812][04011] Avg episode reward: [(0, '32.078')] [2023-03-11 12:30:52,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000169632_86851584.pth... [2023-03-11 12:30:52,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000168896_86474752.pth [2023-03-11 12:30:54,557][04298] Updated weights for policy 0, policy_version 169680 (0.0004) [2023-03-11 12:30:57,708][04298] Updated weights for policy 0, policy_version 169760 (0.0003) [2023-03-11 12:30:57,811][04011] Fps is (10 sec: 12697.6, 60 sec: 12629.3, 300 sec: 12635.1). Total num frames: 86917120. Throughput: 0: 12708.5. Samples: 86915384. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-11 12:30:57,811][04011] Avg episode reward: [(0, '33.310')] [2023-03-11 12:31:00,927][04298] Updated weights for policy 0, policy_version 169840 (0.0004) [2023-03-11 12:31:02,811][04011] Fps is (10 sec: 13107.3, 60 sec: 12765.9, 300 sec: 12662.9). Total num frames: 86982656. Throughput: 0: 12714.3. Samples: 86953984. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-11 12:31:02,811][04011] Avg episode reward: [(0, '32.461')] [2023-03-11 12:31:04,034][04298] Updated weights for policy 0, policy_version 169920 (0.0004) [2023-03-11 12:31:07,065][04298] Updated weights for policy 0, policy_version 170000 (0.0004) [2023-03-11 12:31:07,811][04011] Fps is (10 sec: 13107.2, 60 sec: 12765.9, 300 sec: 12676.8). Total num frames: 87048192. Throughput: 0: 12734.2. Samples: 87032968. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-11 12:31:07,811][04011] Avg episode reward: [(0, '31.187')] [2023-03-11 12:31:07,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000170016_87048192.pth... [2023-03-11 12:31:07,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000169272_86667264.pth [2023-03-11 12:31:10,169][04298] Updated weights for policy 0, policy_version 170080 (0.0004) [2023-03-11 12:31:12,811][04011] Fps is (10 sec: 13107.2, 60 sec: 12834.1, 300 sec: 12704.5). Total num frames: 87113728. Throughput: 0: 12817.2. Samples: 87113028. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-11 12:31:12,812][04011] Avg episode reward: [(0, '31.690')] [2023-03-11 12:31:13,218][04298] Updated weights for policy 0, policy_version 170160 (0.0004) [2023-03-11 12:31:16,260][04298] Updated weights for policy 0, policy_version 170240 (0.0004) [2023-03-11 12:31:17,811][04011] Fps is (10 sec: 13516.8, 60 sec: 12902.4, 300 sec: 12746.2). Total num frames: 87183360. Throughput: 0: 12841.2. Samples: 87152956. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-11 12:31:17,811][04011] Avg episode reward: [(0, '32.095')] [2023-03-11 12:31:19,364][04298] Updated weights for policy 0, policy_version 170320 (0.0004) [2023-03-11 12:31:22,590][04298] Updated weights for policy 0, policy_version 170400 (0.0005) [2023-03-11 12:31:22,811][04011] Fps is (10 sec: 13107.2, 60 sec: 12834.1, 300 sec: 12746.2). Total num frames: 87244800. Throughput: 0: 12897.8. Samples: 87232328. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-11 12:31:22,811][04011] Avg episode reward: [(0, '31.794')] [2023-03-11 12:31:22,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000170400_87244800.pth... [2023-03-11 12:31:22,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000169632_86851584.pth [2023-03-11 12:31:25,780][04298] Updated weights for policy 0, policy_version 170480 (0.0005) [2023-03-11 12:31:27,811][04011] Fps is (10 sec: 12697.6, 60 sec: 12902.4, 300 sec: 12760.1). Total num frames: 87310336. Throughput: 0: 12887.7. Samples: 87309068. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-11 12:31:27,811][04011] Avg episode reward: [(0, '31.075')] [2023-03-11 12:31:28,932][04298] Updated weights for policy 0, policy_version 170560 (0.0004) [2023-03-11 12:31:32,180][04298] Updated weights for policy 0, policy_version 170640 (0.0003) [2023-03-11 12:31:32,811][04011] Fps is (10 sec: 13107.2, 60 sec: 12902.4, 300 sec: 12774.0). Total num frames: 87375872. Throughput: 0: 12926.3. Samples: 87347264. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-11 12:31:32,822][04011] Avg episode reward: [(0, '29.158')] [2023-03-11 12:31:35,401][04298] Updated weights for policy 0, policy_version 170720 (0.0004) [2023-03-11 12:31:37,811][04011] Fps is (10 sec: 12697.5, 60 sec: 12834.1, 300 sec: 12787.8). Total num frames: 87437312. Throughput: 0: 12984.4. Samples: 87423064. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-11 12:31:37,822][04011] Avg episode reward: [(0, '30.327')] [2023-03-11 12:31:37,825][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000170776_87437312.pth... [2023-03-11 12:31:37,828][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000170016_87048192.pth [2023-03-11 12:31:38,690][04298] Updated weights for policy 0, policy_version 170800 (0.0004) [2023-03-11 12:31:41,777][04298] Updated weights for policy 0, policy_version 170880 (0.0004) [2023-03-11 12:31:42,811][04011] Fps is (10 sec: 12697.6, 60 sec: 12902.4, 300 sec: 12815.6). Total num frames: 87502848. Throughput: 0: 13008.6. Samples: 87500772. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-11 12:31:42,822][04011] Avg episode reward: [(0, '29.593')] [2023-03-11 12:31:44,956][04298] Updated weights for policy 0, policy_version 170960 (0.0005) [2023-03-11 12:31:47,811][04011] Fps is (10 sec: 12697.7, 60 sec: 12902.4, 300 sec: 12829.5). Total num frames: 87564288. Throughput: 0: 13016.4. Samples: 87539720. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-11 12:31:47,811][04011] Avg episode reward: [(0, '30.184')] [2023-03-11 12:31:48,130][04298] Updated weights for policy 0, policy_version 171040 (0.0005) [2023-03-11 12:31:51,332][04298] Updated weights for policy 0, policy_version 171120 (0.0005) [2023-03-11 12:31:52,811][04011] Fps is (10 sec: 12697.5, 60 sec: 12970.7, 300 sec: 12843.4). Total num frames: 87629824. Throughput: 0: 12963.9. Samples: 87616344. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-11 12:31:52,812][04011] Avg episode reward: [(0, '30.368')] [2023-03-11 12:31:52,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000171152_87629824.pth... [2023-03-11 12:31:52,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000170400_87244800.pth [2023-03-11 12:31:54,471][04298] Updated weights for policy 0, policy_version 171200 (0.0004) [2023-03-11 12:31:57,675][04298] Updated weights for policy 0, policy_version 171280 (0.0005) [2023-03-11 12:31:57,811][04011] Fps is (10 sec: 13107.1, 60 sec: 12970.7, 300 sec: 12871.2). Total num frames: 87695360. Throughput: 0: 12899.5. Samples: 87693508. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-11 12:31:57,812][04011] Avg episode reward: [(0, '30.545')] [2023-03-11 12:32:00,970][04298] Updated weights for policy 0, policy_version 171360 (0.0005) [2023-03-11 12:32:02,811][04011] Fps is (10 sec: 12697.7, 60 sec: 12902.4, 300 sec: 12871.2). Total num frames: 87756800. Throughput: 0: 12864.8. Samples: 87731872. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-11 12:32:02,811][04011] Avg episode reward: [(0, '28.477')] [2023-03-11 12:32:04,197][04298] Updated weights for policy 0, policy_version 171440 (0.0005) [2023-03-11 12:32:07,361][04298] Updated weights for policy 0, policy_version 171520 (0.0005) [2023-03-11 12:32:07,811][04011] Fps is (10 sec: 12697.6, 60 sec: 12902.4, 300 sec: 12885.0). Total num frames: 87822336. Throughput: 0: 12795.8. Samples: 87808140. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-11 12:32:07,811][04011] Avg episode reward: [(0, '31.804')] [2023-03-11 12:32:07,814][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000171528_87822336.pth... [2023-03-11 12:32:07,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000170776_87437312.pth [2023-03-11 12:32:10,543][04298] Updated weights for policy 0, policy_version 171600 (0.0005) [2023-03-11 12:32:12,811][04011] Fps is (10 sec: 13107.1, 60 sec: 12902.4, 300 sec: 12885.0). Total num frames: 87887872. Throughput: 0: 12794.3. Samples: 87884812. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-11 12:32:12,812][04011] Avg episode reward: [(0, '31.438')] [2023-03-11 12:32:13,715][04298] Updated weights for policy 0, policy_version 171680 (0.0005) [2023-03-11 12:32:16,881][04298] Updated weights for policy 0, policy_version 171760 (0.0004) [2023-03-11 12:32:17,811][04011] Fps is (10 sec: 12697.6, 60 sec: 12765.9, 300 sec: 12885.0). Total num frames: 87949312. Throughput: 0: 12812.4. Samples: 87923824. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-11 12:32:17,811][04011] Avg episode reward: [(0, '30.281')] [2023-03-11 12:32:19,961][04298] Updated weights for policy 0, policy_version 171840 (0.0004) [2023-03-11 12:32:22,811][04011] Fps is (10 sec: 12697.7, 60 sec: 12834.1, 300 sec: 12885.0). Total num frames: 88014848. Throughput: 0: 12879.1. Samples: 88002624. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-11 12:32:22,811][04011] Avg episode reward: [(0, '30.941')] [2023-03-11 12:32:22,814][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000171904_88014848.pth... [2023-03-11 12:32:22,815][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000171152_87629824.pth [2023-03-11 12:32:23,196][04298] Updated weights for policy 0, policy_version 171920 (0.0005) [2023-03-11 12:32:26,332][04298] Updated weights for policy 0, policy_version 172000 (0.0005) [2023-03-11 12:32:27,811][04011] Fps is (10 sec: 13107.3, 60 sec: 12834.1, 300 sec: 12885.0). Total num frames: 88080384. Throughput: 0: 12877.1. Samples: 88080240. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-11 12:32:27,811][04011] Avg episode reward: [(0, '31.895')] [2023-03-11 12:32:29,450][04298] Updated weights for policy 0, policy_version 172080 (0.0005) [2023-03-11 12:32:32,645][04298] Updated weights for policy 0, policy_version 172160 (0.0005) [2023-03-11 12:32:32,811][04011] Fps is (10 sec: 13107.2, 60 sec: 12834.1, 300 sec: 12885.0). Total num frames: 88145920. Throughput: 0: 12864.4. Samples: 88118620. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-11 12:32:32,811][04011] Avg episode reward: [(0, '30.114')] [2023-03-11 12:32:35,776][04298] Updated weights for policy 0, policy_version 172240 (0.0004) [2023-03-11 12:32:37,811][04011] Fps is (10 sec: 13107.1, 60 sec: 12902.4, 300 sec: 12885.0). Total num frames: 88211456. Throughput: 0: 12893.1. Samples: 88196532. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-11 12:32:37,812][04011] Avg episode reward: [(0, '31.744')] [2023-03-11 12:32:37,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000172288_88211456.pth... [2023-03-11 12:32:37,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000171528_87822336.pth [2023-03-11 12:32:38,942][04298] Updated weights for policy 0, policy_version 172320 (0.0004) [2023-03-11 12:32:42,088][04298] Updated weights for policy 0, policy_version 172400 (0.0005) [2023-03-11 12:32:42,811][04011] Fps is (10 sec: 13107.2, 60 sec: 12902.4, 300 sec: 12885.0). Total num frames: 88276992. Throughput: 0: 12915.5. Samples: 88274704. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-11 12:32:42,811][04011] Avg episode reward: [(0, '32.380')] [2023-03-11 12:32:45,266][04298] Updated weights for policy 0, policy_version 172480 (0.0005) [2023-03-11 12:32:47,811][04011] Fps is (10 sec: 13107.2, 60 sec: 12970.7, 300 sec: 12885.0). Total num frames: 88342528. Throughput: 0: 12932.1. Samples: 88313816. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-11 12:32:47,812][04011] Avg episode reward: [(0, '30.677')] [2023-03-11 12:32:48,329][04298] Updated weights for policy 0, policy_version 172560 (0.0004) [2023-03-11 12:32:51,508][04298] Updated weights for policy 0, policy_version 172640 (0.0004) [2023-03-11 12:32:52,811][04011] Fps is (10 sec: 13107.2, 60 sec: 12970.7, 300 sec: 12898.9). Total num frames: 88408064. Throughput: 0: 12971.9. Samples: 88391876. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-11 12:32:52,812][04011] Avg episode reward: [(0, '30.174')] [2023-03-11 12:32:52,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000172672_88408064.pth... [2023-03-11 12:32:52,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000171904_88014848.pth [2023-03-11 12:32:54,648][04298] Updated weights for policy 0, policy_version 172720 (0.0005) [2023-03-11 12:32:57,756][04298] Updated weights for policy 0, policy_version 172800 (0.0004) [2023-03-11 12:32:57,811][04011] Fps is (10 sec: 13107.2, 60 sec: 12970.7, 300 sec: 12898.9). Total num frames: 88473600. Throughput: 0: 13025.5. Samples: 88470960. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-11 12:32:57,811][04011] Avg episode reward: [(0, '30.457')] [2023-03-11 12:33:00,905][04298] Updated weights for policy 0, policy_version 172880 (0.0003) [2023-03-11 12:33:02,811][04011] Fps is (10 sec: 12697.6, 60 sec: 12970.7, 300 sec: 12885.0). Total num frames: 88535040. Throughput: 0: 13032.4. Samples: 88510284. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-11 12:33:02,811][04011] Avg episode reward: [(0, '31.142')] [2023-03-11 12:33:04,169][04298] Updated weights for policy 0, policy_version 172960 (0.0003) [2023-03-11 12:33:07,358][04298] Updated weights for policy 0, policy_version 173040 (0.0003) [2023-03-11 12:33:07,811][04011] Fps is (10 sec: 12697.5, 60 sec: 12970.7, 300 sec: 12898.9). Total num frames: 88600576. Throughput: 0: 12977.4. Samples: 88586608. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-11 12:33:07,812][04011] Avg episode reward: [(0, '29.624')] [2023-03-11 12:33:07,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000173048_88600576.pth... [2023-03-11 12:33:07,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000172288_88211456.pth [2023-03-11 12:33:10,478][04298] Updated weights for policy 0, policy_version 173120 (0.0003) [2023-03-11 12:33:12,811][04011] Fps is (10 sec: 13107.3, 60 sec: 12970.7, 300 sec: 12898.9). Total num frames: 88666112. Throughput: 0: 12999.6. Samples: 88665224. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-11 12:33:12,811][04011] Avg episode reward: [(0, '29.947')] [2023-03-11 12:33:13,666][04298] Updated weights for policy 0, policy_version 173200 (0.0003) [2023-03-11 12:33:16,923][04298] Updated weights for policy 0, policy_version 173280 (0.0003) [2023-03-11 12:33:17,811][04011] Fps is (10 sec: 12697.7, 60 sec: 12970.7, 300 sec: 12885.0). Total num frames: 88727552. Throughput: 0: 12971.6. Samples: 88702340. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-11 12:33:17,811][04011] Avg episode reward: [(0, '30.809')] [2023-03-11 12:33:20,252][04298] Updated weights for policy 0, policy_version 173360 (0.0004) [2023-03-11 12:33:22,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12902.4, 300 sec: 12871.2). Total num frames: 88788992. Throughput: 0: 12865.4. Samples: 88775476. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-11 12:33:22,811][04011] Avg episode reward: [(0, '30.315')] [2023-03-11 12:33:22,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000173416_88788992.pth... [2023-03-11 12:33:22,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000172672_88408064.pth [2023-03-11 12:33:23,692][04298] Updated weights for policy 0, policy_version 173440 (0.0005) [2023-03-11 12:33:27,056][04298] Updated weights for policy 0, policy_version 173520 (0.0005) [2023-03-11 12:33:27,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12834.1, 300 sec: 12857.3). Total num frames: 88850432. Throughput: 0: 12742.3. Samples: 88848108. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-11 12:33:27,811][04011] Avg episode reward: [(0, '30.525')] [2023-03-11 12:33:30,442][04298] Updated weights for policy 0, policy_version 173600 (0.0005) [2023-03-11 12:33:32,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12697.6, 300 sec: 12829.5). Total num frames: 88907776. Throughput: 0: 12676.8. Samples: 88884272. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-11 12:33:32,811][04011] Avg episode reward: [(0, '30.458')] [2023-03-11 12:33:33,900][04298] Updated weights for policy 0, policy_version 173680 (0.0005) [2023-03-11 12:33:37,348][04298] Updated weights for policy 0, policy_version 173760 (0.0005) [2023-03-11 12:33:37,811][04011] Fps is (10 sec: 11878.3, 60 sec: 12629.3, 300 sec: 12829.5). Total num frames: 88969216. Throughput: 0: 12552.5. Samples: 88956740. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-11 12:33:37,811][04011] Avg episode reward: [(0, '28.631')] [2023-03-11 12:33:37,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000173768_88969216.pth... [2023-03-11 12:33:37,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000173048_88600576.pth [2023-03-11 12:33:40,756][04298] Updated weights for policy 0, policy_version 173840 (0.0005) [2023-03-11 12:33:42,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12492.8, 300 sec: 12801.7). Total num frames: 89026560. Throughput: 0: 12348.3. Samples: 89026632. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-11 12:33:42,811][04011] Avg episode reward: [(0, '30.208')] [2023-03-11 12:33:44,277][04298] Updated weights for policy 0, policy_version 173920 (0.0005) [2023-03-11 12:33:47,716][04298] Updated weights for policy 0, policy_version 174000 (0.0005) [2023-03-11 12:33:47,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12424.5, 300 sec: 12787.9). Total num frames: 89088000. Throughput: 0: 12263.0. Samples: 89062120. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-11 12:33:47,811][04011] Avg episode reward: [(0, '27.870')] [2023-03-11 12:33:51,233][04298] Updated weights for policy 0, policy_version 174080 (0.0005) [2023-03-11 12:33:52,811][04011] Fps is (10 sec: 12288.1, 60 sec: 12356.3, 300 sec: 12774.0). Total num frames: 89149440. Throughput: 0: 12143.5. Samples: 89133064. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:33:52,811][04011] Avg episode reward: [(0, '26.789')] [2023-03-11 12:33:52,814][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000174120_89149440.pth... [2023-03-11 12:33:52,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000173416_88788992.pth [2023-03-11 12:33:54,425][04298] Updated weights for policy 0, policy_version 174160 (0.0003) [2023-03-11 12:33:57,673][04298] Updated weights for policy 0, policy_version 174240 (0.0004) [2023-03-11 12:33:57,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12288.0, 300 sec: 12760.1). Total num frames: 89210880. Throughput: 0: 12096.3. Samples: 89209560. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:33:57,811][04011] Avg episode reward: [(0, '27.719')] [2023-03-11 12:34:01,069][04298] Updated weights for policy 0, policy_version 174320 (0.0005) [2023-03-11 12:34:02,811][04011] Fps is (10 sec: 12287.9, 60 sec: 12288.0, 300 sec: 12746.2). Total num frames: 89272320. Throughput: 0: 12075.6. Samples: 89245744. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:34:02,811][04011] Avg episode reward: [(0, '29.779')] [2023-03-11 12:34:04,476][04298] Updated weights for policy 0, policy_version 174400 (0.0005) [2023-03-11 12:34:07,811][04011] Fps is (10 sec: 11878.3, 60 sec: 12151.5, 300 sec: 12718.4). Total num frames: 89329664. Throughput: 0: 12037.1. Samples: 89317144. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:34:07,811][04011] Avg episode reward: [(0, '28.721')] [2023-03-11 12:34:07,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000174472_89329664.pth... [2023-03-11 12:34:07,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000173768_88969216.pth [2023-03-11 12:34:07,996][04298] Updated weights for policy 0, policy_version 174480 (0.0005) [2023-03-11 12:34:11,420][04298] Updated weights for policy 0, policy_version 174560 (0.0005) [2023-03-11 12:34:12,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12083.2, 300 sec: 12718.4). Total num frames: 89391104. Throughput: 0: 12002.6. Samples: 89388224. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:34:12,811][04011] Avg episode reward: [(0, '28.456')] [2023-03-11 12:34:14,861][04298] Updated weights for policy 0, policy_version 174640 (0.0005) [2023-03-11 12:34:17,811][04011] Fps is (10 sec: 11878.5, 60 sec: 12014.9, 300 sec: 12690.7). Total num frames: 89448448. Throughput: 0: 11992.5. Samples: 89423936. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:34:17,811][04011] Avg episode reward: [(0, '27.163')] [2023-03-11 12:34:18,308][04298] Updated weights for policy 0, policy_version 174720 (0.0005) [2023-03-11 12:34:21,797][04298] Updated weights for policy 0, policy_version 174800 (0.0005) [2023-03-11 12:34:22,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12014.9, 300 sec: 12676.8). Total num frames: 89509888. Throughput: 0: 11956.0. Samples: 89494760. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:34:22,811][04011] Avg episode reward: [(0, '27.079')] [2023-03-11 12:34:22,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000174824_89509888.pth... [2023-03-11 12:34:22,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000174120_89149440.pth [2023-03-11 12:34:25,093][04298] Updated weights for policy 0, policy_version 174880 (0.0004) [2023-03-11 12:34:27,811][04011] Fps is (10 sec: 12287.9, 60 sec: 12014.9, 300 sec: 12662.9). Total num frames: 89571328. Throughput: 0: 12055.5. Samples: 89569128. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:34:27,812][04011] Avg episode reward: [(0, '26.888')] [2023-03-11 12:34:28,382][04298] Updated weights for policy 0, policy_version 174960 (0.0003) [2023-03-11 12:34:31,460][04298] Updated weights for policy 0, policy_version 175040 (0.0003) [2023-03-11 12:34:32,811][04011] Fps is (10 sec: 12697.7, 60 sec: 12151.5, 300 sec: 12662.9). Total num frames: 89636864. Throughput: 0: 12136.5. Samples: 89608264. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:34:32,811][04011] Avg episode reward: [(0, '28.831')] [2023-03-11 12:34:34,634][04298] Updated weights for policy 0, policy_version 175120 (0.0004) [2023-03-11 12:34:37,811][04011] Fps is (10 sec: 12697.6, 60 sec: 12151.5, 300 sec: 12649.0). Total num frames: 89698304. Throughput: 0: 12289.2. Samples: 89686080. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:34:37,812][04011] Avg episode reward: [(0, '25.788')] [2023-03-11 12:34:37,841][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000175200_89702400.pth... [2023-03-11 12:34:37,841][04298] Updated weights for policy 0, policy_version 175200 (0.0004) [2023-03-11 12:34:37,843][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000174472_89329664.pth [2023-03-11 12:34:41,123][04298] Updated weights for policy 0, policy_version 175280 (0.0003) [2023-03-11 12:34:42,811][04011] Fps is (10 sec: 12697.6, 60 sec: 12288.0, 300 sec: 12649.0). Total num frames: 89763840. Throughput: 0: 12259.2. Samples: 89761224. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:34:42,812][04011] Avg episode reward: [(0, '21.703')] [2023-03-11 12:34:44,310][04298] Updated weights for policy 0, policy_version 175360 (0.0003) [2023-03-11 12:34:47,569][04298] Updated weights for policy 0, policy_version 175440 (0.0003) [2023-03-11 12:34:47,811][04011] Fps is (10 sec: 12697.6, 60 sec: 12288.0, 300 sec: 12635.1). Total num frames: 89825280. Throughput: 0: 12307.9. Samples: 89799600. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:34:47,812][04011] Avg episode reward: [(0, '21.545')] [2023-03-11 12:34:50,748][04298] Updated weights for policy 0, policy_version 175520 (0.0003) [2023-03-11 12:34:52,811][04011] Fps is (10 sec: 12697.5, 60 sec: 12356.2, 300 sec: 12649.0). Total num frames: 89890816. Throughput: 0: 12429.8. Samples: 89876484. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:34:52,812][04011] Avg episode reward: [(0, '22.632')] [2023-03-11 12:34:52,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000175568_89890816.pth... [2023-03-11 12:34:52,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000174824_89509888.pth [2023-03-11 12:34:53,945][04298] Updated weights for policy 0, policy_version 175600 (0.0004) [2023-03-11 12:34:57,141][04298] Updated weights for policy 0, policy_version 175680 (0.0003) [2023-03-11 12:34:57,811][04011] Fps is (10 sec: 12697.7, 60 sec: 12356.3, 300 sec: 12662.9). Total num frames: 89952256. Throughput: 0: 12543.9. Samples: 89952700. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-11 12:34:57,811][04011] Avg episode reward: [(0, '24.877')] [2023-03-11 12:35:00,698][04298] Updated weights for policy 0, policy_version 175760 (0.0005) [2023-03-11 12:35:02,811][04011] Fps is (10 sec: 11878.5, 60 sec: 12288.0, 300 sec: 12635.1). Total num frames: 90009600. Throughput: 0: 12520.9. Samples: 89987376. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-11 12:35:02,811][04011] Avg episode reward: [(0, '23.753')] [2023-03-11 12:35:04,224][04298] Updated weights for policy 0, policy_version 175840 (0.0005) [2023-03-11 12:35:07,672][04298] Updated weights for policy 0, policy_version 175920 (0.0005) [2023-03-11 12:35:07,811][04011] Fps is (10 sec: 11878.3, 60 sec: 12356.3, 300 sec: 12635.1). Total num frames: 90071040. Throughput: 0: 12512.8. Samples: 90057836. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-11 12:35:07,811][04011] Avg episode reward: [(0, '22.545')] [2023-03-11 12:35:07,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000175920_90071040.pth... [2023-03-11 12:35:07,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000175200_89702400.pth [2023-03-11 12:35:10,965][04298] Updated weights for policy 0, policy_version 176000 (0.0004) [2023-03-11 12:35:12,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12356.3, 300 sec: 12621.2). Total num frames: 90132480. Throughput: 0: 12510.8. Samples: 90132112. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-11 12:35:12,811][04011] Avg episode reward: [(0, '25.394')] [2023-03-11 12:35:14,220][04298] Updated weights for policy 0, policy_version 176080 (0.0003) [2023-03-11 12:35:17,402][04298] Updated weights for policy 0, policy_version 176160 (0.0004) [2023-03-11 12:35:17,811][04011] Fps is (10 sec: 12697.6, 60 sec: 12492.8, 300 sec: 12621.2). Total num frames: 90198016. Throughput: 0: 12488.3. Samples: 90170236. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-11 12:35:17,811][04011] Avg episode reward: [(0, '26.789')] [2023-03-11 12:35:20,573][04298] Updated weights for policy 0, policy_version 176240 (0.0003) [2023-03-11 12:35:22,811][04011] Fps is (10 sec: 12697.5, 60 sec: 12492.8, 300 sec: 12621.2). Total num frames: 90259456. Throughput: 0: 12468.6. Samples: 90247168. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-11 12:35:22,812][04011] Avg episode reward: [(0, '23.604')] [2023-03-11 12:35:22,814][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000176288_90259456.pth... [2023-03-11 12:35:22,816][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000175568_89890816.pth [2023-03-11 12:35:23,799][04298] Updated weights for policy 0, policy_version 176320 (0.0005) [2023-03-11 12:35:26,997][04298] Updated weights for policy 0, policy_version 176400 (0.0005) [2023-03-11 12:35:27,811][04011] Fps is (10 sec: 12697.6, 60 sec: 12561.1, 300 sec: 12621.2). Total num frames: 90324992. Throughput: 0: 12513.7. Samples: 90324340. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-11 12:35:27,811][04011] Avg episode reward: [(0, '25.984')] [2023-03-11 12:35:30,164][04298] Updated weights for policy 0, policy_version 176480 (0.0005) [2023-03-11 12:35:32,811][04011] Fps is (10 sec: 13107.3, 60 sec: 12561.1, 300 sec: 12621.2). Total num frames: 90390528. Throughput: 0: 12504.6. Samples: 90362308. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-11 12:35:32,811][04011] Avg episode reward: [(0, '23.925')] [2023-03-11 12:35:33,342][04298] Updated weights for policy 0, policy_version 176560 (0.0005) [2023-03-11 12:35:36,506][04298] Updated weights for policy 0, policy_version 176640 (0.0004) [2023-03-11 12:35:37,811][04011] Fps is (10 sec: 13107.1, 60 sec: 12629.3, 300 sec: 12635.1). Total num frames: 90456064. Throughput: 0: 12520.2. Samples: 90439892. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-11 12:35:37,812][04011] Avg episode reward: [(0, '24.090')] [2023-03-11 12:35:37,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000176672_90456064.pth... [2023-03-11 12:35:37,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000175920_90071040.pth [2023-03-11 12:35:39,640][04298] Updated weights for policy 0, policy_version 176720 (0.0005) [2023-03-11 12:35:42,811][04011] Fps is (10 sec: 12697.5, 60 sec: 12561.1, 300 sec: 12635.1). Total num frames: 90517504. Throughput: 0: 12552.8. Samples: 90517576. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-11 12:35:42,812][04011] Avg episode reward: [(0, '24.028')] [2023-03-11 12:35:42,849][04298] Updated weights for policy 0, policy_version 176800 (0.0005) [2023-03-11 12:35:46,108][04298] Updated weights for policy 0, policy_version 176880 (0.0005) [2023-03-11 12:35:47,811][04011] Fps is (10 sec: 12697.8, 60 sec: 12629.4, 300 sec: 12649.0). Total num frames: 90583040. Throughput: 0: 12620.2. Samples: 90555284. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-11 12:35:47,822][04011] Avg episode reward: [(0, '22.522')] [2023-03-11 12:35:49,518][04298] Updated weights for policy 0, policy_version 176960 (0.0004) [2023-03-11 12:35:52,811][04011] Fps is (10 sec: 12288.1, 60 sec: 12492.8, 300 sec: 12621.2). Total num frames: 90640384. Throughput: 0: 12672.5. Samples: 90628096. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-11 12:35:52,811][04011] Avg episode reward: [(0, '26.098')] [2023-03-11 12:35:52,814][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000177032_90640384.pth... [2023-03-11 12:35:52,816][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000176288_90259456.pth [2023-03-11 12:35:52,926][04298] Updated weights for policy 0, policy_version 177040 (0.0004) [2023-03-11 12:35:56,305][04298] Updated weights for policy 0, policy_version 177120 (0.0003) [2023-03-11 12:35:57,811][04011] Fps is (10 sec: 11878.3, 60 sec: 12492.8, 300 sec: 12607.3). Total num frames: 90701824. Throughput: 0: 12642.2. Samples: 90701012. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-11 12:35:57,811][04011] Avg episode reward: [(0, '21.033')] [2023-03-11 12:35:59,622][04298] Updated weights for policy 0, policy_version 177200 (0.0004) [2023-03-11 12:36:02,811][04011] Fps is (10 sec: 12287.9, 60 sec: 12561.1, 300 sec: 12593.5). Total num frames: 90763264. Throughput: 0: 12601.0. Samples: 90737280. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-11 12:36:02,811][04011] Avg episode reward: [(0, '25.152')] [2023-03-11 12:36:03,089][04298] Updated weights for policy 0, policy_version 177280 (0.0005) [2023-03-11 12:36:06,532][04298] Updated weights for policy 0, policy_version 177360 (0.0005) [2023-03-11 12:36:07,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12492.8, 300 sec: 12565.7). Total num frames: 90820608. Throughput: 0: 12471.7. Samples: 90808392. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-11 12:36:07,811][04011] Avg episode reward: [(0, '25.056')] [2023-03-11 12:36:07,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000177384_90820608.pth... [2023-03-11 12:36:07,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000176672_90456064.pth [2023-03-11 12:36:10,027][04298] Updated weights for policy 0, policy_version 177440 (0.0005) [2023-03-11 12:36:12,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12492.8, 300 sec: 12537.9). Total num frames: 90882048. Throughput: 0: 12334.2. Samples: 90879380. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-11 12:36:12,811][04011] Avg episode reward: [(0, '23.601')] [2023-03-11 12:36:13,484][04298] Updated weights for policy 0, policy_version 177520 (0.0005) [2023-03-11 12:36:16,851][04298] Updated weights for policy 0, policy_version 177600 (0.0005) [2023-03-11 12:36:17,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12356.3, 300 sec: 12524.0). Total num frames: 90939392. Throughput: 0: 12290.7. Samples: 90915388. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-11 12:36:17,811][04011] Avg episode reward: [(0, '23.352')] [2023-03-11 12:36:20,270][04298] Updated weights for policy 0, policy_version 177680 (0.0005) [2023-03-11 12:36:22,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12424.5, 300 sec: 12524.0). Total num frames: 91004928. Throughput: 0: 12200.9. Samples: 90988932. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-11 12:36:22,811][04011] Avg episode reward: [(0, '24.895')] [2023-03-11 12:36:22,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000177744_91004928.pth... [2023-03-11 12:36:22,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000177032_90640384.pth [2023-03-11 12:36:23,449][04298] Updated weights for policy 0, policy_version 177760 (0.0005) [2023-03-11 12:36:26,725][04298] Updated weights for policy 0, policy_version 177840 (0.0005) [2023-03-11 12:36:27,811][04011] Fps is (10 sec: 12697.6, 60 sec: 12356.3, 300 sec: 12510.2). Total num frames: 91066368. Throughput: 0: 12153.7. Samples: 91064492. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-11 12:36:27,811][04011] Avg episode reward: [(0, '24.610')] [2023-03-11 12:36:29,834][04298] Updated weights for policy 0, policy_version 177920 (0.0004) [2023-03-11 12:36:32,811][04011] Fps is (10 sec: 12697.6, 60 sec: 12356.3, 300 sec: 12524.0). Total num frames: 91131904. Throughput: 0: 12201.9. Samples: 91104372. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-11 12:36:32,812][04011] Avg episode reward: [(0, '23.052')] [2023-03-11 12:36:32,945][04298] Updated weights for policy 0, policy_version 178000 (0.0004) [2023-03-11 12:36:36,155][04298] Updated weights for policy 0, policy_version 178080 (0.0004) [2023-03-11 12:36:37,811][04011] Fps is (10 sec: 12697.5, 60 sec: 12288.0, 300 sec: 12510.2). Total num frames: 91193344. Throughput: 0: 12295.4. Samples: 91181392. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-11 12:36:37,812][04011] Avg episode reward: [(0, '22.777')] [2023-03-11 12:36:37,820][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000178120_91197440.pth... [2023-03-11 12:36:37,822][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000177384_90820608.pth [2023-03-11 12:36:39,356][04298] Updated weights for policy 0, policy_version 178160 (0.0004) [2023-03-11 12:36:42,392][04298] Updated weights for policy 0, policy_version 178240 (0.0004) [2023-03-11 12:36:42,811][04011] Fps is (10 sec: 13107.3, 60 sec: 12424.5, 300 sec: 12537.9). Total num frames: 91262976. Throughput: 0: 12439.0. Samples: 91260768. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-11 12:36:42,811][04011] Avg episode reward: [(0, '23.847')] [2023-03-11 12:36:45,610][04298] Updated weights for policy 0, policy_version 178320 (0.0004) [2023-03-11 12:36:47,811][04011] Fps is (10 sec: 13107.3, 60 sec: 12356.3, 300 sec: 12524.0). Total num frames: 91324416. Throughput: 0: 12495.6. Samples: 91299580. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-11 12:36:47,811][04011] Avg episode reward: [(0, '21.763')] [2023-03-11 12:36:48,767][04298] Updated weights for policy 0, policy_version 178400 (0.0004) [2023-03-11 12:36:51,873][04298] Updated weights for policy 0, policy_version 178480 (0.0004) [2023-03-11 12:36:52,811][04011] Fps is (10 sec: 12697.5, 60 sec: 12492.8, 300 sec: 12524.0). Total num frames: 91389952. Throughput: 0: 12650.6. Samples: 91377672. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-11 12:36:52,812][04011] Avg episode reward: [(0, '26.318')] [2023-03-11 12:36:52,814][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000178504_91394048.pth... [2023-03-11 12:36:52,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000177744_91004928.pth [2023-03-11 12:36:55,015][04298] Updated weights for policy 0, policy_version 178560 (0.0004) [2023-03-11 12:36:57,811][04011] Fps is (10 sec: 13107.2, 60 sec: 12561.1, 300 sec: 12537.9). Total num frames: 91455488. Throughput: 0: 12803.8. Samples: 91455552. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-11 12:36:57,811][04011] Avg episode reward: [(0, '27.414')] [2023-03-11 12:36:58,252][04298] Updated weights for policy 0, policy_version 178640 (0.0005) [2023-03-11 12:37:01,478][04298] Updated weights for policy 0, policy_version 178720 (0.0005) [2023-03-11 12:37:02,811][04011] Fps is (10 sec: 13107.3, 60 sec: 12629.3, 300 sec: 12537.9). Total num frames: 91521024. Throughput: 0: 12823.2. Samples: 91492432. Policy #0 lag: (min: 1.0, avg: 1.0, max: 1.0) [2023-03-11 12:37:02,812][04011] Avg episode reward: [(0, '27.672')] [2023-03-11 12:37:04,639][04298] Updated weights for policy 0, policy_version 178800 (0.0004) [2023-03-11 12:37:07,774][04298] Updated weights for policy 0, policy_version 178880 (0.0004) [2023-03-11 12:37:07,811][04011] Fps is (10 sec: 13107.1, 60 sec: 12765.8, 300 sec: 12537.9). Total num frames: 91586560. Throughput: 0: 12918.1. Samples: 91570248. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-11 12:37:07,812][04011] Avg episode reward: [(0, '27.491')] [2023-03-11 12:37:07,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000178880_91586560.pth... [2023-03-11 12:37:07,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000178120_91197440.pth [2023-03-11 12:37:10,940][04298] Updated weights for policy 0, policy_version 178960 (0.0004) [2023-03-11 12:37:12,811][04011] Fps is (10 sec: 12697.6, 60 sec: 12765.9, 300 sec: 12537.9). Total num frames: 91648000. Throughput: 0: 12978.5. Samples: 91648524. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-11 12:37:12,812][04011] Avg episode reward: [(0, '29.990')] [2023-03-11 12:37:14,085][04298] Updated weights for policy 0, policy_version 179040 (0.0005) [2023-03-11 12:37:17,242][04298] Updated weights for policy 0, policy_version 179120 (0.0004) [2023-03-11 12:37:17,811][04011] Fps is (10 sec: 12697.7, 60 sec: 12902.4, 300 sec: 12537.9). Total num frames: 91713536. Throughput: 0: 12961.0. Samples: 91687616. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-11 12:37:17,812][04011] Avg episode reward: [(0, '26.417')] [2023-03-11 12:37:20,423][04298] Updated weights for policy 0, policy_version 179200 (0.0004) [2023-03-11 12:37:22,811][04011] Fps is (10 sec: 13107.2, 60 sec: 12902.4, 300 sec: 12537.9). Total num frames: 91779072. Throughput: 0: 12966.3. Samples: 91764876. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-11 12:37:22,811][04011] Avg episode reward: [(0, '23.706')] [2023-03-11 12:37:22,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000179256_91779072.pth... [2023-03-11 12:37:22,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000178504_91394048.pth [2023-03-11 12:37:23,551][04298] Updated weights for policy 0, policy_version 179280 (0.0004) [2023-03-11 12:37:26,757][04298] Updated weights for policy 0, policy_version 179360 (0.0005) [2023-03-11 12:37:27,811][04011] Fps is (10 sec: 13107.2, 60 sec: 12970.7, 300 sec: 12537.9). Total num frames: 91844608. Throughput: 0: 12925.9. Samples: 91842436. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-11 12:37:27,811][04011] Avg episode reward: [(0, '27.568')] [2023-03-11 12:37:29,910][04298] Updated weights for policy 0, policy_version 179440 (0.0005) [2023-03-11 12:37:32,811][04011] Fps is (10 sec: 13107.3, 60 sec: 12970.7, 300 sec: 12537.9). Total num frames: 91910144. Throughput: 0: 12932.3. Samples: 91881536. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-11 12:37:32,811][04011] Avg episode reward: [(0, '25.577')] [2023-03-11 12:37:33,081][04298] Updated weights for policy 0, policy_version 179520 (0.0004) [2023-03-11 12:37:36,227][04298] Updated weights for policy 0, policy_version 179600 (0.0004) [2023-03-11 12:37:37,811][04011] Fps is (10 sec: 12697.6, 60 sec: 12970.7, 300 sec: 12524.0). Total num frames: 91971584. Throughput: 0: 12925.2. Samples: 91959304. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-11 12:37:37,811][04011] Avg episode reward: [(0, '26.397')] [2023-03-11 12:37:37,814][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000179632_91971584.pth... [2023-03-11 12:37:37,815][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000178880_91586560.pth [2023-03-11 12:37:39,401][04298] Updated weights for policy 0, policy_version 179680 (0.0004) [2023-03-11 12:37:42,548][04298] Updated weights for policy 0, policy_version 179760 (0.0004) [2023-03-11 12:37:42,811][04011] Fps is (10 sec: 12697.6, 60 sec: 12902.4, 300 sec: 12524.0). Total num frames: 92037120. Throughput: 0: 12925.1. Samples: 92037184. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-11 12:37:42,812][04011] Avg episode reward: [(0, '25.392')] [2023-03-11 12:37:45,651][04298] Updated weights for policy 0, policy_version 179840 (0.0004) [2023-03-11 12:37:47,811][04011] Fps is (10 sec: 13107.1, 60 sec: 12970.7, 300 sec: 12524.0). Total num frames: 92102656. Throughput: 0: 12991.6. Samples: 92077056. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-11 12:37:47,812][04011] Avg episode reward: [(0, '23.373')] [2023-03-11 12:37:48,797][04298] Updated weights for policy 0, policy_version 179920 (0.0004) [2023-03-11 12:37:51,868][04298] Updated weights for policy 0, policy_version 180000 (0.0004) [2023-03-11 12:37:52,811][04011] Fps is (10 sec: 13107.2, 60 sec: 12970.7, 300 sec: 12524.0). Total num frames: 92168192. Throughput: 0: 13014.8. Samples: 92155912. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-11 12:37:52,812][04011] Avg episode reward: [(0, '25.825')] [2023-03-11 12:37:52,847][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000180024_92172288.pth... [2023-03-11 12:37:52,849][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000179256_91779072.pth [2023-03-11 12:37:55,064][04298] Updated weights for policy 0, policy_version 180080 (0.0005) [2023-03-11 12:37:57,811][04011] Fps is (10 sec: 13107.2, 60 sec: 12970.7, 300 sec: 12537.9). Total num frames: 92233728. Throughput: 0: 12990.0. Samples: 92233076. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-11 12:37:57,812][04011] Avg episode reward: [(0, '24.274')] [2023-03-11 12:37:58,228][04298] Updated weights for policy 0, policy_version 180160 (0.0005) [2023-03-11 12:38:01,375][04298] Updated weights for policy 0, policy_version 180240 (0.0004) [2023-03-11 12:38:02,811][04011] Fps is (10 sec: 13107.2, 60 sec: 12970.7, 300 sec: 12537.9). Total num frames: 92299264. Throughput: 0: 12994.0. Samples: 92272344. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-11 12:38:02,811][04011] Avg episode reward: [(0, '26.026')] [2023-03-11 12:38:04,524][04298] Updated weights for policy 0, policy_version 180320 (0.0004) [2023-03-11 12:38:07,709][04298] Updated weights for policy 0, policy_version 180400 (0.0005) [2023-03-11 12:38:07,811][04011] Fps is (10 sec: 13107.1, 60 sec: 12970.7, 300 sec: 12537.9). Total num frames: 92364800. Throughput: 0: 13010.7. Samples: 92350356. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-11 12:38:07,811][04011] Avg episode reward: [(0, '22.705')] [2023-03-11 12:38:07,814][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000180400_92364800.pth... [2023-03-11 12:38:07,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000179632_91971584.pth [2023-03-11 12:38:11,187][04298] Updated weights for policy 0, policy_version 180480 (0.0005) [2023-03-11 12:38:12,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12902.4, 300 sec: 12524.0). Total num frames: 92422144. Throughput: 0: 12882.4. Samples: 92422144. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:38:12,811][04011] Avg episode reward: [(0, '24.142')] [2023-03-11 12:38:14,698][04298] Updated weights for policy 0, policy_version 180560 (0.0006) [2023-03-11 12:38:17,811][04011] Fps is (10 sec: 11878.5, 60 sec: 12834.1, 300 sec: 12524.0). Total num frames: 92483584. Throughput: 0: 12784.2. Samples: 92456824. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:38:17,812][04011] Avg episode reward: [(0, '24.805')] [2023-03-11 12:38:18,049][04298] Updated weights for policy 0, policy_version 180640 (0.0005) [2023-03-11 12:38:21,217][04298] Updated weights for policy 0, policy_version 180720 (0.0005) [2023-03-11 12:38:22,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12765.9, 300 sec: 12524.0). Total num frames: 92545024. Throughput: 0: 12744.3. Samples: 92532800. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:38:22,811][04011] Avg episode reward: [(0, '25.196')] [2023-03-11 12:38:22,814][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000180752_92545024.pth... [2023-03-11 12:38:22,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000180024_92172288.pth [2023-03-11 12:38:24,777][04298] Updated weights for policy 0, policy_version 180800 (0.0005) [2023-03-11 12:38:27,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12629.3, 300 sec: 12524.0). Total num frames: 92602368. Throughput: 0: 12563.6. Samples: 92602544. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:38:27,811][04011] Avg episode reward: [(0, '22.773')] [2023-03-11 12:38:28,198][04298] Updated weights for policy 0, policy_version 180880 (0.0005) [2023-03-11 12:38:31,413][04298] Updated weights for policy 0, policy_version 180960 (0.0004) [2023-03-11 12:38:32,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12629.3, 300 sec: 12537.9). Total num frames: 92667904. Throughput: 0: 12513.6. Samples: 92640168. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:38:32,812][04011] Avg episode reward: [(0, '24.531')] [2023-03-11 12:38:34,525][04298] Updated weights for policy 0, policy_version 181040 (0.0004) [2023-03-11 12:38:37,688][04298] Updated weights for policy 0, policy_version 181120 (0.0004) [2023-03-11 12:38:37,811][04011] Fps is (10 sec: 13107.1, 60 sec: 12697.6, 300 sec: 12565.7). Total num frames: 92733440. Throughput: 0: 12511.2. Samples: 92718916. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:38:37,812][04011] Avg episode reward: [(0, '23.120')] [2023-03-11 12:38:37,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000181120_92733440.pth... [2023-03-11 12:38:37,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000180400_92364800.pth [2023-03-11 12:38:41,200][04298] Updated weights for policy 0, policy_version 181200 (0.0005) [2023-03-11 12:38:42,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12561.1, 300 sec: 12551.8). Total num frames: 92790784. Throughput: 0: 12395.1. Samples: 92790856. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:38:42,811][04011] Avg episode reward: [(0, '22.850')] [2023-03-11 12:38:44,612][04298] Updated weights for policy 0, policy_version 181280 (0.0005) [2023-03-11 12:38:47,811][04011] Fps is (10 sec: 11878.5, 60 sec: 12492.8, 300 sec: 12551.8). Total num frames: 92852224. Throughput: 0: 12326.2. Samples: 92827024. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:38:47,812][04011] Avg episode reward: [(0, '22.971')] [2023-03-11 12:38:47,993][04298] Updated weights for policy 0, policy_version 181360 (0.0005) [2023-03-11 12:38:51,389][04298] Updated weights for policy 0, policy_version 181440 (0.0005) [2023-03-11 12:38:52,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12424.5, 300 sec: 12551.8). Total num frames: 92913664. Throughput: 0: 12200.8. Samples: 92899392. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:38:52,812][04011] Avg episode reward: [(0, '23.505')] [2023-03-11 12:38:52,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000181472_92913664.pth... [2023-03-11 12:38:52,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000180752_92545024.pth [2023-03-11 12:38:54,723][04298] Updated weights for policy 0, policy_version 181520 (0.0004) [2023-03-11 12:38:57,811][04011] Fps is (10 sec: 11878.5, 60 sec: 12288.0, 300 sec: 12537.9). Total num frames: 92971008. Throughput: 0: 12215.1. Samples: 92971824. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:38:57,811][04011] Avg episode reward: [(0, '23.011')] [2023-03-11 12:38:58,160][04298] Updated weights for policy 0, policy_version 181600 (0.0005) [2023-03-11 12:39:01,512][04298] Updated weights for policy 0, policy_version 181680 (0.0005) [2023-03-11 12:39:02,811][04011] Fps is (10 sec: 12288.1, 60 sec: 12288.0, 300 sec: 12565.7). Total num frames: 93036544. Throughput: 0: 12245.8. Samples: 93007884. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:39:02,812][04011] Avg episode reward: [(0, '22.237')] [2023-03-11 12:39:04,686][04298] Updated weights for policy 0, policy_version 181760 (0.0004) [2023-03-11 12:39:07,811][04011] Fps is (10 sec: 12697.5, 60 sec: 12219.7, 300 sec: 12565.7). Total num frames: 93097984. Throughput: 0: 12275.0. Samples: 93085176. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:39:07,811][04011] Avg episode reward: [(0, '24.166')] [2023-03-11 12:39:07,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000181832_93097984.pth... [2023-03-11 12:39:07,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000181120_92733440.pth [2023-03-11 12:39:07,954][04298] Updated weights for policy 0, policy_version 181840 (0.0005) [2023-03-11 12:39:11,222][04298] Updated weights for policy 0, policy_version 181920 (0.0004) [2023-03-11 12:39:12,811][04011] Fps is (10 sec: 12697.6, 60 sec: 12356.3, 300 sec: 12593.5). Total num frames: 93163520. Throughput: 0: 12388.5. Samples: 93160028. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:39:12,811][04011] Avg episode reward: [(0, '23.116')] [2023-03-11 12:39:14,388][04298] Updated weights for policy 0, policy_version 182000 (0.0003) [2023-03-11 12:39:17,722][04298] Updated weights for policy 0, policy_version 182080 (0.0004) [2023-03-11 12:39:17,811][04011] Fps is (10 sec: 12697.6, 60 sec: 12356.3, 300 sec: 12593.5). Total num frames: 93224960. Throughput: 0: 12391.0. Samples: 93197764. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:39:17,812][04011] Avg episode reward: [(0, '20.110')] [2023-03-11 12:39:20,935][04298] Updated weights for policy 0, policy_version 182160 (0.0003) [2023-03-11 12:39:22,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12356.3, 300 sec: 12593.5). Total num frames: 93286400. Throughput: 0: 12337.0. Samples: 93274080. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:39:22,811][04011] Avg episode reward: [(0, '24.032')] [2023-03-11 12:39:22,880][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000182208_93290496.pth... [2023-03-11 12:39:22,882][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000181472_92913664.pth [2023-03-11 12:39:24,243][04298] Updated weights for policy 0, policy_version 182240 (0.0004) [2023-03-11 12:39:27,773][04298] Updated weights for policy 0, policy_version 182320 (0.0005) [2023-03-11 12:39:27,811][04011] Fps is (10 sec: 12287.9, 60 sec: 12424.5, 300 sec: 12579.6). Total num frames: 93347840. Throughput: 0: 12315.4. Samples: 93345048. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:39:27,812][04011] Avg episode reward: [(0, '21.721')] [2023-03-11 12:39:31,197][04298] Updated weights for policy 0, policy_version 182400 (0.0005) [2023-03-11 12:39:32,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12288.0, 300 sec: 12565.7). Total num frames: 93405184. Throughput: 0: 12306.2. Samples: 93380804. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:39:32,811][04011] Avg episode reward: [(0, '23.589')] [2023-03-11 12:39:34,601][04298] Updated weights for policy 0, policy_version 182480 (0.0005) [2023-03-11 12:39:37,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12219.7, 300 sec: 12551.8). Total num frames: 93466624. Throughput: 0: 12306.4. Samples: 93453180. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:39:37,811][04011] Avg episode reward: [(0, '23.973')] [2023-03-11 12:39:37,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000182552_93466624.pth... [2023-03-11 12:39:37,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000181832_93097984.pth [2023-03-11 12:39:38,008][04298] Updated weights for policy 0, policy_version 182560 (0.0005) [2023-03-11 12:39:41,539][04298] Updated weights for policy 0, policy_version 182640 (0.0006) [2023-03-11 12:39:42,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12219.7, 300 sec: 12537.9). Total num frames: 93523968. Throughput: 0: 12269.9. Samples: 93523968. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:39:42,811][04011] Avg episode reward: [(0, '22.891')] [2023-03-11 12:39:45,052][04298] Updated weights for policy 0, policy_version 182720 (0.0005) [2023-03-11 12:39:47,811][04011] Fps is (10 sec: 11878.5, 60 sec: 12219.7, 300 sec: 12524.0). Total num frames: 93585408. Throughput: 0: 12248.1. Samples: 93559048. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:39:47,811][04011] Avg episode reward: [(0, '20.792')] [2023-03-11 12:39:48,490][04298] Updated weights for policy 0, policy_version 182800 (0.0005) [2023-03-11 12:39:51,977][04298] Updated weights for policy 0, policy_version 182880 (0.0005) [2023-03-11 12:39:52,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12151.5, 300 sec: 12510.2). Total num frames: 93642752. Throughput: 0: 12109.3. Samples: 93630096. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:39:52,811][04011] Avg episode reward: [(0, '23.517')] [2023-03-11 12:39:52,814][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000182896_93642752.pth... [2023-03-11 12:39:52,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000182208_93290496.pth [2023-03-11 12:39:55,524][04298] Updated weights for policy 0, policy_version 182960 (0.0005) [2023-03-11 12:39:57,811][04011] Fps is (10 sec: 11468.8, 60 sec: 12151.5, 300 sec: 12510.2). Total num frames: 93700096. Throughput: 0: 12001.8. Samples: 93700108. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:39:57,811][04011] Avg episode reward: [(0, '20.570')] [2023-03-11 12:39:59,008][04298] Updated weights for policy 0, policy_version 183040 (0.0005) [2023-03-11 12:40:02,564][04298] Updated weights for policy 0, policy_version 183120 (0.0005) [2023-03-11 12:40:02,811][04011] Fps is (10 sec: 11468.8, 60 sec: 12014.9, 300 sec: 12496.3). Total num frames: 93757440. Throughput: 0: 11917.5. Samples: 93734052. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:40:02,811][04011] Avg episode reward: [(0, '20.815')] [2023-03-11 12:40:06,044][04298] Updated weights for policy 0, policy_version 183200 (0.0005) [2023-03-11 12:40:07,811][04011] Fps is (10 sec: 11878.3, 60 sec: 12014.9, 300 sec: 12496.3). Total num frames: 93818880. Throughput: 0: 11778.4. Samples: 93804108. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:40:07,811][04011] Avg episode reward: [(0, '19.959')] [2023-03-11 12:40:07,814][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000183240_93818880.pth... [2023-03-11 12:40:07,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000182552_93466624.pth [2023-03-11 12:40:09,524][04298] Updated weights for policy 0, policy_version 183280 (0.0005) [2023-03-11 12:40:12,811][04011] Fps is (10 sec: 11878.4, 60 sec: 11878.4, 300 sec: 12468.5). Total num frames: 93876224. Throughput: 0: 11789.2. Samples: 93875560. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:40:12,811][04011] Avg episode reward: [(0, '24.899')] [2023-03-11 12:40:13,043][04298] Updated weights for policy 0, policy_version 183360 (0.0005) [2023-03-11 12:40:16,571][04298] Updated weights for policy 0, policy_version 183440 (0.0005) [2023-03-11 12:40:17,811][04011] Fps is (10 sec: 11468.8, 60 sec: 11810.1, 300 sec: 12454.6). Total num frames: 93933568. Throughput: 0: 11739.3. Samples: 93909072. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:40:17,811][04011] Avg episode reward: [(0, '21.649')] [2023-03-11 12:40:20,129][04298] Updated weights for policy 0, policy_version 183520 (0.0005) [2023-03-11 12:40:22,811][04011] Fps is (10 sec: 11468.7, 60 sec: 11741.8, 300 sec: 12426.8). Total num frames: 93990912. Throughput: 0: 11676.7. Samples: 93978632. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:40:22,812][04011] Avg episode reward: [(0, '17.726')] [2023-03-11 12:40:22,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000183576_93990912.pth... [2023-03-11 12:40:22,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000182896_93642752.pth [2023-03-11 12:40:23,584][04298] Updated weights for policy 0, policy_version 183600 (0.0005) [2023-03-11 12:40:26,826][04298] Updated weights for policy 0, policy_version 183680 (0.0005) [2023-03-11 12:40:27,811][04011] Fps is (10 sec: 12288.0, 60 sec: 11810.1, 300 sec: 12426.8). Total num frames: 94056448. Throughput: 0: 11762.1. Samples: 94053264. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-11 12:40:27,812][04011] Avg episode reward: [(0, '21.689')] [2023-03-11 12:40:29,982][04298] Updated weights for policy 0, policy_version 183760 (0.0004) [2023-03-11 12:40:32,811][04011] Fps is (10 sec: 12697.6, 60 sec: 11878.4, 300 sec: 12413.0). Total num frames: 94117888. Throughput: 0: 11849.4. Samples: 94092272. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-11 12:40:32,812][04011] Avg episode reward: [(0, '22.641')] [2023-03-11 12:40:33,163][04298] Updated weights for policy 0, policy_version 183840 (0.0004) [2023-03-11 12:40:36,537][04298] Updated weights for policy 0, policy_version 183920 (0.0005) [2023-03-11 12:40:37,811][04011] Fps is (10 sec: 12288.0, 60 sec: 11878.4, 300 sec: 12413.0). Total num frames: 94179328. Throughput: 0: 11933.5. Samples: 94167104. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-11 12:40:37,812][04011] Avg episode reward: [(0, '21.430')] [2023-03-11 12:40:37,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000183944_94179328.pth... [2023-03-11 12:40:37,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000183240_93818880.pth [2023-03-11 12:40:40,020][04298] Updated weights for policy 0, policy_version 184000 (0.0005) [2023-03-11 12:40:42,811][04011] Fps is (10 sec: 12288.0, 60 sec: 11946.7, 300 sec: 12399.1). Total num frames: 94240768. Throughput: 0: 11978.4. Samples: 94239136. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-11 12:40:42,811][04011] Avg episode reward: [(0, '18.304')] [2023-03-11 12:40:43,373][04298] Updated weights for policy 0, policy_version 184080 (0.0004) [2023-03-11 12:40:46,654][04298] Updated weights for policy 0, policy_version 184160 (0.0004) [2023-03-11 12:40:47,811][04011] Fps is (10 sec: 12288.0, 60 sec: 11946.7, 300 sec: 12413.0). Total num frames: 94302208. Throughput: 0: 12062.8. Samples: 94276880. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-11 12:40:47,811][04011] Avg episode reward: [(0, '20.738')] [2023-03-11 12:40:49,991][04298] Updated weights for policy 0, policy_version 184240 (0.0004) [2023-03-11 12:40:52,811][04011] Fps is (10 sec: 12287.9, 60 sec: 12014.9, 300 sec: 12413.0). Total num frames: 94363648. Throughput: 0: 12147.8. Samples: 94350760. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-11 12:40:52,811][04011] Avg episode reward: [(0, '20.676')] [2023-03-11 12:40:52,814][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000184304_94363648.pth... [2023-03-11 12:40:52,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000183576_93990912.pth [2023-03-11 12:40:53,280][04298] Updated weights for policy 0, policy_version 184320 (0.0003) [2023-03-11 12:40:56,633][04298] Updated weights for policy 0, policy_version 184400 (0.0003) [2023-03-11 12:40:57,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12083.2, 300 sec: 12413.0). Total num frames: 94425088. Throughput: 0: 12172.1. Samples: 94423304. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-11 12:40:57,811][04011] Avg episode reward: [(0, '18.422')] [2023-03-11 12:41:00,247][04298] Updated weights for policy 0, policy_version 184480 (0.0005) [2023-03-11 12:41:02,811][04011] Fps is (10 sec: 11878.5, 60 sec: 12083.2, 300 sec: 12413.0). Total num frames: 94482432. Throughput: 0: 12195.2. Samples: 94457856. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-11 12:41:02,811][04011] Avg episode reward: [(0, '20.395')] [2023-03-11 12:41:03,875][04298] Updated weights for policy 0, policy_version 184560 (0.0005) [2023-03-11 12:41:07,358][04298] Updated weights for policy 0, policy_version 184640 (0.0005) [2023-03-11 12:41:07,811][04011] Fps is (10 sec: 11468.8, 60 sec: 12014.9, 300 sec: 12399.1). Total num frames: 94539776. Throughput: 0: 12194.1. Samples: 94527368. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-11 12:41:07,811][04011] Avg episode reward: [(0, '20.289')] [2023-03-11 12:41:07,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000184648_94539776.pth... [2023-03-11 12:41:07,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000183944_94179328.pth [2023-03-11 12:41:10,700][04298] Updated weights for policy 0, policy_version 184720 (0.0005) [2023-03-11 12:41:12,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12083.2, 300 sec: 12413.0). Total num frames: 94601216. Throughput: 0: 12149.5. Samples: 94599992. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-11 12:41:12,812][04011] Avg episode reward: [(0, '17.350')] [2023-03-11 12:41:13,921][04298] Updated weights for policy 0, policy_version 184800 (0.0004) [2023-03-11 12:41:17,312][04298] Updated weights for policy 0, policy_version 184880 (0.0004) [2023-03-11 12:41:17,811][04011] Fps is (10 sec: 12288.1, 60 sec: 12151.5, 300 sec: 12399.1). Total num frames: 94662656. Throughput: 0: 12130.5. Samples: 94638144. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-11 12:41:17,811][04011] Avg episode reward: [(0, '18.726')] [2023-03-11 12:41:20,973][04298] Updated weights for policy 0, policy_version 184960 (0.0005) [2023-03-11 12:41:22,811][04011] Fps is (10 sec: 11878.3, 60 sec: 12151.5, 300 sec: 12385.2). Total num frames: 94720000. Throughput: 0: 11993.9. Samples: 94706828. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-11 12:41:22,811][04011] Avg episode reward: [(0, '17.518')] [2023-03-11 12:41:22,814][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000185000_94720000.pth... [2023-03-11 12:41:22,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000184304_94363648.pth [2023-03-11 12:41:24,521][04298] Updated weights for policy 0, policy_version 185040 (0.0005) [2023-03-11 12:41:27,811][04011] Fps is (10 sec: 11468.8, 60 sec: 12014.9, 300 sec: 12357.4). Total num frames: 94777344. Throughput: 0: 11905.5. Samples: 94774884. Policy #0 lag: (min: 3.0, avg: 3.0, max: 3.0) [2023-03-11 12:41:27,811][04011] Avg episode reward: [(0, '15.401')] [2023-03-11 12:41:28,147][04298] Updated weights for policy 0, policy_version 185120 (0.0005) [2023-03-11 12:41:31,791][04298] Updated weights for policy 0, policy_version 185200 (0.0005) [2023-03-11 12:41:32,811][04011] Fps is (10 sec: 11059.3, 60 sec: 11878.4, 300 sec: 12329.7). Total num frames: 94830592. Throughput: 0: 11826.0. Samples: 94809048. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:41:32,811][04011] Avg episode reward: [(0, '15.693')] [2023-03-11 12:41:35,424][04298] Updated weights for policy 0, policy_version 185280 (0.0005) [2023-03-11 12:41:37,811][04011] Fps is (10 sec: 11059.2, 60 sec: 11810.2, 300 sec: 12288.0). Total num frames: 94887936. Throughput: 0: 11670.9. Samples: 94875948. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:41:37,811][04011] Avg episode reward: [(0, '14.981')] [2023-03-11 12:41:37,814][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000185328_94887936.pth... [2023-03-11 12:41:37,815][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000184648_94539776.pth [2023-03-11 12:41:38,892][04298] Updated weights for policy 0, policy_version 185360 (0.0005) [2023-03-11 12:41:42,201][04298] Updated weights for policy 0, policy_version 185440 (0.0004) [2023-03-11 12:41:42,811][04011] Fps is (10 sec: 11878.4, 60 sec: 11810.1, 300 sec: 12288.0). Total num frames: 94949376. Throughput: 0: 11691.9. Samples: 94949440. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:41:42,811][04011] Avg episode reward: [(0, '15.098')] [2023-03-11 12:41:45,532][04298] Updated weights for policy 0, policy_version 185520 (0.0004) [2023-03-11 12:41:47,811][04011] Fps is (10 sec: 12287.9, 60 sec: 11810.1, 300 sec: 12274.1). Total num frames: 95010816. Throughput: 0: 11743.3. Samples: 94986304. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:41:47,812][04011] Avg episode reward: [(0, '14.699')] [2023-03-11 12:41:48,856][04298] Updated weights for policy 0, policy_version 185600 (0.0004) [2023-03-11 12:41:52,223][04298] Updated weights for policy 0, policy_version 185680 (0.0004) [2023-03-11 12:41:52,811][04011] Fps is (10 sec: 12288.0, 60 sec: 11810.1, 300 sec: 12260.2). Total num frames: 95072256. Throughput: 0: 11839.4. Samples: 95060140. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:41:52,811][04011] Avg episode reward: [(0, '14.731')] [2023-03-11 12:41:52,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000185688_95072256.pth... [2023-03-11 12:41:52,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000185000_94720000.pth [2023-03-11 12:41:55,635][04298] Updated weights for policy 0, policy_version 185760 (0.0004) [2023-03-11 12:41:57,811][04011] Fps is (10 sec: 12288.0, 60 sec: 11810.1, 300 sec: 12246.3). Total num frames: 95133696. Throughput: 0: 11820.7. Samples: 95131924. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:41:57,812][04011] Avg episode reward: [(0, '15.068')] [2023-03-11 12:41:59,055][04298] Updated weights for policy 0, policy_version 185840 (0.0004) [2023-03-11 12:42:02,417][04298] Updated weights for policy 0, policy_version 185920 (0.0004) [2023-03-11 12:42:02,811][04011] Fps is (10 sec: 12288.0, 60 sec: 11878.4, 300 sec: 12232.5). Total num frames: 95195136. Throughput: 0: 11778.1. Samples: 95168160. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:42:02,812][04011] Avg episode reward: [(0, '14.524')] [2023-03-11 12:42:06,001][04298] Updated weights for policy 0, policy_version 186000 (0.0005) [2023-03-11 12:42:07,811][04011] Fps is (10 sec: 11468.9, 60 sec: 11810.2, 300 sec: 12204.7). Total num frames: 95248384. Throughput: 0: 11813.2. Samples: 95238420. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:42:07,811][04011] Avg episode reward: [(0, '13.574')] [2023-03-11 12:42:07,836][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000186040_95252480.pth... [2023-03-11 12:42:07,839][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000185328_94887936.pth [2023-03-11 12:42:09,711][04298] Updated weights for policy 0, policy_version 186080 (0.0005) [2023-03-11 12:42:12,811][04011] Fps is (10 sec: 11059.3, 60 sec: 11741.9, 300 sec: 12176.9). Total num frames: 95305728. Throughput: 0: 11785.7. Samples: 95305240. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:42:12,811][04011] Avg episode reward: [(0, '14.320')] [2023-03-11 12:42:13,392][04298] Updated weights for policy 0, policy_version 186160 (0.0006) [2023-03-11 12:42:16,881][04298] Updated weights for policy 0, policy_version 186240 (0.0005) [2023-03-11 12:42:17,811][04011] Fps is (10 sec: 11468.8, 60 sec: 11673.6, 300 sec: 12149.2). Total num frames: 95363072. Throughput: 0: 11766.9. Samples: 95338560. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:42:17,811][04011] Avg episode reward: [(0, '14.150')] [2023-03-11 12:42:20,212][04298] Updated weights for policy 0, policy_version 186320 (0.0005) [2023-03-11 12:42:22,811][04011] Fps is (10 sec: 11878.3, 60 sec: 11741.9, 300 sec: 12135.3). Total num frames: 95424512. Throughput: 0: 11911.8. Samples: 95411980. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:42:22,812][04011] Avg episode reward: [(0, '20.046')] [2023-03-11 12:42:22,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000186376_95424512.pth... [2023-03-11 12:42:22,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000185688_95072256.pth [2023-03-11 12:42:23,892][04298] Updated weights for policy 0, policy_version 186400 (0.0006) [2023-03-11 12:42:27,589][04298] Updated weights for policy 0, policy_version 186480 (0.0006) [2023-03-11 12:42:27,811][04011] Fps is (10 sec: 11468.8, 60 sec: 11673.6, 300 sec: 12093.6). Total num frames: 95477760. Throughput: 0: 11740.4. Samples: 95477760. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:42:27,811][04011] Avg episode reward: [(0, '15.347')] [2023-03-11 12:42:31,327][04298] Updated weights for policy 0, policy_version 186560 (0.0006) [2023-03-11 12:42:32,811][04011] Fps is (10 sec: 11059.3, 60 sec: 11741.9, 300 sec: 12079.7). Total num frames: 95535104. Throughput: 0: 11649.7. Samples: 95510540. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:42:32,811][04011] Avg episode reward: [(0, '14.306')] [2023-03-11 12:42:35,011][04298] Updated weights for policy 0, policy_version 186640 (0.0006) [2023-03-11 12:42:37,811][04011] Fps is (10 sec: 11059.2, 60 sec: 11673.6, 300 sec: 12038.1). Total num frames: 95588352. Throughput: 0: 11484.4. Samples: 95576936. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:42:37,811][04011] Avg episode reward: [(0, '14.620')] [2023-03-11 12:42:37,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000186696_95588352.pth... [2023-03-11 12:42:37,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000186040_95252480.pth [2023-03-11 12:42:38,663][04298] Updated weights for policy 0, policy_version 186720 (0.0006) [2023-03-11 12:42:42,317][04298] Updated weights for policy 0, policy_version 186800 (0.0006) [2023-03-11 12:42:42,811][04011] Fps is (10 sec: 11059.2, 60 sec: 11605.3, 300 sec: 12010.3). Total num frames: 95645696. Throughput: 0: 11392.5. Samples: 95644584. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:42:42,811][04011] Avg episode reward: [(0, '16.812')] [2023-03-11 12:42:45,922][04298] Updated weights for policy 0, policy_version 186880 (0.0005) [2023-03-11 12:42:47,811][04011] Fps is (10 sec: 11468.8, 60 sec: 11537.1, 300 sec: 11982.5). Total num frames: 95703040. Throughput: 0: 11328.4. Samples: 95677936. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:42:47,811][04011] Avg episode reward: [(0, '15.988')] [2023-03-11 12:42:49,260][04298] Updated weights for policy 0, policy_version 186960 (0.0005) [2023-03-11 12:42:52,639][04298] Updated weights for policy 0, policy_version 187040 (0.0005) [2023-03-11 12:42:52,811][04011] Fps is (10 sec: 11878.4, 60 sec: 11537.1, 300 sec: 11968.7). Total num frames: 95764480. Throughput: 0: 11405.7. Samples: 95751676. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:42:52,811][04011] Avg episode reward: [(0, '13.318')] [2023-03-11 12:42:52,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000187040_95764480.pth... [2023-03-11 12:42:52,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000186376_95424512.pth [2023-03-11 12:42:55,958][04298] Updated weights for policy 0, policy_version 187120 (0.0004) [2023-03-11 12:42:57,811][04011] Fps is (10 sec: 12288.0, 60 sec: 11537.1, 300 sec: 11954.8). Total num frames: 95825920. Throughput: 0: 11551.7. Samples: 95825068. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:42:57,811][04011] Avg episode reward: [(0, '18.007')] [2023-03-11 12:42:59,319][04298] Updated weights for policy 0, policy_version 187200 (0.0005) [2023-03-11 12:43:02,811][04011] Fps is (10 sec: 11878.5, 60 sec: 11468.8, 300 sec: 11927.0). Total num frames: 95883264. Throughput: 0: 11631.6. Samples: 95861980. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:43:02,811][04011] Avg episode reward: [(0, '15.396')] [2023-03-11 12:43:02,814][04298] Updated weights for policy 0, policy_version 187280 (0.0005) [2023-03-11 12:43:06,235][04298] Updated weights for policy 0, policy_version 187360 (0.0005) [2023-03-11 12:43:07,811][04011] Fps is (10 sec: 11878.4, 60 sec: 11605.3, 300 sec: 11940.9). Total num frames: 95944704. Throughput: 0: 11565.4. Samples: 95932424. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:43:07,811][04011] Avg episode reward: [(0, '16.778')] [2023-03-11 12:43:07,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000187392_95944704.pth... [2023-03-11 12:43:07,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000186696_95588352.pth [2023-03-11 12:43:09,584][04298] Updated weights for policy 0, policy_version 187440 (0.0005) [2023-03-11 12:43:12,811][04011] Fps is (10 sec: 12288.0, 60 sec: 11673.6, 300 sec: 11940.9). Total num frames: 96006144. Throughput: 0: 11725.9. Samples: 96005424. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:43:12,822][04011] Avg episode reward: [(0, '16.045')] [2023-03-11 12:43:12,958][04298] Updated weights for policy 0, policy_version 187520 (0.0005) [2023-03-11 12:43:16,323][04298] Updated weights for policy 0, policy_version 187600 (0.0005) [2023-03-11 12:43:17,811][04011] Fps is (10 sec: 12288.0, 60 sec: 11741.9, 300 sec: 11940.9). Total num frames: 96067584. Throughput: 0: 11806.5. Samples: 96041832. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:43:17,811][04011] Avg episode reward: [(0, '16.038')] [2023-03-11 12:43:19,686][04298] Updated weights for policy 0, policy_version 187680 (0.0005) [2023-03-11 12:43:22,811][04011] Fps is (10 sec: 12287.9, 60 sec: 11741.9, 300 sec: 11954.8). Total num frames: 96129024. Throughput: 0: 11962.8. Samples: 96115260. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:43:22,811][04011] Avg episode reward: [(0, '13.917')] [2023-03-11 12:43:22,814][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000187752_96129024.pth... [2023-03-11 12:43:22,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000187040_95764480.pth [2023-03-11 12:43:22,993][04298] Updated weights for policy 0, policy_version 187760 (0.0004) [2023-03-11 12:43:26,415][04298] Updated weights for policy 0, policy_version 187840 (0.0004) [2023-03-11 12:43:27,811][04011] Fps is (10 sec: 12288.0, 60 sec: 11878.4, 300 sec: 11940.9). Total num frames: 96190464. Throughput: 0: 12085.1. Samples: 96188412. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:43:27,811][04011] Avg episode reward: [(0, '16.652')] [2023-03-11 12:43:29,690][04298] Updated weights for policy 0, policy_version 187920 (0.0004) [2023-03-11 12:43:32,811][04011] Fps is (10 sec: 12288.0, 60 sec: 11946.7, 300 sec: 11927.0). Total num frames: 96251904. Throughput: 0: 12177.8. Samples: 96225936. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:43:32,811][04011] Avg episode reward: [(0, '20.134')] [2023-03-11 12:43:32,981][04298] Updated weights for policy 0, policy_version 188000 (0.0005) [2023-03-11 12:43:36,291][04298] Updated weights for policy 0, policy_version 188080 (0.0005) [2023-03-11 12:43:37,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12083.2, 300 sec: 11940.9). Total num frames: 96313344. Throughput: 0: 12192.8. Samples: 96300352. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:43:37,811][04011] Avg episode reward: [(0, '15.522')] [2023-03-11 12:43:37,814][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000188112_96313344.pth... [2023-03-11 12:43:37,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000187392_95944704.pth [2023-03-11 12:43:39,788][04298] Updated weights for policy 0, policy_version 188160 (0.0005) [2023-03-11 12:43:42,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12083.2, 300 sec: 11927.0). Total num frames: 96370688. Throughput: 0: 12094.8. Samples: 96369336. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-11 12:43:42,812][04011] Avg episode reward: [(0, '17.094')] [2023-03-11 12:43:43,389][04298] Updated weights for policy 0, policy_version 188240 (0.0006) [2023-03-11 12:43:46,980][04298] Updated weights for policy 0, policy_version 188320 (0.0005) [2023-03-11 12:43:47,811][04011] Fps is (10 sec: 11468.8, 60 sec: 12083.2, 300 sec: 11913.1). Total num frames: 96428032. Throughput: 0: 12032.8. Samples: 96403456. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-11 12:43:47,812][04011] Avg episode reward: [(0, '19.118')] [2023-03-11 12:43:50,338][04298] Updated weights for policy 0, policy_version 188400 (0.0005) [2023-03-11 12:43:52,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12083.2, 300 sec: 11927.0). Total num frames: 96489472. Throughput: 0: 12077.6. Samples: 96475916. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-11 12:43:52,812][04011] Avg episode reward: [(0, '15.523')] [2023-03-11 12:43:52,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000188456_96489472.pth... [2023-03-11 12:43:52,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000187752_96129024.pth [2023-03-11 12:43:53,714][04298] Updated weights for policy 0, policy_version 188480 (0.0005) [2023-03-11 12:43:57,045][04298] Updated weights for policy 0, policy_version 188560 (0.0004) [2023-03-11 12:43:57,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12083.2, 300 sec: 11913.1). Total num frames: 96550912. Throughput: 0: 12074.8. Samples: 96548792. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-11 12:43:57,812][04011] Avg episode reward: [(0, '16.331')] [2023-03-11 12:44:00,413][04298] Updated weights for policy 0, policy_version 188640 (0.0005) [2023-03-11 12:44:02,811][04011] Fps is (10 sec: 12288.1, 60 sec: 12151.5, 300 sec: 11913.1). Total num frames: 96612352. Throughput: 0: 12078.8. Samples: 96585380. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-11 12:44:02,811][04011] Avg episode reward: [(0, '20.261')] [2023-03-11 12:44:03,761][04298] Updated weights for policy 0, policy_version 188720 (0.0005) [2023-03-11 12:44:07,227][04298] Updated weights for policy 0, policy_version 188800 (0.0005) [2023-03-11 12:44:07,811][04011] Fps is (10 sec: 11878.4, 60 sec: 12083.2, 300 sec: 11885.3). Total num frames: 96669696. Throughput: 0: 12049.3. Samples: 96657480. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-11 12:44:07,812][04011] Avg episode reward: [(0, '18.381')] [2023-03-11 12:44:07,814][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000188808_96669696.pth... [2023-03-11 12:44:07,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000188112_96313344.pth [2023-03-11 12:44:10,863][04298] Updated weights for policy 0, policy_version 188880 (0.0006) [2023-03-11 12:44:12,811][04011] Fps is (10 sec: 11468.7, 60 sec: 12014.9, 300 sec: 11871.5). Total num frames: 96727040. Throughput: 0: 11951.0. Samples: 96726208. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-11 12:44:12,811][04011] Avg episode reward: [(0, '14.759')] [2023-03-11 12:44:14,499][04298] Updated weights for policy 0, policy_version 188960 (0.0005) [2023-03-11 12:44:17,811][04011] Fps is (10 sec: 11468.9, 60 sec: 11946.7, 300 sec: 11857.6). Total num frames: 96784384. Throughput: 0: 11864.0. Samples: 96759816. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-11 12:44:17,811][04011] Avg episode reward: [(0, '12.873')] [2023-03-11 12:44:18,173][04298] Updated weights for policy 0, policy_version 189040 (0.0006) [2023-03-11 12:44:21,841][04298] Updated weights for policy 0, policy_version 189120 (0.0005) [2023-03-11 12:44:22,811][04011] Fps is (10 sec: 11059.3, 60 sec: 11810.1, 300 sec: 11829.8). Total num frames: 96837632. Throughput: 0: 11683.9. Samples: 96826128. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-11 12:44:22,811][04011] Avg episode reward: [(0, '15.230')] [2023-03-11 12:44:22,814][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000189136_96837632.pth... [2023-03-11 12:44:22,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000188456_96489472.pth [2023-03-11 12:44:25,493][04298] Updated weights for policy 0, policy_version 189200 (0.0005) [2023-03-11 12:44:27,811][04011] Fps is (10 sec: 11059.2, 60 sec: 11741.9, 300 sec: 11829.8). Total num frames: 96894976. Throughput: 0: 11640.1. Samples: 96893140. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-11 12:44:27,811][04011] Avg episode reward: [(0, '14.098')] [2023-03-11 12:44:29,177][04298] Updated weights for policy 0, policy_version 189280 (0.0005) [2023-03-11 12:44:32,811][04011] Fps is (10 sec: 11059.2, 60 sec: 11605.3, 300 sec: 11802.0). Total num frames: 96948224. Throughput: 0: 11650.8. Samples: 96927740. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-11 12:44:32,811][04011] Avg episode reward: [(0, '16.046')] [2023-03-11 12:44:32,819][04298] Updated weights for policy 0, policy_version 189360 (0.0005) [2023-03-11 12:44:36,392][04298] Updated weights for policy 0, policy_version 189440 (0.0005) [2023-03-11 12:44:37,811][04011] Fps is (10 sec: 11059.2, 60 sec: 11537.1, 300 sec: 11802.0). Total num frames: 97005568. Throughput: 0: 11542.5. Samples: 96995328. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-11 12:44:37,811][04011] Avg episode reward: [(0, '15.068')] [2023-03-11 12:44:37,863][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000189472_97009664.pth... [2023-03-11 12:44:37,864][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000188808_96669696.pth [2023-03-11 12:44:40,057][04298] Updated weights for policy 0, policy_version 189520 (0.0005) [2023-03-11 12:44:42,811][04011] Fps is (10 sec: 11468.7, 60 sec: 11537.1, 300 sec: 11788.1). Total num frames: 97062912. Throughput: 0: 11424.9. Samples: 97062912. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-11 12:44:42,811][04011] Avg episode reward: [(0, '17.550')] [2023-03-11 12:44:43,664][04298] Updated weights for policy 0, policy_version 189600 (0.0005) [2023-03-11 12:44:47,273][04298] Updated weights for policy 0, policy_version 189680 (0.0005) [2023-03-11 12:44:47,811][04011] Fps is (10 sec: 11468.7, 60 sec: 11537.1, 300 sec: 11788.1). Total num frames: 97120256. Throughput: 0: 11353.8. Samples: 97096300. Policy #0 lag: (min: 2.0, avg: 2.0, max: 2.0) [2023-03-11 12:44:47,812][04011] Avg episode reward: [(0, '17.767')] [2023-03-11 12:44:50,936][04298] Updated weights for policy 0, policy_version 189760 (0.0005) [2023-03-11 12:44:52,811][04011] Fps is (10 sec: 11468.8, 60 sec: 11468.8, 300 sec: 11788.1). Total num frames: 97177600. Throughput: 0: 11271.5. Samples: 97164696. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-11 12:44:52,811][04011] Avg episode reward: [(0, '17.144')] [2023-03-11 12:44:52,814][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000189800_97177600.pth... [2023-03-11 12:44:52,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000189136_96837632.pth [2023-03-11 12:44:54,590][04298] Updated weights for policy 0, policy_version 189840 (0.0005) [2023-03-11 12:44:57,811][04011] Fps is (10 sec: 11059.3, 60 sec: 11332.3, 300 sec: 11774.3). Total num frames: 97230848. Throughput: 0: 11226.3. Samples: 97231392. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-11 12:44:57,811][04011] Avg episode reward: [(0, '17.649')] [2023-03-11 12:44:58,220][04298] Updated weights for policy 0, policy_version 189920 (0.0005) [2023-03-11 12:45:01,767][04298] Updated weights for policy 0, policy_version 190000 (0.0005) [2023-03-11 12:45:02,811][04011] Fps is (10 sec: 11059.3, 60 sec: 11264.0, 300 sec: 11760.4). Total num frames: 97288192. Throughput: 0: 11258.9. Samples: 97266464. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-11 12:45:02,811][04011] Avg episode reward: [(0, '21.560')] [2023-03-11 12:45:05,484][04298] Updated weights for policy 0, policy_version 190080 (0.0005) [2023-03-11 12:45:07,811][04011] Fps is (10 sec: 11468.7, 60 sec: 11264.0, 300 sec: 11760.4). Total num frames: 97345536. Throughput: 0: 11269.5. Samples: 97333256. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-11 12:45:07,811][04011] Avg episode reward: [(0, '15.779')] [2023-03-11 12:45:07,814][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000190128_97345536.pth... [2023-03-11 12:45:07,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000189472_97009664.pth [2023-03-11 12:45:09,025][04298] Updated weights for policy 0, policy_version 190160 (0.0005) [2023-03-11 12:45:12,637][04298] Updated weights for policy 0, policy_version 190240 (0.0005) [2023-03-11 12:45:12,811][04011] Fps is (10 sec: 11468.7, 60 sec: 11264.0, 300 sec: 11760.4). Total num frames: 97402880. Throughput: 0: 11323.3. Samples: 97402688. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-11 12:45:12,812][04011] Avg episode reward: [(0, '15.726')] [2023-03-11 12:45:16,196][04298] Updated weights for policy 0, policy_version 190320 (0.0005) [2023-03-11 12:45:17,811][04011] Fps is (10 sec: 11468.8, 60 sec: 11264.0, 300 sec: 11760.4). Total num frames: 97460224. Throughput: 0: 11301.8. Samples: 97436324. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-11 12:45:17,812][04011] Avg episode reward: [(0, '20.506')] [2023-03-11 12:45:19,844][04298] Updated weights for policy 0, policy_version 190400 (0.0005) [2023-03-11 12:45:22,811][04011] Fps is (10 sec: 11468.8, 60 sec: 11332.2, 300 sec: 11732.6). Total num frames: 97517568. Throughput: 0: 11333.7. Samples: 97505344. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-11 12:45:22,812][04011] Avg episode reward: [(0, '20.020')] [2023-03-11 12:45:22,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000190464_97517568.pth... [2023-03-11 12:45:22,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000189800_97177600.pth [2023-03-11 12:45:23,246][04298] Updated weights for policy 0, policy_version 190480 (0.0004) [2023-03-11 12:45:26,603][04298] Updated weights for policy 0, policy_version 190560 (0.0004) [2023-03-11 12:45:27,811][04011] Fps is (10 sec: 11878.4, 60 sec: 11400.5, 300 sec: 11732.6). Total num frames: 97579008. Throughput: 0: 11469.1. Samples: 97579020. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-11 12:45:27,811][04011] Avg episode reward: [(0, '18.115')] [2023-03-11 12:45:30,036][04298] Updated weights for policy 0, policy_version 190640 (0.0005) [2023-03-11 12:45:32,811][04011] Fps is (10 sec: 12288.1, 60 sec: 11537.0, 300 sec: 11732.6). Total num frames: 97640448. Throughput: 0: 11503.7. Samples: 97613968. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-11 12:45:32,812][04011] Avg episode reward: [(0, '17.262')] [2023-03-11 12:45:33,416][04298] Updated weights for policy 0, policy_version 190720 (0.0004) [2023-03-11 12:45:36,821][04298] Updated weights for policy 0, policy_version 190800 (0.0004) [2023-03-11 12:45:37,811][04011] Fps is (10 sec: 12288.0, 60 sec: 11605.3, 300 sec: 11732.6). Total num frames: 97701888. Throughput: 0: 11582.6. Samples: 97685912. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-11 12:45:37,812][04011] Avg episode reward: [(0, '12.165')] [2023-03-11 12:45:37,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000190824_97701888.pth... [2023-03-11 12:45:37,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000190128_97345536.pth [2023-03-11 12:45:40,171][04298] Updated weights for policy 0, policy_version 190880 (0.0004) [2023-03-11 12:45:42,811][04011] Fps is (10 sec: 12288.1, 60 sec: 11673.6, 300 sec: 11732.6). Total num frames: 97763328. Throughput: 0: 11746.6. Samples: 97759988. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-11 12:45:42,811][04011] Avg episode reward: [(0, '18.956')] [2023-03-11 12:45:43,504][04298] Updated weights for policy 0, policy_version 190960 (0.0004) [2023-03-11 12:45:46,947][04298] Updated weights for policy 0, policy_version 191040 (0.0005) [2023-03-11 12:45:47,811][04011] Fps is (10 sec: 11878.4, 60 sec: 11673.6, 300 sec: 11718.7). Total num frames: 97820672. Throughput: 0: 11769.8. Samples: 97796104. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-11 12:45:47,812][04011] Avg episode reward: [(0, '20.140')] [2023-03-11 12:45:50,507][04298] Updated weights for policy 0, policy_version 191120 (0.0005) [2023-03-11 12:45:52,811][04011] Fps is (10 sec: 11468.7, 60 sec: 11673.6, 300 sec: 11704.8). Total num frames: 97878016. Throughput: 0: 11828.0. Samples: 97865516. Policy #0 lag: (min: 4.0, avg: 4.0, max: 4.0) [2023-03-11 12:45:52,811][04011] Avg episode reward: [(0, '14.751')] [2023-03-11 12:45:52,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000191168_97878016.pth... [2023-03-11 12:45:52,816][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000190464_97517568.pth [2023-03-11 12:45:54,062][04298] Updated weights for policy 0, policy_version 191200 (0.0005) [2023-03-11 12:45:57,712][04298] Updated weights for policy 0, policy_version 191280 (0.0005) [2023-03-11 12:45:57,811][04011] Fps is (10 sec: 11468.8, 60 sec: 11741.8, 300 sec: 11704.8). Total num frames: 97935360. Throughput: 0: 11801.1. Samples: 97933736. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-11 12:45:57,811][04011] Avg episode reward: [(0, '16.550')] [2023-03-11 12:46:01,456][04298] Updated weights for policy 0, policy_version 191360 (0.0005) [2023-03-11 12:46:02,811][04011] Fps is (10 sec: 11059.2, 60 sec: 11673.6, 300 sec: 11691.0). Total num frames: 97988608. Throughput: 0: 11806.3. Samples: 97967608. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-11 12:46:02,822][04011] Avg episode reward: [(0, '10.512')] [2023-03-11 12:46:05,174][04298] Updated weights for policy 0, policy_version 191440 (0.0005) [2023-03-11 12:46:07,811][04011] Fps is (10 sec: 11059.3, 60 sec: 11673.6, 300 sec: 11677.1). Total num frames: 98045952. Throughput: 0: 11720.4. Samples: 98032760. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-11 12:46:07,822][04011] Avg episode reward: [(0, '18.418')] [2023-03-11 12:46:07,825][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000191496_98045952.pth... [2023-03-11 12:46:07,826][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000190824_97701888.pth [2023-03-11 12:46:08,928][04298] Updated weights for policy 0, policy_version 191520 (0.0005) [2023-03-11 12:46:12,473][04298] Updated weights for policy 0, policy_version 191600 (0.0005) [2023-03-11 12:46:12,811][04011] Fps is (10 sec: 11059.2, 60 sec: 11605.4, 300 sec: 11649.3). Total num frames: 98099200. Throughput: 0: 11571.4. Samples: 98099732. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-11 12:46:12,822][04011] Avg episode reward: [(0, '18.096')] [2023-03-11 12:46:15,870][04298] Updated weights for policy 0, policy_version 191680 (0.0005) [2023-03-11 12:46:17,811][04011] Fps is (10 sec: 11468.7, 60 sec: 11673.6, 300 sec: 11663.2). Total num frames: 98160640. Throughput: 0: 11603.7. Samples: 98136136. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-11 12:46:17,811][04011] Avg episode reward: [(0, '18.810')] [2023-03-11 12:46:19,192][04298] Updated weights for policy 0, policy_version 191760 (0.0005) [2023-03-11 12:46:22,609][04298] Updated weights for policy 0, policy_version 191840 (0.0005) [2023-03-11 12:46:22,811][04011] Fps is (10 sec: 12287.8, 60 sec: 11741.9, 300 sec: 11677.1). Total num frames: 98222080. Throughput: 0: 11642.0. Samples: 98209800. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-11 12:46:22,811][04011] Avg episode reward: [(0, '16.508')] [2023-03-11 12:46:22,814][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000191840_98222080.pth... [2023-03-11 12:46:22,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000191168_97878016.pth [2023-03-11 12:46:26,137][04298] Updated weights for policy 0, policy_version 191920 (0.0005) [2023-03-11 12:46:27,811][04011] Fps is (10 sec: 11878.4, 60 sec: 11673.6, 300 sec: 11691.0). Total num frames: 98279424. Throughput: 0: 11544.4. Samples: 98279488. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-11 12:46:27,811][04011] Avg episode reward: [(0, '18.876')] [2023-03-11 12:46:29,612][04298] Updated weights for policy 0, policy_version 192000 (0.0004) [2023-03-11 12:46:32,811][04011] Fps is (10 sec: 11878.4, 60 sec: 11673.6, 300 sec: 11704.8). Total num frames: 98340864. Throughput: 0: 11543.8. Samples: 98315576. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-11 12:46:32,811][04011] Avg episode reward: [(0, '20.577')] [2023-03-11 12:46:33,076][04298] Updated weights for policy 0, policy_version 192080 (0.0004) [2023-03-11 12:46:36,626][04298] Updated weights for policy 0, policy_version 192160 (0.0005) [2023-03-11 12:46:37,811][04011] Fps is (10 sec: 11878.3, 60 sec: 11605.3, 300 sec: 11691.0). Total num frames: 98398208. Throughput: 0: 11563.4. Samples: 98385868. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-11 12:46:37,811][04011] Avg episode reward: [(0, '18.117')] [2023-03-11 12:46:37,814][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000192184_98398208.pth... [2023-03-11 12:46:37,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000191496_98045952.pth [2023-03-11 12:46:40,264][04298] Updated weights for policy 0, policy_version 192240 (0.0005) [2023-03-11 12:46:42,811][04011] Fps is (10 sec: 11059.3, 60 sec: 11468.8, 300 sec: 11663.2). Total num frames: 98451456. Throughput: 0: 11512.4. Samples: 98451792. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-11 12:46:42,811][04011] Avg episode reward: [(0, '16.222')] [2023-03-11 12:46:43,983][04298] Updated weights for policy 0, policy_version 192320 (0.0005) [2023-03-11 12:46:47,745][04298] Updated weights for policy 0, policy_version 192400 (0.0005) [2023-03-11 12:46:47,811][04011] Fps is (10 sec: 11059.3, 60 sec: 11468.8, 300 sec: 11649.3). Total num frames: 98508800. Throughput: 0: 11491.8. Samples: 98484740. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-11 12:46:47,811][04011] Avg episode reward: [(0, '16.381')] [2023-03-11 12:46:51,373][04298] Updated weights for policy 0, policy_version 192480 (0.0005) [2023-03-11 12:46:52,811][04011] Fps is (10 sec: 11059.2, 60 sec: 11400.5, 300 sec: 11621.5). Total num frames: 98562048. Throughput: 0: 11535.4. Samples: 98551856. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-11 12:46:52,811][04011] Avg episode reward: [(0, '18.071')] [2023-03-11 12:46:52,827][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000192512_98566144.pth... [2023-03-11 12:46:52,828][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000191840_98222080.pth [2023-03-11 12:46:55,000][04298] Updated weights for policy 0, policy_version 192560 (0.0005) [2023-03-11 12:46:57,811][04011] Fps is (10 sec: 11059.2, 60 sec: 11400.5, 300 sec: 11607.6). Total num frames: 98619392. Throughput: 0: 11548.0. Samples: 98619392. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-03-11 12:46:57,811][04011] Avg episode reward: [(0, '21.609')] [2023-03-11 12:46:58,685][04298] Updated weights for policy 0, policy_version 192640 (0.0005) [2023-03-11 12:47:02,299][04298] Updated weights for policy 0, policy_version 192720 (0.0005) [2023-03-11 12:47:02,811][04011] Fps is (10 sec: 11468.8, 60 sec: 11468.8, 300 sec: 11621.5). Total num frames: 98676736. Throughput: 0: 11468.8. Samples: 98652232. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:47:02,811][04011] Avg episode reward: [(0, '16.402')] [2023-03-11 12:47:05,964][04298] Updated weights for policy 0, policy_version 192800 (0.0005) [2023-03-11 12:47:07,811][04011] Fps is (10 sec: 11468.8, 60 sec: 11468.8, 300 sec: 11621.5). Total num frames: 98734080. Throughput: 0: 11345.5. Samples: 98720348. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:47:07,811][04011] Avg episode reward: [(0, '16.687')] [2023-03-11 12:47:07,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000192840_98734080.pth... [2023-03-11 12:47:07,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000192184_98398208.pth [2023-03-11 12:47:09,550][04298] Updated weights for policy 0, policy_version 192880 (0.0005) [2023-03-11 12:47:12,811][04011] Fps is (10 sec: 11059.2, 60 sec: 11468.8, 300 sec: 11607.6). Total num frames: 98787328. Throughput: 0: 11309.1. Samples: 98788396. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:47:12,811][04011] Avg episode reward: [(0, '17.989')] [2023-03-11 12:47:13,197][04298] Updated weights for policy 0, policy_version 192960 (0.0005) [2023-03-11 12:47:16,796][04298] Updated weights for policy 0, policy_version 193040 (0.0005) [2023-03-11 12:47:17,811][04011] Fps is (10 sec: 11059.3, 60 sec: 11400.6, 300 sec: 11593.8). Total num frames: 98844672. Throughput: 0: 11269.7. Samples: 98822712. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:47:17,811][04011] Avg episode reward: [(0, '20.221')] [2023-03-11 12:47:20,460][04298] Updated weights for policy 0, policy_version 193120 (0.0005) [2023-03-11 12:47:22,811][04011] Fps is (10 sec: 11468.8, 60 sec: 11332.3, 300 sec: 11607.6). Total num frames: 98902016. Throughput: 0: 11198.3. Samples: 98889792. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:47:22,811][04011] Avg episode reward: [(0, '18.297')] [2023-03-11 12:47:22,814][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000193168_98902016.pth... [2023-03-11 12:47:22,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000192512_98566144.pth [2023-03-11 12:47:24,092][04298] Updated weights for policy 0, policy_version 193200 (0.0005) [2023-03-11 12:47:27,797][04298] Updated weights for policy 0, policy_version 193280 (0.0005) [2023-03-11 12:47:27,811][04011] Fps is (10 sec: 11468.6, 60 sec: 11332.2, 300 sec: 11607.6). Total num frames: 98959360. Throughput: 0: 11222.4. Samples: 98956800. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:47:27,812][04011] Avg episode reward: [(0, '18.432')] [2023-03-11 12:47:31,333][04298] Updated weights for policy 0, policy_version 193360 (0.0005) [2023-03-11 12:47:32,811][04011] Fps is (10 sec: 11468.8, 60 sec: 11264.0, 300 sec: 11621.5). Total num frames: 99016704. Throughput: 0: 11256.1. Samples: 98991264. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:47:32,811][04011] Avg episode reward: [(0, '19.420')] [2023-03-11 12:47:34,980][04298] Updated weights for policy 0, policy_version 193440 (0.0005) [2023-03-11 12:47:37,811][04011] Fps is (10 sec: 11059.3, 60 sec: 11195.7, 300 sec: 11607.6). Total num frames: 99069952. Throughput: 0: 11279.9. Samples: 99059452. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:47:37,811][04011] Avg episode reward: [(0, '20.237')] [2023-03-11 12:47:37,864][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000193504_99074048.pth... [2023-03-11 12:47:37,866][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000192840_98734080.pth [2023-03-11 12:47:38,562][04298] Updated weights for policy 0, policy_version 193520 (0.0005) [2023-03-11 12:47:42,017][04298] Updated weights for policy 0, policy_version 193600 (0.0005) [2023-03-11 12:47:42,811][04011] Fps is (10 sec: 11468.8, 60 sec: 11332.3, 300 sec: 11621.5). Total num frames: 99131392. Throughput: 0: 11339.4. Samples: 99129664. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:47:42,811][04011] Avg episode reward: [(0, '17.231')] [2023-03-11 12:47:45,392][04298] Updated weights for policy 0, policy_version 193680 (0.0004) [2023-03-11 12:47:47,811][04011] Fps is (10 sec: 12288.0, 60 sec: 11400.5, 300 sec: 11621.5). Total num frames: 99192832. Throughput: 0: 11421.7. Samples: 99166208. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:47:47,811][04011] Avg episode reward: [(0, '20.429')] [2023-03-11 12:47:48,781][04298] Updated weights for policy 0, policy_version 193760 (0.0004) [2023-03-11 12:47:52,156][04298] Updated weights for policy 0, policy_version 193840 (0.0004) [2023-03-11 12:47:52,811][04011] Fps is (10 sec: 11878.4, 60 sec: 11468.8, 300 sec: 11607.6). Total num frames: 99250176. Throughput: 0: 11511.1. Samples: 99238348. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:47:52,811][04011] Avg episode reward: [(0, '19.266')] [2023-03-11 12:47:52,814][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000193848_99250176.pth... [2023-03-11 12:47:52,815][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000193168_98902016.pth [2023-03-11 12:47:55,569][04298] Updated weights for policy 0, policy_version 193920 (0.0005) [2023-03-11 12:47:57,811][04011] Fps is (10 sec: 11878.3, 60 sec: 11537.1, 300 sec: 11621.5). Total num frames: 99311616. Throughput: 0: 11627.1. Samples: 99311616. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:47:57,812][04011] Avg episode reward: [(0, '17.296')] [2023-03-11 12:47:58,890][04298] Updated weights for policy 0, policy_version 194000 (0.0004) [2023-03-11 12:48:02,253][04298] Updated weights for policy 0, policy_version 194080 (0.0004) [2023-03-11 12:48:02,811][04011] Fps is (10 sec: 12287.9, 60 sec: 11605.3, 300 sec: 11621.5). Total num frames: 99373056. Throughput: 0: 11685.1. Samples: 99348544. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:48:02,812][04011] Avg episode reward: [(0, '18.132')] [2023-03-11 12:48:05,653][04298] Updated weights for policy 0, policy_version 194160 (0.0004) [2023-03-11 12:48:07,811][04011] Fps is (10 sec: 12288.0, 60 sec: 11673.6, 300 sec: 11621.5). Total num frames: 99434496. Throughput: 0: 11798.6. Samples: 99420732. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:48:07,812][04011] Avg episode reward: [(0, '17.304')] [2023-03-11 12:48:07,815][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000194208_99434496.pth... [2023-03-11 12:48:07,818][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000193504_99074048.pth [2023-03-11 12:48:09,115][04298] Updated weights for policy 0, policy_version 194240 (0.0004) [2023-03-11 12:48:12,811][04011] Fps is (10 sec: 11468.8, 60 sec: 11673.6, 300 sec: 11593.8). Total num frames: 99487744. Throughput: 0: 11806.6. Samples: 99488096. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:48:12,812][04011] Avg episode reward: [(0, '20.145')] [2023-03-11 12:48:12,869][04298] Updated weights for policy 0, policy_version 194320 (0.0005) [2023-03-11 12:48:16,499][04298] Updated weights for policy 0, policy_version 194400 (0.0004) [2023-03-11 12:48:17,811][04011] Fps is (10 sec: 11059.3, 60 sec: 11673.6, 300 sec: 11579.9). Total num frames: 99545088. Throughput: 0: 11786.5. Samples: 99521656. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:48:17,811][04011] Avg episode reward: [(0, '21.299')] [2023-03-11 12:48:19,783][04298] Updated weights for policy 0, policy_version 194480 (0.0004) [2023-03-11 12:48:22,811][04011] Fps is (10 sec: 12288.1, 60 sec: 11810.1, 300 sec: 11593.8). Total num frames: 99610624. Throughput: 0: 11912.4. Samples: 99595512. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:48:22,811][04011] Avg episode reward: [(0, '20.153')] [2023-03-11 12:48:22,814][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000194552_99610624.pth... [2023-03-11 12:48:22,817][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000193848_99250176.pth [2023-03-11 12:48:23,116][04298] Updated weights for policy 0, policy_version 194560 (0.0004) [2023-03-11 12:48:26,566][04298] Updated weights for policy 0, policy_version 194640 (0.0005) [2023-03-11 12:48:27,811][04011] Fps is (10 sec: 12287.9, 60 sec: 11810.1, 300 sec: 11579.9). Total num frames: 99667968. Throughput: 0: 11958.3. Samples: 99667788. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:48:27,812][04011] Avg episode reward: [(0, '18.727')] [2023-03-11 12:48:29,946][04298] Updated weights for policy 0, policy_version 194720 (0.0004) [2023-03-11 12:48:32,811][04011] Fps is (10 sec: 11878.4, 60 sec: 11878.4, 300 sec: 11579.9). Total num frames: 99729408. Throughput: 0: 11962.0. Samples: 99704500. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:48:32,822][04011] Avg episode reward: [(0, '18.657')] [2023-03-11 12:48:33,307][04298] Updated weights for policy 0, policy_version 194800 (0.0004) [2023-03-11 12:48:36,664][04298] Updated weights for policy 0, policy_version 194880 (0.0004) [2023-03-11 12:48:37,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12014.9, 300 sec: 11593.8). Total num frames: 99790848. Throughput: 0: 11978.1. Samples: 99777364. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:48:37,822][04011] Avg episode reward: [(0, '23.934')] [2023-03-11 12:48:37,825][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000194904_99790848.pth... [2023-03-11 12:48:37,828][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000194208_99434496.pth [2023-03-11 12:48:40,093][04298] Updated weights for policy 0, policy_version 194960 (0.0005) [2023-03-11 12:48:42,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12014.9, 300 sec: 11607.6). Total num frames: 99852288. Throughput: 0: 11944.1. Samples: 99849100. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:48:42,822][04011] Avg episode reward: [(0, '16.355')] [2023-03-11 12:48:43,493][04298] Updated weights for policy 0, policy_version 195040 (0.0004) [2023-03-11 12:48:46,800][04298] Updated weights for policy 0, policy_version 195120 (0.0003) [2023-03-11 12:48:47,811][04011] Fps is (10 sec: 12288.0, 60 sec: 12014.9, 300 sec: 11607.6). Total num frames: 99913728. Throughput: 0: 11936.4. Samples: 99885684. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:48:47,822][04011] Avg episode reward: [(0, '21.632')] [2023-03-11 12:48:50,007][04298] Updated weights for policy 0, policy_version 195200 (0.0003) [2023-03-11 12:48:52,811][04011] Fps is (10 sec: 12287.9, 60 sec: 12083.2, 300 sec: 11607.6). Total num frames: 99975168. Throughput: 0: 12024.8. Samples: 99961848. Policy #0 lag: (min: 7.0, avg: 7.0, max: 7.0) [2023-03-11 12:48:52,822][04011] Avg episode reward: [(0, '22.422')] [2023-03-11 12:48:52,825][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000195264_99975168.pth... [2023-03-11 12:48:52,827][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000194552_99610624.pth [2023-03-11 12:48:53,388][04298] Updated weights for policy 0, policy_version 195280 (0.0004) [2023-03-11 12:48:55,100][04254] Early stopping after 2 epochs (8 sgd steps), loss delta 0.0000000 [2023-03-11 12:48:55,475][04254] Early stopping after 2 epochs (8 sgd steps), loss delta 0.0000000 [2023-03-11 12:48:55,476][04306] Stopping RolloutWorker_w6... [2023-03-11 12:48:55,476][04303] Stopping RolloutWorker_w4... [2023-03-11 12:48:55,476][04300] Stopping RolloutWorker_w2... [2023-03-11 12:48:55,476][04301] Stopping RolloutWorker_w0... [2023-03-11 12:48:55,476][04299] Stopping RolloutWorker_w1... [2023-03-11 12:48:55,476][04304] Stopping RolloutWorker_w5... [2023-03-11 12:48:55,476][04306] Loop rollout_proc6_evt_loop terminating... [2023-03-11 12:48:55,476][04303] Loop rollout_proc4_evt_loop terminating... [2023-03-11 12:48:55,476][04307] Stopping RolloutWorker_w7... [2023-03-11 12:48:55,476][04300] Loop rollout_proc2_evt_loop terminating... [2023-03-11 12:48:55,476][04301] Loop rollout_proc0_evt_loop terminating... [2023-03-11 12:48:55,476][04302] Stopping RolloutWorker_w3... [2023-03-11 12:48:55,476][04304] Loop rollout_proc5_evt_loop terminating... [2023-03-11 12:48:55,476][04299] Loop rollout_proc1_evt_loop terminating... [2023-03-11 12:48:55,476][04307] Loop rollout_proc7_evt_loop terminating... [2023-03-11 12:48:55,476][04011] Component RolloutWorker_w6 stopped! [2023-03-11 12:48:55,476][04302] Loop rollout_proc3_evt_loop terminating... [2023-03-11 12:48:55,476][04011] Component RolloutWorker_w4 stopped! [2023-03-11 12:48:55,477][04011] Component RolloutWorker_w5 stopped! [2023-03-11 12:48:55,476][04254] Stopping Batcher_0... [2023-03-11 12:48:55,477][04011] Component RolloutWorker_w2 stopped! [2023-03-11 12:48:55,477][04011] Component RolloutWorker_w1 stopped! [2023-03-11 12:48:55,477][04254] Loop batcher_evt_loop terminating... [2023-03-11 12:48:55,477][04011] Component RolloutWorker_w0 stopped! [2023-03-11 12:48:55,477][04011] Component RolloutWorker_w3 stopped! [2023-03-11 12:48:55,477][04011] Component RolloutWorker_w7 stopped! [2023-03-11 12:48:55,477][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000195328_100007936.pth... [2023-03-11 12:48:55,478][04011] Component Batcher_0 stopped! [2023-03-11 12:48:55,479][04254] Removing /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000194904_99790848.pth [2023-03-11 12:48:55,480][04254] Saving /home/qgallouedec/gia/data/envs/metaworld/train_dir/shelf-place-v2/checkpoint_p0/checkpoint_000195328_100007936.pth... [2023-03-11 12:48:55,481][04254] Stopping LearnerWorker_p0... [2023-03-11 12:48:55,482][04254] Loop learner_proc0_evt_loop terminating... [2023-03-11 12:48:55,482][04011] Component LearnerWorker_p0 stopped! [2023-03-11 12:48:55,531][04298] Weights refcount: 2 0 [2023-03-11 12:48:55,532][04298] Stopping InferenceWorker_p0-w0... [2023-03-11 12:48:55,532][04298] Loop inference_proc0-0_evt_loop terminating... [2023-03-11 12:48:55,532][04011] Component InferenceWorker_p0-w0 stopped! [2023-03-11 12:48:55,533][04011] Waiting for process learner_proc0 to stop... [2023-03-11 12:48:55,923][04011] Waiting for process inference_proc0-0 to join... [2023-03-11 12:48:55,928][04011] Waiting for process rollout_proc0 to join... [2023-03-11 12:48:55,928][04011] Waiting for process rollout_proc1 to join... [2023-03-11 12:48:55,928][04011] Waiting for process rollout_proc2 to join... [2023-03-11 12:48:55,928][04011] Waiting for process rollout_proc3 to join... [2023-03-11 12:48:55,929][04011] Waiting for process rollout_proc4 to join... [2023-03-11 12:48:55,929][04011] Waiting for process rollout_proc5 to join... [2023-03-11 12:48:55,929][04011] Waiting for process rollout_proc6 to join... [2023-03-11 12:48:55,929][04011] Waiting for process rollout_proc7 to join... [2023-03-11 12:48:55,929][04011] Batcher 0 profile tree view: batching: 17.4745, releasing_batches: 14.8191 [2023-03-11 12:48:55,930][04011] InferenceWorker_p0-w0 profile tree view: wait_policy: 0.0051 wait_policy_total: 2826.6861 update_model: 92.7866 weight_update: 0.0004 one_step: 0.0005 handle_policy_step: 4719.7865 deserialize: 199.2265, stack: 47.5459, obs_to_device_normalize: 831.6952, forward: 2335.1864, send_messages: 356.9092 prepare_outputs: 535.2183 to_cpu: 82.8693 [2023-03-11 12:48:55,930][04011] Learner 0 profile tree view: misc: 0.0931, prepare_batch: 90.6841 train: 1171.8835 epoch_init: 0.3782, minibatch_init: 11.8579, losses_postprocess: 12.1663, kl_divergence: 4.2559, after_optimizer: 4.8605 calculate_losses: 482.0287 losses_init: 0.3057, forward_head: 237.7203, bptt_initial: 1.2310, bptt: 1.2194, tail: 113.5082, advantages_returns: 8.7671, losses: 105.1199 update: 640.5472 clip: 56.4414 [2023-03-11 12:48:55,930][04011] RolloutWorker_w0 profile tree view: wait_for_trajectories: 2.7011, enqueue_policy_requests: 124.8130, env_step: 5327.1721, overhead: 297.3163, complete_rollouts: 3.1356 save_policy_outputs: 319.6338 split_output_tensors: 158.0121 [2023-03-11 12:48:55,930][04011] RolloutWorker_w7 profile tree view: wait_for_trajectories: 2.6352, enqueue_policy_requests: 125.7090, env_step: 5336.7991, overhead: 300.1367, complete_rollouts: 3.3060 save_policy_outputs: 323.4185 split_output_tensors: 160.3180 [2023-03-11 12:48:55,930][04011] Loop Runner_EvtLoop terminating... [2023-03-11 12:48:55,931][04011] Runner profile tree view: main_loop: 8220.3621 [2023-03-11 12:48:55,931][04011] Collected {0: 100007936}, FPS: 12165.9